Subliminal update

libs/guessit/language.py

@@ -19,9 +19,9 @@
 #
 
 from __future__ import unicode_literals
-from guessit import fileutils
+from guessit import UnicodeMixin, base_text_type, u, s
+from guessit.fileutils import load_file_in_same_dir
 from guessit.country import Country
-from guessit.textutils import to_unicode
 import re
 import logging
 
@@ -39,8 +39,7 @@ log = logging.getLogger(__name__)
 # "An alpha-3 (bibliographic) code, an alpha-3 (terminologic) code (when given),
 # an alpha-2 code (when given), an English name, and a French name of a language
 # are all separated by pipe (|) characters."
-_iso639_contents = fileutils.load_file_in_same_dir(__file__,
-                                                   'ISO-639-2_utf-8.txt').decode('utf-8')
+_iso639_contents = load_file_in_same_dir(__file__, 'ISO-639-2_utf-8.txt')
 
 # drop the BOM from the beginning of the file
 _iso639_contents = _iso639_contents[1:]
@@ -116,7 +115,6 @@ lng_exceptions = { 'unknown': ('und', None),
                    'cn': ('chi', None),
                    'chs': ('chi', None),
                    'jp': ('jpn', None),
-                   'scc': ('srp', None),
                    'scr': ('hrv', None)
                    }
 
@@ -137,7 +135,7 @@ def lang_set(languages, strict=False):
     return set(Language(l, strict=strict) for l in languages)
 
 
-class Language(object):
+class Language(UnicodeMixin):
     """This class represents a human language.
 
     You can initialize it with pretty much anything, as it knows conversion
@@ -154,30 +152,30 @@ class Language(object):
     >>> Language('fr')
     Language(French)
 
-    >>> Language('eng').french_name
-    u'anglais'
+    >>> s(Language('eng').french_name)
+    'anglais'
 
-    >>> Language('pt(br)').country.english_name
-    u'Brazil'
+    >>> s(Language('pt(br)').country.english_name)
+    'Brazil'
 
-    >>> Language('Español (Latinoamérica)').country.english_name
-    u'Latin America'
+    >>> s(Language('Español (Latinoamérica)').country.english_name)
+    'Latin America'
 
     >>> Language('Spanish (Latin America)') == Language('Español (Latinoamérica)')
     True
 
-    >>> Language('zz', strict=False).english_name
-    u'Undetermined'
+    >>> s(Language('zz', strict=False).english_name)
+    'Undetermined'
 
-    >>> Language('pt(br)').opensubtitles
-    u'pob'
+    >>> s(Language('pt(br)').opensubtitles)
+    'pob'
     """
 
     _with_country_regexp = re.compile('(.*)\((.*)\)')
     _with_country_regexp2 = re.compile('(.*)-(.*)')
 
     def __init__(self, language, country=None, strict=False, scheme=None):
-        language = to_unicode(language.strip().lower())
+        language = u(language.strip().lower())
         with_country = (Language._with_country_regexp.match(language) or
                         Language._with_country_regexp2.match(language))
         if with_country:
@@ -249,7 +247,7 @@ class Language(object):
     def opensubtitles(self):
         if self.lang == 'por' and self.country and self.country.alpha2 == 'br':
             return 'pob'
-        elif self.lang in ['gre', 'eus', 'ice', 'srp']:
+        elif self.lang in ['gre', 'srp']:
             return self.alpha3term
         return self.alpha3
 
@@ -266,7 +264,7 @@ class Language(object):
         if isinstance(other, Language):
             return self.lang == other.lang
 
-        if isinstance(other, basestring):
+        if isinstance(other, base_text_type):
             try:
                 return self == Language(other)
             except ValueError:
@@ -286,9 +284,6 @@ class Language(object):
         else:
             return self.english_name
 
-    def __str__(self):
-        return unicode(self).encode('utf-8')
-
     def __repr__(self):
         if self.country:
             return 'Language(%s, country=%s)' % (self.english_name, self.country)