Update chunk_python_code.py

chunk_python_code.py

@@ -1,52 +1,52 @@
 import ast
 from langchain.schema import Document 
 
-def chunk_python_code_with_metadata(source_code, reference):
+def chunk_python_code_with_metadata(source_code, source):
     """
     Entry point method to process the Python file.
     It invokes the iterate_ast function.
     """
     documents = []
-    print(f"Processing file: {reference}")
+    print(f"Processing file: {source}")
 
-    iterate_ast(source_code, documents, reference)
+    iterate_ast(source_code, documents, source)
 
-    # Determine usage based on the reference path
-    if reference.startswith("kadi_apy/lib/"):
+    # Determine usage based on the source path
+    if source.startswith("kadi_apy/lib/"):
         usage = "library"
-    elif reference.startswith("kadi_apy/cli/"):
+    elif source.startswith("kadi_apy/cli/"):
         usage = "cli_library"
-    elif reference.startswith("doc/"):
+    elif source.startswith("doc/"):
         usage = "doc"
     else:
         usage = "undefined"
 
     # Add metadata for usage to all documents
     for doc in documents:
-        doc.metadata["reference"] = reference
+        doc.metadata["source"] = source
         doc.metadata["usage"] = usage  # Add the determined usage metadata
         print(doc)
     return documents
 
 
-def iterate_ast(source_code, documents, reference):
+def iterate_ast(source_code, documents, source):
     """
     Parses the AST of the given Python file and delegates
     handling to specific methods based on node types.
     """
     # Parse the source code into an abstract syntax tree (AST)
-    tree = ast.parse(source_code, filename=reference)
+    tree = ast.parse(source_code, filename=source)
 
     first_level_nodes = list(ast.iter_child_nodes(tree))
 
     # Check if there are no first-level nodes
     if not first_level_nodes:
-        handle_no_first_level_node_found(documents, source_code, reference)
+        handle_no_first_level_node_found(documents, source_code, source)
         return
 
     all_imports = all(isinstance(node, (ast.Import, ast.ImportFrom)) for node in first_level_nodes)
     if all_imports:
-        handle_first_level_imports_only(documents, source_code, reference)
+        handle_first_level_imports_only(documents, source_code, source)
     
     # Iterate over first-level nodes
     for first_level_node in ast.iter_child_nodes(tree):
@@ -58,11 +58,11 @@ def iterate_ast(source_code, documents, reference):
             handle_first_level_assign(first_level_node, documents, source_code)
 
 
-def handle_first_level_imports_only(documents, source_code, reference):
+def handle_first_level_imports_only(documents, source_code, source):
     """
     Handles cases where the first-level nodes are only imports.
     """
-    if reference.endswith("__init__.py"):
+    if source.endswith("__init__.py"):
         type = "__init__-file"
     else:
         type = "undefined"
@@ -78,11 +78,11 @@ def handle_first_level_imports_only(documents, source_code, reference):
     documents.append(doc)
 
 
-def handle_no_first_level_node_found(documents, source_code, reference):
+def handle_no_first_level_node_found(documents, source_code, source):
     """
     Handles cases where no top-level nodes are found in the AST.
     """
-    if reference.endswith("__init__.py"):
+    if source.endswith("__init__.py"):
         type = "__init__-file"
     else:
         type = "undefined"
@@ -196,9 +196,4 @@ def handle_first_level_func(function_node, documents, source_code):
         page_content=function_source,
         metadata=metadata
     )
-    documents.append(doc)
-
-
-
-
-
+    documents.append(doc)