feat: initial commit - oncology literature search platform

OncoLit: a multi-tenant oncology literature search, feed, and
collaboration platform. Built with FastAPI + Vue 3 + PostgreSQL.
Includes PubMed pipeline, drug approvals, AI summaries, and
systematic review tools.

tmp_run_citation_refresh.py

@@ -0,0 +1,106 @@
+"""
+Full citation refresh - standalone script using direct SQL.
+No app imports needed.
+"""
+import asyncio, sys
+from datetime import datetime, timezone
+from sqlalchemy import text
+from sqlalchemy.ext.asyncio import create_async_engine
+
+DB = 'postgresql+asyncpg://scilit:scilit_prod_2026@postgres:5432/scilit'
+LOG = '/tmp/citation_refresh2.log'
+
+ELINK_URL = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/elink.fcgi"
+BATCH = 200  # NCBI max per request
+RATE = 3.0   # req/s
+INTERVAL = 1.0 / RATE
+
+def log(msg):
+    ts = datetime.now(timezone.utc).isoformat()
+    line = f'[{ts}] {msg}\n'
+    print(line, end='', flush=True)
+    with open(LOG, 'a') as f:
+        f.write(line)
+
+async def fetch_citedby(pmids):
+    """Fetch citation counts for a batch of PMIDs via NCBI elink."""
+    import httpx
+    import xml.etree.ElementTree as ET
+
+    pmid_str = ','.join(str(p) for p in pmids)
+    url = f"{ELINK_URL}?dbfrom=pubmed&linkname=pubmed_pubmed_citedin&id={pmid_str}&retmode=xml"
+
+    async with httpx.AsyncClient(timeout=30.0) as client:
+        resp = await client.get(url)
+        resp.raise_for_status()
+
+    root = ET.fromstring(resp.content)
+    result = {}
+    for linkset in root.findall(".//LinkSet"):
+        src_id_elem = linkset.find("IdList/Id")
+        if src_id_elem is None or not src_id_elem.text:
+            continue
+        src_pmid = int(src_id_elem.text.strip())
+        count = 0
+        for lsdb in linkset.findall(".//LinkSetDb"):
+            ln = lsdb.findtext("LinkName", "")
+            if ln == "pubmed_pubmed_citedin":
+                count = len([e for e in lsdb.findall(".//Link/Id") if e.text])
+                break
+        result[src_pmid] = max(result.get(src_pmid, 0), count)
+
+    return result
+
+async def main():
+    log('Starting citation refresh (standalone)...')
+    engine = create_async_engine(DB, pool_size=4)
+
+    # Get all PMIDs
+    async with engine.connect() as c:
+        rows = (await c.execute(text("SELECT pmid FROM global_literature WHERE pmid IS NOT NULL ORDER BY created_at DESC"))).all()
+    targets = [r[0] for r in rows]
+    total = len(targets)
+    log(f'Found {total} PMIDs')
+
+    total_updated = 0
+    total_errors = 0
+
+    # Process ALL PMIDs via elink (the function handles its own batching)
+    # We do it in chunks of 5000 for progress reporting and recovery
+    CHUNK = 5000
+    for i in range(0, total, CHUNK):
+        chunk = targets[i:i+CHUNK]
+        cn = i // CHUNK + 1
+        tc = (total + CHUNK - 1) // CHUNK
+        log(f'Chunk {cn}/{tc}: {len(chunk)} PMIDs ({i}/{total}, {i*100//total}%)')
+
+        # Process each chunk's PMIDs via elink (internal 200/batch)
+        all_counts = {}
+        for j in range(0, len(chunk), BATCH):
+            batch = chunk[j:j+BATCH]
+            try:
+                counts = await fetch_citedby(batch)
+                all_counts.update(counts)
+            except Exception as e:
+                log(f'  elink sub-batch error: {e}')
+            await asyncio.sleep(INTERVAL)
+
+        # Write to DB
+        updated = 0
+        async with engine.connect() as c:
+            for pmid, count in all_counts.items():
+                await c.execute(
+                    text("UPDATE global_literature SET cited_by_count = :c, updated_at = NOW() WHERE pmid = :p"),
+                    {"c": count, "p": pmid},
+                )
+                updated += 1
+            await c.commit()
+
+        total_updated += updated
+        total_errors += len(chunk) - len(all_counts)
+        log(f'  => +{updated} updated ({total_updated}/{total})')
+
+    log(f'DONE. Updated: {total_updated}, Errors: {total_errors}')
+    await engine.dispose()
+
+asyncio.run(main())