12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030203120322033203420352036203720382039204020412042204320442045204620472048204920502051205220532054205520562057205820592060206120622063206420652066206720682069207020712072207320742075207620772078207920802081208220832084208520862087208820892090209120922093209420952096209720982099210021012102210321042105210621072108210921102111211221132114211521162117211821192120212121222123212421252126212721282129213021312132213321342135213621372138213921402141214221432144214521462147214821492150215121522153215421552156215721582159216021612162216321642165216621672168216921702171217221732174217521762177217821792180218121822183218421852186218721882189219021912192219321942195219621972198219922002201220222032204220522062207220822092210221122122213221422152216221722182219222022212222222322242225222622272228222922302231223222332234223522362237223822392240224122422243224422452246224722482249225022512252225322542255225622572258225922602261226222632264226522662267226822692270227122722273227422752276227722782279228022812282228322842285228622872288228922902291229222932294229522962297229822992300230123022303230423052306230723082309231023112312231323142315231623172318231923202321232223232324232523262327232823292330233123322333233423352336233723382339234023412342234323442345234623472348234923502351235223532354235523562357235823592360236123622363236423652366236723682369237023712372237323742375237623772378237923802381238223832384238523862387238823892390239123922393239423952396239723982399240024012402240324042405240624072408240924102411241224132414241524162417241824192420242124222423242424252426242724282429243024312432243324342435243624372438243924402441244224432444244524462447244824492450245124522453245424552456245724582459246024612462246324642465246624672468246924702471247224732474247524762477247824792480248124822483248424852486248724882489249024912492249324942495249624972498249925002501250225032504250525062507250825092510251125122513251425152516251725182519252025212522252325242525252625272528252925302531253225332534253525362537253825392540254125422543254425452546254725482549255025512552255325542555255625572558255925602561256225632564256525662567256825692570257125722573257425752576257725782579258025812582258325842585258625872588258925902591259225932594259525962597259825992600260126022603260426052606260726082609261026112612261326142615261626172618261926202621262226232624262526262627262826292630263126322633263426352636263726382639264026412642264326442645264626472648264926502651265226532654265526562657265826592660266126622663266426652666266726682669267026712672267326742675267626772678267926802681268226832684268526862687268826892690269126922693269426952696269726982699270027012702270327042705270627072708270927102711271227132714271527162717271827192720272127222723272427252726272727282729273027312732273327342735273627372738273927402741274227432744274527462747274827492750275127522753275427552756275727582759276027612762276327642765276627672768276927702771277227732774277527762777277827792780278127822783 |
- /* GRegex -- regular expression API wrapper around PCRE.
- *
- * Copyright (C) 1999, 2000 Scott Wimer
- * Copyright (C) 2004, Matthias Clasen <mclasen@redhat.com>
- * Copyright (C) 2005 - 2007, Marco Barisione <marco@barisione.org>
- *
- * This library is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation; either
- * version 2.1 of the License, or (at your option) any later version.
- *
- * This library is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with this library; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- */
-
- #include "config.h"
-
- #include <string.h>
-
- #include "glib.h"
- #include "gregex.h"
- #include <pcre.h>
-
-
- /* PCRE 7.3 does not contain the definition of PCRE_ERROR_NULLWSLIMIT */
- #ifndef PCRE_ERROR_NULLWSLIMIT
- #define PCRE_ERROR_NULLWSLIMIT (-22)
- #endif
-
- /* Mask of all the possible values for GRegexCompileFlags. */
- #define G_REGEX_COMPILE_MASK (G_REGEX_CASELESS | \
- G_REGEX_MULTILINE | \
- G_REGEX_DOTALL | \
- G_REGEX_EXTENDED | \
- G_REGEX_ANCHORED | \
- G_REGEX_DOLLAR_ENDONLY | \
- G_REGEX_UNGREEDY | \
- G_REGEX_RAW | \
- G_REGEX_NO_AUTO_CAPTURE | \
- G_REGEX_OPTIMIZE | \
- G_REGEX_DUPNAMES | \
- G_REGEX_NEWLINE_CR | \
- G_REGEX_NEWLINE_LF | \
- G_REGEX_NEWLINE_CRLF)
-
- /* Mask of all the possible values for GRegexMatchFlags. */
- #define G_REGEX_MATCH_MASK (G_REGEX_MATCH_ANCHORED | \
- G_REGEX_MATCH_NOTBOL | \
- G_REGEX_MATCH_NOTEOL | \
- G_REGEX_MATCH_NOTEMPTY | \
- G_REGEX_MATCH_PARTIAL | \
- G_REGEX_MATCH_NEWLINE_CR | \
- G_REGEX_MATCH_NEWLINE_LF | \
- G_REGEX_MATCH_NEWLINE_CRLF | \
- G_REGEX_MATCH_NEWLINE_ANY)
-
- /* if the string is in UTF-8 use g_utf8_ functions, else use
- * use just +/- 1. */
- #define NEXT_CHAR(re, s) (((re)->compile_opts & PCRE_UTF8) ? \
- g_utf8_next_char (s) : \
- ((s) + 1))
- #define PREV_CHAR(re, s) (((re)->compile_opts & PCRE_UTF8) ? \
- g_utf8_prev_char (s) : \
- ((s) - 1))
-
- struct _GMatchInfo
- {
- GRegex *regex; /* the regex */
- GRegexMatchFlags match_opts; /* options used at match time on the regex */
- gint matches; /* number of matching sub patterns */
- gint pos; /* position in the string where last match left off */
- gint *offsets; /* array of offsets paired 0,1 ; 2,3 ; 3,4 etc */
- gint n_offsets; /* number of offsets */
- gint *workspace; /* workspace for pcre_dfa_exec() */
- gint n_workspace; /* number of workspace elements */
- const gchar *string; /* string passed to the match function */
- gssize string_len; /* length of string */
- };
-
- struct _GRegex
- {
- volatile gint ref_count; /* the ref count for the immutable part */
- gchar *pattern; /* the pattern */
- pcre *pcre_re; /* compiled form of the pattern */
- GRegexCompileFlags compile_opts; /* options used at compile time on the pattern */
- GRegexMatchFlags match_opts; /* options used at match time on the regex */
- pcre_extra *extra; /* data stored when G_REGEX_OPTIMIZE is used */
- };
-
- /* TRUE if ret is an error code, FALSE otherwise. */
- #define IS_PCRE_ERROR(ret) ((ret) < PCRE_ERROR_NOMATCH && (ret) != PCRE_ERROR_PARTIAL)
-
- typedef struct _InterpolationData InterpolationData;
- static gboolean interpolation_list_needs_match (GList *list);
- static gboolean interpolate_replacement (const GMatchInfo *match_info,
- GString *result,
- gpointer data);
- static GList *split_replacement (const gchar *replacement,
- GError **error);
- static void free_interpolation_data (InterpolationData *data);
-
-
- static const gchar *
- match_error (gint errcode)
- {
- switch (errcode)
- {
- case PCRE_ERROR_NOMATCH:
- /* not an error */
- break;
- case PCRE_ERROR_NULL:
- /* NULL argument, this should not happen in GRegex */
- g_warning ("A NULL argument was passed to PCRE");
- break;
- case PCRE_ERROR_BADOPTION:
- return "bad options";
- case PCRE_ERROR_BADMAGIC:
- return "corrupted object";
- case PCRE_ERROR_NOMEMORY:
- return "out of memory";
- case PCRE_ERROR_NOSUBSTRING:
- /* not used by pcre_exec() */
- break;
- case PCRE_ERROR_MATCHLIMIT:
- return "backtracking limit reached";
- case PCRE_ERROR_CALLOUT:
- /* callouts are not implemented */
- break;
- case PCRE_ERROR_BADUTF8:
- case PCRE_ERROR_BADUTF8_OFFSET:
- /* we do not check if strings are valid */
- break;
- case PCRE_ERROR_PARTIAL:
- /* not an error */
- break;
- case PCRE_ERROR_BADPARTIAL:
- return "the pattern contains items not supported for partial matching";
- case PCRE_ERROR_INTERNAL:
- return "internal error";
- case PCRE_ERROR_BADCOUNT:
- /* negative ovecsize, this should not happen in GRegex */
- g_warning ("A negative ovecsize was passed to PCRE");
- break;
- case PCRE_ERROR_DFA_UITEM:
- return "the pattern contains items not supported for partial matching";
- case PCRE_ERROR_DFA_UCOND:
- return "back references as conditions are not supported for partial matching";
- case PCRE_ERROR_DFA_UMLIMIT:
- /* the match_field field is not used in GRegex */
- break;
- case PCRE_ERROR_DFA_WSSIZE:
- /* handled expanding the workspace */
- break;
- case PCRE_ERROR_DFA_RECURSE:
- case PCRE_ERROR_RECURSIONLIMIT:
- return "recursion limit reached";
- case PCRE_ERROR_NULLWSLIMIT:
- return "workspace limit for empty substrings reached";
- default:
- break;
- }
- return "unknown error";
- }
-
- static void
- translate_compile_error (gint *errcode, const gchar **errmsg)
- {
- /* Compile errors are created adding 100 to the error code returned
- * by PCRE.
- * If errcode is known we put the translatable error message in
- * erromsg. If errcode is unknown we put the generic
- * G_REGEX_ERROR_COMPILE error code in errcode and keep the
- * untranslated error message returned by PCRE.
- * Note that there can be more PCRE errors with the same GRegexError
- * and that some PCRE errors are useless for us.
- */
- *errcode += 100;
-
- switch (*errcode)
- {
- case G_REGEX_ERROR_STRAY_BACKSLASH:
- *errmsg = "\\ at end of pattern";
- break;
- case G_REGEX_ERROR_MISSING_CONTROL_CHAR:
- *errmsg = "\\c at end of pattern";
- break;
- case G_REGEX_ERROR_UNRECOGNIZED_ESCAPE:
- *errmsg = "unrecognized character follows \\";
- break;
- case 137:
- /* A number of Perl escapes are not handled by PCRE.
- * Therefore it explicitly raises ERR37.
- */
- *errcode = G_REGEX_ERROR_UNRECOGNIZED_ESCAPE;
- *errmsg = "case-changing escapes (\\l, \\L, \\u, \\U) are not allowed here";
- break;
- case G_REGEX_ERROR_QUANTIFIERS_OUT_OF_ORDER:
- *errmsg = "numbers out of order in {} quantifier";
- break;
- case G_REGEX_ERROR_QUANTIFIER_TOO_BIG:
- *errmsg = "number too big in {} quantifier";
- break;
- case G_REGEX_ERROR_UNTERMINATED_CHARACTER_CLASS:
- *errmsg = "missing terminating ] for character class";
- break;
- case G_REGEX_ERROR_INVALID_ESCAPE_IN_CHARACTER_CLASS:
- *errmsg = "invalid escape sequence in character class";
- break;
- case G_REGEX_ERROR_RANGE_OUT_OF_ORDER:
- *errmsg = "range out of order in character class";
- break;
- case G_REGEX_ERROR_NOTHING_TO_REPEAT:
- *errmsg = "nothing to repeat";
- break;
- case G_REGEX_ERROR_UNRECOGNIZED_CHARACTER:
- *errmsg = "unrecognized character after (?";
- break;
- case 124:
- *errcode = G_REGEX_ERROR_UNRECOGNIZED_CHARACTER;
- *errmsg = "unrecognized character after (?<";
- break;
- case 141:
- *errcode = G_REGEX_ERROR_UNRECOGNIZED_CHARACTER;
- *errmsg = "unrecognized character after (?P";
- break;
- case G_REGEX_ERROR_POSIX_NAMED_CLASS_OUTSIDE_CLASS:
- *errmsg = "POSIX named classes are supported only within a class";
- break;
- case G_REGEX_ERROR_UNMATCHED_PARENTHESIS:
- *errmsg = "missing terminating )";
- break;
- case 122:
- *errcode = G_REGEX_ERROR_UNMATCHED_PARENTHESIS;
- *errmsg = ") without opening (";
- break;
- case 129:
- *errcode = G_REGEX_ERROR_UNMATCHED_PARENTHESIS;
- /* translators: '(?R' and '(?[+-]digits' are both meant as (groups of)
- * sequences here, '(?-54' would be an example for the second group.
- */
- *errmsg = "(?R or (?[+-]digits must be followed by )";
- break;
- case G_REGEX_ERROR_INEXISTENT_SUBPATTERN_REFERENCE:
- *errmsg = "reference to non-existent subpattern";
- break;
- case G_REGEX_ERROR_UNTERMINATED_COMMENT:
- *errmsg = "missing ) after comment";
- break;
- case G_REGEX_ERROR_EXPRESSION_TOO_LARGE:
- *errmsg = "regular expression too large";
- break;
- case G_REGEX_ERROR_MEMORY_ERROR:
- *errmsg = "failed to get memory";
- break;
- case G_REGEX_ERROR_VARIABLE_LENGTH_LOOKBEHIND:
- *errmsg = "lookbehind assertion is not fixed length";
- break;
- case G_REGEX_ERROR_MALFORMED_CONDITION:
- *errmsg = "malformed number or name after (?(";
- break;
- case G_REGEX_ERROR_TOO_MANY_CONDITIONAL_BRANCHES:
- *errmsg = "conditional group contains more than two branches";
- break;
- case G_REGEX_ERROR_ASSERTION_EXPECTED:
- *errmsg = "assertion expected after (?(";
- break;
- case G_REGEX_ERROR_UNKNOWN_POSIX_CLASS_NAME:
- *errmsg = "unknown POSIX class name";
- break;
- case G_REGEX_ERROR_POSIX_COLLATING_ELEMENTS_NOT_SUPPORTED:
- *errmsg = "POSIX collating elements are not supported";
- break;
- case G_REGEX_ERROR_HEX_CODE_TOO_LARGE:
- *errmsg = "character value in \\x{...} sequence is too large";
- break;
- case G_REGEX_ERROR_INVALID_CONDITION:
- *errmsg = "invalid condition (?(0)";
- break;
- case G_REGEX_ERROR_SINGLE_BYTE_MATCH_IN_LOOKBEHIND:
- *errmsg = "\\C not allowed in lookbehind assertion";
- break;
- case G_REGEX_ERROR_INFINITE_LOOP:
- *errmsg = "recursive call could loop indefinitely";
- break;
- case G_REGEX_ERROR_MISSING_SUBPATTERN_NAME_TERMINATOR:
- *errmsg = "missing terminator in subpattern name";
- break;
- case G_REGEX_ERROR_DUPLICATE_SUBPATTERN_NAME:
- *errmsg = "two named subpatterns have the same name";
- break;
- case G_REGEX_ERROR_MALFORMED_PROPERTY:
- *errmsg = "malformed \\P or \\p sequence";
- break;
- case G_REGEX_ERROR_UNKNOWN_PROPERTY:
- *errmsg = "unknown property name after \\P or \\p";
- break;
- case G_REGEX_ERROR_SUBPATTERN_NAME_TOO_LONG:
- *errmsg = "subpattern name is too long (maximum 32 characters)";
- break;
- case G_REGEX_ERROR_TOO_MANY_SUBPATTERNS:
- *errmsg = "too many named subpatterns (maximum 10,000)";
- break;
- case G_REGEX_ERROR_INVALID_OCTAL_VALUE:
- *errmsg = "octal value is greater than \\377";
- break;
- case G_REGEX_ERROR_TOO_MANY_BRANCHES_IN_DEFINE:
- *errmsg = "DEFINE group contains more than one branch";
- break;
- case G_REGEX_ERROR_DEFINE_REPETION:
- *errmsg = "repeating a DEFINE group is not allowed";
- break;
- case G_REGEX_ERROR_INCONSISTENT_NEWLINE_OPTIONS:
- *errmsg = "inconsistent NEWLINE options";
- break;
- case G_REGEX_ERROR_MISSING_BACK_REFERENCE:
- *errmsg = "\\g is not followed by a braced name or an optionally "
- "braced non-zero number";
- break;
- case 11:
- *errcode = G_REGEX_ERROR_INTERNAL;
- *errmsg = "unexpected repeat";
- break;
- case 23:
- *errcode = G_REGEX_ERROR_INTERNAL;
- *errmsg = "code overflow";
- break;
- case 52:
- *errcode = G_REGEX_ERROR_INTERNAL;
- *errmsg = "overran compiling workspace";
- break;
- case 53:
- *errcode = G_REGEX_ERROR_INTERNAL;
- *errmsg = "previously-checked referenced subpattern not found";
- break;
- case 16:
- /* This should not happen as we never pass a NULL erroffset */
- g_warning ("erroffset passed as NULL");
- *errcode = G_REGEX_ERROR_COMPILE;
- break;
- case 17:
- /* This should not happen as we check options before passing them
- * to pcre_compile2() */
- g_warning ("unknown option bit(s) set");
- *errcode = G_REGEX_ERROR_COMPILE;
- break;
- case 32:
- case 44:
- case 45:
- /* These errors should not happen as we are using an UTF8-enabled PCRE
- * and we do not check if strings are valid */
- g_warning ("%s", *errmsg);
- *errcode = G_REGEX_ERROR_COMPILE;
- break;
- default:
- *errcode = G_REGEX_ERROR_COMPILE;
- }
- }
-
- /* GMatchInfo */
-
- static GMatchInfo *
- match_info_new (const GRegex *regex,
- const gchar *string,
- gint string_len,
- gint start_position,
- gint match_options,
- gboolean is_dfa)
- {
- GMatchInfo *match_info;
-
- if (string_len < 0)
- string_len = strlen (string);
-
- match_info = g_new0 (GMatchInfo, 1);
- match_info->regex = g_regex_ref ((GRegex *)regex);
- match_info->string = string;
- match_info->string_len = string_len;
- match_info->matches = PCRE_ERROR_NOMATCH;
- match_info->pos = start_position;
- match_info->match_opts = match_options;
-
- if (is_dfa)
- {
- /* These values should be enough for most cases, if they are not
- * enough g_regex_match_all_full() will expand them. */
- match_info->n_offsets = 24;
- match_info->n_workspace = 100;
- match_info->workspace = g_new (gint, match_info->n_workspace);
- }
- else
- {
- gint capture_count;
- pcre_fullinfo (regex->pcre_re, regex->extra,
- PCRE_INFO_CAPTURECOUNT, &capture_count);
- match_info->n_offsets = (capture_count + 1) * 3;
- }
-
- match_info->offsets = g_new0 (gint, match_info->n_offsets);
- /* Set an invalid position for the previous match. */
- match_info->offsets[0] = -1;
- match_info->offsets[1] = -1;
-
- return match_info;
- }
-
- /**
- * g_match_info_get_regex:
- * @match_info: a #GMatchInfo
- *
- * Returns #GRegex object used in @match_info. It belongs to Glib
- * and must not be freed. Use g_regex_ref() if you need to keep it
- * after you free @match_info object.
- *
- * Returns: #GRegex object used in @match_info
- *
- * Since: 2.14
- */
- GRegex *
- g_match_info_get_regex (const GMatchInfo *match_info)
- {
- g_return_val_if_fail (match_info != NULL, NULL);
- return match_info->regex;
- }
-
- /**
- * g_match_info_get_string:
- * @match_info: a #GMatchInfo
- *
- * Returns the string searched with @match_info. This is the
- * string passed to g_regex_match() or g_regex_replace() so
- * you may not free it before calling this function.
- *
- * Returns: the string searched with @match_info
- *
- * Since: 2.14
- */
- const gchar *
- g_match_info_get_string (const GMatchInfo *match_info)
- {
- g_return_val_if_fail (match_info != NULL, NULL);
- return match_info->string;
- }
-
- /**
- * g_match_info_free:
- * @match_info: a #GMatchInfo
- *
- * Frees all the memory associated with the #GMatchInfo structure.
- *
- * Since: 2.14
- */
- void
- g_match_info_free (GMatchInfo *match_info)
- {
- if (match_info)
- {
- g_regex_unref (match_info->regex);
- g_free (match_info->offsets);
- g_free (match_info->workspace);
- g_free (match_info);
- }
- }
-
- /**
- * g_match_info_next:
- * @match_info: a #GMatchInfo structure
- * @error: location to store the error occuring, or %NULL to ignore errors
- *
- * Scans for the next match using the same parameters of the previous
- * call to g_regex_match_full() or g_regex_match() that returned
- * @match_info.
- *
- * The match is done on the string passed to the match function, so you
- * cannot free it before calling this function.
- *
- * Returns: %TRUE is the string matched, %FALSE otherwise
- *
- * Since: 2.14
- */
- gboolean
- g_match_info_next (GMatchInfo *match_info,
- GError **error)
- {
- gint prev_match_start;
- gint prev_match_end;
-
- g_return_val_if_fail (match_info != NULL, FALSE);
- g_return_val_if_fail (error == NULL || *error == NULL, FALSE);
- g_return_val_if_fail (match_info->pos >= 0, FALSE);
-
- prev_match_start = match_info->offsets[0];
- prev_match_end = match_info->offsets[1];
-
- match_info->matches = pcre_exec (match_info->regex->pcre_re,
- match_info->regex->extra,
- match_info->string,
- match_info->string_len,
- match_info->pos,
- match_info->regex->match_opts | match_info->match_opts,
- match_info->offsets,
- match_info->n_offsets);
- if (IS_PCRE_ERROR (match_info->matches))
- {
- g_set_error (error, G_REGEX_ERROR, G_REGEX_ERROR_MATCH,
- "Error while matching regular expression %s: %s",
- match_info->regex->pattern, match_error (match_info->matches));
- return FALSE;
- }
-
- /* avoid infinite loops if the pattern is an empty string or something
- * equivalent */
- if (match_info->pos == match_info->offsets[1])
- {
- if (match_info->pos > match_info->string_len)
- {
- /* we have reached the end of the string */
- match_info->pos = -1;
- match_info->matches = PCRE_ERROR_NOMATCH;
- return FALSE;
- }
-
- match_info->pos = NEXT_CHAR (match_info->regex,
- &match_info->string[match_info->pos]) -
- match_info->string;
- }
- else
- {
- match_info->pos = match_info->offsets[1];
- }
-
- /* it's possibile to get two identical matches when we are matching
- * empty strings, for instance if the pattern is "(?=[A-Z0-9])" and
- * the string is "RegExTest" we have:
- * - search at position 0: match from 0 to 0
- * - search at position 1: match from 3 to 3
- * - search at position 3: match from 3 to 3 (duplicate)
- * - search at position 4: match from 5 to 5
- * - search at position 5: match from 5 to 5 (duplicate)
- * - search at position 6: no match -> stop
- * so we have to ignore the duplicates.
- * see bug #515944: http://bugzilla.gnome.org/show_bug.cgi?id=515944 */
- if (match_info->matches >= 0 &&
- prev_match_start == match_info->offsets[0] &&
- prev_match_end == match_info->offsets[1])
- {
- /* ignore this match and search the next one */
- return g_match_info_next (match_info, error);
- }
-
- return match_info->matches >= 0;
- }
-
- /**
- * g_match_info_matches:
- * @match_info: a #GMatchInfo structure
- *
- * Returns whether the previous match operation succeeded.
- *
- * Returns: %TRUE if the previous match operation succeeded,
- * %FALSE otherwise
- *
- * Since: 2.14
- */
- gboolean
- g_match_info_matches (const GMatchInfo *match_info)
- {
- g_return_val_if_fail (match_info != NULL, FALSE);
-
- return match_info->matches >= 0;
- }
-
- /**
- * g_match_info_get_match_count:
- * @match_info: a #GMatchInfo structure
- *
- * Retrieves the number of matched substrings (including substring 0,
- * that is the whole matched text), so 1 is returned if the pattern
- * has no substrings in it and 0 is returned if the match failed.
- *
- * If the last match was obtained using the DFA algorithm, that is
- * using g_regex_match_all() or g_regex_match_all_full(), the retrieved
- * count is not that of the number of capturing parentheses but that of
- * the number of matched substrings.
- *
- * Returns: Number of matched substrings, or -1 if an error occurred
- *
- * Since: 2.14
- */
- gint
- g_match_info_get_match_count (const GMatchInfo *match_info)
- {
- g_return_val_if_fail (match_info, -1);
-
- if (match_info->matches == PCRE_ERROR_NOMATCH)
- /* no match */
- return 0;
- else if (match_info->matches < PCRE_ERROR_NOMATCH)
- /* error */
- return -1;
- else
- /* match */
- return match_info->matches;
- }
-
- /**
- * g_match_info_is_partial_match:
- * @match_info: a #GMatchInfo structure
- *
- * Usually if the string passed to g_regex_match*() matches as far as
- * it goes, but is too short to match the entire pattern, %FALSE is
- * returned. There are circumstances where it might be helpful to
- * distinguish this case from other cases in which there is no match.
- *
- * Consider, for example, an application where a human is required to
- * type in data for a field with specific formatting requirements. An
- * example might be a date in the form ddmmmyy, defined by the pattern
- * "^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$".
- * If the application sees the user’s keystrokes one by one, and can
- * check that what has been typed so far is potentially valid, it is
- * able to raise an error as soon as a mistake is made.
- *
- * GRegex supports the concept of partial matching by means of the
- * #G_REGEX_MATCH_PARTIAL flag. When this is set the return code for
- * g_regex_match() or g_regex_match_full() is, as usual, %TRUE
- * for a complete match, %FALSE otherwise. But, when these functions
- * return %FALSE, you can check if the match was partial calling
- * g_match_info_is_partial_match().
- *
- * When using partial matching you cannot use g_match_info_fetch*().
- *
- * Because of the way certain internal optimizations are implemented
- * the partial matching algorithm cannot be used with all patterns.
- * So repeated single characters such as "a{2,4}" and repeated single
- * meta-sequences such as "\d+" are not permitted if the maximum number
- * of occurrences is greater than one. Optional items such as "\d?"
- * (where the maximum is one) are permitted. Quantifiers with any values
- * are permitted after parentheses, so the invalid examples above can be
- * coded thus "(a){2,4}" and "(\d)+". If #G_REGEX_MATCH_PARTIAL is set
- * for a pattern that does not conform to the restrictions, matching
- * functions return an error.
- *
- * Returns: %TRUE if the match was partial, %FALSE otherwise
- *
- * Since: 2.14
- */
- gboolean
- g_match_info_is_partial_match (const GMatchInfo *match_info)
- {
- g_return_val_if_fail (match_info != NULL, FALSE);
-
- return match_info->matches == PCRE_ERROR_PARTIAL;
- }
-
- /**
- * g_match_info_expand_references:
- * @match_info: a #GMatchInfo or %NULL
- * @string_to_expand: the string to expand
- * @error: location to store the error occuring, or %NULL to ignore errors
- *
- * Returns a new string containing the text in @string_to_expand with
- * references and escape sequences expanded. References refer to the last
- * match done with @string against @regex and have the same syntax used by
- * g_regex_replace().
- *
- * The @string_to_expand must be UTF-8 encoded even if #G_REGEX_RAW was
- * passed to g_regex_new().
- *
- * The backreferences are extracted from the string passed to the match
- * function, so you cannot call this function after freeing the string.
- *
- * @match_info may be %NULL in which case @string_to_expand must not
- * contain references. For instance "foo\n" does not refer to an actual
- * pattern and '\n' merely will be replaced with \n character,
- * while to expand "\0" (whole match) one needs the result of a match.
- * Use g_regex_check_replacement() to find out whether @string_to_expand
- * contains references.
- *
- * Returns: the expanded string, or %NULL if an error occurred
- *
- * Since: 2.14
- */
- gchar *
- g_match_info_expand_references (const GMatchInfo *match_info,
- const gchar *string_to_expand,
- GError **error)
- {
- GString *result;
- GList *list;
- GError *tmp_error = NULL;
-
- g_return_val_if_fail (string_to_expand != NULL, NULL);
- g_return_val_if_fail (error == NULL || *error == NULL, NULL);
-
- list = split_replacement (string_to_expand, &tmp_error);
- if (tmp_error != NULL)
- {
- g_propagate_error (error, tmp_error);
- return NULL;
- }
-
- if (!match_info && interpolation_list_needs_match (list))
- {
- g_critical ("String '%s' contains references to the match, can't "
- "expand references without GMatchInfo object",
- string_to_expand);
- return NULL;
- }
-
- result = g_string_sized_new (strlen (string_to_expand));
- interpolate_replacement (match_info, result, list);
-
- g_list_foreach (list, (GFunc)free_interpolation_data, NULL);
- g_list_free (list);
-
- return g_string_free (result, FALSE);
- }
-
- /**
- * g_match_info_fetch:
- * @match_info: #GMatchInfo structure
- * @match_num: number of the sub expression
- *
- * Retrieves the text matching the @match_num<!-- -->'th capturing
- * parentheses. 0 is the full text of the match, 1 is the first paren
- * set, 2 the second, and so on.
- *
- * If @match_num is a valid sub pattern but it didn't match anything
- * (e.g. sub pattern 1, matching "b" against "(a)?b") then an empty
- * string is returned.
- *
- * If the match was obtained using the DFA algorithm, that is using
- * g_regex_match_all() or g_regex_match_all_full(), the retrieved
- * string is not that of a set of parentheses but that of a matched
- * substring. Substrings are matched in reverse order of length, so
- * 0 is the longest match.
- *
- * The string is fetched from the string passed to the match function,
- * so you cannot call this function after freeing the string.
- *
- * Returns: The matched substring, or %NULL if an error occurred.
- * You have to free the string yourself
- *
- * Since: 2.14
- */
- gchar *
- g_match_info_fetch (const GMatchInfo *match_info,
- gint match_num)
- {
- /* we cannot use pcre_get_substring() because it allocates the
- * string using pcre_malloc(). */
- gchar *match = NULL;
- gint start, end;
-
- g_return_val_if_fail (match_info != NULL, NULL);
- g_return_val_if_fail (match_num >= 0, NULL);
-
- /* match_num does not exist or it didn't matched, i.e. matching "b"
- * against "(a)?b" then group 0 is empty. */
- if (!g_match_info_fetch_pos (match_info, match_num, &start, &end))
- match = NULL;
- else if (start == -1)
- match = g_strdup ("");
- else
- match = g_strndup (&match_info->string[start], end - start);
-
- return match;
- }
-
- /**
- * g_match_info_fetch_pos:
- * @match_info: #GMatchInfo structure
- * @match_num: number of the sub expression
- * @start_pos: pointer to location where to store the start position
- * @end_pos: pointer to location where to store the end position
- *
- * Retrieves the position in bytes of the @match_num<!-- -->'th capturing
- * parentheses. 0 is the full text of the match, 1 is the first
- * paren set, 2 the second, and so on.
- *
- * If @match_num is a valid sub pattern but it didn't match anything
- * (e.g. sub pattern 1, matching "b" against "(a)?b") then @start_pos
- * and @end_pos are set to -1 and %TRUE is returned.
- *
- * If the match was obtained using the DFA algorithm, that is using
- * g_regex_match_all() or g_regex_match_all_full(), the retrieved
- * position is not that of a set of parentheses but that of a matched
- * substring. Substrings are matched in reverse order of length, so
- * 0 is the longest match.
- *
- * Returns: %TRUE if the position was fetched, %FALSE otherwise. If
- * the position cannot be fetched, @start_pos and @end_pos are left
- * unchanged
- *
- * Since: 2.14
- */
- gboolean
- g_match_info_fetch_pos (const GMatchInfo *match_info,
- gint match_num,
- gint *start_pos,
- gint *end_pos)
- {
- g_return_val_if_fail (match_info != NULL, FALSE);
- g_return_val_if_fail (match_num >= 0, FALSE);
-
- /* make sure the sub expression number they're requesting is less than
- * the total number of sub expressions that were matched. */
- if (match_num >= match_info->matches)
- return FALSE;
-
- if (start_pos != NULL)
- *start_pos = match_info->offsets[2 * match_num];
-
- if (end_pos != NULL)
- *end_pos = match_info->offsets[2 * match_num + 1];
-
- return TRUE;
- }
-
- static gint
- int_pcre_get_stringtable_entries(const pcre *code, const gchar *stringname,
- gchar **firstptr, gchar **lastptr)
- {
- gint rc;
- gint entrysize;
- gint top, bot;
- guchar *nametable, *lastentry;
-
- if ((rc = pcre_fullinfo (code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0)
- return rc;
- if (top <= 0)
- return PCRE_ERROR_NOSUBSTRING;
-
- if ((rc = pcre_fullinfo (code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize))
- != 0)
- return rc;
- if ((rc = pcre_fullinfo (code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0)
- return rc;
-
- lastentry = nametable + entrysize * (top - 1);
- bot = 0;
- while (top > bot)
- {
- int mid = (top + bot) / 2;
- char *entry = nametable + entrysize * mid;
- int c = strcmp (stringname, (char *) (entry + 2));
- if (c == 0) {
- char *first = entry;
- char *last = entry;
- while (first > nametable) {
- if (strcmp (stringname, (char *) (first - entrysize + 2)) != 0)break
- ; first -= entrysize;
- }
- while (last < lastentry) {
- if (strcmp (stringname, (char *) (last + entrysize + 2)) != 0)break
- ; last += entrysize;
- }
- *firstptr = (char *) first;
- *lastptr = (char *) last;
- return entrysize;
- }
- if (c > 0)
- bot = mid + 1;
- else
- top = mid;
- }
-
- return PCRE_ERROR_NOSUBSTRING;
- }
-
- /*
- * Returns number of first matched subpattern with name @name.
- * There may be more than one in case when DUPNAMES is used,
- * and not all subpatterns with that name match;
- * pcre_get_stringnumber() does not work in that case.
- */
- static gint
- get_matched_substring_number (const GMatchInfo *match_info,
- const gchar *name)
- {
- gint entrysize;
- gchar *first, *last;
- guchar *entry;
-
- if (!(match_info->regex->compile_opts & G_REGEX_DUPNAMES))
- return pcre_get_stringnumber (match_info->regex->pcre_re, name);
-
- /* This code is copied from pcre_get.c: get_first_set() */
- entrysize = int_pcre_get_stringtable_entries (match_info->regex->pcre_re,
- name,
- &first,
- &last);
-
- if (entrysize <= 0)
- return entrysize;
-
- for (entry = (guchar*) first; entry <= (guchar*) last; entry += entrysize)
- {
- gint n = (entry[0] << 8) + entry[1];
- if (match_info->offsets[n*2] >= 0)
- return n;
- }
-
- return (first[0] << 8) + first[1];
- }
-
- /**
- * g_match_info_fetch_named:
- * @match_info: #GMatchInfo structure
- * @name: name of the subexpression
- *
- * Retrieves the text matching the capturing parentheses named @name.
- *
- * If @name is a valid sub pattern name but it didn't match anything
- * (e.g. sub pattern "X", matching "b" against "(?P<X>a)?b")
- * then an empty string is returned.
- *
- * The string is fetched from the string passed to the match function,
- * so you cannot call this function after freeing the string.
- *
- * Returns: The matched substring, or %NULL if an error occurred.
- * You have to free the string yourself
- *
- * Since: 2.14
- */
- gchar *
- g_match_info_fetch_named (const GMatchInfo *match_info,
- const gchar *name)
- {
- /* we cannot use pcre_get_named_substring() because it allocates the
- * string using pcre_malloc(). */
- gint num;
-
- g_return_val_if_fail (match_info != NULL, NULL);
- g_return_val_if_fail (name != NULL, NULL);
-
- num = get_matched_substring_number (match_info, name);
- if (num < 0)
- return NULL;
- else
- return g_match_info_fetch (match_info, num);
- }
-
- /**
- * g_match_info_fetch_named_pos:
- * @match_info: #GMatchInfo structure
- * @name: name of the subexpression
- * @start_pos: pointer to location where to store the start position
- * @end_pos: pointer to location where to store the end position
- *
- * Retrieves the position in bytes of the capturing parentheses named @name.
- *
- * If @name is a valid sub pattern name but it didn't match anything
- * (e.g. sub pattern "X", matching "b" against "(?P<X>a)?b")
- * then @start_pos and @end_pos are set to -1 and %TRUE is returned.
- *
- * Returns: %TRUE if the position was fetched, %FALSE otherwise. If
- * the position cannot be fetched, @start_pos and @end_pos are left
- * unchanged
- *
- * Since: 2.14
- */
- gboolean
- g_match_info_fetch_named_pos (const GMatchInfo *match_info,
- const gchar *name,
- gint *start_pos,
- gint *end_pos)
- {
- gint num;
-
- g_return_val_if_fail (match_info != NULL, FALSE);
- g_return_val_if_fail (name != NULL, FALSE);
-
- num = get_matched_substring_number (match_info, name);
- if (num < 0)
- return FALSE;
-
- return g_match_info_fetch_pos (match_info, num, start_pos, end_pos);
- }
-
- /**
- * g_match_info_fetch_all:
- * @match_info: a #GMatchInfo structure
- *
- * Bundles up pointers to each of the matching substrings from a match
- * and stores them in an array of gchar pointers. The first element in
- * the returned array is the match number 0, i.e. the entire matched
- * text.
- *
- * If a sub pattern didn't match anything (e.g. sub pattern 1, matching
- * "b" against "(a)?b") then an empty string is inserted.
- *
- * If the last match was obtained using the DFA algorithm, that is using
- * g_regex_match_all() or g_regex_match_all_full(), the retrieved
- * strings are not that matched by sets of parentheses but that of the
- * matched substring. Substrings are matched in reverse order of length,
- * so the first one is the longest match.
- *
- * The strings are fetched from the string passed to the match function,
- * so you cannot call this function after freeing the string.
- *
- * Returns: a %NULL-terminated array of gchar * pointers. It must be
- * freed using g_strfreev(). If the previous match failed %NULL is
- * returned
- *
- * Since: 2.14
- */
- gchar **
- g_match_info_fetch_all (const GMatchInfo *match_info)
- {
- /* we cannot use pcre_get_substring_list() because the returned value
- * isn't suitable for g_strfreev(). */
- gchar **result;
- gint i;
-
- g_return_val_if_fail (match_info != NULL, NULL);
-
- if (match_info->matches < 0)
- return NULL;
-
- result = g_new (gchar *, match_info->matches + 1);
- for (i = 0; i < match_info->matches; i++)
- result[i] = g_match_info_fetch (match_info, i);
- result[i] = NULL;
-
- return result;
- }
-
-
- /* GRegex */
-
- GQuark
- g_regex_error_quark (void)
- {
- static GQuark error_quark = 0;
-
- if (error_quark == 0)
- error_quark = g_quark_from_static_string ("g-regex-error-quark");
-
- return error_quark;
- }
-
- /**
- * g_regex_ref:
- * @regex: a #GRegex
- *
- * Increases reference count of @regex by 1.
- *
- * Returns: @regex
- *
- * Since: 2.14
- */
- GRegex *
- g_regex_ref (GRegex *regex)
- {
- g_return_val_if_fail (regex != NULL, NULL);
- g_atomic_int_inc (®ex->ref_count);
- return regex;
- }
-
- /**
- * g_regex_unref:
- * @regex: a #GRegex
- *
- * Decreases reference count of @regex by 1. When reference count drops
- * to zero, it frees all the memory associated with the regex structure.
- *
- * Since: 2.14
- */
- void
- g_regex_unref (GRegex *regex)
- {
- g_return_if_fail (regex != NULL);
-
- if (g_atomic_int_exchange_and_add (®ex->ref_count, -1) - 1 == 0)
- {
- g_free (regex->pattern);
- if (regex->pcre_re != NULL)
- pcre_free (regex->pcre_re);
- if (regex->extra != NULL)
- pcre_free (regex->extra);
- g_free (regex);
- }
- }
-
- /**
- * g_regex_new:
- * @pattern: the regular expression
- * @compile_options: compile options for the regular expression, or 0
- * @match_options: match options for the regular expression, or 0
- * @error: return location for a #GError
- *
- * Compiles the regular expression to an internal form, and does
- * the initial setup of the #GRegex structure.
- *
- * Returns: a #GRegex structure. Call g_regex_unref() when you
- * are done with it
- *
- * Since: 2.14
- */
- GRegex *
- g_regex_new (const gchar *pattern,
- GRegexCompileFlags compile_options,
- GRegexMatchFlags match_options,
- GError **error)
- {
- GRegex *regex;
- pcre *re;
- const gchar *errmsg;
- gint erroffset;
- gint errcode;
- gboolean optimize = FALSE;
- static gboolean initialized = FALSE;
- unsigned long int pcre_compile_options;
-
- g_return_val_if_fail (pattern != NULL, NULL);
- g_return_val_if_fail (error == NULL || *error == NULL, NULL);
- g_return_val_if_fail ((compile_options & ~G_REGEX_COMPILE_MASK) == 0, NULL);
- g_return_val_if_fail ((match_options & ~G_REGEX_MATCH_MASK) == 0, NULL);
-
- if (!initialized)
- {
- gint support;
- const gchar *msg;
-
- pcre_config (PCRE_CONFIG_UTF8, &support);
- if (!support)
- {
- msg = "PCRE library is compiled without UTF8 support";
- g_critical ("%s", msg);
- g_set_error (error, G_REGEX_ERROR, G_REGEX_ERROR_COMPILE, msg);
- return NULL;
- }
-
- pcre_config (PCRE_CONFIG_UNICODE_PROPERTIES, &support);
- if (!support)
- {
- msg = "PCRE library is compiled without UTF8 properties support";
- g_critical ("%s", msg);
- g_set_error (error, G_REGEX_ERROR, G_REGEX_ERROR_COMPILE, msg);
- return NULL;
- }
-
- initialized = TRUE;
- }
-
- /* G_REGEX_OPTIMIZE has the same numeric value of PCRE_NO_UTF8_CHECK,
- * as we do not need to wrap PCRE_NO_UTF8_CHECK. */
- if (compile_options & G_REGEX_OPTIMIZE)
- optimize = TRUE;
-
- /* In GRegex the string are, by default, UTF-8 encoded. PCRE
- * instead uses UTF-8 only if required with PCRE_UTF8. */
- if (compile_options & G_REGEX_RAW)
- {
- /* disable utf-8 */
- compile_options &= ~G_REGEX_RAW;
- }
- else
- {
- /* enable utf-8 */
- compile_options |= PCRE_UTF8 | PCRE_NO_UTF8_CHECK;
- match_options |= PCRE_NO_UTF8_CHECK;
- }
-
- /* PCRE_NEWLINE_ANY is the default for the internal PCRE but
- * not for the system one. */
-
- /* compile the pattern */
- re = pcre_compile2 (pattern, compile_options, &errcode,
- &errmsg, &erroffset, NULL);
-
- /* if the compilation failed, set the error member and return
- * immediately */
- if (re == NULL)
- {
- GError *tmp_error;
-
- /* Translate the PCRE error code to GRegexError and use a translated
- * error message if possible */
- translate_compile_error (&errcode, &errmsg);
-
- /* PCRE uses byte offsets but we want to show character offsets */
- erroffset = g_utf8_pointer_to_offset (pattern, &pattern[erroffset]);
-
- tmp_error = g_error_new (G_REGEX_ERROR, errcode,
- "Error while compiling regular "
- "expression %s at char %d: %s",
- pattern, erroffset, errmsg);
- g_propagate_error (error, tmp_error);
-
- return NULL;
- }
-
- /* For options set at the beginning of the pattern, pcre puts them into
- * compile options, e.g. "(?i)foo" will make the pcre structure store
- * PCRE_CASELESS even though it wasn't explicitly given for compilation. */
- pcre_fullinfo (re, NULL, PCRE_INFO_OPTIONS, &pcre_compile_options);
- compile_options = pcre_compile_options;
-
- regex = g_new0 (GRegex, 1);
- regex->ref_count = 1;
- regex->pattern = g_strdup (pattern);
- regex->pcre_re = re;
- regex->compile_opts = compile_options;
- regex->match_opts = match_options;
-
- if (optimize)
- {
- regex->extra = pcre_study (regex->pcre_re, 0, &errmsg);
- if (errmsg != NULL)
- {
- GError *tmp_error = g_error_new (G_REGEX_ERROR,
- G_REGEX_ERROR_OPTIMIZE,
- "Error while optimizing "
- "regular expression %s: %s",
- regex->pattern,
- errmsg);
- g_propagate_error (error, tmp_error);
-
- g_regex_unref (regex);
- return NULL;
- }
- }
-
- return regex;
- }
-
- /**
- * g_regex_get_pattern:
- * @regex: a #GRegex structure
- *
- * Gets the pattern string associated with @regex, i.e. a copy of
- * the string passed to g_regex_new().
- *
- * Returns: the pattern of @regex
- *
- * Since: 2.14
- */
- const gchar *
- g_regex_get_pattern (const GRegex *regex)
- {
- g_return_val_if_fail (regex != NULL, NULL);
-
- return regex->pattern;
- }
-
- /**
- * g_regex_get_max_backref:
- * @regex: a #GRegex
- *
- * Returns the number of the highest back reference
- * in the pattern, or 0 if the pattern does not contain
- * back references.
- *
- * Returns: the number of the highest back reference
- *
- * Since: 2.14
- */
- gint
- g_regex_get_max_backref (const GRegex *regex)
- {
- gint value;
-
- pcre_fullinfo (regex->pcre_re, regex->extra,
- PCRE_INFO_BACKREFMAX, &value);
-
- return value;
- }
-
- /**
- * g_regex_get_capture_count:
- * @regex: a #GRegex
- *
- * Returns the number of capturing subpatterns in the pattern.
- *
- * Returns: the number of capturing subpatterns
- *
- * Since: 2.14
- */
- gint
- g_regex_get_capture_count (const GRegex *regex)
- {
- gint value;
-
- pcre_fullinfo (regex->pcre_re, regex->extra,
- PCRE_INFO_CAPTURECOUNT, &value);
-
- return value;
- }
-
- /**
- * g_regex_match_simple:
- * @pattern: the regular expression
- * @string: the string to scan for matches
- * @compile_options: compile options for the regular expression, or 0
- * @match_options: match options, or 0
- *
- * Scans for a match in @string for @pattern.
- *
- * This function is equivalent to g_regex_match() but it does not
- * require to compile the pattern with g_regex_new(), avoiding some
- * lines of code when you need just to do a match without extracting
- * substrings, capture counts, and so on.
- *
- * If this function is to be called on the same @pattern more than
- * once, it's more efficient to compile the pattern once with
- * g_regex_new() and then use g_regex_match().
- *
- * Returns: %TRUE if the string matched, %FALSE otherwise
- *
- * Since: 2.14
- */
- gboolean
- g_regex_match_simple (const gchar *pattern,
- const gchar *string,
- GRegexCompileFlags compile_options,
- GRegexMatchFlags match_options)
- {
- GRegex *regex;
- gboolean result;
-
- regex = g_regex_new (pattern, compile_options, 0, NULL);
- if (!regex)
- return FALSE;
- result = g_regex_match_full (regex, string, -1, 0, match_options, NULL, NULL);
- g_regex_unref (regex);
- return result;
- }
-
- /**
- * g_regex_match:
- * @regex: a #GRegex structure from g_regex_new()
- * @string: the string to scan for matches
- * @match_options: match options
- * @match_info: pointer to location where to store the #GMatchInfo,
- * or %NULL if you do not need it
- *
- * Scans for a match in string for the pattern in @regex.
- * The @match_options are combined with the match options specified
- * when the @regex structure was created, letting you have more
- * flexibility in reusing #GRegex structures.
- *
- * A #GMatchInfo structure, used to get information on the match,
- * is stored in @match_info if not %NULL. Note that if @match_info
- * is not %NULL then it is created even if the function returns %FALSE,
- * i.e. you must free it regardless if regular expression actually matched.
- *
- * To retrieve all the non-overlapping matches of the pattern in
- * string you can use g_match_info_next().
- *
- * |[
- * static void
- * print_uppercase_words (const gchar *string)
- * {
- * /* Print all uppercase-only words. */
- * GRegex *regex;
- * GMatchInfo *match_info;
- *
- * regex = g_regex_new ("[A-Z]+", 0, 0, NULL);
- * g_regex_match (regex, string, 0, &match_info);
- * while (g_match_info_matches (match_info))
- * {
- * gchar *word = g_match_info_fetch (match_info, 0);
- * g_print ("Found: %s\n", word);
- * g_free (word);
- * g_match_info_next (match_info, NULL);
- * }
- * g_match_info_free (match_info);
- * g_regex_unref (regex);
- * }
- * ]|
- *
- * @string is not copied and is used in #GMatchInfo internally. If
- * you use any #GMatchInfo method (except g_match_info_free()) after
- * freeing or modifying @string then the behaviour is undefined.
- *
- * Returns: %TRUE is the string matched, %FALSE otherwise
- *
- * Since: 2.14
- */
- gboolean
- g_regex_match (const GRegex *regex,
- const gchar *string,
- GRegexMatchFlags match_options,
- GMatchInfo **match_info)
- {
- return g_regex_match_full (regex, string, -1, 0, match_options,
- match_info, NULL);
- }
-
- /**
- * g_regex_match_full:
- * @regex: a #GRegex structure from g_regex_new()
- * @string: the string to scan for matches
- * @string_len: the length of @string, or -1 if @string is nul-terminated
- * @start_position: starting index of the string to match
- * @match_options: match options
- * @match_info: pointer to location where to store the #GMatchInfo,
- * or %NULL if you do not need it
- * @error: location to store the error occuring, or %NULL to ignore errors
- *
- * Scans for a match in string for the pattern in @regex.
- * The @match_options are combined with the match options specified
- * when the @regex structure was created, letting you have more
- * flexibility in reusing #GRegex structures.
- *
- * Setting @start_position differs from just passing over a shortened
- * string and setting #G_REGEX_MATCH_NOTBOL in the case of a pattern
- * that begins with any kind of lookbehind assertion, such as "\b".
- *
- * A #GMatchInfo structure, used to get information on the match, is
- * stored in @match_info if not %NULL. Note that if @match_info is
- * not %NULL then it is created even if the function returns %FALSE,
- * i.e. you must free it regardless if regular expression actually
- * matched.
- *
- * @string is not copied and is used in #GMatchInfo internally. If
- * you use any #GMatchInfo method (except g_match_info_free()) after
- * freeing or modifying @string then the behaviour is undefined.
- *
- * To retrieve all the non-overlapping matches of the pattern in
- * string you can use g_match_info_next().
- *
- * |[
- * static void
- * print_uppercase_words (const gchar *string)
- * {
- * /* Print all uppercase-only words. */
- * GRegex *regex;
- * GMatchInfo *match_info;
- * GError *error = NULL;
- *
- * regex = g_regex_new ("[A-Z]+", 0, 0, NULL);
- * g_regex_match_full (regex, string, -1, 0, 0, &match_info, &error);
- * while (g_match_info_matches (match_info))
- * {
- * gchar *word = g_match_info_fetch (match_info, 0);
- * g_print ("Found: %s\n", word);
- * g_free (word);
- * g_match_info_next (match_info, &error);
- * }
- * g_match_info_free (match_info);
- * g_regex_unref (regex);
- * if (error != NULL)
- * {
- * g_printerr ("Error while matching: %s\n", error->message);
- * g_error_free (error);
- * }
- * }
- * ]|
- *
- * Returns: %TRUE is the string matched, %FALSE otherwise
- *
- * Since: 2.14
- */
- gboolean
- g_regex_match_full (const GRegex *regex,
- const gchar *string,
- gssize string_len,
- gint start_position,
- GRegexMatchFlags match_options,
- GMatchInfo **match_info,
- GError **error)
- {
- GMatchInfo *info;
- gboolean match_ok;
-
- g_return_val_if_fail (regex != NULL, FALSE);
- g_return_val_if_fail (string != NULL, FALSE);
- g_return_val_if_fail (start_position >= 0, FALSE);
- g_return_val_if_fail (error == NULL || *error == NULL, FALSE);
- g_return_val_if_fail ((match_options & ~G_REGEX_MATCH_MASK) == 0, FALSE);
-
- info = match_info_new (regex, string, string_len, start_position,
- match_options, FALSE);
- match_ok = g_match_info_next (info, error);
- if (match_info != NULL)
- *match_info = info;
- else
- g_match_info_free (info);
-
- return match_ok;
- }
-
- /**
- * g_regex_match_all:
- * @regex: a #GRegex structure from g_regex_new()
- * @string: the string to scan for matches
- * @match_options: match options
- * @match_info: pointer to location where to store the #GMatchInfo,
- * or %NULL if you do not need it
- *
- * Using the standard algorithm for regular expression matching only
- * the longest match in the string is retrieved. This function uses
- * a different algorithm so it can retrieve all the possible matches.
- * For more documentation see g_regex_match_all_full().
- *
- * A #GMatchInfo structure, used to get information on the match, is
- * stored in @match_info if not %NULL. Note that if @match_info is
- * not %NULL then it is created even if the function returns %FALSE,
- * i.e. you must free it regardless if regular expression actually
- * matched.
- *
- * @string is not copied and is used in #GMatchInfo internally. If
- * you use any #GMatchInfo method (except g_match_info_free()) after
- * freeing or modifying @string then the behaviour is undefined.
- *
- * Returns: %TRUE is the string matched, %FALSE otherwise
- *
- * Since: 2.14
- */
- gboolean
- g_regex_match_all (const GRegex *regex,
- const gchar *string,
- GRegexMatchFlags match_options,
- GMatchInfo **match_info)
- {
- return g_regex_match_all_full (regex, string, -1, 0, match_options,
- match_info, NULL);
- }
-
- /**
- * g_regex_match_all_full:
- * @regex: a #GRegex structure from g_regex_new()
- * @string: the string to scan for matches
- * @string_len: the length of @string, or -1 if @string is nul-terminated
- * @start_position: starting index of the string to match
- * @match_options: match options
- * @match_info: pointer to location where to store the #GMatchInfo,
- * or %NULL if you do not need it
- * @error: location to store the error occuring, or %NULL to ignore errors
- *
- * Using the standard algorithm for regular expression matching only
- * the longest match in the string is retrieved, it is not possibile
- * to obtain all the available matches. For instance matching
- * "<a> <b> <c>" against the pattern "<.*>"
- * you get "<a> <b> <c>".
- *
- * This function uses a different algorithm (called DFA, i.e. deterministic
- * finite automaton), so it can retrieve all the possible matches, all
- * starting at the same point in the string. For instance matching
- * "<a> <b> <c>" against the pattern "<.*>"
- * you would obtain three matches: "<a> <b> <c>",
- * "<a> <b>" and "<a>".
- *
- * The number of matched strings is retrieved using
- * g_match_info_get_match_count(). To obtain the matched strings and
- * their position you can use, respectively, g_match_info_fetch() and
- * g_match_info_fetch_pos(). Note that the strings are returned in
- * reverse order of length; that is, the longest matching string is
- * given first.
- *
- * Note that the DFA algorithm is slower than the standard one and it
- * is not able to capture substrings, so backreferences do not work.
- *
- * Setting @start_position differs from just passing over a shortened
- * string and setting #G_REGEX_MATCH_NOTBOL in the case of a pattern
- * that begins with any kind of lookbehind assertion, such as "\b".
- *
- * A #GMatchInfo structure, used to get information on the match, is
- * stored in @match_info if not %NULL. Note that if @match_info is
- * not %NULL then it is created even if the function returns %FALSE,
- * i.e. you must free it regardless if regular expression actually
- * matched.
- *
- * @string is not copied and is used in #GMatchInfo internally. If
- * you use any #GMatchInfo method (except g_match_info_free()) after
- * freeing or modifying @string then the behaviour is undefined.
- *
- * Returns: %TRUE is the string matched, %FALSE otherwise
- *
- * Since: 2.14
- */
- gboolean
- g_regex_match_all_full (const GRegex *regex,
- const gchar *string,
- gssize string_len,
- gint start_position,
- GRegexMatchFlags match_options,
- GMatchInfo **match_info,
- GError **error)
- {
- GMatchInfo *info;
- gboolean done;
-
- g_return_val_if_fail (regex != NULL, FALSE);
- g_return_val_if_fail (string != NULL, FALSE);
- g_return_val_if_fail (start_position >= 0, FALSE);
- g_return_val_if_fail (error == NULL || *error == NULL, FALSE);
- g_return_val_if_fail ((match_options & ~G_REGEX_MATCH_MASK) == 0, FALSE);
-
- info = match_info_new (regex, string, string_len, start_position,
- match_options, TRUE);
-
- done = FALSE;
- while (!done)
- {
- done = TRUE;
- info->matches = pcre_dfa_exec (regex->pcre_re, regex->extra,
- info->string, info->string_len,
- info->pos,
- regex->match_opts | match_options,
- info->offsets, info->n_offsets,
- info->workspace, info->n_workspace);
- if (info->matches == PCRE_ERROR_DFA_WSSIZE)
- {
- /* info->workspace is too small. */
- info->n_workspace *= 2;
- info->workspace = g_realloc (info->workspace,
- info->n_workspace * sizeof (gint));
- done = FALSE;
- }
- else if (info->matches == 0)
- {
- /* info->offsets is too small. */
- info->n_offsets *= 2;
- info->offsets = g_realloc (info->offsets,
- info->n_offsets * sizeof (gint));
- done = FALSE;
- }
- else if (IS_PCRE_ERROR (info->matches))
- {
- g_set_error (error, G_REGEX_ERROR, G_REGEX_ERROR_MATCH,
- "Error while matching regular expression %s: %s",
- regex->pattern, match_error (info->matches));
- }
- }
-
- /* set info->pos to -1 so that a call to g_match_info_next() fails. */
- info->pos = -1;
-
- if (match_info != NULL)
- *match_info = info;
- else
- g_match_info_free (info);
-
- return info->matches >= 0;
- }
-
- /**
- * g_regex_get_string_number:
- * @regex: #GRegex structure
- * @name: name of the subexpression
- *
- * Retrieves the number of the subexpression named @name.
- *
- * Returns: The number of the subexpression or -1 if @name
- * does not exists
- *
- * Since: 2.14
- */
- gint
- g_regex_get_string_number (const GRegex *regex,
- const gchar *name)
- {
- gint num;
-
- g_return_val_if_fail (regex != NULL, -1);
- g_return_val_if_fail (name != NULL, -1);
-
- num = pcre_get_stringnumber (regex->pcre_re, name);
- if (num == PCRE_ERROR_NOSUBSTRING)
- num = -1;
-
- return num;
- }
-
- /**
- * g_regex_split_simple:
- * @pattern: the regular expression
- * @string: the string to scan for matches
- * @compile_options: compile options for the regular expression, or 0
- * @match_options: match options, or 0
- *
- * Breaks the string on the pattern, and returns an array of
- * the tokens. If the pattern contains capturing parentheses,
- * then the text for each of the substrings will also be returned.
- * If the pattern does not match anywhere in the string, then the
- * whole string is returned as the first token.
- *
- * This function is equivalent to g_regex_split() but it does
- * not require to compile the pattern with g_regex_new(), avoiding
- * some lines of code when you need just to do a split without
- * extracting substrings, capture counts, and so on.
- *
- * If this function is to be called on the same @pattern more than
- * once, it's more efficient to compile the pattern once with
- * g_regex_new() and then use g_regex_split().
- *
- * As a special case, the result of splitting the empty string ""
- * is an empty vector, not a vector containing a single string.
- * The reason for this special case is that being able to represent
- * a empty vector is typically more useful than consistent handling
- * of empty elements. If you do need to represent empty elements,
- * you'll need to check for the empty string before calling this
- * function.
- *
- * A pattern that can match empty strings splits @string into
- * separate characters wherever it matches the empty string between
- * characters. For example splitting "ab c" using as a separator
- * "\s*", you will get "a", "b" and "c".
- *
- * Returns: a %NULL-terminated array of strings. Free it using g_strfreev()
- *
- * Since: 2.14
- **/
- gchar **
- g_regex_split_simple (const gchar *pattern,
- const gchar *string,
- GRegexCompileFlags compile_options,
- GRegexMatchFlags match_options)
- {
- GRegex *regex;
- gchar **result;
-
- regex = g_regex_new (pattern, compile_options, 0, NULL);
- if (!regex)
- return NULL;
- result = g_regex_split_full (regex, string, -1, 0, match_options, 0, NULL);
- g_regex_unref (regex);
- return result;
- }
-
- /**
- * g_regex_split:
- * @regex: a #GRegex structure
- * @string: the string to split with the pattern
- * @match_options: match time option flags
- *
- * Breaks the string on the pattern, and returns an array of the tokens.
- * If the pattern contains capturing parentheses, then the text for each
- * of the substrings will also be returned. If the pattern does not match
- * anywhere in the string, then the whole string is returned as the first
- * token.
- *
- * As a special case, the result of splitting the empty string "" is an
- * empty vector, not a vector containing a single string. The reason for
- * this special case is that being able to represent a empty vector is
- * typically more useful than consistent handling of empty elements. If
- * you do need to represent empty elements, you'll need to check for the
- * empty string before calling this function.
- *
- * A pattern that can match empty strings splits @string into separate
- * characters wherever it matches the empty string between characters.
- * For example splitting "ab c" using as a separator "\s*", you will get
- * "a", "b" and "c".
- *
- * Returns: a %NULL-terminated gchar ** array. Free it using g_strfreev()
- *
- * Since: 2.14
- **/
- gchar **
- g_regex_split (const GRegex *regex,
- const gchar *string,
- GRegexMatchFlags match_options)
- {
- return g_regex_split_full (regex, string, -1, 0,
- match_options, 0, NULL);
- }
-
- /**
- * g_regex_split_full:
- * @regex: a #GRegex structure
- * @string: the string to split with the pattern
- * @string_len: the length of @string, or -1 if @string is nul-terminated
- * @start_position: starting index of the string to match
- * @match_options: match time option flags
- * @max_tokens: the maximum number of tokens to split @string into.
- * If this is less than 1, the string is split completely
- * @error: return location for a #GError
- *
- * Breaks the string on the pattern, and returns an array of the tokens.
- * If the pattern contains capturing parentheses, then the text for each
- * of the substrings will also be returned. If the pattern does not match
- * anywhere in the string, then the whole string is returned as the first
- * token.
- *
- * As a special case, the result of splitting the empty string "" is an
- * empty vector, not a vector containing a single string. The reason for
- * this special case is that being able to represent a empty vector is
- * typically more useful than consistent handling of empty elements. If
- * you do need to represent empty elements, you'll need to check for the
- * empty string before calling this function.
- *
- * A pattern that can match empty strings splits @string into separate
- * characters wherever it matches the empty string between characters.
- * For example splitting "ab c" using as a separator "\s*", you will get
- * "a", "b" and "c".
- *
- * Setting @start_position differs from just passing over a shortened
- * string and setting #G_REGEX_MATCH_NOTBOL in the case of a pattern
- * that begins with any kind of lookbehind assertion, such as "\b".
- *
- * Returns: a %NULL-terminated gchar ** array. Free it using g_strfreev()
- *
- * Since: 2.14
- **/
- gchar **
- g_regex_split_full (const GRegex *regex,
- const gchar *string,
- gssize string_len,
- gint start_position,
- GRegexMatchFlags match_options,
- gint max_tokens,
- GError **error)
- {
- GError *tmp_error = NULL;
- GMatchInfo *match_info;
- GList *list, *last;
- gint i;
- gint token_count;
- gboolean match_ok;
- /* position of the last separator. */
- gint last_separator_end;
- /* was the last match 0 bytes long? */
- gboolean last_match_is_empty;
- /* the returned array of char **s */
- gchar **string_list;
-
- g_return_val_if_fail (regex != NULL, NULL);
- g_return_val_if_fail (string != NULL, NULL);
- g_return_val_if_fail (start_position >= 0, NULL);
- g_return_val_if_fail (error == NULL || *error == NULL, NULL);
- g_return_val_if_fail ((match_options & ~G_REGEX_MATCH_MASK) == 0, NULL);
-
- if (max_tokens <= 0)
- max_tokens = G_MAXINT;
-
- if (string_len < 0)
- string_len = strlen (string);
-
- /* zero-length string */
- if (string_len - start_position == 0)
- return g_new0 (gchar *, 1);
-
- if (max_tokens == 1)
- {
- string_list = g_new0 (gchar *, 2);
- string_list[0] = g_strndup (&string[start_position],
- string_len - start_position);
- return string_list;
- }
-
- list = NULL;
- token_count = 0;
- last_separator_end = start_position;
- last_match_is_empty = FALSE;
-
- match_ok = g_regex_match_full (regex, string, string_len, start_position,
- match_options, &match_info, &tmp_error);
- while (tmp_error == NULL)
- {
- if (match_ok)
- {
- last_match_is_empty =
- (match_info->offsets[0] == match_info->offsets[1]);
-
- /* we need to skip empty separators at the same position of the end
- * of another separator. e.g. the string is "a b" and the separator
- * is " *", so from 1 to 2 we have a match and at position 2 we have
- * an empty match. */
- if (last_separator_end != match_info->offsets[1])
- {
- gchar *token;
- gint match_count;
-
- token = g_strndup (string + last_separator_end,
- match_info->offsets[0] - last_separator_end);
- list = g_list_prepend (list, token);
- token_count++;
-
- /* if there were substrings, these need to be added to
- * the list. */
- match_count = g_match_info_get_match_count (match_info);
- if (match_count > 1)
- {
- for (i = 1; i < match_count; i++)
- list = g_list_prepend (list, g_match_info_fetch (match_info, i));
- }
- }
- }
- else
- {
- /* if there was no match, copy to end of string. */
- if (!last_match_is_empty)
- {
- gchar *token = g_strndup (string + last_separator_end,
- match_info->string_len - last_separator_end);
- list = g_list_prepend (list, token);
- }
- /* no more tokens, end the loop. */
- break;
- }
-
- /* -1 to leave room for the last part. */
- if (token_count >= max_tokens - 1)
- {
- /* we have reached the maximum number of tokens, so we copy
- * the remaining part of the string. */
- if (last_match_is_empty)
- {
- /* the last match was empty, so we have moved one char
- * after the real position to avoid empty matches at the
- * same position. */
- match_info->pos = PREV_CHAR (regex, &string[match_info->pos]) - string;
- }
- /* the if is needed in the case we have terminated the available
- * tokens, but we are at the end of the string, so there are no
- * characters left to copy. */
- if (string_len > match_info->pos)
- {
- gchar *token = g_strndup (string + match_info->pos,
- string_len - match_info->pos);
- list = g_list_prepend (list, token);
- }
- /* end the loop. */
- break;
- }
-
- last_separator_end = match_info->pos;
- if (last_match_is_empty)
- /* if the last match was empty, g_match_info_next() has moved
- * forward to avoid infinite loops, but we still need to copy that
- * character. */
- last_separator_end = PREV_CHAR (regex, &string[last_separator_end]) - string;
-
- match_ok = g_match_info_next (match_info, &tmp_error);
- }
- g_match_info_free (match_info);
- if (tmp_error != NULL)
- {
- g_propagate_error (error, tmp_error);
- g_list_foreach (list, (GFunc)g_free, NULL);
- g_list_free (list);
- match_info->pos = -1;
- return NULL;
- }
-
- string_list = g_new (gchar *, g_list_length (list) + 1);
- i = 0;
- for (last = g_list_last (list); last; last = g_list_previous (last))
- string_list[i++] = last->data;
- string_list[i] = NULL;
- g_list_free (list);
-
- return string_list;
- }
-
- enum
- {
- REPL_TYPE_STRING,
- REPL_TYPE_CHARACTER,
- REPL_TYPE_SYMBOLIC_REFERENCE,
- REPL_TYPE_NUMERIC_REFERENCE,
- REPL_TYPE_CHANGE_CASE
- };
-
- typedef enum
- {
- CHANGE_CASE_NONE = 1 << 0,
- CHANGE_CASE_UPPER = 1 << 1,
- CHANGE_CASE_LOWER = 1 << 2,
- CHANGE_CASE_UPPER_SINGLE = 1 << 3,
- CHANGE_CASE_LOWER_SINGLE = 1 << 4,
- CHANGE_CASE_SINGLE_MASK = CHANGE_CASE_UPPER_SINGLE | CHANGE_CASE_LOWER_SINGLE,
- CHANGE_CASE_LOWER_MASK = CHANGE_CASE_LOWER | CHANGE_CASE_LOWER_SINGLE,
- CHANGE_CASE_UPPER_MASK = CHANGE_CASE_UPPER | CHANGE_CASE_UPPER_SINGLE
- } ChangeCase;
-
- struct _InterpolationData
- {
- gchar *text;
- gint type;
- gint num;
- gchar c;
- ChangeCase change_case;
- };
-
- static void
- free_interpolation_data (InterpolationData *data)
- {
- g_free (data->text);
- g_free (data);
- }
-
- static const gchar *
- expand_escape (const gchar *replacement,
- const gchar *p,
- InterpolationData *data,
- GError **error)
- {
- const gchar *q, *r;
- gint x, d, h, i;
- const gchar *error_detail;
- gint base = 0;
- GError *tmp_error = NULL;
-
- p++;
- switch (*p)
- {
- case 't':
- p++;
- data->c = '\t';
- data->type = REPL_TYPE_CHARACTER;
- break;
- case 'n':
- p++;
- data->c = '\n';
- data->type = REPL_TYPE_CHARACTER;
- break;
- case 'v':
- p++;
- data->c = '\v';
- data->type = REPL_TYPE_CHARACTER;
- break;
- case 'r':
- p++;
- data->c = '\r';
- data->type = REPL_TYPE_CHARACTER;
- break;
- case 'f':
- p++;
- data->c = '\f';
- data->type = REPL_TYPE_CHARACTER;
- break;
- case 'a':
- p++;
- data->c = '\a';
- data->type = REPL_TYPE_CHARACTER;
- break;
- case 'b':
- p++;
- data->c = '\b';
- data->type = REPL_TYPE_CHARACTER;
- break;
- case '\\':
- p++;
- data->c = '\\';
- data->type = REPL_TYPE_CHARACTER;
- break;
- case 'x':
- p++;
- x = 0;
- if (*p == '{')
- {
- p++;
- do
- {
- h = g_ascii_xdigit_value (*p);
- if (h < 0)
- {
- error_detail = "hexadecimal digit or '}' expected";
- goto error;
- }
- x = x * 16 + h;
- p++;
- }
- while (*p != '}');
- p++;
- }
- else
- {
- for (i = 0; i < 2; i++)
- {
- h = g_ascii_xdigit_value (*p);
- if (h < 0)
- {
- error_detail = "hexadecimal digit expected";
- goto error;
- }
- x = x * 16 + h;
- p++;
- }
- }
- data->type = REPL_TYPE_STRING;
- data->text = g_new0 (gchar, 8);
- g_unichar_to_utf8 (x, data->text);
- break;
- case 'l':
- p++;
- data->type = REPL_TYPE_CHANGE_CASE;
- data->change_case = CHANGE_CASE_LOWER_SINGLE;
- break;
- case 'u':
- p++;
- data->type = REPL_TYPE_CHANGE_CASE;
- data->change_case = CHANGE_CASE_UPPER_SINGLE;
- break;
- case 'L':
- p++;
- data->type = REPL_TYPE_CHANGE_CASE;
- data->change_case = CHANGE_CASE_LOWER;
- break;
- case 'U':
- p++;
- data->type = REPL_TYPE_CHANGE_CASE;
- data->change_case = CHANGE_CASE_UPPER;
- break;
- case 'E':
- p++;
- data->type = REPL_TYPE_CHANGE_CASE;
- data->change_case = CHANGE_CASE_NONE;
- break;
- case 'g':
- p++;
- if (*p != '<')
- {
- error_detail = "missing '<' in symbolic reference";
- goto error;
- }
- q = p + 1;
- do
- {
- p++;
- if (!*p)
- {
- error_detail = "unfinished symbolic reference";
- goto error;
- }
- }
- while (*p != '>');
- if (p - q == 0)
- {
- error_detail = "zero-length symbolic reference";
- goto error;
- }
- if (g_ascii_isdigit (*q))
- {
- x = 0;
- do
- {
- h = g_ascii_digit_value (*q);
- if (h < 0)
- {
- error_detail = "digit expected";
- p = q;
- goto error;
- }
- x = x * 10 + h;
- q++;
- }
- while (q != p);
- data->num = x;
- data->type = REPL_TYPE_NUMERIC_REFERENCE;
- }
- else
- {
- r = q;
- do
- {
- if (!g_ascii_isalnum (*r))
- {
- error_detail = "illegal symbolic reference";
- p = r;
- goto error;
- }
- r++;
- }
- while (r != p);
- data->text = g_strndup (q, p - q);
- data->type = REPL_TYPE_SYMBOLIC_REFERENCE;
- }
- p++;
- break;
- case '0':
- /* if \0 is followed by a number is an octal number representing a
- * character, else it is a numeric reference. */
- if (g_ascii_digit_value (*g_utf8_next_char (p)) >= 0)
- {
- base = 8;
- p = g_utf8_next_char (p);
- }
- case '1':
- case '2':
- case '3':
- case '4':
- case '5':
- case '6':
- case '7':
- case '8':
- case '9':
- x = 0;
- d = 0;
- for (i = 0; i < 3; i++)
- {
- h = g_ascii_digit_value (*p);
- if (h < 0)
- break;
- if (h > 7)
- {
- if (base == 8)
- break;
- else
- base = 10;
- }
- if (i == 2 && base == 10)
- break;
- x = x * 8 + h;
- d = d * 10 + h;
- p++;
- }
- if (base == 8 || i == 3)
- {
- data->type = REPL_TYPE_STRING;
- data->text = g_new0 (gchar, 8);
- g_unichar_to_utf8 (x, data->text);
- }
- else
- {
- data->type = REPL_TYPE_NUMERIC_REFERENCE;
- data->num = d;
- }
- break;
- case 0:
- error_detail = "stray final '\\'";
- goto error;
- break;
- default:
- error_detail = "unknown escape sequence";
- goto error;
- }
-
- return p;
-
- error:
- /* G_GSSIZE_FORMAT doesn't work with gettext, so we use %lu */
- tmp_error = g_error_new (G_REGEX_ERROR,
- G_REGEX_ERROR_REPLACE,
- "Error while parsing replacement "
- "text \"%s\" at char %lu: %s",
- replacement,
- (gulong)(p - replacement),
- error_detail);
- g_propagate_error (error, tmp_error);
-
- return NULL;
- }
-
- static GList *
- split_replacement (const gchar *replacement,
- GError **error)
- {
- GList *list = NULL;
- InterpolationData *data;
- const gchar *p, *start;
-
- start = p = replacement;
- while (*p)
- {
- if (*p == '\\')
- {
- data = g_new0 (InterpolationData, 1);
- start = p = expand_escape (replacement, p, data, error);
- if (p == NULL)
- {
- g_list_foreach (list, (GFunc)free_interpolation_data, NULL);
- g_list_free (list);
- free_interpolation_data (data);
-
- return NULL;
- }
- list = g_list_prepend (list, data);
- }
- else
- {
- p++;
- if (*p == '\\' || *p == '\0')
- {
- if (p - start > 0)
- {
- data = g_new0 (InterpolationData, 1);
- data->text = g_strndup (start, p - start);
- data->type = REPL_TYPE_STRING;
- list = g_list_prepend (list, data);
- }
- }
- }
- }
-
- return g_list_reverse (list);
- }
-
- /* Change the case of c based on change_case. */
- #define CHANGE_CASE(c, change_case) \
- (((change_case) & CHANGE_CASE_LOWER_MASK) ? \
- g_unichar_tolower (c) : \
- g_unichar_toupper (c))
-
- static void
- string_append (GString *string,
- const gchar *text,
- ChangeCase *change_case)
- {
- gunichar c;
-
- if (text[0] == '\0')
- return;
-
- if (*change_case == CHANGE_CASE_NONE)
- {
- g_string_append (string, text);
- }
- else if (*change_case & CHANGE_CASE_SINGLE_MASK)
- {
- c = g_utf8_get_char (text);
- g_string_append_unichar (string, CHANGE_CASE (c, *change_case));
- g_string_append (string, g_utf8_next_char (text));
- *change_case = CHANGE_CASE_NONE;
- }
- else
- {
- while (*text != '\0')
- {
- c = g_utf8_get_char (text);
- g_string_append_unichar (string, CHANGE_CASE (c, *change_case));
- text = g_utf8_next_char (text);
- }
- }
- }
-
- static gboolean
- interpolate_replacement (const GMatchInfo *match_info,
- GString *result,
- gpointer data)
- {
- GList *list;
- InterpolationData *idata;
- gchar *match;
- ChangeCase change_case = CHANGE_CASE_NONE;
-
- for (list = data; list; list = list->next)
- {
- idata = list->data;
- switch (idata->type)
- {
- case REPL_TYPE_STRING:
- string_append (result, idata->text, &change_case);
- break;
- case REPL_TYPE_CHARACTER:
- g_string_append_c (result, CHANGE_CASE (idata->c, change_case));
- if (change_case & CHANGE_CASE_SINGLE_MASK)
- change_case = CHANGE_CASE_NONE;
- break;
- case REPL_TYPE_NUMERIC_REFERENCE:
- match = g_match_info_fetch (match_info, idata->num);
- if (match)
- {
- string_append (result, match, &change_case);
- g_free (match);
- }
- break;
- case REPL_TYPE_SYMBOLIC_REFERENCE:
- match = g_match_info_fetch_named (match_info, idata->text);
- if (match)
- {
- string_append (result, match, &change_case);
- g_free (match);
- }
- break;
- case REPL_TYPE_CHANGE_CASE:
- change_case = idata->change_case;
- break;
- }
- }
-
- return FALSE;
- }
-
- /* whether actual match_info is needed for replacement, i.e.
- * whether there are references
- */
- static gboolean
- interpolation_list_needs_match (GList *list)
- {
- while (list != NULL)
- {
- InterpolationData *data = list->data;
-
- if (data->type == REPL_TYPE_SYMBOLIC_REFERENCE ||
- data->type == REPL_TYPE_NUMERIC_REFERENCE)
- {
- return TRUE;
- }
-
- list = list->next;
- }
-
- return FALSE;
- }
-
- /**
- * g_regex_replace:
- * @regex: a #GRegex structure
- * @string: the string to perform matches against
- * @string_len: the length of @string, or -1 if @string is nul-terminated
- * @start_position: starting index of the string to match
- * @replacement: text to replace each match with
- * @match_options: options for the match
- * @error: location to store the error occuring, or %NULL to ignore errors
- *
- * Replaces all occurrences of the pattern in @regex with the
- * replacement text. Backreferences of the form '\number' or
- * '\g<number>' in the replacement text are interpolated by the
- * number-th captured subexpression of the match, '\g<name>' refers
- * to the captured subexpression with the given name. '\0' refers to the
- * complete match, but '\0' followed by a number is the octal representation
- * of a character. To include a literal '\' in the replacement, write '\\'.
- * There are also escapes that changes the case of the following text:
- *
- * <variablelist>
- * <varlistentry><term>\l</term>
- * <listitem>
- * <para>Convert to lower case the next character</para>
- * </listitem>
- * </varlistentry>
- * <varlistentry><term>\u</term>
- * <listitem>
- * <para>Convert to upper case the next character</para>
- * </listitem>
- * </varlistentry>
- * <varlistentry><term>\L</term>
- * <listitem>
- * <para>Convert to lower case till \E</para>
- * </listitem>
- * </varlistentry>
- * <varlistentry><term>\U</term>
- * <listitem>
- * <para>Convert to upper case till \E</para>
- * </listitem>
- * </varlistentry>
- * <varlistentry><term>\E</term>
- * <listitem>
- * <para>End case modification</para>
- * </listitem>
- * </varlistentry>
- * </variablelist>
- *
- * If you do not need to use backreferences use g_regex_replace_literal().
- *
- * The @replacement string must be UTF-8 encoded even if #G_REGEX_RAW was
- * passed to g_regex_new(). If you want to use not UTF-8 encoded stings
- * you can use g_regex_replace_literal().
- *
- * Setting @start_position differs from just passing over a shortened
- * string and setting #G_REGEX_MATCH_NOTBOL in the case of a pattern that
- * begins with any kind of lookbehind assertion, such as "\b".
- *
- * Returns: a newly allocated string containing the replacements
- *
- * Since: 2.14
- */
- gchar *
- g_regex_replace (const GRegex *regex,
- const gchar *string,
- gssize string_len,
- gint start_position,
- const gchar *replacement,
- GRegexMatchFlags match_options,
- GError **error)
- {
- gchar *result;
- GList *list;
- GError *tmp_error = NULL;
-
- g_return_val_if_fail (regex != NULL, NULL);
- g_return_val_if_fail (string != NULL, NULL);
- g_return_val_if_fail (start_position >= 0, NULL);
- g_return_val_if_fail (replacement != NULL, NULL);
- g_return_val_if_fail (error == NULL || *error == NULL, NULL);
- g_return_val_if_fail ((match_options & ~G_REGEX_MATCH_MASK) == 0, NULL);
-
- list = split_replacement (replacement, &tmp_error);
- if (tmp_error != NULL)
- {
- g_propagate_error (error, tmp_error);
- return NULL;
- }
-
- result = g_regex_replace_eval (regex,
- string, string_len, start_position,
- match_options,
- interpolate_replacement,
- (gpointer)list,
- &tmp_error);
- if (tmp_error != NULL)
- g_propagate_error (error, tmp_error);
-
- g_list_foreach (list, (GFunc)free_interpolation_data, NULL);
- g_list_free (list);
-
- return result;
- }
-
- static gboolean
- literal_replacement (const GMatchInfo *match_info,
- GString *result,
- gpointer data)
- {
- g_string_append (result, data);
- return FALSE;
- }
-
- /**
- * g_regex_replace_literal:
- * @regex: a #GRegex structure
- * @string: the string to perform matches against
- * @string_len: the length of @string, or -1 if @string is nul-terminated
- * @start_position: starting index of the string to match
- * @replacement: text to replace each match with
- * @match_options: options for the match
- * @error: location to store the error occuring, or %NULL to ignore errors
- *
- * Replaces all occurrences of the pattern in @regex with the
- * replacement text. @replacement is replaced literally, to
- * include backreferences use g_regex_replace().
- *
- * Setting @start_position differs from just passing over a
- * shortened string and setting #G_REGEX_MATCH_NOTBOL in the
- * case of a pattern that begins with any kind of lookbehind
- * assertion, such as "\b".
- *
- * Returns: a newly allocated string containing the replacements
- *
- * Since: 2.14
- */
- gchar *
- g_regex_replace_literal (const GRegex *regex,
- const gchar *string,
- gssize string_len,
- gint start_position,
- const gchar *replacement,
- GRegexMatchFlags match_options,
- GError **error)
- {
- g_return_val_if_fail (replacement != NULL, NULL);
- g_return_val_if_fail ((match_options & ~G_REGEX_MATCH_MASK) == 0, NULL);
-
- return g_regex_replace_eval (regex,
- string, string_len, start_position,
- match_options,
- literal_replacement,
- (gpointer)replacement,
- error);
- }
-
- /**
- * g_regex_replace_eval:
- * @regex: a #GRegex structure from g_regex_new()
- * @string: string to perform matches against
- * @string_len: the length of @string, or -1 if @string is nul-terminated
- * @start_position: starting index of the string to match
- * @match_options: options for the match
- * @eval: a function to call for each match
- * @user_data: user data to pass to the function
- * @error: location to store the error occuring, or %NULL to ignore errors
- *
- * Replaces occurrences of the pattern in regex with the output of
- * @eval for that occurrence.
- *
- * Setting @start_position differs from just passing over a shortened
- * string and setting #G_REGEX_MATCH_NOTBOL in the case of a pattern
- * that begins with any kind of lookbehind assertion, such as "\b".
- *
- * The following example uses g_regex_replace_eval() to replace multiple
- * strings at once:
- * |[
- * static gboolean
- * eval_cb (const GMatchInfo *info,
- * GString *res,
- * gpointer data)
- * {
- * gchar *match;
- * gchar *r;
- *
- * match = g_match_info_fetch (info, 0);
- * r = g_hash_table_lookup ((GHashTable *)data, match);
- * g_string_append (res, r);
- * g_free (match);
- *
- * return FALSE;
- * }
- *
- * /* ... */
- *
- * GRegex *reg;
- * GHashTable *h;
- * gchar *res;
- *
- * h = g_hash_table_new (g_str_hash, g_str_equal);
- *
- * g_hash_table_insert (h, "1", "ONE");
- * g_hash_table_insert (h, "2", "TWO");
- * g_hash_table_insert (h, "3", "THREE");
- * g_hash_table_insert (h, "4", "FOUR");
- *
- * reg = g_regex_new ("1|2|3|4", 0, 0, NULL);
- * res = g_regex_replace_eval (reg, text, -1, 0, 0, eval_cb, h, NULL);
- * g_hash_table_destroy (h);
- *
- * /* ... */
- * ]|
- *
- * Returns: a newly allocated string containing the replacements
- *
- * Since: 2.14
- */
- gchar *
- g_regex_replace_eval (const GRegex *regex,
- const gchar *string,
- gssize string_len,
- gint start_position,
- GRegexMatchFlags match_options,
- GRegexEvalCallback eval,
- gpointer user_data,
- GError **error)
- {
- GMatchInfo *match_info;
- GString *result;
- gint str_pos = 0;
- gboolean done = FALSE;
- GError *tmp_error = NULL;
-
- g_return_val_if_fail (regex != NULL, NULL);
- g_return_val_if_fail (string != NULL, NULL);
- g_return_val_if_fail (start_position >= 0, NULL);
- g_return_val_if_fail (eval != NULL, NULL);
- g_return_val_if_fail ((match_options & ~G_REGEX_MATCH_MASK) == 0, NULL);
-
- if (string_len < 0)
- string_len = strlen (string);
-
- result = g_string_sized_new (string_len);
-
- /* run down the string making matches. */
- g_regex_match_full (regex, string, string_len, start_position,
- match_options, &match_info, &tmp_error);
- while (!done && g_match_info_matches (match_info))
- {
- g_string_append_len (result,
- string + str_pos,
- match_info->offsets[0] - str_pos);
- done = (*eval) (match_info, result, user_data);
- str_pos = match_info->offsets[1];
- g_match_info_next (match_info, &tmp_error);
- }
- g_match_info_free (match_info);
- if (tmp_error != NULL)
- {
- g_propagate_error (error, tmp_error);
- g_string_free (result, TRUE);
- return NULL;
- }
-
- g_string_append_len (result, string + str_pos, string_len - str_pos);
- return g_string_free (result, FALSE);
- }
-
- /**
- * g_regex_check_replacement:
- * @replacement: the replacement string
- * @has_references: location to store information about
- * references in @replacement or %NULL
- * @error: location to store error
- *
- * Checks whether @replacement is a valid replacement string
- * (see g_regex_replace()), i.e. that all escape sequences in
- * it are valid.
- *
- * If @has_references is not %NULL then @replacement is checked
- * for pattern references. For instance, replacement text 'foo\n'
- * does not contain references and may be evaluated without information
- * about actual match, but '\0\1' (whole match followed by first
- * subpattern) requires valid #GMatchInfo object.
- *
- * Returns: whether @replacement is a valid replacement string
- *
- * Since: 2.14
- */
- gboolean
- g_regex_check_replacement (const gchar *replacement,
- gboolean *has_references,
- GError **error)
- {
- GList *list;
- GError *tmp = NULL;
-
- list = split_replacement (replacement, &tmp);
-
- if (tmp)
- {
- g_propagate_error (error, tmp);
- return FALSE;
- }
-
- if (has_references)
- *has_references = interpolation_list_needs_match (list);
-
- g_list_foreach (list, (GFunc) free_interpolation_data, NULL);
- g_list_free (list);
-
- return TRUE;
- }
-
- /**
- * g_regex_escape_string:
- * @string: the string to escape
- * @length: the length of @string, or -1 if @string is nul-terminated
- *
- * Escapes the special characters used for regular expressions
- * in @string, for instance "a.b*c" becomes "a\.b\*c". This
- * function is useful to dynamically generate regular expressions.
- *
- * @string can contain nul characters that are replaced with "\0",
- * in this case remember to specify the correct length of @string
- * in @length.
- *
- * Returns: a newly-allocated escaped string
- *
- * Since: 2.14
- */
- gchar *
- g_regex_escape_string (const gchar *string,
- gint length)
- {
- GString *escaped;
- const char *p, *piece_start, *end;
-
- g_return_val_if_fail (string != NULL, NULL);
-
- if (length < 0)
- length = strlen (string);
-
- end = string + length;
- p = piece_start = string;
- escaped = g_string_sized_new (length + 1);
-
- while (p < end)
- {
- switch (*p)
- {
- case '\0':
- case '\\':
- case '|':
- case '(':
- case ')':
- case '[':
- case ']':
- case '{':
- case '}':
- case '^':
- case '$':
- case '*':
- case '+':
- case '?':
- case '.':
- if (p != piece_start)
- /* copy the previous piece. */
- g_string_append_len (escaped, piece_start, p - piece_start);
- g_string_append_c (escaped, '\\');
- if (*p == '\0')
- g_string_append_c (escaped, '0');
- else
- g_string_append_c (escaped, *p);
- piece_start = ++p;
- break;
- default:
- p = g_utf8_next_char (p);
- break;
- }
- }
-
- if (piece_start < end)
- g_string_append_len (escaped, piece_start, end - piece_start);
-
- return g_string_free (escaped, FALSE);
- }
|