add pdf media type

The new media type supports pdf and a subset of media recognized by libreoffice via
unoconv.

Every document added goes through:
* conversion to pdf with unoconv if not already a pdf
* creation of thumbnail and medium sized image, and pdfinfo generates
 some information (even for unoconv produces docs - should fix this)

Poppler (pdftocairo, pdfinfo) is used.  http://poppler.freedesktop.org/

A working but uglified pdf.js integration exists, which is enabled by
setting pdf.pdf_js=true mediagoblin_local.ini (disabled in mediagoblin.ini)

Adds one test to the test_submission test suite, and another separate test_pdf suite.
The tests are only run if media_types.pdf.processing.check_prerequisites passes, so
the test suite will not require any extra package.

TODO: make test suite say 'skipped' in that case instead of just 'ok'

Signed-off-by: Alon Levy <alon@pobox.com>

mediagoblin/tests/test_mgoblin_app.ini

@@ -16,6 +16,8 @@ allow_attachments = True
 # mediagoblin.init.celery.from_celery
 celery_setup_elsewhere = true
 
+media_types = mediagoblin.media_types.image, mediagoblin.media_types.pdf
+
 [storage:publicstore]
 base_dir = %(here)s/test_user_dev/media/public
 base_url = /mgoblin_media/

mediagoblin/tests/test_pdf.py

@@ -0,0 +1,45 @@
+# GNU MediaGoblin -- federated, autonomous media hosting
+# Copyright (C) 2013 MediaGoblin contributors.  See AUTHORS.
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 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 Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+import tempfile
+import shutil
+import os
+
+from mediagoblin.tests.tools import fixture_add_collection, fixture_add_user, \
+    get_app
+from mediagoblin.db.models import Collection, User
+from mediagoblin.db.base import Session
+from nose.tools import assert_equal
+
+from mediagoblin.media_types.pdf.processing import (
+    pdf_info, check_prerequisites, create_pdf_thumb)
+
+GOOD='mediagoblin/tests/test_submission/good.pdf'
+
+def test_pdf():
+    if not check_prerequisites():
+        return
+    good_dict = {'pdf_version_major': 1, 'pdf_title': '',
+        'pdf_page_size_width': 612, 'pdf_author': '',
+        'pdf_keywords': '', 'pdf_pages': 10,
+        'pdf_producer': 'dvips + GNU Ghostscript 7.05',
+        'pdf_version_minor': 3,
+        'pdf_creator': 'LaTeX with hyperref package',
+        'pdf_page_size_height': 792}
+    assert pdf_info(GOOD) == good_dict
+    temp_dir = tempfile.mkdtemp()
+    create_pdf_thumb(GOOD, os.path.join(temp_dir, 'good_256_256.png'), 256, 256)
+    shutil.rmtree(temp_dir)

mediagoblin/tests/test_submission.py

@@ -28,6 +28,7 @@ from mediagoblin import mg_globals
 from mediagoblin.db.models import MediaEntry
 from mediagoblin.tools import template
 from mediagoblin.media_types.image import MEDIA_MANAGER as img_MEDIA_MANAGER
+from mediagoblin.media_types.pdf.processing import check_prerequisites as pdf_check_prerequisites
 
 def resource(filename):
     return resource_filename('mediagoblin.tests', 'test_submission/' + filename)
@@ -39,6 +40,8 @@ EVIL_FILE = resource('evil')
 EVIL_JPG = resource('evil.jpg')
 EVIL_PNG = resource('evil.png')
 BIG_BLUE = resource('bigblue.png')
+GOOD_PDF = resource('good.pdf')
+
 from .test_exif import GPS_JPG
 
 GOOD_TAG_STRING = u'yin,yang'
@@ -125,6 +128,16 @@ class TestSubmission:
         self._setup(test_app)
         self.check_normal_upload(u'Normal upload 2', GOOD_PNG)
 
+    def test_normal_pdf(self, test_app):
+        if not pdf_check_prerequisites():
+            return
+        self._setup(test_app)
+        response, context = self.do_post({'title': u'Normal upload 3 (pdf)'},
+                                         do_follow=True,
+                                         **self.upload_data(GOOD_PDF))
+        self.check_url(response, '/u/{0}/'.format(self.test_user.username))
+        assert 'mediagoblin/user_pages/user.html' in context
+
     def check_media(self, request, find_data, count=None):
         media = MediaEntry.find(find_data)
         if count is not None: