app.py

# app.py
import os
import gradio as gr
from gradio_pdf import PDF
import logging
from model import model_initialized
from pdf_processor import to_pdf, to_markdown
from config import config
from tts import text_to_speech  # Import TTS module

# Set up logging with ANSI escape codes for colored output
logging.basicConfig(level=logging.INFO, format="%(levelname)s: %(message)s")

def log_info(message: str):
    logging.info(f"\033[92m{message}\033[0m")  # Green for info

def log_error(message: str):
    logging.error(f"\033[91m{message}\033[0m")  # Red for errors

# Load header HTML content
try:
    with open("header.html", "r") as file:
        header = file.read()
    log_info("Header loaded successfully.")
except Exception as e:
    log_error(f"Failed to load header.html. Error: {e}")
    header = "<h1>Header not found</h1>"

# Define language options
latin_lang = ['af', 'az', 'bs', 'cs', 'cy', 'da', 'de', 'es', 'et', 'fr', 'ga', 'hr', 'hu', 'id', 'is', 'it', 'ku', 'la', 'lt', 'lv', 'mi', 'ms', 'mt', 'nl', 'no', 'oc', 'pi', 'pl', 'pt', 'ro', 'rs_latin', 'sk', 'sl', 'sq', 'sv', 'sw', 'tl', 'tr', 'uz', 'vi', 'french', 'german']
arabic_lang = ['ar', 'fa', 'ug', 'ur']
cyrillic_lang = ['ru', 'rs_cyrillic', 'be', 'bg', 'uk', 'mn', 'abq', 'ady', 'kbd', 'ava', 'dar', 'inh', 'che', 'lbe', 'lez', 'tab']
devanagari_lang = ['hi', 'mr', 'ne', 'bh', 'mai', 'ang', 'bho', 'mah', 'sck', 'new', 'gom', 'sa', 'bgc']
other_lang = ['ch', 'en', 'korean', 'japan', 'chinese_cht', 'ta', 'te', 'ka']
all_lang = ['', 'auto'] + other_lang + latin_lang + arabic_lang + cyrillic_lang + devanagari_lang

def file_to_pdf(file_obj):
    if file_obj is not None:
        try:
            pdf_path = to_pdf(file_obj.name)
            log_info("File converted to PDF successfully.")
            return pdf_path
        except Exception as e:
            log_error(f"Error converting file to PDF: {e}")
    return None

def generate_audio(text: str) -> str:
    """
    Converts the provided text to speech and returns the path of the audio file.
    """
    if text:
        try:
            audio_file = text_to_speech(text)
            log_info("Audio generated successfully.")
            return audio_file
        except Exception as e:
            log_error(f"Audio generation failed: {e}")
            return ""
    log_error("No text provided for TTS.")
    return ""

with gr.Blocks() as demo:
    gr.HTML(header)
    with gr.Row():
        with gr.Column(variant='panel', scale=5):
            file_input = gr.File(label="Please upload a PDF or image", file_types=[".pdf", ".png", ".jpeg", ".jpg"])
            max_pages = gr.Slider(1, 20, config.get("max_pages_default", 10), step=1, label='Max convert pages')
            with gr.Row():
                layout_mode = gr.Dropdown(
                    ["layoutlmv3", "doclayout_yolo"],
                    label="Layout model",
                    value=config.get("layout_model_default", "doclayout_yolo")
                )
                language = gr.Dropdown(
                    all_lang,
                    label="Language",
                    value=config.get("language_default", "auto")
                )
            with gr.Row():
                formula_enable = gr.Checkbox(label="Enable formula recognition", value=True)
                is_ocr = gr.Checkbox(label="Force enable OCR", value=False)
                table_enable = gr.Checkbox(label="Enable table recognition", value=True)
            with gr.Row():
                convert_button = gr.Button("Convert")
                clear_button = gr.ClearButton(value="Clear")
            pdf_display = PDF(label='PDF preview', interactive=False, visible=True, height=800)
            with gr.Accordion("Examples:"):
                example_root = os.path.join(os.path.dirname(__file__), "examples")
                examples = [os.path.join(example_root, f) for f in os.listdir(example_root) if f.endswith("pdf")]
                gr.Examples(examples=examples, inputs=file_input)
        with gr.Column(variant='panel', scale=5):
            output_file = gr.File(label="Convert result", interactive=False)
            with gr.Tabs():
                with gr.Tab("Markdown rendering"):
                    md_render = gr.Markdown(label="Markdown rendering", height=1100, show_copy_button=True, line_breaks=True)
                with gr.Tab("Markdown text"):
                    md_text = gr.TextArea(lines=45, show_copy_button=True)
            # Audio component for TTS playback
            audio_output = gr.Audio(label="Read Aloud", type="filepath")
            read_button = gr.Button("Read Aloud")
    
    file_input.change(fn=file_to_pdf, inputs=file_input, outputs=pdf_display)
    
    convert_button.click(
        fn=to_markdown,
        inputs=[file_input, max_pages, is_ocr, layout_mode, formula_enable, table_enable, language],
        outputs=[md_render, md_text, output_file, pdf_display]
    )
    
    # When "Read Aloud" is clicked, generate audio from the markdown text
    read_button.click(
        fn=generate_audio,
        inputs=md_text,
        outputs=audio_output
    )
    
    clear_button.add([file_input, md_render, pdf_display, md_text, output_file, is_ocr])

if __name__ == "__main__":
    demo.launch(ssr_mode=True)