diff --git a/Doc/library/binascii.rst b/Doc/library/binascii.rst index e3f134b53ac..b3b4aac8735 100644 --- a/Doc/library/binascii.rst +++ b/Doc/library/binascii.rst @@ -110,15 +110,16 @@ The :mod:`binascii` module defines the following functions: possibly the last fragment). -.. function:: crc_hqx(data, crc) +.. function:: crc_hqx(data, value) - Compute the binhex4 crc value of *data*, starting with an initial *crc* and - returning the result. + Compute the binhex4 crc value of *data*, starting with *value* as the + initial crc, and return the result. -.. function:: crc32(data[, crc]) +.. function:: crc32(data[, value]) - Compute CRC-32, the 32-bit checksum of data, starting with an initial crc. This + Compute CRC-32, the 32-bit checksum of *data*, starting with an + initial CRC of *value*. The default initial CRC is zero. The algorithm is consistent with the ZIP file checksum. Since the algorithm is designed for use as a checksum algorithm, it is not suitable for use as a general hash algorithm. Use as follows:: @@ -126,15 +127,13 @@ The :mod:`binascii` module defines the following functions: print(binascii.crc32(b"hello world")) # Or, in two pieces: crc = binascii.crc32(b"hello") - crc = binascii.crc32(b" world", crc) & 0xffffffff + crc = binascii.crc32(b" world", crc) print('crc32 = {:#010x}'.format(crc)) -.. note:: - To generate the same numeric value across all Python versions and - platforms use crc32(data) & 0xffffffff. If you are only using - the checksum in packed binary format this is not necessary as the - return value is the correct 32bit binary representation - regardless of sign. + .. versionchanged:: 3.0 + The result is always unsigned. + To generate the same numeric value across all Python versions and + platforms, use ``crc32(data) & 0xffffffff``. .. function:: b2a_hex(data) diff --git a/Doc/library/zlib.rst b/Doc/library/zlib.rst index 58fc31b0952..a815d1fb18b 100644 --- a/Doc/library/zlib.rst +++ b/Doc/library/zlib.rst @@ -31,22 +31,19 @@ The available exception and functions in this module are: .. function:: adler32(data[, value]) Computes an Adler-32 checksum of *data*. (An Adler-32 checksum is almost as - reliable as a CRC32 but can be computed much more quickly.) If *value* is - present, it is used as the starting value of the checksum; otherwise, a fixed - default value is used. This allows computing a running checksum over the + reliable as a CRC32 but can be computed much more quickly.) The result + is an unsigned 32-bit integer. If *value* is present, it is used as + the starting value of the checksum; otherwise, a default value of 1 + is used. Passing in *value* allows computing a running checksum over the concatenation of several inputs. The algorithm is not cryptographically strong, and should not be used for authentication or digital signatures. Since the algorithm is designed for use as a checksum algorithm, it is not suitable for use as a general hash algorithm. - Always returns an unsigned 32-bit integer. - -.. note:: - To generate the same numeric value across all Python versions and - platforms use adler32(data) & 0xffffffff. If you are only using - the checksum in packed binary format this is not necessary as the - return value is the correct 32bit binary representation - regardless of sign. + .. versionchanged:: 3.0 + Always returns an unsigned value. + To generate the same numeric value across all Python versions and + platforms, use ``adler32(data) & 0xffffffff``. .. function:: compress(data[, level]) @@ -97,23 +94,19 @@ The available exception and functions in this module are: single: Cyclic Redundancy Check single: checksum; Cyclic Redundancy Check - Computes a CRC (Cyclic Redundancy Check) checksum of *data*. If *value* is - present, it is used as the starting value of the checksum; otherwise, a fixed - default value is used. This allows computing a running checksum over the + Computes a CRC (Cyclic Redundancy Check) checksum of *data*. The + result is an unsigned 32-bit integer. If *value* is present, it is used + as the starting value of the checksum; otherwise, a default value of 0 + is used. Passing in *value* allows computing a running checksum over the concatenation of several inputs. The algorithm is not cryptographically strong, and should not be used for authentication or digital signatures. Since the algorithm is designed for use as a checksum algorithm, it is not suitable for use as a general hash algorithm. - Always returns an unsigned 32-bit integer. - - .. note:: - + .. versionchanged:: 3.0 + Always returns an unsigned value. To generate the same numeric value across all Python versions and - platforms, use ``crc32(data) & 0xffffffff``. If you are only using - the checksum in packed binary format this is not necessary as the - return value is the correct 32-bit binary representation - regardless of sign. + platforms, use ``crc32(data) & 0xffffffff``. .. function:: decompress(data[, wbits[, bufsize]]) diff --git a/Lib/gzip.py b/Lib/gzip.py index 45152e440d5..3a2b322732a 100644 --- a/Lib/gzip.py +++ b/Lib/gzip.py @@ -210,7 +210,7 @@ class GzipFile(_compression.BaseStream): def _init_write(self, filename): self.name = filename - self.crc = zlib.crc32(b"") & 0xffffffff + self.crc = zlib.crc32(b"") self.size = 0 self.writebuf = [] self.bufsize = 0 @@ -261,7 +261,7 @@ class GzipFile(_compression.BaseStream): if length > 0: self.fileobj.write(self.compress.compress(data)) self.size += length - self.crc = zlib.crc32(data, self.crc) & 0xffffffff + self.crc = zlib.crc32(data, self.crc) self.offset += length return length @@ -381,7 +381,7 @@ class _GzipReader(_compression.DecompressReader): self._last_mtime = None def _init_read(self): - self._crc = zlib.crc32(b"") & 0xffffffff + self._crc = zlib.crc32(b"") self._stream_size = 0 # Decompressed size of unconcatenated stream def _read_exact(self, n): @@ -485,7 +485,7 @@ class _GzipReader(_compression.DecompressReader): return uncompress def _add_read_data(self, data): - self._crc = zlib.crc32(data, self._crc) & 0xffffffff + self._crc = zlib.crc32(data, self._crc) self._stream_size = self._stream_size + len(data) def _read_eof(self): diff --git a/Lib/tarfile.py b/Lib/tarfile.py index ca45126ff13..9d22c8e37f8 100755 --- a/Lib/tarfile.py +++ b/Lib/tarfile.py @@ -459,13 +459,7 @@ class _Stream: self.fileobj.write(self.buf) self.buf = b"" if self.comptype == "gz": - # The native zlib crc is an unsigned 32-bit integer, but - # the Python wrapper implicitly casts that to a signed C - # long. So, on a 32-bit box self.crc may "look negative", - # while the same crc on a 64-bit box may "look positive". - # To avoid irksome warnings from the `struct` module, force - # it to look positive on all boxes. - self.fileobj.write(struct.pack("