mirror of
https://github.com/python/cpython.git
synced 2024-12-18 14:24:33 +08:00
162 lines
5.7 KiB
Python
162 lines
5.7 KiB
Python
# Copyright (C) 2005-2010 Gregory P. Smith (greg@krypto.org)
|
|
# Licensed to PSF under a Contributor Agreement.
|
|
#
|
|
|
|
__doc__ = """hashlib module - A common interface to many hash functions.
|
|
|
|
new(name, data=b'') - returns a new hash object implementing the
|
|
given hash function; initializing the hash
|
|
using the given binary data.
|
|
|
|
Named constructor functions are also available, these are faster
|
|
than using new(name):
|
|
|
|
md5(), sha1(), sha224(), sha256(), sha384(), and sha512()
|
|
|
|
More algorithms may be available on your platform but the above are guaranteed
|
|
to exist. See the algorithms_guaranteed and algorithms_available attributes
|
|
to find out what algorithm names can be passed to new().
|
|
|
|
NOTE: If you want the adler32 or crc32 hash functions they are available in
|
|
the zlib module.
|
|
|
|
Choose your hash function wisely. Some have known collision weaknesses.
|
|
sha384 and sha512 will be slow on 32 bit platforms.
|
|
|
|
Hash objects have these methods:
|
|
- update(arg): Update the hash object with the bytes in arg. Repeated calls
|
|
are equivalent to a single call with the concatenation of all
|
|
the arguments.
|
|
- digest(): Return the digest of the bytes passed to the update() method
|
|
so far.
|
|
- hexdigest(): Like digest() except the digest is returned as a unicode
|
|
object of double length, containing only hexadecimal digits.
|
|
- copy(): Return a copy (clone) of the hash object. This can be used to
|
|
efficiently compute the digests of strings that share a common
|
|
initial substring.
|
|
|
|
For example, to obtain the digest of the string 'Nobody inspects the
|
|
spammish repetition':
|
|
|
|
>>> import hashlib
|
|
>>> m = hashlib.md5()
|
|
>>> m.update(b"Nobody inspects")
|
|
>>> m.update(b" the spammish repetition")
|
|
>>> m.digest()
|
|
b'\\xbbd\\x9c\\x83\\xdd\\x1e\\xa5\\xc9\\xd9\\xde\\xc9\\xa1\\x8d\\xf0\\xff\\xe9'
|
|
|
|
More condensed:
|
|
|
|
>>> hashlib.sha224(b"Nobody inspects the spammish repetition").hexdigest()
|
|
'a4337bc45a8fc544c03f52dc550cd6e1e87021bc896588bd79e901e2'
|
|
|
|
"""
|
|
|
|
# This tuple and __get_builtin_constructor() must be modified if a new
|
|
# always available algorithm is added.
|
|
__always_supported = ('md5', 'sha1', 'sha224', 'sha256', 'sha384', 'sha512',
|
|
'sha3_224', 'sha3_256', 'sha3_384', 'sha3_512')
|
|
|
|
algorithms_guaranteed = set(__always_supported)
|
|
algorithms_available = set(__always_supported)
|
|
|
|
__all__ = __always_supported + ('new', 'algorithms_guaranteed',
|
|
'algorithms_available')
|
|
|
|
|
|
def __get_builtin_constructor(name):
|
|
try:
|
|
if name in ('SHA1', 'sha1'):
|
|
import _sha1
|
|
return _sha1.sha1
|
|
elif name in ('MD5', 'md5'):
|
|
import _md5
|
|
return _md5.md5
|
|
elif name in ('SHA256', 'sha256', 'SHA224', 'sha224'):
|
|
import _sha256
|
|
bs = name[3:]
|
|
if bs == '256':
|
|
return _sha256.sha256
|
|
elif bs == '224':
|
|
return _sha256.sha224
|
|
elif name in ('SHA512', 'sha512', 'SHA384', 'sha384'):
|
|
import _sha512
|
|
bs = name[3:]
|
|
if bs == '512':
|
|
return _sha512.sha512
|
|
elif bs == '384':
|
|
return _sha512.sha384
|
|
elif name in {'sha3_224', 'sha3_256', 'sha3_384', 'sha3_512',
|
|
'SHA3_224', 'SHA3_256', 'SHA3_384', 'SHA3_512'}:
|
|
import _sha3
|
|
bs = name[5:]
|
|
if bs == '224':
|
|
return _sha3.sha3_224
|
|
elif bs == '256':
|
|
return _sha3.sha3_256
|
|
elif bs == '384':
|
|
return _sha3.sha3_384
|
|
elif bs == '512':
|
|
return _sha3.sha3_512
|
|
except ImportError:
|
|
pass # no extension module, this hash is unsupported.
|
|
|
|
raise ValueError('unsupported hash type ' + name)
|
|
|
|
|
|
def __get_openssl_constructor(name):
|
|
try:
|
|
f = getattr(_hashlib, 'openssl_' + name)
|
|
# Allow the C module to raise ValueError. The function will be
|
|
# defined but the hash not actually available thanks to OpenSSL.
|
|
f()
|
|
# Use the C function directly (very fast)
|
|
return f
|
|
except (AttributeError, ValueError):
|
|
return __get_builtin_constructor(name)
|
|
|
|
|
|
def __py_new(name, data=b''):
|
|
"""new(name, data=b'') - Return a new hashing object using the named algorithm;
|
|
optionally initialized with data (which must be bytes).
|
|
"""
|
|
return __get_builtin_constructor(name)(data)
|
|
|
|
|
|
def __hash_new(name, data=b''):
|
|
"""new(name, data=b'') - Return a new hashing object using the named algorithm;
|
|
optionally initialized with data (which must be bytes).
|
|
"""
|
|
try:
|
|
return _hashlib.new(name, data)
|
|
except ValueError:
|
|
# If the _hashlib module (OpenSSL) doesn't support the named
|
|
# hash, try using our builtin implementations.
|
|
# This allows for SHA224/256 and SHA384/512 support even though
|
|
# the OpenSSL library prior to 0.9.8 doesn't provide them.
|
|
return __get_builtin_constructor(name)(data)
|
|
|
|
|
|
try:
|
|
import _hashlib
|
|
new = __hash_new
|
|
__get_hash = __get_openssl_constructor
|
|
algorithms_available = algorithms_available.union(
|
|
_hashlib.openssl_md_meth_names)
|
|
except ImportError:
|
|
new = __py_new
|
|
__get_hash = __get_builtin_constructor
|
|
|
|
for __func_name in __always_supported:
|
|
# try them all, some may not work due to the OpenSSL
|
|
# version not supporting that algorithm.
|
|
try:
|
|
globals()[__func_name] = __get_hash(__func_name)
|
|
except ValueError:
|
|
import logging
|
|
logging.exception('code for hash %s was not found.', __func_name)
|
|
|
|
# Cleanup locals()
|
|
del __always_supported, __func_name, __get_hash
|
|
del __py_new, __hash_new, __get_openssl_constructor
|