#!/usr/bin/env python3
"""§F: кросс-пары. F1 — zh→en терминолог-проход по голд-ростеру (близость стратегий к ru-банку
владельца). F2 — en→zh на Empire of the Dawn (Кристофф): майнинг термов + терминолог-проход + перевод
двух окон (deepseek-low и glm-5). Сырьё → ~/books/gu-zhenren/bank-arbitration/ (общий durable пака).
"""
from __future__ import annotations
import argparse
import collections
import json
import os
import re
import time
import zipfile
from pathlib import Path

from dotenv import load_dotenv
from openai import OpenAI

REPO = Path("/home/ubuntu/projects/textmachine")
HERE = Path(__file__).resolve().parent
RAW = Path.home() / "books" / "gu-zhenren" / "bank-arbitration"
KRISTOFF = Path.home() / "books" / "Kristoff_Jay_-_Empire_of_the_Vampire_3_-_Empire_of_the_Dawn.epub"
load_dotenv(REPO / "eval" / ".env")

import sys  # noqa: E402
sys.path.insert(0, str(HERE))
import consilium_probe as cp  # noqa: E402  (ростер, батчер, call, цены, клиенты)

TERM_EN_SYS = """You are the terminologist of a publishing-grade translation from Chinese into English.
Book: «蛊真人» (a cultivation webnovel). You are given the book's term list; for each term — contexts
from the SOURCE and renderings the draft translators already proposed (in Russian — a parallel edition;
treat them as evidence of meaning, not as English candidates). You see the whole book at once; pick ONE
English rendering per term, consistent across the whole book. Transcribe personal and place names in
pinyin; translate titles, ranks and realia by MEANING. Keep families of related terms sharing a source
morpheme consistent in English. Dictionary form, no explanations.
Answer format: one line per term, exactly two fields separated by a TAB: source term, English rendering."""

TERM_ZH_SYS = """你是一部出版级奇幻小说英译中项目的术语专家。小说:《Empire of the Dawn》(Jay Kristoff,
吸血鬼史诗奇幻)。给你这本书的术语表:每个术语附有原文语境。你能看到整本书,请为每个术语选定ONE个
统一的中文译名,全书一致。人名用约定俗成的音译;头衔、组织、事物按意义翻译,要求文学性、符合奇幻
小说的中文语感。同源术语的译名要保持词根呼应。只给词典形式,不要解释。
回答格式:每行一个术语,两个字段,用制表符分隔:原文术语、中文译名。"""

TRANSLATE_ZH_SYS = """你是一位专业文学翻译家,把英文小说译成中文。这是 Jay Kristoff 的吸血鬼史诗奇幻
《Empire of the Dawn》。要求:逐句翻译,不删不增;中文要有文学性,句式自然,避免翻译腔;对话用中文
小说的标点习惯。人名音译。只输出译文,不要任何前言、注释或 markdown。"""


def epub_text() -> str:
    out = []
    with zipfile.ZipFile(KRISTOFF) as z:
        for n in sorted(z.namelist()):
            if n.endswith((".xhtml", ".html")):
                html = z.read(n).decode("utf-8", "ignore")
                txt = re.sub(r"<[^>]+>", " ", html)
                txt = re.sub(r"&[a-z]+;", " ", txt)
                out.append(re.sub(r"\s+", " ", txt))
    return "\n".join(out)


def mine_en_terms(text: str, top=14):
    """Рекуррентные капитализированные термы: имена + двусловные (The X / X Y)."""
    stop = {"The", "But", "And", "She", "His", "Her", "They", "That", "This", "What", "When", "With",
            "For", "Not", "You", "All", "Was", "Had", "Chapter", "Then", "Now", "There", "One", "It's",
            "Book", "Part", "From", "Like", "Still", "Yet", "So", "In", "On", "At", "He", "We", "If",
            "God", "Oui", "Non", "Mademoiselle", "Monsieur"}
    words = collections.Counter(re.findall(r"\b[A-Z][a-zà-ÿé]+(?:\s[A-Z][a-zà-ÿé]+)?\b", text))
    cand = [(w, n) for w, n in words.most_common(400)
            if n >= 15 and w.split()[0] not in stop and len(w) > 3]
    # предпочесть двусловные и явные имена/реалии
    seen, out = set(), []
    for w, n in cand:
        head = w.split()[0]
        if head in seen:
            continue
        seen.add(head)
        out.append((w, n))
        if len(out) == top:
            break
    return out


def kwic(text, term, per=3, width=60):
    out, frm = [], 0
    while len(out) < per:
        i = text.find(term, frm)
        if i < 0:
            break
        out.append(text[max(0, i - width):i + len(term) + width])
        frm = i + len(term)
    return out


def run_f1(models=("deepseek-v4-flash",)):
    roster = cp.build_roster()
    batches = cp.batches_of(roster)
    total = 0.0
    for model in models:
        cl = cp.client_for(model)
        short = {"deepseek-v4-flash": "ds", "glm-5": "glm"}[model]
        for i, b in enumerate(batches):
            user = "Термины книги:\n\n" + "\n\n".join(cp.block_of(c) for c in b)
            rec = cp.call(cl, model, TERM_EN_SYS, user, f"xen-{short}-b{i}",
                          "low" if model.startswith("deepseek") else None, model == "glm-5")
            total += rec["cost_usd"]
            time.sleep(1)
    return total


# F2-ростер: майнер дал имена; реалии добраны РУКАМИ по частотам (раскрыто в отчёте). Семья
# *-blood (coldblood/highblood/paleblood) — намеренный тест корневой связности в zh.
TERMS_F2 = ["Dior", "Gabriel", "Phoebe", "Celene", "Voss", "silversaint", "coldblood", "highblood",
            "paleblood", "Forever King", "Grail", "San Michon", "aegis", "duskdancer", "famille"]


def run_f2():
    text = epub_text()
    print(f"epub text: {len(text)} chars")
    terms = [(t, text.count(t)) for t in TERMS_F2]
    print("terms:", terms)
    blocks = []
    for t, n in terms:
        blocks.append(f"### {t}\nfreq: {n}\n" + "\n".join(f"ctx: {c}" for c in kwic(text, t)))
    user = "Terms:\n\n" + "\n\n".join(blocks)
    total = 0.0
    for model, short in [("deepseek-v4-flash", "ds"), ("glm-5", "glm")]:
        cl = cp.client_for(model)
        rec = cp.call(cl, model, TERM_ZH_SYS, user, f"xzh-term-{short}",
                      "low" if model.startswith("deepseek") else None, model == "glm-5")
        total += rec["cost_usd"]
        time.sleep(1)
    # два окна прозы (~900 симв.), разнесённые
    paras = [p for p in text.split("\n") if len(p) > 400]
    wins = [paras[3][:1200], paras[len(paras) // 2][:1200]]
    for k, w in enumerate(wins):
        for model, short in [("deepseek-v4-flash", "ds"), ("glm-5", "glm")]:
            cl = cp.client_for(model)
            rec = cp.call(cl, model, TRANSLATE_ZH_SYS, "翻译下面的段落:\n\n" + w, f"xzh-prose-w{k}-{short}",
                          "low" if model.startswith("deepseek") else None, model == "glm-5")
            total += rec["cost_usd"]
            time.sleep(1)
    return total


def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("--part", default="all", choices=["f1", "f2", "all", "mine"])
    a = ap.parse_args()
    if a.part == "mine":
        print(mine_en_terms(epub_text()))
        return
    total = 0.0
    if a.part in ("f1", "all"):
        total += run_f1()
    if a.part in ("f2", "all"):
        total += run_f2()
    print(f"TOTAL crosslang: ${total:.6f}")


if __name__ == "__main__":
    main()


def score_f1():
    """Джойн en-консолидаций с голдом: печать пар (src, ru владельца, en свежий) для таблицы §F."""
    import glob
    en = {}
    for f in sorted(glob.glob(str(RAW / "xen-ds-b*.json"))):
        for ln in json.load(open(f, encoding="utf-8"))["content"].split("\n"):
            if "\t" in ln:
                s, d = ln.split("\t", 1)
                en[s.strip()] = d.strip()
    gold = [json.loads(l) for l in open(HERE / "gold" / "gold.jsonl", encoding="utf-8")]
    n = 0
    for r in gold:
        if not r.get("in_bank"):
            continue
        s = r["bank_src"]
        if s in en:
            n += 1
            print(f"{s}\t{r['gold_dst']}\t{en[s]}")
    print(f"# joined: {n}")