app.py

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
import threading
import time
import pypandoc
import os

# Check if pandoc is installed
try:
    pypandoc.get_pandoc_version()
except OSError:
    # If not found, attempt to download and install
    print("Pandoc not found. Attempting to download...")
    pypandoc.download_pandoc()
    
    # Verify installation
    try:
        pypandoc.get_pandoc_version()
        print("Pandoc successfully installed.")
    except OSError:
        print("Failed to install Pandoc. Please install it manually.")
        exit(1)

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,
        accept='.docx,.pdf'
    ),
    html.Div(id='upload-output'),
    html.Div(id="upload-status", style={"display": "none"}),
    html.Div(id="conversion-status", style={"display": "none"}),
    dbc.Button("Convert and Download", id="convert-button", color="primary", className="mt-3", disabled=True),
    dcc.Download(id="download-zip")
])

def process_file(contents, filename):
    content_type, content_string = contents.split(',')
    decoded = base64.b64decode(content_string)
    with open(filename, 'wb') as f:
        f.write(decoded)
    
    md_content = pypandoc.convert_file(filename, 'md')
    os.remove(filename)  # Clean up the temporary file
    return md_content

def process_files(contents, filenames):
    processed_files = []
    for c, n in zip(contents, filenames):
        if n.lower().endswith(('.docx', '.pdf')):
            text = process_file(c, n)
            processed_files.append((n.rsplit('.', 1)[0] + '.md', text))
        time.sleep(0.1)  # Simulate processing time

    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()

@app.callback(
    [Output('upload-output', 'children'),
     Output('convert-button', 'disabled'),
     Output('upload-status', 'children'),
     Output('upload-status', 'style'),
     Output('conversion-status', 'children'),
     Output('conversion-status', '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 uploaded: {name}"),
                    html.Hr()
                ]) for name in list_of_names
            ]
            return children, False, "Files uploaded successfully", {"display": "block"}, "", {"display": "none"}, None
        return no_update

    if ctx.triggered[0]['prop_id'] == 'convert-button.n_clicks':
        if n_clicks is None or not contents:
            return no_update

        def process_and_download():
            zip_data = process_files(contents, filenames)
            return dcc.send_bytes(zip_data, "converted_files.zip")

        return (
            no_update,
            True,
            "",
            {"display": "none"},
            "Converting files... This may take a moment.",
            {"display": "block"},
            process_and_download()
        )

    return no_update

if __name__ == '__main__':
    print("Starting the Dash application...")
    app.run(debug=False, host='0.0.0.0', port=7860)
    print("Dash application has finished running.")