#!/usr/bin/env bash
# Regression test for the single assumption this whole caching scheme rests
# on: that a build running inside a hardlink clone cannot mutate the directory
# it was cloned from.
#
# That assumption is FALSE for a plain `cp -al`. Measured, and asserted below
# as an explicit control: build in a raw `cp -al` clone and the source's
# `.fingerprint/<unit>/dep-*` (under CARGO_UNSTABLE_CHECKSUM_FRESHNESS),
# `build/<pkg>/output`, `build/<pkg>/out/**` and `deps/*.d` all change,
# because Cargo and build scripts write those with a plain truncating write
# rather than the write-then-rename Cargo uses for real artifacts.
#
# The consequence is not a slow build, it is a wrong one: a PR clone rewrites
# the base's dep-info to describe the PR's sources while the base's cache
# still holds the artifact built from the base's sources; once the PR merges,
# the base's next run finds the checksums match its (now merged) sources,
# reports `Fresh`, and links a binary built from the pre-merge code.
#
# cache-lib.sh's unshare_mutable_paths() is what closes that, and this test is
# what proves it stays closed. The control matters as much as the fix: a
# scenario that passes for both would prove nothing.
#
# Needs a working cargo on PATH. Everything happens under a mktemp -d scratch
# tree. Run by hand: bash scripts/hardlink-clone-selftest.sh
set -euo pipefail
script_dir=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
. "$script_dir/cache-lib.sh"

command -v cargo >/dev/null || { echo "SKIP: no cargo on PATH"; exit 0; }

scratch=$(mktemp -d)
trap 'rm -rf "$scratch"' EXIT
pass_count=0

fail() { echo "ASSERTION FAILED: $*" >&2; exit 1; }
ok() { pass_count=$((pass_count + 1)); echo "PASS: $*"; }

# Content hash of every file in a tree, keyed by relative path.
snapshot_tree() { (cd "$1" && find . -type f -print0 | sort -z | xargs -0 -r sha1sum) 2>/dev/null; }

# `diff` exits 1 when the trees differ, which is the expected case here and
# must not trip `pipefail` — the difference IS the result.
mutated_paths() {
  { diff <(printf '%s' "$1") <(printf '%s' "$2") || true; } 2>/dev/null \
    | awk '/^[<>]/ { print $3 }' | sort -u
}

# A crate with a build script, because build-script OUT_DIR writes are one of
# the two mutation families and are invisible without one.
mkcrate() {
  local dir="$1"
  mkdir -p "$dir/src"
  cat > "$dir/Cargo.toml" <<'TOML'
[package]
name = "probe"
version = "0.1.0"
edition = "2021"
[workspace]
TOML
  cat > "$dir/build.rs" <<'RS'
use std::{env, fs, path::PathBuf};
fn main() {
    println!("cargo::rerun-if-changed=src/lib.rs");
    let out = PathBuf::from(env::var("OUT_DIR").unwrap());
    let src = fs::read_to_string("src/lib.rs").unwrap();
    fs::write(out.join("gen.txt"), format!("generated from {} bytes", src.len())).unwrap();
}
RS
}

crate_dir="$scratch/probe"
mkcrate "$crate_dir"
cd "$crate_dir"

export CARGO_INCREMENTAL=0
# Checksum freshness is where the worst failure lives (the dep-* file carries
# per-source checksums and is rewritten in place). Only available on nightly;
# without it the test still covers the build/ and *.d families.
CHECKSUM_MODE="off"
if cargo +nightly -V >/dev/null 2>&1; then
  export CARGO_UNSTABLE_CHECKSUM_FRESHNESS=true
  CARGO_BIN=(cargo +nightly)
  CHECKSUM_MODE="on"
else
  CARGO_BIN=(cargo)
fi
echo "=== checksum-freshness mode: ${CHECKSUM_MODE} ==="

CONTENT_A='pub fn f() -> u32 { 1 }'
CONTENT_B='pub fn f() -> u32 { 22222 } pub fn g() -> u32 { 7 }'

build_base() {
  local dir="$1"
  printf '%s\n' "$CONTENT_A" > src/lib.rs
  CARGO_TARGET_DIR="$dir" "${CARGO_BIN[@]}" build -q
}

echo
echo "=== control: a raw \`cp -al\` clone DOES mutate its source ==="
base_ctl="$scratch/base-ctl"; clone_ctl="$scratch/clone-ctl"
build_base "$base_ctl"
before=$(snapshot_tree "$base_ctl")
cp -al "$base_ctl" "$clone_ctl"
strip_cargo_locks "$clone_ctl"            # locks alone are not the hazard under test
printf '%s\n' "$CONTENT_B" > src/lib.rs
CARGO_TARGET_DIR="$clone_ctl" "${CARGO_BIN[@]}" build -q
after=$(snapshot_tree "$base_ctl")
ctl_mutated=$(mutated_paths "$before" "$after")
if [ -z "$ctl_mutated" ]; then
  fail "control produced no mutation — the test can no longer distinguish fixed from broken"
fi
ok "raw cp -al clone mutates the source ($(printf '%s\n' "$ctl_mutated" | wc -l) paths)"
printf '%s\n' "$ctl_mutated" | sed 's/^/       /'

if [ "$CHECKSUM_MODE" = "on" ]; then
  if printf '%s' "$ctl_mutated" | grep -q '\.fingerprint/.*/dep-'; then
    ok "control confirms the checksum-freshness dep-info file is among the mutated set"
  else
    fail "expected .fingerprint/*/dep-* in the control's mutated set under checksum freshness"
  fi
fi

echo
echo "=== fix: hardlink_clone_into() leaves the source byte-identical ==="
base_fix="$scratch/base-fix"; clone_fix="$scratch/clone-fix"
build_base "$base_fix"
before=$(snapshot_tree "$base_fix")
hardlink_clone_into "$base_fix" "$clone_fix" "selftest" || fail "hardlink_clone_into reported the destination already existed"

# The clone's contract, asserted before anything builds in it: artifacts
# share inodes (that is what makes the clone near-free), and every file Cargo
# rewrites in place does not (that is what makes it sound). Checking after a
# rebuild would prove nothing — the rebuild replaces those files anyway.
shared=0; unshared=0
while IFS= read -r f; do
  rel="${f#$base_fix/}"
  [ -e "$clone_fix/$rel" ] || continue
  if [ "$(stat -c '%i' "$f")" = "$(stat -c '%i' "$clone_fix/$rel")" ]; then
    case "$rel" in
      */.fingerprint/*|*/build/*|*.d|.rustc_info.json)
        fail "mutable path still shares an inode with the source: $rel" ;;
    esac
    shared=$((shared + 1))
  else
    unshared=$((unshared + 1))
  fi
done < <(find "$base_fix" -type f)
[ "$shared" -gt 0 ] || fail "nothing is shared — the clone degenerated into a full copy"
[ "$unshared" -gt 0 ] || fail "nothing was unshared — unshare_mutable_paths did not run"
ok "fresh clone shares ${shared} artifact files and privately owns ${unshared} mutable ones"

printf '%s\n' "$CONTENT_B" > src/lib.rs
CARGO_TARGET_DIR="$clone_fix" "${CARGO_BIN[@]}" build -q
after=$(snapshot_tree "$base_fix")
fix_mutated=$(mutated_paths "$before" "$after")
if [ -n "$fix_mutated" ]; then
  echo "  still mutated:" >&2
  printf '%s\n' "$fix_mutated" | sed 's/^/       /' >&2
  fail "a build in the clone mutated the source through a shared inode"
fi
ok "no file in the source changed after a full rebuild in the clone"

echo
echo "=== the whole point: the source's next build is still correct ==="
# The source's cache holds artifacts built from CONTENT_A. Advance the source
# to CONTENT_B (as a merge would) and rebuild in it. If the clone had
# corrupted its dep-info, Cargo would report Fresh and keep the stale rlib.
printf '%s\n' "$CONTENT_B" > src/lib.rs
touch -d '@1000000000' src/lib.rs
log="$scratch/rebuild.log"
CARGO_TARGET_DIR="$base_fix" "${CARGO_BIN[@]}" build -v > "$log" 2>&1 || { cat "$log"; fail "rebuild in the source failed"; }
if grep -qE '^\s+Fresh probe' "$log"; then
  fail "source declared its own crate Fresh against sources it has never built — stale-artifact reuse"
fi
ok "source correctly rebuilt its crate after advancing to the clone's content"

echo
echo "hardlink-clone-selftest: ${pass_count} assertions passed"