File size: 2,543 Bytes
9afc52f
182adbd
4644b40
9358586
1d6fa11
19c8428
 
 
dbc4628
9358586
 
 
182adbd
34165ae
 
 
 
19c8428
4644b40
9358586
 
dbc4628
 
 
4644b40
9358586
4644b40
19c8428
 
34165ae
 
1d6fa11
19c8428
34165ae
19c8428
dbc4628
34165ae
 
 
 
 
 
 
dbc4628
 
 
 
 
 
 
 
 
 
19c8428
dbc4628
 
9358586
19c8428
34165ae
19c8428
9358586
19c8428
9358586
dbc4628
9358586
1d6fa11
 
9358586
1d6fa11
 
9358586
19c8428
1d6fa11
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
import streamlit as st
import json
import os
from Chunker import CodeChunker

# Set Streamlit page config at the very beginning
st.set_page_config(page_title="Cintra Code Chunker", layout="wide")

# Function to load JSON data
def load_json_file(file_path):
    with open(file_path, 'r') as file:
        return json.load(file)

# Function to read code from an uploaded file
def read_code_from_file(uploaded_file):
    return uploaded_file.getvalue().decode("utf-8")

st.link_button('Contribute on GitHub', 'https://github.com/CintraAI/code-chunker', help=None, type="secondary", disabled=False, use_container_width=False)

json_file_path = os.path.join(os.path.dirname(__file__), 'mock_codefiles.json')
code_files_data = load_json_file(json_file_path)

# Extract filenames and contents
code_files = list(code_files_data.keys())

st.title('Cintra Code Chunker')

selection_col, upload_col = st.columns(2)
with selection_col:
    # File selection dropdown
    selected_file_name = st.selectbox("Select an example code file", code_files)

with upload_col:
    # File upload
    uploaded_file = st.file_uploader("Or upload your code file", type=['py', 'js', 'css', 'jsx'])

# Determine the content and file extension based on selection or upload
if uploaded_file is not None:
    code_content = read_code_from_file(uploaded_file)
    file_extension = uploaded_file.name.split('.')[-1]
else:
    code_content = code_files_data.get(selected_file_name, "")
    file_extension = selected_file_name.split('.')[-1] if selected_file_name else None

# Determine the language for syntax highlighting
def get_language_by_extension(file_extension):
    if file_extension in ['py', 'python']:
        return 'python'
    elif file_extension in ['js', 'jsx', 'javascript']:
        return 'javascript'
    elif file_extension == 'css':
        return 'css'
    else:
        return None

language = get_language_by_extension(file_extension)

token_chunk_size = st.number_input('Chunk Size Target Measured in Tokens (tiktoken, gpt-4)', min_value=5, max_value=1000, value=25)

original_col, chunked_col = st.columns(2)

with original_col:
    st.subheader('Original File')
    st.code(code_content, language=language)

# Initialize the code chunker
code_chunker = CodeChunker(file_extension=file_extension)

# Chunk the code content
chunked_code_dict = code_chunker.chunk(code_content, token_chunk_size)

with chunked_col:
    st.subheader('Chunked Code')
    for chunk_key, chunk_code in chunked_code_dict.items():
        st.code(chunk_code, language=language)