Staging
v0.5.1
https://github.com/python/cpython
Revision a4dd011259fa6f3079bd0efd95b3a136c0e3c190 authored by Guido van Rossum on 15 April 2001, 22:16:26 UTC, committed by Guido van Rossum on 15 April 2001, 22:16:26 UTC
and reported to python-dev: because we were calling dict_resize() in
PyDict_Next(), and because GC's dict_traverse() uses PyDict_Next(),
and because PyTuple_New() can cause GC, and because dict_items() calls
PyTuple_New(), it was possible for dict_items() to have the dict
resized right under its nose.

The solution is convoluted, and touches several places: keys(),
values(), items(), popitem(), PyDict_Next(), and PyDict_SetItem().

There are two parts to it. First, we no longer call dict_resize() in
PyDict_Next(), which seems to solve the immediate problem.  But then
PyDict_SetItem() must have a different policy about when *it* calls
dict_resize(), because we want to guarantee (e.g. for an algorithm
that Jeremy uses in the compiler) that you can loop over a dict using
PyDict_Next() and make changes to the dict as long as those changes
are only value replacements for existing keys using PyDict_SetItem().
This is done by resizing *after* the insertion instead of before, and
by remembering the size before we insert the item, and if the size is
still the same, we don't bother to even check if we might need to
resize.  An additional detail is that if the dict starts out empty, we
must still resize it before the insertion.

That was the first part. :-)

The second part is to make keys(), values(), items(), and popitem()
safe against side effects on the dict caused by allocations, under the
assumption that if the GC can cause arbitrary Python code to run, it
can cause other threads to run, and it's not inconceivable that our
dict could be resized -- it would be insane to write code that relies
on this, but not all code is sane.

Now, I have this nagging feeling that the loops in lookdict probably
are blissfully assuming that doing a simple key comparison does not
change the dict's size.  This is not necessarily true (the keys could
be class instances after all).  But that's a battle for another day.
1 parent 0aa30b0
Raw File
Tip revision: a4dd011259fa6f3079bd0efd95b3a136c0e3c190 authored by Guido van Rossum on 15 April 2001, 22:16:26 UTC
Tentative fix for a problem that Tim discovered at the last moment,
Tip revision: a4dd011
gzip.py
"""Functions that read and write gzipped files.

The user of the file doesn't have to worry about the compression,
but random access is not allowed."""

# based on Andrew Kuchling's minigzip.py distributed with the zlib module

import struct, sys, time
import zlib
import __builtin__

__all__ = ["GzipFile","open"]

FTEXT, FHCRC, FEXTRA, FNAME, FCOMMENT = 1, 2, 4, 8, 16

READ, WRITE = 1, 2

def write32(output, value):
    output.write(struct.pack("<l", value))

def write32u(output, value):
    if value < 0:
        value = value + 0x100000000L
    output.write(struct.pack("<L", value))

def read32(input):
    return struct.unpack("<l", input.read(4))[0]

def open(filename, mode="rb", compresslevel=9):
    return GzipFile(filename, mode, compresslevel)

class GzipFile:

    myfileobj = None

    def __init__(self, filename=None, mode=None,
                 compresslevel=9, fileobj=None):
        if fileobj is None:
            fileobj = self.myfileobj = __builtin__.open(filename, mode or 'rb')
        if filename is None:
            if hasattr(fileobj, 'name'): filename = fileobj.name
            else: filename = ''
        if mode is None:
            if hasattr(fileobj, 'mode'): mode = fileobj.mode
            else: mode = 'rb'

        if mode[0:1] == 'r':
            self.mode = READ
            # Set flag indicating start of a new member
            self._new_member = 1
            self.extrabuf = ""
            self.extrasize = 0
            self.filename = filename

        elif mode[0:1] == 'w' or mode[0:1] == 'a':
            self.mode = WRITE
            self._init_write(filename)
            self.compress = zlib.compressobj(compresslevel,
                                             zlib.DEFLATED,
                                             -zlib.MAX_WBITS,
                                             zlib.DEF_MEM_LEVEL,
                                             0)
        else:
            raise ValueError, "Mode " + mode + " not supported"

        self.fileobj = fileobj

        if self.mode == WRITE:
            self._write_gzip_header()

    def __repr__(self):
        s = repr(self.fileobj)
        return '<gzip ' + s[1:-1] + ' ' + hex(id(self)) + '>'

    def _init_write(self, filename):
        if filename[-3:] != '.gz':
            filename = filename + '.gz'
        self.filename = filename
        self.crc = zlib.crc32("")
        self.size = 0
        self.writebuf = []
        self.bufsize = 0

    def _write_gzip_header(self):
        self.fileobj.write('\037\213')             # magic header
        self.fileobj.write('\010')                 # compression method
        fname = self.filename[:-3]
        flags = 0
        if fname:
            flags = FNAME
        self.fileobj.write(chr(flags))
        write32u(self.fileobj, long(time.time()))
        self.fileobj.write('\002')
        self.fileobj.write('\377')
        if fname:
            self.fileobj.write(fname + '\000')

    def _init_read(self):
        self.crc = zlib.crc32("")
        self.size = 0

    def _read_gzip_header(self):
        magic = self.fileobj.read(2)
        if magic != '\037\213':
            raise IOError, 'Not a gzipped file'
        method = ord( self.fileobj.read(1) )
        if method != 8:
            raise IOError, 'Unknown compression method'
        flag = ord( self.fileobj.read(1) )
        # modtime = self.fileobj.read(4)
        # extraflag = self.fileobj.read(1)
        # os = self.fileobj.read(1)
        self.fileobj.read(6)

        if flag & FEXTRA:
            # Read & discard the extra field, if present
            xlen=ord(self.fileobj.read(1))
            xlen=xlen+256*ord(self.fileobj.read(1))
            self.fileobj.read(xlen)
        if flag & FNAME:
            # Read and discard a null-terminated string containing the filename
            while (1):
                s=self.fileobj.read(1)
                if not s or s=='\000': break
        if flag & FCOMMENT:
            # Read and discard a null-terminated string containing a comment
            while (1):
                s=self.fileobj.read(1)
                if not s or s=='\000': break
        if flag & FHCRC:
            self.fileobj.read(2)     # Read & discard the 16-bit header CRC


    def write(self,data):
        if self.fileobj is None:
            raise ValueError, "write() on closed GzipFile object"
        if len(data) > 0:
            self.size = self.size + len(data)
            self.crc = zlib.crc32(data, self.crc)
            self.fileobj.write( self.compress.compress(data) )

    def writelines(self,lines):
        self.write(" ".join(lines))

    def read(self, size=-1):
        if self.extrasize <= 0 and self.fileobj is None:
            return ''

        readsize = 1024
        if size < 0:        # get the whole thing
            try:
                while 1:
                    self._read(readsize)
                    readsize = readsize * 2
            except EOFError:
                size = self.extrasize
        else:               # just get some more of it
            try:
                while size > self.extrasize:
                    self._read(readsize)
                    readsize = readsize * 2
            except EOFError:
                if size > self.extrasize:
                    size = self.extrasize

        chunk = self.extrabuf[:size]
        self.extrabuf = self.extrabuf[size:]
        self.extrasize = self.extrasize - size

        return chunk

    def _unread(self, buf):
        self.extrabuf = buf + self.extrabuf
        self.extrasize = len(buf) + self.extrasize

    def _read(self, size=1024):
        if self.fileobj is None: raise EOFError, "Reached EOF"

        if self._new_member:
            # If the _new_member flag is set, we have to
            # jump to the next member, if there is one.
            #
            # First, check if we're at the end of the file;
            # if so, it's time to stop; no more members to read.
            pos = self.fileobj.tell()   # Save current position
            self.fileobj.seek(0, 2)     # Seek to end of file
            if pos == self.fileobj.tell():
                self.fileobj = None
                raise EOFError, "Reached EOF"
            else:
                self.fileobj.seek( pos ) # Return to original position

            self._init_read()
            self._read_gzip_header()
            self.decompress = zlib.decompressobj(-zlib.MAX_WBITS)
            self._new_member = 0

        # Read a chunk of data from the file
        buf = self.fileobj.read(size)

        # If the EOF has been reached, flush the decompression object
        # and mark this object as finished.

        if buf == "":
            uncompress = self.decompress.flush()
            self._read_eof()
            self.fileobj = None
            self._add_read_data( uncompress )
            raise EOFError, 'Reached EOF'

        uncompress = self.decompress.decompress(buf)
        self._add_read_data( uncompress )

        if self.decompress.unused_data != "":
            # Ending case: we've come to the end of a member in the file,
            # so seek back to the start of the unused data, finish up
            # this member, and read a new gzip header.
            # (The number of bytes to seek back is the length of the unused
            # data, minus 8 because _read_eof() will rewind a further 8 bytes)
            self.fileobj.seek( -len(self.decompress.unused_data)+8, 1)

            # Check the CRC and file size, and set the flag so we read
            # a new member on the next call
            self._read_eof()
            self._new_member = 1

    def _add_read_data(self, data):
        self.crc = zlib.crc32(data, self.crc)
        self.extrabuf = self.extrabuf + data
        self.extrasize = self.extrasize + len(data)
        self.size = self.size + len(data)

    def _read_eof(self):
        # We've read to the end of the file, so we have to rewind in order
        # to reread the 8 bytes containing the CRC and the file size.
        # We check the that the computed CRC and size of the
        # uncompressed data matches the stored values.
        self.fileobj.seek(-8, 1)
        crc32 = read32(self.fileobj)
        isize = read32(self.fileobj)
        if crc32%0x100000000L != self.crc%0x100000000L:
            raise ValueError, "CRC check failed"
        elif isize != self.size:
            raise ValueError, "Incorrect length of data produced"

    def close(self):
        if self.mode == WRITE:
            self.fileobj.write(self.compress.flush())
            write32(self.fileobj, self.crc)
            write32(self.fileobj, self.size)
            self.fileobj = None
        elif self.mode == READ:
            self.fileobj = None
        if self.myfileobj:
            self.myfileobj.close()
            self.myfileobj = None

    def __del__(self):
        try:
            if (self.myfileobj is None and
                self.fileobj is None):
                return
        except AttributeError:
            return
        self.close()

    def flush(self):
        self.fileobj.flush()

    def isatty(self):
        return 0

    def readline(self, size=-1):
        if size < 0: size = sys.maxint
        bufs = []
        orig_size = size
        readsize = min(100, size)    # Read from the file in small chunks
        while 1:
            if size == 0:
                return "".join(bufs) # Return resulting line

            c = self.read(readsize)
            i = c.find('\n')
            if size is not None:
                # We set i=size to break out of the loop under two
                # conditions: 1) there's no newline, and the chunk is
                # larger than size, or 2) there is a newline, but the
                # resulting line would be longer than 'size'.
                if i==-1 and len(c) > size: i=size-1
                elif size <= i: i = size -1

            if i >= 0 or c == '':
                bufs.append(c[:i+1])    # Add portion of last chunk
                self._unread(c[i+1:])   # Push back rest of chunk
                return ''.join(bufs)    # Return resulting line

            # Append chunk to list, decrease 'size',
            bufs.append(c)
            size = size - len(c)
            readsize = min(size, readsize * 2)

    def readlines(self, sizehint=0):
        # Negative numbers result in reading all the lines
        if sizehint <= 0: sizehint = sys.maxint
        L = []
        while sizehint > 0:
            line = self.readline()
            if line == "": break
            L.append( line )
            sizehint = sizehint - len(line)

        return L

    def writelines(self, L):
        for line in L:
            self.write(line)


def _test():
    # Act like gzip; with -d, act like gunzip.
    # The input file is not deleted, however, nor are any other gzip
    # options or features supported.
    import sys
    args = sys.argv[1:]
    decompress = args and args[0] == "-d"
    if decompress:
        args = args[1:]
    if not args:
        args = ["-"]
    for arg in args:
        if decompress:
            if arg == "-":
                f = GzipFile(filename="", mode="rb", fileobj=sys.stdin)
                g = sys.stdout
            else:
                if arg[-3:] != ".gz":
                    print "filename doesn't end in .gz:", `arg`
                    continue
                f = open(arg, "rb")
                g = __builtin__.open(arg[:-3], "wb")
        else:
            if arg == "-":
                f = sys.stdin
                g = GzipFile(filename="", mode="wb", fileobj=sys.stdout)
            else:
                f = __builtin__.open(arg, "rb")
                g = open(arg + ".gz", "wb")
        while 1:
            chunk = f.read(1024)
            if not chunk:
                break
            g.write(chunk)
        if g is not sys.stdout:
            g.close()
        if f is not sys.stdin:
            f.close()

if __name__ == '__main__':
    _test()
back to top