MinerU/magic_pdf/model/sub_modules/table/rapidtable/rapid_table.py

import cv2
import numpy as np
from loguru import logger
from rapid_table import RapidTable
from rapidocr_paddle import RapidOCR


class RapidTableModel(object):
    def __init__(self, ocr_engine):
        self.table_model = RapidTable()
        if ocr_engine is None:
            self.ocr_model_name = "RapidOCR"
            self.ocr_engine = RapidOCR(det_use_cuda=True, cls_use_cuda=True, rec_use_cuda=True)
        else:
            self.ocr_model_name = "PaddleOCR"
            self.ocr_engine = ocr_engine

    def predict(self, image):

        if self.ocr_model_name == "RapidOCR":
            ocr_result, _ = self.ocr_engine(np.asarray(image))
        elif self.ocr_model_name == "PaddleOCR":
            bgr_image = cv2.cvtColor(np.asarray(image), cv2.COLOR_RGB2BGR)
            ocr_result = self.ocr_engine.ocr(bgr_image)[0]
            ocr_result = [[item[0], item[1][0], item[1][1]] for item in ocr_result if
                          len(item) == 2 and isinstance(item[1], tuple)]
        else:
            logger.error("OCR model not supported")
            ocr_result = None

        if ocr_result:
            html_code, table_cell_bboxes, elapse = self.table_model(np.asarray(image), ocr_result)
            return html_code, table_cell_bboxes, elapse
        else:
            return None, None, None