#!/usr/bin/env bash
# Regression test for seed-target-dir.sh: which source a run seeds from, and
# what happens when two jobs sharing one cache key seed at the same time.
#
# Runs the ACTUAL script against a real scratch cache directory with fake
# target trees standing in for cargo output — no compiler needed, so this is
# the fast half of the suite. hardlink-clone-selftest.sh covers the parts that
# need a real build.
#
# What each scenario demonstrates:
#
#   1. BASE SNAPSHOT PREFERRED — a PR whose base has published a snapshot
#      seeds from it, and the seeded directory really is a hardlink clone
#      (shared inodes), not a copy.
#   2. OWN DIR WINS — a second run of the same ref reuses what is already
#      there and does not re-seed over its own work.
#   3. OWN SNAPSHOT AS SELF-RESTORE — a publisher whose live target dir was
#      evicted restores from the snapshot it last published, instead of
#      rebuilding cold.
#   4. FALLBACK DIR — with no snapshot at all, an explicitly configured
#      fallback (a pre-existing flat cache, during a migration) is used.
#   5. COLD — with nothing available, the directory is created empty rather
#      than the script failing.
#   6. LOCK FILES STRIPPED — Cargo's in-place-flock'd lock files never
#      survive a clone, because a shared lock inode would make two branches
#      contend on one mutex.
#   7. CONCURRENT SEED IS ATOMIC — two seeds racing on one cache key: the
#      loser discards its staging copy and uses the winner's directory, and
#      at no point is a partially-populated directory visible under the final
#      name. This is the property that replaces "the runner only has one job
#      slot" with an actual guarantee.
#   8. SEED VS PUBLISH ROTATION — the race scenario 7 does NOT cover, and the
#      one that actually mattered: a consumer hardlink-cloning a snapshot
#      while the publisher of that snapshot rotates it and unlinks the
#      generation being read. Two seeds racing on a DESTINATION is a different
#      race from a seed racing a publisher on its SOURCE, and only the second
#      one can truncate a tree. Against the unguarded version this scenario
#      reproduces a silent partial clone reported as success — 20,328 of
#      48,805 entries, `seed: cloned in 1s`, exit 0, seeded-from=base-snapshot.
#   9. AN UNREADABLE SOURCE FAILS LOUDLY — the clone reports a distinct status
#      instead of renaming whatever it managed to produce into place, and the
#      seed SCRIPT turns that status into a failed job rather than a silent
#      cold build. Retries are what make a torn read survivable; exhausting
#      them must not degrade into "start cold and rebuild everything", which
#      would turn a corrupt-cache bug into an invisible 4x-slower CI job.
#      (The publisher's half of the rotation race — deferring reclamation
#      while a reader is still in flight — lives in
#      publish-snapshot-selftest.sh, next to the swap it modifies.)
set -euo pipefail
script_dir=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
. "$script_dir/cache-lib.sh"

scratch=$(mktemp -d)
trap 'rm -rf "$scratch"' EXIT
root="$scratch/cache"
mkdir -p "$root"
pass_count=0

fail() { echo "ASSERTION FAILED: $*" >&2; exit 1; }
ok() { pass_count=$((pass_count + 1)); echo "PASS: $*"; }
assert_file() { [ -e "$1" ] || fail "expected $1 to exist ($2)"; ok "$2"; }
assert_absent() { [ -e "$1" ] && fail "expected $1 to be gone ($2)"; ok "$2"; }
assert_content() { [ "$(cat "$1")" = "$2" ] || fail "expected '$2' in $1, got '$(cat "$1")' ($3)"; ok "$3"; }

# A plausible target tree: a big shared artifact, a mutable fingerprint, a
# build-script output, and a lock file.
make_tree() {
  local d="$1" marker="$2"
  mkdir -p "$d/debug/deps" "$d/debug/.fingerprint/x" "$d/debug/build/x/out"
  echo "$marker" > "$d/debug/deps/libx.rlib"
  echo "$marker" > "$d/debug/.fingerprint/x/dep-lib-x"
  echo "$marker" > "$d/debug/build/x/out/gen.txt"
  : > "$d/debug/.cargo-lock"
}

seed() { bash "$script_dir/seed-target-dir.sh" "$@" > "$scratch/log" 2>&1 || { tail -40 "$scratch/log"; fail "seed-target-dir.sh exited non-zero"; }; }

# Always succeeds and always prints a number: an absent directory is "0
# entries so far", which is the normal state at the top of the progress poll
# below, not an error worth aborting the suite over.
tree_entries() {
  local n
  n=$(find "$1" -mindepth 1 2>/dev/null | wc -l) || n=0
  printf '%s\n' "$n"
  return 0
}

# A tree wide enough that a hardlink clone of it takes long enough to be
# caught mid-walk. The race under test is a real interleaving, not a mocked
# one, so the fixture has to be big enough for the window to exist: a
# four-file tree clones in microseconds and no scheduling could ever land
# inside it. Built by cloning one small template directory N times, which is N
# forks rather than N*M file creations.
make_wide_tree() {
  local d="$1" marker="$2" ndirs="$3" i
  mkdir -p "$d/debug/deps/.tmpl" "$d/debug/.fingerprint/x"
  for i in $(seq 0 59); do echo "$marker" > "$d/debug/deps/.tmpl/f$i"; done
  for i in $(seq -w 1 "$ndirs"); do cp -al "$d/debug/deps/.tmpl" "$d/debug/deps/d$i"; done
  rm -rf "$d/debug/deps/.tmpl"
  echo "$marker" > "$d/debug/.fingerprint/x/dep-lib-x"
}

BASE_KEY=$(cache_key dev)
OWN_KEY=$(cache_key feat/thing)

echo "=== 1: base snapshot preferred, and cloned by hardlink ==="
make_tree "$root/snapshot-$BASE_KEY" base-content
seed "$OWN_KEY" "$BASE_KEY" "$root" job1
own="$root/target-$OWN_KEY"
assert_content "$own/debug/deps/libx.rlib" base-content "seeded from the base snapshot"
[ "$(stat -c '%i' "$own/debug/deps/libx.rlib")" = "$(stat -c '%i' "$root/snapshot-$BASE_KEY/debug/deps/libx.rlib")" ] \
  || fail "artifact was copied, not hardlinked"
ok "artifact shares an inode with the snapshot (hardlink clone, not a copy)"
[ "$(stat -c '%i' "$own/debug/.fingerprint/x/dep-lib-x")" != "$(stat -c '%i' "$root/snapshot-$BASE_KEY/debug/.fingerprint/x/dep-lib-x")" ] \
  || fail "fingerprint still shares an inode with the snapshot"
ok "fingerprint is privately owned (unshare_mutable_paths ran)"

echo
echo "=== 6: Cargo lock files never survive a clone ==="
assert_absent "$own/debug/.cargo-lock" "cloned .cargo-lock removed"

echo
echo "=== 2: an existing own dir is reused, never re-seeded over ==="
echo own-work > "$own/debug/deps/libx.rlib"
seed "$OWN_KEY" "$BASE_KEY" "$root" job1
assert_content "$own/debug/deps/libx.rlib" own-work "own directory reused as-is"
grep -q 'reusing this ref' "$scratch/log" || fail "expected the reuse path in the log"
ok "reuse is reported in the log"

echo
echo "=== 3: a publisher restores from its own snapshot after eviction ==="
make_tree "$root/snapshot-$BASE_KEY" published-dev
seed "$BASE_KEY" "" "$root" job1
assert_content "$root/target-$BASE_KEY/debug/deps/libx.rlib" published-dev "publisher self-restored from its own snapshot"

echo
echo "=== 4: explicit fallback dir when no snapshot exists ==="
OTHER=$(cache_key feat/other)
make_tree "$scratch/legacy-flat" legacy
seed "$OTHER" "$(cache_key nosuch)" "$root" job1 "$scratch/legacy-flat"
assert_content "$root/target-$OTHER/debug/deps/libx.rlib" legacy "seeded from the fallback dir"

echo
echo "=== 5: cold start when nothing is available ==="
COLD=$(cache_key feat/cold)
seed "$COLD" "$(cache_key nosuch)" "$root" job1
[ -d "$root/target-$COLD" ] || fail "cold start did not create the directory"
[ -z "$(ls -A "$root/target-$COLD")" ] || fail "cold start directory is not empty"
ok "cold start creates an empty directory rather than failing"

echo
echo "=== 7: two jobs racing on one cache key ==="
RACE=$(cache_key feat/race)
make_tree "$root/snapshot-$BASE_KEY" race-source
# Both jobs seed concurrently from the same snapshot into the same key. Each
# stages under its own tag, so the only interaction is the final rename.
( bash "$script_dir/seed-target-dir.sh" "$RACE" "$BASE_KEY" "$root" jobA > "$scratch/logA" 2>&1 ) &
( bash "$script_dir/seed-target-dir.sh" "$RACE" "$BASE_KEY" "$root" jobB > "$scratch/logB" 2>&1 ) &
wait
race_dir="$root/target-$RACE"
assert_content "$race_dir/debug/deps/libx.rlib" race-source "the surviving directory is complete"
[ -z "$(find "$root" -maxdepth 1 -name '.stage-*' -print -quit)" ] || fail "a staging directory was left behind"
ok "no staging directory survived the race"
# Exactly one job may claim it seeded; the other must report either the
# concurrent-peer path or a plain reuse (if it started after the winner
# finished). Neither may report a cold start.
if grep -q 'starts cold' "$scratch/logA" "$scratch/logB"; then
  cat "$scratch/logA" "$scratch/logB"; fail "a racing job reported a cold start"
fi
ok "neither racing job fell through to a cold start"

echo
echo "=== 8: seeding while the base republishes the snapshot underneath it ==="
ROT=$(cache_key feat/rotate)
rm -rf "$root/snapshot-$BASE_KEY" "$root/target-$BASE_KEY"
# Generation 1 is wide (the consumer will still be walking it when the swap
# happens); the generation replacing it is small, so the publisher's own
# staging clone does not itself outlast the consumer's.
make_wide_tree "$root/snapshot-$BASE_KEY" gen1 800
make_wide_tree "$root/target-$BASE_KEY" gen2 8
gen1_entries=$(tree_entries "$root/snapshot-$BASE_KEY")

( bash "$script_dir/seed-target-dir.sh" "$ROT" "$BASE_KEY" "$root" jobRot > "$scratch/logRot" 2>&1; echo $? > "$scratch/rcRot" ) &
seed_pid=$!

# Rotate only once the clone is demonstrably mid-walk. Gating on observed
# progress rather than on a sleep is what makes the interleaving reproducible
# instead of a coin flip that passes on a fast machine for the wrong reason.
threshold=$(( gen1_entries / 5 ))
progress=0
deadline=$(( $(date +%s) + 60 ))
while :; do
  progress=$(tree_entries "$root/.stage-jobRot")
  if [ "$progress" -ge "$threshold" ]; then break; fi
  if ! kill -0 "$seed_pid" 2>/dev/null; then
    fail "the seed finished before its clone could be caught mid-walk (fixture too small for this machine?)"
  fi
  if [ "$(date +%s)" -ge "$deadline" ]; then
    fail "the staging clone never reached ${threshold} of ${gen1_entries} entries"
  fi
done
ok "caught the consumer's clone mid-walk at ${progress}/${gen1_entries} entries"

bash "$script_dir/publish-snapshot.sh" "$BASE_KEY" "$root" pubRot > "$scratch/logPub" 2>&1 \
  || { tail -40 "$scratch/logPub"; fail "publish-snapshot.sh exited non-zero"; }
wait "$seed_pid"

rot_dir="$root/target-$ROT"
[ "$(cat "$scratch/rcRot")" = "0" ] || { tail -40 "$scratch/logRot"; fail "the seed exited non-zero"; }
ok "the seed completed"
# THE assertion. Before the guard, this is where it failed: the seed reported
# `cloned in 1s` and exit 0 while target-<rot> held less than half the entries
# of the snapshot it claimed to have cloned. Comparing against the snapshot as
# it stands NOW is the right bar either way — a clone that raced the rotation
# must end up holding one complete generation, and a consumer caught mid-walk
# re-reads, so that generation is the new one.
snap_entries=$(tree_entries "$root/snapshot-$BASE_KEY")
rot_entries=$(tree_entries "$rot_dir")
[ "$rot_entries" -eq "$snap_entries" ] \
  || fail "the seeded tree is truncated: ${rot_entries} entries against the snapshot's ${snap_entries} (was ${gen1_entries} before the rotation)"
ok "the seeded tree is complete (${rot_entries} entries, no silent truncation)"
assert_content "$rot_dir/debug/.fingerprint/x/dep-lib-x" gen2 "the seeded tree holds one whole generation, not a splice of two"
grep -q 'was torn' "$scratch/logRot" || fail "the rotation was not detected as a torn read"
ok "the torn read was detected and reported, not swallowed"
[ -z "$(find "$root" -maxdepth 1 \( -name '.stage-*' -o -name '.reading-*' -o -name '.publish-*' \) -print -quit)" ] \
  || fail "scratch left behind: $(find "$root" -maxdepth 1 \( -name '.stage-*' -o -name '.reading-*' -o -name '.publish-*' \) -print)"
ok "no staging, reader-marker or deferred-generation scratch left behind"

echo
echo "=== 9: a source that cannot be read fails loudly ==="
rc=0
hardlink_clone_into "$root/nosuch-source" "$root/target-nosuch" nosuch-tag > "$scratch/logMissing" 2>&1 || rc=$?
[ "$rc" -eq 2 ] || fail "expected status 2 for an unreadable source, got ${rc}"
ok "an unreadable source returns the distinct hard-failure status"
assert_absent "$root/target-nosuch" "nothing was renamed into place"

# The status only matters if the script acts on it. A source that exists but
# cannot be read exercises the whole path: retries exhaust, the function
# returns 2, and seed-target-dir.sh must exit non-zero rather than falling
# through to its cold-start branch.
if [ "$(id -u)" = "0" ]; then
  echo "SKIP: running as root — mode bits do not deny access"
else
  UNREADABLE=$(cache_key feat/unreadable)
  VICTIM=$(cache_key feat/victim)
  make_tree "$root/snapshot-$UNREADABLE" locked-away
  chmod 000 "$root/snapshot-$UNREADABLE"
  rc=0
  CACHE_CLONE_ATTEMPTS=2 bash "$script_dir/seed-target-dir.sh" \
    "$VICTIM" "$UNREADABLE" "$root" jobUnread > "$scratch/logUnread" 2>&1 || rc=$?
  chmod 755 "$root/snapshot-$UNREADABLE"
  [ "$rc" -ne 0 ] || { tail -20 "$scratch/logUnread"; fail "the seed reported success against a source it could not read"; }
  ok "the seed exits non-zero when its source cannot be cloned"
  grep -q 'refusing to build against a partial cache' "$scratch/logUnread" \
    || { tail -20 "$scratch/logUnread"; fail "the failure was not reported as such"; }
  ok "the failure names the reason rather than exiting silently"
  if grep -q 'starts cold' "$scratch/logUnread"; then
    tail -20 "$scratch/logUnread"; fail "an unreadable source degraded into a silent cold build"
  fi
  ok "it does not degrade into a silent cold build"
  assert_absent "$root/target-$VICTIM" "no target dir was left behind by the failed seed"
fi

echo
echo "seed-target-dir-selftest: ${pass_count} assertions passed"