Question

我正在运行一个替换文件名中的德语变音符号的脚本。我需要执行此操作的文件超过1700个，但是在脚本运行一段时间后，我收到的错误表明打开的文件太多。任何人有任何想法如何解决这个问题？非常感谢您的反馈！

代码：

# -*- coding: utf-8 -*-

''' Script replaces all umlauts in filenames within a root directory and its subdirectories with the English
    equivalent (ie. ä replaced with ae, Ä replaced with Ae).'''

import os
import itertools
import logging
from itertools import groupby

##workspace = u'G:\\Dvkoord\\GIS\\TEMP\\Tle\\Scripts\\Umlaut'
workspace = u'G:\\Gis\\DATEN'
log = 'Umlauts.log'
logPath = r"G:\Dvkoord\GIS\TEMP\Tle\Scripts\Umlaut\Umlauts.log"
logMessageFormat = '%(asctime)s - %(levelname)s - %(message)s'


def GetFilepaths(directory):
    """Function returns a list of file paths in a directory tree using os.walk.  Parameter: directory
    """
    file_paths = []
    for root, directories, files in os.walk(directory):
        for filename in files:
            filepath = os.path.join(root, filename)
            file_paths.append(filepath)
##    file_paths = list(set(file_paths))
    return file_paths

def uniq(input):
  output = []
  for x in input:
    if x not in output:
      output.append(x)
  return output

def Logging(logFile, logLevel, destination, textFormat, comment):
    """Function writes a log file.  Parameters: logFile (name the log file w/extension),
        logLevel (DEBUG, INFO, etc.), destination (path under which the log file will be
        saved including name and extension), textFormat (how the log text will be formatted)
        and comment.
    """
    # logging
    logger = logging.getLogger(__name__)
    # set log level
    logger.setLevel(logLevel)
    # create a file handler for the log -- unless a separate path is specified, it will output to the directory where this script is stored
    logging.FileHandler(logFile)
    handler = logging.FileHandler(destination)
    handler.setLevel(logLevel)
    # create a logging format
    formatter = logging.Formatter(textFormat)
    handler.setFormatter(formatter)
    # add the handlers to the logger
    logger.addHandler(handler)
    logger.info(comment)


def main():
    # dictionary of umlaut unicode representations (keys) and their replacements (values)
    umlautDictionary = {
                        u'Ä': 'Ae',
                        u'Ö': 'Oe',
                        u'Ü': 'Ue',
                        u'ä': 'ae',
                        u'ö': 'oe',
                        u'ü': 'ue',
                        u'ß': 'ss'
                        }
    dataTypes = [".CPG",
                 ".dbf",
                 ".prj",
                 ".sbn",
                 ".sbx",
                 ".shp",
                 ".shx",
                 ".shp.xml",
                 ".lyr"]
    # get file paths in root directory and subfolders
    filePathsList = GetFilepaths(workspace)
    # put all filepaths with an umlaut in filePathsUmlaut list
    filePathsUmlaut = []
    for fileName in filePathsList:
##        print fileName
        for umlaut in umlautDictionary:
            if umlaut in os.path.basename(fileName):
                for dataType in dataTypes:
                    if dataType in fileName:
##                        print fileName
                        filePathsUmlaut.append(fileName)
    # remove duplicate paths from filePathsUmlaut
    uniquesUmlauts = uniq(filePathsUmlaut)

    # create a dictionary for umlaut translation
    umap = {
            ord(key):unicode(val)
            for key, val in umlautDictionary.items()
            }
    # use translate and umap dictionary to replace umlauts in file name and put them in the newFilePaths list
    # without changing any of the umlauts in folder names or upper directories
    newFilePaths = []
    for fileName in uniquesUmlauts:
        pardir = os.path.dirname(fileName)
        baseName = os.path.basename(fileName)
        newBaseFileName = baseName.translate(umap)
        newPath = os.path.join(pardir, newBaseFileName)
        newFilePaths.append(newPath)
    newFilePaths = uniq(newFilePaths)

    # create a dictionary with the old umlaut path as key and new non-umlaut path as value
    dictionaryOldNew = dict(itertools.izip(uniquesUmlauts, newFilePaths))
    # rename old file (key) as new file (value)
    for files in uniquesUmlauts:
        for key, value in dictionaryOldNew.iteritems():

            if key == files:
                comment = '%s'%files + ' wurde als ' '%s'%value + ' umbenannt.'
                print comment
                if os.path.exists(value):
                    os.remove(value)
                os.rename(files, value)
                Logging(log, logging.INFO, logPath, logMessageFormat, comment)


if __name__ == '__main__':
    main()

Answer 1

我认为问题是你的Logging功能。每次登录时，您都要创建一个新的FileHandler并将其添加到处理程序集中，并为重命名的每个文件执行此操作，这样您就可以快速达到打开文件描述符的限制。配置您的记录器一次，然后多次使用它，每次使用时都不要配置它。

请注意，Logging中可能不会引发异常;在Windows上删除文件涉及将其打开以进行删除，因此您可以使用记录器最大限度地打开文件，然后在尝试删除文件时失败。

Windows上的Python 2.7 - 打开文件太多

1 个答案: