pdf_title_image/extract_price.py

import os
os.environ['TRANSFORMERS_OFFLINE'] = '1'
os.environ['HF_DATASETS_OFFLINE'] = '1'

from re import findall
from typing import List

from text_extractor import get_instance


def rmb_to_digit(rmb_str):
    digit_map = {'零': 0, '壹': 1, '贰': 2, '叁': 3, '肆': 4, '伍': 5, '陆': 6, '柒': 7, '捌': 8, '玖': 9}
    unit_map = {'分': 0.01, '角': 0.1, '元': 1, '拾': 10, '佰': 100, '仟': 1000, '万': 10000, '亿': 100000000}

    digit = 0
    total = 0
    tmp = 0
    for char in rmb_str:
        if char in digit_map:
            digit = digit_map[char]
        elif char in unit_map:
            if digit + tmp:
                total += (tmp + digit) * unit_map[char]
                tmp = digit = 0
            else:
                total *= unit_map[char]
        else:
            tmp = digit
    total += tmp + digit
    return '{:.2f}'.format(total)


def match_price_zhs(text: str) -> List[str]:
    pattern = (r"[壹,贰,叁,肆,伍,陆,柒,捌,玖,拾,佰,仟][壹,贰,叁,肆,伍,陆,柒,捌,玖,拾,佰,仟,元,角,万,分,百,整,零]+"
               r"[壹,贰,叁,肆,伍,陆,柒,捌,玖,拾,佰,仟,元,角,万,分,百,整,零]")
    temp = findall(pattern, text)
    for i in range(len(temp)):
        if temp[i].endswith('整元') or temp[i].endswith('角元') or temp[i].endswith('分元') or temp[i].endswith('元元'):
            temp[i] = temp[i][:-1]
    return temp


def match_price_num(text: str) -> List[str]:
    pattern = (r"(?:\b(?:[BS]/\.|R(?:D?\$|p))|\b(?:[TN]T|[CJZ])\$|Дин\.|\b(?:Bs|Ft|Gs|K[Mč]|Lek|B[Zr]|k[nr]|[PQLSR]|лв|"
               r"ден|RM|MT|lei|zł|USD|GBP|EUR|JPY|CHF|SEK|DKK|NOK|SGD|HKD|AUD|TWD|NZD|CNY|KRW|INR|CAD|VEF|EGP|THB|IDR|"
               r"PKR|MYR|PHP|MXN|VND|CZK|HUF|PLN|TRY|ZAR|ILS|ARS|CLP|BRL|RUB|QAR|AED|COP|PEN|CNH|KWD|SAR)|\$[Ub]|"
               r"[^\w\s])\s?(?:\d{1,3}(?:,\d{3})*|\d+)(?:\.\d{1,2})?(?!\.?\d)")
    return findall(pattern, text)


def match_duration(text: str) -> List[str]:
    pattern = r"[1-9]+[\d]日历天"
    return findall(pattern, text)


def match_quality(text: str) -> List[str]:
    pattern = r"工程质量.+"
    return findall(pattern, text)


if __name__ == '__main__':
    from pprint import pprint
    from get_info import PdfExtractAttr

    pdf_path = r'./data/0预审查初审详审测试数据/三峡左岸及地下电站地坪整治/湖北建新建设工程有限公司_T221100130348%2F01整本文件/MainPdfFile/投标文件-修改版9-5-1-1.pdf'
    file = PdfExtractAttr(file_path=pdf_path)
    titles = file.parse_title()
    texts = file.parse_text()

    price_zhs = get_instance(
        title_instances=['投标函', '开标一览表'],
        content_instances=['人民币投标总报价'],
        titles_list=titles,
        texts_list=texts,
        extractor=match_price_zhs
    )
    price_num = get_instance(
        title_instances=['投标函', '开标一览表'],
        content_instances=['人民币投标总报价'],
        titles_list=titles,
        texts_list=texts,
        extractor=match_price_num
    )
    duration = get_instance(
        title_instances=['投标函', '开标一览表'], 
        content_instances=['工期日历天'],
        titles_list=titles,
        texts_list=texts,
        extractor=match_duration
    )
    quality = get_instance(
        title_instances=['投标函', '开标一览表'], 
        content_instances=['工程质量'],
        titles_list=titles,
        texts_list=texts,
        extractor=match_quality
    )
    # valid = rmb_to_digit(price_zhs[0][0][0]) == price_num[0][0][0][1:]

    pprint({
        "price_zhs": price_zhs,
        "price_num": price_num,
        "duration": duration,
        "quality": quality,
        # "valid": valid
    })