yuzu/src/common/string_util.cpp

481 lines
12 KiB
C++
Raw Normal View History

2014-12-17 05:38:14 +00:00
// Copyright 2013 Dolphin Emulator Project / 2014 Citra Emulator Project
// Licensed under GPLv2 or any later version
// Refer to the license.txt file included.
#include <boost/range/algorithm.hpp>
2015-05-06 07:06:12 +00:00
#include "common/common_funcs.h"
#include "common/common_paths.h"
#include "common/logging/log.h"
#include "common/string_util.h"
#ifdef _MSC_VER
2014-04-01 22:20:08 +00:00
#include <Windows.h>
#include <codecvt>
#else
2014-04-01 22:20:08 +00:00
#include <iconv.h>
#endif
namespace Common {
/// Make a string lowercase
std::string ToLower(std::string str) {
boost::transform(str, str.begin(), ::tolower);
return str;
}
/// Make a string uppercase
std::string ToUpper(std::string str) {
boost::transform(str, str.begin(), ::toupper);
return str;
}
// faster than sscanf
bool AsciiToHex(const char* _szValue, u32& result)
{
2014-12-03 18:57:57 +00:00
char *endptr = nullptr;
2014-04-01 22:20:08 +00:00
const u32 value = strtoul(_szValue, &endptr, 16);
2014-04-01 22:20:08 +00:00
if (!endptr || *endptr)
return false;
2014-04-01 22:20:08 +00:00
result = value;
return true;
}
bool CharArrayFromFormatV(char* out, int outsize, const char* format, va_list args)
{
2014-04-01 22:20:08 +00:00
int writtenCount;
#ifdef _MSC_VER
2014-04-01 22:20:08 +00:00
// 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.
//
// This is why we lookup an ANSI (cp1252) locale here and use _vsnprintf_l.
2014-12-03 18:57:57 +00:00
static locale_t c_locale = nullptr;
2014-04-01 22:20:08 +00:00
if (!c_locale)
c_locale = _create_locale(LC_ALL, ".1252");
writtenCount = _vsnprintf_l(out, outsize, format, c_locale, args);
#else
2014-04-01 22:20:08 +00:00
writtenCount = vsnprintf(out, outsize, format, args);
#endif
2014-04-01 22:20:08 +00:00
if (writtenCount > 0 && writtenCount < outsize)
{
out[writtenCount] = '\0';
return true;
}
else
{
out[outsize - 1] = '\0';
return false;
}
}
std::string StringFromFormat(const char* format, ...)
{
2014-04-01 22:20:08 +00:00
va_list args;
2014-12-03 18:57:57 +00:00
char *buf = nullptr;
#ifdef _WIN32
2014-04-01 22:20:08 +00:00
int required = 0;
2014-04-01 22:20:08 +00:00
va_start(args, format);
required = _vscprintf(format, args);
buf = new char[required + 1];
CharArrayFromFormatV(buf, required + 1, format, args);
va_end(args);
2014-04-01 22:20:08 +00:00
std::string temp = buf;
delete[] buf;
#else
2014-04-01 22:20:08 +00:00
va_start(args, format);
if (vasprintf(&buf, format, args) < 0)
LOG_ERROR(Common, "Unable to allocate memory for string");
2014-04-01 22:20:08 +00:00
va_end(args);
2014-04-01 22:20:08 +00:00
std::string temp = buf;
free(buf);
#endif
2014-04-01 22:20:08 +00:00
return temp;
}
// For Debugging. Read out an u8 array.
std::string ArrayToString(const u8 *data, u32 size, int line_len, bool spaces)
{
2014-04-01 22:20:08 +00:00
std::ostringstream oss;
oss << std::setfill('0') << std::hex;
2014-04-01 22:20:08 +00:00
for (int line = 0; size; ++data, --size)
{
oss << std::setw(2) << (int)*data;
2014-04-01 22:20:08 +00:00
if (line_len == ++line)
{
oss << '\n';
line = 0;
}
else if (spaces)
oss << ' ';
}
return oss.str();
}
// Turns " hej " into "hej". Also handles tabs.
std::string StripSpaces(const std::string &str)
{
2014-04-01 22:20:08 +00:00
const size_t s = str.find_first_not_of(" \t\r\n");
2014-04-01 22:20:08 +00:00
if (str.npos != s)
return str.substr(s, str.find_last_not_of(" \t\r\n") - s + 1);
else
return "";
}
// "\"hello\"" is turned to "hello"
// This one assumes that the string has already been space stripped in both
// ends, as done by StripSpaces above, for example.
std::string StripQuotes(const std::string& s)
{
2014-04-01 22:20:08 +00:00
if (s.size() && '\"' == s[0] && '\"' == *s.rbegin())
return s.substr(1, s.size() - 2);
else
return s;
}
bool TryParse(const std::string &str, u32 *const output)
{
2014-12-03 18:57:57 +00:00
char *endptr = nullptr;
2014-04-01 22:20:08 +00:00
// Reset errno to a value other than ERANGE
errno = 0;
2014-04-01 22:20:08 +00:00
unsigned long value = strtoul(str.c_str(), &endptr, 0);
2014-04-01 22:20:08 +00:00
if (!endptr || *endptr)
return false;
2014-04-01 22:20:08 +00:00
if (errno == ERANGE)
return false;
#if ULONG_MAX > UINT_MAX
2014-04-01 22:20:08 +00:00
if (value >= 0x100000000ull
&& value <= 0xFFFFFFFF00000000ull)
return false;
#endif
2014-04-01 22:20:08 +00:00
*output = static_cast<u32>(value);
return true;
}
bool TryParse(const std::string &str, bool *const output)
{
if ("1" == str || "true" == ToLower(str))
2014-04-01 22:20:08 +00:00
*output = true;
else if ("0" == str || "false" == ToLower(str))
2014-04-01 22:20:08 +00:00
*output = false;
else
return false;
return true;
}
std::string StringFromBool(bool value)
{
2014-04-01 22:20:08 +00:00
return value ? "True" : "False";
}
bool SplitPath(const std::string& full_path, std::string* _pPath, std::string* _pFilename, std::string* _pExtension)
{
2014-04-01 22:20:08 +00:00
if (full_path.empty())
return false;
2014-04-01 22:20:08 +00:00
size_t dir_end = full_path.find_last_of("/"
// windows needs the : included for something like just "C:" to be considered a directory
#ifdef _WIN32
2014-04-01 22:20:08 +00:00
":"
#endif
2014-04-01 22:20:08 +00:00
);
if (std::string::npos == dir_end)
dir_end = 0;
else
dir_end += 1;
2014-04-01 22:20:08 +00:00
size_t fname_end = full_path.rfind('.');
if (fname_end < dir_end || std::string::npos == fname_end)
fname_end = full_path.size();
2014-04-01 22:20:08 +00:00
if (_pPath)
*_pPath = full_path.substr(0, dir_end);
2014-04-01 22:20:08 +00:00
if (_pFilename)
*_pFilename = full_path.substr(dir_end, fname_end - dir_end);
2014-04-01 22:20:08 +00:00
if (_pExtension)
*_pExtension = full_path.substr(fname_end);
2014-04-01 22:20:08 +00:00
return true;
}
void BuildCompleteFilename(std::string& _CompleteFilename, const std::string& _Path, const std::string& _Filename)
{
2014-04-01 22:20:08 +00:00
_CompleteFilename = _Path;
2014-04-01 22:20:08 +00:00
// check for seperator
if (DIR_SEP_CHR != *_CompleteFilename.rbegin())
_CompleteFilename += DIR_SEP_CHR;
2014-04-01 22:20:08 +00:00
// add the filename
_CompleteFilename += _Filename;
}
void SplitString(const std::string& str, const char delim, std::vector<std::string>& output)
{
2014-04-01 22:20:08 +00:00
std::istringstream iss(str);
output.resize(1);
2014-04-01 22:20:08 +00:00
while (std::getline(iss, *output.rbegin(), delim))
output.push_back("");
2014-04-01 22:20:08 +00:00
output.pop_back();
}
std::string TabsToSpaces(int tab_size, const std::string &in)
{
2014-04-01 22:20:08 +00:00
const std::string spaces(tab_size, ' ');
std::string out(in);
2014-04-01 22:20:08 +00:00
size_t i = 0;
while (out.npos != (i = out.find('\t')))
out.replace(i, 1, spaces);
2014-04-01 22:20:08 +00:00
return out;
}
std::string ReplaceAll(std::string result, const std::string& src, const std::string& dest)
{
size_t pos = 0;
if (src == dest)
return result;
while ((pos = result.find(src, pos)) != std::string::npos)
2014-04-01 22:20:08 +00:00
{
result.replace(pos, src.size(), dest);
pos += dest.length();
2014-04-01 22:20:08 +00:00
}
2014-04-01 22:20:08 +00:00
return result;
}
#ifdef _MSC_VER
std::string UTF16ToUTF8(const std::u16string& input)
{
std::wstring_convert<std::codecvt_utf8_utf16<char16_t>, char16_t> convert;
return convert.to_bytes(input);
}
std::u16string UTF8ToUTF16(const std::string& input)
{
std::wstring_convert<std::codecvt_utf8_utf16<char16_t>, char16_t> convert;
return convert.from_bytes(input);
}
static std::string UTF16ToUTF8(const std::wstring& input)
{
2015-02-01 20:31:21 +00:00
auto const size = WideCharToMultiByte(CP_UTF8, 0, input.data(), static_cast<int>(input.size()), nullptr, 0, nullptr, nullptr);
2014-04-01 22:20:08 +00:00
std::string output;
output.resize(size);
2014-04-01 22:20:08 +00:00
if (size == 0 || size != WideCharToMultiByte(CP_UTF8, 0, input.data(), input.size(), &output[0], output.size(), nullptr, nullptr))
output.clear();
2014-04-01 22:20:08 +00:00
return output;
}
static std::wstring CPToUTF16(u32 code_page, const std::string& input)
{
2015-02-01 20:31:21 +00:00
auto const size = MultiByteToWideChar(code_page, 0, input.data(), static_cast<int>(input.size()), nullptr, 0);
2014-04-01 22:20:08 +00:00
std::wstring output;
output.resize(size);
2015-02-01 20:31:21 +00:00
if (size == 0 || size != MultiByteToWideChar(code_page, 0, input.data(), static_cast<int>(input.size()), &output[0], static_cast<int>(output.size())))
2014-04-01 22:20:08 +00:00
output.clear();
2014-04-01 22:20:08 +00:00
return output;
}
std::wstring UTF8ToUTF16W(const std::string &input)
{
2014-04-01 22:20:08 +00:00
return CPToUTF16(CP_UTF8, input);
}
std::string SHIFTJISToUTF8(const std::string& input)
{
2014-04-01 22:20:08 +00:00
return UTF16ToUTF8(CPToUTF16(932, input));
}
std::string CP1252ToUTF8(const std::string& input)
{
2014-04-01 22:20:08 +00:00
return UTF16ToUTF8(CPToUTF16(1252, input));
}
#else
template <typename T>
static std::string CodeToUTF8(const char* fromcode, const std::basic_string<T>& input)
{
2014-04-01 22:20:08 +00:00
std::string result;
iconv_t const conv_desc = iconv_open("UTF-8", fromcode);
if ((iconv_t)(-1) == conv_desc)
2014-04-01 22:20:08 +00:00
{
LOG_ERROR(Common, "Iconv initialization failure [%s]: %s", fromcode, strerror(errno));
iconv_close(conv_desc);
return {};
2014-04-01 22:20:08 +00:00
}
const size_t in_bytes = sizeof(T) * input.size();
// Multiply by 4, which is the max number of bytes to encode a codepoint
const size_t out_buffer_size = 4 * in_bytes;
2014-04-01 22:20:08 +00:00
std::string out_buffer;
out_buffer.resize(out_buffer_size);
2014-04-01 22:20:08 +00:00
auto src_buffer = &input[0];
size_t src_bytes = in_bytes;
auto dst_buffer = &out_buffer[0];
size_t dst_bytes = out_buffer.size();
2014-04-01 22:20:08 +00:00
while (0 != src_bytes)
{
size_t const iconv_result = iconv(conv_desc, (char**)(&src_buffer), &src_bytes,
&dst_buffer, &dst_bytes);
if (static_cast<size_t>(-1) == iconv_result)
{
if (EILSEQ == errno || EINVAL == errno)
2014-04-01 22:20:08 +00:00
{
// Try to skip the bad character
if (0 != src_bytes)
2014-04-01 22:20:08 +00:00
{
--src_bytes;
++src_buffer;
2014-04-01 22:20:08 +00:00
}
}
else
{
LOG_ERROR(Common, "iconv failure [%s]: %s", fromcode, strerror(errno));
break;
}
2014-04-01 22:20:08 +00:00
}
}
2014-04-01 22:20:08 +00:00
out_buffer.resize(out_buffer_size - dst_bytes);
out_buffer.swap(result);
iconv_close(conv_desc);
return result;
}
std::u16string UTF8ToUTF16(const std::string& input)
{
std::u16string result;
iconv_t const conv_desc = iconv_open("UTF-16LE", "UTF-8");
if ((iconv_t)(-1) == conv_desc)
{
LOG_ERROR(Common, "Iconv initialization failure [UTF-8]: %s", strerror(errno));
2014-04-01 22:20:08 +00:00
iconv_close(conv_desc);
return {};
2014-04-01 22:20:08 +00:00
}
const size_t in_bytes = sizeof(char) * input.size();
// Multiply by 4, which is the max number of bytes to encode a codepoint
const size_t out_buffer_size = 4 * sizeof(char16_t) * in_bytes;
std::u16string out_buffer;
out_buffer.resize(out_buffer_size);
char* src_buffer = const_cast<char*>(&input[0]);
size_t src_bytes = in_bytes;
char* dst_buffer = (char*)(&out_buffer[0]);
size_t dst_bytes = out_buffer.size();
while (0 != src_bytes)
{
size_t const iconv_result = iconv(conv_desc, &src_buffer, &src_bytes,
&dst_buffer, &dst_bytes);
if (static_cast<size_t>(-1) == iconv_result)
{
if (EILSEQ == errno || EINVAL == errno)
{
// Try to skip the bad character
if (0 != src_bytes)
{
--src_bytes;
++src_buffer;
}
}
else
{
LOG_ERROR(Common, "iconv failure [UTF-8]: %s", strerror(errno));
break;
}
}
}
out_buffer.resize(out_buffer_size - dst_bytes);
out_buffer.swap(result);
iconv_close(conv_desc);
2014-04-01 22:20:08 +00:00
return result;
}
std::string UTF16ToUTF8(const std::u16string& input)
{
return CodeToUTF8("UTF-16LE", input);
}
std::string CP1252ToUTF8(const std::string& input)
{
2014-04-01 22:20:08 +00:00
//return CodeToUTF8("CP1252//TRANSLIT", input);
//return CodeToUTF8("CP1252//IGNORE", input);
return CodeToUTF8("CP1252", input);
}
std::string SHIFTJISToUTF8(const std::string& input)
{
2014-04-01 22:20:08 +00:00
//return CodeToUTF8("CP932", input);
return CodeToUTF8("SJIS", input);
}
#endif
}