base58_tests.cpp

// Copyright (c) 2011-2022 The Bitcoin Core developers
// Distributed under the MIT software license, see the accompanying
// file COPYING or http://www.opensource.org/licenses/mit-license.php.

#include <test/data/base58_encode_decode.json.h>

#include <base58.h>
#include <test/util/json.h>
#include <test/util/random.h>
#include <test/util/setup_common.h>
#include <util/strencodings.h>
#include <util/vector.h>
#include <base58.h>

#include <hash.h>
#include <uint256.h>
#include <util/strencodings.h>
#include <util/string.h>

#include <assert.h>
#include <string.h>

#include <limits>

#include <univalue.h>

#include <boost/test/unit_test.hpp>
#include <string>
using util::ContainsNoNUL;

using namespace std::literals;

BOOST_FIXTURE_TEST_SUITE(base58_tests, BasicTestingSetup)

// Goal: test low-level base58 encoding functionality
BOOST_AUTO_TEST_CASE(base58_EncodeBase58)
{
    UniValue tests = read_json(json_tests::base58_encode_decode);
    for (unsigned int idx = 0; idx < tests.size(); idx++) {
        const UniValue& test = tests[idx];
        auto strTest = test.write();
        if (test.size() < 2) // Allow for extra stuff (useful for comments)
        {
            BOOST_ERROR("Bad test: " << strTest);
            continue;
        }
        auto encodedSource = EncodeBase58(ParseHex(test[0].get_str()));
        auto base58string = test[1].get_str();
        BOOST_CHECK_MESSAGE(
            encodedSource == base58string,
            strTest << ": got \"" << encodedSource << "\""
        );
    }
}

// Goal: test low-level base58 decoding functionality
BOOST_AUTO_TEST_CASE(base58_DecodeBase58)
{
    UniValue tests = read_json(json_tests::base58_encode_decode);
    std::vector<unsigned char> result;

    for (unsigned int idx = 0; idx < tests.size(); idx++) {
        const UniValue& test = tests[idx];
        std::string strTest = test.write();
        if (test.size() < 2) // Allow for extra stuff (useful for comments)
        {
            BOOST_ERROR("Bad test: " << strTest);
            continue;
        }
        std::vector<unsigned char> expected = ParseHex(test[0].get_str());
        std::string base58string = test[1].get_str();

        BOOST_CHECK_MESSAGE(DecodeBase58(base58string, result, 256), strTest);
        BOOST_CHECK_MESSAGE(
            result == expected,
            strTest << ": got \"" << HexStr(result) << "\""
        );
    }

    BOOST_CHECK(!DecodeBase58("invalid"s, result, 100));
    BOOST_CHECK(!DecodeBase58("invalid\0"s, result, 100));
    BOOST_CHECK(!DecodeBase58("\0invalid"s, result, 100));

    BOOST_CHECK(DecodeBase58("good"s, result, 100));
    BOOST_CHECK(!DecodeBase58("bad0IOl"s, result, 100));
    BOOST_CHECK(!DecodeBase58("goodbad0IOl"s, result, 100));
    BOOST_CHECK(!DecodeBase58("good\0bad0IOl"s, result, 100));

    // check that DecodeBase58 skips whitespace, but still fails with unexpected non-whitespace at the end.
    BOOST_CHECK(!DecodeBase58(" \t\n\v\f\r skip \r\f\v\n\t a", result, 3));
    BOOST_CHECK(DecodeBase58(" \t\n\v\f\r skip \r\f\v\n\t ", result, 3));
    std::vector<unsigned char> expected = ParseHex("971a55");
    BOOST_CHECK_EQUAL_COLLECTIONS(result.begin(), result.end(), expected.begin(), expected.end());

    BOOST_CHECK(DecodeBase58Check("3vQB7B6MrGQZaxCuFg4oh"s, result, 100));
    BOOST_CHECK(!DecodeBase58Check("3vQB7B6MrGQZaxCuFg4oi"s, result, 100));
    BOOST_CHECK(!DecodeBase58Check("3vQB7B6MrGQZaxCuFg4oh0IOl"s, result, 100));
    BOOST_CHECK(!DecodeBase58Check("3vQB7B6MrGQZaxCuFg4oh\0" "0IOl"s, result, 100));
}

/** All alphanumeric characters except for "0", "I", "O", and "l" */
static const char* pszBase58_old = "123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz";
static const int8_t mapBase58_old[256] = {
    -1,-1,-1,-1,-1,-1,-1,-1, -1,-1,-1,-1,-1,-1,-1,-1,
    -1,-1,-1,-1,-1,-1,-1,-1, -1,-1,-1,-1,-1,-1,-1,-1,
    -1,-1,-1,-1,-1,-1,-1,-1, -1,-1,-1,-1,-1,-1,-1,-1,
    -1, 0, 1, 2, 3, 4, 5, 6,  7, 8,-1,-1,-1,-1,-1,-1,
    -1, 9,10,11,12,13,14,15, 16,-1,17,18,19,20,21,-1,
    22,23,24,25,26,27,28,29, 30,31,32,-1,-1,-1,-1,-1,
    -1,33,34,35,36,37,38,39, 40,41,42,43,-1,44,45,46,
    47,48,49,50,51,52,53,54, 55,56,57,-1,-1,-1,-1,-1,
    -1,-1,-1,-1,-1,-1,-1,-1, -1,-1,-1,-1,-1,-1,-1,-1,
    -1,-1,-1,-1,-1,-1,-1,-1, -1,-1,-1,-1,-1,-1,-1,-1,
    -1,-1,-1,-1,-1,-1,-1,-1, -1,-1,-1,-1,-1,-1,-1,-1,
    -1,-1,-1,-1,-1,-1,-1,-1, -1,-1,-1,-1,-1,-1,-1,-1,
    -1,-1,-1,-1,-1,-1,-1,-1, -1,-1,-1,-1,-1,-1,-1,-1,
    -1,-1,-1,-1,-1,-1,-1,-1, -1,-1,-1,-1,-1,-1,-1,-1,
    -1,-1,-1,-1,-1,-1,-1,-1, -1,-1,-1,-1,-1,-1,-1,-1,
    -1,-1,-1,-1,-1,-1,-1,-1, -1,-1,-1,-1,-1,-1,-1,-1,
};

[[nodiscard]] static bool DecodeBase58_old(const char* psz, std::vector<unsigned char>& vch, int max_ret_len)
{
    // Skip leading spaces.
    while (*psz && IsSpace(*psz))
        psz++;
    // Skip and count leading '1's.
    int zeroes = 0;
    int length = 0;
    while (*psz == '1') {
        zeroes++;
        if (zeroes > max_ret_len) return false;
        psz++;
    }
    // Allocate enough space in big-endian base256 representation.
    int size = strlen(psz) * 733 /1000 + 1; // log(58) / log(256), rounded up.
    std::vector<unsigned char> b256(size);
    // Process the characters.
    static_assert(std::size(mapBase58_old) == 256, "mapBase58_old.size() should be 256"); // guarantee not out of range
    while (*psz && !IsSpace(*psz)) {
        // Decode base58 character
        int carry = mapBase58_old[(uint8_t)*psz];
        if (carry == -1)  // Invalid b58 character
            return false;
        int i = 0;
        for (std::vector<unsigned char>::reverse_iterator it = b256.rbegin(); (carry != 0 || i < length) && (it != b256.rend()); ++it, ++i) {
            carry += 58 * (*it);
            *it = carry % 256;
            carry /= 256;
        }
        assert(carry == 0);
        length = i;
        if (length + zeroes > max_ret_len) return false;
        psz++;
    }
    // Skip trailing spaces.
    while (IsSpace(*psz))
        psz++;
    if (*psz != 0)
        return false;
    // Skip leading zeroes in b256.
    std::vector<unsigned char>::iterator it = b256.begin() + (size - length);
    // Copy result into output vector.
    vch.reserve(zeroes + (b256.end() - it));
    vch.assign(zeroes, 0x00);
    while (it != b256.end())
        vch.push_back(*(it++));
    return true;
}

std::string EncodeBase58_old(Span<const unsigned char> input)
{
    // Skip & count leading zeroes.
    int zeroes = 0;
    int length = 0;
    while (input.size() > 0 && input[0] == 0) {
        input = input.subspan(1);
        zeroes++;
    }
    // Allocate enough space in big-endian base58 representation.
    int size = input.size() * 138 / 100 + 1; // log(256) / log(58), rounded up.
    std::vector<unsigned char> b58(size);
    // Process the bytes.
    while (input.size() > 0) {
        int carry = input[0];
        int i = 0;
        // Apply "b58 = b58 * 256 + ch".
        for (std::vector<unsigned char>::reverse_iterator it = b58.rbegin(); (carry != 0 || i < length) && (it != b58.rend()); it++, i++) {
            carry += 256 * (*it);
            *it = carry % 58;
            carry /= 58;
        }

        assert(carry == 0);
        length = i;
        input = input.subspan(1);
    }
    // Skip leading zeroes in base58 result.
    std::vector<unsigned char>::iterator it = b58.begin() + (size - length);
    while (it != b58.end() && *it == 0)
        it++;
    // Translate the result into a string.
    std::string str;
    str.reserve(zeroes + (b58.end() - it));
    str.assign(zeroes, '1');
    while (it != b58.end())
        str += pszBase58_old[*(it++)];
    return str;
}

BOOST_AUTO_TEST_CASE(base58_random_encode_decode_with_optional_spaces)
{
    for (int n = 0; n < 10'000'000; ++n) {
        auto len = 1 + InsecureRandBits(8);
        auto zeroes = InsecureRandBool() ? InsecureRandRange(len + 1) : 0;
        auto data = Cat(std::vector<unsigned char>(zeroes, '\000'), g_insecure_rand_ctx.randbytes(len - zeroes));

        auto leadingSpaces = InsecureRandBool() ? std::string(InsecureRandRange(10), ' ') : "";
        auto trailingSpaces = InsecureRandBool() ? std::string(InsecureRandRange(10), ' ') : "";

        // Test encoding
        auto encoded = leadingSpaces + EncodeBase58(data) + trailingSpaces;
        auto encoded_old = leadingSpaces + EncodeBase58_old(data) + trailingSpaces;
        BOOST_CHECK_MESSAGE(encoded == encoded_old, "New and old encoding should match for input: " << HexStr(data));

        // Test decoding
        std::vector<unsigned char> decoded, decoded_old;
        auto invalidSmallResultLength = InsecureRandRange(len);

        bool new_decode_result = DecodeBase58(encoded, decoded, invalidSmallResultLength);
        bool old_decode_result = DecodeBase58_old(encoded_old.c_str(), decoded_old, invalidSmallResultLength);
        BOOST_CHECK_MESSAGE(new_decode_result == old_decode_result,
                            "New and old decoding should have the same result for invalid length: " << invalidSmallResultLength);

        auto maxResultLength = len + InsecureRandRange(257 - len);
        new_decode_result = DecodeBase58(encoded, decoded, maxResultLength);
        old_decode_result = DecodeBase58_old(encoded_old.c_str(), decoded_old, maxResultLength);

        BOOST_CHECK_MESSAGE(new_decode_result == old_decode_result,
                            "New and old decoding should have the same result for max length: " << maxResultLength);

        if (new_decode_result && old_decode_result) {
            BOOST_CHECK_MESSAGE(decoded == decoded_old,
                                "New and old decoding should produce the same output for input: " << encoded);
            BOOST_CHECK_MESSAGE(data == decoded,
                                "Decoding `" << encoded << "` as `" << HexStr(decoded) << "` should match `" << HexStr(data) << "`");
        }
    }
}

BOOST_AUTO_TEST_SUITE_END()