"""三层去重主流程。

调用顺序: check / ingest 内部按 L1 → L2 → L3 顺序判定，任意层命中即返回。

Deduper 不要求线程安全；批处理串行调用即可。
"""

import logging
from datetime import datetime
from pathlib import Path

import yaml

from dedup.hasher import DEFAULT_HAMMING_THRESHOLD, content_hash, hamming, simhash64
from dedup.models import DedupLayer, DedupResult, DedupStats, Fingerprint
from dedup.store import DEFAULT_DB_PATH, FingerprintStore
from extractor.models import ProcessedArticle

logger = logging.getLogger(__name__)

# 默认时间窗口（±N 天）
DEFAULT_TIME_WINDOW_DAYS = 30


def _load_dedup_config() -> dict:
    """从 system.yaml 加载去重配置。"""
    config_path = Path("configs/system.yaml")
    if config_path.exists():
        try:
            with open(config_path, encoding="utf-8") as f:
                raw = yaml.safe_load(f)
            return raw.get("dedup", {})
        except Exception:
            logger.warning("加载 dedup 配置失败，使用默认值")
    return {}


def _publish_date(article: ProcessedArticle) -> str | None:
    """从 ProcessedArticle.publish_time 取 YYYY-MM-DD 字符串。"""
    if not article.publish_time:
        return None
    # publish_time 格式为 ISO 8601，如 "2026-06-21T10:30:00"
    try:
        return article.publish_time[:10]
    except (IndexError, TypeError):
        return None


def article_to_fingerprint(article: ProcessedArticle) -> Fingerprint:
    """构造 Fingerprint（用于 ingest 写入或对外只读）。"""
    return Fingerprint(
        url_hash=article.url_hash,
        content_hash=content_hash(article.content),
        simhash=simhash64(article.content),
        source_id=article.source_id,
        url=article.url,
        title=article.title,
        publish_date=_publish_date(article),
        ingested_at=datetime.now(),
    )


class Deduper:
    """三层去重器。

    构造完毕后:
        - check(article)  仅判断，不写入
        - ingest(article) 判断，不重复则写入指纹库，返回结果
    """

    def __init__(
        self,
        db_path: str | Path = DEFAULT_DB_PATH,
        simhash_threshold: int | None = None,
        time_window_days: int | None = None,
    ) -> None:
        config = _load_dedup_config()

        self.store = FingerprintStore(db_path)
        self.simhash_threshold = (
            simhash_threshold
            if simhash_threshold is not None
            else config.get("hamming_distance_threshold", DEFAULT_HAMMING_THRESHOLD)
        )
        self.time_window_days = (
            time_window_days
            if time_window_days is not None
            else config.get("simhash_window_days", DEFAULT_TIME_WINDOW_DAYS)
        )

    def close(self) -> None:
        self.store.close()

    def __enter__(self) -> "Deduper":
        return self

    def __exit__(self, *_: object) -> None:
        self.close()

    # ------------------------------------------------------------------ #
    # 公共 API
    # ------------------------------------------------------------------ #

    def check(self, article: ProcessedArticle) -> DedupResult:
        """三层判重（只读，不写入指纹库）。"""
        fp = article_to_fingerprint(article)

        # L1: URL hash
        existing = self.store.get_by_url_hash(fp.url_hash)
        if existing is not None:
            return DedupResult(
                url_hash=fp.url_hash,
                is_duplicate=True,
                matched_layer=DedupLayer.URL,
                matched_url_hash=existing.url_hash,
                matched_url=existing.url,
                matched_title=existing.title,
            )

        # L2: 内容 hash
        existing = self.store.find_by_content_hash(fp.content_hash)
        if existing is not None:
            return DedupResult(
                url_hash=fp.url_hash,
                is_duplicate=True,
                matched_layer=DedupLayer.CONTENT,
                matched_url_hash=existing.url_hash,
                matched_url=existing.url,
                matched_title=existing.title,
            )

        # L3: SimHash 模糊
        candidates = self.store.candidates_for_simhash(
            fp.publish_date, self.time_window_days
        )
        best_dist: int | None = None
        best_match: Fingerprint | None = None
        for c in candidates:
            d = hamming(fp.simhash, c.simhash)
            if d <= self.simhash_threshold and (best_dist is None or d < best_dist):
                best_dist = d
                best_match = c
                if d == 0:  # 不可能更近，提前结束
                    break

        if best_match is not None:
            return DedupResult(
                url_hash=fp.url_hash,
                is_duplicate=True,
                matched_layer=DedupLayer.SIMHASH,
                matched_url_hash=best_match.url_hash,
                matched_url=best_match.url,
                matched_title=best_match.title,
                hamming_distance=best_dist,
            )

        return DedupResult(url_hash=fp.url_hash, is_duplicate=False)

    def ingest(self, article: ProcessedArticle) -> DedupResult:
        """判重 + 不重复则入库。"""
        result = self.check(article)
        if not result.is_duplicate:
            fp = article_to_fingerprint(article)
            self.store.upsert(fp)
            logger.debug("指纹入库: %s %s", fp.url_hash, fp.title[:40])
        else:
            logger.debug("命中重复: %s", result.short_summary())
        return result

    def stats(self) -> DedupStats:
        """指纹库统计信息。"""
        lo, hi = self.store.date_range()
        return DedupStats(
            total=self.store.count(),
            by_source=self.store.count_by_source(),
            earliest=lo,
            latest=hi,
        )