Merge branch 'nexedi'

MANIFEST.in

-include README.txt
-include CHANGES.txt
+include README.rst
+include CHANGELOG.rst
 recursive-include cloudooo *

cloudooo/handler/imagemagick/tests/testImagemagickHandler.py

@@ -53,7 +53,7 @@ class TestHandler(HandlerTestCase):
     metadata = handler.getMetadata()
     self.assertEquals(metadata.get("Compression"), "Zip")
     self.assertEquals(metadata.get("Colorspace"), "sRGB")
-    self.assertEquals(metadata.get("Matte color"), "grey74")
+    self.assertEquals(metadata.get("Alpha color"), "grey74")
 
   def testsetMetadata(self):
     """ Test if metadata are inserted correclty """

cloudooo/handler/ooo/helper/unoconverter.py

@@ -108,7 +108,12 @@ class UnoConverter(object):
     elif filter_name == "impress_pdf_Export":
       property = PropertyValue('FilterData', 0,
                        uno.Any('[]com.sun.star.beans.PropertyValue',
-                       (PropertyValue('ExportNotesPages', 0, True, 0),),), 0)
+                       (PropertyValue('ExportNotesPages', 0, True, 0),
+                       PropertyValue('SelectPdfVersion', 0, 1, 0),),), 0)
+    elif "pdf_Export" in filter_name :
+      property = PropertyValue('FilterData', 0,
+                       uno.Any('[]com.sun.star.beans.PropertyValue',
+                       (PropertyValue('SelectPdfVersion', 0, 1, 0),),), 0)
     elif filter_name in ("draw_html_Export", "HTML (StarCalc)"):
       property = PropertyValue('FilterData', 0,
                         uno.Any('[]com.sun.star.beans.PropertyValue',

cloudooo/handler/ooo/helper/unomimemapper.py

@@ -35,11 +35,17 @@ except ImportError:
 import helper_util
 from getopt import getopt, GetoptError
 
+# python3 support
 try:
   basestring
 except NameError:
   basestring = str
 
+try:
+  long
+except NameError:
+  long = int
+
 __doc__ = """
 
 usage: unomimemapper [options]
@@ -76,7 +82,7 @@ class UnoMimemapper(object):
         for obj in iter(element_list):
             if obj.Name in ignore_name_list:
               continue
-            if not isinstance(obj.Value, (bool, int, basestring, tuple)):
+            if not isinstance(obj.Value, (bool, int, long, basestring, tuple)):
               continue
             element_dict[obj.Name] = obj.Value
             service_dict[name] = element_dict

cloudooo/handler/ooo/mimemapper.py

@@ -136,10 +136,10 @@ class MimeMapper(object):
     filter_dict, type_dict = json.loads(stdout)
 
     ooo_disable_filter_list = kw.get("ooo_disable_filter_list") or [] + [
-        'writer_jpg_Export', # Seems not working from cloudooo in Libre Office 4.3.3.2
-        'writer_png_Export', # Seems not working from cloudooo in Libre Office 4.3.3.2
-        'draw_eps_Export', #  Seems not working from cloudooo in Libre Office 5.0.0.5
-        'impress_eps_Export', #  Seems not working from cloudooo in Libre Office 5.0.0.5
+      # 'writer_jpg_Export', # Seems not working from cloudooo in Libre Office 4.3.3.2
+      # 'writer_png_Export', # Seems not working from cloudooo in Libre Office 4.3.3.2
+      # 'draw_eps_Export', #  Seems not working from cloudooo in Libre Office 5.0.0.5
+      # 'impress_eps_Export', #  Seems not working from cloudooo in Libre Office 5.0.0.5
     ]
     ooo_disable_filter_name_list = kw.get("ooo_disable_filter_name_list") or [] + [
         'Text', # Use 'Text - Choose Encoding' instead

cloudooo/handler/ooo/tests/testOooMimemapper.py

@@ -36,10 +36,10 @@ text_expected_tuple = (
     ('docx', 'Office Open XML Text'),
     ('fodt', 'Flat XML ODF Text Document'),
     ('html', 'HTML Document (Writer)'),
-#    ('jpg', 'JPEG - Joint Photographic Experts Group'),
+    ('jpg', 'JPEG - Joint Photographic Experts Group'),
     ('odt', 'ODF Text Document'),
     ('pdf', 'PDF - Portable Document Format'),
-#    ('png', 'PNG - Portable Network Graphic'),
+    ('png', 'PNG - Portable Network Graphic'),
     ('rtf', 'Rich Text'),
     ('txt', 'Text - Choose Encoding'),
     ('docy', 'Docy'),
@@ -51,7 +51,7 @@ global_expected_tuple = (
 drawing_expected_tuple = (
     ('bmp', 'BMP - Windows Bitmap'),
     ('emf', 'EMF - Enhanced Metafile'),
-#    ('eps', 'EPS - Encapsulated PostScript'),
+    ('eps', 'EPS - Encapsulated PostScript'),
     ('fodg', 'Flat XML ODF Drawing'),
     ('gif', 'GIF - Graphics Interchange Format'),
     ('html', 'HTML Document (Draw)'),
@@ -84,7 +84,7 @@ web_expected_tuple = (
 presentation_expected_tuple = (
     ('bmp', 'BMP - Windows Bitmap'),
     ('emf', 'EMF - Enhanced Metafile'),
-#    ('eps', 'EPS - Encapsulated PostScript'),
+    ('eps', 'EPS - Encapsulated PostScript'),
     ('fodp', 'Flat XML ODF Presentation'),
     ('gif', 'GIF - Graphics Interchange Format'),
     ('html', 'HTML Document (Impress)'),
@@ -119,8 +119,10 @@ spreadsheet_expected_tuple = (
     ('html', 'HTML Document (Calc)'),
     ('ods', 'ODF Spreadsheet'),
     ('pdf', 'PDF - Portable Document Format'),
+    ('png', 'PNG - Portable Network Graphic'),
     ('slk', 'SYLK'),
     ('xls', 'Microsoft Excel 97-2003'),
+    ('xlsm', 'Microsoft Excel 2007-2016 XML (macro enabled)'),
     ('ms.xlsx', 'Microsoft Excel 2007-2013 XML'),
     ('xlsx', 'Office Open XML Spreadsheet'),
     ('xlsy', 'Xlsy'),

cloudooo/handler/ooo/tests/testOooServer.py

@@ -480,25 +480,23 @@ class TestServer(TestCase):
     """Test if getImageItemList can get the list of images items from odt file"""
     data = encodestring(open("./data/granulate_test.odt").read())
     image_list = self.proxy.getImageItemList(data, "odt")
-    self.assertEquals([['10000000000000C80000009C76245A92.jpg', ''],
-                      ['10000201000000C80000004EE2BCEED0.png', 'TioLive Logo'],
-                      ['10000201000000C80000004EE2BCEED0.png', ''],
-                      ['2000004F00004233000013707E7DE37A.svm', 'Python Logo'],
-                      ['10000201000000C80000004EE2BCEED0.png',
-                                                        'Again TioLive Logo']],
-                                                                    image_list)
+    self.assertEquals([['10000000000000C80000009CBF079A6E41EE290C.jpg', ''],
+                       ['10000201000000C80000004EF26C99A54A61B987.png', 'TioLive Logo'],
+                       ['10000201000000C80000004EF26C99A54A61B987.png', ''],
+                       ['2000004F0000423300001370ADF6545B2997B448.svm', 'Python Logo'],
+                       ['10000201000000C80000004EF26C99A54A61B987.png', 'Again TioLive Logo']],
+                      image_list)
 
   def testGetImageItemListFromDoc(self):
     """Test if getImageItemList can get the list of images items from doc file"""
     data = encodestring(open("./data/granulate_test.doc").read())
     image_list = self.proxy.getImageItemList(data, "doc")
-    self.assertEquals([['10000000000000C80000009C76245A92.jpg', ''],
-                      ['10000201000000C80000004EE2BCEED0.png', 'TioLive Logo'],
-                      ['10000201000000C80000004EE2BCEED0.png', ''],
-                      ['2000031600004233000013706A5EA1C8.wmf', 'Python Logo'],
-                      ['10000201000000C80000004EE2BCEED0.png',
-                                                        'Again TioLive Logo']],
-                                                                    image_list)
+    self.assertEquals([['10000000000000C80000009CBF079A6E41EE290C.jpg', ''],
+                       ['10000201000000C80000004EF26C99A54A61B987.png', 'TioLive Logo'],
+                       ['10000201000000C80000004EF26C99A54A61B987.png', ''],
+                       ['2000031600004233000013702113A0E70B910778.wmf', 'Python Logo'],
+                       ['10000201000000C80000004EF26C99A54A61B987.png', 'Again TioLive Logo']],
+                      image_list)
 
   def testGetImageFromOdt(self):
     """Test if getImage can get a image from odt file after zip"""
@@ -516,7 +514,7 @@ class TestServer(TestCase):
     #so compare with the server return.
     data_odt = self.proxy.convertFile(data, 'doc', 'odt', False)
     zip = ZipFile(StringIO(decodestring(data_odt)))
-    image_id = '10000000000000C80000009C76245A92.jpg'
+    image_id = '10000000000000C80000009CBF079A6E41EE290C.jpg'
     original_image = zip.read('Pictures/%s' % image_id)
     geted_image = decodestring(self.proxy.getImage(data, image_id, "doc"))
     self.assertEquals(original_image, geted_image)

cloudooo/handler/wkhtmltopdf/tests/data/test_toc.xsl

+<?xml version="1.0" encoding="UTF-8"?>
+<xsl:stylesheet version="2.0"
+    xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+    xmlns:outline="http://wkhtmltopdf.org/outline"
+    xmlns="http://www.w3.org/1999/xhtml">
+  <xsl:output method="html" encoding="utf-8" indent="yes" doctype-system="about:legacy-compat"/>
+
+  <xsl:template match="outline:outline">
+    <xsl:param name="count" select="0" />
+    <html>
+      <head>
+        <title>Table of Contents</title>
+        <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+        <style>
+          html, body {
+            overflow-x: initial !important;
+          }
+        </style>
+      </head>
+      <body>
+        <p class="ci-document-faux-h1">Table of Contents</p>
+        <div class="ci-document-table-of-content">
+          <p class="ci-document-helper"></p>
+          <ol>
+            <xsl:apply-templates select="outline:item/outline:item">
+              <xsl:with-param name="count" select="$count" />
+            </xsl:apply-templates>
+          </ol>
+        </div>
+      </body>
+    </html>
+  </xsl:template>
+  <xsl:template match="outline:item">
+    <xsl:param name="count" />
+      <xsl:choose>
+        <xsl:when test="number($count)=0">
+          <li class="ci-document-table-of-content-lead-item">
+            <xsl:if test="@title!=''">
+              <div>
+                <a>
+                  <xsl:if test="@link">
+                    <xsl:attribute name="href"><xsl:value-of select="@link"/></xsl:attribute>
+                  </xsl:if>
+                  <xsl:if test="@backLink">
+                    <xsl:attribute name="name"><xsl:value-of select="@backLink"/></xsl:attribute>
+                  </xsl:if>
+                  <xsl:value-of select="@title" />
+                </a>
+                <span><xsl:value-of select="@page" /> </span>
+              </div>
+            </xsl:if>
+            <ol>
+              <xsl:comment>added to prevent self-closing tags in QtXmlPatterns</xsl:comment>
+              <xsl:apply-templates select="outline:item"></xsl:apply-templates>
+            </ol>
+          </li>
+        </xsl:when>
+        <xsl:otherwise>
+          <li>
+            <xsl:if test="@title!=''">
+              <div>
+                <a>
+                  <xsl:if test="@link">
+                    <xsl:attribute name="href"><xsl:value-of select="@link"/></xsl:attribute>
+                  </xsl:if>
+                  <xsl:if test="@backLink">
+                    <xsl:attribute name="name"><xsl:value-of select="@backLink"/></xsl:attribute>
+                  </xsl:if>
+                  <xsl:value-of select="@title" />
+                </a>
+                <span><xsl:value-of select="@page" /> </span>
+              </div>
+            </xsl:if>
+            <ol>
+              <xsl:comment>added to prevent self-closing tags in QtXmlPatterns</xsl:comment>
+              <xsl:apply-templates select="outline:item"></xsl:apply-templates>
+            </ol>
+          </li>
+        </xsl:otherwise>
+      </xsl:choose>
+  </xsl:template>
+</xsl:stylesheet>

cloudooo/handler/wkhtmltopdf/tests/data/test_with_opacity_style.html

+<!DOCTYPE html>
+<html>
+  <head>
+    <meta charset="utf-8" />
+    <title>Test Title With Opacity Style</title>
+  </head>
+  <body>
+    <p style="opacity:0.5;">Hello</p>
+  </body>
+</html>

cloudooo/handler/wkhtmltopdf/tests/data/test_with_png_dataurl.html

+<!DOCTYPE html>
+<html>
+  <head>
+    <meta charset="utf-8" />
+    <title>Test Title With PNG Data URL</title>
+  </head>
+  <body>
+    <p>Hello</p>
+    <img src="data:image/png;base64,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" />
+  </body>
+</html>

cloudooo/handler/wkhtmltopdf/tests/data/test_with_script.html

+<!DOCTYPE html>
+<html>
+  <head>
+    <meta charset="utf-8" />
+    <title>Test Title With Script</title>
+    <script>
+      window.addEventListener("load", function () {
+        document.querySelector("p").textContent = atob("V29ybGQ=");
+      });
+    </script>
+  </head>
+  <body>
+    <p>Hello</p>
+  </body>
+</html>

cloudooo/handler/wkhtmltopdf/tests/data/test_with_toc.html

+<!DOCTYPE html>
+<html>
+  <head>
+    <meta charset="utf-8" />
+    <title>Test Title With Table of Content</title>
+  </head>
+  <body>
+    <h1>Title</h1>
+    <p>Description paragraph</p>
+    <h2>Sub Title</h2>
+    <p>Subject paragraph</p>
+    <h2>Sub Title number 2</h2>
+    <p>Again subject paragraph</p>
+  </body>
+</html>

cloudooo/handler/wkhtmltopdf/tests/testWkhtmltopdfHandler.py

+##############################################################################
+#
+# Copyright (c) 2016 Nexedi SA and Contributors. All Rights Reserved.
+#
+# WARNING: This program as such is intended to be used by professional
+# programmers who take the whole responsibility of assessing all potential
+# consequences resulting from its eventual inadequacies and bugs
+# End users who are looking for a ready-to-use solution with commercial
+# guarantees and support are strongly adviced to contract a Free Software
+# Service Company
+#
+# 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.
+#
+##############################################################################
+
+from base64 import b64encode
+
+import magic
+from cloudooo.handler.wkhtmltopdf.handler import Handler
+from cloudooo.tests.handlerTestCase import HandlerTestCase, make_suite
+
+
+class TestHandler(HandlerTestCase):
+
+  def afterSetUp(self):
+    self.kw = dict(env=dict(PATH=self.env_path))
+
+  def _testBase(self, html_path, **conversion_kw):
+    html_file = open(html_path).read()
+    handler = Handler(self.tmp_url, html_file, "html", **self.kw)
+    pdf_file = handler.convert("pdf", **conversion_kw)
+    mime = magic.Magic(mime=True)
+    pdf_mimetype = mime.from_buffer(pdf_file)
+    self.assertEquals("application/pdf", pdf_mimetype)
+
+  def testConvertHtmlWithPngDataUrlToPdf(self):
+    """Test conversion of html with png data url to pdf"""
+    self._testBase("data/test_with_png_dataurl.html")
+
+  def testConvertHtmlWithScriptToPdf(self):
+    """Test conversion of html with script to pdf"""
+    self._testBase("data/test_with_script.html")
+
+  def testConvertHtmlWithOpacityStyleToPdf(self):
+    """Test conversion of html with opacity style to pdf
+
+    Opacity style in a web pages causes Segmentation Fault only if wkhtmltopdf
+    is not connected to a graphical service like Xorg.
+    """
+    self._testBase("data/test_with_opacity_style.html")
+
+  # TODO: def testConvertHtmlWithHeaderAndFooter(self):
+
+  def testConvertHtmlWithTableOfContent(self):
+    """Test conversion of html with an additional table of content"""
+    self._testBase(
+      "data/test_with_toc.html",
+      toc=True,
+      xsl_style_sheet_data=b64encode(open("data/test_toc.xsl").read()),
+    )
+    # XXX how to check for table of content presence ?
+
+  def testsetMetadata(self):
+    """ Test if metadata are inserted correclty """
+    handler = Handler(self.tmp_url, "", "png", **self.kw)
+    self.assertRaises(NotImplementedError, handler.setMetadata)
+
+
+def test_suite():
+  return make_suite(TestHandler)

cloudooo/handler/wkhtmltopdf/tests/testWkhtmltopdfServer.py

+##############################################################################
+#
+# Copyright (c) 2016 Nexedi SA and Contributors. All Rights Reserved.
+#
+# WARNING: This program as such is intended to be used by professional
+# programmers who take the whole responsibility of assessing all potential
+# consequences resulting from its eventual inadequacies and bugs
+# End users who are looking for a ready-to-use solution with commercial
+# guarantees and support are strongly adviced to contract a Free Software
+# Service Company
+#
+# 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.
+#
+##############################################################################
+from os.path import join
+from cloudooo.tests.cloudoooTestCase import TestCase, make_suite
+
+
+class TestServer(TestCase):
+  """Test XmlRpc Server. Needs cloudooo server started"""
+
+  def ConversionScenarioList(self):
+    return [
+      (join('data', 'test_with_png_dataurl.html'), "html", "pdf", "application/pdf"),
+      (join('data', 'test_with_script.html'), "html", "pdf", "application/pdf"),
+    ]
+
+  def testConvertHtmltoPdf(self):
+    """Converts html to pdf"""
+    self.runConversionList(self.ConversionScenarioList())
+
+  def FaultConversionScenarioList(self):
+    return [
+      # Test to verify if server fail when a empty string is sent
+      ('', '', ''),
+      # Try convert one html for a invalid format
+      (open(join('data', 'test_with_png_dataurl.html')).read(), 'html', 'xyz'),
+    ]
+
+def test_suite():
+  return make_suite(TestServer)

cloudooo/handler/x2t/handler.py

@@ -26,16 +26,16 @@
 #
 ##############################################################################
 from xml.etree import ElementTree
-from os.path import join, dirname, realpath
 from subprocess import Popen, PIPE
-from tempfile import NamedTemporaryFile
+from tempfile import NamedTemporaryFile, mktemp
 import sys
+import os
 
 from zope.interface import implements
 
 from cloudooo.interfaces.handler import IHandler
 from cloudooo.file import File
-from cloudooo.util import logger
+from cloudooo.util import logger, zipTree, unzip
 
 AVS_OFFICESTUDIO_FILE_UNKNOWN = "0"
 AVS_OFFICESTUDIO_FILE_DOCUMENT_DOCX = "65"
@@ -52,7 +52,7 @@ AVS_OFFICESTUDIO_FILE_CANVAS_PRESENTATION = "8195"
 AVS_OFFICESTUDIO_FILE_OTHER_HTMLZIP = "2051"
 AVS_OFFICESTUDIO_FILE_OTHER_ZIP = "2057"
 
-Ext2Formats = {
+format_code_map = {
   "docy": AVS_OFFICESTUDIO_FILE_CANVAS_WORD,
   "docx": AVS_OFFICESTUDIO_FILE_DOCUMENT_DOCX,
   "xlsy": AVS_OFFICESTUDIO_FILE_CANVAS_SPREADSHEET,
@@ -61,11 +61,6 @@ Ext2Formats = {
   "pptx": AVS_OFFICESTUDIO_FILE_PRESENTATION_PPTX,
 }
 
-dir_name = dirname(realpath(sys.argv[0]))
-#dir_name = join(dirname(realpath(__file__)), 'bin')
-converter_bin = join(dir_name, 'x2t')
-converter_lib_dirname = join(dir_name, 'lib')
-
 yformat_map = {
   'docy': 'docx',
   'xlsy': 'xlsx',
@@ -78,9 +73,13 @@ yformat_service_map = {
   'ppty': 'com.sun.star.presentation.PresentationDocument',
 }
 
+yformat_tuple = ("docy", "xlsy", "ppty")
 
 class Handler(object):
-  """ImageMagic Handler is used to handler images."""
+  """
+  X2T Handler is used to convert Microsoft Office 2007 documents to OnlyOffice
+  documents.
+  """
 
   implements(IHandler)
 
@@ -91,55 +90,83 @@ class Handler(object):
     data(string)
       The opened and readed file into a string
     source_format(string)
-      The source format of the inputed file"""
+      The source format of the inputed file
+    """
     self.base_folder_url = base_folder_url
     self.file = File(base_folder_url, data, source_format)
     self.environment = kw.get("env", {})
-    self.environment['LD_LIBRARY_PATH'] = converter_lib_dirname
 
   def convert(self, destination_format=None, **kw):
     """ Convert the inputed file to output as format that were informed """
-    logger.debug("yformat convert x2t: %s > %s" % (self.file.source_format, destination_format))
-    in_format = Ext2Formats.get(self.file.source_format)
-    out_format = Ext2Formats.get(destination_format)
-
-    with NamedTemporaryFile(suffix='.%s' % destination_format, dir=self.base_folder_url) as output_file:
-      config = {
-        # 'm_sKey': 'from',
-        'm_sFileFrom': self.file.getUrl(),
-        'm_nFormatFrom': in_format,
-        'm_sFileTo': output_file.name,
-        'm_nFormatTo': out_format,
-        # 'm_bPaid': 'true',
-        # 'm_bEmbeddedFonts': 'false',
-        # 'm_bFromChanges': 'false',
-        # 'm_sFontDir': '/usr/share/fonts',
-        # 'm_sThemeDir': '/var/www/onlyoffice/documentserver/FileConverterService/presentationthemes',
-      }
-      with NamedTemporaryFile(suffix=".xml", dir=self.base_folder_url) as temp_xml:
-        root = ElementTree.Element('root')
-        for key, value in config.items():
-          ElementTree.SubElement(root, key).text = value
-        ElementTree.ElementTree(root).write(temp_xml, encoding='utf-8', xml_declaration=True, default_namespace=None,
-                                            method="xml")
-        temp_xml.flush()
-        p = Popen([converter_bin, temp_xml.name],
-                  env=self.environment,
-                  stdout=PIPE,
-                  stderr=PIPE,
-                  close_fds=True,
-                  )
-        stdout, stderr = p.communicate()
-        with open(output_file.name) as output_file1:
-          file_content = output_file1.read()
-        return_code_msg = "yformat convert x2t return:{}".format(p.returncode)
-        if p.returncode != 0 or not file_content:
-          raise Exception(return_code_msg + '\n' + stderr)
-      logger.debug(stdout)
-      logger.debug(stderr)
-      logger.debug("yformat convert x2t return:{}".format(p.returncode))
+    source_format = self.file.source_format
+    logger.debug("x2t convert: %s > %s" % (source_format, destination_format))
+
+    # init vars and xml configuration file
+    in_format = format_code_map[source_format]
+    out_format = format_code_map[destination_format]
+    root_dir = self.file.directory_name
+    input_dir = os.path.join(root_dir, "input");
+    output_dir = os.path.join(root_dir, "output");
+    final_file_name = os.path.join(root_dir, "document.%s" % destination_format)
+    input_file_name = self.file.getUrl()
+    output_file_name = final_file_name
+    config_file_name = os.path.join(root_dir, "config.xml")
+
+    if source_format in yformat_tuple:
+      os.mkdir(input_dir)
+      unzip(self.file.getUrl(), input_dir)
+      for _, _, files in os.walk(input_dir):
+        input_file_name, = files
+        break
+      input_file_name = os.path.join(input_dir, input_file_name)
+    if destination_format in yformat_tuple:
+      os.mkdir(output_dir)
+      output_file_name = os.path.join(output_dir, "body.txt")
+
+    config_file = open(config_file_name, "w")
+
+    config = {
+      # 'm_sKey': 'from',
+      'm_sFileFrom': input_file_name,
+      'm_nFormatFrom': in_format,
+      'm_sFileTo': output_file_name,
+      'm_nFormatTo': out_format,
+      # 'm_bPaid': 'true',
+      # 'm_bEmbeddedFonts': 'false',
+      # 'm_bFromChanges': 'false',
+      # 'm_sFontDir': '/usr/share/fonts',
+      # 'm_sThemeDir': '/var/www/onlyoffice/documentserver/FileConverterService/presentationthemes',
+    }
+    root = ElementTree.Element('root')
+    for key, value in config.items():
+      ElementTree.SubElement(root, key).text = value
+    ElementTree.ElementTree(root).write(config_file, encoding='utf-8', xml_declaration=True, default_namespace=None, method="xml")
+    config_file.close()
+
+    # run convertion binary
+    p = Popen(
+      ["x2t", config_file.name],
+      stdout=PIPE,
+      stderr=PIPE,
+      close_fds=True,
+      env=self.environment,
+    )
+    stdout, stderr = p.communicate()
+    if p.returncode != 0:
+      raise RuntimeError("x2t: exit code %d != 0\n+ %s\n> stdout: %s\n> stderr: %s@ x2t xml:\n%s" % (p.returncode, " ".join(["x2t", config_file.name]), stdout, stderr, "  " + open(config_file.name).read().replace("\n", "\n  ")))
+
+    if destination_format in yformat_tuple:
+      zipTree(
+        final_file_name,
+        (output_file_name, ""),
+        (os.path.join(os.path.dirname(output_file_name), "media"), ""),
+      )
+
+    self.file.reload(final_file_name)
+    try:
+      return self.file.getContent()
+    finally:
       self.file.trash()
-      return file_content
 
   def getMetadata(self, base_document=False):
     """Returns a dictionary with all metadata of document.

cloudooo/handler/x2t/tests/testX2tHandler.py

+##############################################################################
+#
+# Copyright (c) 2009-2010 Nexedi SA and Contributors. All Rights Reserved.
+#                    Gabriel M. Monnerat <gabriel@tiolive.com>
+#
+# WARNING: This program as such is intended to be used by professional
+# programmers who take the whole responsibility of assessing all potential
+# consequences resulting from its eventual inadequacies and bugs
+# End users who are looking for a ready-to-use solution with commercial
+# guarantees and support are strongly adviced to contract a Free Software
+# Service Company
+#
+# 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.
+#
+##############################################################################
+
+
+import magic
+import os.path
+from zipfile import ZipFile
+from cStringIO import StringIO
+from cloudooo.handler.x2t.handler import Handler
+from cloudooo.tests.handlerTestCase import HandlerTestCase, make_suite
+
+class TestHandler(HandlerTestCase):
+
+  def afterSetUp(self):
+    self.kw = dict(env=dict(PATH=self.env_path))
+
+  def testConvertXlsx(self):
+    """Test conversion of xlsx to xlsy and back"""
+    y_data = Handler(self.tmp_url, open("data/test.xlsx").read(), "xlsx", **self.kw).convert("xlsy")
+    y_body_data = ZipFile(StringIO(y_data)).open("body.txt").read()
+    self.assertTrue(y_body_data.startswith("XLSY;v2;5883;"), "%r... does not start with 'XLSY;v2;5883;'" % (y_body_data[:20],))
+
+    x_data = Handler(self.tmp_url, y_data, "xlsy", **self.kw).convert("xlsx")
+    # magic inspired by https://github.com/minad/mimemagic/pull/19/files
+    self.assertIn("xl/", x_data[:2000])
+
+  def testConvertXlsy(self):
+    """Test conversion of xlsy to xlsx and back"""
+    x_data = Handler(self.tmp_url, open("data/test.xlsy").read(), "xlsy", **self.kw).convert("xlsx")
+    self.assertIn("xl/", x_data[:2000])
+
+    y_data = Handler(self.tmp_url, x_data, "xlsx", **self.kw).convert("xlsy")
+    y_body_data = ZipFile(StringIO(y_data)).open("body.txt").read()
+    self.assertTrue(y_body_data.startswith("XLSY;v2;10579;"), "%r... does not start with 'XLSY;v2;10579;'" % (y_body_data[:20],))
+
+  def testConvertDocx(self):
+    """Test conversion of docx to docy and back"""
+    y_data = Handler(self.tmp_url, open("data/test_with_image.docx").read(), "docx", **self.kw).convert("docy")
+    y_zip = ZipFile(StringIO(y_data))
+    y_body_data = y_zip.open("body.txt").read()
+    self.assertTrue(y_body_data.startswith("DOCY;v5;2795;"), "%r... does not start with 'DOCY;v5;2795;'" % (y_body_data[:20],))
+    y_zip.open("media/image1.png")
+
+    x_data = Handler(self.tmp_url, y_data, "docy", **self.kw).convert("docx")
+    # magic inspired by https://github.com/minad/mimemagic/pull/19/files
+    self.assertIn("word/", x_data[:2000])
+
+  def testConvertDocy(self):
+    """Test conversion of docy to docx and back"""
+    x_data = Handler(self.tmp_url, open("data/test_with_image.docy").read(), "docy", **self.kw).convert("docx")
+    self.assertIn("word/", x_data[:2000])
+
+    y_data = Handler(self.tmp_url, x_data, "docx", **self.kw).convert("docy")
+    y_zip = ZipFile(StringIO(y_data))
+    y_body_data = y_zip.open("body.txt").read()
+    self.assertTrue(y_body_data.startswith("DOCY;v5;7519;"), "%r... does not start with 'DOCY;v5;7519;'" % (y_body_data[:20],))
+    y_zip.open("media/image1.png")
+
+  def testgetMetadataFromImage(self):
+    """Test getMetadata not implemented form yformats"""
+    handler = Handler(self.tmp_url, "", "xlsy", **self.kw)
+    self.assertRaises(NotImplementedError, handler.getMetadata)
+
+  def testsetMetadata(self):
+    """Test setMetadata not implemented for yformats"""
+    handler = Handler(self.tmp_url, "", "xlsy", **self.kw)
+    self.assertRaises(NotImplementedError, handler.setMetadata)
+
+
+def test_suite():
+  return make_suite(TestHandler)

cloudooo/handler/x2t/tests/testX2tServer.py

+##############################################################################
+#
+# Copyright (c) 2016 Nexedi SA and Contributors. All Rights Reserved.
+#
+# WARNING: This program as such is intended to be used by professional
+# programmers who take the whole responsibility of assessing all potential
+# consequences resulting from its eventual inadequacies and bugs
+# End users who are looking for a ready-to-use solution with commercial
+# guarantees and support are strongly adviced to contract a Free Software
+# Service Company
+#
+# 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.
+#
+##############################################################################
+from os.path import join
+from cloudooo.tests.cloudoooTestCase import TestCase, make_suite
+
+
+class TestServer(TestCase):
+  """Test XmlRpc Server. Needs cloudooo server started"""
+
+  def ConversionScenarioList(self):
+    return [
+      (join('data', 'test.xlsx'), "xlsx", "xlsy", "application/zip"),
+      (join('data', 'test.xlsy'), "xlsy", "xlsx", "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"),
+      (join('data', 'test_with_image.docx'), "docx", "docy", "application/zip"),
+      # Here, the content type should be application/vnd.openxmlformats-officedocument.wordprocessingml.document
+      # but "magic" seems to not detect it correctly. However, the document can be read correctly by LibreOffice.
+      (join('data', 'test_with_image.docy'), "docy", "docx", "application/octet-stream"),
+    ]
+
+  def testConvertHtmltoPdf(self):
+    """Converts xlsx,docx to their y format and y to x"""
+    self.runConversionList(self.ConversionScenarioList())
+
+  def FaultConversionScenarioList(self):
+    return [
+      # Test to verify if server fail when a empty string is sent
+      ('', '', ''),
+      # Try convert one xlsx for a invalid format
+      (open(join('data', 'test.xlsx')).read(), 'xlsx', 'xyz'),
+    ]
+
+def test_suite():
+  return make_suite(TestServer)

cloudooo/manager.py

@@ -73,7 +73,7 @@ class Manager(object):
     self.handler_dict = self.kw.pop("handler_dict")
 
   def convertFile(self, file, source_format, destination_format, zip=False,
-                  refresh=False):
+                  refresh=False, conversion_kw={}):
     """Returns the converted file in the given format.
     Keywords arguments:
       file -- File as string in base64
@@ -92,7 +92,7 @@ class Manager(object):
                             decodestring(file),
                             source_format,
                             **self.kw)
-    decode_data = handler.convert(destination_format)
+    decode_data = handler.convert(destination_format, **conversion_kw)
     return encodestring(decode_data)
 
   def updateFileMetadata(self, file, source_format, metadata_dict):

cloudooo/mime.types

@@ -56,6 +56,7 @@ application/vnd.oasis.opendocument.database
 application/vnd.oasis.opendocument.image                                        odi
 application/vnd.ms-word.document.macroEnabled.12                                docm
 application/vnd.openxmlformats-officedocument.wordprocessingml.document         docx
+application/x-asc-text                                                          docy
 application/vnd.openxmlformats-officedocument.wordprocessingml.template         dotx
 application/vnd.ms-powerpoint.template.macroEnabled.12                          potm
 application/vnd.openxmlformats-officedocument.presentationml.template           potx
@@ -64,10 +65,12 @@ application/vnd.ms-powerpoint.slideshow.macroEnabled.12
 application/vnd.openxmlformats-officedocument.presentationml.slideshow          ppsx
 application/vnd.ms-powerpoint.presentation.macroEnabled.12                      pptm
 application/vnd.openxmlformats-officedocument.presentationml.presentation       pptx
+application/x-asc-presentation                                                  ppty
 application/vnd.ms-excel.addin.macroEnabled.12                                  xlam
 application/vnd.ms-excel.sheet.binary.macroEnabled.12                           xlsb
 application/vnd.ms-excel.sheet.macroEnabled.12                                  xlsm
 application/vnd.openxmlformats-officedocument.spreadsheetml.sheet               xlsx
+application/x-asc-spreadsheet                                                   xlsy
 application/vnd.ms-excel.template.macroEnabled.12                               xltm
 application/vnd.openxmlformats-officedocument.spreadsheetml.template            xltx
 application/x-msmetafile                                                        wmf

cloudooo/util.py

@@ -29,6 +29,8 @@
 import logging
 import mimetypes
 import pkg_resources
+import os
+from zipfile import ZipFile, ZIP_DEFLATED
 
 logger = logging.getLogger('Cloudooo')
 
@@ -98,3 +100,36 @@ def convertStringToBool(string):
     return False
   else:
     return None
+
+def zipTree(destination, *tree_path_list):
+  """
+    destination may be a path or a StringIO
+
+    tree_path_list is a list that may contain a path or a couple(path, archive_root)
+  """
+  def archive(arg, archive_root):
+    archive_name = os.path.join(archive_root, os.path.basename(arg))
+    if os.path.islink(arg):
+      pass  # XXX logger.warn("zipTree: symlink %r ignored\n" % arg)
+    elif os.path.isdir(arg):
+      for r, _, ff in os.walk(arg):
+        zfile.write(r, archive_name)
+        for f in ff:
+          archive(os.path.join(r, f), archive_name)
+    elif os.path.isfile(arg):
+      zfile.write(arg, archive_name)
+    else:
+      pass  # XXX logger.warn("zipTree: unknown %r ignored\n" % arg)
+  zfile = ZipFile(destination, "w", ZIP_DEFLATED)
+  for tree_path in tree_path_list:
+    if isinstance(tree_path, tuple):
+      archive(*tree_path)
+    else:
+      archive(tree_path, os.path.dirname(tree_path))
+  zfile.close()
+  return destination
+
+def unzip(source, destination):
+  zipfile = ZipFile(source)
+  zipfile.extractall(destination)
+  zipfile.close()

setup.py

@@ -6,7 +6,7 @@ version = '1.2.5-dev'
 def read(name):
     return open(name).read()
 
-long_description = (read('README.txt') + '\n' + read('CHANGES.txt'))
+long_description = (read('README.rst') + '\n' + read('CHANGELOG.rst'))
 
 install_requires = [
           # -*- Extra requirements: -*-