docx2txt-1.4/docx2txt.bat0000644000175100010010000001070711261356666014200 0ustar manojNone@echo off :: docx2txt, a command-line utility to convert Docx documents to text format. :: Copyright (C) 2008-now Sandeep Kumar :: :: 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 3 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 program; if not, write to the Free Software :: Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA :: :: A simple commandline .docx to .txt converter :: :: This batch file is a wrapper around core docx2txt.pl script. :: :: Author : Sandeep Kumar (shimple0 -AT- Yahoo .DOT. COM) :: :: ChangeLog : :: :: 17/09/2009 - Initial version of this file. It has similar functionality :: as corresponding unix shell script. :: 21/09/2009 - Updations to deal with paths containing spacess. :: 22/09/2009 - Code reorganization, mainly around delayedexpansion command :: extension. :: 24/09/2009 - Required docx2txt.pl is expected in same location as this :: batch file. :: :: :: Set path (without surrounding quotes) to perl binary. :: set PERL=C:\Program Files\strawberry-perl-5.10.0.6\perl\bin\perl.exe :: :: If CAKECMD variable is set, batch file will unzip the content of argument :: .docx file in a directory and pass that directory as the argument to the :: docx2txt.pl script. :: :: set CAKECMD=C:\Program Files\cake\CakeCmd.exe :: :: Ensure that required command extensions are enabled. :: setlocal enableextensions setlocal enabledelayedexpansion :: :: docx2txt.pl is expected to be in same location as this batch file. :: set DOCX2TXT_PL=%~dp0docx2txt.pl if not exist "%DOCX2TXT_PL%" ( echo. echo Can not continue without "%DOCX2TXT_PL%". echo. goto END ) :: :: Check if this batch file is invoked correctly. :: if "%~1" == "" goto USAGE if not "%~2" == "" goto USAGE goto CHECK_ARG :USAGE echo. echo Usage : "%~0" file.docx echo. echo "file.docx" can also specify a directory holding the unzipped echo content of a .docx file. echo. goto END :: :: Check if argument specifies a directory or a file. :: :CHECK_ARG set INPARG=%~1 if exist %~s1\nul ( set ARGISDIR=y :: Remove any trailing '\'s from input directory name. :INP_IS_DIR set LastChar=%INPARG:~-1% if not "!LastChar!" == "\" goto GENERATE_TXTFILE_NAME set INPARG=%INPARG:~0,-1% goto INP_IS_DIR ) else if not exist "%~1" ( echo. echo Argument file/directory "%~1" does not exist. echo. goto END ) :: :: Generate output textfile name from input argument. :: :GENERATE_TXTFILE_NAME set FILEEXT=%INPARG:~-5% if "%FILEEXT%" == ".docx" ( set TXTFILE=%INPARG:~0,-5%.txt ) else ( set TXTFILE=%INPARG%.txt ) :: :: Check whether output text file already exists, and whether user wants to :: overwrite that. :: if exist "%TXTFILE%" ( echo. echo Output file "%TXTFILE%" already exists. set /P confirm=Overwrite "%TXTFILE%" [Y/N - Default Y] ? if /I "!confirm!" == "N" ( echo. echo Please copy "%TXTFILE%" somewhere else and rerun this batch file. echo. goto END ) ) :: :: Since docx2txt.pl script expects an unzipper that can send the extracted :: file to stdout. If CakeCmd.exe is being used as unzipper, then extract the :: contents into a directory and pass that directory as the argument to the :: perl script. :: if defined ARGISDIR goto CONVERT if defined CAKECMD ( rename "%~1" "%~1.zip" echo y | "%CAKECMD%" extract "%~1.zip" \ "%~1" > nul set RENAMEBACK=yes ) :: :: Invoke docx2txt.pl perl script to do the actual text extraction :: :CONVERT "%PERL%" "%DOCX2TXT_PL%" "%INPARG%" "%TXTFILE%" if %ERRORLEVEL% == 2 ( echo. echo Failed to extract text from "%~1"! echo. ) else if %ERRORLEVEL% == 0 ( echo. echo Text extracted from "%~1" is available in "%TXTFILE%". echo. ) :END if defined RENAMEBACK ( rmdir /S /Q "%~1" rename "%~1.zip" "%~1" ) endlocal endlocal set PERL= set DOCX2TXT_PL= set CAKECMD= set FILEEXT= set INPARG= set TXTFILE= set ARGISDIR= set RENAMEBACK= set confirm= docx2txt-1.4/docx2txt.config0000644000175100010010000000332012335201322014645 0ustar manojNone# # User controllable configuration parameters for docx2txt.pl # # Note: # - Ensure that all configuration lines end with single comma (,). # - Lines beginning with '#' are comments. # # # Specify the path to "unzip" command. # # Windows users should specify this path like # # 'C:\Cygwin\bin\unzip.exe' (With Windows native perl.exe) # Or # 'C:/Cygwin/bin/unzip.exe' (With Cygwin/Windows native perl.exe) # # Default : '/usr/bin/unzip' # config_unzip => '/usr/bin/unzip', # # Specify the commandline option(s) to be supplied to the program specified in # config_unzip, that allow silent extraction of specified file from zip archive # to console/standard output/pipe. # # Default : '-p' (for unzip) # # config_unzip_opts => '-p', # # How the newline should be in output text file - "\n" or "\r\n". # # Default : "\n" # # config_newLine => "\n", # # Line width to use for short line (single line paragraph) justifiction. # # Default : 80 # # config_lineWidth => 80, # # Show hyperlink alongside linked text - [yY/nN] # # Note: Even if this option is enabled, hyperlinks will be shown only if # hyperlink differs from the linked text. # # Default : N # config_showHyperLink => "Y", # # Directory for creation of temporary file. # # In case input is provided via STDIN (standard input), it is first stored in a # temporary file and then further processing is done using that file. # Same path specification rules apply here as in case of config_unzip. # # Default : "/tmp" (Non-Windows OSes), Environment variable "TEMP" (Windows) # # config_tempDir => "/path/to/your/temp/directory", # # Approximate mapping of twips to character for layout purpose. # # Default : 120 # config_twipsPerChar => 240, docx2txt-1.4/docx2txt.pl0000755000175100010010000005210412334442444014035 0ustar manojNone#!/usr/bin/env perl # docx2txt, a command-line utility to convert Docx documents to text format. # Copyright (C) 2008-2014 Sandeep Kumar # # 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 3 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 program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA # # This script extracts text from document.xml contained inside .docx file. # Perl v5.10.1 was used for testing this script. # # Author : Sandeep Kumar (shimple0 -AT- Yahoo .DOT. COM) # # ChangeLog : # # 10/08/2008 - Initial version (v0.1) # 15/08/2008 - Script takes two arguments [second optional] now and can be # used independently to extract text from docx file. It accepts # docx file directly, instead of xml file. # 18/08/2008 - Added support for center and right justification of text that # fits in a line 80 characters wide (adjustable). # 03/09/2008 - Fixed the slip in usage message. # 12/09/2008 - Slightly changed the script invocation and argument handling # to incorporate some of the shell script functionality here. # Added support to handle embedded urls in docx document. # 23/09/2008 - Changed #! line to use /usr/bin/env - good suggestion from # Rene Maroufi (info>ATDOTATDOTATDOT '&', apos => '\'', gt => '>', lt => '<', quot => '"', acute => '\'', brvbar => '|', copy => '(C)', divide => '/', laquo => '<<', macr => '-', nbsp => ' ', raquo => '>>', reg => '(R)', shy => '-', times => 'x' ); my %splchars = ( "\xC2" => { "\xA0" => ' ', # non-breaking space "\xA2" => 'cent', # "\xA3" => 'Pound', # "\xA5" => 'Yen', # "\xA6" => '|', # broken vertical bar # "\xA7" => '', # section "\xA9" => '(C)', # copyright "\xAB" => '<<', # angle quotation mark (left) "\xAC" => '-', # negation "\xAE" => '(R)', # registered trademark "\xB1" => '+-', # plus-or-minus "\xB4" => '\'', # "\xB5" => 'u', # # "\xB6" => '', # paragraph "\xBB" => '>>', # angle quotation mark (right) "\xBC" => '(1/4)', # fraction 1/4 "\xBD" => '(1/2)', # fraction 1/2 "\xBE" => '(3/4)', # fraction 3/4 }, "\xC3" => { "\x97" => 'x', # multiplication "\xB7" => '/', # division }, "\xCF" => { "\x80" => 'PI', # }, "\xE2\x80" => { "\x82" => ' ', # en space "\x83" => ' ', # em space "\x85" => ' ', # "\x93" => ' - ', # en dash "\x94" => ' -- ', # em dash "\x95" => '--', # "\x98" => '`', # "\x99" => '\'', # "\x9C" => '"', # "\x9D" => '"', # "\xA2" => '::', # "\xA6" => '...', # horizontal ellipsis "\xB0" => '%.', # per mille }, "\xE2\x82" => { "\xAC" => 'Euro' # }, "\xE2\x84" => { "\x85" => 'c/o', # "\x97" => '(P)', # "\xA0" => '(SM)', # "\xA2" => '(TM)', # trademark "\xA6" => 'Ohm', # }, "\xE2\x85" => { "\x93" => '(1/3)', "\x94" => '(2/3)', "\x95" => '(1/5)', "\x96" => '(2/5)', "\x97" => '(3/5)', "\x98" => '(4/5)', "\x99" => '(1/6)', "\x9B" => '(1/8)', "\x9C" => '(3/8)', "\x9D" => '(5/8)', "\x9E" => '(7/8)', "\x9F" => '1/', }, "\xE2\x86" => { "\x90" => '<--', # left arrow "\x92" => '-->', # right arrow "\x94" => '<-->', # left right arrow }, "\xE2\x88" => { "\x82" => 'd', # partial differential "\x9E" => 'infinity', }, "\xE2\x89" => { "\xA0" => '!=', # "\xA4" => '<=', # "\xA5" => '>=', # }, "\xEF\x82" => { "\xB7" => '*' # small white square } ); # # Check argument(s) sanity. # my $usage = < outfile.txt In second usage, output is dumped on STDOUT. Use '-h' as the first argument to get this usage information. Use '-' as the infile name to read the docx file from STDIN. Use '-' as the outfile name to dump the text on STDOUT. Output is saved in infile.txt if second argument is omitted. Note: infile.docx can also be a directory name holding the unzipped content of concerned .docx file. USAGE die $usage if (@ARGV > 2 || $ARGV[0] eq '-h'); # # Look for configuration file in current directory/ user configuration # directory/ system configuration directory - in the given order. # my %config; if (-f "docx2txt.config") { %config = do 'docx2txt.config'; } elsif (-f "$userConfigDir/docx2txt.config") { %config = do "$userConfigDir/docx2txt.config"; } elsif (-f "$systemConfigDir/docx2txt.config") { %config = do "$systemConfigDir/docx2txt.config"; } if (%config) { foreach my $var (keys %config) { $$var = $config{$var}; } } # # Check for unzip utility, before proceeding further. # die "Failed to locate unzip command '$config_unzip'!\n" if ! -f $config_unzip; # # Handle cases where this script reads docx file from STDIN. # if (@ARGV == 0) { $ARGV[0] = '-'; $ARGV[1] = '-'; $inputFileName = "STDIN"; } elsif (@ARGV == 1 && $ARGV[0] eq '-') { $ARGV[1] = '-'; $inputFileName = "STDIN"; } else { $inputFileName = $ARGV[0]; } if ($ARGV[0] eq '-') { $tempFile = "${config_tempDir}/dx2tTemp_${$}_" . time() . ".docx"; open my $fhTemp, "> $tempFile" or die "Can't create temporary file for storing docx file read from STDIN!\n"; binmode $fhTemp; local $/ = undef; my $docxFileContent = ; print $fhTemp $docxFileContent; close $fhTemp; $ARGV[0] = $tempFile; } # # Check for existence and readability of required file in specified directory, # and whether it is a text file. # sub check_for_required_file_in_folder { stat("$_[1]/$_[0]"); die "Can't read <$_[0]> in <$_[1]>!\n" if ! (-f _ && -r _); die "<$_[1]/$_[0]> does not seem to be a text file!\n" if ! -T _; } sub readFileInto { local $/ = undef; open my $fh, "$_[0]" or die "Couldn't read file <$_[0]>!\n"; binmode $fh; $_[1] = <$fh>; close $fh; } sub readOptionalFileInto { local $/ = undef; stat("$_[0]"); if (-f _) { if (-r _ && -T _) { open my $fh, "$_[0]" or die "Couldn't read file <$_[0]>!\n"; binmode $fh; $_[1] = <$fh>; close $fh; } else { die "Invalid <$_[0]>!\n"; } } } # # Check whether first argument is specifying a directory holding extracted # content of .docx file, or .docx file itself. # sub cleandie { unlink("$tempFile") if -e "$tempFile"; die "$_[0]"; } stat($ARGV[0]); if (-d _) { check_for_required_file_in_folder("word/document.xml", $ARGV[0]); check_for_required_file_in_folder("word/_rels/document.xml.rels", $ARGV[0]); $inpIsDir = 'y'; } else { cleandie "Can't read docx file <$inputFileName>!\n" if ! (-f _ && -r _); cleandie "<$inputFileName> does not seem to be a docx file!\n" if -T _; } # # Extract xml document content from argument docx file/directory. # my $unzip_cmd = "'$config_unzip' $config_unzip_opts"; if ($inpIsDir eq 'y') { readFileInto("$ARGV[0]/word/document.xml", $content); } else { $content = `$unzip_cmd "$ARGV[0]" word/document.xml 2>$nullDevice`; } cleandie "Failed to extract required information from <$inputFileName>!\n" if ! $content; # # Be ready for outputting the extracted text contents. # if (@ARGV == 1) { $ARGV[1] = $ARGV[0]; # Remove any trailing slashes to generate proper output filename, when # input is directory. $ARGV[1] =~ s%[/\\]+$%% if ($inpIsDir eq 'y'); $ARGV[1] .= ".txt" if !($ARGV[1] =~ s/\.docx$/\.txt/); } my $txtfile; open($txtfile, "> $ARGV[1]") || cleandie "Can't create <$ARGV[1]> for output!\n"; binmode $txtfile; # Ensure no auto-conversion of '\n' to '\r\n' on Windows. # # Gather information about header, footer, hyperlinks, images, footnotes etc. # if ($inpIsDir eq 'y') { readFileInto("$ARGV[0]/word/_rels/document.xml.rels", $_); } else { $_ = `$unzip_cmd "$ARGV[0]" word/_rels/document.xml.rels 2>$nullDevice`; } my %docurels; while (//g) { $docurels{"$2:$1"} = $3; } # # Gather list numbering information. # $_ = ""; if ($inpIsDir eq 'y') { readOptionalFileInto("$ARGV[0]/word/numbering.xml", $_); } else { $_ = `$unzip_cmd "$ARGV[0]" word/numbering.xml 2>$nullDevice`; } my %abstractNum; my @N2ANId = (); my %NFList = ( "bullet" => \&bullet, "decimal" => \&decimal, "lowerLetter" => \&lowerLetter, "upperLetter" => \&upperLetter, "lowerRoman" => \&lowerRoman, "upperRoman" => \&upperRoman ); if ($_) { while (/(.*?)<\/w:abstractNum>/g) { my $abstractNumId = $1, $temp = $2; while ($temp =~ /]*>]*>]*>.*?]*>.*?]*>/g ) { # $2: Start $3: NumFmt, $4: LvlText, ($5,$6): (Indent (twips), hanging) @{$abstractNum{"$abstractNumId:$1"}} = ( $NFList{$3}, $4, $2, int ((($5-$6) / $config_twipsPerChar) + 0.5), $5 ); } } while ( /]*?>//og; $hltext .= " [HYPERLINK: $hlink]" if (lc $config_showHyperLink eq "y" && $hltext ne $hlink); return $hltext; } # # Subroutines for processing numbering information. # my @RomanNumbers = ( "", "i", "ii", "iii", "iv", "v", "vi", "vii", "viii", "ix", "x", "xi", "xii", "xiii", "xiv", "xv", "xvi", "xvii", "xviii", "xix", "xx", "xxi", "xxii", "xxiii", "xxiv", "xxv", "xxvi", "xxvii", "xxviii", "xxix", "xxx", "xxxi", "xxxii", "xxxiii", "xxxiv", "xxxv", "xxxvi", "xxxvii", "xxxviii", "xxxix", "xl", "xli", "xlii", "xliii", "xliv", "xlv", "xlvi", "xlvii", "xlviii", "xlix", "l", "li" ); sub lowerRoman { return $RomanNumbers[$_[0]] if ($_[0] < @RomanNumbers); @rcode = ("i", "iv", "v", "ix", "x", "xl", "l", "xc", "c", "cd", "d", "cm", "m"); @dval = (1, 4, 5, 9, 10, 40, 50, 90, 100, 400, 500, 900, 1000); my $roman = ""; my $num = $_[0]; my $div, $i = (@rcode - 1); while ($num > 0) { $i-- while ($num < $dval[$i]); $div = $num / $dval[$i]; $num = $num % $dval[$i]; $roman .= $rcode[$i] x $div; } return $roman; } sub upperRoman { return uc lowerRoman(@_); } sub lowerLetter { @Alphabets = split '' , "abcdefghijklmnopqrstuvwxyz"; return $Alphabets[($_[0] % 26) - 1] x (($_[0] - 1)/26 + 1); } sub upperLetter { return uc lowerLetter(@_); } sub decimal { return $_[0]; } my %bullets = ( "\x6F" => 'o', "\xEF\x81\xB6" => '::', # Diamond "\xEF\x82\xA7" => '#', # Small Black Square "\xEF\x82\xB7" => '*', # Small Black Circle "\xEF\x83\x98" => '>', # Arrowhead "\xEF\x83\xBC" => '+' # Right Sign ); sub bullet { return $bullets{$_[0]} ? $bullets{$_[0]} : 'oo'; } my @lastCnt = (0); my @twipStack = (0); my @keyStack = (undef); my $ssiz = 1; sub listNumbering { my $aref = \@{$abstractNum{"$N2ANId[$_[0]]:$_[1]"}}; my $lvlText; if ($aref->[0] != \&bullet) { my $key = "$N2ANId[$_[0]]:$_[1]"; my $ccnt; if ($aref->[4] < $twipStack[$ssiz-1]) { while ($twipStack[$ssiz-1] > $aref->[4]) { pop @twipStack; pop @keyStack; pop @lastCnt; $ssiz--; } } if ($aref->[4] == $twipStack[$ssiz-1]) { if ($key eq $keyStack[$ssiz-1]) { ++$lastCnt[$ssiz-1]; } else { $keyStack[$ssiz-1] = $key; $lastCnt[$ssiz-1] = $aref->[2]; } } elsif ($aref->[4] > $twipStack[$ssiz-1]) { push @twipStack, $aref->[4]; push @keyStack, $key; push @lastCnt, $aref->[2]; $ssiz++; } $ccnt = $lastCnt[$ssiz-1]; $lvlText = $aref->[1]; $lvlText =~ s/%\d([^%]*)$/($aref->[0]->($ccnt)).$1/oe; my $i = $ssiz - 2; $i-- while ($lvlText =~ s/%\d([^%]*)$/$lastCnt[$i]$1/o); } else { $lvlText = $aref->[0]->($aref->[1]); } return ' ' x $aref->[3] . $lvlText . ' '; } # # Subroutines for processing paragraph content. # sub processParagraph { my $para = $_[0] . "$config_newLine"; my $align = $1 if ($_[0] =~ //); $para =~ s/<.*?>//og; return justify($align,$para) if $align; return $para; } # # Text extraction starts. # my %tag2chr = (tab => "\t", noBreakHyphen => "-", softHyphen => " - "); $content =~ s/(\r)?\n//; $content =~ s{<(wp14|wp):[^>]*>.*?]*>}||og; # Remove the field instructions (instrText) and data (fldData), and deleted # text. $content =~ s{]*>.*?}||ogs; # Mark cross-reference superscripting within [...]. $content =~ s|(.*?)|[$1]|og; $content =~ s{}|$tag2chr{$1}|og; my $hr = '-' x $config_lineWidth . $config_newLine; $content =~ s|.*?|$hr|og; $content =~ s{.*?(|]+>)(.*?)}/uc $2/oge; $content =~ s{(.*?)}/hyperlink($1,$2)/oge; $content =~ s||listNumbering($2,$1)|oge; $content =~ s{]*>}|' ' x int((($2-$4)/$config_twipsPerChar)+0.5)|oge; $content =~ s{]+?/>|}|$config_newLine|og; $content =~ s/]+?>(.*?)<\/w:p>/processParagraph($1)/ogse; $content =~ s/<.*?>//og; # # Convert non-ASCII characters/character sequences to ASCII characters. # $content =~ s/(\xC2|\xC3|\xCF|\xE2.|\xEF.)(.)/($splchars{$1}{$2} ? $splchars{$1}{$2} : $1.$2)/oge; # # Convert docx specific (reserved HTML/XHTML) escape characters. # $content =~ s/(&)(amp|apos|gt|lt|quot)(;)/$escChrs{lc $2}/iog; # # Write the extracted and converted text contents to output. # print $txtfile $content; close $txtfile; docx2txt-1.4/docx2txt.sh0000755000175100010010000000644311303300706014026 0ustar manojNone#!/usr/bin/env bash # docx2txt, a command-line utility to convert Docx documents to text format. # Copyright (C) 2008 Sandeep Kumar # # 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 3 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 program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA # # A simple .docx to .txt converter # # This script is a wrapper around core docx2txt.pl and saves text output for # (filename or) filename.docx in filename.txt . # # Author : Sandeep Kumar (shimple0 -AT- Yahoo .DOT. COM) # # ChangeLog : # # 10/08/2008 - Initial version (v0.1) # 15/08/2008 - Invoking docx2txt.pl with docx document instead of xml file, # so don't need unzip and rm actions now. # Removed dependency on sed for generating output filename. # 23/09/2008 - Changed #! line to use /usr/bin/env - good suggestion from # Rene Maroufi (info>ATDOT can also specify a directory holding the unzipped content of a .docx file. _USAGE_ exit 1 } [ $# != 1 ] && usage # # Remove trailing '/'s if any, when input specifies a directory. # shopt -s extglob set "${1%%+(/)}" if [ -d "$1" ] then if ! [ -r "$1" -a -x "$1" ] then echo -e "\nCan't access/read input directory <$1>!\n" exit 1 fi elif ! [ -f "$1" -a -r "$1" -a -s "$1" ] then echo -e "\nCheck if <$1> exists, is readable and has non-zero size!\n" exit 1 fi TEXTFILE=${1/%.docx/.txt} [ "$1" == "$TEXTFILE" ] && TEXTFILE="$1.txt" # # $1 : filename to check for existence # $2 : message regarding file # function check_for_existence () { if [ -f "$1" ] then read -p "overwrite $2 <$1> [y/n] ? " yn if [ "$yn" != "y" ] then echo -e "\nPlease copy <$1> somewhere before running the script.\n" echeck=1 fi fi } echeck=0 check_for_existence "$TEXTFILE" "Output text file" [ $echeck -ne 0 ] && exit 1 # # Invoke perl script to do the actual text extraction # "$MYLOC/docx2txt.pl" "$1" "$TEXTFILE" if [ $? == 0 ] then echo -e "\nText extracted from <$1> is available in <$TEXTFILE>.\n" else echo -e "\nFailed to extract text from <$1>!\n" fi docx2txt-1.4/BSDmakefile0000644000175100010010000000070411671411412013740 0ustar manojNone# # BSD makefile for docx2txt # BINDIR ?= /usr/local/bin CONFIGDIR ?= /etc INSTALL != which install BINFILES = docx2txt.sh docx2txt.pl CONFIGFILE = docx2txt.config .PHONY: install installbin installconfig install: installbin installconfig installbin: $(BINFILES) [ -d $(BINDIR) ] || mkdir -p $(BINDIR) $(INSTALL) -m 755 $> $(BINDIR) installconfig: $(CONFIGFILE) [ -d $(CONFIGDIR) ] || mkdir -p $(CONFIGDIR) $(INSTALL) -m 755 $> $(CONFIGDIR) docx2txt-1.4/Makefile0000644000175100010010000000222011701402524013340 0ustar manojNone# # Makefile for docx2txt # BINDIR ?= /usr/local/bin CONFIGDIR ?= /etc INSTALL = $(shell which install 2>/dev/null) ifeq ($(INSTALL),) $(error "Need 'install' to install docx2txt") endif PERL = $(shell which perl 2>/dev/null) ifeq ($(PERL),) $(warning "*** Make sure 'perl' is installed and is in your PATH, before running the installed script. ***") endif BINFILES = docx2txt.sh docx2txt.pl CONFIGFILE = docx2txt.config .PHONY: install installbin installconfig install: installbin installconfig installbin: $(BINFILES) @echo "Installing script files [$(BINFILES)] in \"$(BINDIR)\" .." @[ -d "$(BINDIR)" ] || mkdir -p "$(BINDIR)" $(INSTALL) -m 755 $^ "$(BINDIR)" ifneq ($(PERL),) @echo "Setting systemConfigDir to [$(CONFIGDIR)] in \"$(BINDIR)/docx2txt.pl\" .." $(PERL) -pi -e "s%\"/etc\";%\"$(CONFIGDIR)\";%" "$(BINDIR)/docx2txt.pl"\ && rm -f "$(BINDIR)/docx2txt.pl.bak" else @echo "*** Set systemConfigDir to \"$(CONFIGDIR)\" in \"$(BINDIR)/docx2txt.pl\"." endif installconfig: $(CONFIGFILE) @echo "Installing config file [$(CONFIGFILE)] in \"$(CONFIGDIR)\" .." @[ -d "$(CONFIGDIR)" ] || mkdir -p "$(CONFIGDIR)" $(INSTALL) -m 755 $^ "$(CONFIGDIR)" docx2txt-1.4/WInstall.bat0000644000175100010010000001176311261360506014145 0ustar manojNone@echo off :: docx2txt, a command-line utility to convert Docx documents to text format. :: Copyright (C) 2008-now Sandeep Kumar :: :: 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 3 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 program; if not, write to the Free Software :: Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA :: :: A simple commandline installer for docx2txt on Windows. :: :: Author : Sandeep Kumar (shimple0 -AT- Yahoo .DOT. COM) :: :: ChangeLog : :: :: 02/10/2009 - Initial version of command line installation script for :: Windows users. Script will prompt user for perl, unzip and :: cakecmd paths and will update these paths in the installed :: files using perl, if perl path is valid. Else it will simply :: copy the concerned files to the installation folder. :: :: :: Ensure that required command extensions are enabled. :: setlocal enableextensions setlocal enabledelayedexpansion echo. echo Welcome to command line installer for docx2txt. echo. :: :: Check if this install script is invoked correctly. :: if not "%~2" == "" ( echo. echo Usage : "%~0" [WhereToInstall] echo. echo WhereToInstall specifies a folder to install into. echo. echo If destination folder is not specified on command line, echo then it will be asked for during the installation. echo. goto END ) :: :: Check if destination folder was specified on command line, else ask for it. :: if "%~1" == "" ( echo. echo Where should the docx2txt tool be installed? Specify the location echo without surrounding quotes. echo. set /P destdir=Installation Folder : echo. ) else ( set destdir=%~1 ) if not exist "%destdir%" ( echo. echo ** Folder "%destdir%" does not exist. It will be created now. echo. mkdir "%destdir%" ) :: :: Check if user specified destdir is a valid folder or a not. :: pushd "%destdir%" 2>nul if ERRORLEVEL 1 ( echo. echo ** "%destdir%" does not specify a valid folder name. echo ** Exiting installer. echo. goto END ) else if ERRORLEVEL 0 ( popd ) echo. echo Please specify fully qualified paths to utilities when requested. echo Perl.exe is required for docx2txt tool as well as for this installation. echo. set /A attempts=0 :GET_PERL_PATH set /P PERL=Path to Perl.exe : call :CHECK_FILE_EXISTENCE "%PERL%" "perl" if ERRORLEVEL 7 ( set /A attempts=attempts+1 if !attempts! == 3 ( echo. echo Continuing with simple installation .... echo. goto SIMPLE_INSTALL ) else ( goto GET_PERL_PATH ) ) echo. echo. echo If you do not have CakeCmd.exe installed, simply press Enter/Return key. echo. set /P CAKECMD=Path to CakeCmd.exe : echo. echo. echo In case you are using Cygwin Perl.exe, you need to specify Unzip.exe path echo using forward slashes i.e. like C:/path/to/unzip.exe . echo If you do not have Unzip.exe installed, simply press Enter/Return key. echo. set /P UNZIP=Path to Unzip.exe : echo. echo. echo Here is the information you have provided. echo. echo Installation folder = %destdir% echo Perl = %PERL% echo CakeCmd = %CAKECMD% echo Unzip = %UNZIP% echo. pause echo. echo Installing script files to "%destdir%" .... copy docx2txt.pl "%destdir%" > nul if not "%UNZIP%" == "" ( %PERL% -e "undef $/; $_ = <>; s/(unzip\s*=>)[^,]*,/$1 '$ARGV[0]',/; print;" docx2txt.config "%UNZIP%" > "%destdir%\docx2txt.config" ) if "%CAKECMD%" == "" ( %PERL% -e "undef $/; $_ = <>; s/(set PERL=).*?(\r?\n)/$1$ARGV[0]$2/; print;" docx2txt.bat "%PERL%" > "%destdir%\docx2txt.bat" ) else ( %PERL% -e "undef $/; $_ = <>; s/(set PERL=).*?(\r?\n)/$1$ARGV[0]$2/; s/:: (set CAKECMD=).*?(\r?\n)/$1$ARGV[1]$2/; print;" docx2txt.bat "%PERL%" "%CAKECMD%" > "%destdir%\docx2txt.bat" ) goto END :SIMPLE_INSTALL echo Copying script files to "%destdir%" .... copy docx2txt.bat "%destdir%" > nul copy docx2txt.pl "%destdir%" > nul copy docx2txt.config "%destdir%" > nul echo. echo Please adjust perl, unzip and cakecmd paths (as needed) in echo "%destdir%\docx2txt.bat" and "%destdir%\docx2txt.config" echo. goto END :: :: Check whether the argument executable exists? :: :CHECK_FILE_EXISTENCE if not exist "%~1" ( echo. echo ** Can not find executable "%~1". echo. ) else if /I "%~nx1" NEQ "%~2.exe" ( echo. echo ** "%~1" does not seem to be an executable file. echo. ) else exit /B 0 exit /B 7 :END endlocal endlocal set PERL= set CAKECMD= set UNZIP= set FILES= set attempts= docx2txt-1.4/VERSION0000644000175100010010000000000412335160526012755 0ustar manojNone1.4 docx2txt-1.4/INSTALL0000644000175100010010000001027012334426234012744 0ustar manojNoneNon-Windows users, please adjust following executables paths before proceeding for installation. - #! path for env in docx2txt.sh and docx2txt.pl - path for unzip in docx2txt.config You can skip installing docx2txt.sh and docx2txt.bat wrapper scripts (as applicable) during manual installation. These check for overwriting the output text file and have slightly restricted usage as compared to core docx2txt.pl script. [check README for details] However if you are using CakeCmd unzipper, docx2txt.bat can be quite handy as it internally manages unzipping the .docx files that do not have .zip extension. Installation on Linux, Cygwin, BSD and similar systems ------------------------------------------------------ Type "make" as root to install docx2txt script files for all users in /usr/local/bin and system-wide configuration file in /etc . If you want to install these in some other directory, you can do so via make BINDIR=/path/to/scripts/directory CONFIGDIR=/path/to/config/directory BSD users can use either GNU make or BSD make. Linux "make" installation also attempts to set systemConfigDir variable in installed docx2txt.pl file to specified CONFIGDIR. You will need make and install utilities installed on your system for installation via Makefile. In case, you don't want to use Makefile for installation, you can follow these steps for manual installation. 1. Copy docx2txt.pl, docx2txt.sh and docx2txt.config to the desired directories. cp docx2txt.pl docx2txt.sh /path/to/scripts/directory cp docx2txt.config /path/to/config/directory 2. Change the permission of copied files to 755 for docx2txt.pl and docx2txt.sh, and 644 for docx2txt.config . chmod 755 /path/to/scripts/directory/docx2txt.* chmod 644 /path/to/config/directory/docx2txt.config 3. Change the value of systemConfigDir variable (in non-Windows settings) in installed docx2txt.pl file from "/etc" to specified config directory. 4. Add the concerned scripts directory to your PATH, if not already in PATH. PATH=$PATH:/path/to/scripts/directory Installation on Windows ----------------------- I. You can install minimal Cygwin packages from http://www.cygwin.com/ to have working bash, cat, env, install, make, perl and unzip utilities and thus create the required Cygwin environment for using this utility. II. If you do not want to install even minimal Cygwin, you can try following sequence for manual installation. a. Get following files from /usr/bin/ of cygwin installation and place them in, say C:\docx2txt . cygwin1.dll perl.exe cygperl*.dll unzip.exe cygcrypt*.dll b. Copy docx2txt.pl, docx2txt.bat and docx2txt.config to C:\docx2txt . c. Change path for unzip in docx2txt.config to C:/docx2txt/unzip.exe and path for perl in docx2txt.bat to C:\docx2txt\perl.exe . d. You can now use this tool from within C:\docx2txt as follows. docx2txt.bat file.docx docx2txt.bat path-to-directory\file.docx perl docx2txt.pl file.docx perl docx2txt.pl directory\file.docx - perl docx2txt.pl directory/file.docx file.txt perl docx2txt.pl C:/somedir/file.docx perl docx2txt.pl C:\somedir\file.docx C:\otherdir\converted.txt Please view README for further examples using I/O redirection. III. You can also install this utility via WInstall.bat and follow the instructions during installation. WInstall.bat can be invoked in two ways. WInstall.bat installation-folder-name WInstall.bat In second case, install script will ask user for installation folder name. It is advisable to have working installations of perl and atleast one command line unzipper (Unzip/CakeCmd) before running this install script, so that it can automatically set the desired paths in installed files. You can use - Cygwin perl or Strawberry perl [http://strawberryperl.com/] or any other Windows native perl implementation - Any commandline unzipper meeting the dependencies requirement in README. * Cygwin unzip or UnZip for Windows [http://gnuwin32.sourceforge.net/downlinks/unzip.php] * 7z [http://www.7-zip.org/] * pkzipc [http://www.pkware.com/software/pkzip/] * wzunzip [http://www.winzip.com/] * CakeCmd unzipper [http://www.quickzip.org/cakecmd.html] docx2txt-1.4/README0000644000175100010010000001750312334444374012606 0ustar manojNonedocx2txt (http://docx2txt.sourceforge.net/) is a simple tool to generate equivalent text files from (even corrupted) Microsoft .docx documents, with an attempt towards preserving sufficient formatting and document information, and appropriate character conversions for a good text experience. Dependencies ------------ You will need to have following programs installed on your system for using this tool. Mandatory : * PERL * A commandline unzipping program that can silently extract single file from zip archive to console/standard output/pipe. Unzip, 7-Zip (7z), PKZip (pkzipc), and WinZip (wzunzip) are some such known programs that serve the purpose when invoked with appropriate command/options. Optional : * Bash [Needed only if you want to use wrapper docx2txt.sh] How to Use ---------- You can do the text conversion in different ways depending upon your usage environment. 1. Using docx2txt.sh : docx2txt.sh file.docx OR docx2txt.sh file In both these cases output text will be saved in file.txt . 2. Using docx2txt.bat : docx2txt.bat file.docx OR docx2txt.bat file In both these cases output text will be saved in file.txt . 3. Using docx2txt.pl : a. docx2txt.pl infile.docx outfile.txt Use - as the name of output text file, to send extracted text to STDOUT, that is, console. b. docx2txt.pl file.docx OR docx2txt.pl file In both these cases output text will be saved in file.txt . Input can also be provided via STDIN (console) using - as the name of input docx file. Moreover redirection of input/output is possible with this script, making it feasible to invoke it in even more ways as illustrated below. c. docx2txt.pl < infile.docx In this case input is read from infile.docx and output is sent to STDOUT. d. docx2txt.pl < infile.docx > outfile.txt In this case input is read from infile.docx and output is sent to outfile.txt . e. cat infile.docx | ./docx2txt.pl In this case content of infile.docx is read via STDIN and output is sent to STDOUT. f. cat infile.docx | ./docx2txt.pl - outfile.txt In this case content of infile.docx is read via STDIN and output is sent to outfile.txt . Input argument in all the above cases can also be a directory holding the unzipped content of a .docx file. This feature is particulary useful if you do not have a commandline unzipping program as required in dependencies. Usage help can be obtained by giving '-h' as the first argument to the script. docx2txt.pl -h Tune your Experience -------------------- You can change following settings via docx2txt.config file that is looked for - in the current directory, - user configuration directory (APPDATA on Windows, HOME on non-Windows), and - in the system configuration directory (same directory that holds the script files on Windows, /etc or as set during installation on non-Windows), in the specified order. In case script does not find any configuration file, it continues with builtin default settings. a. Path to unzip program, and relevant command/options to be passed to it [#] b. Path to temp directory c. Newline in output text file (Unix/Dos way) d. Line width (used for short line justification) e. Showing of hyperlink along with linked text f. Twips per character, to obtain desired list indentation in text output You can also adjust representative bullet indicators in docx2txt.pl, but be careful while modifying it. [#] Unzipping Program | Relevant Command/Options ------------------+------------------------------------------------------ unzip | -p 7z | e -so -tzip pkzipc | -console -silent -translate=none -noarchiveextension wzunzip | -c Viewing the text content of Docx file in Editors and File browsers ------------------------------------------------------------------ 1. MC (Midnight Commander) ----------------------- You can add following binding in ~/.mc/bindings and view the text content of a .docx file by hitting F3 key (assuming default key mappings) after moving the cursor over concerned filename in mc pannel. # Microsoft .docx Document regex/\.(docx|DOCX|Docx)$ View=%view{ascii} docx2txt.pl %f - 2. VIm Editor ---------- You can add following lines in your ~/.vimrc to view the text content of a .docx file directly when using vim. "use docx2txt.pl to allow VIm to view the text content of a .docx file directly. autocmd BufReadPre *.docx set ro autocmd BufReadPost *.docx %!docx2txt.pl Note that above .vimrc addition will allow you to view the text content of .docx files specified as command line argument to vim, but not of those read using ":r file.docx". Please refer to http://vimdoc.sourceforge.net/htmldoc/autocmd.html for more information on autocmd. 3. Emacs Editor ------------ You can add following lines in your ~/.emacs file to view the text content of a .docx file directly when using emacs. (add-to-list 'auto-mode-alist '("\\.docx\\'" . docx2txt)) (defun docx2txt () "Run docx2txt on the entire buffer." (shell-command-on-region (point-min) (point-max) "docx2txt.pl" t t)) Be warned that with above ~/.emacs code addition, if you happen to save the buffer/file, it will overwrite the .docx file with the text content. Please explore "Filters -- making things readable:" section at http://www.emacswiki.org/emacs/CategoryExternalUtilities for more ways to view .docx file text content directly in emacs. Recovering text from corrupted .docx file ----------------------------------------- A .docx file is a zip archive of a collection of XML files. Two kind of corruptions - zip archive corruption, and component XML file(s) corruption, can cause a common Docx Reader/Viewer to fail while reading the file. The way docx2txt.pl extracts text content from .docx file, it is somewhat immune to XML corruption, and can extract reasonable text content from even corrupted XML file. As for zip archive corruption, if you have an unzipper that can fix a corrupted zip archive[#] and/or extract atleast required XML files from a corrupted zip archive[*], you are ready to extract text from the corrupted .docx file. You may temporarily need to rename .docx file as .zip file, if required by unzipper. If this unzipper can extract specific files to pipe/standard output/console, you can simply specify it in config file. Otherwise you can extract the archive content in a directory, suitably named as per your need, and specify this directory as the filename argument to the docx2txt.pl script. [#] Program Name | Example Usage --------------+------------------------------------------------------ zip | zip -FF corrupted.docx --out fixed.docx ALZipCon | ALZipCon.exe -r corrupted.zip pkzipc | pkzipc.exe -fix t.zip winrar[GUI] | Repair archive, [*] Keep broken extracted files Request ------- If you are using this work directly/indirectly for non-personal purpose(s), please inform the author about it along with relevant url(s), so that it can be mentioned on the project homepage. In case you come across some issue with it, or need a feature that can be handled in docx to text conversion, please feel free to communicate. An accompanying test .docx document depicting the issue/need and the corresponding text file generated by MSOffice with character substitution enabled (or as you would like the text file to be) will be helpful. You can track the project via http://sourceforge.net/projects/docx2txt and refer to project cvs if there have been changes since this release. Disclaimer ---------- This program includes no warranty whatsoever. It is provided "AS IS". For more information please read the COPYING document, which should be included with the package, and describes the GNU Public License, which covers docx2txt. Sandeep Kumar ( shimple0 -AT- yahoo .DOT. com ) docx2txt-1.4/COPYING0000644000175100010010000010451311065260620012745 0ustar manojNone GNU GENERAL PUBLIC LICENSE Version 3, 29 June 2007 Copyright (C) 2007 Free Software Foundation, Inc. Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed. Preamble The GNU General Public License is a free, copyleft license for software and other kinds of works. The licenses for most software and other practical works are designed to take away your freedom to share and change the works. By contrast, the GNU General Public License is intended to guarantee your freedom to share and change all versions of a program--to make sure it remains free software for all its users. We, the Free Software Foundation, use the GNU General Public License for most of our software; it applies also to any other work released this way by its authors. You can apply it to your programs, too. When we speak of free software, we are referring to freedom, not price. Our General Public Licenses are designed to make sure that you have the freedom to distribute copies of free software (and charge for them if you wish), that you receive source code or can get it if you want it, that you can change the software or use pieces of it in new free programs, and that you know you can do these things. To protect your rights, we need to prevent others from denying you these rights or asking you to surrender the rights. Therefore, you have certain responsibilities if you distribute copies of the software, or if you modify it: responsibilities to respect the freedom of others. For example, if you distribute copies of such a program, whether gratis or for a fee, you must pass on to the recipients the same freedoms that you received. You must make sure that they, too, receive or can get the source code. And you must show them these terms so they know their rights. Developers that use the GNU GPL protect your rights with two steps: (1) assert copyright on the software, and (2) offer you this License giving you legal permission to copy, distribute and/or modify it. For the developers' and authors' protection, the GPL clearly explains that there is no warranty for this free software. For both users' and authors' sake, the GPL requires that modified versions be marked as changed, so that their problems will not be attributed erroneously to authors of previous versions. Some devices are designed to deny users access to install or run modified versions of the software inside them, although the manufacturer can do so. This is fundamentally incompatible with the aim of protecting users' freedom to change the software. The systematic pattern of such abuse occurs in the area of products for individuals to use, which is precisely where it is most unacceptable. Therefore, we have designed this version of the GPL to prohibit the practice for those products. If such problems arise substantially in other domains, we stand ready to extend this provision to those domains in future versions of the GPL, as needed to protect the freedom of users. Finally, every program is threatened constantly by software patents. States should not allow patents to restrict development and use of software on general-purpose computers, but in those that do, we wish to avoid the special danger that patents applied to a free program could make it effectively proprietary. To prevent this, the GPL assures that patents cannot be used to render the program non-free. The precise terms and conditions for copying, distribution and modification follow. TERMS AND CONDITIONS 0. Definitions. "This License" refers to version 3 of the GNU General Public License. "Copyright" also means copyright-like laws that apply to other kinds of works, such as semiconductor masks. "The Program" refers to any copyrightable work licensed under this License. Each licensee is addressed as "you". "Licensees" and "recipients" may be individuals or organizations. To "modify" a work means to copy from or adapt all or part of the work in a fashion requiring copyright permission, other than the making of an exact copy. The resulting work is called a "modified version" of the earlier work or a work "based on" the earlier work. A "covered work" means either the unmodified Program or a work based on the Program. To "propagate" a work means to do anything with it that, without permission, would make you directly or secondarily liable for infringement under applicable copyright law, except executing it on a computer or modifying a private copy. Propagation includes copying, distribution (with or without modification), making available to the public, and in some countries other activities as well. To "convey" a work means any kind of propagation that enables other parties to make or receive copies. Mere interaction with a user through a computer network, with no transfer of a copy, is not conveying. An interactive user interface displays "Appropriate Legal Notices" to the extent that it includes a convenient and prominently visible feature that (1) displays an appropriate copyright notice, and (2) tells the user that there is no warranty for the work (except to the extent that warranties are provided), that licensees may convey the work under this License, and how to view a copy of this License. If the interface presents a list of user commands or options, such as a menu, a prominent item in the list meets this criterion. 1. Source Code. The "source code" for a work means the preferred form of the work for making modifications to it. "Object code" means any non-source form of a work. A "Standard Interface" means an interface that either is an official standard defined by a recognized standards body, or, in the case of interfaces specified for a particular programming language, one that is widely used among developers working in that language. The "System Libraries" of an executable work include anything, other than the work as a whole, that (a) is included in the normal form of packaging a Major Component, but which is not part of that Major Component, and (b) serves only to enable use of the work with that Major Component, or to implement a Standard Interface for which an implementation is available to the public in source code form. A "Major Component", in this context, means a major essential component (kernel, window system, and so on) of the specific operating system (if any) on which the executable work runs, or a compiler used to produce the work, or an object code interpreter used to run it. The "Corresponding Source" for a work in object code form means all the source code needed to generate, install, and (for an executable work) run the object code and to modify the work, including scripts to control those activities. However, it does not include the work's System Libraries, or general-purpose tools or generally available free programs which are used unmodified in performing those activities but which are not part of the work. For example, Corresponding Source includes interface definition files associated with source files for the work, and the source code for shared libraries and dynamically linked subprograms that the work is specifically designed to require, such as by intimate data communication or control flow between those subprograms and other parts of the work. The Corresponding Source need not include anything that users can regenerate automatically from other parts of the Corresponding Source. The Corresponding Source for a work in source code form is that same work. 2. Basic Permissions. All rights granted under this License are granted for the term of copyright on the Program, and are irrevocable provided the stated conditions are met. This License explicitly affirms your unlimited permission to run the unmodified Program. The output from running a covered work is covered by this License only if the output, given its content, constitutes a covered work. This License acknowledges your rights of fair use or other equivalent, as provided by copyright law. You may make, run and propagate covered works that you do not convey, without conditions so long as your license otherwise remains in force. You may convey covered works to others for the sole purpose of having them make modifications exclusively for you, or provide you with facilities for running those works, provided that you comply with the terms of this License in conveying all material for which you do not control copyright. Those thus making or running the covered works for you must do so exclusively on your behalf, under your direction and control, on terms that prohibit them from making any copies of your copyrighted material outside their relationship with you. Conveying under any other circumstances is permitted solely under the conditions stated below. Sublicensing is not allowed; section 10 makes it unnecessary. 3. Protecting Users' Legal Rights From Anti-Circumvention Law. No covered work shall be deemed part of an effective technological measure under any applicable law fulfilling obligations under article 11 of the WIPO copyright treaty adopted on 20 December 1996, or similar laws prohibiting or restricting circumvention of such measures. When you convey a covered work, you waive any legal power to forbid circumvention of technological measures to the extent such circumvention is effected by exercising rights under this License with respect to the covered work, and you disclaim any intention to limit operation or modification of the work as a means of enforcing, against the work's users, your or third parties' legal rights to forbid circumvention of technological measures. 4. Conveying Verbatim Copies. You may convey verbatim copies of the Program's source code as you receive it, in any medium, provided that you conspicuously and appropriately publish on each copy an appropriate copyright notice; keep intact all notices stating that this License and any non-permissive terms added in accord with section 7 apply to the code; keep intact all notices of the absence of any warranty; and give all recipients a copy of this License along with the Program. You may charge any price or no price for each copy that you convey, and you may offer support or warranty protection for a fee. 5. Conveying Modified Source Versions. You may convey a work based on the Program, or the modifications to produce it from the Program, in the form of source code under the terms of section 4, provided that you also meet all of these conditions: a) The work must carry prominent notices stating that you modified it, and giving a relevant date. b) The work must carry prominent notices stating that it is released under this License and any conditions added under section 7. This requirement modifies the requirement in section 4 to "keep intact all notices". c) You must license the entire work, as a whole, under this License to anyone who comes into possession of a copy. This License will therefore apply, along with any applicable section 7 additional terms, to the whole of the work, and all its parts, regardless of how they are packaged. This License gives no permission to license the work in any other way, but it does not invalidate such permission if you have separately received it. d) If the work has interactive user interfaces, each must display Appropriate Legal Notices; however, if the Program has interactive interfaces that do not display Appropriate Legal Notices, your work need not make them do so. A compilation of a covered work with other separate and independent works, which are not by their nature extensions of the covered work, and which are not combined with it such as to form a larger program, in or on a volume of a storage or distribution medium, is called an "aggregate" if the compilation and its resulting copyright are not used to limit the access or legal rights of the compilation's users beyond what the individual works permit. Inclusion of a covered work in an aggregate does not cause this License to apply to the other parts of the aggregate. 6. Conveying Non-Source Forms. You may convey a covered work in object code form under the terms of sections 4 and 5, provided that you also convey the machine-readable Corresponding Source under the terms of this License, in one of these ways: a) Convey the object code in, or embodied in, a physical product (including a physical distribution medium), accompanied by the Corresponding Source fixed on a durable physical medium customarily used for software interchange. b) Convey the object code in, or embodied in, a physical product (including a physical distribution medium), accompanied by a written offer, valid for at least three years and valid for as long as you offer spare parts or customer support for that product model, to give anyone who possesses the object code either (1) a copy of the Corresponding Source for all the software in the product that is covered by this License, on a durable physical medium customarily used for software interchange, for a price no more than your reasonable cost of physically performing this conveying of source, or (2) access to copy the Corresponding Source from a network server at no charge. c) Convey individual copies of the object code with a copy of the written offer to provide the Corresponding Source. This alternative is allowed only occasionally and noncommercially, and only if you received the object code with such an offer, in accord with subsection 6b. d) Convey the object code by offering access from a designated place (gratis or for a charge), and offer equivalent access to the Corresponding Source in the same way through the same place at no further charge. You need not require recipients to copy the Corresponding Source along with the object code. If the place to copy the object code is a network server, the Corresponding Source may be on a different server (operated by you or a third party) that supports equivalent copying facilities, provided you maintain clear directions next to the object code saying where to find the Corresponding Source. Regardless of what server hosts the Corresponding Source, you remain obligated to ensure that it is available for as long as needed to satisfy these requirements. e) Convey the object code using peer-to-peer transmission, provided you inform other peers where the object code and Corresponding Source of the work are being offered to the general public at no charge under subsection 6d. A separable portion of the object code, whose source code is excluded from the Corresponding Source as a System Library, need not be included in conveying the object code work. A "User Product" is either (1) a "consumer product", which means any tangible personal property which is normally used for personal, family, or household purposes, or (2) anything designed or sold for incorporation into a dwelling. In determining whether a product is a consumer product, doubtful cases shall be resolved in favor of coverage. For a particular product received by a particular user, "normally used" refers to a typical or common use of that class of product, regardless of the status of the particular user or of the way in which the particular user actually uses, or expects or is expected to use, the product. A product is a consumer product regardless of whether the product has substantial commercial, industrial or non-consumer uses, unless such uses represent the only significant mode of use of the product. "Installation Information" for a User Product means any methods, procedures, authorization keys, or other information required to install and execute modified versions of a covered work in that User Product from a modified version of its Corresponding Source. The information must suffice to ensure that the continued functioning of the modified object code is in no case prevented or interfered with solely because modification has been made. If you convey an object code work under this section in, or with, or specifically for use in, a User Product, and the conveying occurs as part of a transaction in which the right of possession and use of the User Product is transferred to the recipient in perpetuity or for a fixed term (regardless of how the transaction is characterized), the Corresponding Source conveyed under this section must be accompanied by the Installation Information. But this requirement does not apply if neither you nor any third party retains the ability to install modified object code on the User Product (for example, the work has been installed in ROM). The requirement to provide Installation Information does not include a requirement to continue to provide support service, warranty, or updates for a work that has been modified or installed by the recipient, or for the User Product in which it has been modified or installed. Access to a network may be denied when the modification itself materially and adversely affects the operation of the network or violates the rules and protocols for communication across the network. Corresponding Source conveyed, and Installation Information provided, in accord with this section must be in a format that is publicly documented (and with an implementation available to the public in source code form), and must require no special password or key for unpacking, reading or copying. 7. Additional Terms. "Additional permissions" are terms that supplement the terms of this License by making exceptions from one or more of its conditions. Additional permissions that are applicable to the entire Program shall be treated as though they were included in this License, to the extent that they are valid under applicable law. If additional permissions apply only to part of the Program, that part may be used separately under those permissions, but the entire Program remains governed by this License without regard to the additional permissions. When you convey a copy of a covered work, you may at your option remove any additional permissions from that copy, or from any part of it. (Additional permissions may be written to require their own removal in certain cases when you modify the work.) You may place additional permissions on material, added by you to a covered work, for which you have or can give appropriate copyright permission. Notwithstanding any other provision of this License, for material you add to a covered work, you may (if authorized by the copyright holders of that material) supplement the terms of this License with terms: a) Disclaiming warranty or limiting liability differently from the terms of sections 15 and 16 of this License; or b) Requiring preservation of specified reasonable legal notices or author attributions in that material or in the Appropriate Legal Notices displayed by works containing it; or c) Prohibiting misrepresentation of the origin of that material, or requiring that modified versions of such material be marked in reasonable ways as different from the original version; or d) Limiting the use for publicity purposes of names of licensors or authors of the material; or e) Declining to grant rights under trademark law for use of some trade names, trademarks, or service marks; or f) Requiring indemnification of licensors and authors of that material by anyone who conveys the material (or modified versions of it) with contractual assumptions of liability to the recipient, for any liability that these contractual assumptions directly impose on those licensors and authors. All other non-permissive additional terms are considered "further restrictions" within the meaning of section 10. If the Program as you received it, or any part of it, contains a notice stating that it is governed by this License along with a term that is a further restriction, you may remove that term. If a license document contains a further restriction but permits relicensing or conveying under this License, you may add to a covered work material governed by the terms of that license document, provided that the further restriction does not survive such relicensing or conveying. If you add terms to a covered work in accord with this section, you must place, in the relevant source files, a statement of the additional terms that apply to those files, or a notice indicating where to find the applicable terms. Additional terms, permissive or non-permissive, may be stated in the form of a separately written license, or stated as exceptions; the above requirements apply either way. 8. Termination. You may not propagate or modify a covered work except as expressly provided under this License. Any attempt otherwise to propagate or modify it is void, and will automatically terminate your rights under this License (including any patent licenses granted under the third paragraph of section 11). However, if you cease all violation of this License, then your license from a particular copyright holder is reinstated (a) provisionally, unless and until the copyright holder explicitly and finally terminates your license, and (b) permanently, if the copyright holder fails to notify you of the violation by some reasonable means prior to 60 days after the cessation. Moreover, your license from a particular copyright holder is reinstated permanently if the copyright holder notifies you of the violation by some reasonable means, this is the first time you have received notice of violation of this License (for any work) from that copyright holder, and you cure the violation prior to 30 days after your receipt of the notice. Termination of your rights under this section does not terminate the licenses of parties who have received copies or rights from you under this License. If your rights have been terminated and not permanently reinstated, you do not qualify to receive new licenses for the same material under section 10. 9. Acceptance Not Required for Having Copies. You are not required to accept this License in order to receive or run a copy of the Program. Ancillary propagation of a covered work occurring solely as a consequence of using peer-to-peer transmission to receive a copy likewise does not require acceptance. However, nothing other than this License grants you permission to propagate or modify any covered work. These actions infringe copyright if you do not accept this License. Therefore, by modifying or propagating a covered work, you indicate your acceptance of this License to do so. 10. Automatic Licensing of Downstream Recipients. Each time you convey a covered work, the recipient automatically receives a license from the original licensors, to run, modify and propagate that work, subject to this License. You are not responsible for enforcing compliance by third parties with this License. An "entity transaction" is a transaction transferring control of an organization, or substantially all assets of one, or subdividing an organization, or merging organizations. If propagation of a covered work results from an entity transaction, each party to that transaction who receives a copy of the work also receives whatever licenses to the work the party's predecessor in interest had or could give under the previous paragraph, plus a right to possession of the Corresponding Source of the work from the predecessor in interest, if the predecessor has it or can get it with reasonable efforts. You may not impose any further restrictions on the exercise of the rights granted or affirmed under this License. For example, you may not impose a license fee, royalty, or other charge for exercise of rights granted under this License, and you may not initiate litigation (including a cross-claim or counterclaim in a lawsuit) alleging that any patent claim is infringed by making, using, selling, offering for sale, or importing the Program or any portion of it. 11. Patents. A "contributor" is a copyright holder who authorizes use under this License of the Program or a work on which the Program is based. The work thus licensed is called the contributor's "contributor version". A contributor's "essential patent claims" are all patent claims owned or controlled by the contributor, whether already acquired or hereafter acquired, that would be infringed by some manner, permitted by this License, of making, using, or selling its contributor version, but do not include claims that would be infringed only as a consequence of further modification of the contributor version. For purposes of this definition, "control" includes the right to grant patent sublicenses in a manner consistent with the requirements of this License. Each contributor grants you a non-exclusive, worldwide, royalty-free patent license under the contributor's essential patent claims, to make, use, sell, offer for sale, import and otherwise run, modify and propagate the contents of its contributor version. In the following three paragraphs, a "patent license" is any express agreement or commitment, however denominated, not to enforce a patent (such as an express permission to practice a patent or covenant not to sue for patent infringement). To "grant" such a patent license to a party means to make such an agreement or commitment not to enforce a patent against the party. If you convey a covered work, knowingly relying on a patent license, and the Corresponding Source of the work is not available for anyone to copy, free of charge and under the terms of this License, through a publicly available network server or other readily accessible means, then you must either (1) cause the Corresponding Source to be so available, or (2) arrange to deprive yourself of the benefit of the patent license for this particular work, or (3) arrange, in a manner consistent with the requirements of this License, to extend the patent license to downstream recipients. "Knowingly relying" means you have actual knowledge that, but for the patent license, your conveying the covered work in a country, or your recipient's use of the covered work in a country, would infringe one or more identifiable patents in that country that you have reason to believe are valid. If, pursuant to or in connection with a single transaction or arrangement, you convey, or propagate by procuring conveyance of, a covered work, and grant a patent license to some of the parties receiving the covered work authorizing them to use, propagate, modify or convey a specific copy of the covered work, then the patent license you grant is automatically extended to all recipients of the covered work and works based on it. A patent license is "discriminatory" if it does not include within the scope of its coverage, prohibits the exercise of, or is conditioned on the non-exercise of one or more of the rights that are specifically granted under this License. You may not convey a covered work if you are a party to an arrangement with a third party that is in the business of distributing software, under which you make payment to the third party based on the extent of your activity of conveying the work, and under which the third party grants, to any of the parties who would receive the covered work from you, a discriminatory patent license (a) in connection with copies of the covered work conveyed by you (or copies made from those copies), or (b) primarily for and in connection with specific products or compilations that contain the covered work, unless you entered into that arrangement, or that patent license was granted, prior to 28 March 2007. Nothing in this License shall be construed as excluding or limiting any implied license or other defenses to infringement that may otherwise be available to you under applicable patent law. 12. No Surrender of Others' Freedom. If conditions are imposed on you (whether by court order, agreement or otherwise) that contradict the conditions of this License, they do not excuse you from the conditions of this License. If you cannot convey a covered work so as to satisfy simultaneously your obligations under this License and any other pertinent obligations, then as a consequence you may not convey it at all. For example, if you agree to terms that obligate you to collect a royalty for further conveying from those to whom you convey the Program, the only way you could satisfy both those terms and this License would be to refrain entirely from conveying the Program. 13. Use with the GNU Affero General Public License. Notwithstanding any other provision of this License, you have permission to link or combine any covered work with a work licensed under version 3 of the GNU Affero General Public License into a single combined work, and to convey the resulting work. The terms of this License will continue to apply to the part which is the covered work, but the special requirements of the GNU Affero General Public License, section 13, concerning interaction through a network will apply to the combination as such. 14. Revised Versions of this License. The Free Software Foundation may publish revised and/or new versions of the GNU General Public License from time to time. Such new versions will be similar in spirit to the present version, but may differ in detail to address new problems or concerns. Each version is given a distinguishing version number. If the Program specifies that a certain numbered version of the GNU General Public License "or any later version" applies to it, you have the option of following the terms and conditions either of that numbered version or of any later version published by the Free Software Foundation. If the Program does not specify a version number of the GNU General Public License, you may choose any version ever published by the Free Software Foundation. If the Program specifies that a proxy can decide which future versions of the GNU General Public License can be used, that proxy's public statement of acceptance of a version permanently authorizes you to choose that version for the Program. Later license versions may give you additional or different permissions. However, no additional obligations are imposed on any author or copyright holder as a result of your choosing to follow a later version. 15. Disclaimer of Warranty. THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 16. Limitation of Liability. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. 17. Interpretation of Sections 15 and 16. If the disclaimer of warranty and limitation of liability provided above cannot be given local legal effect according to their terms, reviewing courts shall apply local law that most closely approximates an absolute waiver of all civil liability in connection with the Program, unless a warranty or assumption of liability accompanies a copy of the Program in return for a fee. END OF TERMS AND CONDITIONS How to Apply These Terms to Your New Programs If you develop a new program, and you want it to be of the greatest possible use to the public, the best way to achieve this is to make it free software which everyone can redistribute and change under these terms. To do so, attach the following notices to the program. It is safest to attach them to the start of each source file to most effectively state the exclusion of warranty; and each file should have at least the "copyright" line and a pointer to where the full notice is found. Copyright (C) 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 3 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 program. If not, see . Also add information on how to contact you by electronic and paper mail. If the program does terminal interaction, make it output a short notice like this when it starts in an interactive mode: Copyright (C) This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. This is free software, and you are welcome to redistribute it under certain conditions; type `show c' for details. The hypothetical commands `show w' and `show c' should show the appropriate parts of the General Public License. Of course, your program's commands might be different; for a GUI interface, you would use an "about box". You should also get your employer (if you work as a programmer) or school, if any, to sign a "copyright disclaimer" for the program, if necessary. For more information on this, and how to apply and follow the GNU GPL, see . The GNU General Public License does not permit incorporating your program into proprietary programs. If your program is a subroutine library, you may consider it more useful to permit linking proprietary applications with the library. If this is what you want to do, use the GNU Lesser General Public License instead of this License. But first, please read . docx2txt-1.4/ChangeLog0000644000175100010010000001212412335160506013463 0ustar manojNonev1.4 : 15/05/2014 New feature: - Added configuration variable config_unzip_opts. This removes dependency on unzip program, and allows users to use unzipping programs like 7z, pkzipc, winzip as well. Updates: - Fixed list numbering. - Improved list/paragraph indentation and corresponding code. - Updated README with brief guidance on how this utility can be used to recover text from corrupted docx file. v1.3 : 07/04/2014 New feature: - Added support for handling lists (bullet, decimal, letter, roman) along with (attempt at) indentation. Updates: - Added configuration variable config_twipsPerChar. - Removed configuration variables: config_listIndent, config_exp_extra_deEscape. - Text output omits deleted text. This matters in case changes are being tracked in docx document. - Text output omits non-document_text content marked by wp/wp14 tags. v1.2 : 15/01/2012 New features: - Perl script usage is extended to accept docx file from standard input. It also works with input/output redirection now. Please refer to the documentation for more information. - Script files and configuration file can be installed in separate directories on (non-Windows) systems using Makefile for installation. - Linux Makefile also attempts to update the system configuration directory to desired directory in installed Perl script. - User specific and system wide configuration files can be maintained separately even on windows. Updates: - "-h" has to be given as the first argument to Perl script to get usage help. - Added new configuration variable "config_tempDir". - Configuration file is uniformly looked for in current directory, user configuration directory (APPDATA on Windows and HOME on non-Windows), system configuration directory (same location as script files on Windows, /etc or as set during installation on non-Windows systems) in the specified order. - Documentation has been updated with usage examples and information on how .docx file text content can directly be viewed using Vim and Emacs editors. - Improved handling of special (non-text) characters, along with support for more non-text characters like fractions. - Fixed Bug #3463033: added ' and " to docx specific escape character conversions. - Fixed the wrong code that had got committed during earlier fixing of nullDevice for Cygwin. v1.1 : 11/12/2011 New features: - Added a check for existence of unzip command. - Configuration file is looked for in HOME directory as well. Updates: - Configuration variables now begin with config_ . - Fixed bugs #3003903, #3082018 and #3082035. - Fixed nulldevice for Cygwin. - Superscripted cross-references are placed within [...] now. v1.0 : 04/10/2009 New features: - Input argument can also be a directory holding the unzipped content of .docx file. - Windows wrapper script, and support for using CakeCmd command line unzipper. - Configuration file support for easy control over settings. - Windows installation script. Updates: - Hyperlink is not displayed if hyperlink and hyperlinked text are same, even though user has enabled hyperlink display. - Improved handling of short line justification, capturing many cases that were missed in earlier approach. - Path names containing spaces are now handled. Please refer to the updated documentation for more details. v0.4 : 06/09/2009 New features: [suggestions from "Sergei Kulakov (sergei>ATDOTATDOT - ... etc.). Euro character is converted to E, however you can change this behaviour by comment-uncomment in perl script. docx2txt-1.4/ToDo0000644000175100010010000000143512320501252012473 0ustar manojNone1. Heuristics based cleanup of damaged document content. [Looking for more test samples.] 2. Extract images. Now there has been a user request as well. [target pre v2.0] 3. Handle footnotes. 4. Improve table and short line justification handling. Ideally table columns in a single row should be separated by pipe. Short line justification needs to be adjusted to situations when tab occurs in line. A quick look into these issues suggests that logic/code will need to be reorganised to handle these. 5. Create a simple manpage, hopefully after resolving footnote and list issues. 6. Implement simple state-machine for speedup [partially worked towards it]. 7. XML parsing??? and making things more efficient. When it has matured enough, may be a C/C++ version should be looked into. docx2txt-1.4/AUTHORS0000644000175100010010000000006011065260616012757 0ustar manojNoneSandeep Kumar ( shimple0 -AT- yahoo .DOT. com )