Create search.py

src/api/search.py

@@ -0,0 +1,156 @@
+from fastapi import APIRouter, HTTPException
+from pydantic import BaseModel
+from typing import Optional
+import httpx
+import os
+
+router = APIRouter()
+
+class SearchRequest(BaseModel):
+    query: str
+    source: str = "primo"
+    limit: int = 5
+    peer_reviewed: bool = False
+    open_access: bool = False
+    year_from: Optional[str] = None
+    year_to: Optional[str] = None
+
+@router.post("")
+async def search_endpoint(req: SearchRequest):
+    settings = get_settings()
+    
+    if req.source == "primo":
+        return await search_primo(req, settings.primo_api_key)
+    elif req.source == "pubmed":
+        return await search_pubmed(req)
+    elif req.source == "scholar":
+        return await search_scholar(req)
+    else:
+        raise HTTPException(status_code=400, detail=f"Unknown source: {req.source}")
+
+async def search_primo(req: SearchRequest, api_key: str):
+    if not api_key:
+        return {"error": "PRIMO_API_KEY not configured", "results": []}
+    
+    # Simple query for now
+    from urllib.parse import quote
+    query = quote(req.query)
+    
+    url = f"https://api-eu.hosted.exlibrisgroup.com/primo/v1/search?vid=971KUOSTAR_INST:KU&tab=Everything&scope=MyInst_and_CI&q=any,contains,{query}&lang=en&sort=rank&limit={req.limit}&offset=0&mode=advanced&apikey={api_key}"
+    
+    try:
+        async with httpx.AsyncClient(timeout=15) as client:
+            r = await client.get(url, headers={"Accept": "application/json"})
+            if r.status_code != 200:
+                return {"error": f"PRIMO API error: {r.status_code}", "results": []}
+            
+            data = r.json()
+            results = []
+            for doc in data.get("docs", [])[:req.limit]:
+                pnx = doc.get("pnx", {})
+                d = pnx.get("display", {})
+                a = pnx.get("addata", {})
+                
+                results.append({
+                    "title": (d.get("title") or ["Untitled"])[0],
+                    "creator": "; ".join(d.get("creator") or d.get("contributor") or []) or "Unknown",
+                    "date": (d.get("date") or [""])[0],
+                    "type": (d.get("type") or [""])[0],
+                    "source": (d.get("source") or [""])[0],
+                    "primo_url": f"https://khalifa.primo.exlibrisgroup.com/discovery/search?query=any,contains,{query}&vid=971KUOSTAR_INST:KU",
+                    "_source": "PRIMO"
+                })
+            
+            return {"total": data.get("info", {}).get("total", 0), "results": results, "source": "PRIMO"}
+    
+    except Exception as e:
+        return {"error": str(e), "results": []}
+
+async def search_pubmed(req: SearchRequest):
+    try:
+        async with httpx.AsyncClient(timeout=15) as client:
+            # Search
+            search_url = f"https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term={req.query}&retmax={req.limit}&retmode=json"
+            r = await client.get(search_url)
+            if r.status_code != 200:
+                return {"error": "PubMed search failed", "results": []}
+            
+            ids = r.json().get("esearchresult", {}).get("idlist", [])
+            if not ids:
+                return {"total": 0, "results": [], "source": "PubMed"}
+            
+            # Fetch details
+            fetch_url = f"https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi?db=pubmed&id={','.join(ids)}&retmode=json"
+            r2 = await client.get(fetch_url)
+            if r2.status_code != 200:
+                return {"error": "PubMed fetch failed", "results": []}
+            
+            data = r2.json().get("result", {})
+            results = []
+            for pid in ids:
+                rec = data.get(pid, {})
+                if not isinstance(rec, dict):
+                    continue
+                authors = ", ".join(a.get("name", "") for a in rec.get("authors", [])[:3])
+                if len(rec.get("authors", [])) > 3:
+                    authors += " et al."
+                
+                results.append({
+                    "title": rec.get("title", ""),
+                    "creator": authors,
+                    "date": rec.get("pubdate", ""),
+                    "source": rec.get("fulljournalname", rec.get("source", "")),
+                    "pmid": pid,
+                    "link": f"https://pubmed.ncbi.nlm.nih.gov/{pid}/",
+                    "type": "Journal Article",
+                    "_source": "PubMed"
+                })
+            
+            return {"total": len(ids), "results": results, "source": "PubMed"}
+    
+    except Exception as e:
+        return {"error": str(e), "results": []}
+
+async def search_scholar(req: SearchRequest):
+    # Semantic Scholar implementation
+    try:
+        url = "https://api.semanticscholar.org/graph/v1/paper/search"
+        params = {
+            "query": req.query,
+            "limit": req.limit,
+            "fields": "title,authors,year,venue,externalIds,citationCount"
+        }
+        
+        async with httpx.AsyncClient(timeout=15) as client:
+            r = await client.get(url, params=params)
+            if r.status_code != 200:
+                return {"error": f"Semantic Scholar API: {r.status_code}", "results": []}
+            
+            data = r.json()
+            results = []
+            for paper in data.get("data", []):
+                authors = ", ".join(a.get("name", "") for a in (paper.get("authors") or [])[:3])
+                if len(paper.get("authors") or []) > 3:
+                    authors += " et al."
+                
+                ext_ids = paper.get("externalIds") or {}
+                
+                results.append({
+                    "title": paper.get("title", ""),
+                    "creator": authors,
+                    "date": str(paper.get("year", "")),
+                    "source": paper.get("venue", ""),
+                    "citations": paper.get("citationCount", 0),
+                    "link": f"https://www.semanticscholar.org/paper/{paper.get('paperId')}" if paper.get("paperId") else None,
+                    "type": "Article",
+                    "_source": "Semantic Scholar"
+                })
+            
+            return {"total": data.get("total", 0), "results": results, "source": "Semantic Scholar"}
+    
+    except Exception as e:
+        return {"error": str(e), "results": []}
+
+def get_settings():
+    from src.config import get_settings as gs
+    return gs()