"""Generate a CSV report matching merged images to source stamp images.

This script is intentionally standalone and does not import cmbot project code.
Edit the three paths below, then run:

    python match_stamp.py

It does not copy, move, rename, or delete any image files.
"""
from __future__ import print_function

import csv
from datetime import datetime
from pathlib import Path


OUTPUT_DIR = r"D:\chengma\cmbot\output\20260623_094529"
STAMP_DIR = r"D:\chengma\印花和底图\已处理印花\卡通71（66大码200斤 KEKE已上）\横1"
REPORT_PATH = r"D:\chengma\cmbot\match_stamp_report.csv"

IMAGE_EXTENSIONS = {".png", ".jpg", ".jpeg", ".webp"}
FIELDNAMES = [
    "status",
    "code",
    "merged_image",
    "stamp_image",
    "merged_folder",
    "message",
]


def is_image(path):
    return path.is_file() and path.suffix.lower() in IMAGE_EXTENSIONS


def extract_code_from_merged_name(path):
    """Extract stamp code from the final underscore suffix.

    Example: 1_TY037.png -> TY037.
    """
    stem = path.stem
    if "_" not in stem:
        return ""
    code = stem.rsplit("_", 1)[1].strip()
    return code


def iter_images(root):
    root = Path(root)
    if not root.exists():
        return
    for path in sorted(root.rglob("*")):
        if is_image(path):
            yield path


def build_stamp_index(stamp_dir):
    index = {}
    for path in iter_images(stamp_dir):
        code = path.stem.strip()
        if not code:
            continue
        index.setdefault(code, []).append(path.resolve())
    return index


def match_merged_image(path, stamp_index):
    code = extract_code_from_merged_name(path)
    if not code:
        return {
            "status": "bad_name",
            "code": "",
            "merged_image": str(path.resolve()),
            "stamp_image": "",
            "merged_folder": str(path.parent.resolve()),
            "message": "File name has no underscore suffix code",
        }

    candidates = stamp_index.get(code, [])
    if not candidates:
        return {
            "status": "missing",
            "code": code,
            "merged_image": str(path.resolve()),
            "stamp_image": "",
            "merged_folder": str(path.parent.resolve()),
            "message": "No stamp image found for code",
        }

    stamp_paths = " | ".join(str(p) for p in candidates)
    if len(candidates) > 1:
        return {
            "status": "duplicate",
            "code": code,
            "merged_image": str(path.resolve()),
            "stamp_image": stamp_paths,
            "merged_folder": str(path.parent.resolve()),
            "message": "Multiple stamp images found for code",
        }

    return {
        "status": "matched",
        "code": code,
        "merged_image": str(path.resolve()),
        "stamp_image": stamp_paths,
        "merged_folder": str(path.parent.resolve()),
        "message": "",
    }


def write_csv(rows, report_path):
    report_path = Path(report_path)
    report_path.parent.mkdir(parents=True, exist_ok=True)
    with report_path.open("w", encoding="utf-8-sig", newline="") as f:
        writer = csv.DictWriter(f, fieldnames=FIELDNAMES)
        writer.writeheader()
        for row in rows:
            writer.writerow(row)


def generate_report(output_dir, stamp_dir, report_path):
    output_dir = Path(output_dir)
    stamp_dir = Path(stamp_dir)

    stamp_index = build_stamp_index(stamp_dir)
    rows = []
    for path in iter_images(output_dir):
        rows.append(match_merged_image(path, stamp_index))

    write_csv(rows, report_path)
    return rows


def summarize(rows):
    counts = {}
    for row in rows:
        status = row.get("status", "")
        counts[status] = counts.get(status, 0) + 1
    return counts


def main():
    started = datetime.now()
    rows = generate_report(OUTPUT_DIR, STAMP_DIR, REPORT_PATH)
    counts = summarize(rows)
    print("Generated report: {}".format(Path(REPORT_PATH).resolve()))
    print("Merged images: {}".format(len(rows)))
    print("Matched: {}".format(counts.get("matched", 0)))
    print("Missing: {}".format(counts.get("missing", 0)))
    print("Duplicate: {}".format(counts.get("duplicate", 0)))
    print("Bad name: {}".format(counts.get("bad_name", 0)))
    print("Elapsed: {}".format(datetime.now() - started))


if __name__ == "__main__":
    main()