问如何保护自己免受gzip或bzip2炸弹的攻击？

EN

class SafeUncompressor(object):
    """Small proxy class that enables external file object
    support for uncompressed, bzip2 and gzip files. Works transparently, and
    supports a maximum size to avoid zipbombs.
    """
    blocksize = 16 * 1024

    class FileTooLarge(Exception):
        pass

    def __init__(self, fileobj, maxsize=10*1024*1024):
        self.fileobj = fileobj
        self.name = getattr(self.fileobj, "name", None)
        self.maxsize = maxsize
        self.init()

    def init(self):
        import bz2
        import gzip
        self.pos = 0
        self.fileobj.seek(0)
        self.buf = ""
        self.format = "plain"

        magic = self.fileobj.read(2)
        if magic == '\037\213':
            self.format = "gzip"
            self.gzipobj = gzip.GzipFile(fileobj = self.fileobj, mode = 'r')
        elif magic == 'BZ':
            raise IOError, "bzip2 support in SafeUncompressor disabled, as self.bz2obj.decompress is not safe"
            self.format = "bz2"
            self.bz2obj = bz2.BZ2Decompressor()
        self.fileobj.seek(0)


    def read(self, size):
        b = [self.buf]
        x = len(self.buf)
        while x < size:
            if self.format == 'gzip':
                data = self.gzipobj.read(self.blocksize)
                if not data:
                    break
            elif self.format == 'bz2':
                raw = self.fileobj.read(self.blocksize)
                if not raw:
                    break
                # this can already bomb here, to some extend.
                # so disable bzip support until resolved.
                # Also monitor http://stackoverflow.com/questions/13622706/how-to-protect-myself-from-a-gzip-or-bzip2-bomb for ideas
                data = self.bz2obj.decompress(raw)
            else:
                data = self.fileobj.read(self.blocksize)
                if not data:
                    break
            b.append(data)
            x += len(data)

            if self.pos + x > self.maxsize:
                self.buf = ""
                self.pos = 0
                raise SafeUncompressor.FileTooLarge, "Compressed file too large"
        self.buf = "".join(b)

        buf = self.buf[:size]
        self.buf = self.buf[size:]
        self.pos += len(buf)
        return buf

    def seek(self, pos, whence=0):
        if whence != 0:
            raise IOError, "SafeUncompressor only supports whence=0"
        if pos < self.pos:
            self.init()
        self.read(pos - self.pos)

    def tell(self):
        return self.pos

import contextlib
import resource

@contextlib.contextmanager
def limit(limit, type=resource.RLIMIT_AS):
    soft_limit, hard_limit = resource.getrlimit(type)
    resource.setrlimit(type, (limit, hard_limit)) # set soft limit
    try:
        yield
    finally:
        resource.setrlimit(type, (soft_limit, hard_limit)) # restore

with limit(1 << 30): # 1GB 
    # do the thing that might try to consume all memory

#!/usr/bin/python
import sys
import zlib
f = open(sys.argv[1], "rb")
z = zlib.decompressobj(15+16)
total = 0
while True:
    buf = z.unconsumed_tail
    if buf == "":
        buf = f.read(1024)
        if buf == "":
            break
    got = z.decompress(buf, 4096)
    if got == "":
        break
    total += len(got)
print total
if z.unused_data != "" or f.read(1024) != "":
    print "warning: more input after end of gzip stream"

#!/usr/bin/python

import sys
import zlib

def decompn(f, z, n):
    """Return n uncompressed bytes, or fewer if at the end of the compressed
       stream.  This only decompresses as much as necessary, in order to
       avoid excessive memory usage for highly compressed input.
    """
    blk = ""
    while len(blk) < n:
        buf = z.unconsumed_tail
        if buf == "":
            buf = f.read(1024)
        got = z.decompress(buf, n - len(blk))
        blk += got
        if got == "":
            break
    return blk

f = open(sys.argv[1], "rb")
z = zlib.decompressobj(15+16)
total = 0
left = 0
while True:
    blk = decompn(f, z, 512)
    if len(blk) < 512:
        break
    if left == 0:
        if blk == "\0"*512:
            continue
        if blk[156] in ["1", "2", "3", "4", "5", "6"]:
            continue
        if blk[124] == 0x80:
            size = 0
            for i in range(125, 136):
                size <<= 8
                size += blk[i]
        else:
            size = int(blk[124:136].split()[0].split("\0")[0], 8)
        if blk[156] not in ["x", "g", "X", "L", "K"]:
                total += size
        left = (size + 511) // 512
    else:
        left -= 1
print total
if blk != "":
    print "warning: partial final block"
if left != 0:
    print "warning: tar file ended in the middle of an entry"
if z.unused_data != "" or f.read(1024) != "":
    print "warning: more input after end of gzip stream"