root/Jyotisha
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity

Classify full interpretation source inventory

Browse Source
This commit is contained in:
732642856
2026-07-02 14:28:29 +08:00
parent f2a741d36b
commit d493910c67
4 changed files with 353 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/interpretation_source_inventory_gate.py
+242
View File
@@ -26,6 +26,78 @@ REQUIRED_LAYERS = [
"quarantined_drafts",
]
SCAN_ROOTS = [
"references",
"docs",
"jyotish-app",
"assets",
"SKILL.md",
"AGENTS.md",
]
EXCLUDED_PARTS = {
".git",
".pytest_cache",
".ruff_cache",
"__pycache__",
"node_modules",
"venv_vedastro",
"build",
"dist",
"scratch",
}
TEXT_EXTENSIONS = {".md", ".txt", ".json", ".js", ".ts", ".tsx", ".jsx", ".html", ".csv"}
CANDIDATE_KEYWORDS = [
"interpret",
"解释",
"解读",
"reading",
"reader",
"rule",
"rules",
"规则",
"template",
"模板",
"case",
"案例",
"bphs",
"parashara",
"parasara",
"raman",
"jataka",
"saravali",
"phaladeepika",
"hora",
"house",
"宫",
"lord",
"主",
"yoga",
"saham",
"dasha",
"transit",
"career",
"profession",
"事业",
"wealth",
"finance",
"财富",
"marriage",
"relationship",
"婚",
"关系",
"timing",
"应期",
"event",
"预测",
"validation",
"校验",
"qa",
"workflow",
]
def build_report() -> dict[str, Any]:
source_pack = _existing_interpretation_source_pack()
@@ -63,6 +135,7 @@ def build_report() -> dict[str, Any]:
"summary": summary,
"layers": layers,
"runtime_source_refs": source_refs,
"full_classification": _build_full_classification(source_refs, layers),
"failures": failures,
"boundary": (
"This gate validates explicit source inventory wiring. It does not promote drafts "
@@ -71,6 +144,175 @@ def build_report() -> dict[str, Any]:
}
def _relative(path: Path) -> str:
return str(path.relative_to(ROOT))
def _should_skip(path: Path) -> bool:
return any(part in EXCLUDED_PARTS for part in path.parts)
def _iter_candidate_files() -> list[Path]:
items: list[Path] = []
for root_name in SCAN_ROOTS:
root = ROOT / root_name
if root.is_file():
items.append(root)
elif root.exists():
items.extend(path for path in root.rglob("*") if path.is_file())
return sorted(set(items))
def _is_candidate(path: Path) -> bool:
if _should_skip(path) or path.suffix.lower() not in TEXT_EXTENSIONS:
return False
rel = _relative(path).lower()
name = path.name.lower()
if any(keyword.lower() in rel or keyword.lower() in name for keyword in CANDIDATE_KEYWORDS):
return True
if path.stat().st_size > 300_000:
return False
try:
text = path.read_text(encoding="utf-8", errors="ignore")[:4000].lower()
except OSError:
return False
return any(keyword.lower() in text for keyword in CANDIDATE_KEYWORDS)
def _classify_candidate(path: str, runtime_source_refs: set[str], layer_refs: set[str]) -> dict[str, Any]:
if path in runtime_source_refs:
return {
"classification": "runtime_reference_layer",
"priority": "runtime",
"promotion_status": "already_wired",
"reason": "Already exposed through interpretation_source_pack.source_refs.",
}
if path in layer_refs:
return {
"classification": "indexed_reference_layer",
"priority": "runtime",
"promotion_status": "indexed",
"reason": "Indexed by the interpretation source inventory.",
}
if path.startswith("references/real_case_studies/"):
return {
"classification": "real_case_calibration",
"priority": "priority_1",
"promotion_status": "reference_layer_candidate",
"reason": "Real-case material should be reviewed before confidence calibration claims.",
}
if path.startswith("references/open_source_sources/rishi-ai-mcp/"):
return {
"classification": "open_source_reference",
"priority": "priority_1",
"promotion_status": "reference_layer_candidate",
"reason": "User-prioritized open-source skill/workflow corpus; must remain license-aware.",
}
if path.startswith("references/open_source_sources/vedic-astro-skills/"):
return {
"classification": "open_source_reference",
"priority": "priority_1",
"promotion_status": "reference_layer_candidate",
"reason": "User-prioritized open-source Jyotish skills corpus; classify before selective reuse.",
}
if path.startswith("references/open_source_sources/"):
return {
"classification": "open_source_reference",
"priority": "priority_2",
"promotion_status": "reference_layer_candidate",
"reason": "Open-source reference corpus; classify with license boundary before runtime use.",
}
if path.startswith("references/oracle/"):
return {
"classification": "oracle_artifact",
"priority": "priority_2",
"promotion_status": "oracle_evidence_only",
"reason": "External evidence artifact; do not convert into interpretive rule text.",
}
if path.startswith("references/"):
return {
"classification": "reference_candidate",
"priority": "priority_1",
"promotion_status": "reference_layer_candidate",
"reason": "Core references directory; review for source-of-truth or reference-layer promotion.",
}
if path.startswith("docs/research/local_drafts/"):
return {
"classification": "quarantined_draft",
"priority": "priority_3",
"promotion_status": "not_truth_source",
"reason": "Local draft; index for awareness but do not promote without explicit review.",
}
if path.startswith("docs/research/"):
return {
"classification": "research_governance",
"priority": "priority_3",
"promotion_status": "governance_or_history",
"reason": "Research/governance history; useful for audit, not direct interpretation truth.",
}
if path.startswith("docs/benchmark/") or path.startswith("benchmarks/") or path.startswith("benchmark/"):
return {
"classification": "benchmark_evidence",
"priority": "priority_2",
"promotion_status": "benchmark_evidence_only",
"reason": "Benchmark or evidence report; use for validation boundaries, not direct rules.",
}
if path.startswith("jyotish-app/"):
return {
"classification": "frontend_surface",
"priority": "priority_3",
"promotion_status": "product_surface",
"reason": "Frontend implementation or copy surface; classify separately from source truth.",
}
if path.startswith("assets/"):
return {
"classification": "template_asset",
"priority": "priority_2",
"promotion_status": "template_reference",
"reason": "Reusable template asset; can guide output structure but is not a rule source.",
}
return {
"classification": "project_governance",
"priority": "priority_3",
"promotion_status": "governance_or_history",
"reason": "Project-level planning/governance material.",
}
def _build_full_classification(source_refs: list[str], layers: dict[str, Any]) -> dict[str, Any]:
runtime_source_refs = set(source_refs)
layer_refs: set[str] = set()
for layer in layers.values():
if isinstance(layer, dict):
refs = layer.get("source_refs")
if isinstance(refs, list):
layer_refs.update(str(ref) for ref in refs)
candidate_paths = [_relative(path) for path in _iter_candidate_files() if _is_candidate(path)]
by_path = {
path: _classify_candidate(path, runtime_source_refs, layer_refs)
for path in candidate_paths
}
classification_counts: dict[str, int] = {}
priority_bucket_counts: dict[str, int] = {}
promotion_status_counts: dict[str, int] = {}
for item in by_path.values():
classification_counts[item["classification"]] = classification_counts.get(item["classification"], 0) + 1
priority_bucket_counts[item["priority"]] = priority_bucket_counts.get(item["priority"], 0) + 1
promotion_status_counts[item["promotion_status"]] = promotion_status_counts.get(item["promotion_status"], 0) + 1
return {
"status": "classified",
"candidate_count": len(candidate_paths),
"classified_candidate_count": len(by_path),
"unclassified_candidate_count": 0,
"classification_counts": dict(sorted(classification_counts.items())),
"priority_bucket_counts": dict(sorted(priority_bucket_counts.items())),
"promotion_status_counts": dict(sorted(promotion_status_counts.items())),
"by_path": by_path,
"boundary": "Classification is a triage map; promotion still requires source review and tests.",
}
def main() -> int:
report = build_report()
print(json.dumps(report, ensure_ascii=False, indent=2))