#!/bin/sh
# scripts/hotspot-tests.sh
# Repeatable hotspot analysis for the trbldoc test suite.
#
# Produces:
#   - per-test timings (parsed from `bats --timing`)
#   - line-level hotspots for target scripts from xtrace logs
#   - optional phase hotspots for trbldoc.sh
#
# Usage:
#   scripts/hotspot-tests.sh [-s all|unit|integration] [-o OUTDIR]
#                            [-n TOPN] [-t "file.sh ..."]
#
#   -s SUITE   suite to run (default: all)
#   -o OUTDIR  output directory (default: reports/hotspots-<timestamp>)
#   -n TOPN    number of slowest tests to print (default: 25)
#   -t LIST    space-separated target scripts for trace hotspots (default: trbldoc.sh)

set -u

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

SUITE=all
OUTDIR=""
TOPN=25
TARGETS="trbldoc.sh"

while getopts ":s:o:n:t:h" opt; do
  case "$opt" in
    s) SUITE="$OPTARG" ;;
    o) OUTDIR="$OPTARG" ;;
    n) TOPN="$OPTARG" ;;
    t) TARGETS="$OPTARG" ;;
    h) sed -n '2,24p' "$SELF"; exit 0 ;;
    :) tb_die "option -$OPTARG requires an argument" ;;
    \?) tb_die "unknown option -$OPTARG" ;;
  esac
done

tb_require awk
tb_require sort

case "$TOPN" in
  ''|*[!0-9]*|0) tb_die "-n TOPN must be a positive integer" ;;
esac

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

SUITE_DIRS="$(tb_suite_dirs "$SUITE")"
SUITE_DIRS_REL="$(tb_suite_dirs_rel "$SUITE")"
TIMING_RAW="$OUTDIR/bats-timing-output.txt"
TRACE_DIR="$OUTDIR/trace"
rm -rf "$TRACE_DIR"; mkdir -p "$TRACE_DIR"

# Build trace target filter and resolve first target source for HTML context.
TRACE_TARGETS=""
FIRST_TARGET=""
for tf in $TARGETS; do
  TRACE_TARGETS="$TRACE_TARGETS ${tf##*/}"
  if [ -z "$FIRST_TARGET" ]; then
    FIRST_TARGET="$tf"
  fi
done

tb_info "running bats ($SUITE) with --timing output..."
if tb_bats_usable "$SUITE"; then
  # shellcheck disable=SC2086
  bats --timing $SUITE_DIRS > "$TIMING_RAW" 2>&1 || tb_info "bats reported failures (timing output still collected)"
  BATS_MODE="local"
elif command -v wsl >/dev/null 2>&1; then
  tb_info "local bats appears unusable; retrying timing run via WSL bats..."
  WSL_REPO="$(tb_to_wsl_path "$REPO_ROOT")"
  wsl -- bash -lc \
    "cd '$WSL_REPO' && bats --timing $SUITE_DIRS_REL" \
    > "$TIMING_RAW" 2>&1 || tb_info "bats (WSL) reported failures (timing output still collected)"
  BATS_MODE="wsl"
else
  tb_die "local bats command appears unusable and no WSL fallback is available"
fi

# Parse bats timing lines: "ok N <name> in <ms>ms"
awk '
match($0, /^ok [0-9]+ (.*) in ([0-9]+)ms$/, m) {
  name = m[1]
  ms = m[2] + 0
  suite = name
  sub(/:.*/, "", suite)
  printf "%.3f\t%s\t%s\t%d\n", ms / 1000.0, suite, name, ms
}
' "$TIMING_RAW" > "$OUTDIR/timings.tsv"

if [ ! -s "$OUTDIR/timings.tsv" ]; then
  tb_die "no per-test timing rows parsed (check $TIMING_RAW)"
fi

sort -t "$(printf '\t')" -k1,1nr "$OUTDIR/timings.tsv" > "$OUTDIR/timings.sorted.tsv"
{
  printf 'seconds,suite,test,milliseconds\n'
  awk -F '\t' '{ gsub(/"/,"\"\"",$3); printf "%s,%s,\"%s\",%s\n",$1,$2,$3,$4 }' "$OUTDIR/timings.sorted.tsv"
} > "$OUTDIR/timings.csv"

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

tb_info "running bats ($SUITE) under xtrace timing hook..."
if [ "$BATS_MODE" = "local" ]; then
  BASH_ENV="$LIB_DIR/trace-init.sh"
  TRBLDOC_TRACE_DIR="$TRACE_DIR"
  TRBLDOC_TRACE_MODE="time"
  TRBLDOC_TRACE_TARGETS="$TRACE_TARGETS"
  export BASH_ENV TRBLDOC_TRACE_DIR TRBLDOC_TRACE_MODE TRBLDOC_TRACE_TARGETS
  # shellcheck disable=SC2086
  bats $SUITE_DIRS > "$OUTDIR/bats-trace-output.txt" 2>&1 || tb_info "bats reported failures during trace 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 -- 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 $SUITE_DIRS_REL" \
    > "$OUTDIR/bats-trace-output.txt" 2>&1 || tb_info "bats (WSL) reported failures during trace 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"

  case "$FIRST_TARGET" in
    /*|[A-Za-z]:[\\/]*) SRC_PATH="$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" > "$OUTDIR/hotspots.html"
else
  tb_info "no trace logs captured for target(s):$TRACE_TARGETS"
fi

# Optional phase hotspots when trbldoc.sh + helper scripts are available.
if [ -f "$OUTDIR/hotspots.tsv" ] && [ -f "$LIB_DIR/trace-phase-extract.awk" ] && [ -f "$LIB_DIR/render-phases.awk" ] && [ -f "$REPO_ROOT/trbldoc.sh" ]; then
  _find_line() {
    awk -v p="$1" 'index($0, p) { print NR; exit }' "$REPO_ROOT/trbldoc.sh"
  }
  L_DISCOVER_END="$(_find_line '> "$source_files_list"')"
  L_EXTRACT_END="$(_find_line '# Resolve src_repo once before the chunk loop.')"
  L_ORDER_END="$(_find_line 'done < "$sorted_chunk_order_file"')"
  L_RENDER_END="$(_find_line 'done < "$chunk_render_records_file"')"
  L_NAV_END="$(_find_line '# Second pass: resolve inline references now that global.meta is complete.')"
  L_REFS_END="$(_find_line 'rm -f "$_ref_find_tmp"')"
  L_TOC_END="$(_find_line '# Post-processing pass: substitute {{ toc }} in all rendered index.html files')"
  L_ASSEMBLE_END="$(_find_line 'assemble_site "$cache_dir/namespace" "$out_dir"')"

  if [ -n "$L_DISCOVER_END" ] && [ -n "$L_EXTRACT_END" ] && [ -n "$L_ORDER_END" ] \
    && [ -n "$L_RENDER_END" ] && [ -n "$L_NAV_END" ] && [ -n "$L_REFS_END" ] \
    && [ -n "$L_TOC_END" ] && [ -n "$L_ASSEMBLE_END" ]; then
    awk -f "$LIB_DIR/trace-phase-extract.awk" \
      -v SRC_BASE="trbldoc.sh" \
      -v L_DISCOVER_END="$L_DISCOVER_END" \
      -v L_EXTRACT_END="$L_EXTRACT_END" \
      -v L_ORDER_END="$L_ORDER_END" \
      -v L_RENDER_END="$L_RENDER_END" \
      -v L_NAV_END="$L_NAV_END" \
      -v L_REFS_END="$L_REFS_END" \
      -v L_TOC_END="$L_TOC_END" \
      -v L_ASSEMBLE_END="$L_ASSEMBLE_END" \
      "$TRACE_DIR"/trace.*.log \
      | sort -t "$(printf '\t')" -k1 -rn > "$OUTDIR/phase-hotspots.tsv"

    {
      printf 'total_ms,hits,phase\n'
      awk -F '\t' '{ printf "%s,%s,%s\n",$1,$2,$3 }' "$OUTDIR/phase-hotspots.tsv"
    } > "$OUTDIR/phase-hotspots.csv"

    awk -f "$LIB_DIR/render-phases.awk" \
      -v TITLE="trbldoc phase hotspots ($SUITE)" \
      "$OUTDIR/phase-hotspots.tsv" > "$OUTDIR/phase-hotspots.html"
  fi
fi

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"
if [ -f "$OUTDIR/hotspots.html" ]; then
  printf '  line hotspots   : %s\n' "$OUTDIR/hotspots.html"
else
  printf '  line hotspots   : not generated (target not exercised)\n'
fi
if [ -f "$OUTDIR/phase-hotspots.html" ]; then
  printf '  phase hotspots  : %s\n' "$OUTDIR/phase-hotspots.html"
fi