#!/usr/bin/env python3
# Copyright (C) 2014 J.F.Dockes
# 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.,
# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
######################################
from __future__ import print_function
import sys
import rclexecm
import rclxslt
from rclbasehandler import RclBaseHandler
from zipfile import ZipFile
stylesheet_meta = '''
<xsl:value-of select="."/>
abstract
keywords
author
keywords
'''
stylesheet_content = '''
'''
class OOExtractor(RclBaseHandler):
def __init__(self, em):
super(OOExtractor, self).__init__(em)
def html_text(self, fn):
f = open(fn, 'rb')
zip = ZipFile(f)
docdata = b'\n\n'
# Wrap metadata extraction because it can sometimes throw
# while the main text will be valid
try:
metadata = zip.read("meta.xml")
if metadata:
res = rclxslt.apply_sheet_data(stylesheet_meta, metadata)
docdata += res
except:
# To be checked. I'm under the impression that I get this when
# nothing matches?
#self.em.rclog("No/bad metadata in %s" % fn)
pass
docdata += b'\n\n'
content = zip.read("content.xml")
if content:
res = rclxslt.apply_sheet_data(stylesheet_content, content)
docdata += res
docdata += b''
return docdata
if __name__ == '__main__':
proto = rclexecm.RclExecM()
extract = OOExtractor(proto)
rclexecm.main(proto, extract)