bitcoin/src/test/fuzz/locale.cpp

// Copyright (c) 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.

#include <test/fuzz/FuzzedDataProvider.h>
#include <test/fuzz/fuzz.h>
#include <tinyformat.h>
#include <util/strencodings.h>
#include <util/string.h>

#include <cassert>
#include <clocale>
#include <cstdint>
#include <locale>
#include <string>
#include <vector>

namespace {
const std::string locale_identifiers[] = {
    "C", "C.UTF-8", "aa_DJ", "aa_DJ.ISO-8859-1", "aa_DJ.UTF-8", "aa_ER", "aa_ER.UTF-8", "aa_ET", "aa_ET.UTF-8", "af_ZA", "af_ZA.ISO-8859-1", "af_ZA.UTF-8", "agr_PE", "agr_PE.UTF-8", "ak_GH", "ak_GH.UTF-8", "am_ET", "am_ET.UTF-8", "an_ES", "an_ES.ISO-8859-15", "an_ES.UTF-8", "anp_IN", "anp_IN.UTF-8", "ar_AE", "ar_AE.ISO-8859-6", "ar_AE.UTF-8", "ar_BH", "ar_BH.ISO-8859-6", "ar_BH.UTF-8", "ar_DZ", "ar_DZ.ISO-8859-6", "ar_DZ.UTF-8", "ar_EG", "ar_EG.ISO-8859-6", "ar_EG.UTF-8", "ar_IN", "ar_IN.UTF-8", "ar_IQ", "ar_IQ.ISO-8859-6", "ar_IQ.UTF-8", "ar_JO", "ar_JO.ISO-8859-6", "ar_JO.UTF-8", "ar_KW", "ar_KW.ISO-8859-6", "ar_KW.UTF-8", "ar_LB", "ar_LB.ISO-8859-6", "ar_LB.UTF-8", "ar_LY", "ar_LY.ISO-8859-6", "ar_LY.UTF-8", "ar_MA", "ar_MA.ISO-8859-6", "ar_MA.UTF-8", "ar_OM", "ar_OM.ISO-8859-6", "ar_OM.UTF-8", "ar_QA", "ar_QA.ISO-8859-6", "ar_QA.UTF-8", "ar_SA", "ar_SA.ISO-8859-6", "ar_SA.UTF-8", "ar_SD", "ar_SD.ISO-8859-6", "ar_SD.UTF-8", "ar_SS", "ar_SS.UTF-8", "ar_SY", "ar_SY.ISO-8859-6", "ar_SY.UTF-8", "ar_TN", "ar_TN.ISO-8859-6", "ar_TN.UTF-8", "ar_YE", "ar_YE.ISO-8859-6", "ar_YE.UTF-8", "as_IN", "as_IN.UTF-8", "ast_ES", "ast_ES.ISO-8859-15", "ast_ES.UTF-8", "ayc_PE", "ayc_PE.UTF-8", "az_AZ", "az_AZ.UTF-8", "az_IR", "az_IR.UTF-8", "be_BY", "be_BY.CP1251", "be_BY.UTF-8", "bem_ZM", "bem_ZM.UTF-8", "ber_DZ", "ber_DZ.UTF-8", "ber_MA", "ber_MA.UTF-8", "bg_BG", "bg_BG.CP1251", "bg_BG.UTF-8", "bho_IN", "bho_IN.UTF-8", "bho_NP", "bho_NP.UTF-8", "bi_VU", "bi_VU.UTF-8", "bn_BD", "bn_BD.UTF-8", "bn_IN", "bn_IN.UTF-8", "bo_CN", "bo_CN.UTF-8", "bo_IN", "bo_IN.UTF-8", "br_FR", "br_FR.ISO-8859-1", "br_FR.UTF-8", "brx_IN", "brx_IN.UTF-8", "bs_BA", "bs_BA.ISO-8859-2", "bs_BA.UTF-8", "byn_ER", "byn_ER.UTF-8", "ca_AD", "ca_AD.ISO-8859-15", "ca_AD.UTF-8", "ca_ES", "ca_ES.ISO-8859-1", "ca_ES.UTF-8", "ca_FR", "ca_FR.ISO-8859-15", "ca_FR.UTF-8", "ca_IT", "ca_IT.ISO-8859-15", "ca_IT.UTF-8", "ce_RU", "ce_RU.UTF-8", "chr_US", "chr_US.UTF-8", "ckb_IQ", "ckb_IQ.UTF-8", "cmn_TW", "cmn_TW.UTF-8", "crh_UA", "crh_UA.UTF-8", "csb_PL", "csb_PL.UTF-8", "cs_CZ", "cs_CZ.ISO-8859-2", "cs_CZ.UTF-8", "cv_RU", "cv_RU.UTF-8", "cy_GB", "cy_GB.ISO-8859-14", "cy_GB.UTF-8", "da_DK", "da_DK.ISO-8859-1", "da_DK.UTF-8", "de_AT", "de_AT.ISO-8859-1", "de_AT.UTF-8", "de_BE", "de_BE.ISO-8859-1", "de_BE.UTF-8", "de_CH", "de_CH.ISO-8859-1", "de_CH.UTF-8", "de_DE", "de_DE.ISO-8859-1", "de_DE.UTF-8", "de_IT", "de_IT.ISO-8859-1", "de_IT.UTF-8", "de_LU", "de_LU.ISO-8859-1", "de_LU.UTF-8", "doi_IN", "doi_IN.UTF-8", "dv_MV", "dv_MV.UTF-8", "dz_BT", "dz_BT.UTF-8", "el_CY", "el_CY.ISO-8859-7", "el_CY.UTF-8", "el_GR", "el_GR.ISO-8859-7", "el_GR.UTF-8", "en_AG", "en_AG.UTF-8", "en_AU", "en_AU.ISO-8859-1", "en_AU.UTF-8", "en_BW", "en_BW.ISO-8859-1", "en_BW.UTF-8", "en_CA", "en_CA.ISO-8859-1", "en_CA.UTF-8", "en_DK", "en_DK.ISO-8859-1", "en_DK.ISO-8859-15", "en_DK.UTF-8", "en_GB", "en_GB.ISO-8859-1", "en_GB.ISO-8859-15", "en_GB.UTF-8", "en_HK", "en_HK.ISO-8859-1", "en_HK.UTF-8", "en_IE", "en_IE.ISO-8859-1", "en_IE.UTF-8", "en_IL", "en_IL.UTF-8", "en_IN", "en_IN.UTF-8", "en_NG", "en_NG.UTF-8", "en_NZ", "en_NZ.ISO-8859-1", "en_NZ.UTF-8", "en_PH", "en_PH.ISO-8859-1", "en_PH.UTF-8", "en_SG", "en_SG.ISO-8859-1", "en_SG.UTF-8", "en_US", "en_US.ISO-8859-1", "en_US.ISO-8859-15", "en_US.UTF-8", "en_ZA", "en_ZA.ISO-8859-1", "en_ZA.UTF-8", "en_ZM", "en_ZM.UTF-8", "en_ZW", "en_ZW.ISO-8859-1", "en_ZW.UTF-8", "es_AR", "es_AR.ISO-8859-1", "es_AR.UTF-8", "es_BO", "es_BO.ISO-8859-1", "es_BO.UTF-8", "es_CL", "es_CL.ISO-8859-1", "es_CL.UTF-8", "es_CO", "es_CO.ISO-8859-1", "es_CO.UTF-8", "es_CR", "es_CR.ISO-8859-1", "es_CR.UTF-8", "es_CU", "es_CU.UTF-8", "es_DO", "es_DO.ISO-8859-1", "es_DO.UTF-8", "es_EC", "es_EC.ISO-8859-1", "es_EC.UTF-8", "es_ES", "es_ES.ISO-8859-1", "es_ES.UTF-8", "es_GT", "es_GT.ISO-8859-1", "es_GT.UTF-8", "es_HN", "es_HN.ISO-8859-1", "es_HN.UTF-8", "es_MX", "es_MX.ISO-8859-1", "es_MX.UTF-8", "es_NI", "es_NI.ISO-8859-1", "es_NI.UTF-8", "es_PA", "es_PA.ISO-8859-1", "es_PA.UTF-8", "es_PE", "es_PE.ISO-8859-1", "es_PE.UTF-8", "es_PR", "es_PR.ISO-8859-1", "es_PR.UTF-8", "es_PY", "es_PY.ISO-8859-1"

std::string ConsumeLocaleIdentifier(FuzzedDataProvider& fuzzed_data_provider)
{
    return fuzzed_data_provider.PickValueInArray<std::string>(locale_identifiers);
}

bool IsAvailableLocale(const std::string& locale_identifier)
{
    try {
        (void)std::locale(locale_identifier);
    } catch (const std::runtime_error&) {
        return false;
    }
    return true;
}
} // namespace

FUZZ_TARGET(locale)
{
    FuzzedDataProvider fuzzed_data_provider(buffer.data(), buffer.size());
    const std::string locale_identifier = ConsumeLocaleIdentifier(fuzzed_data_provider);
    if (!IsAvailableLocale(locale_identifier)) {
        return;
    }
    const char* c_locale = std::setlocale(LC_ALL, "C");
    assert(c_locale != nullptr);

    const std::string random_string = fuzzed_data_provider.ConsumeRandomLengthString(5);
    int32_t parseint32_out_without_locale;
    const bool parseint32_without_locale = ParseInt32(random_string, &parseint32_out_without_locale);
    int64_t parseint64_out_without_locale;
    const bool parseint64_without_locale = ParseInt64(random_string, &parseint64_out_without_locale);
    const int64_t atoi64_without_locale = atoi64(random_string);
    const int atoi_without_locale = atoi(random_string);
    const int64_t random_int64 = fuzzed_data_provider.ConsumeIntegral<int64_t>();
    const std::string tostring_without_locale = ToString(random_int64);
    // The variable `random_int32` is no longer used, but the harness still needs to
    // consume the same data that it did previously to not invalidate existing seeds.
    const int32_t random_int32 = fuzzed_data_provider.ConsumeIntegral<int32_t>();
    (void)random_int32;
    const std::string strprintf_int_without_locale = strprintf("%d", random_int64);
    const double random_double = fuzzed_data_provider.ConsumeFloatingPoint<double>();
    const std::string strprintf_double_without_locale = strprintf("%f", random_double);

    const char* new_locale = std::setlocale(LC_ALL, locale_identifier.c_str());
    assert(new_locale != nullptr);

    int32_t parseint32_out_with_locale;
    const bool parseint32_with_locale = ParseInt32(random_string, &parseint32_out_with_locale);
    assert(parseint32_without_locale == parseint32_with_locale);
    if (parseint32_without_locale) {
        assert(parseint32_out_without_locale == parseint32_out_with_locale);
    }
    int64_t parseint64_out_with_locale;
    const bool parseint64_with_locale = ParseInt64(random_string, &parseint64_out_with_locale);
    assert(parseint64_without_locale == parseint64_with_locale);
    if (parseint64_without_locale) {
        assert(parseint64_out_without_locale == parseint64_out_with_locale);
    }
    const int64_t atoi64_with_locale = atoi64(random_string);
    assert(atoi64_without_locale == atoi64_with_locale);
    const int atoi_with_locale = atoi(random_string);
    assert(atoi_without_locale == atoi_with_locale);
    const std::string tostring_with_locale = ToString(random_int64);
    assert(tostring_without_locale == tostring_with_locale);
    const std::string strprintf_int_with_locale = strprintf("%d", random_int64);
    assert(strprintf_int_without_locale == strprintf_int_with_locale);
    const std::string strprintf_double_with_locale = strprintf("%f", random_double);
    assert(strprintf_double_without_locale == strprintf_double_with_locale);

    const std::locale current_cpp_locale;
    assert(current_cpp_locale == std::locale::classic());
}