diff options
83 files changed, 16245 insertions, 12 deletions
diff --git a/.gitmodules b/.gitmodules deleted file mode 100644 index 037d1fc0d..000000000 --- a/.gitmodules +++ /dev/null @@ -1,12 +0,0 @@ -[submodule "interface"] - path = interface - url = git://github.com/vstakhov/rspamd-interface -[submodule "doc/doxydown"] - path = doc/doxydown - url = https://github.com/vstakhov/doxydown.git -[submodule "contrib/snowball"] - path = contrib/snowball - url = https://github.com/vstakhov/snowball -[submodule "contrib/siphash"] - path = contrib/siphash - url = https://github.com/vstakhov/siphash diff --git a/contrib/snowball b/contrib/snowball deleted file mode 160000 -Subproject c381f4fa958b59d41b0c596f0cbfe3ed48831e9 diff --git a/contrib/snowball/.gitignore b/contrib/snowball/.gitignore new file mode 100644 index 000000000..2147da841 --- /dev/null +++ b/contrib/snowball/.gitignore @@ -0,0 +1,5 @@ +*.o +/libstemmer +/snowball +/src_c +/stemwords diff --git a/contrib/snowball/.travis.yml b/contrib/snowball/.travis.yml new file mode 100644 index 000000000..e576233dc --- /dev/null +++ b/contrib/snowball/.travis.yml @@ -0,0 +1,4 @@ +language: c +compiler: gcc +before_script: git clone https://github.com/snowballstem/snowball-data ../data +script: make check diff --git a/contrib/snowball/AUTHORS b/contrib/snowball/AUTHORS new file mode 100644 index 000000000..60eae6f04 --- /dev/null +++ b/contrib/snowball/AUTHORS @@ -0,0 +1,27 @@ +Authors +======= + +Martin Porter +------------- + + - Designed the snowball language. + - Implemented the snowball to C compiler. + - Implemented the stemming algorithms in C. + - Wrote the documentation. + +Richard Boulton +--------------- + + - Implemented Java backend of the snowball compiler. + - Developed build system. + - Assisted with website maintenance. + + +Assistance from +--------------- + +Olivier Bornet - fixes to java packaging and build system. +Andreas Jung - useful bug reports on the libstemmer library. +Olly Betts - several patches, bug reports, and performance improvements. +Sebastiano Vigna and Oerd Cukalla - patches for the Java stemming algorithms. +Ralf Junker - fix a potential memory leak in sb_stemmer_new(). diff --git a/contrib/snowball/CMakeLists.txt b/contrib/snowball/CMakeLists.txt new file mode 100644 index 000000000..1dee79490 --- /dev/null +++ b/contrib/snowball/CMakeLists.txt @@ -0,0 +1,85 @@ +PROJECT(snowball C) + +cmake_minimum_required(VERSION 2.8) + +INCLUDE(CheckCCompilerFlag) +INCLUDE(FindPerl) + +# End of configuration +SET(LIBSTEM_ALGORITHMS danish dutch english finnish french german hungarian + italian norwegian porter portuguese romanian + russian spanish swedish turkish) +SET(KOI8_ALGORITHMS russian) +SET(ISO_8859_1_ALGORITHMS danish dutch english finnish french german italian + norwegian porter portuguese spanish swedish) +SET(ISO_8859_2_ALGORITHMS hungarian romanian) +SET(OTHER_ALGORITHMS german2 kraaij_pohlmann lovins) +SET(ALL_ALGORITHMS ${LIBSTEM_ALGORITHMS} ${OTHER_ALGORITHMS}) + +SET(COMPILER_SOURCES compiler/space.c + compiler/tokeniser.c + compiler/analyser.c + compiler/generator.c + compiler/driver.c + compiler/generator_java.c) + +SET(SNOWBALL_RUNTIME runtime/api.c + runtime/utilities.c) +SET(LIBSTEMMER_SOURCES libstemmer/libstemmer.c) +SET(LIBSTEMMER_UTF8_SOURCES libstemmer/libstemmer_utf8.c) +#LIBSTEMMER_UTF8_SOURCES = libstemmer/libstemmer_utf8.c +#LIBSTEMMER_HEADERS = include/libstemmer.h libstemmer/modules.h libstemmer/modules_utf8.h +#LIBSTEMMER_EXTRA = libstemmer/modules.txt libstemmer/modules_utf8.txt libstemmer/libstemmer_c.in + +SET(STEMWORDS_SOURCES examples/stemwords.c) +SET(MODULES_H "modules.h") +CONFIGURE_FILE(${CMAKE_CURRENT_SOURCE_DIR}/libstemmer/libstemmer_c.in ${CMAKE_CURRENT_BINARY_DIR}/libstemmer/libstemmer.c @ONLY) + +MACRO(gen_stem IN ENCODING) + FOREACH(_it ${IN}) + SET(_base "${CMAKE_CURRENT_BINARY_DIR}/libstemmer/stem_${ENCODING}_${_it}") + SET(_header "${_base}.h") + SET(_source "${_base}.c") + STRING(REPLACE "UTF_8" "Unicode" _in_enc "${ENCODING}") + SET(_input "${CMAKE_CURRENT_SOURCE_DIR}/algorithms/${_it}/stem_${_in_enc}.sbl") + IF(${_in_enc} STREQUAL "Unicode" AND NOT EXISTS ${_input}) + ADD_CUSTOM_COMMAND(OUTPUT ${_source} + COMMAND ${CMAKE_CURRENT_BINARY_DIR}/snowball "${CMAKE_CURRENT_SOURCE_DIR}/algorithms/${_it}/stem_ISO_8859_1.sbl" -o ${_base} -eprefix ${_it}_${ENCODING}_ -r ${CMAKE_CURRENT_SOURCE_DIR}/runtime -u + DEPENDS snowball) + LIST(APPEND STEMMER_SOURCES ${_source}) + + ELSE() + IF(EXISTS "${_input}") + ADD_CUSTOM_COMMAND(OUTPUT ${_source} + COMMAND ${CMAKE_CURRENT_BINARY_DIR}/snowball ${_input} -o ${_base} -eprefix ${_it}_${ENCODING}_ -r ${CMAKE_CURRENT_SOURCE_DIR}/runtime -u + DEPENDS snowball) + LIST(APPEND STEMMER_SOURCES ${_source}) + ENDIF() + ENDIF() + ENDFOREACH() +ENDMACRO() + +INCLUDE_DIRECTORIES("include") +INCLUDE_DIRECTORIES("${CMAKE_CURRENT_BINARY_DIR}/libstemmer") + +ADD_EXECUTABLE(snowball ${COMPILER_SOURCES}) + +ADD_CUSTOM_COMMAND(OUTPUT ${CMAKE_CURRENT_BINARY_DIR}/libstemmer/modules.h + COMMAND ${PERL_EXECUTABLE} ${CMAKE_CURRENT_SOURCE_DIR}/libstemmer/mkmodules.pl -f ${CMAKE_CURRENT_BINARY_DIR}/libstemmer/modules.h ${CMAKE_CURRENT_BINARY_DIR}/libstemmer ${CMAKE_CURRENT_SOURCE_DIR}/libstemmer/modules.txt ${CMAKE_CURRENT_BINARY_DIR}/libstemmer/mkinc.mak) +ADD_CUSTOM_TARGET(modules DEPENDS "${CMAKE_CURRENT_BINARY_DIR}/libstemmer/modules.h") + +SET(STEMMER_SOURCES "${CMAKE_CURRENT_BINARY_DIR}/libstemmer/libstemmer.c") +ADD_CUSTOM_TARGET(stemmer_deps ALL) +ADD_DEPENDENCIES(stemmer_deps modules) + +gen_stem("${LIBSTEM_ALGORITHMS}" "UTF_8") +gen_stem("${KOI8_ALGORITHMS}" "KOI8_R") +gen_stem("${ISO_8859_1_ALGORITHMS}" "ISO_8859_1") +gen_stem("${ISO_8859_2_ALGORITHMS}" "ISO_8859_2") + + +ADD_LIBRARY(stemmer ${LINK_TYPE} ${SNOWBALL_RUNTIME} ${STEMMER_SOURCES}) +ADD_DEPENDENCIES(stemmer stemmer_deps) + +ADD_EXECUTABLE(stemwords ${STEMWORDS_SOURCES}) +TARGET_LINK_LIBRARIES(stemwords stemmer) diff --git a/contrib/snowball/GNUmakefile b/contrib/snowball/GNUmakefile new file mode 100644 index 000000000..a30cafd89 --- /dev/null +++ b/contrib/snowball/GNUmakefile @@ -0,0 +1,300 @@ +# -*- makefile -*- + +c_src_dir = src_c +java_src_main_dir = java/org/tartarus/snowball +java_src_dir = $(java_src_main_dir)/ext + +libstemmer_algorithms = danish dutch english finnish french german hungarian \ + italian \ + norwegian porter portuguese romanian \ + russian spanish swedish turkish + +KOI8_R_algorithms = russian +ISO_8859_1_algorithms = danish dutch english finnish french german italian \ + norwegian porter portuguese spanish swedish +ISO_8859_2_algorithms = hungarian romanian + +other_algorithms = german2 kraaij_pohlmann lovins + +all_algorithms = $(libstemmer_algorithms) $(other_algorithms) + +COMPILER_SOURCES = compiler/space.c \ + compiler/tokeniser.c \ + compiler/analyser.c \ + compiler/generator.c \ + compiler/driver.c \ + compiler/generator_java.c +COMPILER_HEADERS = compiler/header.h \ + compiler/syswords.h \ + compiler/syswords2.h + +RUNTIME_SOURCES = runtime/api.c \ + runtime/utilities.c +RUNTIME_HEADERS = runtime/api.h \ + runtime/header.h + +JAVARUNTIME_SOURCES = java/org/tartarus/snowball/Among.java \ + java/org/tartarus/snowball/SnowballProgram.java \ + java/org/tartarus/snowball/SnowballStemmer.java \ + java/org/tartarus/snowball/TestApp.java + +LIBSTEMMER_SOURCES = libstemmer/libstemmer.c +LIBSTEMMER_UTF8_SOURCES = libstemmer/libstemmer_utf8.c +LIBSTEMMER_HEADERS = include/libstemmer.h libstemmer/modules.h libstemmer/modules_utf8.h +LIBSTEMMER_EXTRA = libstemmer/modules.txt libstemmer/modules_utf8.txt libstemmer/libstemmer_c.in + +STEMWORDS_SOURCES = examples/stemwords.c + +ALL_ALGORITHM_FILES = $(all_algorithms:%=algorithms/%/stem*.sbl) +C_LIB_SOURCES = $(libstemmer_algorithms:%=$(c_src_dir)/stem_UTF_8_%.c) \ + $(KOI8_R_algorithms:%=$(c_src_dir)/stem_KOI8_R_%.c) \ + $(ISO_8859_1_algorithms:%=$(c_src_dir)/stem_ISO_8859_1_%.c) \ + $(ISO_8859_2_algorithms:%=$(c_src_dir)/stem_ISO_8859_2_%.c) +C_LIB_HEADERS = $(libstemmer_algorithms:%=$(c_src_dir)/stem_UTF_8_%.h) \ + $(KOI8_R_algorithms:%=$(c_src_dir)/stem_KOI8_R_%.h) \ + $(ISO_8859_1_algorithms:%=$(c_src_dir)/stem_ISO_8859_1_%.h) \ + $(ISO_8859_2_algorithms:%=$(c_src_dir)/stem_ISO_8859_2_%.h) +C_OTHER_SOURCES = $(other_algorithms:%=$(c_src_dir)/stem_UTF_8_%.c) +C_OTHER_HEADERS = $(other_algorithms:%=$(c_src_dir)/stem_UTF_8_%.h) +JAVA_SOURCES = $(libstemmer_algorithms:%=$(java_src_dir)/%Stemmer.java) + +COMPILER_OBJECTS=$(COMPILER_SOURCES:.c=.o) +RUNTIME_OBJECTS=$(RUNTIME_SOURCES:.c=.o) +LIBSTEMMER_OBJECTS=$(LIBSTEMMER_SOURCES:.c=.o) +LIBSTEMMER_UTF8_OBJECTS=$(LIBSTEMMER_UTF8_SOURCES:.c=.o) +STEMWORDS_OBJECTS=$(STEMWORDS_SOURCES:.c=.o) +C_LIB_OBJECTS = $(C_LIB_SOURCES:.c=.o) +C_OTHER_OBJECTS = $(C_OTHER_SOURCES:.c=.o) +JAVA_CLASSES = $(JAVA_SOURCES:.java=.class) +JAVA_RUNTIME_CLASSES=$(JAVARUNTIME_SOURCES:.java=.class) + +CFLAGS=-Iinclude -O2 +CPPFLAGS=-W -Wall -Wmissing-prototypes -Wmissing-declarations + +all: snowball libstemmer.o stemwords $(C_OTHER_SOURCES) $(C_OTHER_HEADERS) $(C_OTHER_OBJECTS) + +clean: + rm -f $(COMPILER_OBJECTS) $(RUNTIME_OBJECTS) \ + $(LIBSTEMMER_OBJECTS) $(LIBSTEMMER_UTF8_OBJECTS) $(STEMWORDS_OBJECTS) snowball \ + libstemmer.o stemwords \ + libstemmer/modules.h \ + libstemmer/modules_utf8.h \ + snowball.splint \ + $(C_LIB_SOURCES) $(C_LIB_HEADERS) $(C_LIB_OBJECTS) \ + $(C_OTHER_SOURCES) $(C_OTHER_HEADERS) $(C_OTHER_OBJECTS) \ + $(JAVA_SOURCES) $(JAVA_CLASSES) $(JAVA_RUNTIME_CLASSES) \ + libstemmer/mkinc.mak libstemmer/mkinc_utf8.mak \ + libstemmer/libstemmer.c libstemmer/libstemmer_utf8.c + rm -rf dist + rmdir $(c_src_dir) || true + +snowball: $(COMPILER_OBJECTS) + $(CC) -o $@ $^ + +$(COMPILER_OBJECTS): $(COMPILER_HEADERS) + +libstemmer/libstemmer.c: libstemmer/libstemmer_c.in + sed 's/@MODULES_H@/modules.h/' $^ >$@ + +libstemmer/libstemmer_utf8.c: libstemmer/libstemmer_c.in + sed 's/@MODULES_H@/modules_utf8.h/' $^ >$@ + +libstemmer/modules.h libstemmer/mkinc.mak: libstemmer/mkmodules.pl libstemmer/modules.txt + libstemmer/mkmodules.pl $@ $(c_src_dir) libstemmer/modules.txt libstemmer/mkinc.mak + +libstemmer/modules_utf8.h libstemmer/mkinc_utf8.mak: libstemmer/mkmodules.pl libstemmer/modules_utf8.txt + libstemmer/mkmodules.pl $@ $(c_src_dir) libstemmer/modules_utf8.txt libstemmer/mkinc_utf8.mak utf8 + +libstemmer/libstemmer.o: libstemmer/modules.h $(C_LIB_HEADERS) + +libstemmer.o: libstemmer/libstemmer.o $(RUNTIME_OBJECTS) $(C_LIB_OBJECTS) + $(AR) -cru $@ $^ + +stemwords: $(STEMWORDS_OBJECTS) libstemmer.o + $(CC) -o $@ $^ + +algorithms/%/stem_Unicode.sbl: algorithms/%/stem_ISO_8859_1.sbl + cp $^ $@ + +$(c_src_dir)/stem_UTF_8_%.c $(c_src_dir)/stem_UTF_8_%.h: algorithms/%/stem_Unicode.sbl snowball + @mkdir -p $(c_src_dir) + @l=`echo "$<" | sed 's!\(.*\)/stem_Unicode.sbl$$!\1!;s!^.*/!!'`; \ + o="$(c_src_dir)/stem_UTF_8_$${l}"; \ + echo "./snowball $< -o $${o} -eprefix $${l}_UTF_8_ -r ../runtime -u"; \ + ./snowball $< -o $${o} -eprefix $${l}_UTF_8_ -r ../runtime -u + +$(c_src_dir)/stem_KOI8_R_%.c $(c_src_dir)/stem_KOI8_R_%.h: algorithms/%/stem_KOI8_R.sbl snowball + @mkdir -p $(c_src_dir) + @l=`echo "$<" | sed 's!\(.*\)/stem_KOI8_R.sbl$$!\1!;s!^.*/!!'`; \ + o="$(c_src_dir)/stem_KOI8_R_$${l}"; \ + echo "./snowball $< -o $${o} -eprefix $${l}_KOI8_R_ -r ../runtime"; \ + ./snowball $< -o $${o} -eprefix $${l}_KOI8_R_ -r ../runtime + +$(c_src_dir)/stem_ISO_8859_1_%.c $(c_src_dir)/stem_ISO_8859_1_%.h: algorithms/%/stem_ISO_8859_1.sbl snowball + @mkdir -p $(c_src_dir) + @l=`echo "$<" | sed 's!\(.*\)/stem_ISO_8859_1.sbl$$!\1!;s!^.*/!!'`; \ + o="$(c_src_dir)/stem_ISO_8859_1_$${l}"; \ + echo "./snowball $< -o $${o} -eprefix $${l}_ISO_8859_1_ -r ../runtime"; \ + ./snowball $< -o $${o} -eprefix $${l}_ISO_8859_1_ -r ../runtime + +$(c_src_dir)/stem_ISO_8859_2_%.c $(c_src_dir)/stem_ISO_8859_2_%.h: algorithms/%/stem_ISO_8859_2.sbl snowball + @mkdir -p $(c_src_dir) + @l=`echo "$<" | sed 's!\(.*\)/stem_ISO_8859_2.sbl$$!\1!;s!^.*/!!'`; \ + o="$(c_src_dir)/stem_ISO_8859_2_$${l}"; \ + echo "./snowball $< -o $${o} -eprefix $${l}_ISO_8859_2_ -r ../runtime"; \ + ./snowball $< -o $${o} -eprefix $${l}_ISO_8859_2_ -r ../runtime + +$(c_src_dir)/stem_%.o: $(c_src_dir)/stem_%.c $(c_src_dir)/stem_%.h + $(CC) $(CFLAGS) $(CPPFLAGS) -c -o $@ $< + +$(java_src_dir)/%Stemmer.java: algorithms/%/stem_Unicode.sbl snowball + @mkdir -p $(java_src_dir) + @l=`echo "$<" | sed 's!\(.*\)/stem_Unicode.sbl$$!\1!;s!^.*/!!'`; \ + o="$(java_src_dir)/$${l}Stemmer"; \ + echo "./snowball $< -j -o $${o} -p \"org.tartarus.snowball.SnowballStemmer\" -eprefix $${l}_ -r ../runtime -n $${l}Stemmer"; \ + ./snowball $< -j -o $${o} -p "org.tartarus.snowball.SnowballStemmer" -eprefix $${l}_ -r ../runtime -n $${l}Stemmer + +splint: snowball.splint +snowball.splint: $(COMPILER_SOURCES) + splint $^ >$@ -weak + +# Make a full source distribution +dist: dist_snowball dist_libstemmer_c dist_libstemmer_java + +# Make a distribution of all the sources involved in snowball +dist_snowball: $(COMPILER_SOURCES) $(COMPILER_HEADERS) \ + $(RUNTIME_SOURCES) $(RUNTIME_HEADERS) \ + $(LIBSTEMMER_SOURCES) \ + $(LIBSTEMMER_UTF8_SOURCES) \ + $(LIBSTEMMER_HEADERS) \ + $(LIBSTEMMER_EXTRA) \ + $(ALL_ALGORITHM_FILES) $(STEMWORDS_SOURCES) \ + GNUmakefile README doc/TODO libstemmer/mkmodules.pl + destname=snowball_code; \ + dest=dist/$${destname}; \ + rm -rf $${dest} && \ + rm -f $${dest}.tgz && \ + for file in $^; do \ + dir=`dirname $$file` && \ + mkdir -p $${dest}/$${dir} && \ + cp -a $${file} $${dest}/$${dir} || exit 1 ; \ + done && \ + (cd dist && tar zcf $${destname}.tgz $${destname}) && \ + rm -rf $${dest} + +# Make a distribution of all the sources required to compile the C library. +dist_libstemmer_c: \ + $(RUNTIME_SOURCES) \ + $(RUNTIME_HEADERS) \ + $(LIBSTEMMER_SOURCES) \ + $(LIBSTEMMER_UTF8_SOURCES) \ + $(LIBSTEMMER_HEADERS) \ + $(LIBSTEMMER_EXTRA) \ + $(C_LIB_SOURCES) \ + $(C_LIB_HEADERS) \ + libstemmer/mkinc.mak \ + libstemmer/mkinc_utf8.mak + destname=libstemmer_c; \ + dest=dist/$${destname}; \ + rm -rf $${dest} && \ + rm -f $${dest}.tgz && \ + mkdir -p $${dest} && \ + cp -a doc/libstemmer_c_README $${dest}/README && \ + mkdir -p $${dest}/examples && \ + cp -a examples/stemwords.c $${dest}/examples && \ + mkdir -p $${dest}/$(c_src_dir) && \ + cp -a $(C_LIB_SOURCES) $(C_LIB_HEADERS) $${dest}/$(c_src_dir) && \ + mkdir -p $${dest}/runtime && \ + cp -a $(RUNTIME_SOURCES) $(RUNTIME_HEADERS) $${dest}/runtime && \ + mkdir -p $${dest}/libstemmer && \ + cp -a $(LIBSTEMMER_SOURCES) $(LIBSTEMMER_UTF8_SOURCES) $(LIBSTEMMER_HEADERS) $(LIBSTEMMER_EXTRA) $${dest}/libstemmer && \ + mkdir -p $${dest}/include && \ + mv $${dest}/libstemmer/libstemmer.h $${dest}/include && \ + (cd $${dest} && \ + echo "README" >> MANIFEST && \ + ls $(c_src_dir)/*.c $(c_src_dir)/*.h >> MANIFEST && \ + ls runtime/*.c runtime/*.h >> MANIFEST && \ + ls libstemmer/*.c libstemmer/*.h >> MANIFEST && \ + ls include/*.h >> MANIFEST) && \ + cp -a libstemmer/mkinc.mak libstemmer/mkinc_utf8.mak $${dest}/ && \ + echo 'include mkinc.mak' >> $${dest}/Makefile && \ + echo 'CFLAGS=-Iinclude' >> $${dest}/Makefile && \ + echo 'all: libstemmer.o stemwords' >> $${dest}/Makefile && \ + echo 'libstemmer.o: $$(snowball_sources:.c=.o)' >> $${dest}/Makefile && \ + echo ' $$(AR) -cru $$@ $$^' >> $${dest}/Makefile && \ + echo 'stemwords: examples/stemwords.o libstemmer.o' >> $${dest}/Makefile && \ + echo ' $$(CC) -o $$@ $$^' >> $${dest}/Makefile && \ + echo 'clean:' >> $${dest}/Makefile && \ + echo ' rm -f stemwords *.o $(c_src_dir)/*.o runtime/*.o libstemmer/*.o' >> $${dest}/Makefile && \ + (cd dist && tar zcf $${destname}.tgz $${destname}) && \ + rm -rf $${dest} + +# Make a distribution of all the sources required to compile the Java library. +dist_libstemmer_java: $(RUNTIME_SOURCES) $(RUNTIME_HEADERS) \ + $(LIBSTEMMER_EXTRA) \ + $(JAVA_SOURCES) + destname=libstemmer_java; \ + dest=dist/$${destname}; \ + rm -rf $${dest} && \ + rm -f $${dest}.tgz && \ + mkdir -p $${dest} && \ + cp -a doc/libstemmer_java_README $${dest}/README && \ + mkdir -p $${dest}/$(java_src_dir) && \ + cp -a $(JAVA_SOURCES) $${dest}/$(java_src_dir) && \ + mkdir -p $${dest}/$(java_src_main_dir) && \ + cp -a $(JAVARUNTIME_SOURCES) $${dest}/$(java_src_main_dir) && \ + (cd $${dest} && \ + echo "README" >> MANIFEST && \ + ls $(java_src_dir)/*.java >> MANIFEST && \ + ls $(java_src_main_dir)/*.java >> MANIFEST) && \ + (cd dist && tar zcf $${destname}.tgz $${destname}) && \ + rm -rf $${dest} + +check: check_utf8 check_iso_8859_1 check_iso_8859_2 check_koi8r + +check_utf8: $(libstemmer_algorithms:%=check_utf8_%) + +check_iso_8859_1: $(ISO_8859_1_algorithms:%=check_iso_8859_1_%) + +check_iso_8859_2: $(ISO_8859_2_algorithms:%=check_iso_8859_2_%) + +check_koi8r: $(KOI8_R_algorithms:%=check_koi8r_%) + +# Where the data files are located - assumed their repo is checked out as +# a sibling to this one. +STEMMING_DATA = ../snowball-data + +check_utf8_%: $(STEMMING_DATA)/% stemwords + @echo "Checking output of `echo $<|sed 's!.*/!!'` stemmer with UTF-8" + @./stemwords -c UTF_8 -l `echo $<|sed 's!.*/!!'` -i $</voc.txt -o tmp.txt + @diff -u $</output.txt tmp.txt + @if [ -e $</diffs.txt ] ; \ + then \ + ./stemwords -c UTF_8 -l `echo $<|sed 's!.*/!!'` -i $</voc.txt -o tmp.txt -p2 && \ + diff -u $</diffs.txt tmp.txt; \ + fi + @rm tmp.txt + +check_iso_8859_1_%: $(STEMMING_DATA)/% stemwords + @echo "Checking output of `echo $<|sed 's!.*/!!'` stemmer with ISO_8859_1" + @python -c 'print(open("$</voc.txt").read().decode("utf8").encode("iso8859-1"))' | \ + ./stemwords -c ISO_8859_1 -l `echo $<|sed 's!.*/!!'` -o tmp.txt + @python -c 'print(open("$</output.txt").read().decode("utf8").encode("iso8859-1"))' | \ + diff -u - tmp.txt + @rm tmp.txt + +check_iso_8859_2_%: $(STEMMING_DATA)/% stemwords + @echo "Checking output of `echo $<|sed 's!.*/!!'` stemmer with ISO_8859_2" + @python -c 'print(open("$</voc.txt").read().decode("utf8").encode("iso8859-2"))' | \ + ./stemwords -c ISO_8859_2 -l `echo $<|sed 's!.*/!!'` -o tmp.txt + @python -c 'print(open("$</output.txt").read().decode("utf8").encode("iso8859-2"))' | \ + diff -u - tmp.txt + @rm tmp.txt + +check_koi8r_%: $(STEMMING_DATA)/% stemwords + @echo "Checking output of `echo $<|sed 's!.*/!!'` stemmer with KOI8R" + @python -c 'print(open("$</voc.txt").read().decode("utf8").encode("koi8_r"))' | \ + ./stemwords -c KOI8_R -l `echo $<|sed 's!.*/!!'` -o tmp.txt + @python -c 'print(open("$</output.txt").read().decode("utf8").encode("koi8_r"))' | \ + diff -u - tmp.txt + @rm tmp.txt diff --git a/contrib/snowball/README b/contrib/snowball/README new file mode 100644 index 000000000..afb51b340 --- /dev/null +++ b/contrib/snowball/README @@ -0,0 +1,5 @@ +This contains the source code for the snowball compiler and the stemming +algorithms on the website. + +See http://snowball.tartarus.org/ for more details. + diff --git a/contrib/snowball/algorithms/danish/stem_ISO_8859_1.sbl b/contrib/snowball/algorithms/danish/stem_ISO_8859_1.sbl new file mode 100644 index 000000000..0a8190a08 --- /dev/null +++ b/contrib/snowball/algorithms/danish/stem_ISO_8859_1.sbl @@ -0,0 +1,91 @@ +routines ( + mark_regions + main_suffix + consonant_pair + other_suffix + undouble +) + +externals ( stem ) + +strings ( ch ) + +integers ( p1 x ) + +groupings ( v s_ending ) + +stringescapes {} + +/* special characters (in ISO Latin I) */ + +stringdef ae hex 'E6' +stringdef ao hex 'E5' +stringdef o/ hex 'F8' + +define v 'aeiouy{ae}{ao}{o/}' + +define s_ending 'abcdfghjklmnoprtvyz{ao}' + +define mark_regions as ( + + $p1 = limit + + test ( hop 3 setmark x ) + goto v gopast non-v setmark p1 + try ( $p1 < x $p1 = x ) +) + +backwardmode ( + + define main_suffix as ( + setlimit tomark p1 for ([substring]) + among( + + 'hed' 'ethed' 'ered' 'e' 'erede' 'ende' 'erende' 'ene' 'erne' 'ere' + 'en' 'heden' 'eren' 'er' 'heder' 'erer' 'heds' 'es' 'endes' + 'erendes' 'enes' 'ernes' 'eres' 'ens' 'hedens' 'erens' 'ers' 'ets' + 'erets' 'et' 'eret' + (delete) + 's' + (s_ending delete) + ) + ) + + define consonant_pair as ( + test ( + setlimit tomark p1 for ([substring]) + among( + 'gd' // significant in the call from other_suffix + 'dt' 'gt' 'kt' + ) + ) + next] delete + ) + + define other_suffix as ( + do ( ['st'] 'ig' delete ) + setlimit tomark p1 for ([substring]) + among( + 'ig' 'lig' 'elig' 'els' + (delete do consonant_pair) + 'l{o/}st' + (<-'l{o/}s') + ) + ) + define undouble as ( + setlimit tomark p1 for ([non-v] ->ch) + ch + delete + ) +) + +define stem as ( + + do mark_regions + backwards ( + do main_suffix + do consonant_pair + do other_suffix + do undouble + ) +) diff --git a/contrib/snowball/algorithms/danish/stem_MS_DOS_Latin_I.sbl b/contrib/snowball/algorithms/danish/stem_MS_DOS_Latin_I.sbl new file mode 100644 index 000000000..1131a1cb7 --- /dev/null +++ b/contrib/snowball/algorithms/danish/stem_MS_DOS_Latin_I.sbl @@ -0,0 +1,91 @@ +routines ( + mark_regions + main_suffix + consonant_pair + other_suffix + undouble +) + +externals ( stem ) + +strings ( ch ) + +integers ( p1 x ) + +groupings ( v s_ending ) + +stringescapes {} + +/* special characters (in MS-DOS Latin I) */ + +stringdef ae hex '91' +stringdef ao hex '86' +stringdef o/ hex '9B' + +define v 'aeiouy{ae}{ao}{o/}' + +define s_ending 'abcdfghjklmnoprtvyz{ao}' + +define mark_regions as ( + + $p1 = limit + + test ( hop 3 setmark x ) + goto v gopast non-v setmark p1 + try ( $p1 < x $p1 = x ) +) + +backwardmode ( + + define main_suffix as ( + setlimit tomark p1 for ([substring]) + among( + + 'hed' 'ethed' 'ered' 'e' 'erede' 'ende' 'erende' 'ene' 'erne' 'ere' + 'en' 'heden' 'eren' 'er' 'heder' 'erer' 'heds' 'es' 'endes' + 'erendes' 'enes' 'ernes' 'eres' 'ens' 'hedens' 'erens' 'ers' 'ets' + 'erets' 'et' 'eret' + (delete) + 's' + (s_ending delete) + ) + ) + + define consonant_pair as ( + test ( + setlimit tomark p1 for ([substring]) + among( + 'gd' // significant in the call from other_suffix + 'dt' 'gt' 'kt' + ) + ) + next] delete + ) + + define other_suffix as ( + do ( ['st'] 'ig' delete ) + setlimit tomark p1 for ([substring]) + among( + 'ig' 'lig' 'elig' 'els' + (delete do consonant_pair) + 'l{o/}st' + (<-'l{o/}s') + ) + ) + define undouble as ( + setlimit tomark p1 for ([non-v] ->ch) + ch + delete + ) +) + +define stem as ( + + do mark_regions + backwards ( + do main_suffix + do consonant_pair + do other_suffix + do undouble + ) +) diff --git a/contrib/snowball/algorithms/dutch/stem_ISO_8859_1.sbl b/contrib/snowball/algorithms/dutch/stem_ISO_8859_1.sbl new file mode 100644 index 000000000..f7609f766 --- /dev/null +++ b/contrib/snowball/algorithms/dutch/stem_ISO_8859_1.sbl @@ -0,0 +1,164 @@ +routines ( + prelude postlude + e_ending + en_ending + mark_regions + R1 R2 + undouble + standard_suffix +) + +externals ( stem ) + +booleans ( e_found ) + +integers ( p1 p2 ) + +groupings ( v v_I v_j ) + +stringescapes {} + +/* special characters (in ISO Latin I) */ + +stringdef a" hex 'E4' +stringdef e" hex 'EB' +stringdef i" hex 'EF' +stringdef o" hex 'F6' +stringdef u" hex 'FC' + +stringdef a' hex 'E1' +stringdef e' hex 'E9' +stringdef i' hex 'ED' +stringdef o' hex 'F3' +stringdef u' hex 'FA' + +stringdef e` hex 'E8' + +define v 'aeiouy{e`}' +define v_I v + 'I' +define v_j v + 'j' + +define prelude as ( + test repeat ( + [substring] among( + '{a"}' '{a'}' + (<- 'a') + '{e"}' '{e'}' + (<- 'e') + '{i"}' '{i'}' + (<- 'i') + '{o"}' '{o'}' + (<- 'o') + '{u"}' '{u'}' + (<- 'u') + '' (next) + ) //or next + ) + try(['y'] <- 'Y') + repeat goto ( + v [('i'] v <- 'I') or + ('y'] <- 'Y') + ) +) + +define mark_regions as ( + + $p1 = limit + $p2 = limit + + gopast v gopast non-v setmark p1 + try($p1 < 3 $p1 = 3) // at least 3 + gopast v gopast non-v setmark p2 + +) + +define postlude as repeat ( + + [substring] among( + 'Y' (<- 'y') + 'I' (<- 'i') + '' (next) + ) //or next + +) + +backwardmode ( + + define R1 as $p1 <= cursor + define R2 as $p2 <= cursor + + define undouble as ( + test among('kk' 'dd' 'tt') [next] delete + ) + + define e_ending as ( + unset e_found + ['e'] R1 test non-v delete + set e_found + undouble + ) + + define en_ending as ( + R1 non-v and not 'gem' delete + undouble + ) + + define standard_suffix as ( + do ( + [substring] among( + 'heden' + ( R1 <- 'heid' + ) + 'en' 'ene' + ( en_ending + ) + 's' 'se' + ( R1 non-v_j delete + ) + ) + ) + do e_ending + + do ( ['heid'] R2 not 'c' delete + ['en'] en_ending + ) + + do ( + [substring] among( + 'end' 'ing' + ( R2 delete + (['ig'] R2 not 'e' delete) or undouble + ) + 'ig' + ( R2 not 'e' delete + ) + 'lijk' + ( R2 delete e_ending + ) + 'baar' + ( R2 delete + ) + 'bar' + ( R2 e_found delete + ) + ) + ) + do ( + non-v_I + test ( + among ('aa' 'ee' 'oo' 'uu') + non-v + ) + [next] delete + ) + ) +) + +define stem as ( + + do prelude + do mark_regions + backwards + do standard_suffix + do postlude +) diff --git a/contrib/snowball/algorithms/dutch/stem_MS_DOS_Latin_I.sbl b/contrib/snowball/algorithms/dutch/stem_MS_DOS_Latin_I.sbl new file mode 100644 index 000000000..15b8718d1 --- /dev/null +++ b/contrib/snowball/algorithms/dutch/stem_MS_DOS_Latin_I.sbl @@ -0,0 +1,164 @@ +routines ( + prelude postlude + e_ending + en_ending + mark_regions + R1 R2 + undouble + standard_suffix +) + +externals ( stem ) + +booleans ( e_found ) + +integers ( p1 p2 ) + +groupings ( v v_I v_j ) + +stringescapes {} + +/* special characters (in MS-DOS Latin I) */ + +stringdef a" hex '84' +stringdef e" hex '89' +stringdef i" hex '8B' +stringdef o" hex '94' +stringdef u" hex '81' + +stringdef a' hex 'A0' +stringdef e' hex '82' +stringdef i' hex 'A1' +stringdef o' hex 'A2' +stringdef u' hex 'A3' + +stringdef e` hex '8A' + +define v 'aeiouy{e`}' +define v_I v + 'I' +define v_j v + 'j' + +define prelude as ( + test repeat ( + [substring] among( + '{a"}' '{a'}' + (<- 'a') + '{e"}' '{e'}' + (<- 'e') + '{i"}' '{i'}' + (<- 'i') + '{o"}' '{o'}' + (<- 'o') + '{u"}' '{u'}' + (<- 'u') + '' (next) + ) //or next + ) + try(['y'] <- 'Y') + repeat goto ( + v [('i'] v <- 'I') or + ('y'] <- 'Y') + ) +) + +define mark_regions as ( + + $p1 = limit + $p2 = limit + + gopast v gopast non-v setmark p1 + try($p1 < 3 $p1 = 3) // at least 3 + gopast v gopast non-v setmark p2 + +) + +define postlude as repeat ( + + [substring] among( + 'Y' (<- 'y') + 'I' (<- 'i') + '' (next) + ) //or next + +) + +backwardmode ( + + define R1 as $p1 <= cursor + define R2 as $p2 <= cursor + + define undouble as ( + test among('kk' 'dd' 'tt') [next] delete + ) + + define e_ending as ( + unset e_found + ['e'] R1 test non-v delete + set e_found + undouble + ) + + define en_ending as ( + R1 non-v and not 'gem' delete + undouble + ) + + define standard_suffix as ( + do ( + [substring] among( + 'heden' + ( R1 <- 'heid' + ) + 'en' 'ene' + ( en_ending + ) + 's' 'se' + ( R1 non-v_j delete + ) + ) + ) + do e_ending + + do ( ['heid'] R2 not 'c' delete + ['en'] en_ending + ) + + do ( + [substring] among( + 'end' 'ing' + ( R2 delete + (['ig'] R2 not 'e' delete) or undouble + ) + 'ig' + ( R2 not 'e' delete + ) + 'lijk' + ( R2 delete e_ending + ) + 'baar' + ( R2 delete + ) + 'bar' + ( R2 e_found delete + ) + ) + ) + do ( + non-v_I + test ( + among ('aa' 'ee' 'oo' 'uu') + non-v + ) + [next] delete + ) + ) +) + +define stem as ( + + do prelude + do mark_regions + backwards + do standard_suffix + do postlude +) diff --git a/contrib/snowball/algorithms/english/stem_ISO_8859_1.sbl b/contrib/snowball/algorithms/english/stem_ISO_8859_1.sbl new file mode 100644 index 000000000..fe18d7a91 --- /dev/null +++ b/contrib/snowball/algorithms/english/stem_ISO_8859_1.sbl @@ -0,0 +1,229 @@ +integers ( p1 p2 ) +booleans ( Y_found ) + +routines ( + prelude postlude + mark_regions + shortv + R1 R2 + Step_1a Step_1b Step_1c Step_2 Step_3 Step_4 Step_5 + exception1 + exception2 +) + +externals ( stem ) + +groupings ( v v_WXY valid_LI ) + +stringescapes {} + +define v 'aeiouy' +define v_WXY v + 'wxY' + +define valid_LI 'cdeghkmnrt' + +define prelude as ( + unset Y_found + do ( ['{'}'] delete) + do ( ['y'] <-'Y' set Y_found) + do repeat(goto (v ['y']) <-'Y' set Y_found) +) + +define mark_regions as ( + $p1 = limit + $p2 = limit + do( + among ( + 'gener' + 'commun' // added May 2005 + 'arsen' // added Nov 2006 (arsenic/arsenal) + // ... extensions possible here ... + ) or (gopast v gopast non-v) + setmark p1 + gopast v gopast non-v setmark p2 + ) +) + +backwardmode ( + + define shortv as ( + ( non-v_WXY v non-v ) + or + ( non-v v atlimit ) + ) + + define R1 as $p1 <= cursor + define R2 as $p2 <= cursor + + define Step_1a as ( + try ( + [substring] among ( + '{'}' '{'}s' '{'}s{'}' + (delete) + ) + ) + [substring] among ( + 'sses' (<-'ss') + 'ied' 'ies' + ((hop 2 <-'i') or <-'ie') + 's' (next gopast v delete) + 'us' 'ss' + ) + ) + + define Step_1b as ( + [substring] among ( + 'eed' 'eedly' + (R1 <-'ee') + 'ed' 'edly' 'ing' 'ingly' + ( + test gopast v delete + test substring among( + 'at' 'bl' 'iz' + (<+ 'e') + 'bb' 'dd' 'ff' 'gg' 'mm' 'nn' 'pp' 'rr' 'tt' + // ignoring double c, h, j, k, q, v, w, and x + ([next] delete) + '' (atmark p1 test shortv <+ 'e') + ) + ) + ) + ) + + define Step_1c as ( + ['y' or 'Y'] + non-v not atlimit + <-'i' + ) + + define Step_2 as ( + [substring] R1 among ( + 'tional' (<-'tion') + 'enci' (<-'ence') + 'anci' (<-'ance') + 'abli' (<-'able') + 'entli' (<-'ent') + 'izer' 'ization' + (<-'ize') + 'ational' 'ation' 'ator' + (<-'ate') + 'alism' 'aliti' 'alli' + (<-'al') + 'fulness' (<-'ful') + 'ousli' 'ousness' + (<-'ous') + 'iveness' 'iviti' + (<-'ive') + 'biliti' 'bli' + (<-'ble') + 'ogi' ('l' <-'og') + 'fulli' (<-'ful') + 'lessli' (<-'less') + 'li' (valid_LI delete) + ) + ) + + define Step_3 as ( + [substring] R1 among ( + 'tional' (<- 'tion') + 'ational' (<- 'ate') + 'alize' (<-'al') + 'icate' 'iciti' 'ical' + (<-'ic') + 'ful' 'ness' + (delete) + 'ative' + (R2 delete) // 'R2' added Dec 2001 + ) + ) + + define Step_4 as ( + [substring] R2 among ( + 'al' 'ance' 'ence' 'er' 'ic' 'able' 'ible' 'ant' 'ement' + 'ment' 'ent' 'ism' 'ate' 'iti' 'ous' 'ive' 'ize' + (delete) + 'ion' ('s' or 't' delete) + ) + ) + + define Step_5 as ( + [substring] among ( + 'e' (R2 or (R1 not shortv) delete) + 'l' (R2 'l' delete) + ) + ) + + define exception2 as ( + + [substring] atlimit among( + 'inning' 'outing' 'canning' 'herring' 'earring' + 'proceed' 'exceed' 'succeed' + + // ... extensions possible here ... + + ) + ) +) + +define exception1 as ( + + [substring] atlimit among( + + /* special changes: */ + + 'skis' (<-'ski') + 'skies' (<-'sky') + 'dying' (<-'die') + 'lying' (<-'lie') + 'tying' (<-'tie') + + /* special -LY cases */ + + 'idly' (<-'idl') + 'gently' (<-'gentl') + 'ugly' (<-'ugli') + 'early' (<-'earli') + 'only' (<-'onli') + 'singly' (<-'singl') + + // ... extensions possible here ... + + /* invariant forms: */ + + 'sky' + 'news' + 'howe' + + 'atlas' 'cosmos' 'bias' 'andes' // not plural forms + + // ... extensions possible here ... + ) +) + +define postlude as (Y_found repeat(goto (['Y']) <-'y')) + +define stem as ( + + exception1 or + not hop 3 or ( + do prelude + do mark_regions + backwards ( + + do Step_1a + + exception2 or ( + + do Step_1b + do Step_1c + + do Step_2 + do Step_3 + do Step_4 + + do Step_5 + ) + ) + do postlude + ) +) diff --git a/contrib/snowball/algorithms/finnish/stem_ISO_8859_1.sbl b/contrib/snowball/algorithms/finnish/stem_ISO_8859_1.sbl new file mode 100644 index 000000000..9ac74f292 --- /dev/null +++ b/contrib/snowball/algorithms/finnish/stem_ISO_8859_1.sbl @@ -0,0 +1,196 @@ + +/* Finnish stemmer. + + Numbers in square brackets refer to the sections in + Fred Karlsson, Finnish: An Essential Grammar. Routledge, 1999 + ISBN 0-415-20705-3 + +*/ + +routines ( + mark_regions + R2 + particle_etc possessive + LONG VI + case_ending + i_plural + t_plural + other_endings + tidy +) + +externals ( stem ) + +integers ( p1 p2 ) +strings ( x ) +booleans ( ending_removed ) +groupings ( AEI V1 V2 particle_end ) + +stringescapes {} + +/* special characters (in ISO Latin I) */ + +stringdef a" hex 'E4' +stringdef o" hex 'F6' + +define AEI 'a{a"}ei' +define V1 'aeiouy{a"}{o"}' +define V2 'aeiou{a"}{o"}' +define particle_end V1 + 'nt' + +define mark_regions as ( + + $p1 = limit + $p2 = limit + + goto V1 gopast non-V1 setmark p1 + goto V1 gopast non-V1 setmark p2 +) + +backwardmode ( + + define R2 as $p2 <= cursor + + define particle_etc as ( + setlimit tomark p1 for ([substring]) + among( + 'kin' + 'kaan' 'k{a"}{a"}n' + 'ko' 'k{o"}' + 'han' 'h{a"}n' + 'pa' 'p{a"}' // Particles [91] + (particle_end) + 'sti' // Adverb [87] + (R2) + ) + delete + ) + define possessive as ( // [36] + setlimit tomark p1 for ([substring]) + among( + 'si' + (not 'k' delete) // take 'ksi' as the Comitative case + 'ni' + (delete ['kse'] <- 'ksi') // kseni = ksi + ni + 'nsa' 'ns{a"}' + 'mme' + 'nne' + (delete) + /* Now for Vn possessives after case endings: [36] */ + 'an' + (among('ta' 'ssa' 'sta' 'lla' 'lta' 'na') delete) + '{a"}n' + (among('t{a"}' 'ss{a"}' 'st{a"}' + 'll{a"}' 'lt{a"}' 'n{a"}') delete) + 'en' + (among('lle' 'ine') delete) + ) + ) + + define LONG as + among('aa' 'ee' 'ii' 'oo' 'uu' '{a"}{a"}' '{o"}{o"}') + + define VI as ('i' V2) + + define case_ending as ( + setlimit tomark p1 for ([substring]) + among( + 'han' ('a') //-. + 'hen' ('e') // | + 'hin' ('i') // | + 'hon' ('o') // | + 'h{a"}n' ('{a"}') // Illative [43] + 'h{o"}n' ('{o"}') // | + 'siin' VI // | + 'seen' LONG //-' + + 'den' VI + 'tten' VI // Genitive plurals [34] + () + 'n' // Genitive or Illative + ( try ( LONG // Illative + or 'ie' // Genitive + and next ] + ) + /* otherwise Genitive */ + ) + + 'a' '{a"}' //-. + (V1 non-V1) // | + 'tta' 'tt{a"}' // Partitive [32] + ('e') // | + 'ta' 't{a"}' //-' + + 'ssa' 'ss{a"}' // Inessive [41] + 'sta' 'st{a"}' // Elative [42] + + 'lla' 'll{a"}' // Adessive [44] + 'lta' 'lt{a"}' // Ablative [51] + 'lle' // Allative [46] + 'na' 'n{a"}' // Essive [49] + 'ksi' // Translative[50] + 'ine' // Comitative [51] + + /* Abessive and Instructive are too rare for + inclusion [51] */ + + ) + delete + set ending_removed + ) + define other_endings as ( + setlimit tomark p2 for ([substring]) + among( + 'mpi' 'mpa' 'mp{a"}' + 'mmi' 'mma' 'mm{a"}' // Comparative forms [85] + (not 'po') //-improves things + 'impi' 'impa' 'imp{a"}' + 'immi' 'imma' 'imm{a"}' // Superlative forms [86] + 'eja' 'ej{a"}' // indicates agent [93.1B] + ) + delete + ) + define i_plural as ( // [26] + setlimit tomark p1 for ([substring]) + among( + 'i' 'j' + ) + delete + ) + define t_plural as ( // [26] + setlimit tomark p1 for ( + ['t'] test V1 + delete + ) + setlimit tomark p2 for ([substring]) + among( + 'mma' (not 'po') //-mmat endings + 'imma' //-immat endings + ) + delete + ) + define tidy as ( + setlimit tomark p1 for ( + do ( LONG and ([next] delete ) ) // undouble vowel + do ( [AEI] non-V1 delete ) // remove trailing a, a", e, i + do ( ['j'] 'o' or 'u' delete ) + do ( ['o'] 'j' delete ) + ) + goto non-V1 [next] -> x x delete // undouble consonant + ) +) + +define stem as ( + + do mark_regions + unset ending_removed + backwards ( + do particle_etc + do possessive + do case_ending + do other_endings + (ending_removed do i_plural) or do t_plural + do tidy + ) +) + diff --git a/contrib/snowball/algorithms/french/stem_ISO_8859_1.sbl b/contrib/snowball/algorithms/french/stem_ISO_8859_1.sbl new file mode 100644 index 000000000..e972f227f --- /dev/null +++ b/contrib/snowball/algorithms/french/stem_ISO_8859_1.sbl @@ -0,0 +1,248 @@ +routines ( + prelude postlude mark_regions + RV R1 R2 + standard_suffix + i_verb_suffix + verb_suffix + residual_suffix + un_double + un_accent +) + +externals ( stem ) + +integers ( pV p1 p2 ) + +groupings ( v keep_with_s ) + +stringescapes {} + +/* special characters (in ISO Latin I) */ + +stringdef a^ hex 'E2' // a-circumflex +stringdef a` hex 'E0' // a-grave +stringdef c, hex 'E7' // c-cedilla + +stringdef e" hex 'EB' // e-diaeresis (rare) +stringdef e' hex 'E9' // e-acute +stringdef e^ hex 'EA' // e-circumflex +stringdef e` hex 'E8' // e-grave +stringdef i" hex 'EF' // i-diaeresis +stringdef i^ hex 'EE' // i-circumflex +stringdef o^ hex 'F4' // o-circumflex +stringdef u^ hex 'FB' // u-circumflex +stringdef u` hex 'F9' // u-grave + +define v 'aeiouy{a^}{a`}{e"}{e'}{e^}{e`}{i"}{i^}{o^}{u^}{u`}' + +define prelude as repeat goto ( + + ( v [ ('u' ] v <- 'U') or + ('i' ] v <- 'I') or + ('y' ] <- 'Y') + ) + or + ( ['y'] v <- 'Y' ) + or + ( 'q' ['u'] <- 'U' ) +) + +define mark_regions as ( + + $pV = limit + $p1 = limit + $p2 = limit // defaults + + do ( + ( v v next ) + or + among ( // this exception list begun Nov 2006 + 'par' // paris, parie, pari + 'col' // colis + 'tap' // tapis + // extensions possible here + ) + or + ( next gopast v ) + setmark pV + ) + do ( + gopast v gopast non-v setmark p1 + gopast v gopast non-v setmark p2 + ) +) + +define postlude as repeat ( + + [substring] among( + 'I' (<- 'i') + 'U' (<- 'u') + 'Y' (<- 'y') + '' (next) + ) +) + +backwardmode ( + + define RV as $pV <= cursor + define R1 as $p1 <= cursor + define R2 as $p2 <= cursor + + define standard_suffix as ( + [substring] among( + + 'ance' 'iqUe' 'isme' 'able' 'iste' 'eux' + 'ances' 'iqUes' 'ismes' 'ables' 'istes' + ( R2 delete ) + 'atrice' 'ateur' 'ation' + 'atrices' 'ateurs' 'ations' + ( R2 delete + try ( ['ic'] (R2 delete) or <-'iqU' ) + ) + 'logie' + 'logies' + ( R2 <- 'log' ) + 'usion' 'ution' + 'usions' 'utions' + ( R2 <- 'u' ) + 'ence' + 'ences' + ( R2 <- 'ent' ) + 'ement' + 'ements' + ( + RV delete + try ( + [substring] among( + 'iv' (R2 delete ['at'] R2 delete) + 'eus' ((R2 delete) or (R1<-'eux')) + 'abl' 'iqU' + (R2 delete) + 'i{e`}r' 'I{e`}r' //) + (RV <-'i') //)--new 2 Sept 02 + ) + ) + ) + 'it{e'}' + 'it{e'}s' + ( + R2 delete + try ( + [substring] among( + 'abil' ((R2 delete) or <-'abl') + 'ic' ((R2 delete) or <-'iqU') + 'iv' (R2 delete) + ) + ) + ) + 'if' 'ive' + 'ifs' 'ives' + ( + R2 delete + try ( ['at'] R2 delete ['ic'] (R2 delete) or <-'iqU' ) + ) + 'eaux' (<- 'eau') + 'aux' (R1 <- 'al') + 'euse' + 'euses'((R2 delete) or (R1<-'eux')) + + 'issement' + 'issements'(R1 non-v delete) // verbal + + // fail(...) below forces entry to verb_suffix. -ment typically + // follows the p.p., e.g 'confus{e'}ment'. + + 'amment' (RV fail(<- 'ant')) + 'emment' (RV fail(<- 'ent')) + 'ment' + 'ments' (test(v RV) fail(delete)) + // v is e,i,u,{e'},I or U + ) + ) + + define i_verb_suffix as setlimit tomark pV for ( + [substring] among ( + '{i^}mes' '{i^}t' '{i^}tes' 'i' 'ie' 'ies' 'ir' 'ira' 'irai' + 'iraIent' 'irais' 'irait' 'iras' 'irent' 'irez' 'iriez' + 'irions' 'irons' 'iront' 'is' 'issaIent' 'issais' 'issait' + 'issant' 'issante' 'issantes' 'issants' 'isse' 'issent' 'isses' + 'issez' 'issiez' 'issions' 'issons' 'it' + (non-v delete) + ) + ) + + define verb_suffix as setlimit tomark pV for ( + [substring] among ( + 'ions' + (R2 delete) + + '{e'}' '{e'}e' '{e'}es' '{e'}s' '{e`}rent' 'er' 'era' 'erai' + 'eraIent' 'erais' 'erait' 'eras' 'erez' 'eriez' 'erions' + 'erons' 'eront' 'ez' 'iez' + + // 'ons' //-best omitted + + (delete) + + '{a^}mes' '{a^}t' '{a^}tes' 'a' 'ai' 'aIent' 'ais' 'ait' 'ant' + 'ante' 'antes' 'ants' 'as' 'asse' 'assent' 'asses' 'assiez' + 'assions' + (delete + try(['e'] delete) + ) + ) + ) + + define keep_with_s 'aiou{e`}s' + + define residual_suffix as ( + try(['s'] test non-keep_with_s delete) + setlimit tomark pV for ( + [substring] among( + 'ion' (R2 's' or 't' delete) + 'ier' 'i{e`}re' + 'Ier' 'I{e`}re' (<-'i') + 'e' (delete) + '{e"}' ('gu' delete) + ) + ) + ) + + define un_double as ( + test among('enn' 'onn' 'ett' 'ell' 'eill') [next] delete + ) + + define un_accent as ( + atleast 1 non-v + [ '{e'}' or '{e`}' ] <-'e' + ) +) + +define stem as ( + + do prelude + do mark_regions + backwards ( + + do ( + ( + ( standard_suffix or + i_verb_suffix or + verb_suffix + ) + and + try( [ ('Y' ] <- 'i' ) or + ('{c,}'] <- 'c' ) + ) + ) or + residual_suffix + ) + + // try(['ent'] RV delete) // is best omitted + + do un_double + do un_accent + ) + do postlude +) + diff --git a/contrib/snowball/algorithms/french/stem_MS_DOS_Latin_I.sbl b/contrib/snowball/algorithms/french/stem_MS_DOS_Latin_I.sbl new file mode 100644 index 000000000..996eba1ab --- /dev/null +++ b/contrib/snowball/algorithms/french/stem_MS_DOS_Latin_I.sbl @@ -0,0 +1,239 @@ +routines ( + prelude postlude mark_regions + RV R1 R2 + standard_suffix + i_verb_suffix + verb_suffix + residual_suffix + un_double + un_accent +) + +externals ( stem ) + +integers ( pV p1 p2 ) + +groupings ( v keep_with_s ) + +stringescapes {} + +/* special characters (in MS-DOS Latin I) */ + +stringdef a^ hex '83' // a-circumflex +stringdef a` hex '85' // a-grave +stringdef c, hex '87' // c-cedilla + +stringdef e" hex '89' // e-diaeresis (rare) +stringdef e' hex '82' // e-acute +stringdef e^ hex '88' // e-circumflex +stringdef e` hex '8A' // e-grave +stringdef i" hex '8B' // i-diaeresis +stringdef i^ hex '8C' // i-circumflex +stringdef o^ hex '93' // o-circumflex +stringdef u^ hex '96' // u-circumflex +stringdef u` hex '97' // u-grave + +define v 'aeiouy{a^}{a`}{e"}{e'}{e^}{e`}{i"}{i^}{o^}{u^}{u`}' + +define prelude as repeat goto ( + + ( v [ ('u' ] v <- 'U') or + ('i' ] v <- 'I') or + ('y' ] <- 'Y') + ) + or + ( ['y'] v <- 'Y' ) + or + ( 'q' ['u'] <- 'U' ) +) + +define mark_regions as ( + + $pV = limit + $p1 = limit + $p2 = limit // defaults + + do ( + ( v v next ) or ( next gopast v ) + setmark pV + ) + do ( + gopast v gopast non-v setmark p1 + gopast v gopast non-v setmark p2 + ) +) + +define postlude as repeat ( + + [substring] among( + 'I' (<- 'i') + 'U' (<- 'u') + 'Y' (<- 'y') + '' (next) + ) +) + +backwardmode ( + + define RV as $pV <= cursor + define R1 as $p1 <= cursor + define R2 as $p2 <= cursor + + define standard_suffix as ( + [substring] among( + + 'ance' 'iqUe' 'isme' 'able' 'iste' 'eux' + 'ances' 'iqUes' 'ismes' 'ables' 'istes' + ( R2 delete ) + 'atrice' 'ateur' 'ation' + 'atrices' 'ateurs' 'ations' + ( R2 delete + try ( ['ic'] (R2 delete) or <-'iqU' ) + ) + 'logie' + 'logies' + ( R2 <- 'log' ) + 'usion' 'ution' + 'usions' 'utions' + ( R2 <- 'u' ) + 'ence' + 'ences' + ( R2 <- 'ent' ) + 'ement' + 'ements' + ( + RV delete + try ( + [substring] among( + 'iv' (R2 delete ['at'] R2 delete) + 'eus' ((R2 delete) or (R1<-'eux')) + 'abl' 'iqU' + (R2 delete) + 'i{e`}r' 'I{e`}r' //) + (RV <-'i') //)--new 2 Sept 02 + ) + ) + ) + 'it{e'}' + 'it{e'}s' + ( + R2 delete + try ( + [substring] among( + 'abil' ((R2 delete) or <-'abl') + 'ic' ((R2 delete) or <-'iqU') + 'iv' (R2 delete) + ) + ) + ) + 'if' 'ive' + 'ifs' 'ives' + ( + R2 delete + try ( ['at'] R2 delete ['ic'] (R2 delete) or <-'iqU' ) + ) + 'eaux' (<- 'eau') + 'aux' (R1 <- 'al') + 'euse' + 'euses'((R2 delete) or (R1<-'eux')) + + 'issement' + 'issements'(R1 non-v delete) // verbal + + // fail(...) below forces entry to verb_suffix. -ment typically + // follows the p.p., e.g 'confus{e'}ment'. + + 'amment' (RV fail(<- 'ant')) + 'emment' (RV fail(<- 'ent')) + 'ment' + 'ments' (test(v RV) fail(delete)) + // v is e,i,u,{e'},I or U + ) + ) + + define i_verb_suffix as setlimit tomark pV for ( + [substring] among ( + '{i^}mes' '{i^}t' '{i^}tes' 'i' 'ie' 'ies' 'ir' 'ira' 'irai' + 'iraIent' 'irais' 'irait' 'iras' 'irent' 'irez' 'iriez' + 'irions' 'irons' 'iront' 'is' 'issaIent' 'issais' 'issait' + 'issant' 'issante' 'issantes' 'issants' 'isse' 'issent' 'isses' + 'issez' 'issiez' 'issions' 'issons' 'it' + (non-v delete) + ) + ) + + define verb_suffix as setlimit tomark pV for ( + [substring] among ( + 'ions' + (R2 delete) + + '{e'}' '{e'}e' '{e'}es' '{e'}s' '{e`}rent' 'er' 'era' 'erai' + 'eraIent' 'erais' 'erait' 'eras' 'erez' 'eriez' 'erions' + 'erons' 'eront' 'ez' 'iez' + + // 'ons' //-best omitted + + (delete) + + '{a^}mes' '{a^}t' '{a^}tes' 'a' 'ai' 'aIent' 'ais' 'ait' 'ant' + 'ante' 'antes' 'ants' 'as' 'asse' 'assent' 'asses' 'assiez' + 'assions' + (delete + try(['e'] delete) + ) + ) + ) + + define keep_with_s 'aiou{e`}s' + + define residual_suffix as ( + try(['s'] test non-keep_with_s delete) + setlimit tomark pV for ( + [substring] among( + 'ion' (R2 's' or 't' delete) + 'ier' 'i{e`}re' + 'Ier' 'I{e`}re' (<-'i') + 'e' (delete) + '{e"}' ('gu' delete) + ) + ) + ) + + define un_double as ( + test among('enn' 'onn' 'ett' 'ell' 'eill') [next] delete + ) + + define un_accent as ( + atleast 1 non-v + [ '{e'}' or '{e`}' ] <-'e' + ) +) + +define stem as ( + + do prelude + do mark_regions + backwards ( + + do ( + ( + ( standard_suffix or + i_verb_suffix or + verb_suffix + ) + and + try( [ ('Y' ] <- 'i' ) or + ('{c,}'] <- 'c' ) + ) + ) or + residual_suffix + ) + + // try(['ent'] RV delete) // is best omitted + + do un_double + do un_accent + ) + do postlude +) + diff --git a/contrib/snowball/algorithms/german/stem_ISO_8859_1.sbl b/contrib/snowball/algorithms/german/stem_ISO_8859_1.sbl new file mode 100644 index 000000000..7069daf0d --- /dev/null +++ b/contrib/snowball/algorithms/german/stem_ISO_8859_1.sbl @@ -0,0 +1,139 @@ + +/* + Extra rule for -nisse ending added 11 Dec 2009 +*/ + +routines ( + prelude postlude + mark_regions + R1 R2 + standard_suffix +) + +externals ( stem ) + +integers ( p1 p2 x ) + +groupings ( v s_ending st_ending ) + +stringescapes {} + +/* special characters (in ISO Latin I) */ + +stringdef a" hex 'E4' +stringdef o" hex 'F6' +stringdef u" hex 'FC' +stringdef ss hex 'DF' + +define v 'aeiouy{a"}{o"}{u"}' + +define s_ending 'bdfghklmnrt' +define st_ending s_ending - 'r' + +define prelude as ( + + test repeat ( + ( + ['{ss}'] <- 'ss' + ) or next + ) + + repeat goto ( + v [('u'] v <- 'U') or + ('y'] v <- 'Y') + ) +) + +define mark_regions as ( + + $p1 = limit + $p2 = limit + + test(hop 3 setmark x) + + gopast v gopast non-v setmark p1 + try($p1 < x $p1 = x) // at least 3 + gopast v gopast non-v setmark p2 + +) + +define postlude as repeat ( + + [substring] among( + 'Y' (<- 'y') + 'U' (<- 'u') + '{a"}' (<- 'a') + '{o"}' (<- 'o') + '{u"}' (<- 'u') + '' (next) + ) + +) + +backwardmode ( + + define R1 as $p1 <= cursor + define R2 as $p2 <= cursor + + define standard_suffix as ( + do ( + [substring] R1 among( + 'em' 'ern' 'er' + ( delete + ) + 'e' 'en' 'es' + ( delete + try (['s'] 'nis' delete) + ) + 's' + ( s_ending delete + ) + ) + ) + do ( + [substring] R1 among( + 'en' 'er' 'est' + ( delete + ) + 'st' + ( st_ending hop 3 delete + ) + ) + ) + do ( + [substring] R2 among( + 'end' 'ung' + ( delete + try (['ig'] not 'e' R2 delete) + ) + 'ig' 'ik' 'isch' + ( not 'e' delete + ) + 'lich' 'heit' + ( delete + try ( + ['er' or 'en'] R1 delete + ) + ) + 'keit' + ( delete + try ( + [substring] R2 among( + 'lich' 'ig' + ( delete + ) + ) + ) + ) + ) + ) + ) +) + +define stem as ( + do prelude + do mark_regions + backwards + do standard_suffix + do postlude +) diff --git a/contrib/snowball/algorithms/german/stem_MS_DOS_Latin_I.sbl b/contrib/snowball/algorithms/german/stem_MS_DOS_Latin_I.sbl new file mode 100644 index 000000000..3effb3257 --- /dev/null +++ b/contrib/snowball/algorithms/german/stem_MS_DOS_Latin_I.sbl @@ -0,0 +1,139 @@ + +/* + Extra rule for -nisse ending added 11 Dec 2009 +*/ + +routines ( + prelude postlude + mark_regions + R1 R2 + standard_suffix +) + +externals ( stem ) + +integers ( p1 p2 x ) + +groupings ( v s_ending st_ending ) + +stringescapes {} + +/* special characters (in MS-DOS Latin I) */ + +stringdef a" hex '84' +stringdef o" hex '94' +stringdef u" hex '81' +stringdef ss hex 'E1' + +define v 'aeiouy{a"}{o"}{u"}' + +define s_ending 'bdfghklmnrt' +define st_ending s_ending - 'r' + +define prelude as ( + + test repeat ( + ( + ['{ss}'] <- 'ss' + ) or next + ) + + repeat goto ( + v [('u'] v <- 'U') or + ('y'] v <- 'Y') + ) +) + +define mark_regions as ( + + $p1 = limit + $p2 = limit + + test(hop 3 setmark x) + + gopast v gopast non-v setmark p1 + try($p1 < x $p1 = x) // at least 3 + gopast v gopast non-v setmark p2 + +) + +define postlude as repeat ( + + [substring] among( + 'Y' (<- 'y') + 'U' (<- 'u') + '{a"}' (<- 'a') + '{o"}' (<- 'o') + '{u"}' (<- 'u') + '' (next) + ) + +) + +backwardmode ( + + define R1 as $p1 <= cursor + define R2 as $p2 <= cursor + + define standard_suffix as ( + do ( + [substring] R1 among( + 'em' 'ern' 'er' + ( delete + ) + 'e' 'en' 'es' + ( delete + try (['s'] 'nis' delete) + ) + 's' + ( s_ending delete + ) + ) + ) + do ( + [substring] R1 among( + 'en' 'er' 'est' + ( delete + ) + 'st' + ( st_ending hop 3 delete + ) + ) + ) + do ( + [substring] R2 among( + 'end' 'ung' + ( delete + try (['ig'] not 'e' R2 delete) + ) + 'ig' 'ik' 'isch' + ( not 'e' delete + ) + 'lich' 'heit' + ( delete + try ( + ['er' or 'en'] R1 delete + ) + ) + 'keit' + ( delete + try ( + [substring] R2 among( + 'lich' 'ig' + ( delete + ) + ) + ) + ) + ) + ) + ) +) + +define stem as ( + do prelude + do mark_regions + backwards + do standard_suffix + do postlude +) diff --git a/contrib/snowball/algorithms/german2/stem_ISO_8859_1.sbl b/contrib/snowball/algorithms/german2/stem_ISO_8859_1.sbl new file mode 100644 index 000000000..ce6026a86 --- /dev/null +++ b/contrib/snowball/algorithms/german2/stem_ISO_8859_1.sbl @@ -0,0 +1,145 @@ + +/* + Extra rule for -nisse ending added 11 Dec 2009 +*/ + +routines ( + prelude postlude + mark_regions + R1 R2 + standard_suffix +) + +externals ( stem ) + +integers ( p1 p2 x ) + +groupings ( v s_ending st_ending ) + +stringescapes {} + +/* special characters (in ISO Latin I) */ + +stringdef a" hex 'E4' +stringdef o" hex 'F6' +stringdef u" hex 'FC' +stringdef ss hex 'DF' + +define v 'aeiouy{a"}{o"}{u"}' + +define s_ending 'bdfghklmnrt' +define st_ending s_ending - 'r' + +define prelude as ( + + test repeat goto ( + v [('u'] v <- 'U') or + ('y'] v <- 'Y') + ) + + repeat ( + [substring] among( + '{ss}' (<- 'ss') + 'ae' (<- '{a"}') + 'oe' (<- '{o"}') + 'ue' (<- '{u"}') + 'qu' (hop 2) + '' (next) + ) + ) + +) + +define mark_regions as ( + + $p1 = limit + $p2 = limit + + test(hop 3 setmark x) + + gopast v gopast non-v setmark p1 + try($p1 < x $p1 = x) // at least 3 + gopast v gopast non-v setmark p2 + +) + +define postlude as repeat ( + + [substring] among( + 'Y' (<- 'y') + 'U' (<- 'u') + '{a"}' (<- 'a') + '{o"}' (<- 'o') + '{u"}' (<- 'u') + '' (next) + ) + +) + +backwardmode ( + + define R1 as $p1 <= cursor + define R2 as $p2 <= cursor + + define standard_suffix as ( + do ( + [substring] R1 among( + 'em' 'ern' 'er' + ( delete + ) + 'e' 'en' 'es' + ( delete + try (['s'] 'nis' delete) + ) + 's' + ( s_ending delete + ) + ) + ) + do ( + [substring] R1 among( + 'en' 'er' 'est' + ( delete + ) + 'st' + ( st_ending hop 3 delete + ) + ) + ) + do ( + [substring] R2 among( + 'end' 'ung' + ( delete + try (['ig'] not 'e' R2 delete) + ) + 'ig' 'ik' 'isch' + ( not 'e' delete + ) + 'lich' 'heit' + ( delete + try ( + ['er' or 'en'] R1 delete + ) + ) + 'keit' + ( delete + try ( + [substring] R2 among( + 'lich' 'ig' + ( delete + ) + ) + ) + ) + ) + ) + ) +) + +define stem as ( + do prelude + do mark_regions + backwards + do standard_suffix + do postlude +) diff --git a/contrib/snowball/algorithms/hungarian/stem_ISO_8859_2.sbl b/contrib/snowball/algorithms/hungarian/stem_ISO_8859_2.sbl new file mode 100644 index 000000000..d1a644931 --- /dev/null +++ b/contrib/snowball/algorithms/hungarian/stem_ISO_8859_2.sbl @@ -0,0 +1,241 @@ +/* +Hungarian Stemmer +Removes noun inflections +*/ + +routines ( + mark_regions + R1 + v_ending + case + case_special + case_other + plural + owned + sing_owner + plur_owner + instrum + factive + undouble + double +) + +externals ( stem ) + +integers ( p1 ) +groupings ( v ) + +stringescapes {} + +/* special characters (in ISO Latin 2) */ + +stringdef a' hex 'E1' //a-acute +stringdef e' hex 'E9' //e-acute +stringdef i' hex 'ED' //i-acute +stringdef o' hex 'F3' //o-acute +stringdef o" hex 'F6' //o-umlaut +stringdef oq hex 'F5' //o-double acute +stringdef u' hex 'FA' //u-acute +stringdef u" hex 'FC' //u-umlaut +stringdef uq hex 'FB' //u-double acute + +define v 'aeiou{a'}{e'}{i'}{o'}{o"}{oq}{u'}{u"}{uq}' + +define mark_regions as ( + + $p1 = limit + + (v goto non-v + among('cs' 'gy' 'ly' 'ny' 'sz' 'ty' 'zs' 'dzs') or next + setmark p1) + or + + (non-v gopast v setmark p1) +) + +backwardmode ( + + define R1 as $p1 <= cursor + + define v_ending as ( + [substring] R1 among( + '{a'}' (<- 'a') + '{e'}' (<- 'e') + ) + ) + + define double as ( + test among('bb' 'cc' 'ccs' 'dd' 'ff' 'gg' 'ggy' 'jj' 'kk' 'll' 'lly' 'mm' + 'nn' 'nny' 'pp' 'rr' 'ss' 'ssz' 'tt' 'tty' 'vv' 'zz' 'zzs') + ) + + define undouble as ( + next [hop 1] delete + ) + + define instrum as( + [substring] R1 among( + 'al' (double) + 'el' (double) + ) + delete + undouble + ) + + + define case as ( + [substring] R1 among( + 'ban' 'ben' + 'ba' 'be' + 'ra' 're' + 'nak' 'nek' + 'val' 'vel' + 't{o'}l' 't{oq}l' + 'r{o'}l' 'r{oq}l' + 'b{o'}l' 'b{oq}l' + 'hoz' 'hez' 'h{o"}z' + 'n{a'}l' 'n{e'}l' + 'ig' + 'at' 'et' 'ot' '{o"}t' + '{e'}rt' + 'k{e'}pp' 'k{e'}ppen' + 'kor' + 'ul' '{u"}l' + 'v{a'}' 'v{e'}' + 'onk{e'}nt' 'enk{e'}nt' 'ank{e'}nt' + 'k{e'}nt' + 'en' 'on' 'an' '{o"}n' + 'n' + 't' + ) + delete + v_ending + ) + + define case_special as( + [substring] R1 among( + '{e'}n' (<- 'e') + '{a'}n' (<- 'a') + '{a'}nk{e'}nt' (<- 'a') + ) + ) + + define case_other as( + [substring] R1 among( + 'astul' 'est{u"}l' (delete) + 'stul' 'st{u"}l' (delete) + '{a'}stul' (<- 'a') + '{e'}st{u"}l' (<- 'e') + ) + ) + + define factive as( + [substring] R1 among( + '{a'}' (double) + '{e'}' (double) + ) + delete + undouble + ) + + define plural as ( + [substring] R1 among( + '{a'}k' (<- 'a') + '{e'}k' (<- 'e') + '{o"}k' (delete) + 'ak' (delete) + 'ok' (delete) + 'ek' (delete) + 'k' (delete) + ) + ) + + define owned as ( + [substring] R1 among ( + 'ok{e'}' '{o"}k{e'}' 'ak{e'}' 'ek{e'}' (delete) + '{e'}k{e'}' (<- 'e') + '{a'}k{e'}' (<- 'a') + 'k{e'}' (delete) + '{e'}{e'}i' (<- 'e') + '{a'}{e'}i' (<- 'a') + '{e'}i' (delete) + '{e'}{e'}' (<- 'e') + '{e'}' (delete) + ) + ) + + define sing_owner as ( + [substring] R1 among( + '{u"}nk' 'unk' (delete) + '{a'}nk' (<- 'a') + '{e'}nk' (<- 'e') + 'nk' (delete) + '{a'}juk' (<- 'a') + '{e'}j{u"}k' (<- 'e') + 'juk' 'j{u"}k' (delete) + 'uk' '{u"}k' (delete) + 'em' 'om' 'am' (delete) + '{a'}m' (<- 'a') + '{e'}m' (<- 'e') + 'm' (delete) + 'od' 'ed' 'ad' '{o"}d' (delete) + '{a'}d' (<- 'a') + '{e'}d' (<- 'e') + 'd' (delete) + 'ja' 'je' (delete) + 'a' 'e' 'o' (delete) + '{a'}' (<- 'a') + '{e'}' (<- 'e') + ) + ) + + define plur_owner as ( + [substring] R1 among( + 'jaim' 'jeim' (delete) + '{a'}im' (<- 'a') + '{e'}im' (<- 'e') + 'aim' 'eim' (delete) + 'im' (delete) + 'jaid' 'jeid' (delete) + '{a'}id' (<- 'a') + '{e'}id' (<- 'e') + 'aid' 'eid' (delete) + 'id' (delete) + 'jai' 'jei' (delete) + '{a'}i' (<- 'a') + '{e'}i' (<- 'e') + 'ai' 'ei' (delete) + 'i' (delete) + 'jaink' 'jeink' (delete) + 'eink' 'aink' (delete) + '{a'}ink' (<- 'a') + '{e'}ink' (<- 'e') + 'ink' + 'jaitok' 'jeitek' (delete) + 'aitok' 'eitek' (delete) + '{a'}itok' (<- 'a') + '{e'}itek' (<- 'e') + 'itek' (delete) + 'jeik' 'jaik' (delete) + 'aik' 'eik' (delete) + '{a'}ik' (<- 'a') + '{e'}ik' (<- 'e') + 'ik' (delete) + ) + ) +) + +define stem as ( + do mark_regions + backwards ( + do instrum + do case + do case_special + do case_other + do factive + do owned + do sing_owner + do plur_owner + do plural + ) +) diff --git a/contrib/snowball/algorithms/hungarian/stem_Unicode.sbl b/contrib/snowball/algorithms/hungarian/stem_Unicode.sbl new file mode 100644 index 000000000..c812e055c --- /dev/null +++ b/contrib/snowball/algorithms/hungarian/stem_Unicode.sbl @@ -0,0 +1,241 @@ +/* +Hungarian Stemmer +Removes noun inflections +*/ + +routines ( + mark_regions + R1 + v_ending + case + case_special + case_other + plural + owned + sing_owner + plur_owner + instrum + factive + undouble + double +) + +externals ( stem ) + +integers ( p1 ) +groupings ( v ) + +stringescapes {} + +/* special characters (in Unicode) */ + +stringdef a' hex 'E1' //a-acute +stringdef e' hex 'E9' //e-acute +stringdef i' hex 'ED' //i-acute +stringdef o' hex 'F3' //o-acute +stringdef o" hex 'F6' //o-umlaut +stringdef oq hex '151' //o-double acute +stringdef u' hex 'FA' //u-acute +stringdef u" hex 'FC' //u-umlaut +stringdef uq hex '171' //u-double acute + +define v 'aeiou{a'}{e'}{i'}{o'}{o"}{oq}{u'}{u"}{uq}' + +define mark_regions as ( + + $p1 = limit + + (v goto non-v + among('cs' 'gy' 'ly' 'ny' 'sz' 'ty' 'zs' 'dzs') or next + setmark p1) + or + + (non-v gopast v setmark p1) +) + +backwardmode ( + + define R1 as $p1 <= cursor + + define v_ending as ( + [substring] R1 among( + '{a'}' (<- 'a') + '{e'}' (<- 'e') + ) + ) + + define double as ( + test among('bb' 'cc' 'ccs' 'dd' 'ff' 'gg' 'ggy' 'jj' 'kk' 'll' 'lly' 'mm' + 'nn' 'nny' 'pp' 'rr' 'ss' 'ssz' 'tt' 'tty' 'vv' 'zz' 'zzs') + ) + + define undouble as ( + next [hop 1] delete + ) + + define instrum as( + [substring] R1 among( + 'al' (double) + 'el' (double) + ) + delete + undouble + ) + + + define case as ( + [substring] R1 among( + 'ban' 'ben' + 'ba' 'be' + 'ra' 're' + 'nak' 'nek' + 'val' 'vel' + 't{o'}l' 't{oq}l' + 'r{o'}l' 'r{oq}l' + 'b{o'}l' 'b{oq}l' + 'hoz' 'hez' 'h{o"}z' + 'n{a'}l' 'n{e'}l' + 'ig' + 'at' 'et' 'ot' '{o"}t' + '{e'}rt' + 'k{e'}pp' 'k{e'}ppen' + 'kor' + 'ul' '{u"}l' + 'v{a'}' 'v{e'}' + 'onk{e'}nt' 'enk{e'}nt' 'ank{e'}nt' + 'k{e'}nt' + 'en' 'on' 'an' '{o"}n' + 'n' + 't' + ) + delete + v_ending + ) + + define case_special as( + [substring] R1 among( + '{e'}n' (<- 'e') + '{a'}n' (<- 'a') + '{a'}nk{e'}nt' (<- 'a') + ) + ) + + define case_other as( + [substring] R1 among( + 'astul' 'est{u"}l' (delete) + 'stul' 'st{u"}l' (delete) + '{a'}stul' (<- 'a') + '{e'}st{u"}l' (<- 'e') + ) + ) + + define factive as( + [substring] R1 among( + '{a'}' (double) + '{e'}' (double) + ) + delete + undouble + ) + + define plural as ( + [substring] R1 among( + '{a'}k' (<- 'a') + '{e'}k' (<- 'e') + '{o"}k' (delete) + 'ak' (delete) + 'ok' (delete) + 'ek' (delete) + 'k' (delete) + ) + ) + + define owned as ( + [substring] R1 among ( + 'ok{e'}' '{o"}k{e'}' 'ak{e'}' 'ek{e'}' (delete) + '{e'}k{e'}' (<- 'e') + '{a'}k{e'}' (<- 'a') + 'k{e'}' (delete) + '{e'}{e'}i' (<- 'e') + '{a'}{e'}i' (<- 'a') + '{e'}i' (delete) + '{e'}{e'}' (<- 'e') + '{e'}' (delete) + ) + ) + + define sing_owner as ( + [substring] R1 among( + '{u"}nk' 'unk' (delete) + '{a'}nk' (<- 'a') + '{e'}nk' (<- 'e') + 'nk' (delete) + '{a'}juk' (<- 'a') + '{e'}j{u"}k' (<- 'e') + 'juk' 'j{u"}k' (delete) + 'uk' '{u"}k' (delete) + 'em' 'om' 'am' (delete) + '{a'}m' (<- 'a') + '{e'}m' (<- 'e') + 'm' (delete) + 'od' 'ed' 'ad' '{o"}d' (delete) + '{a'}d' (<- 'a') + '{e'}d' (<- 'e') + 'd' (delete) + 'ja' 'je' (delete) + 'a' 'e' 'o' (delete) + '{a'}' (<- 'a') + '{e'}' (<- 'e') + ) + ) + + define plur_owner as ( + [substring] R1 among( + 'jaim' 'jeim' (delete) + '{a'}im' (<- 'a') + '{e'}im' (<- 'e') + 'aim' 'eim' (delete) + 'im' (delete) + 'jaid' 'jeid' (delete) + '{a'}id' (<- 'a') + '{e'}id' (<- 'e') + 'aid' 'eid' (delete) + 'id' (delete) + 'jai' 'jei' (delete) + '{a'}i' (<- 'a') + '{e'}i' (<- 'e') + 'ai' 'ei' (delete) + 'i' (delete) + 'jaink' 'jeink' (delete) + 'eink' 'aink' (delete) + '{a'}ink' (<- 'a') + '{e'}ink' (<- 'e') + 'ink' + 'jaitok' 'jeitek' (delete) + 'aitok' 'eitek' (delete) + '{a'}itok' (<- 'a') + '{e'}itek' (<- 'e') + 'itek' (delete) + 'jeik' 'jaik' (delete) + 'aik' 'eik' (delete) + '{a'}ik' (<- 'a') + '{e'}ik' (<- 'e') + 'ik' (delete) + ) + ) +) + +define stem as ( + do mark_regions + backwards ( + do instrum + do case + do case_special + do case_other + do factive + do owned + do sing_owner + do plur_owner + do plural + ) +) diff --git a/contrib/snowball/algorithms/italian/stem_ISO_8859_1.sbl b/contrib/snowball/algorithms/italian/stem_ISO_8859_1.sbl new file mode 100644 index 000000000..8d25cf64f --- /dev/null +++ b/contrib/snowball/algorithms/italian/stem_ISO_8859_1.sbl @@ -0,0 +1,195 @@ + +routines ( + prelude postlude mark_regions + RV R1 R2 + attached_pronoun + standard_suffix + verb_suffix + vowel_suffix +) + +externals ( stem ) + +integers ( pV p1 p2 ) + +groupings ( v AEIO CG ) + +stringescapes {} + +/* special characters (in ISO Latin I) */ + +stringdef a' hex 'E1' +stringdef a` hex 'E0' +stringdef e' hex 'E9' +stringdef e` hex 'E8' +stringdef i' hex 'ED' +stringdef i` hex 'EC' +stringdef o' hex 'F3' +stringdef o` hex 'F2' +stringdef u' hex 'FA' +stringdef u` hex 'F9' + +define v 'aeiou{a`}{e`}{i`}{o`}{u`}' + +define prelude as ( + test repeat ( + [substring] among( + '{a'}' (<- '{a`}') + '{e'}' (<- '{e`}') + '{i'}' (<- '{i`}') + '{o'}' (<- '{o`}') + '{u'}' (<- '{u`}') + 'qu' (<- 'qU') + '' (next) + ) + ) + repeat goto ( + v [ ('u' ] v <- 'U') or + ('i' ] v <- 'I') + ) +) + +define mark_regions as ( + + $pV = limit + $p1 = limit + $p2 = limit // defaults + + do ( + ( v (non-v gopast v) or (v gopast non-v) ) + or + ( non-v (non-v gopast v) or (v next) ) + setmark pV + ) + do ( + gopast v gopast non-v setmark p1 + gopast v gopast non-v setmark p2 + ) +) + +define postlude as repeat ( + + [substring] among( + 'I' (<- 'i') + 'U' (<- 'u') + '' (next) + ) + +) + +backwardmode ( + + define RV as $pV <= cursor + define R1 as $p1 <= cursor + define R2 as $p2 <= cursor + + define attached_pronoun as ( + [substring] among( + 'ci' 'gli' 'la' 'le' 'li' 'lo' + 'mi' 'ne' 'si' 'ti' 'vi' + // the compound forms are: + 'sene' 'gliela' 'gliele' 'glieli' 'glielo' 'gliene' + 'mela' 'mele' 'meli' 'melo' 'mene' + 'tela' 'tele' 'teli' 'telo' 'tene' + 'cela' 'cele' 'celi' 'celo' 'cene' + 'vela' 'vele' 'veli' 'velo' 'vene' + ) + among( (RV) + 'ando' 'endo' (delete) + 'ar' 'er' 'ir' (<- 'e') + ) + ) + + define standard_suffix as ( + [substring] among( + + 'anza' 'anze' 'ico' 'ici' 'ica' 'ice' 'iche' 'ichi' 'ismo' + 'ismi' 'abile' 'abili' 'ibile' 'ibili' 'ista' 'iste' 'isti' + 'ist{a`}' 'ist{e`}' 'ist{i`}' 'oso' 'osi' 'osa' 'ose' 'mente' + 'atrice' 'atrici' + 'ante' 'anti' // Note 1 + ( R2 delete ) + 'azione' 'azioni' 'atore' 'atori' + ( R2 delete + try ( ['ic'] R2 delete ) + ) + 'logia' 'logie' + ( R2 <- 'log' ) + 'uzione' 'uzioni' 'usione' 'usioni' + ( R2 <- 'u' ) + 'enza' 'enze' + ( R2 <- 'ente' ) + 'amento' 'amenti' 'imento' 'imenti' + ( RV delete ) + 'amente' ( + R1 delete + try ( + [substring] R2 delete among( + 'iv' ( ['at'] R2 delete ) + 'os' 'ic' 'abil' + ) + ) + ) + 'it{a`}' ( + R2 delete + try ( + [substring] among( + 'abil' 'ic' 'iv' (R2 delete) + ) + ) + ) + 'ivo' 'ivi' 'iva' 'ive' ( + R2 delete + try ( ['at'] R2 delete ['ic'] R2 delete ) + ) + ) + ) + + define verb_suffix as setlimit tomark pV for ( + [substring] among( + 'ammo' 'ando' 'ano' 'are' 'arono' 'asse' 'assero' 'assi' + 'assimo' 'ata' 'ate' 'ati' 'ato' 'ava' 'avamo' 'avano' 'avate' + 'avi' 'avo' 'emmo' 'enda' 'ende' 'endi' 'endo' 'er{a`}' 'erai' + 'eranno' 'ere' 'erebbe' 'erebbero' 'erei' 'eremmo' 'eremo' + 'ereste' 'eresti' 'erete' 'er{o`}' 'erono' 'essero' 'ete' + 'eva' 'evamo' 'evano' 'evate' 'evi' 'evo' 'Yamo' 'iamo' 'immo' + 'ir{a`}' 'irai' 'iranno' 'ire' 'irebbe' 'irebbero' 'irei' + 'iremmo' 'iremo' 'ireste' 'iresti' 'irete' 'ir{o`}' 'irono' + 'isca' 'iscano' 'isce' 'isci' 'isco' 'iscono' 'issero' 'ita' + 'ite' 'iti' 'ito' 'iva' 'ivamo' 'ivano' 'ivate' 'ivi' 'ivo' + 'ono' 'uta' 'ute' 'uti' 'uto' + + 'ar' 'ir' // but 'er' is problematical + (delete) + ) + ) + + define AEIO 'aeio{a`}{e`}{i`}{o`}' + define CG 'cg' + + define vowel_suffix as ( + try ( + [AEIO] RV delete + ['i'] RV delete + ) + try ( + ['h'] CG RV delete + ) + ) +) + +define stem as ( + do prelude + do mark_regions + backwards ( + do attached_pronoun + do (standard_suffix or verb_suffix) + do vowel_suffix + ) + do postlude +) + +/* + Note 1: additions of 15 Jun 2005 +*/ + diff --git a/contrib/snowball/algorithms/italian/stem_MS_DOS_Latin_I.sbl b/contrib/snowball/algorithms/italian/stem_MS_DOS_Latin_I.sbl new file mode 100644 index 000000000..b43295c09 --- /dev/null +++ b/contrib/snowball/algorithms/italian/stem_MS_DOS_Latin_I.sbl @@ -0,0 +1,195 @@ + +routines ( + prelude postlude mark_regions + RV R1 R2 + attached_pronoun + standard_suffix + verb_suffix + vowel_suffix +) + +externals ( stem ) + +integers ( pV p1 p2 ) + +groupings ( v AEIO CG ) + +stringescapes {} + +/* special characters (in MS-DOS Latin I) */ + +stringdef a' hex 'A0' +stringdef a` hex '85' +stringdef e' hex '82' +stringdef e` hex '8A' +stringdef i' hex 'A1' +stringdef i` hex '8D' +stringdef o' hex 'A2' +stringdef o` hex '95' +stringdef u' hex 'A3' +stringdef u` hex '97' + +define v 'aeiou{a`}{e`}{i`}{o`}{u`}' + +define prelude as ( + test repeat ( + [substring] among( + '{a'}' (<- '{a`}') + '{e'}' (<- '{e`}') + '{i'}' (<- '{i`}') + '{o'}' (<- '{o`}') + '{u'}' (<- '{u`}') + 'qu' (<- 'qU') + '' (next) + ) + ) + repeat goto ( + v [ ('u' ] v <- 'U') or + ('i' ] v <- 'I') + ) +) + +define mark_regions as ( + + $pV = limit + $p1 = limit + $p2 = limit // defaults + + do ( + ( v (non-v gopast v) or (v gopast non-v) ) + or + ( non-v (non-v gopast v) or (v next) ) + setmark pV + ) + do ( + gopast v gopast non-v setmark p1 + gopast v gopast non-v setmark p2 + ) +) + +define postlude as repeat ( + + [substring] among( + 'I' (<- 'i') + 'U' (<- 'u') + '' (next) + ) + +) + +backwardmode ( + + define RV as $pV <= cursor + define R1 as $p1 <= cursor + define R2 as $p2 <= cursor + + define attached_pronoun as ( + [substring] among( + 'ci' 'gli' 'la' 'le' 'li' 'lo' + 'mi' 'ne' 'si' 'ti' 'vi' + // the compound forms are: + 'sene' 'gliela' 'gliele' 'glieli' 'glielo' 'gliene' + 'mela' 'mele' 'meli' 'melo' 'mene' + 'tela' 'tele' 'teli' 'telo' 'tene' + 'cela' 'cele' 'celi' 'celo' 'cene' + 'vela' 'vele' 'veli' 'velo' 'vene' + ) + among( (RV) + 'ando' 'endo' (delete) + 'ar' 'er' 'ir' (<- 'e') + ) + ) + + define standard_suffix as ( + [substring] among( + + 'anza' 'anze' 'ico' 'ici' 'ica' 'ice' 'iche' 'ichi' 'ismo' + 'ismi' 'abile' 'abili' 'ibile' 'ibili' 'ista' 'iste' 'isti' + 'ist{a`}' 'ist{e`}' 'ist{i`}' 'oso' 'osi' 'osa' 'ose' 'mente' + 'atrice' 'atrici' + 'ante' 'anti' // Note 1 + ( R2 delete ) + 'azione' 'azioni' 'atore' 'atori' + ( R2 delete + try ( ['ic'] R2 delete ) + ) + 'logia' 'logie' + ( R2 <- 'log' ) + 'uzione' 'uzioni' 'usione' 'usioni' + ( R2 <- 'u' ) + 'enza' 'enze' + ( R2 <- 'ente' ) + 'amento' 'amenti' 'imento' 'imenti' + ( RV delete ) + 'amente' ( + R1 delete + try ( + [substring] R2 delete among( + 'iv' ( ['at'] R2 delete ) + 'os' 'ic' 'abil' + ) + ) + ) + 'it{a`}' ( + R2 delete + try ( + [substring] among( + 'abil' 'ic' 'iv' (R2 delete) + ) + ) + ) + 'ivo' 'ivi' 'iva' 'ive' ( + R2 delete + try ( ['at'] R2 delete ['ic'] R2 delete ) + ) + ) + ) + + define verb_suffix as setlimit tomark pV for ( + [substring] among( + 'ammo' 'ando' 'ano' 'are' 'arono' 'asse' 'assero' 'assi' + 'assimo' 'ata' 'ate' 'ati' 'ato' 'ava' 'avamo' 'avano' 'avate' + 'avi' 'avo' 'emmo' 'enda' 'ende' 'endi' 'endo' 'er{a`}' 'erai' + 'eranno' 'ere' 'erebbe' 'erebbero' 'erei' 'eremmo' 'eremo' + 'ereste' 'eresti' 'erete' 'er{o`}' 'erono' 'essero' 'ete' + 'eva' 'evamo' 'evano' 'evate' 'evi' 'evo' 'Yamo' 'iamo' 'immo' + 'ir{a`}' 'irai' 'iranno' 'ire' 'irebbe' 'irebbero' 'irei' + 'iremmo' 'iremo' 'ireste' 'iresti' 'irete' 'ir{o`}' 'irono' + 'isca' 'iscano' 'isce' 'isci' 'isco' 'iscono' 'issero' 'ita' + 'ite' 'iti' 'ito' 'iva' 'ivamo' 'ivano' 'ivate' 'ivi' 'ivo' + 'ono' 'uta' 'ute' 'uti' 'uto' + + 'ar' 'ir' // but 'er' is problematical + (delete) + ) + ) + + define AEIO 'aeio{a`}{e`}{i`}{o`}' + define CG 'cg' + + define vowel_suffix as ( + try ( + [AEIO] RV delete + ['i'] RV delete + ) + try ( + ['h'] CG RV delete + ) + ) +) + +define stem as ( + do prelude + do mark_regions + backwards ( + do attached_pronoun + do (standard_suffix or verb_suffix) + do vowel_suffix + ) + do postlude +) + +/* + Note 1: additions of 15 Jun 2005 +*/ + diff --git a/contrib/snowball/algorithms/kraaij_pohlmann/stem_ISO_8859_1.sbl b/contrib/snowball/algorithms/kraaij_pohlmann/stem_ISO_8859_1.sbl new file mode 100644 index 000000000..cd79d1280 --- /dev/null +++ b/contrib/snowball/algorithms/kraaij_pohlmann/stem_ISO_8859_1.sbl @@ -0,0 +1,245 @@ +strings ( ch ) +integers ( x p1 p2 ) +booleans ( Y_found stemmed GE_removed ) + +routines ( + + R1 R2 + C V VX + lengthen_V + Step_1 Step_2 Step_3 Step_4 Step_7 + Step_6 Step_1c + Lose_prefix + Lose_infix + measure +) + +externals ( stem ) + +groupings ( v v_WX AOU AIOU ) + +stringescapes {} + +stringdef ' hex '27' // yuk + +define v 'aeiouy' +define v_WX v + 'wx' +define AOU 'aou' +define AIOU 'aiou' + +backwardmode ( + + define R1 as (setmark x $x >= p1) + define R2 as (setmark x $x >= p2) + + define V as test (v or 'ij') + define VX as test (next v or 'ij') + define C as test (not 'ij' non-v) + + define lengthen_V as do ( + non-v_WX [ (AOU] test (non-v or atlimit)) or + ('e'] test (non-v or atlimit + not AIOU + not (next AIOU non-v))) + ->ch insert ch + ) + + define Step_1 as + ( + [among ( (]) + + '{'}s' (delete) + 's' (R1 not ('t' R1) C delete) + 'ies' (R1 <-'ie') + 'es' + (('ar' R1 C ] delete lengthen_V) or + ('er' R1 C ] delete) or + (R1 C <-'e')) + + 'aus' (R1 V <-'au') + 'en' (('hed' R1 ] <-'heid') or + ('nd' delete) or + ('d' R1 C ] delete) or + ('i' or 'j' V delete) or + (R1 C delete lengthen_V)) + 'nde' (<-'nd') + ) + ) + + define Step_2 as + ( + [among ( (]) + 'je' (('{'}t' ] delete) or + ('et' ] R1 C delete) or + ('rnt' ] <-'rn') or + ('t' ] R1 VX delete) or + ('ink' ] <-'ing') or + ('mp' ] <-'m') or + ('{'}' ] R1 delete) or + (] R1 C delete)) + 'ge' (R1 <-'g') + 'lijke'(R1 <-'lijk') + 'ische'(R1 <-'isch') + 'de' (R1 C delete) + 'te' (R1 <-'t') + 'se' (R1 <-'s') + 're' (R1 <-'r') + 'le' (R1 delete attach 'l' lengthen_V) + 'ene' (R1 C delete attach 'en' lengthen_V) + 'ieve' (R1 C <-'ief') + ) + ) + + define Step_3 as + ( + [among ( (]) + 'atie' (R1 <-'eer') + 'iteit' (R1 delete lengthen_V) + 'heid' + 'sel' + 'ster' (R1 delete) + 'rder' (<-'r') + 'ing' + 'isme' + 'erij' (R1 delete lengthen_V) + 'arij' (R1 C <-'aar') + 'fie' (R2 delete attach 'f' lengthen_V) + 'gie' (R2 delete attach 'g' lengthen_V) + 'tst' (R1 C <-'t') + 'dst' (R1 C <-'d') + ) + ) + + define Step_4 as + ( + ( [among ( (]) + 'ioneel' (R1 <-'ie') + 'atief' (R1 <-'eer') + 'baar' (R1 delete) + 'naar' (R1 V <-'n') + 'laar' (R1 V <-'l') + 'raar' (R1 V <-'r') + 'tant' (R1 <-'teer') + 'lijker' + 'lijkst' (R1 <-'lijk') + 'achtig' + 'achtiger' + 'achtigst'(R1 delete) + 'eriger' + 'erigst' + 'erig' + 'end' (R1 C delete lengthen_V) + ) + ) + or + ( [among ( (]) + 'iger' + 'igst' + 'ig' (R1 C delete lengthen_V) + ) + ) + ) + + define Step_7 as + ( + [among ( (]) + 'kt' (<-'k') + 'ft' (<-'f') + 'pt' (<-'p') + ) + ) + + define Step_6 as + ( + [among ( (]) + 'bb' (<-'b') + 'cc' (<-'c') + 'dd' (<-'d') + 'ff' (<-'f') + 'gg' (<-'g') + 'hh' (<-'h') + 'jj' (<-'j') + 'kk' (<-'k') + 'll' (<-'l') + 'mm' (<-'m') + 'nn' (<-'n') + 'pp' (<-'p') + 'qq' (<-'q') + 'rr' (<-'r') + 'ss' (<-'s') + 'tt' (<-'t') + 'vv' (<-'v') + 'ww' (<-'w') + 'xx' (<-'x') + 'zz' (<-'z') + 'v' (<-'f') + 'z' (<-'s') + ) + ) + + define Step_1c as + ( + [among ( (] R1 C) + 'd' (not ('n' R1) delete) + 't' (not ('h' R1) delete) + ) + ) +) + +define Lose_prefix as ( + ['ge'] test hop 3 (goto v goto non-v) + set GE_removed + delete +) + +define Lose_infix as ( + next + gopast (['ge']) test hop 3 (goto v goto non-v) + set GE_removed + delete +) + +define measure as ( + do ( + tolimit + setmark p1 + setmark p2 + ) + do( + repeat non-v atleast 1 ('ij' or v) non-v setmark p1 + repeat non-v atleast 1 ('ij' or v) non-v setmark p2 + ) + +) +define stem as ( + + unset Y_found + unset stemmed + do ( ['y'] <-'Y' set Y_found ) + do repeat(goto (v ['y'])<-'Y' set Y_found ) + + measure + + backwards ( + do (Step_1 set stemmed ) + do (Step_2 set stemmed ) + do (Step_3 set stemmed ) + do (Step_4 set stemmed ) + ) + unset GE_removed + do (Lose_prefix and measure) + backwards ( + do (GE_removed Step_1c) + ) + unset GE_removed + do (Lose_infix and measure) + backwards ( + do (GE_removed Step_1c) + ) + backwards ( + do (Step_7 set stemmed ) + do (stemmed or GE_removed Step_6) + ) + do(Y_found repeat(goto (['Y']) <-'y')) +) + diff --git a/contrib/snowball/algorithms/lovins/stem_ISO_8859_1.sbl b/contrib/snowball/algorithms/lovins/stem_ISO_8859_1.sbl new file mode 100644 index 000000000..3f69f1572 --- /dev/null +++ b/contrib/snowball/algorithms/lovins/stem_ISO_8859_1.sbl @@ -0,0 +1,208 @@ + +stringescapes {} + +routines ( + A B C D E F G H I J K L M N O P Q R S T U V W X Y Z AA BB CC + + endings + + undouble respell +) + +externals ( stem ) + +backwardmode ( + + /* Lovins' conditions A, B ... CC, as given in her Appendix B, where + a test for a two letter prefix ('test hop 2') is implicitly + assumed. Note that 'e' next 'u' corresponds to her u*e because + Snowball is scanning backwards. */ + + define A as ( hop 2 ) + define B as ( hop 3 ) + define C as ( hop 4 ) + define D as ( hop 5 ) + define E as ( test hop 2 not 'e' ) + define F as ( test hop 3 not 'e' ) + define G as ( test hop 3 'f' ) + define H as ( test hop 2 't' or 'll' ) + define I as ( test hop 2 not 'o' not 'e' ) + define J as ( test hop 2 not 'a' not 'e' ) + define K as ( test hop 3 'l' or 'i' or ('e' next 'u') ) + define L as ( test hop 2 not 'u' not 'x' not ('s' not 'o') ) + define M as ( test hop 2 not 'a' not 'c' not 'e' not 'm' ) + define N as ( test hop 3 ( hop 2 not 's' or hop 2 ) ) + define O as ( test hop 2 'l' or 'i' ) + define P as ( test hop 2 not 'c' ) + define Q as ( test hop 2 test hop 3 not 'l' not 'n' ) + define R as ( test hop 2 'n' or 'r' ) + define S as ( test hop 2 'dr' or ('t' not 't') ) + define T as ( test hop 2 's' or ('t' not 'o') ) + define U as ( test hop 2 'l' or 'm' or 'n' or 'r' ) + define V as ( test hop 2 'c' ) + define W as ( test hop 2 not 's' not 'u' ) + define X as ( test hop 2 'l' or 'i' or ('e' next 'u') ) + define Y as ( test hop 2 'in' ) + define Z as ( test hop 2 not 'f' ) + define AA as ( test hop 2 among ( 'd' 'f' 'ph' 'th' 'l' 'er' 'or' + 'es' 't' ) ) + define BB as ( test hop 3 not 'met' not 'ryst' ) + define CC as ( test hop 2 'l' ) + + + /* The system of endings, as given in Appendix A. */ + + define endings as ( + [substring] among( + 'alistically' B 'arizability' A 'izationally' B + + 'antialness' A 'arisations' A 'arizations' A 'entialness' A + + 'allically' C 'antaneous' A 'antiality' A 'arisation' A + 'arization' A 'ationally' B 'ativeness' A 'eableness' E + 'entations' A 'entiality' A 'entialize' A 'entiation' A + 'ionalness' A 'istically' A 'itousness' A 'izability' A + 'izational' A + + 'ableness' A 'arizable' A 'entation' A 'entially' A + 'eousness' A 'ibleness' A 'icalness' A 'ionalism' A + 'ionality' A 'ionalize' A 'iousness' A 'izations' A + 'lessness' A + + 'ability' A 'aically' A 'alistic' B 'alities' A + 'ariness' E 'aristic' A 'arizing' A 'ateness' A + 'atingly' A 'ational' B 'atively' A 'ativism' A + 'elihood' E 'encible' A 'entally' A 'entials' A + 'entiate' A 'entness' A 'fulness' A 'ibility' A + 'icalism' A 'icalist' A 'icality' A 'icalize' A + 'ication' G 'icianry' A 'ination' A 'ingness' A + 'ionally' A 'isation' A 'ishness' A 'istical' A + 'iteness' A 'iveness' A 'ivistic' A 'ivities' A + 'ization' F 'izement' A 'oidally' A 'ousness' A + + 'aceous' A 'acious' B 'action' G 'alness' A + 'ancial' A 'ancies' A 'ancing' B 'ariser' A + 'arized' A 'arizer' A 'atable' A 'ations' B + 'atives' A 'eature' Z 'efully' A 'encies' A + 'encing' A 'ential' A 'enting' C 'entist' A + 'eously' A 'ialist' A 'iality' A 'ialize' A + 'ically' A 'icance' A 'icians' A 'icists' A + 'ifully' A 'ionals' A 'ionate' D 'ioning' A + 'ionist' A 'iously' A 'istics' A 'izable' E + 'lessly' A 'nesses' A 'oidism' A + + 'acies' A 'acity' A 'aging' B 'aical' A + 'alist' A 'alism' B 'ality' A 'alize' A + 'allic'BB 'anced' B 'ances' B 'antic' C + 'arial' A 'aries' A 'arily' A 'arity' B + 'arize' A 'aroid' A 'ately' A 'ating' I + 'ation' B 'ative' A 'ators' A 'atory' A + 'ature' E 'early' Y 'ehood' A 'eless' A + 'elity' A 'ement' A 'enced' A 'ences' A + 'eness' E 'ening' E 'ental' A 'ented' C + 'ently' A 'fully' A 'ially' A 'icant' A + 'ician' A 'icide' A 'icism' A 'icist' A + 'icity' A 'idine' I 'iedly' A 'ihood' A + 'inate' A 'iness' A 'ingly' B 'inism' J + 'inity'CC 'ional' A 'ioned' A 'ished' A + 'istic' A 'ities' A 'itous' A 'ively' A + 'ivity' A 'izers' F 'izing' F 'oidal' A + 'oides' A 'otide' A 'ously' A + + 'able' A 'ably' A 'ages' B 'ally' B + 'ance' B 'ancy' B 'ants' B 'aric' A + 'arly' K 'ated' I 'ates' A 'atic' B + 'ator' A 'ealy' Y 'edly' E 'eful' A + 'eity' A 'ence' A 'ency' A 'ened' E + 'enly' E 'eous' A 'hood' A 'ials' A + 'ians' A 'ible' A 'ibly' A 'ical' A + 'ides' L 'iers' A 'iful' A 'ines' M + 'ings' N 'ions' B 'ious' A 'isms' B + 'ists' A 'itic' H 'ized' F 'izer' F + 'less' A 'lily' A 'ness' A 'ogen' A + 'ward' A 'wise' A 'ying' B 'yish' A + + 'acy' A 'age' B 'aic' A 'als'BB + 'ant' B 'ars' O 'ary' F 'ata' A + 'ate' A 'eal' Y 'ear' Y 'ely' E + 'ene' E 'ent' C 'ery' E 'ese' A + 'ful' A 'ial' A 'ian' A 'ics' A + 'ide' L 'ied' A 'ier' A 'ies' P + 'ily' A 'ine' M 'ing' N 'ion' Q + 'ish' C 'ism' B 'ist' A 'ite'AA + 'ity' A 'ium' A 'ive' A 'ize' F + 'oid' A 'one' R 'ous' A + + 'ae' A 'al'BB 'ar' X 'as' B + 'ed' E 'en' F 'es' E 'ia' A + 'ic' A 'is' A 'ly' B 'on' S + 'or' T 'um' U 'us' V 'yl' R + '{'}s' A 's{'}' A + + 'a' A 'e' A 'i' A 'o' A + 's' W 'y' B + + (delete) + ) + ) + + /* Undoubling is rule 1 of appendix C. */ + + define undouble as ( + test substring among ('bb' 'dd' 'gg' 'll' 'mm' 'nn' 'pp' 'rr' 'ss' + 'tt') + [next] delete + ) + + /* The other appendix C rules can be done together. */ + + define respell as ( + [substring] among ( + 'iev' (<-'ief') + 'uct' (<-'uc') + 'umpt' (<-'um') + 'rpt' (<-'rb') + 'urs' (<-'ur') + 'istr' (<-'ister') + 'metr' (<-'meter') + 'olv' (<-'olut') + 'ul' (not 'a' not 'i' not 'o' <-'l') + 'bex' (<-'bic') + 'dex' (<-'dic') + 'pex' (<-'pic') + 'tex' (<-'tic') + 'ax' (<-'ac') + 'ex' (<-'ec') + 'ix' (<-'ic') + 'lux' (<-'luc') + 'uad' (<-'uas') + 'vad' (<-'vas') + 'cid' (<-'cis') + 'lid' (<-'lis') + 'erid' (<-'eris') + 'pand' (<-'pans') + 'end' (not 's' <-'ens') + 'ond' (<-'ons') + 'lud' (<-'lus') + 'rud' (<-'rus') + 'her' (not 'p' not 't' <-'hes') + 'mit' (<-'mis') + 'ent' (not 'm' <-'ens') + /* 'ent' was 'end' in the 1968 paper - a typo. */ + 'ert' (<-'ers') + 'et' (not 'n' <-'es') + 'yt' (<-'ys') + 'yz' (<-'ys') + ) + ) +) + +define stem as ( + + backwards ( + do endings + do undouble + do respell + ) +) + diff --git a/contrib/snowball/algorithms/norwegian/stem_ISO_8859_1.sbl b/contrib/snowball/algorithms/norwegian/stem_ISO_8859_1.sbl new file mode 100644 index 000000000..94a071653 --- /dev/null +++ b/contrib/snowball/algorithms/norwegian/stem_ISO_8859_1.sbl @@ -0,0 +1,80 @@ +routines ( + mark_regions + main_suffix + consonant_pair + other_suffix +) + +externals ( stem ) + +integers ( p1 x ) + +groupings ( v s_ending ) + +stringescapes {} + +/* special characters (in ISO Latin I) */ + +stringdef ae hex 'E6' +stringdef ao hex 'E5' +stringdef o/ hex 'F8' + +define v 'aeiouy{ae}{ao}{o/}' + +define s_ending 'bcdfghjlmnoprtvyz' + +define mark_regions as ( + + $p1 = limit + + test ( hop 3 setmark x ) + goto v gopast non-v setmark p1 + try ( $p1 < x $p1 = x ) +) + +backwardmode ( + + define main_suffix as ( + setlimit tomark p1 for ([substring]) + among( + + 'a' 'e' 'ede' 'ande' 'ende' 'ane' 'ene' 'hetene' 'en' 'heten' 'ar' + 'er' 'heter' 'as' 'es' 'edes' 'endes' 'enes' 'hetenes' 'ens' + 'hetens' 'ers' 'ets' 'et' 'het' 'ast' + (delete) + 's' + (s_ending or ('k' non-v) delete) + 'erte' 'ert' + (<-'er') + ) + ) + + define consonant_pair as ( + test ( + setlimit tomark p1 for ([substring]) + among( + 'dt' 'vt' + ) + ) + next] delete + ) + + define other_suffix as ( + setlimit tomark p1 for ([substring]) + among( + 'leg' 'eleg' 'ig' 'eig' 'lig' 'elig' 'els' 'lov' 'elov' 'slov' + 'hetslov' + (delete) + ) + ) +) + +define stem as ( + + do mark_regions + backwards ( + do main_suffix + do consonant_pair + do other_suffix + ) +) diff --git a/contrib/snowball/algorithms/norwegian/stem_MS_DOS_Latin_I.sbl b/contrib/snowball/algorithms/norwegian/stem_MS_DOS_Latin_I.sbl new file mode 100644 index 000000000..f57483354 --- /dev/null +++ b/contrib/snowball/algorithms/norwegian/stem_MS_DOS_Latin_I.sbl @@ -0,0 +1,80 @@ +routines ( + mark_regions + main_suffix + consonant_pair + other_suffix +) + +externals ( stem ) + +integers ( p1 x ) + +groupings ( v s_ending ) + +stringescapes {} + +/* special characters (in MS-DOS Latin I) */ + +stringdef ae hex '91' +stringdef ao hex '86' +stringdef o/ hex '9B' + +define v 'aeiouy{ae}{ao}{o/}' + +define s_ending 'bcdfghjlmnoprtvyz' + +define mark_regions as ( + + $p1 = limit + + test ( hop 3 setmark x ) + goto v gopast non-v setmark p1 + try ( $p1 < x $p1 = x ) +) + +backwardmode ( + + define main_suffix as ( + setlimit tomark p1 for ([substring]) + among( + + 'a' 'e' 'ede' 'ande' 'ende' 'ane' 'ene' 'hetene' 'en' 'heten' 'ar' + 'er' 'heter' 'as' 'es' 'edes' 'endes' 'enes' 'hetenes' 'ens' + 'hetens' 'ers' 'ets' 'et' 'het' 'ast' + (delete) + 's' + (s_ending or ('k' non-v) delete) + 'erte' 'ert' + (<-'er') + ) + ) + + define consonant_pair as ( + test ( + setlimit tomark p1 for ([substring]) + among( + 'dt' 'vt' + ) + ) + next] delete + ) + + define other_suffix as ( + setlimit tomark p1 for ([substring]) + among( + 'leg' 'eleg' 'ig' 'eig' 'lig' 'elig' 'els' 'lov' 'elov' 'slov' + 'hetslov' + (delete) + ) + ) +) + +define stem as ( + + do mark_regions + backwards ( + do main_suffix + do consonant_pair + do other_suffix + ) +) diff --git a/contrib/snowball/algorithms/porter/stem_ISO_8859_1.sbl b/contrib/snowball/algorithms/porter/stem_ISO_8859_1.sbl new file mode 100644 index 000000000..9533b7932 --- /dev/null +++ b/contrib/snowball/algorithms/porter/stem_ISO_8859_1.sbl @@ -0,0 +1,139 @@ +integers ( p1 p2 ) +booleans ( Y_found ) + +routines ( + shortv + R1 R2 + Step_1a Step_1b Step_1c Step_2 Step_3 Step_4 Step_5a Step_5b +) + +externals ( stem ) + +groupings ( v v_WXY ) + +define v 'aeiouy' +define v_WXY v + 'wxY' + +backwardmode ( + + define shortv as ( non-v_WXY v non-v ) + + define R1 as $p1 <= cursor + define R2 as $p2 <= cursor + + define Step_1a as ( + [substring] among ( + 'sses' (<-'ss') + 'ies' (<-'i') + 'ss' () + 's' (delete) + ) + ) + + define Step_1b as ( + [substring] among ( + 'eed' (R1 <-'ee') + 'ed' + 'ing' ( + test gopast v delete + test substring among( + 'at' 'bl' 'iz' + (<+ 'e') + 'bb' 'dd' 'ff' 'gg' 'mm' 'nn' 'pp' 'rr' 'tt' + // ignoring double c, h, j, k, q, v, w, and x + ([next] delete) + '' (atmark p1 test shortv <+ 'e') + ) + ) + ) + ) + + define Step_1c as ( + ['y' or 'Y'] + gopast v + <-'i' + ) + + define Step_2 as ( + [substring] R1 among ( + 'tional' (<-'tion') + 'enci' (<-'ence') + 'anci' (<-'ance') + 'abli' (<-'able') + 'entli' (<-'ent') + 'eli' (<-'e') + 'izer' 'ization' + (<-'ize') + 'ational' 'ation' 'ator' + (<-'ate') + 'alli' (<-'al') + 'alism' 'aliti' + (<-'al') + 'fulness' (<-'ful') + 'ousli' 'ousness' + (<-'ous') + 'iveness' 'iviti' + (<-'ive') + 'biliti' (<-'ble') + ) + ) + + define Step_3 as ( + [substring] R1 among ( + 'alize' (<-'al') + 'icate' 'iciti' 'ical' + (<-'ic') + 'ative' 'ful' 'ness' + (delete) + ) + ) + + define Step_4 as ( + [substring] R2 among ( + 'al' 'ance' 'ence' 'er' 'ic' 'able' 'ible' 'ant' 'ement' + 'ment' 'ent' 'ou' 'ism' 'ate' 'iti' 'ous' 'ive' 'ize' + (delete) + 'ion' ('s' or 't' delete) + ) + ) + + define Step_5a as ( + ['e'] + R2 or (R1 not shortv) + delete + ) + + define Step_5b as ( + ['l'] + R2 'l' + delete + ) +) + +define stem as ( + + unset Y_found + do ( ['y'] <-'Y' set Y_found) + do repeat(goto (v ['y']) <-'Y' set Y_found) + + $p1 = limit + $p2 = limit + do( + gopast v gopast non-v setmark p1 + gopast v gopast non-v setmark p2 + ) + + backwards ( + do Step_1a + do Step_1b + do Step_1c + do Step_2 + do Step_3 + do Step_4 + do Step_5a + do Step_5b + ) + + do(Y_found repeat(goto (['Y']) <-'y')) + +) diff --git a/contrib/snowball/algorithms/portuguese/stem_ISO_8859_1.sbl b/contrib/snowball/algorithms/portuguese/stem_ISO_8859_1.sbl new file mode 100644 index 000000000..3e7da08d4 --- /dev/null +++ b/contrib/snowball/algorithms/portuguese/stem_ISO_8859_1.sbl @@ -0,0 +1,218 @@ +routines ( + prelude postlude mark_regions + RV R1 R2 + standard_suffix + verb_suffix + residual_suffix + residual_form +) + +externals ( stem ) + +integers ( pV p1 p2 ) + +groupings ( v ) + +stringescapes {} + +/* special characters (in ISO Latin I) */ + +stringdef a' hex 'E1' // a-acute +stringdef a^ hex 'E2' // a-circumflex e.g. 'bota^nico +stringdef e' hex 'E9' // e-acute +stringdef e^ hex 'EA' // e-circumflex +stringdef i' hex 'ED' // i-acute +stringdef o^ hex 'F4' // o-circumflex +stringdef o' hex 'F3' // o-acute +stringdef u' hex 'FA' // u-acute +stringdef c, hex 'E7' // c-cedilla + +stringdef a~ hex 'E3' // a-tilde +stringdef o~ hex 'F5' // o-tilde + + +define v 'aeiou{a'}{e'}{i'}{o'}{u'}{a^}{e^}{o^}' + +define prelude as repeat ( + [substring] among( + '{a~}' (<- 'a~') + '{o~}' (<- 'o~') + '' (next) + ) //or next +) + +define mark_regions as ( + + $pV = limit + $p1 = limit + $p2 = limit // defaults + + do ( + ( v (non-v gopast v) or (v gopast non-v) ) + or + ( non-v (non-v gopast v) or (v next) ) + setmark pV + ) + do ( + gopast v gopast non-v setmark p1 + gopast v gopast non-v setmark p2 + ) +) + +define postlude as repeat ( + [substring] among( + 'a~' (<- '{a~}') + 'o~' (<- '{o~}') + '' (next) + ) //or next +) + +backwardmode ( + + define RV as $pV <= cursor + define R1 as $p1 <= cursor + define R2 as $p2 <= cursor + + define standard_suffix as ( + [substring] among( + + 'eza' 'ezas' + 'ico' 'ica' 'icos' 'icas' + 'ismo' 'ismos' + '{a'}vel' + '{i'}vel' + 'ista' 'istas' + 'oso' 'osa' 'osos' 'osas' + 'amento' 'amentos' + 'imento' 'imentos' + + 'adora' 'ador' 'a{c,}a~o' + 'adoras' 'adores' 'a{c,}o~es' // no -ic test + 'ante' 'antes' '{a^}ncia' // Note 1 + ( + R2 delete + ) + 'log{i'}a' + 'log{i'}as' + ( + R2 <- 'log' + ) + 'uci{o'}n' 'uciones' + ( + R2 <- 'u' + ) + '{e^}ncia' '{e^}ncias' + ( + R2 <- 'ente' + ) + 'amente' + ( + R1 delete + try ( + [substring] R2 delete among( + 'iv' (['at'] R2 delete) + 'os' + 'ic' + 'ad' + ) + ) + ) + 'mente' + ( + R2 delete + try ( + [substring] among( + 'ante' // Note 1 + 'avel' + '{i'}vel' (R2 delete) + ) + ) + ) + 'idade' + 'idades' + ( + R2 delete + try ( + [substring] among( + 'abil' + 'ic' + 'iv' (R2 delete) + ) + ) + ) + 'iva' 'ivo' + 'ivas' 'ivos' + ( + R2 delete + try ( + ['at'] R2 delete // but not a further ['ic'] R2 delete + ) + ) + 'ira' 'iras' + ( + RV 'e' // -eira -eiras usually non-verbal + <- 'ir' + ) + ) + ) + + define verb_suffix as setlimit tomark pV for ( + [substring] among( + 'ada' 'ida' 'ia' 'aria' 'eria' 'iria' 'ar{a'}' 'ara' 'er{a'}' + 'era' 'ir{a'}' 'ava' 'asse' 'esse' 'isse' 'aste' 'este' 'iste' + 'ei' 'arei' 'erei' 'irei' 'am' 'iam' 'ariam' 'eriam' 'iriam' + 'aram' 'eram' 'iram' 'avam' 'em' 'arem' 'erem' 'irem' 'assem' + 'essem' 'issem' 'ado' 'ido' 'ando' 'endo' 'indo' 'ara~o' + 'era~o' 'ira~o' 'ar' 'er' 'ir' 'as' 'adas' 'idas' 'ias' + 'arias' 'erias' 'irias' 'ar{a'}s' 'aras' 'er{a'}s' 'eras' + 'ir{a'}s' 'avas' 'es' 'ardes' 'erdes' 'irdes' 'ares' 'eres' + 'ires' 'asses' 'esses' 'isses' 'astes' 'estes' 'istes' 'is' + 'ais' 'eis' '{i'}eis' 'ar{i'}eis' 'er{i'}eis' 'ir{i'}eis' + '{a'}reis' 'areis' '{e'}reis' 'ereis' '{i'}reis' 'ireis' + '{a'}sseis' '{e'}sseis' '{i'}sseis' '{a'}veis' 'ados' 'idos' + '{a'}mos' 'amos' '{i'}amos' 'ar{i'}amos' 'er{i'}amos' + 'ir{i'}amos' '{a'}ramos' '{e'}ramos' '{i'}ramos' '{a'}vamos' + 'emos' 'aremos' 'eremos' 'iremos' '{a'}ssemos' '{e^}ssemos' + '{i'}ssemos' 'imos' 'armos' 'ermos' 'irmos' 'eu' 'iu' 'ou' + + 'ira' 'iras' + (delete) + ) + ) + + define residual_suffix as ( + [substring] among( + 'os' + 'a' 'i' 'o' '{a'}' '{i'}' '{o'}' + ( RV delete ) + ) + ) + + define residual_form as ( + [substring] among( + 'e' '{e'}' '{e^}' + ( RV delete [('u'] test 'g') or + ('i'] test 'c') RV delete ) + '{c,}' (<-'c') + ) + ) +) + +define stem as ( + do prelude + do mark_regions + backwards ( + do ( + ( ( standard_suffix or verb_suffix ) + and do ( ['i'] test 'c' RV delete ) + ) + or residual_suffix + ) + do residual_form + ) + do postlude +) + +/* + Note 1: additions of 15 Jun 2005 +*/ diff --git a/contrib/snowball/algorithms/portuguese/stem_MS_DOS_Latin_I.sbl b/contrib/snowball/algorithms/portuguese/stem_MS_DOS_Latin_I.sbl new file mode 100644 index 000000000..4d6c85214 --- /dev/null +++ b/contrib/snowball/algorithms/portuguese/stem_MS_DOS_Latin_I.sbl @@ -0,0 +1,218 @@ +routines ( + prelude postlude mark_regions + RV R1 R2 + standard_suffix + verb_suffix + residual_suffix + residual_form +) + +externals ( stem ) + +integers ( pV p1 p2 ) + +groupings ( v ) + +stringescapes {} + +/* special characters (in MS-DOS Latin I) */ + +stringdef a' hex 'A0' // a-acute +stringdef a^ hex '83' // a-circumflex e.g. 'bota^nico +stringdef e' hex '82' // e-acute +stringdef e^ hex '88' // e-circumflex +stringdef i' hex 'A1' // i-acute +stringdef o^ hex '93' // o-circumflex +stringdef o' hex 'A2' // o-acute +stringdef u' hex 'A3' // u-acute +stringdef c, hex '87' // c-cedilla + +stringdef a~ hex 'C6' // a-tilde +stringdef o~ hex 'E4' // o-tilde + + +define v 'aeiou{a'}{e'}{i'}{o'}{u'}{a^}{e^}{o^}' + +define prelude as repeat ( + [substring] among( + '{a~}' (<- 'a~') + '{o~}' (<- 'o~') + '' (next) + ) //or next +) + +define mark_regions as ( + + $pV = limit + $p1 = limit + $p2 = limit // defaults + + do ( + ( v (non-v gopast v) or (v gopast non-v) ) + or + ( non-v (non-v gopast v) or (v next) ) + setmark pV + ) + do ( + gopast v gopast non-v setmark p1 + gopast v gopast non-v setmark p2 + ) +) + +define postlude as repeat ( + [substring] among( + 'a~' (<- '{a~}') + 'o~' (<- '{o~}') + '' (next) + ) //or next +) + +backwardmode ( + + define RV as $pV <= cursor + define R1 as $p1 <= cursor + define R2 as $p2 <= cursor + + define standard_suffix as ( + [substring] among( + + 'eza' 'ezas' + 'ico' 'ica' 'icos' 'icas' + 'ismo' 'ismos' + '{a'}vel' + '{i'}vel' + 'ista' 'istas' + 'oso' 'osa' 'osos' 'osas' + 'amento' 'amentos' + 'imento' 'imentos' + + 'adora' 'ador' 'a{c,}a~o' + 'adoras' 'adores' 'a{c,}o~es' // no -ic test + 'ante' 'antes' '{a^}ncia' // Note 1 + ( + R2 delete + ) + 'log{i'}a' + 'log{i'}as' + ( + R2 <- 'log' + ) + 'uci{o'}n' 'uciones' + ( + R2 <- 'u' + ) + '{e^}ncia' '{e^}ncias' + ( + R2 <- 'ente' + ) + 'amente' + ( + R1 delete + try ( + [substring] R2 delete among( + 'iv' (['at'] R2 delete) + 'os' + 'ic' + 'ad' + ) + ) + ) + 'mente' + ( + R2 delete + try ( + [substring] among( + 'ante' // Note 1 + 'avel' + '{i'}vel' (R2 delete) + ) + ) + ) + 'idade' + 'idades' + ( + R2 delete + try ( + [substring] among( + 'abil' + 'ic' + 'iv' (R2 delete) + ) + ) + ) + 'iva' 'ivo' + 'ivas' 'ivos' + ( + R2 delete + try ( + ['at'] R2 delete // but not a further ['ic'] R2 delete + ) + ) + 'ira' 'iras' + ( + RV 'e' // -eira -eiras usually non-verbal + <- 'ir' + ) + ) + ) + + define verb_suffix as setlimit tomark pV for ( + [substring] among( + 'ada' 'ida' 'ia' 'aria' 'eria' 'iria' 'ar{a'}' 'ara' 'er{a'}' + 'era' 'ir{a'}' 'ava' 'asse' 'esse' 'isse' 'aste' 'este' 'iste' + 'ei' 'arei' 'erei' 'irei' 'am' 'iam' 'ariam' 'eriam' 'iriam' + 'aram' 'eram' 'iram' 'avam' 'em' 'arem' 'erem' 'irem' 'assem' + 'essem' 'issem' 'ado' 'ido' 'ando' 'endo' 'indo' 'ara~o' + 'era~o' 'ira~o' 'ar' 'er' 'ir' 'as' 'adas' 'idas' 'ias' + 'arias' 'erias' 'irias' 'ar{a'}s' 'aras' 'er{a'}s' 'eras' + 'ir{a'}s' 'avas' 'es' 'ardes' 'erdes' 'irdes' 'ares' 'eres' + 'ires' 'asses' 'esses' 'isses' 'astes' 'estes' 'istes' 'is' + 'ais' 'eis' '{i'}eis' 'ar{i'}eis' 'er{i'}eis' 'ir{i'}eis' + '{a'}reis' 'areis' '{e'}reis' 'ereis' '{i'}reis' 'ireis' + '{a'}sseis' '{e'}sseis' '{i'}sseis' '{a'}veis' 'ados' 'idos' + '{a'}mos' 'amos' '{i'}amos' 'ar{i'}amos' 'er{i'}amos' + 'ir{i'}amos' '{a'}ramos' '{e'}ramos' '{i'}ramos' '{a'}vamos' + 'emos' 'aremos' 'eremos' 'iremos' '{a'}ssemos' '{e^}ssemos' + '{i'}ssemos' 'imos' 'armos' 'ermos' 'irmos' 'eu' 'iu' 'ou' + + 'ira' 'iras' + (delete) + ) + ) + + define residual_suffix as ( + [substring] among( + 'os' + 'a' 'i' 'o' '{a'}' '{i'}' '{o'}' + ( RV delete ) + ) + ) + + define residual_form as ( + [substring] among( + 'e' '{e'}' '{e^}' + ( RV delete [('u'] test 'g') or + ('i'] test 'c') RV delete ) + '{c,}' (<-'c') + ) + ) +) + +define stem as ( + do prelude + do mark_regions + backwards ( + do ( + ( ( standard_suffix or verb_suffix ) + and do ( ['i'] test 'c' RV delete ) + ) + or residual_suffix + ) + do residual_form + ) + do postlude +) + +/* + Note 1: additions of 15 Jun 2005 +*/ diff --git a/contrib/snowball/algorithms/romanian/stem_ISO_8859_2.sbl b/contrib/snowball/algorithms/romanian/stem_ISO_8859_2.sbl new file mode 100644 index 000000000..48a148321 --- /dev/null +++ b/contrib/snowball/algorithms/romanian/stem_ISO_8859_2.sbl @@ -0,0 +1,236 @@ + +routines ( + prelude postlude mark_regions + RV R1 R2 + step_0 + standard_suffix combo_suffix + verb_suffix + vowel_suffix +) + +externals ( stem ) + +integers ( pV p1 p2 ) + +groupings ( v ) + +booleans ( standard_suffix_removed ) + +stringescapes {} + +/* special characters */ + +stringdef a^ hex 'E2' // a circumflex +stringdef i^ hex 'EE' // i circumflex +stringdef a+ hex 'E3' // a breve +stringdef s, hex 'BA' // s cedilla +stringdef t, hex 'FE' // t cedilla + +define v 'aeiou{a^}{i^}{a+}' + +define prelude as ( + repeat goto ( + v [ ('u' ] v <- 'U') or + ('i' ] v <- 'I') + ) +) + +define mark_regions as ( + + $pV = limit + $p1 = limit + $p2 = limit // defaults + + do ( + ( v (non-v gopast v) or (v gopast non-v) ) + or + ( non-v (non-v gopast v) or (v next) ) + setmark pV + ) + do ( + gopast v gopast non-v setmark p1 + gopast v gopast non-v setmark p2 + ) +) + +define postlude as repeat ( + + [substring] among( + 'I' (<- 'i') + 'U' (<- 'u') + '' (next) + ) + +) + +backwardmode ( + + define RV as $pV <= cursor + define R1 as $p1 <= cursor + define R2 as $p2 <= cursor + + define step_0 as ( + [substring] R1 among( + 'ul' 'ului' + ( delete ) + 'aua' + ( <-'a' ) + 'ea' 'ele' 'elor' + ( <-'e' ) + 'ii' 'iua' 'iei' 'iile' 'iilor' 'ilor' + ( <-'i') + 'ile' + ( not 'ab' <- 'i' ) + 'atei' + ( <- 'at' ) + 'a{t,}ie' 'a{t,}ia' + ( <- 'a{t,}i' ) + ) + ) + + define combo_suffix as test ( + [substring] R1 ( + among( + /* 'IST'. alternative: include the following + 'alism' 'alisme' + 'alist' 'alista' 'aliste' 'alisti' 'alist{a+}' 'ali{s,}ti' ( + <- 'al' + ) + */ + 'abilitate' 'abilitati' 'abilit{a+}i' 'abilit{a+}{t,}i' ( + <- 'abil' + ) + 'ibilitate' ( + <- 'ibil' + ) + 'ivitate' 'ivitati' 'ivit{a+}i' 'ivit{a+}{t,}i' ( + <- 'iv' + ) + 'icitate' 'icitati' 'icit{a+}i' 'icit{a+}{t,}i' + 'icator' 'icatori' + 'iciv' 'iciva' 'icive' 'icivi' 'iciv{a+}' + 'ical' 'icala' 'icale' 'icali' 'ical{a+}' ( + <- 'ic' + ) + 'ativ' 'ativa' 'ative' 'ativi' 'ativ{a+}' 'a{t,}iune' + 'atoare' 'ator' 'atori' + '{a+}toare' '{a+}tor' '{a+}tori' ( + <- 'at' + ) + 'itiv' 'itiva' 'itive' 'itivi' 'itiv{a+}' 'i{t,}iune' + 'itoare' 'itor' 'itori' ( + <- 'it' + ) + ) + set standard_suffix_removed + ) + ) + + define standard_suffix as ( + unset standard_suffix_removed + repeat combo_suffix + [substring] R2 ( + among( + + // past participle is treated here, rather than + // as a verb ending: + 'at' 'ata' 'at{a+}' 'ati' 'ate' + 'ut' 'uta' 'ut{a+}' 'uti' 'ute' + 'it' 'ita' 'it{a+}' 'iti' 'ite' + + 'ic' 'ica' 'ice' 'ici' 'ic{a+}' + 'abil' 'abila' 'abile' 'abili' 'abil{a+}' + 'ibil' 'ibila' 'ibile' 'ibili' 'ibil{a+}' + 'oasa' 'oas{a+}' 'oase' 'os' 'osi' 'o{s,}i' + 'ant' 'anta' 'ante' 'anti' 'ant{a+}' + 'ator' 'atori' + 'itate' 'itati' 'it{a+}i' 'it{a+}{t,}i' + 'iv' 'iva' 'ive' 'ivi' 'iv{a+}' ( + delete + ) + 'iune' 'iuni' ( + '{t,}'] <- 't' + ) + 'ism' 'isme' + 'ist' 'ista' 'iste' 'isti' 'ist{a+}' 'i{s,}ti' ( + <- 'ist' + /* 'IST'. alternative: remove with <- '' */ + ) + ) + set standard_suffix_removed + ) + ) + + define verb_suffix as setlimit tomark pV for ( + [substring] among( + // 'long' infinitive: + 'are' 'ere' 'ire' '{a^}re' + + // gerund: + 'ind' '{a^}nd' + 'indu' '{a^}ndu' + + 'eze' + 'easc{a+}' + // present: + 'ez' 'ezi' 'eaz{a+}' 'esc' 'e{s,}ti' + 'e{s,}te' + '{a+}sc' '{a+}{s,}ti' + '{a+}{s,}te' + + // imperfect: + 'am' 'ai' 'au' + 'eam' 'eai' 'ea' 'ea{t,}i' 'eau' + 'iam' 'iai' 'ia' 'ia{t,}i' 'iau' + + // past: // (not 'ii') + 'ui' + 'a{s,}i' 'ar{a+}m' 'ar{a+}{t,}i' 'ar{a+}' + 'u{s,}i' 'ur{a+}m' 'ur{a+}{t,}i' 'ur{a+}' + 'i{s,}i' 'ir{a+}m' 'ir{a+}{t,}i' 'ir{a+}' + '{a^}i' '{a^}{s,}i' '{a^}r{a+}m' '{a^}r{a+}{t,}i' '{a^}r{a+}' + + // pluferfect: + 'asem' 'ase{s,}i' 'ase' 'aser{a+}m' 'aser{a+}{t,}i' 'aser{a+}' + 'isem' 'ise{s,}i' 'ise' 'iser{a+}m' 'iser{a+}{t,}i' 'iser{a+}' + '{a^}sem' '{a^}se{s,}i' '{a^}se' '{a^}ser{a+}m' '{a^}ser{a+}{t,}i' + '{a^}ser{a+}' + 'usem' 'use{s,}i' 'use' 'user{a+}m' 'user{a+}{t,}i' 'user{a+}' + + ( non-v or 'u' delete ) + + // present: + '{a+}m' 'a{t,}i' + 'em' 'e{t,}i' + 'im' 'i{t,}i' + '{a^}m' '{a^}{t,}i' + + // past: + 'se{s,}i' 'ser{a+}m' 'ser{a+}{t,}i' 'ser{a+}' + 'sei' 'se' + + // pluperfect: + 'sesem' 'sese{s,}i' 'sese' 'seser{a+}m' 'seser{a+}{t,}i' 'seser{a+}' + (delete) + ) + ) + + define vowel_suffix as ( + [substring] RV among ( + 'a' 'e' 'i' 'ie' '{a+}' ( delete ) + ) + ) +) + +define stem as ( + do prelude + do mark_regions + backwards ( + do step_0 + do standard_suffix + do ( standard_suffix_removed or verb_suffix ) + do vowel_suffix + ) + do postlude +) + diff --git a/contrib/snowball/algorithms/romanian/stem_Unicode.sbl b/contrib/snowball/algorithms/romanian/stem_Unicode.sbl new file mode 100644 index 000000000..09aec6429 --- /dev/null +++ b/contrib/snowball/algorithms/romanian/stem_Unicode.sbl @@ -0,0 +1,236 @@ + +routines ( + prelude postlude mark_regions + RV R1 R2 + step_0 + standard_suffix combo_suffix + verb_suffix + vowel_suffix +) + +externals ( stem ) + +integers ( pV p1 p2 ) + +groupings ( v ) + +booleans ( standard_suffix_removed ) + +stringescapes {} + +/* special characters */ + +stringdef a^ hex '0E2' // a circumflex +stringdef i^ hex '0EE' // i circumflex +stringdef a+ hex '103' // a breve +stringdef s, hex '15F' // s cedilla +stringdef t, hex '163' // t cedilla + +define v 'aeiou{a^}{i^}{a+}' + +define prelude as ( + repeat goto ( + v [ ('u' ] v <- 'U') or + ('i' ] v <- 'I') + ) +) + +define mark_regions as ( + + $pV = limit + $p1 = limit + $p2 = limit // defaults + + do ( + ( v (non-v gopast v) or (v gopast non-v) ) + or + ( non-v (non-v gopast v) or (v next) ) + setmark pV + ) + do ( + gopast v gopast non-v setmark p1 + gopast v gopast non-v setmark p2 + ) +) + +define postlude as repeat ( + + [substring] among( + 'I' (<- 'i') + 'U' (<- 'u') + '' (next) + ) + +) + +backwardmode ( + + define RV as $pV <= cursor + define R1 as $p1 <= cursor + define R2 as $p2 <= cursor + + define step_0 as ( + [substring] R1 among( + 'ul' 'ului' + ( delete ) + 'aua' + ( <-'a' ) + 'ea' 'ele' 'elor' + ( <-'e' ) + 'ii' 'iua' 'iei' 'iile' 'iilor' 'ilor' + ( <-'i') + 'ile' + ( not 'ab' <- 'i' ) + 'atei' + ( <- 'at' ) + 'a{t,}ie' 'a{t,}ia' + ( <- 'a{t,}i' ) + ) + ) + + define combo_suffix as test ( + [substring] R1 ( + among( + /* 'IST'. alternative: include the following + 'alism' 'alisme' + 'alist' 'alista' 'aliste' 'alisti' 'alist{a+}' 'ali{s,}ti' ( + <- 'al' + ) + */ + 'abilitate' 'abilitati' 'abilit{a+}i' 'abilit{a+}{t,}i' ( + <- 'abil' + ) + 'ibilitate' ( + <- 'ibil' + ) + 'ivitate' 'ivitati' 'ivit{a+}i' 'ivit{a+}{t,}i' ( + <- 'iv' + ) + 'icitate' 'icitati' 'icit{a+}i' 'icit{a+}{t,}i' + 'icator' 'icatori' + 'iciv' 'iciva' 'icive' 'icivi' 'iciv{a+}' + 'ical' 'icala' 'icale' 'icali' 'ical{a+}' ( + <- 'ic' + ) + 'ativ' 'ativa' 'ative' 'ativi' 'ativ{a+}' 'a{t,}iune' + 'atoare' 'ator' 'atori' + '{a+}toare' '{a+}tor' '{a+}tori' ( + <- 'at' + ) + 'itiv' 'itiva' 'itive' 'itivi' 'itiv{a+}' 'i{t,}iune' + 'itoare' 'itor' 'itori' ( + <- 'it' + ) + ) + set standard_suffix_removed + ) + ) + + define standard_suffix as ( + unset standard_suffix_removed + repeat combo_suffix + [substring] R2 ( + among( + + // past participle is treated here, rather than + // as a verb ending: + 'at' 'ata' 'at{a+}' 'ati' 'ate' + 'ut' 'uta' 'ut{a+}' 'uti' 'ute' + 'it' 'ita' 'it{a+}' 'iti' 'ite' + + 'ic' 'ica' 'ice' 'ici' 'ic{a+}' + 'abil' 'abila' 'abile' 'abili' 'abil{a+}' + 'ibil' 'ibila' 'ibile' 'ibili' 'ibil{a+}' + 'oasa' 'oas{a+}' 'oase' 'os' 'osi' 'o{s,}i' + 'ant' 'anta' 'ante' 'anti' 'ant{a+}' + 'ator' 'atori' + 'itate' 'itati' 'it{a+}i' 'it{a+}{t,}i' + 'iv' 'iva' 'ive' 'ivi' 'iv{a+}' ( + delete + ) + 'iune' 'iuni' ( + '{t,}'] <- 't' + ) + 'ism' 'isme' + 'ist' 'ista' 'iste' 'isti' 'ist{a+}' 'i{s,}ti' ( + <- 'ist' + /* 'IST'. alternative: remove with <- '' */ + ) + ) + set standard_suffix_removed + ) + ) + + define verb_suffix as setlimit tomark pV for ( + [substring] among( + // 'long' infinitive: + 'are' 'ere' 'ire' '{a^}re' + + // gerund: + 'ind' '{a^}nd' + 'indu' '{a^}ndu' + + 'eze' + 'easc{a+}' + // present: + 'ez' 'ezi' 'eaz{a+}' 'esc' 'e{s,}ti' + 'e{s,}te' + '{a+}sc' '{a+}{s,}ti' + '{a+}{s,}te' + + // imperfect: + 'am' 'ai' 'au' + 'eam' 'eai' 'ea' 'ea{t,}i' 'eau' + 'iam' 'iai' 'ia' 'ia{t,}i' 'iau' + + // past: // (not 'ii') + 'ui' + 'a{s,}i' 'ar{a+}m' 'ar{a+}{t,}i' 'ar{a+}' + 'u{s,}i' 'ur{a+}m' 'ur{a+}{t,}i' 'ur{a+}' + 'i{s,}i' 'ir{a+}m' 'ir{a+}{t,}i' 'ir{a+}' + '{a^}i' '{a^}{s,}i' '{a^}r{a+}m' '{a^}r{a+}{t,}i' '{a^}r{a+}' + + // pluferfect: + 'asem' 'ase{s,}i' 'ase' 'aser{a+}m' 'aser{a+}{t,}i' 'aser{a+}' + 'isem' 'ise{s,}i' 'ise' 'iser{a+}m' 'iser{a+}{t,}i' 'iser{a+}' + '{a^}sem' '{a^}se{s,}i' '{a^}se' '{a^}ser{a+}m' '{a^}ser{a+}{t,}i' + '{a^}ser{a+}' + 'usem' 'use{s,}i' 'use' 'user{a+}m' 'user{a+}{t,}i' 'user{a+}' + + ( non-v or 'u' delete ) + + // present: + '{a+}m' 'a{t,}i' + 'em' 'e{t,}i' + 'im' 'i{t,}i' + '{a^}m' '{a^}{t,}i' + + // past: + 'se{s,}i' 'ser{a+}m' 'ser{a+}{t,}i' 'ser{a+}' + 'sei' 'se' + + // pluperfect: + 'sesem' 'sese{s,}i' 'sese' 'seser{a+}m' 'seser{a+}{t,}i' 'seser{a+}' + (delete) + ) + ) + + define vowel_suffix as ( + [substring] RV among ( + 'a' 'e' 'i' 'ie' '{a+}' ( delete ) + ) + ) +) + +define stem as ( + do prelude + do mark_regions + backwards ( + do step_0 + do standard_suffix + do ( standard_suffix_removed or verb_suffix ) + do vowel_suffix + ) + do postlude +) + diff --git a/contrib/snowball/algorithms/russian/stem_KOI8_R.sbl b/contrib/snowball/algorithms/russian/stem_KOI8_R.sbl new file mode 100644 index 000000000..cdacb19c4 --- /dev/null +++ b/contrib/snowball/algorithms/russian/stem_KOI8_R.sbl @@ -0,0 +1,217 @@ +stringescapes {} + +/* the 32 Cyrillic letters in the KOI8-R coding scheme, and represented + in Latin characters following the conventions of the standard Library + of Congress transliteration: */ + +stringdef a hex 'C1' +stringdef b hex 'C2' +stringdef v hex 'D7' +stringdef g hex 'C7' +stringdef d hex 'C4' +stringdef e hex 'C5' +stringdef zh hex 'D6' +stringdef z hex 'DA' +stringdef i hex 'C9' +stringdef i` hex 'CA' +stringdef k hex 'CB' +stringdef l hex 'CC' +stringdef m hex 'CD' +stringdef n hex 'CE' +stringdef o hex 'CF' +stringdef p hex 'D0' +stringdef r hex 'D2' +stringdef s hex 'D3' +stringdef t hex 'D4' +stringdef u hex 'D5' +stringdef f hex 'C6' +stringdef kh hex 'C8' +stringdef ts hex 'C3' +stringdef ch hex 'DE' +stringdef sh hex 'DB' +stringdef shch hex 'DD' +stringdef " hex 'DF' +stringdef y hex 'D9' +stringdef ' hex 'D8' +stringdef e` hex 'DC' +stringdef iu hex 'C0' +stringdef ia hex 'D1' + +routines ( mark_regions R2 + perfective_gerund + adjective + adjectival + reflexive + verb + noun + derivational + tidy_up +) + +externals ( stem ) + +integers ( pV p2 ) + +groupings ( v ) + +define v '{a}{e}{i}{o}{u}{y}{e`}{iu}{ia}' + +define mark_regions as ( + + $pV = limit + $p2 = limit + do ( + gopast v setmark pV gopast non-v + gopast v gopast non-v setmark p2 + ) +) + +backwardmode ( + + define R2 as $p2 <= cursor + + define perfective_gerund as ( + [substring] among ( + '{v}' + '{v}{sh}{i}' + '{v}{sh}{i}{s}{'}' + ('{a}' or '{ia}' delete) + '{i}{v}' + '{i}{v}{sh}{i}' + '{i}{v}{sh}{i}{s}{'}' + '{y}{v}' + '{y}{v}{sh}{i}' + '{y}{v}{sh}{i}{s}{'}' + (delete) + ) + ) + + define adjective as ( + [substring] among ( + '{e}{e}' '{i}{e}' '{y}{e}' '{o}{e}' '{i}{m}{i}' '{y}{m}{i}' + '{e}{i`}' '{i}{i`}' '{y}{i`}' '{o}{i`}' '{e}{m}' '{i}{m}' + '{y}{m}' '{o}{m}' '{e}{g}{o}' '{o}{g}{o}' '{e}{m}{u}' + '{o}{m}{u}' '{i}{kh}' '{y}{kh}' '{u}{iu}' '{iu}{iu}' '{a}{ia}' + '{ia}{ia}' + // and - + '{o}{iu}' // - which is somewhat archaic + '{e}{iu}' // - soft form of {o}{iu} + (delete) + ) + ) + + define adjectival as ( + adjective + + /* of the participle forms, em, vsh, ivsh, yvsh are readily removable. + nn, {iu}shch, shch, u{iu}shch can be removed, with a small proportion of + errors. Removing im, uem, enn creates too many errors. + */ + + try ( + [substring] among ( + '{e}{m}' // present passive participle + '{n}{n}' // adjective from past passive participle + '{v}{sh}' // past active participle + '{iu}{shch}' '{shch}' // present active participle + ('{a}' or '{ia}' delete) + + //but not '{i}{m}' '{u}{e}{m}' // present passive participle + //or '{e}{n}{n}' // adjective from past passive participle + + '{i}{v}{sh}' '{y}{v}{sh}'// past active participle + '{u}{iu}{shch}' // present active participle + (delete) + ) + ) + + ) + + define reflexive as ( + [substring] among ( + '{s}{ia}' + '{s}{'}' + (delete) + ) + ) + + define verb as ( + [substring] among ( + '{l}{a}' '{n}{a}' '{e}{t}{e}' '{i`}{t}{e}' '{l}{i}' '{i`}' + '{l}' '{e}{m}' '{n}' '{l}{o}' '{n}{o}' '{e}{t}' '{iu}{t}' + '{n}{y}' '{t}{'}' '{e}{sh}{'}' + + '{n}{n}{o}' + ('{a}' or '{ia}' delete) + + '{i}{l}{a}' '{y}{l}{a}' '{e}{n}{a}' '{e}{i`}{t}{e}' + '{u}{i`}{t}{e}' '{i}{t}{e}' '{i}{l}{i}' '{y}{l}{i}' '{e}{i`}' + '{u}{i`}' '{i}{l}' '{y}{l}' '{i}{m}' '{y}{m}' '{e}{n}' + '{i}{l}{o}' '{y}{l}{o}' '{e}{n}{o}' '{ia}{t}' '{u}{e}{t}' + '{u}{iu}{t}' '{i}{t}' '{y}{t}' '{e}{n}{y}' '{i}{t}{'}' + '{y}{t}{'}' '{i}{sh}{'}' '{u}{iu}' '{iu}' + (delete) + /* note the short passive participle tests: + '{n}{a}' '{n}' '{n}{o}' '{n}{y}' + '{e}{n}{a}' '{e}{n}' '{e}{n}{o}' '{e}{n}{y}' + */ + ) + ) + + define noun as ( + [substring] among ( + '{a}' '{e}{v}' '{o}{v}' '{i}{e}' '{'}{e}' '{e}' + '{i}{ia}{m}{i}' '{ia}{m}{i}' '{a}{m}{i}' '{e}{i}' '{i}{i}' + '{i}' '{i}{e}{i`}' '{e}{i`}' '{o}{i`}' '{i}{i`}' '{i`}' + '{i}{ia}{m}' '{ia}{m}' '{i}{e}{m}' '{e}{m}' '{a}{m}' '{o}{m}' + '{o}' '{u}' '{a}{kh}' '{i}{ia}{kh}' '{ia}{kh}' '{y}' '{'}' + '{i}{iu}' '{'}{iu}' '{iu}' '{i}{ia}' '{'}{ia}' '{ia}' + (delete) + /* the small class of neuter forms '{e}{n}{i}' '{e}{n}{e}{m}' + '{e}{n}{a}' '{e}{n}' '{e}{n}{a}{m}' '{e}{n}{a}{m}{i}' '{e}{n}{a}{x}' + omitted - they only occur on 12 words. + */ + ) + ) + + define derivational as ( + [substring] R2 among ( + '{o}{s}{t}' + '{o}{s}{t}{'}' + (delete) + ) + ) + + define tidy_up as ( + [substring] among ( + + '{e}{i`}{sh}' + '{e}{i`}{sh}{e}' // superlative forms + (delete + ['{n}'] '{n}' delete + ) + '{n}' + ('{n}' delete) // e.g. -nno endings + '{'}' + (delete) // with some slight false conflations + ) + ) +) + +define stem as ( + + do mark_regions + backwards setlimit tomark pV for ( + do ( + perfective_gerund or + ( try reflexive + adjectival or verb or noun + ) + ) + try([ '{i}' ] delete) + // because noun ending -i{iu} is being treated as verb ending -{iu} + + do derivational + do tidy_up + ) +) diff --git a/contrib/snowball/algorithms/russian/stem_Unicode.sbl b/contrib/snowball/algorithms/russian/stem_Unicode.sbl new file mode 100644 index 000000000..9e1a93f93 --- /dev/null +++ b/contrib/snowball/algorithms/russian/stem_Unicode.sbl @@ -0,0 +1,215 @@ +stringescapes {} + +/* the 32 Cyrillic letters in Unicode */ + +stringdef a hex '430' +stringdef b hex '431' +stringdef v hex '432' +stringdef g hex '433' +stringdef d hex '434' +stringdef e hex '435' +stringdef zh hex '436' +stringdef z hex '437' +stringdef i hex '438' +stringdef i` hex '439' +stringdef k hex '43A' +stringdef l hex '43B' +stringdef m hex '43C' +stringdef n hex '43D' +stringdef o hex '43E' +stringdef p hex '43F' +stringdef r hex '440' +stringdef s hex '441' +stringdef t hex '442' +stringdef u hex '443' +stringdef f hex '444' +stringdef kh hex '445' +stringdef ts hex '446' +stringdef ch hex '447' +stringdef sh hex '448' +stringdef shch hex '449' +stringdef " hex '44A' +stringdef y hex '44B' +stringdef ' hex '44C' +stringdef e` hex '44D' +stringdef iu hex '44E' +stringdef ia hex '44F' + +routines ( mark_regions R2 + perfective_gerund + adjective + adjectival + reflexive + verb + noun + derivational + tidy_up +) + +externals ( stem ) + +integers ( pV p2 ) + +groupings ( v ) + +define v '{a}{e}{i}{o}{u}{y}{e`}{iu}{ia}' + +define mark_regions as ( + + $pV = limit + $p2 = limit + do ( + gopast v setmark pV gopast non-v + gopast v gopast non-v setmark p2 + ) +) + +backwardmode ( + + define R2 as $p2 <= cursor + + define perfective_gerund as ( + [substring] among ( + '{v}' + '{v}{sh}{i}' + '{v}{sh}{i}{s}{'}' + ('{a}' or '{ia}' delete) + '{i}{v}' + '{i}{v}{sh}{i}' + '{i}{v}{sh}{i}{s}{'}' + '{y}{v}' + '{y}{v}{sh}{i}' + '{y}{v}{sh}{i}{s}{'}' + (delete) + ) + ) + + define adjective as ( + [substring] among ( + '{e}{e}' '{i}{e}' '{y}{e}' '{o}{e}' '{i}{m}{i}' '{y}{m}{i}' + '{e}{i`}' '{i}{i`}' '{y}{i`}' '{o}{i`}' '{e}{m}' '{i}{m}' + '{y}{m}' '{o}{m}' '{e}{g}{o}' '{o}{g}{o}' '{e}{m}{u}' + '{o}{m}{u}' '{i}{kh}' '{y}{kh}' '{u}{iu}' '{iu}{iu}' '{a}{ia}' + '{ia}{ia}' + // and - + '{o}{iu}' // - which is somewhat archaic + '{e}{iu}' // - soft form of {o}{iu} + (delete) + ) + ) + + define adjectival as ( + adjective + + /* of the participle forms, em, vsh, ivsh, yvsh are readily removable. + nn, {iu}shch, shch, u{iu}shch can be removed, with a small proportion of + errors. Removing im, uem, enn creates too many errors. + */ + + try ( + [substring] among ( + '{e}{m}' // present passive participle + '{n}{n}' // adjective from past passive participle + '{v}{sh}' // past active participle + '{iu}{shch}' '{shch}' // present active participle + ('{a}' or '{ia}' delete) + + //but not '{i}{m}' '{u}{e}{m}' // present passive participle + //or '{e}{n}{n}' // adjective from past passive participle + + '{i}{v}{sh}' '{y}{v}{sh}'// past active participle + '{u}{iu}{shch}' // present active participle + (delete) + ) + ) + + ) + + define reflexive as ( + [substring] among ( + '{s}{ia}' + '{s}{'}' + (delete) + ) + ) + + define verb as ( + [substring] among ( + '{l}{a}' '{n}{a}' '{e}{t}{e}' '{i`}{t}{e}' '{l}{i}' '{i`}' + '{l}' '{e}{m}' '{n}' '{l}{o}' '{n}{o}' '{e}{t}' '{iu}{t}' + '{n}{y}' '{t}{'}' '{e}{sh}{'}' + + '{n}{n}{o}' + ('{a}' or '{ia}' delete) + + '{i}{l}{a}' '{y}{l}{a}' '{e}{n}{a}' '{e}{i`}{t}{e}' + '{u}{i`}{t}{e}' '{i}{t}{e}' '{i}{l}{i}' '{y}{l}{i}' '{e}{i`}' + '{u}{i`}' '{i}{l}' '{y}{l}' '{i}{m}' '{y}{m}' '{e}{n}' + '{i}{l}{o}' '{y}{l}{o}' '{e}{n}{o}' '{ia}{t}' '{u}{e}{t}' + '{u}{iu}{t}' '{i}{t}' '{y}{t}' '{e}{n}{y}' '{i}{t}{'}' + '{y}{t}{'}' '{i}{sh}{'}' '{u}{iu}' '{iu}' + (delete) + /* note the short passive participle tests: + '{n}{a}' '{n}' '{n}{o}' '{n}{y}' + '{e}{n}{a}' '{e}{n}' '{e}{n}{o}' '{e}{n}{y}' + */ + ) + ) + + define noun as ( + [substring] among ( + '{a}' '{e}{v}' '{o}{v}' '{i}{e}' '{'}{e}' '{e}' + '{i}{ia}{m}{i}' '{ia}{m}{i}' '{a}{m}{i}' '{e}{i}' '{i}{i}' + '{i}' '{i}{e}{i`}' '{e}{i`}' '{o}{i`}' '{i}{i`}' '{i`}' + '{i}{ia}{m}' '{ia}{m}' '{i}{e}{m}' '{e}{m}' '{a}{m}' '{o}{m}' + '{o}' '{u}' '{a}{kh}' '{i}{ia}{kh}' '{ia}{kh}' '{y}' '{'}' + '{i}{iu}' '{'}{iu}' '{iu}' '{i}{ia}' '{'}{ia}' '{ia}' + (delete) + /* the small class of neuter forms '{e}{n}{i}' '{e}{n}{e}{m}' + '{e}{n}{a}' '{e}{n}' '{e}{n}{a}{m}' '{e}{n}{a}{m}{i}' '{e}{n}{a}{x}' + omitted - they only occur on 12 words. + */ + ) + ) + + define derivational as ( + [substring] R2 among ( + '{o}{s}{t}' + '{o}{s}{t}{'}' + (delete) + ) + ) + + define tidy_up as ( + [substring] among ( + + '{e}{i`}{sh}' + '{e}{i`}{sh}{e}' // superlative forms + (delete + ['{n}'] '{n}' delete + ) + '{n}' + ('{n}' delete) // e.g. -nno endings + '{'}' + (delete) // with some slight false conflations + ) + ) +) + +define stem as ( + + do mark_regions + backwards setlimit tomark pV for ( + do ( + perfective_gerund or + ( try reflexive + adjectival or verb or noun + ) + ) + try([ '{i}' ] delete) + // because noun ending -i{iu} is being treated as verb ending -{iu} + + do derivational + do tidy_up + ) +) diff --git a/contrib/snowball/algorithms/spanish/stem_ISO_8859_1.sbl b/contrib/snowball/algorithms/spanish/stem_ISO_8859_1.sbl new file mode 100644 index 000000000..9dee289cc --- /dev/null +++ b/contrib/snowball/algorithms/spanish/stem_ISO_8859_1.sbl @@ -0,0 +1,230 @@ +routines ( + postlude mark_regions + RV R1 R2 + attached_pronoun + standard_suffix + y_verb_suffix + verb_suffix + residual_suffix +) + +externals ( stem ) + +integers ( pV p1 p2 ) + +groupings ( v ) + +stringescapes {} + +/* special characters (in ISO Latin I) */ + +stringdef a' hex 'E1' // a-acute +stringdef e' hex 'E9' // e-acute +stringdef i' hex 'ED' // i-acute +stringdef o' hex 'F3' // o-acute +stringdef u' hex 'FA' // u-acute +stringdef u" hex 'FC' // u-diaeresis +stringdef n~ hex 'F1' // n-tilde + +define v 'aeiou{a'}{e'}{i'}{o'}{u'}{u"}' + +define mark_regions as ( + + $pV = limit + $p1 = limit + $p2 = limit // defaults + + do ( + ( v (non-v gopast v) or (v gopast non-v) ) + or + ( non-v (non-v gopast v) or (v next) ) + setmark pV + ) + do ( + gopast v gopast non-v setmark p1 + gopast v gopast non-v setmark p2 + ) +) + +define postlude as repeat ( + [substring] among( + '{a'}' (<- 'a') + '{e'}' (<- 'e') + '{i'}' (<- 'i') + '{o'}' (<- 'o') + '{u'}' (<- 'u') + // and possibly {u"}->u here, or in prelude + '' (next) + ) //or next +) + +backwardmode ( + + define RV as $pV <= cursor + define R1 as $p1 <= cursor + define R2 as $p2 <= cursor + + define attached_pronoun as ( + [substring] among( + 'me' 'se' 'sela' 'selo' 'selas' 'selos' 'la' 'le' 'lo' + 'las' 'les' 'los' 'nos' + ) + substring RV among( + 'i{e'}ndo' (] <- 'iendo') + '{a'}ndo' (] <- 'ando') + '{a'}r' (] <- 'ar') + '{e'}r' (] <- 'er') + '{i'}r' (] <- 'ir') + 'ando' + 'iendo' + 'ar' 'er' 'ir' + (delete) + 'yendo' ('u' delete) + ) + ) + + define standard_suffix as ( + [substring] among( + + 'anza' 'anzas' + 'ico' 'ica' 'icos' 'icas' + 'ismo' 'ismos' + 'able' 'ables' + 'ible' 'ibles' + 'ista' 'istas' + 'oso' 'osa' 'osos' 'osas' + 'amiento' 'amientos' + 'imiento' 'imientos' + ( + R2 delete + ) + 'adora' 'ador' 'aci{o'}n' + 'adoras' 'adores' 'aciones' + 'ante' 'antes' 'ancia' 'ancias'// Note 1 + ( + R2 delete + try ( ['ic'] R2 delete ) + ) + 'log{i'}a' + 'log{i'}as' + ( + R2 <- 'log' + ) + 'uci{o'}n' 'uciones' + ( + R2 <- 'u' + ) + 'encia' 'encias' + ( + R2 <- 'ente' + ) + 'amente' + ( + R1 delete + try ( + [substring] R2 delete among( + 'iv' (['at'] R2 delete) + 'os' + 'ic' + 'ad' + ) + ) + ) + 'mente' + ( + R2 delete + try ( + [substring] among( + 'ante' // Note 1 + 'able' + 'ible' (R2 delete) + ) + ) + ) + 'idad' + 'idades' + ( + R2 delete + try ( + [substring] among( + 'abil' + 'ic' + 'iv' (R2 delete) + ) + ) + ) + 'iva' 'ivo' + 'ivas' 'ivos' + ( + R2 delete + try ( + ['at'] R2 delete // but not a further ['ic'] R2 delete + ) + ) + ) + ) + + define y_verb_suffix as ( + setlimit tomark pV for ([substring]) among( + 'ya' 'ye' 'yan' 'yen' 'yeron' 'yendo' 'yo' 'y{o'}' + 'yas' 'yes' 'yais' 'yamos' + ('u' delete) + ) + ) + + define verb_suffix as ( + setlimit tomark pV for ([substring]) among( + + 'en' 'es' '{e'}is' 'emos' + (try ('u' test 'g') ] delete) + + 'ar{i'}an' 'ar{i'}as' 'ar{a'}n' 'ar{a'}s' 'ar{i'}ais' + 'ar{i'}a' 'ar{e'}is' 'ar{i'}amos' 'aremos' 'ar{a'}' + 'ar{e'}' + 'er{i'}an' 'er{i'}as' 'er{a'}n' 'er{a'}s' 'er{i'}ais' + 'er{i'}a' 'er{e'}is' 'er{i'}amos' 'eremos' 'er{a'}' + 'er{e'}' + 'ir{i'}an' 'ir{i'}as' 'ir{a'}n' 'ir{a'}s' 'ir{i'}ais' + 'ir{i'}a' 'ir{e'}is' 'ir{i'}amos' 'iremos' 'ir{a'}' + 'ir{e'}' + + 'aba' 'ada' 'ida' '{i'}a' 'ara' 'iera' 'ad' 'ed' + 'id' 'ase' 'iese' 'aste' 'iste' 'an' 'aban' '{i'}an' + 'aran' 'ieran' 'asen' 'iesen' 'aron' 'ieron' 'ado' + 'ido' 'ando' 'iendo' 'i{o'}' 'ar' 'er' 'ir' 'as' + 'abas' 'adas' 'idas' '{i'}as' 'aras' 'ieras' 'ases' + 'ieses' '{i'}s' '{a'}is' 'abais' '{i'}ais' 'arais' + 'ierais' 'aseis' 'ieseis' 'asteis' 'isteis' 'ados' + 'idos' 'amos' '{a'}bamos' '{i'}amos' 'imos' + '{a'}ramos' 'i{e'}ramos' 'i{e'}semos' '{a'}semos' + (delete) + ) + ) + + define residual_suffix as ( + [substring] among( + 'os' + 'a' 'o' '{a'}' '{i'}' '{o'}' + ( RV delete ) + 'e' '{e'}' + ( RV delete try( ['u'] test 'g' RV delete ) ) + ) + ) +) + +define stem as ( + do mark_regions + backwards ( + do attached_pronoun + do ( standard_suffix or + y_verb_suffix or + verb_suffix + ) + do residual_suffix + ) + do postlude +) + +/* + Note 1: additions of 15 Jun 2005 +*/ diff --git a/contrib/snowball/algorithms/spanish/stem_MS_DOS_Latin_I.sbl b/contrib/snowball/algorithms/spanish/stem_MS_DOS_Latin_I.sbl new file mode 100644 index 000000000..db7a46201 --- /dev/null +++ b/contrib/snowball/algorithms/spanish/stem_MS_DOS_Latin_I.sbl @@ -0,0 +1,230 @@ +routines ( + postlude mark_regions + RV R1 R2 + attached_pronoun + standard_suffix + y_verb_suffix + verb_suffix + residual_suffix +) + +externals ( stem ) + +integers ( pV p1 p2 ) + +groupings ( v ) + +stringescapes {} + +/* special characters (in MS-DOS Latin I) */ + +stringdef a' hex 'A0' // a-acute +stringdef e' hex '82' // e-acute +stringdef i' hex 'A1' // i-acute +stringdef o' hex 'A2' // o-acute +stringdef u' hex 'A3' // u-acute +stringdef u" hex '81' // u-diaeresis +stringdef n~ hex 'A4' // n-tilde + +define v 'aeiou{a'}{e'}{i'}{o'}{u'}{u"}' + +define mark_regions as ( + + $pV = limit + $p1 = limit + $p2 = limit // defaults + + do ( + ( v (non-v gopast v) or (v gopast non-v) ) + or + ( non-v (non-v gopast v) or (v next) ) + setmark pV + ) + do ( + gopast v gopast non-v setmark p1 + gopast v gopast non-v setmark p2 + ) +) + +define postlude as repeat ( + [substring] among( + '{a'}' (<- 'a') + '{e'}' (<- 'e') + '{i'}' (<- 'i') + '{o'}' (<- 'o') + '{u'}' (<- 'u') + // and possibly {u"}->u here, or in prelude + '' (next) + ) //or next +) + +backwardmode ( + + define RV as $pV <= cursor + define R1 as $p1 <= cursor + define R2 as $p2 <= cursor + + define attached_pronoun as ( + [substring] among( + 'me' 'se' 'sela' 'selo' 'selas' 'selos' 'la' 'le' 'lo' + 'las' 'les' 'los' 'nos' + ) + substring RV among( + 'i{e'}ndo' (] <- 'iendo') + '{a'}ndo' (] <- 'ando') + '{a'}r' (] <- 'ar') + '{e'}r' (] <- 'er') + '{i'}r' (] <- 'ir') + 'ando' + 'iendo' + 'ar' 'er' 'ir' + (delete) + 'yendo' ('u' delete) + ) + ) + + define standard_suffix as ( + [substring] among( + + 'anza' 'anzas' + 'ico' 'ica' 'icos' 'icas' + 'ismo' 'ismos' + 'able' 'ables' + 'ible' 'ibles' + 'ista' 'istas' + 'oso' 'osa' 'osos' 'osas' + 'amiento' 'amientos' + 'imiento' 'imientos' + ( + R2 delete + ) + 'adora' 'ador' 'aci{o'}n' + 'adoras' 'adores' 'aciones' + 'ante' 'antes' 'ancia' 'ancias'// Note 1 + ( + R2 delete + try ( ['ic'] R2 delete ) + ) + 'log{i'}a' + 'log{i'}as' + ( + R2 <- 'log' + ) + 'uci{o'}n' 'uciones' + ( + R2 <- 'u' + ) + 'encia' 'encias' + ( + R2 <- 'ente' + ) + 'amente' + ( + R1 delete + try ( + [substring] R2 delete among( + 'iv' (['at'] R2 delete) + 'os' + 'ic' + 'ad' + ) + ) + ) + 'mente' + ( + R2 delete + try ( + [substring] among( + 'ante' // Note 1 + 'able' + 'ible' (R2 delete) + ) + ) + ) + 'idad' + 'idades' + ( + R2 delete + try ( + [substring] among( + 'abil' + 'ic' + 'iv' (R2 delete) + ) + ) + ) + 'iva' 'ivo' + 'ivas' 'ivos' + ( + R2 delete + try ( + ['at'] R2 delete // but not a further ['ic'] R2 delete + ) + ) + ) + ) + + define y_verb_suffix as ( + setlimit tomark pV for ([substring]) among( + 'ya' 'ye' 'yan' 'yen' 'yeron' 'yendo' 'yo' 'y{o'}' + 'yas' 'yes' 'yais' 'yamos' + ('u' delete) + ) + ) + + define verb_suffix as ( + setlimit tomark pV for ([substring]) among( + + 'en' 'es' '{e'}is' 'emos' + (try ('u' test 'g') ] delete) + + 'ar{i'}an' 'ar{i'}as' 'ar{a'}n' 'ar{a'}s' 'ar{i'}ais' + 'ar{i'}a' 'ar{e'}is' 'ar{i'}amos' 'aremos' 'ar{a'}' + 'ar{e'}' + 'er{i'}an' 'er{i'}as' 'er{a'}n' 'er{a'}s' 'er{i'}ais' + 'er{i'}a' 'er{e'}is' 'er{i'}amos' 'eremos' 'er{a'}' + 'er{e'}' + 'ir{i'}an' 'ir{i'}as' 'ir{a'}n' 'ir{a'}s' 'ir{i'}ais' + 'ir{i'}a' 'ir{e'}is' 'ir{i'}amos' 'iremos' 'ir{a'}' + 'ir{e'}' + + 'aba' 'ada' 'ida' '{i'}a' 'ara' 'iera' 'ad' 'ed' + 'id' 'ase' 'iese' 'aste' 'iste' 'an' 'aban' '{i'}an' + 'aran' 'ieran' 'asen' 'iesen' 'aron' 'ieron' 'ado' + 'ido' 'ando' 'iendo' 'i{o'}' 'ar' 'er' 'ir' 'as' + 'abas' 'adas' 'idas' '{i'}as' 'aras' 'ieras' 'ases' + 'ieses' '{i'}s' '{a'}is' 'abais' '{i'}ais' 'arais' + 'ierais' 'aseis' 'ieseis' 'asteis' 'isteis' 'ados' + 'idos' 'amos' '{a'}bamos' '{i'}amos' 'imos' + '{a'}ramos' 'i{e'}ramos' 'i{e'}semos' '{a'}semos' + (delete) + ) + ) + + define residual_suffix as ( + [substring] among( + 'os' + 'a' 'o' '{a'}' '{i'}' '{o'}' + ( RV delete ) + 'e' '{e'}' + ( RV delete try( ['u'] test 'g' RV delete ) ) + ) + ) +) + +define stem as ( + do mark_regions + backwards ( + do attached_pronoun + do ( standard_suffix or + y_verb_suffix or + verb_suffix + ) + do residual_suffix + ) + do postlude +) + +/* + Note 1: additions of 15 Jun 2005 +*/ diff --git a/contrib/snowball/algorithms/swedish/stem_ISO_8859_1.sbl b/contrib/snowball/algorithms/swedish/stem_ISO_8859_1.sbl new file mode 100644 index 000000000..03ce1e22f --- /dev/null +++ b/contrib/snowball/algorithms/swedish/stem_ISO_8859_1.sbl @@ -0,0 +1,72 @@ +routines ( + mark_regions + main_suffix + consonant_pair + other_suffix +) + +externals ( stem ) + +integers ( p1 x ) + +groupings ( v s_ending ) + +stringescapes {} + +/* special characters (in ISO Latin I) */ + +stringdef a" hex 'E4' +stringdef ao hex 'E5' +stringdef o" hex 'F6' + +define v 'aeiouy{a"}{ao}{o"}' + +define s_ending 'bcdfghjklmnoprtvy' + +define mark_regions as ( + + $p1 = limit + test ( hop 3 setmark x ) + goto v gopast non-v setmark p1 + try ( $p1 < x $p1 = x ) +) + +backwardmode ( + + define main_suffix as ( + setlimit tomark p1 for ([substring]) + among( + + 'a' 'arna' 'erna' 'heterna' 'orna' 'ad' 'e' 'ade' 'ande' 'arne' + 'are' 'aste' 'en' 'anden' 'aren' 'heten' 'ern' 'ar' 'er' 'heter' + 'or' 'as' 'arnas' 'ernas' 'ornas' 'es' 'ades' 'andes' 'ens' 'arens' + 'hetens' 'erns' 'at' 'andet' 'het' 'ast' + (delete) + 's' + (s_ending delete) + ) + ) + + define consonant_pair as setlimit tomark p1 for ( + among('dd' 'gd' 'nn' 'dt' 'gt' 'kt' 'tt') + and ([next] delete) + ) + + define other_suffix as setlimit tomark p1 for ( + [substring] among( + 'lig' 'ig' 'els' (delete) + 'l{o"}st' (<-'l{o"}s') + 'fullt' (<-'full') + ) + ) +) + +define stem as ( + + do mark_regions + backwards ( + do main_suffix + do consonant_pair + do other_suffix + ) +) diff --git a/contrib/snowball/algorithms/swedish/stem_MS_DOS_Latin_I.sbl b/contrib/snowball/algorithms/swedish/stem_MS_DOS_Latin_I.sbl new file mode 100644 index 000000000..1631f401a --- /dev/null +++ b/contrib/snowball/algorithms/swedish/stem_MS_DOS_Latin_I.sbl @@ -0,0 +1,72 @@ +routines ( + mark_regions + main_suffix + consonant_pair + other_suffix +) + +externals ( stem ) + +integers ( p1 x ) + +groupings ( v s_ending ) + +stringescapes {} + +/* special characters (in MS-DOS Latin I) */ + +stringdef a" hex '84' +stringdef ao hex '86' +stringdef o" hex '94' + +define v 'aeiouy{a"}{ao}{o"}' + +define s_ending 'bcdfghjklmnoprtvy' + +define mark_regions as ( + + $p1 = limit + test ( hop 3 setmark x ) + goto v gopast non-v setmark p1 + try ( $p1 < x $p1 = x ) +) + +backwardmode ( + + define main_suffix as ( + setlimit tomark p1 for ([substring]) + among( + + 'a' 'arna' 'erna' 'heterna' 'orna' 'ad' 'e' 'ade' 'ande' 'arne' + 'are' 'aste' 'en' 'anden' 'aren' 'heten' 'ern' 'ar' 'er' 'heter' + 'or' 'as' 'arnas' 'ernas' 'ornas' 'es' 'ades' 'andes' 'ens' 'arens' + 'hetens' 'erns' 'at' 'andet' 'het' 'ast' + (delete) + 's' + (s_ending delete) + ) + ) + + define consonant_pair as setlimit tomark p1 for ( + among('dd' 'gd' 'nn' 'dt' 'gt' 'kt' 'tt') + and ([next] delete) + ) + + define other_suffix as setlimit tomark p1 for ( + [substring] among( + 'lig' 'ig' 'els' (delete) + 'l{o"}st' (<-'l{o"}s') + 'fullt' (<-'full') + ) + ) +) + +define stem as ( + + do mark_regions + backwards ( + do main_suffix + do consonant_pair + do other_suffix + ) +) diff --git a/contrib/snowball/algorithms/turkish/stem_Unicode.sbl b/contrib/snowball/algorithms/turkish/stem_Unicode.sbl new file mode 100644 index 000000000..16c02a51f --- /dev/null +++ b/contrib/snowball/algorithms/turkish/stem_Unicode.sbl @@ -0,0 +1,477 @@ +/* Stemmer for Turkish + * author: Evren (Kapusuz) Çilden + * email: evren.kapusuz at gmail.com + * version: 1.0 (15.01.2007) + + + * stems nominal verb suffixes + * stems nominal inflections + * more than one syllable word check + * (y,n,s,U) context check + * vowel harmony check + * last consonant check and conversion (b, c, d, ğ to p, ç, t, k) + + * The stemming algorithm is based on the paper "An Affix Stripping + * Morphological Analyzer for Turkish" by Gülşen Eryiğit and + * Eşref Adalı (Proceedings of the IAESTED International Conference + * ARTIFICIAL INTELLIGENCE AND APPLICATIONS, February 16-18,2004, + * Innsbruck, Austria + + * Turkish is an agglutinative language and has a very rich morphological + * structure. In Turkish, you can form many different words from a single stem + * by appending a sequence of suffixes. Eg. The word "doktoruymuşsunuz" means + * "You had been the doctor of him". The stem of the word is "doktor" and it + * takes three different suffixes -sU, -ymUs, and -sUnUz. The rules about + * the append order of suffixes can be clearly described as FSMs. + * The paper referenced above defines some FSMs for right to left + * morphological analysis. I generated a method for constructing snowball + * expressions from right to left FSMs for stemming suffixes. +*/ + +routines ( + append_U_to_stems_ending_with_d_or_g // for preventing some overstemmings + check_vowel_harmony // tests vowel harmony for suffixes + is_reserved_word // tests whether current string is a reserved word ('ad','soyad') + mark_cAsInA // nominal verb suffix + mark_DA // noun suffix + mark_DAn // noun suffix + mark_DUr // nominal verb suffix + mark_ki // noun suffix + mark_lAr // noun suffix, nominal verb suffix + mark_lArI // noun suffix + mark_nA // noun suffix + mark_ncA // noun suffix + mark_ndA // noun suffix + mark_ndAn // noun suffix + mark_nU // noun suffix + mark_nUn // noun suffix + mark_nUz // nominal verb suffix + mark_sU // noun suffix + mark_sUn // nominal verb suffix + mark_sUnUz // nominal verb suffix + mark_possessives // -(U)m,-(U)n,-(U)mUz,-(U)nUz, + mark_yA // noun suffix + mark_ylA // noun suffix + mark_yU // noun suffix + mark_yUm // nominal verb suffix + mark_yUz // nominal verb suffix + mark_yDU // nominal verb suffix + mark_yken // nominal verb suffix + mark_ymUs_ // nominal verb suffix + mark_ysA // nominal verb suffix + + mark_suffix_with_optional_y_consonant + mark_suffix_with_optional_U_vowel + mark_suffix_with_optional_n_consonant + mark_suffix_with_optional_s_consonant + + more_than_one_syllable_word + + post_process_last_consonants + postlude + + stem_nominal_verb_suffixes + stem_noun_suffixes + stem_suffix_chain_before_ki +) + +/* Special characters in Unicode Latin-1 and Latin Extended-A */ +stringdef c. hex 'E7' // LATIN SMALL LETTER C WITH CEDILLA +stringdef g~ hex '011F' // LATIN SMALL LETTER G WITH BREVE +stringdef i' hex '0131' // LATIN SMALL LETTER I WITHOUT DOT +stringdef o" hex 'F6' // LATIN SMALL LETTER O WITH DIAERESIS +stringdef s. hex '015F' // LATIN SMALL LETTER S WITH CEDILLA +stringdef u" hex 'FC' // LATIN SMALL LETTER U WITH DIAERESIS + +stringescapes { } + +integers ( strlen ) // length of a string + +booleans ( continue_stemming_noun_suffixes ) + +groupings ( vowel U vowel1 vowel2 vowel3 vowel4 vowel5 vowel6) + +define vowel 'ae{i'}io{o"}u{u"}' +define U '{i'}iu{u"}' + +// the vowel grouping definitions below are used for checking vowel harmony +define vowel1 'a{i'}ou' // vowels that can end with suffixes containing 'a' +define vowel2 'ei{o"}{u"}' // vowels that can end with suffixes containing 'e' +define vowel3 'a{i'}' // vowels that can end with suffixes containing 'i'' +define vowel4 'ei' // vowels that can end with suffixes containing 'i' +define vowel5 'ou' // vowels that can end with suffixes containing 'o' or 'u' +define vowel6 '{o"}{u"}' // vowels that can end with suffixes containing 'o"' or 'u"' + +externals ( stem ) + +backwardmode ( + // checks vowel harmony for possible suffixes, + // helps to detect whether the candidate for suffix applies to vowel harmony + // this rule is added to prevent over stemming + define check_vowel_harmony as ( + test + ( + (goto vowel) // if there is a vowel + ( + ('a' goto vowel1) or + ('e' goto vowel2) or + ('{i'}' goto vowel3) or + ('i' goto vowel4) or + ('o' goto vowel5) or + ('{o"}' goto vowel6) or + ('u' goto vowel5) or + ('{u"}' goto vowel6) + ) + ) + ) + + // if the last consonant before suffix is vowel and n then advance and delete + // if the last consonant before suffix is non vowel and n do nothing + // if the last consonant before suffix is not n then only delete the suffix + // assumption: slice beginning is set correctly + define mark_suffix_with_optional_n_consonant as ( + ((test 'n') next (test vowel)) + or + ((not(test 'n')) test(next (test vowel))) + + ) + + // if the last consonant before suffix is vowel and s then advance and delete + // if the last consonant before suffix is non vowel and s do nothing + // if the last consonant before suffix is not s then only delete the suffix + // assumption: slice beginning is set correctly + define mark_suffix_with_optional_s_consonant as ( + ((test 's') next (test vowel)) + or + ((not(test 's')) test(next (test vowel))) + ) + + // if the last consonant before suffix is vowel and y then advance and delete + // if the last consonant before suffix is non vowel and y do nothing + // if the last consonant before suffix is not y then only delete the suffix + // assumption: slice beginning is set correctly + define mark_suffix_with_optional_y_consonant as ( + ((test 'y') next (test vowel)) + or + ((not(test 'y')) test(next (test vowel))) + ) + + define mark_suffix_with_optional_U_vowel as ( + ((test U) next (test non-vowel)) + or + ((not(test U)) test(next (test non-vowel))) + + ) + + define mark_possessives as ( + among ('m{i'}z' 'miz' 'muz' 'm{u"}z' + 'n{i'}z' 'niz' 'nuz' 'n{u"}z' 'm' 'n') + (mark_suffix_with_optional_U_vowel) + ) + + define mark_sU as ( + check_vowel_harmony + U + (mark_suffix_with_optional_s_consonant) + ) + + define mark_lArI as ( + among ('leri' 'lar{i'}') + ) + + define mark_yU as ( + check_vowel_harmony + U + (mark_suffix_with_optional_y_consonant) + ) + + define mark_nU as ( + check_vowel_harmony + among ('n{i'}' 'ni' 'nu' 'n{u"}') + ) + + define mark_nUn as ( + check_vowel_harmony + among ('{i'}n' 'in' 'un' '{u"}n') + (mark_suffix_with_optional_n_consonant) + ) + + define mark_yA as ( + check_vowel_harmony + among('a' 'e') + (mark_suffix_with_optional_y_consonant) + ) + + define mark_nA as ( + check_vowel_harmony + among('na' 'ne') + ) + + define mark_DA as ( + check_vowel_harmony + among('da' 'de' 'ta' 'te') + ) + + define mark_ndA as ( + check_vowel_harmony + among('nda' 'nde') + ) + + define mark_DAn as ( + check_vowel_harmony + among('dan' 'den' 'tan' 'ten') + ) + + define mark_ndAn as ( + check_vowel_harmony + among('ndan' 'nden') + ) + + define mark_ylA as ( + check_vowel_harmony + among('la' 'le') + (mark_suffix_with_optional_y_consonant) + ) + + define mark_ki as ( + 'ki' + ) + + define mark_ncA as ( + check_vowel_harmony + among('ca' 'ce') + (mark_suffix_with_optional_n_consonant) + ) + + define mark_yUm as ( + check_vowel_harmony + among ('{i'}m' 'im' 'um' '{u"}m') + (mark_suffix_with_optional_y_consonant) + ) + + define mark_sUn as ( + check_vowel_harmony + among ('s{i'}n' 'sin' 'sun' 's{u"}n' ) + ) + + define mark_yUz as ( + check_vowel_harmony + among ('{i'}z' 'iz' 'uz' '{u"}z') + (mark_suffix_with_optional_y_consonant) + ) + + define mark_sUnUz as ( + among ('s{i'}n{i'}z' 'siniz' 'sunuz' 's{u"}n{u"}z') + ) + + define mark_lAr as ( + check_vowel_harmony + among ('ler' 'lar') + ) + + define mark_nUz as ( + check_vowel_harmony + among ('n{i'}z' 'niz' 'nuz' 'n{u"}z') + ) + + define mark_DUr as ( + check_vowel_harmony + among ('t{i'}r' 'tir' 'tur' 't{u"}r' 'd{i'}r' 'dir' 'dur' 'd{u"}r') + ) + + define mark_cAsInA as ( + among ('cas{i'}na' 'cesine') + ) + + define mark_yDU as ( + check_vowel_harmony + among ('t{i'}m' 'tim' 'tum' 't{u"}m' 'd{i'}m' 'dim' 'dum' 'd{u"}m' + 't{i'}n' 'tin' 'tun' 't{u"}n' 'd{i'}n' 'din' 'dun' 'd{u"}n' + 't{i'}k' 'tik' 'tuk' 't{u"}k' 'd{i'}k' 'dik' 'duk' 'd{u"}k' + 't{i'}' 'ti' 'tu' 't{u"}' 'd{i'}' 'di' 'du' 'd{u"}') + (mark_suffix_with_optional_y_consonant) + ) + + // does not fully obey vowel harmony + define mark_ysA as ( + among ('sam' 'san' 'sak' 'sem' 'sen' 'sek' 'sa' 'se') + (mark_suffix_with_optional_y_consonant) + ) + + define mark_ymUs_ as ( + check_vowel_harmony + among ('m{i'}{s.}' 'mi{s.}' 'mu{s.}' 'm{u"}{s.}') + (mark_suffix_with_optional_y_consonant) + ) + + define mark_yken as ( + 'ken' (mark_suffix_with_optional_y_consonant) + ) + + define stem_nominal_verb_suffixes as ( + [ + set continue_stemming_noun_suffixes + (mark_ymUs_ or mark_yDU or mark_ysA or mark_yken) + or + (mark_cAsInA (mark_sUnUz or mark_lAr or mark_yUm or mark_sUn or mark_yUz or true) mark_ymUs_) + or + ( + mark_lAr ] delete try([(mark_DUr or mark_yDU or mark_ysA or mark_ymUs_)) + unset continue_stemming_noun_suffixes + ) + or + (mark_nUz (mark_yDU or mark_ysA)) + or + ((mark_sUnUz or mark_yUz or mark_sUn or mark_yUm) ] delete try([ mark_ymUs_)) + or + (mark_DUr ] delete try([ (mark_sUnUz or mark_lAr or mark_yUm or mark_sUn or mark_yUz or true) mark_ymUs_)) + ]delete + ) + + // stems noun suffix chains ending with -ki + define stem_suffix_chain_before_ki as ( + [ + mark_ki + ( + (mark_DA] delete try([ + (mark_lAr] delete try(stem_suffix_chain_before_ki)) + or + (mark_possessives] delete try([mark_lAr] delete stem_suffix_chain_before_ki)) + + )) + or + (mark_nUn] delete try([ + (mark_lArI] delete) + or + ([mark_possessives or mark_sU] delete try([mark_lAr] delete stem_suffix_chain_before_ki)) + or + (stem_suffix_chain_before_ki) + )) + or + (mark_ndA ( + (mark_lArI] delete) + or + ((mark_sU] delete try([mark_lAr]delete stem_suffix_chain_before_ki))) + or + (stem_suffix_chain_before_ki) + )) + ) + ) + + define stem_noun_suffixes as ( + ([mark_lAr] delete try(stem_suffix_chain_before_ki)) + or + ([mark_ncA] delete + try( + ([mark_lArI] delete) + or + ([mark_possessives or mark_sU] delete try([mark_lAr] delete stem_suffix_chain_before_ki)) + or + ([mark_lAr] delete stem_suffix_chain_before_ki) + ) + ) + or + ([(mark_ndA or mark_nA) + ( + (mark_lArI] delete) + or + (mark_sU] delete try([mark_lAr] delete stem_suffix_chain_before_ki)) + or + (stem_suffix_chain_before_ki) + ) + ) + or + ([(mark_ndAn or mark_nU) ((mark_sU ] delete try([mark_lAr] delete stem_suffix_chain_before_ki)) or (mark_lArI))) + or + ( [mark_DAn] delete try ([ + ( + (mark_possessives ] delete try([mark_lAr] delete stem_suffix_chain_before_ki)) + or + (mark_lAr] delete try(stem_suffix_chain_before_ki)) + or + (stem_suffix_chain_before_ki) + )) + ) + or + ([mark_nUn or mark_ylA] delete + try( + ([mark_lAr] delete stem_suffix_chain_before_ki) + or + ([mark_possessives or mark_sU] delete try([mark_lAr] delete stem_suffix_chain_before_ki)) + or + stem_suffix_chain_before_ki + ) + ) + or + ([mark_lArI] delete) + or + (stem_suffix_chain_before_ki) + or + ([mark_DA or mark_yU or mark_yA] delete try([((mark_possessives] delete try([mark_lAr)) or mark_lAr) ] delete [ stem_suffix_chain_before_ki)) + or + ([mark_possessives or mark_sU] delete try([mark_lAr] delete stem_suffix_chain_before_ki)) + ) + + define post_process_last_consonants as ( + [substring] among ( + 'b' (<- 'p') + 'c' (<- '{c.}') + 'd' (<- 't') + '{g~}' (<- 'k') + ) + ) + + // after stemming if the word ends with 'd' or 'g' most probably last U is overstemmed + // like in 'kedim' -> 'ked' + // Turkish words don't usually end with 'd' or 'g' + // some very well known words are ignored (like 'ad' 'soyad' + // appends U to stems ending with d or g, decides which vowel to add + // based on the last vowel in the stem + define append_U_to_stems_ending_with_d_or_g as ( + test('d' or 'g') + (test((goto vowel) 'a' or '{i'}') <+ '{i'}') + or + (test((goto vowel) 'e' or 'i') <+ 'i') + or + (test((goto vowel) 'o' or 'u') <+ 'u') + or + (test((goto vowel) '{o"}' or '{u"}') <+ '{u"}') + ) + +) + +// Tests if there are more than one syllables +// In Turkish each vowel indicates a distinct syllable +define more_than_one_syllable_word as ( + test (atleast 2 (gopast vowel)) +) + +define is_reserved_word as ( + test(gopast 'ad' ($strlen = 2) ($strlen == limit)) + or + test(gopast 'soyad' ($strlen = 5) ($strlen == limit)) +) + +define postlude as ( + not(is_reserved_word) + backwards ( + do append_U_to_stems_ending_with_d_or_g + do post_process_last_consonants + + ) +) + +define stem as ( + (more_than_one_syllable_word) + ( + backwards ( + do stem_nominal_verb_suffixes + continue_stemming_noun_suffixes + do stem_noun_suffixes + ) + + postlude + ) +) + + diff --git a/contrib/snowball/compiler/analyser.c b/contrib/snowball/compiler/analyser.c new file mode 100644 index 000000000..68c0d2d90 --- /dev/null +++ b/contrib/snowball/compiler/analyser.c @@ -0,0 +1,959 @@ + +#include <stdio.h> /* printf etc */ +#include <stdlib.h> /* exit */ +#include <string.h> /* memmove */ +#include "header.h" + +/* recursive usage: */ + +static void read_program_(struct analyser * a, int terminator); +static struct node * read_C(struct analyser * a); +static struct node * C_style(struct analyser * a, char * s, int token); + + +static void fault(int n) { fprintf(stderr, "fault %d\n", n); exit(1); } + +static void print_node_(struct node * p, int n, const char * s) { + + int i; + for (i = 0; i < n; i++) fputs(i == n - 1 ? s : " ", stdout); + printf("%s ", name_of_token(p->type)); + unless (p->name == 0) report_b(stdout, p->name->b); + unless (p->literalstring == 0) { + printf("'"); + report_b(stdout, p->literalstring); + printf("'"); + } + printf("\n"); + unless (p->AE == 0) print_node_(p->AE, n+1, "# "); + unless (p->left == 0) print_node_(p->left, n+1, " "); + unless (p->right == 0) print_node_(p->right, n, " "); + if (p->aux != 0) print_node_(p->aux, n+1, "@ "); +} + +extern void print_program(struct analyser * a) { + print_node_(a->program, 0, " "); +} + +static struct node * new_node(struct analyser * a, int type) { + NEW(node, p); + p->next = a->nodes; a->nodes = p; + p->left = 0; + p->right = 0; + p->aux = 0; + p->AE = 0; + p->name = 0; + p->literalstring = 0; + p->mode = a->mode; + p->line_number = a->tokeniser->line_number; + p->type = type; + return p; +} + +static const char * name_of_mode(int n) { + switch (n) { + default: fault(0); + case m_backward: return "string backward"; + case m_forward: return "string forward"; + /* case m_integer: return "integer"; */ + } +} + +static const char * name_of_type(int n) { + switch (n) { + default: fault(1); + case 's': return "string"; + case 'i': return "integer"; + case 'r': return "routine"; + case 'R': return "routine or grouping"; + case 'g': return "grouping"; + } +} + +static void count_error(struct analyser * a) { + struct tokeniser * t = a->tokeniser; + if (t->error_count >= 20) { fprintf(stderr, "... etc\n"); exit(1); } + t->error_count++; +} + +static void error2(struct analyser * a, int n, int x) { + struct tokeniser * t = a->tokeniser; + count_error(a); + fprintf(stderr, "%s:%d: ", t->file, t->line_number); + if (n >= 30) report_b(stderr, t->b); + switch (n) { + case 0: + fprintf(stderr, "%s omitted", name_of_token(t->omission)); break; + case 3: + fprintf(stderr, "in among(...), "); + case 1: + fprintf(stderr, "unexpected %s", name_of_token(t->token)); + if (t->token == c_number) fprintf(stderr, " %d", t->number); + if (t->token == c_name) { + fprintf(stderr, " "); + report_b(stderr, t->b); + } break; + case 2: + fprintf(stderr, "string omitted"); break; + + case 14: + fprintf(stderr, "unresolved substring on line %d", x); break; + case 15: + fprintf(stderr, "%s not allowed inside reverse(...)", name_of_token(t->token)); break; + case 16: + fprintf(stderr, "empty grouping"); break; + case 17: + fprintf(stderr, "backwards used when already in this mode"); break; + case 18: + fprintf(stderr, "empty among(...)"); break; + case 19: + fprintf(stderr, "two adjacent bracketed expressions in among(...)"); break; + case 20: + fprintf(stderr, "substring preceded by another substring on line %d", x); break; + + case 30: + fprintf(stderr, " re-declared"); break; + case 31: + fprintf(stderr, " undeclared"); break; + case 32: + fprintf(stderr, " declared as %s mode; used as %s mode", + name_of_mode(a->mode), name_of_mode(x)); break; + case 33: + fprintf(stderr, " not of type %s", name_of_type(x)); break; + case 34: + fprintf(stderr, " not of type string or integer"); break; + case 35: + fprintf(stderr, " misplaced"); break; + case 36: + fprintf(stderr, " redefined"); break; + case 37: + fprintf(stderr, " mis-used as %s mode", + name_of_mode(x)); break; + default: + fprintf(stderr, " error %d", n); break; + + } + if (n <= 13 && t->previous_token > 0) + fprintf(stderr, " after %s", name_of_token(t->previous_token)); + fprintf(stderr, "\n"); +} + +static void error(struct analyser * a, int n) { error2(a, n, 0); } + +static void error3(struct analyser * a, struct node * p, symbol * b) { + count_error(a); + fprintf(stderr, "%s:%d: among(...) has repeated string '", a->tokeniser->file, p->line_number); + report_b(stderr, b); + fprintf(stderr, "'\n"); +} + +static void error4(struct analyser * a, struct name * q) { + count_error(a); + report_b(stderr, q->b); + fprintf(stderr, " undefined\n"); +} + +static void omission_error(struct analyser * a, int n) { + a->tokeniser->omission = n; + error(a, 0); +} + +static int check_token(struct analyser * a, int code) { + struct tokeniser * t = a->tokeniser; + if (t->token != code) { omission_error(a, code); return false; } + return true; +} + +static int get_token(struct analyser * a, int code) { + struct tokeniser * t = a->tokeniser; + read_token(t); + { + int x = check_token(a, code); + unless (x) t->token_held = true; + return x; + } +} + +static struct name * look_for_name(struct analyser * a) { + struct name * p = a->names; + symbol * q = a->tokeniser->b; + repeat { + if (p == 0) return 0; + { symbol * b = p->b; + int n = SIZE(b); + if (n == SIZE(q) && memcmp(q, b, n * sizeof(symbol)) == 0) { + p->referenced = true; + return p; + } + } + p = p->next; + } +} + +static struct name * find_name(struct analyser * a) { + struct name * p = look_for_name(a); + if (p == 0) error(a, 31); + return p; +} + +static void check_routine_mode(struct analyser * a, struct name * p, int mode) { + if (p->mode < 0) p->mode = mode; else + unless (p->mode == mode) error2(a, 37, mode); +} + +static void check_name_type(struct analyser * a, struct name * p, int type) { + switch (type) { + case 's': if (p->type == t_string) return; break; + case 'i': if (p->type == t_integer) return; break; + case 'b': if (p->type == t_boolean) return; break; + case 'R': if (p->type == t_grouping) return; + case 'r': if (p->type == t_routine || + p->type == t_external) return; break; + case 'g': if (p->type == t_grouping) return; break; + } + error2(a, 33, type); +} + +static void read_names(struct analyser * a, int type) { + struct tokeniser * t = a->tokeniser; + unless (get_token(a, c_bra)) return; + repeat { + if (read_token(t) != c_name) break; + if (look_for_name(a) != 0) error(a, 30); else { + NEW(name, p); + p->b = copy_b(t->b); + p->type = type; + p->mode = -1; /* routines, externals */ + p->count = a->name_count[type]; + p->referenced = false; + p->used = false; + p->grouping = 0; + p->definition = 0; + a->name_count[type] ++; + p->next = a->names; + a->names = p; + } + } + unless (check_token(a, c_ket)) t->token_held = true; +} + +static symbol * new_literalstring(struct analyser * a) { + NEW(literalstring, p); + p->b = copy_b(a->tokeniser->b); + p->next = a->literalstrings; + a->literalstrings = p; + return p->b; +} + +static int read_AE_test(struct analyser * a) { + + struct tokeniser * t = a->tokeniser; + switch (read_token(t)) { + case c_assign: return c_mathassign; + case c_plusassign: + case c_minusassign: + case c_multiplyassign: + case c_divideassign: + case c_eq: + case c_ne: + case c_gr: + case c_ge: + case c_ls: + case c_le: return t->token; + default: error(a, 1); t->token_held = true; return c_eq; + } +} + +static int binding(int t) { + switch (t) { + case c_plus: case c_minus: return 1; + case c_multiply: case c_divide: return 2; + default: return -2; + } +} + +static void name_to_node(struct analyser * a, struct node * p, int type) { + struct name * q = find_name(a); + unless (q == 0) { + check_name_type(a, q, type); + q->used = true; + } + p->name = q; +} + +static struct node * read_AE(struct analyser * a, int B) { + struct tokeniser * t = a->tokeniser; + struct node * p; + struct node * q; + switch (read_token(t)) { + case c_minus: /* monadic */ + p = new_node(a, c_neg); + p->right = read_AE(a, 100); + break; + case c_bra: + p = read_AE(a, 0); + get_token(a, c_ket); + break; + case c_name: + p = new_node(a, c_name); + name_to_node(a, p, 'i'); + break; + case c_maxint: + case c_minint: + case c_cursor: + case c_limit: + case c_size: + p = new_node(a, t->token); + break; + case c_number: + p = new_node(a, c_number); + p->number = t->number; + break; + case c_sizeof: + p = C_style(a, "s", c_sizeof); + break; + default: + error(a, 1); + t->token_held = true; + return 0; + } + repeat { + int token = read_token(t); + int b = binding(token); + unless (binding(token) > B) { + t->token_held = true; + return p; + } + q = new_node(a, token); + q->left = p; + q->right = read_AE(a, b); + p = q; + } +} + +static struct node * read_C_connection(struct analyser * a, struct node * q, int op) { + struct tokeniser * t = a->tokeniser; + struct node * p = new_node(a, op); + struct node * p_end = q; + p->left = q; + repeat { + q = read_C(a); + p_end->right = q; p_end = q; + if (read_token(t) != op) { + t->token_held = true; + break; + } + } + return p; +} + +static struct node * read_C_list(struct analyser * a) { + struct tokeniser * t = a->tokeniser; + struct node * p = new_node(a, c_bra); + struct node * p_end = 0; + repeat { + int token = read_token(t); + if (token == c_ket) return p; + if (token < 0) { omission_error(a, c_ket); return p; } + t->token_held = true; + { + struct node * q = read_C(a); + repeat { + token = read_token(t); + if (token != c_and && token != c_or) { + t->token_held = true; + break; + } + q = read_C_connection(a, q, token); + } + if (p_end == 0) p->left = q; else p_end->right = q; + p_end = q; + } + } +} + +static struct node * C_style(struct analyser * a, char * s, int token) { + int i; + struct node * p = new_node(a, token); + for (i = 0; s[i] != 0; i++) switch(s[i]) { + case 'C': + p->left = read_C(a); continue; + case 'D': + p->aux = read_C(a); continue; + case 'A': + p->AE = read_AE(a, 0); continue; + case 'f': + get_token(a, c_for); continue; + case 'S': + { + int str_token = read_token(a->tokeniser); + if (str_token == c_name) name_to_node(a, p, 's'); else + if (str_token == c_literalstring) p->literalstring = new_literalstring(a); + else error(a, 2); + } + continue; + case 'b': + case 's': + case 'i': + if (get_token(a, c_name)) name_to_node(a, p, s[i]); + continue; + } + return p; +} + +static struct node * read_literalstring(struct analyser * a) { + struct node * p = new_node(a, c_literalstring); + p->literalstring = new_literalstring(a); + return p; +} + +static void reverse_b(symbol * b) { + int i = 0; int j = SIZE(b) - 1; + until (i >= j) { + int ch1 = b[i]; int ch2 = b[j]; + b[i++] = ch2; b[j--] = ch1; + } +} + +static int compare_amongvec(const void *pv, const void *qv) { + const struct amongvec * p = (const struct amongvec*)pv; + const struct amongvec * q = (const struct amongvec*)qv; + symbol * b_p = p->b; int p_size = p->size; + symbol * b_q = q->b; int q_size = q->size; + int smaller_size = p_size < q_size ? p_size : q_size; + int i; + for (i = 0; i < smaller_size; i++) + if (b_p[i] != b_q[i]) return b_p[i] - b_q[i]; + return p_size - q_size; +} + +static void make_among(struct analyser * a, struct node * p, struct node * substring) { + + NEW(among, x); + NEWVEC(amongvec, v, p->number); + struct node * q = p->left; + struct amongvec * w0 = v; + struct amongvec * w1 = v; + int result = 1; + + int direction = substring != 0 ? substring->mode : p->mode; + int backward = direction == m_backward; + + if (a->amongs == 0) a->amongs = x; else a->amongs_end->next = x; + a->amongs_end = x; + x->next = 0; + x->b = v; + x->number = a->among_count++; + x->starter = 0; + + if (q->type == c_bra) { x->starter = q; q = q->right; } + + until (q == 0) { + if (q->type == c_literalstring) { + symbol * b = q->literalstring; + w1->b = b; /* pointer to case string */ + w1->p = 0; /* pointer to corresponding case expression */ + w1->size = SIZE(b); /* number of characters in string */ + w1->i = -1; /* index of longest substring */ + w1->result = -1; /* number of corresponding case expression */ + w1->function = q->left == 0 ? 0 : q->left->name; + unless (w1->function == 0) + check_routine_mode(a, w1->function, direction); + w1++; + } + else + if (q->left == 0) /* empty command: () */ + w0 = w1; + else { + until (w0 == w1) { + w0->p = q; + w0->result = result; + w0++; + } + result++; + } + q = q->right; + } + unless (w1-v == p->number) { fprintf(stderr, "oh! %d %d\n", (int)(w1-v), p->number); exit(1); } + if (backward) for (w0 = v; w0 < w1; w0++) reverse_b(w0->b); + qsort(v, w1 - v, sizeof(struct amongvec), compare_amongvec); + + /* the following loop is O(n squared) */ + for (w0 = w1 - 1; w0 >= v; w0--) { + symbol * b = w0->b; + int size = w0->size; + struct amongvec * w; + + for (w = w0 - 1; w >= v; w--) { + if (w->size < size && memcmp(w->b, b, w->size * sizeof(symbol)) == 0) { + w0->i = w - v; /* fill in index of longest substring */ + break; + } + } + } + if (backward) for (w0 = v; w0 < w1; w0++) reverse_b(w0->b); + + for (w0 = v; w0 < w1 - 1; w0++) + if (w0->size == (w0 + 1)->size && + memcmp(w0->b, (w0 + 1)->b, w0->size * sizeof(symbol)) == 0) error3(a, p, w0->b); + + x->literalstring_count = p->number; + x->command_count = result - 1; + p->among = x; + + x->substring = substring; + if (substring != 0) substring->among = x; + unless (x->command_count == 0 && x->starter == 0) a->amongvar_needed = true; +} + +static struct node * read_among(struct analyser * a) { + struct tokeniser * t = a->tokeniser; + struct node * p = new_node(a, c_among); + struct node * p_end = 0; + int previous_token = -1; + struct node * substring = a->substring; + + a->substring = 0; + p->number = 0; /* counts the number of literals */ + unless (get_token(a, c_bra)) return p; + repeat { + struct node * q; + int token = read_token(t); + switch (token) { + case c_literalstring: + q = read_literalstring(a); + if (read_token(t) == c_name) { + struct node * r = new_node(a, c_name); + name_to_node(a, r, 'r'); + q->left = r; + } + else t->token_held = true; + p->number++; break; + case c_bra: + if (previous_token == c_bra) error(a, 19); + q = read_C_list(a); break; + default: + error(a, 3); + case c_ket: + if (p->number == 0) error(a, 18); + if (t->error_count == 0) make_among(a, p, substring); + return p; + } + previous_token = token; + if (p_end == 0) p->left = q; else p_end->right = q; + p_end = q; + } +} + +static struct node * read_substring(struct analyser * a) { + + struct node * p = new_node(a, c_substring); + if (a->substring != 0) error2(a, 20, a->substring->line_number); + a->substring = p; + return p; +} + +static void check_modifyable(struct analyser * a) { + unless (a->modifyable) error(a, 15); +} + +static struct node * read_C(struct analyser * a) { + struct tokeniser * t = a->tokeniser; + int token = read_token(t); + switch (token) { + case c_bra: + return read_C_list(a); + case c_backwards: + { + int mode = a->mode; + if (a->mode == m_backward) error(a, 17); else a->mode = m_backward; + { struct node * p = C_style(a, "C", token); + a->mode = mode; + return p; + } + } + case c_reverse: + { + int mode = a->mode; + int modifyable = a->modifyable; + a->modifyable = false; + a->mode = mode == m_forward ? m_backward : m_forward; + { + struct node * p = C_style(a, "C", token); + a->mode = mode; + a->modifyable = modifyable; + return p; + } + } + case c_not: + case c_try: + case c_fail: + case c_test: + case c_do: + case c_goto: + case c_gopast: + case c_repeat: + return C_style(a, "C", token); + case c_loop: + case c_atleast: + return C_style(a, "AC", token); + case c_setmark: + return C_style(a, "i", token); + case c_tomark: + case c_atmark: + case c_hop: + return C_style(a, "A", token); + case c_delete: + check_modifyable(a); + case c_next: + case c_tolimit: + case c_atlimit: + case c_leftslice: + case c_rightslice: + case c_true: + case c_false: + case c_debug: + return C_style(a, "", token); + case c_assignto: + case c_sliceto: + check_modifyable(a); + return C_style(a, "s", token); + case c_assign: + case c_insert: + case c_attach: + case c_slicefrom: + check_modifyable(a); + return C_style(a, "S", token); + case c_setlimit: + return C_style(a, "CfD", token); + case c_set: + case c_unset: + return C_style(a, "b", token); + case c_dollar: + get_token(a, c_name); + { + struct node * p; + struct name * q = find_name(a); + int mode = a->mode; + int modifyable = a->modifyable; + switch (q ? q->type : t_string) + /* above line was: switch (q->type) - bug #1 fix 7/2/2003 */ + { + default: error(a, 34); + case t_string: + a->mode = m_forward; + a->modifyable = true; + p = new_node(a, c_dollar); + p->left = read_C(a); break; + case t_integer: + /* a->mode = m_integer; */ + p = new_node(a, read_AE_test(a)); + p->AE = read_AE(a, 0); break; + } + p->name = q; + a->mode = mode; + a->modifyable = modifyable; + return p; + } + case c_name: + { + struct name * q = find_name(a); + struct node * p = new_node(a, c_name); + unless (q == 0) { + q->used = true; + switch (q->type) { + case t_boolean: + p->type = c_booltest; break; + case t_integer: + error(a, 35); /* integer name misplaced */ + case t_string: + break; + case t_routine: + case t_external: + p->type = c_call; + check_routine_mode(a, q, a->mode); + break; + case t_grouping: + p->type = c_grouping; break; + } + } + p->name = q; + return p; + } + case c_non: + { + struct node * p = new_node(a, token); + read_token(t); + if (t->token == c_minus) read_token(t); + unless (check_token(a, c_name)) { omission_error(a, c_name); return p; } + name_to_node(a, p, 'g'); + return p; + } + case c_literalstring: + return read_literalstring(a); + case c_among: return read_among(a); + case c_substring: return read_substring(a); + default: error(a, 1); return 0; + } +} + +static int next_symbol(symbol * p, symbol * W, int utf8) { + if (utf8) { + int ch; + int j = get_utf8(p, & ch); + W[0] = ch; return j; + } else { + W[0] = p[0]; return 1; + } +} + +static symbol * alter_grouping(symbol * p, symbol * q, int style, int utf8) { + int j = 0; + symbol W[1]; + int width; + if (style == c_plus) { + while (j < SIZE(q)) { + width = next_symbol(q + j, W, utf8); + p = add_to_b(p, 1, W); + j += width; + } + } else { + while (j < SIZE(q)) { + int i; + width = next_symbol(q + j, W, utf8); + for (i = 0; i < SIZE(p); i++) { + if (p[i] == W[0]) { + memmove(p + i, p + i + 1, (SIZE(p) - i - 1) * sizeof(symbol)); + SIZE(p)--; + } + } + j += width; + } + } + return p; +} + +static void read_define_grouping(struct analyser * a, struct name * q) { + struct tokeniser * t = a->tokeniser; + int style = c_plus; + { + NEW(grouping, p); + if (a->groupings == 0) a->groupings = p; else a->groupings_end->next = p; + a->groupings_end = p; + q->grouping = p; + p->next = 0; + p->name = q; + p->number = q->count; + p->b = create_b(0); + repeat { + switch (read_token(t)) { + case c_name: + { + struct name * r = find_name(a); + unless (r == 0) { + check_name_type(a, r, 'g'); + p->b = alter_grouping(p->b, r->grouping->b, style, false); + } + } + break; + case c_literalstring: + p->b = alter_grouping(p->b, t->b, style, a->utf8); + break; + default: error(a, 1); return; + } + switch (read_token(t)) { + case c_plus: + case c_minus: style = t->token; break; + default: goto label0; + } + } + label0: + { + int i; + int max = 0; + int min = 1<<16; + for (i = 0; i < SIZE(p->b); i++) { + if (p->b[i] > max) max = p->b[i]; + if (p->b[i] < min) min = p->b[i]; + } + p->largest_ch = max; + p->smallest_ch = min; + if (min == 1<<16) error(a, 16); + } + t->token_held = true; return; + } +} + +static void read_define_routine(struct analyser * a, struct name * q) { + struct node * p = new_node(a, c_define); + a->amongvar_needed = false; + unless (q == 0) { + check_name_type(a, q, 'R'); + if (q->definition != 0) error(a, 36); + if (q->mode < 0) q->mode = a->mode; else + if (q->mode != a->mode) error2(a, 32, q->mode); + } + p->name = q; + if (a->program == 0) a->program = p; else a->program_end->right = p; + a->program_end = p; + get_token(a, c_as); + p->left = read_C(a); + unless (q == 0) q->definition = p->left; + + if (a->substring != 0) { + error2(a, 14, a->substring->line_number); + a->substring = 0; + } + p->amongvar_needed = a->amongvar_needed; +} + +static void read_define(struct analyser * a) { + unless (get_token(a, c_name)) return; + { + struct name * q = find_name(a); + if (q != 0 && q->type == t_grouping) read_define_grouping(a, q); + else read_define_routine(a, q); + } +} + +static void read_backwardmode(struct analyser * a) { + int mode = a->mode; + a->mode = m_backward; + if (get_token(a, c_bra)) { + read_program_(a, c_ket); + check_token(a, c_ket); + } + a->mode = mode; +} + +static void read_program_(struct analyser * a, int terminator) { + struct tokeniser * t = a->tokeniser; + repeat { + switch (read_token(t)) { + case c_strings: read_names(a, t_string); break; + case c_booleans: read_names(a, t_boolean); break; + case c_integers: read_names(a, t_integer); break; + case c_routines: read_names(a, t_routine); break; + case c_externals: read_names(a, t_external); break; + case c_groupings: read_names(a, t_grouping); break; + case c_define: read_define(a); break; + case c_backwardmode:read_backwardmode(a); break; + case c_ket: + if (terminator == c_ket) return; + default: + error(a, 1); break; + case -1: + unless (terminator < 0) omission_error(a, c_ket); + return; + } + } +} + +extern void read_program(struct analyser * a) { + read_program_(a, -1); + { + struct name * q = a->names; + until (q == 0) { + switch(q->type) { + case t_external: case t_routine: + if (q->used && q->definition == 0) error4(a, q); break; + case t_grouping: + if (q->used && q->grouping == 0) error4(a, q); break; + } + q = q->next; + } + } + + if (a->tokeniser->error_count == 0) { + struct name * q = a->names; + int warned = false; + until (q == 0) { + unless (q->referenced) { + unless (warned) { + fprintf(stderr, "Declared but not used:"); + warned = true; + } + fprintf(stderr, " "); report_b(stderr, q->b); + } + q = q->next; + } + if (warned) fprintf(stderr, "\n"); + + q = a->names; + warned = false; + until (q == 0) { + if (! q->used && (q->type == t_routine || + q->type == t_grouping)) { + unless (warned) { + fprintf(stderr, "Declared and defined but not used:"); + warned = true; + } + fprintf(stderr, " "); report_b(stderr, q->b); + } + q = q->next; + } + if (warned) fprintf(stderr, "\n"); + } +} + +extern struct analyser * create_analyser(struct tokeniser * t) { + NEW(analyser, a); + a->tokeniser = t; + a->nodes = 0; + a->names = 0; + a->literalstrings = 0; + a->program = 0; + a->amongs = 0; + a->among_count = 0; + a->groupings = 0; + a->mode = m_forward; + a->modifyable = true; + { int i; for (i = 0; i < t_size; i++) a->name_count[i] = 0; } + a->substring = 0; + return a; +} + +extern void close_analyser(struct analyser * a) { + { + struct node * q = a->nodes; + until (q == 0) { + struct node * q_next = q->next; + FREE(q); + q = q_next; + } + } + { + struct name * q = a->names; + until (q == 0) { + struct name * q_next = q->next; + lose_b(q->b); FREE(q); + q = q_next; + } + } + { + struct literalstring * q = a->literalstrings; + until (q == 0) { + struct literalstring * q_next = q->next; + lose_b(q->b); FREE(q); + q = q_next; + } + } + { + struct among * q = a->amongs; + until (q == 0) { + struct among * q_next = q->next; + FREE(q->b); FREE(q); + q = q_next; + } + } + { + struct grouping * q = a->groupings; + until (q == 0) { + struct grouping * q_next = q->next; + lose_b(q->b); FREE(q); + q = q_next; + } + } + FREE(a); +} + diff --git a/contrib/snowball/compiler/driver.c b/contrib/snowball/compiler/driver.c new file mode 100644 index 000000000..fbb1e9cae --- /dev/null +++ b/contrib/snowball/compiler/driver.c @@ -0,0 +1,257 @@ +#include <stdio.h> /* for fprintf etc */ +#include <stdlib.h> /* for free etc */ +#include <string.h> /* for strlen */ +#include "header.h" + +#define DEFAULT_PACKAGE "org.tartarus.snowball.ext" +#define DEFAULT_BASE_CLASS "org.tartarus.snowball.SnowballProgram" +#define DEFAULT_AMONG_CLASS "org.tartarus.snowball.Among" +#define DEFAULT_STRING_CLASS "java.lang.StringBuilder" + +static int eq(const char * s1, const char * s2) { + int s1_len = strlen(s1); + int s2_len = strlen(s2); + return s1_len == s2_len && memcmp(s1, s2, s1_len) == 0; +} + +static void print_arglist(void) { + fprintf(stderr, "Usage: snowball <file> [options]\n\n" + "options are: [-o[utput] file]\n" + " [-s[yntax]]\n" +#ifndef DISABLE_JAVA + " [-j[ava]]\n" +#endif + " [-c++]\n" + " [-w[idechars]]\n" + " [-u[tf8]]\n" + " [-n[ame] class name]\n" + " [-ep[refix] string]\n" + " [-vp[refix] string]\n" + " [-i[nclude] directory]\n" + " [-r[untime] path to runtime headers]\n" +#ifndef DISABLE_JAVA + " [-p[arentclassname] fully qualified parent class name]\n" + " [-P[ackage] package name for stemmers]\n" + " [-S[tringclass] StringBuffer-compatible class]\n" + " [-a[mongclass] fully qualified name of the Among class]\n" +#endif + ); + exit(1); +} + +static void check_lim(int i, int argc) { + if (i >= argc) { + fprintf(stderr, "argument list is one short\n"); + print_arglist(); + } +} + +static FILE * get_output(symbol * b) { + char * s = b_to_s(b); + FILE * output = fopen(s, "w"); + if (output == 0) { + fprintf(stderr, "Can't open output %s\n", s); + exit(1); + } + free(s); + return output; +} + +static void read_options(struct options * o, int argc, char * argv[]) { + char * s; + int i = 2; + + /* set defaults: */ + + o->output_file = 0; + o->syntax_tree = false; + o->externals_prefix = ""; + o->variables_prefix = 0; + o->runtime_path = 0; + o->parent_class_name = DEFAULT_BASE_CLASS; + o->string_class = DEFAULT_STRING_CLASS; + o->among_class = DEFAULT_AMONG_CLASS; + o->package = DEFAULT_PACKAGE; + o->name = ""; + o->make_lang = LANG_C; + o->widechars = false; + o->includes = 0; + o->includes_end = 0; + o->utf8 = false; + + /* read options: */ + + repeat { + if (i >= argc) break; + s = argv[i++]; + { if (eq(s, "-o") || eq(s, "-output")) { + check_lim(i, argc); + o->output_file = argv[i++]; + continue; + } + if (eq(s, "-n") || eq(s, "-name")) { + check_lim(i, argc); + o->name = argv[i++]; + continue; + } +#ifndef DISABLE_JAVA + if (eq(s, "-j") || eq(s, "-java")) { + o->make_lang = LANG_JAVA; + o->widechars = true; + continue; + } +#endif + if (eq(s, "-c++")) { + o->make_lang = LANG_CPLUSPLUS; + continue; + } + if (eq(s, "-w") || eq(s, "-widechars")) { + o->widechars = true; + o->utf8 = false; + continue; + } + if (eq(s, "-s") || eq(s, "-syntax")) { + o->syntax_tree = true; + continue; + } + if (eq(s, "-ep") || eq(s, "-eprefix")) { + check_lim(i, argc); + o->externals_prefix = argv[i++]; + continue; + } + if (eq(s, "-vp") || eq(s, "-vprefix")) { + check_lim(i, argc); + o->variables_prefix = argv[i++]; + continue; + } + if (eq(s, "-i") || eq(s, "-include")) { + check_lim(i, argc); + + { + NEW(include, p); + symbol * b = add_s_to_b(0, argv[i++]); + b = add_s_to_b(b, "/"); + p->next = 0; p->b = b; + + if (o->includes == 0) o->includes = p; else + o->includes_end->next = p; + o->includes_end = p; + } + continue; + } + if (eq(s, "-r") || eq(s, "-runtime")) { + check_lim(i, argc); + o->runtime_path = argv[i++]; + continue; + } + if (eq(s, "-u") || eq(s, "-utf8")) { + o->utf8 = true; + o->widechars = false; + continue; + } +#ifndef DISABLE_JAVA + if (eq(s, "-p") || eq(s, "-parentclassname")) { + check_lim(i, argc); + o->parent_class_name = argv[i++]; + continue; + } + if (eq(s, "-P") || eq(s, "-Package")) { + check_lim(i, argc); + o->package = argv[i++]; + continue; + } + if (eq(s, "-S") || eq(s, "-stringclass")) { + check_lim(i, argc); + o->string_class = argv[i++]; + continue; + } + if (eq(s, "-a") || eq(s, "-amongclass")) { + check_lim(i, argc); + o->among_class = argv[i++]; + continue; + } +#endif + fprintf(stderr, "'%s' misplaced\n", s); + print_arglist(); + } + } +} + +extern int main(int argc, char * argv[]) { + + NEW(options, o); + if (argc == 1) print_arglist(); + read_options(o, argc, argv); + { + symbol * filename = add_s_to_b(0, argv[1]); + char * file; + symbol * u = get_input(filename, &file); + if (u == 0) { + fprintf(stderr, "Can't open input %s\n", argv[1]); + exit(1); + } + { + struct tokeniser * t = create_tokeniser(u, file); + struct analyser * a = create_analyser(t); + t->widechars = o->widechars; + t->includes = o->includes; + a->utf8 = t->utf8 = o->utf8; + read_program(a); + if (t->error_count > 0) exit(1); + if (o->syntax_tree) print_program(a); + close_tokeniser(t); + unless (o->syntax_tree) { + struct generator * g; + + char * s = o->output_file; + unless (s) { + fprintf(stderr, "Please include the -o option\n"); + print_arglist(); + exit(1); + } + if (o->make_lang == LANG_C || o->make_lang == LANG_CPLUSPLUS) { + symbol * b = add_s_to_b(0, s); + b = add_s_to_b(b, ".h"); + o->output_h = get_output(b); + b[SIZE(b) - 1] = 'c'; + if (o->make_lang == LANG_CPLUSPLUS) { + b = add_s_to_b(b, "c"); + } + o->output_c = get_output(b); + lose_b(b); + + g = create_generator_c(a, o); + generate_program_c(g); + close_generator_c(g); + fclose(o->output_c); + fclose(o->output_h); + } +#ifndef DISABLE_JAVA + if (o->make_lang == LANG_JAVA) { + symbol * b = add_s_to_b(0, s); + b = add_s_to_b(b, ".java"); + o->output_java = get_output(b); + lose_b(b); + g = create_generator_java(a, o); + generate_program_java(g); + close_generator_java(g); + fclose(o->output_java); + } +#endif + } + close_analyser(a); + } + lose_b(u); + lose_b(filename); + } + { struct include * p = o->includes; + until (p == 0) + { struct include * q = p->next; + lose_b(p->b); FREE(p); p = q; + } + } + FREE(o); + unless (space_count == 0) fprintf(stderr, "%d blocks unfreed\n", space_count); + return 0; +} + diff --git a/contrib/snowball/compiler/generator.c b/contrib/snowball/compiler/generator.c new file mode 100644 index 000000000..7294b0471 --- /dev/null +++ b/contrib/snowball/compiler/generator.c @@ -0,0 +1,1465 @@ + +#include <limits.h> /* for INT_MAX */ +#include <stdio.h> /* for fprintf etc */ +#include <stdlib.h> /* for free etc */ +#include <string.h> /* for strlen */ +#include "header.h" + +/* Define this to get warning messages when optimisations can't be used. */ +/* #define OPTIMISATION_WARNINGS */ + +/* recursive use: */ + +static void generate(struct generator * g, struct node * p); + +enum special_labels { + + x_return = -1 + +}; + +static int new_label(struct generator * g) { + return g->next_label++; +} + +/* Output routines */ +static void output_str(FILE * outfile, struct str * str) { + + char * s = b_to_s(str_data(str)); + fprintf(outfile, "%s", s); + free(s); +} + +static void wch(struct generator * g, int ch) { + str_append_ch(g->outbuf, ch); /* character */ +} + +static void wnl(struct generator * g) { + str_append_ch(g->outbuf, '\n'); /* newline */ + g->line_count++; +} + +static void ws(struct generator * g, const char * s) { + str_append_string(g->outbuf, s); /* string */ +} + +static void wi(struct generator * g, int i) { + str_append_int(g->outbuf, i); /* integer */ +} + +static void wh_ch(struct generator * g, int i) { + str_append_ch(g->outbuf, "0123456789ABCDEF"[i & 0xF]); /* hexchar */ +} + +static void wh(struct generator * g, int i) { + if (i >> 4) wh(g, i >> 4); + wh_ch(g, i); /* hex integer */ +} + +static void wi3(struct generator * g, int i) { + if (i < 100) wch(g, ' '); + if (i < 10) wch(g, ' '); + wi(g, i); /* integer (width 3) */ +} + +static void wvn(struct generator * g, struct name * p) { /* variable name */ + + int ch = "SBIrxg"[p->type]; + switch (p->type) { + case t_string: + case t_boolean: + case t_integer: + wch(g, ch); wch(g, '['); wi(g, p->count); wch(g, ']'); return; + case t_external: + ws(g, g->options->externals_prefix); break; + default: + wch(g, ch); wch(g, '_'); + } + str_append_b(g->outbuf, p->b); +} + +static void wv(struct generator * g, struct name * p) { /* reference to variable */ + if (p->type < t_routine) ws(g, "z->"); + wvn(g, p); +} + +static void wlitarray(struct generator * g, symbol * p) { /* write literal array */ + + ws(g, "{ "); + { + int i; + for (i = 0; i < SIZE(p); i++) { + int ch = p[i]; + if (32 <= ch && ch < 127) { + wch(g, '\''); + switch (ch) { + case '\'': + case '\\': wch(g, '\\'); + default: wch(g, ch); + } + wch(g, '\''); + } else { + wch(g, '0'); wch(g, 'x'); wh(g, ch); + } + if (i < SIZE(p) - 1) ws(g, ", "); + } + } + ws(g, " }"); +} + +static void wlitref(struct generator * g, symbol * p) { /* write ref to literal array */ + + if (SIZE(p) == 0) ws(g, "0"); else { + struct str * s = g->outbuf; + g->outbuf = g->declarations; + ws(g, "static const symbol s_"); wi(g, g->literalstring_count); ws(g, "[] = "); + wlitarray(g, p); + ws(g, ";\n"); + g->outbuf = s; + ws(g, "s_"); wi(g, g->literalstring_count); + g->literalstring_count++; + } +} + + +static void wm(struct generator * g) { /* margin */ + int i; + for (i = 0; i < g->margin; i++) ws(g, " "); +} + +static void wc(struct generator * g, struct node * p) { /* comment */ + + ws(g, " /* "); + switch (p->type) { + case c_mathassign: + case c_plusassign: + case c_minusassign: + case c_multiplyassign: + case c_divideassign: + case c_eq: + case c_ne: + case c_gr: + case c_ge: + case c_ls: + case c_le: + if (p->name) { + wch(g, '$'); + str_append_b(g->outbuf, p->name->b); + wch(g, ' '); + } + ws(g, name_of_token(p->type)); + ws(g, " <integer expression>"); + break; + default: + ws(g, name_of_token(p->type)); + if (p->name) { + wch(g, ' '); + str_append_b(g->outbuf, p->name->b); + } + } + ws(g, ", line "); wi(g, p->line_number); ws(g, " */"); + wnl(g); +} + +static void wms(struct generator * g, const char * s) { + wm(g); ws(g, s); } /* margin + string */ + +static void wbs(struct generator * g) { /* block start */ + wms(g, "{ "); + g->margin++; +} + +static void wbe(struct generator * g) { /* block end */ + + if (g->line_labelled == g->line_count) { wms(g, ";"); wnl(g); } + g->margin--; + wms(g, "}"); wnl(g); +} + +static void wk(struct generator * g, struct node * p) { /* keep c */ + ++g->keep_count; + if (p->mode == m_forward) { + ws(g, "int c"); wi(g, g->keep_count); ws(g, " = z->c;"); + } else { + ws(g, "int m"); wi(g, g->keep_count); ws(g, " = z->l - z->c; (void)m"); + wi(g, g->keep_count); ws(g, ";"); + } +} + +static void wrestore(struct generator * g, struct node * p, int keep_token) { /* restore c */ + if (p->mode == m_forward) { + ws(g, "z->c = c"); + } else { + ws(g, "z->c = z->l - m"); + } + wi(g, keep_token); ws(g, ";"); +} + +static void winc(struct generator * g, struct node * p) { /* increment c */ + ws(g, p->mode == m_forward ? "z->c++;" : + "z->c--;"); +} + +static void wsetl(struct generator * g, int n) { + + g->margin--; + wms(g, "lab"); wi(g, n); wch(g, ':'); wnl(g); + g->line_labelled = g->line_count; + g->margin++; +} + +static void wgotol(struct generator * g, int n) { + wms(g, "goto lab"); wi(g, n); wch(g, ';'); wnl(g); +} + +static void wf(struct generator * g) { /* fail */ + if (g->failure_string != 0) { ws(g, "{ "); ws(g, g->failure_string); wch(g, ' '); } + switch (g->failure_label) + { + case x_return: + ws(g, "return 0;"); + break; + default: + ws(g, "goto lab"); + wi(g, g->failure_label); + wch(g, ';'); + g->label_used = 1; + } + if (g->failure_string != 0) ws(g, " }"); +} + +static void wlim(struct generator * g, struct node * p) { /* if at limit fail */ + + ws(g, p->mode == m_forward ? "if (z->c >= z->l) " : + "if (z->c <= z->lb) "); + wf(g); +} + +static void wp(struct generator * g, const char * s, struct node * p) { /* formatted write */ + int i = 0; + int l = strlen(s); + until (i >= l) { + int ch = s[i++]; + if (ch != '~') wch(g, ch); else + switch(s[i++]) { + default: wch(g, s[i - 1]); continue; + case 'C': wc(g, p); continue; + case 'k': wk(g, p); continue; + case 'K': /* keep for c_test */ + ws(g, p->mode == m_forward ? "int c_test = z->c;" : + "int m_test = z->l - z->c;"); + continue; + case 'R': /* restore for c_test */ + ws(g, p->mode == m_forward ? "z->c = c_test;" : + "z->c = z->l - m_test;"); + continue; + case 'i': winc(g, p); continue; + case 'l': wlim(g, p); continue; + case 'f': wf(g); continue; + case 'M': wm(g); continue; + case 'N': wnl(g); continue; + case '{': wbs(g); continue; + case '}': wbe(g); continue; + case 'S': ws(g, g->S[s[i++] - '0']); continue; + case 'I': wi(g, g->I[s[i++] - '0']); continue; + case 'J': wi3(g, g->I[s[i++] - '0']); continue; + case 'V': wv(g, g->V[s[i++] - '0']); continue; + case 'W': wvn(g, g->V[s[i++] - '0']); continue; + case 'L': wlitref(g, g->L[s[i++] - '0']); continue; + case 'A': wlitarray(g, g->L[s[i++] - '0']); continue; + case '+': g->margin++; continue; + case '-': g->margin--; continue; + case '$': /* insert_s, insert_v etc */ + wch(g, p->literalstring == 0 ? 'v' : 's'); + continue; + case 'p': ws(g, g->options->externals_prefix); continue; + } + } +} + +static void w(struct generator * g, const char * s) { wp(g, s, 0); } + +static void generate_AE(struct generator * g, struct node * p) { + char * s; + switch (p->type) { + case c_name: + wv(g, p->name); break; + case c_number: + wi(g, p->number); break; + case c_maxint: + ws(g, "MAXINT"); break; + case c_minint: + ws(g, "MININT"); break; + case c_neg: + wch(g, '-'); generate_AE(g, p->right); break; + case c_multiply: + s = " * "; goto label0; + case c_plus: + s = " + "; goto label0; + case c_minus: + s = " - "; goto label0; + case c_divide: + s = " / "; + label0: + wch(g, '('); generate_AE(g, p->left); + ws(g, s); generate_AE(g, p->right); wch(g, ')'); break; + case c_sizeof: + g->V[0] = p->name; + w(g, "SIZE(~V0)"); break; + case c_cursor: + w(g, "z->c"); break; + case c_limit: + w(g, p->mode == m_forward ? "z->l" : "z->lb"); break; + case c_size: + w(g, "SIZE(z->p)"); break; + } +} + +/* K_needed() tests to see if we really need to keep c. Not true when the + the command does not touch the cursor. This and repeat_score() could be + elaborated almost indefinitely. +*/ + +static int K_needed(struct generator * g, struct node * p) { + until (p == 0) { + switch (p->type) { + case c_dollar: + case c_leftslice: + case c_rightslice: + case c_mathassign: + case c_plusassign: + case c_minusassign: + case c_multiplyassign: + case c_divideassign: + case c_eq: + case c_ne: + case c_gr: + case c_ge: + case c_ls: + case c_le: + case c_sliceto: + case c_true: + case c_false: + case c_debug: + break; + + case c_call: + if (K_needed(g, p->name->definition)) return true; + break; + + case c_bra: + if (K_needed(g, p->left)) return true; + break; + + default: return true; + } + p = p->right; + } + return false; +} + +static int repeat_score(struct generator * g, struct node * p) { + int score = 0; + until (p == 0) + { + switch (p->type) { + case c_dollar: + case c_leftslice: + case c_rightslice: + case c_mathassign: + case c_plusassign: + case c_minusassign: + case c_multiplyassign: + case c_divideassign: + case c_eq: + case c_ne: + case c_gr: + case c_ge: + case c_ls: + case c_le: + case c_sliceto: /* case c_not: must not be included here! */ + case c_debug: + break; + + case c_call: + score += repeat_score(g, p->name->definition); + break; + + case c_bra: + score += repeat_score(g, p->left); + break; + + case c_name: + case c_literalstring: + case c_next: + case c_grouping: + case c_non: + case c_hop: + score = score + 1; break; + + default: score = 2; break; + } + p = p->right; + } + return score; +} + +/* tests if an expression requires cursor reinstatement in a repeat */ + +static int repeat_restore(struct generator * g, struct node * p) { + return repeat_score(g, p) >= 2; +} + +static void generate_bra(struct generator * g, struct node * p) { + p = p->left; + until (p == 0) { generate(g, p); p = p->right; } +} + +static void generate_and(struct generator * g, struct node * p) { + int keep_c = 0; + if (K_needed(g, p->left)) { + wp(g, "~{~k~C", p); + keep_c = g->keep_count; + } else { + wp(g, "~M~C", p); + } + p = p->left; + until (p == 0) { + generate(g, p); + if (keep_c && p->right != 0) { + w(g, "~M"); wrestore(g, p, keep_c); w(g, "~N"); + } + p = p->right; + } + if (keep_c) w(g, "~}"); +} + +static void generate_or(struct generator * g, struct node * p) { + int keep_c = 0; + + int used = g->label_used; + int a0 = g->failure_label; + const char * a1 = g->failure_string; + + int out_lab = new_label(g); + + if (K_needed(g, p->left)) { + wp(g, "~{~k~C", p); + keep_c = g->keep_count; + } else { + wp(g, "~M~C", p); + } + p = p->left; + g->failure_string = 0; + until (p->right == 0) { + g->failure_label = new_label(g); + g->label_used = 0; + generate(g, p); + wgotol(g, out_lab); + if (g->label_used) + wsetl(g, g->failure_label); + if (keep_c) { + w(g, "~M"); wrestore(g, p, keep_c); w(g, "~N"); + } + p = p->right; + } + g->label_used = used; + g->failure_label = a0; + g->failure_string = a1; + + generate(g, p); + if (keep_c) w(g, "~}"); + wsetl(g, out_lab); +} + +static void generate_backwards(struct generator * g, struct node * p) { + + wp(g,"~Mz->lb = z->c; z->c = z->l;~C~N", p); + generate(g, p->left); + w(g, "~Mz->c = z->lb;~N"); +} + + +static void generate_not(struct generator * g, struct node * p) { + int keep_c = 0; + + int used = g->label_used; + int a0 = g->failure_label; + const char * a1 = g->failure_string; + + if (K_needed(g, p->left)) { + wp(g, "~{~k~C", p); + keep_c = g->keep_count; + } else { + wp(g, "~M~C", p); + } + + g->failure_label = new_label(g); + g->label_used = 0; + g->failure_string = 0; + generate(g, p->left); + + { + int l = g->failure_label; + int u = g->label_used; + + g->label_used = used; + g->failure_label = a0; + g->failure_string = a1; + + w(g, "~M~f~N"); + if (u) + wsetl(g, l); + } + if (keep_c) { + w(g, "~M"); wrestore(g, p, keep_c); w(g, "~N~}"); + } +} + + +static void generate_try(struct generator * g, struct node * p) { + int keep_c = K_needed(g, p->left); + + if (keep_c) { + if (p->mode == m_forward) { + wp(g, "~{int c_keep = z->c;~C", p); + g->failure_string = "z->c = c_keep;"; + } else { + wp(g, "~{int m_keep = z->l - z->c;/* (void) m_keep;*/~C", p); + g->failure_string = "z->c = z->l - m_keep;"; + } + } else { + wp(g, "~M~C", p); + g->failure_string = 0; + } + + g->failure_label = new_label(g); + g->label_used = 0; + generate(g, p->left); + + if (g->label_used) + wsetl(g, g->failure_label); + + if (keep_c) w(g, "~}"); +} + +static void generate_set(struct generator * g, struct node * p) { + g->V[0] = p->name; wp(g, "~M~V0 = 1;~C", p); +} + +static void generate_unset(struct generator * g, struct node * p) { + g->V[0] = p->name; wp(g, "~M~V0 = 0;~C", p); +} + +static void generate_fail(struct generator * g, struct node * p) { + generate(g, p->left); + wp(g, "~M~f~C", p); +} + +/* generate_test() also implements 'reverse' */ + +static void generate_test(struct generator * g, struct node * p) { + int keep_c = K_needed(g, p->left); + if (keep_c) wp(g, "~{~K~C", p); + else wp(g, "~M~C", p); + + generate(g, p->left); + + if (keep_c) wp(g, "~M~R~N" + "~}", p); +} + +static void generate_do(struct generator * g, struct node * p) { + int keep_c = 0; + if (K_needed(g, p->left)) { + wp(g, "~{~k~C", p); + keep_c = g->keep_count; + } else { + wp(g, "~M~C", p); + } + + g->failure_label = new_label(g); + g->label_used = 0; + g->failure_string = 0; + generate(g, p->left); + + if (g->label_used) + wsetl(g, g->failure_label); + if (keep_c) { + w(g, "~M"); wrestore(g, p, keep_c); + w(g, "~N~}"); + } +} + +static void generate_next(struct generator * g, struct node * p) { + if (g->options->utf8) { + if (p->mode == m_forward) + w(g, "~{int ret = skip_utf8(z->p, z->c, 0, z->l, 1"); + else + w(g, "~{int ret = skip_utf8(z->p, z->c, z->lb, 0, -1"); + wp(g, ");~N" + "~Mif (ret < 0) ~f~N" + "~Mz->c = ret;~C" + "~}", p); + } else + wp(g, "~M~l~N" + "~M~i~C", p); +} + +static void generate_GO_grouping(struct generator * g, struct node * p, int is_goto, int complement) { + + struct grouping * q = p->name->grouping; + g->S[0] = p->mode == m_forward ? "" : "_b"; + g->S[1] = complement ? "in" : "out"; + g->S[2] = g->options->utf8 ? "_U" : ""; + g->V[0] = p->name; + g->I[0] = q->smallest_ch; + g->I[1] = q->largest_ch; + if (is_goto) { + wp(g, "~Mif (~S1_grouping~S0~S2(z, ~V0, ~I0, ~I1, 1) < 0) ~f /* goto */~C", p); + } else { + wp(g, "~{ /* gopast */~C" + "~Mint ret = ~S1_grouping~S0~S2(z, ~V0, ~I0, ~I1, 1);~N" + "~Mif (ret < 0) ~f~N", p); + if (p->mode == m_forward) + w(g, "~Mz->c += ret;~N"); + else + w(g, "~Mz->c -= ret;~N"); + w(g, "~}"); + } +} + +static void generate_GO(struct generator * g, struct node * p, int style) { + int keep_c = 0; + + int used = g->label_used; + int a0 = g->failure_label; + const char * a1 = g->failure_string; + + if (p->left->type == c_grouping || p->left->type == c_non) { + /* Special case for "goto" or "gopast" when used on a grouping or an + * inverted grouping - the movement of c by the matching action is + * exactly what we want! */ +#ifdef OPTIMISATION_WARNINGS + printf("Optimising %s %s\n", style ? "goto" : "gopast", p->left->type == c_non ? "non" : "grouping"); +#endif + generate_GO_grouping(g, p->left, style, p->left->type == c_non); + return; + } + + w(g, "~Mwhile(1) {"); wp(g, "~C~+", p); + + if (style == 1 || repeat_restore(g, p->left)) { + wp(g, "~M~k~N", p); + keep_c = g->keep_count; + } + + g->failure_label = new_label(g); + g->label_used = 0; + generate(g, p->left); + + if (style == 1) { + /* include for goto; omit for gopast */ + w(g, "~M"); wrestore(g, p, keep_c); w(g, "~N"); + } + w(g, "~Mbreak;~N"); + if (g->label_used) + wsetl(g, g->failure_label); + if (keep_c) { + w(g, "~M"); wrestore(g, p, keep_c); w(g, "~N"); + } + + g->label_used = used; + g->failure_label = a0; + g->failure_string = a1; + +/* wp(g, "~M~l~N" + "~M~i~N", p); */ + generate_next(g, p); + w(g, "~}"); +} + +static void generate_loop(struct generator * g, struct node * p) { + w(g, "~{int i; for (i = "); generate_AE(g, p->AE); wp(g, "; i > 0; i--)~C" + "~{", p); + + generate(g, p->left); + + w(g, "~}" + "~}"); +} + +static void generate_repeat(struct generator * g, struct node * p, int atleast_case) { + int keep_c = 0; + wp(g, "~Mwhile(1) {~C~+", p); + + if (repeat_restore(g, p->left)) { + wp(g, "~M~k~N", p); + keep_c = g->keep_count; + } + + g->failure_label = new_label(g); + g->label_used = 0; + g->failure_string = 0; + generate(g, p->left); + + if (atleast_case) w(g, "~Mi--;~N"); + + w(g, "~Mcontinue;~N"); + if (g->label_used) + wsetl(g, g->failure_label); + + if (keep_c) { + w(g, "~M"); wrestore(g, p, keep_c); w(g, "~N"); + } + + w(g, "~Mbreak;~N" + "~}"); +} + +static void generate_atleast(struct generator * g, struct node * p) { + w(g, "~{int i = "); generate_AE(g, p->AE); w(g, ";~N"); + { + int used = g->label_used; + int a0 = g->failure_label; + const char * a1 = g->failure_string; + + generate_repeat(g, p, true); + + g->label_used = used; + g->failure_label = a0; + g->failure_string = a1; + } + w(g, "~Mif (i > 0) ~f~N" + "~}"); +} + +static void generate_setmark(struct generator * g, struct node * p) { + g->V[0] = p->name; + wp(g, "~M~V0 = z->c;~C", p); +} + +static void generate_tomark(struct generator * g, struct node * p) { + g->S[0] = p->mode == m_forward ? ">" : "<"; + + w(g, "~Mif (z->c ~S0 "); generate_AE(g, p->AE); w(g, ") ~f~N"); + w(g, "~Mz->c = "); generate_AE(g, p->AE); wp(g, ";~C", p); +} + +static void generate_atmark(struct generator * g, struct node * p) { + + w(g, "~Mif (z->c != "); generate_AE(g, p->AE); wp(g, ") ~f~C", p); +} + +static void generate_hop(struct generator * g, struct node * p) { + g->S[0] = p->mode == m_forward ? "+" : "-"; + g->S[1] = p->mode == m_forward ? "0" : "z->lb"; + if (g->options->utf8) { + w(g, "~{int ret = skip_utf8(z->p, z->c, ~S1, z->l, ~S0 "); + generate_AE(g, p->AE); wp(g, ");~C", p); + w(g, "~Mif (ret < 0) ~f~N"); + } else { + w(g, "~{int ret = z->c ~S0 "); + generate_AE(g, p->AE); wp(g, ";~C", p); + w(g, "~Mif (~S1 > ret || ret > z->l) ~f~N"); + } + wp(g, "~Mz->c = ret;~C" + "~}", p); +} + +static void generate_delete(struct generator * g, struct node * p) { + wp(g, "~{int ret = slice_del(z);~C", p); + wp(g, "~Mif (ret < 0) return ret;~N" + "~}", p); +} + +static void generate_tolimit(struct generator * g, struct node * p) { + g->S[0] = p->mode == m_forward ? "" : "b"; + wp(g, "~Mz->c = z->l~S0;~C", p); +} + +static void generate_atlimit(struct generator * g, struct node * p) { + g->S[0] = p->mode == m_forward ? "" : "b"; + g->S[1] = p->mode == m_forward ? "<" : ">"; + wp(g, "~Mif (z->c ~S1 z->l~S0) ~f~C", p); +} + +static void generate_leftslice(struct generator * g, struct node * p) { + g->S[0] = p->mode == m_forward ? "bra" : "ket"; + wp(g, "~Mz->~S0 = z->c;~C", p); +} + +static void generate_rightslice(struct generator * g, struct node * p) { + g->S[0] = p->mode == m_forward ? "ket" : "bra"; + wp(g, "~Mz->~S0 = z->c;~C", p); +} + +static void generate_assignto(struct generator * g, struct node * p) { + g->V[0] = p->name; + wp(g, "~M~V0 = assign_to(z, ~V0);~C" + "~Mif (~V0 == 0) return -1;~C", p); +} + +static void generate_sliceto(struct generator * g, struct node * p) { + g->V[0] = p->name; + wp(g, "~M~V0 = slice_to(z, ~V0);~C" + "~Mif (~V0 == 0) return -1;~C", p); +} + +static void generate_data_address(struct generator * g, struct node * p) { + + symbol * b = p->literalstring; + if (b != 0) { + wi(g, SIZE(b)); w(g, ", "); + wlitref(g, b); + } else + wv(g, p->name); +} + +static void generate_insert(struct generator * g, struct node * p, int style) { + + int keep_c = style == c_attach; + if (p->mode == m_backward) keep_c = !keep_c; + wp(g, "~{", p); + if (keep_c) w(g, "int c_keep = z->c;~N~M"); + wp(g, "int ret = insert_~$(z, z->c, z->c, ", p); + generate_data_address(g, p); + wp(g, ");~C", p); + if (keep_c) w(g, "~Mz->c = c_keep;~N"); + wp(g, "~Mif (ret < 0) return ret;~N" + "~}", p); +} + +static void generate_assignfrom(struct generator * g, struct node * p) { + + int keep_c = p->mode == m_forward; /* like 'attach' */ + wp(g, "~{", p); + if (keep_c) wp(g, "int c_keep = z->c;~N" + "~Mret = insert_~$(z, z->c, z->l, ", p); + else wp(g, "ret = insert_~$(z, z->lb, z->c, ", p); + generate_data_address(g, p); + wp(g, ");~C", p); + if (keep_c) w(g, "~Mz->c = c_keep;~N"); + wp(g, "~Mif (ret < 0) return ret;~N" + "~}", p); +} + +/* bugs marked <======= fixed 22/7/02. Similar fixes required for Java */ + +static void generate_slicefrom(struct generator * g, struct node * p) { + +/* w(g, "~Mslice_from_s(z, "); <============= bug! should be: */ + wp(g, "~{int ret = slice_from_~$(z, ", p); + generate_data_address(g, p); + wp(g, ");~C", p); + wp(g, "~Mif (ret < 0) return ret;~N" + "~}", p); +} + +static void generate_setlimit(struct generator * g, struct node * p) { + int keep_c; + wp(g, "~{int mlimit;~C" + "~M~k~N" + , p); + keep_c = g->keep_count; + generate(g, p->left); + if (p->mode == m_forward) w(g, "~Mmlimit = z->l - z->c; z->l = z->c;~N"); + else w(g, "~Mmlimit = z->lb; z->lb = z->c;~N"); + w(g, "~M"); wrestore(g, p, keep_c); w(g, "~N"); + g->failure_string = p->mode == m_forward ? "z->l += mlimit;" : + "z->lb = mlimit;"; + generate(g, p->aux); + wms(g, g->failure_string); + w(g, "~N" + "~}"); +} + +static void generate_dollar(struct generator * g, struct node * p) { + + int used = g->label_used; + int a0 = g->failure_label; + const char * a1 = g->failure_string; + g->failure_label = new_label(g); + g->label_used = 0; + g->failure_string = 0; + + g->V[0] = p->name; + wp(g, "~{struct SN_env env = * z;~C" + "~Mint failure = 1; /* assume failure */~N" + "~Mz->p = ~V0;~N" + "~Mz->lb = z->c = 0;~N" + "~Mz->l = SIZE(z->p);~N", p); + generate(g, p->left); + w(g, "~Mfailure = 0; /* mark success */~N"); + if (g->label_used) + wsetl(g, g->failure_label); + g->V[0] = p->name; /* necessary */ + + g->label_used = used; + g->failure_label = a0; + g->failure_string = a1; + + w(g, "~M~V0 = z->p;~N" + "~M* z = env;~N" + "~Mif (failure) ~f~N~}"); +} + +static void generate_integer_assign(struct generator * g, struct node * p, char * s) { + + g->V[0] = p->name; + g->S[0] = s; + w(g, "~M~V0 ~S0 "); generate_AE(g, p->AE); wp(g, ";~C", p); +} + +static void generate_integer_test(struct generator * g, struct node * p, char * s) { + + g->V[0] = p->name; + g->S[0] = s; + w(g, "~Mif (!(~V0 ~S0 "); generate_AE(g, p->AE); wp(g, ")) ~f~C", p); +} + +static void generate_call(struct generator * g, struct node * p) { + + g->V[0] = p->name; + wp(g, "~{int ret = ~V0(z);~C" + "~Mif (ret == 0) ~f~N" + "~Mif (ret < 0) return ret;~N~}", p); +} + +static void generate_grouping(struct generator * g, struct node * p, int complement) { + + struct grouping * q = p->name->grouping; + g->S[0] = p->mode == m_forward ? "" : "_b"; + g->S[1] = complement ? "out" : "in"; + g->S[2] = g->options->utf8 ? "_U" : ""; + g->V[0] = p->name; + g->I[0] = q->smallest_ch; + g->I[1] = q->largest_ch; + wp(g, "~Mif (~S1_grouping~S0~S2(z, ~V0, ~I0, ~I1, 0)) ~f~C", p); +} + +static void generate_namedstring(struct generator * g, struct node * p) { + + g->S[0] = p->mode == m_forward ? "" : "_b"; + g->V[0] = p->name; + wp(g, "~Mif (!(eq_v~S0(z, ~V0))) ~f~C", p); +} + +static void generate_literalstring(struct generator * g, struct node * p) { + symbol * b = p->literalstring; + g->S[0] = p->mode == m_forward ? "" : "_b"; + g->I[0] = SIZE(b); + g->L[0] = b; + + wp(g, "~Mif (!(eq_s~S0(z, ~I0, ~L0))) ~f~C", p); +} + +static void generate_define(struct generator * g, struct node * p) { + struct name * q = p->name; + g->next_label = 0; + + g->S[0] = q->type == t_routine ? "static" : "extern"; + g->V[0] = q; + + w(g, "~N~S0 int ~V0(struct SN_env * z) {~N~+"); + if (p->amongvar_needed) w(g, "~Mint among_var;~N"); + g->failure_string = 0; + g->failure_label = x_return; + g->label_used = 0; + g->keep_count = 0; + generate(g, p->left); + w(g, "~Mreturn 1;~N~}"); +} + +static void generate_substring(struct generator * g, struct node * p) { + + struct among * x = p->among; + int block = -1; + unsigned int bitmap = 0; + struct amongvec * among_cases = x->b; + int c; + int empty_case = -1; + int n_cases = 0; + symbol cases[2]; + int shortest_size = INT_MAX; + + g->S[0] = p->mode == m_forward ? "" : "_b"; + g->I[0] = x->number; + g->I[1] = x->literalstring_count; + + /* In forward mode with non-ASCII UTF-8 characters, the first character + * of the string will often be the same, so instead look at the last + * common character position. + * + * In backward mode, we can't match if there are fewer characters before + * the current position than the minimum length. + */ + for (c = 0; c < x->literalstring_count; ++c) { + int size = among_cases[c].size; + if (size != 0 && size < shortest_size) { + shortest_size = size; + } + } + + for (c = 0; c < x->literalstring_count; ++c) { + symbol ch; + if (among_cases[c].size == 0) { + empty_case = c; + continue; + } + if (p->mode == m_forward) { + ch = among_cases[c].b[shortest_size - 1]; + } else { + ch = among_cases[c].b[among_cases[c].size - 1]; + } + if (n_cases == 0) { + block = ch >> 5; + } else if (ch >> 5 != block) { + block = -1; + if (n_cases > 2) break; + } + if (block == -1) { + if (ch == cases[0]) continue; + if (n_cases < 2) { + cases[n_cases++] = ch; + } else if (ch != cases[1]) { + ++n_cases; + break; + } + } else { + if ((bitmap & (1u << (ch & 0x1f))) == 0) { + bitmap |= 1u << (ch & 0x1f); + if (n_cases < 2) + cases[n_cases] = ch; + ++n_cases; + } + } + } + + if (block != -1 || n_cases <= 2) { + char buf[64]; + g->I[2] = block; + g->I[3] = bitmap; + g->I[4] = shortest_size - 1; + if (p->mode == m_forward) { + sprintf(buf, "z->p[z->c + %d]", shortest_size - 1); + g->S[1] = buf; + if (shortest_size == 1) { + wp(g, "~Mif (z->c >= z->l || ", p); + } else { + wp(g, "~Mif (z->c + ~I4 >= z->l || ", p); + } + } else { + g->S[1] = "z->p[z->c - 1]"; + if (shortest_size == 1) { + wp(g, "~Mif (z->c <= z->lb || ", p); + } else { + wp(g, "~Mif (z->c - ~I4 <= z->lb || ", p); + } + } + if (n_cases == 0) { + /* We get this for the degenerate case: among { '' } + * This doesn't seem to be a useful construct, but it is + * syntactically valid. + */ + wp(g, "0", p); + } else if (n_cases == 1) { + g->I[4] = cases[0]; + wp(g, "~S1 != ~I4", p); + } else if (n_cases == 2) { + g->I[4] = cases[0]; + g->I[5] = cases[1]; + wp(g, "(~S1 != ~I4 && ~S1 != ~I5)", p); + } else { + wp(g, "~S1 >> 5 != ~I2 || !((~I3 >> (~S1 & 0x1f)) & 1)", p); + } + ws(g, ") "); + if (empty_case != -1) { + /* If the among includes the empty string, it can never fail + * so not matching the bitmap means we match the empty string. + */ + g->I[4] = among_cases[empty_case].result; + wp(g, "among_var = ~I4; else~C", p); + } else { + wp(g, "~f~C", p); + } + } else { +#ifdef OPTIMISATION_WARNINGS + printf("Couldn't shortcut among %d\n", x->number); +#endif + } + + if (x->command_count == 0 && x->starter == 0) + wp(g, "~Mif (!(find_among~S0(z, a_~I0, ~I1))) ~f~C", p); + else + wp(g, "~Mamong_var = find_among~S0(z, a_~I0, ~I1);~C" + "~Mif (!(among_var)) ~f~N", p); +} + +static void generate_among(struct generator * g, struct node * p) { + + struct among * x = p->among; + int case_number = 1; + + if (x->substring == 0) generate_substring(g, p); + if (x->command_count == 0 && x->starter == 0) return; + + unless (x->starter == 0) generate(g, x->starter); + + p = p->left; + if (p != 0 && p->type != c_literalstring) p = p->right; + w(g, "~Mswitch(among_var) {~N~+" + "~Mcase 0: ~f~N"); + + until (p == 0) { + if (p->type == c_bra && p->left != 0) { + g->I[0] = case_number++; + w(g, "~Mcase ~I0:~N~+"); generate(g, p); w(g, "~Mbreak;~N~-"); + } + p = p->right; + } + w(g, "~}"); +} + +static void generate_booltest(struct generator * g, struct node * p) { + + g->V[0] = p->name; + wp(g, "~Mif (!(~V0)) ~f~C", p); +} + +static void generate_false(struct generator * g, struct node * p) { + + wp(g, "~M~f~C", p); +} + +static void generate_debug(struct generator * g, struct node * p) { + + g->I[0] = g->debug_count++; + g->I[1] = p->line_number; + wp(g, "~Mdebug(z, ~I0, ~I1);~C", p); + +} + +static void generate(struct generator * g, struct node * p) { + + int used = g->label_used; + int a0 = g->failure_label; + const char * a1 = g->failure_string; + + switch (p->type) + { + case c_define: generate_define(g, p); break; + case c_bra: generate_bra(g, p); break; + case c_and: generate_and(g, p); break; + case c_or: generate_or(g, p); break; + case c_backwards: generate_backwards(g, p); break; + case c_not: generate_not(g, p); break; + case c_set: generate_set(g, p); break; + case c_unset: generate_unset(g, p); break; + case c_try: generate_try(g, p); break; + case c_fail: generate_fail(g, p); break; + case c_reverse: + case c_test: generate_test(g, p); break; + case c_do: generate_do(g, p); break; + case c_goto: generate_GO(g, p, 1); break; + case c_gopast: generate_GO(g, p, 0); break; + case c_repeat: generate_repeat(g, p, false); break; + case c_loop: generate_loop(g, p); break; + case c_atleast: generate_atleast(g, p); break; + case c_setmark: generate_setmark(g, p); break; + case c_tomark: generate_tomark(g, p); break; + case c_atmark: generate_atmark(g, p); break; + case c_hop: generate_hop(g, p); break; + case c_delete: generate_delete(g, p); break; + case c_next: generate_next(g, p); break; + case c_tolimit: generate_tolimit(g, p); break; + case c_atlimit: generate_atlimit(g, p); break; + case c_leftslice: generate_leftslice(g, p); break; + case c_rightslice: generate_rightslice(g, p); break; + case c_assignto: generate_assignto(g, p); break; + case c_sliceto: generate_sliceto(g, p); break; + case c_assign: generate_assignfrom(g, p); break; + case c_insert: + case c_attach: generate_insert(g, p, p->type); break; + case c_slicefrom: generate_slicefrom(g, p); break; + case c_setlimit: generate_setlimit(g, p); break; + case c_dollar: generate_dollar(g, p); break; + case c_mathassign: generate_integer_assign(g, p, "="); break; + case c_plusassign: generate_integer_assign(g, p, "+="); break; + case c_minusassign: generate_integer_assign(g, p, "-="); break; + case c_multiplyassign:generate_integer_assign(g, p, "*="); break; + case c_divideassign: generate_integer_assign(g, p, "/="); break; + case c_eq: generate_integer_test(g, p, "=="); break; + case c_ne: generate_integer_test(g, p, "!="); break; + case c_gr: generate_integer_test(g, p, ">"); break; + case c_ge: generate_integer_test(g, p, ">="); break; + case c_ls: generate_integer_test(g, p, "<"); break; + case c_le: generate_integer_test(g, p, "<="); break; + case c_call: generate_call(g, p); break; + case c_grouping: generate_grouping(g, p, false); break; + case c_non: generate_grouping(g, p, true); break; + case c_name: generate_namedstring(g, p); break; + case c_literalstring: generate_literalstring(g, p); break; + case c_among: generate_among(g, p); break; + case c_substring: generate_substring(g, p); break; + case c_booltest: generate_booltest(g, p); break; + case c_false: generate_false(g, p); break; + case c_true: break; + case c_debug: generate_debug(g, p); break; + default: fprintf(stderr, "%d encountered\n", p->type); + exit(1); + } + + if (g->failure_label != a0) + g->label_used = used; + g->failure_label = a0; + g->failure_string = a1; +} + +static void generate_start_comment(struct generator * g) { + + w(g, "~N/* This file was generated automatically by the Snowball to ANSI C compiler */~N"); +} + +static void generate_head(struct generator * g) { + + if (g->options->runtime_path == 0) { + w(g, "~N#include \"header.h\"~N~N"); + } else { + w(g, "~N#include \""); + ws(g, g->options->runtime_path); + if (g->options->runtime_path[strlen(g->options->runtime_path) - 1] != '/') + wch(g, '/'); + w(g, "header.h\"~N~N"); + } +} + +static void generate_routine_headers(struct generator * g) { + struct name * q = g->analyser->names; + until (q == 0) { + g->V[0] = q; + switch (q->type) { + case t_routine: + w(g, "static int ~W0(struct SN_env * z);~N"); + break; + case t_external: + w(g, + "#ifdef __cplusplus~N" + "extern \"C\" {~N" + "#endif~N" + "extern int ~W0(struct SN_env * z);~N" + "#ifdef __cplusplus~N" + "}~N" + "#endif~N" + ); + break; + } + q = q->next; + } +} + +static void generate_among_table(struct generator * g, struct among * x) { + + struct amongvec * v = x->b; + + g->I[0] = x->number; + { + int i; + for (i = 0; i < x->literalstring_count; i++) + { + g->I[1] = i; + g->I[2] = v->size; + g->L[0] = v->b; + unless (v->size == 0) + w(g, "static const symbol s_~I0_~I1[~I2] = ~A0;~N"); + v++; + } + } + + g->I[1] = x->literalstring_count; + w(g, "~N~Mstatic const struct among a_~I0[~I1] =~N{~N"); + + v = x->b; + { + int i; + for (i = 0; i < x->literalstring_count; i++) { + g->I[1] = i; + g->I[2] = v->size; + g->I[3] = v->i; + g->I[4] = v->result; + g->S[0] = i < x->literalstring_count - 1 ? "," : ""; + + w(g, "/*~J1 */ { ~I2, "); + if (v->size == 0) w(g, "0,"); + else w(g, "s_~I0_~I1,"); + w(g, " ~I3, ~I4, "); + if (v->function == 0) w(g, "0"); else + wvn(g, v->function); + w(g, "}~S0~N"); + v++; + } + } + w(g, "};~N~N"); +} + +static void generate_amongs(struct generator * g) { + struct among * x = g->analyser->amongs; + until (x == 0) { + generate_among_table(g, x); + x = x->next; + } +} + +static void set_bit(symbol * b, int i) { b[i/8] |= 1 << i%8; } + +static void generate_grouping_table(struct generator * g, struct grouping * q) { + + int range = q->largest_ch - q->smallest_ch + 1; + int size = (range + 7)/ 8; /* assume 8 bits per symbol */ + symbol * b = q->b; + symbol * map = create_b(size); + int i; + for (i = 0; i < size; i++) map[i] = 0; + + for (i = 0; i < SIZE(b); i++) set_bit(map, b[i] - q->smallest_ch); + + { + g->V[0] = q->name; + + w(g, "static const unsigned char ~V0[] = { "); + for (i = 0; i < size; i++) { + wi(g, map[i]); + if (i < size - 1) w(g, ", "); + } + w(g, " };~N~N"); + } + lose_b(map); +} + +static void generate_groupings(struct generator * g) { + struct grouping * q = g->analyser->groupings; + until (q == 0) { + generate_grouping_table(g, q); + q = q->next; + } +} + +static void generate_create(struct generator * g) { + + int * p = g->analyser->name_count; + g->I[0] = p[t_string]; + g->I[1] = p[t_integer]; + g->I[2] = p[t_boolean]; + w(g, "~N" + "extern struct SN_env * ~pcreate_env(void) { return SN_create_env(~I0, ~I1, ~I2); }" + "~N"); +} + +static void generate_close(struct generator * g) { + + int * p = g->analyser->name_count; + g->I[0] = p[t_string]; + w(g, "~Nextern void ~pclose_env(struct SN_env * z) { SN_close_env(z, ~I0); }~N~N"); +} + +static void generate_create_and_close_templates(struct generator * g) { + w(g, "~N" + "extern struct SN_env * ~pcreate_env(void);~N" + "extern void ~pclose_env(struct SN_env * z);~N" + "~N"); +} + +static void generate_header_file(struct generator * g) { + + struct name * q = g->analyser->names; + char * vp = g->options->variables_prefix; + g->S[0] = vp; + + w(g, "~N" + "#ifdef __cplusplus~N" + "extern \"C\" {~N" + "#endif~N"); /* for C++ */ + + generate_create_and_close_templates(g); + until (q == 0) { + g->V[0] = q; + switch (q->type) + { + case t_external: + w(g, "extern int ~W0(struct SN_env * z);~N"); + break; + case t_string: g->S[1] = "S"; goto label0; + case t_integer: g->S[1] = "I"; goto label0; + case t_boolean: g->S[1] = "B"; + label0: + if (vp) { + g->I[0] = q->count; + w(g, "#define ~S0"); + str_append_b(g->outbuf, q->b); + w(g, " (~S1[~I0])~N"); + } + break; + } + q = q->next; + } + + w(g, "~N" + "#ifdef __cplusplus~N" + "}~N" + "#endif~N"); /* for C++ */ + + w(g, "~N"); +} + +extern void generate_program_c(struct generator * g) { + + g->outbuf = str_new(); + generate_start_comment(g); + generate_head(g); + generate_routine_headers(g); + w(g, "#ifdef __cplusplus~N" + "extern \"C\" {~N" + "#endif~N" + "~N"); + generate_create_and_close_templates(g); + w(g, "~N" + "#ifdef __cplusplus~N" + "}~N" + "#endif~N"); + generate_amongs(g); + generate_groupings(g); + g->declarations = g->outbuf; + g->outbuf = str_new(); + g->literalstring_count = 0; + { + struct node * p = g->analyser->program; + until (p == 0) { generate(g, p); p = p->right; } + } + generate_create(g); + generate_close(g); + output_str(g->options->output_c, g->declarations); + str_delete(g->declarations); + output_str(g->options->output_c, g->outbuf); + str_clear(g->outbuf); + + generate_start_comment(g); + generate_header_file(g); + output_str(g->options->output_h, g->outbuf); + str_delete(g->outbuf); +} + +extern struct generator * create_generator_c(struct analyser * a, struct options * o) { + NEW(generator, g); + g->analyser = a; + g->options = o; + g->margin = 0; + g->debug_count = 0; + g->line_count = 0; + return g; +} + +extern void close_generator_c(struct generator * g) { + + FREE(g); +} + diff --git a/contrib/snowball/compiler/generator_java.c b/contrib/snowball/compiler/generator_java.c new file mode 100644 index 000000000..07a4b8e2e --- /dev/null +++ b/contrib/snowball/compiler/generator_java.c @@ -0,0 +1,1452 @@ + +#include <stdlib.h> /* for exit */ +#include <string.h> /* for strlen */ +#include <stdio.h> /* for fprintf etc */ +#include "header.h" + +/* prototypes */ + +static void generate(struct generator * g, struct node * p); +static void w(struct generator * g, const char * s); +static void writef(struct generator * g, const char * s, struct node * p); + + +enum special_labels { + x_return = -1 +}; + +static int new_label(struct generator * g) { + + return g->next_label++; +} + +static struct str * vars_newname(struct generator * g) { + + struct str * output; + g->var_number ++; + output = str_new(); + str_append_string(output, "v_"); + str_append_int(output, g->var_number); + return output; +} + +/* Output routines */ +static void output_str(FILE * outfile, struct str * str) { + + char * s = b_to_s(str_data(str)); + fprintf(outfile, "%s", s); + free(s); +} + +/* Write routines for simple entities */ + +static void write_char(struct generator * g, int ch) { + + str_append_ch(g->outbuf, ch); +} + +static void write_newline(struct generator * g) { + + str_append_string(g->outbuf, "\n"); +} + +static void write_string(struct generator * g, const char * s) { + + str_append_string(g->outbuf, s); +} + +static void write_b(struct generator * g, symbol * b) { + + str_append_b(g->outbuf, b); +} + +static void write_str(struct generator * g, struct str * str) { + + str_append(g->outbuf, str); +} + +static void write_int(struct generator * g, int i) { + + str_append_int(g->outbuf, i); +} + + +/* Write routines for items from the syntax tree */ + +static void write_varname(struct generator * g, struct name * p) { + + int ch = "SBIrxg"[p->type]; + if (p->type != t_external) + { + write_char(g, ch); + write_char(g, '_'); + } + str_append_b(g->outbuf, p->b); +} + +static void write_varref(struct generator * g, struct name * p) { + + /* In java, references look just the same */ + write_varname(g, p); +} + +static void write_hexdigit(struct generator * g, int n) { + + write_char(g, n < 10 ? n + '0' : n - 10 + 'A'); +} + +static void write_hex(struct generator * g, int ch) { + + write_string(g, "\\u"); + { + int i; + for (i = 12; i >= 0; i -= 4) write_hexdigit(g, ch >> i & 0xf); + } +} + +static void write_literal_string(struct generator * g, symbol * p) { + + int i; + write_string(g, "\""); + for (i = 0; i < SIZE(p); i++) { + int ch = p[i]; + if (32 <= ch && ch <= 127) { + if (ch == '\"' || ch == '\\') write_string(g, "\\"); + write_char(g, ch); + } else { + write_hex(g, ch); + } + } + write_string(g, "\""); +} + +static void write_margin(struct generator * g) { + + int i; + for (i = 0; i < g->margin; i++) write_string(g, " "); +} + +/* Write a variable declaration. */ +static void write_declare(struct generator * g, + char * declaration, + struct node * p) { + + struct str * temp = g->outbuf; + g->outbuf = g->declarations; + write_string(g, " "); + writef(g, declaration, p); + write_string(g, ";"); + write_newline(g); + g->outbuf = temp; +} + +static void write_comment(struct generator * g, struct node * p) { + + write_margin(g); + write_string(g, "// "); + write_string(g, name_of_token(p->type)); + if (p->name != 0) { + write_string(g, " "); + str_append_b(g->outbuf, p->name->b); + } + write_string(g, ", line "); + write_int(g, p->line_number); + write_newline(g); +} + +static void write_block_start(struct generator * g) { + + w(g, "~M{~+~N"); +} + +static void write_block_end(struct generator * g) /* block end */ { + + w(g, "~-~M}~N"); +} + +static void write_savecursor(struct generator * g, struct node * p, + struct str * savevar) { + + g->B[0] = str_data(savevar); + g->S[1] = ""; + if (p->mode != m_forward) g->S[1] = "limit - "; + write_declare(g, "int ~B0", p); + writef(g, "~M~B0 = ~S1cursor;~N" , p); +} + +static void restore_string(struct node * p, struct str * out, struct str * savevar) { + + str_clear(out); + str_append_string(out, "cursor = "); + if (p->mode != m_forward) str_append_string(out, "limit - "); + str_append(out, savevar); + str_append_string(out, ";"); +} + +static void write_restorecursor(struct generator * g, struct node * p, + struct str * savevar) { + + struct str * temp = str_new(); + write_margin(g); + restore_string(p, temp, savevar); + write_str(g, temp); + write_newline(g); + str_delete(temp); +} + +static void write_inc_cursor(struct generator * g, struct node * p) { + + write_margin(g); + write_string(g, p->mode == m_forward ? "cursor++;" : "cursor--;"); + write_newline(g); +} + +static void wsetlab_begin(struct generator * g, int n) { + + w(g, "~Mlab"); + write_int(g, n); + w(g, ": do {~+~N"); +} + +static void wsetlab_end(struct generator * g) { + + w(g, "~-~M} while (false);~N"); +} + +static void wgotol(struct generator * g, int n) { + + write_margin(g); + write_string(g, "break lab"); + write_int(g, n); + write_string(g, ";"); + write_newline(g); +} + +static void write_failure(struct generator * g) { + + if (str_len(g->failure_str) != 0) { + write_margin(g); + write_str(g, g->failure_str); + write_newline(g); + } + write_margin(g); + switch (g->failure_label) + { + case x_return: + write_string(g, "return false;"); + break; + default: + write_string(g, "break lab"); + write_int(g, g->failure_label); + write_string(g, ";"); + g->unreachable = true; + } + write_newline(g); +} + +static void write_failure_if(struct generator * g, char * s, struct node * p) { + + writef(g, "~Mif (", p); + writef(g, s, p); + writef(g, ")~N", p); + write_block_start(g); + write_failure(g); + write_block_end(g); + g->unreachable = false; +} + +/* if at limit fail */ +static void write_check_limit(struct generator * g, struct node * p) { + + if (p->mode == m_forward) { + write_failure_if(g, "cursor >= limit", p); + } else { + write_failure_if(g, "cursor <= limit_backward", p); + } +} + +/* Formatted write. */ +static void writef(struct generator * g, const char * input, struct node * p) { + + int i = 0; + int l = strlen(input); + + while (i < l) { + int ch = input[i++]; + if (ch == '~') { + switch(input[i++]) { + default: write_char(g, input[i - 1]); continue; + case 'C': write_comment(g, p); continue; + case 'f': write_block_start(g); + write_failure(g); + g->unreachable = false; + write_block_end(g); + continue; + case 'M': write_margin(g); continue; + case 'N': write_newline(g); continue; + case '{': write_block_start(g); continue; + case '}': write_block_end(g); continue; + case 'S': write_string(g, g->S[input[i++] - '0']); continue; + case 'B': write_b(g, g->B[input[i++] - '0']); continue; + case 'I': write_int(g, g->I[input[i++] - '0']); continue; + case 'V': write_varref(g, g->V[input[i++] - '0']); continue; + case 'W': write_varname(g, g->V[input[i++] - '0']); continue; + case 'L': write_literal_string(g, g->L[input[i++] - '0']); continue; + case '+': g->margin++; continue; + case '-': g->margin--; continue; + case 'n': write_string(g, g->options->name); continue; + } + } else { + write_char(g, ch); + } + } +} + +static void w(struct generator * g, const char * s) { + writef(g, s, 0); +} + +static void generate_AE(struct generator * g, struct node * p) { + char * s; + switch (p->type) { + case c_name: + write_varref(g, p->name); break; + case c_number: + write_int(g, p->number); break; + case c_maxint: + write_string(g, "MAXINT"); break; + case c_minint: + write_string(g, "MININT"); break; + case c_neg: + write_string(g, "-"); generate_AE(g, p->right); break; + case c_multiply: + s = " * "; goto label0; + case c_plus: + s = " + "; goto label0; + case c_minus: + s = " - "; goto label0; + case c_divide: + s = " / "; + label0: + write_string(g, "("); generate_AE(g, p->left); + write_string(g, s); generate_AE(g, p->right); write_string(g, ")"); break; + case c_sizeof: + g->V[0] = p->name; + w(g, "(~V0.length())"); break; + case c_cursor: + w(g, "cursor"); break; + case c_limit: + w(g, p->mode == m_forward ? "limit" : "limit_backward"); break; + case c_size: + w(g, "(current.length())"); break; + } +} + +/* K_needed() tests to see if we really need to keep c. Not true when the + the command does not touch the cursor. This and repeat_score() could be + elaborated almost indefinitely. +*/ + +static int K_needed(struct generator * g, struct node * p) { + + while (p != 0) { + switch (p->type) { + case c_dollar: + case c_leftslice: + case c_rightslice: + case c_mathassign: + case c_plusassign: + case c_minusassign: + case c_multiplyassign: + case c_divideassign: + case c_eq: + case c_ne: + case c_gr: + case c_ge: + case c_ls: + case c_le: + case c_sliceto: + case c_booltest: + case c_true: + case c_false: + case c_debug: + break; + + case c_call: + if (K_needed(g, p->name->definition)) return true; + break; + + case c_bra: + if (K_needed(g, p->left)) return true; + break; + + default: return true; + } + p = p->right; + } + return false; +} + +static int repeat_score(struct generator * g, struct node * p) { + + int score = 0; + while (p != 0) { + switch (p->type) { + case c_dollar: + case c_leftslice: + case c_rightslice: + case c_mathassign: + case c_plusassign: + case c_minusassign: + case c_multiplyassign: + case c_divideassign: + case c_eq: + case c_ne: + case c_gr: + case c_ge: + case c_ls: + case c_le: + case c_sliceto: /* case c_not: must not be included here! */ + case c_debug: + break; + + case c_call: + score += repeat_score(g, p->name->definition); + break; + + case c_bra: + score += repeat_score(g, p->left); + break; + + case c_name: + case c_literalstring: + case c_next: + case c_grouping: + case c_non: + case c_hop: + score = score + 1; + break; + + default: + score = 2; + break; + } + p = p->right; + } + return score; +} + +/* tests if an expression requires cursor reinstatement in a repeat */ + +static int repeat_restore(struct generator * g, struct node * p) { + + return repeat_score(g, p) >= 2; +} + +static void generate_bra(struct generator * g, struct node * p) { + + write_comment(g, p); + p = p->left; + while (p != 0) { + generate(g, p); + p = p->right; + } +} + +static void generate_and(struct generator * g, struct node * p) { + + struct str * savevar = vars_newname(g); + int keep_c = K_needed(g, p->left); + + write_comment(g, p); + + if (keep_c) write_savecursor(g, p, savevar); + + p = p->left; + while (p != 0) { + generate(g, p); + if (g->unreachable) break; + if (keep_c && p->right != 0) write_restorecursor(g, p, savevar); + p = p->right; + } + str_delete(savevar); +} + +static void generate_or(struct generator * g, struct node * p) { + + struct str * savevar = vars_newname(g); + int keep_c = K_needed(g, p->left); + + int a0 = g->failure_label; + struct str * a1 = str_copy(g->failure_str); + + int out_lab = new_label(g); + write_comment(g, p); + wsetlab_begin(g, out_lab); + + if (keep_c) write_savecursor(g, p, savevar); + + p = p->left; + str_clear(g->failure_str); + + if (p == 0) { + /* p should never be 0 after an or: there should be at least two + * sub nodes. */ + fprintf(stderr, "Error: \"or\" node without children nodes."); + exit (1); + } + while (p->right != 0) { + g->failure_label = new_label(g); + wsetlab_begin(g, g->failure_label); + generate(g, p); + if (!g->unreachable) wgotol(g, out_lab); + wsetlab_end(g); + g->unreachable = false; + if (keep_c) write_restorecursor(g, p, savevar); + p = p->right; + } + + g->failure_label = a0; + str_delete(g->failure_str); + g->failure_str = a1; + + generate(g, p); + wsetlab_end(g); + str_delete(savevar); +} + +static void generate_backwards(struct generator * g, struct node * p) { + + write_comment(g, p); + writef(g,"~Mlimit_backward = cursor; cursor = limit;~N", p); + generate(g, p->left); + w(g, "~Mcursor = limit_backward;"); +} + + +static void generate_not(struct generator * g, struct node * p) { + + struct str * savevar = vars_newname(g); + int keep_c = K_needed(g, p->left); + + int a0 = g->failure_label; + struct str * a1 = str_copy(g->failure_str); + + write_comment(g, p); + if (keep_c) { + write_block_start(g); + write_savecursor(g, p, savevar); + } + + g->failure_label = new_label(g); + str_clear(g->failure_str); + + wsetlab_begin(g, g->failure_label); + + generate(g, p->left); + + g->failure_label = a0; + str_delete(g->failure_str); + g->failure_str = a1; + + if (!g->unreachable) write_failure(g); + + wsetlab_end(g); + g->unreachable = false; + + if (keep_c) write_restorecursor(g, p, savevar); + if (keep_c) write_block_end(g); + str_delete(savevar); +} + + +static void generate_try(struct generator * g, struct node * p) { + + struct str * savevar = vars_newname(g); + int keep_c = K_needed(g, p->left); + + write_comment(g, p); + if (keep_c) write_savecursor(g, p, savevar); + + g->failure_label = new_label(g); + if (keep_c) restore_string(p, g->failure_str, savevar); + + wsetlab_begin(g, g->failure_label); + generate(g, p->left); + wsetlab_end(g); + g->unreachable = false; + + str_delete(savevar); +} + +static void generate_set(struct generator * g, struct node * p) { + + write_comment(g, p); + g->V[0] = p->name; + writef(g, "~M~V0 = true;~N", p); +} + +static void generate_unset(struct generator * g, struct node * p) { + + write_comment(g, p); + g->V[0] = p->name; + writef(g, "~M~V0 = false;~N", p); +} + +static void generate_fail(struct generator * g, struct node * p) { + + write_comment(g, p); + generate(g, p->left); + if (!g->unreachable) write_failure(g); +} + +/* generate_test() also implements 'reverse' */ + +static void generate_test(struct generator * g, struct node * p) { + + struct str * savevar = vars_newname(g); + int keep_c = K_needed(g, p->left); + + write_comment(g, p); + + if (keep_c) { + write_savecursor(g, p, savevar); + } + + generate(g, p->left); + + if (!g->unreachable) { + if (keep_c) { + write_restorecursor(g, p, savevar); + } + } + str_delete(savevar); +} + +static void generate_do(struct generator * g, struct node * p) { + + struct str * savevar = vars_newname(g); + int keep_c = K_needed(g, p->left); + write_comment(g, p); + if (keep_c) write_savecursor(g, p, savevar); + + g->failure_label = new_label(g); + str_clear(g->failure_str); + + wsetlab_begin(g, g->failure_label); + generate(g, p->left); + wsetlab_end(g); + g->unreachable = false; + + if (keep_c) write_restorecursor(g, p, savevar); + str_delete(savevar); +} + +static void generate_GO(struct generator * g, struct node * p, int style) { + + int end_unreachable = false; + struct str * savevar = vars_newname(g); + int keep_c = style == 1 || repeat_restore(g, p->left); + + int a0 = g->failure_label; + struct str * a1 = str_copy(g->failure_str); + + int golab = new_label(g); + g->I[0] = golab; + write_comment(g, p); + w(g, "~Mgolab~I0: while(true)~N"); + w(g, "~{"); + + if (keep_c) write_savecursor(g, p, savevar); + + g->failure_label = new_label(g); + wsetlab_begin(g, g->failure_label); + generate(g, p->left); + + if (g->unreachable) { + /* Cannot break out of this loop: therefore the code after the + * end of the loop is unreachable.*/ + end_unreachable = true; + } else { + /* include for goto; omit for gopast */ + if (style == 1) write_restorecursor(g, p, savevar); + g->I[0] = golab; + w(g, "~Mbreak golab~I0;~N"); + } + g->unreachable = false; + wsetlab_end(g); + if (keep_c) write_restorecursor(g, p, savevar); + + g->failure_label = a0; + str_delete(g->failure_str); + g->failure_str = a1; + + write_check_limit(g, p); + write_inc_cursor(g, p); + write_block_end(g); + str_delete(savevar); + g->unreachable = end_unreachable; +} + +static void generate_loop(struct generator * g, struct node * p) { + + struct str * loopvar = vars_newname(g); + write_comment(g, p); + g->B[0] = str_data(loopvar); + write_declare(g, "int ~B0", p); + w(g, "~Mfor (~B0 = "); + generate_AE(g, p->AE); + g->B[0] = str_data(loopvar); + writef(g, "; ~B0 > 0; ~B0--)~N", p); + writef(g, "~{", p); + + generate(g, p->left); + + w(g, "~}"); + str_delete(loopvar); + g->unreachable = false; +} + +static void generate_repeat(struct generator * g, struct node * p, struct str * loopvar) { + + struct str * savevar = vars_newname(g); + int keep_c = repeat_restore(g, p->left); + int replab = new_label(g); + g->I[0] = replab; + write_comment(g, p); + writef(g, "~Mreplab~I0: while(true)~N~{", p); + + if (keep_c) write_savecursor(g, p, savevar); + + g->failure_label = new_label(g); + str_clear(g->failure_str); + wsetlab_begin(g, g->failure_label); + generate(g, p->left); + + if (!g->unreachable) { + if (loopvar != 0) { + g->B[0] = str_data(loopvar); + w(g, "~M~B0--;~N"); + } + + g->I[0] = replab; + w(g, "~Mcontinue replab~I0;~N"); + } + + wsetlab_end(g); + g->unreachable = false; + + if (keep_c) write_restorecursor(g, p, savevar); + + g->I[0] = replab; + w(g, "~Mbreak replab~I0;~N~}"); + str_delete(savevar); +} + +static void generate_atleast(struct generator * g, struct node * p) { + + struct str * loopvar = vars_newname(g); + write_comment(g, p); + w(g, "~{"); + g->B[0] = str_data(loopvar); + w(g, "~Mint ~B0 = "); + generate_AE(g, p->AE); + w(g, ";~N"); + { + int a0 = g->failure_label; + struct str * a1 = str_copy(g->failure_str); + + generate_repeat(g, p, loopvar); + + g->failure_label = a0; + str_delete(g->failure_str); + g->failure_str = a1; + } + g->B[0] = str_data(loopvar); + write_failure_if(g, "~B0 > 0", p); + w(g, "~}"); + str_delete(loopvar); +} + +static void generate_setmark(struct generator * g, struct node * p) { + + write_comment(g, p); + g->V[0] = p->name; + writef(g, "~M~V0 = cursor;~N", p); +} + +static void generate_tomark(struct generator * g, struct node * p) { + + write_comment(g, p); + g->S[0] = p->mode == m_forward ? ">" : "<"; + + w(g, "~Mif (cursor ~S0 "); generate_AE(g, p->AE); w(g, ")~N"); + write_block_start(g); + write_failure(g); + write_block_end(g); + g->unreachable = false; + w(g, "~Mcursor = "); generate_AE(g, p->AE); writef(g, ";~N", p); +} + +static void generate_atmark(struct generator * g, struct node * p) { + + write_comment(g, p); + w(g, "~Mif (cursor != "); generate_AE(g, p->AE); writef(g, ")~N", p); + write_block_start(g); + write_failure(g); + write_block_end(g); + g->unreachable = false; +} + + +static void generate_hop(struct generator * g, struct node * p) { + + write_comment(g, p); + g->S[0] = p->mode == m_forward ? "+" : "-"; + + w(g, "~{~Mint c = cursor ~S0 "); + generate_AE(g, p->AE); + w(g, ";~N"); + + g->S[0] = p->mode == m_forward ? "0" : "limit_backward"; + + write_failure_if(g, "~S0 > c || c > limit", p); + writef(g, "~Mcursor = c;~N", p); + writef(g, "~}", p); +} + +static void generate_delete(struct generator * g, struct node * p) { + + write_comment(g, p); + writef(g, "~Mslice_del();~N", p); +} + + +static void generate_next(struct generator * g, struct node * p) { + + write_comment(g, p); + write_check_limit(g, p); + write_inc_cursor(g, p); +} + +static void generate_tolimit(struct generator * g, struct node * p) { + + write_comment(g, p); + g->S[0] = p->mode == m_forward ? "limit" : "limit_backward"; + writef(g, "~Mcursor = ~S0;~N", p); +} + +static void generate_atlimit(struct generator * g, struct node * p) { + + write_comment(g, p); + g->S[0] = p->mode == m_forward ? "limit" : "limit_backward"; + g->S[1] = p->mode == m_forward ? "<" : ">"; + write_failure_if(g, "cursor ~S1 ~S0", p); +} + +static void generate_leftslice(struct generator * g, struct node * p) { + + write_comment(g, p); + g->S[0] = p->mode == m_forward ? "bra" : "ket"; + writef(g, "~M~S0 = cursor;~N", p); +} + +static void generate_rightslice(struct generator * g, struct node * p) { + + write_comment(g, p); + g->S[0] = p->mode == m_forward ? "ket" : "bra"; + writef(g, "~M~S0 = cursor;~N", p); +} + +static void generate_assignto(struct generator * g, struct node * p) { + + write_comment(g, p); + g->V[0] = p->name; + writef(g, "~M~V0 = assign_to(~V0);~N", p); +} + +static void generate_sliceto(struct generator * g, struct node * p) { + + write_comment(g, p); + g->V[0] = p->name; + writef(g, "~M~V0 = slice_to(~V0);~N", p); +} + +static void generate_address(struct generator * g, struct node * p) { + + symbol * b = p->literalstring; + if (b != 0) { + write_literal_string(g, b); + } else { + write_varref(g, p->name); + } +} + +static void generate_insert(struct generator * g, struct node * p, int style) { + + int keep_c = style == c_attach; + write_comment(g, p); + if (p->mode == m_backward) keep_c = !keep_c; + if (keep_c) w(g, "~{~Mint c = cursor;~N"); + writef(g, "~Minsert(cursor, cursor, ", p); + generate_address(g, p); + writef(g, ");~N", p); + if (keep_c) w(g, "~Mcursor = c;~N~}"); +} + +static void generate_assignfrom(struct generator * g, struct node * p) { + + int keep_c = p->mode == m_forward; /* like 'attach' */ + + write_comment(g, p); + if (keep_c) writef(g, "~{~Mint c = cursor;~N", p); + if (p->mode == m_forward) { + writef(g, "~Minsert(cursor, limit, ", p); + } else { + writef(g, "~Minsert(limit_backward, cursor, ", p); + } + generate_address(g, p); + writef(g, ");~N", p); + if (keep_c) w(g, "~Mcursor = c;~N~}"); +} + + +static void generate_slicefrom(struct generator * g, struct node * p) { + + write_comment(g, p); + w(g, "~Mslice_from("); + generate_address(g, p); + writef(g, ");~N", p); +} + +static void generate_setlimit(struct generator * g, struct node * p) { + + struct str * savevar = vars_newname(g); + struct str * varname = vars_newname(g); + write_comment(g, p); + write_savecursor(g, p, savevar); + generate(g, p->left); + + if (!g->unreachable) { + g->B[0] = str_data(varname); + write_declare(g, "int ~B0", p); + if (p->mode == m_forward) { + w(g, "~M~B0 = limit - cursor;~N"); + w(g, "~Mlimit = cursor;~N"); + } else { + w(g, "~M~B0 = limit_backward;~N"); + w(g, "~Mlimit_backward = cursor;~N"); + } + write_restorecursor(g, p, savevar); + + if (p->mode == m_forward) { + str_assign(g->failure_str, "limit += "); + str_append(g->failure_str, varname); + str_append_ch(g->failure_str, ';'); + } else { + str_assign(g->failure_str, "limit_backward = "); + str_append(g->failure_str, varname); + str_append_ch(g->failure_str, ';'); + } + generate(g, p->aux); + + if (!g->unreachable) { + write_margin(g); + write_str(g, g->failure_str); + write_newline(g); + } + } + str_delete(varname); + str_delete(savevar); +} + +/* dollar sets snowball up to operate on a string variable as if it were the + * current string */ +static void generate_dollar(struct generator * g, struct node * p) { + + struct str * savevar = vars_newname(g); + write_comment(g, p); + g->V[0] = p->name; + + str_assign(g->failure_str, "copy_from("); + str_append(g->failure_str, savevar); + str_append_string(g->failure_str, ");"); + g->B[0] = str_data(savevar); + writef(g, "~{~M~n ~B0 = this;~N" + "~Mcurrent = new StringBuffer(~V0.toString());~N" + "~Mcursor = 0;~N" + "~Mlimit = (current.length());~N", p); + generate(g, p->left); + if (!g->unreachable) { + write_margin(g); + write_str(g, g->failure_str); + write_newline(g); + } + w(g, "~}"); + str_delete(savevar); +} + +static void generate_integer_assign(struct generator * g, struct node * p, char * s) { + + g->V[0] = p->name; + g->S[0] = s; + w(g, "~M~V0 ~S0 "); generate_AE(g, p->AE); w(g, ";~N"); +} + +static void generate_integer_test(struct generator * g, struct node * p, char * s) { + + g->V[0] = p->name; + g->S[0] = s; + w(g, "~Mif (!(~V0 ~S0 "); generate_AE(g, p->AE); w(g, "))~N"); + write_block_start(g); + write_failure(g); + write_block_end(g); + g->unreachable = false; +} + +static void generate_call(struct generator * g, struct node * p) { + + write_comment(g, p); + g->V[0] = p->name; + write_failure_if(g, "!~V0()", p); +} + +static void generate_grouping(struct generator * g, struct node * p, int complement) { + + struct grouping * q = p->name->grouping; + g->S[0] = p->mode == m_forward ? "" : "_b"; + g->S[1] = complement ? "out" : "in"; + g->V[0] = p->name; + g->I[0] = q->smallest_ch; + g->I[1] = q->largest_ch; + if (q->no_gaps) + write_failure_if(g, "!(~S1_range~S0(~I0, ~I1))", p); + else + write_failure_if(g, "!(~S1_grouping~S0(~V0, ~I0, ~I1))", p); +} + +static void generate_namedstring(struct generator * g, struct node * p) { + + write_comment(g, p); + g->S[0] = p->mode == m_forward ? "" : "_b"; + g->V[0] = p->name; + write_failure_if(g, "!(eq_v~S0(~V0))", p); +} + +static void generate_literalstring(struct generator * g, struct node * p) { + + symbol * b = p->literalstring; + write_comment(g, p); + g->S[0] = p->mode == m_forward ? "" : "_b"; + g->I[0] = SIZE(b); + g->L[0] = b; + write_failure_if(g, "!(eq_s~S0(~I0, ~L0))", p); +} + +static void generate_define(struct generator * g, struct node * p) { + + struct name * q = p->name; + + struct str * saved_output = g->outbuf; + struct str * saved_declarations = g->declarations; + + g->S[0] = q->type == t_routine ? "private" : "public"; + g->V[0] = q; + w(g, "~+~+~N~M~S0 boolean ~V0() {~+~N"); + + g->outbuf = str_new(); + g->declarations = str_new(); + + g->next_label = 0; + g->var_number = 0; + + if (p->amongvar_needed) write_declare(g, "int among_var", p); + str_clear(g->failure_str); + g->failure_label = x_return; + g->unreachable = false; + generate(g, p->left); + if (!g->unreachable) w(g, "~Mreturn true;~N"); + w(g, "~}~-~-"); + + str_append(saved_output, g->declarations); + str_append(saved_output, g->outbuf); + str_delete(g->declarations); + str_delete(g->outbuf); + g->declarations = saved_declarations; + g->outbuf = saved_output; +} + +static void generate_substring(struct generator * g, struct node * p) { + + struct among * x = p->among; + + write_comment(g, p); + + g->S[0] = p->mode == m_forward ? "" : "_b"; + g->I[0] = x->number; + g->I[1] = x->literalstring_count; + + if (x->command_count == 0 && x->starter == 0) { + write_failure_if(g, "find_among~S0(a_~I0, ~I1) == 0", p); + } else { + writef(g, "~Mamong_var = find_among~S0(a_~I0, ~I1);~N", p); + write_failure_if(g, "among_var == 0", p); + } +} + +static void generate_among(struct generator * g, struct node * p) { + + struct among * x = p->among; + int case_number = 1; + + if (x->substring == 0) generate_substring(g, p); + if (x->command_count == 0 && x->starter == 0) return; + + if (x->starter != 0) generate(g, x->starter); + + p = p->left; + if (p != 0 && p->type != c_literalstring) p = p->right; + w(g, "~Mswitch(among_var) {~N~+"); + w(g, "~Mcase 0:~N~+"); + write_failure(g); + g->unreachable = false; + w(g, "~-"); + + while (p != 0) { + if (p->type == c_bra && p->left != 0) { + g->I[0] = case_number++; + w(g, "~Mcase ~I0:~N~+"); + generate(g, p); + if (!g->unreachable) w(g, "~Mbreak;~N"); + w(g, "~-"); + g->unreachable = false; + } + p = p->right; + } + write_block_end(g); +} + +static void generate_booltest(struct generator * g, struct node * p) { + + write_comment(g, p); + g->V[0] = p->name; + write_failure_if(g, "!(~V0)", p); +} + +static void generate_false(struct generator * g, struct node * p) { + + write_comment(g, p); + write_failure(g); +} + +static void generate_debug(struct generator * g, struct node * p) { + + write_comment(g, p); + g->I[0] = g->debug_count++; + g->I[1] = p->line_number; + writef(g, "~Mdebug(~I0, ~I1);~N", p); +} + +static void generate(struct generator * g, struct node * p) { + + int a0; + struct str * a1; + + if (g->unreachable) return; + + a0 = g->failure_label; + a1 = str_copy(g->failure_str); + + switch (p->type) + { + case c_define: generate_define(g, p); break; + case c_bra: generate_bra(g, p); break; + case c_and: generate_and(g, p); break; + case c_or: generate_or(g, p); break; + case c_backwards: generate_backwards(g, p); break; + case c_not: generate_not(g, p); break; + case c_set: generate_set(g, p); break; + case c_unset: generate_unset(g, p); break; + case c_try: generate_try(g, p); break; + case c_fail: generate_fail(g, p); break; + case c_reverse: + case c_test: generate_test(g, p); break; + case c_do: generate_do(g, p); break; + case c_goto: generate_GO(g, p, 1); break; + case c_gopast: generate_GO(g, p, 0); break; + case c_repeat: generate_repeat(g, p, 0); break; + case c_loop: generate_loop(g, p); break; + case c_atleast: generate_atleast(g, p); break; + case c_setmark: generate_setmark(g, p); break; + case c_tomark: generate_tomark(g, p); break; + case c_atmark: generate_atmark(g, p); break; + case c_hop: generate_hop(g, p); break; + case c_delete: generate_delete(g, p); break; + case c_next: generate_next(g, p); break; + case c_tolimit: generate_tolimit(g, p); break; + case c_atlimit: generate_atlimit(g, p); break; + case c_leftslice: generate_leftslice(g, p); break; + case c_rightslice: generate_rightslice(g, p); break; + case c_assignto: generate_assignto(g, p); break; + case c_sliceto: generate_sliceto(g, p); break; + case c_assign: generate_assignfrom(g, p); break; + case c_insert: + case c_attach: generate_insert(g, p, p->type); break; + case c_slicefrom: generate_slicefrom(g, p); break; + case c_setlimit: generate_setlimit(g, p); break; + case c_dollar: generate_dollar(g, p); break; + case c_mathassign: generate_integer_assign(g, p, "="); break; + case c_plusassign: generate_integer_assign(g, p, "+="); break; + case c_minusassign: generate_integer_assign(g, p, "-="); break; + case c_multiplyassign:generate_integer_assign(g, p, "*="); break; + case c_divideassign: generate_integer_assign(g, p, "/="); break; + case c_eq: generate_integer_test(g, p, "=="); break; + case c_ne: generate_integer_test(g, p, "!="); break; + case c_gr: generate_integer_test(g, p, ">"); break; + case c_ge: generate_integer_test(g, p, ">="); break; + case c_ls: generate_integer_test(g, p, "<"); break; + case c_le: generate_integer_test(g, p, "<="); break; + case c_call: generate_call(g, p); break; + case c_grouping: generate_grouping(g, p, false); break; + case c_non: generate_grouping(g, p, true); break; + case c_name: generate_namedstring(g, p); break; + case c_literalstring: generate_literalstring(g, p); break; + case c_among: generate_among(g, p); break; + case c_substring: generate_substring(g, p); break; + case c_booltest: generate_booltest(g, p); break; + case c_false: generate_false(g, p); break; + case c_true: break; + case c_debug: generate_debug(g, p); break; + default: fprintf(stderr, "%d encountered\n", p->type); + exit(1); + } + + g->failure_label = a0; + str_delete(g->failure_str); + g->failure_str = a1; +} + +static void generate_start_comment(struct generator * g) { + + w(g, "// This file was generated automatically by the Snowball to Java compiler~N"); + w(g, "~N"); +} + +static void generate_class_begin(struct generator * g) { + + w(g, "package " ); + w(g, g->options->package); + w(g, ";~N~N" ); + + w(g, "import "); + w(g, g->options->among_class ); + w(g, ";~N" + "~N" + " /**~N" + " * This class was automatically generated by a Snowball to Java compiler ~N" + " * It implements the stemming algorithm defined by a snowball script.~N" + " */~N" + "~N" + "public class ~n extends "); + + w(g, g->options->parent_class_name); + w(g, " {~N" + "~N" + "private static final long serialVersionUID = 1L;~N" + "~N" + "~+~+~Mprivate final static ~n methodObject = new ~n ();~N" + "~N"); +} + +static void generate_class_end(struct generator * g) { + + w(g, "~N}"); + w(g, "~N~N"); +} + +static void generate_equals(struct generator * g) { + + w(g, "~N" + "~Mpublic boolean equals( Object o ) {~N" + "~+~Mreturn o instanceof "); + w(g, g->options->name); + w(g, ";~N~-~M}~N" + "~N" + "~Mpublic int hashCode() {~N" + "~+~Mreturn "); + w(g, g->options->name); + w(g, ".class.getName().hashCode();~N" + "~-~M}~N"); + w(g, "~N~N"); +} + +static void generate_among_table(struct generator * g, struct among * x) { + + struct amongvec * v = x->b; + + g->I[0] = x->number; + g->I[1] = x->literalstring_count; + + w(g, "~+~+~Mprivate final static Among a_~I0[] = {~N~+"); + { + int i; + for (i = 0; i < x->literalstring_count; i++) { + g->I[0] = i; + g->I[1] = v->i; + g->I[2] = v->result; + g->L[0] = v->b; + g->S[0] = i < x->literalstring_count - 1 ? "," : ""; + + w(g, "~Mnew Among ( ~L0, ~I1, ~I2, \""); + if (v->function != 0) { + write_varname(g, v->function); + } + w(g, "\", methodObject )~S0~N"); + v++; + } + } + w(g, "~-~M};~-~-~N~N"); +} + +static void generate_amongs(struct generator * g) { + + struct among * x = g->analyser->amongs; + while (x != 0) { + generate_among_table(g, x); + x = x->next; + } +} + +static void set_bit(symbol * b, int i) { b[i/8] |= 1 << i%8; } + +static int bit_is_set(symbol * b, int i) { return b[i/8] & 1 << i%8; } + +static void generate_grouping_table(struct generator * g, struct grouping * q) { + + int range = q->largest_ch - q->smallest_ch + 1; + int size = (range + 7)/ 8; /* assume 8 bits per symbol */ + symbol * b = q->b; + symbol * map = create_b(size); + int i; + for (i = 0; i < size; i++) map[i] = 0; + + /* Using unicode would require revision here */ + + for (i = 0; i < SIZE(b); i++) set_bit(map, b[i] - q->smallest_ch); + + q->no_gaps = true; + for (i = 0; i < range; i++) unless (bit_is_set(map, i)) q->no_gaps = false; + + unless (q->no_gaps) { + g->V[0] = q->name; + + w(g, "~+~+~Mprivate static final char ~V0[] = {"); + for (i = 0; i < size; i++) { + write_int(g, map[i]); + if (i < size - 1) w(g, ", "); + } + w(g, " };~N~-~-~N"); + } + lose_b(map); +} + +static void generate_groupings(struct generator * g) { + struct grouping * q = g->analyser->groupings; + until (q == 0) { + generate_grouping_table(g, q); + q = q->next; + } +} + +static void generate_members(struct generator * g) { + + struct name * q = g->analyser->names; + until (q == 0) { + g->V[0] = q; + switch (q->type) { + case t_string: + w(g, " private "); + w(g, g->options->string_class ); + w(g, " ~W0 = new "); + w(g, g->options->string_class); + w(g, "();~N"); + break; + case t_integer: + w(g, " private int ~W0;~N"); + break; + case t_boolean: + w(g, " private boolean ~W0;~N"); + break; + } + q = q->next; + } + w(g, "~N"); +} + +static void generate_copyfrom(struct generator * g) { + + struct name * q; + w(g, "~+~+~Mprivate void copy_from(~n other) {~+~N"); + for (q = g->analyser->names; q != 0; q = q->next) { + g->V[0] = q; + switch (q->type) { + case t_string: + case t_integer: + case t_boolean: + w(g, "~M~W0 = other.~W0;~N"); + break; + } + } + w(g, "~Msuper.copy_from(other);~N"); + w(g, "~-~M}~-~-~N"); +} + +static void generate_methods(struct generator * g) { + + struct node * p = g->analyser->program; + while (p != 0) { + generate(g, p); + g->unreachable = false; + p = p->right; + } +} + +extern void generate_program_java(struct generator * g) { + + g->outbuf = str_new(); + g->failure_str = str_new(); + + generate_start_comment(g); + generate_class_begin(g); + + generate_amongs(g); + generate_groupings(g); + + generate_members(g); + generate_copyfrom(g); + generate_methods(g); + generate_equals(g); + + generate_class_end(g); + + output_str(g->options->output_java, g->outbuf); + str_delete(g->failure_str); + str_delete(g->outbuf); +} + +extern struct generator * create_generator_java(struct analyser * a, struct options * o) { + + NEW(generator, g); + g->analyser = a; + g->options = o; + g->margin = 0; + g->debug_count = 0; + g->unreachable = false; + return g; +} + +extern void close_generator_java(struct generator * g) { + + FREE(g); +} + diff --git a/contrib/snowball/compiler/header.h b/contrib/snowball/compiler/header.h new file mode 100644 index 000000000..9baf1d917 --- /dev/null +++ b/contrib/snowball/compiler/header.h @@ -0,0 +1,324 @@ + +typedef unsigned char byte; +typedef unsigned short symbol; + +#define true 1 +#define false 0 +#define repeat while(true) +#define unless(C) if(!(C)) +#define until(C) while(!(C)) + +#define MALLOC check_malloc +#define FREE check_free + +#define NEW(type, p) struct type * p = (struct type *) MALLOC(sizeof(struct type)) +#define NEWVEC(type, p, n) struct type * p = (struct type *) MALLOC(sizeof(struct type) * n) + +#define STARTSIZE 10 +#define SIZE(p) ((int *)(p))[-1] +#define CAPACITY(p) ((int *)(p))[-2] + +extern symbol * create_b(int n); +extern void report_b(FILE * out, symbol * p); +extern void lose_b(symbol * p); +extern symbol * increase_capacity(symbol * p, int n); +extern symbol * move_to_b(symbol * p, int n, symbol * q); +extern symbol * add_to_b(symbol * p, int n, symbol * q); +extern symbol * copy_b(symbol * p); +extern char * b_to_s(symbol * p); +extern symbol * add_s_to_b(symbol * p, const char * s); + +struct str; /* defined in space.c */ + +extern struct str * str_new(void); +extern void str_delete(struct str * str); +extern void str_append(struct str * str, struct str * add); +extern void str_append_ch(struct str * str, char add); +extern void str_append_b(struct str * str, symbol * q); +extern void str_append_string(struct str * str, const char * s); +extern void str_append_int(struct str * str, int i); +extern void str_clear(struct str * str); +extern void str_assign(struct str * str, char * s); +extern struct str * str_copy(struct str * old); +extern symbol * str_data(struct str * str); +extern int str_len(struct str * str); +extern int get_utf8(const symbol * p, int * slot); +extern int put_utf8(int ch, symbol * p); + +struct m_pair { + + struct m_pair * next; + symbol * name; + symbol * value; + +}; + +/* struct input must be a prefix of struct tokeniser. */ +struct input { + + struct input * next; + symbol * p; + int c; + char * file; + int line_number; + +}; + +struct include { + + struct include * next; + symbol * b; + +}; + +/* struct input must be a prefix of struct tokeniser. */ +struct tokeniser { + + struct input * next; + symbol * p; + int c; + char * file; + int line_number; + symbol * b; + symbol * b2; + int number; + int m_start; + int m_end; + struct m_pair * m_pairs; + int get_depth; + int error_count; + int token; + int previous_token; + byte token_held; + byte widechars; + byte utf8; + + int omission; + struct include * includes; + +}; + +extern symbol * get_input(symbol * p, char ** p_file); +extern struct tokeniser * create_tokeniser(symbol * b, char * file); +extern int read_token(struct tokeniser * t); +extern const char * name_of_token(int code); +extern void close_tokeniser(struct tokeniser * t); + +enum token_codes { + +#include "syswords2.h" + + c_mathassign, + c_name, + c_number, + c_literalstring, + c_neg, + c_call, + c_grouping, + c_booltest +}; + +extern int space_count; +extern void * check_malloc(int n); +extern void check_free(void * p); + +struct node; + +struct name { + + struct name * next; + symbol * b; + int type; /* t_string etc */ + int mode; /* )_ for routines, externals */ + struct node * definition; /* ) */ + int count; /* 0, 1, 2 for each type */ + struct grouping * grouping; /* for grouping names */ + byte referenced; + byte used; + +}; + +struct literalstring { + + struct literalstring * next; + symbol * b; + +}; + +struct amongvec { + + symbol * b; /* the string giving the case */ + int size; /* - and its size */ + struct node * p; /* the corresponding command */ + int i; /* the amongvec index of the longest substring of b */ + int result; /* the numeric result for the case */ + struct name * function; + +}; + +struct among { + + struct among * next; + struct amongvec * b; /* pointer to the amongvec */ + int number; /* amongs are numbered 0, 1, 2 ... */ + int literalstring_count; /* in this among */ + int command_count; /* in this among */ + struct node * starter; /* i.e. among( (starter) 'string' ... ) */ + struct node * substring; /* i.e. substring ... among ( ... ) */ +}; + +struct grouping { + + struct grouping * next; + int number; /* groupings are numbered 0, 1, 2 ... */ + symbol * b; /* the characters of this group */ + int largest_ch; /* character with max code */ + int smallest_ch; /* character with min code */ + byte no_gaps; /* not used in generator.c after 11/5/05 */ + struct name * name; /* so g->name->grouping == g */ +}; + +struct node { + + struct node * next; + struct node * left; + struct node * aux; /* used in setlimit */ + struct among * among; /* used in among */ + struct node * right; + int type; + int mode; + struct node * AE; + struct name * name; + symbol * literalstring; + int number; + int line_number; + int amongvar_needed; /* used in routine definitions */ +}; + +enum name_types { + + t_size = 6, + + t_string = 0, t_boolean = 1, t_integer = 2, t_routine = 3, t_external = 4, + t_grouping = 5 + +/* If this list is extended, adjust wvn in generator.c */ +}; + +/* In name_count[i] below, remember that + type is + ----+---- + 0 | string + 1 | boolean + 2 | integer + 3 | routine + 4 | external + 5 | grouping +*/ + +struct analyser { + + struct tokeniser * tokeniser; + struct node * nodes; + struct name * names; + struct literalstring * literalstrings; + int mode; + byte modifyable; /* false inside reverse(...) */ + struct node * program; + struct node * program_end; + int name_count[t_size]; /* name_count[i] counts the number of names of type i */ + struct among * amongs; + struct among * amongs_end; + int among_count; + int amongvar_needed; /* used in reading routine definitions */ + struct grouping * groupings; + struct grouping * groupings_end; + struct node * substring; /* pending 'substring' in current routine definition */ + byte utf8; +}; + +enum analyser_modes { + + m_forward = 0, m_backward /*, m_integer */ + +}; + +extern void print_program(struct analyser * a); +extern struct analyser * create_analyser(struct tokeniser * t); +extern void close_analyser(struct analyser * a); + +extern void read_program(struct analyser * a); + +struct generator { + + struct analyser * analyser; + struct options * options; + int unreachable; /* 0 if code can be reached, 1 if current code + * is unreachable. */ + int var_number; /* Number of next variable to use. */ + struct str * outbuf; /* temporary str to store output */ + struct str * declarations; /* str storing variable declarations */ + int next_label; + int margin; + + const char * failure_string; /* String to output in case of a failure. */ +#ifndef DISABLE_JAVA + struct str * failure_str; /* This is used by the java generator instead of failure_string */ +#endif + + int label_used; /* Keep track of whether the failure label is used. */ + int failure_label; + int debug_count; + + const char * S[10]; /* strings */ + symbol * B[10]; /* blocks */ + int I[10]; /* integers */ + struct name * V[5]; /* variables */ + symbol * L[5]; /* literals, used in formatted write */ + + int line_count; /* counts number of lines output */ + int line_labelled; /* in ANSI C, will need extra ';' if it is a block end */ + int literalstring_count; + int keep_count; /* used to number keep/restore pairs to avoid compiler warnings + about shadowed variables */ +}; + +struct options { + + /* for the command line: */ + + char * output_file; + char * name; + FILE * output_c; + FILE * output_h; +#ifndef DISABLE_JAVA + FILE * output_java; +#endif + byte syntax_tree; + byte widechars; + enum { LANG_JAVA, LANG_C, LANG_CPLUSPLUS } make_lang; + char * externals_prefix; + char * variables_prefix; + char * runtime_path; + char * parent_class_name; + char * package; + char * string_class; + char * among_class; + struct include * includes; + struct include * includes_end; + byte utf8; +}; + +/* Generator for C code. */ +extern struct generator * create_generator_c(struct analyser * a, struct options * o); +extern void close_generator_c(struct generator * g); + +extern void generate_program_c(struct generator * g); + +#ifndef DISABLE_JAVA +/* Generator for Java code. */ +extern struct generator * create_generator_java(struct analyser * a, struct options * o); +extern void close_generator_java(struct generator * g); + +extern void generate_program_java(struct generator * g); +#endif diff --git a/contrib/snowball/compiler/space.c b/contrib/snowball/compiler/space.c new file mode 100644 index 000000000..cd5fd863d --- /dev/null +++ b/contrib/snowball/compiler/space.c @@ -0,0 +1,263 @@ + +#include <stdio.h> /* for printf */ +#include <stdlib.h> /* malloc, free */ +#include <string.h> /* memmove */ + +#include "header.h" + +#define HEAD 2*sizeof(int) +#define EXTENDER 40 + + +/* This modules provides a simple mechanism for arbitrary length writable + strings, called 'blocks'. They are 'symbol *' items rather than 'char *' + items however. + + The calls are: + + symbol * b = create_b(n); + - create an empty block b with room for n symbols + b = increase_capacity(b, n); + - increase the capacity of block b by n symbols (b may change) + b2 = copy_b(b) + - copy block b into b2 + lose_b(b); + - lose block b + b = move_to_b(b, n, p); + - set the data in b to be the n symbols at address p + b = add_to_b(b, n, p); + - add the n symbols at address p to the end of the data in b + SIZE(b) + - is the number of symbols in b + For example: + + symbol * b = create_b(0); + { int i; + char p[10]; + for (i = 0; i < 100; i++) { + sprintf(p, " %d", i); + add_s_to_b(b, p); + } + } + + and b contains " 0 1 2 ... 99" spaced out as symbols. +*/ + +/* For a block b, SIZE(b) is the number of symbols so far written into it, + CAPACITY(b) the total number it can contain, so SIZE(b) <= CAPACITY(b). + In fact blocks have 1 extra character over the promised capacity so + they can be zero terminated by 'b[SIZE(b)] = 0;' without fear of + overwriting. +*/ + +extern symbol * create_b(int n) { + symbol * p = (symbol *) (HEAD + (char *) MALLOC(HEAD + (n + 1) * sizeof(symbol))); + CAPACITY(p) = n; + SIZE(p) = 0; + return p; +} + +extern void report_b(FILE * out, symbol * p) { + int i; + for (i = 0; i < SIZE(p); i++) fprintf(out, "%c", p[i]); +} + +extern void lose_b(symbol * p) { + if (p == 0) return; + FREE((char *) p - HEAD); +} + +extern symbol * increase_capacity(symbol * p, int n) { + symbol * q = create_b(CAPACITY(p) + n + EXTENDER); + memmove(q, p, CAPACITY(p) * sizeof(symbol)); + SIZE(q) = SIZE(p); + lose_b(p); return q; +} + +extern symbol * move_to_b(symbol * p, int n, symbol * q) { + int x = n - CAPACITY(p); + if (x > 0) p = increase_capacity(p, x); + memmove(p, q, n * sizeof(symbol)); SIZE(p) = n; return p; +} + +extern symbol * add_to_b(symbol * p, int n, symbol * q) { + int x = SIZE(p) + n - CAPACITY(p); + if (x > 0) p = increase_capacity(p, x); + memmove(p + SIZE(p), q, n * sizeof(symbol)); SIZE(p) += n; return p; +} + +extern symbol * copy_b(symbol * p) { + int n = SIZE(p); + symbol * q = create_b(n); + move_to_b(q, n, p); + return q; +} + +int space_count = 0; + +extern void * check_malloc(int n) { + space_count++; + return malloc(n); +} + +extern void check_free(void * p) { + space_count--; + free(p); +} + +/* To convert a block to a zero terminated string: */ + +extern char * b_to_s(symbol * p) { + int n = SIZE(p); + char * s = (char *)malloc(n + 1); + { + int i; + for (i = 0; i < n; i++) { + if (p[i] > 255) { + printf("In b_to_s, can't convert p[%d] to char because it's 0x%02x\n", i, (int)p[i]); + exit(1); + } + s[i] = (char)p[i]; + } + } + s[n] = 0; + return s; +} + +/* To add a zero terminated string to a block. If p = 0 the + block is created. */ + +extern symbol * add_s_to_b(symbol * p, const char * s) { + int n = strlen(s); + int k; + if (p == 0) p = create_b(n); + k = SIZE(p); + { + int x = k + n - CAPACITY(p); + if (x > 0) p = increase_capacity(p, x); + } + { + int i; + for (i = 0; i < n; i++) p[i + k] = s[i]; + } + SIZE(p) += n; + return p; +} + +/* The next section defines string handling capabilities in terms + of the lower level block handling capabilities of space.c */ +/* -------------------------------------------------------------*/ + +struct str { + symbol * data; +}; + +/* Create a new string. */ +extern struct str * str_new() { + + struct str * output = (struct str *) malloc(sizeof(struct str)); + output->data = create_b(0); + return output; +} + +/* Delete a string. */ +extern void str_delete(struct str * str) { + + lose_b(str->data); + free(str); +} + +/* Append a str to this str. */ +extern void str_append(struct str * str, struct str * add) { + + symbol * q = add->data; + str->data = add_to_b(str->data, SIZE(q), q); +} + +/* Append a character to this str. */ +extern void str_append_ch(struct str * str, char add) { + + symbol q[1]; + q[0] = add; + str->data = add_to_b(str->data, 1, q); +} + +/* Append a low level block to a str. */ +extern void str_append_b(struct str * str, symbol * q) { + + str->data = add_to_b(str->data, SIZE(q), q); +} + +/* Append a (char *, null teminated) string to a str. */ +extern void str_append_string(struct str * str, const char * s) { + + str->data = add_s_to_b(str->data, s); +} + +/* Append an integer to a str. */ +extern void str_append_int(struct str * str, int i) { + + char s[30]; + sprintf(s, "%d", i); + str_append_string(str, s); +} + +/* Clear a string */ +extern void str_clear(struct str * str) { + + SIZE(str->data) = 0; +} + +/* Set a string */ +extern void str_assign(struct str * str, char * s) { + + str_clear(str); + str_append_string(str, s); +} + +/* Copy a string. */ +extern struct str * str_copy(struct str * old) { + + struct str * newstr = str_new(); + str_append(newstr, old); + return newstr; +} + +/* Get the data stored in this str. */ +extern symbol * str_data(struct str * str) { + + return str->data; +} + +/* Get the length of the str. */ +extern int str_len(struct str * str) { + + return SIZE(str->data); +} + +extern int get_utf8(const symbol * p, int * slot) { + int b0, b1; + b0 = *p++; + if (b0 < 0xC0) { /* 1100 0000 */ + * slot = b0; return 1; + } + b1 = *p++; + if (b0 < 0xE0) { /* 1110 0000 */ + * slot = (b0 & 0x1F) << 6 | (b1 & 0x3F); return 2; + } + * slot = (b0 & 0xF) << 12 | (b1 & 0x3F) << 6 | (*p & 0x3F); return 3; +} + +extern int put_utf8(int ch, symbol * p) { + if (ch < 0x80) { + p[0] = ch; return 1; + } + if (ch < 0x800) { + p[0] = (ch >> 6) | 0xC0; + p[1] = (ch & 0x3F) | 0x80; return 2; + } + p[0] = (ch >> 12) | 0xE0; + p[1] = ((ch >> 6) & 0x3F) | 0x80; + p[2] = (ch & 0x3F) | 0x80; return 3; +} + diff --git a/contrib/snowball/compiler/syswords.h b/contrib/snowball/compiler/syswords.h new file mode 100644 index 000000000..917dd5751 --- /dev/null +++ b/contrib/snowball/compiler/syswords.h @@ -0,0 +1,84 @@ +static const struct system_word vocab[80+1] = { + { 0, (const byte *)"", 80+1}, + + { 1, (const byte *)"$", c_dollar }, + { 1, (const byte *)"(", c_bra }, + { 1, (const byte *)")", c_ket }, + { 1, (const byte *)"*", c_multiply }, + { 1, (const byte *)"+", c_plus }, + { 1, (const byte *)"-", c_minus }, + { 1, (const byte *)"/", c_divide }, + { 1, (const byte *)"<", c_ls }, + { 1, (const byte *)"=", c_assign }, + { 1, (const byte *)">", c_gr }, + { 1, (const byte *)"?", c_debug }, + { 1, (const byte *)"[", c_leftslice }, + { 1, (const byte *)"]", c_rightslice }, + { 2, (const byte *)"!=", c_ne }, + { 2, (const byte *)"*=", c_multiplyassign }, + { 2, (const byte *)"+=", c_plusassign }, + { 2, (const byte *)"-=", c_minusassign }, + { 2, (const byte *)"->", c_sliceto }, + { 2, (const byte *)"/*", c_comment2 }, + { 2, (const byte *)"//", c_comment1 }, + { 2, (const byte *)"/=", c_divideassign }, + { 2, (const byte *)"<+", c_insert }, + { 2, (const byte *)"<-", c_slicefrom }, + { 2, (const byte *)"<=", c_le }, + { 2, (const byte *)"==", c_eq }, + { 2, (const byte *)"=>", c_assignto }, + { 2, (const byte *)">=", c_ge }, + { 2, (const byte *)"as", c_as }, + { 2, (const byte *)"do", c_do }, + { 2, (const byte *)"or", c_or }, + { 3, (const byte *)"and", c_and }, + { 3, (const byte *)"for", c_for }, + { 3, (const byte *)"get", c_get }, + { 3, (const byte *)"hex", c_hex }, + { 3, (const byte *)"hop", c_hop }, + { 3, (const byte *)"non", c_non }, + { 3, (const byte *)"not", c_not }, + { 3, (const byte *)"set", c_set }, + { 3, (const byte *)"try", c_try }, + { 4, (const byte *)"fail", c_fail }, + { 4, (const byte *)"goto", c_goto }, + { 4, (const byte *)"loop", c_loop }, + { 4, (const byte *)"next", c_next }, + { 4, (const byte *)"size", c_size }, + { 4, (const byte *)"test", c_test }, + { 4, (const byte *)"true", c_true }, + { 5, (const byte *)"among", c_among }, + { 5, (const byte *)"false", c_false }, + { 5, (const byte *)"limit", c_limit }, + { 5, (const byte *)"unset", c_unset }, + { 6, (const byte *)"atmark", c_atmark }, + { 6, (const byte *)"attach", c_attach }, + { 6, (const byte *)"cursor", c_cursor }, + { 6, (const byte *)"define", c_define }, + { 6, (const byte *)"delete", c_delete }, + { 6, (const byte *)"gopast", c_gopast }, + { 6, (const byte *)"insert", c_insert }, + { 6, (const byte *)"maxint", c_maxint }, + { 6, (const byte *)"minint", c_minint }, + { 6, (const byte *)"repeat", c_repeat }, + { 6, (const byte *)"sizeof", c_sizeof }, + { 6, (const byte *)"tomark", c_tomark }, + { 7, (const byte *)"atleast", c_atleast }, + { 7, (const byte *)"atlimit", c_atlimit }, + { 7, (const byte *)"decimal", c_decimal }, + { 7, (const byte *)"reverse", c_reverse }, + { 7, (const byte *)"setmark", c_setmark }, + { 7, (const byte *)"strings", c_strings }, + { 7, (const byte *)"tolimit", c_tolimit }, + { 8, (const byte *)"booleans", c_booleans }, + { 8, (const byte *)"integers", c_integers }, + { 8, (const byte *)"routines", c_routines }, + { 8, (const byte *)"setlimit", c_setlimit }, + { 9, (const byte *)"backwards", c_backwards }, + { 9, (const byte *)"externals", c_externals }, + { 9, (const byte *)"groupings", c_groupings }, + { 9, (const byte *)"stringdef", c_stringdef }, + { 9, (const byte *)"substring", c_substring }, + { 12, (const byte *)"backwardmode", c_backwardmode }, + { 13, (const byte *)"stringescapes", c_stringescapes } +}; diff --git a/contrib/snowball/compiler/syswords2.h b/contrib/snowball/compiler/syswords2.h new file mode 100644 index 000000000..eb8a91241 --- /dev/null +++ b/contrib/snowball/compiler/syswords2.h @@ -0,0 +1,13 @@ + c_among = 4, c_and, c_as, c_assign, c_assignto, c_atleast, + c_atlimit, c_atmark, c_attach, c_backwardmode, c_backwards, + c_booleans, c_bra, c_comment1, c_comment2, c_cursor, c_debug, + c_decimal, c_define, c_delete, c_divide, c_divideassign, c_do, + c_dollar, c_eq, c_externals, c_fail, c_false, c_for, c_ge, c_get, + c_gopast, c_goto, c_gr, c_groupings, c_hex, c_hop, c_insert, + c_integers, c_ket, c_le, c_leftslice, c_limit, c_loop, c_ls, + c_maxint, c_minint, c_minus, c_minusassign, c_multiply, + c_multiplyassign, c_ne, c_next, c_non, c_not, c_or, c_plus, + c_plusassign, c_repeat, c_reverse, c_rightslice, c_routines, + c_set, c_setlimit, c_setmark, c_size, c_sizeof, c_slicefrom, + c_sliceto, c_stringdef, c_stringescapes, c_strings, c_substring, + c_test, c_tolimit, c_tomark, c_true, c_try, c_unset, diff --git a/contrib/snowball/compiler/tokeniser.c b/contrib/snowball/compiler/tokeniser.c new file mode 100644 index 000000000..3dae5f744 --- /dev/null +++ b/contrib/snowball/compiler/tokeniser.c @@ -0,0 +1,470 @@ + +#include <stdio.h> /* stderr etc */ +#include <stdlib.h> /* malloc free */ +#include <string.h> /* strlen */ +#include <ctype.h> /* isalpha etc */ +#include "header.h" + +struct system_word { + int s_size; /* size of system word */ + const byte * s; /* pointer to the system word */ + int code; /* its internal code */ +}; + + +/* ASCII collating assumed in syswords.c */ + +#include "syswords.h" + +static int smaller(int a, int b) { return a < b ? a : b; } + +extern symbol * get_input(symbol * p, char ** p_file) { + + char * s = b_to_s(p); + { + FILE * input = fopen(s, "r"); + if (input == 0) { free(s); return 0; } + *p_file = s; + { + symbol * u = create_b(STARTSIZE); + int size = 0; + repeat + { int ch = getc(input); + if (ch == EOF) break; + if (size >= CAPACITY(u)) u = increase_capacity(u, size/2); + u[size++] = ch; + } + fclose(input); + SIZE(u) = size; return u; + } + } +} + +static void error(struct tokeniser * t, char * s1, int n, symbol * p, char * s2) { + if (t->error_count == 20) { fprintf(stderr, "... etc\n"); exit(1); } + fprintf(stderr, "%s:%d: ", t->file, t->line_number); + unless (s1 == 0) fprintf(stderr, "%s", s1); + unless (p == 0) { + int i; + for (i = 0; i < n; i++) fprintf(stderr, "%c", p[i]); + } + unless (s2 == 0) fprintf(stderr, "%s", s2); + fprintf(stderr, "\n"); + t->error_count++; +} + +static void error1(struct tokeniser * t, char * s) { + error(t, s, 0,0, 0); +} + +static void error2(struct tokeniser * t, char * s) { + error(t, "unexpected end of text after ", 0,0, s); +} + +static int compare_words(int m, symbol * p, int n, const byte * q) { + unless (m == n) return m - n; + { + int i; for (i = 0; i < n; i++) { + int diff = p[i] - q[i]; + unless (diff == 0) return diff; + } + } + return 0; +} + +static int find_word(int n, symbol * p) { + int i = 0; int j = vocab->code; + repeat { + int k = i + (j - i)/2; + const struct system_word * w = vocab + k; + int diff = compare_words(n, p, w->s_size, w->s); + if (diff == 0) return w->code; + if (diff < 0) j = k; else i = k; + if (j - i == 1) break; + } + return -1; +} + +static int get_number(int n, symbol * p) { + int x = 0; + int i; for (i = 0; i < n; i++) x = 10*x + p[i] - '0'; + return x; +} + +static int eq_s(struct tokeniser * t, char * s) { + int l = strlen(s); + if (SIZE(t->p) - t->c < l) return false; + { + int i; + for (i = 0; i < l; i++) if (t->p[t->c + i] != s[i]) return false; + } + t->c += l; return true; +} + +static int white_space(struct tokeniser * t, int ch) { + switch (ch) { + case '\n': t->line_number++; + case '\r': + case '\t': + case ' ': return true; + } + return false; +} + +static symbol * find_in_m(struct tokeniser * t, int n, symbol * p) { + struct m_pair * q = t->m_pairs; + repeat { + if (q == 0) return 0; + { + symbol * name = q->name; + if (n == SIZE(name) && memcmp(name, p, n * sizeof(symbol)) == 0) return q->value; + } + q = q->next; + } +} + +static int read_literal_string(struct tokeniser * t, int c) { + symbol * p = t->p; + int ch; + SIZE(t->b) = 0; + repeat { + if (c >= SIZE(p)) { error2(t, "'"); return c; } + ch = p[c]; + if (ch == '\n') { error1(t, "string not terminated"); return c; } + c++; + if (ch == t->m_start) { + int c0 = c; + int newlines = false; /* no newlines as yet */ + int black_found = false; /* no printing chars as yet */ + repeat { + if (c >= SIZE(p)) { error2(t, "'"); return c; } + ch = p[c]; c++; + if (ch == t->m_end) break; + unless (white_space(t, ch)) black_found = true; + if (ch == '\n') newlines = true; + if (newlines && black_found) { + error1(t, "string not terminated"); + return c; + } + } + unless (newlines) { + int n = c - c0 - 1; /* macro size */ + int firstch = p[c0]; + symbol * q = find_in_m(t, n, p + c0); + if (q == 0) { + if (n == 1 && (firstch == '\'' || firstch == t->m_start)) + t->b = add_to_b(t->b, 1, p + c0); + else + error(t, "string macro '", n, p + c0, "' undeclared"); + } else + t->b = add_to_b(t->b, SIZE(q), q); + } + } else { + if (ch == '\'') return c; + t->b = add_to_b(t->b, 1, p + c - 1); + } + } +} + +static int next_token(struct tokeniser * t) { + symbol * p = t->p; + int c = t->c; + int ch; + int code = -1; + repeat { + if (c >= SIZE(p)) { t->c = c; return -1; } + ch = p[c]; + if (white_space(t, ch)) { c++; continue; } + if (isalpha(ch)) { + int c0 = c; + while (c < SIZE(p) && (isalnum(p[c]) || p[c] == '_')) c++; + code = find_word(c - c0, p + c0); + if (code < 0) { + t->b = move_to_b(t->b, c - c0, p + c0); + code = c_name; + } + } else + if (isdigit(ch)) { + int c0 = c; + while (c < SIZE(p) && isdigit(p[c])) c++; + t->number = get_number(c - c0, p + c0); + code = c_number; + } else + if (ch == '\'') { + c = read_literal_string(t, c + 1); + code = c_literalstring; + } else + { + int lim = smaller(2, SIZE(p) - c); + int i; + for (i = lim; i > 0; i--) { + code = find_word(i, p + c); + if (code >= 0) { c += i; break; } + } + } + if (code >= 0) { + t->c = c; + return code; + } + error(t, "'", 1, p + c, "' unknown"); + c++; + continue; + } +} + +static int next_char(struct tokeniser * t) { + if (t->c >= SIZE(t->p)) return -1; + return t->p[t->c++]; +} + +static int next_real_char(struct tokeniser * t) { + repeat { + int ch = next_char(t); + if (white_space(t, ch)) continue; + return ch; + } +} + +static void read_chars(struct tokeniser * t) { + int ch = next_real_char(t); + if (ch < 0) { error2(t, "stringdef"); return; } + { + int c0 = t->c-1; + repeat { + ch = next_char(t); + if (white_space(t, ch) || ch < 0) break; + } + t->b2 = move_to_b(t->b2, t->c - c0 - 1, t->p + c0); + } +} + +static int decimal_to_num(int ch) { + if ('0' <= ch && ch <= '9') return ch - '0'; + return -1; +} + +static int hex_to_num(int ch) { + if ('0' <= ch && ch <= '9') return ch - '0'; + if ('a' <= ch && ch <= 'f') return ch - 'a' + 10; + return -1; +} + +static void convert_numeric_string(struct tokeniser * t, symbol * p, int base) { + int c = 0; int d = 0; + repeat { + while (c < SIZE(p) && p[c] == ' ') c++; + if (c == SIZE(p)) break; + { + int number = 0; + repeat { + int ch = p[c]; + if (c == SIZE(p) || ch == ' ') break; + if (base == 10) { + ch = decimal_to_num(ch); + if (ch < 0) { + error1(t, "decimal string contains non-digits"); + return; + } + } else { + ch = hex_to_num(tolower(ch)); + if (ch < 0) { + error1(t, "hex string contains non-hex characters"); + return; + } + } + number = base * number + ch; + c++; + } + if (t->widechars || t->utf8) { + unless (0 <= number && number <= 0xffff) { + error1(t, "character values exceed 64K"); + return; + } + } else { + unless (0 <= number && number <= 0xff) { + error1(t, "character values exceed 256"); + return; + } + } + if (t->utf8) + d += put_utf8(number, p + d); + else + p[d++] = number; + } + } + SIZE(p) = d; +} + +extern int read_token(struct tokeniser * t) { + symbol * p = t->p; + int held = t->token_held; + t->token_held = false; + if (held) return t->token; + repeat { + int code = next_token(t); + switch (code) { + case c_comment1: /* slash-slash comment */ + while (t->c < SIZE(p) && p[t->c] != '\n') t->c++; + continue; + case c_comment2: /* slash-star comment */ + repeat { + if (t->c >= SIZE(p)) { + error1(t, "/* comment not terminated"); + t->token = -1; + return -1; + } + if (p[t->c] == '\n') t->line_number++; + if (eq_s(t, "*/")) break; + t->c++; + } + continue; + case c_stringescapes: + { + int ch1 = next_real_char(t); + int ch2 = next_real_char(t); + if (ch2 < 0) + { error2(t, "stringescapes"); continue; } + if (ch1 == '\'') + { error1(t, "first stringescape cannot be '"); continue; } + t->m_start = ch1; + t->m_end = ch2; + } + continue; + case c_stringdef: + { + int base = 0; + read_chars(t); + code = read_token(t); + if (code == c_hex) { base = 16; code = read_token(t); } else + if (code == c_decimal) { base = 10; code = read_token(t); } + unless (code == c_literalstring) + { error1(t, "string omitted after stringdef"); continue; } + if (base > 0) convert_numeric_string(t, t->b, base); + { NEW(m_pair, q); + q->next = t->m_pairs; + q->name = copy_b(t->b2); + q->value = copy_b(t->b); + t->m_pairs = q; + } + } + continue; + case c_get: + code = read_token(t); + unless (code == c_literalstring) { + error1(t, "string omitted after get"); continue; + } + t->get_depth++; + if (t->get_depth > 10) { + fprintf(stderr, "get directives go 10 deep. Looping?\n"); + exit(1); + } + { + char * file; + NEW(input, q); + symbol * u = get_input(t->b, &file); + if (u == 0) { + struct include * r = t->includes; + until (r == 0) { + symbol * b = copy_b(r->b); + b = add_to_b(b, SIZE(t->b), t->b); + u = get_input(b, &file); + lose_b(b); + unless (u == 0) break; + r = r->next; + } + } + if (u == 0) { + error(t, "Can't get '", SIZE(t->b), t->b, "'"); + exit(1); + } + memmove(q, t, sizeof(struct input)); + t->next = q; + t->p = u; + t->c = 0; + t->file = file; + t->line_number = 1; + } + p = t->p; + continue; + case -1: + unless (t->next == 0) { + lose_b(p); + { + struct input * q = t->next; + memmove(t, q, sizeof(struct input)); p = t->p; + FREE(q); + } + t->get_depth--; + continue; + } + /* drop through */ + default: + t->previous_token = t->token; + t->token = code; + return code; + } + } +} + +extern const char * name_of_token(int code) { + int i; + for (i = 1; i < vocab->code; i++) + if ((vocab + i)->code == code) return (const char *)(vocab + i)->s; + switch (code) { + case c_mathassign: return "="; + case c_name: return "name"; + case c_number: return "number"; + case c_literalstring:return "literal"; + case c_neg: return "neg"; + case c_grouping: return "grouping"; + case c_call: return "call"; + case c_booltest: return "Boolean test"; + case -2: return "start of text"; + case -1: return "end of text"; + default: return "?"; + } +} + +extern struct tokeniser * create_tokeniser(symbol * p, char * file) { + NEW(tokeniser, t); + t->next = 0; + t->p = p; + t->c = 0; + t->file = file; + t->line_number = 1; + t->b = create_b(0); + t->b2 = create_b(0); + t->m_start = -1; + t->m_pairs = 0; + t->get_depth = 0; + t->error_count = 0; + t->token_held = false; + t->token = -2; + t->previous_token = -2; + return t; +} + +extern void close_tokeniser(struct tokeniser * t) { + lose_b(t->b); + lose_b(t->b2); + { + struct m_pair * q = t->m_pairs; + until (q == 0) { + struct m_pair * q_next = q->next; + lose_b(q->name); + lose_b(q->value); + FREE(q); + q = q_next; + } + } + { + struct input * q = t->next; + until (q == 0) { + struct input * q_next = q->next; + FREE(q); + q = q_next; + } + } + free(t->file); + FREE(t); +} diff --git a/contrib/snowball/doc/TODO b/contrib/snowball/doc/TODO new file mode 100644 index 000000000..0cfa1b1a8 --- /dev/null +++ b/contrib/snowball/doc/TODO @@ -0,0 +1,15 @@ +Things to do: + + - Write documentation for how to use libstemmer (as opposed to how stemming + algorithms themselves work). + Currently, the documentation in the include/libstemmer.h header file is + pretty clear and comprehensive, but an overview document wouldn't go amiss. + +Things that would be nice to include at some point. + + - Add version numbers to each stemming algorithm, and allow the interface to + request a specific version of the stemming algorithms. Default to providing + the latest version of the algorithm. + - Make mkmodules.pl generate the build system, instead of being called from it. + This would allow it to generate the list of modules to be built, so that it's + not necessary to change things in more than one place to add a new algorithm. diff --git a/contrib/snowball/doc/libstemmer_c_README b/contrib/snowball/doc/libstemmer_c_README new file mode 100644 index 000000000..9d3af8bec --- /dev/null +++ b/contrib/snowball/doc/libstemmer_c_README @@ -0,0 +1,125 @@ +libstemmer_c +============ + +This document pertains to the C version of the libstemmer distribution, +available for download from: + +http://snowball.tartarus.org/dist/libstemmer_c.tgz + + +Compiling the library +===================== + +A simple makefile is provided for Unix style systems. On such systems, it +should be possible simply to run "make", and the file "libstemmer.o" +and the example program "stemwords" will be generated. + +If this doesn't work on your system, you need to write your own build +system (or call the compiler directly). The files to compile are +all contained in the "libstemmer", "runtime" and "src_c" directories, +and the public header file is contained in the "include" directory. + +The library comes in two flavours; UTF-8 only, and UTF-8 plus other character +sets. To use the utf-8 only flavour, compile "libstemmer_utf8.c" instead of +"libstemmer.c". + +For convenience "mkinc.mak" is a makefile fragment listing the source files and +header files used to compile the standard version of the library. +"mkinc_utf8.mak" is a comparable makefile fragment listing just the source +files for the UTF-8 only version of the library. + + +Using the library +================= + +The library provides a simple C API. Essentially, a new stemmer can +be obtained by using "sb_stemmer_new". "sb_stemmer_stem" is then +used to stem a word, "sb_stemmer_length" returns the stemmed +length of the last word processed, and "sb_stemmer_delete" is +used to delete a stemmer. + +Creating a stemmer is a relatively expensive operation - the expected +usage pattern is that a new stemmer is created when needed, used +to stem many words, and deleted after some time. + +Stemmers are re-entrant, but not threadsafe. In other words, if +you wish to access the same stemmer object from multiple threads, +you must ensure that all access is protected by a mutex or similar +device. + +libstemmer does not currently incorporate any mechanism for caching the results +of stemming operations. Such caching can greatly increase the performance of a +stemmer under certain situations, so suitable patches will be considered for +inclusion. + +The standard libstemmer sources contain an algorithm for each of the supported +languages. The algorithm may be selected using the english name of the +language, or using the 2 or 3 letter ISO 639 language codes. In addition, +the traditional "Porter" stemming algorithm for english is included for +backwards compatibility purposes, but we recommend use of the "English" +stemmer in preference for new projects. + +(Some minor algorithms which are included only as curiosities in the snowball +website, such as the Lovins stemmer and the Kraaij Pohlmann stemmer, are not +included in the standard libstemmer sources. These are not really supported by +the snowball project, but it would be possible to compile a modified libstemmer +library containing these if desired.) + + +The stemwords example +===================== + +The stemwords example program allows you to run any of the stemmers +compiled into the libstemmer library on a sample vocabulary. For +details on how to use it, run it with the "-h" command line option. + + +Using the library in a larger system +==================================== + +If you are incorporating the library into the build system of a larger +program, I recommend copying the unpacked tarball without modification into +a subdirectory of the sources of your program. Future versions of the +library are intended to keep the same structure, so this will keep the +work required to move to a new version of the library to a minimum. + +As an additional convenience, the list of source and header files used +in the library is detailed in mkinc.mak - a file which is in a suitable +format for inclusion by a Makefile. By including this file in your build +system, you can link the snowball system into your program with a few +extra rules. + +Using the library in a system using GNU autotools +================================================= + +The libstemmer_c library can be integrated into a larger system which uses the +GNU autotool framework (and in particular, automake and autoconf) as follows: + +1) Unpack libstemmer_c.tgz in the top level project directory so that there is + a libstemmer_c subdirectory of the top level directory of the project. + +2) Add a file "Makefile.am" to the unpacked libstemmer_c folder, containing: + +noinst_LTLIBRARIES = libstemmer.la +include $(srcdir)/mkinc.mak +noinst_HEADERS = $(snowball_headers) +libstemmer_la_SOURCES = $(snowball_sources) + +(You may also need to add other lines to this, for example, if you are using +compiler options which are not compatible with compiling the libstemmer +library.) + +3) Add libstemmer_c to the AC_CONFIG_FILES declaration in the project's + configure.ac file. + +4) Add to the top level makefile the following lines (or modify existing + assignments to these variables appropriately): + +AUTOMAKE_OPTIONS = subdir-objects +AM_CPPFLAGS = -I$(top_srcdir)/libstemmer_c/include +SUBDIRS=libstemmer_c +<name>_LIBADD = libstemmer_c/libstemmer.la + +(Where <name> is the name of the library or executable which links against +libstemmer.) + diff --git a/contrib/snowball/doc/libstemmer_java_README b/contrib/snowball/doc/libstemmer_java_README new file mode 100644 index 000000000..38b1af693 --- /dev/null +++ b/contrib/snowball/doc/libstemmer_java_README @@ -0,0 +1,40 @@ +libstemmer_java +=============== + +This document pertains to the Java version of the libstemmer distribution, +available for download from: + +http://snowball.tartarus.org/dist/libstemmer_java.tgz + + +Compiling the library +===================== + +Simply run the java compiler on all the java source files under the java +directory. For example, this can be done under unix by changing directory into +the java directory, and running: + + javac org/tartarus/snowball/*.java org/tartarus/snowball/ext/*.java + +This will compile the library and also an example program "TestApp" which +provides a command line interface to the library. + + +Using the library +================= + +There is currently no formal documentation on the use of the Java version +of the library. Additionally, its interface is not guaranteed to be +stable. + +The best documentation of the library is the source of the TestApp example +program. + + +The TestApp example +=================== + +The TestApp example program allows you to run any of the stemmers +compiled into the libstemmer library on a sample vocabulary. For +details on how to use it, run it with no command line parameters. + diff --git a/contrib/snowball/examples/stemwords.c b/contrib/snowball/examples/stemwords.c new file mode 100644 index 000000000..995bf40dc --- /dev/null +++ b/contrib/snowball/examples/stemwords.c @@ -0,0 +1,209 @@ +/* This is a simple program which uses libstemmer to provide a command + * line interface for stemming using any of the algorithms provided. + */ + +#include <stdio.h> +#include <stdlib.h> /* for malloc, free */ +#include <string.h> /* for memmove */ +#include <ctype.h> /* for isupper, tolower */ + +#include "libstemmer.h" + +const char * progname; +static int pretty = 1; + +static void +stem_file(struct sb_stemmer * stemmer, FILE * f_in, FILE * f_out) +{ +#define INC 10 + int lim = INC; + sb_symbol * b = (sb_symbol *) malloc(lim * sizeof(sb_symbol)); + + while(1) { + int ch = getc(f_in); + if (ch == EOF) { + free(b); return; + } + { + int i = 0; + int inlen = 0; + while(1) { + if (ch == '\n' || ch == EOF) break; + if (i == lim) { + sb_symbol * newb; + newb = (sb_symbol *) + realloc(b, (lim + INC) * sizeof(sb_symbol)); + if (newb == 0) goto error; + b = newb; + lim = lim + INC; + } + /* Update count of utf-8 characters. */ + if (ch < 0x80 || ch > 0xBF) inlen += 1; + /* force lower case: */ + if (isupper(ch)) ch = tolower(ch); + + b[i] = ch; + i++; + ch = getc(f_in); + } + + { + const sb_symbol * stemmed = sb_stemmer_stem(stemmer, b, i); + if (stemmed == NULL) + { + fprintf(stderr, "Out of memory"); + exit(1); + } + else + { + if (pretty == 1) { + fwrite(b, i, 1, f_out); + fputs(" -> ", f_out); + } else if (pretty == 2) { + fwrite(b, i, 1, f_out); + if (sb_stemmer_length(stemmer) > 0) { + int j; + if (inlen < 30) { + for (j = 30 - inlen; j > 0; j--) + fputs(" ", f_out); + } else { + fputs("\n", f_out); + for (j = 30; j > 0; j--) + fputs(" ", f_out); + } + } + } + + fputs((const char *)stemmed, f_out); + putc('\n', f_out); + } + } + } + } +error: + if (b != 0) free(b); + return; +} + +/** Display the command line syntax, and then exit. + * @param n The value to exit with. + */ +static void +usage(int n) +{ + printf("usage: %s [-l <language>] [-i <input file>] [-o <output file>] [-c <character encoding>] [-p[2]] [-h]\n" + "\n" + "The input file consists of a list of words to be stemmed, one per\n" + "line. Words should be in lower case, but (for English) A-Z letters\n" + "are mapped to their a-z equivalents anyway. If omitted, stdin is\n" + "used.\n" + "\n" + "If -c is given, the argument is the character encoding of the input\n" + "and output files. If it is omitted, the UTF-8 encoding is used.\n" + "\n" + "If -p is given the output file consists of each word of the input\n" + "file followed by \"->\" followed by its stemmed equivalent.\n" + "If -p2 is given the output file is a two column layout containing\n" + "the input words in the first column and the stemmed equivalents in\n" + "the second column.\n" + "Otherwise, the output file consists of the stemmed words, one per\n" + "line.\n" + "\n" + "-h displays this help\n", + progname); + exit(n); +} + +int +main(int argc, char * argv[]) +{ + char * in = 0; + char * out = 0; + FILE * f_in; + FILE * f_out; + struct sb_stemmer * stemmer; + + char * language = "english"; + char * charenc = NULL; + + char * s; + int i = 1; + pretty = 0; + + progname = argv[0]; + + while(i < argc) { + s = argv[i++]; + if (s[0] == '-') { + if (strcmp(s, "-o") == 0) { + if (i >= argc) { + fprintf(stderr, "%s requires an argument\n", s); + exit(1); + } + out = argv[i++]; + } else if (strcmp(s, "-i") == 0) { + if (i >= argc) { + fprintf(stderr, "%s requires an argument\n", s); + exit(1); + } + in = argv[i++]; + } else if (strcmp(s, "-l") == 0) { + if (i >= argc) { + fprintf(stderr, "%s requires an argument\n", s); + exit(1); + } + language = argv[i++]; + } else if (strcmp(s, "-c") == 0) { + if (i >= argc) { + fprintf(stderr, "%s requires an argument\n", s); + exit(1); + } + charenc = argv[i++]; + } else if (strcmp(s, "-p2") == 0) { + pretty = 2; + } else if (strcmp(s, "-p") == 0) { + pretty = 1; + } else if (strcmp(s, "-h") == 0) { + usage(0); + } else { + fprintf(stderr, "option %s unknown\n", s); + usage(1); + } + } else { + fprintf(stderr, "unexpected parameter %s\n", s); + usage(1); + } + } + + /* prepare the files */ + f_in = (in == 0) ? stdin : fopen(in, "r"); + if (f_in == 0) { + fprintf(stderr, "file %s not found\n", in); + exit(1); + } + f_out = (out == 0) ? stdout : fopen(out, "w"); + if (f_out == 0) { + fprintf(stderr, "file %s cannot be opened\n", out); + exit(1); + } + + /* do the stemming process: */ + stemmer = sb_stemmer_new(language, charenc); + if (stemmer == 0) { + if (charenc == NULL) { + fprintf(stderr, "language `%s' not available for stemming\n", language); + exit(1); + } else { + fprintf(stderr, "language `%s' not available for stemming in encoding `%s'\n", language, charenc); + exit(1); + } + } + stem_file(stemmer, f_in, f_out); + sb_stemmer_delete(stemmer); + + if (in != 0) (void) fclose(f_in); + if (out != 0) (void) fclose(f_out); + + return 0; +} + diff --git a/contrib/snowball/include/libstemmer.h b/contrib/snowball/include/libstemmer.h new file mode 100644 index 000000000..9d86b8581 --- /dev/null +++ b/contrib/snowball/include/libstemmer.h @@ -0,0 +1,79 @@ + +/* Make header file work when included from C++ */ +#ifdef __cplusplus +extern "C" { +#endif + +struct sb_stemmer; +typedef unsigned char sb_symbol; + +/* FIXME - should be able to get a version number for each stemming + * algorithm (which will be incremented each time the output changes). */ + +/** Returns an array of the names of the available stemming algorithms. + * Note that these are the canonical names - aliases (ie, other names for + * the same algorithm) will not be included in the list. + * The list is terminated with a null pointer. + * + * The list must not be modified in any way. + */ +const char ** sb_stemmer_list(void); + +/** Create a new stemmer object, using the specified algorithm, for the + * specified character encoding. + * + * All algorithms will usually be available in UTF-8, but may also be + * available in other character encodings. + * + * @param algorithm The algorithm name. This is either the english + * name of the algorithm, or the 2 or 3 letter ISO 639 codes for the + * language. Note that case is significant in this parameter - the + * value should be supplied in lower case. + * + * @param charenc The character encoding. NULL may be passed as + * this value, in which case UTF-8 encoding will be assumed. Otherwise, + * the argument may be one of "UTF_8", "ISO_8859_1" (ie, Latin 1), + * "CP850" (ie, MS-DOS Latin 1) or "KOI8_R" (Russian). Note that + * case is significant in this parameter. + * + * @return NULL if the specified algorithm is not recognised, or the + * algorithm is not available for the requested encoding. Otherwise, + * returns a pointer to a newly created stemmer for the requested algorithm. + * The returned pointer must be deleted by calling sb_stemmer_delete(). + * + * @note NULL will also be returned if an out of memory error occurs. + */ +struct sb_stemmer * sb_stemmer_new(const char * algorithm, const char * charenc); + +/** Delete a stemmer object. + * + * This frees all resources allocated for the stemmer. After calling + * this function, the supplied stemmer may no longer be used in any way. + * + * It is safe to pass a null pointer to this function - this will have + * no effect. + */ +void sb_stemmer_delete(struct sb_stemmer * stemmer); + +/** Stem a word. + * + * The return value is owned by the stemmer - it must not be freed or + * modified, and it will become invalid when the stemmer is called again, + * or if the stemmer is freed. + * + * The length of the return value can be obtained using sb_stemmer_length(). + * + * If an out-of-memory error occurs, this will return NULL. + */ +const sb_symbol * sb_stemmer_stem(struct sb_stemmer * stemmer, + const sb_symbol * word, int size); + +/** Get the length of the result of the last stemmed word. + * This should not be called before sb_stemmer_stem() has been called. + */ +int sb_stemmer_length(struct sb_stemmer * stemmer); + +#ifdef __cplusplus +} +#endif + diff --git a/contrib/snowball/java/org/tartarus/snowball/Among.java b/contrib/snowball/java/org/tartarus/snowball/Among.java new file mode 100644 index 000000000..5ed37b503 --- /dev/null +++ b/contrib/snowball/java/org/tartarus/snowball/Among.java @@ -0,0 +1,31 @@ +package org.tartarus.snowball; + +import java.lang.reflect.Method; + +public class Among { + public Among (String s, int substring_i, int result, + String methodname, SnowballProgram methodobject) { + this.s_size = s.length(); + this.s = s.toCharArray(); + this.substring_i = substring_i; + this.result = result; + this.methodobject = methodobject; + if (methodname.length() == 0) { + this.method = null; + } else { + try { + this.method = methodobject.getClass(). + getDeclaredMethod(methodname, new Class[0]); + } catch (NoSuchMethodException e) { + throw new RuntimeException(e); + } + } + } + + public final int s_size; /* search string */ + public final char[] s; /* search string */ + public final int substring_i; /* index to longest matching substring */ + public final int result; /* result of the lookup */ + public final Method method; /* method to use if substring matches */ + public final SnowballProgram methodobject; /* object to invoke method on */ +}; diff --git a/contrib/snowball/java/org/tartarus/snowball/SnowballProgram.java b/contrib/snowball/java/org/tartarus/snowball/SnowballProgram.java new file mode 100644 index 000000000..52d6baa78 --- /dev/null +++ b/contrib/snowball/java/org/tartarus/snowball/SnowballProgram.java @@ -0,0 +1,432 @@ + +package org.tartarus.snowball; +import java.lang.reflect.InvocationTargetException; + +public class SnowballProgram { + protected SnowballProgram() + { + current = new StringBuffer(); + setCurrent(""); + } + + /** + * Set the current string. + */ + public void setCurrent(String value) + { + current.replace(0, current.length(), value); + cursor = 0; + limit = current.length(); + limit_backward = 0; + bra = cursor; + ket = limit; + } + + /** + * Get the current string. + */ + public String getCurrent() + { + String result = current.toString(); + // Make a new StringBuffer. If we reuse the old one, and a user of + // the library keeps a reference to the buffer returned (for example, + // by converting it to a String in a way which doesn't force a copy), + // the buffer size will not decrease, and we will risk wasting a large + // amount of memory. + // Thanks to Wolfram Esser for spotting this problem. + current = new StringBuffer(); + return result; + } + + // current string + protected StringBuffer current; + + protected int cursor; + protected int limit; + protected int limit_backward; + protected int bra; + protected int ket; + + protected void copy_from(SnowballProgram other) + { + current = other.current; + cursor = other.cursor; + limit = other.limit; + limit_backward = other.limit_backward; + bra = other.bra; + ket = other.ket; + } + + protected boolean in_grouping(char [] s, int min, int max) + { + if (cursor >= limit) return false; + char ch = current.charAt(cursor); + if (ch > max || ch < min) return false; + ch -= min; + if ((s[ch >> 3] & (0X1 << (ch & 0X7))) == 0) return false; + cursor++; + return true; + } + + protected boolean in_grouping_b(char [] s, int min, int max) + { + if (cursor <= limit_backward) return false; + char ch = current.charAt(cursor - 1); + if (ch > max || ch < min) return false; + ch -= min; + if ((s[ch >> 3] & (0X1 << (ch & 0X7))) == 0) return false; + cursor--; + return true; + } + + protected boolean out_grouping(char [] s, int min, int max) + { + if (cursor >= limit) return false; + char ch = current.charAt(cursor); + if (ch > max || ch < min) { + cursor++; + return true; + } + ch -= min; + if ((s[ch >> 3] & (0X1 << (ch & 0X7))) == 0) { + cursor ++; + return true; + } + return false; + } + + protected boolean out_grouping_b(char [] s, int min, int max) + { + if (cursor <= limit_backward) return false; + char ch = current.charAt(cursor - 1); + if (ch > max || ch < min) { + cursor--; + return true; + } + ch -= min; + if ((s[ch >> 3] & (0X1 << (ch & 0X7))) == 0) { + cursor--; + return true; + } + return false; + } + + protected boolean in_range(int min, int max) + { + if (cursor >= limit) return false; + char ch = current.charAt(cursor); + if (ch > max || ch < min) return false; + cursor++; + return true; + } + + protected boolean in_range_b(int min, int max) + { + if (cursor <= limit_backward) return false; + char ch = current.charAt(cursor - 1); + if (ch > max || ch < min) return false; + cursor--; + return true; + } + + protected boolean out_range(int min, int max) + { + if (cursor >= limit) return false; + char ch = current.charAt(cursor); + if (!(ch > max || ch < min)) return false; + cursor++; + return true; + } + + protected boolean out_range_b(int min, int max) + { + if (cursor <= limit_backward) return false; + char ch = current.charAt(cursor - 1); + if(!(ch > max || ch < min)) return false; + cursor--; + return true; + } + + protected boolean eq_s(int s_size, String s) + { + if (limit - cursor < s_size) return false; + int i; + for (i = 0; i != s_size; i++) { + if (current.charAt(cursor + i) != s.charAt(i)) return false; + } + cursor += s_size; + return true; + } + + protected boolean eq_s_b(int s_size, String s) + { + if (cursor - limit_backward < s_size) return false; + int i; + for (i = 0; i != s_size; i++) { + if (current.charAt(cursor - s_size + i) != s.charAt(i)) return false; + } + cursor -= s_size; + return true; + } + + protected boolean eq_v(CharSequence s) + { + return eq_s(s.length(), s.toString()); + } + + protected boolean eq_v_b(CharSequence s) + { return eq_s_b(s.length(), s.toString()); + } + + protected int find_among(Among v[], int v_size) + { + int i = 0; + int j = v_size; + + int c = cursor; + int l = limit; + + int common_i = 0; + int common_j = 0; + + boolean first_key_inspected = false; + + while(true) { + int k = i + ((j - i) >> 1); + int diff = 0; + int common = common_i < common_j ? common_i : common_j; // smaller + Among w = v[k]; + int i2; + for (i2 = common; i2 < w.s_size; i2++) { + if (c + common == l) { + diff = -1; + break; + } + diff = current.charAt(c + common) - w.s[i2]; + if (diff != 0) break; + common++; + } + if (diff < 0) { + j = k; + common_j = common; + } else { + i = k; + common_i = common; + } + if (j - i <= 1) { + if (i > 0) break; // v->s has been inspected + if (j == i) break; // only one item in v + + // - but now we need to go round once more to get + // v->s inspected. This looks messy, but is actually + // the optimal approach. + + if (first_key_inspected) break; + first_key_inspected = true; + } + } + while(true) { + Among w = v[i]; + if (common_i >= w.s_size) { + cursor = c + w.s_size; + if (w.method == null) return w.result; + boolean res; + try { + Object resobj = w.method.invoke(w.methodobject, + new Object[0]); + res = resobj.toString().equals("true"); + } catch (InvocationTargetException e) { + res = false; + // FIXME - debug message + } catch (IllegalAccessException e) { + res = false; + // FIXME - debug message + } + cursor = c + w.s_size; + if (res) return w.result; + } + i = w.substring_i; + if (i < 0) return 0; + } + } + + // find_among_b is for backwards processing. Same comments apply + protected int find_among_b(Among v[], int v_size) + { + int i = 0; + int j = v_size; + + int c = cursor; + int lb = limit_backward; + + int common_i = 0; + int common_j = 0; + + boolean first_key_inspected = false; + + while(true) { + int k = i + ((j - i) >> 1); + int diff = 0; + int common = common_i < common_j ? common_i : common_j; + Among w = v[k]; + int i2; + for (i2 = w.s_size - 1 - common; i2 >= 0; i2--) { + if (c - common == lb) { + diff = -1; + break; + } + diff = current.charAt(c - 1 - common) - w.s[i2]; + if (diff != 0) break; + common++; + } + if (diff < 0) { + j = k; + common_j = common; + } else { + i = k; + common_i = common; + } + if (j - i <= 1) { + if (i > 0) break; + if (j == i) break; + if (first_key_inspected) break; + first_key_inspected = true; + } + } + while(true) { + Among w = v[i]; + if (common_i >= w.s_size) { + cursor = c - w.s_size; + if (w.method == null) return w.result; + + boolean res; + try { + Object resobj = w.method.invoke(w.methodobject, + new Object[0]); + res = resobj.toString().equals("true"); + } catch (InvocationTargetException e) { + res = false; + // FIXME - debug message + } catch (IllegalAccessException e) { + res = false; + // FIXME - debug message + } + cursor = c - w.s_size; + if (res) return w.result; + } + i = w.substring_i; + if (i < 0) return 0; + } + } + + /* to replace chars between c_bra and c_ket in current by the + * chars in s. + */ + protected int replace_s(int c_bra, int c_ket, String s) + { + int adjustment = s.length() - (c_ket - c_bra); + current.replace(c_bra, c_ket, s); + limit += adjustment; + if (cursor >= c_ket) cursor += adjustment; + else if (cursor > c_bra) cursor = c_bra; + return adjustment; + } + + protected void slice_check() + { + if (bra < 0 || + bra > ket || + ket > limit || + limit > current.length()) // this line could be removed + { + System.err.println("faulty slice operation"); + // FIXME: report error somehow. + /* + fprintf(stderr, "faulty slice operation:\n"); + debug(z, -1, 0); + exit(1); + */ + } + } + + protected void slice_from(String s) + { + slice_check(); + replace_s(bra, ket, s); + } + + protected void slice_from(CharSequence s) + { + slice_from(s.toString()); + } + + protected void slice_del() + { + slice_from(""); + } + + protected void insert(int c_bra, int c_ket, String s) + { + int adjustment = replace_s(c_bra, c_ket, s); + if (c_bra <= bra) bra += adjustment; + if (c_bra <= ket) ket += adjustment; + } + + protected void insert(int c_bra, int c_ket, CharSequence s) + { + insert(c_bra, c_ket, s.toString()); + } + + /* Copy the slice into the supplied StringBuffer */ + protected StringBuffer slice_to(StringBuffer s) + { + slice_check(); + int len = ket - bra; + s.replace(0, s.length(), current.substring(bra, ket)); + return s; + } + + /* Copy the slice into the supplied StringBuilder */ + protected StringBuilder slice_to(StringBuilder s) + { + slice_check(); + int len = ket - bra; + s.replace(0, s.length(), current.substring(bra, ket)); + return s; + } + + protected StringBuffer assign_to(StringBuffer s) + { + s.replace(0, s.length(), current.substring(0, limit)); + return s; + } + + protected StringBuilder assign_to(StringBuilder s) + { + s.replace(0, s.length(), current.substring(0, limit)); + return s; + } + +/* +extern void debug(struct SN_env * z, int number, int line_count) +{ int i; + int limit = SIZE(z->p); + //if (number >= 0) printf("%3d (line %4d): '", number, line_count); + if (number >= 0) printf("%3d (line %4d): [%d]'", number, line_count,limit); + for (i = 0; i <= limit; i++) + { if (z->lb == i) printf("{"); + if (z->bra == i) printf("["); + if (z->c == i) printf("|"); + if (z->ket == i) printf("]"); + if (z->l == i) printf("}"); + if (i < limit) + { int ch = z->p[i]; + if (ch == 0) ch = '#'; + printf("%c", ch); + } + } + printf("'\n"); +} +*/ + +}; diff --git a/contrib/snowball/java/org/tartarus/snowball/SnowballStemmer.java b/contrib/snowball/java/org/tartarus/snowball/SnowballStemmer.java new file mode 100644 index 000000000..960bd55f6 --- /dev/null +++ b/contrib/snowball/java/org/tartarus/snowball/SnowballStemmer.java @@ -0,0 +1,7 @@ + +package org.tartarus.snowball; +import java.lang.reflect.InvocationTargetException; + +public abstract class SnowballStemmer extends SnowballProgram { + public abstract boolean stem(); +}; diff --git a/contrib/snowball/java/org/tartarus/snowball/TestApp.java b/contrib/snowball/java/org/tartarus/snowball/TestApp.java new file mode 100644 index 000000000..38803f673 --- /dev/null +++ b/contrib/snowball/java/org/tartarus/snowball/TestApp.java @@ -0,0 +1,77 @@ + +package org.tartarus.snowball; + +import java.lang.reflect.Method; +import java.io.Reader; +import java.io.Writer; +import java.io.BufferedReader; +import java.io.BufferedWriter; +import java.io.FileInputStream; +import java.io.InputStreamReader; +import java.io.OutputStreamWriter; +import java.io.OutputStream; +import java.io.FileOutputStream; + +public class TestApp { + private static void usage() + { + System.err.println("Usage: TestApp <algorithm> <input file> [-o <output file>]"); + } + + public static void main(String [] args) throws Throwable { + if (args.length < 2) { + usage(); + return; + } + + Class stemClass = Class.forName("org.tartarus.snowball.ext." + + args[0] + "Stemmer"); + SnowballStemmer stemmer = (SnowballStemmer) stemClass.newInstance(); + + Reader reader; + reader = new InputStreamReader(new FileInputStream(args[1])); + reader = new BufferedReader(reader); + + StringBuffer input = new StringBuffer(); + + OutputStream outstream; + + if (args.length > 2) { + if (args.length >= 4 && args[2].equals("-o")) { + outstream = new FileOutputStream(args[3]); + } else { + usage(); + return; + } + } else { + outstream = System.out; + } + Writer output = new OutputStreamWriter(outstream); + output = new BufferedWriter(output); + + int repeat = 1; + if (args.length > 4) { + repeat = Integer.parseInt(args[4]); + } + + Object [] emptyArgs = new Object[0]; + int character; + while ((character = reader.read()) != -1) { + char ch = (char) character; + if (Character.isWhitespace((char) ch)) { + if (input.length() > 0) { + stemmer.setCurrent(input.toString()); + for (int i = repeat; i != 0; i--) { + stemmer.stem(); + } + output.write(stemmer.getCurrent()); + output.write('\n'); + input.delete(0, input.length()); + } + } else { + input.append(Character.toLowerCase(ch)); + } + } + output.flush(); + } +} diff --git a/contrib/snowball/runtime/api.c b/contrib/snowball/runtime/api.c new file mode 100644 index 000000000..40039ef4a --- /dev/null +++ b/contrib/snowball/runtime/api.c @@ -0,0 +1,66 @@ + +#include <stdlib.h> /* for calloc, free */ +#include "header.h" + +extern struct SN_env * SN_create_env(int S_size, int I_size, int B_size) +{ + struct SN_env * z = (struct SN_env *) calloc(1, sizeof(struct SN_env)); + if (z == NULL) return NULL; + z->p = create_s(); + if (z->p == NULL) goto error; + if (S_size) + { + int i; + z->S = (symbol * *) calloc(S_size, sizeof(symbol *)); + if (z->S == NULL) goto error; + + for (i = 0; i < S_size; i++) + { + z->S[i] = create_s(); + if (z->S[i] == NULL) goto error; + } + } + + if (I_size) + { + z->I = (int *) calloc(I_size, sizeof(int)); + if (z->I == NULL) goto error; + } + + if (B_size) + { + z->B = (unsigned char *) calloc(B_size, sizeof(unsigned char)); + if (z->B == NULL) goto error; + } + + return z; +error: + SN_close_env(z, S_size); + return NULL; +} + +extern void SN_close_env(struct SN_env * z, int S_size) +{ + if (z == NULL) return; + if (S_size) + { + int i; + for (i = 0; i < S_size; i++) + { + lose_s(z->S[i]); + } + free(z->S); + } + free(z->I); + free(z->B); + if (z->p) lose_s(z->p); + free(z); +} + +extern int SN_set_current(struct SN_env * z, int size, const symbol * s) +{ + int err = replace_s(z, 0, z->l, size, s, NULL); + z->c = 0; + return err; +} + diff --git a/contrib/snowball/runtime/api.h b/contrib/snowball/runtime/api.h new file mode 100644 index 000000000..8b997f0c2 --- /dev/null +++ b/contrib/snowball/runtime/api.h @@ -0,0 +1,26 @@ + +typedef unsigned char symbol; + +/* Or replace 'char' above with 'short' for 16 bit characters. + + More precisely, replace 'char' with whatever type guarantees the + character width you need. Note however that sizeof(symbol) should divide + HEAD, defined in header.h as 2*sizeof(int), without remainder, otherwise + there is an alignment problem. In the unlikely event of a problem here, + consult Martin Porter. + +*/ + +struct SN_env { + symbol * p; + int c; int l; int lb; int bra; int ket; + symbol * * S; + int * I; + unsigned char * B; +}; + +extern struct SN_env * SN_create_env(int S_size, int I_size, int B_size); +extern void SN_close_env(struct SN_env * z, int S_size); + +extern int SN_set_current(struct SN_env * z, int size, const symbol * s); + diff --git a/contrib/snowball/runtime/header.h b/contrib/snowball/runtime/header.h new file mode 100644 index 000000000..4d3078f50 --- /dev/null +++ b/contrib/snowball/runtime/header.h @@ -0,0 +1,58 @@ + +#include <limits.h> + +#include "api.h" + +#define MAXINT INT_MAX +#define MININT INT_MIN + +#define HEAD 2*sizeof(int) + +#define SIZE(p) ((int *)(p))[-1] +#define SET_SIZE(p, n) ((int *)(p))[-1] = n +#define CAPACITY(p) ((int *)(p))[-2] + +struct among +{ int s_size; /* number of chars in string */ + const symbol * s; /* search string */ + int substring_i;/* index to longest matching substring */ + int result; /* result of the lookup */ + int (* function)(struct SN_env *); +}; + +extern symbol * create_s(void); +extern void lose_s(symbol * p); + +extern int skip_utf8(const symbol * p, int c, int lb, int l, int n); + +extern int in_grouping_U(struct SN_env * z, const unsigned char * s, int min, int max, int repeat); +extern int in_grouping_b_U(struct SN_env * z, const unsigned char * s, int min, int max, int repeat); +extern int out_grouping_U(struct SN_env * z, const unsigned char * s, int min, int max, int repeat); +extern int out_grouping_b_U(struct SN_env * z, const unsigned char * s, int min, int max, int repeat); + +extern int in_grouping(struct SN_env * z, const unsigned char * s, int min, int max, int repeat); +extern int in_grouping_b(struct SN_env * z, const unsigned char * s, int min, int max, int repeat); +extern int out_grouping(struct SN_env * z, const unsigned char * s, int min, int max, int repeat); +extern int out_grouping_b(struct SN_env * z, const unsigned char * s, int min, int max, int repeat); + +extern int eq_s(struct SN_env * z, int s_size, const symbol * s); +extern int eq_s_b(struct SN_env * z, int s_size, const symbol * s); +extern int eq_v(struct SN_env * z, const symbol * p); +extern int eq_v_b(struct SN_env * z, const symbol * p); + +extern int find_among(struct SN_env * z, const struct among * v, int v_size); +extern int find_among_b(struct SN_env * z, const struct among * v, int v_size); + +extern int replace_s(struct SN_env * z, int c_bra, int c_ket, int s_size, const symbol * s, int * adjustment); +extern int slice_from_s(struct SN_env * z, int s_size, const symbol * s); +extern int slice_from_v(struct SN_env * z, const symbol * p); +extern int slice_del(struct SN_env * z); + +extern int insert_s(struct SN_env * z, int bra, int ket, int s_size, const symbol * s); +extern int insert_v(struct SN_env * z, int bra, int ket, const symbol * p); + +extern symbol * slice_to(struct SN_env * z, symbol * p); +extern symbol * assign_to(struct SN_env * z, symbol * p); + +extern void debug(struct SN_env * z, int number, int line_count); + diff --git a/contrib/snowball/runtime/utilities.c b/contrib/snowball/runtime/utilities.c new file mode 100644 index 000000000..1840f0280 --- /dev/null +++ b/contrib/snowball/runtime/utilities.c @@ -0,0 +1,478 @@ + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include "header.h" + +#define unless(C) if(!(C)) + +#define CREATE_SIZE 1 + +extern symbol * create_s(void) { + symbol * p; + void * mem = malloc(HEAD + (CREATE_SIZE + 1) * sizeof(symbol)); + if (mem == NULL) return NULL; + p = (symbol *) (HEAD + (char *) mem); + CAPACITY(p) = CREATE_SIZE; + SET_SIZE(p, CREATE_SIZE); + return p; +} + +extern void lose_s(symbol * p) { + if (p == NULL) return; + free((char *) p - HEAD); +} + +/* + new_p = skip_utf8(p, c, lb, l, n); skips n characters forwards from p + c + if n +ve, or n characters backwards from p + c - 1 if n -ve. new_p is the new + position, or 0 on failure. + + -- used to implement hop and next in the utf8 case. +*/ + +extern int skip_utf8(const symbol * p, int c, int lb, int l, int n) { + int b; + if (n >= 0) { + for (; n > 0; n--) { + if (c >= l) return -1; + b = p[c++]; + if (b >= 0xC0) { /* 1100 0000 */ + while (c < l) { + b = p[c]; + if (b >= 0xC0 || b < 0x80) break; + /* break unless b is 10------ */ + c++; + } + } + } + } else { + for (; n < 0; n++) { + if (c <= lb) return -1; + b = p[--c]; + if (b >= 0x80) { /* 1000 0000 */ + while (c > lb) { + b = p[c]; + if (b >= 0xC0) break; /* 1100 0000 */ + c--; + } + } + } + } + return c; +} + +/* Code for character groupings: utf8 cases */ + +static int get_utf8(const symbol * p, int c, int l, int * slot) { + int b0, b1; + if (c >= l) return 0; + b0 = p[c++]; + if (b0 < 0xC0 || c == l) { /* 1100 0000 */ + * slot = b0; return 1; + } + b1 = p[c++]; + if (b0 < 0xE0 || c == l) { /* 1110 0000 */ + * slot = (b0 & 0x1F) << 6 | (b1 & 0x3F); return 2; + } + * slot = (b0 & 0xF) << 12 | (b1 & 0x3F) << 6 | (p[c] & 0x3F); return 3; +} + +static int get_b_utf8(const symbol * p, int c, int lb, int * slot) { + int b0, b1; + if (c <= lb) return 0; + b0 = p[--c]; + if (b0 < 0x80 || c == lb) { /* 1000 0000 */ + * slot = b0; return 1; + } + b1 = p[--c]; + if (b1 >= 0xC0 || c == lb) { /* 1100 0000 */ + * slot = (b1 & 0x1F) << 6 | (b0 & 0x3F); return 2; + } + * slot = (p[c] & 0xF) << 12 | (b1 & 0x3F) << 6 | (b0 & 0x3F); return 3; +} + +extern int in_grouping_U(struct SN_env * z, const unsigned char * s, int min, int max, int repeat) { + do { + int ch; + int w = get_utf8(z->p, z->c, z->l, & ch); + unless (w) return -1; + if (ch > max || (ch -= min) < 0 || (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0) + return w; + z->c += w; + } while (repeat); + return 0; +} + +extern int in_grouping_b_U(struct SN_env * z, const unsigned char * s, int min, int max, int repeat) { + do { + int ch; + int w = get_b_utf8(z->p, z->c, z->lb, & ch); + unless (w) return -1; + if (ch > max || (ch -= min) < 0 || (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0) + return w; + z->c -= w; + } while (repeat); + return 0; +} + +extern int out_grouping_U(struct SN_env * z, const unsigned char * s, int min, int max, int repeat) { + do { + int ch; + int w = get_utf8(z->p, z->c, z->l, & ch); + unless (w) return -1; + unless (ch > max || (ch -= min) < 0 || (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0) + return w; + z->c += w; + } while (repeat); + return 0; +} + +extern int out_grouping_b_U(struct SN_env * z, const unsigned char * s, int min, int max, int repeat) { + do { + int ch; + int w = get_b_utf8(z->p, z->c, z->lb, & ch); + unless (w) return -1; + unless (ch > max || (ch -= min) < 0 || (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0) + return w; + z->c -= w; + } while (repeat); + return 0; +} + +/* Code for character groupings: non-utf8 cases */ + +extern int in_grouping(struct SN_env * z, const unsigned char * s, int min, int max, int repeat) { + do { + int ch; + if (z->c >= z->l) return -1; + ch = z->p[z->c]; + if (ch > max || (ch -= min) < 0 || (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0) + return 1; + z->c++; + } while (repeat); + return 0; +} + +extern int in_grouping_b(struct SN_env * z, const unsigned char * s, int min, int max, int repeat) { + do { + int ch; + if (z->c <= z->lb) return -1; + ch = z->p[z->c - 1]; + if (ch > max || (ch -= min) < 0 || (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0) + return 1; + z->c--; + } while (repeat); + return 0; +} + +extern int out_grouping(struct SN_env * z, const unsigned char * s, int min, int max, int repeat) { + do { + int ch; + if (z->c >= z->l) return -1; + ch = z->p[z->c]; + unless (ch > max || (ch -= min) < 0 || (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0) + return 1; + z->c++; + } while (repeat); + return 0; +} + +extern int out_grouping_b(struct SN_env * z, const unsigned char * s, int min, int max, int repeat) { + do { + int ch; + if (z->c <= z->lb) return -1; + ch = z->p[z->c - 1]; + unless (ch > max || (ch -= min) < 0 || (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0) + return 1; + z->c--; + } while (repeat); + return 0; +} + +extern int eq_s(struct SN_env * z, int s_size, const symbol * s) { + if (z->l - z->c < s_size || memcmp(z->p + z->c, s, s_size * sizeof(symbol)) != 0) return 0; + z->c += s_size; return 1; +} + +extern int eq_s_b(struct SN_env * z, int s_size, const symbol * s) { + if (z->c - z->lb < s_size || memcmp(z->p + z->c - s_size, s, s_size * sizeof(symbol)) != 0) return 0; + z->c -= s_size; return 1; +} + +extern int eq_v(struct SN_env * z, const symbol * p) { + return eq_s(z, SIZE(p), p); +} + +extern int eq_v_b(struct SN_env * z, const symbol * p) { + return eq_s_b(z, SIZE(p), p); +} + +extern int find_among(struct SN_env * z, const struct among * v, int v_size) { + + int i = 0; + int j = v_size; + + int c = z->c; int l = z->l; + symbol * q = z->p + c; + + const struct among * w; + + int common_i = 0; + int common_j = 0; + + int first_key_inspected = 0; + + while(1) { + int k = i + ((j - i) >> 1); + int diff = 0; + int common = common_i < common_j ? common_i : common_j; /* smaller */ + w = v + k; + { + int i2; for (i2 = common; i2 < w->s_size; i2++) { + if (c + common == l) { diff = -1; break; } + diff = q[common] - w->s[i2]; + if (diff != 0) break; + common++; + } + } + if (diff < 0) { j = k; common_j = common; } + else { i = k; common_i = common; } + if (j - i <= 1) { + if (i > 0) break; /* v->s has been inspected */ + if (j == i) break; /* only one item in v */ + + /* - but now we need to go round once more to get + v->s inspected. This looks messy, but is actually + the optimal approach. */ + + if (first_key_inspected) break; + first_key_inspected = 1; + } + } + while(1) { + w = v + i; + if (common_i >= w->s_size) { + z->c = c + w->s_size; + if (w->function == 0) return w->result; + { + int res = w->function(z); + z->c = c + w->s_size; + if (res) return w->result; + } + } + i = w->substring_i; + if (i < 0) return 0; + } +} + +/* find_among_b is for backwards processing. Same comments apply */ + +extern int find_among_b(struct SN_env * z, const struct among * v, int v_size) { + + int i = 0; + int j = v_size; + + int c = z->c; int lb = z->lb; + symbol * q = z->p + c - 1; + + const struct among * w; + + int common_i = 0; + int common_j = 0; + + int first_key_inspected = 0; + + while(1) { + int k = i + ((j - i) >> 1); + int diff = 0; + int common = common_i < common_j ? common_i : common_j; + w = v + k; + { + int i2; for (i2 = w->s_size - 1 - common; i2 >= 0; i2--) { + if (c - common == lb) { diff = -1; break; } + diff = q[- common] - w->s[i2]; + if (diff != 0) break; + common++; + } + } + if (diff < 0) { j = k; common_j = common; } + else { i = k; common_i = common; } + if (j - i <= 1) { + if (i > 0) break; + if (j == i) break; + if (first_key_inspected) break; + first_key_inspected = 1; + } + } + while(1) { + w = v + i; + if (common_i >= w->s_size) { + z->c = c - w->s_size; + if (w->function == 0) return w->result; + { + int res = w->function(z); + z->c = c - w->s_size; + if (res) return w->result; + } + } + i = w->substring_i; + if (i < 0) return 0; + } +} + + +/* Increase the size of the buffer pointed to by p to at least n symbols. + * If insufficient memory, returns NULL and frees the old buffer. + */ +static symbol * increase_size(symbol * p, int n) { + symbol * q; + int new_size = n + 20; + void * mem = realloc((char *) p - HEAD, + HEAD + (new_size + 1) * sizeof(symbol)); + if (mem == NULL) { + lose_s(p); + return NULL; + } + q = (symbol *) (HEAD + (char *)mem); + CAPACITY(q) = new_size; + return q; +} + +/* to replace symbols between c_bra and c_ket in z->p by the + s_size symbols at s. + Returns 0 on success, -1 on error. + Also, frees z->p (and sets it to NULL) on error. +*/ +extern int replace_s(struct SN_env * z, int c_bra, int c_ket, int s_size, const symbol * s, int * adjptr) +{ + int adjustment; + int len; + if (z->p == NULL) { + z->p = create_s(); + if (z->p == NULL) return -1; + } + adjustment = s_size - (c_ket - c_bra); + len = SIZE(z->p); + if (adjustment != 0) { + if (adjustment + len > CAPACITY(z->p)) { + z->p = increase_size(z->p, adjustment + len); + if (z->p == NULL) return -1; + } + memmove(z->p + c_ket + adjustment, + z->p + c_ket, + (len - c_ket) * sizeof(symbol)); + SET_SIZE(z->p, adjustment + len); + z->l += adjustment; + if (z->c >= c_ket) + z->c += adjustment; + else + if (z->c > c_bra) + z->c = c_bra; + } + unless (s_size == 0) memmove(z->p + c_bra, s, s_size * sizeof(symbol)); + if (adjptr != NULL) + *adjptr = adjustment; + return 0; +} + +static int slice_check(struct SN_env * z) { + + if (z->bra < 0 || + z->bra > z->ket || + z->ket > z->l || + z->p == NULL || + z->l > SIZE(z->p)) /* this line could be removed */ + { +#if 0 + fprintf(stderr, "faulty slice operation:\n"); + debug(z, -1, 0); +#endif + return -1; + } + return 0; +} + +extern int slice_from_s(struct SN_env * z, int s_size, const symbol * s) { + if (slice_check(z)) return -1; + return replace_s(z, z->bra, z->ket, s_size, s, NULL); +} + +extern int slice_from_v(struct SN_env * z, const symbol * p) { + return slice_from_s(z, SIZE(p), p); +} + +extern int slice_del(struct SN_env * z) { + return slice_from_s(z, 0, 0); +} + +extern int insert_s(struct SN_env * z, int bra, int ket, int s_size, const symbol * s) { + int adjustment; + if (replace_s(z, bra, ket, s_size, s, &adjustment)) + return -1; + if (bra <= z->bra) z->bra += adjustment; + if (bra <= z->ket) z->ket += adjustment; + return 0; +} + +extern int insert_v(struct SN_env * z, int bra, int ket, const symbol * p) { + int adjustment; + if (replace_s(z, bra, ket, SIZE(p), p, &adjustment)) + return -1; + if (bra <= z->bra) z->bra += adjustment; + if (bra <= z->ket) z->ket += adjustment; + return 0; +} + +extern symbol * slice_to(struct SN_env * z, symbol * p) { + if (slice_check(z)) { + lose_s(p); + return NULL; + } + { + int len = z->ket - z->bra; + if (CAPACITY(p) < len) { + p = increase_size(p, len); + if (p == NULL) + return NULL; + } + memmove(p, z->p + z->bra, len * sizeof(symbol)); + SET_SIZE(p, len); + } + return p; +} + +extern symbol * assign_to(struct SN_env * z, symbol * p) { + int len = z->l; + if (CAPACITY(p) < len) { + p = increase_size(p, len); + if (p == NULL) + return NULL; + } + memmove(p, z->p, len * sizeof(symbol)); + SET_SIZE(p, len); + return p; +} + +#if 0 +extern void debug(struct SN_env * z, int number, int line_count) { + int i; + int limit = SIZE(z->p); + /*if (number >= 0) printf("%3d (line %4d): '", number, line_count);*/ + if (number >= 0) printf("%3d (line %4d): [%d]'", number, line_count,limit); + for (i = 0; i <= limit; i++) { + if (z->lb == i) printf("{"); + if (z->bra == i) printf("["); + if (z->c == i) printf("|"); + if (z->ket == i) printf("]"); + if (z->l == i) printf("}"); + if (i < limit) + { int ch = z->p[i]; + if (ch == 0) ch = '#'; + printf("%c", ch); + } + } + printf("'\n"); +} +#endif diff --git a/doc/doxydown b/doc/doxydown deleted file mode 160000 -Subproject 6c1f79c4294ef66a55bfc75845f3fdf3e2e1c32 diff --git a/doc/doxydown/.gitignore b/doc/doxydown/.gitignore new file mode 100644 index 000000000..eaca02ed3 --- /dev/null +++ b/doc/doxydown/.gitignore @@ -0,0 +1,19 @@ +/blib/ +/.build/ +_build/ +cover_db/ +inc/ +Build +!Build/ +Build.bat +.last_cover_stats +/Makefile +/Makefile.old +/MANIFEST.bak +/META.yml +/META.json +/MYMETA.* +nytprof.out +/pm_to_blib +*.o +*.bs diff --git a/doc/doxydown/LICENSE b/doc/doxydown/LICENSE new file mode 100644 index 000000000..d39277a3e --- /dev/null +++ b/doc/doxydown/LICENSE @@ -0,0 +1,21 @@ +The MIT License (MIT) + +Copyright (c) 2014 Vsevolod Stakhov + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. diff --git a/doc/doxydown/README.md b/doc/doxydown/README.md new file mode 100644 index 000000000..fb3f9f14b --- /dev/null +++ b/doc/doxydown/README.md @@ -0,0 +1,139 @@ +# Doxydown - documentation utility + +## Introduction + +Doxydown is an utility to convert `doxygen`-like comments from the source code to markdown. +Unlike other documentation systems, `doxydown` is specifically designed to generate markdown output only. +At the moment, doxydown can work with C and lua comments and produce kramdown/pandoc or github +flavoured markdown. Doxydown produces output with anchors, links and table of content. +It also can highlight syntax for examples in the documentation. + +### Why markdown + +Markdown is used by many contemporary engines and can be rendered to HTML using +advanced templates, styles and scripts. Markdown provides excellent formatting +capabilities while it doesn't require authors to be web designers to create +documentation. Markdown is rendered by [`github`](https://github.com) and +doxydown can generate documentation easily viewed directly inside github. Moreover, +doxydown supports pandoc style of markdown and that means that markdown output +can be converted to all formats supported by pandoc (html, pdf, latex, +man pages and many others). + +### Why not `other documentation generator` + +Doxydown is extremely simple as it can output markdown only but it is very +convenient tool to generate nice markdown with all features required from the +documentation system. Doxydown uses input format that is very close to `doxygen` +that allows to re-use the existing documentation comments. Currenly, doxydown +does not support many features but they could be easily added on demand. + +## Input format + +Doxydown extracts documentation from the comments blocks. The start of block is indicated by + + /*** + +in `C` or by + + --[[[ + +in `lua`. The end of documentation block is the normal multiline comment ending +specific for the input language. Doxydown also strips an initial comment character, +therefore the following inputs are equal: + +~~~c +/*** + * some text + * other text + * + */ +~~~ +and + +~~~c +/*** +some text +other text + +*/ +~~~ + +Note that doxydown preserves empty lines and all markdown elements. + +### Documentation blocks + +Each documentation block describes either module or function/method. Modules are +logical compounds of functions and methods. The difference between method and +function is significant for languages with methods support (e.g. by `lua` via +metatables). To define method or function you can use the following: + + /*** + @function my_awesome_function(param1[, param2]) + This function is awesome. + */ + +All text met in the current documentation block is used as function or method description. +You can also define parameters and return values for functions and methods: + + @param {type} param1 mandatory param + +Here, `{type}` is optional type description for a parameter, `param1` is parameter's name +and the rest of the string is parameter description. Currently, you cannot split +parameter description by newline character. In future versions of doxydown this might +be fixed. + +You can specify return type of your function by using of `@return` tag: + + @return {type} some cool result + +This tag is similar to `@param` and has the same limitation regarding newlines. +You can also add some example code by using of `@example` tag: + + @example + my_awesome_function('hello'); // returns 42 + +All text after `@example` tag and until documentation block end is used as an example +and is highlighted in markdown. Also you can switch the language of example by using +the extended `@example` tag: + + @example lua + +In this example, the code will be highlighted as `lua` code. + +Modules descriptions uses the same conventions, but `@param` and `@return` are +meaningless for the modules. Function and methods blocks that follows some `@module` +block are automatically attached to that module. + +Both modules and function can use links to other functions and methods by using of +`@see` tag: + + @see my_awesome_function + +This inserts a hyperlink to the specified function definition to the markdown. + +## Output format + +Doxydown can generate github flavoured markdown and pandoc/kramdown compatible +markdown. The main difference is in how anchors are organized. In kramdown and +pandoc it is possible to specify an explicit id for each header, whilst in +GH flavoured markdown we can use only implicit anchors. + +### Examples + +You can see an example of github flavoured markdown render at +[libucl github page](https://github.com/vstakhov/libucl/blob/master/doc/lua_api.md). +The same page bu rendered by kramdown engine in `jekyll` platform can be +accessed by [this address](https://rspamd.com/doc/lua/ucl.html). + +## Program invocation + + doxydown [-hg] [-l language] < input_source > markdown.md + +* `-h`: help message +* `-e`: sets default example language (default: lua) +* `-l`: sets input language (default: c) +* `-g`: use github flavoured markdown (default: kramdown/pandoc) + +## License + +Doxydown is published by terms of `MIT` license.
\ No newline at end of file diff --git a/doc/doxydown/doxydown.pl b/doc/doxydown/doxydown.pl new file mode 100755 index 000000000..3aa1b6b1d --- /dev/null +++ b/doc/doxydown/doxydown.pl @@ -0,0 +1,388 @@ +#!/usr/bin/env perl + +$VERSION = "0.1"; + +use strict; +use warnings; +use Data::Dumper; +use Digest::MD5 qw(md5_hex); + +my @modules; +my %options = (); +my $cur_module; +my $example_language = "lua"; + +my %languages = ( + c => { + start => qr/^\s*\/\*\*\*(?:\s*|(\s+\S.+\s*))$/, + end => qr/^\s*\*+\/\s*$/, + filter => qr/^(?:\s*\*+\s?)?(\s*[^*].+)\s*$/, + }, + lua => { + start => qr/^\s*\--\[\[\[\s*$/, + end => qr/^\s*--\]\]\s*/, + filter => qr/^(?:\s*--\s)?(\s*\S.+)\s*$/, + }, +); + +my $function_re = qr/^\s*\@(function|fn|method)\s*(\S.+)$/oi; +my $module_re = qr/^\s*\@(?:module|file)\s*(\S.+)$/oi; + +my $language; + +sub print_module_markdown { + my ( $mname, $m ) = @_; + + my $idline = $options{g} ? "" : " {#$m->{'id'}}"; + print <<EOD; +## Module `$mname`$idline + +$m->{'data'} +EOD + if ( $m->{'example'} ) { + print <<EOD; + +Example: + +~~~$m->{'example_language'} +$m->{'example'} +~~~ +EOD + } + + sub print_func { + my ($f) = @_; + + my $name = $f->{'name'}; + my $id = $f->{'id'}; + if ($f->{'brief'}) { + print "> [`$name`](#$id): ". $f->{'brief'} . "\n\n"; + } + else { + print "> [`$name`](#$id)\n\n"; + } + } + + print "\n### Brief content:\n\n"; + if (scalar(@{ $m->{'functions'} }) > 0) { + print "**Functions**:\n\n"; + foreach ( @{ $m->{'functions'} } ) { + print_func($_); + } + } + if (scalar(@{ $m->{'methods'} }) > 0) { + print "\n\n**Methods**:\n\n"; + foreach (@{ $m->{'methods'} }) { + print_func($_); + } + } +} + +sub print_function_markdown { + my ( $type, $fname, $f ) = @_; + + my $idline = $options{g} ? "" : " {#$f->{'id'}}"; + print <<EOD; +### $type `$fname`$idline + +$f->{'data'} +EOD + print "\n**Parameters:**\n\n"; + if ( $f->{'params'} && scalar @{ $f->{'params'} } > 0 ) { + foreach ( @{ $f->{'params'} } ) { + if ( $_->{'type'} ) { + print + "- `$_->{'name'} \{$_->{'type'}\}`: $_->{'description'}\n"; + } + else { + print "- `$_->{'name'}`: $_->{'description'}\n"; + } + } + } + else { + print "\tnothing\n"; + } + print "\n**Returns:**\n\n"; + if ( $f->{'return'} && $f->{'return'}->{'description'} ) { + $_ = $f->{'return'}; + if ( $_->{'type'} ) { + print "- `\{$_->{'type'}\}`: $_->{'description'}\n"; + } + else { + print "- $_->{'description'}\n"; + } + } + else { + print "\tnothing\n"; + } + if ( $f->{'example'} ) { + print <<EOD; + +Example: + +~~~$f->{'example_language'} +$f->{'example'} +~~~ +EOD + } +} + +sub print_markdown { + for my $m (@modules) { + my $mname = $m->{name}; + print_module_markdown( $mname, $m ); + + if (scalar(@{ $m->{'functions'} }) > 0) { + print + "\n## Functions\n\nThe module `$mname` defines the following functions.\n\n"; + foreach (@{ $m->{'functions'} }) { + print_function_markdown( "Function", $_->{'name'}, $_ ); + print "\nBack to [module description](#$m->{'id'}).\n\n"; + + } + } + + if (scalar(@{ $m->{'methods'} }) > 0) { + print + "\n## Methods\n\nThe module `$mname` defines the following methods.\n\n"; + foreach (@{ $m->{'methods'} }) { + print_function_markdown( "Method", $_->{'name'}, $_ ); + print "\nBack to [module description](#$m->{'id'}).\n\n"; + + } + } + + print "\nBack to [top](#).\n\n"; + } +} + +sub make_id { + my ( $name, $prefix ) = @_; + + if ( !$prefix ) { + $prefix = "f"; + } + if ( !$options{g} ) { + + # Kramdown/pandoc version of ID's + $name =~ /^(\S+).*$/; + return substr( substr( $prefix, 0, 1 ) . md5_hex($1), 0, 6 ); + } + else { + my $input = lc $prefix . "-" . $name; + my $id = join '-', split /\s+/, $input; + $id =~ s/[^\w_-]+//g; + return $id; + } +} + +sub substitute_data_keywords { + my ($line) = @_; + + if ( $line =~ /^.*\@see\s+(\S+)\s*.*$/ ) { + my $name = $1; + my $id = make_id($name); + return $line =~ s/\@see\s+\S+/[`$name`](#$id)/r; + } + + return $line; +} + +sub parse_function { + my ( $func, @data ) = @_; + + my ( $type, $name ) = ( $func =~ $function_re ); + + chomp $name; + + my $f = { + name => $name, + data => '', + example => undef, + example_language => $example_language, + id => make_id( $name, $type ), + }; + my $example = 0; + + foreach (@data) { + if (/^\s*\@param\s*(?:\{([^}]+)\})?\s*(\S+)\s*(.+)?\s*$/) { + my $p = { name => $2, type => $1, description => $3 }; + push @{ $f->{'params'} }, $p; + } + elsif (/^\s*\@return\s*(?:\{([^}]+)\})?\s*(.+)?\s*$/) { + my $r = { type => $1, description => $2 }; + $f->{'return'} = $r; + } + elsif (/^\s*\@brief\s*(\S.+)$/) { + $f->{'brief'} = $1; + } + elsif (/^\s*\@example\s*(\S)?\s*$/) { + $example = 1; + if ($1) { + $f->{'example_language'} = $1; + } + } + elsif ( $_ ne $func ) { + if ($example) { + $f->{'example'} .= $_; + } + else { + $f->{'data'} .= substitute_data_keywords($_); + } + } + } + if ( $f->{'data'} ) { + chomp $f->{'data'}; + } + elsif ($f->{'brief'}) { + chomp $f->{'brief'}; + $f->{'data'} = $f->{'brief'}; + } + if ( $f->{'example'} ) { + chomp $f->{'example'}; + } + + if ( $type eq "method" ) { + push @{ $cur_module->{'methods'} }, $f; + } + else { + push @{ $cur_module->{'functions'} }, $f; + } +} + +sub parse_module { + my ( $module, @data ) = @_; + my ( $name ) = ( $module =~ $module_re ); + + chomp $name; + + my $f = { + name => $name, + functions => [], + methods => [], + data => '', + example => undef, + example_language => $example_language, + id => make_id( $name, "module" ), + }; + my $example = 0; + + foreach (@data) { + if (/^\s*\@example\s*(\S)?\s*$/) { + $example = 1; + if ($1) { + $f->{'example_language'} = $1; + } + } + elsif (/^\s*\@brief\s*(\S.+)$/) { + $f->{'brief'} = $1; + } + elsif ( $_ ne $module ) { + if ($example) { + $f->{'example'} .= $_; + } + else { + $f->{'data'} .= substitute_data_keywords($_); + } + } + } + if ( $f->{'data'} ) { + chomp $f->{'data'}; + } + elsif ($f->{'brief'}) { + chomp $f->{'brief'}; + $f->{'data'} = $f->{'brief'}; + } + if ( $f->{'example'} ) { + chomp $f->{'example'}; + } + $cur_module = $f; + push @modules, $f; +} + +sub parse_content { + my @func = grep /$function_re/, @_; + if ( scalar @func > 0 ) { + parse_function( $func[0], @_ ); + } + + my @module = grep /$module_re/, @_; + if ( scalar @module > 0 ) { + parse_module( $module[0], @_ ); + } +} + +sub HELP_MESSAGE { + print STDERR <<EOF; +Utility to convert doxygen comments to markdown. + +usage: $0 [-hg] [-l language] < input_source > markdown.md + + -h : this (help) message + -e : sets default example language (default: lua) + -l : sets input language (default: c) + -g : use github flavoured markdown (default: kramdown/pandoc) +EOF + exit; +} + +$Getopt::Std::STANDARD_HELP_VERSION = 1; +use Getopt::Std; +getopts( 'he:gl:', \%options ); + +HELP_MESSAGE() if $options{h}; + +$example_language = $options{e} if $options{e}; +$language = $languages{ lc $options{l} } if $options{l}; + +if ( !$language ) { + $language = $languages{c}; +} + +use constant { + STATE_READ_SKIP => 0, + STATE_READ_CONTENT => 1, + STATE_READ_ENUM => 2, + STATE_READ_STRUCT => 3, +}; + +my $state = STATE_READ_SKIP; +my $content; + +while (<>) { + if ( $state == STATE_READ_SKIP ) { + if ( $_ =~ $language->{start} ) { + $state = STATE_READ_CONTENT; + if (defined($1)) { + chomp($content = $1); + $content =~ tr/\r//d; + $content .= "\n"; + } + else { + $content = ""; + } + } + } + elsif ( $state == STATE_READ_CONTENT ) { + if ( $_ =~ $language->{end} ) { + $state = STATE_READ_SKIP; + parse_content( split /^/, $content ); + $content = ""; + } + else { + my ($line) = ( $_ =~ $language->{filter} ); + + if ($line) { + $line =~ tr/\r//d; + $content .= $line . "\n"; + } + else { + # Preserve empty lines + $content .= "\n"; + } + } + } +} + +#print Dumper( \@modules ); +print_markdown; diff --git a/interface b/interface deleted file mode 160000 -Subproject db96fa946f8c79cf3d25d44efce1426496a6ee7 diff --git a/interface/README.md b/interface/README.md new file mode 100644 index 000000000..0507301bc --- /dev/null +++ b/interface/README.md @@ -0,0 +1,50 @@ +#Rspamd web interface + +##Overview. + +This is a simple control interface for rspamd spam filtering system. +It provides basic functions for setting metric actions, scores, +viewing statistic and learning. + +<img src="https://rspamd.com/img/webui.png" class="img-responsive" alt="Webui screenshot"> + +##Rspamd setup. + +It is required to configure dynamic settings to store configured values. +Basically this can be done by providing the following line in options settings: + +~~~nginx +options { + dynamic_conf = "/var/lib/rspamd/rspamd_dynamic"; +} +~~~ + +Please note that this path must have write access for rspamd user. + +Then controller worker should be configured: + +~~~nginx +worker { + type = "controller"; + bind_socket = "localhost:11334"; + count = 1; + # Password for normal commands + password = "q1"; + # Password for privilleged commands + enable_password = "q2"; + # Path to webiu static files + static_dir = "${WWWDIR}"; +} +~~~ + +Password option should be changed for sure for your specific configuration. Encrypted password using is encouraged (`rspamadm pw --encrypt`). + +##Interface setup. + +Interface itself is written in pure HTML5/js and, hence, it requires zero setup. +Just enter a password for webui access and you are ready. + +##Contact information. + +Rspamd interface is distributed under the terms of [MIT license](http://opensource.org/licenses/MIT). For all questions related to this +product please see the [support page](https://rspamd.com/support.html) diff --git a/interface/css/datatables.min.css b/interface/css/datatables.min.css new file mode 100644 index 000000000..ef2aa4d37 --- /dev/null +++ b/interface/css/datatables.min.css @@ -0,0 +1,24 @@ +/* + * This combined file was created by the DataTables downloader builder: + * https://datatables.net/download + * + * To rebuild or modify this file with the latest versions of the included + * software please visit: + * https://datatables.net/download/#bs-3.3.5/jqc-1.11.3,dt-1.10.9,fh-3.0.0,r-1.0.7,sc-1.3.0 + * + * Included libraries: + * jQuery compat 1.11.3, Bootstrap 3.3.5, DataTables 1.10.9, FixedHeader 3.0.0, Responsive 1.0.7, Scroller 1.3.0 + */ + +table.dataTable{clear:both;margin-top:6px !important;margin-bottom:6px !important;max-width:none !important}table.dataTable td,table.dataTable th{-webkit-box-sizing:content-box;-moz-box-sizing:content-box;box-sizing:content-box}table.dataTable td.dataTables_empty,table.dataTable th.dataTables_empty{text-align:center}table.dataTable.nowrap th,table.dataTable.nowrap td{white-space:nowrap}div.dataTables_wrapper div.dataTables_length label{font-weight:normal;text-align:left;white-space:nowrap}div.dataTables_wrapper div.dataTables_length select{width:75px;display:inline-block}div.dataTables_wrapper div.dataTables_filter{text-align:right}div.dataTables_wrapper div.dataTables_filter label{font-weight:normal;white-space:nowrap;text-align:left}div.dataTables_wrapper div.dataTables_filter input{margin-left:0.5em;display:inline-block;width:auto}div.dataTables_wrapper div.dataTables_info{padding-top:8px;white-space:nowrap}div.dataTables_wrapper div.dataTables_paginate{margin:0;white-space:nowrap;text-align:right}div.dataTables_wrapper div.dataTables_paginate ul.pagination{margin:2px 0;white-space:nowrap}table.dataTable thead>tr>th.sorting_asc,table.dataTable thead>tr>th.sorting_desc,table.dataTable thead>tr>th.sorting,table.dataTable thead>tr>td.sorting_asc,table.dataTable thead>tr>td.sorting_desc,table.dataTable thead>tr>td.sorting{padding-right:30px}table.dataTable thead>tr>th:active,table.dataTable thead>tr>td:active{outline:none}table.dataTable thead .sorting,table.dataTable thead .sorting_asc,table.dataTable thead .sorting_desc,table.dataTable thead .sorting_asc_disabled,table.dataTable thead .sorting_desc_disabled{cursor:pointer;position:relative}table.dataTable thead .sorting:after,table.dataTable thead .sorting_asc:after,table.dataTable thead .sorting_desc:after,table.dataTable thead .sorting_asc_disabled:after,table.dataTable thead .sorting_desc_disabled:after{position:absolute;bottom:8px;right:8px;display:block;font-family:'Glyphicons Halflings';opacity:0.5}table.dataTable thead .sorting:after{opacity:0.2;content:"\e150"}table.dataTable thead .sorting_asc:after{content:"\e155"}table.dataTable thead .sorting_desc:after{content:"\e156"}table.dataTable thead .sorting_asc_disabled:after,table.dataTable thead .sorting_desc_disabled:after{color:#eee}div.dataTables_scrollHead table.dataTable{margin-bottom:0 !important}div.dataTables_scrollBody table{border-top:none;margin-top:0 !important;margin-bottom:0 !important}div.dataTables_scrollBody table thead .sorting:after,div.dataTables_scrollBody table thead .sorting_asc:after,div.dataTables_scrollBody table thead .sorting_desc:after{display:none}div.dataTables_scrollBody table tbody tr:first-child th,div.dataTables_scrollBody table tbody tr:first-child td{border-top:none}div.dataTables_scrollFoot table{margin-top:0 !important;border-top:none}@media screen and (max-width: 767px){div.dataTables_wrapper div.dataTables_length,div.dataTables_wrapper div.dataTables_filter,div.dataTables_wrapper div.dataTables_info,div.dataTables_wrapper div.dataTables_paginate{text-align:center}}table.dataTable.table-condensed>thead>tr>th{padding-right:20px}table.dataTable.table-condensed .sorting:after,table.dataTable.table-condensed .sorting_asc:after,table.dataTable.table-condensed .sorting_desc:after{top:6px;right:6px}table.table-bordered.dataTable{border-collapse:separate !important}table.table-bordered.dataTable th,table.table-bordered.dataTable td{border-left-width:0}table.table-bordered.dataTable th:last-child,table.table-bordered.dataTable th:last-child,table.table-bordered.dataTable td:last-child,table.table-bordered.dataTable td:last-child{border-right-width:0}table.table-bordered.dataTable tbody th,table.table-bordered.dataTable tbody td{border-bottom-width:0}div.dataTables_scrollHead table.table-bordered{border-bottom-width:0} + + +table.dataTable.fixedHeader-floating,table.dataTable.fixedHeader-locked{background-color:white;margin-top:0 !important;margin-bottom:0 !important}table.dataTable.fixedHeader-floating{position:fixed}table.dataTable.fixedHeader-locked{position:absolute} + + +table.dataTable.dtr-inline.collapsed>tbody>tr>td:first-child,table.dataTable.dtr-inline.collapsed>tbody>tr>th:first-child{position:relative;padding-left:30px;cursor:pointer}table.dataTable.dtr-inline.collapsed>tbody>tr>td:first-child:before,table.dataTable.dtr-inline.collapsed>tbody>tr>th:first-child:before{top:8px;left:4px;height:16px;width:16px;display:block;position:absolute;color:white;border:2px solid white;border-radius:16px;text-align:center;line-height:14px;box-shadow:0 0 3px #444;box-sizing:content-box;content:'+';background-color:#337ab7}table.dataTable.dtr-inline.collapsed>tbody>tr>td:first-child.dataTables_empty:before,table.dataTable.dtr-inline.collapsed>tbody>tr>th:first-child.dataTables_empty:before{display:none}table.dataTable.dtr-inline.collapsed>tbody>tr.parent>td:first-child:before,table.dataTable.dtr-inline.collapsed>tbody>tr.parent>th:first-child:before{content:'-';background-color:#d33333}table.dataTable.dtr-inline.collapsed>tbody>tr.child td:before{display:none}table.dataTable.dtr-inline.collapsed.compact>tbody>tr>td:first-child,table.dataTable.dtr-inline.collapsed.compact>tbody>tr>th:first-child{padding-left:27px}table.dataTable.dtr-inline.collapsed.compact>tbody>tr>td:first-child:before,table.dataTable.dtr-inline.collapsed.compact>tbody>tr>th:first-child:before{top:5px;left:4px;height:14px;width:14px;border-radius:14px;line-height:12px}table.dataTable.dtr-column>tbody>tr>td.control,table.dataTable.dtr-column>tbody>tr>th.control{position:relative;cursor:pointer}table.dataTable.dtr-column>tbody>tr>td.control:before,table.dataTable.dtr-column>tbody>tr>th.control:before{top:50%;left:50%;height:16px;width:16px;margin-top:-10px;margin-left:-10px;display:block;position:absolute;color:white;border:2px solid white;border-radius:16px;text-align:center;line-height:14px;box-shadow:0 0 3px #444;box-sizing:content-box;content:'+';background-color:#337ab7}table.dataTable.dtr-column>tbody>tr.parent td.control:before,table.dataTable.dtr-column>tbody>tr.parent th.control:before{content:'-';background-color:#d33333}table.dataTable>tbody>tr.child{padding:0.5em 1em}table.dataTable>tbody>tr.child:hover{background:transparent !important}table.dataTable>tbody>tr.child ul{display:inline-block;list-style-type:none;margin:0;padding:0}table.dataTable>tbody>tr.child ul li{border-bottom:1px solid #efefef;padding:0.5em 0}table.dataTable>tbody>tr.child ul li:first-child{padding-top:0}table.dataTable>tbody>tr.child ul li:last-child{border-bottom:none}table.dataTable>tbody>tr.child span.dtr-title{display:inline-block;min-width:75px;font-weight:bold} + + +div.DTS tbody th,div.DTS tbody td{white-space:nowrap}div.DTS tbody tr.even{background-color:white}div.DTS div.DTS_Loading{z-index:1}div.DTS div.dataTables_scrollBody{background:repeating-linear-gradient(45deg, #edeeff, #edeeff 10px, #fff 10px, #fff 20px)}div.DTS div.dataTables_scrollBody table{z-index:2}div.DTS div.dataTables_paginate{display:none} + + diff --git a/interface/css/glyphicons-halflings-regular.woff b/interface/css/glyphicons-halflings-regular.woff Binary files differnew file mode 100644 index 000000000..9e612858f --- /dev/null +++ b/interface/css/glyphicons-halflings-regular.woff diff --git a/interface/css/glyphicons-halflings-regular.woff2 b/interface/css/glyphicons-halflings-regular.woff2 Binary files differnew file mode 100644 index 000000000..64539b54c --- /dev/null +++ b/interface/css/glyphicons-halflings-regular.woff2 diff --git a/interface/css/rspamd.css b/interface/css/rspamd.css new file mode 100644 index 000000000..0e4ebd939 --- /dev/null +++ b/interface/css/rspamd.css @@ -0,0 +1,635 @@ +/* +The MIT License (MIT) + +Copyright (C) 2012-2013 Anton Simonov <untone@gmail.com> +Copyright (C) 2014-2015 Vsevolod Stakhov <vsevolod@highsecure.ru> + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in +all copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN +THE SOFTWARE. +*/ + +a { + outline:none; + } +textarea { + font-family:Monaco,Menlo,Consolas,"Courier New",monospace; + } + +.login { + width:480px; + margin-top:120px; + margin-left:-240px; + } + +/* local overrides */ +.disconnect { + margin:9px 0 0; + padding-bottom:5px; + font-size:11px; + color:#777; + -moz-text-shadow:0 1px 0 #fff; + -webkit-text-shadow:0 1px 0 #fff; + -o-text-shadow:0 1px 0 #fff; + -ms-text-shadow:0 1px 0 #fff; + text-shadow:0 1px 0 #fff; + } +.chart-content { + text-align:center; + } + .chart { + height:400px; + margin:0 auto; + text-align:center; + background:#fff; + } +.notice { + display:none; + } +#js .notice { + display:inline; + } + +.form-sliders .control-label { + width:340px; + } + .form-sliders .controls { + margin-left:280px; + } +.slider-controls { + padding-right:8em !important; + } + .jslider { + top:13px !important; + } + input.slider { + width:4em; + margin:5px -7em 5px 0; + padding:2px 0; + text-align:center; + } + .symbols-label { + font-size:11px !important; + } + +/* spinners optional */ +input { + margin:0px; + padding:0px; + width:40px; + } +input[type=number] { + padding-right:25px; /* at least image width */ + text-align:right; + width:40px; + } +input.number { /* should be same as type=number for IE and overriding */ + padding-right:25px; /* at least image width */ + text-align:right; + } +input::-webkit-outer-spin-button, +input::-webkit-inner-spin-button { + /* display:none; <- Crashes Chrome on hover */ + -webkit-appearance:none; + margin:0; /* <-- Apparently some margin are still there even though it's hidden */ +} +.k-numerictextbox, +.k-numeric-wrap { + display:block; + } + .k-numeric-wrap { + position:relative; + } + input.numeric { + text-align:right; + } + .k-select { + overflow:hidden; + position:absolute; + top:5px; + left:52px; + width:11px; + height:22px; + font-size:1px; + line-height:1px; + text-indent:-999px; + } + .k-link, + .k-icon { + display:block; + width:11px; + height:10px; + } + .k-icon { + cursor:pointer; + background-image:url('../img/spinner.png'); + } + .k-i-arrow-n { + background-position:0 0; + } + .k-i-arrow-n:hover, + .k-i-arrow-n:focus { + background-position:-11px 0; + } + .k-i-arrow-n:active { + background-position:-22px 0; + } + .k-i-arrow-s { + margin-top:-1px; + background-position:0 -10px; + } + .k-i-arrow-s:hover, + .k-i-arrow-s:focus { + background-position:-11px -10px; + } + .k-i-arrow-s:active { + background-position:-22px -10px; + } +/* spinners default style */ +/* .spin-cell { + position:relative; + } + .spinControl { + position:absolute; + height:20px; + top:6px; + left:56px; + } + .spinControl.MOZ, .spinControl.IE6, .spinControl.IE7 { + } + .spinControl button { + position:absolute; + left:0; + width:11px; + height:10px; + margin:0; + padding:0; + border:0; + background-color:none; + cursor:pointer; + background-image:url('../img/spinner.png'); + } + .spinControl button.down { + bottom:1px; + } + .spinControl button.up { + } + .spinControl button.up:hover, + .spinControl button.up:focus { + background-position:-11px 0; + } + .spinControl button.up:active { + background-position:-22px 0; + } + .spinControl button.down { + background-position:0 -10px; + } + .spinControl button.down:hover, + .spinControl button.down:focus { + background-position:-11px -10px; + } + .spinControl button.down:active { + background-position:-22px -10px; + } */ + +/* history table */ +.table-log { + table-layout:fixed; + border:0 !important; + } + .table-log .col1 { + width:130px; + } + .table-log .col2, + .table-log .col6 { + width:100%; + } + .table-log .col3, + .table-log .col4, + .table-log .col5 { + width:100px; + } + .table-log .col7, + .table-log .col8, + .table-log .col9 { + width:50px; + } + .table-log th { + padding:4px 10px; + font-size:10px; + color:#666666; + white-space:nowrap; + border-bottom:1px solid #ddd; + } + .table-log thead th, + .table-log tbody td { + text-align:left; + line-height:16px; + vertical-align:top; + } + .table-log td, + .table-log td .label { + font-family:Monaco,Menlo,Consolas,"Courier New",monospace; + font-size:11px; + } + .table-log th:first-child, + .table-log td:first-child { + border-left:0; + } + .table-log .cell-overflow { + white-space:nowrap; + overflow:hidden; + -o-text-overflow:ellipsis; + text-overflow:ellipsis; + } + .table-log .cell-overflow:focus { + margin:-3px -8px; + padding:2px 7px 3px; + position:absolute; + overflow:visible; + background:#fff; + border:1px solid #ccc; + -moz-box-shadow:0 2px 2px -2px #CCCCCC inset; + box-shadow:0 2px 2px -2px #CCCCCC inset; + cursor:text; + } + .table-log th { + background-color:#efefef; + border-left:1px solid #CDCDCD; + } + .table-log th.header { + cursor:pointer; + } + .table-log th:first-child { + border-left:0; + } + .table-log th.headerSortUp, + .table-log th.headerSortDown { + background-color:#fefefe; + background-position:100% 12px; + background-repeat:no-repeat; + } + .table-log th.headerSortUp { + background-image:url('../img/asc.png'); + } + .table-log th.headerSortDown { + background-image:url('../img/desc.png'); + } + +.btn-upload-trigger { + position:relative; + z-index:1; + } +.upload-textarea, +.scan-textarea { + width:100% !important; + } +.upload-textarea { + height:200px; + } +.scan-textarea { + height:400px; + } +.stat-boxes { + overflow:hidden !important; + height:73px !important; + } + +.row-bordered { + margin-bottom:13px; + border-bottom:1px solid #cdcdcd; + } +.symbol-description { + display:block; + margin:4px 0 0 6px; + font-size:10px; + font-weight:bold; + color:#666; + } + +.list-textarea { + width:100%; + height:360px; + } +.align-right { + text-align:right !important; + } +td.maps-cell { + vertical-align:middle; + } + +.map-link { + display:block; + color:#0088cc; + cursor:pointer; + } +.map-link:hover, +.map-link:focus { + color:#005580; + text-decoration:underline; + } +.spinner { + background:url('../img/spinner.gif') no-repeat -100px; + padding-left:25px; + } +.loading .spinner { + background-position:0 50%; + } + +/* widget */ +.widget-box { + background:none repeat scroll 0 0 #F9F9F9; + border-top:1px solid #CDCDCD; + border-left:1px solid #CDCDCD; + border-right:1px solid #CDCDCD; + clear:both; + margin-top:16px; + margin-bottom:16px; + position:relative; + } +.widget-box.widget-calendar, .widget-box.widget-chat { + overflow:hidden !important; + } +.accordion .widget-box { + margin-top:-2px; + margin-bottom:0; + border-radius:0; + } +.widget-box.widget-plain { + background:transparent; + border:none; + margin-top:0; + margin-bottom:0; + } +.widget-title, .modal-header { + background-color:#efefef; + background-image:-webkit-gradient(linear, 0 0%, 0 100%, from(#fdfdfd), to(#eaeaea)); + background-image:-webkit-linear-gradient(top, #fdfdfd 0%, #eaeaea 100%); + background-image:-moz-linear-gradient(top, #fdfdfd 0%, #eaeaea 100%); + background-image:-ms-linear-gradient(top, #fdfdfd 0%, #eaeaea 100%); + background-image:-o-linear-gradient(top, #fdfdfd 0%, #eaeaea 100%); + background-image:-linear-gradient(top, #fdfdfd 0%, #eaeaea 100%); + filter:progid:DXImageTransform.Microsoft.gradient( startColorstr='#fdfdfd', endColorstr='#eaeaea',GradientType=0 ); /* IE6-9 */ + border-bottom:1px solid #CDCDCD; + height:36px; + } +.widget-title span.icon { + border-right:1px solid #cdcdcd; + padding:9px 10px 7px 11px; + float:left; + opacity:.7; + } +.widget-title h5 { + color:#666666; + text-shadow:0 1px 0 #ffffff; + /* float:left; */ + display:block; + font-size:12px; + font-weight:bold; + padding:12px; + line-height:12px; + margin:0 0 0 36px; + } +.widget-title .buttons { + float:left; + margin:0px 0px 0 0; + } +.widget-title .label { + padding:3px 5px 2px; + float:right; + margin:9px 15px 0 0; + box-shadow:0 1px 2px rgba(0,0,0,0.3) inset, 0 1px 0 #ffffff; + } +.widget-content { + padding:12px 15px; + border-bottom:1px solid #cdcdcd; + -moz-box-shadow:0 1px 2px -1px rgba(0, 0, 0, 0.2); + box-shadow:0 1px 2px -1px rgba(0, 0, 0, 0.2); + } +.widget-inner { + padding:12px 15px; + } +.stats-plain { + width:100%; + } +.stat-boxes, .quick-actions, .quick-actions-horizontal, .stats-plain { + display:block; + list-style:none outside none; + margin:0; + } + .stat-box { + background-color:#F6F6F6; + background-image:-webkit-gradient(linear, 0 0%, 0 100%, from(#F9F9F9), to(#EDEDED)); + background-image:-webkit-linear-gradient(top, #F9F9F9 0%, #EDEDED 100%); + background-image:-moz-linear-gradient(top, #F9F9F9 0%, #EDEDED 100%); + background-image:-ms-linear-gradient(top, #F9F9F9 0%, #EDEDED 100%); + background-image:-o-linear-gradient(top, #F9F9F9 0%, #EDEDED 100%); + background-image:linear-gradient(top, #F9F9F9 0%, #EDEDED 100%); + border:1px solid #d5d5d5; + border-radius:4px 4px 4px 4px; + box-shadow:0 1px 0 0 #FFFFFF inset, 0 1px 0 rgba(255,255,255,0.4); + display:inline-block; + line-height:18px; + margin:0 10px 10px 0; + padding:0 10px; + } + /*.stat-boxes .stat-box:first-child { + margin-right:0; + }*/ + .stat-box .widget { + overflow:hidden; + margin: 0 12px; + padding: 10px 0 6px; + font-size: 10px; + font-weight: bold; + text-align: center; + text-transform:capitalize; + text-shadow: 0 1px 0 white; + color: #666; + } + .stat-box .left, + .stat-box .right { + float:left; + } + .stat-box .left { + border-right: 1px solid gainsboro; + box-shadow: 1px 0 0 0 white; + margin-right: 14px; + padding-right:18px; + font-size: 10px; + font-weight: bold; + } + .stat-box .right { + padding-left:4px; + } + .stat-box .widget span, .stat-box .widget strong { + display: block; + } + .stat-box .widget strong { + font-size: 26px; + margin-bottom: 3px; + margin-top: 6px; + } +.nomargin { + margin:0 !important; + } +.nopadding { + padding:0 !important; + } +.activity-list { + list-style:none outside none; + margin:0; + } + .activity-list li { + border-bottom:1px solid #EEEEEE; + display:block; + } + .activity-list li:last-child { + border-bottom:medium none; + } + .activity-list li a { + color:#888888; + display:block; + padding:7px 10px; + } + .activity-list li a:hover { + background-color:#FBFBFB; + } + .activity-list li a span { + color:#AAAAAA; + font-size:11px; + font-style:italic; + } + .activity-list li a i { + margin-right:10px; + opacity:0.6; + vertical-align:middle; + } +.recent-posts, .recent-comments, .recent-users { + margin:0; + padding:0; + } + .recent-posts li, .article-post li { + border-bottom:1px dotted #AEBDC8; + list-style:none outside none; + padding:10px; + } +.modal-header { + height:auto; + padding:8px 15px 5px; + } + .modal-header h3 { + font-size:12px; + text-shadow:0 1px 0 #FFFFFF; + } +.alert { + position:fixed; + z-index:1050; + top:41px; + right:0; + left:0; + padding:8px 0 8px; + margin:0 0 10px; + text-shadow:0 1px 0 rgba(255, 255, 255, 0.5); + background-color:#fcf8e3; + border-bottom:1px solid #fbeed5; + } +.alert.alert-modal { + top:0; + } + .alert strong { + display:inline-block; + padding-left:35px; + } +.alert, +.alert h4 { + color:#c09853; + } +.alert h4 { + margin:0; + } +.alert .close { + position:relative; + top:0; + right:9px; + line-height:20px; + } +.alert-block { + position:static; + padding: 8px 14px; + border: 1px solid #fbeed5; + -webkit-border-radius: 4px; + -moz-border-radius: 4px; + border-radius: 4px; + -moz-text-shadow: 0 1px 0 rgba(255, 255, 255, 0.5); + -webkit-text-shadow: 0 1px 0 rgba(255, 255, 255, 0.5); + text-shadow: 0 1px 0 rgba(255, 255, 255, 0.5); + } +.alert-success { + color:#468847; + background:#dff0d8; + border-color:#d6e9c6; + } +.alert-success h4 { + color:#468847; + } +.alert-danger, +.alert-error { + color:#b94a48; + background:#f2dede; + border-color:#eed3d7; + } +.alert-danger h4, +.alert-error h4 { + color:#b94a48; + } +.alert-info { + color:#3a87ad; + background:#d9edf7; + border-color:#bce8f1; + } +.alert-info h4 { + color:#3a87ad; + } +.alert-block .close { + right:-1px; + } +.alert-block h4 { + margin:5px 0 10px; + } +.alert-block > p, +.alert-block > ul { + margin-bottom:0; + } +.alert-block p + p { + margin-top:10px; + } +.alert-block code { + display:block; + white-space:normal; + } + +.pager li > a, +.pager li > span { + display: inline-block; + padding: 5px 14px; + background-color: #fff; + border: 1px solid #ddd; + -webkit-border-radius: 0px; + -moz-border-radius: 0px; + border-radius: 0px; +} diff --git a/interface/favicon.ico b/interface/favicon.ico Binary files differnew file mode 100644 index 000000000..79dd1db54 --- /dev/null +++ b/interface/favicon.ico diff --git a/interface/img/asc.png b/interface/img/asc.png Binary files differnew file mode 100644 index 000000000..302161589 --- /dev/null +++ b/interface/img/asc.png diff --git a/interface/img/desc.png b/interface/img/desc.png Binary files differnew file mode 100644 index 000000000..068c5494f --- /dev/null +++ b/interface/img/desc.png diff --git a/interface/img/spinner.gif b/interface/img/spinner.gif Binary files differnew file mode 100644 index 000000000..9ad345573 --- /dev/null +++ b/interface/img/spinner.gif diff --git a/interface/img/spinner.png b/interface/img/spinner.png Binary files differnew file mode 100644 index 000000000..bccc78605 --- /dev/null +++ b/interface/img/spinner.png diff --git a/interface/index.html b/interface/index.html new file mode 100644 index 000000000..a02a2d668 --- /dev/null +++ b/interface/index.html @@ -0,0 +1,320 @@ +<!DOCTYPE html> +<html lang="en"> +<head> + <meta charset="utf-8"> + <title>Rspamd Web Interface</title> + <meta name="viewport" content="width=device-width, initial-scale=1.0"> + <meta name="description" content=""> + <meta name="author" content=""> + <link href="//cdnjs.cloudflare.com/ajax/libs/file-uploader/3.7.0/fineuploader.min.css" rel="stylesheet"> + <link href="//maxcdn.bootstrapcdn.com/bootstrap/3.3.5/css/bootstrap.min.css" rel="stylesheet"> + <link rel="stylesheet" type="text/css" href="./css/datatables.min.css"/> + <link href="./css/rspamd.css" rel="stylesheet"> +</head> + +<body> + +<nav class="navbar navbar-default" id="navBar"> + <div class="container-fluid"> + <div class="navbar-header"> + <a class="navbar-brand" href="."><b>Rspamd</b></a> + </div> + <ul class="nav pull-right navbar-nav" style="display:none"> + <li><a href="#" data-toggle="tab" id="refresh">Refresh</a></li> + <li class="spinner"><a href="#" data-toggle="tab" id="disconnect">Disconnect</a></li> + </ul> + <ul class="nav navbar-nav nav-pills" role="tablist"> + <li role="presentation" class="active"><a id="status_nav" aria-controls="status" role="tab" href="#status" data-toggle="tab">Status</a></li> + <li role="presentation"><a id="configuration_nav" aria-controls="configuration" role="tab" href="#configuration" data-toggle="tab">Configuration</a></li> + <li role="presentation"><a id="learning_nav" aria-controls="learning" role="tab" href="#learning" data-toggle="tab">Learning</a></li> + <li role="presentation"><a id="scan_nav"aria-controls="scan" role="tab" href="#scan" data-toggle="tab">Scan</a></li> + <li role="presentation"><a id="history_nav" aria-controls="history" role="tab" href="#history" data-toggle="tab">History</a></li> + </ul> + </div> +</nav> + +<div id="mainUI" style="display:none"> + + <div class="container-fluid"> + + <div class="tab-content"> + <div class="tab-pane active" id="status"> + <div class="row"> + <div class="col-md-12"> + <div class="widget-box widget-plain"> + <ul id="statWidgets" class="stat-boxes" style="display:none"> + </ul> + </div> + </div> + </div> + + <div class="widget-box"> + <div class="widget-title"> + <span class="icon"><i class="glyphicon glyphicon-signal"></i></span> + <h5>Statistics</h5> + </div> + <div class="widget-content chart-content"> + <div class="row row-chart"> + <div class="chart" id="chart"> + <span class="notice">Loading..</span> + <noscript>Please enable Javascript</noscript> + </div> + </div> + </div> + </div> + </div> + + <div class="tab-pane" id="configuration"> + <div class="widget-box"> + <div class="widget-title"> + <span class="icon"><i class="glyphicon glyphicon-tasks"></i></span><h5>Actions</h5> + </div> + <div class="widget-content actions-content" id="actionsBody"> + </div> + </div> + <div class="widget-box"> + <div class="widget-title"> + <span class="icon"><i class="glyphicon glyphicon-filter"></i></span><h5>Rules</h5> + </div> + <div class="widget-content"> + <button role="button" class="btn btn-primary" + data-toggle="modal" + data-source="#symbolsForm" + data-target="#modalDialog" + data-title="Symbols">Edit Rules</button> + </div> + </div> + <div class="widget-box"> + <div class="widget-title"> + <span class="icon"><i class="glyphicon glyphicon-list"></i></span><h5>Lists</h5> + </div> + <div class="widget-content nopadding"> + <table class="table table-condensed table-hover" id="listMaps"> + </table> + </div> + </div> + </div> + + <div class="tab-pane" id="learning"> + <div class="widget-box"> + <div class="widget-title"> + <span class="icon"><i class="glyphicon glyphicon-file"></i></span> + <h5>Learn RSPAMD</h5> + </div> + <div class="widget-content"> + <div class="row"> + <form class="col-md-6 upload-form" id="uploadSpamForm"> + <h5>Upload SPAM examples:</h5> + <button id="uploadSpamTrigger" class="btn pull-right btn-upload-trigger"><i class="glyphicon glyphicon-upload"></i> Upload files</button> + <div id="uploadSpamFiles"></div> + </form> + <form class="col-md-6 upload-form" id="uploadHamForm"> + <h5>Upload HAM examples:</h5> + <button id="uploadHamTrigger" class="btn pull-right btn-upload-trigger"><i class="glyphicon glyphicon-upload"></i> Upload files</button> + <div id="uploadHamFiles"></div> + </form> + </div> + </div> + <div class="widget-content"> + <div class="row"> + <form class="col-md-6"> + <h5>Insert raw SPAM source:</h5> + <textarea class="col-md-5 upload-textarea" id="spamTextSource" value=""></textarea> + <p><button class="btn btn-default pull-right" data-upload="spam"><i class="glyphicon glyphicon-upload"></i> Upload text</button></p> + </form> + <form class="col-md-6"> + <h5>Insert raw HAM source:</h5> + <textarea class="col-md-5 upload-textarea" id="hamTextSource" value=""></textarea> + <p><button class="btn btn-default pull-right" data-upload="ham"><i class="glyphicon glyphicon-upload"></i> Upload text</button></p> + </form> + </div> + <div class="row"> + <form class="col-md-6 upload-form" id="uploadFuzzyForm"> + <h5>Upload Fuzzy examples:</h5> + <div class="row"> + <label class="pull-left"> + Flag + </label> + <div class="pull-right col-md-10"> + <input id="fuzzyFlagUpload" class="slider" type="slider" value="0"/> + </div> + </div> + <div class="row"> + <label class="pull-left"> + Weight + </label> + <div class="pull-right col-md-10"> + <input id="fuzzyWeightUpload" class="slider" type="slider" value="0"/> + </div> + </div> + <button id="uploadFuzzyTrigger" class="btn pull-right btn-upload-trigger"><i class="glyphicon glyphicon-upload"></i> Upload files</button> + <div id="uploadFuzzyFiles"></div> + </form> + </div> + <div class="row"> + <form class="col-md-6"> + <h5>Insert raw Fuzzy storage:</h5> + <textarea class="col-md-5 upload-textarea" id="fuzzyTextSource" value=""></textarea> + <div class="row"> + <label class="pull-left"> + Flag + </label> + <div class="pull-right col-md-10"> + <input id="fuzzyFlagText" class="slider" type="slider" value="0"/> + </div> + </div> + <div class="row"> + <label class="pull-left"> + Weight + </label> + <div class="pull-right col-md-10"> + <input id="fuzzyWeightText" class="slider" type="slider" value="0"/> + </div> + </div> + <p><button class="btn btn-default pull-right" data-upload="fuzzy"><i class="glyphicon glyphicon-upload"></i> Upload text</button></p> + </form> + </div> + </div> + </div> + </div> + + <div class="tab-pane" id="scan"> + <div class="widget-box"> + <div class="widget-title"> + <span class="icon"><i class="glyphicon glyphicon-info-sign"></i></span> + <h5>Online scan suspected message</h5> + </div> + <div class="widget-content"> + <h5>Paste and scan suspicious message</h5> + <div class="row"> + <form class="col-md-12 nomargin" id="scanForm"> + <textarea class="col-md-12 scan-textarea" id="scanTextSource"></textarea> + <p><button class="btn btn-default btn-primary" data-upload="scan">Scan message</button> + <button class="btn btn-default pull-right" id="scanClean">Clean form</button></p> + </form> + </div> + <div id="scanResult" style="display:none"> + <h4>Scan results:</h4> + <div class="well nomargin nopadding"> + <table class="table table-log table-hover" id="scanOutput"> + <thead> + <th class="col4" title="Action">Action</th> + <th class="col5" title="Score / Req. score">Score / Req. score</th> + <th class="col6" title="Symbols">Symbols</th> + </thead> + </table> + </div> + </div> + </div> + </div> + </div> + + <div class="tab-pane" id="history"> + + <div class="widget-box"> + <div class="widget-title"> + <div class="buttons pull-right"> + <button class="btn btn-danger btn-sm" id="resetHistory"> + <i class="glyphicon glyphicon-remove-circle"></i> Reset + </button> + <button class="btn btn-info btn-sm" id="updateHistory"> + <i class="glyphicon glyphicon-refresh"></i> Update + </button> + </div> + <span class="icon"><i class="glyphicon glyphicon-eye-open"></i></span> + <h5>History</h5> + </div> + <div class="widget-content nopadding"> + <table class="table table-log table-hover" id="historyLog"> + <thead> + <th class="col1" title="Time">Time</th> + <th class="col2" title="ID">ID</th> + <th class="col3" title="IP">IP</th> + <th class="col4" title="Action">Action</th> + <th class="col5" title="Score / Req. score">Score / Req. score</th> + <th class="col6" title="Symbols">Symbols</th> + <th class="col7" title="Size">Size</th> + <th class="col8" title="Scan Time (s)"><div class="cell-overflow">Scan Time (s)</div></th> + <th class="col9" title="User">User</th> + </thead> + </table> + </div> + </div> + + </div> + + + </div> + </div> + +</div> + +<!-- Common modal --> +<div id="modalDialog" class="modal fade" tabindex="-1" role="dialog" aria-labelledby="modalLabel"> + <div class="modal-dialog"> + <div class="modal-content"> + <div class="modal-header"> + <button type="button" class="close" data-dismiss="modal" aria-hidden="true">×</button> + <h3 id="modalTitle"></h3> + </div> + <div class="modal-body" id="modalBody"> + <div class="progress progress-striped active"> + <div class="bar" style="width:100%;"></div> + </div> + </div> + <div class="modal-footer"> + <button class="btn btn-default" data-dismiss="modal" aria-hidden="true" id="modalClose">Close</button> + <button class="btn btn-primary" id="modalSave">Save changes</button> + </div> + </div> + </div> +</div> + +<!-- login modal --> +<div id="connectDialog" class="modal" tabindex="-1" role="dialog" aria-labelledby="RSPAMD Connect"> + <div class="modal-dialog"> + <div class="modal-content"> + <div class="modal-header"> + <h3>RSPAMD Connect</h3> + </div> + <div class="modal-body" id="connectBody"> + <form id="connectForm"> + <!-- + <div class="form-group"> + <label class="control-label" for="connectHost">Hostname</label> + <div class="controls"> + <input class=col-md-2" type="text" id="connectHost" placeholder="Hostname" tabindex="1"> + </div> + </div> + --> + <div class="form-group"> + <label class="col-sm-2 control-label" for="connectPassword">Password:</label> + <div class="col-sm-10"> + <input class="form-control" + type="password" + id="connectPassword" + placeholder="Password" + tabindex="1" /> + </div> + </div> + <div class="form-group"> + <button type="submit" id="connectButton" class="btn btn-primary" tabindex="1">Connect</button> + </div> + </form> + </div> + </div> + </div> +</div> + +<div id="backDrop" class="modal-backdrop fade in" style="display:none"></div> +<script src="//code.jquery.com/jquery-2.1.4.min.js"></script> +<script src="//maxcdn.bootstrapcdn.com/bootstrap/3.3.5/js/bootstrap.min.js"></script> +<script src="//cdnjs.cloudflare.com/ajax/libs/jquery-cookie/1.4.1/jquery.cookie.min.js"></script> +<script src="//cdnjs.cloudflare.com/ajax/libs/file-uploader/3.7.0/fineuploader.min.js"></script> +<script src="//cdnjs.cloudflare.com/ajax/libs/d3/3.5.5/d3.min.js"></script> +<script src="./js/d3pie.min.js"></script> +<script src="./js/rspamd.js"></script> +<script type="text/javascript" src="./js/datatables.min.js"></script> + +</body> +</html> diff --git a/interface/js/d3pie.min.js b/interface/js/d3pie.min.js new file mode 100644 index 000000000..8bf6e3734 --- /dev/null +++ b/interface/js/d3pie.min.js @@ -0,0 +1,9 @@ +/*! +* d3pie +* @author Ben Keen +* @version 0.1.8 +* @date April 2015 +* @repo http://github.com/benkeen/d3pie +*/ +!function(a,b){"function"==typeof define&&define.amd?define([],b):"object"==typeof exports?module.exports=b(require()):a.d3pie=b(a)}(this,function(){var a="d3pie",b="0.1.6",c=0,d={header:{title:{text:"",color:"#333333",fontSize:18,font:"arial"},subtitle:{text:"",color:"#666666",fontSize:14,font:"arial"},location:"top-center",titleSubtitlePadding:8},footer:{text:"",color:"#666666",fontSize:14,font:"arial",location:"left"},size:{canvasHeight:500,canvasWidth:500,pieInnerRadius:"0%",pieOuterRadius:null},data:{sortOrder:"none",ignoreSmallSegments:{enabled:!1,valueType:"percentage",value:null},smallSegmentGrouping:{enabled:!1,value:1,valueType:"percentage",label:"Other",color:"#cccccc"},content:[]},labels:{outer:{format:"label",hideWhenLessThanPercentage:null,pieDistance:30},inner:{format:"percentage",hideWhenLessThanPercentage:null},mainLabel:{color:"#333333",font:"arial",fontSize:10},percentage:{color:"#dddddd",font:"arial",fontSize:10,decimalPlaces:0},value:{color:"#cccc44",font:"arial",fontSize:10},lines:{enabled:!0,style:"curved",color:"segment"},truncation:{enabled:!1,truncateLength:30},formatter:null},effects:{load:{effect:"default",speed:1e3},pullOutSegmentOnClick:{effect:"bounce",speed:300,size:10},highlightSegmentOnMouseover:!0,highlightLuminosity:-.2},tooltips:{enabled:!1,type:"placeholder",string:"",placeholderParser:null,styles:{fadeInSpeed:250,backgroundColor:"#000000",backgroundOpacity:.5,color:"#efefef",borderRadius:2,font:"arial",fontSize:10,padding:4}},misc:{colors:{background:null,segments:["#2484c1","#65a620","#7b6888","#a05d56","#961a1a","#d8d23a","#e98125","#d0743c","#635222","#6ada6a","#0c6197","#7d9058","#207f33","#44b9b0","#bca44a","#e4a14b","#a3acb2","#8cc3e9","#69a6f9","#5b388f","#546e91","#8bde95","#d2ab58","#273c71","#98bf6e","#4daa4b","#98abc5","#cc1010","#31383b","#006391","#c2643f","#b0a474","#a5a39c","#a9c2bc","#22af8c","#7fcecf","#987ac6","#3d3b87","#b77b1c","#c9c2b6","#807ece","#8db27c","#be66a2","#9ed3c6","#00644b","#005064","#77979f","#77e079","#9c73ab","#1f79a7"],segmentStroke:"#ffffff"},gradient:{enabled:!1,percentage:95,color:"#000000"},canvasPadding:{top:5,right:5,bottom:5,left:5},pieCenterOffset:{x:0,y:0},cssPrefix:null},callbacks:{onload:null,onMouseoverSegment:null,onMouseoutSegment:null,onClickSegment:null}},e={initialCheck:function(a){var b=a.cssPrefix,c=a.element,d=a.options;if(!window.d3||!window.d3.hasOwnProperty("version"))return console.error("d3pie error: d3 is not available"),!1;if(!(c instanceof HTMLElement||c instanceof SVGElement))return console.error("d3pie error: the first d3pie() param must be a valid DOM element (not jQuery) or a ID string."),!1;if(!/[a-zA-Z][a-zA-Z0-9_-]*$/.test(b))return console.error("d3pie error: invalid options.misc.cssPrefix"),!1;if(!f.isArray(d.data.content))return console.error("d3pie error: invalid config structure: missing data.content property."),!1;if(0===d.data.content.length)return console.error("d3pie error: no data supplied."),!1;for(var e=[],g=0;g<d.data.content.length;g++)"number"!=typeof d.data.content[g].value||isNaN(d.data.content[g].value)?console.log("not valid: ",d.data.content[g]):d.data.content[g].value<=0?console.log("not valid - should have positive value: ",d.data.content[g]):e.push(d.data.content[g]);return a.options.data.content=e,!0}},f={addSVGSpace:function(a){var b=a.element,c=a.options.size.canvasWidth,d=a.options.size.canvasHeight,e=a.options.misc.colors.background,f=d3.select(b).append("svg:svg").attr("width",c).attr("height",d);return"transparent"!==e&&f.style("background-color",function(){return e}),f},whenIdExists:function(a,b){var c=1,d=1e3,e=setInterval(function(){document.getElementById(a)&&(clearInterval(e),b()),c>d&&clearInterval(e),c++},1)},whenElementsExist:function(a,b){var c=1,d=1e3,e=setInterval(function(){for(var f=!0,g=0;g<a.length;g++)if(!document.getElementById(a[g])){f=!1;break}f&&(clearInterval(e),b()),c>d&&clearInterval(e),c++},1)},shuffleArray:function(a){for(var b,c,d=a.length;0!==d;)c=Math.floor(Math.random()*d),d-=1,b=a[d],a[d]=a[c],a[c]=b;return a},processObj:function(a,b,c){return"string"==typeof b?f.processObj(a,b.split("."),c):1===b.length&&void 0!==c?(a[b[0]]=c,a[b[0]]):0===b.length?a:f.processObj(a[b[0]],b.slice(1),c)},getDimensions:function(a){var b=document.getElementById(a),c=0,d=0;if(b){var e=b.getBBox();c=e.width,d=e.height}else console.log("error: getDimensions() "+a+" not found.");return{w:c,h:d}},rectIntersect:function(a,b){var c=b.x>a.x+a.w||b.x+b.w<a.x||b.y+b.h<a.y||b.y>a.y+a.h;return!c},getColorShade:function(a,b){a=String(a).replace(/[^0-9a-f]/gi,""),a.length<6&&(a=a[0]+a[0]+a[1]+a[1]+a[2]+a[2]),b=b||0;for(var c="#",d=0;3>d;d++){var e=parseInt(a.substr(2*d,2),16);e=Math.round(Math.min(Math.max(0,e+e*b),255)).toString(16),c+=("00"+e).substr(e.length)}return c},initSegmentColors:function(a){for(var b=a.options.data.content,c=a.options.misc.colors.segments,d=[],e=0;e<b.length;e++)d.push(b[e].hasOwnProperty("color")?b[e].color:c[e]);return d},applySmallSegmentGrouping:function(a,b){var c;"percentage"===b.valueType&&(c=h.getTotalPieSize(a));for(var d=[],e=[],f=0,g=0;g<a.length;g++)if("percentage"===b.valueType){var i=a[g].value/c*100;if(i<=b.value){e.push(a[g]),f+=a[g].value;continue}a[g].isGrouped=!1,d.push(a[g])}else{if(a[g].value<=b.value){e.push(a[g]),f+=a[g].value;continue}a[g].isGrouped=!1,d.push(a[g])}return e.length&&d.push({color:b.color,label:b.label,value:f,isGrouped:!0,groupedData:e}),d},showPoint:function(a,b,c){a.append("circle").attr("cx",b).attr("cy",c).attr("r",2).style("fill","black")},isFunction:function(a){var b={};return a&&"[object Function]"===b.toString.call(a)},isArray:function(a){return"[object Array]"===Object.prototype.toString.call(a)}},g=function(){var a,b,c,d,e,f,h=arguments[0]||{},i=1,j=arguments.length,k=!1,l=Object.prototype.toString,m=Object.prototype.hasOwnProperty,n={"[object Boolean]":"boolean","[object Number]":"number","[object String]":"string","[object Function]":"function","[object Array]":"array","[object Date]":"date","[object RegExp]":"regexp","[object Object]":"object"},o={isFunction:function(a){return"function"===o.type(a)},isArray:Array.isArray||function(a){return"array"===o.type(a)},isWindow:function(a){return null!==a&&a===a.window},isNumeric:function(a){return!isNaN(parseFloat(a))&&isFinite(a)},type:function(a){return null===a?String(a):n[l.call(a)]||"object"},isPlainObject:function(a){if(!a||"object"!==o.type(a)||a.nodeType)return!1;try{if(a.constructor&&!m.call(a,"constructor")&&!m.call(a.constructor.prototype,"isPrototypeOf"))return!1}catch(b){return!1}var c;for(c in a);return void 0===c||m.call(a,c)}};for("boolean"==typeof h&&(k=h,h=arguments[1]||{},i=2),"object"==typeof h||o.isFunction(h)||(h={}),j===i&&(h=this,--i),i;j>i;i++)if(null!==(a=arguments[i]))for(b in a)c=h[b],d=a[b],h!==d&&(k&&d&&(o.isPlainObject(d)||(e=o.isArray(d)))?(e?(e=!1,f=c&&o.isArray(c)?c:[]):f=c&&o.isPlainObject(c)?c:{},h[b]=g(k,f,d)):void 0!==d&&(h[b]=d));return h},h={toRadians:function(a){return a*(Math.PI/180)},toDegrees:function(a){return a*(180/Math.PI)},computePieRadius:function(a){var b=a.options.size,c=a.options.misc.canvasPadding,d=b.canvasWidth-c.left-c.right,e=b.canvasHeight-c.top-c.bottom;"pie-center"!==a.options.header.location&&(e-=a.textComponents.headerHeight),a.textComponents.footer.exists&&(e-=a.textComponents.footer.h),e=0>e?0:e;var f,g,h=(e>d?d:e)/3;if(null!==b.pieOuterRadius)if(/%/.test(b.pieOuterRadius)){g=parseInt(b.pieOuterRadius.replace(/[\D]/,""),10),g=g>99?99:g,g=0>g?0:g;var i=e>d?d:e;if("none"!==a.options.labels.outer.format){var j=2*parseInt(a.options.labels.outer.pieDistance,10);i-j>0&&(i-=j)}h=Math.floor(i/100*g)/2}else h=parseInt(b.pieOuterRadius,10);/%/.test(b.pieInnerRadius)?(g=parseInt(b.pieInnerRadius.replace(/[\D]/,""),10),g=g>99?99:g,g=0>g?0:g,f=Math.floor(h/100*g)):f=parseInt(b.pieInnerRadius,10),a.innerRadius=f,a.outerRadius=h},getTotalPieSize:function(a){for(var b=0,c=0;c<a.length;c++)b+=a[c].value;return b},sortPieData:function(a){var b=a.options.data.content,c=a.options.data.sortOrder;switch(c){case"none":break;case"random":b=f.shuffleArray(b);break;case"value-asc":b.sort(function(a,b){return a.value<b.value?-1:1});break;case"value-desc":b.sort(function(a,b){return a.value<b.value?1:-1});break;case"label-asc":b.sort(function(a,b){return a.label.toLowerCase()>b.label.toLowerCase()?1:-1});break;case"label-desc":b.sort(function(a,b){return a.label.toLowerCase()<b.label.toLowerCase()?1:-1})}return b},getPieTranslateCenter:function(a){return"translate("+a.x+","+a.y+")"},calculatePieCenter:function(a){var b=a.options.misc.pieCenterOffset,c=a.textComponents.title.exists&&"pie-center"!==a.options.header.location,d=a.textComponents.subtitle.exists&&"pie-center"!==a.options.header.location,e=a.options.misc.canvasPadding.top;c&&d?e+=a.textComponents.title.h+a.options.header.titleSubtitlePadding+a.textComponents.subtitle.h:c?e+=a.textComponents.title.h:d&&(e+=a.textComponents.subtitle.h);var f=0;a.textComponents.footer.exists&&(f=a.textComponents.footer.h+a.options.misc.canvasPadding.bottom);var g=(a.options.size.canvasWidth-a.options.misc.canvasPadding.left-a.options.misc.canvasPadding.right)/2+a.options.misc.canvasPadding.left,h=(a.options.size.canvasHeight-f-e)/2+e;g+=b.x,h+=b.y,a.pieCenter={x:g,y:h}},rotate:function(a,b,c,d,e){e=e*Math.PI/180;var f=Math.cos,g=Math.sin,h=(a-c)*f(e)-(b-d)*g(e)+c,i=(a-c)*g(e)+(b-d)*f(e)+d;return{x:h,y:i}},translate:function(a,b,c,d){var e=h.toRadians(d);return{x:a+c*Math.sin(e),y:b-c*Math.cos(e)}},pointIsInArc:function(a,b,c){var d=c.innerRadius()(b),e=c.outerRadius()(b),f=c.startAngle()(b),g=c.endAngle()(b),h=a.x*a.x+a.y*a.y,i=Math.atan2(a.x,-a.y);return i=0>i?i+2*Math.PI:i,h>=d*d&&e*e>=h&&i>=f&&g>=i}},i={add:function(a,b,c){var d=i.getIncludes(c),e=a.options.labels,f=a.svg.insert("g","."+a.cssPrefix+"labels-"+b).attr("class",a.cssPrefix+"labels-"+b),g=f.selectAll("."+a.cssPrefix+"labelGroup-"+b).data(a.options.data.content).enter().append("g").attr("id",function(c,d){return a.cssPrefix+"labelGroup"+d+"-"+b}).attr("data-index",function(a,b){return b}).attr("class",a.cssPrefix+"labelGroup-"+b).style("opacity",0),h={section:b,sectionDisplayType:c};d.mainLabel&&g.append("text").attr("id",function(c,d){return a.cssPrefix+"segmentMainLabel"+d+"-"+b}).attr("class",a.cssPrefix+"segmentMainLabel-"+b).text(function(a,b){var c=a.label;return e.formatter?(h.index=b,h.part="mainLabel",h.value=a.value,h.label=c,c=e.formatter(h)):e.truncation.enabled&&a.label.length>e.truncation.truncateLength&&(c=a.label.substring(0,e.truncation.truncateLength)+"..."),c}).style("font-size",e.mainLabel.fontSize+"px").style("font-family",e.mainLabel.font).style("fill",e.mainLabel.color),d.percentage&&g.append("text").attr("id",function(c,d){return a.cssPrefix+"segmentPercentage"+d+"-"+b}).attr("class",a.cssPrefix+"segmentPercentage-"+b).text(function(b,c){var d=j.getPercentage(a,c,a.options.labels.percentage.decimalPlaces);return e.formatter?(h.index=c,h.part="percentage",h.value=b.value,h.label=d,d=e.formatter(h)):d+="%",d}).style("font-size",e.percentage.fontSize+"px").style("font-family",e.percentage.font).style("fill",e.percentage.color),d.value&&g.append("text").attr("id",function(c,d){return a.cssPrefix+"segmentValue"+d+"-"+b}).attr("class",a.cssPrefix+"segmentValue-"+b).text(function(a,b){return h.index=b,h.part="value",h.value=a.value,h.label=a.value,e.formatter?e.formatter(h,a.value):a.value}).style("font-size",e.value.fontSize+"px").style("font-family",e.value.font).style("fill",e.value.color)},positionLabelElements:function(a,b,c){i["dimensions-"+b]=[];var d=d3.selectAll("."+a.cssPrefix+"labelGroup-"+b);d.each(function(c,d){var e=d3.select(this).selectAll("."+a.cssPrefix+"segmentMainLabel-"+b),f=d3.select(this).selectAll("."+a.cssPrefix+"segmentPercentage-"+b),g=d3.select(this).selectAll("."+a.cssPrefix+"segmentValue-"+b);i["dimensions-"+b].push({mainLabel:null!==e.node()?e.node().getBBox():null,percentage:null!==f.node()?f.node().getBBox():null,value:null!==g.node()?g.node().getBBox():null})});var e=5,f=i["dimensions-"+b];switch(c){case"label-value1":d3.selectAll("."+a.cssPrefix+"segmentValue-"+b).attr("dx",function(a,b){return f[b].mainLabel.width+e});break;case"label-value2":d3.selectAll("."+a.cssPrefix+"segmentValue-"+b).attr("dy",function(a,b){return f[b].mainLabel.height});break;case"label-percentage1":d3.selectAll("."+a.cssPrefix+"segmentPercentage-"+b).attr("dx",function(a,b){return f[b].mainLabel.width+e});break;case"label-percentage2":d3.selectAll("."+a.cssPrefix+"segmentPercentage-"+b).attr("dx",function(a,b){return f[b].mainLabel.width/2-f[b].percentage.width/2}).attr("dy",function(a,b){return f[b].mainLabel.height})}},computeLabelLinePositions:function(a){a.lineCoordGroups=[],d3.selectAll("."+a.cssPrefix+"labelGroup-outer").each(function(b,c){return i.computeLinePosition(a,c)})},computeLinePosition:function(a,b){var c,d,e,f,g=j.getSegmentAngle(b,a.options.data.content,a.totalSize,{midpoint:!0}),i=h.rotate(a.pieCenter.x,a.pieCenter.y-a.outerRadius,a.pieCenter.x,a.pieCenter.y,g),k=a.outerLabelGroupData[b].h/5,l=6,m=Math.floor(g/90),n=4;switch(2===m&&180===g&&(m=1),m){case 0:c=a.outerLabelGroupData[b].x-l-(a.outerLabelGroupData[b].x-l-i.x)/2,d=a.outerLabelGroupData[b].y+(i.y-a.outerLabelGroupData[b].y)/n,e=a.outerLabelGroupData[b].x-l,f=a.outerLabelGroupData[b].y-k;break;case 1:c=i.x+(a.outerLabelGroupData[b].x-i.x)/n,d=i.y+(a.outerLabelGroupData[b].y-i.y)/n,e=a.outerLabelGroupData[b].x-l,f=a.outerLabelGroupData[b].y-k;break;case 2:var o=a.outerLabelGroupData[b].x+a.outerLabelGroupData[b].w+l;c=i.x-(i.x-o)/n,d=i.y+(a.outerLabelGroupData[b].y-i.y)/n,e=a.outerLabelGroupData[b].x+a.outerLabelGroupData[b].w+l,f=a.outerLabelGroupData[b].y-k;break;case 3:var p=a.outerLabelGroupData[b].x+a.outerLabelGroupData[b].w+l;c=p+(i.x-p)/n,d=a.outerLabelGroupData[b].y+(i.y-a.outerLabelGroupData[b].y)/n,e=a.outerLabelGroupData[b].x+a.outerLabelGroupData[b].w+l,f=a.outerLabelGroupData[b].y-k}"straight"===a.options.labels.lines.style?a.lineCoordGroups[b]=[{x:i.x,y:i.y},{x:e,y:f}]:a.lineCoordGroups[b]=[{x:i.x,y:i.y},{x:c,y:d},{x:e,y:f}]},addLabelLines:function(a){var b=a.svg.insert("g","."+a.cssPrefix+"pieChart").attr("class",a.cssPrefix+"lineGroups").style("opacity",0),c=b.selectAll("."+a.cssPrefix+"lineGroup").data(a.lineCoordGroups).enter().append("g").attr("class",a.cssPrefix+"lineGroup"),d=d3.svg.line().interpolate("basis").x(function(a){return a.x}).y(function(a){return a.y});c.append("path").attr("d",d).attr("stroke",function(b,c){return"segment"===a.options.labels.lines.color?a.options.colors[c]:a.options.labels.lines.color}).attr("stroke-width",1).attr("fill","none").style("opacity",function(b,c){var d=a.options.labels.outer.hideWhenLessThanPercentage,e=j.getPercentage(a,c,a.options.labels.percentage.decimalPlaces),f=null!==d&&d>e||""===a.options.data.content[c].label;return f?0:1})},positionLabelGroups:function(a,b){"none"!==a.options.labels[b].format&&d3.selectAll("."+a.cssPrefix+"labelGroup-"+b).style("opacity",0).attr("transform",function(c,d){var e,i;if("outer"===b)e=a.outerLabelGroupData[d].x,i=a.outerLabelGroupData[d].y;else{var k=g(!0,{},a.pieCenter);if(a.innerRadius>0){var l=j.getSegmentAngle(d,a.options.data.content,a.totalSize,{midpoint:!0}),m=h.translate(a.pieCenter.x,a.pieCenter.y,a.innerRadius,l);k.x=m.x,k.y=m.y}var n=f.getDimensions(a.cssPrefix+"labelGroup"+d+"-inner"),o=n.w/2,p=n.h/4;e=k.x+(a.lineCoordGroups[d][0].x-k.x)/1.8,i=k.y+(a.lineCoordGroups[d][0].y-k.y)/1.8,e-=o,i+=p}return"translate("+e+","+i+")"})},fadeInLabelsAndLines:function(a){var b="default"===a.options.effects.load.effect?a.options.effects.load.speed:1;setTimeout(function(){var b="default"===a.options.effects.load.effect?400:1;d3.selectAll("."+a.cssPrefix+"labelGroup-outer").transition().duration(b).style("opacity",function(b,c){var d=a.options.labels.outer.hideWhenLessThanPercentage,e=j.getPercentage(a,c,a.options.labels.percentage.decimalPlaces);return null!==d&&d>e?0:1}),d3.selectAll("."+a.cssPrefix+"labelGroup-inner").transition().duration(b).style("opacity",function(b,c){var d=a.options.labels.inner.hideWhenLessThanPercentage,e=j.getPercentage(a,c,a.options.labels.percentage.decimalPlaces);return null!==d&&d>e?0:1}),d3.selectAll("g."+a.cssPrefix+"lineGroups").transition().duration(b).style("opacity",1),f.isFunction(a.options.callbacks.onload)&&setTimeout(function(){try{a.options.callbacks.onload()}catch(b){}},b)},b)},getIncludes:function(a){var b=!1,c=!1,d=!1;switch(a){case"label":b=!0;break;case"value":c=!0;break;case"percentage":d=!0;break;case"label-value1":case"label-value2":b=!0,c=!0;break;case"label-percentage1":case"label-percentage2":b=!0,d=!0}return{mainLabel:b,value:c,percentage:d}},computeOuterLabelCoords:function(a){a.svg.selectAll("."+a.cssPrefix+"labelGroup-outer").each(function(b,c){return i.getIdealOuterLabelPositions(a,c)}),i.resolveOuterLabelCollisions(a)},resolveOuterLabelCollisions:function(a){if("none"!==a.options.labels.outer.format){var b=a.options.data.content.length;i.checkConflict(a,0,"clockwise",b),i.checkConflict(a,b-1,"anticlockwise",b)}},checkConflict:function(a,b,c,d){var e,g;if(!(1>=d)){var h=a.outerLabelGroupData[b].hs;if(!("clockwise"===c&&"right"!==h||"anticlockwise"===c&&"left"!==h)){var j="clockwise"===c?b+1:b-1,k=a.outerLabelGroupData[b],l=a.outerLabelGroupData[j],m={labelHeights:a.outerLabelGroupData[0].h,center:a.pieCenter,lineLength:a.outerRadius+a.options.labels.outer.pieDistance,heightChange:a.outerLabelGroupData[0].h+1};if("clockwise"===c){for(e=0;b>=e;e++)if(g=a.outerLabelGroupData[e],f.rectIntersect(g,l)){i.adjustLabelPos(a,j,k,m);break}}else for(e=d-1;e>=b;e--)if(g=a.outerLabelGroupData[e],f.rectIntersect(g,l)){i.adjustLabelPos(a,j,k,m);break}i.checkConflict(a,j,c,d)}}},adjustLabelPos:function(a,b,c,d){var e,f,g,h;h=c.y+d.heightChange,f=d.center.y-h,e=Math.sqrt(Math.abs(d.lineLength)>Math.abs(f)?d.lineLength*d.lineLength-f*f:f*f-d.lineLength*d.lineLength),g="right"===c.hs?d.center.x+e:d.center.x-e-a.outerLabelGroupData[b].w,a.outerLabelGroupData[b].x=g,a.outerLabelGroupData[b].y=h},getIdealOuterLabelPositions:function(a,b){var c=d3.select("#"+a.cssPrefix+"labelGroup"+b+"-outer").node();if(c){var d=c.getBBox(),e=j.getSegmentAngle(b,a.options.data.content,a.totalSize,{midpoint:!0}),f=a.pieCenter.x,g=a.pieCenter.y-(a.outerRadius+a.options.labels.outer.pieDistance),i=h.rotate(f,g,a.pieCenter.x,a.pieCenter.y,e),k="right";e>180?(i.x-=d.width+8,k="left"):i.x+=8,a.outerLabelGroupData[b]={x:i.x,y:i.y,w:d.width,h:d.height,hs:k}}}},j={create:function(a){var b=a.pieCenter,c=a.options.colors,d=a.options.effects.load,e=a.options.misc.colors.segmentStroke,f=a.svg.insert("g","#"+a.cssPrefix+"title").attr("transform",function(){return h.getPieTranslateCenter(b)}).attr("class",a.cssPrefix+"pieChart"),g=d3.svg.arc().innerRadius(a.innerRadius).outerRadius(a.outerRadius).startAngle(0).endAngle(function(b){return b.value/a.totalSize*2*Math.PI}),i=f.selectAll("."+a.cssPrefix+"arc").data(a.options.data.content).enter().append("g").attr("class",a.cssPrefix+"arc"),k=d.speed;"none"===d.effect&&(k=0),i.append("path").attr("id",function(b,c){return a.cssPrefix+"segment"+c}).attr("fill",function(b,d){var e=c[d];return a.options.misc.gradient.enabled&&(e="url(#"+a.cssPrefix+"grad"+d+")"),e}).style("stroke",e).style("stroke-width",1).transition().ease("cubic-in-out").duration(k).attr("data-index",function(a,b){return b}).attrTween("d",function(b){var c=d3.interpolate({value:0},b);return function(b){return a.arc(c(b))}}),a.svg.selectAll("g."+a.cssPrefix+"arc").attr("transform",function(b,c){var d=0;return c>0&&(d=j.getSegmentAngle(c-1,a.options.data.content,a.totalSize)),"rotate("+d+")"}),a.arc=g},addGradients:function(a){var b=a.svg.append("defs").selectAll("radialGradient").data(a.options.data.content).enter().append("radialGradient").attr("gradientUnits","userSpaceOnUse").attr("cx",0).attr("cy",0).attr("r","120%").attr("id",function(b,c){return a.cssPrefix+"grad"+c});b.append("stop").attr("offset","0%").style("stop-color",function(b,c){return a.options.colors[c]}),b.append("stop").attr("offset",a.options.misc.gradient.percentage+"%").style("stop-color",a.options.misc.gradient.color)},addSegmentEventHandlers:function(a){var b=d3.selectAll("."+a.cssPrefix+"arc,."+a.cssPrefix+"labelGroup-inner,."+a.cssPrefix+"labelGroup-outer");b.on("click",function(){var b,c=d3.select(this);if(c.attr("class")===a.cssPrefix+"arc")b=c.select("path");else{var d=c.attr("data-index");b=d3.select("#"+a.cssPrefix+"segment"+d)}var e=b.attr("class")===a.cssPrefix+"expanded";j.onSegmentEvent(a,a.options.callbacks.onClickSegment,b,e),"none"!==a.options.effects.pullOutSegmentOnClick.effect&&(e?j.closeSegment(a,b.node()):j.openSegment(a,b.node()))}),b.on("mouseover",function(){var b,c,d=d3.select(this);if(d.attr("class")===a.cssPrefix+"arc"?b=d.select("path"):(c=d.attr("data-index"),b=d3.select("#"+a.cssPrefix+"segment"+c)),a.options.effects.highlightSegmentOnMouseover){c=b.attr("data-index");var e=a.options.colors[c];b.style("fill",f.getColorShade(e,a.options.effects.highlightLuminosity))}a.options.tooltips.enabled&&(c=b.attr("data-index"),l.showTooltip(a,c));var g=b.attr("class")===a.cssPrefix+"expanded";j.onSegmentEvent(a,a.options.callbacks.onMouseoverSegment,b,g)}),b.on("mousemove",function(){l.moveTooltip(a)}),b.on("mouseout",function(){var b,c,d=d3.select(this);if(d.attr("class")===a.cssPrefix+"arc"?b=d.select("path"):(c=d.attr("data-index"),b=d3.select("#"+a.cssPrefix+"segment"+c)),a.options.effects.highlightSegmentOnMouseover){c=b.attr("data-index");var e=a.options.colors[c];a.options.misc.gradient.enabled&&(e="url(#"+a.cssPrefix+"grad"+c+")"),b.style("fill",e)}a.options.tooltips.enabled&&(c=b.attr("data-index"),l.hideTooltip(a,c));var f=b.attr("class")===a.cssPrefix+"expanded";j.onSegmentEvent(a,a.options.callbacks.onMouseoutSegment,b,f)})},onSegmentEvent:function(a,b,c,d){if(f.isFunction(b)){var e=parseInt(c.attr("data-index"),10);b({segment:c.node(),index:e,expanded:d,data:a.options.data.content[e]})}},openSegment:function(a,b){a.isOpeningSegment||(a.isOpeningSegment=!0,d3.selectAll("."+a.cssPrefix+"expanded").length>0&&j.closeSegment(a,d3.select("."+a.cssPrefix+"expanded").node()),d3.select(b).transition().ease(a.options.effects.pullOutSegmentOnClick.effect).duration(a.options.effects.pullOutSegmentOnClick.speed).attr("transform",function(b,c){var d=a.arc.centroid(b),e=d[0],f=d[1],g=Math.sqrt(e*e+f*f),h=parseInt(a.options.effects.pullOutSegmentOnClick.size,10);return"translate("+e/g*h+","+f/g*h+")"}).each("end",function(c,d){a.currentlyOpenSegment=b,a.isOpeningSegment=!1,d3.select(this).attr("class",a.cssPrefix+"expanded")}))},closeSegment:function(a,b){d3.select(b).transition().duration(400).attr("transform","translate(0,0)").each("end",function(b,c){d3.select(this).attr("class",""),a.currentlyOpenSegment=null})},getCentroid:function(a){var b=a.getBBox();return{x:b.x+b.width/2,y:b.y+b.height/2}},getSegmentAngle:function(a,b,c,d){var e,f=g({compounded:!0,midpoint:!1},d),h=b[a].value;if(f.compounded){e=0;for(var i=0;a>=i;i++)e+=b[i].value}"undefined"==typeof e&&(e=h);var j=e/c*360;if(f.midpoint){var k=h/c*360;j-=k/2}return j},getPercentage:function(a,b,c){var d=a.options.data.content[b].value/a.totalSize;return 0>=c?Math.round(100*d):(100*d).toFixed(c)}},k={offscreenCoord:-1e4,addTitle:function(a){a.svg.selectAll("."+a.cssPrefix+"title").data([a.options.header.title]).enter().append("text").text(function(a){return a.text}).attr({id:a.cssPrefix+"title","class":a.cssPrefix+"title",x:k.offscreenCoord,y:k.offscreenCoord}).attr("text-anchor",function(){var b;return b="top-center"===a.options.header.location||"pie-center"===a.options.header.location?"middle":"left"}).attr("fill",function(a){return a.color}).style("font-size",function(a){return a.fontSize+"px"}).style("font-family",function(a){return a.font})},positionTitle:function(a){var b,c=a.textComponents,d=a.options.header.location,e=a.options.misc.canvasPadding,f=a.options.size.canvasWidth,g=a.options.header.titleSubtitlePadding;b="top-left"===d?e.left:(f-e.right)/2+e.left,b+=a.options.misc.pieCenterOffset.x;var h=e.top+c.title.h;if("pie-center"===d)if(h=a.pieCenter.y,c.subtitle.exists){var i=c.title.h+g+c.subtitle.h;h=h-i/2+c.title.h}else h+=c.title.h/4;a.svg.select("#"+a.cssPrefix+"title").attr("x",b).attr("y",h)},addSubtitle:function(a){var b=a.options.header.location;a.svg.selectAll("."+a.cssPrefix+"subtitle").data([a.options.header.subtitle]).enter().append("text").text(function(a){return a.text}).attr("x",k.offscreenCoord).attr("y",k.offscreenCoord).attr("id",a.cssPrefix+"subtitle").attr("class",a.cssPrefix+"subtitle").attr("text-anchor",function(){var a;return a="top-center"===b||"pie-center"===b?"middle":"left"}).attr("fill",function(a){return a.color}).style("font-size",function(a){return a.fontSize+"px"}).style("font-family",function(a){return a.font})},positionSubtitle:function(a){var b,c=a.options.misc.canvasPadding,d=a.options.size.canvasWidth;b="top-left"===a.options.header.location?c.left:(d-c.right)/2+c.left,b+=a.options.misc.pieCenterOffset.x;var e=k.getHeaderHeight(a);a.svg.select("#"+a.cssPrefix+"subtitle").attr("x",b).attr("y",e)},addFooter:function(a){a.svg.selectAll("."+a.cssPrefix+"footer").data([a.options.footer]).enter().append("text").text(function(a){return a.text}).attr("x",k.offscreenCoord).attr("y",k.offscreenCoord).attr("id",a.cssPrefix+"footer").attr("class",a.cssPrefix+"footer").attr("text-anchor",function(){var b="left";return"bottom-center"===a.options.footer.location?b="middle":"bottom-right"===a.options.footer.location&&(b="left"),b}).attr("fill",function(a){return a.color}).style("font-size",function(a){return a.fontSize+"px"}).style("font-family",function(a){return a.font})},positionFooter:function(a){var b,c=a.options.footer.location,d=a.textComponents.footer.w,e=a.options.size.canvasWidth,f=a.options.size.canvasHeight,g=a.options.misc.canvasPadding;b="bottom-left"===c?g.left:"bottom-right"===c?e-d-g.right:e/2,a.svg.select("#"+a.cssPrefix+"footer").attr("x",b).attr("y",f-g.bottom)},getHeaderHeight:function(a){var b;if(a.textComponents.title.exists){var c=a.textComponents.title.h+a.options.header.titleSubtitlePadding+a.textComponents.subtitle.h;b="pie-center"===a.options.header.location?a.pieCenter.y-c/2+c:c+a.options.misc.canvasPadding.top}else if("pie-center"===a.options.header.location){var d=a.options.misc.canvasPadding.bottom+a.textComponents.footer.h;b=(a.options.size.canvasHeight-d)/2+a.options.misc.canvasPadding.top+a.textComponents.subtitle.h/2}else b=a.options.misc.canvasPadding.top+a.textComponents.subtitle.h;return b}},l={addTooltips:function(a){var b=a.svg.insert("g").attr("class",a.cssPrefix+"tooltips");b.selectAll("."+a.cssPrefix+"tooltip").data(a.options.data.content).enter().append("g").attr("class",a.cssPrefix+"tooltip").attr("id",function(b,c){return a.cssPrefix+"tooltip"+c}).style("opacity",0).append("rect").attr({rx:a.options.tooltips.styles.borderRadius,ry:a.options.tooltips.styles.borderRadius,x:-a.options.tooltips.styles.padding,opacity:a.options.tooltips.styles.backgroundOpacity}).style("fill",a.options.tooltips.styles.backgroundColor),b.selectAll("."+a.cssPrefix+"tooltip").data(a.options.data.content).append("text").attr("fill",function(b){return a.options.tooltips.styles.color}).style("font-size",function(b){return a.options.tooltips.styles.fontSize}).style("font-family",function(b){return a.options.tooltips.styles.font}).text(function(b,c){var d=a.options.tooltips.string;return"caption"===a.options.tooltips.type&&(d=b.caption),l.replacePlaceholders(a,d,c,{label:b.label,value:b.value,percentage:j.getPercentage(a,c,a.options.labels.percentage.decimalPlaces)})}),b.selectAll("."+a.cssPrefix+"tooltip rect").attr({width:function(b,c){var d=f.getDimensions(a.cssPrefix+"tooltip"+c);return d.w+2*a.options.tooltips.styles.padding},height:function(b,c){var d=f.getDimensions(a.cssPrefix+"tooltip"+c);return d.h+2*a.options.tooltips.styles.padding},y:function(b,c){var d=f.getDimensions(a.cssPrefix+"tooltip"+c);return-(d.h/2)+1}})},showTooltip:function(a,b){var c=a.options.tooltips.styles.fadeInSpeed;l.currentTooltip===b&&(c=1),l.currentTooltip=b,d3.select("#"+a.cssPrefix+"tooltip"+b).transition().duration(c).style("opacity",function(){return 1}),l.moveTooltip(a)},moveTooltip:function(a){d3.selectAll("#"+a.cssPrefix+"tooltip"+l.currentTooltip).attr("transform",function(b){var c=d3.mouse(this.parentNode),d=c[0]+a.options.tooltips.styles.padding+2,e=c[1]-2*a.options.tooltips.styles.padding-2;return"translate("+d+","+e+")"})},hideTooltip:function(a,b){d3.select("#"+a.cssPrefix+"tooltip"+b).style("opacity",function(){return 0}),d3.select("#"+a.cssPrefix+"tooltip"+l.currentTooltip).attr("transform",function(b,c){var d=a.options.size.canvasWidth+1e3,e=a.options.size.canvasHeight+1e3;return"translate("+d+","+e+")"})},replacePlaceholders:function(a,b,c,d){f.isFunction(a.options.tooltips.placeholderParser)&&a.options.tooltips.placeholderParser(c,d);var e=function(){return function(a){var b=arguments[1];return d.hasOwnProperty(b)?d[arguments[1]]:arguments[0]}};return b.replace(/\{(\w+)\}/g,e(d))}},m=function(i,j){if(this.element=i,"string"==typeof i){var k=i.replace(/^#/,"");this.element=document.getElementById(k)}var l={};g(!0,l,d,j),this.options=l,null!==this.options.misc.cssPrefix?this.cssPrefix=this.options.misc.cssPrefix:(this.cssPrefix="p"+c+"_",c++),e.initialCheck(this)&&(d3.select(this.element).attr(a,b),this.options.data.content=h.sortPieData(this),this.options.data.smallSegmentGrouping.enabled&&(this.options.data.content=f.applySmallSegmentGrouping(this.options.data.content,this.options.data.smallSegmentGrouping)),this.options.colors=f.initSegmentColors(this),this.totalSize=h.getTotalPieSize(this.options.data.content),n.call(this))};m.prototype.recreate=function(){e.initialCheck(this)&&(this.options.data.content=h.sortPieData(this),this.options.data.smallSegmentGrouping.enabled&&(this.options.data.content=f.applySmallSegmentGrouping(this.options.data.content,this.options.data.smallSegmentGrouping)),this.options.colors=f.initSegmentColors(this),this.totalSize=h.getTotalPieSize(this.options.data.content),n.call(this))},m.prototype.redraw=function(){this.element.innerHTML="",n.call(this)},m.prototype.destroy=function(){this.element.innerHTML="",d3.select(this.element).attr(a,null)},m.prototype.getOpenSegment=function(){var a=this.currentlyOpenSegment;if(null!==a&&"undefined"!=typeof a){var b=parseInt(d3.select(a).attr("data-index"),10);return{element:a,index:b,data:this.options.data.content[b]}}return null},m.prototype.openSegment=function(a){a=parseInt(a,10),0>a||a>this.options.data.content.length-1||j.openSegment(this,d3.select("#"+this.cssPrefix+"segment"+a).node())},m.prototype.closeSegment=function(){var a=this.currentlyOpenSegment;a&&j.closeSegment(this,a)},m.prototype.updateProp=function(a,b){switch(a){case"header.title.text":var c=f.processObj(this.options,a);f.processObj(this.options,a,b),d3.select("#"+this.cssPrefix+"title").html(b),(""===c&&""!==b||""!==c&&""===b)&&this.redraw();break;case"header.subtitle.text":var d=f.processObj(this.options,a);f.processObj(this.options,a,b),d3.select("#"+this.cssPrefix+"subtitle").html(b),(""===d&&""!==b||""!==d&&""===b)&&this.redraw();break;case"callbacks.onload":case"callbacks.onMouseoverSegment":case"callbacks.onMouseoutSegment":case"callbacks.onClickSegment":case"effects.pullOutSegmentOnClick.effect":case"effects.pullOutSegmentOnClick.speed":case"effects.pullOutSegmentOnClick.size":case"effects.highlightSegmentOnMouseover":case"effects.highlightLuminosity":f.processObj(this.options,a,b);break;default:f.processObj(this.options,a,b),this.destroy(),this.recreate()}};var n=function(){this.svg=f.addSVGSpace(this),this.textComponents={headerHeight:0,title:{exists:""!==this.options.header.title.text,h:0,w:0},subtitle:{exists:""!==this.options.header.subtitle.text,h:0,w:0},footer:{exists:""!==this.options.footer.text,h:0,w:0}},this.outerLabelGroupData=[], +this.textComponents.title.exists&&k.addTitle(this),this.textComponents.subtitle.exists&&k.addSubtitle(this),k.addFooter(this);var a=this;f.whenIdExists(this.cssPrefix+"footer",function(){k.positionFooter(a);var b=f.getDimensions(a.cssPrefix+"footer");a.textComponents.footer.h=b.h,a.textComponents.footer.w=b.w});var b=[];this.textComponents.title.exists&&b.push(this.cssPrefix+"title"),this.textComponents.subtitle.exists&&b.push(this.cssPrefix+"subtitle"),this.textComponents.footer.exists&&b.push(this.cssPrefix+"footer"),f.whenElementsExist(b,function(){if(a.textComponents.title.exists){var b=f.getDimensions(a.cssPrefix+"title");a.textComponents.title.h=b.h,a.textComponents.title.w=b.w}if(a.textComponents.subtitle.exists){var c=f.getDimensions(a.cssPrefix+"subtitle");a.textComponents.subtitle.h=c.h,a.textComponents.subtitle.w=c.w}if(a.textComponents.title.exists||a.textComponents.subtitle.exists){var d=0;a.textComponents.title.exists&&(d+=a.textComponents.title.h,a.textComponents.subtitle.exists&&(d+=a.options.header.titleSubtitlePadding)),a.textComponents.subtitle.exists&&(d+=a.textComponents.subtitle.h),a.textComponents.headerHeight=d}h.computePieRadius(a),h.calculatePieCenter(a),k.positionTitle(a),k.positionSubtitle(a),a.options.misc.gradient.enabled&&j.addGradients(a),j.create(a),i.add(a,"inner",a.options.labels.inner.format),i.add(a,"outer",a.options.labels.outer.format),i.positionLabelElements(a,"inner",a.options.labels.inner.format),i.positionLabelElements(a,"outer",a.options.labels.outer.format),i.computeOuterLabelCoords(a),i.positionLabelGroups(a,"outer"),i.computeLabelLinePositions(a),a.options.labels.lines.enabled&&"none"!==a.options.labels.outer.format&&i.addLabelLines(a),i.positionLabelGroups(a,"inner"),i.fadeInLabelsAndLines(a),a.options.tooltips.enabled&&l.addTooltips(a),j.addSegmentEventHandlers(a)})};return m});
\ No newline at end of file diff --git a/interface/js/datatables.min.js b/interface/js/datatables.min.js new file mode 100644 index 000000000..3c51a42cc --- /dev/null +++ b/interface/js/datatables.min.js @@ -0,0 +1,253 @@ +/* + * This combined file was created by the DataTables downloader builder: + * https://datatables.net/download + * + * To rebuild or modify this file with the latest versions of the included + * software please visit: + * https://datatables.net/download/#bs-3.3.5/jqc-1.11.3,dt-1.10.9,fh-3.0.0,r-1.0.7,sc-1.3.0 + * + * Included libraries: + * jQuery compat 1.11.3, Bootstrap 3.3.5, DataTables 1.10.9, FixedHeader 3.0.0, Responsive 1.0.7, Scroller 1.3.0 + */ + +/*! + DataTables 1.10.9 + ©2008-2015 SpryMedia Ltd - datatables.net/license +*/ +(function(Fa,T,k){var S=function(h){function X(a){var b,c,d={};h.each(a,function(e){if((b=e.match(/^([^A-Z]+?)([A-Z])/))&&-1!=="a aa ai ao as b fn i m o s ".indexOf(b[1]+" "))c=e.replace(b[0],b[2].toLowerCase()),d[c]=e,"o"===b[1]&&X(a[e])});a._hungarianMap=d}function I(a,b,c){a._hungarianMap||X(a);var d;h.each(b,function(e){d=a._hungarianMap[e];if(d!==k&&(c||b[d]===k))"o"===d.charAt(0)?(b[d]||(b[d]={}),h.extend(!0,b[d],b[e]),I(a[d],b[d],c)):b[d]=b[e]})}function S(a){var b=m.defaults.oLanguage,c=a.sZeroRecords; +!a.sEmptyTable&&(c&&"No data available in table"===b.sEmptyTable)&&F(a,a,"sZeroRecords","sEmptyTable");!a.sLoadingRecords&&(c&&"Loading..."===b.sLoadingRecords)&&F(a,a,"sZeroRecords","sLoadingRecords");a.sInfoThousands&&(a.sThousands=a.sInfoThousands);(a=a.sDecimal)&&cb(a)}function db(a){A(a,"ordering","bSort");A(a,"orderMulti","bSortMulti");A(a,"orderClasses","bSortClasses");A(a,"orderCellsTop","bSortCellsTop");A(a,"order","aaSorting");A(a,"orderFixed","aaSortingFixed");A(a,"paging","bPaginate"); +A(a,"pagingType","sPaginationType");A(a,"pageLength","iDisplayLength");A(a,"searching","bFilter");"boolean"===typeof a.sScrollX&&(a.sScrollX=a.sScrollX?"100%":"");if(a=a.aoSearchCols)for(var b=0,c=a.length;b<c;b++)a[b]&&I(m.models.oSearch,a[b])}function eb(a){A(a,"orderable","bSortable");A(a,"orderData","aDataSort");A(a,"orderSequence","asSorting");A(a,"orderDataType","sortDataType");var b=a.aDataSort;b&&!h.isArray(b)&&(a.aDataSort=[b])}function fb(a){if(!m.__browser){var b={};m.__browser=b;var c= +h("<div/>").css({position:"fixed",top:0,left:0,height:1,width:1,overflow:"hidden"}).append(h("<div/>").css({position:"absolute",top:1,left:1,width:100,overflow:"scroll"}).append(h("<div/>").css({width:"100%",height:10}))).appendTo("body"),d=c.children(),e=d.children();b.barWidth=d[0].offsetWidth-d[0].clientWidth;b.bScrollOversize=100===e[0].offsetWidth&&100!==d[0].clientWidth;b.bScrollbarLeft=1!==Math.round(e.offset().left);b.bBounding=c[0].getBoundingClientRect().width?!0:!1;c.remove()}h.extend(a.oBrowser, +m.__browser);a.oScroll.iBarWidth=m.__browser.barWidth}function gb(a,b,c,d,e,f){var g,i=!1;c!==k&&(g=c,i=!0);for(;d!==e;)a.hasOwnProperty(d)&&(g=i?b(g,a[d],d,a):a[d],i=!0,d+=f);return g}function Ga(a,b){var c=m.defaults.column,d=a.aoColumns.length,c=h.extend({},m.models.oColumn,c,{nTh:b?b:T.createElement("th"),sTitle:c.sTitle?c.sTitle:b?b.innerHTML:"",aDataSort:c.aDataSort?c.aDataSort:[d],mData:c.mData?c.mData:d,idx:d});a.aoColumns.push(c);c=a.aoPreSearchCols;c[d]=h.extend({},m.models.oSearch,c[d]); +la(a,d,h(b).data())}function la(a,b,c){var b=a.aoColumns[b],d=a.oClasses,e=h(b.nTh);if(!b.sWidthOrig){b.sWidthOrig=e.attr("width")||null;var f=(e.attr("style")||"").match(/width:\s*(\d+[pxem%]+)/);f&&(b.sWidthOrig=f[1])}c!==k&&null!==c&&(eb(c),I(m.defaults.column,c),c.mDataProp!==k&&!c.mData&&(c.mData=c.mDataProp),c.sType&&(b._sManualType=c.sType),c.className&&!c.sClass&&(c.sClass=c.className),h.extend(b,c),F(b,c,"sWidth","sWidthOrig"),c.iDataSort!==k&&(b.aDataSort=[c.iDataSort]),F(b,c,"aDataSort")); +var g=b.mData,i=P(g),j=b.mRender?P(b.mRender):null,c=function(a){return"string"===typeof a&&-1!==a.indexOf("@")};b._bAttrSrc=h.isPlainObject(g)&&(c(g.sort)||c(g.type)||c(g.filter));b.fnGetData=function(a,b,c){var d=i(a,b,k,c);return j&&b?j(d,b,a,c):d};b.fnSetData=function(a,b,c){return Q(g)(a,b,c)};"number"!==typeof g&&(a._rowReadObject=!0);a.oFeatures.bSort||(b.bSortable=!1,e.addClass(d.sSortableNone));a=-1!==h.inArray("asc",b.asSorting);c=-1!==h.inArray("desc",b.asSorting);!b.bSortable||!a&&!c? +(b.sSortingClass=d.sSortableNone,b.sSortingClassJUI=""):a&&!c?(b.sSortingClass=d.sSortableAsc,b.sSortingClassJUI=d.sSortJUIAscAllowed):!a&&c?(b.sSortingClass=d.sSortableDesc,b.sSortingClassJUI=d.sSortJUIDescAllowed):(b.sSortingClass=d.sSortable,b.sSortingClassJUI=d.sSortJUI)}function Y(a){if(!1!==a.oFeatures.bAutoWidth){var b=a.aoColumns;Ha(a);for(var c=0,d=b.length;c<d;c++)b[c].nTh.style.width=b[c].sWidth}b=a.oScroll;(""!==b.sY||""!==b.sX)&&Z(a);w(a,null,"column-sizing",[a])}function $(a,b){var c= +aa(a,"bVisible");return"number"===typeof c[b]?c[b]:null}function ba(a,b){var c=aa(a,"bVisible"),c=h.inArray(b,c);return-1!==c?c:null}function ca(a){return aa(a,"bVisible").length}function aa(a,b){var c=[];h.map(a.aoColumns,function(a,e){a[b]&&c.push(e)});return c}function Ia(a){var b=a.aoColumns,c=a.aoData,d=m.ext.type.detect,e,f,g,i,j,h,l,r,q;e=0;for(f=b.length;e<f;e++)if(l=b[e],q=[],!l.sType&&l._sManualType)l.sType=l._sManualType;else if(!l.sType){g=0;for(i=d.length;g<i;g++){j=0;for(h=c.length;j< +h;j++){q[j]===k&&(q[j]=B(a,j,e,"type"));r=d[g](q[j],a);if(!r&&g!==d.length-1)break;if("html"===r)break}if(r){l.sType=r;break}}l.sType||(l.sType="string")}}function hb(a,b,c,d){var e,f,g,i,j,n,l=a.aoColumns;if(b)for(e=b.length-1;0<=e;e--){n=b[e];var r=n.targets!==k?n.targets:n.aTargets;h.isArray(r)||(r=[r]);f=0;for(g=r.length;f<g;f++)if("number"===typeof r[f]&&0<=r[f]){for(;l.length<=r[f];)Ga(a);d(r[f],n)}else if("number"===typeof r[f]&&0>r[f])d(l.length+r[f],n);else if("string"===typeof r[f]){i=0; +for(j=l.length;i<j;i++)("_all"==r[f]||h(l[i].nTh).hasClass(r[f]))&&d(i,n)}}if(c){e=0;for(a=c.length;e<a;e++)d(e,c[e])}}function L(a,b,c,d){var e=a.aoData.length,f=h.extend(!0,{},m.models.oRow,{src:c?"dom":"data",idx:e});f._aData=b;a.aoData.push(f);for(var g=a.aoColumns,i=0,j=g.length;i<j;i++)g[i].sType=null;a.aiDisplayMaster.push(e);b=a.rowIdFn(b);b!==k&&(a.aIds[b]=f);(c||!a.oFeatures.bDeferRender)&&Ja(a,e,c,d);return e}function ma(a,b){var c;b instanceof h||(b=h(b));return b.map(function(b,e){c= +Ka(a,e);return L(a,c.data,e,c.cells)})}function B(a,b,c,d){var e=a.iDraw,f=a.aoColumns[c],g=a.aoData[b]._aData,i=f.sDefaultContent,c=f.fnGetData(g,d,{settings:a,row:b,col:c});if(c===k)return a.iDrawError!=e&&null===i&&(J(a,0,"Requested unknown parameter "+("function"==typeof f.mData?"{function}":"'"+f.mData+"'")+" for row "+b,4),a.iDrawError=e),i;if((c===g||null===c)&&null!==i)c=i;else if("function"===typeof c)return c.call(g);return null===c&&"display"==d?"":c}function ib(a,b,c,d){a.aoColumns[c].fnSetData(a.aoData[b]._aData, +d,{settings:a,row:b,col:c})}function La(a){return h.map(a.match(/(\\.|[^\.])+/g)||[""],function(a){return a.replace(/\\./g,".")})}function P(a){if(h.isPlainObject(a)){var b={};h.each(a,function(a,c){c&&(b[a]=P(c))});return function(a,c,f,g){var i=b[c]||b._;return i!==k?i(a,c,f,g):a}}if(null===a)return function(a){return a};if("function"===typeof a)return function(b,c,f,g){return a(b,c,f,g)};if("string"===typeof a&&(-1!==a.indexOf(".")||-1!==a.indexOf("[")||-1!==a.indexOf("("))){var c=function(a,b, +f){var g,i;if(""!==f){i=La(f);for(var j=0,n=i.length;j<n;j++){f=i[j].match(da);g=i[j].match(U);if(f){i[j]=i[j].replace(da,"");""!==i[j]&&(a=a[i[j]]);g=[];i.splice(0,j+1);i=i.join(".");if(h.isArray(a)){j=0;for(n=a.length;j<n;j++)g.push(c(a[j],b,i))}a=f[0].substring(1,f[0].length-1);a=""===a?g:g.join(a);break}else if(g){i[j]=i[j].replace(U,"");a=a[i[j]]();continue}if(null===a||a[i[j]]===k)return k;a=a[i[j]]}}return a};return function(b,e){return c(b,e,a)}}return function(b){return b[a]}}function Q(a){if(h.isPlainObject(a))return Q(a._); +if(null===a)return function(){};if("function"===typeof a)return function(b,d,e){a(b,"set",d,e)};if("string"===typeof a&&(-1!==a.indexOf(".")||-1!==a.indexOf("[")||-1!==a.indexOf("("))){var b=function(a,d,e){var e=La(e),f;f=e[e.length-1];for(var g,i,j=0,n=e.length-1;j<n;j++){g=e[j].match(da);i=e[j].match(U);if(g){e[j]=e[j].replace(da,"");a[e[j]]=[];f=e.slice();f.splice(0,j+1);g=f.join(".");if(h.isArray(d)){i=0;for(n=d.length;i<n;i++)f={},b(f,d[i],g),a[e[j]].push(f)}else a[e[j]]=d;return}i&&(e[j]=e[j].replace(U, +""),a=a[e[j]](d));if(null===a[e[j]]||a[e[j]]===k)a[e[j]]={};a=a[e[j]]}if(f.match(U))a[f.replace(U,"")](d);else a[f.replace(da,"")]=d};return function(c,d){return b(c,d,a)}}return function(b,d){b[a]=d}}function Ma(a){return D(a.aoData,"_aData")}function na(a){a.aoData.length=0;a.aiDisplayMaster.length=0;a.aiDisplay.length=0;a.aIds={}}function oa(a,b,c){for(var d=-1,e=0,f=a.length;e<f;e++)a[e]==b?d=e:a[e]>b&&a[e]--; -1!=d&&c===k&&a.splice(d,1)}function ea(a,b,c,d){var e=a.aoData[b],f,g=function(c,d){for(;c.childNodes.length;)c.removeChild(c.firstChild); +c.innerHTML=B(a,b,d,"display")};if("dom"===c||(!c||"auto"===c)&&"dom"===e.src)e._aData=Ka(a,e,d,d===k?k:e._aData).data;else{var i=e.anCells;if(i)if(d!==k)g(i[d],d);else{c=0;for(f=i.length;c<f;c++)g(i[c],c)}}e._aSortData=null;e._aFilterData=null;g=a.aoColumns;if(d!==k)g[d].sType=null;else{c=0;for(f=g.length;c<f;c++)g[c].sType=null;Na(a,e)}}function Ka(a,b,c,d){var e=[],f=b.firstChild,g,i,j=0,n,l=a.aoColumns,r=a._rowReadObject,d=d!==k?d:r?{}:[],q=function(a,b){if("string"===typeof a){var c=a.indexOf("@"); +-1!==c&&(c=a.substring(c+1),Q(a)(d,b.getAttribute(c)))}},jb=function(a){if(c===k||c===j)i=l[j],n=h.trim(a.innerHTML),i&&i._bAttrSrc?(Q(i.mData._)(d,n),q(i.mData.sort,a),q(i.mData.type,a),q(i.mData.filter,a)):r?(i._setter||(i._setter=Q(i.mData)),i._setter(d,n)):d[j]=n;j++};if(f)for(;f;){g=f.nodeName.toUpperCase();if("TD"==g||"TH"==g)jb(f),e.push(f);f=f.nextSibling}else{e=b.anCells;g=0;for(var o=e.length;g<o;g++)jb(e[g])}if(b=f?b:b.nTr)(b=b.getAttribute("id"))&&Q(a.rowId)(d,b);return{data:d,cells:e}} +function Ja(a,b,c,d){var e=a.aoData[b],f=e._aData,g=[],i,j,h,l,r;if(null===e.nTr){i=c||T.createElement("tr");e.nTr=i;e.anCells=g;i._DT_RowIndex=b;Na(a,e);l=0;for(r=a.aoColumns.length;l<r;l++){h=a.aoColumns[l];j=c?d[l]:T.createElement(h.sCellType);g.push(j);if(!c||h.mRender||h.mData!==l)j.innerHTML=B(a,b,l,"display");h.sClass&&(j.className+=" "+h.sClass);h.bVisible&&!c?i.appendChild(j):!h.bVisible&&c&&j.parentNode.removeChild(j);h.fnCreatedCell&&h.fnCreatedCell.call(a.oInstance,j,B(a,b,l),f,b,l)}w(a, +"aoRowCreatedCallback",null,[i,f,b])}e.nTr.setAttribute("role","row")}function Na(a,b){var c=b.nTr,d=b._aData;if(c){var e=a.rowIdFn(d);e&&(c.id=e);d.DT_RowClass&&(e=d.DT_RowClass.split(" "),b.__rowc=b.__rowc?pa(b.__rowc.concat(e)):e,h(c).removeClass(b.__rowc.join(" ")).addClass(d.DT_RowClass));d.DT_RowAttr&&h(c).attr(d.DT_RowAttr);d.DT_RowData&&h(c).data(d.DT_RowData)}}function kb(a){var b,c,d,e,f,g=a.nTHead,i=a.nTFoot,j=0===h("th, td",g).length,n=a.oClasses,l=a.aoColumns;j&&(e=h("<tr/>").appendTo(g)); +b=0;for(c=l.length;b<c;b++)f=l[b],d=h(f.nTh).addClass(f.sClass),j&&d.appendTo(e),a.oFeatures.bSort&&(d.addClass(f.sSortingClass),!1!==f.bSortable&&(d.attr("tabindex",a.iTabIndex).attr("aria-controls",a.sTableId),Oa(a,f.nTh,b))),f.sTitle!=d[0].innerHTML&&d.html(f.sTitle),Pa(a,"header")(a,d,f,n);j&&fa(a.aoHeader,g);h(g).find(">tr").attr("role","row");h(g).find(">tr>th, >tr>td").addClass(n.sHeaderTH);h(i).find(">tr>th, >tr>td").addClass(n.sFooterTH);if(null!==i){a=a.aoFooter[0];b=0;for(c=a.length;b< +c;b++)f=l[b],f.nTf=a[b].cell,f.sClass&&h(f.nTf).addClass(f.sClass)}}function ga(a,b,c){var d,e,f,g=[],i=[],j=a.aoColumns.length,n;if(b){c===k&&(c=!1);d=0;for(e=b.length;d<e;d++){g[d]=b[d].slice();g[d].nTr=b[d].nTr;for(f=j-1;0<=f;f--)!a.aoColumns[f].bVisible&&!c&&g[d].splice(f,1);i.push([])}d=0;for(e=g.length;d<e;d++){if(a=g[d].nTr)for(;f=a.firstChild;)a.removeChild(f);f=0;for(b=g[d].length;f<b;f++)if(n=j=1,i[d][f]===k){a.appendChild(g[d][f].cell);for(i[d][f]=1;g[d+j]!==k&&g[d][f].cell==g[d+j][f].cell;)i[d+ +j][f]=1,j++;for(;g[d][f+n]!==k&&g[d][f].cell==g[d][f+n].cell;){for(c=0;c<j;c++)i[d+c][f+n]=1;n++}h(g[d][f].cell).attr("rowspan",j).attr("colspan",n)}}}}function M(a){var b=w(a,"aoPreDrawCallback","preDraw",[a]);if(-1!==h.inArray(!1,b))C(a,!1);else{var b=[],c=0,d=a.asStripeClasses,e=d.length,f=a.oLanguage,g=a.iInitDisplayStart,i="ssp"==y(a),j=a.aiDisplay;a.bDrawing=!0;g!==k&&-1!==g&&(a._iDisplayStart=i?g:g>=a.fnRecordsDisplay()?0:g,a.iInitDisplayStart=-1);var g=a._iDisplayStart,n=a.fnDisplayEnd(); +if(a.bDeferLoading)a.bDeferLoading=!1,a.iDraw++,C(a,!1);else if(i){if(!a.bDestroying&&!lb(a))return}else a.iDraw++;if(0!==j.length){f=i?a.aoData.length:n;for(i=i?0:g;i<f;i++){var l=j[i],r=a.aoData[l];null===r.nTr&&Ja(a,l);l=r.nTr;if(0!==e){var q=d[c%e];r._sRowStripe!=q&&(h(l).removeClass(r._sRowStripe).addClass(q),r._sRowStripe=q)}w(a,"aoRowCallback",null,[l,r._aData,c,i]);b.push(l);c++}}else c=f.sZeroRecords,1==a.iDraw&&"ajax"==y(a)?c=f.sLoadingRecords:f.sEmptyTable&&0===a.fnRecordsTotal()&&(c=f.sEmptyTable), +b[0]=h("<tr/>",{"class":e?d[0]:""}).append(h("<td />",{valign:"top",colSpan:ca(a),"class":a.oClasses.sRowEmpty}).html(c))[0];w(a,"aoHeaderCallback","header",[h(a.nTHead).children("tr")[0],Ma(a),g,n,j]);w(a,"aoFooterCallback","footer",[h(a.nTFoot).children("tr")[0],Ma(a),g,n,j]);d=h(a.nTBody);d.children().detach();d.append(h(b));w(a,"aoDrawCallback","draw",[a]);a.bSorted=!1;a.bFiltered=!1;a.bDrawing=!1}}function R(a,b){var c=a.oFeatures,d=c.bFilter;c.bSort&&mb(a);d?ha(a,a.oPreviousSearch):a.aiDisplay= +a.aiDisplayMaster.slice();!0!==b&&(a._iDisplayStart=0);a._drawHold=b;M(a);a._drawHold=!1}function nb(a){var b=a.oClasses,c=h(a.nTable),c=h("<div/>").insertBefore(c),d=a.oFeatures,e=h("<div/>",{id:a.sTableId+"_wrapper","class":b.sWrapper+(a.nTFoot?"":" "+b.sNoFooter)});a.nHolding=c[0];a.nTableWrapper=e[0];a.nTableReinsertBefore=a.nTable.nextSibling;for(var f=a.sDom.split(""),g,i,j,n,l,r,q=0;q<f.length;q++){g=null;i=f[q];if("<"==i){j=h("<div/>")[0];n=f[q+1];if("'"==n||'"'==n){l="";for(r=2;f[q+r]!=n;)l+= +f[q+r],r++;"H"==l?l=b.sJUIHeader:"F"==l&&(l=b.sJUIFooter);-1!=l.indexOf(".")?(n=l.split("."),j.id=n[0].substr(1,n[0].length-1),j.className=n[1]):"#"==l.charAt(0)?j.id=l.substr(1,l.length-1):j.className=l;q+=r}e.append(j);e=h(j)}else if(">"==i)e=e.parent();else if("l"==i&&d.bPaginate&&d.bLengthChange)g=ob(a);else if("f"==i&&d.bFilter)g=pb(a);else if("r"==i&&d.bProcessing)g=qb(a);else if("t"==i)g=rb(a);else if("i"==i&&d.bInfo)g=sb(a);else if("p"==i&&d.bPaginate)g=tb(a);else if(0!==m.ext.feature.length){j= +m.ext.feature;r=0;for(n=j.length;r<n;r++)if(i==j[r].cFeature){g=j[r].fnInit(a);break}}g&&(j=a.aanFeatures,j[i]||(j[i]=[]),j[i].push(g),e.append(g))}c.replaceWith(e);a.nHolding=null}function fa(a,b){var c=h(b).children("tr"),d,e,f,g,i,j,n,l,r,q;a.splice(0,a.length);f=0;for(j=c.length;f<j;f++)a.push([]);f=0;for(j=c.length;f<j;f++){d=c[f];for(e=d.firstChild;e;){if("TD"==e.nodeName.toUpperCase()||"TH"==e.nodeName.toUpperCase()){l=1*e.getAttribute("colspan");r=1*e.getAttribute("rowspan");l=!l||0===l|| +1===l?1:l;r=!r||0===r||1===r?1:r;g=0;for(i=a[f];i[g];)g++;n=g;q=1===l?!0:!1;for(i=0;i<l;i++)for(g=0;g<r;g++)a[f+g][n+i]={cell:e,unique:q},a[f+g].nTr=d}e=e.nextSibling}}}function qa(a,b,c){var d=[];c||(c=a.aoHeader,b&&(c=[],fa(c,b)));for(var b=0,e=c.length;b<e;b++)for(var f=0,g=c[b].length;f<g;f++)if(c[b][f].unique&&(!d[f]||!a.bSortCellsTop))d[f]=c[b][f].cell;return d}function ra(a,b,c){w(a,"aoServerParams","serverParams",[b]);if(b&&h.isArray(b)){var d={},e=/(.*?)\[\]$/;h.each(b,function(a,b){var c= +b.name.match(e);c?(c=c[0],d[c]||(d[c]=[]),d[c].push(b.value)):d[b.name]=b.value});b=d}var f,g=a.ajax,i=a.oInstance,j=function(b){w(a,null,"xhr",[a,b,a.jqXHR]);c(b)};if(h.isPlainObject(g)&&g.data){f=g.data;var n=h.isFunction(f)?f(b,a):f,b=h.isFunction(f)&&n?n:h.extend(!0,b,n);delete g.data}n={data:b,success:function(b){var c=b.error||b.sError;c&&J(a,0,c);a.json=b;j(b)},dataType:"json",cache:!1,type:a.sServerMethod,error:function(b,c){var d=w(a,null,"xhr",[a,null,a.jqXHR]);-1===h.inArray(!0,d)&&("parsererror"== +c?J(a,0,"Invalid JSON response",1):4===b.readyState&&J(a,0,"Ajax error",7));C(a,!1)}};a.oAjaxData=b;w(a,null,"preXhr",[a,b]);a.fnServerData?a.fnServerData.call(i,a.sAjaxSource,h.map(b,function(a,b){return{name:b,value:a}}),j,a):a.sAjaxSource||"string"===typeof g?a.jqXHR=h.ajax(h.extend(n,{url:g||a.sAjaxSource})):h.isFunction(g)?a.jqXHR=g.call(i,b,j,a):(a.jqXHR=h.ajax(h.extend(n,g)),g.data=f)}function lb(a){return a.bAjaxDataGet?(a.iDraw++,C(a,!0),ra(a,ub(a),function(b){vb(a,b)}),!1):!0}function ub(a){var b= +a.aoColumns,c=b.length,d=a.oFeatures,e=a.oPreviousSearch,f=a.aoPreSearchCols,g,i=[],j,n,l,r=V(a);g=a._iDisplayStart;j=!1!==d.bPaginate?a._iDisplayLength:-1;var q=function(a,b){i.push({name:a,value:b})};q("sEcho",a.iDraw);q("iColumns",c);q("sColumns",D(b,"sName").join(","));q("iDisplayStart",g);q("iDisplayLength",j);var k={draw:a.iDraw,columns:[],order:[],start:g,length:j,search:{value:e.sSearch,regex:e.bRegex}};for(g=0;g<c;g++)n=b[g],l=f[g],j="function"==typeof n.mData?"function":n.mData,k.columns.push({data:j, +name:n.sName,searchable:n.bSearchable,orderable:n.bSortable,search:{value:l.sSearch,regex:l.bRegex}}),q("mDataProp_"+g,j),d.bFilter&&(q("sSearch_"+g,l.sSearch),q("bRegex_"+g,l.bRegex),q("bSearchable_"+g,n.bSearchable)),d.bSort&&q("bSortable_"+g,n.bSortable);d.bFilter&&(q("sSearch",e.sSearch),q("bRegex",e.bRegex));d.bSort&&(h.each(r,function(a,b){k.order.push({column:b.col,dir:b.dir});q("iSortCol_"+a,b.col);q("sSortDir_"+a,b.dir)}),q("iSortingCols",r.length));b=m.ext.legacy.ajax;return null===b?a.sAjaxSource? +i:k:b?i:k}function vb(a,b){var c=sa(a,b),d=b.sEcho!==k?b.sEcho:b.draw,e=b.iTotalRecords!==k?b.iTotalRecords:b.recordsTotal,f=b.iTotalDisplayRecords!==k?b.iTotalDisplayRecords:b.recordsFiltered;if(d){if(1*d<a.iDraw)return;a.iDraw=1*d}na(a);a._iRecordsTotal=parseInt(e,10);a._iRecordsDisplay=parseInt(f,10);d=0;for(e=c.length;d<e;d++)L(a,c[d]);a.aiDisplay=a.aiDisplayMaster.slice();a.bAjaxDataGet=!1;M(a);a._bInitComplete||ta(a,b);a.bAjaxDataGet=!0;C(a,!1)}function sa(a,b){var c=h.isPlainObject(a.ajax)&& +a.ajax.dataSrc!==k?a.ajax.dataSrc:a.sAjaxDataProp;return"data"===c?b.aaData||b[c]:""!==c?P(c)(b):b}function pb(a){var b=a.oClasses,c=a.sTableId,d=a.oLanguage,e=a.oPreviousSearch,f=a.aanFeatures,g='<input type="search" class="'+b.sFilterInput+'"/>',i=d.sSearch,i=i.match(/_INPUT_/)?i.replace("_INPUT_",g):i+g,b=h("<div/>",{id:!f.f?c+"_filter":null,"class":b.sFilter}).append(h("<label/>").append(i)),f=function(){var b=!this.value?"":this.value;b!=e.sSearch&&(ha(a,{sSearch:b,bRegex:e.bRegex,bSmart:e.bSmart, +bCaseInsensitive:e.bCaseInsensitive}),a._iDisplayStart=0,M(a))},g=null!==a.searchDelay?a.searchDelay:"ssp"===y(a)?400:0,j=h("input",b).val(e.sSearch).attr("placeholder",d.sSearchPlaceholder).bind("keyup.DT search.DT input.DT paste.DT cut.DT",g?ua(f,g):f).bind("keypress.DT",function(a){if(13==a.keyCode)return!1}).attr("aria-controls",c);h(a.nTable).on("search.dt.DT",function(b,c){if(a===c)try{j[0]!==T.activeElement&&j.val(e.sSearch)}catch(d){}});return b[0]}function ha(a,b,c){var d=a.oPreviousSearch, +e=a.aoPreSearchCols,f=function(a){d.sSearch=a.sSearch;d.bRegex=a.bRegex;d.bSmart=a.bSmart;d.bCaseInsensitive=a.bCaseInsensitive};Ia(a);if("ssp"!=y(a)){wb(a,b.sSearch,c,b.bEscapeRegex!==k?!b.bEscapeRegex:b.bRegex,b.bSmart,b.bCaseInsensitive);f(b);for(b=0;b<e.length;b++)xb(a,e[b].sSearch,b,e[b].bEscapeRegex!==k?!e[b].bEscapeRegex:e[b].bRegex,e[b].bSmart,e[b].bCaseInsensitive);yb(a)}else f(b);a.bFiltered=!0;w(a,null,"search",[a])}function yb(a){for(var b=m.ext.search,c=a.aiDisplay,d,e,f=0,g=b.length;f< +g;f++){for(var i=[],j=0,n=c.length;j<n;j++)e=c[j],d=a.aoData[e],b[f](a,d._aFilterData,e,d._aData,j)&&i.push(e);c.length=0;h.merge(c,i)}}function xb(a,b,c,d,e,f){if(""!==b)for(var g=a.aiDisplay,d=Qa(b,d,e,f),e=g.length-1;0<=e;e--)b=a.aoData[g[e]]._aFilterData[c],d.test(b)||g.splice(e,1)}function wb(a,b,c,d,e,f){var d=Qa(b,d,e,f),e=a.oPreviousSearch.sSearch,f=a.aiDisplayMaster,g;0!==m.ext.search.length&&(c=!0);g=zb(a);if(0>=b.length)a.aiDisplay=f.slice();else{if(g||c||e.length>b.length||0!==b.indexOf(e)|| +a.bSorted)a.aiDisplay=f.slice();b=a.aiDisplay;for(c=b.length-1;0<=c;c--)d.test(a.aoData[b[c]]._sFilterRow)||b.splice(c,1)}}function Qa(a,b,c,d){a=b?a:va(a);c&&(a="^(?=.*?"+h.map(a.match(/"[^"]+"|[^ ]+/g)||[""],function(a){if('"'===a.charAt(0))var b=a.match(/^"(.*)"$/),a=b?b[1]:a;return a.replace('"',"")}).join(")(?=.*?")+").*$");return RegExp(a,d?"i":"")}function va(a){return a.replace(Yb,"\\$1")}function zb(a){var b=a.aoColumns,c,d,e,f,g,i,j,h,l=m.ext.type.search;c=!1;d=0;for(f=a.aoData.length;d< +f;d++)if(h=a.aoData[d],!h._aFilterData){i=[];e=0;for(g=b.length;e<g;e++)c=b[e],c.bSearchable?(j=B(a,d,e,"filter"),l[c.sType]&&(j=l[c.sType](j)),null===j&&(j=""),"string"!==typeof j&&j.toString&&(j=j.toString())):j="",j.indexOf&&-1!==j.indexOf("&")&&(wa.innerHTML=j,j=Zb?wa.textContent:wa.innerText),j.replace&&(j=j.replace(/[\r\n]/g,"")),i.push(j);h._aFilterData=i;h._sFilterRow=i.join(" ");c=!0}return c}function Ab(a){return{search:a.sSearch,smart:a.bSmart,regex:a.bRegex,caseInsensitive:a.bCaseInsensitive}} +function Bb(a){return{sSearch:a.search,bSmart:a.smart,bRegex:a.regex,bCaseInsensitive:a.caseInsensitive}}function sb(a){var b=a.sTableId,c=a.aanFeatures.i,d=h("<div/>",{"class":a.oClasses.sInfo,id:!c?b+"_info":null});c||(a.aoDrawCallback.push({fn:Cb,sName:"information"}),d.attr("role","status").attr("aria-live","polite"),h(a.nTable).attr("aria-describedby",b+"_info"));return d[0]}function Cb(a){var b=a.aanFeatures.i;if(0!==b.length){var c=a.oLanguage,d=a._iDisplayStart+1,e=a.fnDisplayEnd(),f=a.fnRecordsTotal(), +g=a.fnRecordsDisplay(),i=g?c.sInfo:c.sInfoEmpty;g!==f&&(i+=" "+c.sInfoFiltered);i+=c.sInfoPostFix;i=Db(a,i);c=c.fnInfoCallback;null!==c&&(i=c.call(a.oInstance,a,d,e,f,g,i));h(b).html(i)}}function Db(a,b){var c=a.fnFormatNumber,d=a._iDisplayStart+1,e=a._iDisplayLength,f=a.fnRecordsDisplay(),g=-1===e;return b.replace(/_START_/g,c.call(a,d)).replace(/_END_/g,c.call(a,a.fnDisplayEnd())).replace(/_MAX_/g,c.call(a,a.fnRecordsTotal())).replace(/_TOTAL_/g,c.call(a,f)).replace(/_PAGE_/g,c.call(a,g?1:Math.ceil(d/ +e))).replace(/_PAGES_/g,c.call(a,g?1:Math.ceil(f/e)))}function ia(a){var b,c,d=a.iInitDisplayStart,e=a.aoColumns,f;c=a.oFeatures;var g=a.bDeferLoading;if(a.bInitialised){nb(a);kb(a);ga(a,a.aoHeader);ga(a,a.aoFooter);C(a,!0);c.bAutoWidth&&Ha(a);b=0;for(c=e.length;b<c;b++)f=e[b],f.sWidth&&(f.nTh.style.width=u(f.sWidth));w(a,null,"preInit",[a]);R(a);e=y(a);if("ssp"!=e||g)"ajax"==e?ra(a,[],function(c){var f=sa(a,c);for(b=0;b<f.length;b++)L(a,f[b]);a.iInitDisplayStart=d;R(a);C(a,!1);ta(a,c)},a):(C(a,!1), +ta(a))}else setTimeout(function(){ia(a)},200)}function ta(a,b){a._bInitComplete=!0;(b||a.oInit.aaData)&&Y(a);w(a,"aoInitComplete","init",[a,b])}function Ra(a,b){var c=parseInt(b,10);a._iDisplayLength=c;Sa(a);w(a,null,"length",[a,c])}function ob(a){for(var b=a.oClasses,c=a.sTableId,d=a.aLengthMenu,e=h.isArray(d[0]),f=e?d[0]:d,d=e?d[1]:d,e=h("<select/>",{name:c+"_length","aria-controls":c,"class":b.sLengthSelect}),g=0,i=f.length;g<i;g++)e[0][g]=new Option(d[g],f[g]);var j=h("<div><label/></div>").addClass(b.sLength); +a.aanFeatures.l||(j[0].id=c+"_length");j.children().append(a.oLanguage.sLengthMenu.replace("_MENU_",e[0].outerHTML));h("select",j).val(a._iDisplayLength).bind("change.DT",function(){Ra(a,h(this).val());M(a)});h(a.nTable).bind("length.dt.DT",function(b,c,d){a===c&&h("select",j).val(d)});return j[0]}function tb(a){var b=a.sPaginationType,c=m.ext.pager[b],d="function"===typeof c,e=function(a){M(a)},b=h("<div/>").addClass(a.oClasses.sPaging+b)[0],f=a.aanFeatures;d||c.fnInit(a,b,e);f.p||(b.id=a.sTableId+ +"_paginate",a.aoDrawCallback.push({fn:function(a){if(d){var b=a._iDisplayStart,j=a._iDisplayLength,h=a.fnRecordsDisplay(),l=-1===j,b=l?0:Math.ceil(b/j),j=l?1:Math.ceil(h/j),h=c(b,j),k,l=0;for(k=f.p.length;l<k;l++)Pa(a,"pageButton")(a,f.p[l],l,h,b,j)}else c.fnUpdate(a,e)},sName:"pagination"}));return b}function Ta(a,b,c){var d=a._iDisplayStart,e=a._iDisplayLength,f=a.fnRecordsDisplay();0===f||-1===e?d=0:"number"===typeof b?(d=b*e,d>f&&(d=0)):"first"==b?d=0:"previous"==b?(d=0<=e?d-e:0,0>d&&(d=0)):"next"== +b?d+e<f&&(d+=e):"last"==b?d=Math.floor((f-1)/e)*e:J(a,0,"Unknown paging action: "+b,5);b=a._iDisplayStart!==d;a._iDisplayStart=d;b&&(w(a,null,"page",[a]),c&&M(a));return b}function qb(a){return h("<div/>",{id:!a.aanFeatures.r?a.sTableId+"_processing":null,"class":a.oClasses.sProcessing}).html(a.oLanguage.sProcessing).insertBefore(a.nTable)[0]}function C(a,b){a.oFeatures.bProcessing&&h(a.aanFeatures.r).css("display",b?"block":"none");w(a,null,"processing",[a,b])}function rb(a){var b=h(a.nTable);b.attr("role", +"grid");var c=a.oScroll;if(""===c.sX&&""===c.sY)return a.nTable;var d=c.sX,e=c.sY,f=a.oClasses,g=b.children("caption"),i=g.length?g[0]._captionSide:null,j=h(b[0].cloneNode(!1)),n=h(b[0].cloneNode(!1)),l=b.children("tfoot");c.sX&&"100%"===b.attr("width")&&b.removeAttr("width");l.length||(l=null);j=h("<div/>",{"class":f.sScrollWrapper}).append(h("<div/>",{"class":f.sScrollHead}).css({overflow:"hidden",position:"relative",border:0,width:d?!d?null:u(d):"100%"}).append(h("<div/>",{"class":f.sScrollHeadInner}).css({"box-sizing":"content-box", +width:c.sXInner||"100%"}).append(j.removeAttr("id").css("margin-left",0).append("top"===i?g:null).append(b.children("thead"))))).append(h("<div/>",{"class":f.sScrollBody}).css({position:"relative",overflow:"auto",width:!d?null:u(d)}).append(b));l&&j.append(h("<div/>",{"class":f.sScrollFoot}).css({overflow:"hidden",border:0,width:d?!d?null:u(d):"100%"}).append(h("<div/>",{"class":f.sScrollFootInner}).append(n.removeAttr("id").css("margin-left",0).append("bottom"===i?g:null).append(b.children("tfoot"))))); +var b=j.children(),k=b[0],f=b[1],q=l?b[2]:null;if(d)h(f).on("scroll.DT",function(){var a=this.scrollLeft;k.scrollLeft=a;l&&(q.scrollLeft=a)});h(f).css(e&&c.bCollapse?"max-height":"height",e);a.nScrollHead=k;a.nScrollBody=f;a.nScrollFoot=q;a.aoDrawCallback.push({fn:Z,sName:"scrolling"});return j[0]}function Z(a){var b=a.oScroll,c=b.sX,d=b.sXInner,e=b.sY,b=b.iBarWidth,f=h(a.nScrollHead),g=f[0].style,i=f.children("div"),j=i[0].style,n=i.children("table"),i=a.nScrollBody,l=h(i),k=i.style,q=h(a.nScrollFoot).children("div"), +m=q.children("table"),o=h(a.nTHead),E=h(a.nTable),p=E[0],t=p.style,N=a.nTFoot?h(a.nTFoot):null,Eb=a.oBrowser,w=Eb.bScrollOversize,s,v,O,x,y=[],z=[],A=[],B,C=function(a){a=a.style;a.paddingTop="0";a.paddingBottom="0";a.borderTopWidth="0";a.borderBottomWidth="0";a.height=0};E.children("thead, tfoot").remove();x=o.clone().prependTo(E);o=o.find("tr");v=x.find("tr");x.find("th, td").removeAttr("tabindex");N&&(O=N.clone().prependTo(E),s=N.find("tr"),O=O.find("tr"));c||(k.width="100%",f[0].style.width="100%"); +h.each(qa(a,x),function(b,c){B=$(a,b);c.style.width=a.aoColumns[B].sWidth});N&&H(function(a){a.style.width=""},O);f=E.outerWidth();if(""===c){t.width="100%";if(w&&(E.find("tbody").height()>i.offsetHeight||"scroll"==l.css("overflow-y")))t.width=u(E.outerWidth()-b);f=E.outerWidth()}else""!==d&&(t.width=u(d),f=E.outerWidth());H(C,v);H(function(a){A.push(a.innerHTML);y.push(u(h(a).css("width")))},v);H(function(a,b){a.style.width=y[b]},o);h(v).height(0);N&&(H(C,O),H(function(a){z.push(u(h(a).css("width")))}, +O),H(function(a,b){a.style.width=z[b]},s),h(O).height(0));H(function(a,b){a.innerHTML='<div class="dataTables_sizing" style="height:0;overflow:hidden;">'+A[b]+"</div>";a.style.width=y[b]},v);N&&H(function(a,b){a.innerHTML="";a.style.width=z[b]},O);if(E.outerWidth()<f){s=i.scrollHeight>i.offsetHeight||"scroll"==l.css("overflow-y")?f+b:f;if(w&&(i.scrollHeight>i.offsetHeight||"scroll"==l.css("overflow-y")))t.width=u(s-b);(""===c||""!==d)&&J(a,1,"Possible column misalignment",6)}else s="100%";k.width= +u(s);g.width=u(s);N&&(a.nScrollFoot.style.width=u(s));!e&&w&&(k.height=u(p.offsetHeight+b));c=E.outerWidth();n[0].style.width=u(c);j.width=u(c);d=E.height()>i.clientHeight||"scroll"==l.css("overflow-y");e="padding"+(Eb.bScrollbarLeft?"Left":"Right");j[e]=d?b+"px":"0px";N&&(m[0].style.width=u(c),q[0].style.width=u(c),q[0].style[e]=d?b+"px":"0px");l.scroll();if((a.bSorted||a.bFiltered)&&!a._drawHold)i.scrollTop=0}function H(a,b,c){for(var d=0,e=0,f=b.length,g,i;e<f;){g=b[e].firstChild;for(i=c?c[e].firstChild: +null;g;)1===g.nodeType&&(c?a(g,i,d):a(g,d),d++),g=g.nextSibling,i=c?i.nextSibling:null;e++}}function Ha(a){var b=a.nTable,c=a.aoColumns,d=a.oScroll,e=d.sY,f=d.sX,g=d.sXInner,i=c.length,j=aa(a,"bVisible"),n=h("th",a.nTHead),l=b.getAttribute("width"),k=b.parentNode,q=!1,m,o,p;p=a.oBrowser;d=p.bScrollOversize;(m=b.style.width)&&-1!==m.indexOf("%")&&(l=m);for(m=0;m<j.length;m++)o=c[j[m]],null!==o.sWidth&&(o.sWidth=Fb(o.sWidthOrig,k),q=!0);if(d||!q&&!f&&!e&&i==ca(a)&&i==n.length)for(m=0;m<i;m++){if(j= +$(a,m))c[j].sWidth=u(n.eq(m).width())}else{i=h(b).clone().css("visibility","hidden").removeAttr("id");i.find("tbody tr").remove();var t=h("<tr/>").appendTo(i.find("tbody"));i.find("thead, tfoot").remove();i.append(h(a.nTHead).clone()).append(h(a.nTFoot).clone());i.find("tfoot th, tfoot td").css("width","");n=qa(a,i.find("thead")[0]);for(m=0;m<j.length;m++)o=c[j[m]],n[m].style.width=null!==o.sWidthOrig&&""!==o.sWidthOrig?u(o.sWidthOrig):"";if(a.aoData.length)for(m=0;m<j.length;m++)q=j[m],o=c[q],h(Gb(a, +q)).clone(!1).append(o.sContentPadding).appendTo(t);q=h("<div/>").css(f||e?{position:"absolute",top:0,left:0,height:1,right:0,overflow:"hidden"}:{}).append(i).appendTo(k);f&&g?i.width(g):f?(i.css("width","auto"),i.width()<k.clientWidth&&i.width(k.clientWidth)):e?i.width(k.clientWidth):l&&i.width(l);if(f){for(m=g=0;m<j.length;m++)o=c[j[m]],e=p.bBounding?n[m].getBoundingClientRect().width:h(n[m]).outerWidth(),g+=null===o.sWidthOrig?e:parseInt(o.sWidth,10)+e-h(n[m]).width();i.width(u(g));b.style.width= +u(g)}for(m=0;m<j.length;m++)if(o=c[j[m]],p=h(n[m]).width())o.sWidth=u(p);b.style.width=u(i.css("width"));q.remove()}l&&(b.style.width=u(l));if((l||f)&&!a._reszEvt)b=function(){h(Fa).bind("resize.DT-"+a.sInstance,ua(function(){Y(a)}))},d?setTimeout(b,1E3):b(),a._reszEvt=!0}function ua(a,b){var c=b!==k?b:200,d,e;return function(){var b=this,g=+new Date,i=arguments;d&&g<d+c?(clearTimeout(e),e=setTimeout(function(){d=k;a.apply(b,i)},c)):(d=g,a.apply(b,i))}}function Fb(a,b){if(!a)return 0;var c=h("<div/>").css("width", +u(a)).appendTo(b||T.body),d=c[0].offsetWidth;c.remove();return d}function Gb(a,b){var c=Hb(a,b);if(0>c)return null;var d=a.aoData[c];return!d.nTr?h("<td/>").html(B(a,c,b,"display"))[0]:d.anCells[b]}function Hb(a,b){for(var c,d=-1,e=-1,f=0,g=a.aoData.length;f<g;f++)c=B(a,f,b,"display")+"",c=c.replace($b,""),c.length>d&&(d=c.length,e=f);return e}function u(a){return null===a?"0px":"number"==typeof a?0>a?"0px":a+"px":a.match(/\d$/)?a+"px":a}function V(a){var b,c,d=[],e=a.aoColumns,f,g,i,j;b=a.aaSortingFixed; +c=h.isPlainObject(b);var n=[];f=function(a){a.length&&!h.isArray(a[0])?n.push(a):h.merge(n,a)};h.isArray(b)&&f(b);c&&b.pre&&f(b.pre);f(a.aaSorting);c&&b.post&&f(b.post);for(a=0;a<n.length;a++){j=n[a][0];f=e[j].aDataSort;b=0;for(c=f.length;b<c;b++)g=f[b],i=e[g].sType||"string",n[a]._idx===k&&(n[a]._idx=h.inArray(n[a][1],e[g].asSorting)),d.push({src:j,col:g,dir:n[a][1],index:n[a]._idx,type:i,formatter:m.ext.type.order[i+"-pre"]})}return d}function mb(a){var b,c,d=[],e=m.ext.type.order,f=a.aoData,g= +0,i,j=a.aiDisplayMaster,h;Ia(a);h=V(a);b=0;for(c=h.length;b<c;b++)i=h[b],i.formatter&&g++,Ib(a,i.col);if("ssp"!=y(a)&&0!==h.length){b=0;for(c=j.length;b<c;b++)d[j[b]]=b;g===h.length?j.sort(function(a,b){var c,e,g,i,j=h.length,k=f[a]._aSortData,m=f[b]._aSortData;for(g=0;g<j;g++)if(i=h[g],c=k[i.col],e=m[i.col],c=c<e?-1:c>e?1:0,0!==c)return"asc"===i.dir?c:-c;c=d[a];e=d[b];return c<e?-1:c>e?1:0}):j.sort(function(a,b){var c,g,i,j,k=h.length,m=f[a]._aSortData,p=f[b]._aSortData;for(i=0;i<k;i++)if(j=h[i], +c=m[j.col],g=p[j.col],j=e[j.type+"-"+j.dir]||e["string-"+j.dir],c=j(c,g),0!==c)return c;c=d[a];g=d[b];return c<g?-1:c>g?1:0})}a.bSorted=!0}function Jb(a){for(var b,c,d=a.aoColumns,e=V(a),a=a.oLanguage.oAria,f=0,g=d.length;f<g;f++){c=d[f];var i=c.asSorting;b=c.sTitle.replace(/<.*?>/g,"");var j=c.nTh;j.removeAttribute("aria-sort");c.bSortable&&(0<e.length&&e[0].col==f?(j.setAttribute("aria-sort","asc"==e[0].dir?"ascending":"descending"),c=i[e[0].index+1]||i[0]):c=i[0],b+="asc"===c?a.sSortAscending: +a.sSortDescending);j.setAttribute("aria-label",b)}}function Ua(a,b,c,d){var e=a.aaSorting,f=a.aoColumns[b].asSorting,g=function(a,b){var c=a._idx;c===k&&(c=h.inArray(a[1],f));return c+1<f.length?c+1:b?null:0};"number"===typeof e[0]&&(e=a.aaSorting=[e]);c&&a.oFeatures.bSortMulti?(c=h.inArray(b,D(e,"0")),-1!==c?(b=g(e[c],!0),null===b&&1===e.length&&(b=0),null===b?e.splice(c,1):(e[c][1]=f[b],e[c]._idx=b)):(e.push([b,f[0],0]),e[e.length-1]._idx=0)):e.length&&e[0][0]==b?(b=g(e[0]),e.length=1,e[0][1]=f[b], +e[0]._idx=b):(e.length=0,e.push([b,f[0]]),e[0]._idx=0);R(a);"function"==typeof d&&d(a)}function Oa(a,b,c,d){var e=a.aoColumns[c];Va(b,{},function(b){!1!==e.bSortable&&(a.oFeatures.bProcessing?(C(a,!0),setTimeout(function(){Ua(a,c,b.shiftKey,d);"ssp"!==y(a)&&C(a,!1)},0)):Ua(a,c,b.shiftKey,d))})}function xa(a){var b=a.aLastSort,c=a.oClasses.sSortColumn,d=V(a),e=a.oFeatures,f,g;if(e.bSort&&e.bSortClasses){e=0;for(f=b.length;e<f;e++)g=b[e].src,h(D(a.aoData,"anCells",g)).removeClass(c+(2>e?e+1:3));e=0; +for(f=d.length;e<f;e++)g=d[e].src,h(D(a.aoData,"anCells",g)).addClass(c+(2>e?e+1:3))}a.aLastSort=d}function Ib(a,b){var c=a.aoColumns[b],d=m.ext.order[c.sSortDataType],e;d&&(e=d.call(a.oInstance,a,b,ba(a,b)));for(var f,g=m.ext.type.order[c.sType+"-pre"],i=0,h=a.aoData.length;i<h;i++)if(c=a.aoData[i],c._aSortData||(c._aSortData=[]),!c._aSortData[b]||d)f=d?e[i]:B(a,i,b,"sort"),c._aSortData[b]=g?g(f):f}function ya(a){if(a.oFeatures.bStateSave&&!a.bDestroying){var b={time:+new Date,start:a._iDisplayStart, +length:a._iDisplayLength,order:h.extend(!0,[],a.aaSorting),search:Ab(a.oPreviousSearch),columns:h.map(a.aoColumns,function(b,d){return{visible:b.bVisible,search:Ab(a.aoPreSearchCols[d])}})};w(a,"aoStateSaveParams","stateSaveParams",[a,b]);a.oSavedState=b;a.fnStateSaveCallback.call(a.oInstance,a,b)}}function Kb(a){var b,c,d=a.aoColumns;if(a.oFeatures.bStateSave){var e=a.fnStateLoadCallback.call(a.oInstance,a);if(e&&e.time&&(b=w(a,"aoStateLoadParams","stateLoadParams",[a,e]),-1===h.inArray(!1,b)&&(b= +a.iStateDuration,!(0<b&&e.time<+new Date-1E3*b)&&d.length===e.columns.length))){a.oLoadedState=h.extend(!0,{},e);e.start!==k&&(a._iDisplayStart=e.start,a.iInitDisplayStart=e.start);e.length!==k&&(a._iDisplayLength=e.length);e.order!==k&&(a.aaSorting=[],h.each(e.order,function(b,c){a.aaSorting.push(c[0]>=d.length?[0,c[1]]:c)}));e.search!==k&&h.extend(a.oPreviousSearch,Bb(e.search));b=0;for(c=e.columns.length;b<c;b++){var f=e.columns[b];f.visible!==k&&(d[b].bVisible=f.visible);f.search!==k&&h.extend(a.aoPreSearchCols[b], +Bb(f.search))}w(a,"aoStateLoaded","stateLoaded",[a,e])}}}function za(a){var b=m.settings,a=h.inArray(a,D(b,"nTable"));return-1!==a?b[a]:null}function J(a,b,c,d){c="DataTables warning: "+(a?"table id="+a.sTableId+" - ":"")+c;d&&(c+=". For more information about this error, please see http://datatables.net/tn/"+d);if(b)Fa.console&&console.log&&console.log(c);else if(b=m.ext,b=b.sErrMode||b.errMode,a&&w(a,null,"error",[a,d,c]),"alert"==b)alert(c);else{if("throw"==b)throw Error(c);"function"==typeof b&& +b(a,d,c)}}function F(a,b,c,d){h.isArray(c)?h.each(c,function(c,d){h.isArray(d)?F(a,b,d[0],d[1]):F(a,b,d)}):(d===k&&(d=c),b[c]!==k&&(a[d]=b[c]))}function Lb(a,b,c){var d,e;for(e in b)b.hasOwnProperty(e)&&(d=b[e],h.isPlainObject(d)?(h.isPlainObject(a[e])||(a[e]={}),h.extend(!0,a[e],d)):a[e]=c&&"data"!==e&&"aaData"!==e&&h.isArray(d)?d.slice():d);return a}function Va(a,b,c){h(a).bind("click.DT",b,function(b){a.blur();c(b)}).bind("keypress.DT",b,function(a){13===a.which&&(a.preventDefault(),c(a))}).bind("selectstart.DT", +function(){return!1})}function z(a,b,c,d){c&&a[b].push({fn:c,sName:d})}function w(a,b,c,d){var e=[];b&&(e=h.map(a[b].slice().reverse(),function(b){return b.fn.apply(a.oInstance,d)}));null!==c&&(b=h.Event(c+".dt"),h(a.nTable).trigger(b,d),e.push(b.result));return e}function Sa(a){var b=a._iDisplayStart,c=a.fnDisplayEnd(),d=a._iDisplayLength;b>=c&&(b=c-d);b-=b%d;if(-1===d||0>b)b=0;a._iDisplayStart=b}function Pa(a,b){var c=a.renderer,d=m.ext.renderer[b];return h.isPlainObject(c)&&c[b]?d[c[b]]||d._:"string"=== +typeof c?d[c]||d._:d._}function y(a){return a.oFeatures.bServerSide?"ssp":a.ajax||a.sAjaxSource?"ajax":"dom"}function Aa(a,b){var c=[],c=Mb.numbers_length,d=Math.floor(c/2);b<=c?c=W(0,b):a<=d?(c=W(0,c-2),c.push("ellipsis"),c.push(b-1)):(a>=b-1-d?c=W(b-(c-2),b):(c=W(a-d+2,a+d-1),c.push("ellipsis"),c.push(b-1)),c.splice(0,0,"ellipsis"),c.splice(0,0,0));c.DT_el="span";return c}function cb(a){h.each({num:function(b){return Ba(b,a)},"num-fmt":function(b){return Ba(b,a,Wa)},"html-num":function(b){return Ba(b, +a,Ca)},"html-num-fmt":function(b){return Ba(b,a,Ca,Wa)}},function(b,c){v.type.order[b+a+"-pre"]=c;b.match(/^html\-/)&&(v.type.search[b+a]=v.type.search.html)})}function Nb(a){return function(){var b=[za(this[m.ext.iApiIndex])].concat(Array.prototype.slice.call(arguments));return m.ext.internal[a].apply(this,b)}}var m,v,t,p,s,Xa={},Ob=/[\r\n]/g,Ca=/<.*?>/g,ac=/^[\w\+\-]/,bc=/[\w\+\-]$/,Yb=RegExp("(\\/|\\.|\\*|\\+|\\?|\\||\\(|\\)|\\[|\\]|\\{|\\}|\\\\|\\$|\\^|\\-)","g"),Wa=/[',$£€¥%\u2009\u202F\u20BD\u20a9\u20BArfk]/gi, +K=function(a){return!a||!0===a||"-"===a?!0:!1},Pb=function(a){var b=parseInt(a,10);return!isNaN(b)&&isFinite(a)?b:null},Qb=function(a,b){Xa[b]||(Xa[b]=RegExp(va(b),"g"));return"string"===typeof a&&"."!==b?a.replace(/\./g,"").replace(Xa[b],"."):a},Ya=function(a,b,c){var d="string"===typeof a;if(K(a))return!0;b&&d&&(a=Qb(a,b));c&&d&&(a=a.replace(Wa,""));return!isNaN(parseFloat(a))&&isFinite(a)},Rb=function(a,b,c){return K(a)?!0:!(K(a)||"string"===typeof a)?null:Ya(a.replace(Ca,""),b,c)?!0:null},D=function(a, +b,c){var d=[],e=0,f=a.length;if(c!==k)for(;e<f;e++)a[e]&&a[e][b]&&d.push(a[e][b][c]);else for(;e<f;e++)a[e]&&d.push(a[e][b]);return d},ja=function(a,b,c,d){var e=[],f=0,g=b.length;if(d!==k)for(;f<g;f++)a[b[f]][c]&&e.push(a[b[f]][c][d]);else for(;f<g;f++)e.push(a[b[f]][c]);return e},W=function(a,b){var c=[],d;b===k?(b=0,d=a):(d=b,b=a);for(var e=b;e<d;e++)c.push(e);return c},Sb=function(a){for(var b=[],c=0,d=a.length;c<d;c++)a[c]&&b.push(a[c]);return b},pa=function(a){var b=[],c,d,e=a.length,f,g=0; +d=0;a:for(;d<e;d++){c=a[d];for(f=0;f<g;f++)if(b[f]===c)continue a;b.push(c);g++}return b},A=function(a,b,c){a[b]!==k&&(a[c]=a[b])},da=/\[.*?\]$/,U=/\(\)$/,wa=h("<div>")[0],Zb=wa.textContent!==k,$b=/<.*?>/g;m=function(a){this.$=function(a,b){return this.api(!0).$(a,b)};this._=function(a,b){return this.api(!0).rows(a,b).data()};this.api=function(a){return a?new t(za(this[v.iApiIndex])):new t(this)};this.fnAddData=function(a,b){var c=this.api(!0),d=h.isArray(a)&&(h.isArray(a[0])||h.isPlainObject(a[0]))? +c.rows.add(a):c.row.add(a);(b===k||b)&&c.draw();return d.flatten().toArray()};this.fnAdjustColumnSizing=function(a){var b=this.api(!0).columns.adjust(),c=b.settings()[0],d=c.oScroll;a===k||a?b.draw(!1):(""!==d.sX||""!==d.sY)&&Z(c)};this.fnClearTable=function(a){var b=this.api(!0).clear();(a===k||a)&&b.draw()};this.fnClose=function(a){this.api(!0).row(a).child.hide()};this.fnDeleteRow=function(a,b,c){var d=this.api(!0),a=d.rows(a),e=a.settings()[0],h=e.aoData[a[0][0]];a.remove();b&&b.call(this,e,h); +(c===k||c)&&d.draw();return h};this.fnDestroy=function(a){this.api(!0).destroy(a)};this.fnDraw=function(a){this.api(!0).draw(a)};this.fnFilter=function(a,b,c,d,e,h){e=this.api(!0);null===b||b===k?e.search(a,c,d,h):e.column(b).search(a,c,d,h);e.draw()};this.fnGetData=function(a,b){var c=this.api(!0);if(a!==k){var d=a.nodeName?a.nodeName.toLowerCase():"";return b!==k||"td"==d||"th"==d?c.cell(a,b).data():c.row(a).data()||null}return c.data().toArray()};this.fnGetNodes=function(a){var b=this.api(!0); +return a!==k?b.row(a).node():b.rows().nodes().flatten().toArray()};this.fnGetPosition=function(a){var b=this.api(!0),c=a.nodeName.toUpperCase();return"TR"==c?b.row(a).index():"TD"==c||"TH"==c?(a=b.cell(a).index(),[a.row,a.columnVisible,a.column]):null};this.fnIsOpen=function(a){return this.api(!0).row(a).child.isShown()};this.fnOpen=function(a,b,c){return this.api(!0).row(a).child(b,c).show().child()[0]};this.fnPageChange=function(a,b){var c=this.api(!0).page(a);(b===k||b)&&c.draw(!1)};this.fnSetColumnVis= +function(a,b,c){a=this.api(!0).column(a).visible(b);(c===k||c)&&a.columns.adjust().draw()};this.fnSettings=function(){return za(this[v.iApiIndex])};this.fnSort=function(a){this.api(!0).order(a).draw()};this.fnSortListener=function(a,b,c){this.api(!0).order.listener(a,b,c)};this.fnUpdate=function(a,b,c,d,e){var h=this.api(!0);c===k||null===c?h.row(b).data(a):h.cell(b,c).data(a);(e===k||e)&&h.columns.adjust();(d===k||d)&&h.draw();return 0};this.fnVersionCheck=v.fnVersionCheck;var b=this,c=a===k,d=this.length; +c&&(a={});this.oApi=this.internal=v.internal;for(var e in m.ext.internal)e&&(this[e]=Nb(e));this.each(function(){var e={},e=1<d?Lb(e,a,!0):a,g=0,i,j=this.getAttribute("id"),n=!1,l=m.defaults,r=h(this);if("table"!=this.nodeName.toLowerCase())J(null,0,"Non-table node initialisation ("+this.nodeName+")",2);else{db(l);eb(l.column);I(l,l,!0);I(l.column,l.column,!0);I(l,h.extend(e,r.data()));var q=m.settings,g=0;for(i=q.length;g<i;g++){var p=q[g];if(p.nTable==this||p.nTHead.parentNode==this||p.nTFoot&& +p.nTFoot.parentNode==this){g=e.bRetrieve!==k?e.bRetrieve:l.bRetrieve;if(c||g)return p.oInstance;if(e.bDestroy!==k?e.bDestroy:l.bDestroy){p.oInstance.fnDestroy();break}else{J(p,0,"Cannot reinitialise DataTable",3);return}}if(p.sTableId==this.id){q.splice(g,1);break}}if(null===j||""===j)this.id=j="DataTables_Table_"+m.ext._unique++;var o=h.extend(!0,{},m.models.oSettings,{sDestroyWidth:r[0].style.width,sInstance:j,sTableId:j});o.nTable=this;o.oApi=b.internal;o.oInit=e;q.push(o);o.oInstance=1===b.length? +b:r.dataTable();db(e);e.oLanguage&&S(e.oLanguage);e.aLengthMenu&&!e.iDisplayLength&&(e.iDisplayLength=h.isArray(e.aLengthMenu[0])?e.aLengthMenu[0][0]:e.aLengthMenu[0]);e=Lb(h.extend(!0,{},l),e);F(o.oFeatures,e,"bPaginate bLengthChange bFilter bSort bSortMulti bInfo bProcessing bAutoWidth bSortClasses bServerSide bDeferRender".split(" "));F(o,e,["asStripeClasses","ajax","fnServerData","fnFormatNumber","sServerMethod","aaSorting","aaSortingFixed","aLengthMenu","sPaginationType","sAjaxSource","sAjaxDataProp", +"iStateDuration","sDom","bSortCellsTop","iTabIndex","fnStateLoadCallback","fnStateSaveCallback","renderer","searchDelay","rowId",["iCookieDuration","iStateDuration"],["oSearch","oPreviousSearch"],["aoSearchCols","aoPreSearchCols"],["iDisplayLength","_iDisplayLength"],["bJQueryUI","bJUI"]]);F(o.oScroll,e,[["sScrollX","sX"],["sScrollXInner","sXInner"],["sScrollY","sY"],["bScrollCollapse","bCollapse"]]);F(o.oLanguage,e,"fnInfoCallback");z(o,"aoDrawCallback",e.fnDrawCallback,"user");z(o,"aoServerParams", +e.fnServerParams,"user");z(o,"aoStateSaveParams",e.fnStateSaveParams,"user");z(o,"aoStateLoadParams",e.fnStateLoadParams,"user");z(o,"aoStateLoaded",e.fnStateLoaded,"user");z(o,"aoRowCallback",e.fnRowCallback,"user");z(o,"aoRowCreatedCallback",e.fnCreatedRow,"user");z(o,"aoHeaderCallback",e.fnHeaderCallback,"user");z(o,"aoFooterCallback",e.fnFooterCallback,"user");z(o,"aoInitComplete",e.fnInitComplete,"user");z(o,"aoPreDrawCallback",e.fnPreDrawCallback,"user");o.rowIdFn=P(e.rowId);fb(o);j=o.oClasses; +e.bJQueryUI?(h.extend(j,m.ext.oJUIClasses,e.oClasses),e.sDom===l.sDom&&"lfrtip"===l.sDom&&(o.sDom='<"H"lfr>t<"F"ip>'),o.renderer)?h.isPlainObject(o.renderer)&&!o.renderer.header&&(o.renderer.header="jqueryui"):o.renderer="jqueryui":h.extend(j,m.ext.classes,e.oClasses);r.addClass(j.sTable);o.iInitDisplayStart===k&&(o.iInitDisplayStart=e.iDisplayStart,o._iDisplayStart=e.iDisplayStart);null!==e.iDeferLoading&&(o.bDeferLoading=!0,g=h.isArray(e.iDeferLoading),o._iRecordsDisplay=g?e.iDeferLoading[0]:e.iDeferLoading, +o._iRecordsTotal=g?e.iDeferLoading[1]:e.iDeferLoading);var t=o.oLanguage;h.extend(!0,t,e.oLanguage);""!==t.sUrl&&(h.ajax({dataType:"json",url:t.sUrl,success:function(a){S(a);I(l.oLanguage,a);h.extend(true,t,a);ia(o)},error:function(){ia(o)}}),n=!0);null===e.asStripeClasses&&(o.asStripeClasses=[j.sStripeOdd,j.sStripeEven]);var g=o.asStripeClasses,s=r.children("tbody").find("tr").eq(0);-1!==h.inArray(!0,h.map(g,function(a){return s.hasClass(a)}))&&(h("tbody tr",this).removeClass(g.join(" ")),o.asDestroyStripes= +g.slice());q=[];g=this.getElementsByTagName("thead");0!==g.length&&(fa(o.aoHeader,g[0]),q=qa(o));if(null===e.aoColumns){p=[];g=0;for(i=q.length;g<i;g++)p.push(null)}else p=e.aoColumns;g=0;for(i=p.length;g<i;g++)Ga(o,q?q[g]:null);hb(o,e.aoColumnDefs,p,function(a,b){la(o,a,b)});if(s.length){var u=function(a,b){return a.getAttribute("data-"+b)!==null?b:null};h(s[0]).children("th, td").each(function(a,b){var c=o.aoColumns[a];if(c.mData===a){var d=u(b,"sort")||u(b,"order"),e=u(b,"filter")||u(b,"search"); +if(d!==null||e!==null){c.mData={_:a+".display",sort:d!==null?a+".@data-"+d:k,type:d!==null?a+".@data-"+d:k,filter:e!==null?a+".@data-"+e:k};la(o,a)}}})}var v=o.oFeatures;e.bStateSave&&(v.bStateSave=!0,Kb(o,e),z(o,"aoDrawCallback",ya,"state_save"));if(e.aaSorting===k){q=o.aaSorting;g=0;for(i=q.length;g<i;g++)q[g][1]=o.aoColumns[g].asSorting[0]}xa(o);v.bSort&&z(o,"aoDrawCallback",function(){if(o.bSorted){var a=V(o),b={};h.each(a,function(a,c){b[c.src]=c.dir});w(o,null,"order",[o,a,b]);Jb(o)}});z(o, +"aoDrawCallback",function(){(o.bSorted||y(o)==="ssp"||v.bDeferRender)&&xa(o)},"sc");g=r.children("caption").each(function(){this._captionSide=r.css("caption-side")});i=r.children("thead");0===i.length&&(i=h("<thead/>").appendTo(this));o.nTHead=i[0];i=r.children("tbody");0===i.length&&(i=h("<tbody/>").appendTo(this));o.nTBody=i[0];i=r.children("tfoot");if(0===i.length&&0<g.length&&(""!==o.oScroll.sX||""!==o.oScroll.sY))i=h("<tfoot/>").appendTo(this);0===i.length||0===i.children().length?r.addClass(j.sNoFooter): +0<i.length&&(o.nTFoot=i[0],fa(o.aoFooter,o.nTFoot));if(e.aaData)for(g=0;g<e.aaData.length;g++)L(o,e.aaData[g]);else(o.bDeferLoading||"dom"==y(o))&&ma(o,h(o.nTBody).children("tr"));o.aiDisplay=o.aiDisplayMaster.slice();o.bInitialised=!0;!1===n&&ia(o)}});b=null;return this};var Tb=[],x=Array.prototype,cc=function(a){var b,c,d=m.settings,e=h.map(d,function(a){return a.nTable});if(a){if(a.nTable&&a.oApi)return[a];if(a.nodeName&&"table"===a.nodeName.toLowerCase())return b=h.inArray(a,e),-1!==b?[d[b]]: +null;if(a&&"function"===typeof a.settings)return a.settings().toArray();"string"===typeof a?c=h(a):a instanceof h&&(c=a)}else return[];if(c)return c.map(function(){b=h.inArray(this,e);return-1!==b?d[b]:null}).toArray()};t=function(a,b){if(!(this instanceof t))return new t(a,b);var c=[],d=function(a){(a=cc(a))&&(c=c.concat(a))};if(h.isArray(a))for(var e=0,f=a.length;e<f;e++)d(a[e]);else d(a);this.context=pa(c);b&&h.merge(this,b);this.selector={rows:null,cols:null,opts:null};t.extend(this,this,Tb)}; +m.Api=t;h.extend(t.prototype,{any:function(){return 0!==this.count()},concat:x.concat,context:[],count:function(){return this.flatten().length},each:function(a){for(var b=0,c=this.length;b<c;b++)a.call(this,this[b],b,this);return this},eq:function(a){var b=this.context;return b.length>a?new t(b[a],this[a]):null},filter:function(a){var b=[];if(x.filter)b=x.filter.call(this,a,this);else for(var c=0,d=this.length;c<d;c++)a.call(this,this[c],c,this)&&b.push(this[c]);return new t(this.context,b)},flatten:function(){var a= +[];return new t(this.context,a.concat.apply(a,this.toArray()))},join:x.join,indexOf:x.indexOf||function(a,b){for(var c=b||0,d=this.length;c<d;c++)if(this[c]===a)return c;return-1},iterator:function(a,b,c,d){var e=[],f,g,h,j,n,l=this.context,m,q,p=this.selector;"string"===typeof a&&(d=c,c=b,b=a,a=!1);g=0;for(h=l.length;g<h;g++){var o=new t(l[g]);if("table"===b)f=c.call(o,l[g],g),f!==k&&e.push(f);else if("columns"===b||"rows"===b)f=c.call(o,l[g],this[g],g),f!==k&&e.push(f);else if("column"===b||"column-rows"=== +b||"row"===b||"cell"===b){q=this[g];"column-rows"===b&&(m=Da(l[g],p.opts));j=0;for(n=q.length;j<n;j++)f=q[j],f="cell"===b?c.call(o,l[g],f.row,f.column,g,j):c.call(o,l[g],f,g,j,m),f!==k&&e.push(f)}}return e.length||d?(a=new t(l,a?e.concat.apply([],e):e),b=a.selector,b.rows=p.rows,b.cols=p.cols,b.opts=p.opts,a):this},lastIndexOf:x.lastIndexOf||function(a,b){return this.indexOf.apply(this.toArray.reverse(),arguments)},length:0,map:function(a){var b=[];if(x.map)b=x.map.call(this,a,this);else for(var c= +0,d=this.length;c<d;c++)b.push(a.call(this,this[c],c));return new t(this.context,b)},pluck:function(a){return this.map(function(b){return b[a]})},pop:x.pop,push:x.push,reduce:x.reduce||function(a,b){return gb(this,a,b,0,this.length,1)},reduceRight:x.reduceRight||function(a,b){return gb(this,a,b,this.length-1,-1,-1)},reverse:x.reverse,selector:null,shift:x.shift,sort:x.sort,splice:x.splice,toArray:function(){return x.slice.call(this)},to$:function(){return h(this)},toJQuery:function(){return h(this)}, +unique:function(){return new t(this.context,pa(this))},unshift:x.unshift});t.extend=function(a,b,c){if(c.length&&b&&(b instanceof t||b.__dt_wrapper)){var d,e,f,g=function(a,b,c){return function(){var d=b.apply(a,arguments);t.extend(d,d,c.methodExt);return d}};d=0;for(e=c.length;d<e;d++)f=c[d],b[f.name]="function"===typeof f.val?g(a,f.val,f):h.isPlainObject(f.val)?{}:f.val,b[f.name].__dt_wrapper=!0,t.extend(a,b[f.name],f.propExt)}};t.register=p=function(a,b){if(h.isArray(a))for(var c=0,d=a.length;c< +d;c++)t.register(a[c],b);else for(var e=a.split("."),f=Tb,g,i,c=0,d=e.length;c<d;c++){g=(i=-1!==e[c].indexOf("()"))?e[c].replace("()",""):e[c];var j;a:{j=0;for(var n=f.length;j<n;j++)if(f[j].name===g){j=f[j];break a}j=null}j||(j={name:g,val:{},methodExt:[],propExt:[]},f.push(j));c===d-1?j.val=b:f=i?j.methodExt:j.propExt}};t.registerPlural=s=function(a,b,c){t.register(a,c);t.register(b,function(){var a=c.apply(this,arguments);return a===this?this:a instanceof t?a.length?h.isArray(a[0])?new t(a.context, +a[0]):a[0]:k:a})};p("tables()",function(a){var b;if(a){b=t;var c=this.context;if("number"===typeof a)a=[c[a]];else var d=h.map(c,function(a){return a.nTable}),a=h(d).filter(a).map(function(){var a=h.inArray(this,d);return c[a]}).toArray();b=new b(a)}else b=this;return b});p("table()",function(a){var a=this.tables(a),b=a.context;return b.length?new t(b[0]):a});s("tables().nodes()","table().node()",function(){return this.iterator("table",function(a){return a.nTable},1)});s("tables().body()","table().body()", +function(){return this.iterator("table",function(a){return a.nTBody},1)});s("tables().header()","table().header()",function(){return this.iterator("table",function(a){return a.nTHead},1)});s("tables().footer()","table().footer()",function(){return this.iterator("table",function(a){return a.nTFoot},1)});s("tables().containers()","table().container()",function(){return this.iterator("table",function(a){return a.nTableWrapper},1)});p("draw()",function(a){return this.iterator("table",function(b){"page"=== +a?M(b):("string"===typeof a&&(a="full-hold"===a?!1:!0),R(b,!1===a))})});p("page()",function(a){return a===k?this.page.info().page:this.iterator("table",function(b){Ta(b,a)})});p("page.info()",function(){if(0===this.context.length)return k;var a=this.context[0],b=a._iDisplayStart,c=a._iDisplayLength,d=a.fnRecordsDisplay(),e=-1===c;return{page:e?0:Math.floor(b/c),pages:e?1:Math.ceil(d/c),start:b,end:a.fnDisplayEnd(),length:c,recordsTotal:a.fnRecordsTotal(),recordsDisplay:d,serverSide:"ssp"===y(a)}}); +p("page.len()",function(a){return a===k?0!==this.context.length?this.context[0]._iDisplayLength:k:this.iterator("table",function(b){Ra(b,a)})});var Ub=function(a,b,c){if(c){var d=new t(a);d.one("draw",function(){c(d.ajax.json())})}if("ssp"==y(a))R(a,b);else{C(a,!0);var e=a.jqXHR;e&&4!==e.readyState&&e.abort();ra(a,[],function(c){na(a);for(var c=sa(a,c),d=0,e=c.length;d<e;d++)L(a,c[d]);R(a,b);C(a,!1)})}};p("ajax.json()",function(){var a=this.context;if(0<a.length)return a[0].json});p("ajax.params()", +function(){var a=this.context;if(0<a.length)return a[0].oAjaxData});p("ajax.reload()",function(a,b){return this.iterator("table",function(c){Ub(c,!1===b,a)})});p("ajax.url()",function(a){var b=this.context;if(a===k){if(0===b.length)return k;b=b[0];return b.ajax?h.isPlainObject(b.ajax)?b.ajax.url:b.ajax:b.sAjaxSource}return this.iterator("table",function(b){h.isPlainObject(b.ajax)?b.ajax.url=a:b.ajax=a})});p("ajax.url().load()",function(a,b){return this.iterator("table",function(c){Ub(c,!1===b,a)})}); +var Za=function(a,b,c,d,e){var f=[],g,i,j,n,l,m;j=typeof b;if(!b||"string"===j||"function"===j||b.length===k)b=[b];j=0;for(n=b.length;j<n;j++){i=b[j]&&b[j].split?b[j].split(","):[b[j]];l=0;for(m=i.length;l<m;l++)(g=c("string"===typeof i[l]?h.trim(i[l]):i[l]))&&g.length&&(f=f.concat(g))}a=v.selector[a];if(a.length){j=0;for(n=a.length;j<n;j++)f=a[j](d,e,f)}return pa(f)},$a=function(a){a||(a={});a.filter&&a.search===k&&(a.search=a.filter);return h.extend({search:"none",order:"current",page:"all"},a)}, +ab=function(a){for(var b=0,c=a.length;b<c;b++)if(0<a[b].length)return a[0]=a[b],a[0].length=1,a.length=1,a.context=[a.context[b]],a;a.length=0;return a},Da=function(a,b){var c,d,e,f=[],g=a.aiDisplay;c=a.aiDisplayMaster;var i=b.search;d=b.order;e=b.page;if("ssp"==y(a))return"removed"===i?[]:W(0,c.length);if("current"==e){c=a._iDisplayStart;for(d=a.fnDisplayEnd();c<d;c++)f.push(g[c])}else if("current"==d||"applied"==d)f="none"==i?c.slice():"applied"==i?g.slice():h.map(c,function(a){return-1===h.inArray(a, +g)?a:null});else if("index"==d||"original"==d){c=0;for(d=a.aoData.length;c<d;c++)"none"==i?f.push(c):(e=h.inArray(c,g),(-1===e&&"removed"==i||0<=e&&"applied"==i)&&f.push(c))}return f};p("rows()",function(a,b){a===k?a="":h.isPlainObject(a)&&(b=a,a="");var b=$a(b),c=this.iterator("table",function(c){var e=b;return Za("row",a,function(a){var b=Pb(a);if(b!==null&&!e)return[b];var i=Da(c,e);if(b!==null&&h.inArray(b,i)!==-1)return[b];if(!a)return i;if(typeof a==="function")return h.map(i,function(b){var e= +c.aoData[b];return a(b,e._aData,e.nTr)?b:null});b=Sb(ja(c.aoData,i,"nTr"));if(a.nodeName&&h.inArray(a,b)!==-1)return[a._DT_RowIndex];if(typeof a==="string"&&a.charAt(0)==="#"){i=c.aIds[a.replace(/^#/,"")];if(i!==k)return[i.idx]}return h(b).filter(a).map(function(){return this._DT_RowIndex}).toArray()},c,e)},1);c.selector.rows=a;c.selector.opts=b;return c});p("rows().nodes()",function(){return this.iterator("row",function(a,b){return a.aoData[b].nTr||k},1)});p("rows().data()",function(){return this.iterator(!0, +"rows",function(a,b){return ja(a.aoData,b,"_aData")},1)});s("rows().cache()","row().cache()",function(a){return this.iterator("row",function(b,c){var d=b.aoData[c];return"search"===a?d._aFilterData:d._aSortData},1)});s("rows().invalidate()","row().invalidate()",function(a){return this.iterator("row",function(b,c){ea(b,c,a)})});s("rows().indexes()","row().index()",function(){return this.iterator("row",function(a,b){return b},1)});s("rows().ids()","row().id()",function(a){for(var b=[],c=this.context, +d=0,e=c.length;d<e;d++)for(var f=0,g=this[d].length;f<g;f++){var h=c[d].rowIdFn(c[d].aoData[this[d][f]]._aData);b.push((!0===a?"#":"")+h)}return new t(c,b)});s("rows().remove()","row().remove()",function(){var a=this;this.iterator("row",function(b,c,d){var e=b.aoData,f=e[c];e.splice(c,1);for(var g=0,h=e.length;g<h;g++)null!==e[g].nTr&&(e[g].nTr._DT_RowIndex=g);oa(b.aiDisplayMaster,c);oa(b.aiDisplay,c);oa(a[d],c,!1);Sa(b);c=b.rowIdFn(f._aData);c!==k&&delete b.aIds[c]});this.iterator("table",function(a){for(var c= +0,d=a.aoData.length;c<d;c++)a.aoData[c].idx=c});return this});p("rows.add()",function(a){var b=this.iterator("table",function(b){var c,f,g,h=[];f=0;for(g=a.length;f<g;f++)c=a[f],c.nodeName&&"TR"===c.nodeName.toUpperCase()?h.push(ma(b,c)[0]):h.push(L(b,c));return h},1),c=this.rows(-1);c.pop();h.merge(c,b);return c});p("row()",function(a,b){return ab(this.rows(a,b))});p("row().data()",function(a){var b=this.context;if(a===k)return b.length&&this.length?b[0].aoData[this[0]]._aData:k;b[0].aoData[this[0]]._aData= +a;ea(b[0],this[0],"data");return this});p("row().node()",function(){var a=this.context;return a.length&&this.length?a[0].aoData[this[0]].nTr||null:null});p("row.add()",function(a){a instanceof h&&a.length&&(a=a[0]);var b=this.iterator("table",function(b){return a.nodeName&&"TR"===a.nodeName.toUpperCase()?ma(b,a)[0]:L(b,a)});return this.row(b[0])});var bb=function(a,b){var c=a.context;if(c.length&&(c=c[0].aoData[b!==k?b:a[0]])&&c._details)c._details.remove(),c._detailsShow=k,c._details=k},Vb=function(a, +b){var c=a.context;if(c.length&&a.length){var d=c[0].aoData[a[0]];if(d._details){(d._detailsShow=b)?d._details.insertAfter(d.nTr):d._details.detach();var e=c[0],f=new t(e),g=e.aoData;f.off("draw.dt.DT_details column-visibility.dt.DT_details destroy.dt.DT_details");0<D(g,"_details").length&&(f.on("draw.dt.DT_details",function(a,b){e===b&&f.rows({page:"current"}).eq(0).each(function(a){a=g[a];a._detailsShow&&a._details.insertAfter(a.nTr)})}),f.on("column-visibility.dt.DT_details",function(a,b){if(e=== +b)for(var c,d=ca(b),f=0,h=g.length;f<h;f++)c=g[f],c._details&&c._details.children("td[colspan]").attr("colspan",d)}),f.on("destroy.dt.DT_details",function(a,b){if(e===b)for(var c=0,d=g.length;c<d;c++)g[c]._details&&bb(f,c)}))}}};p("row().child()",function(a,b){var c=this.context;if(a===k)return c.length&&this.length?c[0].aoData[this[0]]._details:k;if(!0===a)this.child.show();else if(!1===a)bb(this);else if(c.length&&this.length){var d=c[0],c=c[0].aoData[this[0]],e=[],f=function(a,b){if(h.isArray(a)|| +a instanceof h)for(var c=0,k=a.length;c<k;c++)f(a[c],b);else a.nodeName&&"tr"===a.nodeName.toLowerCase()?e.push(a):(c=h("<tr><td/></tr>").addClass(b),h("td",c).addClass(b).html(a)[0].colSpan=ca(d),e.push(c[0]))};f(a,b);c._details&&c._details.remove();c._details=h(e);c._detailsShow&&c._details.insertAfter(c.nTr)}return this});p(["row().child.show()","row().child().show()"],function(){Vb(this,!0);return this});p(["row().child.hide()","row().child().hide()"],function(){Vb(this,!1);return this});p(["row().child.remove()", +"row().child().remove()"],function(){bb(this);return this});p("row().child.isShown()",function(){var a=this.context;return a.length&&this.length?a[0].aoData[this[0]]._detailsShow||!1:!1});var dc=/^(.+):(name|visIdx|visible)$/,Wb=function(a,b,c,d,e){for(var c=[],d=0,f=e.length;d<f;d++)c.push(B(a,e[d],b));return c};p("columns()",function(a,b){a===k?a="":h.isPlainObject(a)&&(b=a,a="");var b=$a(b),c=this.iterator("table",function(c){var e=a,f=b,g=c.aoColumns,i=D(g,"sName"),j=D(g,"nTh");return Za("column", +e,function(a){var b=Pb(a);if(a==="")return W(g.length);if(b!==null)return[b>=0?b:g.length+b];if(typeof a==="function"){var e=Da(c,f);return h.map(g,function(b,f){return a(f,Wb(c,f,0,0,e),j[f])?f:null})}var k=typeof a==="string"?a.match(dc):"";if(k)switch(k[2]){case "visIdx":case "visible":b=parseInt(k[1],10);if(b<0){var m=h.map(g,function(a,b){return a.bVisible?b:null});return[m[m.length+b]]}return[$(c,b)];case "name":return h.map(i,function(a,b){return a===k[1]?b:null})}else return h(j).filter(a).map(function(){return h.inArray(this, +j)}).toArray()},c,f)},1);c.selector.cols=a;c.selector.opts=b;return c});s("columns().header()","column().header()",function(){return this.iterator("column",function(a,b){return a.aoColumns[b].nTh},1)});s("columns().footer()","column().footer()",function(){return this.iterator("column",function(a,b){return a.aoColumns[b].nTf},1)});s("columns().data()","column().data()",function(){return this.iterator("column-rows",Wb,1)});s("columns().dataSrc()","column().dataSrc()",function(){return this.iterator("column", +function(a,b){return a.aoColumns[b].mData},1)});s("columns().cache()","column().cache()",function(a){return this.iterator("column-rows",function(b,c,d,e,f){return ja(b.aoData,f,"search"===a?"_aFilterData":"_aSortData",c)},1)});s("columns().nodes()","column().nodes()",function(){return this.iterator("column-rows",function(a,b,c,d,e){return ja(a.aoData,e,"anCells",b)},1)});s("columns().visible()","column().visible()",function(a,b){return this.iterator("column",function(c,d){if(a===k)return c.aoColumns[d].bVisible; +var e=c.aoColumns,f=e[d],g=c.aoData,i,j,m;if(a!==k&&f.bVisible!==a){if(a){var l=h.inArray(!0,D(e,"bVisible"),d+1);i=0;for(j=g.length;i<j;i++)m=g[i].nTr,e=g[i].anCells,m&&m.insertBefore(e[d],e[l]||null)}else h(D(c.aoData,"anCells",d)).detach();f.bVisible=a;ga(c,c.aoHeader);ga(c,c.aoFooter);if(b===k||b)Y(c),(c.oScroll.sX||c.oScroll.sY)&&Z(c);w(c,null,"column-visibility",[c,d,a]);ya(c)}})});s("columns().indexes()","column().index()",function(a){return this.iterator("column",function(b,c){return"visible"=== +a?ba(b,c):c},1)});p("columns.adjust()",function(){return this.iterator("table",function(a){Y(a)},1)});p("column.index()",function(a,b){if(0!==this.context.length){var c=this.context[0];if("fromVisible"===a||"toData"===a)return $(c,b);if("fromData"===a||"toVisible"===a)return ba(c,b)}});p("column()",function(a,b){return ab(this.columns(a,b))});p("cells()",function(a,b,c){h.isPlainObject(a)&&(a.row===k?(c=a,a=null):(c=b,b=null));h.isPlainObject(b)&&(c=b,b=null);if(null===b||b===k)return this.iterator("table", +function(b){var d=a,e=$a(c),f=b.aoData,g=Da(b,e),i=Sb(ja(f,g,"anCells")),j=h([].concat.apply([],i)),l,m=b.aoColumns.length,n,p,t,s,u,v;return Za("cell",d,function(a){var c=typeof a==="function";if(a===null||a===k||c){n=[];p=0;for(t=g.length;p<t;p++){l=g[p];for(s=0;s<m;s++){u={row:l,column:s};if(c){v=f[l];a(u,B(b,l,s),v.anCells?v.anCells[s]:null)&&n.push(u)}else n.push(u)}}return n}return h.isPlainObject(a)?[a]:j.filter(a).map(function(a,b){if(b.parentNode)l=b.parentNode._DT_RowIndex;else{a=0;for(t= +f.length;a<t;a++)if(h.inArray(b,f[a].anCells)!==-1){l=a;break}}return{row:l,column:h.inArray(b,f[l].anCells)}}).toArray()},b,e)});var d=this.columns(b,c),e=this.rows(a,c),f,g,i,j,m,l=this.iterator("table",function(a,b){f=[];g=0;for(i=e[b].length;g<i;g++){j=0;for(m=d[b].length;j<m;j++)f.push({row:e[b][g],column:d[b][j]})}return f},1);h.extend(l.selector,{cols:b,rows:a,opts:c});return l});s("cells().nodes()","cell().node()",function(){return this.iterator("cell",function(a,b,c){return(a=a.aoData[b].anCells)? +a[c]:k},1)});p("cells().data()",function(){return this.iterator("cell",function(a,b,c){return B(a,b,c)},1)});s("cells().cache()","cell().cache()",function(a){a="search"===a?"_aFilterData":"_aSortData";return this.iterator("cell",function(b,c,d){return b.aoData[c][a][d]},1)});s("cells().render()","cell().render()",function(a){return this.iterator("cell",function(b,c,d){return B(b,c,d,a)},1)});s("cells().indexes()","cell().index()",function(){return this.iterator("cell",function(a,b,c){return{row:b, +column:c,columnVisible:ba(a,c)}},1)});s("cells().invalidate()","cell().invalidate()",function(a){return this.iterator("cell",function(b,c,d){ea(b,c,a,d)})});p("cell()",function(a,b,c){return ab(this.cells(a,b,c))});p("cell().data()",function(a){var b=this.context,c=this[0];if(a===k)return b.length&&c.length?B(b[0],c[0].row,c[0].column):k;ib(b[0],c[0].row,c[0].column,a);ea(b[0],c[0].row,"data",c[0].column);return this});p("order()",function(a,b){var c=this.context;if(a===k)return 0!==c.length?c[0].aaSorting: +k;"number"===typeof a?a=[[a,b]]:h.isArray(a[0])||(a=Array.prototype.slice.call(arguments));return this.iterator("table",function(b){b.aaSorting=a.slice()})});p("order.listener()",function(a,b,c){return this.iterator("table",function(d){Oa(d,a,b,c)})});p(["columns().order()","column().order()"],function(a){var b=this;return this.iterator("table",function(c,d){var e=[];h.each(b[d],function(b,c){e.push([c,a])});c.aaSorting=e})});p("search()",function(a,b,c,d){var e=this.context;return a===k?0!==e.length? +e[0].oPreviousSearch.sSearch:k:this.iterator("table",function(e){e.oFeatures.bFilter&&ha(e,h.extend({},e.oPreviousSearch,{sSearch:a+"",bRegex:null===b?!1:b,bSmart:null===c?!0:c,bCaseInsensitive:null===d?!0:d}),1)})});s("columns().search()","column().search()",function(a,b,c,d){return this.iterator("column",function(e,f){var g=e.aoPreSearchCols;if(a===k)return g[f].sSearch;e.oFeatures.bFilter&&(h.extend(g[f],{sSearch:a+"",bRegex:null===b?!1:b,bSmart:null===c?!0:c,bCaseInsensitive:null===d?!0:d}),ha(e, +e.oPreviousSearch,1))})});p("state()",function(){return this.context.length?this.context[0].oSavedState:null});p("state.clear()",function(){return this.iterator("table",function(a){a.fnStateSaveCallback.call(a.oInstance,a,{})})});p("state.loaded()",function(){return this.context.length?this.context[0].oLoadedState:null});p("state.save()",function(){return this.iterator("table",function(a){ya(a)})});m.versionCheck=m.fnVersionCheck=function(a){for(var b=m.version.split("."),a=a.split("."),c,d,e=0,f= +a.length;e<f;e++)if(c=parseInt(b[e],10)||0,d=parseInt(a[e],10)||0,c!==d)return c>d;return!0};m.isDataTable=m.fnIsDataTable=function(a){var b=h(a).get(0),c=!1;h.each(m.settings,function(a,e){var f=e.nScrollHead?h("table",e.nScrollHead)[0]:null,g=e.nScrollFoot?h("table",e.nScrollFoot)[0]:null;if(e.nTable===b||f===b||g===b)c=!0});return c};m.tables=m.fnTables=function(a){var b=!1;h.isPlainObject(a)&&(b=a.api,a=a.visible);var c=h.map(m.settings,function(b){if(!a||a&&h(b.nTable).is(":visible"))return b.nTable}); +return b?new t(c):c};m.util={throttle:ua,escapeRegex:va};m.camelToHungarian=I;p("$()",function(a,b){var c=this.rows(b).nodes(),c=h(c);return h([].concat(c.filter(a).toArray(),c.find(a).toArray()))});h.each(["on","one","off"],function(a,b){p(b+"()",function(){var a=Array.prototype.slice.call(arguments);a[0].match(/\.dt\b/)||(a[0]+=".dt");var d=h(this.tables().nodes());d[b].apply(d,a);return this})});p("clear()",function(){return this.iterator("table",function(a){na(a)})});p("settings()",function(){return new t(this.context, +this.context)});p("init()",function(){var a=this.context;return a.length?a[0].oInit:null});p("data()",function(){return this.iterator("table",function(a){return D(a.aoData,"_aData")}).flatten()});p("destroy()",function(a){a=a||!1;return this.iterator("table",function(b){var c=b.nTableWrapper.parentNode,d=b.oClasses,e=b.nTable,f=b.nTBody,g=b.nTHead,i=b.nTFoot,j=h(e),f=h(f),k=h(b.nTableWrapper),l=h.map(b.aoData,function(a){return a.nTr}),p;b.bDestroying=!0;w(b,"aoDestroyCallback","destroy",[b]);a|| +(new t(b)).columns().visible(!0);k.unbind(".DT").find(":not(tbody *)").unbind(".DT");h(Fa).unbind(".DT-"+b.sInstance);e!=g.parentNode&&(j.children("thead").detach(),j.append(g));i&&e!=i.parentNode&&(j.children("tfoot").detach(),j.append(i));b.aaSorting=[];b.aaSortingFixed=[];xa(b);h(l).removeClass(b.asStripeClasses.join(" "));h("th, td",g).removeClass(d.sSortable+" "+d.sSortableAsc+" "+d.sSortableDesc+" "+d.sSortableNone);b.bJUI&&(h("th span."+d.sSortIcon+", td span."+d.sSortIcon,g).detach(),h("th, td", +g).each(function(){var a=h("div."+d.sSortJUIWrapper,this);h(this).append(a.contents());a.detach()}));f.children().detach();f.append(l);g=a?"remove":"detach";j[g]();k[g]();!a&&c&&(c.insertBefore(e,b.nTableReinsertBefore),j.css("width",b.sDestroyWidth).removeClass(d.sTable),(p=b.asDestroyStripes.length)&&f.children().each(function(a){h(this).addClass(b.asDestroyStripes[a%p])}));c=h.inArray(b,m.settings);-1!==c&&m.settings.splice(c,1)})});h.each(["column","row","cell"],function(a,b){p(b+"s().every()", +function(a){return this.iterator(b,function(d,e,f,g,h){a.call((new t(d))[b](e,"cell"===b?f:k),e,f,g,h)})})});p("i18n()",function(a,b,c){var d=this.context[0],a=P(a)(d.oLanguage);a===k&&(a=b);c!==k&&h.isPlainObject(a)&&(a=a[c]!==k?a[c]:a._);return a.replace("%d",c)});m.version="1.10.9";m.settings=[];m.models={};m.models.oSearch={bCaseInsensitive:!0,sSearch:"",bRegex:!1,bSmart:!0};m.models.oRow={nTr:null,anCells:null,_aData:[],_aSortData:null,_aFilterData:null,_sFilterRow:null,_sRowStripe:"",src:null, +idx:-1};m.models.oColumn={idx:null,aDataSort:null,asSorting:null,bSearchable:null,bSortable:null,bVisible:null,_sManualType:null,_bAttrSrc:!1,fnCreatedCell:null,fnGetData:null,fnSetData:null,mData:null,mRender:null,nTh:null,nTf:null,sClass:null,sContentPadding:null,sDefaultContent:null,sName:null,sSortDataType:"std",sSortingClass:null,sSortingClassJUI:null,sTitle:null,sType:null,sWidth:null,sWidthOrig:null};m.defaults={aaData:null,aaSorting:[[0,"asc"]],aaSortingFixed:[],ajax:null,aLengthMenu:[10, +25,50,100],aoColumns:null,aoColumnDefs:null,aoSearchCols:[],asStripeClasses:null,bAutoWidth:!0,bDeferRender:!1,bDestroy:!1,bFilter:!0,bInfo:!0,bJQueryUI:!1,bLengthChange:!0,bPaginate:!0,bProcessing:!1,bRetrieve:!1,bScrollCollapse:!1,bServerSide:!1,bSort:!0,bSortMulti:!0,bSortCellsTop:!1,bSortClasses:!0,bStateSave:!1,fnCreatedRow:null,fnDrawCallback:null,fnFooterCallback:null,fnFormatNumber:function(a){return a.toString().replace(/\B(?=(\d{3})+(?!\d))/g,this.oLanguage.sThousands)},fnHeaderCallback:null, +fnInfoCallback:null,fnInitComplete:null,fnPreDrawCallback:null,fnRowCallback:null,fnServerData:null,fnServerParams:null,fnStateLoadCallback:function(a){try{return JSON.parse((-1===a.iStateDuration?sessionStorage:localStorage).getItem("DataTables_"+a.sInstance+"_"+location.pathname))}catch(b){}},fnStateLoadParams:null,fnStateLoaded:null,fnStateSaveCallback:function(a,b){try{(-1===a.iStateDuration?sessionStorage:localStorage).setItem("DataTables_"+a.sInstance+"_"+location.pathname,JSON.stringify(b))}catch(c){}}, +fnStateSaveParams:null,iStateDuration:7200,iDeferLoading:null,iDisplayLength:10,iDisplayStart:0,iTabIndex:0,oClasses:{},oLanguage:{oAria:{sSortAscending:": activate to sort column ascending",sSortDescending:": activate to sort column descending"},oPaginate:{sFirst:"First",sLast:"Last",sNext:"Next",sPrevious:"Previous"},sEmptyTable:"No data available in table",sInfo:"Showing _START_ to _END_ of _TOTAL_ entries",sInfoEmpty:"Showing 0 to 0 of 0 entries",sInfoFiltered:"(filtered from _MAX_ total entries)", +sInfoPostFix:"",sDecimal:"",sThousands:",",sLengthMenu:"Show _MENU_ entries",sLoadingRecords:"Loading...",sProcessing:"Processing...",sSearch:"Search:",sSearchPlaceholder:"",sUrl:"",sZeroRecords:"No matching records found"},oSearch:h.extend({},m.models.oSearch),sAjaxDataProp:"data",sAjaxSource:null,sDom:"lfrtip",searchDelay:null,sPaginationType:"simple_numbers",sScrollX:"",sScrollXInner:"",sScrollY:"",sServerMethod:"GET",renderer:null,rowId:"DT_RowId"};X(m.defaults);m.defaults.column={aDataSort:null, +iDataSort:-1,asSorting:["asc","desc"],bSearchable:!0,bSortable:!0,bVisible:!0,fnCreatedCell:null,mData:null,mRender:null,sCellType:"td",sClass:"",sContentPadding:"",sDefaultContent:null,sName:"",sSortDataType:"std",sTitle:null,sType:null,sWidth:null};X(m.defaults.column);m.models.oSettings={oFeatures:{bAutoWidth:null,bDeferRender:null,bFilter:null,bInfo:null,bLengthChange:null,bPaginate:null,bProcessing:null,bServerSide:null,bSort:null,bSortMulti:null,bSortClasses:null,bStateSave:null},oScroll:{bCollapse:null, +iBarWidth:0,sX:null,sXInner:null,sY:null},oLanguage:{fnInfoCallback:null},oBrowser:{bScrollOversize:!1,bScrollbarLeft:!1,bBounding:!1,barWidth:0},ajax:null,aanFeatures:[],aoData:[],aiDisplay:[],aiDisplayMaster:[],aIds:{},aoColumns:[],aoHeader:[],aoFooter:[],oPreviousSearch:{},aoPreSearchCols:[],aaSorting:null,aaSortingFixed:[],asStripeClasses:null,asDestroyStripes:[],sDestroyWidth:0,aoRowCallback:[],aoHeaderCallback:[],aoFooterCallback:[],aoDrawCallback:[],aoRowCreatedCallback:[],aoPreDrawCallback:[], +aoInitComplete:[],aoStateSaveParams:[],aoStateLoadParams:[],aoStateLoaded:[],sTableId:"",nTable:null,nTHead:null,nTFoot:null,nTBody:null,nTableWrapper:null,bDeferLoading:!1,bInitialised:!1,aoOpenRows:[],sDom:null,searchDelay:null,sPaginationType:"two_button",iStateDuration:0,aoStateSave:[],aoStateLoad:[],oSavedState:null,oLoadedState:null,sAjaxSource:null,sAjaxDataProp:null,bAjaxDataGet:!0,jqXHR:null,json:k,oAjaxData:k,fnServerData:null,aoServerParams:[],sServerMethod:null,fnFormatNumber:null,aLengthMenu:null, +iDraw:0,bDrawing:!1,iDrawError:-1,_iDisplayLength:10,_iDisplayStart:0,_iRecordsTotal:0,_iRecordsDisplay:0,bJUI:null,oClasses:{},bFiltered:!1,bSorted:!1,bSortCellsTop:null,oInit:null,aoDestroyCallback:[],fnRecordsTotal:function(){return"ssp"==y(this)?1*this._iRecordsTotal:this.aiDisplayMaster.length},fnRecordsDisplay:function(){return"ssp"==y(this)?1*this._iRecordsDisplay:this.aiDisplay.length},fnDisplayEnd:function(){var a=this._iDisplayLength,b=this._iDisplayStart,c=b+a,d=this.aiDisplay.length,e= +this.oFeatures,f=e.bPaginate;return e.bServerSide?!1===f||-1===a?b+d:Math.min(b+a,this._iRecordsDisplay):!f||c>d||-1===a?d:c},oInstance:null,sInstance:null,iTabIndex:0,nScrollHead:null,nScrollFoot:null,aLastSort:[],oPlugins:{},rowIdFn:null,rowId:null};m.ext=v={buttons:{},classes:{},errMode:"alert",feature:[],search:[],selector:{cell:[],column:[],row:[]},internal:{},legacy:{ajax:null},pager:{},renderer:{pageButton:{},header:{}},order:{},type:{detect:[],search:{},order:{}},_unique:0,fnVersionCheck:m.fnVersionCheck, +iApiIndex:0,oJUIClasses:{},sVersion:m.version};h.extend(v,{afnFiltering:v.search,aTypes:v.type.detect,ofnSearch:v.type.search,oSort:v.type.order,afnSortData:v.order,aoFeatures:v.feature,oApi:v.internal,oStdClasses:v.classes,oPagination:v.pager});h.extend(m.ext.classes,{sTable:"dataTable",sNoFooter:"no-footer",sPageButton:"paginate_button",sPageButtonActive:"current",sPageButtonDisabled:"disabled",sStripeOdd:"odd",sStripeEven:"even",sRowEmpty:"dataTables_empty",sWrapper:"dataTables_wrapper",sFilter:"dataTables_filter", +sInfo:"dataTables_info",sPaging:"dataTables_paginate paging_",sLength:"dataTables_length",sProcessing:"dataTables_processing",sSortAsc:"sorting_asc",sSortDesc:"sorting_desc",sSortable:"sorting",sSortableAsc:"sorting_asc_disabled",sSortableDesc:"sorting_desc_disabled",sSortableNone:"sorting_disabled",sSortColumn:"sorting_",sFilterInput:"",sLengthSelect:"",sScrollWrapper:"dataTables_scroll",sScrollHead:"dataTables_scrollHead",sScrollHeadInner:"dataTables_scrollHeadInner",sScrollBody:"dataTables_scrollBody", +sScrollFoot:"dataTables_scrollFoot",sScrollFootInner:"dataTables_scrollFootInner",sHeaderTH:"",sFooterTH:"",sSortJUIAsc:"",sSortJUIDesc:"",sSortJUI:"",sSortJUIAscAllowed:"",sSortJUIDescAllowed:"",sSortJUIWrapper:"",sSortIcon:"",sJUIHeader:"",sJUIFooter:""});var Ea="",Ea="",G=Ea+"ui-state-default",ka=Ea+"css_right ui-icon ui-icon-",Xb=Ea+"fg-toolbar ui-toolbar ui-widget-header ui-helper-clearfix";h.extend(m.ext.oJUIClasses,m.ext.classes,{sPageButton:"fg-button ui-button "+G,sPageButtonActive:"ui-state-disabled", +sPageButtonDisabled:"ui-state-disabled",sPaging:"dataTables_paginate fg-buttonset ui-buttonset fg-buttonset-multi ui-buttonset-multi paging_",sSortAsc:G+" sorting_asc",sSortDesc:G+" sorting_desc",sSortable:G+" sorting",sSortableAsc:G+" sorting_asc_disabled",sSortableDesc:G+" sorting_desc_disabled",sSortableNone:G+" sorting_disabled",sSortJUIAsc:ka+"triangle-1-n",sSortJUIDesc:ka+"triangle-1-s",sSortJUI:ka+"carat-2-n-s",sSortJUIAscAllowed:ka+"carat-1-n",sSortJUIDescAllowed:ka+"carat-1-s",sSortJUIWrapper:"DataTables_sort_wrapper", +sSortIcon:"DataTables_sort_icon",sScrollHead:"dataTables_scrollHead "+G,sScrollFoot:"dataTables_scrollFoot "+G,sHeaderTH:G,sFooterTH:G,sJUIHeader:Xb+" ui-corner-tl ui-corner-tr",sJUIFooter:Xb+" ui-corner-bl ui-corner-br"});var Mb=m.ext.pager;h.extend(Mb,{simple:function(){return["previous","next"]},full:function(){return["first","previous","next","last"]},numbers:function(a,b){return[Aa(a,b)]},simple_numbers:function(a,b){return["previous",Aa(a,b),"next"]},full_numbers:function(a,b){return["first", +"previous",Aa(a,b),"next","last"]},_numbers:Aa,numbers_length:7});h.extend(!0,m.ext.renderer,{pageButton:{_:function(a,b,c,d,e,f){var g=a.oClasses,i=a.oLanguage.oPaginate,j,k,l=0,m=function(b,d){var p,q,t,s,u=function(b){Ta(a,b.data.action,true)};p=0;for(q=d.length;p<q;p++){s=d[p];if(h.isArray(s)){t=h("<"+(s.DT_el||"div")+"/>").appendTo(b);m(t,s)}else{j=null;k="";switch(s){case "ellipsis":b.append('<span class="ellipsis">…</span>');break;case "first":j=i.sFirst;k=s+(e>0?"":" "+g.sPageButtonDisabled); +break;case "previous":j=i.sPrevious;k=s+(e>0?"":" "+g.sPageButtonDisabled);break;case "next":j=i.sNext;k=s+(e<f-1?"":" "+g.sPageButtonDisabled);break;case "last":j=i.sLast;k=s+(e<f-1?"":" "+g.sPageButtonDisabled);break;default:j=s+1;k=e===s?g.sPageButtonActive:""}if(j!==null){t=h("<a>",{"class":g.sPageButton+" "+k,"aria-controls":a.sTableId,"data-dt-idx":l,tabindex:a.iTabIndex,id:c===0&&typeof s==="string"?a.sTableId+"_"+s:null}).html(j).appendTo(b);Va(t,{action:s},u);l++}}}},p;try{p=h(b).find(T.activeElement).data("dt-idx")}catch(t){}m(h(b).empty(), +d);p&&h(b).find("[data-dt-idx="+p+"]").focus()}}});h.extend(m.ext.type.detect,[function(a,b){var c=b.oLanguage.sDecimal;return Ya(a,c)?"num"+c:null},function(a){if(a&&!(a instanceof Date)&&(!ac.test(a)||!bc.test(a)))return null;var b=Date.parse(a);return null!==b&&!isNaN(b)||K(a)?"date":null},function(a,b){var c=b.oLanguage.sDecimal;return Ya(a,c,!0)?"num-fmt"+c:null},function(a,b){var c=b.oLanguage.sDecimal;return Rb(a,c)?"html-num"+c:null},function(a,b){var c=b.oLanguage.sDecimal;return Rb(a,c, +!0)?"html-num-fmt"+c:null},function(a){return K(a)||"string"===typeof a&&-1!==a.indexOf("<")?"html":null}]);h.extend(m.ext.type.search,{html:function(a){return K(a)?a:"string"===typeof a?a.replace(Ob," ").replace(Ca,""):""},string:function(a){return K(a)?a:"string"===typeof a?a.replace(Ob," "):a}});var Ba=function(a,b,c,d){if(0!==a&&(!a||"-"===a))return-Infinity;b&&(a=Qb(a,b));a.replace&&(c&&(a=a.replace(c,"")),d&&(a=a.replace(d,"")));return 1*a};h.extend(v.type.order,{"date-pre":function(a){return Date.parse(a)|| +0},"html-pre":function(a){return K(a)?"":a.replace?a.replace(/<.*?>/g,"").toLowerCase():a+""},"string-pre":function(a){return K(a)?"":"string"===typeof a?a.toLowerCase():!a.toString?"":a.toString()},"string-asc":function(a,b){return a<b?-1:a>b?1:0},"string-desc":function(a,b){return a<b?1:a>b?-1:0}});cb("");h.extend(!0,m.ext.renderer,{header:{_:function(a,b,c,d){h(a.nTable).on("order.dt.DT",function(e,f,g,h){if(a===f){e=c.idx;b.removeClass(c.sSortingClass+" "+d.sSortAsc+" "+d.sSortDesc).addClass(h[e]== +"asc"?d.sSortAsc:h[e]=="desc"?d.sSortDesc:c.sSortingClass)}})},jqueryui:function(a,b,c,d){h("<div/>").addClass(d.sSortJUIWrapper).append(b.contents()).append(h("<span/>").addClass(d.sSortIcon+" "+c.sSortingClassJUI)).appendTo(b);h(a.nTable).on("order.dt.DT",function(e,f,g,h){if(a===f){e=c.idx;b.removeClass(d.sSortAsc+" "+d.sSortDesc).addClass(h[e]=="asc"?d.sSortAsc:h[e]=="desc"?d.sSortDesc:c.sSortingClass);b.find("span."+d.sSortIcon).removeClass(d.sSortJUIAsc+" "+d.sSortJUIDesc+" "+d.sSortJUI+" "+ +d.sSortJUIAscAllowed+" "+d.sSortJUIDescAllowed).addClass(h[e]=="asc"?d.sSortJUIAsc:h[e]=="desc"?d.sSortJUIDesc:c.sSortingClassJUI)}})}}});m.render={number:function(a,b,c,d,e){return{display:function(f){if("number"!==typeof f&&"string"!==typeof f)return f;var g=0>f?"-":"",f=Math.abs(parseFloat(f)),h=parseInt(f,10),f=c?b+(f-h).toFixed(c).substring(2):"";return g+(d||"")+h.toString().replace(/\B(?=(\d{3})+(?!\d))/g,a)+f+(e||"")}}}};h.extend(m.ext.internal,{_fnExternApiFunc:Nb,_fnBuildAjax:ra,_fnAjaxUpdate:lb, +_fnAjaxParameters:ub,_fnAjaxUpdateDraw:vb,_fnAjaxDataSrc:sa,_fnAddColumn:Ga,_fnColumnOptions:la,_fnAdjustColumnSizing:Y,_fnVisibleToColumnIndex:$,_fnColumnIndexToVisible:ba,_fnVisbleColumns:ca,_fnGetColumns:aa,_fnColumnTypes:Ia,_fnApplyColumnDefs:hb,_fnHungarianMap:X,_fnCamelToHungarian:I,_fnLanguageCompat:S,_fnBrowserDetect:fb,_fnAddData:L,_fnAddTr:ma,_fnNodeToDataIndex:function(a,b){return b._DT_RowIndex!==k?b._DT_RowIndex:null},_fnNodeToColumnIndex:function(a,b,c){return h.inArray(c,a.aoData[b].anCells)}, +_fnGetCellData:B,_fnSetCellData:ib,_fnSplitObjNotation:La,_fnGetObjectDataFn:P,_fnSetObjectDataFn:Q,_fnGetDataMaster:Ma,_fnClearTable:na,_fnDeleteIndex:oa,_fnInvalidate:ea,_fnGetRowElements:Ka,_fnCreateTr:Ja,_fnBuildHead:kb,_fnDrawHead:ga,_fnDraw:M,_fnReDraw:R,_fnAddOptionsHtml:nb,_fnDetectHeader:fa,_fnGetUniqueThs:qa,_fnFeatureHtmlFilter:pb,_fnFilterComplete:ha,_fnFilterCustom:yb,_fnFilterColumn:xb,_fnFilter:wb,_fnFilterCreateSearch:Qa,_fnEscapeRegex:va,_fnFilterData:zb,_fnFeatureHtmlInfo:sb,_fnUpdateInfo:Cb, +_fnInfoMacros:Db,_fnInitialise:ia,_fnInitComplete:ta,_fnLengthChange:Ra,_fnFeatureHtmlLength:ob,_fnFeatureHtmlPaginate:tb,_fnPageChange:Ta,_fnFeatureHtmlProcessing:qb,_fnProcessingDisplay:C,_fnFeatureHtmlTable:rb,_fnScrollDraw:Z,_fnApplyToChildren:H,_fnCalculateColumnWidths:Ha,_fnThrottle:ua,_fnConvertToWidth:Fb,_fnGetWidestNode:Gb,_fnGetMaxLenString:Hb,_fnStringToCss:u,_fnSortFlatten:V,_fnSort:mb,_fnSortAria:Jb,_fnSortListener:Ua,_fnSortAttachListener:Oa,_fnSortingClasses:xa,_fnSortData:Ib,_fnSaveState:ya, +_fnLoadState:Kb,_fnSettingsFromNode:za,_fnLog:J,_fnMap:F,_fnBindAction:Va,_fnCallbackReg:z,_fnCallbackFire:w,_fnLengthOverflow:Sa,_fnRenderer:Pa,_fnDataSource:y,_fnRowAttributes:Na,_fnCalculateEnd:function(){}});h.fn.dataTable=m;h.fn.dataTableSettings=m.settings;h.fn.dataTableExt=m.ext;h.fn.DataTable=function(a){return h(this).dataTable(a).api()};h.each(m,function(a,b){h.fn.DataTable[a]=b});return h.fn.dataTable};"function"===typeof define&&define.amd?define("datatables",["jquery"],S):"object"=== +typeof exports?module.exports=S(require("jquery")):jQuery&&!jQuery.fn.dataTable&&S(jQuery)})(window,document); + + +/*! + DataTables Bootstrap 3 integration + ©2011-2014 SpryMedia Ltd - datatables.net/license +*/ +(function(l,q){var d=function(b,c){b.extend(!0,c.defaults,{dom:"<'row'<'col-sm-6'l><'col-sm-6'f>><'row'<'col-sm-12'tr>><'row'<'col-sm-5'i><'col-sm-7'p>>",renderer:"bootstrap"});b.extend(c.ext.classes,{sWrapper:"dataTables_wrapper form-inline dt-bootstrap",sFilterInput:"form-control input-sm",sLengthSelect:"form-control input-sm"});c.ext.renderer.pageButton.bootstrap=function(g,d,r,s,i,m){var t=new c.Api(g),u=g.oClasses,j=g.oLanguage.oPaginate,e,f,n=0,p=function(c,d){var k,h,o,a,l=function(a){a.preventDefault(); +b(a.currentTarget).hasClass("disabled")||t.page(a.data.action).draw("page")};k=0;for(h=d.length;k<h;k++)if(a=d[k],b.isArray(a))p(c,a);else{f=e="";switch(a){case "ellipsis":e="…";f="disabled";break;case "first":e=j.sFirst;f=a+(0<i?"":" disabled");break;case "previous":e=j.sPrevious;f=a+(0<i?"":" disabled");break;case "next":e=j.sNext;f=a+(i<m-1?"":" disabled");break;case "last":e=j.sLast;f=a+(i<m-1?"":" disabled");break;default:e=a+1,f=i===a?"active":""}e&&(o=b("<li>",{"class":u.sPageButton+ +" "+f,id:0===r&&"string"===typeof a?g.sTableId+"_"+a:null}).append(b("<a>",{href:"#","aria-controls":g.sTableId,"data-dt-idx":n,tabindex:g.iTabIndex}).html(e)).appendTo(c),g.oApi._fnBindAction(o,{action:a},l),n++)}},h;try{h=b(d).find(q.activeElement).data("dt-idx")}catch(l){}p(b(d).empty().html('<ul class="pagination"/>').children("ul"),s);h&&b(d).find("[data-dt-idx="+h+"]").focus()};c.TableTools&&(b.extend(!0,c.TableTools.classes,{container:"DTTT btn-group",buttons:{normal:"btn btn-default",disabled:"disabled"}, +collection:{container:"DTTT_dropdown dropdown-menu",buttons:{normal:"",disabled:"disabled"}},print:{info:"DTTT_print_info"},select:{row:"active"}}),b.extend(!0,c.TableTools.DEFAULTS.oTags,{collection:{container:"ul",button:"li",liner:"a"}}))};"function"===typeof define&&define.amd?define(["jquery","datatables"],d):"object"===typeof exports?d(require("jquery"),require("datatables")):jQuery&&d(jQuery,jQuery.fn.dataTable)})(window,document); + + +jQuery.fn.dataTable.ext.builder = "bs-3.3.5\/jqc-1.11.3,dt-1.10.9,fh-3.0.0,r-1.0.7,sc-1.3.0"; + +/*! + FixedHeader 3.0.0 + ©2009-2015 SpryMedia Ltd - datatables.net/license +*/ +(function(h,j){var g=function(e,i){var g=0,f=function(b,a){if(!(this instanceof f))throw"FixedHeader must be initialised with the 'new' keyword.";!0===a&&(a={});b=new i.Api(b);this.c=e.extend(!0,{},f.defaults,a);this.s={dt:b,position:{theadTop:0,tbodyTop:0,tfootTop:0,tfootBottom:0,width:0,left:0,tfootHeight:0,theadHeight:0,windowHeight:e(h).height(),visible:!0},headerMode:null,footerMode:null,namespace:".dtfc"+g++};this.dom={floatingHeader:null,thead:e(b.table().header()),tbody:e(b.table().body()), +tfoot:e(b.table().footer()),header:{host:null,floating:null,placeholder:null},footer:{host:null,floating:null,placeholder:null}};this.dom.header.host=this.dom.thead.parent();this.dom.footer.host=this.dom.tfoot.parent();var c=b.settings()[0];if(c._fixedHeader)throw"FixedHeader already initialised on table "+c.nTable.id;c._fixedHeader=this;this._constructor()};f.prototype={update:function(){this._positions();this._scroll(!0)},_constructor:function(){var b=this,a=this.s.dt;e(h).on("scroll"+this.s.namespace, +function(){b._scroll()}).on("resize"+this.s.namespace,function(){b.s.position.windowHeight=e(h).height();b._positions();b._scroll(!0)});a.on("column-reorder.dt.dtfc column-visibility.dt.dtfc",function(){b._positions();b._scroll(!0)}).on("draw.dtfc",function(){b._positions();b._scroll()});a.on("destroy.dtfc",function(){a.off(".dtfc");e(h).off(this.s.namespace)});this._positions();this._scroll()},_clone:function(b,a){var c=this.s.dt,d=this.dom[b],k="header"===b?this.dom.thead:this.dom.tfoot;!a&&d.floating? +d.floating.removeClass("fixedHeader-floating fixedHeader-locked"):(d.floating&&(d.placeholder.remove(),d.floating.children().detach(),d.floating.remove()),d.floating=e(c.table().node().cloneNode(!1)).removeAttr("id").append(k).appendTo("body"),d.placeholder=k.clone(!1),d.host.append(d.placeholder),"footer"===b&&this._footerMatch(d.placeholder,d.floating))},_footerMatch:function(b,a){var c=function(d){var c=e(d,b).map(function(){return e(this).width()}).toArray();e(d,a).each(function(a){e(this).width(c[a])})}; +c("th");c("td")},_footerUnsize:function(){var b=this.dom.footer.floating;b&&e("th, td",b).css("width","")},_modeChange:function(b,a,c){var d=this.dom[a],e=this.s.position;"in-place"===b?(d.placeholder&&(d.placeholder.remove(),d.placeholder=null),d.host.append("header"===a?this.dom.thead:this.dom.tfoot),d.floating&&(d.floating.remove(),d.floating=null),"footer"===a&&this._footerUnsize()):"in"===b?(this._clone(a,c),d.floating.addClass("fixedHeader-floating").css("header"===a?"top":"bottom",this.c[a+ +"Offset"]).css("left",e.left+"px").css("width",e.width+"px"),"footer"===a&&d.floating.css("top","")):"below"===b?(this._clone(a,c),d.floating.addClass("fixedHeader-locked").css("top",e.tfootTop-e.theadHeight).css("left",e.left+"px").css("width",e.width+"px")):"above"===b&&(this._clone(a,c),d.floating.addClass("fixedHeader-locked").css("top",e.tbodyTop).css("left",e.left+"px").css("width",e.width+"px"));this.s[a+"Mode"]=b},_positions:function(){var b=this.s.dt.table(),a=this.s.position,c=this.dom, +b=e(b.node()),d=b.children("thead"),f=b.children("tfoot"),c=c.tbody;a.visible=b.is(":visible");a.width=b.outerWidth();a.left=b.offset().left;a.theadTop=d.offset().top;a.tbodyTop=c.offset().top;a.theadHeight=a.tbodyTop-a.theadTop;f.length?(a.tfootTop=f.offset().top,a.tfootBottom=a.tfootTop+f.outerHeight(),a.tfootHeight=a.tfootBottom-a.tfootTop):(a.tfootTop=a.tbodyTop+c.outerHeight(),a.tfootBottom=a.tfootTop,a.tfootHeight=a.tfootTop)},_scroll:function(b){var a=e(j).scrollTop(),c=this.s.position,d;this.c.header&& +(d=!c.visible||a<=c.theadTop-this.c.headerOffset?"in-place":a<=c.tfootTop-c.theadHeight-this.c.headerOffset?"in":"below",(b||d!==this.s.headerMode)&&this._modeChange(d,"header",b));this.c.footer&&this.dom.tfoot.length&&(a=!c.visible||a+c.windowHeight>=c.tfootBottom+this.c.footerOffset?"in-place":c.windowHeight+a>c.tbodyTop+c.tfootHeight+this.c.footerOffset?"in":"above",(b||a!==this.s.footerMode)&&this._modeChange(a,"footer",b))}};f.version="3.0.0";f.defaults={header:!0,footer:!1,headerOffset:0,footerOffset:0}; +e.fn.dataTable.FixedHeader=f;e.fn.DataTable.FixedHeader=f;e(j).on("init.dt.dtb",function(b,a){if("dt"===b.namespace){var c=a.oInit.fixedHeader||i.defaults.fixedHeader;c&&!a._buttons&&new f(a,c)}});i.Api.register("fixedHeader()",function(){});i.Api.register("fixedHeader.adjust()",function(){return this.iterator("table",function(b){(b=b._fixedHeader)&&b.update()})});return f};"function"===typeof define&&define.amd?define(["jquery","datatables"],g):"object"===typeof exports?g(require("jquery"),require("datatables")): +jQuery&&!jQuery.fn.dataTable.FixedHeader&&g(jQuery,jQuery.fn.dataTable)})(window,document); + + +/*! + Responsive 1.0.7 + 2014-2015 SpryMedia Ltd - datatables.net/license +*/ +(function(n,p){var o=function(e,k){var h=function(d,a){if(!k.versionCheck||!k.versionCheck("1.10.1"))throw"DataTables Responsive requires DataTables 1.10.1 or newer";this.s={dt:new k.Api(d),columns:[]};this.s.dt.settings()[0].responsive||(a&&"string"===typeof a.details&&(a.details={type:a.details}),this.c=e.extend(!0,{},h.defaults,k.defaults.responsive,a),d.responsive=this,this._constructor())};h.prototype={_constructor:function(){var d=this,a=this.s.dt;a.settings()[0]._responsive=this;e(n).on("resize.dtr orientationchange.dtr", +a.settings()[0].oApi._fnThrottle(function(){d._resize()}));a.on("destroy.dtr",function(){e(n).off("resize.dtr orientationchange.dtr draw.dtr")});this.c.breakpoints.sort(function(a,c){return a.width<c.width?1:a.width>c.width?-1:0});this._classLogic();this._resizeAuto();var c=this.c.details;c.type&&(d._detailsInit(),this._detailsVis(),a.on("column-visibility.dtr",function(){d._detailsVis()}),a.on("draw.dtr",function(){a.rows({page:"current"}).iterator("row",function(b,c){var f=a.row(c);if(f.child.isShown()){var i= +d.c.details.renderer(a,c);f.child(i,"child").show()}})}),e(a.table().node()).addClass("dtr-"+c.type));this._resize()},_columnsVisiblity:function(d){var a=this.s.dt,c=this.s.columns,b,g,f=e.map(c,function(a){return a.auto&&null===a.minWidth?!1:!0===a.auto?"-":-1!==e.inArray(d,a.includeIn)}),i=0;b=0;for(g=f.length;b<g;b++)!0===f[b]&&(i+=c[b].minWidth);b=a.settings()[0].oScroll;b=b.sY||b.sX?b.iBarWidth:0;a=a.table().container().offsetWidth-b-i;b=0;for(g=f.length;b<g;b++)c[b].control&&(a-=c[b].minWidth); +i=!1;b=0;for(g=f.length;b<g;b++)"-"===f[b]&&!c[b].control&&(i||0>a-c[b].minWidth?(i=!0,f[b]=!1):f[b]=!0,a-=c[b].minWidth);a=!1;b=0;for(g=c.length;b<g;b++)if(!c[b].control&&!c[b].never&&!f[b]){a=!0;break}b=0;for(g=c.length;b<g;b++)c[b].control&&(f[b]=a);-1===e.inArray(!0,f)&&(f[0]=!0);return f},_classLogic:function(){var d=this,a=this.c.breakpoints,c=this.s.dt.columns().eq(0).map(function(a){a=this.column(a).header().className;return{className:a,includeIn:[],auto:!1,control:!1,never:a.match(/\bnever\b/)? +!0:!1}}),b=function(a,b){var d=c[a].includeIn;-1===e.inArray(b,d)&&d.push(b)},g=function(f,g,e,j){if(e)if("max-"===e){j=d._find(g).width;g=0;for(e=a.length;g<e;g++)a[g].width<=j&&b(f,a[g].name)}else if("min-"===e){j=d._find(g).width;g=0;for(e=a.length;g<e;g++)a[g].width>=j&&b(f,a[g].name)}else{if("not-"===e){g=0;for(e=a.length;g<e;g++)-1===a[g].name.indexOf(j)&&b(f,a[g].name)}}else c[f].includeIn.push(g)};c.each(function(b,c){for(var d=b.className.split(" "),j=!1,h=0,k=d.length;h<k;h++){var l=e.trim(d[h]); +if("all"===l){j=!0;b.includeIn=e.map(a,function(a){return a.name});return}if("none"===l||"never"===l){j=!0;return}if("control"===l){j=!0;b.control=!0;return}e.each(a,function(a,b){var d=b.name.split("-"),e=l.match(RegExp("(min\\-|max\\-|not\\-)?("+d[0]+")(\\-[_a-zA-Z0-9])?"));e&&(j=!0,e[2]===d[0]&&e[3]==="-"+d[1]?g(c,b.name,e[1],e[2]+e[3]):e[2]===d[0]&&!e[3]&&g(c,b.name,e[1],e[2]))})}j||(b.auto=!0)});this.s.columns=c},_detailsInit:function(){var d=this,a=this.s.dt,c=this.c.details;"inline"===c.type&& +(c.target="td:first-child");var b=c.target;e(a.table().body()).on("click","string"===typeof b?b:"td",function(){if(e(a.table().node()).hasClass("collapsed")&&a.row(e(this).closest("tr")).length){if(typeof b==="number"){var c=b<0?a.columns().eq(0).length+b:b;if(a.cell(this).index().column!==c)return}c=a.row(e(this).closest("tr"));if(c.child.isShown()){c.child(false);e(c.node()).removeClass("parent")}else{var f=d.c.details.renderer(a,c[0]);c.child(f,"child").show();e(c.node()).addClass("parent")}}})}, +_detailsVis:function(){var d=this,a=this.s.dt,c=a.columns().indexes().filter(function(b){var c=a.column(b);return c.visible()?null:e(c.header()).hasClass("never")?null:b}),b=!0;if(0===c.length||1===c.length&&this.s.columns[c[0]].control)b=!1;b?a.rows({page:"current"}).eq(0).each(function(b){b=a.row(b);if(b.child()){var c=d.c.details.renderer(a,b[0]);!1===c?b.child.hide():b.child(c,"child").show()}}):a.rows({page:"current"}).eq(0).each(function(b){a.row(b).child.hide()})},_find:function(d){for(var a= +this.c.breakpoints,c=0,b=a.length;c<b;c++)if(a[c].name===d)return a[c]},_resize:function(){var d=this.s.dt,a=e(n).width(),c=this.c.breakpoints,b=c[0].name,g=this.s.columns,f;for(f=c.length-1;0<=f;f--)if(a<=c[f].width){b=c[f].name;break}var i=this._columnsVisiblity(b),c=!1;f=0;for(a=g.length;f<a;f++)if(!1===i[f]&&!g[f].never){c=!0;break}e(d.table().node()).toggleClass("collapsed",c);d.columns().eq(0).each(function(a,b){d.column(a).visible(i[b])})},_resizeAuto:function(){var d=this.s.dt,a=this.s.columns; +if(this.c.auto&&-1!==e.inArray(!0,e.map(a,function(a){return a.auto}))){d.table().node();var c=d.table().node().cloneNode(!1),b=e(d.table().header().cloneNode(!1)).appendTo(c),g=e(d.table().body().cloneNode(!1)).appendTo(c);e(d.table().footer()).clone(!1).appendTo(c);d.rows({page:"current"}).indexes().flatten().each(function(a){var b=d.row(a).node().cloneNode(!0);d.columns(":hidden").flatten().length&&e(b).append(d.cells(a,":hidden").nodes().to$().clone());e(b).appendTo(g)});var f=d.columns().header().to$().clone(!1); +e("<tr/>").append(f).appendTo(b);"inline"===this.c.details.type&&e(c).addClass("dtr-inline collapsed");c=e("<div/>").css({width:1,height:1,overflow:"hidden"}).append(c);c.find("th.never, td.never").remove();c.insertBefore(d.table().node());d.columns().eq(0).each(function(b){a[b].minWidth=f[b].offsetWidth||0});c.remove()}}};h.breakpoints=[{name:"desktop",width:Infinity},{name:"tablet-l",width:1024},{name:"tablet-p",width:768},{name:"mobile-l",width:480},{name:"mobile-p",width:320}];h.defaults={breakpoints:h.breakpoints, +auto:!0,details:{renderer:function(d,a){var c=d.cells(a,":hidden").eq(0).map(function(a){var c=e(d.column(a.column).header()),a=d.cell(a).index();if(c.hasClass("control")||c.hasClass("never"))return"";var f=d.settings()[0],f=f.oApi._fnGetCellData(f,a.row,a.column,"display");(c=c.text())&&(c+=":");return'<li data-dtr-index="'+a.column+'"><span class="dtr-title">'+c+'</span> <span class="dtr-data">'+f+"</span></li>"}).toArray().join("");return c?e('<ul data-dtr-index="'+a+'"/>').append(c):!1},target:0, +type:"inline"}};var m=e.fn.dataTable.Api;m.register("responsive()",function(){return this});m.register("responsive.index()",function(d){d=e(d);return{column:d.data("dtr-index"),row:d.parent().data("dtr-index")}});m.register("responsive.rebuild()",function(){return this.iterator("table",function(d){d._responsive&&d._responsive._classLogic()})});m.register("responsive.recalc()",function(){return this.iterator("table",function(d){d._responsive&&(d._responsive._resizeAuto(),d._responsive._resize())})}); +h.version="1.0.7";e.fn.dataTable.Responsive=h;e.fn.DataTable.Responsive=h;e(p).on("init.dt.dtr",function(d,a){if("dt"===d.namespace&&(e(a.nTable).hasClass("responsive")||e(a.nTable).hasClass("dt-responsive")||a.oInit.responsive||k.defaults.responsive)){var c=a.oInit.responsive;!1!==c&&new h(a,e.isPlainObject(c)?c:{})}});return h};"function"===typeof define&&define.amd?define(["jquery","datatables"],o):"object"===typeof exports?o(require("jquery"),require("datatables")):jQuery&&!jQuery.fn.dataTable.Responsive&& +o(jQuery,jQuery.fn.dataTable)})(window,document); + + +/*! + Scroller 1.3.0 + ©2011-2015 SpryMedia Ltd - datatables.net/license +*/ +(function(m,n,k){var j=function(e,j){var g=function(a,b){this instanceof g?(b===k&&(b={}),this.s={dt:e.fn.dataTable.Api(a).settings()[0],tableTop:0,tableBottom:0,redrawTop:0,redrawBottom:0,autoHeight:!0,viewportRows:0,stateTO:null,drawTO:null,heights:{jump:null,page:null,virtual:null,scroll:null,row:null,viewport:null},topRowFloat:0,scrollDrawDiff:null,loaderVisible:!1},this.s=e.extend(this.s,g.oDefaults,b),this.s.heights.row=this.s.rowHeight,this.dom={force:n.createElement("div"),scroller:null,table:null, +loader:null},this.s.dt.oScroller||(this.s.dt.oScroller=this,this._fnConstruct())):alert("Scroller warning: Scroller must be initialised with the 'new' keyword.")};g.prototype={fnRowToPixels:function(a,b,c){a=c?this._domain("virtualToPhysical",a*this.s.heights.row):this.s.baseScrollTop+(a-this.s.baseRowTop)*this.s.heights.row;return b||b===k?parseInt(a,10):a},fnPixelsToRow:function(a,b,c){var d=a-this.s.baseScrollTop,a=c?this._domain("physicalToVirtual",a)/this.s.heights.row:d/this.s.heights.row+this.s.baseRowTop; +return b||b===k?parseInt(a,10):a},fnScrollToRow:function(a,b){var c=this,d=!1,f=this.fnRowToPixels(a),i=a-(this.s.displayBuffer-1)/2*this.s.viewportRows;0>i&&(i=0);if((f>this.s.redrawBottom||f<this.s.redrawTop)&&this.s.dt._iDisplayStart!==i)d=!0,f=this.fnRowToPixels(a,!1,!0);"undefined"==typeof b||b?(this.s.ani=d,e(this.dom.scroller).animate({scrollTop:f},function(){setTimeout(function(){c.s.ani=!1},25)})):e(this.dom.scroller).scrollTop(f)},fnMeasure:function(a){this.s.autoHeight&&this._fnCalcRowHeight(); +var b=this.s.heights;b.viewport=e(this.dom.scroller).height();this.s.viewportRows=parseInt(b.viewport/b.row,10)+1;this.s.dt._iDisplayLength=this.s.viewportRows*this.s.displayBuffer;(a===k||a)&&this.s.dt.oInstance.fnDraw()},_fnConstruct:function(){var a=this;if(this.s.dt.oFeatures.bPaginate){this.dom.force.style.position="relative";this.dom.force.style.top="0px";this.dom.force.style.left="0px";this.dom.force.style.width="1px";this.dom.scroller=e("div."+this.s.dt.oClasses.sScrollBody,this.s.dt.nTableWrapper)[0]; +this.dom.scroller.appendChild(this.dom.force);this.dom.scroller.style.position="relative";this.dom.table=e(">table",this.dom.scroller)[0];this.dom.table.style.position="absolute";this.dom.table.style.top="0px";this.dom.table.style.left="0px";e(this.s.dt.nTableWrapper).addClass("DTS");this.s.loadingIndicator&&(this.dom.loader=e('<div class="dataTables_processing DTS_Loading">'+this.s.dt.oLanguage.sLoadingRecords+"</div>").css("display","none"),e(this.dom.scroller.parentNode).css("position","relative").append(this.dom.loader)); +this.s.heights.row&&"auto"!=this.s.heights.row&&(this.s.autoHeight=!1);this.fnMeasure(!1);this.s.ingnoreScroll=!0;this.s.stateSaveThrottle=this.s.dt.oApi._fnThrottle(function(){a.s.dt.oApi._fnSaveState(a.s.dt)},500);e(this.dom.scroller).on("scroll.DTS",function(){a._fnScroll.call(a)});e(this.dom.scroller).on("touchstart.DTS",function(){a._fnScroll.call(a)});this.s.dt.aoDrawCallback.push({fn:function(){a.s.dt.bInitialised&&a._fnDrawCallback.call(a)},sName:"Scroller"});e(m).on("resize.DTS",function(){a.fnMeasure(false); +a._fnInfo()});var b=!0;this.s.dt.oApi._fnCallbackReg(this.s.dt,"aoStateSaveParams",function(c,d){if(b&&a.s.dt.oLoadedState){d.iScroller=a.s.dt.oLoadedState.iScroller;d.iScrollerTopRow=a.s.dt.oLoadedState.iScrollerTopRow;b=false}else{d.iScroller=a.dom.scroller.scrollTop;d.iScrollerTopRow=a.s.topRowFloat}},"Scroller_State");this.s.dt.oLoadedState&&(this.s.topRowFloat=this.s.dt.oLoadedState.iScrollerTopRow||0);e(this.s.dt.nTable).on("init.dt",function(){a.fnMeasure()});this.s.dt.aoDestroyCallback.push({sName:"Scroller", +fn:function(){e(m).off("resize.DTS");e(a.dom.scroller).off("touchstart.DTS scroll.DTS");e(a.s.dt.nTableWrapper).removeClass("DTS");e("div.DTS_Loading",a.dom.scroller.parentNode).remove();e(a.s.dt.nTable).off("init.dt");a.dom.table.style.position="";a.dom.table.style.top="";a.dom.table.style.left=""}})}else this.s.dt.oApi._fnLog(this.s.dt,0,"Pagination must be enabled for Scroller")},_fnScroll:function(){var a=this,b=this.s.heights,c=this.dom.scroller.scrollTop,d;if(!this.s.skip&&!this.s.ingnoreScroll)if(this.s.dt.bFiltered|| +this.s.dt.bSorted)this.s.lastScrollTop=0;else{this._fnInfo();clearTimeout(this.s.stateTO);this.s.stateTO=setTimeout(function(){a.s.dt.oApi._fnSaveState(a.s.dt)},250);if(c<this.s.redrawTop||c>this.s.redrawBottom){var f=Math.ceil((this.s.displayBuffer-1)/2*this.s.viewportRows);Math.abs(c-this.s.lastScrollTop)>b.viewport||this.s.ani?(d=parseInt(this._domain("physicalToVirtual",c)/b.row,10)-f,this.s.topRowFloat=this._domain("physicalToVirtual",c)/b.row):(d=this.fnPixelsToRow(c)-f,this.s.topRowFloat=this.fnPixelsToRow(c, +!1));0>=d?d=0:d+this.s.dt._iDisplayLength>this.s.dt.fnRecordsDisplay()?(d=this.s.dt.fnRecordsDisplay()-this.s.dt._iDisplayLength,0>d&&(d=0)):0!==d%2&&d++;if(d!=this.s.dt._iDisplayStart&&(this.s.tableTop=e(this.s.dt.nTable).offset().top,this.s.tableBottom=e(this.s.dt.nTable).height()+this.s.tableTop,b=function(){if(a.s.scrollDrawReq===null)a.s.scrollDrawReq=c;a.s.dt._iDisplayStart=d;a.s.dt.oApi._fnDraw(a.s.dt)},this.s.dt.oFeatures.bServerSide?(clearTimeout(this.s.drawTO),this.s.drawTO=setTimeout(b, +this.s.serverWait)):b(),this.dom.loader&&!this.s.loaderVisible))this.dom.loader.css("display","block"),this.s.loaderVisible=!0}this.s.lastScrollTop=c;this.s.stateSaveThrottle()}},_domain:function(a,b){var c=this.s.heights,d;if(c.virtual===c.scroll){d=(c.virtual-c.viewport)/(c.scroll-c.viewport);if("virtualToPhysical"===a)return b/d;if("physicalToVirtual"===a)return b*d}var e=(c.scroll-c.viewport)/2,i=(c.virtual-c.viewport)/2;d=i/(e*e);if("virtualToPhysical"===a){if(b<i)return Math.pow(b/d,0.5);b= +2*i-b;return 0>b?c.scroll:2*e-Math.pow(b/d,0.5)}if("physicalToVirtual"===a){if(b<e)return b*b*d;b=2*e-b;return 0>b?c.virtual:2*i-b*b*d}},_fnDrawCallback:function(){var a=this,b=this.s.heights,c=this.dom.scroller.scrollTop,d=e(this.s.dt.nTable).height(),f=this.s.dt._iDisplayStart,i=this.s.dt._iDisplayLength,g=this.s.dt.fnRecordsDisplay();this.s.skip=!0;this._fnScrollForce();c=0===f?this.s.topRowFloat*b.row:f+i>=g?b.scroll-(g-this.s.topRowFloat)*b.row:this._domain("virtualToPhysical",this.s.topRowFloat* +b.row);this.dom.scroller.scrollTop=c;this.s.baseScrollTop=c;this.s.baseRowTop=this.s.topRowFloat;var l=c-(this.s.topRowFloat-f)*b.row;0===f?l=0:f+i>=g&&(l=b.scroll-d);this.dom.table.style.top=l+"px";this.s.tableTop=l;this.s.tableBottom=d+this.s.tableTop;d=(c-this.s.tableTop)*this.s.boundaryScale;this.s.redrawTop=c-d;this.s.redrawBottom=c+d;this.s.skip=!1;this.s.dt.oFeatures.bStateSave&&null!==this.s.dt.oLoadedState&&"undefined"!=typeof this.s.dt.oLoadedState.iScroller?((c=(this.s.dt.sAjaxSource|| +a.s.dt.ajax)&&!this.s.dt.oFeatures.bServerSide?!0:!1)&&2==this.s.dt.iDraw||!c&&1==this.s.dt.iDraw)&&setTimeout(function(){e(a.dom.scroller).scrollTop(a.s.dt.oLoadedState.iScroller);a.s.redrawTop=a.s.dt.oLoadedState.iScroller-b.viewport/2;setTimeout(function(){a.s.ingnoreScroll=!1},0)},0):a.s.ingnoreScroll=!1;setTimeout(function(){a._fnInfo.call(a)},0);this.dom.loader&&this.s.loaderVisible&&(this.dom.loader.css("display","none"),this.s.loaderVisible=!1)},_fnScrollForce:function(){var a=this.s.heights; +a.virtual=a.row*this.s.dt.fnRecordsDisplay();a.scroll=a.virtual;1E6<a.scroll&&(a.scroll=1E6);this.dom.force.style.height=a.scroll>this.s.heights.row?a.scroll+"px":this.s.heights.row+"px"},_fnCalcRowHeight:function(){var a=this.s.dt,b=a.nTable,c=b.cloneNode(!1),d=e("<tbody/>").appendTo(c),f=e('<div class="'+a.oClasses.sWrapper+' DTS"><div class="'+a.oClasses.sScrollWrapper+'"><div class="'+a.oClasses.sScrollBody+'"></div></div></div>');for(e("tbody tr:lt(4)",b).clone().appendTo(d);3>e("tr",d).length;)d.append("<tr><td> </td></tr>"); +e("div."+a.oClasses.sScrollBody,f).append(c);f.appendTo(this.s.dt.nHolding||b.parentNode);this.s.heights.row=e("tr",d).eq(1).outerHeight();f.remove()},_fnInfo:function(){if(this.s.dt.oFeatures.bInfo){var a=this.s.dt,b=a.oLanguage,c=this.dom.scroller.scrollTop,d=Math.floor(this.fnPixelsToRow(c,!1,this.s.ani)+1),f=a.fnRecordsTotal(),g=a.fnRecordsDisplay(),c=Math.ceil(this.fnPixelsToRow(c+this.s.heights.viewport,!1,this.s.ani)),c=g<c?g:c,h=a.fnFormatNumber(d),l=a.fnFormatNumber(c),j=a.fnFormatNumber(f), +k=a.fnFormatNumber(g),h=0===a.fnRecordsDisplay()&&a.fnRecordsDisplay()==a.fnRecordsTotal()?b.sInfoEmpty+b.sInfoPostFix:0===a.fnRecordsDisplay()?b.sInfoEmpty+" "+b.sInfoFiltered.replace("_MAX_",j)+b.sInfoPostFix:a.fnRecordsDisplay()==a.fnRecordsTotal()?b.sInfo.replace("_START_",h).replace("_END_",l).replace("_MAX_",j).replace("_TOTAL_",k)+b.sInfoPostFix:b.sInfo.replace("_START_",h).replace("_END_",l).replace("_MAX_",j).replace("_TOTAL_",k)+" "+b.sInfoFiltered.replace("_MAX_",a.fnFormatNumber(a.fnRecordsTotal()))+ +b.sInfoPostFix;(b=b.fnInfoCallback)&&(h=b.call(a.oInstance,a,d,c,f,g,h));a=a.aanFeatures.i;if("undefined"!=typeof a){d=0;for(f=a.length;d<f;d++)e(a[d]).html(h)}}}};g.defaults={trace:!1,rowHeight:"auto",serverWait:200,displayBuffer:9,boundaryScale:0.5,loadingIndicator:!1};g.oDefaults=g.defaults;g.version="1.3.0";"function"==typeof e.fn.dataTable&&"function"==typeof e.fn.dataTableExt.fnVersionCheck&&e.fn.dataTableExt.fnVersionCheck("1.10.0")?e.fn.dataTableExt.aoFeatures.push({fnInit:function(a){var b= +a.oInit;new g(a,b.scroller||b.oScroller||{})},cFeature:"S",sFeature:"Scroller"}):alert("Warning: Scroller requires DataTables 1.10.0 or greater - www.datatables.net/download");e(n).on("preInit.dt.dtscroller",function(a,b){if("dt"===a.namespace){var c=b.oInit.scroller,d=j.defaults.scroller;if(c||d)d=e.extend({},c,d),!1!==c&&new g(b,d)}});e.fn.dataTable.Scroller=g;e.fn.DataTable.Scroller=g;var h=e.fn.dataTable.Api;h.register("scroller()",function(){return this});h.register("scroller().rowToPixels()", +function(a,b,c){var d=this.context;if(d.length&&d[0].oScroller)return d[0].oScroller.fnRowToPixels(a,b,c)});h.register("scroller().pixelsToRow()",function(a,b,c){var d=this.context;if(d.length&&d[0].oScroller)return d[0].oScroller.fnPixelsToRow(a,b,c)});h.register("scroller().scrollToRow()",function(a,b){this.iterator("table",function(c){c.oScroller&&c.oScroller.fnScrollToRow(a,b)});return this});h.register("row().scrollTo()",function(a){var b=this;this.iterator("row",function(c,d){if(c.oScroller){var e= +b.rows({order:"applied",search:"applied"}).indexes().indexOf(d);c.oScroller.fnScrollToRow(e,a)}});return this});h.register("scroller.measure()",function(a){this.iterator("table",function(b){b.oScroller&&b.oScroller.fnMeasure(a)});return this});return g};"function"===typeof define&&define.amd?define(["jquery","datatables"],j):"object"===typeof exports?j(require("jquery"),require("datatables")):jQuery&&!jQuery.fn.dataTable.Scroller&&j(jQuery,jQuery.fn.dataTable)})(window,document); + + diff --git a/interface/js/rspamd.js b/interface/js/rspamd.js new file mode 100644 index 000000000..5f276f5f5 --- /dev/null +++ b/interface/js/rspamd.js @@ -0,0 +1,1121 @@ +/* + The MIT License (MIT) + + Copyright (C) 2012-2013 Anton Simonov <untone@gmail.com> + Copyright (C) 2014-2015 Vsevolod Stakhov <vsevolod@highsecure.ru> + + Permission is hereby granted, free of charge, to any person obtaining a copy + of this software and associated documentation files (the "Software"), to deal + in the Software without restriction, including without limitation the rights + to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + copies of the Software, and to permit persons to whom the Software is + furnished to do so, subject to the following conditions: + + The above copyright notice and this permission notice shall be included in + all copies or substantial portions of the Software. + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + THE SOFTWARE. + */ +(function () { + $(document).ready(function () { + // begin + //$.cookie.json = true; + var pie; + var history; + $('#disconnect').on('click', function (event) { + if (pie) { + pie.destroy(); + } + if (history) { + history.destroy(); + } + cleanCredentials(); + connectRSPAMD(); + // window.location.reload(); + return false; + }); + $('#refresh').on('click', function (event) { + statWidgets(); + getChart(); + }); + // @supports session storage + function supportsSessionStorage() { + return typeof(Storage) !== "undefined"; + } + // @return password + function getPassword() { + if (sessionState()) { + if (!supportsSessionStorage()) { + return password = $.cookie('rspamdpasswd'); + } + else { + return password = sessionStorage.getItem('Password'); + } + } + } + // @return session state + function sessionState() { + if ((supportsSessionStorage() && (sessionStorage.getItem('Password') !== null)) + || (!supportsSessionStorage() && ($.cookie('rspamdsession')) !== null)) { + return true; + } + else { + return false; + } + } + + // @detect session storate + supportsSessionStorage(); + // @request credentials + function requestCredentials() { + $.ajax({ + dataType: 'json', + type: 'GET', + url: 'auth', + data: { + password: getPassword() + }, + success: function (data) { + if (data.auth === 'failed') { + connectRSPAMD(); + } + } + }); + } + // @request credentials + function updateCredentials() { + $.ajax({ + dataType: 'json', + type: 'GET', + url: 'auth', + data: { + password: getPassword() + }, + success: function (data) { + saveCredentials(data, password); + } + }); + } + // @save credentials + function saveCredentials(data, password) { + if (!supportsSessionStorage()) { + $.cookie('rspamdsession', data, { expires: 1 }, { path: '/' }); + $.cookie('rspamdpasswd', password, { expires: 1 }, { path: '/' }); + } + else { + sessionStorage.setItem('Password', password); + sessionStorage.setItem('Credentials', JSON.stringify(data)); + } + } + // @update credentials + function saveActions(data) { + if (!supportsSessionStorage()) { + $.cookie('rspamdactions', data); + } + else { + sessionStorage.setItem('Actions', JSON.stringify(data)); + } + } + // @update credentials + function saveMaps(data) { + if (!supportsSessionStorage()) { + $.cookie('rspamdmaps', data, { expires: 1 }, { path: '/' }); + } + else { + sessionStorage.setItem('Maps', JSON.stringify(data)); + } + } + // @clean credentials + function cleanCredentials() { + if (!supportsSessionStorage()) { + $.removeCookie('rspamdlogged'); + $.removeCookie('rspamdsession'); + $.removeCookie('rspamdpasswd'); + } + else { + sessionStorage.clear(); + } + $('#statWidgets').empty(); + $('#listMaps').empty(); + $('#historyLog tbody').remove(); + $('#modalBody').empty(); + } + function isLogged() { + if (!supportsSessionStorage()) { + if ($.cookie('rspamdpasswd') != null) { + return true; + } + } + else { + if (sessionStorage.getItem('Password') != null) { + return true; + } + } + return false; + } + // @alert popover + function alertMessage(alertState, alertText) { + if ($('.alert').is(':visible')) { + $(alert).hide().remove(); + } + var alert = $('<div class="alert ' + alertState + '" style="display:none">' + + '<button type="button" class="close" data-dismiss="alert" tutle="Dismiss">×</button>' + + '<strong>' + alertText + '</strong>') + .prependTo('body'); + $(alert).show(); + setTimeout(function () { + $(alert).remove(); + }, 3600); + } + // @get maps id + function getMaps() { + var items = []; + $('#listMaps').closest('.widget-box').hide(); + $.ajax({ + dataType: 'json', + url: 'maps', + data: { + password: getPassword() + }, + error: function () { + alertMessage('alert-modal alert-error', data.statusText); + }, + success: function (data) { + $('#listMaps').empty(); + saveMaps(data); + getMapById(); + $.each(data, function (i, item) { + if ((item.editable == false)) { + var caption = 'View'; + var label = '<span class="label label-default">Read</span>'; + } + else { + var caption = 'Edit'; + var label = '<span class="label label-default">Read</span> <span class="label label-success">Write</span>'; + } + items.push('<tr>' + + '<td class="col-md-2 maps-cell">' + label + '</td>' + + '<td>' + + '<span class="map-link" ' + + 'data-source="#' + item.map + '" ' + + 'data-editable="' + item.editable + '" ' + + 'data-target="#modalDialog" ' + + 'data-title="' + item.description + + '" data-toggle="modal">' + item.description + '</span>' + + '</td>' + + '</tr>'); + }); + $('<tbody/>', { + html: items.join('') + }).appendTo('#listMaps'); + $('#listMaps').closest('.widget-box').show(); + } + }); + } + // @get map by id + function getMapById(mode) { + var data; + if (!supportsSessionStorage()) { + data = $.cookie('rspamdmaps', data, { expires: 1 }, { path: '/' }); + } + else { + data = JSON.parse(sessionStorage.getItem('Maps')); + } + if (mode === 'update') { + $('#modalBody').empty(); + getSymbols(); + } + $.each(data, function (i, item) { + $.ajax({ + dataType: 'text', + url: 'getmap', + beforeSend: function (xhr) { + xhr.setRequestHeader('Password', getPassword()); + xhr.setRequestHeader('Map', item.map); + }, + error: function () { + alertMessage('alert-error', 'Cannot receive maps data'); + }, + success: function (text) { + var disabled = ''; + if ((item.editable == false)) { + disabled = 'disabled="disabled"'; + } + + $('<form class="form-horizontal form-map" method="post "action="/savemap" data-type="map" id="' + + item.map + '" style="display:none">' + + '<textarea class="list-textarea"' + disabled + '>' + text + + '</textarea>' + + '</form').appendTo('#modalBody'); + } + }); + }); + } + // @ ms to date + function msToTime(seconds) { + minutes = parseInt(seconds / 60); + hours = parseInt(seconds / 3600); + days = parseInt(seconds / 3600 / 24); + weeks = parseInt(seconds / 3600 / 24 / 7); + years = parseInt(seconds / 3600 / 168 / 365); + if (weeks > 0) { + years = years >= 10 ? years : '0' + years; + weeks -= years * 168; + weeks = weeks >= 10 ? weeks : '0' + weeks; + // Return in format X years and Y weeks + return years + ' years ' + weeks + ' weeks'; + } + seconds -= minutes * 60; + minutes -= hours * 60; + hours -= days * 24; + days = days >= 10 ? days : '0' + days; + hours = hours >= 10 ? hours : '0' + hours; + minutes = minutes >= 10 ? minutes : '0' + minutes; + seconds = seconds >= 10 ? seconds : '0' + seconds; + if (days > 0) { + return days + ' days, ' + hours + ':' + minutes + ':' + seconds; + } + else { + return hours + ':' + minutes + ':' + seconds; + } + } + // @show widgets + function statWidgets() { + var widgets = $('#statWidgets'); + updateCredentials(); + $(widgets).empty().hide(); + var data; + if (!supportsSessionStorage()) { + data = $.cookie('rspamdsession'); + } + else { + data = JSON.parse(sessionStorage.getItem('Credentials')); + } + var stat_w = []; + $.each(data, function (i, item) { + var widget = ''; + if (i == 'auth') { + } + else if (i == 'error') { + } + else if (i == 'version') { + widget = '<div class="left"><strong>' + item + '</strong>' + + i + '</div>'; + $(widget).appendTo(widgets); + } + else if (i == 'uptime') { + widget = '<div class="right"><strong>' + msToTime(item) + + '</strong>' + i + '</div>'; + $(widget).appendTo(widgets); + } + else { + widget = '<li class="stat-box"><div class="widget"><strong>' + + item + '</strong>' + i + '</div></li>'; + if (i == 'scanned') { + stat_w[0] = widget; + } + else if (i == 'clean') { + stat_w[1] = widget; + } + else if (i == 'greylist') { + stat_w[2] = widget; + } + else if (i == 'probable') { + stat_w[3] = widget; + } + else if (i == 'reject') { + stat_w[4] = widget; + } + else if (i == 'learned') { + stat_w[5] = widget; + } + } + }); + $.each(stat_w, function (i, item) { $(item).appendTo(widgets); }); + $('#statWidgets .left,#statWidgets .right').wrapAll('<li class="stat-box pull-right"><div class="widget"></div></li>'); + $(widgets).show(); + window.setTimeout(statWidgets, 10000); + } + // @opem modal with target form enabled + $(document).on('click', '[data-toggle="modal"]', function (e) { + var source = $(this).data('source'); + var editable = $(this).data('editable'); + var title = $(this).data('title'); + var caption = $('#modalTitle').html(title); + var body = $('#modalBody ' + source).show(); + var target = $(this).data('target'); + var progress = $(target + ' .progress').hide(); + $(target).modal(show = true, backdrop = true, keyboard = show); + if (editable === false) { + $('#modalSave').hide(); + } + else { + $('#modalSave').show(); + } + return false; + }); + // close modal without saving + $(document).on('click', '[data-dismiss="modal"]', function (e) { + $('#modalBody form').hide(); + }); + function getChart() { + $.ajax({ + dataType: 'json', + type: 'GET', + url: 'pie', + data: { + password: getPassword() + }, + success: function (data) { + if (pie) { + pie.destroy(); + } + pie = new d3pie("chart", { + "header": { + "title": { + "text": "Rspamd filter stats", + "fontSize": 24, + "font": "open sans" + }, + "subtitle": { + "color": "#999999", + "fontSize": 12, + "font": "open sans" + }, + "titleSubtitlePadding": 9 + }, + "footer": { + "color": "#999999", + "fontSize": 10, + "font": "open sans", + "location": "bottom-left" + }, + "size": { + "canvasWidth": 600, + "canvasHeight": 400, + "pieInnerRadius": "20%", + "pieOuterRadius": "85%" + }, + "data": { + //"sortOrder": "value-desc", + "content": data.filter(function(elt) { + return elt.value > 0; + }) + }, + "labels": { + "outer": { + "hideWhenLessThanPercentage": 1, + "pieDistance": 30 + }, + "inner": { + "hideWhenLessThanPercentage": 4 + }, + "mainLabel": { + "fontSize": 14 + }, + "percentage": { + "color": "#eeeeee", + "fontSize": 14, + "decimalPlaces": 0 + }, + "lines": { + "enabled": true + }, + "truncation": { + "enabled": true + } + }, + "tooltips": { + "enabled": true, + "type": "placeholder", + "string": "{label}: {value}, {percentage}%" + }, + "effects": { + "pullOutSegmentOnClick": { + "effect": "back", + "speed": 400, + "size": 8 + }, + "load": { + "speed": 500 + } + }, + "misc": { + "gradient": { + "enabled": true, + "percentage": 100 + } + } + }); + } + }); + } + // @get history log + // function getChart() { + // //console.log(data) + // $.ajax({ + // dataType: 'json', + // url: './pie', + // beforeSend: function(xhr) { + // xhr.setRequestHeader('Password', getPassword()) + // }, + // error: function() { + // alertMessage('alert-error', 'Cannot receive history'); + // }, + // success: function(data) { + // console.log(data); + // } + // }); + // } + // @get history log + function getHistory() { + var items = []; + $.ajax({ + dataType: 'json', + url: 'history', + data: { + password: getPassword() + }, + error: function () { + alertMessage('alert-error', 'Cannot receive history'); + }, + success: function (data) { + $.each(data, function (i, item) { + var action; + + if (item.action === 'clean' || item.action === 'no action') { + action = 'label-success'; + } + else if (item.action === 'rewrite subject' || item.action === 'add header' || item.action === 'probable spam') { + action = 'label-warning'; + } + else if (item.action === 'spam' || item.action === 'reject') { + action = 'label-danger'; + } + else { + action = 'label-info'; + } + + var score; + if (item.score < item.required_score) { + score = 'label-success'; + } + else { + score = 'label-danger'; + } + + items.push( + '<tr><td data-order="' + item.unix_time + '">' + item.time + '</td>' + + '<td data-order="' + item.id + '"><div class="cell-overflow" tabindex="1" title="' + item.id + '">' + item.id + '</td>' + + '<td data-order="' + item.ip + '"><div class="cell-overflow" tabindex="1" title="' + item.ip + '">' + item.ip + '</div></td>' + + '<td data-order="' + item.action + '"><span class="label ' + action + '">' + item.action + '</span></td>' + + '<td data-order="' + item.score + '"><span class="label ' + score + '">' + item.score.toFixed(2) + ' / ' + item.required_score.toFixed(2) + '</span></td>' + + '<td data-order="' + item.symbols + '"><div class="cell-overflow" tabindex="1" title="' + item.symbols + '">' + item.symbols + '</div></td>' + + '<td data-order="' + item.size + '">' + item.size + '</td>' + + '<td data-order="' + item.scan_time + '">' + item.scan_time.toFixed(3) + '</td>' + + '<td data-order="' + item.user + '"><div class="cell-overflow" tabindex="1" "title="' + item.user + '">' + item.user + '</div></td></tr>'); + }); + $('<tbody/>', { html: items.join('') }).insertAfter('#historyLog thead'); + history = $('#historyLog').DataTable({ + "order": [[ 0, "desc" ]] + }); + } + }); + } + function decimalStep(number) { + var digits = ((+number).toFixed(20)).replace(/^-?\d*\.?|0+$/g, '').length; + if (digits == 0 || digits > 4) { + return 0.1; + } + else { + return 1.0 / (Math.pow(10, digits)); + } + } + // @get symbols into modal form + function getSymbols() { + var items = []; + $.ajax({ + dataType: 'json', + type: 'GET', + url: 'symbols', + data: { + password: getPassword() + }, + success: function (data) { + $('#modalBody').empty(); + $.each(data, function (i, group) { + items.push(' <div class="row row-bordered" data-slider="hover">' + + '<h4>' + group.group + '</h4>' + + '</div>'); + $.each(group.rules, function (i, item) { + var max = 20; + var min = -20; + if (item.weight > max) { + max = item.weight * 2; + } + if (item.weight < min) { + min = item.weight * 2; + } + items.push(' <div class="row row-bordered" data-slider="hover">' + + '<label class="col-md-7" for="' + item.symbol + '" title="' + item.description + '">' + + '<code>' + item.symbol + '</code><p class="symbol-description">' + item.description + '</p>' + + '</label>' + + '<div class="col-md-3 spin-cell">' + + '<input class="numeric" data-role="numerictextbox" autocomplete="off" "type="number" class="input-mini" min="' + + min + '" max="' + + max + '" step="' + decimalStep(item.weight) + + '" tabindex="1" value="' + Number(item.weight).toFixed(2) + + '" id="' + item.symbol + '">' + + '</div>' + + '</div>'); + }); + }); + $('<form/>', { + id: 'symbolsForm', + method: 'post', + action: '/savesymbols', + 'data-type': 'symbols', + style: 'display:none', + html: items.join('') }).appendTo('#modalBody'); + }, + error: function (data) { + alertMessage('alert-modal alert-error', data.statusText); + } + }); + } + // @update history log + $('#resetHistory').on('click', function () { + history.destroy(); + $('#historyLog').children('tbody').remove(); + $.ajax({ + dataType: 'json', + type: 'GET', + url: 'historyreset', + data: { + password: getPassword() + }, + success: function (data) { + getHistory(); + }, + error: function (data) { + alertMessage('alert-modal alert-error', data.statusText); + } + }); + }); + // @reset history log + $('#updateHistory').on('click', function () { + history.destroy(); + $('#historyLog').children('tbody').remove(); + getHistory(); + }); + // @spam upload form + function createUploaders() { + var spamUploader = new qq.FineUploader({ + element: $('#uploadSpamFiles')[0], + request: { + endpoint: 'learnspam', + customHeaders: { + 'Password': getPassword() + } + }, + validation: { + allowedExtensions: ['eml', 'msg', 'txt', 'html'], + sizeLimit: 52428800 + }, + autoUpload: false, + text: { + uploadButton: '<i class="glyphicon glyphicon-plus glyphicon-white"></i> Select Files' + }, + retry: { + enableAuto: false + }, + template: '<div class="qq-uploader">' + + '<pre class="qq-upload-drop-area span12"><span>{dragZoneText}</span></pre>' + + '<div class="qq-upload-button btn btn-danger">{uploadButtonText}</div>' + + '<span class="qq-drop-processing"><span>{dropProcessingText}</span><span class="qq-drop-processing-spinner"></span></span>' + + '<ul class="qq-upload-list"></ul>' + + '</div>', + classes: { + success: 'alert-success', + fail: 'alert-error' + }, + debug: true, + callbacks: { + onError: function () { + alertMessage('alert-error', 'Cannot upload data'); + } + } + }); + var hamUploader = new qq.FineUploader({ + element: $('#uploadHamFiles')[0], + request: { + endpoint: 'learnham', + customHeaders: { + 'Password': getPassword() + } + }, + validation: { + allowedExtensions: ['eml', 'msg', 'txt', 'html'], + sizeLimit: 52428800 + }, + autoUpload: false, + text: { + uploadButton: '<i class="glyphicon glyphicon-plus glyphicon-white"></i> Select Files' + }, + retry: { + enableAuto: true + }, + template: '<div class="qq-uploader">' + + '<pre class="qq-upload-drop-area span12"><span>{dragZoneText}</span></pre>' + + '<div class="qq-upload-button btn btn-success">{uploadButtonText}</div>' + + '<span class="qq-drop-processing"><span>{dropProcessingText}</span><span class="qq-drop-processing-spinner"></span></span>' + + '<ul class="qq-upload-list"></ul>' + + '</div>', + classes: { + success: 'alert-success', + fail: 'alert-error' + }, + debug: true, + callbacks: { + onError: function () { + alertMessage('alert-error', 'Cannot upload data'); + } + } + }); + var data = { + flag: $('#fuzzyFlagUpload').val(), + weight: $('#fuzzyWeightUpload').val() + }; + var fuzzyUploader = new qq.FineUploader({ + element: $('#uploadFuzzyFiles')[0], + request: { + endpoint: 'learnfuzzy', + customHeaders: { + 'Password': getPassword() + } + }, + validation: { + allowedExtensions: ['eml', 'msg', 'txt', 'html', 'pdf'], + sizeLimit: 52428800 + }, + autoUpload: false, + text: { + uploadButton: '<i class="glyphicon glyphicon-plus glyphicon-white"></i> Select Files' + }, + retry: { + enableAuto: true + }, + template: '<div class="qq-uploader">' + + '<pre class="qq-upload-drop-area span12"><span>{dragZoneText}</span></pre>' + + '<div class="qq-upload-button btn btn-success">{uploadButtonText}</div>' + + '<span class="qq-drop-processing"><span>{dropProcessingText}</span><span class="qq-drop-processing-spinner"></span></span>' + + '<ul class="qq-upload-list"></ul>' + + '</div>', + classes: { + success: 'alert-success', + fail: 'alert-error' + }, + debug: true, + callbacks: { + onError: function () { + alertMessage('alert-error', 'Cannot upload data'); + } + } + }); + // @upload spam button + $('#uploadSpamTrigger').on('click', function () { + spamUploader.uploadStoredFiles(); + return false; + }); + // @upload ham button + $('#uploadHamTrigger').on('click', function () { + hamUploader.uploadStoredFiles(); + return false; + }); + // @upload fuzzy button + $('#uploadFuzzyTrigger').on('click', function () { + fuzzyUploader.uploadStoredFiles(); + uploadText(data, 'fuzzy'); + return false; + }); + } + // @upload text + function uploadText(data, source) { + if (source === 'spam') { + var url = 'learnspam'; + } + else if (source === 'ham') { + var url = 'learnham'; + } + else if (source == 'fuzzy') { + var url = 'learnfuzzy'; + } + else if (source === 'scan') { + var url = 'scan'; + } + $.ajax({ + data: data, + dataType: 'json', + type: 'POST', + url: url, + beforeSend: function (xhr) { + xhr.setRequestHeader('Password', getPassword()); + }, + success: function (data) { + cleanTextUpload(source); + if (data.success) { + alertMessage('alert-success', 'Data successfully uploaded'); + } + }, + // error: function() { + // alertMessage('alert-error', 'Cannot upload data'); + // }, + statusCode: { + 404: function () { + alertMessage('alert-error', 'Cannot upload data, no server found'); + }, + 503: function () { + alertMessage('alert-error', 'Cannot tokenize message, no text data'); + } + } + }); + } + // @upload text + function scanText(data) { + var url = 'scan'; + var items = []; + $.ajax({ + data: data, + dataType: 'json', + type: 'POST', + url: url, + beforeSend: function (xhr) { + xhr.setRequestHeader('Password', getPassword()); + }, + success: function (input) { + var data = input['default']; + if (data.action) { + alertMessage('alert-success', 'Data successfully scanned'); + if (data.action === 'clean' || 'no action') { + var action = 'label-success'; + } + if (data.action === 'rewrite subject' || 'add header' || 'probable spam') { + var action = 'label-warning'; + } + if (data.action === 'spam') { + var action = 'label-danger'; + } + if (data.score <= data.required_score) { + var score = 'label-success'; + } + if (data.score >= data.required_score) { + var score = 'label-danger'; + } + $('<tbody id="tmpBody"><tr>' + + '<td><span class="label ' + action + '">' + data.action + '</span></td>' + + '<td><span class="label ' + score + '">' + data.score.toFixed(2) + '/' + data.required_score.toFixed(2) + '</span></td>' + + '</tr></tbody>') + .insertAfter('#scanOutput thead'); + $.each(data, function (i, item) { + if (typeof item == 'object') { + items.push('<div class="cell-overflow" tabindex="1">' + item.name + ': ' + item.score.toFixed(2) + '</div>'); + } + }); + $('<td/>', { id: 'tmpSymbols', html: items.join('') }).appendTo('#scanResult'); + $('#tmpSymbols').insertAfter('#tmpBody td:last').removeAttr('id'); + $('#tmpBody').removeAttr('id'); + $('#scanResult').show(); + $('html, body').animate({ + scrollTop: $('#scanResult').offset().top + }, 1000); + } + else { + alertMessage('alert-error', 'Cannot scan data'); + } + }, + statusCode: { + 404: function () { + alertMessage('alert-error', 'Cannot upload data, no server found'); + }, + 500: function () { + alertMessage('alert-error', 'Cannot tokenize message: no text data'); + }, + 503: function () { + alertMessage('alert-error', 'Cannot tokenize message: no text data'); + } + } + }); + } + // @close scan output + $('#scanClean').on('click', function () { + $('#scanTextSource').val(''); + $('#scanResult').hide(); + $('#scanOutput tbody').remove(); + $('html, body').animate({ + scrollTop: 0 + }, 1000); + }); + // @init upload + $('[data-upload]').on('click', function () { + var source = $(this).data('upload'); + var data; + if (source == 'fuzzy') { + //To access the proper + data = new String($('#' + source + 'TextSource').val()); + data.flag = $('#fuzzyFlagText').val(); + data.weigth = $('#fuzzyWeightText').val(); + data.string = data.toString(); + } + else { + data = $('#' + source + 'TextSource').val(); + } + if (data.length > 0) { + if (source == 'scan') { + scanText(data); + } + else { + uploadText(data, source); + } + } + return false; + }); + // @empty textarea on upload complete + function cleanTextUpload(source) { + $('#' + source + 'TextSource').val(''); + } + // @get acions + function getActions() { + var items = []; + $.ajax({ + dataType: 'json', + type: 'GET', + url: 'actions', + data: { + password: getPassword() + }, + success: function (data) { + // Order of sliders greylist -> probable spam -> spam + $('#actionsBody').empty(); + $('#actionsForm').empty(); + items = []; + var min = 0; + var max = Number.MIN_VALUE; + $.each(data, function (i, item) { + var idx = -1; + var label; + if (item.action === 'add header') { + label = 'Probably Spam'; + idx = 1; + } + else if (item.action === 'greylist') { + label = 'Greylist'; + idx = 0; + } + else if (item.action === 'reject') { + label = 'Spam'; + idx = 2; + } + if (idx >= 0) { + items[idx] = + '<div class="form-group">' + + '<label class="control-label col-sm-2">' + label + '</label>' + + '<div class="controls slider-controls col-sm-10">' + + '<input class="slider" type="slider" value="' + item.value + '">' + + '</div>' + + '</div>'; + } + if (item.value > max) { + max = item.value * 2; + } + if (item.value < min) { + min = item.value; + } + }); + $('<form/>', { id: 'actionsForm', class: '', html: items.join('') }).appendTo('#actionsBody'); + $('<br><div class="form-group">' + + '<button class="btn btn-primary" ' + + 'type="submit">Save actions</button></div>').appendTo('#actionsForm'); + } + }); + } + // @upload edited actions + $(document).on('submit', '#actionsForm', function () { + var inputs = $('#actionsForm :input[type="slider"]'); + var url = 'saveactions'; + var values = []; + // Rspamd order: [spam,probable_spam,greylist] + values[0] = parseFloat(inputs[2].value); + values[1] = parseFloat(inputs[1].value); + values[2] = parseFloat(inputs[0].value); + $.ajax({ + data: JSON.stringify(values), + dataType: 'json', + type: 'POST', + url: url, + beforeSend: function (xhr) { + xhr.setRequestHeader('Password', getPassword()); + }, + success: function () { + alertMessage('alert-success', 'Actions successfully saved'); + }, + error: function () { + alertMessage('alert-modal alert-error', data.statusText); + } + }); + getMapById('update'); + return false; + }); + // @catch changes of file upload form + $(window).resize(function (e) { + var form = $(this).attr('id'); + var height = $(form).height(); + }); + // @watch textarea changes + $('textarea').change(function () { + if ($(this).val().length != '') { + $(this).closest('form').find('button').removeAttr('disabled').removeClass('disabled'); + } + else { + $(this).closest('form').find('button').attr('disabled').addClass('disabled'); + } + }); + // @save forms from modal + $(document).on('click', '#modalSave', function () { + var form = $('#modalBody').children().filter(':visible'); + // var map = $(form).data('map'); + // var type = $(form).data('type'); + var action = $(form).attr('action'); + var id = $(form).attr('id'); + var type = $(form).data('type'); + if (type === 'symbols') { + saveSymbols(action, id); + } + else if (type === 'map') { + saveMap(action, id); + } + }); + // @upload map from modal + function saveMap(action, id) { + var data = $('#' + id).find('textarea').val(); + $.ajax({ + data: data, + dataType: 'text', + type: 'POST', + url: action, + beforeSend: function (xhr) { + xhr.setRequestHeader('Password', getPassword()); + xhr.setRequestHeader('Map', id); + xhr.setRequestHeader('Debug', true); + }, + error: function (data) { + alertMessage('alert-modal alert-error', data.statusText); + }, + success: function (data) { + alertMessage('alert-modal alert-success', 'Map data successfully saved'); + $('#modalDialog').modal('hide'); + } + }); + } + // @upload symbols from modal + function saveSymbols(action, id) { + var inputs = $('#' + id + ' :input[data-role="numerictextbox"]'); + var url = action; + var values = []; + $(inputs).each(function () { + values.push({ name: $(this).attr('id'), value: parseFloat($(this).val()) }); + }); + $.ajax({ + data: JSON.stringify(values), + dataType: 'json', + type: 'POST', + url: url, + beforeSend: function (xhr) { + xhr.setRequestHeader('Password', getPassword()); + }, + success: function () { + alertMessage('alert-modal alert-success', 'Symbols successfully saved'); + }, + error: function (data) { + alertMessage('alert-modal alert-error', data.statusText); + } }); + $('#modalDialog').modal('hide'); + return false; + } + // @connect to server + function connectRSPAMD() { + if (isLogged()) { + displayUI(); + return; + } + var nav = $('#navBar'); + var ui = $('#mainUI'); + var dialog = $('#connectDialog'); + var backdrop = $('#backDrop'); + var disconnect = $('#navBar .pull-right'); + $(ui).hide(); + $(dialog).show(); + $('#connectHost').focus(); + $(backdrop).show(); + $(document).on('submit', '#connectForm', function (e) { + e.preventDefault(); + var password = $('#connectPassword').val(); + $.ajax({ + global: false, + dataType: 'json', + type: 'GET', + url: 'auth', + data: { + password: password + }, + success: function (data) { + if (data.auth === 'failed') { + $(form).each(function () { + $('.form-group').addClass('error'); + }); + } + else { + saveCredentials(data, password); + $(dialog).hide(); + $(backdrop).hide(); + displayUI(); + } + }, + error: function (data) { + alertMessage('alert-modal alert-error', data.statusText); + } + }); + }); + } + function displayUI() { + // @toggle auth and main + var disconnect = $('#navBar .pull-right'); + statWidgets(); + $('#mainUI').show(); + $('#progress').show(); + getActions(); + getMaps(); + createUploaders(); + getSymbols(); + getHistory(); + getChart(); + $('#progress').hide(); + $(disconnect).show(); + } + connectRSPAMD(); + $(document).ajaxStart(function () { + $('#navBar').addClass('loading'); + }); + $(document).ajaxComplete(function () { + $('#navBar').removeClass('loading'); + }); + $('#status_nav').bind('click', function (e) { + getChart(); + }); + }); +})(); diff --git a/interface/plugins.txt b/interface/plugins.txt new file mode 100644 index 000000000..54c7285b9 --- /dev/null +++ b/interface/plugins.txt @@ -0,0 +1,2 @@ +https://github.com/valums/file-uploader/ +https://github.com/flot/flot
\ No newline at end of file diff --git a/interface/react-index.html b/interface/react-index.html new file mode 100644 index 000000000..0cd26d805 --- /dev/null +++ b/interface/react-index.html @@ -0,0 +1,18 @@ +<html lang="en"> +<head> + <meta charset="utf-8"> + <title>RSPAMD Admin</title> + <meta name="viewport" content="width=device-width, initial-scale=1.0"> + <meta name="description" content=""> + <meta name="author" content=""> + <link href="./css/fineuploader.min.css" rel="stylesheet"> + <link href="./css/bootstrap.min.css" rel="stylesheet"> + <link href="./css/rspamd.css" rel="stylesheet"> +</head> + +<body> + <script src="./js/jquery-2.1.4.min.js"></script> + <script src="./js/bootstrap.min.js"></script> + <script src="bundle.js"></script> +</body> +</hml> |
