Files
superpowers/skills/agentic-end-to-end-testing/scripts/check-cards-against-spec
Drew Ritter 7dff0b2d48 fix(e2e): confine scenario card validation
Reuse the bounded fence filter for every scenario-card structural check so headings, coverage text, and falsification prose inside examples cannot satisfy the gate. Valid cards may still contain unrelated fenced examples.\n\nTreat each Card cell as a filename stem: remove at most one enclosing backtick pair, require lowercase kebab case, and reject invalid values before they can be stored or joined to the cards directory. This blocks parent traversal, subdirectories, uppercase names, and empty segments.\n\nAdd real-process RED/GREEN coverage for fenced-only cards, traversal, invalid stems, preserved backtick behavior, and the explicit diagnostic for intentionally unsupported pipe-less tables.
2026-08-06 14:50:46 -07:00

217 lines
6.6 KiB
Bash
Executable File

#!/usr/bin/env bash
# check-cards-against-spec — verify scenario cards carry their spec table's
# falsification lines verbatim. See authoring-cards-from-a-spec.md.
set -euo pipefail
usage() {
cat <<'EOF'
Usage: check-cards-against-spec <spec.md> <cards-dir>
Verifies the spec's "E2E scenario cards" table against the cards directory:
1. table parses (>=1 row; non-empty Card and Falsification cells)
2. every row has <cards-dir>/<card>.md
3. every card contains its Falsification line verbatim
(whitespace-normalized, fixed-string, case-sensitive)
4. every card has **What this covers** (bold inline) and ## headings
Pre-state, Steps, Expected, Cleanup (Sharp edges not required)
5. extra cards in <cards-dir> are reported as warnings, not failures
Exit: 0 all pass; 1 check failed; 2 no "E2E scenario cards" table; 64 usage.
EOF
}
[ "${1:-}" = "--help" ] && { usage; exit 0; }
[ $# -eq 2 ] || { usage >&2; exit 64; }
SPEC="$1"; CARDS="$2"
[ -f "$SPEC" ] || { echo "error: spec not found: $SPEC" >&2; exit 64; }
[ -d "$CARDS" ] || { echo "error: cards dir not found: $CARDS" >&2; exit 64; }
FAILURES=0
fail() { echo "FAIL: $1"; FAILURES=$((FAILURES + 1)); }
warn() { echo "warn: $1"; }
# Collapse every whitespace run to one space; trim ends. (Normative per the
# design spec: markdown re-wrapping must not defeat the verbatim check.)
normalize() { tr -s '[:space:]' ' ' | sed -e 's/^ //' -e 's/ $//'; }
# Exclude fenced examples from structural matching. This intentionally models
# only backtick/tilde fences; it is not a general Markdown parser.
without_fenced_code() {
awk '
function fence_family(line, first, count) {
sub(/^[[:space:]]*/, "", line)
first = substr(line, 1, 1)
if (first != "`" && first != "~") return ""
count = 0
while (substr(line, count + 1, 1) == first) count++
return count >= 3 ? first : ""
}
{
marker = fence_family($0)
if (!in_fence && marker != "") {
in_fence = 1
family = marker
next
}
if (in_fence && marker == family) {
in_fence = 0
family = ""
next
}
if (!in_fence) print
}
' "$1"
}
# Text of the card's Expected section only (case-insensitive heading match,
# any ##+ level; section ends at the next heading or EOF).
expected_section() {
awk '
/^#{1,6}[[:space:]]/ {
low = tolower($0)
if (low ~ /^#+[[:space:]]*expected[[:space:]]*$/) { insec = 1; next }
if (insec) exit
}
insec { print }
'
}
# --- extract the first table under the (case-insensitive) heading ----------
TABLE="$(awk '
/^#{1,6}[[:space:]]/ {
h = $0; sub(/^#+[[:space:]]*/, "", h); sub(/[[:space:]]+$/, "", h)
if (tolower(h) == "e2e scenario cards") { insec = 1; next }
if (insec) exit
}
insec && /^[[:space:]]*\|/ { intable = 1; print; next }
insec && intable { exit }
' < <(without_fenced_code "$SPEC"))"
if [ -z "$TABLE" ]; then
echo "no scenario table: $SPEC has no \"E2E scenario cards\" heading with a table under it" >&2
echo "(heading must be exactly \"E2E scenario cards\" — no numbering or extra words)" >&2
echo "(scenario table rows must use leading and trailing outer pipes)" >&2
exit 2
fi
# --- parse: protect escaped pipes, split rows into cells -------------------
US=$'\x1f'
CARD_COL=-1; FALS_COL=-1; ROWS=0
declare -a ROW_CARD ROW_FALS
HEADER_COLS=0; TABLE_VALID=1
lineno=0
while IFS= read -r line; do
lineno=$((lineno + 1))
row="$(printf '%s' "$line" | sed -e 's/^[[:space:]]*//' -e 's/[[:space:]]*$//')"
case "$row" in
\|*\|) ;;
*)
fail "row $lineno: canonical table rows require leading and trailing pipes"
TABLE_VALID=0
break
;;
esac
row="${row#|}"
row="${row%|}"
esc="${row//\\|/$US}"
IFS='|' read -r -a cells <<< "$esc"
trimmed=()
for c in "${cells[@]}"; do
c="${c//$US/|}"
c="$(printf '%s' "$c" | normalize)"
trimmed+=("$c")
done
if [ "$lineno" -eq 1 ]; then
for i in "${!trimmed[@]}"; do
low="$(printf '%s' "${trimmed[$i]}" | tr '[:upper:]' '[:lower:]')"
[ "$low" = "card" ] && CARD_COL=$i
[ "$low" = "falsification" ] && FALS_COL=$i
done
HEADER_COLS=${#trimmed[@]}
if [ "$CARD_COL" -lt 0 ] || [ "$FALS_COL" -lt 0 ]; then
fail "table header must name Card and Falsification columns"
TABLE_VALID=0
break
fi
continue
fi
if [ "$lineno" -eq 2 ]; then
delimiter_ok=1
[ "${#trimmed[@]}" -eq "$HEADER_COLS" ] || delimiter_ok=0
for c in "${trimmed[@]}"; do
if ! printf '%s\n' "$c" | grep -Eq '^:?-{3,}:?$'; then
delimiter_ok=0
fi
done
if [ "$delimiter_ok" -ne 1 ]; then
fail "row 2: malformed table delimiter"
TABLE_VALID=0
break
fi
continue
fi
card="${trimmed[$CARD_COL]:-}"
falsif="${trimmed[$FALS_COL]:-}"
if [ -z "$card" ] || [ -z "$falsif" ]; then
fail "row $lineno: empty Card or Falsification cell"
continue
fi
case "$card" in
\`*\`)
card="${card#\`}"
card="${card%\`}"
;;
esac
if ! [[ "$card" =~ ^[a-z0-9]+(-[a-z0-9]+)*$ ]]; then
fail "row $lineno: invalid Card value: $card"
continue
fi
ROW_CARD[$ROWS]="$card"; ROW_FALS[$ROWS]="$falsif"; ROWS=$((ROWS + 1))
done <<< "$TABLE"
if [ "$TABLE_VALID" -eq 1 ] && [ "$ROWS" -lt 1 ]; then
fail "scenario table has no data rows"
fi
# --- checks 2-4 per row -----------------------------------------------------
i=0
while [ "$i" -lt "$ROWS" ]; do
card="${ROW_CARD[$i]}"; falsif="${ROW_FALS[$i]}"
f="$CARDS/$card.md"
if [ ! -f "$f" ]; then
fail "missing card file: $f"
i=$((i + 1)); continue
fi
card_text="$(without_fenced_code "$f")"
hay="$(printf '%s\n' "$card_text" | expected_section | normalize)"
case "$hay" in
*"$falsif"*) : ;;
*) fail "$f: falsification line not present verbatim in the ## Expected section.
expected (normalized): $falsif" ;;
esac
grep -q '\*\*What this covers\*\*' <<< "$card_text" || fail "$f: missing **What this covers**"
for sec in Pre-state Steps Expected Cleanup; do
grep -Eiq "^#{2,}[[:space:]]*${sec}[[:space:]]*$" <<< "$card_text" || fail "$f: missing ## ${sec} section"
done
i=$((i + 1))
done
# --- check 5: extra cards are warnings --------------------------------------
for f in "$CARDS"/*.md; do
[ -e "$f" ] || continue
base="$(basename "$f" .md)"
known=0; i=0
while [ "$i" -lt "$ROWS" ]; do
[ "${ROW_CARD[$i]}" = "$base" ] && known=1
i=$((i + 1))
done
[ "$known" -eq 1 ] || warn "extra card not in spec table: $base"
done
if [ "$FAILURES" -gt 0 ]; then
echo "$FAILURES check(s) failed"
exit 1
fi
echo "all checks passed ($ROWS card(s))"