app_blocks.py

from typing import List
import os
import sys
import subprocess
from pathlib import Path

import pytesseract
from PIL import Image

import gradio as gr

def check_tesseract_installed():
    try:
        subprocess.run(['tesseract', '--version'], capture_output=True, check=True)
        return True
    except (subprocess.CalledProcessError, FileNotFoundError):
        return False

def setup_tesseract():
    # Check if Tesseract is installed
    if not check_tesseract_installed():
        print("Tesseract is not installed. Please install it using:")
        print("sudo apt-get update && sudo apt-get install -y tesseract-ocr")
        print("For additional languages: sudo apt-get install -y tesseract-ocr-all")
        sys.exit(1)
    
    # Set TESSDATA_PREFIX if not already set
    if 'TESSDATA_PREFIX' not in os.environ:
        # Common locations for tessdata
        tessdata_paths = [
            '/usr/share/tesseract-ocr/4.00/tessdata',  # Newer versions
            '/usr/share/tesseract-ocr/tessdata',       # Older versions
            '/usr/share/tessdata',                     # Alternative location
        ]
        
        for path in tessdata_paths:
            if Path(path).exists():
                os.environ['TESSDATA_PREFIX'] = path
                print(f"Set TESSDATA_PREFIX to {path}")
                break
        else:
            print("Warning: Could not find tessdata directory")
            print("Please install language data files or set TESSDATA_PREFIX manually")

def tesseract_ocr(filepath: str, languages: List[str]=None):
    if languages is None:
        languages = ['eng']  # Default to English if no language specified
    image = Image.open(filepath)
    return pytesseract.image_to_string(image=image, lang='+'.join(languages))

title = "Tesseract OCR"
description = "Gradio demo for Tesseract. Tesseract is an open source text recognition (OCR) Engine."
article = "<p style='text-align: center'><a href='https://tesseract-ocr.github.io/' target='_blank'>Tesseract documentation</a> | <a href='https://github.com/tesseract-ocr/tesseract' target='_blank'>Github Repo</a></p>"
examples = [
    ["examples/weird_unicode_math_symbols.png", []],
    ["examples/eurotext.png", ["eng"]],
    ["examples/tesseract_sample.png", ["jpn", "eng"]],
    ["examples/chi.jpg", ["HanS", "HanT"]],
]

with gr.Blocks(title=title) as demo:
    gr.Markdown(f'<h1 style="text-align: center; margin-bottom: 1rem;">{title}</h1>')
    gr.Markdown(description)
    with gr.Row():
        with gr.Column():
            image = gr.Image(type="filepath", label="Input")
            language_choices = pytesseract.get_languages()
            with gr.Accordion("Languages", open=False):
                languages = gr.CheckboxGroup(language_choices, type="value", value=["eng"], label='language')
            with gr.Row():
                btn_clear = gr.ClearButton([image, languages])
                btn_submit = gr.Button(value="Submit", variant="primary")
        with gr.Column():
            text = gr.Textbox(label="Output")

    btn_submit.click(tesseract_ocr, inputs=[image, languages], outputs=text, api_name="tesseract-ocr")
    btn_clear.add(text)

    gr.Examples(
        examples=examples,
        inputs=[image, languages],
    )

    gr.Markdown(article)

if __name__ == '__main__':
    setup_tesseract()
    demo.launch()