app.py

from transformers import TrOCRProcessor, VisionEncoderDecoderModel
from PIL import Image
import os
import re

# Load Hugging Face OCR model
processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-stage1")
model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-stage1")

# Directory where patient records are stored
PATIENT_RECORDS_DIR = "records/"

# Function to extract patient name from filename
def extract_patient_name(file_name):
    match = re.match(r"([A-Za-z]+[A-Za-z]*)_.*\.(jpg|png|jpeg|pdf)$", file_name)
    if match:
        return match.group(1)
    return None

# OCR function
def extract_text_from_image(image_path):
    image = Image.open(image_path).convert("RGB")
    pixel_values = processor(images=image, return_tensors="pt").pixel_values
    generated_ids = model.generate(pixel_values)
    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return generated_text.strip()

# Save text to patient record
def save_to_patient_record(patient_name, text):
    os.makedirs(PATIENT_RECORDS_DIR, exist_ok=True)
    filepath = os.path.join(PATIENT_RECORDS_DIR, f"{patient_name}_records.txt")
    with open(filepath, "a") as file:
        file.write("\n\n===== New Upload =====\n")
        file.write(text)

# Main process
def process_uploaded_lab_result(file_path):
    print(f"Processing: {file_path}")
    patient_name = extract_patient_name(os.path.basename(file_path))
    if not patient_name:
        return "❌ Could not determine patient name from filename."

    ocr_text = extract_text_from_image(file_path)
    save_to_patient_record(patient_name, ocr_text)
    return f"✅ OCR completed and saved under {patient_name}'s record."

# Example usage
if __name__ == "__main__":
    file_to_upload = "JuanDelaCruz_2025-06-13.jpg"  # Example uploaded file
    result = process_uploaded_lab_result(file_to_upload)
    print(result)