import base64 import io import os import zipfile from dash import Dash, dcc, html, Input, Output, State, callback_context, no_update import dash_bootstrap_components as dbc from docx import Document import markdown import threading import time app = Dash(__name__, external_stylesheets=[dbc.themes.BOOTSTRAP]) app.layout = dbc.Container([ html.H1("Auto-Wiki", className="my-4"), dcc.Upload( id='upload-data', children=html.Div([ 'Drag and Drop or ', html.A('Select Files') ]), style={ 'width': '100%', 'height': '60px', 'lineHeight': '60px', 'borderWidth': '1px', 'borderStyle': 'dashed', 'borderRadius': '5px', 'textAlign': 'center', 'margin': '10px' }, multiple=True ), html.Div(id='upload-output'), dbc.Progress(id="upload-progress", label="Upload Progress", style={"visibility": "hidden"}), dbc.Progress(id="conversion-progress", label="Conversion Progress", style={"visibility": "hidden"}), dbc.Button("Convert and Download", id="convert-button", color="primary", className="mt-3", disabled=True), dcc.Download(id="download-zip") ]) def process_docx(contents, filename): content_type, content_string = contents.split(',') decoded = base64.b64decode(content_string) doc = Document(io.BytesIO(decoded)) full_text = [] for para in doc.paragraphs: full_text.append(para.text) return '\n\n'.join(full_text) @app.callback( [Output('upload-output', 'children'), Output('convert-button', 'disabled'), Output('upload-progress', 'value'), Output('upload-progress', 'style'), Output('conversion-progress', 'value'), Output('conversion-progress', 'style'), Output('download-zip', 'data')], [Input('upload-data', 'contents'), Input('upload-data', 'filename'), Input('convert-button', 'n_clicks')], [State('upload-data', 'contents'), State('upload-data', 'filename')] ) def update_output(list_of_contents, list_of_names, n_clicks, contents, filenames): ctx = callback_context if not ctx.triggered: return no_update if ctx.triggered[0]['prop_id'] == 'upload-data.contents': if list_of_contents is not None: children = [ html.Div([ html.H5(f"File: {name}"), html.Hr() ]) for name in list_of_names ] return children, False, 100, {"visibility": "visible"}, 0, {"visibility": "hidden"}, None return no_update if ctx.triggered[0]['prop_id'] == 'convert-button.n_clicks': if n_clicks is None: return no_update if not contents: return no_update def process_files(): processed_files = [] for i, (c, n) in enumerate(zip(contents, filenames)): text = process_docx(c, n) md = markdown.markdown(text) processed_files.append((n.replace('.docx', '.md'), md)) time.sleep(0.1) # Simulate processing time app.callback_context.response.set_data(f'{{"progress": {(i+1)/len(contents)*100}}}') zip_buffer = io.BytesIO() with zipfile.ZipFile(zip_buffer, 'w', zipfile.ZIP_DEFLATED) as zip_file: for name, content in processed_files: zip_file.writestr(name, content) return zip_buffer.getvalue() thread = threading.Thread(target=process_files) thread.start() return no_update, True, 100, {"visibility": "visible"}, 0, {"visibility": "visible"}, dcc.send_bytes(process_files(), "converted_files.zip") return no_update if __name__ == '__main__': print("Starting the Dash application...") app.run(debug=True, host='0.0.0.0', port=7860) print("Dash application has finished running.")