0
我想帮助重构此代码以减少冗余行/概念。这个def的代码基本上重复了3次。重构此Python代码以简化重复的简单方法
限制条件: - 我是新手,所以一个真正的幻想列表理解或将事物转化为对象,使用dunders和方法覆盖是我先进的方法。 - 仅内置模块。这是Pyhton 2.7代码,只能导入os和re。
整个脚本的作用: 查找具有固定前缀的文件。这些文件是管道分隔的文本文件。第一行是标题。它有一个可以是1行或更多行的页脚。根据前缀,脚本会从文本文件中丢弃另一步中不需要的“列”。它将以逗号分隔的数据保存在扩展名为.csv的新文件中。
大部分工作都是在processRawFiles()中完成的。这是我想重构的,因为它是非常重复的。
def separateTranslationTypes(translationFileList):
'''Takes in list of all files to process and find which are roomtypes
, ratecodes or sourcecodes. The type of file determines how it will be processed.'''
rates = []
rooms = []
sources = []
for afile in translationFileList:
rates.append([m.group() for m in re.finditer('cf_ratecodeheader+(.*)', afile)])
rooms.append([m.group() for m in re.finditer('cf_roomtypes+(.*)', afile)])
sources.append([m.group() for m in re.finditer('cf_sourcecodes+(.*)', afile)])
# empty list equates to False. So if x is True if the list is not empty - thus kept.
rates = [x[0] for x in rates if x]
rooms = [x[0] for x in rooms if x]
sources = [x[0] for x in sources if x]
print '... rateCode files :: ',rates,'\n'
print '... roomType files :: ',rooms,'\n'
print '... sourceCode files :: ',sources, '\n'
return {'rateCodeFiles':rates,
'roomTypeFiles':rooms,
'sourceCodeFiles':sources}
groupedFilestoProcess = separateTranslationTypes(allFilestoProcess)
def processRawFiles(groupedFileDict):
for key in groupedFileDict:
# Process the rateCodes file
if key == 'rateCodeFiles':
for fname_Value in groupedFileDict[key]: # fname_Value is the filename
if os.path.exists(fname_Value):
workingfile = open(fname_Value,'rb')
filedatastring = workingfile.read() # turns entire file contents to a single string
workingfile.close()
outname = 'forUpload_' + fname_Value[:-4:] + '.csv' # removes .txt of any other 3 char extension
outputfile = open(outname,'wb')
filedatalines = filedatastring.split('\n') # a list containing each line of the file
rawheaders = filedatalines[0] # 1st element of the list is the first row of the file, with the headers
parsedheaders = rawheaders.split('|') # turn the header string into a list where | was delimiter
print '\n'
print 'outname: ', outname, '\n'
# print 'rawheaders: ', rawheaders, '\n'
# print 'parsedheaders: ',parsedheaders, '\n'
# print filedatalines[0:2]
print '\n'
ratecodeindex = parsedheaders.index('RATE_CODE')
ratecodemeaning = parsedheaders.index('DESCRIPTION')
for dataline in filedatalines:
if dataline[:4] == 'LOGO':
firstuselessline = filedatalines.index(dataline)
# print firstuselessline
# ignore the first line which was the headers
# stop before the line that starts with LOGO - the first useless line
for dataline in filedatalines[1:firstuselessline-1:]:
# print dataline.split('|')
theratecode = dataline.split('|')[ratecodeindex]
theratemeaning = dataline.split('|')[ratecodemeaning]
# print theratecode, '\t', theratemeaning, '\n'
linetowrite = theratecode + ',' + theratemeaning + '\n'
outputfile.write(linetowrite)
outputfile.close()
# Process the roomTypes file
if key == 'roomTypeFiles':
for fname_Value in groupedFileDict[key]: # fname_Value is the filename
if os.path.exists(fname_Value):
workingfile = open(fname_Value,'rb')
filedatastring = workingfile.read() # turns entire file contents to a single string
workingfile.close()
outname = 'forUpload_' + fname_Value[:-4:] + '.csv' # removes .txt of any other 3 char extension
outputfile = open(outname,'wb')
filedatalines = filedatastring.split('\n') # a list containing each line of the file
rawheaders = filedatalines[0] # 1st element of the list is the first row of the file, with the headers
parsedheaders = rawheaders.split('|') # turn the header string into a list where | was delimiter
print '\n'
print 'outname: ', outname, '\n'
# print 'rawheaders: ', rawheaders, '\n'
# print 'parsedheaders: ',parsedheaders, '\n'
# print filedatalines[0:2]
print '\n'
ratecodeindex = parsedheaders.index('LABEL')
ratecodemeaning = parsedheaders.index('SHORT_DESCRIPTION')
for dataline in filedatalines:
if dataline[:4] == 'LOGO':
firstuselessline = filedatalines.index(dataline)
# print firstuselessline
# ignore the first line which was the headers
# stop before the line that starts with LOGO - the first useless line
for dataline in filedatalines[1:firstuselessline-1:]:
# print dataline.split('|')
theratecode = dataline.split('|')[ratecodeindex]
theratemeaning = dataline.split('|')[ratecodemeaning]
# print theratecode, '\t', theratemeaning, '\n'
linetowrite = theratecode + ',' + theratemeaning + '\n'
outputfile.write(linetowrite)
outputfile.close()
# Process sourceCodes file
if key == 'sourceCodeFiles':
for fname_Value in groupedFileDict[key]: # fname_Value is the filename
if os.path.exists(fname_Value):
workingfile = open(fname_Value,'rb')
filedatastring = workingfile.read() # turns entire file contents to a single string
workingfile.close()
outname = 'forUpload_' + fname_Value[:-4:] + '.csv' # removes .txt of any other 3 char extension
outputfile = open(outname,'wb')
filedatalines = filedatastring.split('\n') # a list containing each line of the file
rawheaders = filedatalines[0] # 1st element of the list is the first row of the file, with the headers
parsedheaders = rawheaders.split('|') # turn the header string into a list where | was delimiter
print '\n'
print 'outname: ', outname, '\n'
# print 'rawheaders: ', rawheaders, '\n'
# print 'parsedheaders: ',parsedheaders, '\n'
# print filedatalines[0:2]
print '\n'
ratecodeindex = parsedheaders.index('SOURCE_CODE')
ratecodemeaning = parsedheaders.index('DESCRIPTION')
for dataline in filedatalines:
if dataline[:4] == 'LOGO':
firstuselessline = filedatalines.index(dataline)
# print firstuselessline
# ignore the first line which was the headers
# stop before the line that starts with LOGO - the first useless line
for dataline in filedatalines[1:firstuselessline-1:]:
# print dataline.split('|')
theratecode = dataline.split('|')[ratecodeindex]
theratemeaning = dataline.split('|')[ratecodemeaning]
# print theratecode, '\t', theratemeaning, '\n'
linetowrite = theratecode + ',' + theratemeaning + '\n'
outputfile.write(linetowrite)
outputfile.close()
processRawFiles(groupedFilestoProcess)