用于进度条的Python zipfile线程

时间:2010-12-05 02:11:20

标签: python multithreading progress-bar

我发现自己最近越来越多了。在尝试学习Python时(通过直接跳入并尝试从C#移植应用程序),我遇到了一些我以前从未听说过的东西:线程化。当我以为我有一个基本的理解,我尝试转换程序的部分拉链充满文件(和子目录)的目录。这是我到目前为止所提出的 - 在最后列出的几个来源的帮助下:

from Queue import Queue

import os
import gtk
import threading
import time
import zipfile

debug = True

class ProduceToQueue( threading.Thread ):
    def __init__( self, threadName, queue, window, maximum, zipobj, dirPath ):
        threading.Thread.__init__( self, name = threadName )
        self.sharedObject = queue
        self.maximum = maximum
        self.zip = zipobj
        self.dirPath = dirPath
        self.window = window

        global debug

        if debug:
            print self.getName(), "got all params."

    def run( self ):
        if debug:
            print "Beginning zip."
        files = 0
        parentDir, dirToZip = os.path.split(self.dirPath)
        includeDirInZip = False
        #Little nested function to prepare the proper archive path
        def trimPath(path):
            archivePath = path.replace(parentDir, "", 1)
            if parentDir:
                archivePath = archivePath.replace(os.path.sep, "", 1)
            if not includeDirInZip:
                archivePath = archivePath.replace(dirToZip + os.path.sep, "", 1)
            return os.path.normcase(archivePath)
        for (archiveDirPath, dirNames, fileNames) in os.walk(self.dirPath):
            #if debug:
                #print "Walking path..."
            for fileName in fileNames:
                time.sleep( 0.001 )
                #if debug:
                    #print "After a small sleep, I'll start zipping."
                filePath = os.path.join(archiveDirPath, fileName)
                self.zip.write(filePath, trimPath(filePath))
                #if debug:
                    #print "File zipped - ",
                files = files + 1
                #if debug:
                    #print "I now have ", files, " files in the zip."
                self.sharedObject.put( files )
            #Make sure we get empty directories as well
            if not fileNames and not dirNames:
                zipInfo = zipfile.ZipInfo(trimPath(archiveDirPath) + "/")
                #some web sites suggest doing
                #zipInfo.external_attr = 16
                #or
                #zipInfo.external_attr = 48
                #Here to allow for inserting an empty directory.  Still TBD/TODO.
                outFile.writestr(zipInfo, "")

class ConsumeFromQueue( threading.Thread ):
    def __init__( self, threadName, queue, window, maximum ):
        threading.Thread.__init__( self, name = threadName )
        self.sharedObject = queue
        self.maximum = maximum
        self.window = window

        global debug

        if debug:
            print self.getName(), "got all params."

    def run( self ):
        print "Beginning progress bar update."
        for i in range( self.maximum ):
            time.sleep( 0.001 )
            #if debug:
                #print "After a small sleep, I'll get cracking on those numbers."
            current = self.sharedObject.get()
            fraction = current / float(self.maximum)
            self.window.progress_bar.set_fraction(fraction)
            #if debug:
                #print "Progress bar updated."

class MainWindow(gtk.Window):
    def __init__(self):
        super(MainWindow, self).__init__()
        self.connect("destroy", gtk.main_quit)
        vb = gtk.VBox()
        self.add(vb)
        self.progress_bar = gtk.ProgressBar()
        vb.pack_start(self.progress_bar)
        b = gtk.Button(stock=gtk.STOCK_OK)
        vb.pack_start(b)
        b.connect('clicked', self.on_button_clicked)
        b2 = gtk.Button(stock=gtk.STOCK_CLOSE)
        vb.pack_start(b2)
        b2.connect('clicked', self.on_close_clicked)
        self.show_all()

        global debug

    def on_button_clicked(self, button):
        folder_to_zip = "/home/user/folder/with/lotsoffiles"
        file_count = sum((len(f) + len(d) for _, d, f in os.walk(folder_to_zip)))
        outFile = zipfile.ZipFile("/home/user/multithreadziptest.zip", "w", compression=zipfile.ZIP_DEFLATED)

        queue = Queue()

        producer = ProduceToQueue("Zipper", queue, self, file_count, outFile, folder_to_zip)
        consumer = ConsumeFromQueue("ProgressBar", queue, self, file_count)

        producer.start()
        consumer.start()

        producer.join()
        consumer.join()

        outFile.close()

        if debug:
            print "Done!"

    def on_close_clicked(self, widget):
        gtk.main_quit()

w = MainWindow()
gtk.main()

问题是在程序锁定大约7,000个文件后我必须强行退出它。我没有尝试过任何比这更少的文件,但我认为它可能会有同样的问题。此外,进度条不会更新。我知道它很混乱(编程风格明智,混合下划线和CamelCase,以及一般的noobish错误),但我想不出任何理由不能工作。

这是我最重要的地方:

http://www.java2s.com/Code/Python/File/Multithreadingzipfile.htm http://www.java2s.com/Tutorial/Python/0340__Thread/Multiplethreadsproducingconsumingvalues.htm

1 个答案:

答案 0 :(得分:0)

我猜file_count是错的,消费者会永远等待.get的另一个对象。将行更改为current = self.sharedObject.get(timeout=5),如果是这样的话,它应该在结尾处抛出错误。

此外,是的,您的代码存在许多问题 - 例如,当您使用GTK时,您根本不需要自己的线程。

GTK拥有自己的线程库,可以安全地使用gtks主循环。查看http://www.pardon-sleeuwaegen.be/antoon/python/page0.html等网页或google for“gtk threading”