From d6b13283d19b3229ec1aee62bf7b4747c581ddab Mon Sep 17 00:00:00 2001 From: "Wladimir J. van der Laan" Date: Sat, 29 Sep 2012 11:13:32 +0200 Subject: data-driven base58 CBitcoinAddress/CBitcoinSecret tests Arbitrary numbers of test vectors can be generated using the script `gen_base58_test_vectors.py`. --- contrib/testgen/README | 1 + contrib/testgen/base58.py | 104 ++++++++++++++++++++++++ contrib/testgen/gen_base58_test_vectors.py | 126 +++++++++++++++++++++++++++++ 3 files changed, 231 insertions(+) create mode 100644 contrib/testgen/README create mode 100644 contrib/testgen/base58.py create mode 100755 contrib/testgen/gen_base58_test_vectors.py (limited to 'contrib') diff --git a/contrib/testgen/README b/contrib/testgen/README new file mode 100644 index 0000000000..02d6c4cdc2 --- /dev/null +++ b/contrib/testgen/README @@ -0,0 +1 @@ +Utilities to generate test vectors for the data-driven Bitcoin tests diff --git a/contrib/testgen/base58.py b/contrib/testgen/base58.py new file mode 100644 index 0000000000..b716495145 --- /dev/null +++ b/contrib/testgen/base58.py @@ -0,0 +1,104 @@ +''' +Bitcoin base58 encoding and decoding. + +Based on https://bitcointalk.org/index.php?topic=1026.0 (public domain) +''' +import hashlib + +# for compatibility with following code... +class SHA256: + new = hashlib.sha256 + +if str != bytes: + # Python 3.x + def ord(c): + return c + def chr(n): + return bytes( (n,) ) + +__b58chars = '123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz' +__b58base = len(__b58chars) +b58chars = __b58chars + +def b58encode(v): + """ encode v, which is a string of bytes, to base58. + """ + long_value = 0 + for (i, c) in enumerate(v[::-1]): + long_value += (256**i) * ord(c) + + result = '' + while long_value >= __b58base: + div, mod = divmod(long_value, __b58base) + result = __b58chars[mod] + result + long_value = div + result = __b58chars[long_value] + result + + # Bitcoin does a little leading-zero-compression: + # leading 0-bytes in the input become leading-1s + nPad = 0 + for c in v: + if c == '\0': nPad += 1 + else: break + + return (__b58chars[0]*nPad) + result + +def b58decode(v, length = None): + """ decode v into a string of len bytes + """ + long_value = 0 + for (i, c) in enumerate(v[::-1]): + long_value += __b58chars.find(c) * (__b58base**i) + + result = bytes() + while long_value >= 256: + div, mod = divmod(long_value, 256) + result = chr(mod) + result + long_value = div + result = chr(long_value) + result + + nPad = 0 + for c in v: + if c == __b58chars[0]: nPad += 1 + else: break + + result = chr(0)*nPad + result + if length is not None and len(result) != length: + return None + + return result + +def checksum(v): + """Return 32-bit checksum based on SHA256""" + return SHA256.new(SHA256.new(v).digest()).digest()[0:4] + +def b58encode_chk(v): + """b58encode a string, with 32-bit checksum""" + return b58encode(v + checksum(v)) + +def b58decode_chk(v): + """decode a base58 string, check and remove checksum""" + result = b58decode(v) + if result is None: + return None + h3 = checksum(result[:-4]) + if result[-4:] == checksum(result[:-4]): + return result[:-4] + else: + return None + +def get_bcaddress_version(strAddress): + """ Returns None if strAddress is invalid. Otherwise returns integer version of address. """ + addr = b58decode_chk(strAddress) + if addr is None or len(addr)!=21: return None + version = addr[0] + return ord(version) + +if __name__ == '__main__': + # Test case (from http://gitorious.org/bitcoin/python-base58.git) + assert get_bcaddress_version('15VjRaDX9zpbA8LVnbrCAFzrVzN7ixHNsC') is 0 + _ohai = 'o hai'.encode('ascii') + _tmp = b58encode(_ohai) + assert _tmp == 'DYB3oMS' + assert b58decode(_tmp, 5) == _ohai + print("Tests passed") diff --git a/contrib/testgen/gen_base58_test_vectors.py b/contrib/testgen/gen_base58_test_vectors.py new file mode 100755 index 0000000000..1813436953 --- /dev/null +++ b/contrib/testgen/gen_base58_test_vectors.py @@ -0,0 +1,126 @@ +#!/usr/bin/env python +''' +Generate valid and invalid base58 address and private key test vectors. + +Usage: + gen_base58_test_vectors.py valid 50 > ../../src/test/data/base58_keys_valid.json + gen_base58_test_vectors.py invalid 50 > ../../src/test/data/base58_keys_invalid.json +''' +# 2012 Wladimir J. van der Laan +# Released under MIT License +import os +from itertools import islice +from base58 import b58encode, b58decode, b58encode_chk, b58decode_chk, b58chars +import random +from binascii import b2a_hex + +# key types +PUBKEY_ADDRESS = 0 +SCRIPT_ADDRESS = 5 +PUBKEY_ADDRESS_TEST = 111 +SCRIPT_ADDRESS_TEST = 196 +PRIVKEY = 128 +PRIVKEY_TEST = 239 + +metadata_keys = ['isPrivkey', 'isTestnet', 'addrType', 'isCompressed'] +# templates for valid sequences +templates = [ + # prefix, payload_size, suffix, metadata + # None = N/A + ((PUBKEY_ADDRESS,), 20, (), (False, False, 'pubkey', None)), + ((SCRIPT_ADDRESS,), 20, (), (False, False, 'script', None)), + ((PUBKEY_ADDRESS_TEST,), 20, (), (False, True, 'pubkey', None)), + ((SCRIPT_ADDRESS_TEST,), 20, (), (False, True, 'script', None)), + ((PRIVKEY,), 32, (), (True, False, None, False)), + ((PRIVKEY,), 32, (1,), (True, False, None, True)), + ((PRIVKEY_TEST,), 32, (), (True, True, None, False)), + ((PRIVKEY_TEST,), 32, (1,), (True, True, None, True)) +] + +def is_valid(v): + '''Check vector v for validity''' + result = b58decode_chk(v) + if result is None: + return False + valid = False + for template in templates: + prefix = str(bytearray(template[0])) + suffix = str(bytearray(template[2])) + if result.startswith(prefix) and result.endswith(suffix): + if (len(result) - len(prefix) - len(suffix)) == template[1]: + return True + return False + +def gen_valid_vectors(): + '''Generate valid test vectors''' + while True: + for template in templates: + prefix = str(bytearray(template[0])) + payload = os.urandom(template[1]) + suffix = str(bytearray(template[2])) + rv = b58encode_chk(prefix + payload + suffix) + assert is_valid(rv) + metadata = dict([(x,y) for (x,y) in zip(metadata_keys,template[3]) if y is not None]) + yield (rv, b2a_hex(payload), metadata) + +def gen_invalid_vector(template, corrupt_prefix, randomize_payload_size, corrupt_suffix): + '''Generate possibly invalid vector''' + if corrupt_prefix: + prefix = os.urandom(1) + else: + prefix = str(bytearray(template[0])) + + if randomize_payload_size: + payload = os.urandom(max(int(random.expovariate(0.5)), 50)) + else: + payload = os.urandom(template[1]) + + if corrupt_suffix: + suffix = os.urandom(len(template[2])) + else: + suffix = str(bytearray(template[2])) + + return b58encode_chk(prefix + payload + suffix) + +def randbool(p = 0.5): + '''Return True with P(p)''' + return random.random() < p + +def gen_invalid_vectors(): + '''Generate invalid test vectors''' + # start with some manual edge-cases + yield "", + yield "x", + while True: + # kinds of invalid vectors: + # invalid prefix + # invalid payload length + # invalid (randomized) suffix (add random data) + # corrupt checksum + for template in templates: + val = gen_invalid_vector(template, randbool(0.2), randbool(0.2), randbool(0.2)) + if random.randint(0,10)<1: # line corruption + if randbool(): # add random character to end + val += random.choice(b58chars) + else: # replace random character in the middle + n = random.randint(0, len(val)) + val = val[0:n] + random.choice(b58chars) + val[n+1:] + if not is_valid(val): + yield val, + +if __name__ == '__main__': + import sys, json + iters = {'valid':gen_valid_vectors, 'invalid':gen_invalid_vectors} + try: + uiter = iters[sys.argv[1]] + except IndexError: + uiter = gen_valid_vectors + try: + count = int(sys.argv[2]) + except IndexError: + count = 0 + + data = list(islice(uiter(), count)) + json.dump(data, sys.stdout, sort_keys=True, indent=4) + sys.stdout.write('\n') + -- cgit v1.2.3