mirror of
https://github.com/zhayujie/chatgpt-on-wechat.git
synced 2026-07-17 11:07:11 +08:00
ed36ca99c0
The uniqueness guard counted occurrences via normalize_for_fuzzy_match, while fuzzy_find_text located matches with a whitespace-flexible regex, so the two could disagree. Extract the pattern builder as a single source of truth (_build_fuzzy_pattern) and add count_matches, which counts with the same exact-then-fuzzy strategy used to locate and replace. This is the optional follow-up suggested in the review of #2942. Adds regression tests for exact and fuzzy multi-match rejection.
50 lines
963 B
Python
50 lines
963 B
Python
from .truncate import (
|
|
truncate_head,
|
|
truncate_tail,
|
|
truncate_line,
|
|
format_size,
|
|
TruncationResult,
|
|
DEFAULT_MAX_LINES,
|
|
DEFAULT_MAX_BYTES,
|
|
GREP_MAX_LINE_LENGTH
|
|
)
|
|
|
|
from .diff import (
|
|
strip_bom,
|
|
detect_line_ending,
|
|
normalize_to_lf,
|
|
restore_line_endings,
|
|
normalize_for_fuzzy_match,
|
|
count_matches,
|
|
fuzzy_find_text,
|
|
generate_diff_string,
|
|
FuzzyMatchResult
|
|
)
|
|
|
|
from .url_safety import (
|
|
validate_url_safe,
|
|
assert_public_ip
|
|
)
|
|
|
|
__all__ = [
|
|
'truncate_head',
|
|
'truncate_tail',
|
|
'truncate_line',
|
|
'format_size',
|
|
'TruncationResult',
|
|
'DEFAULT_MAX_LINES',
|
|
'DEFAULT_MAX_BYTES',
|
|
'GREP_MAX_LINE_LENGTH',
|
|
'strip_bom',
|
|
'detect_line_ending',
|
|
'normalize_to_lf',
|
|
'restore_line_endings',
|
|
'normalize_for_fuzzy_match',
|
|
'count_matches',
|
|
'fuzzy_find_text',
|
|
'generate_diff_string',
|
|
'FuzzyMatchResult',
|
|
'validate_url_safe',
|
|
'assert_public_ip'
|
|
]
|