cc-4105: Fixed up mutagen metadata related stuff. Included utf8 routines from old media monitor

python_apps/media-monitor2/media/monitor/metadata.py

@@ -92,13 +92,14 @@ def truncate_to_length(item, length):
 
 class Metadata(Loggable):
     def __init__(self, fpath):
-        try: full_mutagen  = mutagen.File(self.path, easy=True)
-        except Exception: raise BadSongFile(self.path)
+        try: full_mutagen  = mutagen.File(fpath, easy=True)
+        except Exception: raise BadSongFile(fpath)
+        self.path = fpath
         # TODO : Simplify the way all of these rules are handled right not it's
         # extremely unclear and needs to be refactored.
         metadata = {}
         # Load only the metadata avilable in mutagen into metdata
-        for k,v in full_mutagen:
+        for k,v in full_mutagen.iteritems():
             # Special handling of attributes here
             if isinstance(v, list):
                 if len(v) == 1: metadata[k] = v[0]
@@ -118,15 +119,17 @@ class Metadata(Loggable):
                 self.__metadata[ airtime_key ] = muta_v
         # Now we extra the special values that are calculated from the mutagen
         # object itself:
-        for special_key,f in airtime_special:
+        for special_key,f in airtime_special.iteritems():
             new_val = f(full_mutagen)
             if new_val is not None:
                 self.__metadata[special_key] = f(full_mutagen)
         # Finally, we "normalize" all the metadata here:
         self.__metadata = mmp.normalized_metadata(self.__metadata, fpath)
         # Now we must load the md5:
-        self.__metadata['MDATA_KEY_MD5'] = mmp.fild_md5(fpath)
+        self.__metadata['MDATA_KEY_MD5'] = mmp.file_md5(fpath)
 
     def extract(self):
         return copy.deepcopy(self.__metadata)
 
+    def utf8(self):
+        return mmp.convert_dict_value_to_utf8(self.extract())

python_apps/media-monitor2/media/monitor/pure.py

@@ -125,7 +125,7 @@ def normalized_metadata(md, original_path):
     new_md = copy.deepcopy(md)
     # replace all slashes with dashes
     for k,v in new_md.iteritems():
-        new_md[k] = str(v).replace('/','-')
+        new_md[k] = unicode(v).replace('/','-')
     # Specific rules that are applied in a per attribute basis
     format_rules = {
         # It's very likely that the following isn't strictly necessary. But the old
@@ -206,6 +206,15 @@ def file_md5(path,max_length=100):
             return m.hexdigest()
     else: raise ValueError("'%s' must exist to find its md5")
 
+def encode_to(obj, encoding='utf-8'):
+    if isinstance(obj, unicode):
+        obj = obj.encode(encoding)
+    return obj
+
+def convert_dict_value_to_utf8(md):
+    #list comprehension to convert all values of md to utf-8
+    return dict([(item[0], encode_to(item[1], "utf-8")) for item in md.items()])
+
 if __name__ == '__main__':
     import doctest
     doctest.testmod()