Python-将CSV转换为对象-代码设计
我有一个小脚本,我们用来读取包含员工的CSV文件,并对这些数据执行一些基本操作 我们读入数据(import_gdu_dump),并创建一个Python-将CSV转换为对象-代码设计,python,oop,Python,Oop,我有一个小脚本,我们用来读取包含员工的CSV文件,并对这些数据执行一些基本操作 我们读入数据(import_gdu_dump),并创建一个Employees对象,其中包含Employees对象的列表(也许我应该考虑一个更好的命名约定…lol)。然后,我们在员工上调用clean\u-all\u-phone\u-numbers(),在每个员工上调用clean\u-phone\u-numbers(),在员工上调用clean\u-phone\u-numbers() import csv import r
Employees
对象,其中包含Employees
对象的列表(也许我应该考虑一个更好的命名约定…lol)。然后,我们在员工
上调用clean\u-all\u-phone\u-numbers()
,在每个员工
上调用clean\u-phone\u-numbers()
,在员工
上调用clean\u-phone\u-numbers()
import csv
import re
import sys
#class CSVLoader:
# """Virtual class to assist with loading in CSV files."""
# def import_gd_dump(self, input_file='Gp Directory 20100331 original.csv'):
# gd_extract = csv.DictReader(open(input_file), dialect='excel')
# employees = []
# for row in gd_extract:
# curr_employee = Employee(row)
# employees.append(curr_employee)
# return employees
# #self.employees = {row['dbdirid']:row for row in gd_extract}
# Previously, this was inside a (virtual) class called "CSVLoader".
# However, according to here (http://tomayko.com/writings/the-static-method-thing) - the idiomatic way of doing this in Python is not with a class-function but with a module-level function
def import_gd_dump(input_file='Gp Directory 20100331 original.csv'):
"""Return a list ('employee') of dict objects, taken from a Group Directory CSV file."""
gd_extract = csv.DictReader(open(input_file), dialect='excel')
employees = []
for row in gd_extract:
employees.append(row)
return employees
def write_gd_formatted(employees_dict, output_file="gd_formatted.csv"):
"""Read in an Employees() object, and write out each Employee() inside this to a CSV file"""
gd_output_fieldnames = ('hrid', 'mail', 'givenName', 'sn', 'dbcostcenter', 'dbdirid', 'hrreportsto', 'PHFull', 'PHFull_message', 'SupervisorEmail', 'SupervisorFirstName', 'SupervisorSurname')
try:
gd_formatted = csv.DictWriter(open(output_file, 'w', newline=''), fieldnames=gd_output_fieldnames, extrasaction='ignore', dialect='excel')
except IOError:
print('Unable to open file, IO error (Is it locked?)')
sys.exit(1)
headers = {n:n for n in gd_output_fieldnames}
gd_formatted.writerow(headers)
for employee in employees_dict.employee_list:
# We're using the employee object's inbuilt __dict__ attribute - hmm, is this good practice?
gd_formatted.writerow(employee.__dict__)
class Employee:
"""An Employee in the system, with employee attributes (name, email, cost-centre etc.)"""
def __init__(self, employee_attributes):
"""We use the Employee constructor to convert a dictionary into instance attributes."""
for k, v in employee_attributes.items():
setattr(self, k, v)
def clean_phone_number(self):
"""Perform some rudimentary checks and corrections, to make sure numbers are in the right format.
Numbers should be in the form 0XYYYYYYYY, where X is the area code, and Y is the local number."""
if self.telephoneNumber is None or self.telephoneNumber == '':
return '', 'Missing phone number.'
else:
standard_format = re.compile(r'^\+(?P<intl_prefix>\d{2})\((?P<area_code>\d)\)(?P<local_first_half>\d{4})-(?P<local_second_half>\d{4})')
extra_zero = re.compile(r'^\+(?P<intl_prefix>\d{2})\(0(?P<area_code>\d)\)(?P<local_first_half>\d{4})-(?P<local_second_half>\d{4})')
missing_hyphen = re.compile(r'^\+(?P<intl_prefix>\d{2})\(0(?P<area_code>\d)\)(?P<local_first_half>\d{4})(?P<local_second_half>\d{4})')
if standard_format.search(self.telephoneNumber):
result = standard_format.search(self.telephoneNumber)
return '0' + result.group('area_code') + result.group('local_first_half') + result.group('local_second_half'), ''
elif extra_zero.search(self.telephoneNumber):
result = extra_zero.search(self.telephoneNumber)
return '0' + result.group('area_code') + result.group('local_first_half') + result.group('local_second_half'), 'Extra zero in area code - ask user to remediate. '
elif missing_hyphen.search(self.telephoneNumber):
result = missing_hyphen.search(self.telephoneNumber)
return '0' + result.group('area_code') + result.group('local_first_half') + result.group('local_second_half'), 'Missing hyphen in local component - ask user to remediate. '
else:
return '', "Number didn't match recognised format. Original text is: " + self.telephoneNumber
class Employees:
def __init__(self, import_list):
self.employee_list = []
for employee in import_list:
self.employee_list.append(Employee(employee))
def clean_all_phone_numbers(self):
for employee in self.employee_list:
#Should we just set this directly in Employee.clean_phone_number() instead?
employee.PHFull, employee.PHFull_message = employee.clean_phone_number()
# Hmm, the search is O(n^2) - there's probably a better way of doing this search?
def lookup_all_supervisors(self):
for employee in self.employee_list:
if employee.hrreportsto is not None and employee.hrreportsto != '':
for supervisor in self.employee_list:
if supervisor.hrid == employee.hrreportsto:
(employee.SupervisorEmail, employee.SupervisorFirstName, employee.SupervisorSurname) = supervisor.mail, supervisor.givenName, supervisor.sn
break
else:
(employee.SupervisorEmail, employee.SupervisorFirstName, employee.SupervisorSurname) = ('Supervisor not found.', 'Supervisor not found.', 'Supervisor not found.')
else:
(employee.SupervisorEmail, employee.SupervisorFirstName, employee.SupervisorSurname) = ('Supervisor not set.', 'Supervisor not set.', 'Supervisor not set.')
#Is thre a more pythonic way of doing this?
def print_employees(self):
for employee in self.employee_list:
print(employee.__dict__)
if __name__ == '__main__':
db_employees = Employees(import_gd_dump())
db_employees.clean_all_phone_numbers()
db_employees.lookup_all_supervisors()
#db_employees.print_employees()
write_gd_formatted(db_employees)
导入csv
进口稀土
导入系统
#CSV类装载机:
#“”“帮助加载CSV文件的虚拟类。”“”
#def导入_gd_转储(自身,输入文件='Gp目录20100331 original.csv'):
#gd_extract=csv.DictReader(打开(输入文件),方言='excel')
#雇员=[]
#对于gd_摘录中的行:
#当前员工=员工(行)
#employees.append(当前员工)
#返回员工
##self.employees={row['dbdirid']:gd_extract中的行对行}
#以前,它位于一个名为“CSVLoader”的(虚拟)类中。
#但是根据这里的说法,(http://tomayko.com/writings/the-static-method-thing)-Python中的惯用方法不是使用类函数,而是使用模块级函数
def导入_gd_转储(输入_file='Gp Directory 20100331 original.csv'):
“”“返回从组目录CSV文件中获取的dict对象列表('employee')。”
gd_extract=csv.DictReader(打开(输入文件),方言='excel')
雇员=[]
对于gd_摘录中的行:
employees.append(行)
返回员工
def write_gd_formatted(员工dict,output_file=“gd_formatted.csv”):
“”“读入Employees()对象,并将其中的每个Employees()写入CSV文件”“”
gd_输出_字段名=('hrid','mail','givenName','sn','dbcostcenter','dbdirid','hrreportsto','PHFull','PHFull_消息','SupervisorMail','SupervisorFirstName','SupervisorUrName')
尝试:
gd_formatted=csv.DictWriter(打开(输出文件'w',换行符=''),字段名=gd_输出字段名,extraction='ignore',方言='excel')
除IOError外:
打印('无法打开文件,IO错误(是否已锁定?))
系统出口(1)
headers={n:n表示gd_output_fieldnames中的n}
gd_格式化的.writerow(标题)
对于员工目录中的员工:
#我们正在使用employee对象的内置dict属性-嗯,这是一种好的做法吗?
gd_格式化的.writerow(雇员.uuu命令)
班级员工:
“”“系统中的员工,具有员工属性(姓名、电子邮件、成本中心等)。”“”
定义初始化(自我、员工属性):
“”“我们使用Employee构造函数将字典转换为实例属性。”“”
对于employee_attributes.items()中的k、v:
setattr(自、k、v)
def清洁电话号码(自身):
“”“执行一些基本检查和更正,以确保数字的格式正确。”。
数字的格式应为0xyyyyyy,其中X是区号,Y是本地号码。”“”
如果self.telephoneNumber为None或self.telephoneNumber='':
返回“”,“缺少电话号码。”
其他:
标准格式=重新编译(r'^\+(?P\d{2})\(?P\d)\(?P\d{4})-(?P\d{4}))
额外零=重新编译(r'^\+(?P\d{2})\(0(?P\d)\(?P\d{4})-(?P\d{4}))
缺少重新编译(r'^\+(?P\d{2})\(0(?P\d)\)(?P\d{4})(?P\d{4}))
如果是标准格式搜索(self.telephoneNumber):
结果=标准格式搜索(self.telephoneNumber)
返回“0”+result.group('area_code')+result.group('local_first_half')+result.group('local_second_half'),“”
elif extra_zero.搜索(自身电话号码):
结果=额外零搜索(自身电话号码)
返回“0”+result.group('area_code')+result.group('local_first_half')+result.group('local_second_half'),“区号中的额外零-请用户进行修正。”
elif缺少连字符搜索(self.telephoneNumber):
结果=缺少连字符搜索(self.telephoneNumber)
返回“0”+result.group('area_code')+result.group('local_first_half')+result.group('local_second_half'),“本地组件中缺少连字符-请用户进行修正。”
其他:
返回“”,“号码与识别的格式不匹配。原始文本为:“+self.telephoneNumber”
类别雇员:
定义初始化(自我,导入列表):
self.employee_list=[]
对于导入列表中的员工:
self.employee_list.append(employee(employee))
def clean_所有电话号码(自身):
对于self.employee_列表中的员工:
#我们应该直接在Employee.clean\u phone\u number()中设置吗?
employee.PHFull,employee.PHFull\u message=employee.clean\u电话号码()
#嗯,搜索是O(n^2)-可能有更好的搜索方法?
def查找\u所有\u主管(自我):
对于self.employee_列表中的员工:
如果employee.hrreportsto不是None,employee.hrreportsto!='':
对于self.employee_列表中的主管:
如果supervisor.hrid==employee.hrreportsto:
(employee.SupervisorEmail,employee.SupervisorFirstName,employee.supervisorUrName)=supervisor.mail,supervisor.givenName,supervisor.sn
打破
其他:
(employee.SupervisorEmail、employee.SupervisorFirstName、employee.SupervisorUrName)=(“未找到主管”、“未找到主管”、“未找到主管”)
其他:
(employee.SupervisorEmail、employee.SupervisorFirstName、employee.SupervisorUrName)=(‘未设置主管’、‘未设置主管’、‘未设置主管’)
#是t吗