#!/usr/bin/env python3
import json
import re
import sys
from pathlib import Path


EMAIL_RE = re.compile(r"[\w.+-]+@[\w.-]+\.[A-Za-z]{2,}")
PHONE_RE = re.compile(r"(?<!\d)(?:\+?\d[\d -]{6,}\d)(?!\d)")
PRICE_RE = re.compile(r"(?i)(?:rmb|usd|eur|cny|￥|\$)?\s*\d+(?:\.\d+)?\s*(?:元|块|usd|rmb|eur|cny|/pcs|/pc|/k|pcs)?")


def redact(text: str) -> str:
    text = EMAIL_RE.sub("[email]", text)
    text = PHONE_RE.sub("[number]", text)
    text = PRICE_RE.sub("[number]", text)
    return text


def main() -> int:
    if len(sys.argv) < 3:
        print("usage: extract_email_thread_snippets.py file.jsonl thread_id...", file=sys.stderr)
        return 2
    path = Path(sys.argv[1])
    wanted = set(sys.argv[2:])
    with path.open(encoding="utf-8", errors="replace") as fh:
        for line in fh:
            obj = json.loads(line)
            if obj.get("thread_id") not in wanted:
                continue
            print("=" * 80)
            print("thread_id:", obj.get("thread_id"))
            print("subject:", redact(obj.get("suggested_title_from_subject", "")))
            print("date:", obj.get("date_start"), "->", obj.get("date_end"))
            print("messages:", len(obj.get("messages", [])), "attachments:", len(obj.get("attachments", [])))
            for i, msg in enumerate(obj.get("messages", [])[:8], 1):
                body = redact(msg.get("body_text") or "")
                body = re.sub(r"\n{3,}", "\n\n", body).strip()
                if len(body) > 1400:
                    body = body[:1400] + "\n[...truncated...]"
                print("-" * 40)
                print("message", i, "date", msg.get("date", ""))
                print("subject:", redact(msg.get("subject", "")))
                print(body)
            if len(obj.get("messages", [])) > 8:
                print("[remaining messages omitted]")
    return 0


if __name__ == "__main__":
    raise SystemExit(main())