projix 0.1.2__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
analysis_compat.py ADDED
@@ -0,0 +1,66 @@
1
+ """Keep full analysis configuration in workers and reconcile pinned TSX gaps."""
2
+ from concurrent.futures import ProcessPoolExecutor, as_completed
3
+ import hashlib
4
+ import multiprocessing as mp
5
+ from pathlib import Path
6
+
7
+
8
+ def configured_file(arguments):
9
+ from code2llm.core.file_analyzer import FileAnalyzer
10
+ path, name, config = arguments
11
+ return FileAnalyzer(config, None).analyze_file(path, name)
12
+
13
+
14
+ def parallel(self, files):
15
+ try:
16
+ context = mp.get_context('forkserver')
17
+ except ValueError:
18
+ context = None
19
+ results = []
20
+ workers = min(self.config.performance.get_workers(), len(files))
21
+ with ProcessPoolExecutor(max_workers=workers, mp_context=context) as executor:
22
+ futures = {executor.submit(configured_file, (path, name, self.config)): path for path, name in files}
23
+ for future in as_completed(futures):
24
+ try:
25
+ result = future.result()
26
+ if result:
27
+ results.append(result)
28
+ except Exception as error:
29
+ if self.config.verbose:
30
+ print(f'Error analyzing {futures[future]}: {error}')
31
+ return results
32
+
33
+
34
+ def install():
35
+ from code2llm.core.analyzer import ProjectAnalyzer
36
+ from tsx_compat import recover_file
37
+ from graph_compat import install as install_graph
38
+ install_graph()
39
+ if getattr(ProjectAnalyzer, '_project_analysis_full_config', False):
40
+ return
41
+ original = ProjectAnalyzer._run_analysis
42
+
43
+ def analyze(self, files):
44
+ results = original(self, files)
45
+ processed = {item.get('file') for item in results if item.get('module')}
46
+ notes = []
47
+ for path, module in files:
48
+ if path in processed or Path(path).suffix.lower() not in {'.tsx', '.jsx', '.js'}:
49
+ continue
50
+ try:
51
+ recovered = recover_file(self.config, path, module)
52
+ except (ValueError, OSError, UnicodeError):
53
+ continue
54
+ if recovered:
55
+ result, offsets = recovered
56
+ results.append(result)
57
+ notes.append({'path': path, 'kind': 'Pinned JSX/TSX grammar rejects valid plain-text ampersands',
58
+ 'source_sha256': hashlib.sha256(Path(path).read_bytes()).hexdigest(),
59
+ 'jsx_text_ampersand_byte_offsets': offsets, 'source_unchanged': True,
60
+ 'aggregation': 'Included before normal graph/metric aggregation'})
61
+ self._project_analysis_compatibility_notes = notes
62
+ return results
63
+
64
+ ProjectAnalyzer._analyze_parallel = parallel
65
+ ProjectAnalyzer._run_analysis = analyze
66
+ ProjectAnalyzer._project_analysis_full_config = True
graph_compat.py ADDED
@@ -0,0 +1,101 @@
1
+ """Reproducible graph inference with complete ambiguity evidence."""
2
+ from collections import defaultdict
3
+ import builtins
4
+ from pathlib import Path
5
+
6
+
7
+ def language(file):
8
+ suffix = Path(file).suffix.lower()
9
+ for family, extensions in [("python", {".py", ".pyi", ".pyw"}),
10
+ ("javascript", {".js", ".mjs", ".cjs", ".jsx", ".ts", ".tsx"}),
11
+ ("c-family", {".c", ".cc", ".cpp", ".cxx", ".h", ".hpp", ".hxx"}),
12
+ ("shell", {".sh", ".bash", ".zsh"})]:
13
+ if suffix in extensions:
14
+ return family
15
+ return suffix
16
+
17
+
18
+ def build_call_graph(self, result):
19
+ """Keep unresolved candidates instead of selecting an arbitrary first one."""
20
+ names = defaultdict(list)
21
+ for name in sorted(result.functions):
22
+ names[name.rsplit(".", 1)[-1]].append(name)
23
+ for function in result.functions.values():
24
+ function.called_by = []
25
+ ambiguous = []
26
+ unproven = []
27
+ for caller in sorted(result.functions):
28
+ function = result.functions[caller]
29
+ caller_scope = caller.rsplit(".", 1)[0]
30
+ for number, called in enumerate(function.calls):
31
+ candidates = names.get(called, [])
32
+ local = [name for name in candidates if name.rsplit(".", 1)[0] == caller_scope]
33
+ resolved = called if called in result.functions else local[0] if len(local) == 1 else None
34
+ reason = None
35
+ if resolved is None and candidates:
36
+ if language(function.file) == "python" and hasattr(builtins, called):
37
+ reason = "Python builtin or imported shadow; non-local target not proven"
38
+ elif len(candidates) > 1:
39
+ reason = "Multiple non-local targets"
40
+ elif language(function.file) != language(result.functions[candidates[0]].file):
41
+ reason = "Cross-language target requires bridge or import evidence"
42
+ else:
43
+ resolved = candidates[0]
44
+ if resolved is not None:
45
+ function.calls[number] = resolved
46
+ result.functions[resolved].called_by.append(caller)
47
+ elif reason is not None:
48
+ record = {"caller": caller, "call": called, "call_index": number,
49
+ "candidate_targets": list(candidates), "reason": reason}
50
+ (ambiguous if len(candidates) > 1 else unproven).append(record)
51
+ for function in result.functions.values():
52
+ function.called_by.sort()
53
+ result.entry_points = sorted(name for name, function in result.functions.items()
54
+ if not function.called_by)
55
+ result.metrics["call_graph_inference"] = {
56
+ "policy": "Preserve exact, same-scope and same-language unique targets; uncertain calls remain unresolved",
57
+ "ambiguous_calls": ambiguous,
58
+ "unproven_calls": unproven,
59
+ "unproven_count": len(unproven),
60
+ "ambiguity_count": len(ambiguous),
61
+ "candidate_order": "Qualified source identities sorted lexically",
62
+ "limit": "Static inference; unique inferred targets and external names are not runtime proof",
63
+ }
64
+
65
+
66
+ def calculate_centrality(self, call_graph, result):
67
+ """Use canonical insertion order and a local random seed for sampling."""
68
+ import networkx as nx
69
+
70
+ graph = nx.DiGraph()
71
+ graph.add_nodes_from(sorted(call_graph.nodes()))
72
+ graph.add_edges_from(sorted(call_graph.edges()))
73
+ size = len(graph)
74
+ k = min(int(size * (0.1 if size > 2000 else 0.2)), 200) if size > 500 else None
75
+ scores = nx.betweenness_centrality(graph, k=k, normalized=True, seed=0) if size else {}
76
+ for name, value in scores.items():
77
+ if name in result.functions:
78
+ result.functions[name].centrality = value
79
+ result.metrics.setdefault("call_graph_inference", {})["centrality"] = {
80
+ "backend": "networkx", "version": nx.__version__, "nodes": size,
81
+ "sampled": k is not None, "sample_count": k, "seed": 0 if k is not None else None,
82
+ "node_order": "Lexical qualified source identity", "normalized": True,
83
+ }
84
+
85
+
86
+ def install():
87
+ from code2llm.core.analyzer import ProjectAnalyzer
88
+ from code2llm.core.refactoring import RefactoringAnalyzer
89
+
90
+ if getattr(ProjectAnalyzer, "_project_analysis_reproducible_graph", False):
91
+ return
92
+ original_merge = ProjectAnalyzer._merge_results
93
+
94
+ def merge(self, results, project_path):
95
+ ordered = sorted(results, key=lambda item: str(item.get("file", "")))
96
+ return original_merge(self, ordered, project_path)
97
+
98
+ ProjectAnalyzer._merge_results = merge
99
+ ProjectAnalyzer._build_call_graph = build_call_graph
100
+ RefactoringAnalyzer._calculate_centrality = calculate_centrality
101
+ ProjectAnalyzer._project_analysis_reproducible_graph = True
project_analysis.py ADDED
@@ -0,0 +1,624 @@
1
+ #!/usr/bin/env python3
2
+ """Generate compact reports from one explicitly recorded analysis scope.
3
+
4
+ Use --scope-only to inspect selection, --full for a compressed raw analysis.
5
+ Tool versions are recorded, never upgraded implicitly. Compatibility adapters
6
+ are tested with code2llm 0.5.183, code2docs 3.0.36 and sumd 0.3.60.
7
+ """
8
+
9
+ from __future__ import annotations
10
+
11
+ import argparse
12
+ import contextlib
13
+ from dataclasses import replace, asdict
14
+ import fcntl
15
+ import fnmatch
16
+ import gzip
17
+ import hashlib
18
+ import importlib.metadata
19
+ import json
20
+ import os
21
+ from pathlib import Path
22
+ import subprocess
23
+ import sys
24
+ import tempfile
25
+ import time
26
+ import traceback
27
+ from unittest.mock import patch
28
+
29
+
30
+ # Never exclude packages merely named artifacts, logs, state or schemas.
31
+ # [p] keeps code2llm's directory pruning from applying a root-only glob to
32
+ # component project/*.sh scripts as well (installed code2llm 0.5.183).
33
+ EXCLUDES = [
34
+ "[p]roject/**", "**/output/artifacts/**", "**/output/logs/**",
35
+ "**/.worktrees/**", "**/.subactor/**", "**/.local/**",
36
+ "**/.governance/**", "**/.planfile/**", "**/.koru/**", "**/.regres/**",
37
+ "**/venv/**", "**/.venv/**", "**/.venv-test/**", "**/site-packages/**",
38
+ "**/node_modules/**", "**/.playwright-browsers/**", "**/.code2llm_cache/**",
39
+ "**/build/**", "**/dist/**", "**/target/**",
40
+ ]
41
+ TOOLS = ("code2llm", "code2docs", "sumd", "redup", "prefact", "doql")
42
+ # Root adapter propagates the same declared runtime exclusions to the DOQL
43
+ # child process. Existing four deployments keep their accepted core unchanged.
44
+ EXCLUDES += json.loads(os.environ.get("PROJECT_ANALYSIS_WORKSPACE_EXCLUDES", "[]"))
45
+
46
+
47
+ def atomic_text(path: Path, text: str) -> None:
48
+ path.parent.mkdir(parents=True, exist_ok=True)
49
+ with tempfile.NamedTemporaryFile(mode="w", encoding="utf-8", dir=path.parent,
50
+ delete=False) as stream:
51
+ temporary = Path(stream.name)
52
+ try:
53
+ stream.write(text)
54
+ stream.flush()
55
+ os.replace(temporary, path)
56
+ finally:
57
+ temporary.unlink(missing_ok=True)
58
+
59
+
60
+ def write_json(path: Path, data: dict) -> None:
61
+ atomic_text(path, json.dumps(data, indent=2, ensure_ascii=False) + "\n")
62
+
63
+
64
+ def digest(path: Path) -> str:
65
+ return hashlib.sha256(path.read_bytes()).hexdigest()
66
+
67
+
68
+ def json_collection(value):
69
+ # code2llm's non-compact result still contains sets in nested graph metrics.
70
+ # Preserve their members as deterministic JSON arrays, never stringify them.
71
+ if isinstance(value, (set, frozenset)):
72
+ return sorted(value, key=repr)
73
+ raise TypeError(f"Cannot serialize {type(value).__name__}")
74
+
75
+
76
+ @contextlib.contextmanager
77
+ def writer_lock(root: Path):
78
+ path = root / ".planfile/.project-analysis.lock"
79
+ path.parent.mkdir(parents=True, exist_ok=True)
80
+ with path.open("a+") as stream:
81
+ try:
82
+ fcntl.flock(stream, fcntl.LOCK_EX | fcntl.LOCK_NB)
83
+ except BlockingIOError:
84
+ raise RuntimeError("Project analysis is already running; retry after it finishes.")
85
+ try:
86
+ yield
87
+ finally:
88
+ fcntl.flock(stream, fcntl.LOCK_UN)
89
+
90
+
91
+ def build_config():
92
+ from code2llm.api import Config
93
+ from analysis_compat import install
94
+
95
+ install()
96
+
97
+ config = Config(mode="static")
98
+ config.filters.exclude_patterns += EXCLUDES
99
+ config.filters.skip_properties = False
100
+ config.filters.skip_accessors = False
101
+ config.performance.parallel_workers = 2
102
+ # Cache entries in this version do not bind every configuration field.
103
+ config.no_cache = True
104
+ config.performance.enable_cache = False
105
+ return config
106
+
107
+
108
+ def export_map(result, path: Path) -> None:
109
+ """Render compact comments on one line without mutating full docstrings."""
110
+ import re
111
+ from code2llm.exporters import get_exporter
112
+ from code2llm.exporters.map import details
113
+
114
+ original = details._render_map_class
115
+
116
+ def render_class(result, info, lines):
117
+ preview = " ".join(info.docstring.split()) if info.docstring else info.docstring
118
+ original(result, replace(info, docstring=preview), lines)
119
+
120
+ with patch.object(details, "_render_map_class", render_class):
121
+ get_exporter("map")().export(result, str(path))
122
+ text = re.sub(r"(?m)^(# stats:.*?\| )\d+ cls( \|)",
123
+ lambda m: m[1] + str(len(result.classes)) + " cls" + m[2],
124
+ path.read_text(encoding="utf-8"))
125
+ # Upstream always emits zero here; it never computes a cycle count.
126
+ text = re.sub(r"(?m)^(# stats:.*?\| cycles:)0$", r"\g<1>unknown", text)
127
+ atomic_text(path, text)
128
+
129
+
130
+ def export_analysis(result, output: Path, full: bool) -> list[Path]:
131
+ from code2llm.exporters import get_exporter, MermaidExporter, YAMLExporter
132
+ from code2llm.exporters.toon_view import ToonViewGenerator
133
+ from code2llm.exporters.project_yaml_exporter import ProjectYAMLExporter
134
+ from code2llm.exporters.project_yaml.evolution import load_previous_evolution
135
+
136
+ names = []
137
+ for format_, name in [("toon", "analysis.toon.yaml"), ("map", "map.toon.yaml"),
138
+ ("context", "context.md"), ("evolution", "evolution.toon.yaml"),
139
+ ("planfile", "planfile-tickets.yaml")]:
140
+ if format_ == "map":
141
+ export_map(result, output / name)
142
+ else:
143
+ get_exporter(format_)().export(result, str(output / name))
144
+ names.append(name)
145
+ overview = ProjectYAMLExporter()._build_project_yaml(
146
+ result, load_previous_evolution(output / "project.yaml"))
147
+ ToonViewGenerator().generate(overview, str(output / "project.toon.yaml"))
148
+ diagrams = MermaidExporter()
149
+ diagrams.export_flow_compact(result, str(output / "flow.mmd"))
150
+ diagrams.export_call_graph(result, str(output / "calls.mmd"))
151
+ diagrams.export_compact(result, str(output / "compact_flow.mmd"))
152
+ calls = YAMLExporter()
153
+ calls.export_calls(result, str(output / "calls.yaml"))
154
+ calls.export_calls_toon(result, str(output / "calls.toon.yaml"))
155
+ names += ["project.toon.yaml", "flow.mmd", "calls.mmd", "compact_flow.mmd", "calls.yaml", "calls.toon.yaml"]
156
+ graph_evidence = result.metrics.get("call_graph_inference")
157
+ if graph_evidence is not None:
158
+ payload = {"schema": "project-analysis.call-graph-evidence/v1", **graph_evidence}
159
+ with tempfile.NamedTemporaryFile(dir=output, delete=False) as temporary:
160
+ temporary.write(gzip.compress(json.dumps(payload, ensure_ascii=False, sort_keys=True,
161
+ default=json_collection).encode(), mtime=0))
162
+ evidence_path = Path(temporary.name)
163
+ try:
164
+ os.replace(evidence_path, output / "call-graph-evidence.json.gz")
165
+ finally:
166
+ evidence_path.unlink(missing_ok=True)
167
+ names.append("call-graph-evidence.json.gz")
168
+ if full:
169
+ with tempfile.NamedTemporaryFile(dir=output, delete=False) as temporary:
170
+ raw_path = Path(temporary.name)
171
+ try:
172
+ with gzip.open(raw_path, "wt", encoding="utf-8") as stream:
173
+ json.dump(result.to_dict(compact=False), stream, ensure_ascii=False, default=json_collection)
174
+ os.replace(raw_path, output / "analysis.json.gz")
175
+ finally:
176
+ raw_path.unlink(missing_ok=True)
177
+ names.append("analysis.json.gz")
178
+ return [output / name for name in names]
179
+
180
+
181
+ def coverage_note(errors: list[dict]) -> str:
182
+ if not errors:
183
+ return ""
184
+ paths = ", ".join(f"`{e['path']}`" for e in errors)
185
+ return (f"> Analysis has {len(errors)} source errors: {paths}. These files are in the "
186
+ "input inventory but have no parsed metrics. See `project/analysis-manifest.json`.\n\n")
187
+
188
+
189
+ def source_errors(root: Path, selected: list[str], result, config) -> list[dict]:
190
+ """Expose parser failures that the installed analyzer silently discards."""
191
+ from code2llm.core.file_analyzer import FileAnalyzer
192
+
193
+ modules = {str(Path(m.file).relative_to(root)) for m in result.modules.values()}
194
+ if modules - set(selected):
195
+ raise RuntimeError("Analyzer returned files outside the selected inventory")
196
+ errors = []
197
+ for name in sorted(set(selected) - modules):
198
+ path = root / name
199
+ if path.is_symlink() and not path.exists():
200
+ errors.append({"path": name, "kind": "broken_symlink", "error": os.readlink(path)})
201
+ continue
202
+ try:
203
+ parsed = FileAnalyzer(config).analyze_file(str(path), "coverage_probe")
204
+ except Exception as error:
205
+ errors.append({"path": name, "kind": "parser_error", "error": str(error)})
206
+ continue
207
+ if parsed.get("module"):
208
+ raise RuntimeError(f"Analyzer lost a successfully parsed module: {name}")
209
+ errors.append({"path": name, "kind": "no_parse_result", "error": "Analyzer returned no module"})
210
+ return errors
211
+
212
+
213
+ def generate_readme(root: Path, result, errors: list[dict] | None = None, *, full_export: bool = False) -> Path:
214
+ from code2docs.config import Code2DocsConfig
215
+ from code2docs.generators.readme_gen import ReadmeGenerator, MARKER_START, MARKER_END
216
+
217
+ config_path = next((root / name for name in ("code2docs.yaml", "code2docs.yml")
218
+ if (root / name).is_file()), None)
219
+ config = (Code2DocsConfig.from_yaml(str(config_path)) if config_path
220
+ else Code2DocsConfig(project_name=root.name, readme_output="project/README.md"))
221
+ if not config_path:
222
+ # The upstream default repeats every module twice plus all public APIs
223
+ # and advertises a code2docs CLI under the analyzed project's name.
224
+ # Keep a factual overview; full inventories live in their own reports.
225
+ config.readme.sections = ["overview", "requirements"]
226
+ config.readme.sync_markers = False
227
+ config.llm.enabled = False
228
+ path = (root / config.readme_output).resolve()
229
+ if not path.is_relative_to(root):
230
+ raise ValueError("README output must stay inside the analyzed workspace")
231
+ content = ReadmeGenerator(config, result).generate()
232
+ if not config_path:
233
+ # These badges/author fields are tool defaults, not registered workspace
234
+ # metadata. Keep the actual counters and omit inferred package claims.
235
+ content = "\n".join(line for line in content.splitlines()
236
+ if not line.startswith(("![", "**Author:**"))) + "\n"
237
+ links = [("Structure", "map.toon.yaml"), ("Diagnostics", "analysis.toon.yaml"),
238
+ ("Architecture", "context.md"), ("Input inventory", "analysis-scope.json"),
239
+ ("Run status and view limits", "analysis-manifest.json")]
240
+ if full_export and (root / "project/analysis.json.gz").is_file():
241
+ links.append(("Raw analysis (gzip)", "analysis.json.gz"))
242
+ extra = "\n## Reports\n\n" + "\n".join(
243
+ f"- [{label}]({os.path.relpath(root / 'project' / name, path.parent)})"
244
+ for label, name in links)
245
+ extra += ("\n\n## Regeneration\n\nRun from the workspace root:\n\n"
246
+ "```bash\nbash project.sh\nbash project.sh --full\nbash project.sh --scope-only\n```\n\n"
247
+ "Compact views summarize the selected source. The inventory records its scope; "
248
+ "the manifest records omitted files and graph limits. Exit 2 means source errors.\n\n")
249
+ content = content.replace(MARKER_END, extra + MARKER_END) if MARKER_END in content else content + extra
250
+ note = coverage_note(errors or [])
251
+ if note and MARKER_START in content:
252
+ content = content.replace(MARKER_START, MARKER_START + "\n\n" + note, 1)
253
+ else:
254
+ content = note + content
255
+ if path.exists() and config_path:
256
+ existing = path.read_text(encoding="utf-8")
257
+ if MARKER_START in existing and MARKER_END in existing:
258
+ import re
259
+ content = re.sub(re.escape(MARKER_START) + ".*?" + re.escape(MARKER_END),
260
+ lambda _: content, existing, flags=re.DOTALL)
261
+ elif path.name == "README.md" and path.parent == root:
262
+ path = root / "project/README.md"
263
+ atomic_text(path, content)
264
+ return path
265
+
266
+
267
+ def write_scoped_logic(root: Path, result) -> Path:
268
+ """Build fresh SUMD facts from the completed analyzer inventory."""
269
+ from collections import Counter
270
+ from sumd.extractor import generate_project_logic, _lang_of
271
+
272
+ modules = [(Path(m.file).relative_to(root), m.line_count, _lang_of(Path(m.file)))
273
+ for m in result.modules.values()]
274
+
275
+ def function(info):
276
+ return {"mod": str(Path(info.file).relative_to(root)), "name": info.name,
277
+ "args": info.args, "cc": info.complexity.get("cyclomatic_complexity", 0),
278
+ "fan": len(set(info.calls))}
279
+
280
+ functions = [function(info) for info in result.functions.values()
281
+ if _lang_of(Path(info.file)) == "python" and not info.is_method]
282
+ classes = [{"mod": str(Path(info.file).relative_to(root)), "name": info.name,
283
+ "methods": [function(result.functions[name]) for name in info.methods
284
+ if name in result.functions]}
285
+ for info in result.classes.values() if _lang_of(Path(info.file)) == "python"]
286
+ with patch("sumd.extractor._collect_map_files", return_value=(dict(Counter(m[2] for m in modules)), modules)), \
287
+ patch("sumd.extractor._render_map_detail", return_value=([], functions, classes, len(classes))):
288
+ content = generate_project_logic(root)
289
+ path = root / "project/logic.pl"
290
+ atomic_text(path, content)
291
+ return path
292
+
293
+
294
+ def render_summaries(root: Path, errors: list[dict] | None = None, result=None) -> list[Path]:
295
+ from sumd.pipeline import RenderPipeline
296
+
297
+ paths = [write_scoped_logic(root, result)] if result is not None else []
298
+ # sumd 0.3.60 regenerates maps and may rerun external tools while rendering.
299
+ # Reuse the completed artifacts; these process-local patches are restored
300
+ # on every exit and do not modify installed packages or component repos.
301
+ with patch("sumd.pipeline._refresh_map_toon"), patch("sumd.pipeline._refresh_analysis_files"):
302
+ for name, profile in [("SUMD.md", "rich"), ("SUMR.md", "refactor")]:
303
+ content = coverage_note(errors or []) + RenderPipeline(root).run(profile=profile)
304
+ path = root / name
305
+ atomic_text(path, content)
306
+ if name == "SUMD.md" and result is not None:
307
+ # Semantic declarations must come from this freshly rendered
308
+ # document; then embed exactly the resulting current logic file.
309
+ write_scoped_logic(root, result)
310
+ content = coverage_note(errors or []) + RenderPipeline(root).run(profile=profile)
311
+ atomic_text(path, content)
312
+ paths.append(path)
313
+ return paths
314
+
315
+
316
+ def indexed_simple_matches(index, block, original):
317
+ """Prune signature candidates without losing any original threshold match.
318
+
319
+ With at most d mismatches, d+1 disjoint bands contain an identical band.
320
+ Every candidate is still scored by the original method, in original order.
321
+ The library builds its signature vectors before querying this fixed index.
322
+ """
323
+ import math
324
+ from redup.core import lsh_matcher, tokens_hasher
325
+
326
+ threshold = index.threshold
327
+ if (not isinstance(threshold, (int, float)) or not math.isfinite(threshold)
328
+ or not 0 < threshold <= 1 or tokens_hasher.redup_fast_hash is not None
329
+ or len(index.blocks) != len(index.minhashes)):
330
+ return original(index, block)
331
+ query = lsh_matcher._create_simple_minhash(block.text, index.num_perm)
332
+ if not query.hash_values:
333
+ return []
334
+ width = len(query.hash_values)
335
+ required = math.ceil(threshold * width)
336
+ # Follow the original floating-point matches/width comparison exactly,
337
+ # including ratios such as 7/25 whose product can round above an integer.
338
+ while required > 0 and (required - 1) / width >= threshold:
339
+ required -= 1
340
+ while required / width < threshold:
341
+ required += 1
342
+ bands = width - required + 1
343
+ key = (id(index.minhashes), len(index.minhashes), threshold, width)
344
+ cached = getattr(index, "_project_analysis_signature_index", None)
345
+ if cached is None or cached[0] != key:
346
+ spans = [(i * width // bands, (i + 1) * width // bands) for i in range(bands)]
347
+ tables = [{} for _ in spans]
348
+ for number, stored in enumerate(index.minhashes):
349
+ if not isinstance(stored, lsh_matcher._SimpleMinHash) or len(stored.hash_values) != width:
350
+ continue
351
+ for table, (start, stop) in zip(tables, spans):
352
+ signature = tuple(stored.hash_values[start:stop])
353
+ table.setdefault(signature, []).append(number)
354
+ cached = (key, spans, tables)
355
+ index._project_analysis_signature_index = cached
356
+ _, spans, tables = cached
357
+ candidates = set()
358
+ for table, (start, stop) in zip(tables, spans):
359
+ candidates.update(table.get(tuple(query.hash_values[start:stop]), ()))
360
+ matches = []
361
+ for number in sorted(candidates):
362
+ score = query.jaccard(index.minhashes[number])
363
+ if score >= threshold:
364
+ matches.append((index.blocks[number], score))
365
+ return sorted(matches, key=lambda item: item[1], reverse=True)
366
+
367
+
368
+ def duplication(root: Path, selected: list[str]) -> dict:
369
+ from redup.core.config import config_to_scan_config, load_config
370
+ from redup.core.pipeline import analyze
371
+ from redup.reporters.toon_reporter import to_toon
372
+ from redup.core import lsh_matcher
373
+
374
+ config = config_to_scan_config(load_config(root), root)
375
+ config.target_files = [name for name in selected
376
+ if Path(name).suffix in config.extensions]
377
+ # Selection already removed non-source trees. reDUP's defaults exclude
378
+ # every directory named logs/data, including actual Python packages.
379
+ config.exclude_patterns = []
380
+ config.include_tests = True
381
+ original = lsh_matcher.LSHIndex._find_near_duplicates_simple
382
+ with patch.object(lsh_matcher.LSHIndex, "_find_near_duplicates_simple",
383
+ lambda index, block: indexed_simple_matches(index, block, original)):
384
+ result = analyze(config)
385
+ atomic_text(root / "project/duplication.toon.yaml", to_toon(result))
386
+ return {"requested_files": len(config.target_files), "scanned_files": result.stats.files_scanned,
387
+ "groups": result.total_groups,
388
+ "near_duplicates": {
389
+ "enabled": config.lsh_enabled, "threshold": config.lsh_threshold,
390
+ "minimum_lines": config.lsh_min_lines,
391
+ "backend": "datasketch" if lsh_matcher.MinHash is not None else "simple-minhash-exact-candidate-index",
392
+ "score_model": "Original backend unchanged; simple fallback uses up to 10 normalized prefix features",
393
+ "candidate_coverage": "Every original threshold match retained; original scores and stable ordering"}}
394
+
395
+
396
+ def generate_doql(root: Path) -> None:
397
+ """Keep DOQL's recursive probes out of runtime and generated output trees."""
398
+ from doql.adopt.scanner import scan_project
399
+ from doql.adopt.emitter import emit_spec
400
+
401
+ original_rglob = Path.rglob
402
+ original_glob = Path.glob
403
+
404
+ def allowed(path, *, directory=False):
405
+ try:
406
+ relative = path.relative_to(root)
407
+ except ValueError:
408
+ return True
409
+ name = relative.as_posix() + ("/" if directory else "")
410
+ return not (any(part.startswith(".") for part in relative.parts)
411
+ or any(fnmatch.fnmatchcase(candidate, excluded)
412
+ for candidate in (name, "/" + name) for excluded in EXCLUDES))
413
+
414
+ def scoped_rglob(directory, pattern, *arguments, **keywords):
415
+ # Every recursive probe in pinned DOQL 1.0.44 uses a basename glob.
416
+ # Prune before scandir so discarded receipt/venv trees are never opened.
417
+ if not allowed(directory, directory=True):
418
+ return
419
+ pattern = os.fspath(pattern)
420
+ if "/" in pattern or arguments or keywords:
421
+ for path in original_rglob(directory, pattern, *arguments, **keywords):
422
+ if allowed(path, directory=path.is_dir()):
423
+ yield path
424
+ return
425
+ for parent, directories, files in os.walk(directory, followlinks=False):
426
+ parent = Path(parent)
427
+ directories[:] = [name for name in directories
428
+ if allowed(parent / name, directory=True)]
429
+ for name in directories + files:
430
+ path = parent / name
431
+ if fnmatch.fnmatchcase(name, pattern) and allowed(path):
432
+ yield path
433
+
434
+ def scoped_glob(directory, pattern, *arguments, **keywords):
435
+ pattern = os.fspath(pattern)
436
+ if pattern.startswith("**/") and not arguments and not keywords:
437
+ suffix = pattern[3:]
438
+ for path in scoped_rglob(directory, "*"):
439
+ if path.relative_to(directory).match(suffix):
440
+ yield path
441
+ else:
442
+ yield from original_glob(directory, pattern, *arguments, **keywords)
443
+
444
+ # The adapter lives only in this child process. Tests and real packages
445
+ # called logs/artifacts remain visible; installed DOQL is unchanged.
446
+ with patch.object(Path, "rglob", scoped_rglob), patch.object(Path, "glob", scoped_glob):
447
+ spec = scan_project(root)
448
+ output = root / "app.doql.less"
449
+ emit_spec(spec, output, fmt="less")
450
+ if not output.is_file() or not output.stat().st_size:
451
+ raise RuntimeError("DOQL produced no descriptor")
452
+
453
+
454
+ def run(root: Path, args) -> int:
455
+ from code2llm.core.analyzer import ProjectAnalyzer
456
+
457
+ output = root / "project"
458
+ output.mkdir(exist_ok=True)
459
+ report_path = output / ("scope-manifest.json" if args.scope_only else "analysis-manifest.json")
460
+ report = {"schema": "project-analysis/v1", "root": str(root), "status": "running",
461
+ "started_at": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),
462
+ "versions": {name: importlib.metadata.version(name) for name in TOOLS},
463
+ "stages": {}, "artifacts": {}, "full_export": args.full,
464
+ "limits": {"scope": "Production source plus manifests/docs; analyzer defaults exclude tests, hidden, vendor and archive trees.",
465
+ "calls": {"max_edges": 500, "max_calls_per_function": 10},
466
+ "health_issues_shown": 20,
467
+ "raw_analysis": "analysis.json.gz contains the analyzer result, not original source or excluded files; generated only with --full.",
468
+ "quality": "prefact scan reports findings without autonomous ticket/TODO generation or fixes."}}
469
+ report["generator_sha256"] = digest(Path(__file__).resolve())
470
+ report["runtime"] = {"python": sys.version.split()[0], "mcp": importlib.metadata.version("mcp")}
471
+ validator = importlib.metadata.distribution("sumd").locate_file("sumd/validator.py")
472
+ report["sumd_validator_sha256"] = digest(Path(validator))
473
+ report["limits"]["doql"] = "Heuristic descriptor scan; recursive probes exclude hidden/runtime trees and the root project output, while retaining tests."
474
+ report["limits"]["logic"] = "Current parsed file inventory; SUMD predicates cover Python functions/classes/methods plus current root metadata and semantic declarations. Raw analysis retains all supported languages."
475
+ report["limits"]["map_cycles"] = "Map cycle count is unknown: the pinned exporter does not calculate it. It is not evidence that the source has no cycles."
476
+
477
+ def stage(name, action):
478
+ print(f"run {name}", flush=True)
479
+ log_path = root / ".planfile" / f"project-analysis-{name}.log"
480
+ start = time.monotonic()
481
+ record = {"status": "running", "log": str(log_path.relative_to(root))}
482
+ report["stages"][name] = record
483
+ write_json(report_path, report)
484
+ try:
485
+ with log_path.open("w", encoding="utf-8") as log:
486
+ with contextlib.redirect_stdout(log), contextlib.redirect_stderr(log):
487
+ value = action(log)
488
+ record.update(status="ok", seconds=round(time.monotonic() - start, 2))
489
+ print(f"ok {name} ({record['seconds']}s)", flush=True)
490
+ return value
491
+ except Exception as error:
492
+ with log_path.open("a", encoding="utf-8") as log:
493
+ traceback.print_exc(file=log)
494
+ record.update(status="failed", error=str(error), seconds=round(time.monotonic() - start, 2))
495
+ raise
496
+ finally:
497
+ write_json(report_path, report)
498
+
499
+ def command(log, tool, *arguments):
500
+ subprocess.run([str(Path(sys.executable).parent / tool), *arguments], cwd=root,
501
+ stdout=log, stderr=log, timeout=args.timeout, check=True)
502
+
503
+ def remember(paths):
504
+ for path in paths:
505
+ report["artifacts"][str(path.relative_to(root))] = {
506
+ "sha256": digest(path), "bytes": path.stat().st_size}
507
+
508
+ try:
509
+ if not args.scope_only:
510
+ doql_script = ("from pathlib import Path; import sys; "
511
+ "sys.path.insert(0, sys.argv[1]); "
512
+ "from project_analysis import generate_doql; "
513
+ "generate_doql(Path(sys.argv[2]))")
514
+ stage("doql", lambda log: subprocess.run(
515
+ [sys.executable, "-c", doql_script, str(Path(__file__).resolve().parent), str(root)],
516
+ cwd=root, stdout=log, stderr=log, timeout=args.timeout, check=True))
517
+ remember([root / "app.doql.less"])
518
+ analyzer = ProjectAnalyzer(build_config(), root)
519
+ inventory = stage("scope", lambda _: analyzer._collect_files(root))
520
+ selected = sorted(str(Path(path).relative_to(root)) for path, _ in inventory)
521
+ scope_path = output / ("source-selection-preview.json" if args.scope_only else "analysis-scope.json")
522
+ write_json(scope_path, {"root": str(root), "selected_files": selected,
523
+ "exclude_patterns": analyzer.config.filters.exclude_patterns,
524
+ "exclude_tests": analyzer.config.filters.exclude_tests,
525
+ "skip_properties": False, "skip_accessors": False})
526
+ remember([scope_path])
527
+ report["selected_file_count"] = len(selected)
528
+ if args.scope_only:
529
+ report["status"] = "scope_only"
530
+ return 0
531
+ # A second live traversal can add new runtime/ticket files after scope
532
+ # was recorded. Bind the actual analysis to that exact first inventory.
533
+ with patch.object(analyzer, "_collect_files", return_value=inventory):
534
+ result = stage("code2llm", lambda _: analyzer.analyze_project(str(root)))
535
+ report["input_inventory_frozen"] = True
536
+ report["analyzer_configuration"] = {
537
+ "parallel_workers": analyzer.config.performance.parallel_workers,
538
+ "skip_properties": analyzer.config.filters.skip_properties,
539
+ "skip_accessors": analyzer.config.filters.skip_accessors,
540
+ "worker_configuration": "Complete Config passed unchanged to each worker",
541
+ "filters": asdict(analyzer.config.filters),
542
+ }
543
+ report["parser_compatibility"] = [
544
+ {**note, "path": str(Path(note["path"]).relative_to(root))}
545
+ for note in getattr(analyzer, "_project_analysis_compatibility_notes", [])]
546
+ report["compatibility_modules"] = {
547
+ name: digest(Path(__file__).with_name(name))
548
+ for name in ("analysis_compat.py", "tsx_compat.py", "graph_compat.py")}
549
+ modules = sorted(str(Path(m.file).relative_to(root)) for m in result.modules.values())
550
+ report["coverage"] = {"selected_without_module": sorted(set(selected) - set(modules)),
551
+ "modules_not_selected": sorted(set(modules) - set(selected))}
552
+ report.update(module_count=len(modules), function_count=len(result.functions), class_count=len(result.classes))
553
+ errors = source_errors(root, selected, result, analyzer.config)
554
+ report["coverage"]["source_errors"] = errors
555
+ result.metrics["source_coverage"] = report["coverage"]
556
+ scope = json.loads(scope_path.read_text(encoding="utf-8"))
557
+ scope.update(analyzed_file_count=len(modules), source_errors=errors)
558
+ write_json(scope_path, scope)
559
+ remember([scope_path])
560
+ stage("exports", lambda _: remember(export_analysis(result, output, args.full)))
561
+ graph_evidence = result.metrics.get("call_graph_inference")
562
+ if graph_evidence is not None:
563
+ report["call_graph_inference"] = {key: value for key, value in graph_evidence.items()
564
+ if key not in {"ambiguous_calls", "unproven_calls"}}
565
+ report["call_graph_inference"]["evidence"] = "project/call-graph-evidence.json.gz"
566
+ stage("code2docs", lambda _: remember([generate_readme(root, result, errors, full_export=args.full)]))
567
+ if not args.no_quality:
568
+ report["duplication"] = stage("redup", lambda _: duplication(root, selected))
569
+ prefact_args = ["scan", "--path", str(root), "--format", "json",
570
+ "--output", str(output / "prefact.json")]
571
+ for pattern in EXCLUDES:
572
+ prefact_args += ["--exclude", pattern]
573
+ def prefact(log):
574
+ command(log, "prefact", *prefact_args)
575
+ remember([output / "prefact.json"])
576
+ stage("prefact", prefact)
577
+ remember([output / "duplication.toon.yaml"])
578
+ else:
579
+ report["stages"]["quality"] = {"status": "skipped", "reason": "--no-quality"}
580
+ map_hash = digest(output / "map.toon.yaml")
581
+ stage("sumd-sumr", lambda _: remember(render_summaries(root, errors, result)))
582
+ if digest(output / "map.toon.yaml") != map_hash:
583
+ raise RuntimeError("SUMD renderer changed the canonical map")
584
+ report["retained_files_from_other_runs"] = sorted(
585
+ str(path.relative_to(root)) for path in output.iterdir()
586
+ if path.is_file() and path != report_path
587
+ and str(path.relative_to(root)) not in report["artifacts"])
588
+ report["status"] = ("complete_with_source_errors" if errors else
589
+ "complete_without_quality" if args.no_quality else "complete")
590
+ print(f"Reports generated: {len(modules)}/{len(selected)} files parsed; {len(errors)} source errors.", flush=True)
591
+ return 2 if errors else 0
592
+ except Exception as error:
593
+ report.update(status="failed", error=str(error))
594
+ print(f"FAIL {error}; see {report_path}", file=sys.stderr, flush=True)
595
+ return 1
596
+ finally:
597
+ report["finished_at"] = time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime())
598
+ write_json(report_path, report)
599
+
600
+
601
+ def main() -> int:
602
+ parser = argparse.ArgumentParser(description=__doc__)
603
+ parser.add_argument("--root", type=Path, default=Path.cwd())
604
+ parser.add_argument("--full", action="store_true", help="Also write compressed raw analyzer result")
605
+ parser.add_argument("--scope-only", action="store_true", help="Only write source-selection inventory")
606
+ parser.add_argument("--no-quality", action="store_true", help="Skip redup/prefact; recorded explicitly")
607
+ parser.add_argument("--timeout", type=int, default=600, help="Per external tool timeout, in seconds")
608
+ args = parser.parse_args()
609
+ root = args.root.expanduser().resolve()
610
+ if not root.is_dir():
611
+ parser.error("root must be an existing directory")
612
+ if args.timeout <= 0:
613
+ parser.error("timeout must be positive")
614
+ os.chdir(root)
615
+ try:
616
+ with writer_lock(root):
617
+ return run(root, args)
618
+ except Exception as error:
619
+ print(f"FAIL {error}", file=sys.stderr)
620
+ return 75 if "already running" in str(error) else 1
621
+
622
+
623
+ if __name__ == "__main__":
624
+ raise SystemExit(main())
@@ -0,0 +1,58 @@
1
+ Metadata-Version: 2.4
2
+ Name: projix
3
+ Version: 0.1.2
4
+ Summary: Generate evidence-backed project analysis and documentation
5
+ License-Expression: Apache-2.0
6
+ Project-URL: Repository, https://github.com/semcod/project-python
7
+ Requires-Python: >=3.11
8
+ Description-Content-Type: text/markdown
9
+ License-File: LICENSE
10
+ Requires-Dist: code2llm==0.5.183
11
+ Requires-Dist: code2docs==3.0.36
12
+ Requires-Dist: sumd==0.3.60
13
+ Requires-Dist: redup==0.4.49
14
+ Requires-Dist: prefact==0.1.69
15
+ Requires-Dist: doql==1.0.44
16
+ Requires-Dist: mcp==2.3.0
17
+ Dynamic: license-file
18
+
19
+ # project
20
+
21
+
22
+ ## AI Cost Tracking
23
+
24
+ ![PyPI](https://img.shields.io/badge/pypi-costs-blue) ![Version](https://img.shields.io/badge/version-0.1.2-blue) ![Python](https://img.shields.io/badge/python-3.9+-blue) ![License](https://img.shields.io/badge/license-Apache--2.0-green)
25
+ ![AI Cost](https://img.shields.io/badge/AI%20Cost-$0.25-orange) ![Human Time](https://img.shields.io/badge/Human%20Time-1.0h-blue) ![Model](https://img.shields.io/badge/Model-openrouter%2Fqwen%2Fqwen3--coder--next-lightgrey)
26
+
27
+ - 🤖 **LLM usage:** $0.2500 (2 commits)
28
+ - 👤 **Human dev:** ~$100 (1.0h @ $100/h, 30min dedup)
29
+
30
+ Generated on 2026-11-18 using [openrouter/qwen/qwen3-coder-next](https://openrouter.ai/qwen/qwen3-coder-next)
31
+
32
+ ---
33
+
34
+ Generate a project inventory, source maps, call graphs, documentation and quality
35
+ reports using the existing code2llm, code2docs, redup, prefact, sumd and doql tools.
36
+
37
+ ```bash
38
+ pip install projix
39
+ project --root /path/to/workspace
40
+ ```
41
+
42
+ The default root is the current working directory. The command writes generated
43
+ reports to `project/`, `SUMD.md`, `SUMR.md`, `app.doql.less` and logs under
44
+ `.planfile/` in that root. Existing generated files may be replaced. It does not
45
+ publish or commit changes. Use `project --scope-only` to write only a source
46
+ selection preview, `project --no-quality` to omit quality scans, or
47
+ `project --full` to include the compressed raw analysis.
48
+
49
+ Exit status is 0 for a completed run, 1 for a failure, 2 for source errors and
50
+ 75 if another analysis owns the workspace lock. Reports record actual package
51
+ versions, selected files, compatibility adjustments and stage outcomes.
52
+
53
+ The implementation derives from the existing Semcod workspace analysis scripts.
54
+ It uses POSIX file locking and is currently intended for POSIX systems.
55
+
56
+ ## License
57
+
58
+ Licensed under Apache-2.0.
@@ -0,0 +1,10 @@
1
+ analysis_compat.py,sha256=JnVi7qCmz8fd-O0q6uEDatVyiBpjujNnc2fmW2aUcVk,2721
2
+ graph_compat.py,sha256=28fZXNS6ul1WgY0LN4KZUvz4rnza8-tIjxXA35k4JBE,4823
3
+ project_analysis.py,sha256=xMLlsh5DBRKiX8GwdFVisUszY2l4yzm-4fGVg_Or6Is,32097
4
+ tsx_compat.py,sha256=du9MtqIVZA8Qfk5RI3g79-KRnst-sqROjKDINFDOoAI,2762
5
+ projix-0.1.2.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
6
+ projix-0.1.2.dist-info/METADATA,sha256=D5gAF3MIvDE_M1mktrRnwO7o688_qs3pNeBr6WkyN2Y,2342
7
+ projix-0.1.2.dist-info/WHEEL,sha256=mOdXR9C3wMVov7cSY8PY-XCzo3SmmWCHvGQr5csJoao,91
8
+ projix-0.1.2.dist-info/entry_points.txt,sha256=GisnfUgz-lZBRjo5Dvn0lCAJQ5x5TU5REceCM8nHnKo,50
9
+ projix-0.1.2.dist-info/top_level.txt,sha256=N48LsMJq-vB4nzZ7CJOSzcV4UNPY3Zxb96cnkPuFlEg,57
10
+ projix-0.1.2.dist-info/RECORD,,
@@ -0,0 +1,5 @@
1
+ Wheel-Version: 1.0
2
+ Generator: setuptools (84.2.1)
3
+ Root-Is-Purelib: true
4
+ Tag: py3-none-any
5
+
@@ -0,0 +1,2 @@
1
+ [console_scripts]
2
+ project = project_analysis:main
@@ -0,0 +1,201 @@
1
+ Apache License
2
+ Version 2.0, January 2004
3
+ http://www.apache.org/licenses/
4
+
5
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6
+
7
+ 1. Definitions.
8
+
9
+ "License" shall mean the terms and conditions for use, reproduction,
10
+ and distribution as defined by Sections 1 through 9 of this document.
11
+
12
+ "Licensor" shall mean the copyright owner or entity authorized by
13
+ the copyright owner that is granting the License.
14
+
15
+ "Legal Entity" shall mean the union of the acting entity and all
16
+ other entities that control, are controlled by, or are under common
17
+ control with that entity. For the purposes of this definition,
18
+ "control" means (i) the power, direct or indirect, to cause the
19
+ direction or management of such entity, whether by contract or
20
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
21
+ outstanding shares, or (iii) beneficial ownership of such entity.
22
+
23
+ "You" (or "Your") shall mean an individual or Legal Entity
24
+ exercising permissions granted by this License.
25
+
26
+ "Source" form shall mean the preferred form for making modifications,
27
+ including but not limited to software source code, documentation
28
+ source, and configuration files.
29
+
30
+ "Object" form shall mean any form resulting from mechanical
31
+ transformation or translation of a Source form, including but
32
+ not limited to compiled object code, generated documentation,
33
+ and conversions to other media types.
34
+
35
+ "Work" shall mean the work of authorship, whether in Source or
36
+ Object form, made available under the License, as indicated by a
37
+ copyright notice that is included in or attached to the work
38
+ (an example is provided in the Appendix below).
39
+
40
+ "Derivative Works" shall mean any work, whether in Source or Object
41
+ form, that is based on (or derived from) the Work and for which the
42
+ editorial revisions, annotations, elaborations, or other modifications
43
+ represent, as a whole, an original work of authorship. For the purposes
44
+ of this License, Derivative Works shall not include works that remain
45
+ separable from, or merely link (or bind by name) to the interfaces of,
46
+ the Work and Derivative Works thereof.
47
+
48
+ "Contribution" shall mean any work of authorship, including
49
+ the original version of the Work and any modifications or additions
50
+ to that Work or Derivative Works thereof, that is intentionally
51
+ submitted to Licensor for inclusion in the Work by the copyright owner
52
+ or by an individual or Legal Entity authorized to submit on behalf of
53
+ the copyright owner. For the purposes of this definition, "submitted"
54
+ means any form of electronic, verbal, or written communication sent
55
+ to the Licensor or its representatives, including but not limited to
56
+ communication on electronic mailing lists, source code control systems,
57
+ and issue tracking systems that are managed by, or on behalf of, the
58
+ Licensor for the purpose of discussing and improving the Work, but
59
+ excluding communication that is conspicuously marked or otherwise
60
+ designated in writing by the copyright owner as "Not a Contribution."
61
+
62
+ "Contributor" shall mean Licensor and any individual or Legal Entity
63
+ on behalf of whom a Contribution has been received by Licensor and
64
+ subsequently incorporated within the Work.
65
+
66
+ 2. Grant of Copyright License. Subject to the terms and conditions of
67
+ this License, each Contributor hereby grants to You a perpetual,
68
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69
+ copyright license to reproduce, prepare Derivative Works of,
70
+ publicly display, publicly perform, sublicense, and distribute the
71
+ Work and such Derivative Works in Source or Object form.
72
+
73
+ 3. Grant of Patent License. Subject to the terms and conditions of
74
+ this License, each Contributor hereby grants to You a perpetual,
75
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76
+ (except as stated in this section) patent license to make, have made,
77
+ use, offer to sell, sell, import, and otherwise transfer the Work,
78
+ where such license applies only to those patent claims licensable
79
+ by such Contributor that are necessarily infringed by their
80
+ Contribution(s) alone or by combination of their Contribution(s)
81
+ with the Work to which such Contribution(s) was submitted. If You
82
+ institute patent litigation against any entity (including a
83
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
84
+ or a Contribution incorporated within the Work constitutes direct
85
+ or contributory patent infringement, then any patent licenses
86
+ granted to You under this License for that Work shall terminate
87
+ as of the date such litigation is filed.
88
+
89
+ 4. Redistribution. You may reproduce and distribute copies of the
90
+ Work or Derivative Works thereof in any medium, with or without
91
+ modifications, and in Source or Object form, provided that You
92
+ meet the following conditions:
93
+
94
+ (a) You must give any other recipients of the Work or
95
+ Derivative Works a copy of this License; and
96
+
97
+ (b) You must cause any modified files to carry prominent notices
98
+ stating that You changed the files; and
99
+
100
+ (c) You must retain, in the Source form of any Derivative Works
101
+ that You distribute, all copyright, patent, trademark, and
102
+ attribution notices from the Source form of the Work,
103
+ excluding those notices that do not pertain to any part of
104
+ the Derivative Works; and
105
+
106
+ (d) If the Work includes a "NOTICE" text file as part of its
107
+ distribution, then any Derivative Works that You distribute must
108
+ include a readable copy of the attribution notices contained
109
+ within such NOTICE file, excluding those notices that do not
110
+ pertain to any part of the Derivative Works, in at least one
111
+ of the following places: within a NOTICE text file distributed
112
+ as part of the Derivative Works; within the Source form or
113
+ documentation, if provided along with the Derivative Works; or,
114
+ within a display generated by the Derivative Works, if and
115
+ wherever such third-party notices normally appear. The contents
116
+ of the NOTICE file are for informational purposes only and
117
+ do not modify the License. You may add Your own attribution
118
+ notices within Derivative Works that You distribute, alongside
119
+ or as an addendum to the NOTICE text from the Work, provided
120
+ that such additional attribution notices cannot be construed
121
+ as modifying the License.
122
+
123
+ You may add Your own copyright statement to Your modifications and
124
+ may provide additional or different license terms and conditions
125
+ for use, reproduction, or distribution of Your modifications, or
126
+ for any such Derivative Works as a whole, provided Your use,
127
+ reproduction, and distribution of the Work otherwise complies with
128
+ the conditions stated in this License.
129
+
130
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
131
+ any Contribution intentionally submitted for inclusion in the Work
132
+ by You to the Licensor shall be under the terms and conditions of
133
+ this License, without any additional terms or conditions.
134
+ Notwithstanding the above, nothing herein shall supersede or modify
135
+ the terms of any separate license agreement you may have executed
136
+ with Licensor regarding such Contributions.
137
+
138
+ 6. Trademarks. This License does not grant permission to use the trade
139
+ names, trademarks, service marks, or product names of the Licensor,
140
+ except as required for reasonable and customary use in describing the
141
+ origin of the Work and reproducing the content of the NOTICE file.
142
+
143
+ 7. Disclaimer of Warranty. Unless required by applicable law or
144
+ agreed to in writing, Licensor provides the Work (and each
145
+ Contributor provides its Contributions) on an "AS IS" BASIS,
146
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147
+ implied, including, without limitation, any warranties or conditions
148
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149
+ PARTICULAR PURPOSE. You are solely responsible for determining the
150
+ appropriateness of using or redistributing the Work and assume any
151
+ risks associated with Your exercise of permissions under this License.
152
+
153
+ 8. Limitation of Liability. In no event and under no legal theory,
154
+ whether in tort (including negligence), contract, or otherwise,
155
+ unless required by applicable law (such as deliberate and grossly
156
+ negligent acts) or agreed to in writing, shall any Contributor be
157
+ liable to You for damages, including any direct, indirect, special,
158
+ incidental, or consequential damages of any character arising as a
159
+ result of this License or out of the use or inability to use the
160
+ Work (including but not limited to damages for loss of goodwill,
161
+ work stoppage, computer failure or malfunction, or any and all
162
+ other commercial damages or losses), even if such Contributor
163
+ has been advised of the possibility of such damages.
164
+
165
+ 9. Accepting Warranty or Additional Liability. While redistributing
166
+ the Work or Derivative Works thereof, You may choose to offer,
167
+ and charge a fee for, acceptance of support, warranty, indemnity,
168
+ or other liability obligations and/or rights consistent with this
169
+ License. However, in accepting such obligations, You may act only
170
+ on Your own behalf and on Your sole responsibility, not on behalf
171
+ of any other Contributor, and only if You agree to indemnify,
172
+ defend, and hold each Contributor harmless for any liability
173
+ incurred by, or claims asserted against, such Contributor by reason
174
+ of your accepting any such warranty or additional liability.
175
+
176
+ END OF TERMS AND CONDITIONS
177
+
178
+ APPENDIX: How to apply the Apache License to your work.
179
+
180
+ To apply the Apache License to your work, attach the following
181
+ boilerplate notice, with the fields enclosed by brackets "[]"
182
+ replaced with your own identifying information. (Don't include
183
+ the brackets!) The text should be enclosed in the appropriate
184
+ comment syntax for the file format. We also recommend that a
185
+ file or class name and description of purpose be included on the
186
+ same "printed page" as the copyright notice for easier
187
+ identification within third-party archives.
188
+
189
+ Copyright [yyyy] [name of copyright owner]
190
+
191
+ Licensed under the Apache License, Version 2.0 (the "License");
192
+ you may not use this file except in compliance with the License.
193
+ You may obtain a copy of the License at
194
+
195
+ http://www.apache.org/licenses/LICENSE-2.0
196
+
197
+ Unless required by applicable law or agreed to in writing, software
198
+ distributed under the License is distributed on an "AS IS" BASIS,
199
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200
+ See the License for the specific language governing permissions and
201
+ limitations under the License.
@@ -0,0 +1,4 @@
1
+ analysis_compat
2
+ graph_compat
3
+ project_analysis
4
+ tsx_compat
tsx_compat.py ADDED
@@ -0,0 +1,68 @@
1
+ """Recover a pinned TSX grammar's false error on plain JSX text ampersands.
2
+
3
+ No source file is changed. Only error nodes inside JSX text are eligible; byte
4
+ positions remain identical, and the remaining grammar must parse without errors.
5
+ """
6
+ from pathlib import Path
7
+ from unittest.mock import patch
8
+
9
+
10
+ def parse_text(content, extension='.tsx'):
11
+ from tree_sitter import Language, Parser
12
+ if extension == '.tsx':
13
+ import tree_sitter_typescript
14
+ grammar = tree_sitter_typescript.language_tsx()
15
+ else:
16
+ import tree_sitter_javascript
17
+ grammar = tree_sitter_javascript.language()
18
+ parser = Parser(Language(grammar))
19
+ raw = content.encode('utf-8')
20
+ tree = parser.parse(raw)
21
+ positions = []
22
+ pending = [tree.root_node]
23
+ while pending:
24
+ node = pending.pop()
25
+ if node.is_missing:
26
+ raise ValueError('TSX contains a missing syntax node')
27
+ if node.is_error:
28
+ if (node.parent is None or node.parent.type not in {'jsx_element', 'jsx_fragment'}
29
+ or raw[node.start_byte:node.start_byte + 1] != b'&'):
30
+ raise ValueError('TSX error is not a plain JSX text ampersand')
31
+ positions.append(node.start_byte)
32
+ pending.extend(node.children)
33
+ if not positions:
34
+ raise ValueError('TSX fallback does not address this parse failure')
35
+ normalized = bytearray(raw)
36
+ for position in positions:
37
+ normalized[position] = ord(' ')
38
+ tree = parser.parse(bytes(normalized))
39
+ if tree.root_node.has_error:
40
+ raise ValueError('TSX remains invalid after JSX text normalization')
41
+ return tree, sorted(positions)
42
+
43
+
44
+ def recover_file(config, file_path, module_name):
45
+ from code2llm.core.file_analyzer import FileAnalyzer
46
+ from code2llm.core.lang import js_analysis
47
+
48
+ extension = Path(file_path).suffix.lower()
49
+ if extension not in {'.tsx', '.jsx', '.js'}:
50
+ return None
51
+ content = Path(file_path).read_text(encoding='utf-8')
52
+ raw = content.encode('utf-8')
53
+ tree, positions = parse_text(content, extension)
54
+ original_parse = js_analysis._parse
55
+
56
+ def parse(value, ext):
57
+ return tree if ext == extension and value == content else original_parse(value, ext)
58
+
59
+ # Native extractors using _text still see the exact original text. Every
60
+ # normalized character is ASCII and same-width, preserving all positions.
61
+ def text(node):
62
+ return raw[node.start_byte:node.end_byte].decode('utf-8') if node is not None else ''
63
+
64
+ with patch.object(js_analysis, '_parse', parse), patch.object(js_analysis, '_text', text):
65
+ result = FileAnalyzer(config, None).analyze_file(file_path, module_name)
66
+ if not result.get('module'):
67
+ return None
68
+ return result, positions