fix(patch): harden V4A patch parser and fuzzy match — 9 correctness bugs
- Bug 1: replace read_file(limit=10000) with read_file_raw in _apply_update, preventing silent truncation of files >2000 lines and corruption of lines >2000 chars; add read_file_raw to FileOperations abstract interface and ShellFileOperations - Bug 2: split apply_v4a_operations into validate-then-apply phases; if any hunk fails validation, zero writes occur (was: continue after failure, leaving filesystem partially modified) - Bug 3: parse_v4a_patch now returns an error for begin-marker-with-no-ops, empty file paths, and moves missing a destination (was: always returned error=None) - Bug 4: raise strategy 7 (block anchor) single-candidate similarity threshold from 0.10 to 0.50, eliminating false-positive matches in repetitive code - Bug 5: add _strategy_unicode_normalized (new strategy 7) with position mapping via _build_orig_to_norm_map; smart quotes and em-dashes in LLM-generated patches now match via strategies 1-6 before falling through to fuzzy strategies - Bug 6: extend fuzzy_find_and_replace to return 4-tuple (content, count, error, strategy); update all 5 call sites across patch_parser.py, file_operations.py, and skill_manager_tool.py - Bug 7: guard in _apply_update returns error when addition-only context hint is ambiguous (>1 occurrences); validation phase errors on both 0 and >1 - Bug 8: _apply_delete returns error (not silent success) on missing file - Bug 9: _validate_operations checks source existence and destination absence for MOVE operations before any write occurs
This commit is contained in:
KUSH42
@@ -6,31 +6,31 @@ from tools.fuzzy_match import fuzzy_find_and_replace
|
||||
class TestExactMatch:
|
||||
def test_single_replacement(self):
|
||||
content = "hello world"
|
||||
new, count, err = fuzzy_find_and_replace(content, "hello", "hi")
|
||||
new, count, _, err = fuzzy_find_and_replace(content, "hello", "hi")
|
||||
assert err is None
|
||||
assert count == 1
|
||||
assert new == "hi world"
|
||||
|
||||
def test_no_match(self):
|
||||
content = "hello world"
|
||||
new, count, err = fuzzy_find_and_replace(content, "xyz", "abc")
|
||||
new, count, _, err = fuzzy_find_and_replace(content, "xyz", "abc")
|
||||
assert count == 0
|
||||
assert err is not None
|
||||
assert new == content
|
||||
|
||||
def test_empty_old_string(self):
|
||||
new, count, err = fuzzy_find_and_replace("abc", "", "x")
|
||||
new, count, _, err = fuzzy_find_and_replace("abc", "", "x")
|
||||
assert count == 0
|
||||
assert err is not None
|
||||
|
||||
def test_identical_strings(self):
|
||||
new, count, err = fuzzy_find_and_replace("abc", "abc", "abc")
|
||||
new, count, _, err = fuzzy_find_and_replace("abc", "abc", "abc")
|
||||
assert count == 0
|
||||
assert "identical" in err
|
||||
|
||||
def test_multiline_exact(self):
|
||||
content = "line1\nline2\nline3"
|
||||
new, count, err = fuzzy_find_and_replace(content, "line1\nline2", "replaced")
|
||||
new, count, _, err = fuzzy_find_and_replace(content, "line1\nline2", "replaced")
|
||||
assert err is None
|
||||
assert count == 1
|
||||
assert new == "replaced\nline3"
|
||||
@@ -39,7 +39,7 @@ class TestExactMatch:
|
||||
class TestWhitespaceDifference:
|
||||
def test_extra_spaces_match(self):
|
||||
content = "def foo( x, y ):"
|
||||
new, count, err = fuzzy_find_and_replace(content, "def foo( x, y ):", "def bar(x, y):")
|
||||
new, count, _, err = fuzzy_find_and_replace(content, "def foo( x, y ):", "def bar(x, y):")
|
||||
assert count == 1
|
||||
assert "bar" in new
|
||||
|
||||
@@ -47,7 +47,7 @@ class TestWhitespaceDifference:
|
||||
class TestIndentDifference:
|
||||
def test_different_indentation(self):
|
||||
content = " def foo():\n pass"
|
||||
new, count, err = fuzzy_find_and_replace(content, "def foo():\n pass", "def bar():\n return 1")
|
||||
new, count, _, err = fuzzy_find_and_replace(content, "def foo():\n pass", "def bar():\n return 1")
|
||||
assert count == 1
|
||||
assert "bar" in new
|
||||
|
||||
@@ -55,13 +55,96 @@ class TestIndentDifference:
|
||||
class TestReplaceAll:
|
||||
def test_multiple_matches_without_flag_errors(self):
|
||||
content = "aaa bbb aaa"
|
||||
new, count, err = fuzzy_find_and_replace(content, "aaa", "ccc", replace_all=False)
|
||||
new, count, _, err = fuzzy_find_and_replace(content, "aaa", "ccc", replace_all=False)
|
||||
assert count == 0
|
||||
assert "Found 2 matches" in err
|
||||
|
||||
def test_multiple_matches_with_flag(self):
|
||||
content = "aaa bbb aaa"
|
||||
new, count, err = fuzzy_find_and_replace(content, "aaa", "ccc", replace_all=True)
|
||||
new, count, _, err = fuzzy_find_and_replace(content, "aaa", "ccc", replace_all=True)
|
||||
assert err is None
|
||||
assert count == 2
|
||||
assert new == "ccc bbb ccc"
|
||||
|
||||
|
||||
class TestUnicodeNormalized:
|
||||
"""Tests for the unicode_normalized strategy (Bug 5)."""
|
||||
|
||||
def test_em_dash_matched(self):
|
||||
"""Em-dash in content should match ASCII '--' in pattern."""
|
||||
content = "return value\u2014fallback"
|
||||
new, count, strategy, err = fuzzy_find_and_replace(
|
||||
content, "return value--fallback", "return value or fallback"
|
||||
)
|
||||
assert count == 1, f"Expected match via unicode_normalized, got err={err}"
|
||||
assert strategy == "unicode_normalized"
|
||||
assert "return value or fallback" in new
|
||||
|
||||
def test_smart_quotes_matched(self):
|
||||
"""Smart double quotes in content should match straight quotes in pattern."""
|
||||
content = 'print(\u201chello\u201d)'
|
||||
new, count, strategy, err = fuzzy_find_and_replace(
|
||||
content, 'print("hello")', 'print("world")'
|
||||
)
|
||||
assert count == 1, f"Expected match via unicode_normalized, got err={err}"
|
||||
assert "world" in new
|
||||
|
||||
def test_no_unicode_skips_strategy(self):
|
||||
"""When content and pattern have no Unicode variants, strategy is skipped."""
|
||||
content = "hello world"
|
||||
# Should match via exact, not unicode_normalized
|
||||
new, count, strategy, err = fuzzy_find_and_replace(content, "hello", "hi")
|
||||
assert count == 1
|
||||
assert strategy == "exact"
|
||||
|
||||
|
||||
class TestBlockAnchorThreshold:
|
||||
"""Tests for the raised block_anchor threshold (Bug 4)."""
|
||||
|
||||
def test_high_similarity_matches(self):
|
||||
"""A block with >50% middle similarity should match."""
|
||||
content = "def foo():\n x = 1\n y = 2\n return x + y\n"
|
||||
pattern = "def foo():\n x = 1\n y = 9\n return x + y"
|
||||
new, count, strategy, err = fuzzy_find_and_replace(content, pattern, "def foo():\n return 0\n")
|
||||
# Should match via block_anchor or earlier strategy
|
||||
assert count == 1
|
||||
|
||||
def test_completely_different_middle_does_not_match(self):
|
||||
"""A block where only first+last lines match but middle is completely different
|
||||
should NOT match under the raised 0.50 threshold."""
|
||||
content = (
|
||||
"class Foo:\n"
|
||||
" completely = 'unrelated'\n"
|
||||
" content = 'here'\n"
|
||||
" nothing = 'in common'\n"
|
||||
" pass\n"
|
||||
)
|
||||
# Pattern has same first/last lines but completely different middle
|
||||
pattern = (
|
||||
"class Foo:\n"
|
||||
" x = 1\n"
|
||||
" y = 2\n"
|
||||
" z = 3\n"
|
||||
" pass"
|
||||
)
|
||||
new, count, strategy, err = fuzzy_find_and_replace(content, pattern, "replaced")
|
||||
# With threshold=0.50, this near-zero-similarity middle should not match
|
||||
assert count == 0, (
|
||||
f"Block with unrelated middle should not match under threshold=0.50, "
|
||||
f"but matched via strategy={strategy}"
|
||||
)
|
||||
|
||||
|
||||
class TestStrategyNameSurfaced:
|
||||
"""Tests for the strategy name in the 4-tuple return (Bug 6)."""
|
||||
|
||||
def test_exact_strategy_name(self):
|
||||
new, count, strategy, err = fuzzy_find_and_replace("hello", "hello", "world")
|
||||
assert strategy == "exact"
|
||||
assert count == 1
|
||||
|
||||
def test_failed_match_returns_none_strategy(self):
|
||||
new, count, strategy, err = fuzzy_find_and_replace("hello", "xyz", "world")
|
||||
assert count == 0
|
||||
assert strategy is None
|
||||
assert err is not None
|
||||
|
||||
Reference in New Issue
Block a user