goldeneye-pc-port/tools_pc/gen_findings_index.py

#!/usr/bin/env python3
"""Generate docs/dev/findings-index.csv from the §F/§H tables in findings.md.

Agentic speed-ups plan Step 4 / R8: findings.md is ~200 KB. Agents should grep
this CSV (label, status, one-liner) to decide *which* Dxx entries to actually
read, instead of linear-reading the log.

Heuristic parser: every markdown table row whose first cell matches a Dxx
label (`D12`, `D88.4`, `D75 · D77`, `D24-D30`, ...). The topic cell is
truncated to a one-liner; the status cell is normalised to a short bucket
(RESOLVED / OPEN / FIXED / PARTIAL / PROPOSED / ?) with the raw text kept.

Usage:
    python tools_pc/gen_findings_index.py            # write the CSV
    python tools_pc/gen_findings_index.py --check     # exit 1 if stale
    python tools_pc/gen_findings_index.py --stdout     # print, don't write
"""
from __future__ import annotations

import csv
import io
import re
import sys
from pathlib import Path

ROOT = Path(__file__).resolve().parent.parent
SRC = ROOT / "docs" / "dev" / "findings.md"
OUT = ROOT / "docs" / "dev" / "findings-index.csv"

LABEL_RE = re.compile(r"^D\d+(?:\.\d+)?(?:[-–]D\d+)?(?:\s*[·,]\s*D\d+(?:\.\d+)?)*\+?$")

STATUS_BUCKETS = [
    ("FIXED", re.compile(r"\bfixed\b", re.I)),
    ("RESOLVED", re.compile(r"\bresolved\b", re.I)),
    ("PARTIAL", re.compile(r"\bpartial|clamp landed|landed\b|safety-net", re.I)),
    ("PROPOSED", re.compile(r"\bproposed|not applied|design\b", re.I)),
    ("OPEN", re.compile(r"\bopen\b|not started|awaiting|owed|pending", re.I)),
]


def one_liner(cell: str, limit: int = 160) -> str:
    """Strip markdown emphasis/code and collapse to a single short line."""
    txt = cell.replace("**", "").replace("`", "")
    txt = re.sub(r"\[([^\]]+)\]\([^)]+\)", r"\1", txt)  # [t](u) -> t
    txt = re.sub(r"\s+", " ", txt).strip()
    # first sentence-ish
    m = re.match(r"(.{20,}?[.—:])\s", txt)
    if m and len(m.group(1)) <= limit:
        txt = m.group(1)
    if len(txt) > limit:
        txt = txt[: limit - 1].rstrip() + "…"
    return txt


LEAD_RE = re.compile(
    r"^\**\s*(OPEN|RESOLVED|FIXED|PROPOSED|PARTIAL|LANDED|CLAMP|DISPROVEN"
    r"|ROOT-CAUSED|GUARDED|ANALYZED|DIAGNOSTIC SHIPPED|NOT A BUG|CLOSED)",
    re.I,
)


def bucket(status_cell: str) -> str:
    # An explicit leading verdict token wins over prose keywords deeper in the
    # cell (e.g. "OPEN (parked). ... D168 fixed ..." is OPEN, not FIXED).
    lead = LEAD_RE.match(status_cell.strip())
    if lead:
        tok = lead.group(1).upper()
        return {
            "LANDED": "PARTIAL",
            "CLAMP": "PARTIAL",
            "DISPROVEN": "RESOLVED",
            "ROOT-CAUSED": "RESOLVED",
            "GUARDED": "PARTIAL",
            "ANALYZED": "PARTIAL",
            "DIAGNOSTIC SHIPPED": "PARTIAL",
            "NOT A BUG": "RESOLVED",
        }.get(tok, tok)
    for name, rx in STATUS_BUCKETS:
        if rx.search(status_cell):
            return name
    return "?"


def split_row(line: str) -> list[str] | None:
    line = line.strip()
    if not line.startswith("|"):
        return None
    # split on '|' that is not inside backticks
    cells, buf, tick = [], [], False
    for ch in line:
        if ch == "`":
            tick = not tick
            buf.append(ch)
        elif ch == "|" and not tick:
            cells.append("".join(buf))
            buf = []
        else:
            buf.append(ch)
    cells.append("".join(buf))
    cells = [c.strip() for c in cells]
    # leading/trailing empty from outer pipes
    if cells and cells[0] == "":
        cells = cells[1:]
    if cells and cells[-1] == "":
        cells = cells[:-1]
    return cells or None


def rows():
    section = None
    for raw in SRC.read_text(encoding="utf-8").splitlines():
        h = re.match(r"^#+\s+([A-Z])\.\s", raw) or re.match(r"^#+\s.*§?([FH])\b", raw)
        if raw.startswith("### ") and re.search(r"\b([FH])\.", raw):
            section = re.search(r"\b([FH])\.", raw).group(1)
        cells = split_row(raw)
        if not cells or len(cells) < 2:
            continue
        label = cells[0].replace("–", "-")
        if not LABEL_RE.match(cells[0]):
            continue
        topic = cells[1]
        status = cells[2] if len(cells) > 2 else ""
        yield {
            "label": label,
            "bucket": bucket(status),
            "one_liner": one_liner(topic),
            "status_raw": one_liner(status, 200) if status else "",
        }


def build_csv() -> str:
    buf = io.StringIO()
    w = csv.DictWriter(
        buf, fieldnames=["label", "bucket", "one_liner", "status_raw"], lineterminator="\n"
    )
    w.writeheader()
    seen = set()
    for r in rows():
        key = r["label"]
        if key in seen:
            continue
        seen.add(key)
        w.writerow(r)
    return buf.getvalue()


def main() -> int:
    args = set(sys.argv[1:])
    text = (
        "# GENERATED by tools_pc/gen_findings_index.py -- do not hand-edit.\n"
        "# Grep this to pick which findings.md entries to read; it is not authoritative.\n"
        + build_csv()
    )
    if "--stdout" in args:
        sys.stdout.write(text)
        return 0
    want = text.encode("utf-8")
    if "--check" in args:
        cur = OUT.read_bytes() if OUT.exists() else b""
        if cur != want:
            sys.stderr.write("findings-index.csv is stale: re-run gen_findings_index.py\n")
            return 1
        return 0
    OUT.write_bytes(want)
    print(f"wrote {OUT.relative_to(ROOT)} ({text.count(chr(10))} lines)")
    return 0


if __name__ == "__main__":
    raise SystemExit(main())