#!/bin/sh
# scripts/profile-tests.sh
# Generate timing reports for the trbldoc test suite.
#
# Two levels of detail:
#   1. Per-test wall-clock timings from bats (--timing + JUnit report). Always
#      produced. Answers "which tests take a long time".
#   2. Per-line hotspots inside trbldoc.sh (optional, --hotspots). Uses the
#      BASH_ENV xtrace hook to time individual source lines across the whole
#      run. Answers "which code takes a long time".
#
# POSIX sh; works under mingw bash, WSL bash and Alpine/busybox ash.
#
# Usage:
#   scripts/profile-tests.sh [-s all|unit|integration] [-o OUTDIR]
#                            [-n TOPN] [-p] [-t "file.sh ..."]
#
#   -s SUITE   suite to run (default: integration)
#   -o OUTDIR  output directory (default: reports/profile-<timestamp>)
#   -n TOPN    number of rows in the printed "slowest" summary (default: 20)
#   -p         also collect per-line hotspots inside the target script(s)
#   -t LIST    space-separated target source files for -p (default: trbldoc.sh)

set -u

SELF="$0"
. "$(dirname -- "$0")/lib/common.sh"
tb_resolve_paths "$SELF"

SUITE=integration
OUTDIR=""
TOPN=20
HOTSPOTS=0
TARGETS="trbldoc.sh"

while getopts ":s:o:n:pt:h" opt; do
  case "$opt" in
    s) SUITE="$OPTARG" ;;
    o) OUTDIR="$OPTARG" ;;
    n) TOPN="$OPTARG" ;;
    p) HOTSPOTS=1 ;;
    t) TARGETS="$OPTARG" ;;
    h) sed -n '2,30p' "$SELF"; exit 0 ;;
    :) tb_die "option -$OPTARG requires an argument" ;;
    \?) tb_die "unknown option -$OPTARG" ;;
  esac
done

tb_require awk
tb_require sort

[ -n "$OUTDIR" ] || OUTDIR="$REPO_ROOT/reports/profile-$(tb_timestamp)"
case "$OUTDIR" in
  /*|[A-Za-z]:[\\/]*)
    ;;
  *)
    OUTDIR="$REPO_ROOT/$OUTDIR"
    ;;
esac
mkdir -p "$OUTDIR" || tb_die "cannot create output dir: $OUTDIR"
JUNIT_DIR="$OUTDIR/junit"
mkdir -p "$JUNIT_DIR"

SUITE_DIRS="$(tb_suite_dirs "$SUITE")"
SUITE_DIRS_REL="$(tb_suite_dirs_rel "$SUITE")"

# ── 1. per-test timing via bats JUnit ───────────────────────────────────────
tb_info "running bats ($SUITE) with timing..."
# --timing adds per-test durations; the junit report captures them in XML.
# We do not abort on test failures: timing is still useful.
if tb_bats_usable "$SUITE"; then
  # shellcheck disable=SC2086
  bats --timing --report-formatter junit --output "$JUNIT_DIR" $SUITE_DIRS \
    > "$OUTDIR/bats-output.txt" 2>&1 || tb_info "bats reported failures (see bats-output.txt)"
  BATS_MODE="local"
elif command -v wsl >/dev/null 2>&1; then
  tb_info "local bats appears unusable; retrying via WSL bats..."
  WSL_REPO="$(tb_to_wsl_path "$REPO_ROOT")"
  WSL_JUNIT="$(tb_to_wsl_path "$JUNIT_DIR")"
  wsl -- bash -lc \
    "cd '$WSL_REPO' && bats --timing --report-formatter junit --output '$WSL_JUNIT' $SUITE_DIRS_REL" \
    > "$OUTDIR/bats-output.txt" 2>&1 || tb_info "bats (WSL) reported failures (see bats-output.txt)"
  BATS_MODE="wsl"
else
  tb_die "local bats command appears unusable and no WSL fallback is available"
fi

# Collect all JUnit XML the formatter produced.
: > "$OUTDIR/timings.tsv"
for xml in "$JUNIT_DIR"/*.xml; do
  [ -f "$xml" ] || continue
  awk -f "$LIB_DIR/timing-extract.awk" "$xml" >> "$OUTDIR/timings.tsv"
done

if [ ! -s "$OUTDIR/timings.tsv" ]; then
  if grep -qi "bash\\\\r" "$OUTDIR/bats-output.txt" 2>/dev/null; then
    tb_die "bats appears broken (CRLF shebang: 'bash\\r'). Reinstall bats or run dos2unix on the bats scripts, then retry."
  fi
  tb_die "no per-test timings parsed (check $OUTDIR/bats-output.txt)"
fi

# Sort slowest first.
sort -t "$(printf '\t')" -k1 -rn "$OUTDIR/timings.tsv" > "$OUTDIR/timings.sorted.tsv"

# CSV summary.
{
  printf 'seconds,suite,test\n'
  awk -F '\t' '{ gsub(/"/,"\"\"",$3); printf "%s,%s,\"%s\"\n",$1,$2,$3 }' \
    "$OUTDIR/timings.sorted.tsv"
} > "$OUTDIR/timings.csv"

# HTML report.
awk -f "$LIB_DIR/render-timing.awk" \
  -v TITLE="trbldoc test timings ($SUITE)" \
  "$OUTDIR/timings.sorted.tsv" > "$OUTDIR/timings.html"

# ── 2. optional per-line hotspots ────────────────────────────────────────────
if [ "$HOTSPOTS" -eq 1 ]; then
  tb_info "collecting per-line hotspots (this reruns the suite under xtrace)..."
  TRACE_DIR="$OUTDIR/trace"
  rm -rf "$TRACE_DIR"; mkdir -p "$TRACE_DIR"

  # Build the trace-target basename filter.
  TRACE_TARGETS=""
  for tf in $TARGETS; do
    TRACE_TARGETS="$TRACE_TARGETS ${tf##*/}"
  done

  BASH_ENV="$LIB_DIR/trace-init.sh"
  TRBLDOC_TRACE_DIR="$TRACE_DIR"
  TRBLDOC_TRACE_MODE="time"
  TRBLDOC_TRACE_TARGETS="$TRACE_TARGETS"
  if [ "$BATS_MODE" = "local" ]; then
    export BASH_ENV TRBLDOC_TRACE_DIR TRBLDOC_TRACE_MODE TRBLDOC_TRACE_TARGETS
    # shellcheck disable=SC2086
    bats --report-formatter junit --output "$JUNIT_DIR" $SUITE_DIRS \
      > "$OUTDIR/bats-hotspots-output.txt" 2>&1 \
      || tb_info "bats reported failures during hotspot run"
    unset BASH_ENV TRBLDOC_TRACE_DIR TRBLDOC_TRACE_MODE TRBLDOC_TRACE_TARGETS
  else
    WSL_REPO="$(tb_to_wsl_path "$REPO_ROOT")"
    WSL_LIB="$(tb_to_wsl_path "$LIB_DIR")"
    WSL_TRACE="$(tb_to_wsl_path "$TRACE_DIR")"
    WSL_JUNIT="$(tb_to_wsl_path "$JUNIT_DIR")"
    wsl -- bash -lc \
      "cd '$WSL_REPO' && export BASH_ENV='$WSL_LIB/trace-init.sh' TRBLDOC_TRACE_DIR='$WSL_TRACE' TRBLDOC_TRACE_MODE='time' TRBLDOC_TRACE_TARGETS='$TRACE_TARGETS'; bats --report-formatter junit --output '$WSL_JUNIT' $SUITE_DIRS_REL" \
      > "$OUTDIR/bats-hotspots-output.txt" 2>&1 \
      || tb_info "bats (WSL) reported failures during hotspot run"
  fi

  if ls "$TRACE_DIR"/trace.*.log >/dev/null 2>&1; then
    awk -f "$LIB_DIR/trace-extract.awk" -v MODE=time "$TRACE_DIR"/trace.*.log \
      | sort -t "$(printf '\t')" -k1 -rn > "$OUTDIR/hotspots.tsv"
    {
      printf 'total_ms,hits,file,line\n'
      awk -F '\t' '{ printf "%s,%s,%s,%s\n",$1,$2,$3,$4 }' "$OUTDIR/hotspots.tsv"
    } > "$OUTDIR/hotspots.csv"
    # Resolve first target path for source display in the HTML.
    FIRST_TARGET="${TARGETS%% *}"
    case "$FIRST_TARGET" in
      /*) SRC_PATH="$FIRST_TARGET" ;;
      *)  SRC_PATH="$REPO_ROOT/$FIRST_TARGET" ;;
    esac
    awk -f "$LIB_DIR/render-hotspots.awk" \
      -v TITLE="trbldoc line hotspots ($SUITE)" \
      -v SRC="$SRC_PATH" \
      "$OUTDIR/hotspots.tsv" > "$OUTDIR/hotspots.html"
  else
    if grep -qi "bash\\\\r" "$OUTDIR/bats-hotspots-output.txt" 2>/dev/null; then
      tb_die "bats appears broken (CRLF shebang: 'bash\\r') during hotspot run. Reinstall bats or run dos2unix on the bats scripts."
    fi
    tb_info "no trace data captured; skipping hotspots report"
    HOTSPOTS=0
  fi
fi

# ── printed summary ──────────────────────────────────────────────────────────
printf '\n==== slowest %s tests ====\n' "$TOPN"
awk -F '\t' -v n="$TOPN" 'NR<=n { printf "%8.3fs  %s\n", $1, $3 }' \
  "$OUTDIR/timings.sorted.tsv"

printf '\nReports written to: %s\n' "$OUTDIR"
printf '  per-test timing : %s\n' "$OUTDIR/timings.html"
[ "$HOTSPOTS" -eq 1 ] && printf '  line hotspots   : %s\n' "$OUTDIR/hotspots.html"