import logging
import os
import sys

from pdfminer.layout import LTLine

sys.path.append(os.path.dirname(__file__) + "/../")
import traceback
import cv2
from format_convert import get_memory_info
from format_convert.utils import judge_error_code, add_div, LineTable, get_table_html
from format_convert.table_correct import get_rotated_image
from format_convert.convert_need_interface import from_otr_interface, from_ocr_interface


def image_preprocess(image_np, image_path, use_ocr=True):
    from format_convert.convert_tree import _Table, _Sentence
    logging.info("into image_preprocess")
    try:
        # 图片倾斜校正，写入原来的图片路径
        g_r_i = get_rotated_image(image_np, image_path)
        if g_r_i == [-1]:
            return [-1]

        # otr需要图片resize, 写入另一个路径
        image_np = cv2.imread(image_path)
        best_h, best_w = get_best_predict_size(image_np)
        image_resize = cv2.resize(image_np, (best_w, best_h), interpolation=cv2.INTER_AREA)
        # image_resize_path = image_path[:-4] + "_resize" + image_path[-4:]
        image_resize_path = image_path.split(".")[0] + "_resize." + image_path.split(".")[-1]
        cv2.imwrite(image_resize_path, image_resize)

        # 调用otr模型接口
        with open(image_resize_path, "rb") as f:
            image_bytes = f.read()
        list_line = from_otr_interface(image_bytes)
        if judge_error_code(list_line):
            return list_line, [], [], 0

        # 将resize后得到的bbox根据比例还原
        ratio = (image_np.shape[0]/best_h, image_np.shape[1]/best_w)
        for i in range(len(list_line)):
            point = list_line[i]
            list_line[i] = [int(point[0]*ratio[1]), int(point[1]*ratio[0]),
                            int(point[2]*ratio[1]), int(point[3]*ratio[0])]

        # 调用ocr模型接口
        with open(image_path, "rb") as f:
            image_bytes = f.read()
        text_list, bbox_list = from_ocr_interface(image_bytes, True)
        if judge_error_code(text_list):
            return text_list, [], [], 0

        # 调用现成方法形成表格
        try:
            from format_convert.convert_tree import TableLine
            list_lines = []
            for line in list_line:
                list_lines.append(LTLine(1, (line[0], line[1]), (line[2], line[3])))
            from format_convert.convert_tree import TextBox
            list_text_boxes = []
            print("=============1")
            for i in range(len(bbox_list)):
                bbox = bbox_list[i]
                b_text = text_list[i]
                print("text:",b_text,"bbox:",bbox)
                list_text_boxes.append(TextBox([bbox[0][0], bbox[0][1],
                                                bbox[2][0], bbox[2][1]], b_text))
            lt = LineTable()
            tables, obj_in_table, _ = lt.recognize_table(list_text_boxes, list_lines, False)
            text = [tables, obj_in_table]
            column_list = []

            obj_list = []
            for table in tables:
                obj_list.append(_Table(table["table"], table["bbox"]))
            for text_box in list_text_boxes:
                if text_box not in obj_in_table:
                    obj_list.append(_Sentence(text_box.get_text(), text_box.bbox))
            return obj_list
        except:
            traceback.print_exc()
            return [-8]

    except Exception as e:
        logging.info("image_preprocess error")
        print("image_preprocess", traceback.print_exc())
        return [-1]


@get_memory_info.memory_decorator
def picture2text(path, html=False):
    logging.info("into picture2text")
    try:
        # 判断图片中表格
        img = cv2.imread(path)
        if img is None:
            return [-3]

        text, column_list, outline_points, is_table = image_preprocess(img, path)
        if judge_error_code(text):
            return text

        if html:
            text = add_div(text)
        return [text]
    except Exception as e:
        logging.info("picture2text error!")
        print("picture2text", traceback.print_exc())
        return [-1]


def get_best_predict_size(image_np, times=64):
    sizes = []
    for i in range(1, 100):
        if i*times <= 3000:
            sizes.append(i*times)
    sizes.sort(key=lambda x: x, reverse=True)

    min_len = 10000
    best_height = sizes[0]
    for height in sizes:
        if abs(image_np.shape[0] - height) < min_len:
            min_len = abs(image_np.shape[0] - height)
            best_height = height

    min_len = 10000
    best_width = sizes[0]
    for width in sizes:
        if abs(image_np.shape[1] - width) < min_len:
            min_len = abs(image_np.shape[1] - width)
            best_width = width

    return best_height, best_width