Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions CHANGELOG.rst
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,11 @@
Changelog
=========

2.0.1 (2023-XX-XX)
------------------

- Fix exception when mixing patterns with prematchers and without prematchers.

2.0.0 (2023-03-08)
------------------

Expand Down
11 changes: 7 additions & 4 deletions src/multiregex/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -83,10 +83,13 @@ def __init__(
patterns = self._generate_missing_prematchers(patterns)
self.patterns = [pattern for pattern, _ in patterns]
self.prematchers = dict(patterns)
enumerated_patterns = list(enumerate(patterns))
self.patterns_without_prematchers = {
pattern for pattern, prematchers in patterns if not prematchers
(idx, pattern)
for idx, (pattern, prematchers) in enumerated_patterns
if not prematchers
}
self.automaton = self._make_automaton(patterns)
self.automaton = self._make_automaton(enumerated_patterns)

self.count_prematcher_false_positives = count_prematcher_false_positives
if count_prematcher_false_positives:
Expand Down Expand Up @@ -142,10 +145,10 @@ def _generate_missing_prematchers(self, patterns):
return patterns

@staticmethod
def _make_automaton(patterns):
def _make_automaton(enumerated_patterns):
"""Create the pyahocorasick automaton."""
pattern_candidates_by_prematchers = collections.defaultdict(set)
for pattern_idx, (pattern, prematchers) in enumerate(patterns):
for pattern_idx, (pattern, prematchers) in enumerated_patterns:
for prematcher in prematchers:
# `pattern_idx` is used for keeping patterns in order, see `get_pattern_candidates`.
pattern_candidates_by_prematchers[prematcher].add(
Expand Down
8 changes: 5 additions & 3 deletions tests/test_multiregex.py
Original file line number Diff line number Diff line change
Expand Up @@ -38,11 +38,13 @@ def test_search_match_fullmatch():


def test_ordered():
patterns = [re.compile(c) for c in "abcdef"]
patterns = [
(re.compile(c), None if i % 2 == 0 else []) for i, c in enumerate("abcdef")
] # type: ignore
random.shuffle(patterns)
matcher = RegexMatcher(patterns)
matches = matcher.search("abcdef")
assert [p for p, _ in matches] == patterns
matches = matcher.search("abcdefg")
assert [p for p, _ in matches] == [p for p, _ in patterns]


@pytest.mark.parametrize(
Expand Down