backend/tools/metadata.py

import asyncio
from typing import Optional
from backend.providers.base import fetch_json, normalize_result

async def fetch_metadata(doi: str = None, url: str = None, title: str = None) -> dict:
    """Fetch metadata for a single paper."""
    if doi:
        # Try OpenAlex by DOI
        data = await fetch_json(f"https://api.openalex.org/works/https://doi.org/{doi}")
        if "error" not in data:
            return normalize_result(
                title=data.get("title"),
                authors=[a.get("author", {}).get("display_name", "") for a in data.get("authorships", [])],
                year=data.get("publication_year"),
                abstract=None,  # Need to decode inverted index
                doi=doi,
                pdf_url=data.get("open_access", {}).get("oa_url"),
                source="openalex",
                university=data.get("authorships", [{}])[0].get("institutions", [{}])[0].get("display_name") if data.get("authorships") else None,
                citation_count=data.get("cited_by_count"),
            )
    if title:
        data = await fetch_json("https://api.openalex.org/works", params={"search": title, "per-page": 1})
        if "error" not in data and data.get("results"):
            work = data["results"][0]
            return normalize_result(
                title=work.get("title"),
                authors=[a.get("author", {}).get("display_name", "") for a in work.get("authorships", [])],
                year=work.get("publication_year"),
                abstract=None,
                doi=work.get("ids", {}).get("doi", "").replace("https://doi.org/", ""),
                pdf_url=work.get("open_access", {}).get("oa_url"),
                source="openalex",
            )
    return {"error": "No metadata found"}

async def recover_metadata(doi: str = None, url: str = None, title: str = None) -> dict:
    """Deep metadata recovery from multiple sources."""
    result = {}
    sources_tried = []
    
    # Try OpenAlex
    if doi:
        sources_tried.append("OpenAlex")
        data = await fetch_json(f"https://api.openalex.org/works/https://doi.org/{doi}")
        if "error" not in data:
            result["title"] = data.get("title")
            result["year"] = data.get("publication_year")
            result["doi"] = doi
            result["authors"] = [a.get("author", {}).get("display_name", "") for a in data.get("authorships", [])]
    
    # Try Crossref for abstract
    if doi and not result.get("abstract"):
        sources_tried.append("Crossref")
        data = await fetch_json(f"https://api.crossref.org/works/{doi}")
        if "error" not in data:
            item = data.get("message", {})
            if item.get("abstract"):
                result["abstract"] = item["abstract"][:500]
    
    # Try Semantic Scholar for PDF
    if doi and not result.get("pdfUrl"):
        sources_tried.append("Semantic Scholar")
        data = await fetch_json(f"https://api.semanticscholar.org/graph/v1/paper/DOI:{doi}?fields=openAccessPdf")
        if "error" not in data:
            result["pdfUrl"] = data.get("openAccessPdf", {}).get("url")
    
    result["sourcesTried"] = sources_tried
    return result