from __future__ import annotations

import hashlib
from typing import Iterable

from app.services.ai_tools.schemas import FetchedEvidence, SearchEvidence


def evidence_content_hash(text: str) -> str:
    return hashlib.sha256(text.encode("utf-8")).hexdigest()


def normalize_search_evidence(items: Iterable[SearchEvidence], *, limit: int = 5) -> list[dict]:
    normalized: list[dict] = []
    seen_urls: set[str] = set()
    for item in items:
        if not item.url or item.url in seen_urls:
            continue
        seen_urls.add(item.url)
        normalized.append(
            {
                "title": item.title,
                "url": item.url,
                "snippet": item.snippet,
                "content": item.compact_text(),
                "score": item.score,
                "source_provider": item.source_provider,
                "retrieved_at": item.retrieved_at.isoformat(),
                "metadata": item.metadata,
            }
        )
        if len(normalized) >= limit:
            break
    return normalized


def normalize_fetched_evidence(item: FetchedEvidence, *, text_limit: int = 1200) -> dict:
    text = " ".join(item.text.split())[:text_limit]
    return {
        "title": item.title,
        "url": item.final_url or item.url,
        "text": text,
        "content_hash": item.content_hash or evidence_content_hash(item.text),
        "extractor": item.extractor,
        "retrieved_at": item.retrieved_at.isoformat(),
        "metadata": item.metadata,
    }