resume-parse/tools/resume_parse.py

#!/usr/bin/env python
# coding: utf-8
import os
import sys
import re
import json
import time
from os import walk
import subprocess
import py7zr
import tarfile
from zipfile import ZipFile

import logging

from docx import Document
from docx.shared import Inches

from pdfminer.pdfpage import PDFPage
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument
from pdfminer.high_level import extract_pages
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LTTextContainer, LTChar, LTLine, LAParams, LTTextBox, LTFigure, LTImage, LTText, LTAnno, LTTextLine, LTTextLineHorizontal
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter

import pdfplumber
from paddlenlp import Taskflow

logging.basicConfig(format='%(asctime)s: %(name)s: %(levelname)s: %(filename)s: %(funcName)s: %(lineno)d: %(message)s', level=logging.INFO)

from rich.console import Console
console = Console()

import uvicorn
from fastapi import BackgroundTasks, FastAPI, File, UploadFile
app = FastAPI()

ner = Taskflow("ner", mode='fast')
ner_tag = Taskflow("ner")
base_info_ie = Taskflow('information_extraction', schema=["姓名","性别","婚姻状况","电子邮箱","政治面貌","手机号码","籍贯","出生日期","现任职务","参加工作时间","英语水平","计算机水平","工作年限","当前单位","所在城市","职业资格"])
prize_ie = Taskflow('information_extraction', schema=["时间", "奖项"])
cet_ie = Taskflow('information_extraction', schema=["时间","证书"])
pro_ie = Taskflow("information_extraction", schema=["时间","项目名称","机构","职位"], task_path='./model_100')
global block, block_rev

with open("resources/SegmentName.json", "r", encoding="utf-8") as fp:
    block = json.load(fp)
block_rev = {1:"基本信息", 2:"求职意向", 3:"教育经历", 4:"工作经历", 5:"项目经历", 6:"专业技能", 7:"自我评价", 8:"兴趣爱好", 9:"语言能力", 10:"证书", 11:"获奖情况", 12:"培训经历", 13:"家庭成员", "other":"其他"}



# 基本信息(已完成)
def get_base_info_old(lines):
    logging.info(lines)
    schema = {
        '姓名': None,
    }
    for line in [' '.join(' '.join(lines).split('\n'))]:
        line = line.replace(r'[ ]{5,}','\n')
        w = re.sub(r'[\W]+(\w[:：])[\W]{0,}\w', r'\1', line)

        for i in w.split():
            if '：' in i:
                try:
                    key, val = i.split('：')
                    schema[key] = val
                except Exception as e:
                    logging.error(e)

        if not schema.get('姓名'):
            schema['姓名'] = re.search(r'[姓名:：]{3,}(\w{2,4})', w).group(1) if re.search(r'[姓名:：]{3,}(\w{2,4})', w) else None
            if not schema.get('姓名'):
                for word, tag in ner_tag(w):
                    if tag == "人物类_实体":
                        schema['姓名'] = word
        if not schema.get('性别'):
            schema['性别'] = re.search(r'[男女]', w).group() if re.search(r'[男女]', w) else None
        if not schema.get('婚姻状况'):
            schema['婚姻状况'] = re.search(r'[已未]婚', w).group() if re.search(r'[已未]婚', w) else None
        if not schema.get('电子邮箱'):
            schema['电子邮箱'] = re.search(r'([.\w]+@[.\w]+)', w).group() if re.search(r'([.\w]+@[.\w]+)', w) else None
        if not schema.get('政治面貌'):
            schema['政治面貌'] =  re.search(r'[预备中共党团员群众无派人士]{2,6}', w).group() if re.search(r'[预备中共党团员群众无派人士]{2,6}', w) else None
        if not schema.get('手机号码'):
            schema['手机号码'] = re.search(r'\W(1[\d]{10})\W', w).group(1) if re.search(r'\W(1[\d]{10})\W', w) else None
        # if not schema.get('籍贯'):
        #     schema['籍贯'] = re.search(r'[籍贯:：]{3,}(\w{2,5})', w).group(1) if re.search(r'[籍贯:：]{3,}(\w{2,})', w) else None
        # if not schema.get('出生年月'):
        #     schema['出生年月'] = re.search(r'\d{4}[./年\-]\d{1,2}[月]', w).group() if re.search(r'\d{4}[./年\-]\d{1,2}[月]', w) else None
        # if not schema.get('当前职位'):
        #     schema['当前职位'] = re.search(r'[当前职位： ]{3，}(\w)+', w).group() if re.search(r'[当前职位： ]{3，}(\w)+', w) else None
        # if not schema.get('参加工作时间'):
        #     schema['参加工作时间'] = re.search(r'[参加工作时间：]{3,}(\d{4}[./年\-]\d{1,2}[月])', w).group(1) if re.search(r'[参加工作时间：]{3,}(\d{4}[./年\-]\d{1,2}[月])', w) else None
    return {key:value for key, value in schema.items() if value}


# 基本信息(OIE已完成)
def get_base_info(lines):
    if not lines:
        return
    logging.info(lines)
    data = " ".join(lines)
    rst = base_info_ie(data)[0]
    if rst.get("出生日期"):
        dates = re.findall(r'\d+' ,rst["出生日期"][0]["text"])
        if len(dates) == 1:
            rst["出生日期"][0]["text"] = "{:4d}年01月".format(int(dates[0]))
        elif len(dates) == 2:
            rst["出生日期"][0]["text"] = "{:4d}年{:02d}月".format(int(dates[0]), int(dates[1]))
        elif len(dates) == 3:
            rst["出生日期"][0]["text"] = "{:4d}年{:02d}月".format(int(dates[0]), int(dates[1]))
    if rst.get("参加工作时间"):
        dates = re.findall(r'\d+' ,rst["参加工作时间"][0]["text"])
        if len(dates) == 1:
            rst["参加工作时间"][0]["text"] = "{:4d}年01月".format(int(dates[0]))
        elif len(dates) == 2:
            rst["参加工作时间"][0]["text"] = "{:4d}年{:02d}月".format(int(dates[0]), int(dates[1]))
        elif len(dates) == 3:
            rst["参加工作时间"][0]["text"] = "{:4d}年{:02d}月".format(int(dates[0]), int(dates[1]))
    return {key:rst[key][0]["text"] for key in rst.keys()}


# 求职意向(已完成)
def get_job_intention(lines):
    logging.info(lines)
    schema = {}
    for line in lines:
        regex = re.compile(r'\W{0,3}[：:]\s+')
        line = regex.sub(':', line)
        for i in line.split():
            if ":" in i:
                try:
                    key, val = i.split(":")
                    schema[key] = val
                except Exception as e:
                    logging.error(e)
    return schema


# 教育经历 (已停用)
# ner + 分词 (判断学校，时间，学历)  专业需要单独处理。
def get_edu_list_old(lines):
    logging.info(lines)

    job_list = []
    job_dict = {'edu_time_beg':'', 'edu_time_end':'', 'edu_name':'','edu_leval':'','edu_domain':'', 'edu_statue':0}
    re_txt = '\d{4,4}.\d{1,2}.?\040{0,2}[\-–至－\—～]\040{0,2}\d{4,4}.\d{1,2}[月]?|\d+\.\d+\-至今|\d+年\d+月\-\d+年\d+月|\d+年\d+月\-\~|\d+年\d+月[\-\~]至今|\d+-\d+\040{0,2}[\~至]\040{0,2}\d+-\d+|\d+-\d+\~|\d+-\d+\~至今|\d+-\d+\040{0,2}至今|^\d{4,4}.\d{1,2}|19\d{2,2}.|20\d{2,2}.'
    re_txt_1 =  '\d{4,4}.\d{1,2}.?\040{0,2}[\-–至－\—～]\040{0,2}\d{4,4}.\d{1,2}[月]?|\d+\.\d+\-至今|\d+年\d+月\-\d+年\d+月|\d+年\d+月\-\~|\d+年\d+月[\-\~]至今|\d+-\d+\040{0,2}[\~至]\040{0,2}\d+-\d+|\d+-\d+\~|\d+-\d+\~至今|\d+-\d+\040{0,2}至今'
    nums = []

    for i in range(len(lines)):
        if re.findall(re_txt, lines[i]):
            nums.append(i)

    nums.append(len(lines))


    edu_level = {'本科':18, "大专":17, "博士研究生":20, "学士":18, "博士":20, "硕士":19, "研究生":19, "博后":21, '博士后':21}
    year_dict = {18:4, 17:3,20:3,19:3,21:2}
    edu_dict = {18:'本科', 17:'大专',20:'博士研究生',19:'硕士',21:'博士后'}
    edu_list = []
    for i in range(1, len(nums[:])):
        job_dict = {'edu_time_beg':'', 'edu_time_end':'', 'edu_name':'','edu_leval':'','edu_domain':''}
        data_list = lines[nums[i-1]:nums[i]]
        if len(data_list) > 1 and data_list[1] and  data_list[1][-1] == '|' and data_list[0][-1] != '|':
            data_list[0] = data_list[0] + data_list[1]
            data_list[1] = ''
        if len(data_list) > 2 and data_list[2] and  data_list[2][-1] == '|' and data_list[0][-1] != '|' and '|' in str(data_list[0]) and data_list[1] and  data_list[1][-1] != '|':
            data_list[0] = data_list[0] + data_list[1] + data_list[2]
            data_list[1] = '' 
            data_list[2] = ''
        if '' in data_list:
            data_list.remove('')
        data_line = ' '.join(data_list)
        data_line = re.sub('[\|]', ' ', data_line)
        data_line = re.sub('-{3,}', '', data_line)

        ner_data = ner(''.join(data_list[:2]))

        org = ''
        time_list = []

        for jj in range(1, len(ner_data)):
            if ner_data[jj][1] == ner_data[jj-1][1]:
                ner_data[jj] = list(ner_data[jj])
                ner_data[jj][0] = ner_data[jj-1][0] + ner_data[jj][0]
                ner_data[jj-1] = ('','')

        for _ in ner_data:
            if _[1] == 'ORG' and not org:
                org = _[0].strip()
            elif _[1] == 'TIME' and len(_[1]) >= 4:
                time_list.append(_[0])

            #TIME
        # print(data_line)
        _list_data = re.split('\040+',data_line)
        top_level = 18
        remove_list = []

        logging.info(_list_data)
        logging.info(time_list)

        for ii in range(len(_list_data)):
            for t in time_list:
                if t in _list_data[ii]:
                    _list_data[ii] = ''
                    break

        for i in range(len(_list_data)):
            #if org in _list_data[i]:
            #    _list_data[i] = ''
            if re.findall('^\d{4,4}', _list_data[i]):
                _list_data[i] = ''
            _data = re.findall('本科|学士|硕士|博士研究生|博士后|博后|博士|研究生|大专', _list_data[i])
            if not _data:
                continue
            top_level = edu_level[_data[0]]
            _list_data[i] = ''
            break
            #remove_list.append(i)

        logging.info(_list_data)

        job_time = re.findall(re_txt_1, data_list[0])
        if job_time:
            job_dict['edu_time'] = job_time[0]
        else:
            job_dict['edu_time'] = ''

        
        _nums = re.findall('\d+', job_dict['edu_time'])
        if len(_nums) >= 4:
            job_dict['edu_time_beg'] = '%s-%02d'%(_nums[0], int(_nums[1]))
            job_dict['edu_time_end'] = '%s-%02d'%(_nums[2], int(_nums[3]))
            job_dict['edu_time'] = '%s-%02d~%s-%02d'%(_nums[0], int(_nums[1]), _nums[2], int(_nums[3]))
        elif len(_nums) == 2:
            job_dict['edu_time'] = '%s-%02d~%s'%(_nums[0], int(_nums[1]), '至今')
            job_dict['edu_time_beg'] = '%s-%02d'%(_nums[0], int(_nums[1]))
            job_dict['edu_time_end'] = '%s'%('至今')
        elif len(time_list) == 2:
            nums_1 = re.findall('\d+', time_list[0])
            nums_2 = re.findall('\d+', time_list[1])
            nums_1.append('09')
            nums_2.append('07')

            job_dict['edu_time_beg'] = '%s-%02d'%(nums_1[0], int(nums_1[1]))
            try:
                job_dict['edu_time_end'] = '%s-%02d'%(nums_2[0], int(nums_2[1]))
            except:
                job_dict['edu_time_end'] = None
            try:
                job_dict['edu_time'] = '%s-%02d~%s-%02d'%(nums_1[0], int(nums_1[1]), nums_2[0], int(nums_2[1]))
            except:
                job_dict['edu_time'] = '%s-%02d~今'%(nums_1[0], int(nums_1[1]))

        elif len(time_list) == 1:
            _nums = re.findall('\d+', time_list[0])
            if '毕业' in data_list[0]:
                _nums.append('06')
                _nums.insert(0, '09')
                _nums.insert(0, str(int(_nums[1]) - year_dict[top_level]))
                job_dict['edu_time'] = '%s-%02d~%s-%02d'%(_nums[0], int(_nums[1]),  _nums[2], int(_nums[3]))
                job_dict['edu_time_beg'] = '%s-%02d'%(_nums[0], int(_nums[1]))
                job_dict['edu_time_end'] = '%s-%02d'%(_nums[2], int(_nums[3]))
            else:
                _nums.append('09')
                job_dict['edu_time'] = '%s-%02d~%s'%(_nums[0], int(_nums[1]), '至今')
                job_dict['edu_time_beg'] = '%s-%02d'%(_nums[0], int(_nums[1]))
                job_dict['edu_time_end'] = '%s'%('至今')

        job_dict['edu_leval'] = edu_dict[top_level]
        if org:
            job_dict['edu_name'] = org
        else:
            job_dict['edu_name'] = ''
        edu_domain = ''
        for i in range(len(_list_data)):
            if org in _list_data[i]:
                continue
            if not _list_data[i] and '专业' in _list_data[i]:
                edu_domain = _list_data[i]

        if not edu_domain:
            for i in range(len(_list_data)):
                if org in _list_data[i]:
                    continue 
                if _list_data[i] and len(_list_data[i]) >= 3:
                    edu_domain = _list_data[i]
                    break


        if not edu_domain:
            for i in range(len(_list_data)):
                if org in _list_data[i]:
                    for j in range(i+1, len(_list_data)):
                        if _list_data[i] and len(_list_data[j]) >= 2:
                            edu_domain = _list_data[j]
                            break
                    break

        job_dict['edu_domain'] = edu_domain

        if len(job_list) ==0:
            job_list.append(job_dict)
        else:
            if job_dict in job_list:
                continue
            if not job_dict['edu_time']:
                continue
            if int(job_dict['edu_time'][:4]) > int(job_list[-1]['edu_time'][:4]):
                job_list = [job_dict] + job_list
            else:
                job_list.append(job_dict)
        continue


        data_list[0] = re.sub(job_time[0], '', data_list[0])
        _list = re.split('\|\040+', data_list[0])
        #print(_list)
        if len(_list) == 1:
            __list = re.split('\040+', data_list[0])
            job_dict['edu_name'] = __list[1].strip()
            job_dict['edu_domain'] = __list[2].strip()
            job_dict['edu_leval'] = __list[3].strip()
        else:
            #if  job_dict['edu_leval'] not in 
            if len(_list) > 3:
                job_dict['edu_name'] = _list[2].strip()
                job_dict['edu_domain'] = _list[3].strip()
                job_dict['edu_leval'] = _list[1].strip()
            else:
                job_dict['edu_leval'] = _list[0].strip()
                job_dict['edu_name'] = _list[1].strip()
                job_dict['edu_domain'] = _list[2].strip()
        if '硕士' in _list[0] or '研究生' in _list[0]:
            job_dict['edu_leval'] = '硕士'
        elif '博士' in _list[0]:
            job_dict['edu_leval'] = '博士'
        elif '本科' in _list[0]:
            job_dict['edu_leval'] = '本科'
        elif '学士' in _list[0]:
            job_dict['edu_leval'] = '本科'
        # print(job_dict)
        if len(job_list) ==0:
            job_list.append(job_dict)
        else:
            if job_dict in job_list:
                continue
            if int(job_dict['edu_time'][:4]) > int(job_list[-1]['edu_time'][:4]):
                job_list = [job_dict] + job_list
            else:
                job_list.append(job_dict)
            #edu_list.append(job_dict['edu_time'] + job_dict['edu_name'] + job_dict['edu_domain'] + job_dict['edu_leval'])
    #if job_list[0]['edu_leval'] not in ['硕士', '博士', '本科', '博后'] and len(job_list[0]['edu_leval']) > 5:
    #    job_list[0]['edu_leval'] = '本科'
    return job_list


# 教育经历改 (已完成)
def get_edu_list(lines):
    logging.info(lines)

    edu_list = [{"Time":None, "startTime":None, "endTime":None, "edu_name":None, "edu_domain":None, "edu_level":None}]
    regex_time = re.compile(r'((\d{4})[年\W]{1,2}(\d{1,2})[月\W]?[\d]{0,2})[至到\W]+((\d{4})[年\W]{1,2}(\d{1,2})[月\W]?)?([今])?|(\d{4})[至\W]+([\d今]{4})')
    regex_end = re.compile(r'毕业时间[\w\W]{0,5}(\d{4})[\W年]?(\d{0,2})[月\W]?')
    regex_level = re.compile(r'[大本专科硕博士研究生后]{2,}')
    regex_domain = re.compile(u'[\u4E00-\u9FA5]{2,10}', re.UNICODE)
    count = 0
    for line in lines:
        line = line.replace("学士","本科").replace("专业","").replace("学位","")
        for cell in re.split(r'[·\|\t]', line):
            if not cell.strip():
                continue
            flags = 0
            edu_time = regex_time.search(cell)
            edu_end_time = regex_end.search(cell)
            edu_level = regex_level.search(cell)
            edu_domain = regex_domain.search(cell)
            # 标准时间格式
            if edu_time:
                # 提交信息
                if edu_list[count].get("Time") and edu_list[count].get("edu_name"):
                    edu_list.append({"Time":None, "startTime":None, "endTime":None, "edu_name":None, "edu_domain":None, "edu_level":None})
                    count += 1
                edu_list[count]["startTime"] = '{:4d}-{:02d}'.format(int(edu_time.group(2)),int(edu_time.group(3)))
                # 年月日
                if edu_time.group(5) != None:
                    edu_list[count]["endTime"] = '{:4d}-{:02d}'.format(int(edu_time.group(5)),int(edu_time.group(6)))
                    edu_list[count]["Time"] = '{:4d}-{:02d}~{:4d}-{:02d}'.format(int(edu_time.group(2)),int(edu_time.group(3)),int(edu_time.group(5)),int(edu_time.group(6)))
                # 只有年
                elif edu_time.group(8) != None:
                    edu_list[count]["Time"] = '{:4d}~{:4d}'.format(int(edu_time.group(8)),int(edu_time.group(9)))
                    edu_list[count]["startTime"] = '{:4d}'.format(int(edu_time.group(8)))
                    edu_list[count]["endTime"] = '{:4d}'.format(int(edu_time.group(9)))
                # 至今类
                else:
                    edu_list[count]["endTime"] = edu_time.group(7)
                    edu_list[count]['Time'] = '{:4d}-{:02d}~{}'.format(int(edu_time.group(2)),int(edu_time.group(3)),edu_time.group(7))
                flags = 1
            # 只有毕业时间
            elif edu_end_time:
                # 提交信息
                if edu_list[count].get("endTime") and edu_list[count].get("edu_name"):
                    edu_list.append({"Time":None, "startTime":None, "endTime":None, "edu_name":None, "edu_domain":None, "edu_level":None})
                    count += 1
                # 年月
                if edu_end_time.group(2):
                    edu_list[count]["Time"] = '{:4d}-{:02d}~{:4d}-{:02d}'.format(int(edu_end_time.group(1))-3,int(edu_end_time.group(2)),int(edu_end_time.group(1)),int(edu_end_time.group(2)))
                    edu_list[count]["endTime"] = '{:4d}-{:02d}'.format(int(edu_end_time.group(1)),int(edu_end_time.group(2)))
                # 只有年
                elif edu_end_time.group(1):
                    edu_list[count]["Time"] = '{:4d}~{:4d}'.format(int(edu_end_time.group(1))-3,int(edu_end_time.group(1)))
                    edu_list[count]["endTime"] = '{:4d}'.format(int(edu_end_time.group(1)))
            # 学历
            if (not edu_list[count].get("edu_level")) and edu_level:
                edu_list[count]["edu_level"] = edu_level.group(0)
            # WordTag 识别 学校/专业
            for word, tag in ner_tag(cell):
                if (not edu_list[count].get("edu_name")) and (tag == "组织机构类_教育组织机构"):
                    edu_list[count]["edu_name"] = word.strip()
                    flags = 1
                elif (not edu_list[count].get("edu_domain")) and (tag in "_术语类型"):
                    edu_list[count]["edu_domain"] = word.strip()
                elif edu_list[count].get("edu_name") and edu_list[count].get("edu_domain"):
                    break
            # LAC 识别 学校
            else:
                for word, tag in ner(cell):
                    if (tag == "ORG"):
                        edu_list[count]["edu_name"] = word
                        flags = 1
                        break
            # 未识别成功时填充专业
            if (not (edu_level or flags or edu_list[count].get("edu_domain"))) and edu_domain:
                edu_list[count]["edu_domain"] = edu_domain.group(0)
    # 剔除时间不存在、学校不存在的列
    if (not edu_list[-1].get("Time")) or (not edu_list[-1].get("edu_name")):
        edu_list.pop()
    return edu_list


# 工作经历 （已完成）
# ner + 分词 机构信息，人物身份信息，时间  工作内容区分判断
# 其中，时间是判断是否下一份工作情况的主要标识符之一。字符数量
# 时间类 数量词
def get_job_list(lines):
    logging.info(lines)

    job_list = []
    re_txt = '\d{4,4}\040{0,2}.\d+\040{0,2}.?\040{0,2}[\-–至－\—～]{1,2}\040{0,2}\d{4,4}\040{0,2}.\040{0,2}\d+.?|\d{4,4}.\d+.?\040{0,2}[\-–－—]{0,2}\040{0,2}至?今|\d{4,4}.\d+.?\040{0,2}[\-–－]{1,2}\040{0,2}现在|\d{4,4}年\d+月\-\d{4,4}年\d+月|\d{4,4}年\d+月\-\~|\d{4,4}年\d+月[\-\~－]至今|\d{4,4}-\d+\040{0,2}[－\~至]\040{0,2}\d{4,4}-\d+|\d{4,4}-\d+\~|\d{4,4}-\d+\[~－]至今|\d{4,4}-\d+\040{0,2}至今'
    nums = []
    for i in range(len(lines)):
        #print(lines[i])
        #print(lines[i], re.findall(re_txt, lines[i]), re.findall('\||\040{1,}', lines[i]))
        if re.findall(re_txt, lines[i].replace(' ', '')) and re.findall('\||\040{1,}', lines[i]):
            nums.append(i)
            continue
        if re.findall(re_txt, lines[i].replace(' ', '')[:20]):
            nums.append(i)
            continue
        if len(lines[i].strip().replace(' ', '')) > 50:
            continue

        
        year_list = re.findall('19\d{2,2}.\d{1,2}|20\d{2,2}.\d{1,2}', lines[i])
        if len(year_list) >= 2:
            nums.append(i)
        elif len(year_list) == 1 and '至今' in lines[i]:
            nums.append(i)
    nums.append(len(lines))
    # logging.info(nums)
    logging.info('get_job_list :{}'.format(nums))
    for i in range(1, len(nums[:])):
        job_dict = {'job_time':'', 'job_leval':'','job_company':'','job_content':''}
        data_list = lines[nums[i-1]:nums[i]]
        if '' in data_list:
            data_list.remove('')
        org = ''
        person_professor_list = []
        org_index = -1
        end_index = 3
        job_time = re.findall(re_txt, data_list[0])
        if not job_time:
            year_list = re.findall('19\d{2,2}.\d{1,2}|20\d{2,2}.\d{1,2}', data_list[0])
            if len(year_list) >= 2:
                job_time = ['-'.join(year_list)]
            elif len(year_list) == 1 and '至今' in lines[i]:
                job_time = [year_list[0] + '-' + '至今']

        if not job_time:
            regex = re.compile(r'((\d{4})[年\W]+(\d{1,2})[\W]?[\w]?)[至到\W]+((\d{4})[年\W]+(\d{1,2})[\W]?[\w]?)?([今])?')
            job_time = [re.search(regex, data_list[0]).group(0)]

        job_dict['job_time'] = job_time[0]
        _nums = re.findall('\d+', job_dict['job_time'])
        #print(_nums)
        if len(_nums) >= 4:
            job_dict['job_time'] = '%s-%02d~%s-%02d'%(_nums[0], int(_nums[1]), _nums[2], int(_nums[3]))
        elif len(_nums) == 2:
            job_dict['job_time'] = '%s-%02d~%s'%(_nums[0], int(_nums[1]), '至今')
        if re.findall('\d', job_time[0]):
            job_time[0] = job_time[0][:-1]
        data_list[0] = re.sub(job_time[0], '', data_list[0])
        data_list[0] = data_list[0].strip()
        ner_list = []
        for i in range(len(data_list[:3])):
            if '工作' in data_list[i][:4] and (re.findall('：|\:', data_list[i])):
                end_index = i
                break
            if not re.findall('\040|\||/', data_list[i]) and org:
                end_index = i
                break
            if len(data_list[i]) > 80:
                end_index = i
                break
            if data_list[i]:
                ner_data = ner_tag(data_list[i].strip())
            else:
                continue

            ner_list.append(ner_data)
            for x in ner_data:
                if x[1] == '人物类_概念' and len(x[0]) > 2:
                    person_professor_list.append(x[0].strip())
                    
                elif x[1] == '组织机构类_企事业单位' or x[1] == '组织机构类_教育组织机构':
                    if not org:
                        org = re.split('\040|\|/', x[0].strip())[0]
                        org_index = i
        if not org:
            for i in range(len(ner_list)):
                ner_data = ner_list[i]
                for x in ner_data:
                    if x[1] == '组织机构类':
                        org = re.split('\040|\|/', x[0].strip())[0]
                        break
        if not person_professor_list:
            for i in range(len(ner_list)):
                ner_data = ner_list[i]
                for x in ner_data:
                    if x[1] == '人物类_概念':
                        person_professor_list = [re.split('\040|\|/', x[0].strip())[0]]
                        break
        data_line = ' '.join(data_list[:end_index])
        data_line = re.sub('\||/', ' ', data_line)
        _list_data = re.split('\040+',data_line)
        if len(_list_data) == 1:
            end_index = 0
        if not person_professor_list:
            for x in range(len(_list_data)):
                if re.findall('经理|工程师|会计|董事长|总监|秘书|主管|处长|局长|主任|讲师|教授', _list_data[x][-4:]):
                    person_professor_list.append(_list_data[x])


        if not org:
            for x in range(len(_list_data)):
                if len(_list_data[x]) < 4:
                    _list_data[x] = ''
                elif person_professor_list and re.findall('|'.join(person_professor_list), _list_data[x]):
                    _list_data[x] = ''
                elif '经理' == _list_data[x][-2:]:
                    _list_data[x] = ''
            for x in range(len(_list_data)):
                if _list_data[x]:
                    org = _list_data[x]
                    break
        if not person_professor_list:
            for x in range(len(_list_data)):
                if org in _list_data[x]:
                    for j in range(x+1, len(_list_data)):
                        if _list_data[j]:
                            person_professor_list = [_list_data[j]]
                            break
                    break

        #print(org, person_professor_list, job_time)
        job_dict['job_company'] = org
        job_dict['job_leval'] = ' '.join(person_professor_list)
        job_dict['job_content'] = re.sub('工工作作内内容容::|工工作作内内容容：：|工工作作内内容容', '工作内容：', ''.join(data_list[end_index:]))
        job_dict['job_content'] = re.sub('/', '-', job_dict['job_content'])

        

        job_list.append(job_dict)
        continue
        if len(data_list) > 1 and data_list[1] and  data_list[1][-1] == '|':# and data_list[0] and data_list[0][-1] != '|':
            data_list[0] = data_list[0] + data_list[1]
            data_list[1] = ''
        elif len(data_list) > 2 and data_list[2] and  data_list[2][-1] == '|' and data_list[0][-1] != '|' and '|' in str(data_list[0]) and data_list[1] and  data_list[1][-1] != '|':
            data_list[0] = data_list[0] + data_list[1] + data_list[2]
            data_list[1] = '' 
            data_list[2] = ''
        elif len(data_list) > 1 and data_list[1] and '工作职责：' in data_list[2]:
            data_list[0] = data_list[0] + data_list[1]
            data_list[1] = ''
        elif len(data_list) > 1 and '工作职责：' in data_list[3]:
            data_list[0] = data_list[0] + data_list[1] + data_list[2]
            data_list[1] = '' 
            data_list[2] = ''
        job_time = re.findall(re_txt, data_list[0])
        job_dict['job_time'] = job_time[0]
        _nums = re.findall('\d+', job_dict['job_time'])
        #print(_nums)
        if len(_nums) >= 4:
            job_dict['job_time'] = '%s-%02d~%s-%02d'%(_nums[0], int(_nums[1]), _nums[2], int(_nums[3]))
        elif len(_nums) == 2:
            job_dict['job_time'] = '%s-%02d~%s'%(_nums[0], int(_nums[1]), '至今')
        data_list[0] = re.sub(job_time[0], '', data_list[0])
        data_list[0] = data_list[0].strip()
        data_list[0] = re.sub('历任：', '   ', data_list[0])
        _list = data_list[0].split('|')
        if len(_list) == 1:
            __list = re.split('\040{2,}', data_list[0])
            #print(__list)
            job_dict['job_leval'] = __list[1].strip()
            job_dict['job_company'] = __list[0].strip()
        else:
            job_dict['job_leval'] = _list[0].strip()
            job_dict['job_company'] = _list[1].strip()
        if '职级：' in data_list[1:]:
            data_list.remove('职级：')
        job_dict['job_content'] = re.sub('工工作作内内容容::|工工作作内内容容：：|工工作作内内容容', '工作内容：', ''.join(data_list[1:]))
        job_dict['job_content'] = re.sub('/', '-', job_dict['job_content'])
        #print(job_dict)
        job_list.append(job_dict)
    return job_list


# 项目经历 (已完成)(弃用)
# 项目名称未知
def get_pro_list_old(lines):
    logging.info(lines)

    pro_list = [{"Time":None,"startTime":None,"endTime":None,"pro_name":None,"job_leval":None,"job_company":None,"content":None,},]
    regex = re.compile(r'((\d{4})[年\W]+(\d{1,2})[\W]?[\w]?)[至到\W]+((\d{4})[年\W]+(\d{1,2})[\W]?[\w]?)?([今])?')
    re_con = re.compile(r'负责内容(.*?)')
    re_na = re.compile(r'\W(.*?项目)\W')
    count = 0
    for line in lines:
        regex_time = regex.search(line)
        regex_content = re_con.search(line)
        regex_name = re_na.search(line)
        if regex_time:
            if pro_list[count].get("Time"):
                pro_list.append({"Time":None,"startTime":None,"endTime":None,"pro_name":None,"job_leval":None,"job_company":None,"content":None,})
                count += 1
            pro_list[count]["startTime"] = '{:4d}-{:02d}'.format(int(regex_time.group(2)),int(regex_time.group(3)))
            if regex_time.group(5) != None:
                pro_list[count]["endTime"] = '{:4d}-{:02d}'.format(int(regex_time.group(5)),int(regex_time.group(6)))
                pro_list[count]["Time"] = '{:4d}-{:02d}~{:4d}-{:02d}'.format(int(regex_time.group(2)),int(regex_time.group(3)),int(regex_time.group(5)),int(regex_time.group(6)))
            else:
                pro_list[count]["endTime"] = regex_time.group(7)
                pro_list[count]['Time'] = '{:4d}-{:02d}~{}'.format(int(regex_time.group(2)),int(regex_time.group(3)),regex_time.group(7))
        elif regex_name and (not pro_list[count].get("job_name")):
            pro_list[count]["pro_name"] = regex_name.group()
        elif pro_list[count].get("content"):
            pro_list[count]["content"] += line
        else:
            try:
                for word, tag in ner_tag(line):
                    if (not pro_list[count].get("job_leval")) and (tag == "人物类_概念"):
                        pro_list[count]["job_leval"] = word
                    if (not pro_list[count].get("job_company")) and (tag in "组织机构类_企事业单位"):
                        pro_list[count]["job_company"] = word
            except Exception as e:
                logging.error(e)
            pro_list[count]["content"] = line
    return pro_list


# 项目经历 (UIE)
def get_pro_list(lines):
    logging.info(lines)

    starts = []
    # 时间查找
    for index, line in enumerate(lines):
        if re.search(r'\d{4}', line):
            starts.append(index)

    # 简单筛选
    count = len(starts)
    c = (starts[-1] - starts[0])/count
    for i in range(count-1):
        if (starts[i+1]-starts[i] < c/2):
            starts[i+1] = starts[i]
    # 合并
    pro_list = []
    pros = {}
    index = 0
    for i in range(len(lines)):
        if i in starts:
            index = i
            pros[index] = [lines[i], []]
            pros[index][1].append(lines[i])
        elif not pros:
            continue
        else:
            pros[index][0] += lines[i]
            pros[index][1].append(lines[i])
    # 提取
    for key in pros.keys():
        info = pro_ie(pros[key][0])
        src = pros[key][1]
        for rst in info:
            if not rst.get("时间") or not rst.get("项目名称"):
                continue
            rst["工作内容"] = [{"text":""}]
            logging.info(rst)
            for l in src:
                if rst["时间"][0]["text"] in l:
                    continue
                else:
                    rst["工作内容"][0]["text"] += l
            for key in rst.keys():
                if key == "时间":
                    time_list = [None, None, None, None, None, None]
                    tim_list = re.findall(r'\d+', rst["时间"][0]["text"])
                    i = 0
                    for t in tim_list:
                        if (len(t) == 4) and (i != 0):
                            i = 3
                            time_list[i] = t
                        else:
                            time_list[i] = t
                        i += 1
                else:
                    continue
                if time_list[3] is not None:
                    if time_list[4] is not None:
                        rst["时间"][0]["text"] = "{:4d}-{:02d}~{:4d}-{:02d}".format(int(time_list[0]),int(time_list[1]),int(time_list[3]),int(time_list[4]))
                    else:
                        rst["时间"][0]["text"] = "{:4d}~{:4d}".format(int(time_list[0]),int(time_list[3]))
                else:
                    if time_list[1] is not None:
                        rst["时间"][0]["text"] = "{:4d}-{:02d}~至今".format(int(time_list[0]),int(time_list[1]))
                    else:
                        rst["时间"][0]["text"] = "{:4d}~至今".format(int(time_list[0]))
            pro_list.extend([{key:rst[key][0]["text"] for key in rst.keys()} for rst in info])
    return pro_list


# 培训经历 (已完成)
# ner + 分词 （机构名） 培训项目  时间
def get_cultivate_list(lines):
    logging.info(lines)

    job_list = []
    re_txt = '\d{4,4}.\d{1,2}.?\040{0,2}[\-–至－\—～]\040{0,2}\d{4,4}.\d{1,2}[月]?|\d+\.\d+\-至今|\d+年\d+月\-\d+年\d+月|\d+年\d+月\-\~|\d+年\d+月[\-\~]至今|\d+-\d+\040{0,2}[\~至]\040{0,2}\d+-\d+|\d+-\d+\~|\d+-\d+\~至今|\d+-\d+\040{0,2}至今|^\d{4,4}.\d{1,2}|\d{4,4}.'
    re_txt_1 =  '\d{4,4}.\d{1,2}.?\040{0,2}[\-–至－\—～]\040{0,2}\d{4,4}.\d{1,2}[月]?|\d+\.\d+\-至今|\d+年\d+月\-\d+年\d+月|\d+年\d+月\-\~|\d+年\d+月[\-\~]至今|\d+-\d+\040{0,2}[\~至]\040{0,2}\d+-\d+|\d+-\d+\~|\d+-\d+\~至今|\d+-\d+\040{0,2}至今'
    nums = []
    for i in range(len(lines)):
        if re.findall(re_txt, lines[i].replace(' ', '')) and re.findall('\||\040{1,}', lines[i]):
            nums.append(i)
            continue
        if re.findall(re_txt, lines[i].replace(' ', '')[:20]):
            nums.append(i)
        if len(lines[i].strip().replace(' ', '')) > 50:
            continue
    nums.append(len(lines))
    year_dict = {18:4, 17:3,20:3,19:3,21:2,22:1}
    for i in range(1, len(nums[:])):
        job_dict = {'cultivate_time':'', 'cultivate_time_beg':'', 'cultivate_time_end':'', 'cultivate_name':'','cultivate_leval':'','cultivate_content':''}
        data_list = lines[nums[i-1]:nums[i]]
        data_line = ' '.join(data_list)
        data_line = re.sub('[\|\t]', ' ', data_line)
        data_line = re.sub('-{3,}', '', data_line)
        ner_data = ner(''.join(data_list[:2]))
        org = ''
        time_list = []
        for _ in ner_data:
            if _[1] == 'ORG' and not org:
                org = _[0].strip()
            elif _[1] == 'TIME' and len(_[1]) >= 4:
                time_list.append(_[0])
            #TIME
        logging.info(data_line)
        _list_data = re.split('\040+', data_line)
        top_level = 22
        end_index = 0
        remove_list = []
        if len(_list_data) <= 2:
            end_index = 0
            #continue

        job_time = re.findall(re_txt_1, data_list[0])
        if job_time:
            job_dict['cultivate_time'] = job_time[0]
            data_list[0] = re.sub(job_time[0], '', data_list[0])
        else:
            job_dict['cultivate_time'] = ''
        
        for t in time_list:
            data_list[0] = re.sub(t, '', data_list[0])

        _list = data_list[0].split('|')
        if len(_list) >= 2:
            job_dict['cultivate_name'] = _list[0].strip()
            job_dict['cultivate_leval'] = _list[1].strip()
            end_index = 1

        _nums = re.findall('\d+', job_dict['cultivate_time'])
        if len(_nums) >= 4:
            job_dict['cultivate_time_beg'] = '%s-%02d'%(_nums[0], int(_nums[1]))
            job_dict['cultivate_time_end'] = '%s-%02d'%(_nums[2], int(_nums[3]))
            job_dict['cultivate_time'] = '%s-%02d~%s-%02d'%(_nums[0], int(_nums[1]), _nums[2], int(_nums[3]))
        elif len(_nums) == 2:
            job_dict['cultivate_time'] = '%s-%02d~%s'%(_nums[0], int(_nums[1]), '至今')
            job_dict['cultivate_time_beg'] = '%s-%02d'%(_nums[0], int(_nums[1]))
            job_dict['cultivate_time_end'] = '%s'%('至今')
        elif len(time_list) == 2:
            nums_1 = re.findall('\d+', time_list[0])
            nums_2 = re.findall('\d+', time_list[1])
            nums_1.append('09')
            nums_2.append('07')

            job_dict['cultivate_time_beg'] = '%s-%02d'%(nums_1[0], int(nums_1[1]))
            job_dict['cultivate_time_end'] = '%s-%02d'%(nums_2[0], int(nums_2[1]))
            job_dict['cultivate_time'] = '%s-%02d~%s-%02d'%(nums_1[0], int(nums_1[1]), nums_2[0], int(nums_2[1]))
            
        elif len(time_list) == 1:
            _nums = re.findall('\d+', time_list[0])
            if '获得' in data_list[0]:
                _nums.append('01')
                _nums.insert(0, '01')
                _nums.insert(0, str(int(_nums[1]) - year_dict[top_level]))
                job_dict['cultivate_time'] = '%s-%02d~%s-%02d'%(_nums[0], int(_nums[1]),  _nums[2], int(_nums[3]))
                job_dict['cultivate_time_beg'] = '%s-%02d'%(_nums[0], int(_nums[1]))
                job_dict['cultivate_time_end'] = '%s-%02d'%(_nums[2], int(_nums[3]))
            else:
                _nums.append('01')
                job_dict['cultivate_time'] = '%s-%02d~%s'%(_nums[0], int(_nums[1]), '至今')
                job_dict['cultivate_time_beg'] = '%s-%02d'%(_nums[0], int(_nums[1]))
                job_dict['cultivate_time_end'] = '%s'%('至今')
    
        job_dict['cultivate_content'] = re.sub('培培训训内内容容：：|培培训训内内容容::|培培训训内内容容', '培训内容：', ''.join(data_list[end_index:]))
        if not job_dict['cultivate_name']:
            job_dict['cultivate_name'] = org
        logging.info(job_dict)
        job_list.append(job_dict)
        continue
    '''
    #print(nums)
    for i in range(1, len(nums[:])):
        job_dict = {'cultivate_time':'', 'cultivate_name':'','cultivate_leval':'','cultivate_content':''}
        data_list = lines[nums[i-1]:nums[i]]
        if '' in data_list:
            data_list.remove('')
        if len(data_list) > 1 and data_list[1] and  data_list[1][-1] == '|' and data_list[0][-1] != '|':
            data_list[0] = data_list[0] + data_list[1]
            data_list[1] = ''
        job_time = re.findall(re_txt_1, data_list[0])
        job_dict['cultivate_time'] = job_time[0]
        _nums = re.findall('\d+', job_dict['cultivate_time'])
        if len(_nums) >= 4:
            job_dict['cultivate_time'] = '%s-%02d~%s-%02d'%(_nums[0], int(_nums[1]), _nums[2], int(_nums[3]))
        elif len(_nums) == 2:
            job_dict['cultivate_time'] = '%s-%02d~%s'%(_nums[0], int(_nums[1]), '至今')
        data_list[0] = re.sub(job_time[0], '', data_list[0])
        _list = data_list[0].split('|')
        if len(_list) >= 2:
            job_dict['cultivate_name'] = _list[0].strip()
            job_dict['cultivate_leval'] = _list[1].strip()
            job_dict['cultivate_content'] = re.sub('培培训训内内容容|培培训训内内容容：：|培培训训内内容容::', '培训内容：', ''.join(data_list[1:]))
        else:
            job_dict['cultivate_content'] = re.sub('培培训训内内容容|培培训训内内容容：：|培培训训内内容容::', '培训内容：', ''.join(data_list[0:]))
        #print(job_dict)
    '''
    return job_list


# 语言能力
def get_lag_list(lines):
    logging.info(lines)

    job_list = []
    re_lan = re.compile(r'(\w+[语话])')
    lag_dict = {'lag_name':'', 'lag_leval':""}
    for l in lines:
        if not l.strip():
            continue
        lag_name = re.search(re_lan, l)
        if lag_name and lag_name.group(1):
            if lag_dict['lag_name']:
                job_list.append(lag_dict)
            lag_dict['lag_name'] = lag_name.group(1)
    return job_list


# 家庭情况（弃用）
def get_fam_list(lines):
    job_list = []
    fam_dict = {}
    for l in lines:
        if not l.strip():
            continue
        ls = l.split('|')
        if len(ls) == 1:
            continue
        fam_dict = {'fam_name':"",'fam_company':"",'fam_lable':"","fam_status":"", 'fam_job':""}
        fam_dict["fam_lable"] = ls[0].strip()
        fam_dict["fam_name"] = ls[1].strip()
        flag = 0
        if re.findall('\d岁|\d{4,5}', ls[2]):
            flag = 1
        fam_dict["fam_company"] = ls[flag+2].strip()
        fam_dict["fam_job"] = ls[flag+3].strip()
        fam_dict["fam_status"] = ls[flag+4].strip()
        #print(fam_dict)
        job_list.append(fam_dict)
    return job_list


# 证书情况  时间+证书名称 （已完成）
def get_cet_list_old(lines):
    logging.info(lines)

    job_list = []
    re_txt = '\d+年\d+月|\d+-\d+|\d+\.\d+'
    lines_word = ' '.join(lines)
    lines = re.findall('\d+年\d+月|\d+-\d+|\d+\.\d+', lines_word)
    nums = []
    for x in range(len(lines) - 1):
        
        _index = lines_word.index(lines[x])
        _end_index = lines_word.index(lines[x+1])
        l = lines_word[_index : _end_index]
        if not l.strip():
            continue
        lines_word = lines_word[_end_index:]
        job_time = re.findall(re_txt, l)
        cet_dict = {'cet_name':'','cet_time':""}
        if job_time:
            cet_dict['prize_time'] = job_time[0]
            l = re.sub(job_time[0], '', l)
        else:
            continue
        ls = re.split('\||\040+|\t+', l)
        logging.info(ls)
        for l in ls:
            if len(l) <= 3:
                continue
            cet_dict['prize_name'] = l.strip()
            break
        job_list.append(cet_dict)
    return job_list


# 证书情况  时间+证书名称 （UIE已完成）
def get_cet_list(lines):
    logging.info(lines)
    cet_list = []
    for line in lines:
        info = cet_ie(line)
        cet_list.extend([{key:rst[key][0]["text"] for key in rst.keys()} for rst in info if rst.get("证书")])
    return cet_list


# 获奖情况  时间+获奖名称 （已完成）
def get_prize_list_old(lines):
    logging.info(lines)

    job_list = []
    re_txt = '\d+年\d+月|\d+-\d+|\d{4,4}.\d{1,2}'
    lines_word = ' '.join(lines)
    lines = re.findall('\d+年\d+月|\d{4,4}-\d+|\d{4,4}.\d{1,2}', lines_word)
    nums = []
    for x in range(len(lines) - 1):
        _index = lines_word.index(lines[x])
        _end_index = lines_word.index(lines[x+1])
        l = lines_word[_index : _end_index]
        if not l.strip():
            continue
        lines_word = lines_word[_end_index:]
        job_time = re.findall(re_txt, l)
        cet_dict = {'prize_name':'','prize_time':""}
        if job_time:
            cet_dict['prize_time'] = job_time[0]
            l = re.sub(job_time[0], '', l)
        else:
            continue
        ls = re.split('\||\040+|\t+', l)
        logging.info(ls)
        for l in ls:
            if len(l) <= 3:
                continue
            cet_dict['prize_name'] = l.strip()
            break
        logging.info(cet_dict)
        job_list.append(cet_dict)
    return job_list


# 获奖情况  时间+获奖名称 （UIE已完成）
def get_prize_list(lines):
    logging.info(lines)
    prize_list = []
    for line in lines:
        info = prize_ie(line)
        prize_list.extend([{key:rst[key][0]["text"] for key in rst.keys()} for rst in info if rst.get("奖项")])
    return prize_list


# 返回其他信息
def get_other_list(lines):
    other_list = []
    other_list.append("\n".join(lines))
    return other_list


# Linux doc 文件处理
def doc2pdf_linux(docPath, pdfPath):
    """
    允许的文档格式：doc，docx
    仅在linux平台下可以
    需要在linux中下载好libreoffice
    """
    #  注意cmd中的libreoffice要和linux中安装的一致
    cmd = 'libreoffice6.3 --headless --convert-to pdf'.split() + [docPath] + ['--outdir'] + [pdfPath]
    # cmd = 'libreoffice6.2 --headless --convert-to pdf'.split() + [docPath]
    p = subprocess.Popen(cmd, stderr=subprocess.PIPE, stdout=subprocess.PIPE)
    p.wait(timeout=30)  # 停顿30秒等待转化
    stdout, stderr = p.communicate()
    if stderr:
        raise subprocess.SubprocessError(stderr) 


# Windows doc 文件处理
def doc2pdf_win(docPath, pdfPath):
    console.print(pdfPath+'/'+os.path.splitext(os.path.split(docPath)[-1])[0] + '.pdf')
    import win32com
    from win32com.client import DispatchEx, constants
    word = DispatchEx("Word.Application")  #内部方法
    word.Visible = 1  # 后台运行，不显示
    word.DisplayAlerts = 0  # 不警告
    doc = word.Documents.Open(docPath) #转换源文件
    doc.SaveAs(pdfPath+'/'+os.path.splitext(os.path.split(docPath)[-1])[0] + '.pdf', FileFormat=17) #txt=4,html=10,docx=16,pdf=17 #新文件
    doc.Close() #关闭
    word.Quit() #退出


# doc 文件处理
def doc2pdf(docPath, pdfPath, system):
    """
    注意使用绝对路径
    pdf的生成只写路径，不写名字
    """
    docPathTrue = os.path.abspath(docPath)  # bugfix - searching files in windows/system32
    if system == "Linux":
        return doc2pdf_linux(docPathTrue, pdfPath)
    if system == "Windows":
        return doc2pdf_win(docPathTrue, pdfPath)


# txt 纯文本解析(已完成)
def parse_txt(path, save_dir):
    with open(path, 'r', encoding='utf-8') as fp:
        data = fp.read()
    global block, block_rev
    chun = 1
    page = {1: []}
    if len(data.split("\n")) <= 2:
        for line in data.split("\n"):
            line = line.replace("\xa0", "").replace("【","").replace("】","").replace("教育/培训","教育经历").strip()
            for word in line.split():
                if word in block.keys():
                    chun = block[word]
                    page[chun] = []
                elif word:
                    page[chun].append(word)
    else:
        for line in data.split("\n"):
            line = line.replace("\xa0", "").replace("【","").replace("】","").replace("教育/培训","教育经历")
            regex = re.compile(u'[\u3000]+',re.UNICODE)
            line = regex.sub('', line.strip())
            if line in block.keys():
                chun = block[line]
                page[chun] = []
            elif line:
                page[chun].append(line)

    result_data = []
    for key in page.keys():
        for index, func in zip([1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], [get_base_info, get_job_intention, get_edu_list, get_job_list, get_pro_list, get_other_list, get_other_list, get_other_list, get_lag_list, get_cet_list, get_prize_list, get_cultivate_list]):
            if key == index:
                result_data.append({block_rev[index]:func(page[index])})
    filename = os.path.splitext(os.path.split(path)[-1])[0]+'.json'
    with open(os.path.join(save_dir, filename), 'w', encoding="utf-8") as fp:
            json.dump({"result":result_data}, fp, indent=4, ensure_ascii=False)


# 纯文本 word 解析
def read_from_word(doc, path, save_dir):
    para_text = []
    for para in doc.paragraphs:
        para_text.append(para.text)

    global block, block_rev

    chun = 1
    page = {1: []}
    for line in para_text:
        regex = re.compile(u'[\uF000-\uF0FF]+',re.UNICODE)
        line = regex.sub('', line)
        if line in block.keys():
            chun = block[line]
            page[chun] = []
        elif line:
            page[chun].append(line)

    result_data = []
    for key in page.keys():
        for index, func in zip([1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], [get_base_info, get_job_intention, get_edu_list, get_job_list, get_pro_list, get_other_list, get_other_list, get_other_list, get_lag_list, get_cet_list, get_prize_list, get_cultivate_list]):
            if key == index:
                result_data.append({block_rev[index]:func(page[index])})
    filename = os.path.splitext(os.path.split(path)[-1])[0]+'.json'
    with open(os.path.join(save_dir, filename), 'w', encoding="utf-8") as fp:
            json.dump({"result":result_data}, fp, indent=4, ensure_ascii=False)


# 提取 word 表格(已完成)
def check_word(path, save_dir):
    doc = Document(path)
    tables = doc.tables

    if not tables:
        logging.info("this is raw text")
        read_from_word(doc, path, save_dir=save_dir)
    logging.info("this is a Table")

    global block
    with open("resources/keys.json", "r", encoding="utf-8") as fp:
        prk = json.load(fp)
    chun = 1
    page = {1: []}
    regex = re.compile(r'(\(\w{2,8}\))?(（\w{2,8}）)?')
    for table in tables:
        lo = {} # 存储每一行去重后的数据
        for row in range(0, len(table.rows)):
            row_list = []
            for col in range(0, len(table.row_cells(row))):  # 提取row行的全部列数据
                if len(''.join(table.cell(row, col).text)) <= 20:
                    row_list.append(re.sub(r'(\w)\n', r'\1', table.cell(row, col).text))
                else:
                    row_list.append(regex.sub("", table.cell(row, col).text.replace(" ","").replace("：", ":").replace("学历\n学位","学历学位"))) # 去除字符串中的特殊字符，并添加到临时列表中
            lo[row] = (sorted(set(row_list), key=row_list.index)) # 在不变顺序的前提下，去除List中的重复项
        # 去除空项
        for key in list(lo.keys()):
            if "" in lo[key]:
                lo[key].remove("")
            if not lo[key]:
                lo.pop(key)


        for _, line in lo.items():
            if (line[0] in block.keys()) or (line[0] in prk.keys()):
                # 包含大类目名
                if line[0] in block.keys():
                    # 指向当前类目
                    chun = block[line[0]]
                    if not page.get(chun):
                        page[chun] = []
                    # 去除类目名
                    line = '\n'.join(line[1:])
                # 包含小类目
                elif line[0] in prk.keys():
                    # 指向当前类目
                    chun = prk[line[0]]
                    if not page.get(chun):
                        page[chun] = []
                    # 不去除
                    line = '\n'.join(line)
            else:
                line = '\n'.join(line)
            # 标准化小类目
            for k in prk.keys():
                line = line.replace(k+"\n", k+"：")
            page[chun].extend(line.split())

    result_data = []
    for key in page.keys():
        for index, func in zip([1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], [get_base_info, get_job_intention, get_edu_list, get_job_list, get_pro_list, get_other_list, get_other_list, get_other_list, get_lag_list, get_cet_list, get_prize_list, get_cultivate_list]):
            if key == index:
                result_data.append({block_rev[index]:func(page[index])})
    filename = os.path.splitext(os.path.split(path)[-1])[0]+'.json'
    with open(os.path.join(save_dir, filename), 'w', encoding="utf-8") as fp:
            json.dump({"result":result_data}, fp, indent=4, ensure_ascii=False)


# pdf 解析句子(已完成)
def parse_line_layout(layout, b):
    texts = []
    """解析页面内容，一行一行的解析"""
    # bbox:
    # x0：从页面左侧到框左边缘的距离。
    # y0：从页面底部到框的下边缘的距离。
    # x1：从页面左侧到方框右边缘的距离。
    # y1：从页面底部到框的上边缘的距离
    for textbox in layout:
        if isinstance(textbox, LTTextBox) or isinstance(textbox, LTTextLine):
            for char in textbox:
                if isinstance(char, LTTextLineHorizontal):
                    texts.append([char.bbox[0], char.bbox[3], char.get_text().strip()])
    # 按行排序
    texts.sort(key=lambda x:-x[1])
    global block, block_rev

    chun = b
    page = {chun: []}
    for  _, _, line in texts:
        regex = re.compile(u'[\u007F|\u25A0|\u00B7|\uF000-\uF0FF]+',re.UNICODE)
        line = regex.sub('', line)
        regex_tips = re.compile(r'(\(.*?\))?(（.*?）)?')
        # line = regex_tips.sub('', line)
        line = line.strip()
        if regex_tips.sub('', line).strip() in block.keys():
            chun = block[regex_tips.sub('', line).strip()]
            page[chun] = []
        elif line:
            page[chun].append(line)
    return page, chun


# pdf 样式解析(已完成)
def read_from_pdf(path, save_dir):
    result = {}
    global block_rev
    with open(path, 'rb') as in_file:
        parser = PDFParser(in_file)  # 用文件对象来创建一个pdf文档分析器
        doc: PDFDocument = PDFDocument(parser)  # 创建pdf文档
        rsrcmgr = PDFResourceManager()  # 创建PDF，资源管理器，来共享资源
        # 创建一个PDF设备对象
        laparams = LAParams()
        device = PDFPageAggregator(rsrcmgr, laparams=laparams)
        # 创建一个PDF解释其对象
        interpreter = PDFPageInterpreter(rsrcmgr, device)
        # 循环遍历列表，每次处理一个page内容
        # doc.get_pages() 获取page列表
        interpreter = PDFPageInterpreter(rsrcmgr, device)
        # 处理文档对象中每一页的内容
        # 循环遍历列表，每次处理一个page的内容
        b = 1
        for page in PDFPage.create_pages(doc):
            logging.debug('================ 新页面 ================')
            interpreter.process_page(page)
            layout = device.get_result()
            r, b = parse_line_layout(layout, b)
            for key in r.keys():
                if result.get(key):
                    result[key].extend(r[key])
                else:
                    result[key] = r[key]
        result_data = []
        for key in result.keys():
            for index, func in zip([1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], [get_base_info, get_job_intention, get_edu_list, get_job_list, get_pro_list, get_other_list, get_other_list, get_other_list, get_lag_list, get_cet_list, get_prize_list, get_cultivate_list]):
                if key == index:
                    result_data.append({block_rev[index]:func(result[index])})

        filename = os.path.splitext(os.path.split(path)[-1])[0]+'.json'
        with open(os.path.join(save_dir, filename), 'w', encoding="utf-8") as fp:
            json.dump({"result":result_data}, fp, indent=4, ensure_ascii=False)


# pdf 表格解析 (已完成)
def parse_table_from_pdf(path, save_dir):
    global block, block_rev
    lo = {}
    with pdfplumber.open(path) as pdf:
        for page in pdf.pages:
            for table in page.extract_tables():
                for line in table:
                    row_list = []
                    for word in line:
                        row_list.append(word)
                    lo[len(row.keys())] = row_list
    # 去除空项
    for key in list(lo.keys()):
        if "" in lo[key]:
            lo[key].remove("")
        if not lo[key]:
            lo.pop(key)

    for _, line in lo.items():
        if (line[0] in block.keys()) or (line[0] in prk.keys()):
            # 包含大类目名
            if line[0] in block.keys():
                # 指向当前类目
                chun = block[line[0]]
                if not page.get(chun):
                    page[chun] = []
                # 去除类目名
                line = '\n'.join(line[1:])
            # 包含小类目
            elif line[0] in prk.keys():
                # 指向当前类目
                chun = prk[line[0]]
                if not page.get(chun):
                    page[chun] = []
                # 不去除
                line = '\n'.join(line)
        else:
            line = '\n'.join(line)
        # 标准化小类目
        for k in prk.keys():
            line = line.replace(k+"\n", k+"：")
        page[chun].extend(line.split())

    result_data = []
    for key in page.keys():
        for index, func in zip([1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], [get_base_info, get_job_intention, get_edu_list, get_job_list, get_pro_list, get_other_list, get_other_list, get_other_list, get_lag_list, get_cet_list, get_prize_list, get_cultivate_list]):
            if key == index:
                result_data.append({block_rev[index]:func(page[index])})
    filename = os.path.splitext(os.path.split(path)[-1])[0]+'.json'
    with open(os.path.join(save_dir, filename), 'w', encoding="utf-8") as fp:
            json.dump({"result":result_data}, fp, indent=4, ensure_ascii=False)


# 检测 pdf 格式 (已完成)
def check_pdf(path):
    """
    # 输入：
    # pdf 文件路径
    # 输出：
    # 文件包含元素 [Word, Table]
    """
    rst = []
    for page_layout in extract_pages(path):
        for element in page_layout:
            if isinstance(element, LTFigure):
                for cell in element:
                    if isinstance(cell, LTChar):
                        rst.append("Table")
                        break
            elif isinstance(element, LTTextContainer):
                rst.append("Word")
    return set(rst)


# 检测编码(已完成)
def decode_path(path):
    '''zipfile解压出现乱码，将乱码的路径编码为UTF8'''
    try:
        path_name = path.decode('utf-8')
    except:
        path_name = path.encode('437').decode('gbk')
        path_name = path_name.encode('utf-8').decode('utf-8')
    return path_name


# 检测传入格式(已完成)
def detection_type(path, system):
    tempdir = time.strftime("%Y_%m_%dT%H_%M_%S")
    os.mkdir(tempdir)
    # 传入 tar.gz 压缩文件
    if os.path.isfile(path) and path.endswith('.tar.gz'):
        tf = tarfile.open(path)
        tf.extractall('./cache/' + tempdir)
        tf.close()
        path = "./cache/" + tempdir
    # 传入 .zip .7z 压缩文件
    try:
        if os.path.isfile(path) and path.endswith('.zip'):
            ## 解压方式1：存在乱码
            # f = zipfile.ZipFile(file, mode='r')
            # f.extractall(target_dir)
            ## 解压方式2：防止乱码
            with ZipFile(path, allowZip64=True) as zf:
                # 排除目录文件
                print("zf.filelist", zf.filelist)
                file_iter = (filename for filename in zf.filelist if os.path.isfile(path))
                for filename in file_iter:
                    # 编码文件名称为 utf 格式
                    filename.filename = decode_path(filename.filename)  # 防止乱码的操作
                    zf.extract(filename, "./cache/" + tempdir)
            path = "./cache/" + tempdir
        elif os.path.isfile(path) and path.endswith('.7z'):  # .7z格式文件解压
            zf = py7zr.SevenZipFile(path, mode='r')
            zf.extractall("./cache/" + tempdir)
            path = "./cache/" + tempdir
    except Exception as e:
        logging.error(e)
    # 传入为 doc
    if os.path.isfile(path) and path.endswith('.doc'):
        doc2pdf(docPath = path, pdfPath = './pdf', system=system)
        newfile = './pdf/' + os.path.splitext(os.path.split(path)[-1])[0] + '.pdf'
        if os.path.exists(newfile):
            rst = check_pdf(newfile)
            if "Table" in rst:
                parse_table_from_pdf(newfile, save_dir=tempdir)
                pass
            if "Word" in rst:
                read_from_pdf(newfile, save_dir=tempdir)
    # 传入为 docx
    elif os.path.isfile(path) and path.endswith('.docx'):
        check_word(path, save_dir=tempdir)
    # 传入为 pdf
    elif os.path.isfile(path) and path.endswith('.pdf'):
        rst = check_pdf(path)
        if "Table" in rst:
            parse_table_from_pdf(path, save_dir=tempdir)
        if "Word" in rst:
            read_from_pdf(path, save_dir=tempdir)
    # 传入为 txt
    elif os.path.isfile(path) and path.endswith('.txt'):
        parse_txt(path, save_dir=tempdir)
    # 传入目录
    elif os.path.isdir(path):
        for filename in os.listdir(path):
            filename = os.path.join(path, filename)
            # 传入为 doc
            logging.info(filename)
            if filename.endswith('.doc') and not filename.startswith('.~'):
                doc2pdf(docPath = filename, pdfPath = './pdf', system=system)
                newfile = './pdf/' + os.path.splitext(os.path.split(filename)[-1])[0] + '.pdf'
                if os.path.exists(newfile):
                    rst = check_pdf(newfile)
                    if "Table" in rst:
                        parse_table_from_pdf(newfile, save_dir=tempdir)
                        pass
                    if "Word" in rst:
                        read_from_pdf(newfile, save_dir=tempdir)
            # 传入为 docx
            elif os.path.isfile(filename) and filename.endswith('.docx'):
                check_word(filename, save_dir=tempdir)
            # 传入为 pdf
            if os.path.isfile(filename) and filename.endswith('.pdf'):
                rst = check_pdf(filename)
                if "Table" in rst:
                    parse_table_from_pdf(filename, save_dir=tempdir)
                    pass
                if "Word" in rst:
                    read_from_pdf(filename, save_dir=tempdir)
            # 传入为 txt
            elif os.path.isfile(filename) and filename.endswith('.txt'):
                parse_txt(filename, save_dir=tempdir)
    # 结果返回
    for file in os.listdir(tempdir):
        filename = os.path.join(tempdir, file)
        with open(filename, "r", encoding="utf-8") as ff:
            rst = json.load(ff)
        console.print(rst, style="red", justify="left")


@app.post("/resume_parse")
async def file_upload(background_tasks: BackgroundTasks, file: UploadFile = File(...)):
    """
    简历上传
    格式：pdf，docx，doc，txt，tar，zip，7z
    """
    res = await file.read()
    with open('./uploads/' + file.filename, "wb") as f:
        f.write(res)
    background_tasks.add_task(detection_type, './uploads/' + file.filename, system)
    return {"errno": 0, "msg": "Upload Success"}


if __name__ == '__main__':
    import platform
    system = platform.system()
    if (system == "Windows"):
        logging.info("Windows")
    elif (system == "Linux"):
        logging.info("Linux")
    else:
        logging.error("Unnot support this system")
 
    uvicorn.run(app=app, host="0.0.0.0", port=8320)