# -*- coding: utf-8 -*-
"""WB feedback summary v1. Python 3, standard library, local files only.

Usage: python3 summarize.py input.csv
Columns: id,label,text. Labels must already be assigned; this does NOT classify text.
Outputs JSON to stdout; invalid input produces stderr and exit status 2.
"""
import csv
import io
import json
import re
import sys
from pathlib import Path

LABELS = ("物流", "商品", "其他", "待确认")
MAX_ROWS = 5000


def summarize(data):
    text = data.decode("utf-8-sig")
    reader = csv.reader(io.StringIO(text, newline=""), strict=True)
    if next(reader, None) != ["id", "label", "text"]:
        raise ValueError("expected header: id,label,text")
    seen = set()
    counts = dict.fromkeys(LABELS, 0)
    for row in reader:
        if len(row) != 3:
            raise ValueError("expected exactly three columns at line %s" % reader.line_num)
        record_id, label, _ = row
        if not re.fullmatch(r"[A-Za-z0-9_-]{1,40}", record_id):
            raise ValueError("invalid id at line %s" % reader.line_num)
        if record_id in seen:
            raise ValueError("duplicate id: %s" % record_id)
        if label not in counts:
            raise ValueError("unknown label at line %s" % reader.line_num)
        seen.add(record_id)
        if len(seen) > MAX_ROWS:
            raise ValueError("at most 5000 records supported")
        counts[label] += 1
    if not seen:
        raise ValueError("at least one record required")
    return {"version": "WB-summary-v1", "total": len(seen), "counts": counts}


def main():
    if len(sys.argv) != 2:
        print("usage: python3 summarize.py input.csv", file=sys.stderr)
        return 2
    try:
        result = summarize(Path(sys.argv[1]).read_bytes())
    except (ValueError, UnicodeError, csv.Error, OSError) as exc:
        print("input rejected: %s" % exc, file=sys.stderr)
        return 2
    print(json.dumps(result, ensure_ascii=False, indent=2))
    return 0


if __name__ == "__main__":
    sys.exit(main())