modified: resume_parse.py

tools/resume_parse.py

@@ -27,7 +27,42 @@ 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)
+class Logger:
+    def __init__(self, name: str, console_handler_level: str = logging.INFO, fmt: str = '%(asctime)s: %(name)s: %(levelname)s: %(filename)s: %(funcName)s: %(message)s'):
+        self.logger = logging.getLogger(name)
+        self.logger.setLevel(logging.INFO)
+        self.fmt = logging.Formatter(fmt)
+        self.set_console_handler(console_handler_level)
+
+    def set_console_handler(self, console_handler_level: str = logging.INFO) -> None:
+        ch = logging.StreamHandler()
+        ch.setLevel(console_handler_level)
+        ch.setFormatter(self.fmt)
+        self.logger.addHandler(ch)
+
+    def set_file_handler(self, filename: str, mode: str = "a", file_handler_level: str = logging.WARNING) -> None:
+        fh = logging.FileHandler(filename, mode=mode, encoding='utf-8')
+        fh.setLevel(file_handler_level)
+        fh.setFormatter(self.fmt)
+        self.logger.addHandler(fh)
+
+    def debug(self, msg):
+        self.logger.debug(msg)
+
+    def info(self, msg):
+        self.logger.info(msg)
+
+    def warning(self, msg):
+        self.logger.warning(msg)
+
+    def error(self, msg):
+        self.logger.error(msg)
+
+    def critical(self, msg):
+        self.logger.critical(msg)
+
+logger = Logger("resume_parse")
+logger.set_file_handler(filename='data.log')
 
 from rich.console import Console
 console = Console()
@@ -52,7 +87,7 @@ block_rev = {1:"基本信息", 2:"求职意向", 3:"教育经历", 4:"工作经
 
 # 基本信息(已完成)
 def get_base_info_old(lines):
-    logging.info(lines)
+    logger.info(lines)
     schema = {
         '姓名': None,
     }
@@ -66,7 +101,7 @@ def get_base_info_old(lines):
                     key, val = i.split('：')
                     schema[key] = val
                 except Exception as e:
-                    logging.error(e)
+                    logger.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
@@ -99,7 +134,7 @@ def get_base_info_old(lines):
 def get_base_info(lines):
     if not lines:
         return
-    logging.info(lines)
+    logger.info(lines)
     data = " ".join(lines)
     rst = base_info_ie(data)[0]
     if rst.get("出生日期"):
@@ -123,7 +158,7 @@ def get_base_info(lines):
 
 # 求职意向(已完成)
 def get_job_intention(lines):
-    logging.info(lines)
+    logger.info(lines)
     schema = {}
     for line in lines:
         regex = re.compile(r'\W{0,3}[：:]\s+')
@@ -134,14 +169,14 @@ def get_job_intention(lines):
                     key, val = i.split(":")
                     schema[key] = val
                 except Exception as e:
-                    logging.error(e)
+                    logger.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)
+    logger.info(lines)
 
     job_list = []
     job_dict = {'edu_time_beg':'', 'edu_time_end':'', 'edu_name':'','edu_leval':'','edu_domain':'', 'edu_statue':0}
@@ -199,8 +234,8 @@ def get_edu_list_old(lines):
         top_level = 18
         remove_list = []
 
-        logging.info(_list_data)
-        logging.info(time_list)
+        logger.info(_list_data)
+        logger.info(time_list)
 
         for ii in range(len(_list_data)):
             for t in time_list:
@@ -221,7 +256,7 @@ def get_edu_list_old(lines):
             break
             #remove_list.append(i)
 
-        logging.info(_list_data)
+        logger.info(_list_data)
 
         job_time = re.findall(re_txt_1, data_list[0])
         if job_time:
@@ -360,7 +395,7 @@ def get_edu_list_old(lines):
 
 # 教育经历改 (已完成)
 def get_edu_list(lines):
-    logging.info(lines)
+    logger.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})')
@@ -446,7 +481,7 @@ def get_edu_list(lines):
 # 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)
+    logger.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'
@@ -470,8 +505,8 @@ def get_job_list(lines):
         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))
+    # logger.info(nums)
+    logger.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]]
@@ -631,7 +666,7 @@ def get_job_list(lines):
 # 项目经历 (已完成)(弃用)
 # 项目名称未知
 def get_pro_list_old(lines):
-    logging.info(lines)
+    logger.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])?')
@@ -665,14 +700,14 @@ def get_pro_list_old(lines):
                     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)
+                logger.error(e)
             pro_list[count]["content"] = line
     return pro_list
 
 
 # 项目经历 (UIE)
 def get_pro_list(lines):
-    logging.info(lines)
+    logger.info(lines)
 
     starts = []
     # 时间查找
@@ -708,7 +743,7 @@ def get_pro_list(lines):
             if not rst.get("时间") or not rst.get("项目名称"):
                 continue
             rst["工作内容"] = [{"text":""}]
-            logging.info(rst)
+            logger.info(rst)
             for l in src:
                 if rst["时间"][0]["text"] in l:
                     continue
@@ -745,7 +780,7 @@ def get_pro_list(lines):
 # 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)
+    logger.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}.'
@@ -776,7 +811,7 @@ def get_cultivate_list(lines):
             elif _[1] == 'TIME' and len(_[1]) >= 4:
                 time_list.append(_[0])
             #TIME
-        logging.info(data_line)
+        logger.info(data_line)
         _list_data = re.split('\040+', data_line)
         top_level = 22
         end_index = 0
@@ -838,7 +873,7 @@ def get_cultivate_list(lines):
         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)
+        logger.info(job_dict)
         job_list.append(job_dict)
         continue
     '''
@@ -873,7 +908,7 @@ def get_cultivate_list(lines):
 
 # 语言能力
 def get_lag_list(lines):
-    logging.info(lines)
+    logger.info(lines)
 
     job_list = []
     re_lan = re.compile(r'(\w+[语话])')
@@ -915,7 +950,7 @@ def get_fam_list(lines):
 
 # 证书情况  时间+证书名称 （已完成）
 def get_cet_list_old(lines):
-    logging.info(lines)
+    logger.info(lines)
 
     job_list = []
     re_txt = '\d+年\d+月|\d+-\d+|\d+\.\d+'
@@ -938,7 +973,7 @@ def get_cet_list_old(lines):
         else:
             continue
         ls = re.split('\||\040+|\t+', l)
-        logging.info(ls)
+        logger.info(ls)
         for l in ls:
             if len(l) <= 3:
                 continue
@@ -950,7 +985,7 @@ def get_cet_list_old(lines):
 
 # 证书情况  时间+证书名称 （UIE已完成）
 def get_cet_list(lines):
-    logging.info(lines)
+    logger.info(lines)
     cet_list = []
     for line in lines:
         info = cet_ie(line)
@@ -960,7 +995,7 @@ def get_cet_list(lines):
 
 # 获奖情况  时间+获奖名称 （已完成）
 def get_prize_list_old(lines):
-    logging.info(lines)
+    logger.info(lines)
 
     job_list = []
     re_txt = '\d+年\d+月|\d+-\d+|\d{4,4}.\d{1,2}'
@@ -982,20 +1017,20 @@ def get_prize_list_old(lines):
         else:
             continue
         ls = re.split('\||\040+|\t+', l)
-        logging.info(ls)
+        logger.info(ls)
         for l in ls:
             if len(l) <= 3:
                 continue
             cet_dict['prize_name'] = l.strip()
             break
-        logging.info(cet_dict)
+        logger.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)
+    logger.info(lines)
     prize_list = []
     for line in lines:
         info = prize_ie(line)
@@ -1126,9 +1161,9 @@ def check_word(path, save_dir):
     tables = doc.tables
 
     if not tables:
-        logging.info("this is raw text")
+        logger.info("this is raw text")
         read_from_word(doc, path, save_dir=save_dir)
-    logging.info("this is a Table")
+    logger.info("this is a Table")
 
     global block
     with open("resources/keys.json", "r", encoding="utf-8") as fp:
@@ -1243,7 +1278,7 @@ def read_from_pdf(path, save_dir):
         # 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 ================')
+            logger.debug('================ 新页面 ================')
             interpreter.process_page(page)
             layout = device.get_result()
             r, b = parse_line_layout(layout, b)
@@ -1380,7 +1415,7 @@ def detection_type(path, system):
             zf.extractall("./cache/" + tempdir)
             path = "./cache/" + tempdir
     except Exception as e:
-        logging.error(e)
+        logger.error(e)
     # 传入为 doc
     if os.path.isfile(path) and path.endswith('.doc'):
         doc2pdf(docPath = path, pdfPath = './pdf', system=system)
@@ -1410,7 +1445,7 @@ def detection_type(path, system):
         for filename in os.listdir(path):
             filename = os.path.join(path, filename)
             # 传入为 doc
-            logging.info(filename)
+            logger.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'
@@ -1460,10 +1495,16 @@ if __name__ == '__main__':
     import platform
     system = platform.system()
     if (system == "Windows"):
-        logging.info("Windows")
+        logger.info("Windows")
     elif (system == "Linux"):
-        logging.info("Linux")
+        logger.info("Linux")
     else:
-        logging.error("Unnot support this system")
+        logger.error("Unnot support this system")
+    if not os.path.exists("./uploads"):
+        os.mkdir("./uploads")
+    if not os.path.exists("./pdf"):
+        os.mkdir("./pdf")
+    if not os.path.exists("./cache"):
+        os.mkdir("./cache")
  
     uvicorn.run(app=app, host="0.0.0.0", port=8320)