Allow entity types with dashes (resolves explosion#1967)

youndoldman · Mar 28, 2018 · 3eb67bb · 3eb67bb
1 parent 9615ed5
commit 3eb67bb
Show file tree

Hide file tree

Showing 2 changed files with 16 additions and 3 deletions.
diff --git a/spacy/syntax/ner.pyx b/spacy/syntax/ner.pyx
@@ -84,9 +84,7 @@ cdef class BiluoPushDown(TransitionSystem):
             for (ids, words, tags, heads, labels, biluo), _ in sents:
                 for i, ner_tag in enumerate(biluo):
                     if ner_tag != 'O' and ner_tag != '-':
-                        if ner_tag.count('-') != 1:
-                            raise ValueError(ner_tag)
-                        _, label = ner_tag.split('-')
+                        _, label = ner_tag.split('-', 1)
                         if label not in seen_entities:
                             seen_entities.add(label)
                             for move_str in ('B', 'I', 'L', 'U'):

diff --git a/spacy/tests/regression/test_issue1967.py b/spacy/tests/regression/test_issue1967.py
@@ -0,0 +1,15 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+import pytest
+
+from ...pipeline import EntityRecognizer
+from ...vocab import Vocab
+
+
+@pytest.mark.parametrize('label', ['U-JOB-NAME'])
+def test_issue1967(label):
+    ner = EntityRecognizer(Vocab())
+    entry = ([0], ['word'], ['tag'], [0], ['dep'], [label])
+    gold_parses = [(None, [(entry, None)])]
+    ner.moves.get_actions(gold_parses=gold_parses)