sandbox/odf2docutils/odf2docutils.py

   1 #! /usr/bin/env python
   2 # -*- coding: iso-8859-1 -*-
   3
   4 # Copyright (C) 2013 Stefan Merten
   5
   6 # odf2docutils.py is free software; you can redistribute it and/or modify
   7 # it under the terms of the GNU General Public License as published
   8 # by the Free Software Foundation; either version 2 of the License,
   9 # or (at your option) any later version.
  10
  11 # This program is distributed in the hope that it will be useful,
  12 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  13 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
  14 # General Public License for more details.
  15
  16 # You should have received a copy of the GNU General Public License
  17 # along with this program; if not, write to the Free Software
  18 # Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
  19 # 02111-1307, USA.
  20
  21 """
  22 Convert an Open Document Format (ODF) file to docutils XML.
  23 """
  24
  25 __docformat__ = 'reStructuredText' # Formatted to be rendered by epydoc
  26
  27 ###############################################################################
  28 ###############################################################################
  29 # Import
  30
  31 import sys
  32
  33 import docutils, docutils.core, docutils.frontend
  34 import docutils.io, docutils.readers, docutils.writers.docutils_xml
  35 import docutils_xml.io
  36
  37 ###############################################################################
  38 ###############################################################################
  39 # Constants
  40
  41 ###############################################################################
  42 ###############################################################################
  43 # Variables
  44
  45 ###############################################################################
  46 ###############################################################################
  47 # Functions
  48
  49 ###############################################################################
  50 ###############################################################################
  51 # Classes
  52
  53 class SettingsSpec(docutils.SettingsSpec):
  54     """
  55     Settings specifications for odf2docutils.
  56     """
  57
  58     xsltOptions = ( '-x', '--xslt' )
  59
  60     settings_spec = (
  61         "odf2docutils options", None,
  62         (( "Use Python implementation for conversion instead of the XSLT implementation (default).",
  63            ( '-p', '--python' ),
  64            { 'validator': docutils.frontend.validate_boolean,
  65              'action': 'store_true',
  66              'default': True, }, ),
  67          ( "Use XSLT for conversion instead of the Python implementation.",
  68            xsltOptions,
  69            { 'validator': docutils.frontend.validate_boolean,
  70              'action': 'store_false',
  71              'dest': 'python', },
  72            ), ),
  73         )
  74
  75     config_section = "odf2docutils"
  76
  77 ##############################################################################
  78
  79 class OdfFileInput(docutils_xml.io.ZipFileInput):
  80     """
  81     Input for ODF files.
  82     """
  83
  84     contentPath = 'content.xml'
  85
  86 ##############################################################################
  87 ##############################################################################
  88 # Now work
  89
  90 if __name__ == '__main__':
  91     # Check options to set correct parser and writer
  92     usePython = True
  93
  94     # The following "General Docutils Options" are effectively ignored:
  95     #
  96     #   Used in `transforms.frontmatter.DocTitle` used by
  97     #   `readers.standalone.Reader`:
  98     #     --title
  99     #
 100     #   Used in `transforms.universal.Decorations` used by `readers.Reader`:
 101     #     --generator
 102     #     --no-generator
 103     #     --date
 104     #     --time
 105     #     --no-datestamp
 106     #     --source-link
 107     #     --source-url
 108     #     --no-source-link
 109     #
 110     #   Used in `transforms.parts.Contents` used by `parsers.rst.directives...`:
 111     #     --toc-entry-backlinks
 112     #     --toc-top-backlinks
 113     #     --no-toc-backlinks
 114     #
 115     #   Used in `transforms.parts.SectNum` used by `parsers.rst.directives...`:
 116     #     --section-numbering
 117     #     --no-section-numbering
 118     #
 119     #   Used in `transforms.universal.StripComments` used by `readers.Reader`:
 120     #     --strip-comments
 121     #     --leave-comments
 122     #
 123     #   Used in `transforms.universal.StripClassesAndElements` used by
 124     #   `writers.Writer`:
 125     #     --strip-elements-with-class
 126     #     --strip-class
 127     #
 128     #   Used in `writers.html4css1.HTMLTranslator`:
 129     #     --footnote-backlinks
 130     #     --no-footnote-backlinks
 131     #
 132     #   Used in `core.Publisher`:
 133     #     --input-encoding
 134     #
 135     #   Used in `parsers.rst.directives...`
 136     #     --input-encoding-error-handler
 137
 138     settingsSpec = SettingsSpec()
 139     for arg in sys.argv:
 140         if arg in settingsSpec.xsltOptions:
 141             usePython = False
 142     if usePython:
 143         from odf2docutilslib.python import Parser
 144         from docutils.writers.docutils_xml import Writer
 145     else:
 146         from odf2docutilslib.xslt import Parser, Writer
 147
 148     pub = docutils.core.Publisher(docutils.readers.Reader(), Parser(), Writer(),
 149                                   source_class=OdfFileInput,
 150                                   destination_class=docutils.io.BinaryFileOutput)
 151     pub.process_command_line(settings_spec=settingsSpec,
 152                              description="Reads ODF file <source> (default is stdin) and writes Docutils XML to <destination> (default is stdout).")
 153     if pub.settings.python != usePython:
 154         raise AssertionError("Internal error: Assumed setting of --xslt/--python not confirmed by explicit parsing")
 155     pub.publish()
 156
 157 # TODO Use XSLT variant as export filter for LibreOffice - which works from
 158 #      scratch using https://help.libreoffice.org/Common/Creating_XML_Filters