holocron/tests/run-bats.sh

#!/usr/bin/env bash
# Run all bats test files in the repo.
# Usage: bash tests/run-bats.sh
set -euo pipefail

REPO_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
BATS="$REPO_ROOT/tests/bats/bin/bats"

if [[ ! -x "$BATS" ]]; then
    echo "bats not found at $BATS — initializing submodules..." >&2
    git -C "$REPO_ROOT" submodule update --init --recursive
fi

if [[ ! -x "$BATS" ]]; then
    echo "Error: bats still not found at $BATS after submodule init" >&2
    exit 1
fi

# Collected with a `while read` loop rather than `mapfile` — macOS ships
# /bin/bash 3.2, which has no `mapfile`. Process substitution (not a pipe)
# keeps the loop in this shell so the appends survive. `sort` is still fed
# newline-delimited output, exactly as before. Same convention as
# tests/run-tests.sh.
TEST_FILES=()
while IFS= read -r f; do
    TEST_FILES+=("$f")
done < <(
    find "$REPO_ROOT" -name "*.bats" \
        -not -path "*/tests/bats/*" \
        -not -path "*/test_helper/*" \
        -not -path "*/.claude/worktrees/*" \
        | sort
)

if [[ ${#TEST_FILES[@]} -eq 0 ]]; then
    echo "No .bats test files found." >&2
    exit 0
fi

# Each file gets its own `bats` process, run concurrently (bounded by core
# count) instead of one `bats` invocation working through all files serially.
# A single test file is still serial internally -- this only overlaps the
# fixed per-process startup cost (git/apm subprocess spawns dominate several
# of these suites) across files, which is where the wall-clock actually goes.
# Output is buffered per file so concurrent TAP streams can't interleave, then
# flushed in stable sorted order once every job has finished.
#
# Dispatch and throttling is scripts/lib/batch-run.sh's batch_run -- shared
# with scripts/sync-plugin-content.sh and tests/run-tests.sh so a batching bug
# fix only needs to land once; see that file for why this is batched rather
# than a rolling `wait -n` pool.
SCRATCH_ROOT="$(mktemp -d)"
trap 'rm -rf "$SCRATCH_ROOT"' EXIT
# Repo-root-relative -- see tests/run-tests.sh for why `../scripts/...` does not
# resolve here despite looking right.
# shellcheck source=scripts/lib/batch-run.sh
source "$REPO_ROOT/scripts/lib/batch-run.sh"

declare -a batch_args=()
i=0
for f in ${TEST_FILES[@]+"${TEST_FILES[@]}"}; do
    i=$((i + 1))
    cmd="$(printf '%q %q; echo $? >%q' "$BATS" "$f" "$SCRATCH_ROOT/$i.status")"
    batch_args+=("$i" "$cmd")
done
batch_run "$SCRATCH_ROOT" ${batch_args[@]+"${batch_args[@]}"}

FAIL=0
TOTAL_OK=0
TOTAL_NOT_OK=0
TOTAL_PLANS=0
i=0
for f in ${TEST_FILES[@]+"${TEST_FILES[@]}"}; do
    i=$((i + 1))
    rel="${f#"$REPO_ROOT"/}"
    echo "=== $rel ==="
    cat "$SCRATCH_ROOT/$i.log"
    echo ""
    file_ok="$(grep -c '^ok ' "$SCRATCH_ROOT/$i.log" || true)"
    file_not_ok="$(grep -c '^not ok ' "$SCRATCH_ROOT/$i.log" || true)"
    # The TAP plan line (`1..N`). Counted separately from the results because an
    # empty-but-valid file emits `1..0` and no result lines at all -- that is a
    # file bats really did run, so it has to be distinguishable from a file that
    # produced nothing whatsoever.
    file_plan="$(grep -c '^1\.\.[0-9]' "$SCRATCH_ROOT/$i.log" || true)"
    status="$(cat "$SCRATCH_ROOT/$i.status" 2>/dev/null || echo 1)"
    TOTAL_OK=$((TOTAL_OK + file_ok))
    TOTAL_NOT_OK=$((TOTAL_NOT_OK + file_not_ok))
    TOTAL_PLANS=$((TOTAL_PLANS + file_plan))
    if [[ "$file_not_ok" -gt 0 || "$status" -ne 0 ]]; then
        FAIL=1
    fi
done

# Zero counted tests is never a clean run: files were found (the empty-TEST_FILES
# case exits above), so nothing was executed. Without this, a `bats` that emits
# nothing and exits 0 -- a broken binary, a formatter change, or a wholesale
# `@test` removal -- reports "0 tests, 0 failures" and exits green, silently
# turning a total harness failure into a pass.
#
# The two causes get different messages because they are different problems and
# `1..0` is itself valid TAP: no plan lines at all means bats produced no output
# to parse, while plans present with zero results means bats ran fine and the
# files genuinely declare no tests.
if [[ $((TOTAL_OK + TOTAL_NOT_OK)) -eq 0 ]]; then
    if [[ "$TOTAL_PLANS" -eq 0 ]]; then
        echo "Error: ${#TEST_FILES[@]} .bats file(s) ran but produced no TAP output at all — the bats harness is broken" >&2
    else
        echo "Error: ${#TEST_FILES[@]} .bats file(s) declared 0 tests — every @test appears to have been removed" >&2
    fi
    FAIL=1
fi

echo "$((TOTAL_OK + TOTAL_NOT_OK)) tests, $TOTAL_NOT_OK failures"
exit "$FAIL"