def testIssueSeven(self):
s1 = "HSINCHUANG"
s2 = "SINJHUAN"
s3 = "LSINJHUANG DISTRIC"
s4 = "SINJHUANG DISTRICT"
self.assertTrue(fuzz.partial_ratio(s1, s2) > 75)
self.assertTrue(fuzz.partial_ratio(s1, s3) > 75)
self.assertTrue(fuzz.partial_ratio(s1, s4) > 75)
def detect_old_header_style(file_name: str, comments: list, args: argparse.Namespace) -> Tuple[int, int]:
"""
Detects old header style (Apache-2.0) and extracts the year and line number.
returns: Tuple[year, comment line number]
"""
comments_text = str()
for comment in comments:
if comment.line_number() > args.max_lines:
break
comments_text = f'{comments_text}\n{comment.text().strip()}'
ratio = fuzz.partial_ratio(comments_text, OLD_APACHE_HEADER)
if args.debug:
print(f'{TERMINAL_GRAY}ratio for {file_name}: {ratio}{TERMINAL_RESET}')
if ratio > args.fuzzy_ratio:
for comment in comments:
# only check up to line number MAX_LINES
if comment.line_number() > args.max_lines:
break
try:
year = extract_year_from_espressif_notice(comment.text())
except NotFound:
pass
else:
return (year, comment.line_number())
raise NotFound('Old Espressif header')
def testPartialRatioUnicodeString(self):
s1 = "\u00C1"
s2 = "ABCD"
score = fuzz.partial_ratio(s1, s2)
self.assertEqual(0, score)
def testEmptyStringsScore100(self):
self.assertEqual(fuzz.ratio("", ""), 100)
self.assertEqual(fuzz.partial_ratio("", ""), 100)
def testPartialRatio(self):
self.assertEqual(fuzz.partial_ratio(self.s1, self.s3), 100)
# -*- coding:utf-8 -*-
"""
参考 https://github.com/seatgeek/thefuzz
"""
__author__ = "aaron.qiu"
from pprint import pprint
from thefuzz import fuzz
from thefuzz import process
if __name__ == '__main__':
pprint(fuzz.ratio("this is a test", "this is a test!"))
pprint(fuzz.partial_ratio("this is a test", "this is a test!"))
pprint(fuzz.ratio("fuzzy wuzzy was a bear", "wuzzy fuzzy was a bear"))
pprint(
fuzz.token_sort_ratio("fuzzy wuzzy was a bear",
"wuzzy fuzzy was a bear"))
pprint(fuzz.token_sort_ratio("fuzzy was a bear", "fuzzy fuzzy was a bear"))
pprint(fuzz.token_set_ratio("fuzzy was a bear", "fuzzy fuzzy was a bear"))
choices = [
"Atlanta Falcons", "New York Jets", "New York Giants", "Dallas Cowboys"
]
pprint(process.extract("new york jets", choices, limit=2))
pprint(process.extractOne("cowboys", choices))
songs = "/data/soft"
pprint(process.extractOne("System of a down - Hypnotize - apache", songs))
process.extractOne("System of a down - Hypnotize - Heroin",
songs,
scorer=fuzz.token_sort_ratio)