implement getAllowedConversionFormat

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
 
 
@@ -213,6 +214,37 @@ 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 and mimetype != parsed_mimetype_type:
+            output_set.add((mimetype, title))
+    return list(output_set)
+
 def bootstrapHandler(configuration_dict):
   # Bootstrap handler
   from signal import signal, SIGINT, SIGQUIT, SIGHUP

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/wkhtmltopdf/handler.py

@@ -28,7 +28,7 @@
 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
 from os.path import basename
@@ -96,6 +96,20 @@ 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.

cloudooo/handler/x2t/handler.py

@@ -35,7 +35,7 @@ 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
 
 AVS_OFFICESTUDIO_FILE_UNKNOWN = "0"
 AVS_OFFICESTUDIO_FILE_DOCUMENT_DOCX = "65"
@@ -168,3 +168,27 @@ 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.
+
+    [('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/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

@@ -173,6 +173,42 @@ class Manager(object):
     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

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")))