PyStreamPDF 2.3.1__tar.gz → 2.3.2__tar.gz

{pystreampdf-2.3.1 → pystreampdf-2.3.2}/Cargo.lock

@@ -551,7 +551,7 @@ dependencies = [
 
 [[package]]
 name = "pystreampdf"
-version = "2.3.1"
+version = "2.3.2"
 dependencies = [
  "chrono",
  "pyo3",
@@ -697,7 +697,7 @@ dependencies = [
 
 [[package]]
 name = "streampdf-core"
-version = "2.3.1"
+version = "2.3.2"
 dependencies = [
  "chrono",
  "pdfium-render",

{pystreampdf-2.3.1 → pystreampdf-2.3.2}/Cargo.toml

@@ -3,7 +3,7 @@ members = ["core", "python"]
 resolver = "2"
 
 [workspace.package]
-version = "2.3.1"
+version = "2.3.2"
 edition = "2021"
 authors = ["Georgi Mammen Mullassery <mullassery@gmail.com>"]
 license = "Apache-2.0"

{pystreampdf-2.3.1 → pystreampdf-2.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PyStreamPDF
-Version: 2.3.1
+Version: 2.3.2
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research

{pystreampdf-2.3.1 → pystreampdf-2.3.2}/python/pystreampdf/__init__.py

@@ -5,7 +5,7 @@ Actual token savings depend on your documents — see the README's "Token
 Savings" section rather than relying on a fixed multiplier here.
 """
 
-__version__ = "2.3.1"  # Real MCP tool implementations (extract/OCR/validate/etc.), previously all hardcoded fixture data
+__version__ = "2.3.2"  # Real MCP tool implementations (extract/OCR/validate/etc.), previously all hardcoded fixture data
 
 # Optional: Rust core bindings (requires maturin build)
 try:

{pystreampdf-2.3.1 → pystreampdf-2.3.2}/python/pystreampdf/semantic/citations.py

@@ -36,3 +36,23 @@ class CitationNetwork:
         """Add citation."""
         citation = Citation(source_paper=source, target_paper=target, relation=relation)
         self.citations.append(citation)
+
+    def top_cited(self, limit: int = 3) -> list[str]:
+        """Return formatted labels for the most-cited papers in the network (PYSTREAMPDF-006)."""
+        counts: dict[str, int] = {}
+        for c in self.citations:
+            if c.relation == CitationRelation.CITES:
+                counts[c.target_paper] = counts.get(c.target_paper, 0) + 1
+            elif c.relation == CitationRelation.CITED_BY:
+                counts[c.source_paper] = counts.get(c.source_paper, 0) + 1
+        ranked = sorted(counts.items(), key=lambda item: (-item[1], item[0]))[: max(0, limit)]
+        results: list[str] = []
+        for pid, count in ranked:
+            meta = self.papers.get(pid, {})
+            title = meta.get("title") or pid
+            year = meta.get("year")
+            if year is not None:
+                results.append(f"{title} ({year}, {count} citations)")
+            else:
+                results.append(f"{title} ({count} citations)")
+        return results

{pystreampdf-2.3.1 → pystreampdf-2.3.2}/python/streampdf/server.py

@@ -6,8 +6,8 @@ from typing import Any, Optional
 class StreamPDFServer:
     """REST API server for document processing workflows."""
 
-    def __init__(self, host: str = "0.0.0.0", port: int = 8003):
-        """Initialize server."""
+    def __init__(self, host: str = "127.0.0.1", port: int = 8003):
+        """Initialize server (defaults to loopback 127.0.0.1)."""
         self.host = host
         self.port = port
         self.documents: dict[str, dict[str, Any]] = {}
@@ -188,8 +188,8 @@ def create_flask_app(server: Optional[StreamPDFServer] = None):
     return app
 
 
-def run_server(host: str = "0.0.0.0", port: int = 8003):
-    """Run the REST API server."""
+def run_server(host: str = "127.0.0.1", port: int = 8003):
+    """Run the REST API server (defaults to loopback 127.0.0.1)."""
     app = create_flask_app()
     app.run(host=host, port=port, debug=False)