Merge bitcoin/bitcoin#24576: contrib: testgen: remove redundant base58 implementation

65c49ac750ba39801b349d0a59c27471dfa9868e test: throw `ValueError` for invalid base58 checksum (Sebastian Falbesoner)
219d2c7ee1d35a353a96c55d4c411d43fe39548a contrib: testgen: use base58 methods from test framework (Sebastian Falbesoner)
605fecfb66ba51467b35a3f269116ec786aedd05 scripted-diff: rename `chars` to `b58chars` in test_framework.address (Sebastian Falbesoner)
11c63e374d058d3bde64a725068d29c874950b45 contrib: testgen: import OP_* constants from test framework (Sebastian Falbesoner)
7d755bb31cd58099cd97b604e04a6a4bb99cd2a9 contrib: testgen: avoid need for manually setting PYTHONPATH (Sebastian Falbesoner)

Pull request description:

  This PR removes the redundant base58 implementation [contrib/testgen/base58.py](https://github.com/bitcoin/bitcoin/blob/master/contrib/testgen/base58.py) for the test generation script `gen_key_io_test_vectors.py` and uses the one from the test framework instead. Additionally, three other cleanups/improvements are done:
  - import script operator constants `OP_*` from test framework instead of manually defining them
  - add Python path to test framework directly in the script (via `sys.path.append(...)`) instead of needing the caller to specify `PYTHONPATH=...` on the command line (the same approach is done for the signet miner and the message capture scripts)
  - rename `chars` to `b58chars` in the test_framework.address module (is more explicit and makes the diff for the base58 replacement smaller)

ACKs for top commit:
  laanwj:
    Code review ACK 65c49ac750ba39801b349d0a59c27471dfa9868e

Tree-SHA512: 92e1534cc320cd56262bf455de7231c6ec821bfcd0ed58aa5718271ecec1a89df7951bf31527a2306db6398e7f2664d2ff8508200c28163c0b164d3f5aaf8b0e

3 files changed, 22 insertions, 140 deletions

diff --git a/contrib/testgen/README.md b/contrib/testgen/README.md
index fcc5a378e2..66276ec9dd 100644
--- a/contrib/testgen/README.md
+++ b/contrib/testgen/README.md
@@ -4,5 +4,5 @@ Utilities to generate test vectors for the data-driven Bitcoin tests.
 
 Usage:
 
-    PYTHONPATH=../../test/functional/test_framework ./gen_key_io_test_vectors.py valid 70 > ../../src/test/data/key_io_valid.json
-    PYTHONPATH=../../test/functional/test_framework ./gen_key_io_test_vectors.py invalid 70 > ../../src/test/data/key_io_invalid.json
+    ./gen_key_io_test_vectors.py valid 70 > ../../src/test/data/key_io_valid.json
+    ./gen_key_io_test_vectors.py invalid 70 > ../../src/test/data/key_io_invalid.json
diff --git a/contrib/testgen/base58.py b/contrib/testgen/base58.py
deleted file mode 100644
index 87341ccf96..0000000000
--- a/contrib/testgen/base58.py
+++ /dev/null
@@ -1,115 +0,0 @@
-# Copyright (c) 2012-2020 The Bitcoin Core developers
-# Distributed under the MIT software license, see the accompanying
-# file COPYING or http://www.opensource.org/licenses/mit-license.php.
-'''
-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]):
-        if isinstance(c, str):
-            c = ord(c)
-        long_value += (256**i) * 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]):
-        pos = __b58chars.find(c)
-        assert pos != -1
-        long_value += pos * (__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
-            continue
-        break
-
-    result = bytes(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
-    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') == 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_key_io_test_vectors.py b/contrib/testgen/gen_key_io_test_vectors.py
index eafaaaeceb..4aa7dc200b 100755
--- a/contrib/testgen/gen_key_io_test_vectors.py
+++ b/contrib/testgen/gen_key_io_test_vectors.py
@@ -1,21 +1,25 @@
 #!/usr/bin/env python3
-# Copyright (c) 2012-2021 The Bitcoin Core developers
+# Copyright (c) 2012-2022 The Bitcoin Core developers
 # Distributed under the MIT software license, see the accompanying
 # file COPYING or http://www.opensource.org/licenses/mit-license.php.
 '''
 Generate valid and invalid base58/bech32(m) address and private key test vectors.
 
 Usage:
-    PYTHONPATH=../../test/functional/test_framework ./gen_key_io_test_vectors.py valid 70 > ../../src/test/data/key_io_valid.json
-    PYTHONPATH=../../test/functional/test_framework ./gen_key_io_test_vectors.py invalid 70 > ../../src/test/data/key_io_invalid.json
+    ./gen_key_io_test_vectors.py valid 70 > ../../src/test/data/key_io_valid.json
+    ./gen_key_io_test_vectors.py invalid 70 > ../../src/test/data/key_io_invalid.json
 '''
-# 2012 Wladimir J. van der Laan
-# Released under MIT License
-import os
+
 from itertools import islice
-from base58 import b58encode_chk, b58decode_chk, b58chars
+import os
 import random
-from segwit_addr import bech32_encode, decode_segwit_address, convertbits, CHARSET, Encoding
+import sys
+
+sys.path.append(os.path.join(os.path.dirname(__file__), '../../test/functional'))
+
+from test_framework.address import base58_to_byte, byte_to_base58, b58chars  # noqa: E402
+from test_framework.script import OP_0, OP_1, OP_2, OP_3, OP_16, OP_DUP, OP_EQUAL, OP_EQUALVERIFY, OP_HASH160, OP_CHECKSIG  # noqa: E402
+from test_framework.segwit_addr import bech32_encode, decode_segwit_address, convertbits, CHARSET, Encoding  # noqa: E402
 
 # key types
 PUBKEY_ADDRESS = 0
@@ -29,16 +33,6 @@ PRIVKEY_TEST = 239
 PRIVKEY_REGTEST = 239
 
 # script
-OP_0 = 0x00
-OP_1 = 0x51
-OP_2 = 0x52
-OP_3 = 0x53
-OP_16 = 0x60
-OP_DUP = 0x76
-OP_EQUAL = 0x87
-OP_EQUALVERIFY = 0x88
-OP_HASH160 = 0xa9
-OP_CHECKSIG = 0xac
 pubkey_prefix = (OP_DUP, OP_HASH160, 20)
 pubkey_suffix = (OP_EQUALVERIFY, OP_CHECKSIG)
 script_prefix = (OP_HASH160, 20)
@@ -114,8 +108,10 @@ def is_valid(v):
     '''Check vector v for validity'''
     if len(set(v) - set(b58chars)) > 0:
         return is_valid_bech32(v)
-    result = b58decode_chk(v)
-    if result is None:
+    try:
+        payload, version = base58_to_byte(v)
+        result = bytes([version]) + payload
+    except ValueError:  # thrown if checksum doesn't match
         return is_valid_bech32(v)
     for template in templates:
         prefix = bytearray(template[0])
@@ -139,7 +135,8 @@ def gen_valid_base58_vector(template):
     suffix = bytearray(template[2])
     dst_prefix = bytearray(template[4])
     dst_suffix = bytearray(template[5])
-    rv = b58encode_chk(prefix + payload + suffix)
+    assert len(prefix) == 1
+    rv = byte_to_base58(payload + suffix, prefix[0])
     return rv, dst_prefix + payload + dst_suffix
 
 def gen_valid_bech32_vector(template):
@@ -190,7 +187,8 @@ def gen_invalid_base58_vector(template):
     else:
         suffix = bytearray(template[2])
 
-    val = b58encode_chk(prefix + payload + suffix)
+    assert len(prefix) == 1
+    val = byte_to_base58(payload + suffix, prefix[0])
     if random.randint(0,10)<1: # line corruption
         if randbool(): # add random character to end
             val += random.choice(b58chars)
@@ -250,7 +248,6 @@ def gen_invalid_vectors():
                 yield val,
 
 if __name__ == '__main__':
-    import sys
     import json
     iters = {'valid':gen_valid_vectors, 'invalid':gen_invalid_vectors}
     try: