#!/usr/bin/env python3
"""Is any REFUTED claim still asserted, unmarked, elsewhere in the corpus?

`REFUTED.md` publishes deaths; it does not enforce them. `sylpheed-port`'s
`check-claims` register fails their run when a refuted claim is quoted without a
`[refuted]` token, and feeding it four withdrawals immediately flagged three still
asserted unmarked -- every one inside a correction they had written themselves.
Their point is the one worth stealing: **the token tests for something an author
must place, not for language that sounds retracted.** All three read as
corrections to a human and the marker fired anyway.

This is the equivalent for a prose corpus. For each `* "claim"` in REFUTED.md it
searches `docs/` for that exact claim text and reports every occurrence whose
neighbourhood carries no refutation marker.

⚠️ Its known weakness, stated rather than discovered: it matches the claim's
EXACT wording. A restatement in different words is invisible to it. So a clean run
means "no verbatim revival", not "no revival".

    check_refuted.py [--context N]
"""
import re
import sys
from pathlib import Path

MARKERS = ("refuted", "REFUTED", "withdrawn", "WITHDRAWN", "retracted", "RETRACTED",
           "🔴", "~~", "used to say", "used to read", "was wrong", "is wrong",
           "no longer", "superseded", "corrected", "retracts", "an earlier version",
           # text explicitly DECLINING to revive a claim reads as an assertion to
           # a neighbourhood scan; two real hits were exactly this.
           "does **not** revive", "does not revive")

# ⚠️ STRUCTURAL LIMIT, found by running this against the corpus. `BACKLOG.md` is an
# APPEND-ONLY DATED LOG: an entry under a 2026-08-12 header recording what was
# believed then is history, not revival, and reads identically to a live claim.
# A neighbourhood-language detector cannot separate "asserted now" from "recorded
# as believed then". sylpheed-port's `check-claims` avoids this by testing for a
# TOKEN AN AUTHOR MUST PLACE rather than for language -- their design is right and
# this one is a weaker approximation of it. Files that are chronological records
# are skipped rather than reported, and that is a real hole, not a fix.
CHRONOLOGICAL = {"BACKLOG.md"}
CTX = int(sys.argv[sys.argv.index("--context") + 1]) if "--context" in sys.argv else 4

root = Path("docs")
ref = root / "re" / "REFUTED.md"
claims = []
seen_report = set()
for line in ref.read_text().splitlines():
    m = re.match(r'\s*\*\s*~?~?"([^"]{25,})"', line)
    if m:
        claims.append(m.group(1))

print(f"{len(claims)} quoted claims in REFUTED.md\n")
hits = 0
suppressed = []
seen_marked = set()
for c in claims:
    needle = c.strip()
    for f in root.rglob("*.md"):
        if f == ref or f.name in CHRONOLOGICAL:
            continue
        lines = f.read_text(errors="replace").splitlines()
        for i, l in enumerate(lines):
            if needle in l:
                lo, hi = max(0, i - CTX), min(len(lines), i + CTX + 1)
                # ⚠️ A +-CTX neighbourhood misses the commonest real marker: a
                # SECTION HEADER that retracts a whole list. Two false positives
                # were exactly this -- bullets under "## 🔴 What this retracts",
                # each bullet a claim being killed, no marker within 4 lines.
                # Scope, not proximity, is what marks them, so include the
                # nearest preceding header in the scan.
                hdr = ""
                for j in range(i, -1, -1):
                    if re.match(r"#{1,4} ", lines[j]):
                        hdr = lines[j]
                        break
                near = "\n".join(lines[lo:hi]) + "\n" + hdr
                marked = any(m.lower() in near.lower() for m in MARKERS)
                if marked:
                    # dedup like the reported path: two registered claims can be
                    # substrings of one line, which printed it twice.
                    if (f, i) not in seen_marked:
                        seen_marked.add((f, i))
                        suppressed.append((f, i + 1, needle, l.strip()))
                    continue
                if (f, i) not in seen_report:
                    seen_report.add((f, i))
                    hits += 1
                    print(f"🔴 {f}:{i+1}")
                    print(f'   claim: "{needle[:80]}"')
                    print(f"   line : {l.strip()[:110]}\n")
print(f"{hits} unmarked assertion(s) of a refuted claim")

# 🔴 A CLEAN RUN IS NOT A PASS, and until 2026-08-30 it was reported as though it
# were. Measured: 8 of 8 mentions of a registered claim in this corpus are
# suppressed by marker language, so the count above was 0 whether or not any of
# them was a live revival. A planted REAL revival, written into a paragraph that
# merely discussed corrections, was missed silently -- the marker words in the
# surrounding prose vouched for it.
#
# sylpheed-port's token-based hook has the opposite bias: it OVER-reports on
# well-written corrections, which is the safe direction. This one under-reports,
# which is not. So the suppressed set is printed rather than hidden.
print(f"{len(suppressed)} mention(s) suppressed by nearby marker language "
      f"-- NOT verified, only vouched for by neighbouring prose")
if "--show-marked" in sys.argv:
    for f, ln, c, l in suppressed:
        print(f"   · {f}:{ln}\n     claim: \"{c[:70]}\"\n     line : {l[:100]}")
elif suppressed:
    print("   re-run with --show-marked to read them")