From 7072b395c9e0705338c857e7b1ef7087cdb7b928 Mon Sep 17 00:00:00 2001
From: greg <greg.dubbin@spreemo.com>
Date: Tue, 16 Jan 2018 15:46:13 -0500
Subject: [PATCH] Add greedy matcher tests

---
 spacy/tests/regression/test_issue1855.py | 63 ++++++++++++++++++++++++
 spacy/tests/test_matcher_greedy.py       | 63 ++++++++++++++++++++++++
 2 files changed, 126 insertions(+)
 create mode 100644 spacy/tests/regression/test_issue1855.py
 create mode 100644 spacy/tests/test_matcher_greedy.py

diff --git a/spacy/tests/regression/test_issue1855.py b/spacy/tests/regression/test_issue1855.py
new file mode 100644
index 000000000..882c356ca
--- /dev/null
+++ b/spacy/tests/regression/test_issue1855.py
@@ -0,0 +1,63 @@
+# coding: utf-8
+from __future__ import unicode_literals
+import re
+
+from ..matcher import Matcher
+
+import pytest
+
+pattern1	= [{'ORTH':'A','OP':'1'},{'ORTH':'A','OP':'*'}]
+pattern2	= [{'ORTH':'A','OP':'*'},{'ORTH':'A','OP':'1'}]
+pattern3	= [{'ORTH':'A','OP':'1'},{'ORTH':'A','OP':'1'}]
+pattern4	= [{'ORTH':'B','OP':'1'},{'ORTH':'A','OP':'*'},{'ORTH':'B','OP':'1'}]
+pattern5 	= [{'ORTH':'B','OP':'*'},{'ORTH':'A','OP':'*'},{'ORTH':'B','OP':'1'}]
+
+re_pattern1	= 'AA*'
+re_pattern2 = 'A*A'
+re_pattern3	= 'AA'
+re_pattern4	= 'BA*B'
+re_pattern5	= 'B*A*B'
+
+@pytest.fixture
+def text():
+	return "(ABBAAAAAB)."
+
+@pytest.fixture
+def doc(en_tokenizer,text):
+    doc = en_tokenizer(' '.join(text))
+    return doc
+
+@pytest.mark.parametrize('pattern,re_pattern',[
+	(pattern1,re_pattern1),
+	(pattern2,re_pattern2),
+	(pattern3,re_pattern3),
+	(pattern4,re_pattern4),
+	(pattern5,re_pattern5)])
+def test_greedy_matching(doc,text,pattern,re_pattern):
+	"""
+	Test that the greedy matching behavior of the * op
+	is consistant with other re implementations
+	"""
+	matcher = Matcher(doc.vocab)
+	matcher.add(re_pattern,None,pattern)
+	matches = matcher(doc)
+	re_matches = [m.span() for m in re.finditer(re_pattern,text)]
+	for match,re_match in zip(matches,re_matches):
+		assert match[1:]==re_match
+
+@pytest.mark.parametrize('pattern,re_pattern',[
+	(pattern1,re_pattern1),
+	(pattern2,re_pattern2),
+	(pattern3,re_pattern3),
+	(pattern4,re_pattern4),
+	(pattern5,re_pattern5)])
+def test_match_consuming(doc,text,pattern,re_pattern):
+	"""
+	Test that matcher.__call__ consumes tokens on a match
+	similar to re.findall
+	"""
+	matcher = Matcher(doc.vocab)
+	matcher.add(re_pattern,None,pattern)
+	matches = matcher(doc)
+	re_matches = [m.span() for m in re.finditer(re_pattern,text)]
+	assert len(matches)==len(re_matches)
\ No newline at end of file
diff --git a/spacy/tests/test_matcher_greedy.py b/spacy/tests/test_matcher_greedy.py
new file mode 100644
index 000000000..882c356ca
--- /dev/null
+++ b/spacy/tests/test_matcher_greedy.py
@@ -0,0 +1,63 @@
+# coding: utf-8
+from __future__ import unicode_literals
+import re
+
+from ..matcher import Matcher
+
+import pytest
+
+pattern1	= [{'ORTH':'A','OP':'1'},{'ORTH':'A','OP':'*'}]
+pattern2	= [{'ORTH':'A','OP':'*'},{'ORTH':'A','OP':'1'}]
+pattern3	= [{'ORTH':'A','OP':'1'},{'ORTH':'A','OP':'1'}]
+pattern4	= [{'ORTH':'B','OP':'1'},{'ORTH':'A','OP':'*'},{'ORTH':'B','OP':'1'}]
+pattern5 	= [{'ORTH':'B','OP':'*'},{'ORTH':'A','OP':'*'},{'ORTH':'B','OP':'1'}]
+
+re_pattern1	= 'AA*'
+re_pattern2 = 'A*A'
+re_pattern3	= 'AA'
+re_pattern4	= 'BA*B'
+re_pattern5	= 'B*A*B'
+
+@pytest.fixture
+def text():
+	return "(ABBAAAAAB)."
+
+@pytest.fixture
+def doc(en_tokenizer,text):
+    doc = en_tokenizer(' '.join(text))
+    return doc
+
+@pytest.mark.parametrize('pattern,re_pattern',[
+	(pattern1,re_pattern1),
+	(pattern2,re_pattern2),
+	(pattern3,re_pattern3),
+	(pattern4,re_pattern4),
+	(pattern5,re_pattern5)])
+def test_greedy_matching(doc,text,pattern,re_pattern):
+	"""
+	Test that the greedy matching behavior of the * op
+	is consistant with other re implementations
+	"""
+	matcher = Matcher(doc.vocab)
+	matcher.add(re_pattern,None,pattern)
+	matches = matcher(doc)
+	re_matches = [m.span() for m in re.finditer(re_pattern,text)]
+	for match,re_match in zip(matches,re_matches):
+		assert match[1:]==re_match
+
+@pytest.mark.parametrize('pattern,re_pattern',[
+	(pattern1,re_pattern1),
+	(pattern2,re_pattern2),
+	(pattern3,re_pattern3),
+	(pattern4,re_pattern4),
+	(pattern5,re_pattern5)])
+def test_match_consuming(doc,text,pattern,re_pattern):
+	"""
+	Test that matcher.__call__ consumes tokens on a match
+	similar to re.findall
+	"""
+	matcher = Matcher(doc.vocab)
+	matcher.add(re_pattern,None,pattern)
+	matches = matcher(doc)
+	re_matches = [m.span() for m in re.finditer(re_pattern,text)]
+	assert len(matches)==len(re_matches)
\ No newline at end of file