#!/usr/bin/env bats
# tests/pkg-inventory.bats — black-box tests for scripts/pkg-inventory.sh (Refs #51)
#
# Contract: `install.sh` installs desired-minus-installed from packages/*.pkgs. This tool walks
# the other direction — installed-minus-declared — because a manifest the machine has quietly
# outgrown cannot reproduce the machine on a rebuild. Only stdout, stderr and the exit status are
# observed: 0 no drift, 1 drift (hand-installed packages undeclared), 2 usage, 3 sync databases
# unavailable so repo/AUR classification is impossible.
#
# Every pacman/flatpak call hits a stub: nothing here may query the real package database, and a
# real pacman on PATH would make the fixture answers depend on the workstation.

setup() {
  TEST_TMP="$(mktemp -d)"
  SCRIPT="$BATS_TEST_DIRNAME/../scripts/pkg-inventory.sh"
  REPO="$TEST_TMP/repo"
  mkdir -p "$REPO/packages" "$TEST_TMP/bin"

  # --- manifests: common + host(box) + aur ------------------------------------
  cat > "$REPO/packages/common.pkgs" <<'EOF'
# common desired state
ghostty
zoxide
vlc                     # declared, deliberately NOT installed below
EOF
  cat > "$REPO/packages/box.pkgs" <<'EOF'
neovim
EOF
  cat > "$REPO/packages/aur.pkgs" <<'EOF'
typora          # AUR-only desired state
EOF

  # --- pacman log: install day 2026-01-01, hand installs from 2026-03 ----------
  cat > "$TEST_TMP/pacman.log" <<'EOF'
[2026-01-01T10:00:00-0800] [PACMAN] Running 'pacman --sysroot /tmp/calamares-root-x -S base'
[2026-01-01T10:00:01-0800] [ALPM] installed filesystem (2026.01.01-1)
[2026-01-01T10:00:02-0800] [ALPM] installed base (3-1)
[2026-01-01T10:00:03-0800] [ALPM] installed libfoo (1.0-1)
[2026-03-04T09:00:00-0800] [ALPM] installed bun (1.2-1)
[2026-03-04T09:30:00-0800] [ALPM] upgraded filesystem (2026.01.01-1 -> 2026.03.01-1)
[2026-03-05T09:00:00-0800] [ALPM] installed nirimod-git (r7-1)
[2026-03-07T09:00:00-0800] [ALPM] installed libstray (1.0-1)
[2026-03-06T09:00:00-0800] [ALPM] removed base (3-1)
EOF

  # --- installed state --------------------------------------------------------
  # ghostty/zoxide/neovim/typora declared. libfoo: explicit, arrived with the installer.
  # bun/nirimod-git: installed by hand afterwards, undeclared. python-hatchling and libstray:
  # installed as dependencies and now unrequired (pacman -Qtdq). libstray arrived AFTER the
  # baseline, so the date filter alone cannot keep it out of drift — only the explicit query can.
  printf '%s\n' base bun filesystem ghostty libfoo libstray neovim nirimod-git typora zoxide > "$TEST_TMP/local-all"
  printf '%s\n' bun ghostty libfoo neovim nirimod-git typora zoxide > "$TEST_TMP/local-explicit"
  printf '%s\n' python-hatchling libstray > "$TEST_TMP/orphans"
  # nirimod-git is deliberately ABSENT here: no sync db can serve it, which is the fact that
  # routes it to aur.pkgs in the test below.
  printf '%s\n' bun ghostty neovim typora zoxide libfoo vlc python-hatchling base filesystem > "$TEST_TMP/sync-all"

  # Four flag combinations are the script's whole interface to the package manager; the stub
  # answers those and refuses anything else, so an accidental new query fails loudly.
  cat > "$TEST_TMP/bin/pacman" <<'STUB'
#!/usr/bin/env bash
case "$1" in
  -Sl)   [ "${STUB_SYNC_EMPTY:-0}" = 1 ] && exit 1
         sed 's/^/syncdb /' "$SYNC_ALL" ;;
  -Qqe)  cat "$LOCAL_EXPLICIT" ;;
  -Qtdq) cat "$ORPHANS"; [ -s "$ORPHANS" ] ;;
  -Qq)   cat "$LOCAL_ALL" ;;
  *)     echo "stub pacman: unhandled args: $*" >&2; exit 64 ;;
esac
STUB
  cat > "$TEST_TMP/bin/flatpak" <<'STUB'
#!/usr/bin/env bash
[ "${STUB_NO_FLATPAK:-0}" = 1 ] && exit 127
printf '%s\n' com.discordapp.Discord
STUB
  chmod +x "$TEST_TMP/bin/pacman" "$TEST_TMP/bin/flatpak"

  export PATH="$TEST_TMP/bin:$PATH"
  export PKGINV_REPO="$REPO" PKGINV_HOST=box PKGINV_LOG="$TEST_TMP/pacman.log"
  export LOCAL_ALL="$TEST_TMP/local-all" LOCAL_EXPLICIT="$TEST_TMP/local-explicit"
  export ORPHANS="$TEST_TMP/orphans" SYNC_ALL="$TEST_TMP/sync-all"
}

teardown() { rm -rf "$TEST_TMP"; }

# section RE_START RE_END — the report from RE_START's line up to (not including) RE_END, so an
# assertion proves a name landed in a specific section instead of merely appearing somewhere in the
# report. Start inclusive (the count and the names sit on the label line), terminator exclusive (a
# plain sed range would leak the next section's first line). Anchoring matters: an unanchored start
# runs the range to end-of-output, silently turning every absence assertion into a vacuous pass —
# exactly how four of these tests were passing before this helper was fixed.
section() { printf '%s\n' "$output" | awk -v s="$1" -v e="$2" '$0 ~ e {on=0} $0 ~ s {on=1} on'; }
ADDITIONS() { section "^undeclared additions" "^installer-provided"; }

@test "header names the host and takes the baseline from the oldest install line" {
  run "$SCRIPT"
  [ "$status" -eq 1 ]   # the fixture has drift by design
  [[ "$output" == *"pkg-inventory host=box"* ]]
  [[ "$output" == *"baseline=2026-01-01"* ]]
}

@test "hand-installed packages are reported as additions" {
  run "$SCRIPT"
  [[ "$output" == *"undeclared additions (declare these): 2"* ]]
  s="$(ADDITIONS)"
  [[ "$s" == *bun* ]]
  [[ "$s" == *nirimod-git* ]]
}

@test "a package the installer provided is not reported as an addition" {
  run "$SCRIPT"
  additions="$(ADDITIONS)"
  [[ "$additions" != *libfoo* ]]
  [[ "$(section "^installer-provided" "^declared,")" == *libfoo* ]]
  # The folded block must end in a newline. Without one, the following label is glued onto the
  # last folded line and every section after it vanishes from a sliced report.
  [[ "$(section "^installer-provided" "^declared,")" != *declared,* ]]
}

@test "AUR-only packages are separated from sync-repo packages" {
  run "$SCRIPT"
  # nirimod-git is missing from the sync-DB fixture, so only a helper can install it: it must be
  # routed to aur.pkgs, not to a pacman line that would fail on a fresh box. Bash `*` crosses
  # newlines, so the absence check runs on one line rather than on the whole section.
  repo_line="$(section '^  repo ' '^  aur ')"
  [[ "$repo_line" == *"repo (sync dbs): bun"* ]]
  [[ "$repo_line" != *nirimod-git* ]]
  [[ "$(section '^  aur ' '^installer-provided')" == *"aur (needs a helper): nirimod-git"* ]]
}

@test "declared-but-missing packages are listed for install.sh" {
  run "$SCRIPT"
  [[ "$output" == *"declared, not installed"* ]]
  [[ "$(section "^declared," "^orphans")" == *vlc* ]]
}

@test "orphans are named on their own line, not mixed into the drift answer" {
  run "$SCRIPT"
  [[ "$(section "^orphans" "^flatpak")" == *python-hatchling* ]]
  [[ "$(ADDITIONS)" != *python-hatchling* ]]
}

@test "a dependency installed after the baseline is never drift, orphan or not" {
  # Drift means `pacman -Qqe` — you asked for this one. libstray arrived as a dependency
  # after install day and is now unrequired, so the baseline filter does not exclude it:
  # only the explicit query does. Swap -Qqe for -Qq and every dependency on the machine,
  # dead ones included, becomes a manifest line install.sh will reinstall on a rebuild.
  run "$SCRIPT"
  [[ "$(ADDITIONS)" != *libstray* ]]
  [[ "$output" == *"undeclared additions (declare these): 2"* ]]
  [[ "$(section "^orphans" "^flatpak")" == *libstray* ]]
  run "$SCRIPT" --emit
  [[ "$output" != *libstray* ]]
}

@test "--help prints the header and stops before the shell" {
  # The header IS the contract (report shape, exit status, seams). A hardcoded line range
  # that runs past the comment block hands the reader `set -euo pipefail` as if it were
  # documentation.
  run "$SCRIPT" --help
  [ "$status" -eq 0 ]
  [[ "$output" == *"Exit status"* ]]
  [[ "$output" != *"pipefail"* ]]
  [[ "$output" != *"LC_ALL"* ]]
}

@test "--baseline moves packages installed on that date into the installer set" {
  # Inclusive date semantics: pushing the baseline to bun's install date makes bun installer
  # furniture, while nirimod-git (the next day) is still a hand install.
  run env PKGINV_BASELINE=2026-03-04 "$SCRIPT"
  [[ "$output" == *"baseline=2026-03-04"* ]]
  s="$(ADDITIONS)"
  [[ "$s" != *bun* ]]
  [[ "$s" == *nirimod-git* ]]
}

@test "--emit prints lines that survive the manifest parser" {
  run "$SCRIPT" --emit
  [ "$status" -eq 0 ]
  # install.sh reads manifests as `sed 's/#.*//'` then the first field, so an emitted name must
  # be a bare token: a stray path or trailing note would be handed to pacman as a package name.
  bad="$(printf '%s\n' "$output" | grep -v '^#' | grep -vE '^[A-Za-z0-9@._+-]+$' || true)"
  [ -z "$bad" ]
  printf '%s\n' "$output" > "$REPO/packages/emitted.pkgs"
  names="$(sed 's/#.*//' "$REPO/packages/emitted.pkgs" | awk '{if ($1) print $1}' | sort | tr '\n' ' ')"
  [[ "$names" == *bun* ]]
  [[ "$names" == *nirimod-git* ]]
  [[ "$names" != *ghostty* ]]
  [[ "$names" != *libfoo* ]]
  [[ "$names" != *vlc* ]]
}

@test "an unknown host gets the common manifest only, so host packages look undeclared" {
  # Mirrors install.sh: wrong-host runs are a no-op, not a hazard. Here that means neovim,
  # declared only in box.pkgs, counts as an addition when the host is not box.
  run env PKGINV_HOST=otherbox "$SCRIPT"
  [[ "$(ADDITIONS)" == *neovim* ]]
}

@test "no drift exits 0" {
  printf '%s\n' ghostty libfoo zoxide > "$TEST_TMP/local-explicit"
  run "$SCRIPT"
  [ "$status" -eq 0 ]
  [[ "$output" == *"undeclared additions (declare these): 0"* ]]
}

@test "missing sync databases fail loudly rather than misclassifying everything as AUR" {
  run env STUB_SYNC_EMPTY=1 "$SCRIPT"
  [ "$status" -eq 3 ]
  [[ "$output" == *"sync"* ]]
}

@test "flatpak apps are reported separately from pacman packages" {
  run "$SCRIPT"
  [[ "$output" == *"flatpak"*com.discordapp.Discord* ]]
}

@test "a box without flatpak still reports the pacman inventory" {
  run env STUB_NO_FLATPAK=1 "$SCRIPT"
  [ "$status" -eq 1 ]
  [[ "$output" == *"flatpak"* ]]
  [[ "$(ADDITIONS)" == *bun* ]]
}

@test "the baseline is found in a rotated log when the install day has aged out of the live one" {
  # pacman rotates its log; without reading the rotated file the whole base system would be
  # reported as hand-installed additions on any machine older than the rotation window.
  mv "$TEST_TMP/pacman.log" "$TEST_TMP/pacman.log.1"
  printf '[2026-10-01T09:00:00-0700] [ALPM] upgraded zoxide (0.9-1 -> 0.10-1)\n' > "$TEST_TMP/pacman.log"
  run env PKGINV_LOG="$TEST_TMP/pacman.log $TEST_TMP/pacman.log.1" "$SCRIPT"
  [[ "$output" == *"baseline=2026-01-01"* ]]
  [[ "$(ADDITIONS)" != *libfoo* ]]
}

@test "a log larger than the pipe buffer still yields the baseline" {
  # A real install day writes thousands of install lines. `sort | head -1` under pipefail dies of
  # SIGPIPE once that output exceeds the pipe buffer, and no small fixture can show it — the first
  # run against a real log is where it surfaced. seq, not yes: yes would SIGPIPE in the fixture.
  seq 1 20000 | awk '{print "[2025-05-05T10:00:00-0700] [ALPM] installed pkgfiller (1-1)"}' > "$TEST_TMP/big.log"
  cat "$TEST_TMP/big.log" "$TEST_TMP/pacman.log" > "$TEST_TMP/combined.log"
  run env PKGINV_LOG="$TEST_TMP/combined.log" "$SCRIPT"
  [ "$status" -eq 1 ]
  [[ "$output" == *"baseline=2025-05-05"* ]]
}

@test "usage is a distinct exit status from drift" {
  run "$SCRIPT" --nope
  [ "$status" -eq 2 ]
}