Bug#281351: ITP: sxwtotext -- Simple OpenOffice.org .sxw to text converter

[Liam Morland]

Matthias,

The sxw2text shell script has some serious limitations. I have a written
a perl program which does much the same thing, but doesn't try to write
any files to the current (or any other) directory and does a better job
at converting lists and tables. It also does something useful with OOo
spreadsheets.

Liam

-- 
Liam Morland <[EMAIL PROTECTED]>        Canadian Scout Camps Directory
<http://Liam.Morland.ca/>              <http://ScoutDocs.ca/Camps/>

PGP Public Key: <http://Liam.Morland.ca/public-key.pgp>


#!/usr/bin/perl -w

# sxw2txt -- Coverts OpenOffice.org Writer files to plain text.
# Copyright (C) 2004 Liam Morland
#
# 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 program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307,
# USA.
#
# Liam Morland <[EMAIL PROTECTED]> <http://Liam.Morland.ca/>
# 86A McDougall Road, Waterloo, Ontario, N2L 5C5, CANADA

use strict;

# First argument is taken to be the input file. All other args are ignored.
my $input_file = shift;

# If we have a filename, try to get the content.xml from it,
# otherwise print usage information.
if ($input_file){
	$_ = `unzip -p $input_file content.xml 2>/dev/null`;
} else {
	print "sxw2txt: Coverts OpenOffice.org Writer files to plain text.\n";
	print "Usage: sxw2txt input-file\n";
	exit(1);
}

# If we don't have any content.xml, exit with an error.
if (!$_){
	print "sxw2txt: Error: $input_file is probably not an OpenOffice.org file.\n";
	exit(2);
}

# Convert the OOo XML to text with a series of regex substitutions.
s,\n+, ,g;

# Tables are wrapped with [begin-table] and [end-table].
# Rows and cells begin with [table-row] and [table-cell] respectively.
s,<table:table( [^>]*)?>,\n\n[begin-table],g;
s,</table:table>,\n[end-table],g;
s,<table:table-cell( [^>]*)?>(<[^>]+>)*<text:p[^>]*>,\n[table cell],g;
s,<table:table-row( [^>]*)?>,\n\n[table row],g;

# OOo tabs are made into tab characters.
s,<text:tab-stop/>,\t,g;

# Each list item is given a '*' as a bullet. 
# Sorry, no fancy support for nested lists yet.
s,<text:list-item><text:p[^>]*>,\n\n* ,g;

# Skip two lines before each new paragraph.
s,<text:p[^>]*>,\n\n,g;

# Get rid of any remaining tags. Want to add support for tags not
# handled above? Do it above this line.
s,<[^>]*>,,g;

# Convert common entities into the appropriate character.
s,&lt;,<,g;
s,&gt;,>,g;
s,&apos;,',g;
s,&quot;,",g;
s,&amp;,&,g;

# Remove extra whitespace and print the result, always ending with \n.
s,\n\n\n+,\n\n,sg;
s,^\s*(.+)\s*$,$1,s;
print "$_\n";

signature.asc
Description: Digital signature