explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 18:06:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'develop' of https://github.com/explosion/spaCy into develop

Browse Source
This commit is contained in:
Matthew Honnibal 2017-06-05 13:13:23 +02:00
commit fc4204a12a
1 changed files with 36 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

55
spacy/util.py
View File

@ -99,28 +99,47 @@ def load_model(name, **overrides):
if not data_path or not data_path.exists(): if not data_path or not data_path.exists():
raise IOError("Can't find spaCy data path: %s" % path2str(data_path)) raise IOError("Can't find spaCy data path: %s" % path2str(data_path))
if isinstance(name, basestring_): if isinstance(name, basestring_):
if (data_path / name).exists(): # in data dir or shortcut if name in set([d.name for d in data_path.iterdir()]): # in data dir / shortcut
spec = importlib.util.spec_from_file_location('model', data_path / name) return load_model_from_link(name, **overrides)
cls = importlib.util.module_from_spec(spec)
spec.loader.exec_module(cls)
return cls.load(**overrides)
if is_package(name): # installed as package if is_package(name): # installed as package
cls = importlib.import_module(name) return load_model_from_package(name, **overrides)
return cls.load(**overrides)
if Path(name).exists(): # path to model data directory if Path(name).exists(): # path to model data directory
model_path = Path(name) return load_model_from_path(Path(name), **overrides)
meta = get_package_meta(model_path)
cls = get_lang_class(meta['lang'])
nlp = cls(pipeline=meta.get('pipeline', True), meta=meta)
return nlp.from_disk(model_path, **overrides)
elif hasattr(name, 'exists'): # Path or Path-like to model data elif hasattr(name, 'exists'): # Path or Path-like to model data
meta = get_package_meta(name) return load_model_from_path(name, **overrides)
cls = get_lang_class(meta['lang'])
nlp = cls(pipeline=meta.get('pipeline', True), meta=meta)
return nlp.from_disk(name, **overrides)
raise IOError("Can't find model '%s'" % name) raise IOError("Can't find model '%s'" % name)
def load_model_from_link(name, **overrides):
"""Load a model from a shortcut link, or directory in spaCy data path."""
init_file = get_data_path() / name / '__init__.py'
spec = importlib.util.spec_from_file_location(name, init_file)
try:
cls = importlib.util.module_from_spec(spec)
except AttributeError:
raise IOError(
"Cant' load '%s'. If you're using a shortcut link, make sure it "
"points to a valid model package (not just a data directory)." % name)
spec.loader.exec_module(cls)
return cls.load(**overrides)
def load_model_from_package(name, **overrides):
"""Load a model from an installed package."""
cls = importlib.import_module(name)
return cls.load(**overrides)
def load_model_from_path(model_path, meta=False, **overrides):
"""Load a model from a data directory path. Creates Language class with
pipeline from meta.json and then calls from_disk() with path."""
if not meta:
meta = get_model_meta(model_path)
cls = get_lang_class(meta['lang'])
nlp = cls(pipeline=meta.get('pipeline', True), meta=meta, **overrides)
return nlp.from_disk(model_path)
def load_model_from_init_py(init_file, **overrides): def load_model_from_init_py(init_file, **overrides):
"""Helper function to use in the `load()` method of a model package's """Helper function to use in the `load()` method of a model package's
__init__.py. __init__.py.
@ -135,9 +154,7 @@ def load_model_from_init_py(init_file, **overrides):
data_path = model_path / data_dir data_path = model_path / data_dir
if not model_path.exists(): if not model_path.exists():
raise ValueError("Can't find model directory: %s" % path2str(data_path)) raise ValueError("Can't find model directory: %s" % path2str(data_path))
cls = get_lang_class(meta['lang']) return load_model_from_path(data_path, meta, **overrides)
nlp = cls(pipeline=meta.get('pipeline', True), meta=meta)
return nlp.from_disk(data_path, **overrides)
def get_model_meta(path): def get_model_meta(path):