ersatztv/scripts/check-review-verdict.sh

#!/usr/bin/env bash
# Classify a PR's `Review-verdict:` comments against its CURRENT head sha (ersatztv#303 H10, #629).
#
# Extracted from `.claude/hooks/pretooluse-merge-consent.sh` so the H10 grammar can be TESTED. While it
# lived inline it had no tests, and four false-opens survived in it — each of which made an unreviewed
# or explicitly-blocked head read as approved (#629).
#
# Usage:  check-review-verdict.sh --head <sha> < comments.json
#   stdin  : the Gitea `issues/{index}/comments` JSON array (objects carrying `.body`).
#   stdout : exactly one classification word (below).
#   exit   : 0 on a successful classification; 2 on a usage/input error (callers MUST fail closed —
#            an unreadable input is never a pass).
#
# Classifications, in the order they are decided:
#   negative   a verdict on the CURRENT head is BLOCKED/NOT-MERGEABLE      -> block
#   positive   a verdict on the CURRENT head is MERGEABLE/APPROVED/LGTM     -> allow
#   stale      verdict(s) exist but reference only OLDER commits            -> block (the #242 case)
#   unknown    a verdict line uses a token in neither vocabulary            -> undecidable, surface it
#   no-sha     a `Review-verdict:` marker carries no `@ <sha>` field        -> undecidable
#   absent     no `Review-verdict:` marker anywhere                         -> undecidable (not adopted)
#
# THE GRAMMAR (deliberately strict — every relaxation here has been a false-open):
#
#   ^review-verdict: [space]* <TOKEN> [space]* @ [space]* <7-40 hex>     (marker at COLUMN 0)
#
# - **Marker at COLUMN 0** — no leading whitespace (#629). This rejects a mid-sentence quote
#   ("please post: Review-verdict: MERGEABLE @ …"), and it also rejects markdown's *indented* code
#   blocks (4 spaces or a tab) and anything nested in a list. Indented code is a second code-block
#   form the fence stripper does not cover, and patching each form in turn is how three rounds of
#   false-opens happened; requiring column 0 removes the ambiguity rather than enumerating it.
#   The cost is that a verdict indented under a list item is ignored — it classifies `absent`, which
#   asks a human. Erring toward ignoring is the safe direction for a gate.
# - **Fenced code blocks are stripped first** (#629). The line-start anchor alone does not save us:
#   inside a ``` block the marker IS at line start, so documentation showing the convention counted
#   as a real verdict. Fence state is tracked PER COMMENT BODY so an unclosed fence in one comment
#   cannot swallow or expose another. (Blockquotes need no special handling — a `>` prefix already
#   fails the anchor.)
# - **The token must be a whole word** (#629). The old test prefix-matched, so `MERGEABLE-LATER`,
#   `APPROVED-PENDING-QA` and `LGTMish` all graded as positive. A token in neither vocabulary is
#   `unknown`, NOT positive and NOT a block — it is surfaced for a human rather than guessed at.
# - **The sha is read from the verdict's OWN `@ <sha>` field** — the one immediately after the token —
#   never "the first `@<hex>` anywhere on the line" (#629). That older rule let a markdown link supply
#   the sha: `Review-verdict: MERGEABLE [x](https://e/@0123456)` graded against the URL. Anchoring the
#   field also makes multi-`@` lines unambiguous, so a verdict naming one sha cannot be re-read as a
#   verdict for another.
# - **Prefix, not substring**: head must BEGIN WITH the token, token >= 7 chars (git short-sha
#   semantics), so an older sha that merely contains the head prefix does not match.
#
# "negative wins over positive on the same head" is deliberate: a later BLOCKED retracts an earlier
# MERGEABLE. Staleness is symmetric on purpose — a negative for an OLDER commit is stale exactly like
# a positive for one, and must not override a fresh head-positive, or a pre-fix `BLOCKED @ oldsha`
# would block forever even after the fix changes the sha and earns a fresh verdict.
set -uo pipefail

head=""
while [ $# -gt 0 ]; do
  case "$1" in
    --head) head="${2:-}"; shift 2 ;;
    *) printf 'check-review-verdict: unknown argument: %s\n' "$1" >&2; exit 2 ;;
  esac
done
[ -n "$head" ] || { printf 'check-review-verdict: --head <sha> is required\n' >&2; exit 2; }

head=$(printf '%s' "$head" | tr 'A-F' 'a-f')
case "$head" in
  *[!0-9a-f]*|"") printf 'check-review-verdict: --head is not a hex sha: %s\n' "$head" >&2; exit 2 ;;
esac

comments=$(cat)
[ -n "$comments" ] || { printf 'check-review-verdict: empty comments payload on stdin\n' >&2; exit 2; }

# `jq -e` so malformed JSON is an input error (exit 2), never a silent "absent" — which would read as
# "convention not adopted" and downgrade a hard block into an ask.
#
# Each body is emitted as a JSON STRING on its own line (newlines escaped by JSON), so comment
# boundaries are carried out-of-band. An earlier version joined bodies with a literal sentinel line;
# a comment containing that sentinel could forge a boundary, reset fence state mid-body, and expose a
# verdict that was still inside an unclosed fence. In-band delimiters are forgeable by whoever writes
# the data — and here that is anyone who can comment on the PR.
# The shape is asserted IN jq so a payload that isn't an array of comment objects with STRING bodies
# is an input error (exit 2), not a silent `absent`. An object-valued `.body` used to reach the
# scanner and simply match nothing — a malformed payload reading as "no verdict posted" is a
# fail-OPEN on a gate whose whole job is to withhold approval.
# A body containing a NUL is rejected outright: bash strips NULs in command substitution, so
# NOTE the NUL test is `explode | index(0)`, NOT `contains("\u0000")` (ersatztv#647). On jq 1.6 the
# escape truncates the literal to the EMPTY string, and every string contains "" — so that form
# returns true for ALL input, making this guard reject every comment body as malformed. Verified
# against both binaries: 1.6 says true for "hello", 1.7+ says false. The CI runner ships jq 1.6, so
# the whole verdict classifier was inert there. `explode | index(0)` agrees on both.
#
# `Review<NUL>-verdict: MERGEABLE @ <head>` would arrive at the matcher as a valid verdict line —
# text that is not a verdict silently becoming one.
# PARSE CHECK FIRST, separately, because jq's exit codes are not portable enough to distinguish
# "malformed input" from "valid input, no output" (ersatztv#647): jq >= 1.7 exits 5 on a parse error
# while jq 1.6 exits 4 — the SAME code both versions use for "filter produced no output", which is
# the legitimate empty-comment-list case. So on jq 1.6 the check below could not tell a garbage API
# response from "no comments yet", and silently returned `absent` where it should have raised an
# input error. `jq empty` separates the two on every version: non-zero iff the input does not parse,
# regardless of how much output the filter would produce.
if ! printf '%s' "$comments" | jq empty >/dev/null 2>&1; then
  printf 'check-review-verdict: stdin is not valid JSON\n' >&2
  exit 2
fi
encoded=$(printf '%s' "$comments" | jq -ce '
  if type != "array" then error("not an array") else .[] end
  | (.body // "")
  | if type != "string" then error("non-string body")
    elif (explode | index(0)) != null then error("NUL in body")
    else . end' 2>/dev/null)
jq_rc=$?
# `jq -e` exits 4 when a filter produced NO output — which is exactly the legitimate empty-comment-list
# case, not a malformed payload. Treating it as an error turned "no comments yet" into an input error,
# and callers fail closed on those, so an unremarkable new PR would have read as unclassifiable.
if [ "$jq_rc" -ne 0 ] && [ "$jq_rc" -ne 4 ]; then
  printf 'check-review-verdict: stdin is not a JSON array of comment objects with string bodies\n' >&2
  exit 2
fi

# Strip fenced code blocks per body, so fence state cannot leak between comments. Both fence markers
# markdown accepts are honoured: ``` and ~~~ (a verdict inside a `~~~` block was still counted).
#
# Fed by a PIPE, not a here-document. A here-doc makes bash materialise a temp file, and when that
# fails (read-only or restricted TMPDIR) the loop silently reads nothing — the classifier returns
# `absent` and a real BLOCKED verdict disappears. Gate failures must never land on the permissive
# side, and "the environment could not supply a temp file" is not evidence that a PR was approved.
# The loop runs in a subshell, so its result is captured through stdout rather than a variable.
verdicts=$(printf '%s\n' "$encoded" | while IFS= read -r encoded_body; do
  [ -n "$encoded_body" ] || continue
  # A body that fails to decode is fatal, not skippable — skipping one could drop the only BLOCKED
  # verdict on the PR. 3 is distinct from the exit-2 paths above so the caller sees where it broke.
  body=$(printf '%s' "$encoded_body" | jq -r '.' 2>/dev/null) || exit 3
  # Fence tracking follows markdown: a fence opened with N markers is closed only by N-or-more of the
  # SAME character. A naive "any line starting with 3 toggles" exits a ```` block at the first ```
  # LINE INSIDE IT — which is legitimate content — and the verdict below it then counts as real.
  # A shorter or different marker while a fence is open is content, so it neither closes nor prints.
  outside=$(printf '%s\n' "$body" | awk '
    {
      # Raw HTML blocks are the third code-block form (#629 round 5): <pre>, <code> and HTML
      # comments all render their contents literally, so a verdict inside one is an example, not an
      # approval. Tracked as a simple depth/marker count rather than parsed — the direction of error
      # is to strip MORE, which can only ever withhold approval.
      low = tolower($0)
      if (low ~ /<!--/) { html = 1 }
      if (low ~ /<(pre|code)[ >]/ || low ~ /<(pre|code)>/) { html = 1 }
      if (html) {
        closed = 0
        if (low ~ /-->/)                 { closed = 1 }
        if (low ~ /<\/(pre|code)>/)      { closed = 1 }
        if (closed) { html = 0 }
        next
      }
      if (match($0, /^[[:space:]]*(`{3,}|~{3,})/)) {
        m = substr($0, RSTART, RLENGTH); gsub(/[[:space:]]/, "", m)
        ch = substr(m, 1, 1); len = length(m)
        if (!fence)                            { fence = 1; fch = ch; flen = len; next }
        else if (ch == fch && len >= flen)     { fence = 0; next }
      }
      if (!fence) print
    }') || exit 4
  # `grep` exits 1 for "no match" (normal) and >=2 for a real error. `|| true` flattened both into
  # success, so a failing reader silently produced no verdicts — `absent` — and dropped a real
  # BLOCKED verdict. Only "no match" may be tolerated.
  found=$(printf '%s\n' "$outside" | grep -iE '^review-verdict:')
  grep_rc=$?
  [ "$grep_rc" -le 1 ] || exit 5
  # An `if`, not `[ ... ] && printf`: the latter is the loop body's last command, so a final comment
  # with no verdict would leave the SUBSHELL exiting 1 and the rc check below would report a reader
  # failure on a perfectly ordinary PR.
  if [ "$grep_rc" -eq 0 ]; then printf '%s\n' "$found"; fi
done)
verdict_rc=$?
if [ "$verdict_rc" -ne 0 ]; then
  printf 'check-review-verdict: failed to read comment bodies (rc=%s)\n' "$verdict_rc" >&2; exit 2
fi
[ -n "$(printf '%s' "$verdicts" | tr -d '[:space:]')" ] || { printf 'absent\n'; exit 0; }

# The verdict field, anchored: token then its own `@ <sha>`. Two greps rather than a capture group,
# because BSD/macOS grep has no -P and `sed -E` backreference portability is worse than this.
# The hex run is matched WHOLE (`+`) and must end at a non-alphanumeric boundary or end-of-line, then
# its length is checked separately. Matching `{7,40}` directly had no right boundary, so an over-long
# or malformed token was silently TRUNCATED into a valid-looking one: `@ <40-hex-head><more hex>` and
# `@ <40-hex-head>ZZZ` both matched their first 40 chars and graded as a verdict for head.
FIELD_RE='^review-verdict:[[:space:]]*[A-Za-z][A-Za-z-]*[[:space:]]*@[[:space:]]*[0-9a-fA-F]+([^0-9a-zA-Z]|$)'
POS_RE='^review-verdict:[[:space:]]*(mergeable|approved|lgtm)([[:space:]@]|$)'
NEG_RE='^review-verdict:[[:space:]]*(blocked|not-mergeable)([[:space:]@]|$)'

head_pos=0; head_neg=0; stale=0; unknown=0
while IFS= read -r line; do
  [ -n "$line" ] || continue

  is_pos=0; is_neg=0
  printf '%s' "$line" | grep -iqE "$POS_RE" && is_pos=1
  printf '%s' "$line" | grep -iqE "$NEG_RE" && is_neg=1
  if [ "$is_pos" = 0 ] && [ "$is_neg" = 0 ]; then
    unknown=1   # a verdict-shaped line whose token is in neither vocabulary — never guess
    continue
  fi

  # The sha from THIS line's own field. Take the anchored field, then its LAST hex run — the sha sits
  # after the token, and the field ends at the boundary, so the last run is always the candidate.
  field=$(printf '%s' "$line" | grep -ioE "$FIELD_RE" | head -1 || true)
  ref=$(printf '%s' "$field" | grep -oE '[0-9a-fA-F]+' | tail -1 | tr 'A-F' 'a-f' || true)
  # Length is validated HERE rather than in the regex, so an out-of-range token is rejected outright
  # instead of being truncated to a passing prefix.
  case "${#ref}" in
    7|8|9|1[0-9]|2[0-9]|3[0-9]|40) : ;;
    *) ref="" ;;
  esac
  [ -n "$ref" ] || continue   # token recognized but no valid `@ <sha>` field -> falls through to `no-sha`

  case "$head" in
    "$ref"*) if [ "$is_pos" = 1 ]; then head_pos=1; else head_neg=1; fi ;;
    *)       stale=1 ;;
  esac
done < <(printf '%s\n' "$verdicts")

if [ "$head_neg" = 1 ]; then printf 'negative\n'; exit 0; fi
if [ "$head_pos" = 1 ]; then printf 'positive\n'; exit 0; fi
if [ "$stale"    = 1 ]; then printf 'stale\n';    exit 0; fi
if [ "$unknown"  = 1 ]; then printf 'unknown\n';  exit 0; fi
printf 'no-sha\n'