Fix name parser unicode bugs

sickbeard/name_parser/parser.py

@@ -142,6 +142,12 @@ def _combine_results(self, first, second, attr):
         else:
             return b 
 
+    def _unicodify(self, obj, encoding = "utf-8"):
+        if isinstance(obj, basestring):
+            if not isinstance(obj, unicode):
+                obj = unicode(obj, encoding)
+        return obj
+
     def _convert_number(self, number):
         if type(number) == int:
             return number
@@ -167,6 +173,8 @@ def _convert_number(self, number):
 
     def parse(self, name):
 
+        name = self._unicodify(name)
+
         # break it into parts if there are any (dirname, file name, extension)
         dir_name, file_name = os.path.split(name)
         ext_match = re.match('(.*)\.\w{3,4}$', file_name)
@@ -225,6 +233,7 @@ def __init__(self,
                  release_group=None,
                  air_date=None
                  ):
+
         self.original_name = original_name
 
         self.series_name = series_name
@@ -276,7 +285,7 @@ def __str__(self):
         if self.release_group:
             to_return += ' (' + self.release_group + ')'
 
-        return to_return 
+        return to_return.encode('utf-8')
 
     def _is_air_by_date(self):
         if self.season_number == None and len(self.episode_numbers) == 0 and self.air_date:

sickbeard/postProcessor.py

@@ -313,7 +313,7 @@ def _analyze_name(self, name, file=True):
         # parse the name to break it into show name, season, and episode
         np = NameParser(file)
         parse_result = np.parse(name)
-        self._log("Parsed "+name+" into "+str(parse_result), logger.DEBUG)
+        self._log("Parsed "+name+" into "+str(parse_result).decode('utf-8'), logger.DEBUG)
 
         if parse_result.air_by_date:
             season = -1

tests/name_parser_tests.py

@@ -99,6 +99,27 @@
 
                           ]
 
+unicode_test_cases = [
+                      (u'The.Big.Bang.Theory.2x07.The.Panty.Pi\xf1ata.Polarization.720p.HDTV.x264.AC3-SHELDON.mkv',
+                       parser.ParseResult(None, 'The.Big.Bang.Theory', 2, [7], '720p.HDTV.x264.AC3', 'SHELDON')
+                       ),
+                      ('The.Big.Bang.Theory.2x07.The.Panty.Pi\xc3\xb1ata.Polarization.720p.HDTV.x264.AC3-SHELDON.mkv',
+                       parser.ParseResult(None, 'The.Big.Bang.Theory', 2, [7], '720p.HDTV.x264.AC3', 'SHELDON')
+                       ),
+                      ]
+
+class UnicodeTests(unittest.TestCase):
+
+    def _test_unicode(self, name, result):
+        print repr(name)
+        np = parser.NameParser(True)
+        parse_result = np.parse(name)
+        print repr(str(parse_result))
+
+    def test_unicode(self):
+        for (name, result) in unicode_test_cases:
+            self._test_unicode(name, result)
+
 class ComboTests(unittest.TestCase):
 
     def _test_combo(self, name, result, which_regexes):
@@ -232,7 +253,10 @@ def test_combination_names(self):
         suite = unittest.TestLoader().loadTestsFromName('name_parser_tests.BasicTests.test_'+sys.argv[1])
     else:
         suite = unittest.TestLoader().loadTestsFromTestCase(BasicTests)
-    unittest.TextTestRunner(verbosity=2).run(suite)
+    #unittest.TextTestRunner(verbosity=2).run(suite)
 
     suite = unittest.TestLoader().loadTestsFromTestCase(ComboTests)
+    #unittest.TextTestRunner(verbosity=2).run(suite)
+
+    suite = unittest.TestLoader().loadTestsFromTestCase(UnicodeTests)
     unittest.TextTestRunner(verbosity=2).run(suite)