2015-05-24 04:55:12 +00:00
|
|
|
// Copyright 2008 Dolphin Emulator Project
|
2021-07-05 01:22:19 +00:00
|
|
|
// SPDX-License-Identifier: GPL-2.0-or-later
|
2008-12-08 05:30:24 +00:00
|
|
|
|
2019-06-14 14:53:46 +00:00
|
|
|
#include "Common/StringUtil.h"
|
|
|
|
|
2013-03-03 04:57:49 +00:00
|
|
|
#include <algorithm>
|
2021-05-24 16:44:21 +00:00
|
|
|
#include <array>
|
2020-06-28 17:16:23 +00:00
|
|
|
#include <codecvt>
|
2014-02-20 03:11:52 +00:00
|
|
|
#include <cstdarg>
|
|
|
|
#include <cstddef>
|
2014-02-17 10:18:15 +00:00
|
|
|
#include <cstdio>
|
2014-02-19 00:54:11 +00:00
|
|
|
#include <cstdlib>
|
2014-02-20 03:11:52 +00:00
|
|
|
#include <cstring>
|
|
|
|
#include <iomanip>
|
|
|
|
#include <istream>
|
2016-11-26 14:39:00 +00:00
|
|
|
#include <iterator>
|
2014-02-20 03:11:52 +00:00
|
|
|
#include <limits.h>
|
2017-04-06 14:02:21 +00:00
|
|
|
#include <locale>
|
2016-11-26 14:39:00 +00:00
|
|
|
#include <sstream>
|
2014-02-20 03:11:52 +00:00
|
|
|
#include <string>
|
2020-06-28 16:22:18 +00:00
|
|
|
#include <type_traits>
|
2014-02-20 03:11:52 +00:00
|
|
|
#include <vector>
|
|
|
|
|
2019-06-14 14:53:46 +00:00
|
|
|
#include <fmt/format.h>
|
2024-08-09 05:54:08 +00:00
|
|
|
#include <fmt/ranges.h>
|
2019-06-14 14:53:46 +00:00
|
|
|
|
2015-09-26 21:13:07 +00:00
|
|
|
#include "Common/CommonFuncs.h"
|
2014-02-17 10:18:15 +00:00
|
|
|
#include "Common/CommonPaths.h"
|
2014-09-08 01:06:58 +00:00
|
|
|
#include "Common/CommonTypes.h"
|
2015-09-26 21:13:07 +00:00
|
|
|
#include "Common/Logging/Log.h"
|
2017-11-02 16:05:45 +00:00
|
|
|
#include "Common/Swap.h"
|
2008-12-08 05:30:24 +00:00
|
|
|
|
2013-02-28 00:00:42 +00:00
|
|
|
#ifdef _WIN32
|
2013-03-03 04:57:49 +00:00
|
|
|
#include <Windows.h>
|
2020-09-21 09:23:06 +00:00
|
|
|
#include <shellapi.h>
|
2017-05-01 12:08:47 +00:00
|
|
|
constexpr u32 CODEPAGE_SHIFT_JIS = 932;
|
|
|
|
constexpr u32 CODEPAGE_WINDOWS_1252 = 1252;
|
2013-03-03 04:57:49 +00:00
|
|
|
#else
|
2016-06-24 10:16:10 +00:00
|
|
|
#include <errno.h>
|
2013-03-03 04:57:49 +00:00
|
|
|
#include <iconv.h>
|
2015-02-01 23:45:37 +00:00
|
|
|
#include <locale.h>
|
2013-02-28 00:00:42 +00:00
|
|
|
#endif
|
|
|
|
|
2020-12-04 16:09:42 +00:00
|
|
|
#if !defined(_WIN32) && !defined(ANDROID) && !defined(__HAIKU__) && !defined(__OpenBSD__) && \
|
|
|
|
!defined(__NetBSD__)
|
2015-02-01 23:45:37 +00:00
|
|
|
static locale_t GetCLocale()
|
|
|
|
{
|
2015-03-15 01:20:41 +00:00
|
|
|
static locale_t c_locale = newlocale(LC_ALL_MASK, "C", nullptr);
|
2015-02-01 23:45:37 +00:00
|
|
|
return c_locale;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2016-06-17 00:08:12 +00:00
|
|
|
std::string HexDump(const u8* data, size_t size)
|
|
|
|
{
|
|
|
|
constexpr size_t BYTES_PER_LINE = 16;
|
2016-06-24 08:43:46 +00:00
|
|
|
|
2016-06-17 00:08:12 +00:00
|
|
|
std::string out;
|
|
|
|
for (size_t row_start = 0; row_start < size; row_start += BYTES_PER_LINE)
|
|
|
|
{
|
2019-06-14 14:53:46 +00:00
|
|
|
out += fmt::format("{:06x}: ", row_start);
|
2016-06-17 00:08:12 +00:00
|
|
|
for (size_t i = 0; i < BYTES_PER_LINE; ++i)
|
|
|
|
{
|
|
|
|
if (row_start + i < size)
|
|
|
|
{
|
2019-06-14 14:53:46 +00:00
|
|
|
out += fmt::format("{:02x} ", data[row_start + i]);
|
2016-06-17 00:08:12 +00:00
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
out += " ";
|
|
|
|
}
|
|
|
|
}
|
|
|
|
out += " ";
|
|
|
|
for (size_t i = 0; i < BYTES_PER_LINE; ++i)
|
|
|
|
{
|
|
|
|
if (row_start + i < size)
|
|
|
|
{
|
|
|
|
char c = static_cast<char>(data[row_start + i]);
|
2023-05-16 18:17:54 +00:00
|
|
|
out += Common::IsPrintableCharacter(c) ? c : '.';
|
2016-06-17 00:08:12 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
out += "\n";
|
|
|
|
}
|
|
|
|
return out;
|
|
|
|
}
|
|
|
|
|
2008-07-12 17:40:22 +00:00
|
|
|
bool CharArrayFromFormatV(char* out, int outsize, const char* format, va_list args)
|
|
|
|
{
|
2013-08-08 22:17:29 +00:00
|
|
|
int writtenCount;
|
|
|
|
|
|
|
|
#ifdef _WIN32
|
|
|
|
// You would think *printf are simple, right? Iterate on each character,
|
|
|
|
// if it's a format specifier handle it properly, etc.
|
|
|
|
//
|
|
|
|
// Nooooo. Not according to the C standard.
|
|
|
|
//
|
|
|
|
// According to the C99 standard (7.19.6.1 "The fprintf function")
|
|
|
|
// The format shall be a multibyte character sequence
|
|
|
|
//
|
|
|
|
// Because some character encodings might have '%' signs in the middle of
|
|
|
|
// a multibyte sequence (SJIS for example only specifies that the first
|
|
|
|
// byte of a 2 byte sequence is "high", the second byte can be anything),
|
|
|
|
// printf functions have to decode the multibyte sequences and try their
|
|
|
|
// best to not screw up.
|
|
|
|
//
|
|
|
|
// Unfortunately, on Windows, the locale for most languages is not UTF-8
|
|
|
|
// as we would need. Notably, for zh_TW, Windows chooses EUC-CN as the
|
|
|
|
// locale, and completely fails when trying to decode UTF-8 as EUC-CN.
|
|
|
|
//
|
|
|
|
// On the other hand, the fix is simple: because we use UTF-8, no such
|
|
|
|
// multibyte handling is required as we can simply assume that no '%' char
|
|
|
|
// will be present in the middle of a multibyte sequence.
|
|
|
|
//
|
2015-07-11 14:21:10 +00:00
|
|
|
// This is why we look up the default C locale here and use _vsnprintf_l.
|
2014-12-06 01:54:41 +00:00
|
|
|
static _locale_t c_locale = nullptr;
|
2013-08-08 22:17:29 +00:00
|
|
|
if (!c_locale)
|
2015-07-11 14:21:10 +00:00
|
|
|
c_locale = _create_locale(LC_ALL, "C");
|
2013-08-08 22:17:29 +00:00
|
|
|
writtenCount = _vsnprintf_l(out, outsize, format, c_locale, args);
|
|
|
|
#else
|
2020-12-04 16:09:42 +00:00
|
|
|
#if !defined(ANDROID) && !defined(__HAIKU__) && !defined(__OpenBSD__) && !defined(__NetBSD__)
|
2015-02-01 23:45:37 +00:00
|
|
|
locale_t previousLocale = uselocale(GetCLocale());
|
|
|
|
#endif
|
2013-08-08 22:17:29 +00:00
|
|
|
writtenCount = vsnprintf(out, outsize, format, args);
|
2020-12-04 16:09:42 +00:00
|
|
|
#if !defined(ANDROID) && !defined(__HAIKU__) && !defined(__OpenBSD__) && !defined(__NetBSD__)
|
2015-02-01 23:45:37 +00:00
|
|
|
uselocale(previousLocale);
|
|
|
|
#endif
|
2013-08-08 22:17:29 +00:00
|
|
|
#endif
|
2008-12-08 05:30:24 +00:00
|
|
|
|
2008-09-22 20:35:44 +00:00
|
|
|
if (writtenCount > 0 && writtenCount < outsize)
|
2008-07-12 17:40:22 +00:00
|
|
|
{
|
|
|
|
out[writtenCount] = '\0';
|
2008-09-22 20:35:44 +00:00
|
|
|
return true;
|
2008-07-12 17:40:22 +00:00
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
out[outsize - 1] = '\0';
|
2008-09-22 20:35:44 +00:00
|
|
|
return false;
|
2008-07-12 17:40:22 +00:00
|
|
|
}
|
|
|
|
}
|
2008-12-08 05:30:24 +00:00
|
|
|
|
2010-11-10 04:12:31 +00:00
|
|
|
std::string StringFromFormat(const char* format, ...)
|
2008-07-12 17:40:22 +00:00
|
|
|
{
|
2008-12-10 22:36:26 +00:00
|
|
|
va_list args;
|
2014-12-29 00:09:07 +00:00
|
|
|
va_start(args, format);
|
|
|
|
std::string res = StringFromFormatV(format, args);
|
|
|
|
va_end(args);
|
2015-08-04 08:58:24 +00:00
|
|
|
return res;
|
2014-12-29 00:09:07 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
std::string StringFromFormatV(const char* format, va_list args)
|
|
|
|
{
|
2016-01-21 19:46:25 +00:00
|
|
|
char* buf = nullptr;
|
2010-11-11 04:59:50 +00:00
|
|
|
#ifdef _WIN32
|
2014-12-29 00:09:07 +00:00
|
|
|
int required = _vscprintf(format, args);
|
2010-11-11 04:59:50 +00:00
|
|
|
buf = new char[required + 1];
|
2013-08-08 22:17:29 +00:00
|
|
|
CharArrayFromFormatV(buf, required + 1, format, args);
|
2010-11-11 04:59:50 +00:00
|
|
|
|
2008-12-10 22:36:26 +00:00
|
|
|
std::string temp = buf;
|
2009-11-18 21:11:05 +00:00
|
|
|
delete[] buf;
|
2010-11-11 04:59:50 +00:00
|
|
|
#else
|
2020-12-04 16:09:42 +00:00
|
|
|
#if !defined(ANDROID) && !defined(__HAIKU__) && !defined(__OpenBSD__) && !defined(__NetBSD__)
|
2015-02-01 23:45:37 +00:00
|
|
|
locale_t previousLocale = uselocale(GetCLocale());
|
|
|
|
#endif
|
2013-01-31 21:29:29 +00:00
|
|
|
if (vasprintf(&buf, format, args) < 0)
|
2017-04-08 15:05:12 +00:00
|
|
|
{
|
2020-10-23 18:41:30 +00:00
|
|
|
ERROR_LOG_FMT(COMMON, "Unable to allocate memory for string");
|
2017-04-08 15:05:12 +00:00
|
|
|
buf = nullptr;
|
|
|
|
}
|
|
|
|
|
2020-12-04 16:09:42 +00:00
|
|
|
#if !defined(ANDROID) && !defined(__HAIKU__) && !defined(__OpenBSD__) && !defined(__NetBSD__)
|
2015-02-01 23:45:37 +00:00
|
|
|
uselocale(previousLocale);
|
|
|
|
#endif
|
2016-06-24 08:43:46 +00:00
|
|
|
|
2010-11-11 04:59:50 +00:00
|
|
|
std::string temp = buf;
|
|
|
|
free(buf);
|
|
|
|
#endif
|
2015-08-04 08:58:24 +00:00
|
|
|
return temp;
|
2008-07-12 17:40:22 +00:00
|
|
|
}
|
2008-12-08 05:30:24 +00:00
|
|
|
|
2009-03-28 08:57:34 +00:00
|
|
|
// For Debugging. Read out an u8 array.
|
2016-01-21 20:16:51 +00:00
|
|
|
std::string ArrayToString(const u8* data, u32 size, int line_len, bool spaces)
|
2008-07-12 17:40:22 +00:00
|
|
|
{
|
2010-11-10 04:12:31 +00:00
|
|
|
std::ostringstream oss;
|
|
|
|
oss << std::setfill('0') << std::hex;
|
2016-06-24 08:43:46 +00:00
|
|
|
|
2010-11-10 04:12:31 +00:00
|
|
|
for (int line = 0; size; ++data, --size)
|
2009-02-25 13:31:13 +00:00
|
|
|
{
|
2017-05-01 12:08:47 +00:00
|
|
|
oss << std::setw(2) << static_cast<int>(*data);
|
2016-06-24 08:43:46 +00:00
|
|
|
|
2010-11-10 04:12:31 +00:00
|
|
|
if (line_len == ++line)
|
2009-02-25 13:31:13 +00:00
|
|
|
{
|
2010-11-10 04:12:31 +00:00
|
|
|
oss << '\n';
|
|
|
|
line = 0;
|
2009-02-25 13:31:13 +00:00
|
|
|
}
|
2010-11-10 04:12:31 +00:00
|
|
|
else if (spaces)
|
|
|
|
oss << ' ';
|
2009-02-25 13:31:13 +00:00
|
|
|
}
|
2016-06-24 08:43:46 +00:00
|
|
|
|
2010-11-10 04:12:31 +00:00
|
|
|
return oss.str();
|
|
|
|
}
|
2008-12-08 05:30:24 +00:00
|
|
|
|
2022-07-19 22:13:26 +00:00
|
|
|
template <typename T>
|
|
|
|
static std::string_view StripEnclosingChars(std::string_view str, T chars)
|
2010-11-10 04:12:31 +00:00
|
|
|
{
|
2022-07-19 22:13:26 +00:00
|
|
|
const size_t s = str.find_first_not_of(chars);
|
2008-12-08 05:30:24 +00:00
|
|
|
|
2010-11-10 04:12:31 +00:00
|
|
|
if (str.npos != s)
|
2022-07-19 22:13:26 +00:00
|
|
|
return str.substr(s, str.find_last_not_of(chars) - s + 1);
|
2010-11-10 04:12:31 +00:00
|
|
|
else
|
|
|
|
return "";
|
2009-02-25 10:33:09 +00:00
|
|
|
}
|
2008-12-08 05:30:24 +00:00
|
|
|
|
2022-07-19 22:13:26 +00:00
|
|
|
// Turns "\n\r\t hello " into "hello" (trims at the start and end but not inside).
|
|
|
|
std::string_view StripWhitespace(std::string_view str)
|
|
|
|
{
|
|
|
|
return StripEnclosingChars(str, " \t\r\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
std::string_view StripSpaces(std::string_view str)
|
|
|
|
{
|
|
|
|
return StripEnclosingChars(str, ' ');
|
|
|
|
}
|
|
|
|
|
2008-07-12 17:40:22 +00:00
|
|
|
// "\"hello\"" is turned to "hello"
|
|
|
|
// This one assumes that the string has already been space stripped in both
|
2022-07-19 22:13:26 +00:00
|
|
|
// ends, as done by StripWhitespace above, for example.
|
2019-07-08 11:35:53 +00:00
|
|
|
std::string_view StripQuotes(std::string_view s)
|
2008-07-12 17:40:22 +00:00
|
|
|
{
|
2019-02-12 22:47:17 +00:00
|
|
|
if (!s.empty() && '\"' == s[0] && '\"' == *s.rbegin())
|
2008-10-13 19:21:25 +00:00
|
|
|
return s.substr(1, s.size() - 2);
|
2008-07-12 17:40:22 +00:00
|
|
|
else
|
2008-10-13 19:21:25 +00:00
|
|
|
return s;
|
2008-07-12 17:40:22 +00:00
|
|
|
}
|
2008-12-08 05:30:24 +00:00
|
|
|
|
2021-05-11 13:30:29 +00:00
|
|
|
// Turns "\n\rhello" into " hello".
|
|
|
|
void ReplaceBreaksWithSpaces(std::string& str)
|
|
|
|
{
|
2024-09-29 18:08:08 +00:00
|
|
|
std::ranges::replace(str, '\r', ' ');
|
|
|
|
std::ranges::replace(str, '\n', ' ');
|
2021-05-11 13:30:29 +00:00
|
|
|
}
|
|
|
|
|
2022-07-19 04:45:27 +00:00
|
|
|
void TruncateToCString(std::string* s)
|
|
|
|
{
|
|
|
|
const size_t terminator = s->find_first_of('\0');
|
|
|
|
if (terminator != s->npos)
|
|
|
|
s->resize(terminator);
|
|
|
|
}
|
|
|
|
|
2016-01-21 20:27:56 +00:00
|
|
|
bool TryParse(const std::string& str, bool* const output)
|
2008-07-12 17:40:22 +00:00
|
|
|
{
|
2016-07-12 09:42:41 +00:00
|
|
|
float value;
|
|
|
|
const bool is_valid_float = TryParse(str, &value);
|
|
|
|
if ((is_valid_float && value == 1) || !strcasecmp("true", str.c_str()))
|
2008-07-12 17:40:22 +00:00
|
|
|
*output = true;
|
2016-07-12 09:42:41 +00:00
|
|
|
else if ((is_valid_float && value == 0) || !strcasecmp("false", str.c_str()))
|
2008-07-12 17:40:22 +00:00
|
|
|
*output = false;
|
2010-06-04 19:56:34 +00:00
|
|
|
else
|
|
|
|
return false;
|
2016-06-24 08:43:46 +00:00
|
|
|
|
2010-11-10 04:12:31 +00:00
|
|
|
return true;
|
2010-06-04 19:56:34 +00:00
|
|
|
}
|
|
|
|
|
2018-06-03 12:10:52 +00:00
|
|
|
std::string ValueToString(u16 value)
|
|
|
|
{
|
2019-06-14 14:53:46 +00:00
|
|
|
return fmt::format("0x{:04x}", value);
|
2018-06-03 12:10:52 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
std::string ValueToString(u32 value)
|
|
|
|
{
|
2019-06-14 14:53:46 +00:00
|
|
|
return fmt::format("0x{:08x}", value);
|
2018-06-03 12:10:52 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
std::string ValueToString(u64 value)
|
|
|
|
{
|
2019-06-14 14:53:46 +00:00
|
|
|
return fmt::format("0x{:016x}", value);
|
2018-06-03 12:10:52 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
std::string ValueToString(float value)
|
|
|
|
{
|
2022-04-12 21:35:19 +00:00
|
|
|
return fmt::format("{:#}", value);
|
2018-06-03 12:10:52 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
std::string ValueToString(double value)
|
|
|
|
{
|
2022-04-12 21:35:19 +00:00
|
|
|
return fmt::format("{:#}", value);
|
2018-06-03 12:10:52 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
std::string ValueToString(int value)
|
|
|
|
{
|
|
|
|
return std::to_string(value);
|
|
|
|
}
|
|
|
|
|
|
|
|
std::string ValueToString(s64 value)
|
|
|
|
{
|
2019-06-14 14:53:46 +00:00
|
|
|
return std::to_string(value);
|
2018-06-03 12:10:52 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
std::string ValueToString(bool value)
|
2008-07-12 17:40:22 +00:00
|
|
|
{
|
2008-10-13 19:21:25 +00:00
|
|
|
return value ? "True" : "False";
|
2008-07-12 17:40:22 +00:00
|
|
|
}
|
2008-12-08 05:30:24 +00:00
|
|
|
|
2019-07-08 19:08:35 +00:00
|
|
|
bool SplitPath(std::string_view full_path, std::string* path, std::string* filename,
|
|
|
|
std::string* extension)
|
2008-07-12 17:40:22 +00:00
|
|
|
{
|
2010-11-10 04:12:31 +00:00
|
|
|
if (full_path.empty())
|
|
|
|
return false;
|
2008-12-08 05:30:24 +00:00
|
|
|
|
2010-11-10 04:12:31 +00:00
|
|
|
size_t dir_end = full_path.find_last_of("/"
|
2015-01-11 05:17:29 +00:00
|
|
|
// Windows needs the : included for something like just "C:" to be considered a directory
|
2010-11-10 04:12:31 +00:00
|
|
|
#ifdef _WIN32
|
|
|
|
":"
|
|
|
|
#endif
|
|
|
|
);
|
|
|
|
if (std::string::npos == dir_end)
|
|
|
|
dir_end = 0;
|
|
|
|
else
|
|
|
|
dir_end += 1;
|
2008-12-08 05:30:24 +00:00
|
|
|
|
2010-11-10 04:12:31 +00:00
|
|
|
size_t fname_end = full_path.rfind('.');
|
|
|
|
if (fname_end < dir_end || std::string::npos == fname_end)
|
|
|
|
fname_end = full_path.size();
|
2008-12-08 05:30:24 +00:00
|
|
|
|
2019-07-08 19:08:35 +00:00
|
|
|
if (path)
|
|
|
|
*path = full_path.substr(0, dir_end);
|
2008-12-08 05:30:24 +00:00
|
|
|
|
2019-07-08 19:08:35 +00:00
|
|
|
if (filename)
|
|
|
|
*filename = full_path.substr(dir_end, fname_end - dir_end);
|
2008-12-08 05:30:24 +00:00
|
|
|
|
2019-07-08 19:08:35 +00:00
|
|
|
if (extension)
|
|
|
|
*extension = full_path.substr(fname_end);
|
2008-12-08 05:30:24 +00:00
|
|
|
|
2008-10-13 19:21:25 +00:00
|
|
|
return true;
|
2008-07-12 17:40:22 +00:00
|
|
|
}
|
2008-12-08 05:30:24 +00:00
|
|
|
|
2022-04-16 00:01:24 +00:00
|
|
|
void UnifyPathSeparators(std::string& path)
|
|
|
|
{
|
|
|
|
#ifdef _WIN32
|
|
|
|
for (char& c : path)
|
|
|
|
{
|
|
|
|
if (c == '\\')
|
|
|
|
c = '/';
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
|
|
|
std::string WithUnifiedPathSeparators(std::string path)
|
|
|
|
{
|
|
|
|
UnifyPathSeparators(path);
|
|
|
|
return path;
|
|
|
|
}
|
|
|
|
|
2020-03-16 20:03:21 +00:00
|
|
|
std::string PathToFileName(std::string_view path)
|
|
|
|
{
|
|
|
|
std::string file_name, extension;
|
|
|
|
SplitPath(path, nullptr, &file_name, &extension);
|
|
|
|
return file_name + extension;
|
|
|
|
}
|
|
|
|
|
2017-06-11 14:33:10 +00:00
|
|
|
std::vector<std::string> SplitString(const std::string& str, const char delim)
|
2008-07-12 17:40:22 +00:00
|
|
|
{
|
2010-11-10 04:12:31 +00:00
|
|
|
std::istringstream iss(str);
|
2017-06-11 14:33:10 +00:00
|
|
|
std::vector<std::string> output(1);
|
2008-12-08 05:30:24 +00:00
|
|
|
|
2010-11-10 04:12:31 +00:00
|
|
|
while (std::getline(iss, *output.rbegin(), delim))
|
|
|
|
output.push_back("");
|
2008-12-08 05:30:24 +00:00
|
|
|
|
2010-11-10 04:12:31 +00:00
|
|
|
output.pop_back();
|
2017-06-11 14:33:10 +00:00
|
|
|
return output;
|
2008-07-12 17:40:22 +00:00
|
|
|
}
|
2008-12-08 05:30:24 +00:00
|
|
|
|
2019-07-08 11:35:53 +00:00
|
|
|
std::string TabsToSpaces(int tab_size, std::string str)
|
2008-11-11 16:28:46 +00:00
|
|
|
{
|
2010-11-10 04:12:31 +00:00
|
|
|
const std::string spaces(tab_size, ' ');
|
2009-04-06 06:58:00 +00:00
|
|
|
|
2010-11-10 04:12:31 +00:00
|
|
|
size_t i = 0;
|
2019-07-08 11:35:53 +00:00
|
|
|
while (str.npos != (i = str.find('\t')))
|
|
|
|
str.replace(i, 1, spaces);
|
2009-06-21 08:39:21 +00:00
|
|
|
|
2019-07-08 11:35:53 +00:00
|
|
|
return str;
|
2009-06-28 20:53:26 +00:00
|
|
|
}
|
2011-02-25 23:33:11 +00:00
|
|
|
|
2019-07-08 11:35:53 +00:00
|
|
|
std::string ReplaceAll(std::string result, std::string_view src, std::string_view dest)
|
2011-02-25 23:33:11 +00:00
|
|
|
{
|
2014-09-05 18:34:46 +00:00
|
|
|
size_t pos = 0;
|
|
|
|
|
|
|
|
if (src == dest)
|
|
|
|
return result;
|
|
|
|
|
|
|
|
while ((pos = result.find(src, pos)) != std::string::npos)
|
2011-02-25 23:33:11 +00:00
|
|
|
{
|
|
|
|
result.replace(pos, src.size(), dest);
|
2014-09-05 18:34:46 +00:00
|
|
|
pos += dest.length();
|
2011-02-25 23:33:11 +00:00
|
|
|
}
|
2014-09-05 18:34:46 +00:00
|
|
|
|
2011-02-25 23:33:11 +00:00
|
|
|
return result;
|
|
|
|
}
|
|
|
|
|
2017-06-06 04:08:51 +00:00
|
|
|
void StringPopBackIf(std::string* s, char c)
|
|
|
|
{
|
|
|
|
if (!s->empty() && s->back() == c)
|
|
|
|
s->pop_back();
|
|
|
|
}
|
|
|
|
|
2023-01-24 21:55:41 +00:00
|
|
|
size_t StringUTF8CodePointCount(std::string_view str)
|
2018-11-21 05:15:44 +00:00
|
|
|
{
|
2024-09-22 01:24:22 +00:00
|
|
|
return str.size() - std::ranges::count_if(str, [](char c) -> bool { return (c & 0xC0) == 0x80; });
|
2018-11-21 05:15:44 +00:00
|
|
|
}
|
|
|
|
|
2013-02-28 00:00:42 +00:00
|
|
|
#ifdef _WIN32
|
|
|
|
|
2023-12-29 18:50:55 +00:00
|
|
|
static std::wstring CPToUTF16(u32 code_page, std::string_view input)
|
2013-02-28 00:00:42 +00:00
|
|
|
{
|
2017-05-01 12:08:47 +00:00
|
|
|
auto const size =
|
|
|
|
MultiByteToWideChar(code_page, 0, input.data(), static_cast<int>(input.size()), nullptr, 0);
|
2013-02-28 00:00:42 +00:00
|
|
|
|
|
|
|
std::wstring output;
|
|
|
|
output.resize(size);
|
|
|
|
|
2013-11-13 09:03:46 +00:00
|
|
|
if (size == 0 ||
|
2017-05-01 12:08:47 +00:00
|
|
|
size != MultiByteToWideChar(code_page, 0, input.data(), static_cast<int>(input.size()),
|
|
|
|
&output[0], static_cast<int>(output.size())))
|
2013-11-13 09:03:46 +00:00
|
|
|
{
|
2013-02-28 00:00:42 +00:00
|
|
|
output.clear();
|
2013-11-13 09:03:46 +00:00
|
|
|
}
|
2013-02-28 00:00:42 +00:00
|
|
|
|
|
|
|
return output;
|
|
|
|
}
|
|
|
|
|
2023-12-29 18:50:55 +00:00
|
|
|
static std::string UTF16ToCP(u32 code_page, std::wstring_view input)
|
2017-05-01 12:08:47 +00:00
|
|
|
{
|
2020-10-23 18:41:30 +00:00
|
|
|
if (input.empty())
|
|
|
|
return {};
|
2017-05-01 12:08:47 +00:00
|
|
|
|
2020-10-23 18:41:30 +00:00
|
|
|
// "If cchWideChar [input buffer size] is set to 0, the function fails." -MSDN
|
|
|
|
auto const size = WideCharToMultiByte(code_page, 0, input.data(), static_cast<int>(input.size()),
|
|
|
|
nullptr, 0, nullptr, nullptr);
|
2018-11-18 13:22:28 +00:00
|
|
|
|
2020-10-23 18:41:30 +00:00
|
|
|
std::string output(size, '\0');
|
2018-11-18 13:22:28 +00:00
|
|
|
|
2020-10-23 18:41:30 +00:00
|
|
|
if (size != WideCharToMultiByte(code_page, 0, input.data(), static_cast<int>(input.size()),
|
|
|
|
output.data(), static_cast<int>(output.size()), nullptr, nullptr))
|
|
|
|
{
|
|
|
|
const DWORD error_code = GetLastError();
|
|
|
|
ERROR_LOG_FMT(COMMON, "WideCharToMultiByte Error in String '{}': {}", WStringToUTF8(input),
|
|
|
|
error_code);
|
|
|
|
return {};
|
2017-05-01 12:08:47 +00:00
|
|
|
}
|
2018-11-18 13:22:28 +00:00
|
|
|
|
2017-05-01 12:08:47 +00:00
|
|
|
return output;
|
|
|
|
}
|
|
|
|
|
2020-06-28 16:15:30 +00:00
|
|
|
std::wstring UTF8ToWString(std::string_view input)
|
2013-03-03 01:46:55 +00:00
|
|
|
{
|
|
|
|
return CPToUTF16(CP_UTF8, input);
|
|
|
|
}
|
|
|
|
|
2020-06-28 16:15:30 +00:00
|
|
|
std::string WStringToUTF8(std::wstring_view input)
|
2017-11-11 16:32:44 +00:00
|
|
|
{
|
|
|
|
return UTF16ToCP(CP_UTF8, input);
|
|
|
|
}
|
|
|
|
|
2019-07-08 11:35:53 +00:00
|
|
|
std::string SHIFTJISToUTF8(std::string_view input)
|
2013-03-03 01:46:55 +00:00
|
|
|
{
|
2020-06-28 16:15:30 +00:00
|
|
|
return WStringToUTF8(CPToUTF16(CODEPAGE_SHIFT_JIS, input));
|
2017-05-01 12:08:47 +00:00
|
|
|
}
|
|
|
|
|
2019-07-08 11:35:53 +00:00
|
|
|
std::string UTF8ToSHIFTJIS(std::string_view input)
|
2017-05-01 12:08:47 +00:00
|
|
|
{
|
2020-06-28 16:15:30 +00:00
|
|
|
return UTF16ToCP(CODEPAGE_SHIFT_JIS, UTF8ToWString(input));
|
2013-03-03 01:46:55 +00:00
|
|
|
}
|
|
|
|
|
2019-07-08 11:35:53 +00:00
|
|
|
std::string CP1252ToUTF8(std::string_view input)
|
2013-03-03 04:57:49 +00:00
|
|
|
{
|
2020-06-28 16:15:30 +00:00
|
|
|
return WStringToUTF8(CPToUTF16(CODEPAGE_WINDOWS_1252, input));
|
2013-03-03 04:57:49 +00:00
|
|
|
}
|
|
|
|
|
2018-01-10 14:49:35 +00:00
|
|
|
std::string UTF16BEToUTF8(const char16_t* str, size_t max_size)
|
|
|
|
{
|
|
|
|
const char16_t* str_end = std::find(str, str + max_size, '\0');
|
|
|
|
std::wstring result(static_cast<size_t>(str_end - str), '\0');
|
|
|
|
std::transform(str, str_end, result.begin(), static_cast<u16 (&)(u16)>(Common::swap16));
|
2020-06-28 16:15:30 +00:00
|
|
|
return WStringToUTF8(result);
|
2018-01-10 14:49:35 +00:00
|
|
|
}
|
|
|
|
|
2013-03-03 01:46:55 +00:00
|
|
|
#else
|
|
|
|
|
2013-03-03 04:57:49 +00:00
|
|
|
template <typename T>
|
2019-07-08 11:35:53 +00:00
|
|
|
std::string CodeTo(const char* tocode, const char* fromcode, std::basic_string_view<T> input)
|
2013-03-03 04:57:49 +00:00
|
|
|
{
|
|
|
|
std::string result;
|
2016-06-24 08:43:46 +00:00
|
|
|
|
2017-05-01 12:08:47 +00:00
|
|
|
iconv_t const conv_desc = iconv_open(tocode, fromcode);
|
2013-03-03 04:57:49 +00:00
|
|
|
if ((iconv_t)-1 == conv_desc)
|
|
|
|
{
|
2020-10-23 18:41:30 +00:00
|
|
|
ERROR_LOG_FMT(COMMON, "Iconv initialization failure [{}]: {}", fromcode, strerror(errno));
|
2013-03-03 04:57:49 +00:00
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
size_t const in_bytes = sizeof(T) * input.size();
|
|
|
|
size_t const out_buffer_size = 4 * in_bytes;
|
2016-06-24 08:43:46 +00:00
|
|
|
|
2013-03-03 04:57:49 +00:00
|
|
|
std::string out_buffer;
|
|
|
|
out_buffer.resize(out_buffer_size);
|
2016-06-24 08:43:46 +00:00
|
|
|
|
2019-07-08 11:35:53 +00:00
|
|
|
auto src_buffer = input.data();
|
2013-03-03 04:57:49 +00:00
|
|
|
size_t src_bytes = in_bytes;
|
2019-07-08 11:35:53 +00:00
|
|
|
auto dst_buffer = out_buffer.data();
|
2013-03-03 04:57:49 +00:00
|
|
|
size_t dst_bytes = out_buffer.size();
|
2016-06-24 08:43:46 +00:00
|
|
|
|
2013-03-03 22:51:26 +00:00
|
|
|
while (src_bytes != 0)
|
2013-03-03 04:57:49 +00:00
|
|
|
{
|
2013-03-03 22:51:26 +00:00
|
|
|
size_t const iconv_result =
|
2020-12-04 16:09:42 +00:00
|
|
|
iconv(conv_desc, const_cast<char**>(reinterpret_cast<const char**>(&src_buffer)),
|
|
|
|
&src_bytes, &dst_buffer, &dst_bytes);
|
2013-03-03 22:51:26 +00:00
|
|
|
if ((size_t)-1 == iconv_result)
|
|
|
|
{
|
|
|
|
if (EILSEQ == errno || EINVAL == errno)
|
|
|
|
{
|
|
|
|
// Try to skip the bad character
|
|
|
|
if (src_bytes != 0)
|
|
|
|
{
|
|
|
|
--src_bytes;
|
|
|
|
++src_buffer;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
2020-10-23 18:41:30 +00:00
|
|
|
ERROR_LOG_FMT(COMMON, "iconv failure [{}]: {}", fromcode, strerror(errno));
|
2013-03-03 22:51:26 +00:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
2013-03-03 04:57:49 +00:00
|
|
|
}
|
2016-06-24 08:43:46 +00:00
|
|
|
|
2013-03-03 22:51:26 +00:00
|
|
|
out_buffer.resize(out_buffer_size - dst_bytes);
|
|
|
|
out_buffer.swap(result);
|
2016-06-24 08:43:46 +00:00
|
|
|
|
2013-03-03 04:57:49 +00:00
|
|
|
iconv_close(conv_desc);
|
|
|
|
}
|
2016-06-24 08:43:46 +00:00
|
|
|
|
2013-03-03 04:57:49 +00:00
|
|
|
return result;
|
|
|
|
}
|
|
|
|
|
2017-05-01 12:08:47 +00:00
|
|
|
template <typename T>
|
2019-07-08 11:35:53 +00:00
|
|
|
std::string CodeToUTF8(const char* fromcode, std::basic_string_view<T> input)
|
2017-05-01 12:08:47 +00:00
|
|
|
{
|
|
|
|
return CodeTo("UTF-8", fromcode, input);
|
|
|
|
}
|
|
|
|
|
2019-07-08 11:35:53 +00:00
|
|
|
std::string CP1252ToUTF8(std::string_view input)
|
2013-03-03 01:46:55 +00:00
|
|
|
{
|
2013-03-03 22:51:26 +00:00
|
|
|
// return CodeToUTF8("CP1252//TRANSLIT", input);
|
|
|
|
// return CodeToUTF8("CP1252//IGNORE", input);
|
2013-03-03 04:57:49 +00:00
|
|
|
return CodeToUTF8("CP1252", input);
|
2013-03-03 01:46:55 +00:00
|
|
|
}
|
|
|
|
|
2019-07-08 11:35:53 +00:00
|
|
|
std::string SHIFTJISToUTF8(std::string_view input)
|
2013-03-03 01:46:55 +00:00
|
|
|
{
|
2013-03-03 04:57:49 +00:00
|
|
|
// return CodeToUTF8("CP932", input);
|
|
|
|
return CodeToUTF8("SJIS", input);
|
|
|
|
}
|
|
|
|
|
2019-07-08 11:35:53 +00:00
|
|
|
std::string UTF8ToSHIFTJIS(std::string_view input)
|
2017-05-01 12:08:47 +00:00
|
|
|
{
|
|
|
|
return CodeTo("SJIS", "UTF-8", input);
|
|
|
|
}
|
|
|
|
|
2020-06-28 16:15:30 +00:00
|
|
|
std::string WStringToUTF8(std::wstring_view input)
|
2013-03-03 04:57:49 +00:00
|
|
|
{
|
2020-06-28 16:22:18 +00:00
|
|
|
using codecvt = std::conditional_t<sizeof(wchar_t) == 2, std::codecvt_utf8_utf16<wchar_t>,
|
|
|
|
std::codecvt_utf8<wchar_t>>;
|
|
|
|
|
|
|
|
std::wstring_convert<codecvt, wchar_t> converter;
|
2019-07-08 11:35:53 +00:00
|
|
|
return converter.to_bytes(input.data(), input.data() + input.size());
|
2013-03-03 01:46:55 +00:00
|
|
|
}
|
|
|
|
|
2017-11-02 16:05:45 +00:00
|
|
|
std::string UTF16BEToUTF8(const char16_t* str, size_t max_size)
|
|
|
|
{
|
|
|
|
const char16_t* str_end = std::find(str, str + max_size, '\0');
|
2019-07-08 11:35:53 +00:00
|
|
|
return CodeToUTF8("UTF-16BE", std::u16string_view(str, static_cast<size_t>(str_end - str)));
|
2017-11-02 16:05:45 +00:00
|
|
|
}
|
2018-01-10 14:49:35 +00:00
|
|
|
|
|
|
|
#endif
|
2019-06-21 16:07:59 +00:00
|
|
|
|
2020-06-28 17:16:23 +00:00
|
|
|
std::string UTF16ToUTF8(std::u16string_view input)
|
|
|
|
{
|
|
|
|
std::wstring_convert<std::codecvt_utf8_utf16<char16_t>, char16_t> converter;
|
|
|
|
return converter.to_bytes(input.data(), input.data() + input.size());
|
|
|
|
}
|
|
|
|
|
|
|
|
std::u16string UTF8ToUTF16(std::string_view input)
|
|
|
|
{
|
|
|
|
std::wstring_convert<std::codecvt_utf8_utf16<char16_t>, char16_t> converter;
|
|
|
|
return converter.from_bytes(input.data(), input.data() + input.size());
|
|
|
|
}
|
|
|
|
|
2019-06-21 16:07:59 +00:00
|
|
|
// This is a replacement for path::u8path, which is deprecated starting with C++20.
|
|
|
|
std::filesystem::path StringToPath(std::string_view path)
|
|
|
|
{
|
|
|
|
#ifdef _MSC_VER
|
2020-06-28 16:15:30 +00:00
|
|
|
return std::filesystem::path(UTF8ToWString(path));
|
2019-06-21 16:07:59 +00:00
|
|
|
#else
|
|
|
|
return std::filesystem::path(path);
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
|
|
|
// This is a replacement for path::u8string that always has the return type std::string.
|
|
|
|
// path::u8string returns std::u8string starting with C++20, which is annoying to convert.
|
|
|
|
std::string PathToString(const std::filesystem::path& path)
|
|
|
|
{
|
|
|
|
#ifdef _MSC_VER
|
2020-06-28 16:15:30 +00:00
|
|
|
return WStringToUTF8(path.native());
|
2019-06-21 16:07:59 +00:00
|
|
|
#else
|
|
|
|
return path.native();
|
|
|
|
#endif
|
|
|
|
}
|
2020-09-21 09:23:06 +00:00
|
|
|
|
2023-05-16 18:23:21 +00:00
|
|
|
namespace Common
|
|
|
|
{
|
2020-09-21 09:23:06 +00:00
|
|
|
#ifdef _WIN32
|
|
|
|
std::vector<std::string> CommandLineToUtf8Argv(const wchar_t* command_line)
|
|
|
|
{
|
|
|
|
int nargs;
|
|
|
|
LPWSTR* tokenized = CommandLineToArgvW(command_line, &nargs);
|
|
|
|
if (!tokenized)
|
|
|
|
return {};
|
|
|
|
|
|
|
|
std::vector<std::string> argv(nargs);
|
|
|
|
for (size_t i = 0; i < nargs; ++i)
|
|
|
|
{
|
|
|
|
argv[i] = WStringToUTF8(tokenized[i]);
|
|
|
|
}
|
|
|
|
|
|
|
|
LocalFree(tokenized);
|
|
|
|
return argv;
|
|
|
|
}
|
|
|
|
#endif
|
2021-05-24 16:44:21 +00:00
|
|
|
|
|
|
|
std::string GetEscapedHtml(std::string html)
|
|
|
|
{
|
|
|
|
static constexpr std::array<std::array<const char*, 2>, 5> replacements{{
|
|
|
|
// Escape ampersand first to avoid escaping the ampersands in other replacements
|
|
|
|
{{"&", "&"}},
|
|
|
|
{{"<", "<"}},
|
|
|
|
{{">", ">"}},
|
|
|
|
{{"\"", """}},
|
|
|
|
{{"'", "'"}},
|
|
|
|
}};
|
|
|
|
|
|
|
|
for (const auto& [unescaped, escaped] : replacements)
|
|
|
|
{
|
|
|
|
html = ReplaceAll(html, unescaped, escaped);
|
|
|
|
}
|
|
|
|
return html;
|
|
|
|
}
|
2022-01-17 00:23:12 +00:00
|
|
|
|
|
|
|
void ToLower(std::string* str)
|
|
|
|
{
|
2024-09-29 17:44:00 +00:00
|
|
|
std::ranges::transform(*str, str->begin(), static_cast<char (&)(char)>(Common::ToLower));
|
2022-01-17 00:23:12 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
void ToUpper(std::string* str)
|
|
|
|
{
|
2024-09-29 17:44:00 +00:00
|
|
|
std::ranges::transform(*str, str->begin(), static_cast<char (&)(char)>(Common::ToUpper));
|
2022-01-17 00:23:12 +00:00
|
|
|
}
|
2022-05-31 00:06:42 +00:00
|
|
|
|
|
|
|
bool CaseInsensitiveEquals(std::string_view a, std::string_view b)
|
|
|
|
{
|
2024-09-22 05:32:24 +00:00
|
|
|
return std::ranges::equal(
|
|
|
|
a, b, [](char ca, char cb) { return Common::ToLower(ca) == Common::ToLower(cb); });
|
|
|
|
}
|
|
|
|
|
|
|
|
bool CaseInsensitiveLess::operator()(std::string_view a, std::string_view b) const
|
|
|
|
{
|
|
|
|
return std::ranges::lexicographical_compare(
|
|
|
|
a, b, [](char ca, char cb) { return Common::ToLower(ca) < Common::ToLower(cb); });
|
2022-05-31 00:06:42 +00:00
|
|
|
}
|
2023-08-15 01:02:57 +00:00
|
|
|
|
|
|
|
std::string BytesToHexString(std::span<const u8> bytes)
|
|
|
|
{
|
|
|
|
return fmt::format("{:02x}", fmt::join(bytes, ""));
|
|
|
|
}
|
2022-01-17 00:23:12 +00:00
|
|
|
} // namespace Common
|