import gradio as gr
import os
import cv2
from paddleocr import PPStructure,save_structure_res
from paddleocr.ppstructure.recovery.recovery_to_doc import sorted_layout_boxes, convert_info_docx

# Chinese image
table_engine = PPStructure(recovery=True)
# English image
# table_engine = PPStructure(recovery=True, lang='en')
def find_layout(name):
    save_folder = './output'
    img_path = '0.png'
    img = cv2.imread(img_path)
    result = table_engine(img)
    save_structure_res(result, save_folder, os.path.basename(img_path).split('.')[0])

    final_text = ""
    for line in result:
        line.pop('img')
        print(line)
        final_text += "\n" + line
    h, w, _ = img.shape
    res = sorted_layout_boxes(result, w)
    convert_info_docx(img, res, save_folder, os.path.basename(img_path).split('.')[0])

    return final_text

iface = gr.Interface(fn=find_layout, inputs="text", outputs="text")
iface.launch()