#!/usr/bin/env bash
# Tests for newest_matching_file() in tools/install.sh.
#
# The function answers one question -- "which is the most recent backup / tarball
# here?" -- and its callers act destructively on the answer. Three ways of getting it
# wrong have already been found, and each has a case below:
#
#   * `ls -1t | head -1` returns 141 under `set -o pipefail` once the listing fills a
#     pipe buffer (~1600 names), because head closes the pipe and ls takes SIGPIPE.
#     Callers assign it at top level under `set -e`, so a 141 aborts the run.
#   * `mapfile` is a Bash 4 builtin. macOS ships Bash 3.2 and the installer supports
#     Darwin, so the whole lookup was unavailable there -- and an empty answer is what
#     sends the uninstaller down its delete-the-destination branch.
#   * Any line-based parse of `ls` splits a filename containing a newline into two
#     wrong answers.
#
# The large-population and newline cases are the point: with two or three ordinary
# names every version of this function passes, which is why the first two went
# unnoticed.

set -euo pipefail

ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
TMP="$(mktemp -d "${TMPDIR:-/tmp}/mosaic-newest-match-test-XXXXXX")"
trap 'rm -rf "$TMP"' EXIT

# Load the function under test and the mtime helper it depends on, with the same
# shell options install.sh runs under.
eval "$(sed -n '/^_MTIME_STYLE=/,/^}/p' "$ROOT/tools/install.sh")"
eval "$(sed -n '/^newest_matching_file()/,/^}/p' "$ROOT/tools/install.sh")"

POPULATED="$TMP/many"
mkdir -p "$POPULATED"
# Enough names to overflow a 64 KiB pipe buffer several times over.
for i in $(seq 1 5000); do
  : > "$POPULATED/mosaicstack-mosaic-0.0.${i}.tgz"
done
sleep 1
: > "$POPULATED/mosaicstack-mosaic-9.9.9.tgz"

echo "[test] the newest match is returned from a directory large enough to fill a pipe"
GOT="$(newest_matching_file "$POPULATED" 'mosaicstack-mosaic-*.tgz')"
[[ "$(basename "$GOT")" == "mosaicstack-mosaic-9.9.9.tgz" ]] || {
  echo "expected the newest tarball, got '${GOT}'" >&2
  exit 1
}

echo "[test] a large population does not make the lookup fail"
set +e
newest_matching_file "$POPULATED" 'mosaicstack-mosaic-*.tgz' >/dev/null
RC=$?
set -e
[[ "$RC" -eq 0 ]] || { echo "expected rc=0, got ${RC} (141 means the SIGPIPE regression is back)" >&2; exit 1; }

echo "[test] a small population still works"
SMALL="$TMP/few"
mkdir -p "$SMALL"
: > "$SMALL/mosaicstack-gateway-0.0.1.tgz"
sleep 1
: > "$SMALL/mosaicstack-gateway-0.0.2.tgz"
GOT="$(newest_matching_file "$SMALL" 'mosaicstack-gateway-*.tgz')"
[[ "$(basename "$GOT")" == "mosaicstack-gateway-0.0.2.tgz" ]] || {
  echo "expected the newer gateway tarball, got '${GOT}'" >&2
  exit 1
}

echo "[test] a name containing a space is returned whole"
SPACED="$TMP/spaced"
mkdir -p "$SPACED"
: > "$SPACED/agents.md.mosaic-bak-one two"
GOT="$(newest_matching_file "$SPACED" 'agents.md.mosaic-bak-*')"
[[ "$GOT" == "$SPACED/agents.md.mosaic-bak-one two" ]] || {
  echo "expected the spaced name intact, got '${GOT}'" >&2
  exit 1
}

echo "[test] a name containing a newline is returned whole, not split"
# The old `ls -1t` parse reported this file as two separate shorter names, neither of
# which exists -- so the caller saw a backup path that could not be restored.
NEWLINE="$TMP/newline"
mkdir -p "$NEWLINE"
WEIRD="$NEWLINE/agents.md.mosaic-bak-$(printf 'a\nb')"
: > "$WEIRD"
GOT="$(newest_matching_file "$NEWLINE" 'agents.md.mosaic-bak-*')"
[[ "$GOT" == "$WEIRD" ]] || {
  echo "expected the newline-containing name intact, got '${GOT}'" >&2
  exit 1
}
[[ -f "$GOT" ]] || { echo "the returned path does not name a real file" >&2; exit 1; }

echo "[test] no match is an empty answer, not an error"
EMPTY="$TMP/none"
mkdir -p "$EMPTY"
set +e
GOT="$(newest_matching_file "$EMPTY" 'nothing-*.tgz')"
RC=$?
set -e
[[ "$RC" -eq 0 && -z "$GOT" ]] || { echo "expected empty output and rc=0, got '${GOT}' rc=${RC}" >&2; exit 1; }

echo "[test] a directory that does not exist is an empty answer, not an error"
set +e
GOT="$(newest_matching_file "$TMP/absent" 'nothing-*.tgz')"
RC=$?
set -e
[[ "$RC" -eq 0 && -z "$GOT" ]] || { echo "expected empty output and rc=0, got '${GOT}' rc=${RC}" >&2; exit 1; }

echo "[test] an unanswerable lookup fails loudly instead of reporting no match"
# This is the distinction the uninstaller depends on. "No backup exists" is licence to
# delete the destination; "I could not tell" must never reach that branch.
_MTIME_STYLE=none
set +e
GOT="$(newest_matching_file "$SMALL" 'mosaicstack-gateway-*.tgz')"
RC=$?
set -e
_MTIME_STYLE=""
[[ "$RC" -ne 0 ]] || {
  echo "expected a non-zero rc when no mtime source is usable, got rc=0 output '${GOT}'" >&2
  exit 1
}

echo "[test] the installer uses no Bash 4 syntax"
# A lint, not an execution test: this host has no Bash 3.2 to run under. It is still
# the thing that stops the regression, because every Bash 4 construct that has broken
# macOS here was introduced by someone who never ran the script there either.
# Comments are stripped first -- the ones above name these constructs on purpose.
BASH4_HITS="$(
  sed 's/#.*$//' "$ROOT/tools/install.sh" \
    | grep -nE '(^|[^[:alnum:]_])(mapfile|readarray)([^[:alnum:]_]|$)|declare[[:space:]]+-[a-zA-Z]*A|local[[:space:]]+-[a-zA-Z]*A|\$\{[A-Za-z_][A-Za-z0-9_]*(\^\^|,,)' \
    || true
)"
[[ -z "$BASH4_HITS" ]] || {
  echo "tools/install.sh uses Bash 4+ syntax, which macOS's Bash 3.2 cannot run:" >&2
  echo "$BASH4_HITS" >&2
  exit 1
}

echo "[test] newest_matching_file tests passed"