#!/usr/bin/env bash
# Strip every workspace-crate artifact out of target/, then prove none survived.
#
# The cache is only sound while it contains dependency artifacts alone. A
# workspace crate's artifact carries the code under test, and reusing one can
# turn a red build green -- the worst failure a CI system has, because it is
# silent. So this script ends by asserting its own work and exits non-zero if
# the assertion fails; the caller must treat that as "do not publish".
#
# Exit codes: 0 clean prune, 1 usage/environment error, 2 assertion tripped.
set -euo pipefail

TARGET_DIR="${1:?usage: cargo-cache-prune.sh <target-dir> <manifest-path>}"
MANIFEST="${2:?usage: cargo-cache-prune.sh <target-dir> <manifest-path>}"

[ -d "$TARGET_DIR" ] || { echo "prune: no such target dir: $TARGET_DIR" >&2; exit 1; }
command -v cargo >/dev/null || { echo "prune: cargo not on PATH" >&2; exit 1; }

# --no-deps restricts the listing to workspace members, which is precisely the
# set whose artifacts must never be cached.
members="$(cargo metadata --no-deps --format-version 1 --manifest-path "$MANIFEST" \
    | python3 -c 'import json,sys; print("\n".join(p["name"] for p in json.load(sys.stdin)["packages"]))')"

if [ -z "$members" ]; then
    echo "prune: cargo metadata listed no workspace members" >&2
    exit 1
fi

# Incremental state is large, machine-specific and never reusable across
# clones; examples and docs are not dependencies of anything we build.
rm -rf "$TARGET_DIR"/*/incremental "$TARGET_DIR"/*/examples "$TARGET_DIR"/doc 2>/dev/null || true

prune_one() {
    name="$1"
    snake="${name//-/_}"
    # Fingerprints and build-script output live in per-crate directories.
    find "$TARGET_DIR" -maxdepth 3 \
        \( -path "*/.fingerprint/$name-*" \
        -o -path "*/.fingerprint/$snake-*" \
        -o -path "*/build/$name-*" \
        -o -path "*/build/$snake-*" \) \
        -prune -exec rm -rf {} + 2>/dev/null || true
    # Compiled outputs: rlib/rmeta/d in deps/, plus binaries at the profile root.
    find "$TARGET_DIR" -maxdepth 3 \
        \( -name "$snake-*" -o -name "lib$snake-*" -o -name "lib$snake.*" \
        -o -name "$name" -o -name "$name-*" \) \
        -exec rm -rf {} + 2>/dev/null || true
}

while IFS= read -r name; do
    [ -n "$name" ] || continue
    prune_one "$name"
done <<EOF
$members
EOF

# ── The assertion ────────────────────────────────────────────────────────────
#
# This deliberately does NOT re-use the name patterns above. An assertion built
# from the same globs as the deletion can only prove that `rm` ran; it is blind
# to the failure that actually matters, which is a glob that never matched the
# artifact in the first place. Asked to catch a planted fingerprint, such a
# check "passes" because the prune deleted the evidence before looking.
#
# So ask a different oracle: cargo records in each `.d` depfile the source
# files an artifact was built FROM. A dependency's depfile points into the
# registry; anything built from workspace source points back into the
# workspace. That is the property we actually care about, and it holds however
# the artifact happens to be named.
ws_root="$(cd "$(dirname "$MANIFEST")" && pwd)"
abs_target="$(cd "$TARGET_DIR" && pwd)"

# Every depfile names its own output under target/, so that prefix is excluded;
# what remains is genuine source input.
leaked_paths="$(find "$abs_target" -name '*.d' -print0 2>/dev/null \
    | xargs -0 -r grep -h -oE "${ws_root}/[^ :]*" 2>/dev/null \
    | grep -v "^${abs_target}/" \
    | sort -u || true)"

if [ -n "$leaked_paths" ]; then
    echo "prune: REFUSING to publish -- artifacts still reference workspace source:" >&2
    printf '%s\n' "$leaked_paths" | sed 's/^/  /' | head -20 >&2
    exit 2
fi

echo "prune: ok -- $(printf '%s\n' "$members" | wc -l) workspace member(s) stripped," \
     "no surviving artifact references workspace source"