[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[GNUnet-SVN] r2466 - in Extractor: . src/include src/main src/plugins/wo
|
From: |
grothoff |
|
Subject: |
[GNUnet-SVN] r2466 - in Extractor: . src/include src/main src/plugins/wordleaker |
|
Date: |
Wed, 8 Mar 2006 05:52:22 -0800 (PST) |
Author: grothoff
Date: 2006-03-08 05:52:16 -0800 (Wed, 08 Mar 2006)
New Revision: 2466
Added:
Extractor/src/plugins/wordleaker/Makefile.am
Extractor/src/plugins/wordleaker/SYMBOLS
Extractor/src/plugins/wordleaker/wordextractor.cc
Extractor/src/plugins/wordleaker/wordleaker.cpp
Extractor/src/plugins/wordleaker/wordleaker.h
Removed:
Extractor/src/plugins/wordleaker/WordLeaker.cpp
Extractor/src/plugins/wordleaker/WordLeaker.h
Modified:
Extractor/configure.ac
Extractor/src/include/extractor.h
Extractor/src/main/extractor.c
Log:
wordleaker integration -- draft
Modified: Extractor/configure.ac
===================================================================
--- Extractor/configure.ac 2006-02-22 18:21:26 UTC (rev 2465)
+++ Extractor/configure.ac 2006-03-08 13:52:16 UTC (rev 2466)
@@ -298,6 +298,7 @@
src/plugins/hash/Makefile
src/plugins/thumbnail/Makefile
src/plugins/exiv2/Makefile
+src/plugins/wordleaker/Makefile
src/test/Makefile
])
Modified: Extractor/src/include/extractor.h
===================================================================
--- Extractor/src/include/extractor.h 2006-02-22 18:21:26 UTC (rev 2465)
+++ Extractor/src/include/extractor.h 2006-03-08 13:52:16 UTC (rev 2466)
@@ -140,6 +140,8 @@
EXTRACTOR_ORIENTATION = 87,
EXTRACTOR_TEMPLATE = 88,
EXTRACTOR_SPLIT = 89,
+
+ EXTRACTOR_PRODUCTVERSION = 90,
} EXTRACTOR_KeywordType;
/**
Modified: Extractor/src/main/extractor.c
===================================================================
--- Extractor/src/main/extractor.c 2006-02-22 18:21:26 UTC (rev 2465)
+++ Extractor/src/main/extractor.c 2006-03-08 13:52:16 UTC (rev 2466)
@@ -131,11 +131,12 @@
gettext_noop("orientation"),
gettext_noop("template"),
gettext_noop("split"),
+ gettext_noop("product version"),
NULL,
};
/* the number of keyword types (for bounds-checking) */
-#define HIGHEST_TYPE_NUMBER 90
+#define HIGHEST_TYPE_NUMBER 91
#ifdef HAVE_LIBOGG
#if HAVE_VORBIS
Added: Extractor/src/plugins/wordleaker/Makefile.am
===================================================================
--- Extractor/src/plugins/wordleaker/Makefile.am 2006-02-22 18:21:26 UTC
(rev 2465)
+++ Extractor/src/plugins/wordleaker/Makefile.am 2006-03-08 13:52:16 UTC
(rev 2466)
@@ -0,0 +1,25 @@
+include ../Makefile-plugins.am
+
+plugin_LTLIBRARIES = \
+ libextractor_word.la
+
+libextractor_word_la_LINK = \
+ /bin/sh ../../../libtool --mode=link $(CXXLD) -o libextractor_word.la
+libextractor_word_la_LDFLAGS = \
+ $(PLUGINFLAGS) $(retaincommand) \
+ $(XTRA_CPPLIBS)
+libextractor_word_la_LIBADD = \
+ $(top_builddir)/src/main/libextractor.la \
+ $(top_builddir)/src/plugins/libconvert.la \
+ -lm
+
+libextractor_word_la_SOURCES = \
+ pole.h pole.cpp \
+ wordleaker.h \
+ wordextractor.cc
+
+# gcc 3.3 produces BROKEN code for -O1 and -O2 (PDF extraction
+# would fail silently) hence we MUST override the user flag here
+# which may contain -O1 or -O2!
+# CXXFLAGS = -O0
+
Added: Extractor/src/plugins/wordleaker/SYMBOLS
===================================================================
--- Extractor/src/plugins/wordleaker/SYMBOLS 2006-02-22 18:21:26 UTC (rev
2465)
+++ Extractor/src/plugins/wordleaker/SYMBOLS 2006-03-08 13:52:16 UTC (rev
2466)
@@ -0,0 +1 @@
+libextractor_word_extract
Deleted: Extractor/src/plugins/wordleaker/WordLeaker.cpp
===================================================================
--- Extractor/src/plugins/wordleaker/WordLeaker.cpp 2006-02-22 18:21:26 UTC
(rev 2465)
+++ Extractor/src/plugins/wordleaker/WordLeaker.cpp 2006-03-08 13:52:16 UTC
(rev 2466)
@@ -1,310 +0,0 @@
-/*
- WordLeaker - Shows information about Word DOC files
- Copyright (C) 2005 Sacha Fuentes <address@hidden>
-
- Based on poledump.c
- Original idea from WordDumper (http://www.computerbytesman.com)
- Info on Word format: http://www.aozw65.dsl.pipex.com/generator_wword8.htm
- Info on Word format: http://jakarta.apache.org/poi/hpsf/internals.html
-
- This program is free software; you can redistribute it and/or
- modify it under the terms of the GNU General Public
- License as published by the Free Software Foundation; either
- version 2 of the License, or (at your option) any later version.
-
- This program 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
- General Public License for more details.
-
- You should have received a copy of the GNU General Public License
- along with this library; see the file COPYING. If not, write to
- the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
- Boston, MA 02111-1307, US
-*/
-
-// TAKE CARE: there's not a single check for validity of data,
-// so any malformed or malicious Word file will break it
-
-#include <iostream>
-#include <fstream>
-#include <stdlib.h>
-#include <list>
-#include <ctime>
-
-#include "pole.h"
-#include "WordLeaker.h"
-
-unsigned long fcSttbSavedBy;
-unsigned long lcbSttbSavedBy;
-
-// read the type of the property and displays its value
-void showProperty( POLE::Stream* stream ) {
- unsigned long read, type;
- unsigned char buffer[256];
- unsigned char c;
- unsigned long i;
- unsigned long t, t1, t2;
- char *s;
-
- read = stream->read(buffer, 4);
- type = buffer[0] + (buffer[1] << 8) + (buffer[2] << 16) + (buffer[3] << 24);
-
- switch (type) {
- case 2: // VT_I2
- read = stream->read(buffer, 2);
- i = buffer[0] + (buffer[1] << 8);
- cout << i << endl;
- break;
- case 3: // VT_I4
- read = stream->read(buffer, 4);
- i = buffer[0] + (buffer[1] << 8) + (buffer[2] << 16) + (buffer[3] <<
24);
- cout << i << endl;
- break;
- case 11: // VT_BOOL
- read = stream->read(buffer, 1);
- if ((char) buffer[0] == -1)
- cout << "true" << endl;
- else
- cout << "false" << endl;
- break;
- case 30: // VT_LPSTR
- read = stream->read(buffer, 4);
- i = buffer[0] + (buffer[1] << 8) + (buffer[2] << 16) + (buffer[3] <<
24);
- while ((c = stream->getch()) != 0)
- cout << c;
- cout << endl;
- break;
- case 64: // VT_FILETIME
- read = stream->read(buffer, 8);
- t1 = buffer[0] + (buffer[1] << 8) + (buffer[2] << 16) + (buffer[3] <<
24);
- t2 = buffer[4] + (buffer[5] << 8) + (buffer[6] << 16) + (buffer[7] <<
24);
- t = filetime_to_unixtime(t1, t2);
- s = ctime((time_t *) &t);
- cout << s;
- break;
- default:
- cout << "Unknown format " << type << endl;
- }
-}
-
-// show the revision data (users and files)
-void dumpRevision( POLE::Storage* storage ) {
- unsigned int nRev;
- unsigned int where = 0;
- POLE::Stream* stream;
-
- cout << "Revision:" << endl;
- cout << "---------" << endl << endl;
-
- // FIXME: should look if using 0Table or 1Table
- stream = storage->stream( "1Table" );
- if( !stream ) {
- cout << "There's no revision information" << endl;
- return;
- }
-
- unsigned char * buffer = new unsigned char[lcbSttbSavedBy];
- unsigned char buffer2[1024];
- unsigned int length;
-
- // goto offset of revision
- stream->seek(fcSttbSavedBy);
- // read all the revision history
- stream->read(buffer, lcbSttbSavedBy);
-
- // there are n strings, so n/2 revisions (author & file)
- nRev = (buffer[2] + (buffer[3] << 8)) / 2;
- where = 6;
-
- for (unsigned int i=0; i < nRev; i++) {
- cout << "Rev #" << i << ": Author \"";
- length = buffer[where++];
- // it's unicode, for now we only get the low byte
- for (unsigned int j=0; j < length; j++) {
- where++;
- cout << buffer[where];
- where++;
- }
- where++;
- cout << "\" worked on file \"";
- length = buffer[where++];
- // it's unicode, for now we only get the low byte
- for (unsigned int j=0; j < length; j++) {
- where++;
- cout << buffer[where];
- where++;
- }
- where++;
- cout << "\"" << endl;
- }
-
- cout << endl;
- delete buffer;
-
-}
-
-// show data from DocumentSummary stream
-void dumpDocumentSummary( POLE::Storage* storage ) {
- POLE::Stream* stream;
- unsigned long read, nproperties, propertyID, offsetProp, offsetCur;
- unsigned long begin;
-
- cout << "Document Summary:" << endl;
- cout << "-----------------" << endl << endl;
-
- stream = storage->stream( "DocumentSummaryInformation" );
- if( !stream ) {
- cout << "There's no document summary information" << endl;
- return;
- }
-
- unsigned char buffer[256];
-
- // ClassID & Offset
- stream->seek(28);
- stream->read(buffer, 20);
- // beginning of section
- begin = stream->tell();
- // length of section
- read = stream->read(buffer, 4);
- // number of properties
- read = stream->read(buffer, 4);
- nproperties = buffer[0] + (buffer[1] << 8) + (buffer[2] << 16) + (buffer[3]
<< 24);
- // properties
-
- for (unsigned long i = 0; i < nproperties; i++) {
- read = stream->read(buffer, 8);
- propertyID = buffer[0] + (buffer[1] << 8) + (buffer[2] << 16) + (buffer[3]
<< 24);
- offsetProp = buffer[4] + (buffer[5] << 8) + (buffer[6] << 16) + (buffer[7]
<< 24);
- if (propertyID > 1 && propertyID < 16) {
- cout << DocumentSummaryProperties[propertyID] << ": ";
- offsetCur = stream->tell();
- stream->seek(offsetProp + begin);
- // read and show the property
- showProperty(stream);
- stream->seek(offsetCur);
- }
- }
-
- cout << endl;
-}
-
-// show data from Summary stream
-void dumpSummary( POLE::Storage* storage ) {
- POLE::Stream* stream;
- unsigned long read, nproperties, propertyID, offsetProp, offsetCur;
- unsigned long begin;
-
- cout << "Summary:" << endl;
- cout << "--------" << endl << endl;
-
- stream = storage->stream( "SummaryInformation" );
- if( !stream ) {
- cout << "There's no summary information" << endl;
- return;
- }
-
- unsigned char buffer[256];
-
- // ClassID & Offset
- stream->seek(28);
- stream->read(buffer, 20);
- // beginning of section
- begin = stream->tell();
- // length of section
- read = stream->read(buffer, 4);
- // number of properties
- read = stream->read(buffer, 4);
- nproperties = buffer[0] + (buffer[1] << 8) + (buffer[2] << 16) + (buffer[3]
<< 24);
- // properties
- for (unsigned long i = 0; i < nproperties; i++) {
- read = stream->read(buffer, 8);
- propertyID = buffer[0] + (buffer[1] << 8) + (buffer[2] << 16) + (buffer[3]
<< 24);
- offsetProp = buffer[4] + (buffer[5] << 8) + (buffer[6] << 16) + (buffer[7]
<< 24);
- if (propertyID > 1 && propertyID < 20) {
- cout << SummaryProperties[propertyID] << ": ";
- offsetCur = stream->tell();
- stream->seek(offsetProp + begin);
- // read and show the property
- showProperty(stream);
- stream->seek(offsetCur);
- }
- }
-
- cout << endl;
-}
-
-// reads the header of the file
-bool readFIB( char* filename ) {
- fstream file;
-
- file.open( filename, std::ios::binary | std::ios::in );
- if( !file.good() ) {
- cout << "Can't find the file" << endl;
- return false;
- }
-
- unsigned char * buffer = new unsigned char[898];
- file.seekg( 512 );
- file.read( (char*)buffer, 898 );
- file.close();
-
- unsigned int wIdent = buffer[0] + (buffer[1] << 8);
- unsigned int nProduct = buffer[4] + (buffer[5] << 8);
- unsigned int lid = buffer[6] + (buffer[7] << 8);
- unsigned int envr = buffer[18];
- unsigned int wMagicCreated = buffer[34] + (buffer[35] << 8);
- unsigned int wMagicRevised = buffer[36] + (buffer[37] << 8);
- unsigned long lProductCreated = buffer[68] + (buffer[69] << 8) + (buffer[70]
<< 16) + (buffer[71] << 24);
- unsigned long lProductRevised = buffer[72] + (buffer[73] << 8) + (buffer[74]
<< 16) + (buffer[75] << 24);
- fcSttbSavedBy = buffer[722] + (buffer[723] << 8) + (buffer[724] << 16) +
(buffer[725] << 24);
- lcbSttbSavedBy = buffer[726] + (buffer[727] << 8) + (buffer[728] << 16) +
(buffer[729] << 24);
- delete[] buffer;
-
- cout << "File: " << filename << endl;
- cout << "Product version: " << nProduct << endl;
- cout << "Language: " << lidToLanguage(lid) << endl;
- cout << "Created by: " << idToProduct(wMagicCreated) << " (Build " <<
dateToString(lProductCreated) << ")" << endl;
- cout << "Revised by: " << idToProduct(wMagicRevised) << " (Build " <<
dateToString(lProductRevised) << ")" << endl;
- cout << endl;
-
- return true;
-
-}
-
-int main(int argc, char *argv[]) {
- cout << endl << "WordLeaker v.0.1" << endl;
- cout << " by Madelman (http://elligre.tk/madelman/)" << endl << endl;
-
-
- if( argc < 2 ) {
- cout << " You must supply a filename" << endl << endl;
- return 0;
- }
-
- char* filename = argv[1];
-
- if ( !readFIB(filename) )
- return 1;
-
- POLE::Storage* storage = new POLE::Storage( filename );
- storage->open();
- if( storage->result() != POLE::Storage::Ok ) {
- cout << "The file " << filename << " is not a Word document" << endl;
- return 1;
- }
-
- dumpSummary( storage );
- // FIXME: doesn't always work
- // but there's nothing really interesting in here
- //dumpDocumentSummary( storage );
- dumpRevision( storage );
- // TODO: we don't show the GUID
- // TODO: we don't show the macros
-
- delete storage;
-
- return 0;
-}
-
Deleted: Extractor/src/plugins/wordleaker/WordLeaker.h
===================================================================
--- Extractor/src/plugins/wordleaker/WordLeaker.h 2006-02-22 18:21:26 UTC
(rev 2465)
+++ Extractor/src/plugins/wordleaker/WordLeaker.h 2006-03-08 13:52:16 UTC
(rev 2466)
@@ -1,287 +0,0 @@
-/*
- WordLeaker - Shows information about Word DOC files
- Copyright (C) 2005 Sacha Fuentes <address@hidden>
-
- Based on poledump.c
- Original idea from WordDumper (http://www.computerbytesman.com)
- Info on Word format: http://www.aozw65.dsl.pipex.com/generator_wword8.htm
- Info on Word format: http://jakarta.apache.org/poi/hpsf/internals.html
-
- This program is free software; you can redistribute it and/or
- modify it under the terms of the GNU General Public
- License as published by the Free Software Foundation; either
- version 2 of the License, or (at your option) any later version.
-
- This program 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
- General Public License for more details.
-
- You should have received a copy of the GNU General Public License
- along with this library; see the file COPYING. If not, write to
- the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
- Boston, MA 02111-1307, US
-*/
-
-#include <string>
-
-using namespace std;
-
-static char* SummaryProperties[] = {
-"Unknown",
-"Unknown",
-"Title",
-"Subject",
-"Author",
-"Keywords",
-"Comments",
-"Template",
-"Last Saved By",
-"Revision Number",
-"Total Editing Time",
-"Last Printed",
-"Create Time/Date",
-"Last Saved Time/Date",
-"Number of Pages",
-"Number of Words",
-"Number of Characters",
-"Thumbnails",
-"Creating Application",
-"Security"
-};
-
-static char* DocumentSummaryProperties[] = {
-"Dictionary",
-"Code page",
-"Category",
-"PresentationTarget",
-"Bytes",
-"Lines",
-"Paragraphs",
-"Slides",
-"Notes",
-"HiddenSlides",
-"MMClips",
-"ScaleCrop",
-"HeadingPairs",
-"TitlesofParts",
-"Manager",
-"Company",
-"LinksUpTo"
-};
-
-string dateToString( unsigned long date ) {
- char f[9];
- sprintf(f, "%d/%d/%d", (date / 10000 % 100), (date / 100 % 100), (date %
100));
- return f;
-}
-
-string idToProduct( unsigned int id ) {
- // TODO: find the rest of ids
- switch ( id ) {
- case 0x6A62:
- return "Word 97";
- case 0x626A:
- return "Word 98 (Mac)";
- default:
- return "Unknown";
- }
-}
-
-string lidToLanguage( unsigned int lid ) {
- switch ( lid ) {
- case 0x0400:
- return "No Proofing";
- case 0x0401:
- return "Arabic";
- case 0x0402:
- return "Bulgarian";
- case 0x0403:
- return "Catalan";
- case 0x0404:
- return "Traditional Chinese";
- case 0x0804:
- return "Simplified Chinese";
- case 0x0405:
- return "Czech";
- case 0x0406:
- return "Danish";
- case 0x0407:
- return "German";
- case 0x0807:
- return "Swiss German";
- case 0x0408:
- return "Greek";
- case 0x0409:
- return "U.S. English";
- case 0x0809:
- return "U.K. English";
- case 0x0c09:
- return "Australian English";
- case 0x040a:
- return "Castilian Spanish";
- case 0x080a:
- return "Mexican Spanish";
- case 0x040b:
- return "Finnish";
- case 0x040c:
- return "French";
- case 0x080c:
- return "Belgian French";
- case 0x0c0c:
- return "Canadian French";
- case 0x100c:
- return "Swiss French";
- case 0x040d:
- return "Hebrew";
- case 0x040e:
- return "Hungarian";
- case 0x040f:
- return "Icelandic";
- case 0x0410:
- return "Italian";
- case 0x0810:
- return "Swiss Italian";
- case 0x0411:
- return "Japanese";
- case 0x0412:
- return "Korean";
- case 0x0413:
- return "Dutch";
- case 0x0813:
- return "Belgian Dutch";
- case 0x0414:
- return "Norwegian - Bokmal";
- case 0x0814:
- return "Norwegian - Nynorsk";
- case 0x0415:
- return "Polish";
- case 0x0416:
- return "Brazilian Portuguese";
- case 0x0816:
- return "Portuguese";
- case 0x0417:
- return "Rhaeto-Romanic";
- case 0x0418:
- return "Romanian";
- case 0x0419:
- return "Russian";
- case 0x041a:
- return "Croato-Serbian (Latin)";
- case 0x081a:
- return "Serbo-Croatian (Cyrillic)";
- case 0x041b:
- return "Slovak";
- case 0x041c:
- return "Albanian";
- case 0x041d:
- return "Swedish";
- case 0x041e:
- return "Thai";
- case 0x041f:
- return "Turkish";
- case 0x0420:
- return "Urdu";
- case 0x0421:
- return "Bahasa";
- case 0x0422:
- return "Ukrainian";
- case 0x0423:
- return "Byelorussian";
- case 0x0424:
- return "Slovenian";
- case 0x0425:
- return "Estonian";
- case 0x0426:
- return "Latvian";
- case 0x0427:
- return "Lithuanian";
- case 0x0429:
- return "Farsi";
- case 0x042D:
- return "Basque";
- case 0x042F:
- return "Macedonian";
- case 0x0436:
- return "Afrikaans";
- case 0x043E:
- return "Malaysian";
- default:
- return "Unknown";
- }
-}
-
-/*
- * filetime_to_unixtime
- *
- * Adapted from work in 'wv' by:
- * Caolan McNamara (address@hidden)
- */
-#define HIGH32_DELTA 27111902
-#define MID16_DELTA 54590
-#define LOW16_DELTA 32768
-
-unsigned long filetime_to_unixtime (unsigned long low_time, unsigned long
high_time) {
- unsigned long low16;/* 16 bit, low bits */
- unsigned long mid16;/* 16 bit, medium bits */
- unsigned long hi32;/* 32 bit, high bits */
- unsigned int carry;/* carry bit for subtraction */
- int negative;/* whether a represents a negative value */
-
-/* Copy the time values to hi32/mid16/low16 */
-hi32 = high_time;
-mid16 = low_time >> 16;
-low16 = low_time & 0xffff;
-
-/* Subtract the time difference */
-if (low16 >= LOW16_DELTA )
-low16 -= LOW16_DELTA , carry = 0;
-else
-low16 += (1 << 16) - LOW16_DELTA , carry = 1;
-
-if (mid16 >= MID16_DELTA + carry)
-mid16 -= MID16_DELTA + carry, carry = 0;
-else
-mid16 += (1 << 16) - MID16_DELTA - carry, carry = 1;
-
-hi32 -= HIGH32_DELTA + carry;
-
-/* If a is negative, replace a by (-1-a) */
-negative = (hi32 >= ((unsigned long)1) << 31);
-if (negative) {
-/* Set a to -a - 1 (a is hi32/mid16/low16) */
-low16 = 0xffff - low16;
-mid16 = 0xffff - mid16;
-hi32 = ~hi32;
-}
-
-/*
- * Divide a by 10000000 (a = hi32/mid16/low16), put the rest into r.
- * Split the divisor into 10000 * 1000 which are both less than 0xffff.
- */
-mid16 += (hi32 % 10000) << 16;
-hi32 /= 10000;
-low16 += (mid16 % 10000) << 16;
-mid16 /= 10000;
-low16 /= 10000;
-
-mid16 += (hi32 % 1000) << 16;
-hi32 /= 1000;
-low16 += (mid16 % 1000) << 16;
-mid16 /= 1000;
-low16 /= 1000;
-
-/* If a was negative, replace a by (-1-a) and r by (9999999 - r) */
-if (negative) {
-/* Set a to -a - 1 (a is hi32/mid16/low16) */
-low16 = 0xffff - low16;
-mid16 = 0xffff - mid16;
-hi32 = ~hi32;
-}
-
-/* Do not replace this by << 32, it gives a compiler warning and
- * it does not work
- */
-return ((((unsigned long)hi32) << 16) << 16) + (mid16 << 16) + low16;
-
-}
Added: Extractor/src/plugins/wordleaker/wordextractor.cc
===================================================================
--- Extractor/src/plugins/wordleaker/wordextractor.cc 2006-02-22 18:21:26 UTC
(rev 2465)
+++ Extractor/src/plugins/wordleaker/wordextractor.cc 2006-03-08 13:52:16 UTC
(rev 2466)
@@ -0,0 +1,221 @@
+/*
+ This file is part of libextractor.
+ (C) 2006 Vidyut Samanta and Christian Grothoff
+
+ libextractor is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published
+ by the Free Software Foundation; either version 2, or (at your
+ option) any later version.
+
+ libextractor 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
+ General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with libextractor; see the file COPYING. If not, write to the
+ Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ Boston, MA 02111-1307, USA.
+
+ This code depends heavily on the wordleaker code and
+ a lot of code was borrowed from wordleaker.cpp. See also
+ the README file in this directory.
+ */
+
+#include "platform.h"
+#include "extractor.h"
+#include "../convert.h"
+#include <math.h>
+
+#include "wordleaker.h"
+#include "pole.h"
+
+extern "C" {
+
+ static struct EXTRACTOR_Keywords * addKeyword(EXTRACTOR_KeywordType type,
+ const char * keyword,
+ struct EXTRACTOR_Keywords *
next) {
+ EXTRACTOR_KeywordList * result;
+
+ if (keyword == NULL)
+ return next;
+ result = (EXTRACTOR_KeywordList*) malloc(sizeof(EXTRACTOR_KeywordList));
+ result->next = next;
+ result->keyword = strdup(keyword);
+ result->keywordType = type;
+ return result;
+ }
+
+
+ // read the type of the property and displays its value
+ char * getProperty( POLE::Stream* stream ) {
+ unsigned long read, type;
+ unsigned char buffer[256];
+ unsigned char c;
+ unsigned long i;
+ unsigned int j;
+ unsigned long t, t1, t2;
+ char *s;
+
+ read = stream->read(buffer, 4);
+ type = buffer[0] + (buffer[1] << 8) + (buffer[2] << 16) + (buffer[3] <<
24);
+
+ switch (type) {
+ case 2: // VT_I2
+ read = stream->read(buffer, 2);
+ i = buffer[0] + (buffer[1] << 8);
+ s = (char*) malloc(16);
+ snprintf(s, 16, "%u", i);
+ return s;
+ case 3: // VT_I4
+ read = stream->read(buffer, 4);
+ i = buffer[0] + (buffer[1] << 8) + (buffer[2] << 16) + (buffer[3] << 24);
+ s = (char*) malloc(16);
+ snprintf(s, 16, "%u", i);
+ return s;
+ case 11: // VT_BOOL
+ read = stream->read(buffer, 1);
+ if ((char) buffer[0] == -1)
+ return strdup("true");
+ return strdup("false");
+ case 30: // VT_LPSTR
+ read = stream->read(buffer, 4);
+ i = buffer[0] + (buffer[1] << 8) + (buffer[2] << 16) + (buffer[3] << 24);
+ if ( (i < 0) || (i > 16*1024*1024))
+ return NULL;
+ s = (char*) malloc(i+1);
+ s[i] = '\0';
+ j = 0;
+ while ( ((c = stream->getch()) != 0) && (i > j) )
+ s[j++] = c;
+ if (j != i) {
+ free(s);
+ return NULL;
+ }
+ return s;
+ case 64: // VT_FILETIME
+ read = stream->read(buffer, 8);
+ t1 = buffer[0] + (buffer[1] << 8) + (buffer[2] << 16) + (buffer[3] <<
24);
+ t2 = buffer[4] + (buffer[5] << 8) + (buffer[6] << 16) + (buffer[7] <<
24);
+ t = filetime_to_unixtime(t1, t2);
+ return ctime_r((time_t *) &t, (char*)malloc(32));
+ }
+ return NULL;
+ }
+
+
+ struct EXTRACTOR_Keywords * libextractor_word_extract(const char * filename,
+ const char * data,
+ size_t size,
+ struct
EXTRACTOR_Keywords * prev) {
+ char ver[16];
+ if (size < 512 + 898)
+ return prev;
+ const unsigned char * buffer = (const unsigned char*) &data[512];
+ unsigned int wIdent = buffer[0] + (buffer[1] << 8);
+ unsigned int nProduct = buffer[4] + (buffer[5] << 8);
+ unsigned int lid = buffer[6] + (buffer[7] << 8);
+ unsigned int envr = buffer[18];
+ unsigned int wMagicCreated = buffer[34] + (buffer[35] << 8);
+ unsigned int wMagicRevised = buffer[36] + (buffer[37] << 8);
+ unsigned long lProductCreated = buffer[68] + (buffer[69] << 8) +
(buffer[70] << 16) + (buffer[71] << 24);
+ unsigned long lProductRevised = buffer[72] + (buffer[73] << 8) +
(buffer[74] << 16) + (buffer[75] << 24);
+ unsigned long fcSttbSavedBy = buffer[722] + (buffer[723] << 8) +
(buffer[724] << 16) + (buffer[725] << 24);
+ unsigned long lcbSttbSavedBy = buffer[726] + (buffer[727] << 8) +
(buffer[728] << 16) + (buffer[729] << 24);
+
+ snprintf(ver, 16, "%u", nProduct);
+ prev = addKeyword(EXTRACTOR_PRODUCTVERSION,
+ ver,
+ prev);
+ prev = addKeyword(EXTRACTOR_LANGUAGE,
+ lidToLanguage(lid),
+ prev);
+
+ // cout << "Created by: " << idToProduct(wMagicCreated) << " (Build " <<
dateToString(lProductCreated) << ")" << endl;
+ // cout << "Revised by: " << idToProduct(wMagicRevised) << " (Build " <<
dateToString(lProductRevised) << ")" << endl;
+
+ POLE::Storage* storage = new POLE::Storage( filename );
+ storage->open();
+ if( storage->result() != POLE::Storage::Ok )
+ return prev;
+
+ POLE::Stream * stream = storage->stream( "SummaryInformation" );
+ if (stream) {
+ unsigned char buffer[256];
+
+ // ClassID & Offset
+ stream->seek(28);
+ stream->read(buffer, 20);
+ // beginning of section
+ unsigned long begin = stream->tell();
+ // length of section
+ unsigned long read = stream->read(buffer, 4);
+ // number of properties
+ read = stream->read(buffer, 4);
+ unsigned int nproperties = buffer[0] + (buffer[1] << 8) + (buffer[2] <<
16) + (buffer[3] << 24);
+ // properties
+ for (unsigned int i = 0; i < nproperties; i++) {
+ read = stream->read(buffer, 8);
+ unsigned int propertyID = buffer[0] + (buffer[1] << 8) + (buffer[2] <<
16) + (buffer[3] << 24);
+ unsigned int offsetProp = buffer[4] + (buffer[5] << 8) + (buffer[6] <<
16) + (buffer[7] << 24);
+ if (propertyID > 1 && propertyID < 20) {
+ // cout << SummaryProperties[propertyID] << ": ";
+ unsigned long offsetCur = stream->tell();
+ stream->seek(offsetProp + begin);
+ // read and show the property
+ char * prop = getProperty(stream);
+ free(prop);
+ stream->seek(offsetCur);
+ }
+ }
+ }
+
+ unsigned int where = 0;
+
+ // FIXME: should look if using 0Table or 1Table
+ stream = storage->stream( "1Table" );
+ if (stream) {
+ unsigned char * buffer = new unsigned char[lcbSttbSavedBy];
+ unsigned char buffer2[1024];
+
+ // goto offset of revision
+ stream->seek(fcSttbSavedBy);
+ // read all the revision history
+ stream->read(buffer, lcbSttbSavedBy);
+
+ // there are n strings, so n/2 revisions (author & file)
+ unsigned int nRev = (buffer[2] + (buffer[3] << 8)) / 2;
+ where = 6;
+
+ for (unsigned int i=0; i < nRev; i++) {
+ // cout << "Rev #" << i << ": Author \"";
+ unsigned int length = buffer[where++];
+ // it's unicode, for now we only get the low byte
+ for (unsigned int j=0; j < length; j++) {
+ where++;
+ // cout << buffer[where];
+ where++;
+ }
+ where++;
+ // cout << "\" worked on file \"";
+ length = buffer[where++];
+ // it's unicode, for now we only get the low byte
+ for (unsigned int j=0; j < length; j++) {
+ where++;
+ // cout << buffer[where];
+ where++;
+ }
+ where++;
+ // cout << "\"" << endl;
+ }
+
+ delete buffer;
+
+ }
+ delete storage;
+
+ return prev;
+ }
+
+}
+
Copied: Extractor/src/plugins/wordleaker/wordleaker.cpp (from rev 2465,
Extractor/src/plugins/wordleaker/WordLeaker.cpp)
===================================================================
--- Extractor/src/plugins/wordleaker/WordLeaker.cpp 2006-02-22 18:21:26 UTC
(rev 2465)
+++ Extractor/src/plugins/wordleaker/wordleaker.cpp 2006-03-08 13:52:16 UTC
(rev 2466)
@@ -0,0 +1,311 @@
+/*
+ WordLeaker - Shows information about Word DOC files
+ Copyright (C) 2005 Sacha Fuentes <address@hidden>
+
+ Based on poledump.c
+ Original idea from WordDumper (http://www.computerbytesman.com)
+ Info on Word format: http://www.aozw65.dsl.pipex.com/generator_wword8.htm
+ Info on Word format: http://jakarta.apache.org/poi/hpsf/internals.html
+
+ This program is free software; you can redistribute it and/or
+ modify it under the terms of the GNU General Public
+ License as published by the Free Software Foundation; either
+ version 2 of the License, or (at your option) any later version.
+
+ This program 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
+ General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this library; see the file COPYING. If not, write to
+ the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ Boston, MA 02111-1307, US
+*/
+
+// TAKE CARE: there's not a single check for validity of data,
+// so any malformed or malicious Word file will break it
+
+#include <iostream>
+#include <fstream>
+#include <stdlib.h>
+#include <list>
+#include <ctime>
+
+#include "pole.h"
+#include "WordLeaker.h"
+
+unsigned long fcSttbSavedBy;
+unsigned long lcbSttbSavedBy;
+
+// read the type of the property and displays its value
+void showProperty( POLE::Stream* stream ) {
+ unsigned long read, type;
+ unsigned char buffer[256];
+ unsigned char c;
+ unsigned long i;
+ unsigned long t, t1, t2;
+ char *s;
+
+ read = stream->read(buffer, 4);
+ type = buffer[0] + (buffer[1] << 8) + (buffer[2] << 16) + (buffer[3] << 24);
+
+ switch (type) {
+ case 2: // VT_I2
+ read = stream->read(buffer, 2);
+ i = buffer[0] + (buffer[1] << 8);
+ cout << i << endl;
+ break;
+ case 3: // VT_I4
+ read = stream->read(buffer, 4);
+ i = buffer[0] + (buffer[1] << 8) + (buffer[2] << 16) + (buffer[3] <<
24);
+ cout << i << endl;
+ break;
+ case 11: // VT_BOOL
+ read = stream->read(buffer, 1);
+ if ((char) buffer[0] == -1)
+ cout << "true" << endl;
+ else
+ cout << "false" << endl;
+ break;
+ case 30: // VT_LPSTR
+ read = stream->read(buffer, 4);
+ i = buffer[0] + (buffer[1] << 8) + (buffer[2] << 16) + (buffer[3] <<
24);
+ while ((c = stream->getch()) != 0)
+ cout << c;
+ cout << endl;
+ break;
+ case 64: // VT_FILETIME
+ read = stream->read(buffer, 8);
+ t1 = buffer[0] + (buffer[1] << 8) + (buffer[2] << 16) + (buffer[3] <<
24);
+ t2 = buffer[4] + (buffer[5] << 8) + (buffer[6] << 16) + (buffer[7] <<
24);
+ t = filetime_to_unixtime(t1, t2);
+ s = ctime((time_t *) &t);
+ cout << s;
+ break;
+ default:
+ cout << "Unknown format " << type << endl;
+ }
+}
+
+// show the revision data (users and files)
+void dumpRevision( POLE::Storage* storage ) {
+ unsigned int nRev;
+ unsigned int where = 0;
+ POLE::Stream* stream;
+
+ cout << "Revision:" << endl;
+ cout << "---------" << endl << endl;
+
+ // FIXME: should look if using 0Table or 1Table
+ stream = storage->stream( "1Table" );
+ if( !stream ) {
+ cout << "There's no revision information" << endl;
+ return;
+ }
+
+ unsigned char * buffer = new unsigned char[lcbSttbSavedBy];
+ unsigned char buffer2[1024];
+ unsigned int length;
+
+ // goto offset of revision
+ stream->seek(fcSttbSavedBy);
+ // read all the revision history
+ stream->read(buffer, lcbSttbSavedBy);
+
+ // there are n strings, so n/2 revisions (author & file)
+ nRev = (buffer[2] + (buffer[3] << 8)) / 2;
+ where = 6;
+
+ for (unsigned int i=0; i < nRev; i++) {
+ cout << "Rev #" << i << ": Author \"";
+ length = buffer[where++];
+ // it's unicode, for now we only get the low byte
+ for (unsigned int j=0; j < length; j++) {
+ where++;
+ cout << buffer[where];
+ where++;
+ }
+ where++;
+ cout << "\" worked on file \"";
+ length = buffer[where++];
+ // it's unicode, for now we only get the low byte
+ for (unsigned int j=0; j < length; j++) {
+ where++;
+ cout << buffer[where];
+ where++;
+ }
+ where++;
+ cout << "\"" << endl;
+ }
+
+ cout << endl;
+ delete buffer;
+
+}
+
+// show data from DocumentSummary stream
+void dumpDocumentSummary( POLE::Storage* storage ) {
+ POLE::Stream* stream;
+ unsigned long read, nproperties, propertyID, offsetProp, offsetCur;
+ unsigned long begin;
+
+ cout << "Document Summary:" << endl;
+ cout << "-----------------" << endl << endl;
+
+ stream = storage->stream( "DocumentSummaryInformation" );
+ if( !stream ) {
+ cout << "There's no document summary information" << endl;
+ return;
+ }
+
+ unsigned char buffer[256];
+
+ // ClassID & Offset
+ stream->seek(28);
+ stream->read(buffer, 20);
+ // beginning of section
+ begin = stream->tell();
+ // length of section
+ read = stream->read(buffer, 4);
+ // number of properties
+ read = stream->read(buffer, 4);
+ nproperties = buffer[0] + (buffer[1] << 8) + (buffer[2] << 16) + (buffer[3]
<< 24);
+ // properties
+
+ for (unsigned long i = 0; i < nproperties; i++) {
+ read = stream->read(buffer, 8);
+ propertyID = buffer[0] + (buffer[1] << 8) + (buffer[2] << 16) + (buffer[3]
<< 24);
+ offsetProp = buffer[4] + (buffer[5] << 8) + (buffer[6] << 16) + (buffer[7]
<< 24);
+ if (propertyID > 1 && propertyID < 16) {
+ cout << DocumentSummaryProperties[propertyID] << ": ";
+ offsetCur = stream->tell();
+ stream->seek(offsetProp + begin);
+ // read and show the property
+ showProperty(stream);
+ stream->seek(offsetCur);
+ }
+ }
+
+ cout << endl;
+}
+
+// show data from Summary stream
+void dumpSummary( POLE::Storage* storage ) {
+ POLE::Stream* stream;
+ unsigned long read, nproperties, propertyID, offsetProp, offsetCur;
+ unsigned long begin;
+
+ cout << "Summary:" << endl;
+ cout << "--------" << endl << endl;
+
+ stream = storage->stream( "SummaryInformation" );
+ if( !stream ) {
+ cout << "There's no summary information" << endl;
+ return;
+ }
+
+ unsigned char buffer[256];
+
+ // ClassID & Offset
+ stream->seek(28);
+ stream->read(buffer, 20);
+ // beginning of section
+ begin = stream->tell();
+ // length of section
+ read = stream->read(buffer, 4);
+ // number of properties
+ read = stream->read(buffer, 4);
+ nproperties = buffer[0] + (buffer[1] << 8) + (buffer[2] << 16) + (buffer[3]
<< 24);
+ // properties
+ for (unsigned long i = 0; i < nproperties; i++) {
+ read = stream->read(buffer, 8);
+ propertyID = buffer[0] + (buffer[1] << 8) + (buffer[2] << 16) + (buffer[3]
<< 24);
+ offsetProp = buffer[4] + (buffer[5] << 8) + (buffer[6] << 16) + (buffer[7]
<< 24);
+ if (propertyID > 1 && propertyID < 20) {
+ cout << SummaryProperties[propertyID] << ": ";
+ offsetCur = stream->tell();
+ stream->seek(offsetProp + begin);
+ // read and show the property
+ showProperty(stream);
+ stream->seek(offsetCur);
+ }
+ }
+
+ cout << endl;
+}
+
+// reads the header of the file
+bool readFIB( char* filename ) {
+ fstream file;
+
+ file.open( filename, std::ios::binary | std::ios::in );
+ if( !file.good() ) {
+ cout << "Can't find the file" << endl;
+ return false;
+ }
+
+ unsigned char * buffer = new unsigned char[898];
+ file.seekg( 512 );
+ file.read( (char*)buffer, 898 );
+ file.close();
+
+ unsigned int wIdent = buffer[0] + (buffer[1] << 8);
+ unsigned int nProduct = buffer[4] + (buffer[5] << 8);
+ unsigned int lid = buffer[6] + (buffer[7] << 8);
+ unsigned int envr = buffer[18];
+ unsigned int wMagicCreated = buffer[34] + (buffer[35] << 8);
+ unsigned int wMagicRevised = buffer[36] + (buffer[37] << 8);
+ unsigned long lProductCreated = buffer[68] + (buffer[69] << 8) + (buffer[70]
<< 16) + (buffer[71] << 24);
+ unsigned long lProductRevised = buffer[72] + (buffer[73] << 8) + (buffer[74]
<< 16) + (buffer[75] << 24);
+ fcSttbSavedBy = buffer[722] + (buffer[723] << 8) + (buffer[724] << 16) +
(buffer[725] << 24);
+ lcbSttbSavedBy = buffer[726] + (buffer[727] << 8) + (buffer[728] << 16) +
(buffer[729] << 24);
+ delete[] buffer;
+
+ cout << "File: " << filename << endl;
+ cout << "Product version: " << nProduct << endl;
+ cout << "Language: " << lidToLanguage(lid) << endl;
+ cout << "Created by: " << idToProduct(wMagicCreated) << " (Build " <<
dateToString(lProductCreated) << ")" << endl;
+ cout << "Revised by: " << idToProduct(wMagicRevised) << " (Build " <<
dateToString(lProductRevised) << ")" << endl;
+ cout << endl;
+
+ return true;
+
+}
+
+#if HAVE_MAIN
+int main(int argc, char *argv[]) {
+ cout << endl << "WordLeaker v.0.1" << endl;
+ cout << " by Madelman (http://elligre.tk/madelman/)" << endl << endl;
+
+
+ if( argc < 2 ) {
+ cout << " You must supply a filename" << endl << endl;
+ return 0;
+ }
+
+ char* filename = argv[1];
+
+ if ( !readFIB(filename) )
+ return 1;
+
+ POLE::Storage* storage = new POLE::Storage( filename );
+ storage->open();
+ if( storage->result() != POLE::Storage::Ok ) {
+ cout << "The file " << filename << " is not a Word document" << endl;
+ return 1;
+ }
+
+ dumpSummary( storage );
+ // FIXME: doesn't always work
+ // but there's nothing really interesting in here
+ //dumpDocumentSummary( storage );
+ dumpRevision( storage );
+ // TODO: we don't show the GUID
+ // TODO: we don't show the macros
+
+ delete storage;
+
+ return 0;
+}
+#endif
Copied: Extractor/src/plugins/wordleaker/wordleaker.h (from rev 2465,
Extractor/src/plugins/wordleaker/WordLeaker.h)
===================================================================
--- Extractor/src/plugins/wordleaker/WordLeaker.h 2006-02-22 18:21:26 UTC
(rev 2465)
+++ Extractor/src/plugins/wordleaker/wordleaker.h 2006-03-08 13:52:16 UTC
(rev 2466)
@@ -0,0 +1,287 @@
+/*
+ WordLeaker - Shows information about Word DOC files
+ Copyright (C) 2005 Sacha Fuentes <address@hidden>
+
+ Based on poledump.c
+ Original idea from WordDumper (http://www.computerbytesman.com)
+ Info on Word format: http://www.aozw65.dsl.pipex.com/generator_wword8.htm
+ Info on Word format: http://jakarta.apache.org/poi/hpsf/internals.html
+
+ This program is free software; you can redistribute it and/or
+ modify it under the terms of the GNU General Public
+ License as published by the Free Software Foundation; either
+ version 2 of the License, or (at your option) any later version.
+
+ This program 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
+ General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this library; see the file COPYING. If not, write to
+ the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ Boston, MA 02111-1307, US
+*/
+
+#include <string>
+
+using namespace std;
+
+static char* SummaryProperties[] = {
+"Unknown",
+"Unknown",
+"Title",
+"Subject",
+"Author",
+"Keywords",
+"Comments",
+"Template",
+"Last Saved By",
+"Revision Number",
+"Total Editing Time",
+"Last Printed",
+"Create Time/Date",
+"Last Saved Time/Date",
+"Number of Pages",
+"Number of Words",
+"Number of Characters",
+"Thumbnails",
+"Creating Application",
+"Security"
+};
+
+static char* DocumentSummaryProperties[] = {
+"Dictionary",
+"Code page",
+"Category",
+"PresentationTarget",
+"Bytes",
+"Lines",
+"Paragraphs",
+"Slides",
+"Notes",
+"HiddenSlides",
+"MMClips",
+"ScaleCrop",
+"HeadingPairs",
+"TitlesofParts",
+"Manager",
+"Company",
+"LinksUpTo"
+};
+
+string dateToString( unsigned long date ) {
+ char f[9];
+ sprintf(f, "%d/%d/%d", (date / 10000 % 100), (date / 100 % 100), (date %
100));
+ return f;
+}
+
+string idToProduct( unsigned int id ) {
+ // TODO: find the rest of ids
+ switch ( id ) {
+ case 0x6A62:
+ return "Word 97";
+ case 0x626A:
+ return "Word 98 (Mac)";
+ default:
+ return "Unknown";
+ }
+}
+
+const char * lidToLanguage( unsigned int lid ) {
+ switch ( lid ) {
+ case 0x0400:
+ return "No Proofing";
+ case 0x0401:
+ return "Arabic";
+ case 0x0402:
+ return "Bulgarian";
+ case 0x0403:
+ return "Catalan";
+ case 0x0404:
+ return "Traditional Chinese";
+ case 0x0804:
+ return "Simplified Chinese";
+ case 0x0405:
+ return "Czech";
+ case 0x0406:
+ return "Danish";
+ case 0x0407:
+ return "German";
+ case 0x0807:
+ return "Swiss German";
+ case 0x0408:
+ return "Greek";
+ case 0x0409:
+ return "U.S. English";
+ case 0x0809:
+ return "U.K. English";
+ case 0x0c09:
+ return "Australian English";
+ case 0x040a:
+ return "Castilian Spanish";
+ case 0x080a:
+ return "Mexican Spanish";
+ case 0x040b:
+ return "Finnish";
+ case 0x040c:
+ return "French";
+ case 0x080c:
+ return "Belgian French";
+ case 0x0c0c:
+ return "Canadian French";
+ case 0x100c:
+ return "Swiss French";
+ case 0x040d:
+ return "Hebrew";
+ case 0x040e:
+ return "Hungarian";
+ case 0x040f:
+ return "Icelandic";
+ case 0x0410:
+ return "Italian";
+ case 0x0810:
+ return "Swiss Italian";
+ case 0x0411:
+ return "Japanese";
+ case 0x0412:
+ return "Korean";
+ case 0x0413:
+ return "Dutch";
+ case 0x0813:
+ return "Belgian Dutch";
+ case 0x0414:
+ return "Norwegian - Bokmal";
+ case 0x0814:
+ return "Norwegian - Nynorsk";
+ case 0x0415:
+ return "Polish";
+ case 0x0416:
+ return "Brazilian Portuguese";
+ case 0x0816:
+ return "Portuguese";
+ case 0x0417:
+ return "Rhaeto-Romanic";
+ case 0x0418:
+ return "Romanian";
+ case 0x0419:
+ return "Russian";
+ case 0x041a:
+ return "Croato-Serbian (Latin)";
+ case 0x081a:
+ return "Serbo-Croatian (Cyrillic)";
+ case 0x041b:
+ return "Slovak";
+ case 0x041c:
+ return "Albanian";
+ case 0x041d:
+ return "Swedish";
+ case 0x041e:
+ return "Thai";
+ case 0x041f:
+ return "Turkish";
+ case 0x0420:
+ return "Urdu";
+ case 0x0421:
+ return "Bahasa";
+ case 0x0422:
+ return "Ukrainian";
+ case 0x0423:
+ return "Byelorussian";
+ case 0x0424:
+ return "Slovenian";
+ case 0x0425:
+ return "Estonian";
+ case 0x0426:
+ return "Latvian";
+ case 0x0427:
+ return "Lithuanian";
+ case 0x0429:
+ return "Farsi";
+ case 0x042D:
+ return "Basque";
+ case 0x042F:
+ return "Macedonian";
+ case 0x0436:
+ return "Afrikaans";
+ case 0x043E:
+ return "Malaysian";
+ default:
+ return "Unknown";
+ }
+}
+
+/*
+ * filetime_to_unixtime
+ *
+ * Adapted from work in 'wv' by:
+ * Caolan McNamara (address@hidden)
+ */
+#define HIGH32_DELTA 27111902
+#define MID16_DELTA 54590
+#define LOW16_DELTA 32768
+
+unsigned long filetime_to_unixtime (unsigned long low_time, unsigned long
high_time) {
+ unsigned long low16;/* 16 bit, low bits */
+ unsigned long mid16;/* 16 bit, medium bits */
+ unsigned long hi32;/* 32 bit, high bits */
+ unsigned int carry;/* carry bit for subtraction */
+ int negative;/* whether a represents a negative value */
+
+/* Copy the time values to hi32/mid16/low16 */
+hi32 = high_time;
+mid16 = low_time >> 16;
+low16 = low_time & 0xffff;
+
+/* Subtract the time difference */
+if (low16 >= LOW16_DELTA )
+low16 -= LOW16_DELTA , carry = 0;
+else
+low16 += (1 << 16) - LOW16_DELTA , carry = 1;
+
+if (mid16 >= MID16_DELTA + carry)
+mid16 -= MID16_DELTA + carry, carry = 0;
+else
+mid16 += (1 << 16) - MID16_DELTA - carry, carry = 1;
+
+hi32 -= HIGH32_DELTA + carry;
+
+/* If a is negative, replace a by (-1-a) */
+negative = (hi32 >= ((unsigned long)1) << 31);
+if (negative) {
+/* Set a to -a - 1 (a is hi32/mid16/low16) */
+low16 = 0xffff - low16;
+mid16 = 0xffff - mid16;
+hi32 = ~hi32;
+}
+
+/*
+ * Divide a by 10000000 (a = hi32/mid16/low16), put the rest into r.
+ * Split the divisor into 10000 * 1000 which are both less than 0xffff.
+ */
+mid16 += (hi32 % 10000) << 16;
+hi32 /= 10000;
+low16 += (mid16 % 10000) << 16;
+mid16 /= 10000;
+low16 /= 10000;
+
+mid16 += (hi32 % 1000) << 16;
+hi32 /= 1000;
+low16 += (mid16 % 1000) << 16;
+mid16 /= 1000;
+low16 /= 1000;
+
+/* If a was negative, replace a by (-1-a) and r by (9999999 - r) */
+if (negative) {
+/* Set a to -a - 1 (a is hi32/mid16/low16) */
+low16 = 0xffff - low16;
+mid16 = 0xffff - mid16;
+hi32 = ~hi32;
+}
+
+/* Do not replace this by << 32, it gives a compiler warning and
+ * it does not work
+ */
+return ((((unsigned long)hi32) << 16) << 16) + (mid16 << 16) + low16;
+
+}
| [Prev in Thread] |
Current Thread |
[Next in Thread] |
- [GNUnet-SVN] r2466 - in Extractor: . src/include src/main src/plugins/wordleaker,
grothoff <=