cpg2py 1.0.1__tar.gz → 1.0.3__tar.gz

{cpg2py-1.0.1/cpg2py.egg-info → cpg2py-1.0.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: cpg2py
-Version: 1.0.1
+Version: 1.0.3
 Summary: A graph-based data structure designed for querying CSV files in Joern format in Python
 Home-page: https://github.com/YichaoXu/cpg2py
 Author: Yichao Xu

{cpg2py-1.0.1 → cpg2py-1.0.3}/cpg2py/__init__.py

@@ -1,11 +1,24 @@
+import os
 from pathlib import Path
 from csv import DictReader
 from .cpg import _Graph
 from .abc import *
 
+def __remove_null_bytes(file_path: Path) -> Path:
+    """Create a new clean file without NULL bytes and return its path."""
+    clean_path = file_path.with_suffix(".clean.csv")  # Create a temp clean file
+    if clean_path.exists(): os.remove(clean_path)
+    with open(file_path, "rb") as f:
+        content = f.read().replace(b"\x00", b"")  # Remove NULL bytes
+    with open(clean_path, "wb") as f:
+        f.write(content)
+    return clean_path
+
 def cpg_graph(node_csv: Path, edge_csv: Path) -> _Graph: 
+    # Clean files before reading
+    tmp_node_csv = __remove_null_bytes(node_csv)
     storage = Storage()
-    with open(node_csv, 'r') as n_file: 
+    with open(tmp_node_csv, 'r') as n_file: 
         reader = DictReader(n_file, delimiter='\t')
         for node_props in reader: 
             nid = node_props.get("id:int", None) 
@@ -14,7 +27,9 @@ def cpg_graph(node_csv: Path, edge_csv: Path) -> _Graph:
                 print(f"Node {nid} already exists in the graph")
             if not storage.set_node_props(nid, node_props): 
                 print(f"Failed to set properties for node {nid}")
-    with open(edge_csv, 'r') as f:
+    if tmp_node_csv.exists(): os.remove(tmp_node_csv)
+    tmp_edge_csv = __remove_null_bytes(edge_csv)
+    with open(tmp_edge_csv, 'r') as f:
         reader = DictReader(f, delimiter='\t')
         for edge_props in reader: 
             f_nid = str(edge_props.get("start", None) )
@@ -28,6 +43,7 @@ def cpg_graph(node_csv: Path, edge_csv: Path) -> _Graph:
                 print(f"Edge {f_nid} -> {t_nid} already exists in the graph")
             if not storage.set_edge_props(edge_id, edge_props): 
                 print(f"Failed to set properties for edge {edge_id}")
+    if tmp_edge_csv.exists(): os.remove(tmp_edge_csv)
     return _Graph(storage)
 
 

{cpg2py-1.0.1 → cpg2py-1.0.3}/cpg2py/abc/storage.py

@@ -1,12 +1,12 @@
-from typing import Optional, Iterable, Dict
+from typing import Optional, Iterable, Dict, Tuple
 
 
 class Storage:
     """ A directed multi-graph implementation supporting multiple edges between nodes. """
 
     __NodeID = str
-    __EdgeID = tuple[str, str, str]
-    __Property = dict[str, any]
+    __EdgeID = Tuple[str, str, str]
+    __Property = Dict[str, any]
 
     def __init__(self):
         """ Initializes an empty directed graph. """

{cpg2py-1.0.1 → cpg2py-1.0.3}/cpg2py/cpg/edge.py

@@ -1,6 +1,5 @@
 from __future__ import annotations
 from typing import Optional, Tuple
-from enum import Enum
 from ..abc import AbcGraphQuerier, AbcEdgeQuerier
 
 class _Edge(AbcEdgeQuerier): 

{cpg2py-1.0.1 → cpg2py-1.0.3/cpg2py.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: cpg2py
-Version: 1.0.1
+Version: 1.0.3
 Summary: A graph-based data structure designed for querying CSV files in Joern format in Python
 Home-page: https://github.com/YichaoXu/cpg2py
 Author: Yichao Xu

{cpg2py-1.0.1 → cpg2py-1.0.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "cpg2py"
-version = "1.0.1"
+version = "1.0.3"
 description = "A graph-based data structure designed for querying CSV files in Joern format in Python"
 readme = "README.md"
 authors = [

{cpg2py-1.0.1 → cpg2py-1.0.3}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name="cpg2py",  
-    version="1.0.1", 
+    version="1.0.3", 
     author="Yichao Xu",
     author_email="yxu166@jhu.edu",
     description="A graph-based data structure designed for querying CSV files in Joern format in Python",