added code

app.py

@@ -1,59 +1,53 @@
 import streamlit as st
-from utils import load_json, count_tokens
 import json
 import os
+from Chunker import CodeChunker
+from utils import count_tokens
 
-# Set up the Streamlit page configuration
-st.set_page_config(page_title="Cintra Code Chunker", layout="wide")
+# Load JSON data for code file paths
+def load_json_file(file_path):
+    with open(file_path, 'r') as file:
+        return json.load(file)
 
-# Slider to select a value
-x = st.slider("Select a value")
-st.write(x, "squared is", x * x)
+# Setup Streamlit page
+st.set_page_config(page_title="Cintra Code Chunker", layout="wide")
 
+# Assuming app.py and mock_codefiles.json are in the same directory
+json_file_path = os.path.join(os.path.dirname(__file__), 'mock_codefiles.json')
+code_files_data = load_json_file(json_file_path)
+code_files = code_files_data['files']
 
-code_files_directory = "example_code_files"
-code_files = os.listdir(code_files_directory)
+# UI Elements
+st.title('Cintra Code Chunker')
 
-# Dropdown menu for the user to select a code file
-selected_file = st.selectbox("Select a code file", code_files)
+# File selection
+selected_file_name = st.selectbox("Select a code file", code_files)
 
-file_path = os.path.join(code_files_directory, selected_file)
+# Assuming you have the path or the content in the JSON, adjust accordingly
+# This example assumes paths are stored in the JSON
+file_path = os.path.join(os.path.dirname(__file__), 'example_code_files', selected_file_name)
 with open(file_path, "r") as file:
     code_content = file.read()
-    st.code(code_content, language="python")
-
-
-def main():
-    # Streamlit widgets for file selection
-    st.title("Cintra Code Chunker")
-    uploaded_file = st.file_uploader("Choose a file")
-    if uploaded_file is not None:
-        # Displaying the original file content
-        file_content = uploaded_file.getvalue().decode("utf-8")
-        st.text_area("File content", value=file_content, height=250, max_chars=50000)
-
-        # Input for token chunk size target
-        token_chunk_size = st.slider(
-            "Select token chunk size target", min_value=10, max_value=500, value=100
-        )
-
-        # Button to trigger chunking process
-        if st.button("Chunk Code"):
-            # Assuming the existence of a function to chunk code based on token size
-            # This is a placeholder for the actual chunking logic which would likely involve
-            # the 'count_tokens' function from utils.py and some logic to split the code into chunks
-            # For demonstration, we'll just show a message
-            st.success(
-                f"Code has been chunked with a target of {token_chunk_size} tokens per chunk."
-            )
-            # Displaying the chunked code - this would be replaced with actual chunked code display logic
-            st.text_area(
-                "Chunked Code",
-                value="Chunked code would appear here...",
-                height=250,
-                max_chars=50000,
-            )
-
-
-if __name__ == "__main__":
-    main()
+
+col1, col2 = st.columns(2)
+
+with col1:
+    st.subheader('Original File')
+    st.code(code_content, language='python')  # Adjust language dynamically based on file extension if necessary
+
+with col2:
+    token_chunk_size = st.sidebar.slider('Token Chunk Size Target', min_value=5, max_value=50, value=25)
+    if st.sidebar.button("Chunk Code"):
+        # Initialize the code chunker, assuming it takes file extension and encoding name
+        file_extension = selected_file_name.split('.')[-1]
+        code_chunker = CodeChunker(file_extension=file_extension)
+
+        # Chunk the code content
+        chunked_code_dict = code_chunker.chunk(code_content, token_chunk_size)
+
+        # Select a chunk to display
+        chunk_keys = list(chunked_code_dict.keys())
+        selected_chunk_key = st.selectbox("Select Chunk", options=chunk_keys)
+
+        st.subheader('Chunked Code')
+        st.code(chunked_code_dict[selected_chunk_key], language='python')  # Adjust language dynamically based on file extension if necessary