diff options
Diffstat (limited to 'Lib/gzip.py')
| -rw-r--r-- | Lib/gzip.py | 101 |
1 files changed, 47 insertions, 54 deletions
diff --git a/Lib/gzip.py b/Lib/gzip.py index 67fe1d4..d2d6dd6 100644 --- a/Lib/gzip.py +++ b/Lib/gzip.py @@ -65,9 +65,6 @@ def write32u(output, value): # or unsigned. output.write(struct.pack("<L", value)) -def read32(input): - return struct.unpack("<I", input.read(4))[0] - 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 @@ -281,28 +278,32 @@ class GzipFile(io.BufferedIOBase): self.crc = zlib.crc32(b"") & 0xffffffff self.size = 0 + def _read_exact(self, n): + data = self.fileobj.read(n) + while len(data) < n: + b = self.fileobj.read(n - len(data)) + if not b: + raise EOFError("Compressed file ended before the " + "end-of-stream marker was reached") + data += b + return data + def _read_gzip_header(self): magic = self.fileobj.read(2) if magic == b'': - raise EOFError("Reached EOF") + return False if magic != b'\037\213': - raise IOError('Not a gzipped file') + raise OSError('Not a gzipped file') - method = ord( self.fileobj.read(1) ) + method, flag, self.mtime = struct.unpack("<BBIxx", self._read_exact(8)) 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) + raise OSError('Unknown compression method') 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) + extra_len, = struct.unpack("<H", self._read_exact(2)) + self._read_exact(extra_len) if flag & FNAME: # Read and discard a null-terminated string containing the filename while True: @@ -316,18 +317,19 @@ class GzipFile(io.BufferedIOBase): if not s or s==b'\000': break if flag & FHCRC: - self.fileobj.read(2) # Read & discard the 16-bit header CRC + self._read_exact(2) # Read & discard the 16-bit header CRC unused = self.fileobj.unused() if unused: uncompress = self.decompress.decompress(unused) self._add_read_data(uncompress) + return True def write(self,data): self._check_closed() if self.mode != WRITE: import errno - raise IOError(errno.EBADF, "write() on read-only GzipFile object") + raise OSError(errno.EBADF, "write() on read-only GzipFile object") if self.fileobj is None: raise ValueError("write() on closed GzipFile object") @@ -348,27 +350,23 @@ class GzipFile(io.BufferedIOBase): self._check_closed() if self.mode != READ: import errno - raise IOError(errno.EBADF, "read() on write-only GzipFile object") + raise OSError(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 + while self._read(readsize): + readsize = min(self.max_read_chunk, readsize * 2) + size = self.extrasize else: # just get some more of it - try: - while size > self.extrasize: - self._read(readsize) - readsize = min(self.max_read_chunk, readsize * 2) - except EOFError: - if size > self.extrasize: - size = self.extrasize + while size > self.extrasize: + if not self._read(readsize): + if size > self.extrasize: + size = self.extrasize + break + readsize = min(self.max_read_chunk, readsize * 2) offset = self.offset - self.extrastart chunk = self.extrabuf[offset: offset + size] @@ -381,17 +379,14 @@ class GzipFile(io.BufferedIOBase): self._check_closed() if self.mode != READ: import errno - raise IOError(errno.EBADF, "read1() on write-only GzipFile object") + raise OSError(errno.EBADF, "read1() on write-only GzipFile object") if self.extrasize <= 0 and self.fileobj is None: return b'' - try: - # For certain input data, a single call to _read() may not return - # any data. In this case, retry until we get some data or reach EOF. - while self.extrasize <= 0: - self._read() - except EOFError: + # For certain input data, a single call to _read() may not return + # any data. In this case, retry until we get some data or reach EOF. + while self.extrasize <= 0 and self._read(): pass if size < 0 or size > self.extrasize: size = self.extrasize @@ -405,7 +400,7 @@ class GzipFile(io.BufferedIOBase): def peek(self, n): if self.mode != READ: import errno - raise IOError(errno.EBADF, "peek() on write-only GzipFile object") + raise OSError(errno.EBADF, "peek() on write-only GzipFile object") # Do not return ridiculously small buffers, for one common idiom # is to call peek(1) and expect more bytes in return. @@ -414,12 +409,9 @@ class GzipFile(io.BufferedIOBase): if self.extrasize == 0: if self.fileobj is None: return b'' - try: - # Ensure that we don't return b"" if we haven't reached EOF. - while self.extrasize == 0: - # 1024 is the same buffering heuristic used in read() - self._read(max(n, 1024)) - except EOFError: + # Ensure that we don't return b"" if we haven't reached EOF. + # 1024 is the same buffering heuristic used in read() + while self.extrasize == 0 and self._read(max(n, 1024)): pass offset = self.offset - self.extrastart remaining = self.extrasize @@ -432,13 +424,14 @@ class GzipFile(io.BufferedIOBase): def _read(self, size=1024): if self.fileobj is None: - raise EOFError("Reached EOF") + return False if self._new_member: # If the _new_member flag is set, we have to # jump to the next member, if there is one. self._init_read() - self._read_gzip_header() + if not self._read_gzip_header(): + return False self.decompress = zlib.decompressobj(-zlib.MAX_WBITS) self._new_member = False @@ -455,7 +448,7 @@ class GzipFile(io.BufferedIOBase): self.fileobj.prepend(self.decompress.unused_data, True) self._read_eof() self._add_read_data( uncompress ) - raise EOFError('Reached EOF') + return False uncompress = self.decompress.decompress(buf) self._add_read_data( uncompress ) @@ -471,6 +464,7 @@ class GzipFile(io.BufferedIOBase): # a new member on the next call self._read_eof() self._new_member = True + return True def _add_read_data(self, data): self.crc = zlib.crc32(data, self.crc) & 0xffffffff @@ -485,13 +479,12 @@ class GzipFile(io.BufferedIOBase): # We check the that the computed CRC and size of the # uncompressed data matches the stored values. Note that the size # stored is the true file size mod 2**32. - crc32 = read32(self.fileobj) - isize = read32(self.fileobj) # may exceed 2GB + crc32, isize = struct.unpack("<II", self._read_exact(8)) if crc32 != self.crc: - raise IOError("CRC check failed %s != %s" % (hex(crc32), + raise OSError("CRC check failed %s != %s" % (hex(crc32), hex(self.crc))) elif isize != (self.size & 0xffffffff): - raise IOError("Incorrect length of data produced") + raise OSError("Incorrect length of data produced") # Gzip files can be padded with zeroes and still have archives. # Consume all zero bytes and set the file position to the first @@ -540,7 +533,7 @@ class GzipFile(io.BufferedIOBase): '''Return the uncompressed stream file position indicator to the beginning of the file''' if self.mode != READ: - raise IOError("Can't rewind in write mode") + raise OSError("Can't rewind in write mode") self.fileobj.seek(0) self._new_member = True self.extrabuf = b"" @@ -565,7 +558,7 @@ class GzipFile(io.BufferedIOBase): raise ValueError('Seek from end not supported') if self.mode == WRITE: if offset < self.offset: - raise IOError('Negative seek in write mode') + raise OSError('Negative seek in write mode') count = offset - self.offset chunk = bytes(1024) for i in range(count // 1024): |