新增字段

api/api_v1/endpoints/interview.py

@@ -419,19 +419,62 @@ async def interview_file_insert(
                         if len(true_d_list) == 2:
                             chk_list = deepcopy(true_d_list)
                             chkdict[chk_list[0]] = chk_list[1]
-                    true_dict = deepcopy(chkdict)
+                    dp_dict = {
+                        'time': '',
+                        'name': '',
+                        'work': '',
+                        'comment': '',
+                        'duty': '',
+                    }
+
+                    true_dict = deepcopy(dp_dict)
+                    for key, v in chkdict.items():
+                        if key == '项目名称':
+                            true_dict['name'] = v
+                            continue
+                        if key == '开发周期':
+                            true_dict['time'] = v
+                            continue
+                        if key == '项目描述':
+                            true_dict['comment'] = v
+                            continue
+                        if key in ['技术要点', '功能模块']:
+                            true_dict['work'] += v
+                            continue
+                        if key == '职务':
+                            true_dict['duty'] = v
+                            continue
+                    # true_dict = deepcopy(chkdict)
                     true_upgrade.append(true_dict)
+
             work_list = data['work_list']
+            language = data['language']
+            remembrance = data['remembrance']
             true_work = []
+            language_list = []
+            remembrance_list = []
             if work_list:
                 for dstr in work_list:
                     data1 = eval(dstr)
                     dictdata = deepcopy(data1)
                     true_work.append(dictdata)
+            if language:
+                for dstr in work_list:
+                    data1 = eval(dstr)
+                    dictdata = deepcopy(data1)
+                    language_list.append(dictdata)
+            if remembrance:
+                for dstr in work_list:
+                    data1 = eval(dstr)
+                    dictdata = deepcopy(data1)
+                    remembrance_list.append(dictdata)
+
             res_data = {
                 'data': data,
                 'project_undergo': true_upgrade,
-                'work_list': true_work
+                'work_list': true_work,
+                'language_list': language_list,
+                'remembrance_list': remembrance_list
             }
             return schemas.Msg(code=200, msg='ok', data=res_data)
         else:

models/interview_zsgc.py

@@ -112,7 +112,10 @@ class InterviewDo:
             "notice_state": 1,
             "pass_why": 0,
             "pass_text": [],
-            "file_url": '',
+            "language": [],
+            "remembrance": [],
+            "birthday": '',
+            "file_url": ''
         }
 
         insert_data = []
@@ -127,7 +130,7 @@ class InterviewDo:
               f" education, work_undergo, project_undergo, work_list, school, at_school, specialty, specialty_do, " \
               f"mmended_state, mail, account, id_card, gender, age, gam, interview_state, counts, nation, come_time," \
               f" review, upgrade, now_money, men_state, teacher_state, teacher_back, offer_state, offer_exam_state," \
-              f" notice_state, pass_why, pass_text, file_url) values"
+              f" notice_state, pass_why, pass_text,language,remembrance,birthday, file_url) values"
         now_time = datetime.datetime.now()
         for data in insert_data:
             s1 = data['event_time']

utils/jianli.py

@@ -103,9 +103,121 @@ def chkworlkandtime(listdata):
     ress = []
     if res != {}:
         for i in range(len(res['公司名'])):
+            company_name = ''
+            position_name = ''
+            duty = ''
+            if '公司名' in res:
+                company_name = res['公司名'][i]['text']
+            if '职责' in res:
+                position_name = res['职责'][i]['text']
+            if '工作内容' in res:
+                duty = res['工作内容'][i]['text']
             date = {
-                'name': res['公司名'][i]['text'],
+                'company_name ': company_name,
-                'time': res['时间'][i]['text']
+                'position_name': position_name,
+                'duty': duty
+            }
+            ress.append(str(date))
+    return ress
+
+
+def chkworlkandtime1(listdata):
+    """
+    获取语言能力中语言类型和掌握程度,听说,读写
+    :param dictdata:
+    :return:返回列表格式
+    """
+    res = {}
+    for i in listdata:
+        for key, datalist in i.items():
+            trueDict = {}
+            for data in datalist:
+                if data['text'] in trueDict:
+                    if data['probability'] <= trueDict[data['text']]['probability']:
+                        continue
+                trueDict.update({
+                    data['text']: {
+                        'end': data['end'],
+                        'probability': data['probability'],
+                        'start': data['start'],
+                    }
+                })
+            trueList = []
+            for key1, value1 in trueDict.items():
+                value1.update({
+                    'text': key1
+                })
+                trueDict1 = copy.deepcopy(value1)
+                trueList.append(trueDict1)
+            trueList.sort(key=lambda item: item['start'])
+            res.update({key: trueList})
+    ress = []
+    if res != {}:
+        for i in range(len(res['语言'])):
+            language_name = ''
+            has_sleep = ''
+            reading = ''
+            writing = ''
+            if '语言' in res:
+                language_name = res['语言'][i]['text']
+            if '掌握程度' in res:
+                has_sleep = res['掌握程度'][i]['text']
+            if '听说' in res:
+                reading = res['听说'][i]['text']
+            if '读写' in res:
+                writing = res['读写'][i]['text']
+            date = {
+                'language_name ': language_name,
+                'has_sleep ': has_sleep,
+                'reading': reading,
+                'writing': writing
+            }
+            ress.append(str(date))
+    return ress
+
+
+def chkworlkandtime2(listdata):
+    """
+    获取获奖经历中奖项名称和获奖时间
+    :param dictdata:
+    :return:返回列表格式
+    """
+    res = {}
+    for i in listdata:
+        for key, datalist in i.items():
+            trueDict = {}
+            for data in datalist:
+                if data['text'] in trueDict:
+                    if data['probability'] <= trueDict[data['text']]['probability']:
+                        continue
+                trueDict.update({
+                    data['text']: {
+                        'end': data['end'],
+                        'probability': data['probability'],
+                        'start': data['start'],
+                    }
+                })
+            trueList = []
+            for key1, value1 in trueDict.items():
+                value1.update({
+                    'text': key1
+                })
+                trueDict1 = copy.deepcopy(value1)
+                trueList.append(trueDict1)
+            trueList.sort(key=lambda item: item['start'])
+            res.update({key: trueList})
+    ress = []
+    if res != {}:
+        for i in range(len(res['奖项名'])):
+            prize_name = ''
+            prize_time = ''
+            if '奖项名' in res:
+                prize_name = res['公司名'][i]['text']
+            if '时间' in res:
+                prize_time = res['时间'][i]['text']
+            date = {
+                'prize_name ': prize_name,
+                'prize_time': prize_time,
             }
             ress.append(str(date))
     return ress
@@ -224,6 +336,16 @@ def get_date(schema, dates, schema_dict):
     clash(date, 'phone', 'tels')
 
     work_exp = date['work_exp']
+    if not work_exp:
+        date['work_exp'] = 0
+    # 工作经验float转化
+    if work_exp and isinstance(work_exp, str):
+        true_work_exp = re.search(r"\d+\.?\d*", work_exp)
+        if len(true_work_exp.group()) > 3:
+            work_exp = 0
+        else:
+            work_exp = float(true_work_exp.group())
+
     if 1 <= work_exp < 3:
         date['work_exp'] = 1
     if 3 <= work_exp < 5:
@@ -236,7 +358,7 @@ def get_date(schema, dates, schema_dict):
 def fmtTxt(txt, istable=0):
     # 所有关键字
     chkStr = ['自我评价', '自我描述', '个人优势', '项目经历', '项目经验', '项目描述', '教育经历', '学习经历', '工作经历', '工作经验', '实习经历',
-              '技能特长', '技能', '特长', '专长', '技能专长', '专业技能', '职业技能', '个人评价']
+              '技能特长', '技能', '特长', '专长', '技能专长', '专业技能', '职业技能', '个人评价', '语言', '获奖', '证书', '获奖记录', '获奖经历']
     # 自我描述
     chkList1 = ['自我评价', '自我描述', '个人优势', '个人评价']
     # 项目经验
@@ -247,6 +369,10 @@ def fmtTxt(txt, istable=0):
     chkList4 = ['工作经历', '工作经验', '实习经历']
     # 个人技能
     chkList5 = ['技能特长', '技能', '特长', '专长', '技能专长', '专业技能', '职业技能']
+    # 语言能力
+    chkList6 = ['语言']
+    # 获奖经历
+    chkList7 = ['获奖', '证书', '获奖记录', '获奖经历']
     fmtList = []  # 返回拼接好的字符串列表
     trueIndex = 0
     fmtStr = ''
@@ -309,11 +435,37 @@ def fmtTxt(txt, istable=0):
                 continue
             # 个人技能
             for i in chkList5:
+                # 判断是不是以关键字开头
+                if not text.startswith(i, 0):
+                    continue
+                else:
                     if i in text:
                         fmtStr = text
                         nowChkList = [chk for chk in chkStr if chk not in chkList5]
                         stop_int = 1
                         break
+            if fmtStr:
+                continue
+            # 语言能力
+            for i in chkList6:
+                # 判断是不是以关键字开头
+                if not text.startswith(i, 0):
+                    continue
+                else:
+                    if i in text:
+                        fmtStr = text
+                        nowChkList = [chk for chk in chkStr if chk not in chkList6]
+                        stop_int = 1
+                        break
+            if fmtStr:
+                continue
+            # 获奖经历
+            for i in chkList7:
+                if i in text:
+                    fmtStr = text
+                    nowChkList = [chk for chk in chkStr if chk not in chkList7]
+                    stop_int = 1
+                    break
             continue
         else:
             isTure = 1
@@ -349,6 +501,8 @@ def fmtList(txtlist, dates):
     chkList3 = ['教育经历', '学习经历']
     chkList4 = ['工作经历', '工作经验', '实习经历']
     chkList5 = ['技能特长', '技能', '特长', '专长', '技能专长', '专业技能', '职业技能']
+    chkList6 = ['语言']
+    chkList7 = ['获奖', '证书', '获奖记录', '获奖经历']
     # 自我评价
     review = []
     # 项目经验
@@ -359,6 +513,10 @@ def fmtList(txtlist, dates):
     upgrade = []
     # 技能特长
     specialty = []
+    # 语言能力
+    language = []
+    # 获奖经历
+    remembrance = []
     for text in txtlist:
         ischk = 0
         # 自我评价
@@ -401,16 +559,58 @@ def fmtList(txtlist, dates):
                 break
         if ischk:
             continue
+        # 语言能力
+        for i in chkList6:
+            if i in text:
+                language.append(text)
+                ischk = 1
+                break
+        if ischk:
+            continue
+        # 获奖经历
+        for i in chkList7:
+            if i in text:
+                remembrance.append(text)
+                ischk = 1
+                break
+        if ischk:
+            continue
     # 取出工作经验里面的公司名和时间
     work_list = []
     if len(work) > 0:
         works = ''
         for i in work:
             works += i
-        schema = ['公司名', '时间']
+        schema = ['公司名', '职责', '工作内容']
         ie = Taskflow('information_extraction', schema=schema)
         text_lists = ie(works)
         work_list = chkworlkandtime(text_lists)
+    else:
+        work_list = ["{'company_name ': '','position_name': '','duty': ''}"]
+    # 取出获奖经历里面的公司名和时间
+    remembrance_list = []
+    if len(remembrance) > 0:
+        remembrances = ''
+        for i in remembrance:
+            remembrances += i
+        schema = ['奖项名', '时间']
+        ie = Taskflow('information_extraction', schema=schema)
+        text_lists = ie(remembrances)
+        remembrance_list = chkworlkandtime2(text_lists)
+    else:
+        remembrance_list = ["{'prize_name ': '', 'prize_time': '', }"]
+    # 取出语言能力里面的语言,掌握程度,听说,读写
+    language_list = []
+    if len(language) > 0:
+        works = ''
+        for i in work:
+            works += i
+        schema = ['语言', '掌握程度', '听说', '读写']
+        ie = Taskflow('information_extraction', schema=schema)
+        text_lists = ie(works)
+        language_list = chkworlkandtime1(text_lists)
+    else:
+        language_list = ["{'language_name ': '', 'has_sleep ': '', 'reading': '', 'writing': ''}"]
     # review自我评价, project项目经验，work工作经验，work具体工作的公司和时间，upgrade教育经历，specialty技能特长
     dates.update({
         'review': review,
@@ -419,6 +619,8 @@ def fmtList(txtlist, dates):
         'work_list': work_list,
         'upgrade': upgrade,
         'specialty_do': specialty,
+        'language': language_list,
+        'remembrance': remembrance_list,
     })
 
     return dates