Merge load_lang_class and get_lang_class

spacy/__init__.py

@@ -16,7 +16,7 @@ def load(name, **overrides):
     meta = util.parse_package_meta(model_path)
     if 'lang' not in meta:
         raise IOError('No language setting found in model meta.')
-    cls = util.load_lang_class(meta['lang'])
+    cls = util.get_lang_class(meta['lang'])
     overrides['meta'] = meta
     overrides['path'] = model_path
     return cls(**overrides)

spacy/tests/conftest.py

@@ -18,67 +18,67 @@ _languages = ['bn', 'da', 'de', 'en', 'es', 'fi', 'fr', 'he', 'hu', 'it', 'nb',
 
 @pytest.fixture(params=_languages)
 def tokenizer(request):
-    lang = util.load_lang_class(request.param)
+    lang = util.get_lang_class(request.param)
     return lang.Defaults.create_tokenizer()
 
 
 @pytest.fixture
 def en_tokenizer():
-    return util.load_lang_class('en').Defaults.create_tokenizer()
+    return util.get_lang_class('en').Defaults.create_tokenizer()
 
 
 @pytest.fixture
 def en_vocab():
-    return util.load_lang_class('en').Defaults.create_vocab()
+    return util.get_lang_class('en').Defaults.create_vocab()
 
 
 @pytest.fixture
 def en_parser():
-    return util.load_lang_class('en').Defaults.create_parser()
+    return util.get_lang_class('en').Defaults.create_parser()
 
 
 @pytest.fixture
 def es_tokenizer():
-    return util.load_lang_class('es').Defaults.create_tokenizer()
+    return util.get_lang_class('es').Defaults.create_tokenizer()
 
 
 @pytest.fixture
 def de_tokenizer():
-    return util.load_lang_class('de').Defaults.create_tokenizer()
+    return util.get_lang_class('de').Defaults.create_tokenizer()
 
 
 @pytest.fixture(scope='module')
 def fr_tokenizer():
-    return util.load_lang_class('fr').Defaults.create_tokenizer()
+    return util.get_lang_class('fr').Defaults.create_tokenizer()
 
 
 @pytest.fixture
 def hu_tokenizer():
-    return util.load_lang_class('hu').Defaults.create_tokenizer()
+    return util.get_lang_class('hu').Defaults.create_tokenizer()
 
 
 @pytest.fixture
 def fi_tokenizer():
-    return util.load_lang_class('fi').Defaults.create_tokenizer()
+    return util.get_lang_class('fi').Defaults.create_tokenizer()
 
 
 @pytest.fixture
 def sv_tokenizer():
-    return util.load_lang_class('sv').Defaults.create_tokenizer()
+    return util.get_lang_class('sv').Defaults.create_tokenizer()
 
 
 @pytest.fixture
 def bn_tokenizer():
-    return util.load_lang_class('bn').Defaults.create_tokenizer()
+    return util.get_lang_class('bn').Defaults.create_tokenizer()
 
 
 @pytest.fixture
 def he_tokenizer():
-    return util.load_lang_class('he').Defaults.create_tokenizer()
+    return util.get_lang_class('he').Defaults.create_tokenizer()
 
 @pytest.fixture
 def nb_tokenizer():
-    return util.load_lang_class('nb').Defaults.create_tokenizer()
+    return util.get_lang_class('nb').Defaults.create_tokenizer()
 
 
 @pytest.fixture
@@ -88,12 +88,12 @@ def stringstore():
 
 @pytest.fixture
 def en_entityrecognizer():
-     return util.load_lang_class('en').Defaults.create_entity()
+     return util.get_lang_class('en').Defaults.create_entity()
 
 
 @pytest.fixture
 def lemmatizer():
-    return util.load_lang_class('en').Defaults.create_lemmatizer()
+    return util.get_lang_class('en').Defaults.create_lemmatizer()
 
 
 @pytest.fixture

spacy/util.py

@@ -17,30 +17,30 @@ LANGUAGES = {}
 _data_path = Path(__file__).parent / 'data'
 
 
-def set_lang_class(name, cls):
+def get_lang_class(lang):
+    """Import and load a Language class.
+
+    lang (unicode): Two-letter language code, e.g. 'en'.
+    RETURNS (Language): Language class.
+    """
     global LANGUAGES
-    LANGUAGES[name] = cls
-
-
-def get_lang_class(name):
-    if name in LANGUAGES:
-        return LANGUAGES[name]
-    lang = re.split('[^a-zA-Z0-9]', name, 1)[0]
-    if lang not in LANGUAGES:
-        raise RuntimeError('Language not supported: %s' % name)
+    if not lang in LANGUAGES:
+        try:
+            module = importlib.import_module('.lang.%s' % lang, 'spacy')
+        except ImportError:
+            raise ImportError("Can't import language %s from spacy.lang." %lang)
+        LANGUAGES[lang] = getattr(module, module.__all__[0])
     return LANGUAGES[lang]
 
 
-def load_lang_class(lang):
-    """Import and load a Language class.
+def set_lang_class(name, cls):
+    """Set a custom Language class name that can be loaded via get_lang_class.
 
-    Args:
-        lang (unicode): Two-letter language code, e.g. 'en'.
-    Returns:
-        Language: Language class.
+    name (unicode): Name of Language class.
+    cls (Language): Language class.
     """
-    module = importlib.import_module('.lang.%s' % lang, 'spacy')
-    return getattr(module, module.__all__[0])
+    global LANGUAGES
+    LANGUAGES[name] = cls
 
 
 def get_data_path(require_exists=True):

website/docs/api/util.jade

@@ -49,7 +49,7 @@ p
         +cell unicode or #[code Path]
         +cell Path to new data directory.
 
-+h(2, "load_lang_class") load_lang_class
++h(2, "get_lang_class") get_lang_class
     +tag function
 
 p
@@ -59,7 +59,7 @@ p
 
 +aside-code("Example").
     for lang_id in ['en', 'de']:
-        lang_class = util.load_lang_class(lang_id)
+        lang_class = util.get_lang_class(lang_id)
         lang = lang_class()
         tokenizer = lang.Defaults.create_tokenizer()
 

website/docs/usage/adding-languages.jade

@@ -80,7 +80,7 @@ p
     |  compute. As of spaCy v2.0, #[code Language] classes are not imported on
     |  initialisation and are only loaded when you import them directly, or load
     |  a model that requires a language to be loaded. To lazy-load languages in
-    |  your application, you can use the #[code util.load_lang_class()] helper
+    |  your application, you can use the #[code util.get_lang_class()] helper
     |  function with the two-letter language code as its argument.
 
 +h(2, "language-data") Adding language data
@@ -486,7 +486,7 @@ p
     |  #[+src(gh("spaCy", "spacy/tests/lang")) tests/lang] in a directory named
     |  after the language ID. You'll also need to create a fixture for your
     |  tokenizer in the #[+src(gh("spaCy", "spacy/tests/conftest.py")) conftest.py].
-    |  Always use the #[code load_lang_class()] helper function within the fixture,
+    |  Always use the #[code get_lang_class()] helper function within the fixture,
     |  instead of importing the class at the top of the file. This will load the
     |  language data only when it's needed. (Otherwise, #[em all data] would be
     |  loaded every time you run a test.)
@@ -494,7 +494,7 @@ p
 +code.
     @pytest.fixture
     def en_tokenizer():
-        return util.load_lang_class('en').Defaults.create_tokenizer()
+        return util.get_lang_class('en').Defaults.create_tokenizer()
 
 p
     |  When adding test cases, always