Merge pull request #642 from ExplodingCabbage/specify-data-path

Let --data-path be specified when running download.py scripts

README.rst

@@ -222,6 +222,22 @@ and ``--model`` are optional and enable additional tests:
 
     python -m pytest <spacy-directory> --vectors --model --slow
 
+Download model to custom location
+=================================
+
+You can specify where ``spacy.en.download`` and ``spacy.de.download`` download the language model
+to using the ``--data-path`` or ``-d`` argument:
+
+.. code:: bash
+    
+    python -m spacy.en.download all --data-path /some/dir
+
+
+If you choose to download to a custom location, you will need to tell spaCy where to load the model
+from in order to use it. You can do this either by calling ``spacy.util.set_data_path()`` before
+calling ``spacy.load()``, or by passing a ``path`` argument to the ``spacy.en.English`` or
+``spacy.de.German`` constructors.
+
 Changelog
 =========
 

spacy/de/download.py

@@ -4,9 +4,10 @@
 
 @plac.annotations(
     force=("Force overwrite", "flag", "f", bool),
+    data_path=("Path to download model", "option", "d", str)
 )
-def main(data_size='all', force=False):
-    download('de', force)
+def main(data_size='all', force=False, data_path=None):
+    download('de', force=force, data_path=data_path)
 
 
 if __name__ == '__main__':

spacy/download.py

@@ -10,10 +10,19 @@
 from . import util
 
 
-def download(lang, force=False, fail_on_exist=True):
+def download(lang, force=False, fail_on_exist=True, data_path=None):
+    if not data_path:
+        data_path = util.get_data_path()
+
+    # spaCy uses pathlib, and util.get_data_path returns a pathlib.Path object,
+    # but sputnik (which we're using below) doesn't use pathlib and requires
+    # its data_path parameters to be strings, so we coerce the data_path to a
+    # str here.
+    data_path = str(data_path)
+
     try:
         pkg = sputnik.package(about.__title__, about.__version__,
-                        about.__models__.get(lang, lang))
+                        about.__models__.get(lang, lang), data_path)
         if force:
             shutil.rmtree(pkg.path)
         elif fail_on_exist:
@@ -24,15 +33,14 @@ def download(lang, force=False, fail_on_exist=True):
         pass
 
     package = sputnik.install(about.__title__, about.__version__,
-                              about.__models__.get(lang, lang))
+                              about.__models__.get(lang, lang), data_path)
 
     try:
         sputnik.package(about.__title__, about.__version__,
-                        about.__models__.get(lang, lang))
+                        about.__models__.get(lang, lang), data_path)
     except (PackageNotFoundException, CompatiblePackageNotFoundException):
         print("Model failed to install. Please run 'python -m "
               "spacy.%s.download --force'." % lang, file=sys.stderr)
         sys.exit(1)
 
-    data_path = util.get_data_path()
     print("Model successfully installed to %s" % data_path, file=sys.stderr)

spacy/en/download.py

@@ -7,17 +7,18 @@
 
 @plac.annotations(
     force=("Force overwrite", "flag", "f", bool),
+    data_path=("Path to download model", "option", "d", str)
 )
-def main(data_size='all', force=False):
+def main(data_size='all', force=False, data_path=None):
     if force:
         sputnik.purge(about.__title__, about.__version__)
 
     if data_size in ('all', 'parser'):
         print("Downloading parsing model")
-        download('en', False)
+        download('en', force=False, data_path=data_path)
     if data_size in ('all', 'glove'):
         print("Downloading GloVe vectors")
-        download('en_glove_cc_300_1m_vectors', False)
+        download('en_glove_cc_300_1m_vectors', force=False, data_path=data_path)
 
 
 if __name__ == '__main__':

spacy/language.py

@@ -246,9 +246,8 @@ def train(cls, path, gold_tuples, *configs):
         self.end_training()
 
     def __init__(self, path=True, **overrides):
-        if 'data_dir' in overrides and 'path' not in overrides:
+        if 'data_dir' in overrides and path is True:
             raise ValueError("The argument 'data_dir' has been renamed to 'path'")
-        path = overrides.get('path', True)
         if isinstance(path, basestring):
             path = pathlib.Path(path)
         if path is True:

website/docs/usage/index.jade

@@ -114,3 +114,20 @@ p
     python -m pip install -U pytest
 
     python -m pytest <spacy-directory> --vectors --model --slow
+
++h(2, "custom-location") Download model to custom location
+
+p
+    |   You can specify where #[code spacy.en.download] and
+    |  #[code spacy.de.download] download the language model to using the
+    |  #[code --data-path] or #[code -d] argument:
+
++code(false, "bash").
+    python -m spacy.en.download all --data-path /some/dir
+
+p
+    |  If you choose to download to a custom location, you will need to tell
+    |  spaCy where to load the model from in order to use it. You can do this
+    |  either by calling #[code spacy.util.set_data_path()] before calling
+    |  #[code spacy.load()], or by passing a #[code path] argument to the
+    |  #[code spacy.en.English] or #[code spacy.de.German] constructors.