CloneHunter Report

_select_compare

src/clonehunter/reporting/html_reporter.py:147-151

_select_compare

src/clonehunter/reporting/json_reporter.py:65-69

0.962

5 duplicated lines

	Function A		Function B
147	def _select_compare(matches: list[CandidateMatch]) -> dict[str, object] \| None:	65	def _select_compare(matches: list[CandidateMatch]) -> dict[str, object] \| None:
148	compare = select_compare(matches)	66	compare = select_compare(matches)
149	if compare is None:	67	if compare is None:
150	return None	68	return None
151	return _compare_payload(compare, matches)	69	return _serialize_evidence(compare)

_merge_spans

src/clonehunter/reporting/html_reporter.py:339-350

_covered_lines

src/clonehunter/similarity/rollup.py:152-162

0.921

11 duplicated lines

	Function A		Function B
339	def _merge_spans(spans: list[tuple[int, int]]) -> list[tuple[int, int]]:	152	def _covered_lines(spans: list[tuple[int, int]]) -> int:
340	if not spans:	153	if not spans:
341	return []	154	return 0
342	merged: list[tuple[int, int]] = []	155	merged: list[list[int]] = []
343	for start, end in sorted(spans):	156	for start, end in sorted(spans):
344	if not merged or start > merged[-1][1] + 1:	157	if not merged or start > merged[-1][1] + 1:
345	merged.append((start, end))	158	merged.append([start, end])
346	continue	159	continue
347	prev_start, prev_end = merged[-1]	160	if end > merged[-1][1]:
348	if end > prev_end:	161	merged[-1][1] = end
349	merged[-1] = (prev_start, end)	162	return sum((end - start + 1 for start, end in merged))
350	return merged

_Embedder.embed

src/clonehunter/core/pipeline.py:32-32

Embedder.embed

src/clonehunter/model/interfaces.py:39-39

1.000

1 duplicated lines

	Function A		Function B
32	def embed(self, snippets: list[SnippetRef]) -> list[Embedding]: ...	39	def embed(self, snippets: list[SnippetRef]) -> list[Embedding]: ...

_Embedder.dim

src/clonehunter/core/pipeline.py:35-35

Embedder.dim

src/clonehunter/model/interfaces.py:36-36

1.000

1 duplicated lines

	Function A		Function B
35	def dim(self) -> int: ...	36	def dim(self) -> int: ...

test_func_threshold_edge

tests/test_threshold_edges.py:43-48

test_exp_threshold_edge

tests/test_threshold_edges.py:90-95

0.943

6 duplicated lines

	Function A		Function B
43	def test_func_threshold_edge():	90	def test_exp_threshold_edge():
44	thresholds = Thresholds(func=0.95, win=0.9, exp=0.9, min_window_hits=2, lexical_min_ratio=0.0)	91	thresholds = Thresholds(func=0.95, win=0.9, exp=0.9, min_window_hits=2, lexical_min_ratio=0.0)
45	at = rollup_findings([_match('FUNC', 0.95)], thresholds)	92	at = rollup_findings([_match('EXP', 0.9)], thresholds)
46	below = rollup_findings([_match('FUNC', 0.9499)], thresholds)	93	below = rollup_findings([_match('EXP', 0.8999)], thresholds)
47	assert at	94	assert at
48	assert not below	95	assert not below

test_win_threshold_edge

tests/test_threshold_edges.py:51-87

test_min_window_hits_edge

tests/test_threshold_edges.py:98-122

0.963

25 duplicated lines

	Function A		Function B
51	def test_win_threshold_edge():	98	def test_min_window_hits_edge():
52	thresholds = Thresholds(func=0.95, win=0.9, exp=0.9, min_window_hits=2, lexical_min_ratio=0.0)	99	thresholds = Thresholds(func=0.95, win=0.9, exp=0.9, min_window_hits=2, lexical_min_ratio=0.0)
53	file = FileRef(path='x.py', content_hash='h', language='python')	100	file = FileRef(path='x.py', content_hash='h', language='python')
54	fn_a = FunctionRef(file=file, qualified_name='a', start_line=1, end_line=20, code='pass', code_hash='a')	101	fn_a = FunctionRef(file=file, qualified_name='a', start_line=1, end_line=20, code='pass', code_hash='a')
55	fn_b = FunctionRef(file=file, qualified_name='b', start_line=30, end_line=50, code='pass', code_hash='b')	102	fn_b = FunctionRef(file=file, qualified_name='b', start_line=30, end_line=50, code='pass', code_hash='b')
56	a1 = SnippetRef(kind='WIN', function=fn_a, start_line=1, end_line=3, text='a1', snippet_hash='a1')	103	a1 = SnippetRef(kind='WIN', function=fn_a, start_line=1, end_line=3, text='a1', snippet_hash='a1')
57	b1 = SnippetRef(kind='WIN', function=fn_b, start_line=30, end_line=32, text='b1', snippet_hash='b1')	104	b1 = SnippetRef(kind='WIN', function=fn_b, start_line=30, end_line=32, text='b1', snippet_hash='b1')
58	a2 = SnippetRef(kind='WIN', function=fn_a, start_line=4, end_line=6, text='a2', snippet_hash='a2')	105	a2 = SnippetRef(kind='WIN', function=fn_a, start_line=4, end_line=6, text='a2', snippet_hash='a2')
59	b2 = SnippetRef(kind='WIN', function=fn_b, start_line=33, end_line=35, text='b2', snippet_hash='b2')	106	b2 = SnippetRef(kind='WIN', function=fn_b, start_line=33, end_line=35, text='b2', snippet_hash='b2')
60	at = rollup_findings([CandidateMatch(snippet_a=a1, snippet_b=b1, similarity=0.9, evidence=''), CandidateMatch(snippet_a=a2, snippet_b=b2, similarity=0.9, evidence='')], thresholds)	107	m1 = CandidateMatch(snippet_a=a1, snippet_b=b1, similarity=0.95, evidence='')
61	below = rollup_findings([CandidateMatch(snippet_a=a1, snippet_b=b1, similarity=0.8999, evidence=''), CandidateMatch(snippet_a=a2, snippet_b=b2, similarity=0.8999, evidence='')], thresholds)	108	m2 = CandidateMatch(snippet_a=a2, snippet_b=b2, similarity=0.95, evidence='')
62	assert at	109	findings = rollup_findings([m1, m2], thresholds)
63	assert below	110	assert findings

test_expansion_generates_snippet

tests/test_expansion.py:6-10

test_expansion_respects_max_chars

tests/test_expansion.py:22-26

0.924

5 duplicated lines

	Function A		Function B
6	def test_expansion_generates_snippet():	22	def test_expansion_respects_max_chars():
7	files = collect_files(['fixtures/tiny_repo'], ['*/.py'], [])	23	files = collect_files(['fixtures/tiny_repo'], ['*/.py'], [])
8	functions = [fn for file in files for fn in extract_functions(file)]	24	functions = [fn for file in files for fn in extract_functions(file)]
9	snippets = expand_calls(functions, ExpansionParams(enabled=True, depth=1, max_chars=10000))	25	snippets = expand_calls(functions, ExpansionParams(enabled=True, depth=1, max_chars=1))
10	assert any((snippet.kind == 'EXP' for snippet in snippets))	26	assert snippets == []

test_diff_end_to_end

tests/test_diff_e2e.py:8-83

test_cli_diff_command

tests/test_cli_entrypoints.py:31-82

0.962

52 duplicated lines

	Function A		Function B
	<23 lines not shown>		<1 lines not shown>
31	def test_cli_diff_command(tmp_path: Path):	32	)
32	repo = tmp_path / 'repo'	33	subprocess.check_call(["git", "init"], cwd=repo)
33	repo.mkdir()	34	subprocess.check_call(["git", "config", "user.email", "test@example.com"], cwd=repo)
34	(repo / 'a.py').write_text('\n\ndef add(nums):\n total = 0\n for n in nums:\n total += n\n return total\n', encoding='utf-8')	35	subprocess.check_call(["git", "config", "user.name", "Test User"], cwd=repo)
35	subprocess.check_call(['git', 'init'], cwd=repo)	36	subprocess.check_call(["git", "add", "a.py", "b.py"], cwd=repo)
36	subprocess.check_call(['git', 'config', 'user.email', 'test@example.com'], cwd=repo)	37	subprocess.check_call(["git", "commit", "-m", "init"], cwd=repo)
37	subprocess.check_call(['git', 'config', 'user.name', 'Test User'], cwd=repo)	38	(repo / "a.py").write_text(
38	subprocess.check_call(['git', 'add', 'a.py'], cwd=repo)	39	"""
39	subprocess.check_call(['git', 'commit', '-m', 'init'], cwd=repo)	40	def add(nums):
40	(repo / 'a.py').write_text('\n\ndef add(nums):\n total = 0\n for n in nums:\n total += n\n return total\n\n\ndef add_copy(values):\n total = 0\n for n in values:\n total += n\n return total\n', encoding='utf-8')	41	total = 0
41	out = tmp_path / 'diff.json'	42	for n in nums:
42	cmd = [sys.executable, '-m', 'clonehunter', 'diff', '--base', 'HEAD', '--format', 'json', '--out', str(out)]	43	total += n
43	subprocess.check_call(cmd, cwd=repo, env=_env())	44	return total
44	assert out.exists()	45	def add_copy(values):
		46	total = 0
		47	for n in values:
		48	total += n
		49	return total
		50	""",
		51	encoding="utf-8",
		52	)
		53	out = tmp_path / "diff.json"
		54	env = os.environ.copy()
		55	env["PYTHONPATH"] = str(Path(__file__).resolve().parents[1] / "src")
		56	env["CLONEHUNTER_EMBEDDER"] = "stub"
		57	cmd = [
		58	sys.executable,
		59	"-m",
		60	"clonehunter",
		61	"diff",
		62	"--base",
		63	"HEAD",
		64	"--format",
		65	"json",
			<11 lines not shown>

test_pipeline_non_python_implicit_windows_only

tests/test_pipeline_smoke.py:15-44

test_pipeline_non_python_allows_cross_file_types

tests/test_pipeline_smoke.py:47-72

0.949

26 duplicated lines

	Function A		Function B
15	def test_pipeline_non_python_implicit_windows_only(tmp_path: Path) -> None:	47	def test_pipeline_non_python_allows_cross_file_types(tmp_path: Path) -> None:
16	repo = tmp_path / 'repo'	48	repo = tmp_path / 'repo'
17	repo.mkdir()	49	repo.mkdir()
18	code = 'function add(a, b) {\n return a + b;\n}\n'	50	code = 'function add(a, b) {\n return a + b;\n}\n'
19	(repo / 'a.js').write_text(code, encoding='utf-8')	51	(repo / 'a.js').write_text(code, encoding='utf-8')
20	(repo / 'b.js').write_text(code, encoding='utf-8')	52	(repo / 'b.ts').write_text(code, encoding='utf-8')
21	result = run_pipeline([str(repo)], CloneHunterConfig(include_globs=['*/.js'], exclude_globs=[], embedder=EmbedderConfig(name='stub'), windows=WindowConfig(window_lines=3, stride_lines=1, min_nonempty=1), thresholds=Thresholds(func=0.99, win=0.8, exp=0.99, min_window_hits=1, lexical_min_ratio=0.0, lexical_weight=0.3)))	53	result = run_pipeline([str(repo)], CloneHunterConfig(include_globs=['*/.js', '*/.ts'], exclude_globs=[], embedder=EmbedderConfig(name='stub'), windows=WindowConfig(window_lines=3, stride_lines=1, min_nonempty=1), thresholds=Thresholds(func=0.99, win=0.8, exp=0.99, min_window_hits=1, lexical_min_ratio=0.0, lexical_weight=0.3)))
22	assert result.stats.file_count == 2	54	assert result.stats.file_count == 2
23	assert result.stats.function_count == 0
24	assert result.stats.finding_count >= 1	55	assert result.stats.finding_count >= 1
25	finding = result.findings[0]
26	assert finding.function_a.qualified_name != '<file>'
27	assert finding.function_b.qualified_name != '<file>'

test_rollup_min_window_hits

tests/test_rollup.py:6-34

test_rollup_applies_lexical_filter

tests/test_rollup.py:109-144

0.927

29 duplicated lines

	Function A		Function B
6	def test_rollup_min_window_hits():	109	def test_rollup_applies_lexical_filter() -> None:
7	file = FileRef(path='x.py', content_hash='h', language='python')	110	file = FileRef(path='x.py', content_hash='h', language='python')
8	fn_a = FunctionRef(file=file, qualified_name='a', start_line=1, end_line=5, code='pass', code_hash='a')	111	fn_a = FunctionRef(file=file, qualified_name='a', start_line=1, end_line=5, code='pass', code_hash='a')
9	fn_b = FunctionRef(file=file, qualified_name='b', start_line=10, end_line=14, code='pass', code_hash='b')	112	fn_b = FunctionRef(file=file, qualified_name='b', start_line=10, end_line=14, code='pass', code_hash='b')
10	a1 = SnippetRef(kind='WIN', function=fn_a, start_line=1, end_line=3, text='a1', snippet_hash='a1')	113	a = SnippetRef(kind='WIN', function=fn_a, start_line=1, end_line=3, text='def alpha():\n return 1', snippet_hash='a1')
11	b1 = SnippetRef(kind='WIN', function=fn_b, start_line=10, end_line=12, text='b1', snippet_hash='b1')	114	b = SnippetRef(kind='WIN', function=fn_b, start_line=10, end_line=12, text='def beta():\n return 2', snippet_hash='b1')
12	a2 = SnippetRef(kind='WIN', function=fn_a, start_line=2, end_line=4, text='a2', snippet_hash='a2')	115	match = CandidateMatch(snippet_a=a, snippet_b=b, similarity=0.99, evidence='')
13	b2 = SnippetRef(kind='WIN', function=fn_b, start_line=11, end_line=13, text='b2', snippet_hash='b2')	116	findings = rollup_findings([match], Thresholds(func=0.9, win=0.9, exp=0.9, min_window_hits=1, lexical_min_ratio=0.6))
14	matches = [CandidateMatch(snippet_a=a1, snippet_b=b1, similarity=0.5, evidence=''), CandidateMatch(snippet_a=a2, snippet_b=b2, similarity=0.5, evidence='')]	117	assert findings == []
15	findings = rollup_findings(matches, Thresholds(func=0.9, win=0.9, exp=0.9, min_window_hits=2, lexical_min_ratio=0.0))
16	assert findings

test_rollup_filters_overlapping_windows_same_function

tests/test_rollup.py:37-46

test_rollup_drops_identical_windows_same_function

tests/test_rollup.py:49-58

0.961

10 duplicated lines

	Function A		Function B
37	def test_rollup_filters_overlapping_windows_same_function():	49	def test_rollup_drops_identical_windows_same_function() -> None:
38	file = FileRef(path='x.py', content_hash='h', language='python')	50	file = FileRef(path='x.py', content_hash='h', language='python')
39	fn = FunctionRef(file=file, qualified_name='f', start_line=1, end_line=10, code='pass', code_hash='c')	51	fn = FunctionRef(file=file, qualified_name='f', start_line=1, end_line=30, code='pass', code_hash='c')
40	a = SnippetRef(kind='WIN', function=fn, start_line=1, end_line=5, text='a', snippet_hash='a')	52	a = SnippetRef(kind='WIN', function=fn, start_line=5, end_line=24, text='a', snippet_hash='a')
41	b = SnippetRef(kind='WIN', function=fn, start_line=4, end_line=8, text='b', snippet_hash='b')	53	b = SnippetRef(kind='WIN', function=fn, start_line=5, end_line=24, text='b', snippet_hash='b')
42	match = CandidateMatch(snippet_a=a, snippet_b=b, similarity=1.0, evidence='')	54	match = CandidateMatch(snippet_a=a, snippet_b=b, similarity=1.0, evidence='')
43	findings = rollup_findings([match], Thresholds(func=0.9, win=0.9, exp=0.9, min_window_hits=1))	55	findings = rollup_findings([match], Thresholds(func=0.9, win=0.9, exp=0.9, min_window_hits=1))
44	assert findings == []	56	assert findings == []

test_rollup_filters_overlapping_windows_same_function

tests/test_rollup.py:37-46

test_rollup_drops_identical_func_self_match

tests/test_rollup.py:61-70

0.970

10 duplicated lines

	Function A		Function B
37	def test_rollup_filters_overlapping_windows_same_function():	61	def test_rollup_drops_identical_func_self_match() -> None:
38	file = FileRef(path='x.py', content_hash='h', language='python')	62	file = FileRef(path='x.py', content_hash='h', language='python')
39	fn = FunctionRef(file=file, qualified_name='f', start_line=1, end_line=10, code='pass', code_hash='c')	63	fn = FunctionRef(file=file, qualified_name='f', start_line=1, end_line=10, code='pass', code_hash='c')
40	a = SnippetRef(kind='WIN', function=fn, start_line=1, end_line=5, text='a', snippet_hash='a')	64	a = SnippetRef(kind='FUNC', function=fn, start_line=1, end_line=10, text='a', snippet_hash='a')
41	b = SnippetRef(kind='WIN', function=fn, start_line=4, end_line=8, text='b', snippet_hash='b')	65	b = SnippetRef(kind='FUNC', function=fn, start_line=1, end_line=10, text='b', snippet_hash='b')
42	match = CandidateMatch(snippet_a=a, snippet_b=b, similarity=1.0, evidence='')	66	match = CandidateMatch(snippet_a=a, snippet_b=b, similarity=1.0, evidence='')
43	findings = rollup_findings([match], Thresholds(func=0.9, win=0.9, exp=0.9, min_window_hits=1))	67	findings = rollup_findings([match], Thresholds(func=0.9, win=0.9, exp=0.9, min_window_hits=1))
44	assert findings == []	68	assert findings == []

test_rollup_filters_overlapping_windows_same_function

tests/test_rollup.py:37-46

test_rollup_drops_overlapping_func_win_same_function

tests/test_rollup.py:73-84

0.938

10 duplicated lines

	Function A		Function B
37	def test_rollup_filters_overlapping_windows_same_function():	73	def test_rollup_drops_overlapping_func_win_same_function() -> None:
38	file = FileRef(path='x.py', content_hash='h', language='python')	74	file = FileRef(path='x.py', content_hash='h', language='python')
39	fn = FunctionRef(file=file, qualified_name='f', start_line=1, end_line=10, code='pass', code_hash='c')	75	fn = FunctionRef(file=file, qualified_name='f', start_line=1, end_line=30, code='pass', code_hash='c')
40	a = SnippetRef(kind='WIN', function=fn, start_line=1, end_line=5, text='a', snippet_hash='a')	76	func = SnippetRef(kind='FUNC', function=fn, start_line=1, end_line=30, text='f', snippet_hash='f')
41	b = SnippetRef(kind='WIN', function=fn, start_line=4, end_line=8, text='b', snippet_hash='b')	77	win = SnippetRef(kind='WIN', function=fn, start_line=5, end_line=24, text='w', snippet_hash='w')
42	match = CandidateMatch(snippet_a=a, snippet_b=b, similarity=1.0, evidence='')	78	match = CandidateMatch(snippet_a=func, snippet_b=win, similarity=1.0, evidence='')
43	findings = rollup_findings([match], Thresholds(func=0.9, win=0.9, exp=0.9, min_window_hits=1))	79	findings = rollup_findings([match], Thresholds(func=0.9, win=0.9, exp=0.9, min_window_hits=1))
44	assert findings == []	80	assert findings == []

test_rollup_drops_identical_windows_same_function

tests/test_rollup.py:49-58

test_rollup_drops_identical_func_self_match

tests/test_rollup.py:61-70

0.970

10 duplicated lines

	Function A		Function B
49	def test_rollup_drops_identical_windows_same_function() -> None:	61	def test_rollup_drops_identical_func_self_match() -> None:
50	file = FileRef(path='x.py', content_hash='h', language='python')	62	file = FileRef(path='x.py', content_hash='h', language='python')
51	fn = FunctionRef(file=file, qualified_name='f', start_line=1, end_line=30, code='pass', code_hash='c')	63	fn = FunctionRef(file=file, qualified_name='f', start_line=1, end_line=10, code='pass', code_hash='c')
52	a = SnippetRef(kind='WIN', function=fn, start_line=5, end_line=24, text='a', snippet_hash='a')	64	a = SnippetRef(kind='FUNC', function=fn, start_line=1, end_line=10, text='a', snippet_hash='a')
53	b = SnippetRef(kind='WIN', function=fn, start_line=5, end_line=24, text='b', snippet_hash='b')	65	b = SnippetRef(kind='FUNC', function=fn, start_line=1, end_line=10, text='b', snippet_hash='b')
54	match = CandidateMatch(snippet_a=a, snippet_b=b, similarity=1.0, evidence='')	66	match = CandidateMatch(snippet_a=a, snippet_b=b, similarity=1.0, evidence='')
55	findings = rollup_findings([match], Thresholds(func=0.9, win=0.9, exp=0.9, min_window_hits=1))	67	findings = rollup_findings([match], Thresholds(func=0.9, win=0.9, exp=0.9, min_window_hits=1))
56	assert findings == []	68	assert findings == []

test_rollup_drops_identical_windows_same_function

tests/test_rollup.py:49-58

test_rollup_drops_overlapping_func_win_same_function

tests/test_rollup.py:73-84

0.970

10 duplicated lines

	Function A		Function B
49	def test_rollup_drops_identical_windows_same_function() -> None:	73	def test_rollup_drops_overlapping_func_win_same_function() -> None:
50	file = FileRef(path='x.py', content_hash='h', language='python')	74	file = FileRef(path='x.py', content_hash='h', language='python')
51	fn = FunctionRef(file=file, qualified_name='f', start_line=1, end_line=30, code='pass', code_hash='c')	75	fn = FunctionRef(file=file, qualified_name='f', start_line=1, end_line=30, code='pass', code_hash='c')
52	a = SnippetRef(kind='WIN', function=fn, start_line=5, end_line=24, text='a', snippet_hash='a')	76	func = SnippetRef(kind='FUNC', function=fn, start_line=1, end_line=30, text='f', snippet_hash='f')
53	b = SnippetRef(kind='WIN', function=fn, start_line=5, end_line=24, text='b', snippet_hash='b')	77	win = SnippetRef(kind='WIN', function=fn, start_line=5, end_line=24, text='w', snippet_hash='w')
54	match = CandidateMatch(snippet_a=a, snippet_b=b, similarity=1.0, evidence='')	78	match = CandidateMatch(snippet_a=func, snippet_b=win, similarity=1.0, evidence='')
55	findings = rollup_findings([match], Thresholds(func=0.9, win=0.9, exp=0.9, min_window_hits=1))	79	findings = rollup_findings([match], Thresholds(func=0.9, win=0.9, exp=0.9, min_window_hits=1))
56	assert findings == []	80	assert findings == []

test_rollup_drops_identical_func_self_match

tests/test_rollup.py:61-70

test_rollup_drops_overlapping_func_win_same_function

tests/test_rollup.py:73-84

0.947

10 duplicated lines

	Function A		Function B
61	def test_rollup_drops_identical_func_self_match() -> None:	73	def test_rollup_drops_overlapping_func_win_same_function() -> None:
62	file = FileRef(path='x.py', content_hash='h', language='python')	74	file = FileRef(path='x.py', content_hash='h', language='python')
63	fn = FunctionRef(file=file, qualified_name='f', start_line=1, end_line=10, code='pass', code_hash='c')	75	fn = FunctionRef(file=file, qualified_name='f', start_line=1, end_line=30, code='pass', code_hash='c')
64	a = SnippetRef(kind='FUNC', function=fn, start_line=1, end_line=10, text='a', snippet_hash='a')	76	func = SnippetRef(kind='FUNC', function=fn, start_line=1, end_line=30, text='f', snippet_hash='f')
65	b = SnippetRef(kind='FUNC', function=fn, start_line=1, end_line=10, text='b', snippet_hash='b')	77	win = SnippetRef(kind='WIN', function=fn, start_line=5, end_line=24, text='w', snippet_hash='w')
66	match = CandidateMatch(snippet_a=a, snippet_b=b, similarity=1.0, evidence='')	78	match = CandidateMatch(snippet_a=func, snippet_b=win, similarity=1.0, evidence='')
67	findings = rollup_findings([match], Thresholds(func=0.9, win=0.9, exp=0.9, min_window_hits=1))	79	findings = rollup_findings([match], Thresholds(func=0.9, win=0.9, exp=0.9, min_window_hits=1))
68	assert findings == []	80	assert findings == []

test_rollup_drops_identical_func_self_match

tests/test_rollup.py:61-70

test_rollup_drops_overlapping_functions_same_file

tests/test_rollup.py:87-106

0.915

10 duplicated lines

	Function A		Function B
61	def test_rollup_drops_identical_func_self_match() -> None:	87	def test_rollup_drops_overlapping_functions_same_file() -> None:
62	file = FileRef(path='x.py', content_hash='h', language='python')	88	file = FileRef(path='x.py', content_hash='h', language='python')
63	fn = FunctionRef(file=file, qualified_name='f', start_line=1, end_line=10, code='pass', code_hash='c')	89	fn_outer = FunctionRef(file=file, qualified_name='outer', start_line=1, end_line=40, code='pass', code_hash='o')
64	a = SnippetRef(kind='FUNC', function=fn, start_line=1, end_line=10, text='a', snippet_hash='a')	90	fn_inner = FunctionRef(file=file, qualified_name='inner', start_line=10, end_line=20, code='pass', code_hash='i')
65	b = SnippetRef(kind='FUNC', function=fn, start_line=1, end_line=10, text='b', snippet_hash='b')	91	outer = SnippetRef(kind='FUNC', function=fn_outer, start_line=1, end_line=40, text='o', snippet_hash='o')
66	match = CandidateMatch(snippet_a=a, snippet_b=b, similarity=1.0, evidence='')	92	inner = SnippetRef(kind='FUNC', function=fn_inner, start_line=10, end_line=20, text='i', snippet_hash='i')
67	findings = rollup_findings([match], Thresholds(func=0.9, win=0.9, exp=0.9, min_window_hits=1))	93	match = CandidateMatch(snippet_a=outer, snippet_b=inner, similarity=1.0, evidence='')
		94	findings = rollup_findings([match], Thresholds(func=0.9, win=0.9, exp=0.9, min_window_hits=1, lexical_min_ratio=0.0))
68	assert findings == []	95	assert findings == []

_finding

tests/test_clustering.py:5-26

_sample_result

tests/test_reporters_html_sarif.py:17-44

0.934

22 duplicated lines

	Function A		Function B
5	def _finding(a: str, b: str) -> Finding:	17	def _sample_result() -> ScanResult:
6	file_a = FileRef(path=f'{a}.py', content_hash='h', language='python')	18	file_a = FileRef(path='fixtures/tiny_repo/a.py', content_hash='h', language='python')
7	file_b = FileRef(path=f'{b}.py', content_hash='h', language='python')	19	file_b = FileRef(path='fixtures/tiny_repo/b.py', content_hash='h', language='python')
8	fn_a = FunctionRef(file=file_a, qualified_name=a, start_line=1, end_line=2, code='pass', code_hash=a)	20	fn_a = FunctionRef(file=file_a, qualified_name='a', start_line=1, end_line=2, code='pass', code_hash='a')
9	fn_b = FunctionRef(file=file_b, qualified_name=b, start_line=1, end_line=2, code='pass', code_hash=b)	21	fn_b = FunctionRef(file=file_b, qualified_name='b', start_line=10, end_line=12, code='pass', code_hash='b')
10	snip = SnippetRef(kind='FUNC', function=fn_a, start_line=1, end_line=2, text='pass', snippet_hash=a)	22	snip = SnippetRef(kind='FUNC', function=fn_a, start_line=1, end_line=2, text='pass', snippet_hash='s')
11	match = CandidateMatch(snippet_a=snip, snippet_b=snip, similarity=1.0, evidence='')	23	match = CandidateMatch(snippet_a=snip, snippet_b=snip, similarity=1.0, evidence='')
12	return Finding(function_a=fn_a, function_b=fn_b, score=1.0, duplicated_lines=2, evidence=[match], reasons=['func'], metadata={})	24	finding = Finding(function_a=fn_a, function_b=fn_b, score=1.0, duplicated_lines=2, evidence=[match], reasons=['func'], metadata={})
		25	return ScanResult(findings=[finding], stats=ScanStats(0, 0, 0, 0, 1, 0, 0), config_snapshot={}, timing={})

normalize_customer_name

fixtures/demo_monorepo/orders_pipeline.py:14-16

normalize_client_name

fixtures/demo_monorepo/invoices_pipeline.py:14-16

0.960

3 duplicated lines

	Function A		Function B
14	def normalize_customer_name(raw: str) -> str:	14	def normalize_client_name(raw: str) -> str:
15	cleaned = ' '.join((part for part in raw.strip().split(' ') if part))	15	cleaned = ' '.join((part for part in raw.strip().split(' ') if part))
16	return cleaned.title()	16	return cleaned.title()

summarize_totals

fixtures/demo_monorepo/orders_pipeline.py:76-85

summarize_totals

fixtures/demo_monorepo/invoices_pipeline.py:76-85

0.966

10 duplicated lines

	Function A		Function B
76	def summarize_totals(payload: dict[str, object]) -> str:	76	def summarize_totals(payload: dict[str, object]) -> str:
77	subtotal = float(payload.get('subtotal', 0.0))	77	subtotal = float(payload.get('subtotal', 0.0))
78	discount = float(payload.get('discount', 0.0))	78	discount = float(payload.get('discount', 0.0))
79	tax = float(payload.get('tax', 0.0))	79	tax = float(payload.get('tax', 0.0))
80	shipping = float(payload.get('shipping', 0.0))	80	service_fee = float(payload.get('service_fee', 0.0))
81	total = float(payload.get('total', 0.0))	81	total = float(payload.get('total', 0.0))
82	return f'subtotal=${subtotal:,.2f}; discount=${discount:,.2f}; tax=${tax:,.2f}; shipping=${shipping:,.2f}; total=${total:,.2f}'	82	return f'subtotal=${subtotal:,.2f}; discount=${discount:,.2f}; tax=${tax:,.2f}; service_fee=${service_fee:,.2f}; total=${total:,.2f}'

build_monthly_breakdown

fixtures/demo_monorepo/orders_pipeline.py:88-124

build_monthly_breakdown

fixtures/demo_monorepo/invoices_pipeline.py:88-129

0.935

37 duplicated lines

	Function A		Function B
88	def build_monthly_breakdown(daily_totals: list[float], weekly_marketing_spend: list[float], fixed_cost: float) -> dict[str, object]:	88	def build_monthly_breakdown(daily_totals: list[float], weekly_marketing_spend: list[float], fixed_cost: float) -> dict[str, object]:
89	weeks: list[dict[str, object]] = []	89	weeks: list[dict[str, object]] = []
90	monthly_revenue = 0.0	90	monthly_revenue = 0.0
91	monthly_cost = 0.0	91	monthly_cost = 0.0
92	for idx in range(4):	92	for idx in range(4):
93	start = idx * 7	93	start = idx * 7
94	end = min(start + 7, len(daily_totals))	94	end = min(start + 7, len(daily_totals))
95	revenue = round(sum(daily_totals[start:end]), 2)	95	revenue = round(sum(daily_totals[start:end]), 2)
96	marketing = round(weekly_marketing_spend[idx] if idx < len(weekly_marketing_spend) else 0.0, 2)	96	outreach = round(weekly_marketing_spend[idx] if idx < len(weekly_marketing_spend) else 0.0, 2)
97	fixed = round(fixed_cost, 2)	97	fixed = round(fixed_cost, 2)
98	cost = round(marketing + fixed, 2)	98	support_overhead = 15.0 if idx == 3 else 0.0
		99	cost = round(outreach + fixed + support_overhead, 2)
99	margin = round(revenue - cost, 2)	100	margin = round(revenue - cost, 2)
100	margin_pct = round(margin / revenue * 100, 2) if revenue > 0 else 0.0	101	margin_pct = round(margin / revenue * 100, 2) if revenue > 0 else 0.0
		102	margin_pct = min(margin_pct, 95.0)
101	monthly_revenue += revenue	103	monthly_revenue += revenue
102	monthly_cost += cost	104	monthly_cost += cost
103	weeks.append({'week': idx + 1, 'revenue': revenue, 'cost': cost, 'margin': margin, 'margin_pct': margin_pct})	105	weeks.append({'week': idx + 1, 'revenue': revenue, 'cost': cost, 'margin': margin, 'margin_pct': margin_pct, 'warning': 'low_margin' if margin_pct < 20 else ''})
104	monthly_margin = round(monthly_revenue - monthly_cost, 2)	106	monthly_margin = round(monthly_revenue - monthly_cost, 2)
105	return {'weeks': weeks, 'monthly_revenue': round(monthly_revenue, 2), 'monthly_cost': round(monthly_cost, 2), 'monthly_margin': monthly_margin, 'profitable': monthly_margin > 0}	107	return {'weeks': weeks, 'monthly_revenue': round(monthly_revenue, 2), 'monthly_cost': round(monthly_cost, 2), 'monthly_margin': monthly_margin, 'net_positive': monthly_margin > 0}

compile_weekly_metrics

fixtures/demo_monorepo/orders_pipeline.py:127-163

compile_weekly_metrics

fixtures/demo_monorepo/invoices_pipeline.py:132-170

0.994

37 duplicated lines

Accumulator.total

fixtures/tiny_repo/classes.py:2-6

helper_sum

fixtures/tiny_repo/helpers.py:1-5

0.933

5 duplicated lines

	Function A		Function B
2	def total(self, items):	1	def helper_sum(items):
3	total = 0	2	total = 0
4	for item in items:	3	for item in items:
5	total += item	4	total += item
6	return total	5	return total

order_form_helpers.ts

fixtures/demo_monorepo/order_form_helpers.ts:1-64

invoice_form_helpers.ts

fixtures/demo_monorepo/invoice_form_helpers.ts:1-64

1.000

64 duplicated lines

	Function A		Function B
	<18 lines not shown>		<18 lines not shown>
19	const trimmedEmail = email.trim();	19	const trimmedEmail = email.trim();
20	const trimmedPostal = postalCode.trim();	20	const trimmedPostal = postalCode.trim();
21	if (!trimmedName) {	21	if (!trimmedName) {
22	return { ok: false, message: "Name is required" };	22	return { ok: false, message: "Name is required" };
23	}	23	}
24	if (trimmedName.length < 2) {	24	if (trimmedName.length < 2) {
25	return { ok: false, message: "Name must be at least 2 characters" };	25	return { ok: false, message: "Name must be at least 2 characters" };
26	}	26	}
27	if (!trimmedEmail) {	27	if (!trimmedEmail) {
28	return { ok: false, message: "Email is required" };	28	return { ok: false, message: "Email is required" };
29	}	29	}
30	if (!trimmedEmail.includes("@") \|\| !trimmedEmail.includes(".")) {	30	if (!trimmedEmail.includes("@") \|\| !trimmedEmail.includes(".")) {
31	return { ok: false, message: "Email format is invalid" };	31	return { ok: false, message: "Email format is invalid" };
32	}	32	}
33	if (!/^\d{5}$/.test(trimmedPostal)) {	33	if (!/^\d{5}$/.test(trimmedPostal)) {
34	return { ok: false, message: "Postal code must be 5 digits" };	34	return { ok: false, message: "Postal code must be 5 digits" };
35	}	35	}
36	return { ok: true, message: "" };	36	return { ok: true, message: "" };
37	}	37	}
38	export function buildFormTotals(items: FormItem[], discountPct: number): {	38	export function buildChargeTotals(charges: FormCharge[], discountPct: number): {
39	subtotal: number;	39	subtotal: number;
40	discount: number;	40	discount: number;
41	tax: number;	41	tax: number;
42	total: number;	42	total: number;
43	} {	43	} {
44	let subtotal = 0;	44	let subtotal = 0;
45	for (const item of items) {	45	for (const charge of charges) {
46	subtotal += item.quantity * item.unitPrice;	46	subtotal += charge.units * charge.rate;
47	}	47	}
48	const normalizedSubtotal = Math.round(subtotal * 100) / 100;	48	const normalizedSubtotal = Math.round(subtotal * 100) / 100;
49	const appliedDiscount = Math.round(normalizedSubtotal * Math.max(0, discountPct) * 100) / 100;	49	const appliedDiscount = Math.round(normalizedSubtotal * Math.max(0, discountPct) * 100) / 100;
50	const discountedSubtotal = Math.max(0, normalizedSubtotal - appliedDiscount);	50	const discountedSubtotal = Math.max(0, normalizedSubtotal - appliedDiscount);
51	const tax = Math.round(discountedSubtotal * 0.0825 * 100) / 100;	51	const tax = Math.round(discountedSubtotal * 0.0825 * 100) / 100;
52	const total = Math.round((discountedSubtotal + tax) * 100) / 100;	52	const total = Math.round((discountedSubtotal + tax) * 100) / 100;
53	return {	53	return {
	<6 lines not shown>		<6 lines not shown>

	Function A		Function B
127	def compile_weekly_metrics(daily_orders: list[int], daily_revenue: list[float], refund_counts: list[int]) -> dict[str, object]:	132	def compile_weekly_metrics(daily_orders: list[int], daily_revenue: list[float], refund_counts: list[int]) -> dict[str, object]:
128	weeks: list[dict[str, object]] = []	133	weeks: list[dict[str, object]] = []
129	for idx in range(4):	134	for idx in range(4):
130	start = idx * 7	135	start = idx * 7
131	end = min(start + 7, len(daily_orders))	136	end = min(start + 7, len(daily_orders))
132	order_count = sum(daily_orders[start:end])	137	order_count = sum(daily_orders[start:end])
133	revenue = round(sum(daily_revenue[start:end]), 2)	138	revenue = round(sum(daily_revenue[start:end]), 2)
134	refunds = sum(refund_counts[start:end])	139	refunds = sum(refund_counts[start:end])
135	fulfillment_rate = round((order_count - refunds) / order_count * 100, 2) if order_count else 0.0	140	fulfillment_rate = round((order_count - refunds) / order_count * 100, 2) if order_count else 0.0
136	avg_order_value = round(revenue / order_count, 2) if order_count else 0.0	141	avg_order_value = round(revenue / order_count, 2) if order_count else 0.0
137	weeks.append({'week': idx + 1, 'orders': int(order_count), 'revenue': revenue, 'refunds': int(refunds), 'fulfillment_rate': fulfillment_rate, 'avg_order_value': avg_order_value})	142	weeks.append({'week': idx + 1, 'orders': int(order_count), 'revenue': revenue, 'refunds': int(refunds), 'fulfillment_rate': fulfillment_rate, 'avg_order_value': avg_order_value})
138	total_orders = sum((int(row['orders']) for row in weeks))	143	total_orders = sum((int(row['orders']) for row in weeks))
139	total_revenue = round(sum((float(row['revenue']) for row in weeks)), 2)	144	total_revenue = round(sum((float(row['revenue']) for row in weeks)), 2)
140	total_refunds = sum((int(row['refunds']) for row in weeks))	145	total_refunds = sum((int(row['refunds']) for row in weeks))
141	net_orders = max(0, total_orders - total_refunds)	146	net_orders = max(0, total_orders - total_refunds)
142	return {'weeks': weeks, 'totals': {'orders': total_orders, 'revenue': total_revenue, 'refunds': total_refunds, 'net_orders': net_orders}}	147	adjusted_net = max(0, net_orders - 1)
		148	return {'weeks': weeks, 'totals': {'orders': total_orders, 'revenue': total_revenue, 'refunds': total_refunds, 'net_orders': adjusted_net}}