fix(edit): keep untouched lines intact on fuzzy match

The Edit tool falls back to a whitespace-tolerant fuzzy match when oldText does not match byte-for-byte. On a fuzzy hit it replaced text inside a whitespace-normalized copy of the whole file and wrote that copy back, so every untouched line lost its original indentation (runs of spaces/tabs collapsed to a single space). For indentation-sensitive files such as Python this silently corrupts the file.

Locate the fuzzy match in the original content with a whitespace-flexible regex and return offsets into that original content, so only the matched region is replaced. Adds regression tests.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
xiaweiwei67-stack
2026-07-07 16:50:16 +08:00
parent d531e14fbf
commit a94f4e3c18
2 changed files with 118 additions and 14 deletions

View File

@@ -111,20 +111,39 @@ def fuzzy_find_text(content: str, old_text: str) -> FuzzyMatchResult:
content_for_replacement=content
)
# Try fuzzy match
fuzzy_content = normalize_for_fuzzy_match(content)
fuzzy_old_text = normalize_for_fuzzy_match(old_text)
index = fuzzy_content.find(fuzzy_old_text)
if index != -1:
# Fuzzy match successful, use normalized content for replacement
return FuzzyMatchResult(
found=True,
index=index,
match_length=len(fuzzy_old_text),
content_for_replacement=fuzzy_content
)
# Fuzzy match: the exact substring was not found, most likely because the
# whitespace differs (indentation, spaces around operators, trailing
# spaces). Locate the region in the ORIGINAL content using a
# whitespace-flexible pattern and return offsets into that original
# content.
#
# This must NOT replace inside a whitespace-normalized copy of the file:
# doing so previously returned the normalized copy as
# content_for_replacement, which caused the whole file to be rewritten
# with collapsed indentation (every untouched line got reformatted).
stripped = old_text.strip('\n')
if stripped.strip():
line_patterns = []
for line in stripped.split('\n'):
tokens = line.split()
if tokens:
# Tolerate flexible indentation and any run of blanks between
# tokens, matching the leniency of the old normalized compare.
line_patterns.append(
r'[ \t]*' + r'[ \t]+'.join(re.escape(tok) for tok in tokens) + r'[ \t]*'
)
else:
line_patterns.append(r'[ \t]*')
pattern = '\n'.join(line_patterns)
match = re.search(pattern, content)
if match:
return FuzzyMatchResult(
found=True,
index=match.start(),
match_length=match.end() - match.start(),
content_for_replacement=content
)
# Not found
return FuzzyMatchResult(found=False)