From 7670c745b6370fafd29ccedcdcba875156ccd576 Mon Sep 17 00:00:00 2001
From: ines <ines@ines.io>
Date: Sun, 16 Apr 2017 20:35:00 +0200
Subject: [PATCH] Update spacy.load() and fix path checks

---
 spacy/__init__.py | 47 +++++++++++++++++++++++------------------------
 1 file changed, 23 insertions(+), 24 deletions(-)

diff --git a/spacy/__init__.py b/spacy/__init__.py
index bc668121f..06e9374ea 100644
--- a/spacy/__init__.py
+++ b/spacy/__init__.py
@@ -1,39 +1,38 @@
 # coding: utf8
 from __future__ import unicode_literals
 
-from pathlib import Path
-
-from .util import set_lang_class, get_lang_class, parse_package_meta
+from . import util
 from .deprecated import resolve_model_name
 from .cli import info
 
 from . import en, de, zh, es, it, hu, fr, pt, nl, sv, fi, bn, he
 
 
-set_lang_class(en.English.lang, en.English)
-set_lang_class(de.German.lang, de.German)
-set_lang_class(es.Spanish.lang, es.Spanish)
-set_lang_class(pt.Portuguese.lang, pt.Portuguese)
-set_lang_class(fr.French.lang, fr.French)
-set_lang_class(it.Italian.lang, it.Italian)
-set_lang_class(hu.Hungarian.lang, hu.Hungarian)
-set_lang_class(zh.Chinese.lang, zh.Chinese)
-set_lang_class(nl.Dutch.lang, nl.Dutch)
-set_lang_class(sv.Swedish.lang, sv.Swedish)
-set_lang_class(fi.Finnish.lang, fi.Finnish)
-set_lang_class(bn.Bengali.lang, bn.Bengali)
-set_lang_class(he.Hebrew.lang, he.Hebrew)
+_languages = (en.English, de.German, es.Spanish, pt.Portuguese, fr.French,
+             it.Italian, hu.Hungarian, zh.Chinese, nl.Dutch, sv.Swedish,
+             fi.Finnish, bn.Bengali, he.Hebrew)
+
+
+for _lang in _languages:
+    util.set_lang_class(_lang.lang, _lang)
 
 
 def load(name, **overrides):
-    data_path = overrides.get('path', util.get_data_path())
-    model_name = resolve_model_name(name)
-    meta = parse_package_meta(data_path, model_name, require=False)
+    if overrides.get('path') in (None, False, True):
+        data_path = util.get_data_path()
+        model_name = resolve_model_name(name)
+        model_path = data_path / model_name
+        if not model_path.exists():
+            model_path = None
+            util.print_msg(
+                "Only loading the '{}' tokenizer.".format(name),
+                title="Warning: no model found for '{}'".format(name))
+    else:
+        model_path = util.ensure_path(overrides['path'])
+        data_path = model_path.parent
+    meta = util.parse_package_meta(data_path, model_name, require=False)
     lang = meta['lang'] if meta and 'lang' in meta else name
-    cls = get_lang_class(lang)
+    cls = util.get_lang_class(lang)
     overrides['meta'] = meta
-    model_path = Path(data_path / model_name)
-    if model_path.exists():
-        overrides['path'] = model_path
-
+    overrides['path'] = model_path
     return cls(**overrides)