From: Tim Allison Date: Mon, 29 Oct 2018 15:48:44 +0000 (+0000) Subject: bug 62624 -- fix npe by adding processing of module name mapping in VBAMacroReader X-Git-Tag: REL_4_0_1~40 X-Git-Url: https://source.dussan.org/?a=commitdiff_plain;h=b5653e882986e219b3f2c0faf7b73c2d16f11f41;p=poi.git bug 62624 -- fix npe by adding processing of module name mapping in VBAMacroReader git-svn-id: https://svn.apache.org/repos/asf/poi/trunk@1845138 13f79535-47bb-0310-9956-ffa450edef68 --- diff --git a/src/java/org/apache/poi/poifs/macros/VBAMacroReader.java b/src/java/org/apache/poi/poifs/macros/VBAMacroReader.java index c3a1c89e78..cb6f3b91f3 100644 --- a/src/java/org/apache/poi/poifs/macros/VBAMacroReader.java +++ b/src/java/org/apache/poi/poifs/macros/VBAMacroReader.java @@ -20,9 +20,19 @@ package org.apache.poi.poifs.macros; import static org.apache.poi.util.StringUtil.endsWithIgnoreCase; import static org.apache.poi.util.StringUtil.startsWithIgnoreCase; -import java.io.*; +import java.io.ByteArrayInputStream; +import java.io.ByteArrayOutputStream; +import java.io.Closeable; +import java.io.EOFException; +import java.io.File; +import java.io.FileInputStream; +import java.io.IOException; +import java.io.InputStream; +import java.io.InputStreamReader; import java.nio.charset.Charset; +import java.nio.charset.StandardCharsets; import java.util.HashMap; +import java.util.LinkedHashMap; import java.util.Map; import java.util.zip.ZipEntry; import java.util.zip.ZipInputStream; @@ -39,6 +49,8 @@ import org.apache.poi.util.CodePageUtil; import org.apache.poi.util.HexDump; import org.apache.poi.util.IOUtils; import org.apache.poi.util.LittleEndian; +import org.apache.poi.util.POILogFactory; +import org.apache.poi.util.POILogger; import org.apache.poi.util.RLEDecompressingInputStream; import org.apache.poi.util.StringUtil; @@ -56,6 +68,8 @@ import org.apache.poi.util.StringUtil; * @since 3.15-beta2 */ public class VBAMacroReader implements Closeable { + private static final POILogger LOGGER = POILogFactory.getLogger(VBAMacroReader.class); + protected static final String VBA_PROJECT_OOXML = "vbaProject.bin"; protected static final String VBA_PROJECT_POIFS = "VBA"; @@ -111,8 +125,13 @@ public class VBAMacroReader implements Closeable { public Map readMacroModules() throws IOException { final ModuleMap modules = new ModuleMap(); + //ascii -> unicode mapping for module names + //preserve insertion order + final Map moduleNameMap = new LinkedHashMap<>(); + findMacros(fs.getRoot(), modules); - findProjectProperties(fs.getRoot(), modules); + findModuleNameMap(fs.getRoot(), moduleNameMap, modules); + findProjectProperties(fs.getRoot(), moduleNameMap, modules); Map moduleSources = new HashMap<>(); for (Map.Entry entry : modules.entrySet()) { @@ -327,16 +346,33 @@ public class VBAMacroReader implements Closeable { } } - protected void findProjectProperties(DirectoryNode node, ModuleMap modules) throws IOException { + protected void findProjectProperties(DirectoryNode node, Map moduleNameMap, ModuleMap modules) throws IOException { for (Entry entry : node) { if ("project".equalsIgnoreCase(entry.getName())) { DocumentNode document = (DocumentNode)entry; DocumentInputStream dis = new DocumentInputStream(document); - readProjectProperties(dis, modules); + readProjectProperties(dis, moduleNameMap, modules); + } else { + for (Entry child : node) { + if (child instanceof DirectoryNode) { + findProjectProperties((DirectoryNode)child, moduleNameMap, modules); + } + } + + } + } + } + + protected void findModuleNameMap(DirectoryNode node, Map moduleNameMap, ModuleMap modules) throws IOException { + for (Entry entry : node) { + if ("projectwm".equalsIgnoreCase(entry.getName())) { + DocumentNode document = (DocumentNode)entry; + DocumentInputStream dis = new DocumentInputStream(document); + readNameMapRecords(dis, moduleNameMap, modules.charset); } else { for (Entry child : node) { if (child instanceof DirectoryNode) { - findProjectProperties((DirectoryNode)child, modules); + findModuleNameMap((DirectoryNode)child, moduleNameMap, modules); } } @@ -559,6 +595,75 @@ public class VBAMacroReader implements Closeable { return new ASCIIUnicodeStringPair(ascii, unicode); } + private static void readNameMapRecords(InputStream is, Map moduleNames, Charset charset) throws IOException { + //see 2.3.3 PROJECTwm Stream: Module Name Information + //multibytecharstring + String mbcs = null; + String unicode = null; + do { + try { + mbcs = readMBCS(is, charset); + } catch (EOFException e) { + return; + } + if (mbcs == null) { + return; + } + try { + unicode = readUnicode(is); + } catch (EOFException e) { + return; + } + if (mbcs != null && unicode != null) { + moduleNames.put(mbcs, unicode); + } + } while (mbcs != null && unicode != null); + } + + private static String readUnicode(InputStream is) throws IOException { + //reads null-terminated unicode string + ByteArrayOutputStream bos = new ByteArrayOutputStream(); + int b0 = is.read(); + int b1 = is.read(); + + while ((b0 + b1) != 0) { + if (b0 == -1 || b1 == -1) { + throw new EOFException(); + } + + bos.write(b0); + bos.write(b1); + b0 = is.read(); + b1 = is.read(); + } + return new String (bos.toByteArray(), StandardCharsets.UTF_16LE); + } + + //returns a string if any bytes are read or null if two 0x00 are read + private static String readMBCS(InputStream is, Charset charset) throws IOException { + ByteArrayOutputStream bos = new ByteArrayOutputStream(); + int len = 0; + int b = is.read(); + while (b != 0) { + ++len; + if (b == -1) { + throw new EOFException(); + } + bos.write(b); + b = is.read(); + } + if (len == 0) { + b = is.read(); + if (b == -1) { + throw new EOFException(); + } + if (b != 0) { + LOGGER.log(POILogger.WARN, "expected two 0x00 at end of module name map"); + } + return null; + } + return new String(bos.toByteArray(), charset); + } /** * Read length bytes of MBCS (multi-byte character set) characters from the stream @@ -579,7 +684,8 @@ public class VBAMacroReader implements Closeable { return new String(buffer, 0, length, charset); } - protected void readProjectProperties(DocumentInputStream dis, ModuleMap modules) throws IOException { + protected void readProjectProperties(DocumentInputStream dis, + Map moduleNameMap, ModuleMap modules) throws IOException { InputStreamReader reader = new InputStreamReader(dis, modules.charset); StringBuilder builder = new StringBuilder(); char[] buffer = new char[512]; @@ -588,6 +694,9 @@ public class VBAMacroReader implements Closeable { builder.append(buffer, 0, read); } String properties = builder.toString(); + //the module name map names should be in exactly the same order + //as the module names here. See 2.3.3 PROJECTwm Stream. + //At some point, we might want to enforce that. for (String line : properties.split("\r\n|\n\r")) { if (!line.startsWith("[")) { String[] tokens = line.split("="); @@ -595,22 +704,40 @@ public class VBAMacroReader implements Closeable { && tokens[1].startsWith("\"") && tokens[1].endsWith("\"")) { // Remove any double quotes tokens[1] = tokens[1].substring(1, tokens[1].length() - 1); - } - if ("Document".equals(tokens[0])) { + if ("Document".equals(tokens[0]) && tokens.length > 1) { String mn = tokens[1].substring(0, tokens[1].indexOf("/&H")); - ModuleImpl module = modules.get(mn); - module.moduleType = ModuleType.Document; - } else if ("Module".equals(tokens[0])) { - ModuleImpl module = modules.get(tokens[1]); - module.moduleType = ModuleType.Module; - } else if ("Class".equals(tokens[0])) { - ModuleImpl module = modules.get(tokens[1]); - module.moduleType = ModuleType.Class; + ModuleImpl module = getModule(mn, moduleNameMap, modules); + if (module != null) { + module.moduleType = ModuleType.Document; + } else { + LOGGER.log(POILogger.WARN, "couldn't find module with name: "+mn); + } + } else if ("Module".equals(tokens[0]) && tokens.length > 1) { + ModuleImpl module = getModule(tokens[1], moduleNameMap, modules); + if (module != null) { + module.moduleType = ModuleType.Module; + } else { + LOGGER.log(POILogger.WARN, "couldn't find module with name: "+tokens[1]); + } + } else if ("Class".equals(tokens[0]) && tokens.length > 1) { + ModuleImpl module = getModule(tokens[1], moduleNameMap, modules); + if (module != null) { + module.moduleType = ModuleType.Class; + } else { + LOGGER.log(POILogger.WARN, "couldn't find module with name: "+tokens[1]); + } } } } } + //can return null! + private ModuleImpl getModule(String moduleName, Map moduleNameMap, ModuleMap moduleMap) { + if (moduleNameMap.containsKey(moduleName)) { + return moduleMap.get(moduleNameMap.get(moduleName)); + } + return moduleMap.get(moduleName); + } private String readUnicodeString(RLEDecompressingInputStream in, int unicodeNameRecordLength) throws IOException { byte[] buffer = IOUtils.safelyAllocate(unicodeNameRecordLength, 20000); diff --git a/src/testcases/org/apache/poi/poifs/macros/TestVBAMacroReader.java b/src/testcases/org/apache/poi/poifs/macros/TestVBAMacroReader.java index b4885f1d23..673f82e64f 100644 --- a/src/testcases/org/apache/poi/poifs/macros/TestVBAMacroReader.java +++ b/src/testcases/org/apache/poi/poifs/macros/TestVBAMacroReader.java @@ -286,4 +286,18 @@ public class TestVBAMacroReader { assertContains(content, "Attribute VB_Customizable = True"); r.close(); } + + @Test + public void bug62624() throws IOException { + //macro comes from Common Crawl: HRLOXHGMGLFIJQQU27RIWXOARRHAAAAS + File f = POIDataSamples.getSpreadSheetInstance().getFile("62624.bin"); + VBAMacroReader r = new VBAMacroReader(f); + + Map macros = r.readMacroModules(); + assertEquals(13, macros.size()); + assertNotNull(macros.get("M\u00F3dulo1")); + assertContains(macros.get("M\u00F3dulo1").getContent(), "Calcula_tributos"); + assertEquals(Module.ModuleType.Module, macros.get("M\u00F3dulo1").geModuleType()); + r.close(); + } } diff --git a/test-data/spreadsheet/62624.bin b/test-data/spreadsheet/62624.bin new file mode 100644 index 0000000000..9af59522e5 Binary files /dev/null and b/test-data/spreadsheet/62624.bin differ