troupe-standup/tools/doc_census_check.py

#!/usr/bin/env python3
"""doc_census_check.py -- does a tool's own docstring census match the census
that tool PRINTS?

WHY THIS EXISTS
  This archive's three scanners each carry a census table in their module
  docstring: counts that a reader cites, that no command checks. The docstring
  is prose; prose is not executed. On 2026-10-16 the control plane returned
  exactly this defect against a sibling scanner, in its own words:

    "The scanner's own docstring carries a number that does not match the
     census it prints -- the exact class the tool exists to catch."

  tools/citation_resolve_check.py said `471 UNRESOLVED` on one line and
  `441 UNRESOLVED` nine lines later, over a census the tool prints as 471.
  Nothing was checking the docstring against the output beside it. That is this
  tool's whole job.

WHAT IT MEASURES (read-only: this tool only writes --json)
  Two independent verdicts per tool, and they do not share evidence.

  1. INTERNAL SPLIT -- no oracle, no run. Within one docstring, every numeric
     claim of the form `<value> <unit>` is collected; two claims of ONE unit
     that a single revision scope covers, carrying two different values, is a
     split. This is the verdict that catches the 441/471 instance, and it is
     why the tool is useful with no subprocess at all.

  2. ORACLE -- the tool is RUN, at the revision its own docstring names, and
     each claim is compared against the value that run prints for that unit.
       MATCHES       claim == printed value
       STALE         claim != printed value, and the printed unit is not
                     declared clone-local -- a defect claim
       CLONE_LOCAL   claim != printed value but the tool's own output marks
                     that unit clone-local ("blobs in THIS clone's local object
                     store"), so drift is the documented expectation, not a
                     defect. Reported, never counted as one.
       AMBIGUOUS     the tool prints that unit with 2+ values at that rev
                     (e.g. `citations` prints once per section), so there is no
                     single oracle value; both are printed and no claim is made
       NOT_PRINTED   the unit does not appear in this tool's output at all

  A claim is `<digits> <unitword>` with the unit word ADJACENT, which is the
  archive's own notation. A bare number is not a claim and is not checked.

TWO ORACLE LEGS, AND WHY THE SECOND ONE EXISTS
  Leg 1 is the tool's own run at the block's revision, exactly as above. Leg 2
  is the SAME TOOL'S `--selftest`, added 2026-10-16 after the control plane
  returned a docstring claim of `13 cells` against a selftest that prints `18
  cells` -- the defect class this tool exists to catch, sitting inside its own
  default scope and still read as NOT_PRINTED, because no leg ever passed
  `--selftest` and a cell count is printed by nothing else. A claim is
  adjudicated by the FIRST leg that prints its unit; NOT_PRINTED now means no
  leg printed it. A tool that takes no `--selftest` simply has one leg -- a fact
  about the tool, not a defect in it.

  A leg that exits non-zero having printed nothing is reported RUN_FAILED, never
  read as an empty census, and it adjudicates nothing either: the block's claims
  are still read off any surviving leg -- leg 2 -- and are left unadjudicated
  only when no leg survives, because a failed run is not a reason to stop
  looking. A revision that will not materialise fails the same way rather than
  producing a census at all: an empty queue is a census of zeros, and reading it
  as that revision's census is the phantom this rule refuses.

  A HEX RUN INTRODUCED AS A DIGEST IS NOT A REVISION. A block that quotes a
  truncated sha256 in its prose is a size, not a place: read as a rev it files
  the block under a revision that cannot exist, fails that leg, and then
  adjudicates every claim in the block again beside the real ones. Two signals
  are read, both local to the token -- a digest word in front of it (`sha256
  <hex>`, `hash <hex>`), or an ellipsis behind it (`<hex>…`), which is how this
  archive writes a truncated digest. See `block_revs`.

  The run leg is `<script> --repo R --rev REV`. A tool that takes no `--rev`
  answers it with an argparse diagnosis and prints no census at all, so the leg
  is re-run with the rejected flags DROPPED -- the exact tokens argparse named,
  and only those -- and is tagged `no-rev`; a recipe's leg may carry the same tag
  for the same reason. Such a tool measures the tree it is POINTED AT, so a claim
  in a block that names a revision is reported REV_UNCHECKED -- never counted as
  verified against that revision, and never counted as a defect -- while a block
  that names no revision is checked normally, since the default is what the flag
  means there.

THIS TOOL DOES NOT RUN ITSELF. The default scope is every `tools/*.py` in the
  tree, and this tool is one of them. Running it on itself spawns it, which
  spawns it again, without a floor -- measured, not reasoned, in the check-in of
  2026-10-16. The self target is therefore excluded from the run leg and every
  one of its claims is reported SELF_NOT_RUN. It is deliberately still listed in
  the scanned set, so the exclusion is a printed row and not a silence.

SCOPE, STATED RATHER THAN IMPLIED
  Only module docstrings of .py tools are scanned: a docstring is where a census
  table lives. Only revisions NAMED IN THE BLOCK are used as oracles -- a block
  naming no revision is checked against the tool's default (HEAD) and tagged, so
  a stale rev is never silently attributed. A tool whose subject is not `--repo`
  + `--rev` is driven through a per-tool recipe declared below, with a temp file
  that is removed: `queue_claim_check.py` takes a materialised QUEUE file and so
  its leg IS the revision, while `append_only_owners.py` takes a tree scan that
  no flag can pin to a revision, so its leg is tagged `no-rev`. A tool no recipe
  covers, and that answers `--repo ... --rev ...` with an argparse diagnosis, is
  re-run with the rejected flags dropped and tagged the same way -- measured at
  HEAD on 2026-10-16 against `check_lint.py`, which takes neither flag and whose
  default census is a real one.

  WHAT THIS DOES NOT CHECK, and the measured size of the gap. A claim is only
  adjudicated when the unit it names is a unit the tool PRINTS. Over the three
  scanners at d355395 the run read ninety-two claims: twelve were verified
  against the run they point at, eight were in units the tool prints with two
  values (SECTION_SPLIT_BY_TOOL -- no oracle), and seventy-one were in units the
  tool never prints at all. So the oracle's reach is narrow and its precision is
  the reason: it reported exactly one bad claim on that corpus, and that one was
  the returned defect. A wider rule was tried first and falsified by its own
  first run -- num_agreement_check.py flagged a hundred and seventeen
  restatements across the archive, too coarse to be read -- so the narrow rule
  is the one that ships. Two claim forms are read (`<value> <unit>` and
  `<unit>: <value>`); a claim written in neither form is not seen, and that is a
  stated gap, not a silent one.

  NO CENSUS OF THIS TOOL'S OWN VERDICTS APPEARS IN THIS DOCSTRING, deliberately:
  this scanner scans itself, so a count of its own output written here would
  have to agree with the output of the run that the same commit changes. That is
  the limit citation_hash_class.py records in the same words -- a commit cannot
  measure the file it introduces -- and here it is avoided rather than
  discovered.

USAGE
  python3 doc_census_check.py [--repo DIR] [--rev HEAD] [--tools NAME...]
      [--json OUT] [--no-run] [--selftest]   # selftest: 33 cells, one per claim class
"""
import argparse
import ast
import collections
import json
import os
import re
import subprocess
import sys
import tempfile

DEFAULT_REPO = "/root/troupe-standup"

# A claim, in either of the two forms this archive writes:
#   `<value> <unit>`      -- "471 UNRESOLVED", "1,612 citations"
#   `<unit> [: =] <value>` -- "ACS = 72", "overlap = 20" (markdown bold allowed)
# A bare number is not a claim. Deliberately not "any word": `471 cannot be
# resolved` is prose, and a checker that flags prose is a checker nobody reads.
CLAIM = re.compile(
    r"(?<![0-9A-Za-z_.])(?P<num>[0-9][0-9,]*)(?P<sep>[^A-Za-z0-9\n]{0,2})"
    r"(?P<unit>[A-Za-z_][A-Za-z0-9_]*|[A-Z][A-Z_]{2,})\b")
CLAIM_EQ = re.compile(
    r"(?P<unit>[A-Za-z_][A-Za-z0-9_]*)\s*[:=]\s*\**\s*(?P<num>[0-9][0-9,]*)")
REV_LONG = re.compile(r"\b[0-9a-f]{7,40}\b")

# A hex run introduced as a DIGEST is not a revision, and reading it as one costs
# more than a wrong label: the block is filed under a revision that cannot exist,
# its leg fails, and then every claim in the block is adjudicated once per
# spurious rev beside the real ones. Measured 2026-10-16 at HEAD on
# `tools/queue_claim_check.py`, whose UNITS block quotes the queue's size as
# "/ sha256 `fbe51445a89f81ab…`": three claims emitted FOUR times, once per
# REV_LONG token, and two `git show <sha256-prefix>:WORK-QUEUE.md` leg failures.
# Two signals, both local to the token: a digest word in front of it (sha256,
# sha1, md5, digest, hash), or an ellipsis behind it -- the archive's own way of
# writing a truncated digest. A revision cited in the ordinary way carries
# neither, and a FULL sha256 is already invisible to REV_LONG: the run has no
# word boundary to bite on.
DIGEST_BEFORE = re.compile(
    r"(?:sha[-\s]?256|sha[-\s]?1|md5|digest|hash)\s*[:=]?\s*[`'\"]?\s*$", re.I)
DIGEST_AFTER = re.compile(r"^[`'\"]?\s*(?:…|\.\.\.)")


def block_revs(text):
    """The revisions a block names -- hex runs read as digests excluded."""
    out = set()
    for m in REV_LONG.finditer(text):
        if DIGEST_BEFORE.search(text[:m.start()]) or \
                DIGEST_AFTER.match(text[m.end():]):
            continue
        out.add(m.group(0))
    return sorted(out)

# Function words and units this tool does not adjudicate. `at` in "2026-10-15 at
# rev 9188dd3" is not a census quantity; neither is `B` (bytes differ by
# revision by design, and "1,201,550 B" is a size, not a count). Stated so the
# exclusion is a rule rather than a habit.
STOPWORDS = {
    "at", "the", "of", "in", "is", "are", "was", "and", "or", "to", "for", "on",
    "by", "as", "it", "its", "that", "this", "these", "those", "with", "from",
    "no", "not", "one", "two", "three", "all", "any", "be", "been", "has",
    "have", "had", "his", "her", "our", "your", "their", "but", "if", "then",
    "than", "so", "up", "out", "off", "over", "into", "run", "runs", "may",
    "can", "same", "each", "both", "per", "via", "b", "kb", "mb", "gb",
}

# How to run each tool at a revision. Any tool not listed here is run as
# `<script> --repo R --rev REV`. A recipe returns `(argv, tag)` and the tag says
# whether the recipe could materialise the revision the block names.
#
#   queue_claim_check.py  takes no --rev: its subject is a FILE, and the file is
#     materialised at the revision and handed to it -- so the leg IS that rev.
#     A revision that will NOT materialise is a raised failure, never an empty
#     file: an empty queue is a census of zeros, and a census of zeros reads as
#     that revision's census. Measured 2026-10-16 -- `git show
#     c3b4a290dc64bd24:WORK-QUEUE.md` (a sha256 prefix REV_LONG read as a rev)
#     exits 128, and the leg it fed printed `0 opening records` at rc 0.
#   append_only_owners.py takes a positional AUDIT.json and nothing else: its
#     input is a tree scan, which its sibling produces over the WORKING TREE
#     (`append_only_audit.py` has no --rev either). This scanner is read-only, so
#     it will not add a git worktree to the repository it is only allowed to
#     read: the leg is tagged no-rev and every claim in a block that names a
#     revision is reported REV_UNCHECKED, never adjudicated against a tree it
#     did not stand on.
def _recipe_queue(repo, rev, tmpdir):
    dst = os.path.join(tmpdir, f"WORK-QUEUE.{rev}.md")
    p = subprocess.run(["git", "-C", repo, "show", f"{rev}:WORK-QUEUE.md"],
                       capture_output=True)
    if p.returncode != 0:
        raise RuntimeError("git show %s:WORK-QUEUE.md -> rc=%d: %s"
                           % (rev, p.returncode,
                              p.stderr.decode("utf-8", "replace").strip()[:120]))
    with open(dst, "wb") as fh:
        fh.write(p.stdout)
    return ["--queue", dst, "--census"], ""


def _recipe_owners(repo, rev, tmpdir):
    dst = os.path.join(tmpdir, f"append-only-audit.{rev}.json")
    subprocess.run([sys.executable,
                    os.path.join(repo, "tools", "append_only_audit.py"),
                    "--repo", repo, "--json", dst], capture_output=True)
    return [dst], "no-rev"


RECIPES = {"queue_claim_check.py": _recipe_queue,
           "append_only_owners.py": _recipe_owners}


def git(repo, *a):
    return subprocess.run(["git", "-C", repo, *a], capture_output=True).stdout


def docstring_span(path, text):
    try:
        tree = ast.parse(text)
    except SyntaxError:
        return None
    if not tree.body or not isinstance(tree.body[0], ast.Expr):
        return None
    node = tree.body[0]
    if not isinstance(node.value, ast.Constant) or not isinstance(node.value.value, str):
        return None
    return node.lineno, node.end_lineno


def blocks(lines, lo, hi):
    """Blank-line-delimited paragraphs -- the same scope the sibling scanners
    use (citation_resolve_check.py for inheritance, num_agreement_check.py for
    quantity agreement), so one paragraph is one scope in all three."""
    start, buf = lo, []
    for ln in range(lo, hi + 1):
        raw = lines[ln - 1]
        if raw.strip() == "":
            if buf:
                yield start, buf
            buf, start = [], ln + 1
        else:
            buf.append((ln, raw))
    if buf:
        yield start, buf


# ------------------------------------------------- printed census -> oracle
def parse_printed(stdout):
    """stdout -> {unit: {value: [line, ...]}} plus the set of clone-local units.

    Four line shapes are read, all of them the scanners' own:
      `  RESOLVES        113`      indented label then count (family rows)
      `  citations: 410`           label then count
      `corpus: 307 files at ...`   count then unit
      `overlap A&B = 20 ; ...`     inline assignments, split on the separators
    A unit whose printed line (or the line above it, for a wrapped phrase) says
    "clone" is clone-local: its count is expected to move with the clone.
    """
    units = collections.defaultdict(lambda: collections.defaultdict(list))
    clone = set()
    lines = stdout.split("\n")

    def add(unit, value, ln, cloneline):
        u = unit.strip().lower()
        if len(u) < 3 or not re.fullmatch(r"[a-z_][a-z0-9_]*", u) or u in STOPWORDS:
            return
        units[u][value].append(ln)
        if "clone" in cloneline.lower():
            clone.add(u)

    for i, raw in enumerate(lines, 1):
        ctx = raw + " " + (lines[i - 2] if i >= 2 else "")
        m = re.match(r"^\s{2,}([A-Za-z_][A-Za-z0-9_]*)\s+([0-9][0-9,]*)\s*$", raw)
        if m:                                        # family row: label  count
            add(m.group(1), int(m.group(2).replace(",", "")), i, ctx)
            continue
        m = re.match(r"^\s*([A-Za-z_][A-Za-z0-9_]*)\s*[:=]\s*([0-9][0-9,]*)\b", raw)
        if m:                                        # label: count
            add(m.group(1), int(m.group(2).replace(",", "")), i, ctx)
        for m in re.finditer(r"([0-9][0-9,]*)\s+(?:[a-z]+ )?([A-Za-z_][A-Za-z0-9_]*)\b", raw):
            add(m.group(2), int(m.group(1).replace(",", "")), i, ctx)
        for seg in re.split(r"[;]", raw):            # inline `X = N`
            m = re.match(r"^\s*(.*?)\s*[:=]\s*([0-9][0-9,]*)\s*$", seg)
            if not m or not m.group(1):
                continue
            words = re.findall(r"[A-Za-z_][A-Za-z0-9_]*", m.group(1))
            if not words:
                continue
            val = int(m.group(2).replace(",", ""))
            add("_".join(w.lower() for w in words), val, i, ctx)   # whole phrase
            add(words[-1], val, i, ctx)      # the nearest label: `overlap A&B`
        # the scanners' own unit declaration: `... 6961 (unit: occurrences)`.
        # The unit is named AFTER its number, which no other rule reads.
        for m in re.finditer(r"\(\s*unit\s*:\s*([A-Za-z_][A-Za-z0-9_]*)\s*\)", raw):
            left = raw[:m.start()]
            nums = re.findall(r"([0-9][0-9,]*)\s*$", left.rstrip())
            if nums:
                add(m.group(1), int(nums[-1].replace(",", "")), i, ctx)
    return {k: dict(v) for k, v in units.items()}, clone


def claims_in(blk):
    """[(line, value, unit, token, offset)] for one block.

    Both claim forms are read and a claim found by both is reported once. The
    offset is measured on the block text so a RESTATEMENT (far apart) can be
    told from an ENUMERATION of neighbouring sub-counts, the same
    discrimination num_agreement_check.py applies.
    """
    out, off = [], 0
    for ln, raw in blk:
        found = {}
        for m in CLAIM.finditer(raw):
            u = m.group("unit")
            if len(u) < 3 or u.lower() in STOPWORDS or re.fullmatch(r"[qQ]\d+", u):
                continue
            found[m.start()] = (int(m.group("num").replace(",", "")), u, m.group(0))
        for m in CLAIM_EQ.finditer(raw):
            u = m.group("unit")
            if (len(u) < 3 or u.lower() in STOPWORDS
                    or re.fullmatch(r"[qQ]\d+", u) or m.start() in found):
                continue
            if m.start() and re.match(r"[0-9A-Za-z_.]", raw[m.start() - 1]):
                continue                      # `WORK-QUEUE.md:8586` is a citation
            found[m.start()] = (int(m.group("num").replace(",", "")), u, m.group(0))
        for pos in sorted(found):
            val, u, tok = found[pos]
            out.append((ln, val, u, tok, off + pos))
        off += len(raw) + 1
    return out


def is_label(unit):
    """An uppercase census label -- the vocabulary a split is checked in when
    the tool has not been run (no oracle available)."""
    return len(unit) >= 3 and re.fullmatch(r"[A-Z][A-Z_]*", unit) is not None


def keys_for(unit, printed):
    """Candidate oracle keys for a claimed unit word."""
    cands = [unit, unit.lower(), unit.lower().rstrip("s"), unit.upper()]
    seen, out = set(), []
    for c in cands:
        if c.lower() in printed and c.lower() not in seen:
            seen.add(c.lower())
            out.append(c.lower())
    return out


def oracle(printed, clone, unit, value, tag=""):
    """(verdict, detail) for one claim; `printed` is one revision's map.

    `tag` names the leg a verdict came from when it is not leg 1 ("no-rev",
    "selftest"): a reader can then tell which census the number was read off.
    """
    keys = keys_for(unit, printed)
    vals = set()
    for k in keys:
        vals |= set(printed[k])
    if not vals:
        return "NOT_PRINTED", ""
    if len(vals) > 1:
        return "AMBIGUOUS", "printed: " + ", ".join(str(v) for v in sorted(vals))
    printed_val = vals.pop()
    if printed_val == value:
        return "MATCHES", ""
    if any(k in clone for k in keys):
        return "CLONE_LOCAL", f"printed {printed_val}" + (f" [{tag}]" if tag else "")
    return "STALE", f"printed {printed_val}" + (f" [{tag}]" if tag else "")


def adjudicate(legs, unit, value, block_revs):
    """The first leg that prints the unit adjudicates the claim.

    `legs` is [(printed, clone, tag)] in priority order: leg 1 (the run) first,
    then the selftest leg. NEITHER a `no-rev` leg NOR the selftest leg is a
    verifier for a block that names a revision: one measured a different tree,
    the other measured the tool's own fixtures. Such a claim is reported
    REV_UNCHECKED -- visible, counted as neither a match nor a defect.
    """
    for printed, clone, tag in legs:
        if not printed or not keys_for(unit, printed):
            continue
        if block_revs and tag == "no-rev":
            return "REV_UNCHECKED", ("block names %s; the tool takes no --rev, so this "
                                     "leg measured the working tree"
                                     % ",".join(block_revs))
        if block_revs and tag == "selftest":
            return "REV_UNCHECKED", ("block names %s; the selftest leg prints this "
                                     "tool's own fixtures, not a census at that "
                                     "revision" % ",".join(block_revs))
        return oracle(printed, clone, unit, value, tag)
    return "NOT_PRINTED", ""


# --------------------------------------------------------------- self-test
# Synthetic stdout, so the parsers and the verdicts are executed, not asserted.
FAKE_STDOUT = """\
corpus: 297 markdown files at babdadc in /root/troupe-standup
--- EXPLICIT `<path>:<line>` -- a CLAIM (unit: citations) ---
  citations: 410
  RESOLVES        113
  STALE_LINE      0
--- BARE `:<line>` -- a CANDIDATE, never a claim (unit: citations) ---
  citations: 1612
  UNRESOLVED      471
file mentions with no line: 6961 (unit: occurrences) -- these seed the scope
index: 871 blobs (unit: blobs in THIS clone's local object store), 680 commits
overlap A&B = 20 ; ACS-only = 52
"""
FAKE_DOC = """\
THE CENSUS AT HEAD, WITH ITS UNITS (measured 2026-10-16, rev babdadc, 297 .md)
    BARE     1612 citations: 255 EXTERNAL_NAMED / 471 UNRESOLVED.
  Read every figure as a citation count, never as a defect count: 441 UNRESOLVED
  is not 441 errors.

A SECOND BLOCK, no revision named, quoting 471 UNRESOLVED and nothing else.
"""

# Leg 2's shape: a selftest summary line, and nothing else. The cell count is
# printed here and nowhere else, which is why a claim about it needs this leg.
FAKE_SELFTEST = """\
c1 a NEW byte                            PASS
selftest: 18 cells, 18 passed, 0 failed
"""


def _fixture_checks():
    printed, clone = parse_printed(FAKE_STDOUT)
    ok = True
    cells, bad = [0], [0]

    def check(name, got, want):
        nonlocal ok
        good = got == want
        cells[0] += 1
        bad[0] += 0 if good else 1
        ok = ok and good
        print(f"{'PASS' if good else 'FAIL'} {name}")
        if not good:
            print(f"      got  {got}")
            print(f"      want {want}")

    check("parse: UNRESOLVED single", sorted(printed.get("unresolved", {})), [471])
    check("parse: citations ambiguous", sorted(printed.get("citations", {})), [410, 1612])
    check("parse: count-then-unit", sorted(printed.get("occurrences", {})), [6961])
    check("parse: one word skipped", sorted(printed.get("files", {})), [297])
    check("parse: clone-local marked", "blobs" in clone, True)
    # the phrase rule: `ACS-only = 52` must NOT register as the unit `acs`
    check("parse: inline phrase key", sorted(printed.get("acs_only", {})), [52])

    lines = FAKE_DOC.split("\n")
    got, first_block, revs_seen = [], [], set()
    for first, blk in blocks(lines, 1, len(lines)):
        revs = block_revs("\n".join(r for _, r in blk))
        revs_seen |= set(revs)
        for ln, val, unit, _tok, _pos in claims_in(blk):
            got.append((unit, val))
            if first == 1:
                first_block.append((unit, val))
    # the fixture that matters: one unit, one rev scope, two values -> a split
    check("claims: both UNRESOLVED values in one block",
          [uv for uv in first_block if uv[0] == "UNRESOLVED"],
          [("UNRESOLVED", 471), ("UNRESOLVED", 441)])
    check("claims: `471 cannot be resolved` is not a claim",
          any(u in ("cannot", "resolved") for u, _ in got), False)
    check("claims: the block's rev is read", "babdadc" in revs_seen, True)
    # the digest rule, one signal per cell, and the negative control between
    # them -- the text of each is the text of the defect, measured at HEAD
    check("revs: `sha256 <hex>` is a digest, not the block's revision",
          block_revs("queue 1,170,483 B / sha256 `c3b4a290dc64bd24`"), [])
    check("revs: an ellipsis-truncated hex run is a digest, not a revision",
          block_revs("at `28ca8e5` (1,193,681 B / `c3b4a290dc64bd24…`)"),
          ["28ca8e5"])
    check("revs: an ordinarily cited revision is still the block's revision",
          block_revs("Run 37 read (`29a4872`, queue 1,170,483 B) and `28ca8e5`"),
          ["28ca8e5", "29a4872"])
    check("oracle: 471 matches", oracle(printed, clone, "UNRESOLVED", 471),
          ("MATCHES", ""))
    check("oracle: 441 is stale", oracle(printed, clone, "UNRESOLVED", 441),
          ("STALE", "printed 471"))
    check("oracle: ambiguous unit makes no claim",
          oracle(printed, clone, "citations", 1612),
          ("AMBIGUOUS", "printed: 410, 1612"))
    check("oracle: clone-local is not a defect",
          oracle(printed, clone, "blobs", 1234), ("CLONE_LOCAL", "printed 871"))
    check("oracle: unprinted unit", oracle(printed, clone, "wombats", 3),
          ("NOT_PRINTED", ""))

    # ---- leg 2 (--selftest) and the leg rules. The first check is the defect
    #      the leg was added for: a docstring cell count the run leg cannot see.
    s2, s2c = parse_printed(FAKE_SELFTEST)
    check("selftest leg: the cell count is a printed unit", sorted(s2.get("cells", {})), [18])
    legs = [(printed, clone, "")] + [(s2, s2c, "selftest")]
    check("adjudicate: a cell count leg 1 cannot see is STALE, not NOT_PRINTED",
          adjudicate(legs, "cells", 13, []), ("STALE", "printed 18 [selftest]"))
    check("adjudicate: the corrected cell count matches",
          adjudicate(legs, "cells", 18, []), ("MATCHES", ""))
    check("adjudicate: leg 1 wins when both legs print the unit",
          adjudicate([(s2, s2c, ""), ({**s2, "cells": {99: [1]}}, s2c, "selftest")],
                     "cells", 99, []), ("STALE", "printed 18"))
    check("adjudicate: a no-rev leg does not verify a block that names a revision",
          adjudicate([(s2, s2c, "no-rev")], "cells", 18, ["f5403b2"]),
          ("REV_UNCHECKED", "block names f5403b2; the tool takes no --rev, so this "
                            "leg measured the working tree"))
    check("adjudicate: the selftest leg is not a verifier at a named revision",
          adjudicate([(s2, s2c, "selftest")], "cells", 18, ["f5403b2"]),
          ("REV_UNCHECKED", "block names f5403b2; the selftest leg prints this "
                            "tool's own fixtures, not a census at that revision"))
    check("adjudicate: a no-rev leg IS an oracle for a block naming no revision",
          adjudicate([(s2, s2c, "no-rev")], "cells", 13, []),
          ("STALE", "printed 18 [no-rev]"))
    check("adjudicate: no leg prints the unit -> NOT_PRINTED",
          adjudicate([(printed, clone, "")], "wombats", 3, []), ("NOT_PRINTED", ""))

    # ---- the recipe contract, exercised rather than asserted: run_tool takes a
    #      recipe's (argv, tag) and the tag must survive to the leg, because the
    #      tag is what decides whether a claim may be adjudicated at all. A stub
    #      stands in for a tool so this stays hermetic and instant; the real
    #      owners recipe costs a 107 s tree scan and is exercised by the run.
    with tempfile.TemporaryDirectory(prefix="doccensus-selftest-") as td:
        stub = os.path.join(td, "stub.py")
        with open(stub, "w") as fh:
            fh.write("print('cells: 7')\n")
        for want_tag in ("no-rev", ""):
            RECIPES["stub.py"] = (lambda t: lambda repo, rev, tmp: (["--probe"], t))(want_tag)
            try:
                out, rc, tag = run_tool(td, stub, "HEAD", td)
            finally:
                RECIPES.pop("stub.py", None)
            check(f"recipe: run_tool carries a recipe's tag {want_tag!r} to the leg",
                  (rc, tag, "cells: 7" in out), (0, want_tag, True))

        def _boom(repo_, rev_, tmp_):
            raise RuntimeError("boom")

        RECIPES["stub.py"] = _boom
        raised = ""
        try:
            try:
                run_tool(td, stub, "HEAD", td)
            except RuntimeError as exc:
                raised = str(exc)
        finally:
            RECIPES.pop("stub.py", None)
        check("recipe: an unmaterialisable revision raises, never an empty census",
              raised, "boom")

        # A tool that rejects `--repo`/`--rev` but has a perfectly good default
        # census. The retry must drop exactly the tokens argparse named: the
        # first cut re-ran it as `<script> --repo R`, which was rejected again,
        # and a working tool was reported RUN_FAILED. Both halves are pinned --
        # the retry happens, and it happens only for an argparse rejection.
        apstub = os.path.join(td, "stub_argparse.py")
        with open(apstub, "w") as fh:
            fh.write("import argparse\n"
                     "ap = argparse.ArgumentParser()\n"
                     'ap.add_argument("--selftest", action="store_true")\n'
                     "ap.parse_args()\n"
                     "print('cells: 7')\n")
        out, rc, tag = run_tool(td, apstub, "HEAD", td)
        check("run_tool: argparse rejection retried with the rejected flags dropped",
              (rc, tag, "cells: 7" in out), (0, "no-rev", True))

        rcstub = os.path.join(td, "stub_rc2.py")
        with open(rcstub, "w") as fh:
            fh.write("import sys\n"
                     "sys.stderr.write('boom\\n')\n"
                     "sys.exit(2)\n")
        out, rc, tag = run_tool(td, rcstub, "HEAD", td)
        check("run_tool: a non-argparse failure is not re-tagged no-rev",
              (rc, tag, "rc=2" in out), (2, "", True))
    # ---- a failed run leg does not silence its block. This path lives in
    #      check_tool and needs a subprocess, so it is exercised end to end with
    #      a stub tool rather than asserted: the stub rejects every census
    #      invocation with an argparse diagnosis and answers only `--selftest`.
    with tempfile.TemporaryDirectory(prefix="doccensus-selftest-") as td:
        stub = os.path.join(td, "stub_failing_run.py")
        with open(stub, "w") as fh:
            fh.write("'''stub: a run leg that fails, a selftest that answers.\n"
                     "\n7 cells\n'''\n"
                     "import sys\n"
                     'if "--selftest" in sys.argv:\n'
                     '    print("selftest: 7 cells, 7 passed, 0 failed")\n'
                     "else:\n"
                     '    sys.stderr.write("usage: stub_failing_run.py [-h] [--selftest]\\n")\n'
                     "    sys.exit(2)\n")
        rep = check_tool(td, stub, "stub_failing_run.py", {}, run=True, tmpdir=td)
        check("check_tool: a failed run leg is reported, and leg 2 still adjudicates",
              ([f["verdict"] for f in rep["failures"]],
               [(v["unit"], v["claim"], v["verdict"]) for v in rep["verdicts"]]),
              (["RUN_FAILED"], [("cells", 7, "MATCHES")]))

    # ---- the banner's arithmetic, which is what a reader actually reads: a
    #      RUN_FAILED leg and a STALE claim are counted in two columns, so four
    #      failed runs cannot read as four bad claims.
    synthetic = {"tool": "t", "splits": [], "unchecked": {}, "selftest_leg": True,
                 "failures": [{"verdict": "RUN_FAILED"}],
                 "verdicts": [{"verdict": "MATCHES"}, {"verdict": "STALE"}]}
    check("counts: a leg failure is not a claim defect", counts(synthetic)[:4],
          (0, 1, 1, 2))
    check("counts: an absent leg 2 is noted",
          counts({**synthetic, "selftest_leg": False})[4],
          ["no --selftest: leg 2 absent"])

    print(f"selftest: {cells[0]} cells, {cells[0] - bad[0]} passed, {bad[0]} failed")
    return 0 if ok else 1


# ------------------------------------------------------------------- driver
def run_tool(repo, script, rev, tmpdir, timeout=600):
    """(stdout, rc, tag) for the tool's own run at `rev`.

    `tag` is "" when the leg stood on the revision it was asked for and "no-rev"
    when it did not: either the tool rejected `--rev` and was re-run without it,
    or a recipe in RECIPES declared that it could not materialise the revision.
    Such a leg measures the tree it is pointed at, so a claim in a block that
    names a revision is reported REV_UNCHECKED rather than adjudicated (see
    check_tool). stdout is returned; stderr is only folded in when there is no
    stdout at all, so an argparse diagnosis is visible as a failure instead of
    parsed as a census.
    """
    recipe = RECIPES.get(os.path.basename(script), None)
    if recipe is None:
        argv, tag = [sys.executable, script, "--repo", repo, "--rev", rev], ""
    else:
        args, tag = recipe(repo, rev, tmpdir)
        argv = [sys.executable, script] + args
    p = subprocess.run(argv, capture_output=True, timeout=timeout)
    out = p.stdout.decode("utf-8", "replace")
    err = p.stderr.decode("utf-8", "replace")
    # A tool that takes neither `--repo` nor `--rev` answers with an argparse
    # diagnosis naming the flags it rejected, and NOTHING else: measured
    # 2026-10-16, `check_lint.py --repo R --rev HEAD` exits 2 with stdout empty
    # and `unrecognized arguments: --repo R --rev HEAD`, and the first cut of
    # this rule re-ran it as `<script> --repo R` -- still rejected, still rc 2,
    # so a tool with a perfectly good default census was reported RUN_FAILED.
    # The retry therefore drops the tokens argparse itself named, and only
    # those; a tool whose values collide with a dropped flag is a stated
    # limitation, not a silent one.
    m = re.search(r"unrecognized arguments:\s*(.+)$", err, re.M)
    if tag != "no-rev" and p.returncode != 0 and m:
        drop = set(m.group(1).split())
        argv = [x for x in argv if x not in drop]
        p = subprocess.run(argv, capture_output=True, timeout=timeout)
        out = p.stdout.decode("utf-8", "replace")
        err = p.stderr.decode("utf-8", "replace")
        tag = "no-rev"
    if not out.strip():
        out = "<no stdout; rc=%d> %s" % (p.returncode, err[:200].replace("\n", " "))
    return out, p.returncode, tag


def run_selftest(script, timeout=300):
    """Leg 2: the tool's own `--selftest`, or None if it takes no such flag.

    A cell count is printed here and nowhere else, which is the whole reason
    this leg exists. `None` means the tool has no selftest to offer -- reported
    as one leg, not as a failure.
    """
    try:
        p = subprocess.run([sys.executable, script, "--selftest"],
                           capture_output=True, timeout=timeout)
    except subprocess.TimeoutExpired:
        return "<--selftest timed out>"
    out = p.stdout.decode("utf-8", "replace")
    err = p.stderr.decode("utf-8", "replace")
    if "unrecognized arguments" in err and "--selftest" in err:
        return None
    if not out.strip():
        return "<no stdout; rc=%d> %s" % (p.returncode, err[:200].replace("\n", " "))
    return out


def unit_scope(unit, legs, no_run):
    """Is a split in this unit checkable, and why not if it is not?

    With the oracle legs in hand a unit is checkable when some leg prints it
    with exactly ONE value: the docstring and the output then talk about one
    number. A unit printed with 2+ values is SECTION-SPLIT BY THE TOOL'S OWN
    DESIGN (`citations` prints once under EXPLICIT and once under BARE), so a
    docstring that mirrors both is correct and is reported as such, not flagged.
    A unit no leg prints is not a census unit here. Without a run, only
    uppercase census labels are checked.
    """
    if no_run or not legs:
        return ("LABEL_ONLY" if is_label(unit) else "UNCHECKED_NO_ORACLE")
    saw_split = False
    for printed, clone, _tag in legs:
        vals = set()
        for k in keys_for(unit, printed or {}):
            vals |= set((printed or {})[k])
        if not vals:
            continue
        if len(vals) > 1:
            saw_split = True
            continue
        return "CHECKABLE"
    if saw_split:
        return "SECTION_SPLIT_BY_TOOL"
    return "NOT_A_CENSUS_UNIT"


def check_tool(repo, script, name, cache, run=True, tmpdir=".", isolation=240):
    text = open(script, encoding="utf-8", errors="replace").read()
    span = docstring_span(script, text)
    if span is None:
        return None
    lines = text.split("\n")
    lo, hi = span
    blk_claims = []
    for first, blk in blocks(lines, lo, hi):
        btext = "\n".join(raw for _, raw in blk)
        revs = block_revs(btext)
        cl = claims_in(blk)
        if cl:
            blk_claims.append((first, revs, cl, btext))

    # ---- the legs first. Leg 1: the tool's own run, once per revision the
    #      docstring names. Leg 2: its --selftest, once. The tool under test is
    #      never this tool: running this scanner on itself spawns it, which
    #      spawns it again, without a floor.
    is_self = os.path.basename(script) == os.path.basename(os.path.abspath(__file__))
    printed_by_rev, verdicts, failures = {}, [], []
    selftest_leg = None
    if run and not is_self:
        for first, revs, cl, _b in blk_claims:
            for rev in (revs or ["HEAD"]):
                key = (name, rev)
                if key not in cache:
                    try:
                        out, rc, tag = run_tool(repo, script, rev, tmpdir)
                        cache[key] = (parse_printed(out), rc, out, tag)
                    except Exception as exc:                    # noqa: BLE001
                        cache[key] = (None, None, f"<run failed: {exc}>", "")
                printed_by_rev.setdefault((first, rev), cache[key])
        skey = (name, "<selftest>")
        if skey not in cache:
            try:
                sout = run_selftest(script)
            except Exception as exc:                            # noqa: BLE001
                sout = f"<selftest failed: {exc}>"
            cache[skey] = (parse_printed(sout) if sout else None,
                           0 if sout else None, sout or "", "selftest")
        selftest_leg = cache[skey]

    def legs_for(first, rev):
        """Priority-ordered [(printed, clone, tag)] for one block scope."""
        out = []
        entry = printed_by_rev.get((first, rev))
        if entry and entry[0]:
            out.append((entry[0][0], entry[0][1], entry[3]))
        if selftest_leg and selftest_leg[0]:
            out.append((selftest_leg[0][0], selftest_leg[0][1], "selftest"))
        return out

    # 1. INTERNAL SPLIT: one unit, one revision scope, two values, far enough
    #    apart to be a restatement rather than a neighbouring sub-count.
    splits, unchecked = [], collections.Counter()
    by_unit = collections.defaultdict(list)
    for first, revs, cl, _b in blk_claims:
        scope = tuple(revs)
        for ln, val, unit, _t, pos in cl:
            by_unit[(unit.upper() if unit.isupper() else unit.lower(), scope)].append(
                (first, ln, val, pos))
    for (unit, scope), items in sorted(by_unit.items()):
        vals = {v for _, _, v, _ in items}
        if len(vals) < 2:
            continue
        # a restatement is a pair far apart; an enumeration is neighbours
        far = any(abs(b[3] - a[3]) >= isolation
                  for a, b in [(x, y) for x in items for y in items]
                  if a[1] != b[1] and a[2] != b[2])
        if not far:
            continue
        rev_for_oracle = (items[0][0], scope[0] if len(scope) == 1 else "HEAD")
        why = ("SELF_NOT_RUN" if is_self and run
               else unit_scope(unit, legs_for(*rev_for_oracle), not run))
        if why != "CHECKABLE" and why != "LABEL_ONLY":
            unchecked[why] += 1
            continue
        splits.append({"unit": unit, "revs": list(scope),
                       "values": sorted(vals), "how": why,
                       "rows": [{"line": ln, "value": v, "block": b}
                                for b, ln, v, _ in items]})

    # 2. ORACLE: every claim compared against what the tool prints, leg 1 first.
    if run:
        for first, revs, cl, _b in blk_claims:
            for rev in (revs or ["HEAD"]):
                if is_self:
                    for ln, val, unit, tok, _pos in cl:
                        verdicts.append({"file": name, "block": first, "line": ln,
                                         "rev": rev, "unit": unit, "claim": val,
                                         "token": tok, "verdict": "SELF_NOT_RUN",
                                         "detail": "the tool under test is this tool"})
                    continue
                pr, rc, out, _tag = printed_by_rev[(first, rev)]
                printed, clone = pr if pr else (None, None)
                legs = legs_for(first, rev)
                # A leg with no census -- raised, or exited non-zero having
                # printed nothing -- adjudicates nothing either: drop it and let
                # whichever leg survives answer instead. Only when none survives
                # is the block left unadjudicated.
                no_census = pr is None or (rc not in (0, None)
                                           and not any(printed.values()))
                if pr is None:
                    failures.append({"file": name, "block": first, "rev": rev,
                                     "unit": "-", "claim": None,
                                     "verdict": "RUN_FAILED", "detail": str(out)[:90]})
                elif no_census:
                    failures.append({"file": name, "block": first, "rev": rev,
                                     "unit": "-", "claim": None,
                                     "verdict": "RUN_FAILED",
                                     "detail": "rc=%s, nothing printed: %s"
                                               % (rc, str(out)[:80])})
                if no_census:
                    legs = [l for l in legs if l[2] == "selftest"]
                    if not legs:
                        continue
                for ln, val, unit, tok, _pos in cl:
                    v, detail = adjudicate(legs, unit, val, revs)
                    verdicts.append({"file": name, "block": first, "line": ln,
                                     "rev": rev, "unit": unit, "claim": val,
                                     "token": tok, "verdict": v, "detail": detail})
    return {"tool": name, "splits": splits, "unchecked": dict(unchecked),
            "failures": failures, "verdicts": verdicts,
            "self": is_self and run, "selftest_leg": (not run) or bool(selftest_leg and selftest_leg[0]),
            "blocks_with_claims": len(blk_claims)}


def counts(rep):
    """(splits, claim_defects, leg_failures, claims, notes) -- the banner's rows.

    A LEG FAILURE IS NOT A CLAIM DEFECT. RUN_FAILED says no census came back and
    such a leg adjudicates nothing (see check_tool); STALE says a claim was read
    against a census and disagreed. The first live run of the two-leg tool mixed
    them in one `N STALE/failed` column, so four failed runs read as four bad
    claims -- measured 2026-10-16 at HEAD, check_lint.py 2 and
    queue_claim_check.py 2, none of them a claim disagreement. Two columns, so
    the distinction survives the summary a reader actually reads.
    """
    stale = [v for v in rep["verdicts"] if v["verdict"] == "STALE"]
    notes = []
    if rep.get("self"):
        notes.append("self: no leg run (SELF_NOT_RUN)")
    elif not rep.get("selftest_leg"):
        notes.append("no --selftest: leg 2 absent")
    return (len(rep["splits"]), len(stale), len(rep["failures"]),
            len(rep["verdicts"]), notes)


def main():
    ap = argparse.ArgumentParser(description=__doc__,
                                 formatter_class=argparse.RawDescriptionHelpFormatter)
    ap.add_argument("--repo", default=DEFAULT_REPO)
    ap.add_argument("--rev", default="HEAD")
    ap.add_argument("--tools", nargs="*")
    ap.add_argument("--json")
    ap.add_argument("--no-run", action="store_true",
                    help="internal-split verdicts only; no subprocess")
    ap.add_argument("--selftest", action="store_true")
    a = ap.parse_args()

    if a.selftest:
        return _fixture_checks()

    store = git(a.repo, "ls-tree", "-r", "--name-only", a.rev)
    tree = {p for p in store.decode("utf-8", "replace").split("\n") if p}
    tools = a.tools or sorted(p for p in tree
                              if p.startswith("tools/") and p.endswith(".py"))
    if not tools:
        print(f"no tools found at {a.rev}", file=sys.stderr)
        return 2

    cache, reports = {}, []
    with tempfile.TemporaryDirectory(prefix="doccensus-") as tmpdir:
        for t in tools:
            src = subprocess.run(["git", "-C", a.repo, "show", f"{a.rev}:{t}"],
                                 capture_output=True).stdout
            local = os.path.join(tmpdir, os.path.basename(t))
            with open(local, "wb") as fh:
                fh.write(src)
            try:
                rep = check_tool(a.repo, local, t, cache, run=not a.no_run,
                                 tmpdir=tmpdir)
            except subprocess.TimeoutExpired:
                rep = {"tool": t, "splits": [], "blocks_with_claims": 0,
                       "verdicts": [{"file": t, "verdict": "TIMEOUT", "rev": "-",
                                     "unit": "-", "claim": None, "block": 0}]}
            if rep:
                reports.append(rep)

    print(f"tools scanned at {a.rev}: {len(reports)} "
          f"({'internal-split only, label vocabulary' if a.no_run else 'docstring vs printed census'})")
    tot = collections.Counter()
    for rep in reports:
        bad = rep["failures"] + [v for v in rep["verdicts"] if v["verdict"] == "STALE"]
        nsplits, nstale, nfail, nclaims, notes = counts(rep)
        print(f"\n{rep['tool']}: {nsplits} INTERNAL SPLIT, "
              f"{nstale} STALE claim(s), {nfail} leg failure(s), "
              f"{nclaims} claims checked"
              + (" [" + "; ".join(notes) + "]" if notes else ""))
        for s in rep["splits"]:
            vals = ", ".join(f"{r['value']}@{r['line']}" for r in s["rows"])
            scope = ",".join(s["revs"]) or "no rev named"
            print(f"  SPLIT  {s['unit']} [{scope}] ({s['how']}): {vals}")
        for k, c in sorted(rep["unchecked"].items()):
            print(f"  (not flagged: {c} split(s) in units {k})")
        for v in bad:
            print(f"  {v['verdict']:10s} {v['file']}:{v.get('line', '-')} "
                  f"{v['unit']} claimed {v['claim']} at {v['rev']} -- {v['detail']}")
        for k in sorted({v["verdict"] for v in rep["verdicts"]}):
            if k in ("REV_UNCHECKED", "SELF_NOT_RUN", "CLONE_LOCAL"):
                n = sum(1 for v in rep["verdicts"] if v["verdict"] == k)
                print(f"  ({n} {k}: reported, never counted as a defect)")
        for k, c in collections.Counter(v["verdict"] for v in rep["verdicts"]).items():
            tot[k] += c
    print("\n--- verdict totals (unit: claims) ---")
    for k in sorted(tot):
        print(f"  {k:12s} {tot[k]}")
    if a.json:
        with open(a.json, "w") as fh:
            json.dump({"rev": a.rev, "repo": a.repo, "reports": reports}, fh, indent=1)
        print(f"wrote {a.json}")
    return 0


if __name__ == "__main__":
    sys.exit(main())