app.py

import gradio as gr
import json
import tempfile
import os
from typing import List, Optional, Literal
from PIL import Image
import spaces
from pathlib import Path
from htrflow.volume.volume import Collection
from htrflow.pipeline.pipeline import Pipeline

DEFAULT_OUTPUT = "alto"
CHOICES = ["txt", "alto", "page", "json"]

PIPELINE_CONFIGS = {
    "letter_english": {
        "steps": [
            {
                "step": "Segmentation",
                "settings": {
                    "model": "yolo",
                    "model_settings": {"model": "Riksarkivet/yolov9-lines-within-regions-1"},
                    "generation_settings": {"batch_size": 8},
                },
            },
            {
                "step": "TextRecognition",
                "settings": {
                    "model": "TrOCR",
                    "model_settings": {"model": "microsoft/trocr-base-handwritten"},
                    "generation_settings": {"batch_size": 16},
                },
            },
            {"step": "OrderLines"},
        ]
    },
    "letter_swedish": {
        "steps": [
            {
                "step": "Segmentation",
                "settings": {
                    "model": "yolo",
                    "model_settings": {"model": "Riksarkivet/yolov9-lines-within-regions-1"},
                    "generation_settings": {"batch_size": 8},
                },
            },
            {
                "step": "TextRecognition",
                "settings": {
                    "model": "TrOCR",
                    "model_settings": {"model": "Riksarkivet/trocr-base-handwritten-hist-swe-2"},
                    "generation_settings": {"batch_size": 16},
                },
            },
            {"step": "OrderLines"},
        ]
    },
    "spread_english": {
        "steps": [
            {
                "step": "Segmentation",
                "settings": {
                    "model": "yolo",
                    "model_settings": {"model": "Riksarkivet/yolov9-regions-1"},
                    "generation_settings": {"batch_size": 4},
                },
            },
            {
                "step": "Segmentation",
                "settings": {
                    "model": "yolo",
                    "model_settings": {"model": "Riksarkivet/yolov9-lines-within-regions-1"},
                    "generation_settings": {"batch_size": 8},
                },
            },
            {
                "step": "TextRecognition",
                "settings": {
                    "model": "TrOCR",
                    "model_settings": {"model": "microsoft/trocr-base-handwritten"},
                    "generation_settings": {"batch_size": 16},
                },
            },
            {"step": "ReadingOrderMarginalia", "settings": {"two_page": True}},
        ]
    },
    "spread_swedish": {
        "steps": [
            {
                "step": "Segmentation",
                "settings": {
                    "model": "yolo",
                    "model_settings": {"model": "Riksarkivet/yolov9-regions-1"},
                    "generation_settings": {"batch_size": 4},
                },
            },
            {
                "step": "Segmentation",
                "settings": {
                    "model": "yolo",
                    "model_settings": {"model": "Riksarkivet/yolov9-lines-within-regions-1"},
                    "generation_settings": {"batch_size": 8},
                },
            },
            {
                "step": "TextRecognition",
                "settings": {
                    "model": "TrOCR",
                    "model_settings": {"model": "Riksarkivet/trocr-base-handwritten-hist-swe-2"},
                    "generation_settings": {"batch_size": 16},
                },
            },
            {"step": "ReadingOrderMarginalia", "settings": {"two_page": True}},
        ]
    },
}

@spaces.GPU
def process_htr(image_path: str, document_type: Literal["letter_english", "letter_swedish", "spread_english", "spread_swedish"] = "letter_english", output_format: Literal["txt", "alto", "page", "json"] = DEFAULT_OUTPUT, custom_settings: Optional[str] = None):
    """Process handwritten text recognition and return extracted text with specified format file."""
    if image_path is None:
        return "Error: No image provided", None

    try:
        original_filename = Path(image_path).stem or "output"
        
        if custom_settings:
            try:
                config = json.loads(custom_settings)
            except json.JSONDecodeError:
                return "Error: Invalid JSON in custom_settings parameter", None
        else:
            config = PIPELINE_CONFIGS[document_type]

        collection = Collection([image_path])
        pipeline = Pipeline.from_config(config)
        
        try:
            processed_collection = pipeline.run(collection)
        except Exception as pipeline_error:
            return f"Error: Pipeline execution failed: {str(pipeline_error)}", None

        temp_dir = Path(tempfile.mkdtemp())
        export_dir = temp_dir / output_format
        processed_collection.save(directory=str(export_dir), serializer=output_format)
        
        output_file_path = None
        for root, _, files in os.walk(export_dir):
            for file in files:
                old_path = os.path.join(root, file)
                file_ext = Path(file).suffix
                new_filename = f"{original_filename}.{output_format}" if not file_ext else f"{original_filename}{file_ext}"
                new_path = os.path.join(root, new_filename)
                os.rename(old_path, new_path)
                output_file_path = new_path
                break
        
        extracted_text = extract_text_from_collection(processed_collection)

        return extracted_text, output_file_path
        
    except Exception as e:
        return f"Error: HTR processing failed: {str(e)}", None

def extract_text_from_collection(collection: Collection) -> str:
    text_lines = []
    for page in collection.pages:
        for node in page.traverse():
            if hasattr(node, "text") and node.text:
                text_lines.append(node.text)
    return "\n".join(text_lines)

def create_htrflow_mcp_server():
    demo = gr.Interface(
        fn=process_htr,
        inputs=[
            gr.Image(type="filepath", label="Upload Image or Enter URL"),
            gr.Dropdown(choices=["letter_english", "letter_swedish", "spread_english", "spread_swedish"], value="letter_english", label="Document Type"),
            gr.Dropdown(choices=CHOICES, value=DEFAULT_OUTPUT, label="Output Format"),
            gr.Textbox(label="Custom Settings (JSON)", placeholder="Optional custom pipeline settings"),
        ],
        outputs=[
            gr.Textbox(label="Extracted Text", lines=10),
            gr.File(label="Download Output File")
        ],
        title="HTRflow MCP Server",
        description="Process handwritten text from uploaded file or URL and get extracted text with output file in specified format",
        api_name="process_htr",
    )
    return demo

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