From 98c35d2585c548e6ff2c25a537cfd81c25482283 Mon Sep 17 00:00:00 2001
From: ines <ines@ines.io>
Date: Mon, 30 Oct 2017 18:38:41 +0100
Subject: [PATCH] Fix spacy vocab command

---
 spacy/__main__.py  |  2 +-
 spacy/cli/vocab.py | 38 ++++++++++++++++++++++----------------
 2 files changed, 23 insertions(+), 17 deletions(-)

diff --git a/spacy/__main__.py b/spacy/__main__.py
index 770ce5296..f4b5e6715 100644
--- a/spacy/__main__.py
+++ b/spacy/__main__.py
@@ -19,7 +19,7 @@ if __name__ == '__main__':
         'convert': convert,
         'package': package,
         'model': model,
-        'model': vocab,
+        'vocab': vocab,
         'profile': profile,
         'validate': validate
     }
diff --git a/spacy/cli/vocab.py b/spacy/cli/vocab.py
index c1bab825c..d05eff3f0 100644
--- a/spacy/cli/vocab.py
+++ b/spacy/cli/vocab.py
@@ -1,31 +1,33 @@
-'''Compile a vocabulary from a lexicon jsonl file and word vectors.'''
 # coding: utf8
 from __future__ import unicode_literals
 
-from pathlib import Path
 import plac
 import json
 import spacy
 import numpy
-from spacy.util import ensure_path
+from pathlib import Path
+
+from ..util import prints, ensure_path
 
 
 @plac.annotations(
     lang=("model language", "positional", None, str),
-    output_dir=("output directory to store model in", "positional", None, str),
+    output_dir=("model output directory", "positional", None, Path),
     lexemes_loc=("location of JSONL-formatted lexical data", "positional",
-                None, str),
-    vectors_loc=("location of vectors data, as numpy .npz (optional)",
-              "positional", None, str),
-    version=("Model version", "option", "V", str),
-)
-def make_vocab(lang, output_dir, lexemes_loc, vectors_loc=None, version=None):
-    out_dir = ensure_path(output_dir)
-    jsonl_loc = ensure_path(lexemes_loc)
+                 None, Path),
+    vectors_loc=("optional: location of vectors data, as numpy .npz",
+                 "positional", None, str))
+def make_vocab(cmd, lang, output_dir, lexemes_loc, vectors_loc=None):
+    """Compile a vocabulary from a lexicon jsonl file and word vectors."""
+    if not lexemes_loc.exists():
+        prints(lexemes_loc, title="Can't find lexical data", exits=1)
+    vectors_loc = ensure_path(vectors_loc)
     nlp = spacy.blank(lang)
     for word in nlp.vocab:
         word.rank = 0
-    with jsonl_loc.open() as file_:
+    lex_added = 0
+    vec_added = 0
+    with lexemes_loc.open() as file_:
         for line in file_:
             if line.strip():
                 attrs = json.loads(line)
@@ -35,14 +37,18 @@ def make_vocab(lang, output_dir, lexemes_loc, vectors_loc=None, version=None):
                     lex = nlp.vocab[attrs['orth']]
                     lex.set_attrs(**attrs)
                     assert lex.rank == attrs['id']
+                lex_added += 1
     if vectors_loc is not None:
         vector_data = numpy.load(open(vectors_loc, 'rb'))
         nlp.vocab.clear_vectors(width=vector_data.shape[1])
-        added = 0
         for word in nlp.vocab:
             if word.rank:
                 nlp.vocab.vectors.add(word.orth_, row=word.rank,
                                       vector=vector_data[word.rank])
-                added += 1
-    nlp.to_disk(out_dir)
+                vec_added += 1
+    if not output_dir.exists():
+        output_dir.mkdir()
+    nlp.to_disk(output_dir)
+    prints("{} entries, {} vectors".format(lex_added, vec_added), output_dir,
+           title="Sucessfully compiled vocab and vectors, and saved model")
     return nlp