crossref-local 0.4.0__py3-none-any.whl → 0.5.0__py3-none-any.whl

crossref_local/_remote/base.py

@@ -0,0 +1,356 @@
+"""Remote API client for crossref_local.
+
+Connects to a CrossRef Local API server instead of direct database access.
+Use this when the database is on a remote server accessible via HTTP.
+"""
+
+import json
+import urllib.request
+import urllib.parse
+import urllib.error
+from typing import List, Optional, Dict, Any
+
+from .._core.models import Work, SearchResult
+from .._core.config import DEFAULT_PORT
+
+# Default URL uses SCITEX port convention
+DEFAULT_API_URL = f"http://localhost:{DEFAULT_PORT}"
+
+
+class RemoteClient:
+    """
+    HTTP client for CrossRef Local API server.
+
+    Provides the same interface as the local API but connects
+    to a remote server via HTTP.
+
+    Example:
+        >>> client = RemoteClient("http://localhost:31291")
+        >>> results = client.search(title="machine learning", limit=10)
+        >>> work = client.get("10.1038/nature12373")
+    """
+
+    def __init__(self, base_url: str = DEFAULT_API_URL, timeout: int = 30):
+        """
+        Initialize remote client.
+
+        Args:
+            base_url: API server URL (default: http://localhost:3333)
+            timeout: Request timeout in seconds
+        """
+        self.base_url = base_url.rstrip("/")
+        self.timeout = timeout
+
+    def _request(
+        self,
+        endpoint: str,
+        params: Optional[Dict[str, Any]] = None,
+        method: str = "GET",
+        data: Optional[Dict[str, Any]] = None,
+    ) -> Dict:
+        """Make HTTP request to API."""
+        url = f"{self.base_url}{endpoint}"
+        if params:
+            # Filter out None values
+            params = {k: v for k, v in params.items() if v is not None}
+            if params:
+                url = f"{url}?{urllib.parse.urlencode(params)}"
+
+        try:
+            req_data = None
+            if data is not None:
+                req_data = json.dumps(data).encode("utf-8")
+
+            req = urllib.request.Request(url, data=req_data, method=method)
+            req.add_header("Accept", "application/json")
+            if req_data:
+                req.add_header("Content-Type", "application/json")
+
+            with urllib.request.urlopen(req, timeout=self.timeout) as response:
+                return json.loads(response.read().decode("utf-8"))
+        except urllib.error.HTTPError as e:
+            if e.code == 404:
+                return None
+            raise ConnectionError(f"API request failed: {e.code} {e.reason}") from e
+        except urllib.error.URLError as e:
+            raise ConnectionError(
+                f"Cannot connect to API at {self.base_url}: {e.reason}"
+            ) from e
+
+    def health(self) -> Dict:
+        """Check API server health."""
+        return self._request("/health")
+
+    def info(self) -> Dict:
+        """Get database/API information."""
+        root = self._request("/")
+        info_data = self._request("/info")
+        return {
+            "api_url": self.base_url,
+            "api_version": root.get("version", "unknown"),
+            "status": root.get("status", "unknown"),
+            "mode": "remote",
+            "works": info_data.get("total_papers", 0) if info_data else 0,
+            "fts_indexed": info_data.get("fts_indexed", 0) if info_data else 0,
+            "citations": info_data.get("citations", 0) if info_data else 0,
+        }
+
+    def search(
+        self,
+        query: Optional[str] = None,
+        doi: Optional[str] = None,
+        title: Optional[str] = None,
+        authors: Optional[str] = None,
+        year: Optional[int] = None,
+        limit: int = 10,
+        offset: int = 0,
+    ) -> SearchResult:
+        """
+        Search for papers.
+
+        Args:
+            query: Full-text search query (searches title by default)
+            doi: Search by DOI
+            title: Search by title (explicit)
+            authors: Search by author name
+            year: Filter by publication year
+            limit: Maximum results (default: 10, max: 100)
+            offset: Skip first N results for pagination
+
+        Returns:
+            SearchResult with matching works
+        """
+        # Use new /works endpoint with FTS5 search
+        search_query = query or title
+
+        params = {
+            "q": search_query,
+            "limit": min(limit, 100),
+            "offset": offset,
+        }
+
+        data = self._request("/works", params)
+
+        if not data:
+            return SearchResult(works=[], total=0, query=query or "", elapsed_ms=0.0)
+
+        works = []
+        for item in data.get("results", []):
+            work = Work(
+                doi=item.get("doi", ""),
+                title=item.get("title", ""),
+                authors=item.get("authors", []),
+                year=item.get("year"),
+                journal=item.get("journal"),
+                volume=item.get("volume"),
+                issue=item.get("issue"),
+                page=item.get("page") or item.get("pages"),
+                abstract=item.get("abstract"),
+                citation_count=item.get("citation_count"),
+            )
+            works.append(work)
+
+        return SearchResult(
+            works=works,
+            total=data.get("total", len(works)),
+            query=query or title or doi or "",
+            elapsed_ms=data.get("elapsed_ms", 0.0),
+        )
+
+    def get(self, doi: str) -> Optional[Work]:
+        """
+        Get a work by DOI.
+
+        Args:
+            doi: Digital Object Identifier
+
+        Returns:
+            Work object or None if not found
+        """
+        # Use /works/{doi} endpoint directly
+        data = self._request(f"/works/{doi}")
+        if not data or "error" in data:
+            return None
+
+        return Work(
+            doi=data.get("doi", doi),
+            title=data.get("title", ""),
+            authors=data.get("authors", []),
+            year=data.get("year"),
+            journal=data.get("journal"),
+            volume=data.get("volume"),
+            issue=data.get("issue"),
+            page=data.get("page"),
+            abstract=data.get("abstract"),
+            citation_count=data.get("citation_count"),
+        )
+
+    def get_many(self, dois: List[str]) -> List[Work]:
+        """
+        Get multiple works by DOI using batch endpoint.
+
+        Args:
+            dois: List of DOIs
+
+        Returns:
+            List of Work objects
+        """
+        # Use batch endpoint if available
+        try:
+            data = {"dois": dois}
+            req_data = json.dumps(data).encode("utf-8")
+            req = urllib.request.Request(
+                f"{self.base_url}/works/batch", data=req_data, method="POST"
+            )
+            req.add_header("Content-Type", "application/json")
+            req.add_header("Accept", "application/json")
+
+            with urllib.request.urlopen(req, timeout=self.timeout) as response:
+                result = json.loads(response.read().decode("utf-8"))
+
+            works = []
+            for item in result.get("results", []):
+                work = Work(
+                    doi=item.get("doi", ""),
+                    title=item.get("title", ""),
+                    authors=item.get("authors", []),
+                    year=item.get("year"),
+                    journal=item.get("journal"),
+                    volume=item.get("volume"),
+                    issue=item.get("issue"),
+                    page=item.get("page"),
+                    abstract=item.get("abstract"),
+                    citation_count=item.get("citation_count"),
+                )
+                works.append(work)
+            return works
+        except Exception:
+            # Fallback to individual lookups
+            works = []
+            for doi in dois:
+                work = self.get(doi)
+                if work:
+                    works.append(work)
+            return works
+
+    def exists(self, doi: str) -> bool:
+        """Check if a DOI exists."""
+        return self.get(doi) is not None
+
+    def get_citations(self, doi: str, direction: str = "both") -> Dict:
+        """
+        Get citations for a paper (legacy endpoint).
+
+        Args:
+            doi: Paper DOI
+            direction: 'citing', 'cited_by', or 'both'
+
+        Returns:
+            Dict with citation information
+        """
+        params = {"doi": doi, "direction": direction}
+        return self._request("/api/citations/", params) or {}
+
+    def get_citing(self, doi: str, limit: int = 100) -> List[str]:
+        """
+        Get DOIs of papers that cite the given DOI.
+
+        Args:
+            doi: The DOI to find citations for
+            limit: Maximum number of citing papers to return
+
+        Returns:
+            List of DOIs that cite this paper
+        """
+        data = self._request(f"/citations/{doi}/citing", {"limit": limit})
+        if not data:
+            return []
+        return data.get("papers", [])
+
+    def get_cited(self, doi: str, limit: int = 100) -> List[str]:
+        """
+        Get DOIs of papers that the given DOI cites (references).
+
+        Args:
+            doi: The DOI to find references for
+            limit: Maximum number of referenced papers to return
+
+        Returns:
+            List of DOIs that this paper cites
+        """
+        data = self._request(f"/citations/{doi}/cited", {"limit": limit})
+        if not data:
+            return []
+        return data.get("papers", [])
+
+    def get_citation_count(self, doi: str) -> int:
+        """
+        Get the number of citations for a DOI.
+
+        Args:
+            doi: The DOI to count citations for
+
+        Returns:
+            Number of papers citing this DOI
+        """
+        data = self._request(f"/citations/{doi}/count")
+        if not data:
+            return 0
+        return data.get("citation_count", 0)
+
+    def get_citation_network(
+        self, doi: str, depth: int = 1, max_citing: int = 25, max_cited: int = 25
+    ) -> Dict:
+        """
+        Get citation network graph for a DOI.
+
+        Args:
+            doi: The DOI to build the network around
+            depth: How many levels of citations to include (1-3)
+            max_citing: Max papers citing each node to include
+            max_cited: Max papers each node cites to include
+
+        Returns:
+            Dict with nodes, edges, and stats
+        """
+        params = {
+            "depth": depth,
+            "max_citing": max_citing,
+            "max_cited": max_cited,
+        }
+        data = self._request(f"/citations/{doi}/network", params)
+        return data or {}
+
+    def get_journal(
+        self, issn: Optional[str] = None, name: Optional[str] = None
+    ) -> Dict:
+        """
+        Get journal information.
+
+        Args:
+            issn: Journal ISSN
+            name: Journal name
+
+        Returns:
+            Dict with journal information
+        """
+        params = {"issn": issn, "name": name}
+        return self._request("/api/journal/", params) or {}
+
+
+# Module-level client for convenience
+_client: Optional[RemoteClient] = None
+
+
+def get_client(base_url: str = DEFAULT_API_URL) -> RemoteClient:
+    """Get or create singleton remote client."""
+    global _client
+    if _client is None or _client.base_url != base_url:
+        _client = RemoteClient(base_url)
+    return _client
+
+
+def reset_client() -> None:
+    """Reset singleton client."""
+    global _client
+    _client = None

crossref_local/_remote/collections.py

@@ -0,0 +1,175 @@
+"""Collection methods mixin for RemoteClient."""
+
+import json
+import urllib.request
+import urllib.parse
+import urllib.error
+from typing import Dict, List, Optional, Any
+
+
+class CollectionsMixin:
+    """Mixin providing collection management methods for RemoteClient."""
+
+    def list_collections(self) -> List[Dict]:
+        """
+        List all collections.
+
+        Returns:
+            List of collection info dictionaries
+        """
+        data = self._request("/collections")
+        if not data:
+            return []
+        return data.get("collections", [])
+
+    def create_collection(
+        self,
+        name: str,
+        query: Optional[str] = None,
+        dois: Optional[List[str]] = None,
+        limit: int = 1000,
+    ) -> Dict:
+        """
+        Create a new collection from search query or DOI list.
+
+        Args:
+            name: Collection name
+            query: FTS search query (if dois not provided)
+            dois: Explicit list of DOIs
+            limit: Max papers for query mode
+
+        Returns:
+            Collection info dictionary
+        """
+        body = {"name": name, "limit": limit}
+        if query:
+            body["query"] = query
+        if dois:
+            body["dois"] = dois
+
+        result = self._request("/collections", method="POST", data=body)
+        return result or {}
+
+    def get_collection(
+        self,
+        name: str,
+        fields: Optional[List[str]] = None,
+        include_abstract: bool = False,
+        include_references: bool = False,
+        include_citations: bool = False,
+        year_min: Optional[int] = None,
+        year_max: Optional[int] = None,
+        journal: Optional[str] = None,
+        limit: Optional[int] = None,
+    ) -> Dict:
+        """
+        Query a collection with field filtering.
+
+        Args:
+            name: Collection name
+            fields: Explicit field list
+            include_abstract: Include abstracts
+            include_references: Include references
+            include_citations: Include citation counts
+            year_min: Filter by min year
+            year_max: Filter by max year
+            journal: Filter by journal
+            limit: Max results
+
+        Returns:
+            Dict with collection name, count, and papers
+        """
+        params = {
+            "include_abstract": include_abstract,
+            "include_references": include_references,
+            "include_citations": include_citations,
+            "year_min": year_min,
+            "year_max": year_max,
+            "journal": journal,
+            "limit": limit,
+        }
+        if fields:
+            params["fields"] = ",".join(fields)
+
+        data = self._request(f"/collections/{name}", params)
+        return data or {}
+
+    def get_collection_stats(self, name: str) -> Dict:
+        """
+        Get collection statistics.
+
+        Args:
+            name: Collection name
+
+        Returns:
+            Dict with year distribution, top journals, citation stats
+        """
+        data = self._request(f"/collections/{name}/stats")
+        return data or {}
+
+    def download_collection(
+        self,
+        name: str,
+        output_path: str,
+        format: str = "json",
+        fields: Optional[List[str]] = None,
+    ) -> str:
+        """
+        Download collection as a file.
+
+        Args:
+            name: Collection name
+            output_path: Local file path to save to
+            format: Export format (json, csv, bibtex, dois)
+            fields: Fields to include (json/csv)
+
+        Returns:
+            Output file path
+        """
+        params = {"format": format}
+        if fields:
+            params["fields"] = ",".join(fields)
+
+        url = f"{self.base_url}/collections/{name}/download"
+        if params:
+            url = f"{url}?{urllib.parse.urlencode(params)}"
+
+        try:
+            req = urllib.request.Request(url)
+            with urllib.request.urlopen(req, timeout=self.timeout) as response:
+                content = response.read()
+                with open(output_path, "wb") as f:
+                    f.write(content)
+            return output_path
+        except urllib.error.HTTPError as e:
+            raise ConnectionError(f"Download failed: {e.code} {e.reason}") from e
+        except urllib.error.URLError as e:
+            raise ConnectionError(f"Cannot connect: {e.reason}") from e
+
+    def delete_collection(self, name: str) -> bool:
+        """
+        Delete a collection.
+
+        Args:
+            name: Collection name
+
+        Returns:
+            True if deleted
+        """
+        data = self._request(f"/collections/{name}", method="DELETE")
+        if not data:
+            return False
+        return data.get("deleted", False)
+
+    def collection_exists(self, name: str) -> bool:
+        """
+        Check if a collection exists.
+
+        Args:
+            name: Collection name
+
+        Returns:
+            True if exists
+        """
+        data = self._request(f"/collections/{name}/stats")
+        return data is not None

crossref_local/_server/__init__.py

@@ -0,0 +1,140 @@
+"""FastAPI server for CrossRef Local with FTS5 search.
+
+Modular server structure:
+- routes_works.py: /works endpoints
+- routes_citations.py: /citations endpoints
+- routes_collections.py: /collections endpoints
+- routes_compat.py: Legacy /api/* endpoints
+- models.py: Pydantic response models
+- middleware.py: Request middleware
+"""
+
+import os
+
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+
+from .. import __version__
+from .middleware import UserContextMiddleware
+from .routes_works import router as works_router
+from .routes_citations import router as citations_router
+from .routes_collections import router as collections_router
+from .routes_compat import router as compat_router
+
+# Create FastAPI app
+app = FastAPI(
+    title="CrossRef Local API",
+    description="Fast full-text search across 167M+ scholarly works",
+    version=__version__,
+)
+
+# Middleware
+app.add_middleware(UserContextMiddleware)
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# Include routers
+app.include_router(works_router)
+app.include_router(citations_router)
+app.include_router(collections_router)
+app.include_router(compat_router)
+
+
+@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",
+            "citations_citing": "/citations/{doi}/citing",
+            "citations_cited": "/citations/{doi}/cited",
+            "citations_count": "/citations/{doi}/count",
+            "citations_network": "/citations/{doi}/network",
+            "collections_list": "/collections",
+            "collections_create": "/collections (POST)",
+            "collections_get": "/collections/{name}",
+            "collections_stats": "/collections/{name}/stats",
+            "collections_download": "/collections/{name}/download",
+            "collections_delete": "/collections/{name} (DELETE)",
+        },
+    }
+
+
+@app.get("/health")
+def health():
+    """Health check endpoint."""
+    from .._core.db import get_db
+
+    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")
+def info():
+    """Get database statistics."""
+    from .._core.db import get_db
+    from .models import InfoResponse
+
+    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),
+    )
+
+
+# Default port: SCITEX convention (3129X scheme)
+DEFAULT_PORT = int(
+    os.environ.get(
+        "SCITEX_SCHOLAR_CROSSREF_PORT",
+        os.environ.get("CROSSREF_LOCAL_PORT", "31291"),
+    )
+)
+DEFAULT_HOST = os.environ.get(
+    "SCITEX_SCHOLAR_CROSSREF_HOST",
+    os.environ.get("CROSSREF_LOCAL_HOST", "0.0.0.0"),
+)
+
+
+def run_server(host: str = None, port: int = None):
+    """Run the FastAPI server."""
+    import uvicorn
+
+    host = host or DEFAULT_HOST
+    port = port or DEFAULT_PORT
+    uvicorn.run(app, host=host, port=port)
+
+
+__all__ = ["app", "run_server", "DEFAULT_PORT", "DEFAULT_HOST"]

crossref_local/_server/middleware.py

@@ -0,0 +1,25 @@
+"""Request middleware for CrossRef Local API."""
+
+from fastapi import Request
+from starlette.middleware.base import BaseHTTPMiddleware
+
+
+class UserContextMiddleware(BaseHTTPMiddleware):
+    """Extract X-User-ID header for multi-tenant collection scoping.
+
+    When requests come through scitex-cloud gateway, it passes the
+    authenticated user's ID via X-User-ID header. This middleware
+    extracts it and makes it available via request.state.user_id.
+
+    Usage in endpoints:
+        @app.get("/collections")
+        def list_collections(request: Request):
+            user_id = request.state.user_id  # None for local, set for cloud
+            ...
+    """
+
+    async def dispatch(self, request: Request, call_next):
+        # Extract user ID from header (passed by scitex-cloud gateway)
+        request.state.user_id = request.headers.get("X-User-ID")
+        response = await call_next(request)
+        return response