tests/benchmarks/plugins

"""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, os
import zlib
import builtins
import io

__all__ = ["GzipFile", "open", "compress", "decompress"]

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

READ, WRITE = 1, 2

def U32(i):
    """Return i as an unsigned integer, assuming it fits in 32 bits.
    If it's >= 2GB when viewed as a 32-bit unsigned int, return a long.
    """
    if i < 0:
        i += 1 << 32
    return i

def LOWU32(i):
    """Return the low-order 32 bits, as a non-negative int"""
    return i & 0xFFFFFFFF

def write32u(output, value):
    # The L format writes the bit pattern correctly whether signed
    # or unsigned.
    output.write(struct.pack("<L", value))

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

def open(filename, mode="rb", compresslevel=9):
    """Shorthand for GzipFile(filename, mode, compresslevel).

    The filename argument is required; mode defaults to 'rb'
    and compresslevel defaults to 9.

    """
    return GzipFile(filename, mode, compresslevel)

class _PaddedFile:
    """Minimal read-only file object that prepends a string to the contents
    of an actual file. Shouldn't be used outside of gzip.py, as it lacks
    essential functionality."""

    def __init__(self, f, prepend=b''):
        self._buffer = prepend
        self._length = len(prepend)
        self.file = f
        self._read = 0

    def read(self, size):
        if self._read is None:
            return self.file.read(size)
        if self._read + size <= self._length:
            read = self._read
            self._read += size
            return self._buffer[read:self._read]
        else:
            read = self._read
            self._read = None
            return self._buffer[read:] + \
                   self.file.read(size-self._length+read)

    def prepend(self, prepend=b'', readprevious=False):
        if self._read is None:
            self._buffer = prepend
        elif readprevious and len(prepend) <= self._read:
            self._read -= len(prepend)
            return
        else:
            self._buffer = self._buffer[read:] + prepend
        self._length = len(self._buffer)
        self._read = 0

    def unused(self):
        if self._read is None:
            return b''
        return self._buffer[self._read:]

    def seek(self, offset, whence=0):
        # This is only ever called with offset=whence=0
        if whence == 1 and self._read is not None:
            if 0 <= offset + self._read <= self._length:
                self._read += offset
                return
            else:
                offset += self._length - self._read
        self._read = None
        self._buffer = None
        return self.file.seek(offset, whence)

    def __getattr__(self, name):
        return getattr(self.file, name)


class GzipFile(io.BufferedIOBase):
    """The GzipFile class simulates most of the methods of a file object with
    the exception of the readinto() and truncate() methods.

    This class only supports opening files in binary mode. If you need to open a
    compressed file in text mode, wrap your GzipFile with an io.TextIOWrapper.

    """

    myfileobj = None
    max_read_chunk = 10 * 1024 * 1024   # 10Mb

    def __init__(self, filename=None, mode=None,
                 compresslevel=9, fileobj=None, mtime=None):
        """Constructor for the GzipFile class.

        At least one of fileobj and filename must be given a
        non-trivial value.

        The new class instance is based on fileobj, which can be a regular
        file, a StringIO object, or any other object which simulates a file.
        It defaults to None, in which case filename is opened to provide
        a file object.

        When fileobj is not None, the filename argument is only used to be
        included in the gzip file header, which may includes the original
        filename of the uncompressed file.  It defaults to the filename of
        fileobj, if discernible; otherwise, it defaults to the empty string,
        and in this case the original filename is not included in the header.

        The mode argument can be any of 'r', 'rb', 'a', 'ab', 'w', or 'wb',
        depending on whether the file will be read or written.  The default
        is the mode of fileobj if discernible; otherwise, the default is 'rb'.
        A mode of 'r' is equivalent to one of 'rb', and similarly for 'w' and
        'wb', and 'a' and 'ab'.

        The compresslevel argument is an integer from 1 to 9 controlling the
        level of compression; 1 is fastest and produces the least compression,
        and 9 is slowest and produces the most compression.  The default is 9.

        The mtime argument is an optional numeric timestamp to be written
        to the stream when compressing.  All gzip compressed streams
        are required to contain a timestamp.  If omitted or None, the
        current time is used.  This module ignores the timestamp when
        decompressing; however, some programs, such as gunzip, make use
        of it.  The format of the timestamp is the same as that of the
        return value of time.time() and of the st_mtime member of the
        object returned by os.stat().

        """

        if mode and ('t' in mode or 'U' in mode):
            raise IOError("Mode " + mode + " not supported")
        if mode and 'b' not in mode:
            mode += 'b'
        if fileobj is None:
            fileobj = self.myfileobj = builtins.open(filename, mode or 'rb')
        if filename is None:
            filename = getattr(fileobj, 'name', '')
            if not isinstance(filename, (str, bytes)):
                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 = True
            # Buffer data read from gzip file. extrastart is offset in
            # stream where buffer starts. extrasize is number of
            # bytes remaining in buffer from current stream position.
            self.extrabuf = b""
            self.extrasize = 0
            self.extrastart = 0
            self.name = filename
            # Starts small, scales exponentially
            self.min_readsize = 100
            fileobj = _PaddedFile(fileobj)

        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 IOError("Mode " + mode + " not supported")

        self.fileobj = fileobj
        self.offset = 0
        self.mtime = mtime

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

    @property
    def filename(self):
        import warnings
        warnings.warn("use the name attribute", DeprecationWarning, 2)
        if self.mode == WRITE and self.name[-3:] != ".gz":
            return self.name + ".gz"
        return self.name

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

    def _check_closed(self):
        """Raises a ValueError if the underlying file object has been closed.

        """
        if self.closed:
            raise ValueError('I/O operation on closed file.')

    def _init_write(self, filename):
        self.name = filename
        self.crc = zlib.crc32(b"") & 0xffffffff
        self.size = 0
        self.writebuf = []
        self.bufsize = 0

    def _write_gzip_header(self):
        self.fileobj.write(b'\037\213')             # magic header
        self.fileobj.write(b'\010')                 # compression method
        try:
            # RFC 1952 requires the FNAME field to be Latin-1. Do not
            # include filenames that cannot be represented that way.
            fname = os.path.basename(self.name)
            if not isinstance(fname, bytes):
                fname = fname.encode('latin-1')
            if fname.endswith(b'.gz'):
                fname = fname[:-3]
        except UnicodeEncodeError:
            fname = b''
        flags = 0
        if fname:
            flags = FNAME
        self.fileobj.write(chr(flags).encode('latin-1'))
        mtime = self.mtime
        if mtime is None:
            mtime = time.time()
        write32u(self.fileobj, int(mtime))
        self.fileobj.write(b'\002')
        self.fileobj.write(b'\377')
        if fname:
            self.fileobj.write(fname + b'\000')

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

    def _read_gzip_header(self):
        magic = self.fileobj.read(2)
        if magic == b'':
            raise EOFError("Reached EOF")

        if magic != b'\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) )
        self.mtime = read32(self.fileobj)
        # extraflag = self.fileobj.read(1)
        # os = self.fileobj.read(1)
        self.fileobj.read(2)

        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 True:
                s = self.fileobj.read(1)
                if not s or s==b'\000':
                    break
        if flag & FCOMMENT:
            # Read and discard a null-terminated string containing a comment
            while True:
                s = self.fileobj.read(1)
                if not s or s==b'\000':
                    break
        if flag & FHCRC:
            self.fileobj.read(2)     # Read & discard the 16-bit header CRC

        unused = self.fileobj.unused()
        if unused:
            uncompress = self.decompress.decompress(unused)
            self._add_read_data(uncompress)

    def write(self,data):
        self._check_closed()
        if self.mode != WRITE:
            import errno
            raise IOError(errno.EBADF, "write() on read-only GzipFile object")

        if self.fileobj is None:
            raise ValueError("write() on closed GzipFile object")

        # Convert data type if called by io.BufferedWriter.
        if isinstance(data, memoryview):
            data = data.tobytes()

        if len(data) > 0:
            self.size = self.size + len(data)
            self.crc = zlib.crc32(data, self.crc) & 0xffffffff
            self.fileobj.write( self.compress.compress(data) )
            self.offset += len(data)

        return len(data)

    def read(self, size=-1):
        self._check_closed()
        if self.mode != READ:
            import errno
            raise IOError(errno.EBADF, "read() on write-only GzipFile object")

        if self.extrasize <= 0 and self.fileobj is None:
            return b''

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