import re
from extractor import Extractor
import json

class IdentityCardExtractor(Extractor):
    def extract_text(self,text:str)->dict:
        patterns = {
            "issuingAuthority": r"签发机关\n(.+?)\n",
            "validTime": r"有效期限\n(.+?)\n",
            "name": r"(\S+)\n(?:男|女)",
            "gender": r"(\S+)民族",
            "ethnicity": r"民族(\S+)",
            "dateOfBirth": r"(\d+年\d+月\d+日)",
            "address": r"住址\s*(.*?)公民身份号码",
            "idNumber": r"(\d{18}|\d{17}[Xx])"
        }
        tempText = self.remove_blank_lines(text)
        # 提取信息
        info = {}
        for key, pattern in patterns.items():
            match = re.search(pattern, tempText,re.DOTALL)
            if match:
                tempStr = match.group(1).strip()
                info[key] = tempStr.replace("\n", "")
        return info
    
    def extract_textbyPaddle(self, text:str)->dict:
        patterns = {
            "issuingAuthority": r"签发机关\n(.+?)\n",
            "validTime": r"有效期限\n(.+?)\n",
            "name": r"姓名(.*?)\n", #####
            "gender": r"(\S)民族",  
            "ethnicity": r"民族(\S+)",
            "dateOfBirth": r"(\d+年\d+月\d+日)",
            "address": r"住址|佳址\s*(.*?)公民身份号码",
            "idNumber": r"(\d{18}|\d{17}[Xx])"
        }

        tempText = self.remove_blank_lines(text)
        # 提取信息
        info = {}
        for key, pattern in patterns.items():
            match = re.search(pattern, tempText,re.DOTALL)
            if match:
                tempStr = match.group(1).strip()
                info[key] = tempStr.replace("\n", "")
        return info    


class InvoiceExtractor(Extractor):
    def extract_text(self,text:str)->dict:
        pass


# text = """中华人民共和国
# 居民身份证
# 签发机关合肥市公安局庐阳分局
# 有效期限
# 2022.07.10-长期
# 姓名陈玉振
# 性别男
# 民族汉
# 出生1973年6月19日
# 佳址安徽省合肥市庐阳区固镇
# 路3150号森林城A6地块1
# 幢2001室
# 公民身份号码
# 440203197306192118"""

# extractor = IdentityCardExtractor()

# jsonstring = extractor.extract_textbyPaddle(text)
# print(jsonstring)