Merge branch 'nexedi'

README.rst

 Install Cloudooo
 ================
 
+::
+  
   $ python2.6 setup.py install
 
-  Warnings:
+
+Warnings:
  - you must have installed setuptools>=0.6c11 in this python.
 
 Install LibreOffice / OpenOffice.org
 ====================================
 
-  Install LibreOffice or OpenOffice.org.
+Install LibreOffice or OpenOffice.org.
   - http://www.libreoffice.org/download/
   - http://download.openoffice.org/
 
 Create Configuration File
 =========================
 
-  The configuration file is used to start the application using paster.
+The configuration file is used to start the application using paster.
+
+::
+  
   $ cp ./cloudooo/sample/sample.conf . # Copy to current folder
 
-  The next step is define some attributes in cloudooo.conf:
+The next step is define some attributes in cloudooo.conf:
     - working_path - folder to run the application. This folder need be created.
     - uno_path - folder where UNO library is installed (ex. /opt/libreoffice/basis-link/program/)
     - soffice_binary_path - folder where soffice.bin is installed (ex. /opt/libreoffice/program/)
@@ -27,9 +33,14 @@ Create Configuration File
 Run Application
 ===============
 
+::
+  
   $ paster serve ./cloudooo.conf
 
-  or run as a daemon:
+
+or run as a daemon:
+
+::
   
   $ paster serve ./cloudoo.conf --daemon
 
@@ -37,48 +48,61 @@ Run Application
 Stop Application
 ================
 
+::
+  
   $ kill -1 PASTER_PID
 
-  Warning: always use SIGHUP because only with this signal all processes are
-  stopped correctly.
+Warning: always use SIGHUP because only with this signal all processes are stopped correctly.
 
 Cloudooo Description
 ====================
 
 - XMLRPC + WSGI will be one bridge for easy access to LibreOffice / OpenOffice.org. This will implement one XMLRPC server into WSGI (Paster).
-
 - PyUno is used to connect to LibreOffice / OpenOffice.org stated with open socket. The features will be handled all by pyuno.
-
 - Only a process will have access to LibreOffice / OpenOffice.org by time.
-
 - All clients receive the same object(proxy) when connects with XMLRPC Server.
 
+
 Managing LibreOffice / OpenOffice.org process
 
- - start 'soffice.bin';
-   - Pyuno start 'soffice.bin' processes and the communication is through sockets;
+
+- start 'soffice.bin':
+  
+  - Pyuno start 'soffice.bin' processes and the communication is through sockets
+  
   - 'soffice.bin' processes run in brackground;
- - control 'soffice.bin';
-   - If the socket lose the connection, cloudooo kills the process, restartes processes and submit again the file;
+
+- control 'soffice.bin':
+     
+  - If the socket lose the connection, cloudooo kills the process, restarts processes and submit again the file;
+
 
 XMLRPC Server - XMLRPC + WSGI
 -----------------------------
 
-  - Send document to 'soffice.bin' and return the document converted with metadata;
+- Send document to 'soffice.bin' and return the document converted with metadata
   - XMLRPC receives a file and connects to 'soffice.bin' process by pyuno;
   - The pyuno opens a new document, write, add metadata and returns the document edited or converted to xmlrpc and it return the document to the user;
   - When finalize the use of 'soffice.bin', should make sure that it was finalized;
-  - Export to another format;
-  - Invite document and return metadata only;
-  - Edit metadata of the document;
-  - Problems and possible solution
+- Export to another format;
+- Invite document and return metadata only;
+- Edit metadata of the document;
+- Problems and possible solutions
+  
   - 'soffice.bin' is stalled;
-       - finalize the process, start 'soffice.bin' and submit the document again(without restart the cloudooo);
+  
+    - finalize the process, start 'soffice.bin' and submit the document again (without restart the cloudooo);
+  
   - 'soffice.bin' is crashed;
+    
     - finalize the process, verify if all the process was killed, start 'soffice.bin' and submit the document again(without restart the cloudooo)
+    
   - 'soffice.bin' received the document and stalled;
+    
     - if 'soffice.bin' isn't responding, kill the process and start
-     - The document that was sent is corrupt;
+     
+  - The document that was sent is corrupted;
+    
     - write in log the error and verify that the process aren't in memory
 
 

cloudooo/handler/ffmpeg/handler.py

@@ -123,3 +123,16 @@ class Handler(object):
       return self.input.getContent()
     finally:
       self.input.trash()
+
+  @staticmethod
+  def getAllowedConversionFormatList(source_mimetype):
+    """Returns a list content_type and their titles which are supported
+    by enabled handlers.
+
+    [('audio/ogg;codecs=opus', 'Opus Audio File Format'),
+     ('video/webm', 'Webm Video File Format'),
+     ...
+    ]
+    """
+    # XXX NotImplemented
+    return []

cloudooo/handler/imagemagick/handler.py

@@ -91,3 +91,16 @@ class Handler(object):
     metadata -- expected an dictionary with metadata.
     """
     raise NotImplementedError
+
+  @staticmethod
+  def getAllowedConversionFormatList(source_mimetype):
+    """Returns a list content_type and their titles which are supported
+    by enabled handlers.
+
+    [('image/jpeg', 'Jpeg Image File Format'),
+     ('image/png', 'Png Image File Format'),
+     ...
+    ]
+    """
+    # XXX NotImplemented
+    return []

cloudooo/handler/ooo/handler.py

@@ -29,6 +29,7 @@
 import json
 import re
 import pkg_resources
+import mimetypes
 from base64 import decodestring, encodestring
 from os import environ, path
 from subprocess import Popen, PIPE
@@ -39,7 +40,7 @@ from cloudooo.handler.ooo.mimemapper import mimemapper
 from cloudooo.handler.ooo.document import FileSystemDocument
 from cloudooo.handler.ooo.monitor.timeout import MonitorTimeout
 from cloudooo.handler.ooo.monitor import monitor_sleeping_time
-from cloudooo.util import logger
+from cloudooo.util import logger, parseContentType
 from psutil import pid_exists
 
 try:
@@ -238,6 +239,37 @@ class Handler(object):
     self.document.trash()
     return doc_loaded
 
+  @staticmethod
+  def getAllowedConversionFormatList(source_mimetype):
+    """Returns a list content_type and their titles which are supported
+    by enabled handlers.
+
+    [('application/vnd.oasis.opendocument.text', 'ODF Text Document'),
+     ('application/pdf', 'PDF - Portable Document Format'),
+     ...
+    ]
+    """
+    # XXX please never guess extension from mimetype
+    output_set = set()
+    if "/" in source_mimetype:
+      parsed_mimetype_type = parseContentType(source_mimetype).gettype()
+      # here `guess_all_extensions` never handles mimetype parameters
+      #   (even for `text/plain;charset=UTF-8` which is standard)
+      extension_list = mimetypes.guess_all_extensions(parsed_mimetype_type)  # XXX never guess
+    else:
+      extension_list = [source_mimetype]
+
+    for ext in extension_list:
+      for ext, title in mimemapper.getAllowedExtensionList(extension=ext.replace(".", "")):
+        if ext in ("fodt", ".fodt"):  # BBB
+          output_set.add(("application/vnd.oasis.opendocument.text-flat-xml", title))
+          continue
+        if ext:
+          mimetype, _ = mimetypes.guess_type("a." + ext)  # XXX never guess
+          if mimetype:
+            output_set.add((mimetype, title))
+    return list(output_set)
+
 def bootstrapHandler(configuration_dict):
   # Bootstrap handler
   from signal import signal, SIGINT, SIGQUIT, SIGHUP

cloudooo/handler/ooo/tests/testOooMimemapper.py

@@ -74,8 +74,10 @@ drawing_expected_tuple = (
 
 web_expected_tuple = (
     ('html', 'HTML Document'),
+    ('jpg', 'JPEG - Joint Photographic Experts Group'),
     ('odt', 'Text (Writer/Web)'),
     ('pdf', 'PDF - Portable Document Format'),
+    ('png', 'PNG - Portable Network Graphic'),
     ('sxw', 'OpenOffice.org 1.0 Text Document (Writer/Web)'),
     ('txt', 'Text (Writer/Web)'),
     ('txt', 'Text - Choose Encoding (Writer/Web)'),

cloudooo/handler/ooo/tests/testOooServer.py

@@ -66,20 +66,18 @@ class TestServer(TestCase):
     """Verify if getAllowedExtensionList returns is a list with extension and
     ui_name. The request is by extension"""
     doc_allowed_list = self.proxy.getAllowedExtensionList({'extension': "doc"})
-    doc_allowed_list.sort()
-    for arg in doc_allowed_list:
-      self.assertTrue(tuple(arg) in text_expected_tuple,
-                    "%s not in %s" % (arg, text_expected_tuple))
+    # Verify all expected types ("doc" MAY NOT be present)
+    self.assertEquals(sorted([(a, b) for a, b in doc_allowed_list if a != "doc"]),
+                      sorted(list(filter(lambda (a, b): a != "doc", text_expected_tuple))))
 
   def testGetAllowedExtensionListByMimetype(self):
     """Verify if getAllowedExtensionList returns is a list with extension and
     ui_name. The request is by mimetype"""
     request_dict = {"mimetype": "application/msword"}
     msword_allowed_list = self.proxy.getAllowedExtensionList(request_dict)
-    msword_allowed_list.sort()
-    for arg in msword_allowed_list:
-      self.assertTrue(tuple(arg) in text_expected_tuple,
-                    "%s not in %s" % (arg, text_expected_tuple))
+    # Verify all expected types ("doc" MAY NOT be present)
+    self.assertEquals(sorted([(a, b) for a, b in msword_allowed_list if a != "doc"]),
+                      sorted(list(filter(lambda (a, b): a != "doc", text_expected_tuple))))
 
   def ConversionScenarioList(self):
     return [
@@ -381,14 +379,9 @@ class TestServer(TestCase):
     response_code, response_dict, response_message = \
                   self.proxy.getAllowedTargetItemList(mimetype)
     self.assertEquals(response_code, 200)
-    # Verify if all expected types are in response list
-    for arg in text_expected_tuple:
-      self.assertTrue(list(arg) in response_dict['response_data'],
-                    "%s not in %s" % (arg, response_dict['response_data']))
-    # Verify if all types in response list are expected
-    for arg in response_dict['response_data']:
-      self.assertTrue(tuple(arg) in text_expected_tuple,
-                    "%s not in %s" % (arg, text_expected_tuple))
+    # Verify all expected types ("odt" MAY NOT be present)
+    self.assertEquals(sorted([(a, b) for a, b in response_dict['response_data'] if a != "odt"]),
+                      sorted(list(filter(lambda (a, b): a != "odt", text_expected_tuple))))
 
   def testGetTableItemListFromOdt(self):
     """Test if getTableItemList can get the table item list from odt file"""
@@ -481,10 +474,10 @@ class TestServer(TestCase):
     data = encodestring(open("./data/granulate_test.odt").read())
     image_list = self.proxy.getImageItemList(data, "odt")
     self.assertEquals([['10000000000000C80000009CBF079A6E41EE290C.jpg', ''],
-                       ['10000201000000C80000004EF26C99A54A61B987.png', 'TioLive Logo'],
-                       ['10000201000000C80000004EF26C99A54A61B987.png', ''],
+                       ['10000201000000C80000004E85B3F70C71E07CE8.png', 'TioLive Logo'],
+                       ['10000201000000C80000004E85B3F70C71E07CE8.png', ''],
                        ['2000004F0000423300001370ADF6545B2997B448.svm', 'Python Logo'],
-                       ['10000201000000C80000004EF26C99A54A61B987.png', 'Again TioLive Logo']],
+                       ['10000201000000C80000004E85B3F70C71E07CE8.png', 'Again TioLive Logo']],
                       image_list)
 
   def testGetImageItemListFromDoc(self):
@@ -492,10 +485,10 @@ class TestServer(TestCase):
     data = encodestring(open("./data/granulate_test.doc").read())
     image_list = self.proxy.getImageItemList(data, "doc")
     self.assertEquals([['10000000000000C80000009CBF079A6E41EE290C.jpg', ''],
-                       ['10000201000000C80000004EF26C99A54A61B987.png', 'TioLive Logo'],
-                       ['10000201000000C80000004EF26C99A54A61B987.png', ''],
+                       ['10000201000000C80000004E85B3F70C71E07CE8.png', 'TioLive Logo'],
+                       ['10000201000000C80000004E85B3F70C71E07CE8.png', ''],
                        ['2000031600004233000013702113A0E70B910778.wmf', 'Python Logo'],
-                       ['10000201000000C80000004EF26C99A54A61B987.png', 'Again TioLive Logo']],
+                       ['10000201000000C80000004E85B3F70C71E07CE8.png', 'Again TioLive Logo']],
                       image_list)
 
   def testGetImageFromOdt(self):

cloudooo/handler/pdf/handler.py

@@ -29,7 +29,7 @@
 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, parseContentType
 from subprocess import Popen, PIPE
 from tempfile import mktemp
 
@@ -115,3 +115,17 @@ class Handler(object):
       return self.document.getContent()
     finally:
       self.document.trash()
+
+  @staticmethod
+  def getAllowedConversionFormatList(source_mimetype):
+    """Returns a list content_type and their titles which are supported
+    by enabled handlers.
+
+    [('text/plain', 'Plain Text'),
+     ...
+    ]
+    """
+    source_mimetype = parseContentType(source_mimetype).gettype()
+    if source_mimetype in ("application/pdf", "pdf"):
+      return [("text/plain", "Plain Text")]
+    return []

cloudooo/handler/pdf/tests/testPdfHandler.py

@@ -64,6 +64,19 @@ class TestHandler(HandlerTestCase):
     self.assertEquals(metadata["title"], 'Set Metadata Test')
     self.assertEquals(metadata['creator'], 'gabriel\'@')
 
+  def testGetAllowedConversionFormatList(self):
+    """Test all combination of mimetype
+
+    None of the types below define any mimetype parameter to not ignore so far.
+    """
+    get = Handler.getAllowedConversionFormatList
+    # Handled mimetypes
+    self.assertEquals(get("application/pdf;ignored=param"),
+      [("text/plain", "Plain Text")])
+
+    # Unhandled mimetypes
+    self.assertEquals(get("text/plain;ignored=param"), [])
+    self.assertEquals(get("text/plain;charset=UTF-8;ignored=param"), [])
 
 def test_suite():
   return make_suite(TestHandler)

cloudooo/handler/wkhtmltopdf/handler.py

@@ -28,9 +28,9 @@
 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, parseContentType
 from subprocess import Popen, PIPE
-from tempfile import mktemp
+from tempfile import mktemp, mkdtemp
 from os.path import basename
 from base64 import b64decode
 
@@ -55,6 +55,9 @@ class Handler(object):
     )
     return path
 
+  def makeTempDir(self, *args, **kw):
+    return mkdtemp(*args, dir=self.file.directory_name, **kw)
+
   def convertPathToUrl(self, path):
     if path.startswith("/"):
       return "file://" + path
@@ -96,6 +99,20 @@ class Handler(object):
     """
     raise NotImplementedError
 
+  @staticmethod
+  def getAllowedConversionFormatList(source_mimetype):
+    """Returns a list content_type and their titles which are supported
+    by enabled handlers.
+
+    [('application/pdf', 'PDF - Portable Document Format'),
+     ...
+    ]
+    """
+    source_mimetype = parseContentType(source_mimetype).gettype()
+    if source_mimetype in ("text/html", "htm", "html"):
+      return [("application/pdf", "PDF - Portable Document Format")]
+    return []
+
   def makeSwitchOptionList(self, allowed_option_list, option_dict):
     """
       A switch option is enable if it exists.
@@ -342,6 +359,8 @@ class Handler(object):
       "include_in_outline",
     ], conversion_kw)
     command += self.makeSwitchOptionList(["default_header"], conversion_kw)
+    # put cache in the temp dir - to disable cache
+    command += ["--cache-dir", self.makeTempDir(prefix="cache")]
     command += self.makeOneStringArgumentOptionList([
       #"cache_dir",  # we decide
       "encoding",

cloudooo/handler/wkhtmltopdf/tests/testWkhtmltopdfHandler.py

@@ -77,6 +77,18 @@ class TestHandler(HandlerTestCase):
     handler = Handler(self.tmp_url, "", "png", **self.kw)
     self.assertRaises(NotImplementedError, handler.setMetadata)
 
+  def testGetAllowedConversionFormatList(self):
+    """Test all combination of mimetype
+
+    None of the types below define any mimetype parameter to not ignore so far.
+    """
+    get = Handler.getAllowedConversionFormatList
+    # Handled mimetypes
+    self.assertEquals(get("text/html;ignored=param"),
+      [("application/pdf", "PDF - Portable Document Format")])
+
+    # Unhandled mimetypes
+    self.assertEquals(get("application/pdf;ignored=param"), [])
 
 def test_suite():
   return make_suite(TestHandler)

cloudooo/handler/x2t/handler.py

@@ -35,7 +35,8 @@ from zope.interface import implements
 
 from cloudooo.interfaces.handler import IHandler
 from cloudooo.file import File
-from cloudooo.util import logger, zipTree, unzip
+from cloudooo.util import logger, zipTree, unzip, parseContentType
+from cloudooo.handler.ooo.handler import Handler as OOoHandler
 
 AVS_OFFICESTUDIO_FILE_UNKNOWN = "0"
 AVS_OFFICESTUDIO_FILE_DOCUMENT_DOCX = "65"
@@ -93,6 +94,9 @@ class Handler(object):
       The source format of the inputed file
     """
     self.base_folder_url = base_folder_url
+    self._data = data
+    self._source_format = source_format
+    self._init_kw = kw
     self.file = File(base_folder_url, data, source_format)
     self.environment = kw.get("env", {})
 
@@ -113,6 +117,7 @@ class Handler(object):
     config_file_name = os.path.join(root_dir, "config.xml")
 
     if source_format in yformat_tuple:
+      if self._data.startswith("PK\x03\x04"):
         os.mkdir(input_dir)
         unzip(self.file.getUrl(), input_dir)
         for _, _, files in os.walk(input_dir):
@@ -169,14 +174,61 @@ class Handler(object):
       self.file.trash()
 
   def getMetadata(self, base_document=False):
-    """Returns a dictionary with all metadata of document.
-    along with the metadata.
+    r"""Returns a dictionary with all metadata of document.
+    /!\ Not Implemented: no format are handled correctly.
     """
-    raise NotImplementedError
+    # XXX Cloudooo takes the first handler that can "handle" source_mimetype.
+    #     However, docx documents metadata can only be "handled" by the ooo handler.
+    #     Handlers should provide a way to tell if such capability is available for the required source mimetype.
+    #     We have to define a precise direction on how to know/get what are handlers capabilities according to Cloudooo configuration.
+    #     And then, this method MUST raise on unhandled format. Here xformats are "handled" by cheating.
+    if self._source_format in (
+          "docx", "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+          "xlsx", "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
+          "pptx", "application/vnd.openxmlformats-officedocument.presentationml.presentation",
+        ):
+      return OOoHandler(self.base_folder_url, self._data, self._source_format, **self._init_kw).getMetadata(base_document)
+    return {}
 
   def setMetadata(self, metadata={}):
-    """Returns image with new metadata.
+    r"""Returns document with new metadata.
+    /!\ Not Implemented: no format are handled correctly.
     Keyword arguments:
     metadata -- expected an dictionary with metadata.
     """
-    raise NotImplementedError
+    # XXX Cloudooo takes the first handler that can "handle" source_mimetype.
+    #     However, docx documents metadata can only be "handled" by the ooo handler.
+    #     Handlers should provide a way to tell if such capability is available for the required source mimetype.
+    #     We have to define a precise direction on how to know/get what are handlers capabilities according to Cloudooo configuration.
+    #     And then, this method MUST raise on unhandled format. Here xformats are "handled" by cheating.
+    if self._source_format in (
+          "docx", "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+          "xlsx", "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
+          "pptx", "application/vnd.openxmlformats-officedocument.presentationml.presentation",
+        ):
+      return OOoHandler(self.base_folder_url, self._data, self._source_format, **self._init_kw).setMetadata(metadata)
+    return self.file.getContent()
+
+  @staticmethod
+  def getAllowedConversionFormatList(source_mimetype):
+    """Returns a list content_type and their titles which are supported
+    by enabled handlers.
+
+    [('application/x-asc-text', 'OnlyOffice Text Document'),
+     ...
+    ]
+    """
+    source_mimetype = parseContentType(source_mimetype).gettype()
+    if source_mimetype in ("docx", "application/vnd.openxmlformats-officedocument.wordprocessingml.document"):
+      return [("application/x-asc-text", "OnlyOffice Text Document")]
+    if source_mimetype in ("docy", "application/x-asc-text"):
+      return [("application/vnd.openxmlformats-officedocument.wordprocessingml.document", "Word 2007 Document")]
+    if source_mimetype in ("xlsx", "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"):
+      return [("application/x-asc-spreadsheet", "OnlyOffice Spreadsheet")]
+    if source_mimetype in ("xlsy", "application/x-asc-spreadsheet"):
+      return [("application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", "Excel 2007 Spreadsheet")]
+    if source_mimetype in ("pptx", "application/vnd.openxmlformats-officedocument.presentationml.presentation"):
+      return [("application/x-asc-presentation", "OnlyOffice Presentation")]
+    if source_mimetype in ("ppty", "application/x-asc-presentation"):
+      return [("application/vnd.openxmlformats-officedocument.presentationml.presentation", "PowerPoint 2007 Presentation")]
+    return []

cloudooo/handler/x2t/tests/data/test_body.xlsy

+XLSY;v2;5883;BAKAAgAAA+cHAAAEAwgAAAD3FgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAGMFAAAAEQAAAAEMAAAABwEAAAAACAEAAAAABAoAAAAFAAAAAAUAAAAABnwAAAAHGgAAAAQGCgAAAEEAcgBpAGEAbAAGBQAAAAAAACRABxoAAAAEBgoAAABBAHIAaQBhAGwABgUAAAAAAAAkQAcaAAAABAYKAAAAQQByAGkAYQBsAAYFAAAAAAAAJEAHGgAAAAQGCgAAAEEAcgBpAGEAbAAGBQAAAAAAACRACB8AAAAJGgAAAAAGDgAAAEcARQBOAEUAUgBBAEwAAQSkAAAADhYDAAADPwAAAAABAQEBAQMBAQYEAAAAAAcEAAAAAAgEAAAAAAkEpAAAAA0GGAAAAAABBAEEAAAAAAUBAAYEAAAAAAcBAAgBAAMhAAAAAAEAAQEAAwEBBgQAAAAABwQAAAAACAQBAAAACQQAAAAAAyEAAAAAAQABAQADAQEGBAAAAAAHBAAAAAAIBAEAAAAJBAAAAAADIQAAAAABAAEBAAMBAQYEAAAAAAcEAAAAAAgEAgAAAAkEAAAAAAMhAAAAAAEAAQEAAwEBBgQAAAAABwQAAAAACAQCAAAACQQAAAAAAyEAAAAAAQABAQADAQEGBAAAAAAHBAAAAAAIBAAAAAAJBAAAAAADIQAAAAABAAEBAAMBAQYEAAAAAAcEAAAAAAgEAAAAAAkEAAAAAAMhAAAAAAEAAQEAAwEBBgQAAAAABwQAAAAACAQAAAAACQQAAAAAAyEAAAAAAQABAQADAQEGBAAAAAAHBAAAAAAIBAAAAAAJBAAAAAADIQAAAAABAAEBAAMBAQYEAAAAAAcEAAAAAAgEAAAAAAkEAAAAAAMhAAAAAAEAAQEAAwEBBgQAAAAABwQAAAAACAQAAAAACQQAAAAAAyEAAAAAAQABAQADAQEGBAAAAAAHBAAAAAAIBAAAAAAJBAAAAAADIQAAAAABAAEBAAMBAQYEAAAAAAcEAAAAAAgEAAAAAAkEAAAAAAMhAAAAAAEAAQEAAwEBBgQAAAAABwQAAAAACAQAAAAACQQAAAAAAyEAAAAAAQABAQADAQEGBAAAAAAHBAAAAAAIBAAAAAAJBAAAAAADIQAAAAABAAEBAAMBAQYEAAAAAAcEAAAAAAgEAQAAAAkEKwAAAAMhAAAAAAEAAQEAAwEBBgQAAAAABwQAAAAACAQBAAAACQQpAAAAAyEAAAAAAQABAQADAQEGBAAAAAAHBAAAAAAIBAEAAAAJBCwAAAADIQAAAAABAAEBAAMBAQYEAAAAAAcEAAAAAAgEAQAAAAkEKgAAAAMhAAAAAAEAAQEAAwEBBgQAAAAABwQAAAAACAQBAAAACQQJAAAAAkoAAAADRQAAAAABAAEBAAMBAAYEAAAAAAcEAAAAAAgEAAAAAAkEpAAAAAwEAAAAAA0GGAAAAAABBAEEAAAAAAUBAAYEAAAAAAcBAAgBAA8qAQAAECkAAAAABAAAAAAAAAABAQAAAAAEDAAAAE4AbwByAG0AYQBsAAUEAAAAAAAAABAnAAAAAAQAAAADAAAAAQEAAAAABAoAAABDAG8AbQBtAGEABQQAAAAPAAAAEC8AAAAABAAAAAYAAAABAQAAAAAEEgAAAEMAbwBtAG0AYQAgAFsAMABdAAUEAAAAEAAAABAtAAAAAAQAAAAEAAAAAQEAAAAABBAAAABDAHUAcgByAGUAbgBjAHkABQQAAAARAAAAEDUAAAAABAAAAAcAAAABAQAAAAAEGAAAAEMAdQByAHIAZQBuAGMAeQAgAFsAMABdAAUEAAAAEgAAABArAAAAAAQAAAAFAAAAAQEAAAAABA4AAABQAGUAcgBjAGUAbgB0AAUEAAAAEwAAABgAAAAAAwAAAAABAAELAAAAAgYAAAAABAAAAADwDgAAAOsOAAABGwAAAAAGDAAAAFMAaABlAGUAdAAxAAEEAQAAAAIBAgIkAAAAAx8AAAABAQACBAEEAAADBAEAAAAEBAAAAAAFBX+XU/ByCidABAoAAABBADEAOgBDADcAFhEAAAAXDAAAAAQBAAAAAQYBAAAAAQsKAAAAAQWamZmZmZkpQA48AAAAAAVxPQrXowA0QAEFhPuDDJW9OkACBXE9CtejADRAAwWE+4MMlb06QAQFcT0K16MANEAFBXE9CtejADRADwYAAAAAAQEBAQkQBgAAAAABAQEBAAlVBQAACr4AAAAABAEAAAACBZqZmZmZmSlAAwEABgEABAaiAAAABSkAAAAFCAAAAAAAAAAAAAAAAQQAAAAAAAAAAgEAAAAEAwgAAAAAAAAAAADwPwUpAAAABQgAAAAAAAAAAQAAAAEEAAAAAAAAAAIBAAAABAMIAAAAAAAAAAAAAEAFQQAAAAUIAAAAAAAAAAIAAAABBAAAAAAAAAACAQAAAAQEEwAAAAABAAwGCgAAAEEAMQArAEIAMQADCAAAAAAAAAAAAAhACr4AAAAABAIAAAACBZqZmZmZmSlAAwEABgEABAaiAAAABSkAAAAFCAAAAAEAAAAAAAAAAQQAAAAAAAAAAgEAAAAEAwgAAAAAAAAAAAAAQAUpAAAABQgAAAABAAAAAQAAAAEEAAAAAAAAAAIBAAAABAMIAAAAAAAAAAAACEAFQQAAAAUIAAAAAQAAAAIAAAABBAAAAAAAAAACAQAAAAQEEwAAAAABAAwGCgAAAEEAMgArAEIAMgADCAAAAAAAAAAAABRACr4AAAAABAMAAAACBZqZmZmZmSlAAwEABgEABAaiAAAABSkAAAAFCAAAAAIAAAAAAAAAAQQAAAAAAAAAAgEAAAAEAwgAAAAAAAAAAAAIQAUpAAAABQgAAAACAAAAAQAAAAEEAAAAAAAAAAIBAAAABAMIAAAAAAAAAAAAEEAFQQAAAAUIAAAAAgAAAAIAAAABBAAAAAAAAAACAQAAAAQEEwAAAAABAAwGCgAAAEEAMwArAEIAMwADCAAAAAAAAAAAABxACr4AAAAABAQAAAACBZqZmZmZmSlAAwEABgEABAaiAAAABSkAAAAFCAAAAAMAAAAAAAAAAQQAAAAAAAAAAgEAAAAEAwgAAAAAAAAAAAAQQAUpAAAABQgAAAADAAAAAQAAAAEEAAAAAAAAAAIBAAAABAMIAAAAAAAAAAAAFEAFQQAAAAUIAAAAAwAAAAIAAAABBAAAAAAAAAACAQAAAAQEEwAAAAABAAwGCgAAAEEANAArAEIANAADCAAAAAAAAAAAACJACr4AAAAABAUAAAACBZqZmZmZmSlAAwEABgEABAaiAAAABSkAAAAFCAAAAAQAAAAAAAAAAQQAAAAAAAAAAgEAAAAEAwgAAAAAAAAAAAAUQAUpAAAABQgAAAAEAAAAAQAAAAEEAAAAAAAAAAIBAAAABAMIAAAAAAAAAAAAGEAFQQAAAAUIAAAABAAAAAIAAAABBAAAAAAAAAACAQAAAAQEEwAAAAABAAwGCgAAAEEANQArAEIANQADCAAAAAAAAAAAACZACr4AAAAABAYAAAACBZqZmZmZmSlAAwEABgEABAaiAAAABSkAAAAFCAAAAAUAAAAAAAAAAQQAAAAAAAAAAgEAAAAEAwgAAAAAAAAAAAAYQAUpAAAABQgAAAAFAAAAAQAAAAEEAAAAAAAAAAIBAAAABAMIAAAAAAAAAAAAHEAFQQAAAAUIAAAABQAAAAIAAAABBAAAAAAAAAACAQAAAAQEEwAAAAABAAwGCgAAAEEANgArAEIANgADCAAAAAAAAAAAACpACr4AAAAABAcAAAACBZqZmZmZmSlAAwEABgEABAaiAAAABSkAAAAFCAAAAAYAAAAAAAAAAQQAAAAAAAAAAgEAAAAEAwgAAAAAAAAAAAAcQAUpAAAABQgAAAAGAAAAAQAAAAEEAAAAAAAAAAIBAAAABAMIAAAAAAAAAAAAIEAFQQAAAAUIAAAABgAAAAIAAAABBAAAAAAAAAACAQAAAAQEEwAAAAABAAwGCgAAAEEANwArAEIANwADCAAAAAAAAAAAAC5ADK0IAAANqAgAAAABAAAAAgEgAAAAAAQDAAAAAQUpXI/C9SjwPwIEAAAAAAMFAAAAAAAA8D8CIAAAAAAECgAAAAEFrkfhehSuB0ACBBQAAAADBcP1KFyPwuU/BlMIAAAKSQgAAAEPAAAAAAoAAABlAG4ALQBVAFMACOEHAAAHeQcAAAAAAAAABTEFAAAABgAAAAABAAAAAQEGAAAAAAEAAAABA5oBAAAACQAAAAAEAAAAAAAAAAEJAAAAAAQAAAAAAAAAA0oAAAAARQAAAPr7AQAAAAACFwAAAAMSAAAAAA0AAAABCAAAAPoAAAFFAob7AxgAAAD6+wAFAAAAAgAAAAACBwAAAPoAAAAAAPsEAAAAAAdCAAAAAgYAAAAAAQAAAAYKBgAAAAABAAAAAA0GAAAAAAEAAAAACAYAAAAAAQAAAAAMBgAAAAABAAAAAAsGAAAAAAEAAAAAC+MAAAAB3gAAAAAgAAAAUwBoAGUAZQB0ADEAIQAkAEEAJAAxADoAJABBACQANwABtAAAAAAOAAAARwBlAG4AZQByAGEAbAABCQAAAAAEAAAABwAAAAIQAAAAAAIAAAAxAAEEAAAAAAAAAAIQAAAAAAIAAAAyAAEEAAAAAQAAAAIQAAAAAAIAAAAzAAEEAAAAAgAAAAIQAAAAAAIAAAA0AAEEAAAAAwAAAAIQAAAAAAIAAAA1AAEEAAAABAAAAAIQAAAAAAIAAAA2AAEEAAAABQAAAAIQAAAAAAIAAAA3AAEEAAAABgAAAAOaAQAAAAkAAAAABAAAAAEAAAABCQAAAAAEAAAAAQAAAANKAAAAAEUAAAD6+wEAAAAAAhcAAAADEgAAAAANAAAAAQgAAAD6AP8BQgIO+wMYAAAA+vsABQAAAAIAAAAAAgcAAAD6AAAAAAD7BAAAAAAHQgAAAAIGAAAAAAEAAAAGCgYAAAAAAQAAAAANBgAAAAABAAAAAAgGAAAAAAEAAAAADAYAAAAAAQAAAAALBgAAAAABAAAAAAvjAAAAAd4AAAAAIAAAAFMAaABlAGUAdAAxACEAJABCACQAMQA6ACQAQgAkADcAAbQAAAAADgAAAEcAZQBuAGUAcgBhAGwAAQkAAAAABAAAAAcAAAACEAAAAAACAAAAMgABBAAAAAAAAAACEAAAAAACAAAAMwABBAAAAAEAAAACEAAAAAACAAAANAABBAAAAAIAAAACEAAAAAACAAAANQABBAAAAAMAAAACEAAAAAACAAAANgABBAAAAAQAAAACEAAAAAACAAAANwABBAAAAAUAAAACEAAAAAACAAAAOAABBAAAAAYAAAADoAEAAAAJAAAAAAQAAAACAAAAAQkAAAAABAAAAAIAAAADSgAAAABFAAAA+vsBAAAAAAIXAAAAAxIAAAAADQAAAAEIAAAA+gD/AdMCIPsDGAAAAPr7AAUAAAACAAAAAAIHAAAA+gAAAAAA+wQAAAAAB0IAAAACBgAAAAABAAAABgoGAAAAAAEAAAAADQYAAAAAAQAAAAAIBgAAAAABAAAAAAwGAAAAAAEAAAAACwYAAAAAAQAAAAAL6QAAAAHkAAAAACAAAABTAGgAZQBlAHQAMQAhACQAQwAkADEAOgAkAEMAJAA3AAG6AAAAAA4AAABHAGUAbgBlAHIAYQBsAAEJAAAAAAQAAAAHAAAAAhAAAAAAAgAAADMAAQQAAAAAAAAAAhAAAAAAAgAAADUAAQQAAAABAAAAAhAAAAAAAgAAADcAAQQAAAACAAAAAhAAAAAAAgAAADkAAQQAAAADAAAAAhIAAAAABAAAADEAMQABBAAAAAQAAAACEgAAAAAEAAAAMQAzAAEEAAAABQAAAAISAAAAAAQAAAAxADUAAQQAAAAGAAAABQsAAAAABgAAADEAMAAwAAYHAAAAAAIAAAAwAAgJAAAAAAQAAACfJdkDCAkAAAAABAAAAEdf8AUT3gAAAAAJAAAAAAQAAACfJdkDAQsAAAABBgAAAAABAAAAAQIGAAAAAAEAAAAAAwYAAAAAAQAAAAAIBgAAAAABAAAAAwkGAAAAAAEAAAACCgYAAAAAAQAAAAILRQAAAABAAAAA+vsBAAAAAAIAAAAAAyoAAAD6+wAXAAAAAxIAAAAADQAAAAEIAAAA+gCzAbMCs/sCBwAAAPoAAAAAAPsEAAAAAA0JAAAAAAQAAABHX/AFDgYAAAAAAQAAAAAQBgAAAAABAAAAAREGAAAAAAEAAAAAEgsAAAAABgAAADEAMAAwABYHAQAAAAkAAAAABAAAAEdf8AUBCwAAAAEGAAAAAAEAAAABAgYAAAAAAQAAAAADBgAAAAABAAAAAQRKAAAAAEUAAAAAQAAAAPr7AQAAAAACAAAAAAMqAAAA+vsAFwAAAAMSAAAAAA0AAAABCAAAAPoAswGzArP7AgcAAAD6AAAAAAD7BAAAAAAIBgAAAAABAAAAAwkGAAAAAAEAAAACCgYAAAAAAQAAAAILRQAAAABAAAAA+vsBAAAAAAIAAAAAAyoAAAD6+wAXAAAAAxIAAAAADQAAAAEIAAAA+gCzAbMCs/sCBwAAAPoAAAAAAPsEAAAAAA0JAAAAAAQAAACfJdkDDgYAAAAAAQAAAAAYSgAAAABFAAAA+vsBAAAAAAIFAAAAAgAAAAADKgAAAPr7ABcAAAADEgAAAAANAAAAAQgAAAD6ALMBswKz+wIHAAAA+gAAAAAA+wQAAAAACFMAAAAABgAAAAABAAAAAwMGAAAAAAEAAAAABDgAAAAAMwAAAPr7AQAAAAACBQAAAAIAAAAAAxgAAAD6+wAFAAAAAgAAAAACBwAAAPoAAAAAAPsEAAAAAAkGAAAAAAEAAAABCUoAAAAARQAAAPr7AQAAAAACFwAAAAMSAAAAAA0AAAABCAAAAPoA/wH/Av/7AxgAAAD6+wAFAAAAAgAAAAACBwAAAPoAAAAAAPsEAAAAAAsAAAAAGAYAAAACAQAAAAAAAAAA
\ No newline at end of file

cloudooo/handler/x2t/tests/testX2tHandler.py

@@ -51,6 +51,8 @@ class TestHandler(HandlerTestCase):
 
   def testConvertXlsy(self):
     """Test conversion of xlsy to xlsx and back"""
+    x_data = Handler(self.tmp_url, open("data/test_body.xlsy").read(), "xlsy", **self.kw).convert("xlsx")
+    self.assertIn("xl/", x_data[:2000])
     x_data = Handler(self.tmp_url, open("data/test.xlsy").read(), "xlsy", **self.kw).convert("xlsx")
     self.assertIn("xl/", x_data[:2000])
 
@@ -81,16 +83,38 @@ class TestHandler(HandlerTestCase):
     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"""
+  def testgetMetadata(self):
+    """Test getMetadata from yformats (not implemented)"""
     handler = Handler(self.tmp_url, "", "xlsy", **self.kw)
-    self.assertRaises(NotImplementedError, handler.getMetadata)
+    #   Of course, expected behavior should be a dict of internal metadata
+    # but don't know how to handle it so far.
+    self.assertEquals(handler.getMetadata(), {})
 
   def testsetMetadata(self):
-    """Test setMetadata not implemented for yformats"""
+    """Test setMetadata for yformats (not implemented)"""
     handler = Handler(self.tmp_url, "", "xlsy", **self.kw)
-    self.assertRaises(NotImplementedError, handler.setMetadata)
-
+    #   Of course, expected behavior should be an updated data with new
+    # internal metadata but don't know how to handle it so far.
+    self.assertEquals(handler.setMetadata(), "")
+
+  def testGetAllowedConversionFormatList(self):
+    """Test all combination of mimetype
+
+    None of the types below define any mimetype parameter to not ignore so far.
+    """
+    get = Handler.getAllowedConversionFormatList
+    self.assertEquals(get("application/x-asc-text;ignored=param"),
+      [("application/vnd.openxmlformats-officedocument.wordprocessingml.document", "Word 2007 Document")])
+    self.assertEquals(get("application/x-asc-spreadsheet;ignored=param"),
+      [("application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", "Excel 2007 Spreadsheet")])
+    self.assertEquals(get("application/x-asc-presentation;ignored=param"),
+      [("application/vnd.openxmlformats-officedocument.presentationml.presentation", "PowerPoint 2007 Presentation")])
+    self.assertEquals(get("application/vnd.openxmlformats-officedocument.wordprocessingml.document;ignored=param"),
+      [("application/x-asc-text", "OnlyOffice Text Document")])
+    self.assertEquals(get("application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;ignored=param"),
+      [("application/x-asc-spreadsheet", "OnlyOffice Spreadsheet")])
+    self.assertEquals(get("application/vnd.openxmlformats-officedocument.presentationml.presentation;ignored=param"),
+      [("application/x-asc-presentation", "OnlyOffice Presentation")])
 
 def test_suite():
   return make_suite(TestHandler)

cloudooo/interfaces/manager.py

@@ -87,7 +87,7 @@ class IManager(Interface):
     metadata_dict : Metadatas to include in content
     """
 
-  def getAllowedConversionFormatList(source_mimetype):
+  def getAllowedConversionFormatList(self, source_mimetype):
     """Returns a list content_type and their titles which are supported
     by enabled handlers.
 

cloudooo/manager.py

@@ -28,11 +28,11 @@
 ##############################################################################
 
 import mimetypes
-from mimetypes import guess_all_extensions, guess_extension
+from mimetypes import guess_type, guess_all_extensions, guess_extension
 from base64 import encodestring, decodestring
 from zope.interface import implements
 from interfaces.manager import IManager, IERP5Compatibility
-from cloudooo.util import logger
+from cloudooo.util import logger, parseContentType
 from cloudooo.interfaces.granulate import ITableGranulator
 from cloudooo.interfaces.granulate import IImageGranulator
 from cloudooo.interfaces.granulate import ITextGranulator
@@ -41,6 +41,7 @@ from fnmatch import fnmatch
 #XXX Must be removed
 from cloudooo.handler.ooo.granulator import OOGranulator
 from cloudooo.handler.ooo.mimemapper import mimemapper
+from cloudooo.handler.wkhtmltopdf.handler import Handler as WkhtmltopdfHandler
 
 class HandlerNotFound(Exception):
   pass
@@ -59,6 +60,35 @@ def getHandlerClass(source_format, destination_format, mimetype_registry,
   raise HandlerNotFound('No Handler found for %r=>%r' % (source_format,
                                                          destination_format))
 
+def BBB_guess_type(url):
+  base = url.split("/")[-1].lstrip(".")
+  # if base.endswith(".ms.docx"): return ("application/vnd.openxmlformats-officedocument.wordprocessingml.document", "Microsoft Word 2007-2013 XML")
+  split = base.split(".")
+  ext = '' if len(split) == 1 else split[-1]
+  return {
+    "docy": ("application/x-asc-text", None),
+    "xlsy": ("application/x-asc-spreadsheet", None),
+    "ppty": ("application/x-asc-presentation", None),
+  }.get(ext, None) or guess_type(url)
+
+def BBB_guess_extension(mimetype, title=None):
+  return {
+    # title : extension
+    "Flat XML ODF Text Document": ".fodt",
+    "MET - OS/2 Metafile": ".met",
+    "Microsoft Excel 2007-2013 XML": ".ms.xlsx",
+    "Microsoft PowerPoint 2007-2013 XML": ".ms.pptx",
+    "Microsoft PowerPoint 2007-2013 XML AutoPlay": ".ms.ppsx",
+    "Microsoft Word 2007-2013 XML": ".ms.docx",
+  }.get(title, None) or {
+    # mediatype : extension
+    "application/postscript": ".eps",
+    "application/vnd.ms-excel": ".xls",
+    "application/vnd.ms-excel.sheet.macroenabled.12": ".xlsm",
+    "application/vnd.ms-powerpoint": ".ppt",
+    "text/plain": ".txt",
+    "image/jpeg": ".jpg",
+  }.get(parseContentType(mimetype).gettype(), None) or guess_extension(mimetype)
 
 class Manager(object):
   """Manipulates requisitons of client and temporary files in file system."""
@@ -84,6 +114,19 @@ class Manager(object):
     """
     self.kw['zip'] = zip
     self.kw['refresh'] = refresh
+    # XXX Force the use of wkhtmltopdf handler if converting from html to pdf
+    #     with conversion parameters.
+    #     This is a hack that quickly enables the use of wkhtmltopdf without
+    #     conflicting with other "html to pdf" conversion method
+    #     (i.e. using the ooo handler) that does not use such a parameter.
+    #     This hack should be removed after defining and implementing a way to
+    #     use the conversion_kw in a possible interoperable way between all
+    #     "html to pdf" handlers.
+    if (conversion_kw and
+        source_format in ("html", "text/html") and
+        destination_format in ("pdf", "application/pdf")):
+      handler_class = WkhtmltopdfHandler
+    else:
       handler_class = getHandlerClass(source_format,
                                     destination_format,
                                     self.mimetype_registry,
@@ -143,36 +186,69 @@ class Manager(object):
     return metadata_dict
 
   def getAllowedExtensionList(self, request_dict={}):
-    """List types which can be generated from given type
+    """BBB: extension should not be used, use MIMEType with getAllowedConversionFormatList
+
+    List extension which can be generated from given type
     Type can be given as:
+      - content type
       - filename extension
-      - document type ('text', 'spreadsheet', 'presentation' or 'drawing')
-    e.g
-    self.getAllowedMimetypeList(dict(document_type="text"))
-    return extension_list
+      - document type
     """
     mimetype = request_dict.get('mimetype')
     extension = request_dict.get('extension')
     document_type = request_dict.get('document_type')
-    if mimetype:
-      allowed_extension_list = []
-      for ext in guess_all_extensions(mimetype):
-        ext = ext.replace('.', '')
-        extension_list = mimemapper.getAllowedExtensionList(extension=ext,
-                                                 document_type=document_type)
-        for extension in extension_list:
-          if extension not in allowed_extension_list:
-            allowed_extension_list.append(extension)
-      return allowed_extension_list
-    elif extension:
-      extension = extension.replace('.', '')
-      return mimemapper.getAllowedExtensionList(extension=extension,
-                                                 document_type=document_type)
+    if not mimetype:
+      if extension:
+        mimetype, _ = BBB_guess_type("a." + extension)
       elif document_type:
+        # BBB no other choice than to ask ooo.mimemapper
         return mimemapper.getAllowedExtensionList(document_type=document_type)
+    if mimetype:
+      allowed_extension_set = set()
+      for content_type, title in self.getAllowedConversionFormatList(mimetype):
+        ext = BBB_guess_extension(content_type, title)
+        if ext:
+          allowed_extension_set.add((ext.lstrip('.'), title))
+      return list(allowed_extension_set) or [('', '')]
     else:
       return [('', '')]
 
+  def getAllowedConversionFormatList(self, source_mimetype):
+    r"""Returns a list content_type and their titles which are supported
+    by enabled handlers.
+
+    [('application/vnd.oasis.opendocument.text', 'ODF Text Document'),
+     ('application/pdf', 'PDF - Portable Document Format'),
+     ...
+    ]
+
+    This methods gets handler conversion mimetype availability according
+    to Cloudooo's mimetype registry.
+
+    /!\ unlike `self.getAllowedExtensionList`, it may return empty list
+        instead of `[('', '')]`.
+
+    /!\ the returned list may have the same mimetype twice with different title.
+    """
+    handler_dict = {}  # handler_dict["ooo"] = ["text/*", "application/*"]
+    for entry in self.mimetype_registry:
+      split_entry = entry.split()
+      if fnmatch(source_mimetype, split_entry[0]):
+        if split_entry[2] in handler_dict:
+          handler_dict[split_entry[2]].append(split_entry[1])
+        else:
+          handler_dict[split_entry[2]] = [split_entry[1]]
+
+    output_mimetype_set = set()
+    for handler, mimetype_filter_list in handler_dict.items():
+      for output_mimetype in self.handler_dict[handler].getAllowedConversionFormatList(source_mimetype):
+        for mimetype_filter in mimetype_filter_list:
+          if fnmatch(output_mimetype[0], mimetype_filter):
+            output_mimetype_set.add(output_mimetype)
+            break
+
+    return list(output_mimetype_set)
+
   def run_convert(self, filename='', data=None, meta=None, extension=None,
                   orig_format=None):
     """Method to support the old API. Wrapper getFileMetadataItemList but
@@ -242,7 +318,7 @@ class Manager(object):
     """
     # calculate original extension required by convertFile from
     # given content_type (orig_format)
-    original_extension = guess_extension(orig_format).strip('.')
+    original_extension = BBB_guess_extension(orig_format).strip('.')
     # XXX - ugly way to remove "/" and "."
     orig_format = orig_format.split('.')[-1]
     orig_format = orig_format.split('/')[-1]
@@ -282,7 +358,12 @@ class Manager(object):
     """
     response_dict = {}
     try:
-      extension_list = self.getAllowedExtensionList({"mimetype": content_type})
+      mimetype_list = self.getAllowedConversionFormatList(content_type)
+      extension_list = []
+      for m, t in mimetype_list:
+        ext = BBB_guess_extension(m, t)
+        if ext:
+          extension_list.append((ext.lstrip('.'), t))
       response_dict['response_data'] = extension_list
       return (200, response_dict, '')
     except Exception, e:

cloudooo/util.py

@@ -30,6 +30,8 @@ import logging
 import mimetypes
 import pkg_resources
 import os
+import mimetools
+import cStringIO
 from zipfile import ZipFile, ZIP_DEFLATED
 
 logger = logging.getLogger('Cloudooo')
@@ -133,3 +135,18 @@ def unzip(source, destination):
   zipfile = ZipFile(source)
   zipfile.extractall(destination)
   zipfile.close()
+
+def parseContentType(content_type):
+  """Parses `text/plain;charset="utf-8"` to a mimetools.Message object.
+
+  Note: Content type or MIME type are built like `maintype/subtype[;params]`.
+
+      parsed_content_type = parseContentType('text/plain;charset="utf-8"')
+      parsed_content_type.gettype()  -> 'text/plain'
+      parsed_content_type.getmaintype()  -> 'text'
+      parsed_content_type.getsubtype()  -> 'plain'
+      parsed_content_type.getplist()  -> 'charset="utf-8"'
+      parsed_content_type.getparam('charset')  -> 'utf-8'
+      parsed_content_type.typeheader  -> 'text/plain;charset="utf-8"'
+  """
+  return mimetools.Message(cStringIO.StringIO("Content-Type:" + content_type.replace("\r\n", "\r\n\t")))