#!/usr/bin/env bash
# Convert the reference papers to Markdown with the local doc2md tool
#
# Two things had to line up to make this work:
#
#   1. Call it from bash, not PowerShell. PowerShell prepends a BOM when piping
#      to a native process, has no `<` redirection, and PS 5.1 lacks
#      StandardInputEncoding to turn the BOM off. (main.py now reads
#      utf-8-sig, so the BOM is tolerated - but bash avoids the issue entirely.)
#
#   2. The tool's venv had a CPU-only torch (2.12.0+cpu). marker-pdf picks its
#      device from torch.cuda.is_available(), so it silently ran on CPU and
#      stalled. Replaced with 2.5.1+cu121; no code change was needed.
#
# Runs one paper at a time - they share a single GPU.
set -uo pipefail

TOOL="/d/Teknom/jjangoo/tools/doc.convert.doc2md"
PAPERS="/d/MYCLAUDE_PROJECT/sum-parts-test/docs/papers"
OUT="$PAPERS/md"
WIN_PAPERS="D:/MYCLAUDE_PROJECT/sum-parts-test/docs/papers"
WIN_OUT="D:/MYCLAUDE_PROJECT/sum-parts-test/docs/papers/md"

mkdir -p "$OUT"
cd "$TOOL" || exit 1

for pdf in "$PAPERS"/*.pdf; do
    name=$(basename "$pdf" .pdf)

    if [ -f "$OUT/$name.md" ]; then
        echo "=== $name  (이미 변환됨, 건너뜀) ==="
        continue
    fi

    echo "=== $name ==="
    printf '%s' "{\"file\":\"$WIN_PAPERS/$name.pdf\",\"outputDir\":\"$WIN_OUT\"}" > /tmp/doc2md_req.json

    start=$(date +%s)
    TORCH_DEVICE=cuda ./.venv/Scripts/python.exe main.py < /tmp/doc2md_req.json \
        > "/tmp/doc2md_$name.out" 2>"/tmp/doc2md_$name.err"
    rc=$?
    elapsed=$(( $(date +%s) - start ))

    if [ $rc -ne 0 ]; then
        echo "  FAILED rc=$rc (${elapsed}s)"
        tail -5 "/tmp/doc2md_$name.err"
        continue
    fi

    # the result line is JSON on stdout
    python3 - "/tmp/doc2md_$name.out" "$elapsed" <<'PY'
import json, sys
from pathlib import Path

txt = Path(sys.argv[1]).read_text(encoding="utf-8", errors="replace")
elapsed = sys.argv[2]
for line in txt.splitlines():
    line = line.strip()
    if not line.startswith("{"):
        continue
    try:
        d = json.loads(line)
    except Exception:
        continue
    if d.get("type") == "result":
        o = d["output"]
        md = Path(o["file"])
        size = md.stat().st_size / 1024 if md.exists() else 0
        print(f"  ok  {elapsed}s  {size:,.0f} KB  "
              f"images={len(o.get('images') or [])}  "
              f"pages={len(o.get('pages') or [])}  "
              f"diagrams={o.get('hasDiagrams')}")
    elif d.get("type") == "error":
        print(f"  ERROR {d.get('code')}: {d.get('message')}")
PY
done

echo
echo "=== 결과 ==="
for md in "$OUT"/*.md; do
    [ -f "$md" ] || continue
    n=$(basename "$md")
    kb=$(( $(stat -c%s "$md") / 1024 ))
    heads=$(grep -cE '^#{1,3} ' "$md")
    rows=$(grep -c '^|' "$md")
    echo "  $(printf '%-34s' "$n") ${kb}KB  헤딩 ${heads}  표행 ${rows}"
done