如何从7z压缩的文本文件中读取？

Question

我想从csv(文本)文件中逐行读取(在Python 2.7中),该文件是7z压缩的.我不想解压缩整个(大)文件,而是要对行进行流式处理.

我尝试pylzma.decompressobj()失败了.我收到数据错误.请注意,此代码尚未逐行读取:

input_filename = r"testing.csv.7z"
with open(input_filename, 'rb') as infile:
    obj = pylzma.decompressobj()
    o = open('decompressed.raw', 'wb')
    obj = pylzma.decompressobj()
    while True:
        tmp = infile.read(1)
        if not tmp: break
        o.write(obj.decompress(tmp))
    o.close()

输出:

    o.write(obj.decompress(tmp))
ValueError: data error during decompression

Answer 1

这将允许您迭代线.它部分源于我在另一个问题的答案中找到的一些代码.

据我所知,在这个时间点,pylzma-0.5.0它没有提供允许存档成员作为字节流或字符流读取的API - 它的py7zlib类只提供一个ArchiveFile解压缩并返回所有未压缩数据的函数.一旦包含该成员.鉴于此,您可以做的最好的事情是使用它作为缓冲区迭代地返回字节或行.以下是这样做,但如果问题是存档成员文件本身很大,许多人没有帮助.

我修改了下面的代码,以便在Python 2.7和3.x中工作.

import io
import os
import py7zlib


class SevenZFileError(py7zlib.ArchiveError):
    pass

class SevenZFile(object):
    @classmethod
    def is_7zfile(cls, filepath):
        """ Determine if filepath points to a valid 7z archive. """
        is7z = False
        fp = None
        try:
            fp = open(filepath, 'rb')
            archive = py7zlib.Archive7z(fp)
            _ = len(archive.getnames())
            is7z = True
        finally:
            if fp: fp.close()
        return is7z

    def __init__(self, filepath):
        fp = open(filepath, 'rb')
        self.filepath = filepath
        self.archive = py7zlib.Archive7z(fp)

    def __contains__(self, name):
        return name in self.archive.getnames()

    def readlines(self, name, newline=''):
        r""" Iterator of lines from named archive member.

        `newline` controls how line endings are handled.

        It can be None, '', '\n', '\r', and '\r\n' and works the same way as it does
        in StringIO. Note however that the default value is different and is to enable
        universal newlines mode, but line endings are returned untranslated.
        """
        archivefile = self.archive.getmember(name)
        if not archivefile:
            raise SevenZFileError('archive member %r not found in %r' %
                                  (name, self.filepath))

        # Decompress entire member and return its contents iteratively.
        data = archivefile.read().decode()
        for line in io.StringIO(data, newline=newline):
            yield line


if __name__ == '__main__':

    import csv

    if SevenZFile.is_7zfile('testing.csv.7z'):
        sevenZfile = SevenZFile('testing.csv.7z')

        if 'testing.csv' not in sevenZfile:
            print('testing.csv is not a member of testing.csv.7z')
        else:
            reader = csv.reader(sevenZfile.readlines('testing.csv'))
            for row in reader:
                print(', '.join(row))

样品用法:

import io
import os
import py7zlib


class SevenZFileError(py7zlib.ArchiveError):
    pass

class SevenZFile(object):
    @classmethod
    def is_7zfile(cls, filepath):
        """ Determine if filepath points to a valid 7z archive. """
        is7z = False
        fp = None
        try:
            fp = open(filepath, 'rb')
            archive = py7zlib.Archive7z(fp)
            _ = len(archive.getnames())
            is7z = True
        finally:
            if fp: fp.close()
        return is7z

    def __init__(self, filepath):
        fp = open(filepath, 'rb')
        self.filepath = filepath
        self.archive = py7zlib.Archive7z(fp)

    def __contains__(self, name):
        return name in self.archive.getnames()

    def readlines(self, name, newline=''):
        r""" Iterator of lines from named archive member.

        `newline` controls how line endings are handled.

        It can be None, '', '\n', '\r', and '\r\n' and works the same way as it does
        in StringIO. Note however that the default value is different and is to enable
        universal newlines mode, but line endings are returned untranslated.
        """
        archivefile = self.archive.getmember(name)
        if not archivefile:
            raise SevenZFileError('archive member %r not found in %r' %
                                  (name, self.filepath))

        # Decompress entire member and return its contents iteratively.
        data = archivefile.read().decode()
        for line in io.StringIO(data, newline=newline):
            yield line


if __name__ == '__main__':

    import csv

    if SevenZFile.is_7zfile('testing.csv.7z'):
        sevenZfile = SevenZFile('testing.csv.7z')

        if 'testing.csv' not in sevenZfile:
            print('testing.csv is not a member of testing.csv.7z')
        else:
            reader = csv.reader(sevenZfile.readlines('testing.csv'))
            for row in reader:
                print(', '.join(row))