crossref-local 0.3.0__py3-none-any.whl → 0.4.0__py3-none-any.whl

crossref_local/server.py

@@ -0,0 +1,352 @@
+"""FastAPI server for CrossRef Local with FTS5 search.
+
+This server provides proper full-text search using FTS5 index,
+unlike the Django API which only scans a limited subset.
+
+Usage:
+    crossref-local api                    # Run on default port 8333
+    crossref-local api --port 8080        # Custom port
+
+    # Or directly:
+    uvicorn crossref_local.server:app --host 0.0.0.0 --port 8333
+"""
+
+import time
+from typing import Optional, List
+
+from fastapi import FastAPI, Query, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+
+from . import fts, __version__
+from .db import get_db
+from .models import Work
+
+app = FastAPI(
+    title="CrossRef Local API",
+    description="Fast full-text search across 167M+ scholarly works",
+    version=__version__,
+)
+
+# CORS middleware
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+
+class WorkResponse(BaseModel):
+    doi: str
+    title: Optional[str] = None
+    authors: List[str] = []
+    year: Optional[int] = None
+    journal: Optional[str] = None
+    issn: Optional[str] = None
+    volume: Optional[str] = None
+    issue: Optional[str] = None
+    page: Optional[str] = None
+    abstract: Optional[str] = None
+    citation_count: Optional[int] = None
+
+
+class SearchResponse(BaseModel):
+    query: str
+    total: int
+    returned: int
+    elapsed_ms: float
+    results: List[WorkResponse]
+
+
+class InfoResponse(BaseModel):
+    name: str = "CrossRef Local API"
+    version: str = __version__
+    status: str = "running"
+    mode: str = "local"
+    total_papers: int
+    fts_indexed: int
+    citations: int
+    database_path: str
+
+
+@app.get("/")
+def root():
+    """API root with endpoint information."""
+    return {
+        "name": "CrossRef Local API",
+        "version": __version__,
+        "status": "running",
+        "endpoints": {
+            "health": "/health",
+            "info": "/info",
+            "search": "/works?q=<query>",
+            "get_by_doi": "/works/{doi}",
+            "batch": "/works/batch",
+        },
+    }
+
+
+@app.get("/health")
+def health():
+    """Health check endpoint."""
+    db = get_db()
+    return {
+        "status": "healthy",
+        "database_connected": db is not None,
+        "database_path": str(db.db_path) if db else None,
+    }
+
+
+@app.get("/info", response_model=InfoResponse)
+def info():
+    """Get database statistics."""
+    db = get_db()
+
+    row = db.fetchone("SELECT COUNT(*) as count FROM works")
+    work_count = row["count"] if row else 0
+
+    try:
+        row = db.fetchone("SELECT COUNT(*) as count FROM works_fts")
+        fts_count = row["count"] if row else 0
+    except Exception:
+        fts_count = 0
+
+    try:
+        row = db.fetchone("SELECT COUNT(*) as count FROM citations")
+        citation_count = row["count"] if row else 0
+    except Exception:
+        citation_count = 0
+
+    return InfoResponse(
+        total_papers=work_count,
+        fts_indexed=fts_count,
+        citations=citation_count,
+        database_path=str(db.db_path),
+    )
+
+
+@app.get("/works", response_model=SearchResponse)
+def search_works(
+    q: str = Query(..., description="Search query (FTS5 syntax supported)"),
+    limit: int = Query(10, ge=1, le=100, description="Max results"),
+    offset: int = Query(0, ge=0, description="Skip first N results"),
+):
+    """
+    Full-text search across works.
+
+    Uses FTS5 index for fast searching across titles, abstracts, and authors.
+    Supports FTS5 query syntax like AND, OR, NOT, "exact phrases".
+
+    Examples:
+        /works?q=machine learning
+        /works?q="neural network" AND hippocampus
+        /works?q=CRISPR&limit=20
+    """
+    start = time.perf_counter()
+
+    try:
+        results = fts.search(q, limit=limit, offset=offset)
+    except Exception as e:
+        raise HTTPException(status_code=400, detail=f"Search error: {e}")
+
+    elapsed_ms = (time.perf_counter() - start) * 1000
+
+    return SearchResponse(
+        query=q,
+        total=results.total,
+        returned=len(results.works),
+        elapsed_ms=round(elapsed_ms, 2),
+        results=[
+            WorkResponse(
+                doi=w.doi,
+                title=w.title,
+                authors=w.authors,
+                year=w.year,
+                journal=w.journal,
+                issn=w.issn,
+                volume=w.volume,
+                issue=w.issue,
+                page=w.page,
+                abstract=w.abstract,
+                citation_count=w.citation_count,
+            )
+            for w in results.works
+        ],
+    )
+
+
+@app.get("/works/{doi:path}", response_model=Optional[WorkResponse])
+def get_work(doi: str):
+    """
+    Get work metadata by DOI.
+
+    Examples:
+        /works/10.1038/nature12373
+        /works/10.1016/j.cell.2020.01.001
+    """
+    db = get_db()
+    metadata = db.get_metadata(doi)
+
+    if metadata is None:
+        raise HTTPException(status_code=404, detail=f"DOI not found: {doi}")
+
+    work = Work.from_metadata(doi, metadata)
+
+    return WorkResponse(
+        doi=work.doi,
+        title=work.title,
+        authors=work.authors,
+        year=work.year,
+        journal=work.journal,
+        issn=work.issn,
+        volume=work.volume,
+        issue=work.issue,
+        page=work.page,
+        abstract=work.abstract,
+        citation_count=work.citation_count,
+    )
+
+
+class BatchRequest(BaseModel):
+    dois: List[str]
+
+
+class BatchResponse(BaseModel):
+    requested: int
+    found: int
+    results: List[WorkResponse]
+
+
+@app.post("/works/batch", response_model=BatchResponse)
+def get_works_batch(request: BatchRequest):
+    """
+    Get multiple works by DOI.
+
+    Request body: {"dois": ["10.1038/...", "10.1016/..."]}
+    """
+    db = get_db()
+    results = []
+
+    for doi in request.dois:
+        metadata = db.get_metadata(doi)
+        if metadata:
+            work = Work.from_metadata(doi, metadata)
+            results.append(
+                WorkResponse(
+                    doi=work.doi,
+                    title=work.title,
+                    authors=work.authors,
+                    year=work.year,
+                    journal=work.journal,
+                    abstract=work.abstract,
+                    citation_count=work.citation_count,
+                )
+            )
+
+    return BatchResponse(
+        requested=len(request.dois),
+        found=len(results),
+        results=results,
+    )
+
+
+# For backwards compatibility with existing API endpoints
+@app.get("/api/search/")
+def api_search_compat(
+    title: Optional[str] = None,
+    q: Optional[str] = None,
+    doi: Optional[str] = None,
+    limit: int = 10,
+):
+    """Backwards-compatible search endpoint."""
+    query = title or q
+
+    if doi:
+        # DOI lookup
+        try:
+            work = get_work(doi)
+            return {
+                "query": {"doi": doi},
+                "results": [work.model_dump()],
+                "total": 1,
+                "returned": 1,
+            }
+        except HTTPException:
+            return {"query": {"doi": doi}, "results": [], "total": 0, "returned": 0}
+
+    if not query:
+        raise HTTPException(
+            status_code=400, detail="Specify q, title, or doi parameter"
+        )
+
+    # Call fts.search directly (not the endpoint function)
+    results = fts.search(query, limit=limit, offset=0)
+    return {
+        "query": {
+            "title": query,
+            "doi": None,
+            "year": None,
+            "authors": None,
+            "limit": limit,
+        },
+        "results": [
+            WorkResponse(
+                doi=w.doi,
+                title=w.title,
+                authors=w.authors,
+                year=w.year,
+                journal=w.journal,
+                issn=w.issn,
+                volume=w.volume,
+                issue=w.issue,
+                page=w.page,
+                abstract=w.abstract,
+                citation_count=w.citation_count,
+            ).model_dump()
+            for w in results.works
+        ],
+        "total": results.total,
+        "returned": len(results.works),
+    }
+
+
+@app.get("/api/stats/")
+def api_stats_compat():
+    """Backwards-compatible stats endpoint."""
+    db = get_db()
+
+    row = db.fetchone("SELECT COUNT(*) as count FROM works")
+    work_count = row["count"] if row else 0
+
+    # Get table names
+    tables = []
+    for row in db.fetchall("SELECT name FROM sqlite_master WHERE type='table'"):
+        tables.append(row["name"])
+
+    # Get index names
+    indices = []
+    for row in db.fetchall("SELECT name FROM sqlite_master WHERE type='index'"):
+        if row["name"]:
+            indices.append(row["name"])
+
+    return {
+        "total_papers": work_count,
+        "database_size_mb": None,
+        "year_range": None,
+        "total_journals": 0,
+        "total_citations": None,
+        "tables": tables,
+        "indices": indices,
+    }
+
+
+def run_server(host: str = "0.0.0.0", port: int = 8333):
+    """Run the FastAPI server."""
+    import uvicorn
+
+    uvicorn.run(app, host=host, port=port)
+
+
+if __name__ == "__main__":
+    run_server()

{crossref_local-0.3.0.dist-info → crossref_local-0.4.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: crossref-local
-Version: 0.3.0
+Version: 0.4.0
 Summary: Local CrossRef database with 167M+ works and full-text search
 Project-URL: Homepage, https://github.com/ywatanabe1989/crossref_local
 Project-URL: Repository, https://github.com/ywatanabe1989/crossref_local
@@ -18,15 +18,37 @@ Classifier: Topic :: Database
 Classifier: Topic :: Scientific/Engineering
 Requires-Python: >=3.10
 Requires-Dist: click>=8.0
+Provides-Extra: all
+Requires-Dist: fastapi>=0.100; extra == 'all'
+Requires-Dist: fastmcp>=0.4; extra == 'all'
+Requires-Dist: matplotlib>=3.7; extra == 'all'
+Requires-Dist: networkx>=3.0; extra == 'all'
+Requires-Dist: pytest-asyncio>=0.21; extra == 'all'
+Requires-Dist: pytest-cov>=4.0; extra == 'all'
+Requires-Dist: pytest>=7.0; extra == 'all'
+Requires-Dist: pyvis>=0.3; extra == 'all'
+Requires-Dist: uvicorn>=0.20; extra == 'all'
+Provides-Extra: api
+Requires-Dist: fastapi>=0.100; extra == 'api'
+Requires-Dist: uvicorn>=0.20; extra == 'api'
 Provides-Extra: dev
+Requires-Dist: pytest-asyncio>=0.21; extra == 'dev'
 Requires-Dist: pytest-cov>=4.0; extra == 'dev'
 Requires-Dist: pytest>=7.0; extra == 'dev'
+Provides-Extra: mcp
+Requires-Dist: fastmcp>=0.4; extra == 'mcp'
 Provides-Extra: viz
 Requires-Dist: matplotlib>=3.7; extra == 'viz'
 Requires-Dist: networkx>=3.0; extra == 'viz'
 Requires-Dist: pyvis>=0.3; extra == 'viz'
 Description-Content-Type: text/markdown
 
+<!-- ---
+!-- Timestamp: 2026-01-16 19:15:51
+!-- Author: ywatanabe
+!-- File: /home/ywatanabe/proj/crossref-local/README.md
+!-- --- -->
+
 # CrossRef Local
 
 Local CrossRef database with 167M+ scholarly works, full-text search, and impact factor calculation.
@@ -39,6 +61,22 @@ Local CrossRef database with 167M+ scholarly works, full-text search, and impact
   <img src="examples/readme_figure.png" alt="CrossRef Local Demo" width="800"/>
 </p>
 
+<details>
+<summary><strong>MCP Demo Video</strong></summary>
+
+<p align="center">
+  <a href="https://scitex.ai/media/videos/crossref-local-v0.3.1-demo.mp4">
+    <img src="examples/demo_mcp_out/crossref-local-v0.3.1-demo-thumbnail_6m55s.png" alt="Demo Video Thumbnail" width="600"/>
+  </a>
+</p>
+
+Live demonstration of MCP server integration with Claude Code for `epilepsy seizure prediction` literature review:
+- Full-text search on title, abstracts, and keywords across 167M papers (22ms response)
+
+📄 [Full demo documentation](examples/demo_mcp.org) | 📊 [Generated diagrams](examples/demo_mcp_out/)
+
+</details>
+
 <details>
 <summary><strong>Why CrossRef Local?</strong></summary>
 
@@ -119,24 +157,110 @@ async def main():
 
 ```bash
 crossref-local search "CRISPR genome editing" -n 5
-crossref-local get 10.1038/nature12373
-crossref-local impact-factor Nature -y 2023  # IF: 54.067
+crossref-local search-by-doi 10.1038/nature12373
+crossref-local status  # Configuration and database stats
 ```
 
 With abstracts (`-a` flag):
 ```
-$ crossref-local search "CRISPR" -n 1 -a
+$ crossref-local search "RS-1 enhances CRISPR" -n 1 -a
 
-Found 87,473 matches in 18.2ms
+Found 4 matches in 128.4ms
 
 1. RS-1 enhances CRISPR/Cas9- and TALEN-mediated knock-in efficiency (2016)
    DOI: 10.1038/ncomms10548
    Journal: Nature Communications
    Abstract: Zinc-finger nuclease, transcription activator-like effector nuclease
-   and CRISPR/Cas9 are becoming major tools for genome editing. Importantly,
-   knock-in in several non-rodent species has been finally achieved...
+   and CRISPR/Cas9 are becoming major tools for genome editing...
+```
+
+</details>
+
+<details>
+<summary><strong>HTTP API</strong></summary>
+
+Start the FastAPI server:
+```bash
+crossref-local run-server-http --host 0.0.0.0 --port 8333
+```
+
+Endpoints:
+```bash
+# Search works (FTS5)
+curl "http://localhost:8333/works?q=CRISPR&limit=10"
+
+# Get by DOI
+curl "http://localhost:8333/works/10.1038/nature12373"
+
+# Batch DOI lookup
+curl -X POST "http://localhost:8333/works/batch" \
+  -H "Content-Type: application/json" \
+  -d '{"dois": ["10.1038/nature12373", "10.1126/science.aax0758"]}'
+
+# Database info
+curl "http://localhost:8333/info"
 ```
 
+HTTP mode (connect to running server):
+```bash
+# On local machine (if server is remote)
+ssh -L 8333:127.0.0.1:8333 your-server
+
+# Python client
+from crossref_local import configure_http
+configure_http("http://localhost:8333")
+
+# Or via CLI
+crossref-local --http search "CRISPR"
+```
+
+</details>
+
+<details>
+<summary><strong>MCP Server</strong></summary>
+
+Run as MCP (Model Context Protocol) server:
+```bash
+crossref-local run-server-mcp
+```
+
+Local MCP client configuration:
+```json
+{
+  "mcpServers": {
+    "crossref-local": {
+      "command": "crossref-local",
+      "args": ["run-server-mcp"],
+      "env": {
+        "CROSSREF_LOCAL_DB": "/path/to/crossref.db"
+      }
+    }
+  }
+}
+```
+
+Remote MCP via HTTP (recommended):
+```bash
+# On server: start persistent MCP server
+crossref-local run-server-mcp -t http --host 0.0.0.0 --port 8082
+```
+```json
+{
+  "mcpServers": {
+    "crossref-remote": {
+      "url": "http://your-server:8082/mcp"
+    }
+  }
+}
+```
+
+See [docs/remote-deployment.md](docs/remote-deployment.md) for systemd and Docker setup.
+
+Available tools:
+- `search` - Full-text search across 167M+ papers
+- `search_by_doi` - Get paper by DOI
+- `status` - Database statistics
+
 </details>
 
 <details>
@@ -188,6 +312,27 @@ Searching 167M records in milliseconds via FTS5.
 
 </details>
 
+<details>
+<summary><strong>Related Projects</strong></summary>
+
+**[openalex-local](https://github.com/ywatanabe1989/openalex-local)** - Sister project with OpenAlex data:
+
+| Feature | crossref-local | openalex-local |
+|---------|----------------|----------------|
+| Works | 167M | 284M |
+| Abstracts | ~21% | ~45-60% |
+| Update frequency | Real-time | Monthly |
+| DOI authority | ✓ (source) | Uses CrossRef |
+| Citations | Raw references | Linked works |
+| Concepts/Topics | ❌ | ✓ |
+| Author IDs | ❌ | ✓ |
+| Best for | DOI lookup, raw refs | Semantic search |
+
+**When to use CrossRef**: Real-time DOI updates, raw reference parsing, authoritative metadata.
+**When to use OpenAlex**: Semantic search, citation analysis, topic discovery.
+
+</details>
+
 
 ---
 

crossref_local-0.4.0.dist-info/RECORD

@@ -0,0 +1,27 @@
+crossref_local/__init__.py,sha256=eCvA9q-nZSWCIoMZxINV5xsboXovv4YeqZfjfLzi820,3696
+crossref_local/__main__.py,sha256=N1c1ESGgJkAwsSWXANUgmzxC1OJEIqw-cl9m4pmNP7s,110
+crossref_local/aio.py,sha256=En2btSn3euRbEYav1919gsmdC8iQaMbgGUso-IThCwo,5490
+crossref_local/api.py,sha256=4VGThHU3RZaH5dgjax69iUHfRlh7j91LaM00guDKtKs,7436
+crossref_local/cache.py,sha256=sMrmiUJr8-zRBDXnHg0M_3q3MpgzT7V1bqMKb5kpKVg,12291
+crossref_local/cache_export.py,sha256=DU44Rv894fZz6OnBETbgwYzwVOPg3zJ6sP85yE5EYbc,2519
+crossref_local/cache_viz.py,sha256=0VAHK-i1xR5StEYrJ_IAs0HSk0MQNVFi4EjPtlZEwTY,8498
+crossref_local/citations.py,sha256=QFahv84upNnXP_89A8bHxEbAdz7wHbh5LEniGcAiHas,12402
+crossref_local/cli.py,sha256=OMgrWviTT6Q9wLPWyhb9qDiRlVAJCuRDwDVpddyRPUk,16352
+crossref_local/cli_cache.py,sha256=8QykJ7-H313x7oKRw5fJ9Coay27Y8uBWGx5JR1VQ1_Y,6220
+crossref_local/cli_completion.py,sha256=yzqwMbGbbqXJQHdztuaqji-AdFTd8zDDhHeNGdw4NpU,7341
+crossref_local/cli_main.py,sha256=NgCGB5-ThofTRPoxxwZpsfCQTo5WIw8oP7zBSKhEiDQ,444
+crossref_local/cli_mcp.py,sha256=JBGveR_K7M_EzmHb3G9xr1IZPHAf-vvht-yAn5IzkQM,8524
+crossref_local/config.py,sha256=tBAqnnscLOIF5dobEjOA4b57OVfGeGhpnmRonYKt7ng,4839
+crossref_local/db.py,sha256=x7dXQXjsFN4LavtkNAKTNw1cUBMG-2h53-Z-Xlq6aoQ,3696
+crossref_local/fts.py,sha256=yZMh_vmtFentXKAFGTS4z7ZNNj7p_ItgfFP5i0yQltw,4448
+crossref_local/mcp_server.py,sha256=BN1BByTI54Rh-QoMZA2wUTV7lxdX-fLvoiEaH3YP-W0,10974
+crossref_local/models.py,sha256=b_yYb91O6RwEPpEqe2Wmdz12WIfE5itjEus4-fCLxLI,5476
+crossref_local/remote.py,sha256=Ju4NewXsw_cNX4vq6OeSu8fKtyf9CLwno-4uWkpwAOM,8638
+crossref_local/server.py,sha256=CpCZm5ZVLSPfcke1lGkvEOp1XsH6bUGm5M0i9pj343U,9059
+crossref_local/impact_factor/__init__.py,sha256=pcgVCPogBisANYE5Vp2PHVGPgxoMsSXr-6utqVE97-4,559
+crossref_local/impact_factor/calculator.py,sha256=eZ13URAZzPdRyAQpS8zXe_T33e2lm_gQhtoJCXbfIGM,15977
+crossref_local/impact_factor/journal_lookup.py,sha256=Ztx6ZeWxfmPvA3KfcW5h_yz01XPstIdk91j3nu2Q-qw,8846
+crossref_local-0.4.0.dist-info/METADATA,sha256=l-quaEeSKQwlveyZgKwZfW1SwyNsM9G8yZhGOHtGtMs,9508
+crossref_local-0.4.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+crossref_local-0.4.0.dist-info/entry_points.txt,sha256=1LhHFzJ7VWhNmGY6yIGDJ5EhKTYCyU7CbLEooXQWhLQ,116
+crossref_local-0.4.0.dist-info/RECORD,,

crossref_local-0.4.0.dist-info/entry_points.txt

@@ -0,0 +1,3 @@
+[console_scripts]
+crossref-local = crossref_local.cli_main:main
+crossref-local-mcp = crossref_local.mcp_server:main

crossref_local-0.3.0.dist-info/RECORD

@@ -1,16 +0,0 @@
-crossref_local/__init__.py,sha256=vJFOk5somcdkuTT7UhVjAR4kj8p5JYVVHgmgCtTmENs,1544
-crossref_local/aio.py,sha256=En2btSn3euRbEYav1919gsmdC8iQaMbgGUso-IThCwo,5490
-crossref_local/api.py,sha256=FPZBStNLD7hnjjnpUzKfBFKo7gv3JHOLEIFSydH53bw,3370
-crossref_local/citations.py,sha256=QFahv84upNnXP_89A8bHxEbAdz7wHbh5LEniGcAiHas,12402
-crossref_local/cli.py,sha256=9ISMQSvWZHYrEO_gYXJB-Ju0lZCr9ifH8jFnltkgYTU,8639
-crossref_local/config.py,sha256=_tHZOHBbbw5BcmkWdTlqbSffijlQZkPkexl2YxW4GmE,1980
-crossref_local/db.py,sha256=xiTYFQxsIXmV6_QmXMWf6eX7GJv5D4icy67lBvQjUQI,3529
-crossref_local/fts.py,sha256=e5mxAbHWrO9E1GvG1WFDFxoCs_4RQIdAPYLSuMf8JCM,3395
-crossref_local/models.py,sha256=b_yYb91O6RwEPpEqe2Wmdz12WIfE5itjEus4-fCLxLI,5476
-crossref_local/impact_factor/__init__.py,sha256=pcgVCPogBisANYE5Vp2PHVGPgxoMsSXr-6utqVE97-4,559
-crossref_local/impact_factor/calculator.py,sha256=eZ13URAZzPdRyAQpS8zXe_T33e2lm_gQhtoJCXbfIGM,15977
-crossref_local/impact_factor/journal_lookup.py,sha256=Ztx6ZeWxfmPvA3KfcW5h_yz01XPstIdk91j3nu2Q-qw,8846
-crossref_local-0.3.0.dist-info/METADATA,sha256=3z5SlpYph6S6V6fwu5omXXyyNeGubZGvyqic8BU8-n8,5659
-crossref_local-0.3.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-crossref_local-0.3.0.dist-info/entry_points.txt,sha256=TaFQ1y-tIym2dqgE6xUUeXTvy2uCHNKoYeRO4w6ndWQ,59
-crossref_local-0.3.0.dist-info/RECORD,,

crossref_local-0.3.0.dist-info/entry_points.txt

@@ -1,2 +0,0 @@
-[console_scripts]
-crossref-local = crossref_local.cli:main