Skip to content

Skip regex passes that cannot match (~29% faster slugify) #211

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
deadstrobe5 wants to merge 1 commit into from
Closed

Skip regex passes that cannot match (~29% faster slugify) #211

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
17 changes: 13 additions & 4 deletions slugify/_legacy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,9 @@


def _decode_entities(text: str, entities: bool, decimal: bool, hexadecimal: bool) -> str:
# Non-behavioral: every reference starts with '&', so skip the scans without one.
if '&' not in text:
return text
if entities:
text = CHAR_ENTITY_PATTERN.sub(lambda m: chr(name2codepoint[m.group(1)]), text)
if decimal:
Expand Down Expand Up @@ -134,7 +137,9 @@ def slugify(
for old, new in replacements:
text = text.replace(old, new)

text = QUOTE_PATTERN.sub(DEFAULT_SEPARATOR, text)
# Non-behavioral: skip substitutions that cannot match.
if "'" in text:
text = QUOTE_PATTERN.sub(DEFAULT_SEPARATOR, text)
if allow_unicode:
text = unicodedata.normalize('NFKC', text)
else:
Expand All @@ -143,11 +148,15 @@ def slugify(
text = unicodedata.normalize('NFKC' if allow_unicode else 'NFKD', text)
if lowercase:
text = text.lower()
text = QUOTE_PATTERN.sub('', text)
text = NUMBERS_PATTERN.sub('', text)
if "'" in text:
text = QUOTE_PATTERN.sub('', text)
if ',' in text:
text = NUMBERS_PATTERN.sub('', text)
pattern = regex_pattern or (DISALLOWED_UNICODE_CHARS_PATTERN if allow_unicode else DISALLOWED_CHARS_PATTERN)
text = re.sub(pattern, DEFAULT_SEPARATOR, text)
text = DUPLICATE_DASH_PATTERN.sub(DEFAULT_SEPARATOR, text).strip(DEFAULT_SEPARATOR)
if '--' in text:
text = DUPLICATE_DASH_PATTERN.sub(DEFAULT_SEPARATOR, text)
text = text.strip(DEFAULT_SEPARATOR)

if stopwords:
excluded = [word.lower() for word in stopwords] if lowercase else stopwords
Expand Down
17 changes: 13 additions & 4 deletions slugify/slugify.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,9 @@ def _numeric_reference(match: re.Match[str], base: int) -> str:


def _decode_entities(text: str, entities: bool, decimal: bool, hexadecimal: bool) -> str:
# Every reference starts with '&', so skip the scans without one.
if '&' not in text:
return text
if entities:
text = CHAR_ENTITY_PATTERN.sub(lambda m: chr(name2codepoint[m.group(1)]), text)
if decimal:
Expand Down Expand Up @@ -158,19 +161,25 @@ def _modern_slugify(
text = text.replace(old, new)

text = _decode_entities(text, entities, decimal, hexadecimal)
text = QUOTE_PATTERN.sub(DEFAULT_SEPARATOR, text)
# Skip substitutions that cannot match.
if "'" in text:
text = QUOTE_PATTERN.sub(DEFAULT_SEPARATOR, text)
if allow_unicode:
text = unicodedata.normalize('NFKC', text)
else:
text = _transliterate(unicodedata.normalize('NFKD', text), backend)
text = unicodedata.normalize('NFKC' if allow_unicode else 'NFKD', text)
if lowercase:
text = text.lower()
text = QUOTE_PATTERN.sub('', text)
text = NUMBERS_PATTERN.sub('', text)
if "'" in text:
text = QUOTE_PATTERN.sub('', text)
if ',' in text:
text = NUMBERS_PATTERN.sub('', text)
pattern = regex_pattern or (DISALLOWED_UNICODE_CHARS_PATTERN if allow_unicode else DISALLOWED_CHARS_PATTERN)
text = re.sub(pattern, DEFAULT_SEPARATOR, text)
text = DUPLICATE_DASH_PATTERN.sub(DEFAULT_SEPARATOR, text).strip(DEFAULT_SEPARATOR)
if '--' in text:
text = DUPLICATE_DASH_PATTERN.sub(DEFAULT_SEPARATOR, text)
text = text.strip(DEFAULT_SEPARATOR)

if stopwords:
excluded = {word.lower() if lowercase else word for word in stopwords}
Expand Down