#!/usr/bin/env python3
"""Which negatives in this corpus are about the WORLD, and which about an INSTRUMENT?

The mission's third classification is "undecodable, WITH REACH" -- looked here,
here and here. A negative written as a property of the subject when what was
established is a property of the method is the failure that put
"an individual SE's audio is not extractable yet" at the head of a page whose own
later section located the waves, and left it quoted in INDEX for days
(data/index-vs-pages-audit.txt).

sylpheed-port swept their own docs for this and came back clean. Mine has not been
swept. This finds the candidate sentences; ⚠️ IT DOES NOT JUDGE THEM. A negative
IS allowed to be about the world -- "a 24-bit modulus cannot name an 8-character
identifier uniquely" is a fact, not a limitation of a tool. Every hit is read.

Scored, so the reading is ordered rather than exhaustive: a sentence that already
names an instrument, a search, or a reach is very likely fine.

    impossibility_scope.py [--all]
"""
import re, sys
from pathlib import Path

CLAIM = re.compile(
    r"[^.\n]*\b(?:not (?:extractable|recoverable|available|possible|decodable|knowable)"
    r"|cannot be (?:\w+ ){0,3}\w+|is impossible|are impossible|no \w+ exists"
    r"|nowhere on the disc|unrecoverable|not on the disc)\b[^.\n]*(?:\.|$)", re.I)
# words that SCOPE a negative to a method, a search or a reach
# ⚠️ "yet" and "so far" were in this list and are NOT scopes -- they are temporal
# HEDGES that name no instrument, no search and no place looked. That is exactly
# what made "an individual SE's audio is not extractable yet" read as bounded while
# claiming a property of the audio, and it is why this tool's own control failed
# twice before the list was right. A scope names a METHOD or a PLACE.
SCOPED = ("looked", "searched", "scan", "probe", "reach", "instrument", "harness",
          "this container", "with the tools", "our reader", "from the file",
          "from the disc", "from the image", "from the hash", "by sorting",
          "by counting", "by re-running", "by key list", "attack", "exhaustive",
          "we could not", "i could not", "could not find", "not found by", "tested")

files = sorted(Path("docs").rglob("*.md"))
hits = []
for f in files:
    if f.name in ("REFUTED.md", "METHOD.md"):
        continue          # these are ABOUT dead claims; quoting one is not asserting it
    for n, line in enumerate(f.read_text(errors="replace").splitlines(), 1):
        for m in CLAIM.finditer(line):
            s = m.group(0).strip()
            if len(s) < 30:
                continue
            scoped = sum(1 for w in SCOPED if w in s.lower())
            hits.append((scoped, f, n, s))

hits.sort(key=lambda h: h[0])
show = hits if "--all" in sys.argv else [h for h in hits if h[0] == 0]
print(f"{len(hits)} negative claim(s); {sum(1 for h in hits if h[0]==0)} name no "
      f"instrument, search or reach in the same sentence.\n")
for scoped, f, n, s in show[:40]:
    print(f"  {f}:{n}")
    print(f"      {s[:150]}")

# 🔴 CONTROL, and it must pass before any output above is believed. The one known
# instance of this defect in this corpus was a HEADING -- "an individual SE's audio
# is not extractable yet" -- and the first version of this regex required a
# sentence-ending period, so it matched NOTHING in any heading and would have
# reported the corpus clean. Run the control after every edit to the pattern.
KNOWN = "## \u2754 And a new negative: an individual SE's audio is not extractable yet"
_m = CLAIM.search(KNOWN)
print("\ncontrol -- the known true positive (a heading, since fixed):")
if not _m:
    print("  \U0001F534 CONTROL FAILED: the pattern does not match it. Nothing above means anything.")
else:
    _sc = [w for w in SCOPED if w in _m.group(0).lower()]
    print(f"  matched; scope words {_sc} -> {'HIDDEN by scoring' if _sc else 'shown'}")
    if _sc:
        print("  \U0001F534 CONTROL FAILED: scored as scoped, so it would not appear in the default listing.")

# 🔴 The control above PRINTED its failure and this script exited 0 -- so a broken
# control was indistinguishable from a passing one to anything but a human reading
# the last line. Fixed 2026-08-31, the same day the tool was written, after
# sylpheed-port reported the identical shape in their own suite. The LISTING is a
# prompt and never fails; the CONTROL failing is a hard error, because every hit
# above is meaningless without it.
if (not _m) or [w for w in SCOPED if w in _m.group(0).lower()]:
    sys.exit(2)