diff -r f3b365199366 docs/conf.py

--- a/docs/conf.py	Thu Jul 14 14:34:23 2011 +0200

+++ b/docs/conf.py	Tue Nov 01 13:31:57 2011 +1000

@@ -13,16 +13,18 @@

 import sys, os

 # If extensions (or modules to document with autodoc) are in another directory,

 # add these directories to sys.path here. If the directory is relative to the

 # documentation root, use os.path.abspath to make it absolute, like shown here.

 sys.path.insert(0, os.path.abspath('..'))

+import polib

+

 # -- General configuration -----------------------------------------------------

 # If your documentation needs a minimal Sphinx version, state it here.

 #needs_sphinx = '1.0'

 # Add any Sphinx extension module names here, as strings. They can be extensions

 # coming with Sphinx (named 'sphinx.ext.*') or your custom ones.

 extensions = ['sphinx.ext.autodoc', 'sphinx.ext.todo', 'sphinx.ext.coverage', 'sphinx.ext.viewcode']

@@ -43,19 +45,19 @@ master_doc = 'index'

 project = u'polib'

 copyright = u'2011, David Jean Louis <izimobil@gmail.com>'

 # The version info for the project you're documenting, acts as replacement for

 # |version| and |release|, also used in various other places throughout the

 # built documents.

 #

 # The short X.Y version.

-version = '0.6.0'

+version = polib.__version__

 # The full version, including alpha/beta/rc tags.

-release = '0.6.0'

+release = polib.__version__

 # The language for content autogenerated by Sphinx. Refer to documentation

 # for a list of supported languages.

 #language = None

 # There are two options for replacing |today|: either, you set today to some

 # non-false value, then it is used:

 #today = ''

diff -r f3b365199366 polib.py

--- a/polib.py	Thu Jul 14 14:34:23 2011 +0200

+++ b/polib.py	Tue Nov 01 13:31:57 2011 +1000

@@ -1181,78 +1181,91 @@ class _POFileParser(object):

                 self.entry_obsolete = 1

             else:

                 self.entry_obsolete = 0

             # Take care of keywords like

             # msgid, msgid_plural, msgctxt & msgstr.

             if tokens[0] in keywords and nb_tokens > 1:

                 line = line[len(tokens[0]):].lstrip()

+                if re.search(r'([^\\]|^)"', line[1:-1]):

+                    raise IOError('Syntax error in po file %s (line %s): '\

+                                  'unescaped double quote found' % \

+                                  (self.instance.fpath, i))

                 self.current_token = line

                 self.process(keywords[tokens[0]], i)

                 continue

             self.current_token = line

             if tokens[0] == '#:' and nb_tokens > 1:

                 # we are on a occurrences line

                 self.process('OC', i)

             elif line[:1] == '"':

                 # we are on a continuation line

+                if re.search(r'([^\\]|^)"', line[1:-1]):

+                    raise IOError('Syntax error in po file %s (line %s): '\

+                                  'unescaped double quote found' % \

+                                  (self.instance.fpath, i))

                 self.process('MC', i)

             elif line[:7] == 'msgstr[':

                 # we are on a msgstr plural

                 self.process('MX', i)

-            elif tokens[0] == '#,' and nb_tokens > 1:

+            elif tokens[0] == '#,' and nb_tokens >= 1:

                 # we are on a flags line

                 self.process('FL', i)

             elif tokens[0] == '#':

                 if line == '#': line += ' '

                 # we are on a translator comment line

                 self.process('TC', i)

-            elif tokens[0] == '#.' and nb_tokens > 1:

+            elif tokens[0] == '#.' and nb_tokens >= 1:

                 # we are on a generated comment line

                 self.process('GC', i)

             elif tokens[0] == '#|':

                 if nb_tokens < 2:

-                    self.process('??', i)

-                    continue

+                    raise IOError('Syntax error in po file %s (line %s)' % \

+                                  (self.instance.fpath, i))

                 # Remove the marker and any whitespace right after that.

                 line = line[2:].lstrip()

                 self.current_token = line

                 if tokens[1].startswith('"'):

                     # Continuation of previous metadata.

                     self.process('MC', i)

                     continue

                 if nb_tokens == 2:

                     # Invalid continuation line.

-                    self.process('??', i)

+                    raise IOError('Syntax error in po file %s (line %s): '\

+                                  'invalid continuation line' % \

+                                  (self.instance.fpath, i))

                 # we are on a "previous translation" comment line,

                 if tokens[1] not in prev_keywords:

                     # Unknown keyword in previous translation comment.

-                    self.process('??', i)

+                    raise IOError('Syntax error in po file %s (line %s): '\

+                                  'unknown keyword %s' % \

+                                  (self.instance.fpath, i, tokens[1]))

                 # Remove the keyword and any whitespace

                 # between it and the starting quote.

                 line = line[len(tokens[1]):].lstrip()

                 self.current_token = line

                 self.process(prev_keywords[tokens[1]], i)

             else:

-                self.process('??', i)

+                raise IOError('Syntax error in po file %s (line %s)' % \

+                              (self.instance.fpath, i))

         if self.current_entry:

             # since entries are added when another entry is found, we must add

             # the last entry here (only if there are lines)

             self.instance.append(self.current_entry)

         # before returning the instance, check if there's metadata and if 

         # so extract it in a dict

         firstentry = self.instance[0]

diff -r f3b365199366 tests/test_weird_occurrences.po

--- a/tests/test_weird_occurrences.po	Thu Jul 14 14:34:23 2011 +0200

+++ b/tests/test_weird_occurrences.po	Tue Nov 01 13:31:57 2011 +1000

@@ -9,16 +9,23 @@ msgstr ""

 "MIME-Version: 1.0\n"

 "Content-Type: text/plain; charset=UTF-8\n"

 "Content-Transfer-Encoding: 8bit\n"

 "X-Generator: Pootle 1.1.0rc2\n"

 "X-Launchpad-Export-Date: 2007-12-03 23:40+0000\n"

 "X-Etoys-Domain: etoys\n"

 "X-Etoys-SystemVersion: etoys3.0 of 24 February 2008 update 2029\n"

+#. Test for empty comment lines

+#. 

+#,

+#: main.c:117

+msgid "Override the default prgname"

+msgstr "Override the default prgname"

+

 #: Balloon-Fills,BitmapFillStyle>>addFillStyleMenuItems:hand:from:

 msgid "choose new graphic"

 msgstr "escolher novo gráfico"

 #: Balloon-Fills,BitmapFillStyle>>addFillStyleMenuItems:hand:from:

 msgid "grab new graphic"

 msgstr "agarrar novo gráfico"

diff -r f3b365199366 tests/tests.py

--- a/tests/tests.py	Thu Jul 14 14:34:23 2011 +0200

+++ b/tests/tests.py	Tue Nov 01 13:31:57 2011 +1000

@@ -78,16 +78,84 @@ msgstr "bar"

     def test_pofile_and_mofile7(self):

         """

         Test that encoding is ok when encoding is explicitely given.

         """

         po = polib.pofile('tests/test_iso-8859-15.po', encoding='iso-8859-15')

         self.assertTrue(po.encoding == 'iso-8859-15')

+    def test_pofile_and_mofile8(self):

+        """

+        Test that weird occurrences are correctly parsed.

+        """

+        po = polib.pofile('tests/test_weird_occurrences.po')

+        self.assertEqual(len(po), 46)

+

+    def test_unescaped_double_quote1(self):

+        """

+        Test that polib reports an error when unescaped double quote is found.

+        """

+        data = r'''

+msgid "Some msgid with \"double\" quotes"

+msgid "Some msgstr with "double\" quotes"

+'''

+        try:

+            po = polib.pofile(data)

+            self.fail("Unescaped quote not detected")

+        except IOError, exc:

+            msg = 'Syntax error in po file None (line 3): unescaped double quote found'

+            self.assertEqual(str(exc), msg)

+

+    def test_unescaped_double_quote2(self):

+        """

+        Test that polib reports an error when unescaped double quote is found.

+        """

+        data = r'''

+msgid "Some msgid with \"double\" quotes"

+msgstr ""

+"Some msgstr with "double\" quotes"

+'''

+        try:

+            po = polib.pofile(data)

+            self.fail("Unescaped quote not detected")

+        except IOError, exc:

+            msg = 'Syntax error in po file None (line 4): unescaped double quote found'

+            self.assertEqual(str(exc), msg)

+

+    def test_unescaped_double_quote3(self):

+        """

+        Test that polib reports an error when unescaped double quote is found at the beginning of the string.

+        """

+        data = r'''

+msgid "Some msgid with \"double\" quotes"

+msgid ""Some msgstr with double\" quotes"

+'''

+        try:

+            po = polib.pofile(data)

+            self.fail("Unescaped quote not detected")

+        except IOError, exc:

+            msg = 'Syntax error in po file None (line 3): unescaped double quote found'

+

+    def test_unescaped_double_quote4(self):

+        """

+        Test that polib reports an error when unescaped double quote is found at the beginning of the string.

+        """

+        data = r'''

+msgid "Some msgid with \"double\" quotes"

+msgstr ""

+""Some msgstr with double\" quotes"

+'''

+        try:

+            po = polib.pofile(data)

+            self.fail("Unescaped quote not detected")

+        except IOError, exc:

+            msg = 'Syntax error in po file None (line 4): unescaped double quote found'

+            self.assertEqual(str(exc), msg)

+    

     def test_detect_encoding1(self):

         """

         Test that given enconding is returned when file has no encoding defined.

         """

         self.assertEqual(polib.detect_encoding('tests/test_noencoding.po'), 'utf-8')

     def test_detect_encoding2(self):

         """