ilikecats/stk-code_catmod
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Make tinygettext work

Browse Source 
git-svn-id: svn+ssh://svn.code.sf.net/p/supertuxkart/code/main/branches/tinygettext@7942 178a84e3-b1eb-0310-8ba1-8eac791a3b58
This commit is contained in:
auria 2011-03-16 15:05:25 +00:00
parent 00cfa448fa
commit d3604d050c
9 changed files with 1144 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/ide/Xcode/Config.xcconfig
View File

@ -4,5 +4,5 @@ HEADER_SEARCH_PATHS = /usr/local/include /usr/include /Library/Frameworks/IrrFra
OTHER_CFLAGS = -Wall -DHAVE_OGGVORBIS=1 -DHAS_SOCKLEN_T -DSTDC_HEADERS=1 -DHAVE_SYS_TYPES_H=1 -DHAVE_SYS_STAT_H=1 -DHAVE_STDLIB_H=1 -DHAVE_STRING_H=1 -DHAVE_MEMORY_H=1 -DHAVE_STRINGS_H=1 -DHAVE_INTTYPES_H=1 -DHAVE_STDINT_H=1 -DHAVE_UNISTD_H=1 -DHAS_POLL=1 -DHAS_FCNTL=1 -DHAS_INET_PTON=1 -DHAS_INET_NTOP=1 -DHAS_MSGHDR_FLAGS=1 -DENABLE_NLS=1 -DHAVE_GETTEXT=1 -DHAVE_GLUT=1 -DHAVE_IRRLICHT=1 -DPACKAGE="\"supertuxkart\"" -D__MACOSX__=1 -DHAVE_RTT=0 -DENABLE_BIDI=1 -fvisibility=hidden -DVERSION=\"svn\"
OTHER_LDFLAGS = -lintl
OTHER_LDFLAGS = -liconv
LIBRARY_SEARCH_PATHS = /usr/local/lib /usr/lib

67
src/ide/Xcode/STK_XCode.xcodeproj/project.pbxproj
View File

@ -308,6 +308,15 @@
95833240101243ED00C5137E /* player_info_dialog.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 95833239101243ED00C5137E /* player_info_dialog.cpp */; };
95833241101243ED00C5137E /* press_a_key_dialog.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 9583323B101243ED00C5137E /* press_a_key_dialog.cpp */; };
95833242101243ED00C5137E /* track_info_dialog.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 9583323D101243ED00C5137E /* track_info_dialog.cpp */; };
9584449E1330F89100CEA60A /* dictionary.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 9584448A1330F89100CEA60A /* dictionary.cpp */; };
9584449F1330F89100CEA60A /* dictionary_manager.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 9584448C1330F89100CEA60A /* dictionary_manager.cpp */; };
958444A01330F89100CEA60A /* iconv.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 9584448F1330F89100CEA60A /* iconv.cpp */; };
958444A11330F89100CEA60A /* language.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 958444911330F89100CEA60A /* language.cpp */; };
958444A21330F89100CEA60A /* log.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 958444931330F89100CEA60A /* log.cpp */; };
958444A31330F89100CEA60A /* plural_forms.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 958444961330F89100CEA60A /* plural_forms.cpp */; };
958444A41330F89100CEA60A /* po_parser.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 958444981330F89100CEA60A /* po_parser.cpp */; };
958444A51330F89100CEA60A /* stk_file_system.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 9584449A1330F89100CEA60A /* stk_file_system.cpp */; };
958444A61330F89100CEA60A /* tinygettext.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 9584449C1330F89100CEA60A /* tinygettext.cpp */; };
9586318411B1EC9F00B8B4AF /* grand_prix_lose.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 9586318011B1EC9F00B8B4AF /* grand_prix_lose.cpp */; };
9586318511B1EC9F00B8B4AF /* grand_prix_win.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 9586318211B1EC9F00B8B4AF /* grand_prix_win.cpp */; };
958BD770117F6AE90095B483 /* music_manager.cpp in Sources */ = {isa = PBXBuildFile; fileRef = 958BD76E117F6AE90095B483 /* music_manager.cpp */; };
@ -1045,6 +1054,26 @@
9583323C101243ED00C5137E /* press_a_key_dialog.hpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.h; name = press_a_key_dialog.hpp; path = ../../states_screens/dialogs/press_a_key_dialog.hpp; sourceTree = SOURCE_ROOT; };
9583323D101243ED00C5137E /* track_info_dialog.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; name = track_info_dialog.cpp; path = ../../states_screens/dialogs/track_info_dialog.cpp; sourceTree = SOURCE_ROOT; };
9583323E101243ED00C5137E /* track_info_dialog.hpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.h; name = track_info_dialog.hpp; path = ../../states_screens/dialogs/track_info_dialog.hpp; sourceTree = SOURCE_ROOT; };
9584448A1330F89100CEA60A /* dictionary.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; name = dictionary.cpp; path = ../../tinygettext/dictionary.cpp; sourceTree = SOURCE_ROOT; };
9584448B1330F89100CEA60A /* dictionary.hpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.h; name = dictionary.hpp; path = ../../tinygettext/dictionary.hpp; sourceTree = SOURCE_ROOT; };
9584448C1330F89100CEA60A /* dictionary_manager.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; name = dictionary_manager.cpp; path = ../../tinygettext/dictionary_manager.cpp; sourceTree = SOURCE_ROOT; };
9584448D1330F89100CEA60A /* dictionary_manager.hpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.h; name = dictionary_manager.hpp; path = ../../tinygettext/dictionary_manager.hpp; sourceTree = SOURCE_ROOT; };
9584448E1330F89100CEA60A /* file_system.hpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.h; name = file_system.hpp; path = ../../tinygettext/file_system.hpp; sourceTree = SOURCE_ROOT; };
9584448F1330F89100CEA60A /* iconv.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; name = iconv.cpp; path = ../../tinygettext/iconv.cpp; sourceTree = SOURCE_ROOT; };
958444901330F89100CEA60A /* iconv.hpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.h; name = iconv.hpp; path = ../../tinygettext/iconv.hpp; sourceTree = SOURCE_ROOT; };
958444911330F89100CEA60A /* language.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; name = language.cpp; path = ../../tinygettext/language.cpp; sourceTree = SOURCE_ROOT; };
958444921330F89100CEA60A /* language.hpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.h; name = language.hpp; path = ../../tinygettext/language.hpp; sourceTree = SOURCE_ROOT; };
958444931330F89100CEA60A /* log.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; name = log.cpp; path = ../../tinygettext/log.cpp; sourceTree = SOURCE_ROOT; };
958444941330F89100CEA60A /* log.hpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.h; name = log.hpp; path = ../../tinygettext/log.hpp; sourceTree = SOURCE_ROOT; };
958444951330F89100CEA60A /* log_stream.hpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.h; name = log_stream.hpp; path = ../../tinygettext/log_stream.hpp; sourceTree = SOURCE_ROOT; };
958444961330F89100CEA60A /* plural_forms.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; name = plural_forms.cpp; path = ../../tinygettext/plural_forms.cpp; sourceTree = SOURCE_ROOT; };
958444971330F89100CEA60A /* plural_forms.hpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.h; name = plural_forms.hpp; path = ../../tinygettext/plural_forms.hpp; sourceTree = SOURCE_ROOT; };
958444981330F89100CEA60A /* po_parser.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; name = po_parser.cpp; path = ../../tinygettext/po_parser.cpp; sourceTree = SOURCE_ROOT; };
958444991330F89100CEA60A /* po_parser.hpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.h; name = po_parser.hpp; path = ../../tinygettext/po_parser.hpp; sourceTree = SOURCE_ROOT; };
9584449A1330F89100CEA60A /* stk_file_system.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; name = stk_file_system.cpp; path = ../../tinygettext/stk_file_system.cpp; sourceTree = SOURCE_ROOT; };
9584449B1330F89100CEA60A /* stk_file_system.hpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.h; name = stk_file_system.hpp; path = ../../tinygettext/stk_file_system.hpp; sourceTree = SOURCE_ROOT; };
9584449C1330F89100CEA60A /* tinygettext.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; name = tinygettext.cpp; path = ../../tinygettext/tinygettext.cpp; sourceTree = SOURCE_ROOT; };
9584449D1330F89100CEA60A /* tinygettext.hpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.h; name = tinygettext.hpp; path = ../../tinygettext/tinygettext.hpp; sourceTree = SOURCE_ROOT; };
9586318011B1EC9F00B8B4AF /* grand_prix_lose.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; name = grand_prix_lose.cpp; path = ../../states_screens/grand_prix_lose.cpp; sourceTree = SOURCE_ROOT; };
9586318111B1EC9F00B8B4AF /* grand_prix_lose.hpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.h; name = grand_prix_lose.hpp; path = ../../states_screens/grand_prix_lose.hpp; sourceTree = SOURCE_ROOT; };
9586318211B1EC9F00B8B4AF /* grand_prix_win.cpp */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.cpp.cpp; name = grand_prix_win.cpp; path = ../../states_screens/grand_prix_win.cpp; sourceTree = SOURCE_ROOT; };
@ -2188,6 +2217,34 @@
path = ../../states_screens/dialogs;
sourceTree = SOURCE_ROOT;
};
958444891330F89100CEA60A /* tinygettext */ = {
isa = PBXGroup;
children = (
9584448A1330F89100CEA60A /* dictionary.cpp */,
9584448B1330F89100CEA60A /* dictionary.hpp */,
9584448C1330F89100CEA60A /* dictionary_manager.cpp */,
9584448D1330F89100CEA60A /* dictionary_manager.hpp */,
9584448E1330F89100CEA60A /* file_system.hpp */,
9584448F1330F89100CEA60A /* iconv.cpp */,
958444901330F89100CEA60A /* iconv.hpp */,
958444911330F89100CEA60A /* language.cpp */,
958444921330F89100CEA60A /* language.hpp */,
958444931330F89100CEA60A /* log.cpp */,
958444941330F89100CEA60A /* log.hpp */,
958444951330F89100CEA60A /* log_stream.hpp */,
958444961330F89100CEA60A /* plural_forms.cpp */,
958444971330F89100CEA60A /* plural_forms.hpp */,
958444981330F89100CEA60A /* po_parser.cpp */,
958444991330F89100CEA60A /* po_parser.hpp */,
9584449A1330F89100CEA60A /* stk_file_system.cpp */,
9584449B1330F89100CEA60A /* stk_file_system.hpp */,
9584449C1330F89100CEA60A /* tinygettext.cpp */,
9584449D1330F89100CEA60A /* tinygettext.hpp */,
);
name = tinygettext;
path = ../../tinygettext;
sourceTree = SOURCE_ROOT;
};
95A118280F77EA3100B18B3D /* input */ = {
isa = PBXGroup;
children = (
@ -2226,6 +2283,7 @@
95263DDF0FD7471900CF5F92 /* race */,
95C2B19C0F296545000D3E5D /* replay */,
958330C110122B4A00C5137E /* states_screens */,
958444891330F89100CEA60A /* tinygettext */,
95C2B1CE0F296545000D3E5D /* tracks */,
9576460212BAD1CF00DB80C7 /* tutorial */,
95C2B1DF0F296546000D3E5D /* utils */,
@ -2986,6 +3044,15 @@
9592DC6D13021B350039DBC8 /* minimal_race_gui.cpp in Sources */,
95E1FCDF130369EB004D83CC /* per_camera_node.cpp in Sources */,
95376CAF1320784100C842A4 /* lod_node.cpp in Sources */,
9584449E1330F89100CEA60A /* dictionary.cpp in Sources */,
9584449F1330F89100CEA60A /* dictionary_manager.cpp in Sources */,
958444A01330F89100CEA60A /* iconv.cpp in Sources */,
958444A11330F89100CEA60A /* language.cpp in Sources */,
958444A21330F89100CEA60A /* log.cpp in Sources */,
958444A31330F89100CEA60A /* plural_forms.cpp in Sources */,
958444A41330F89100CEA60A /* po_parser.cpp in Sources */,
958444A51330F89100CEA60A /* stk_file_system.cpp in Sources */,
958444A61330F89100CEA60A /* tinygettext.cpp in Sources */,
);
runOnlyForDeploymentPostprocessing = 0;
};

2
src/tinygettext/iconv.cpp
View File

@ -113,7 +113,7 @@ IConv::convert(const std::string& text)
char* outbuf = &result[0];
// Try to convert the text.
size_t ret = tinygettext_iconv(cd, &inbuf, &inbytesleft, &outbuf, &outbytesleft);
size_t ret = tinygettext_iconv(cd, (const char**)&inbuf, &inbytesleft, &outbuf, &outbytesleft);
if (ret == static_cast<size_t>(-1))
{
if (errno == EILSEQ || errno == EINVAL)

130
src/utils/translation.cpp
View File

@ -40,6 +40,9 @@
#include "io/file_manager.hpp"
#include "utils/constants.hpp"
//#include "tinygettext/iconv.hpp"
#include "utils/utf8.h"
#if ENABLE_BIDI
#include <fribidi/fribidi.h>
#endif
@ -47,6 +50,8 @@
// set to 1 to debug i18n
#define TRANSLATE_VERBOSE 0
using namespace tinygettext;
Translations* translations = NULL;
const bool REMOVE_BOM = false;
@ -65,8 +70,98 @@ const std::vector<std::string>* Translations::getLanguageList() const
return &g_language_list;
}
wchar_t* utf8_to_wide(const char* input)
{
static std::vector<wchar_t> utf16line;
utf16line.clear();
utf8::utf8to16(input, input + strlen(input), back_inserter(utf16line));
utf16line.push_back(0);
return &utf16line[0];
/*
static tinygettext_iconv_t cd = 0;
if (cd == 0) cd = tinygettext_iconv_open("UTF-16", "UTF-8");
if (cd == reinterpret_cast<tinygettext_iconv_t>(-1))
{
fprintf(stderr, "[utf8_to_wide] ERROR: failed to init libiconv\n");
return L"?";
}
size_t inbytesleft = strlen(input);
size_t outbytesleft = 4*inbytesleft; // Worst case scenario: ASCII -> UTF-32?
const unsigned int BUFF_SIZE = 512*4;
if (outbytesleft > BUFF_SIZE)
{
fprintf(stderr, "[utf8_to_wide] ERROR: stirng too long : '%s'\n", input);
}
static char temp_buffer[BUFF_SIZE];
// Try to convert the text.
size_t ret = tinygettext_iconv(cd, &input, &inbytesleft, (char**)&temp_buffer, &outbytesleft);
if (ret == static_cast<size_t>(-1))
{
if (errno == EILSEQ || errno == EINVAL)
{ // invalid multibyte sequence
tinygettext_iconv(cd, NULL, NULL, NULL, NULL); // reset state
// FIXME: Could try to skip the invalid byte and continue
fprintf(stderr, "[Translation] ERROR: invalid multibyte sequence in '%s'\n", input);
}
else if (errno == E2BIG)
{ // output buffer to small
fprintf(stderr, "[Translation] ERROR: E2BIG: This should never be reached\n");
}
else if (errno == EBADF)
{
fprintf(stderr, "[Translation] ERROR: EBADF: This should never be reached\n");
}
else
{
fprintf(stderr, "[Translation] ERROR: <unknown>: This should never be reached\n");
}
return L"?";
}
else
{
if (sizeof(wchar_t) == 2)
{
return (wchar_t*)temp_buffer;
}
else if (sizeof(wchar_t) == 4)
{
static wchar_t out_buffer[512];
// FIXME: endianness?
int i = 0;
for (char* ptr = temp_buffer; ; ptr += 2)
{
out_buffer[i] = (*ptr << 8) | *(ptr + 1);
if (*ptr == 0 && *(ptr + 1) == 0) break;
i++;
}
return out_buffer;
}
else
{
fprintf(stderr, "Unknown wchar_t size : %lui\n", sizeof(wchar_t));
return L"?";
}
}
*/
}
// ----------------------------------------------------------------------------
Translations::Translations()
Translations::Translations() //: m_dictionary_manager("UTF-16")
{
#ifdef ENABLE_NLS
@ -102,6 +197,7 @@ Translations::Translations()
#endif
/*
bindtextdomain (PACKAGE, file_manager->getTranslationDir().c_str());
if (sizeof(wchar_t) == 4)
@ -120,18 +216,38 @@ Translations::Translations()
}
textdomain (PACKAGE);
*/
m_dictionary_manager.add_directory( file_manager->getTranslationDir().c_str() );
const std::set<Language>& languages = m_dictionary_manager.get_languages();
std::cout << "Number of languages: " << languages.size() << std::endl;
for (std::set<Language>::const_iterator i = languages.begin(); i != languages.end(); ++i)
{
const Language& language = *i;
std::cout << "Env: " << language.str() << std::endl
<< "Name: " << language.get_name() << std::endl
<< "Language: " << language.get_language() << std::endl
<< "Country: " << language.get_country() << std::endl
<< "Modifier: " << language.get_modifier() << std::endl
<< std::endl;
}
m_dictionary = m_dictionary_manager.get_dictionary(Language::from_spec("fr", "FR"));
// This is a silly but working hack I added to determine whether the current language is RTL or
// not, since gettext doesn't seem to provide this information
//std::string test = m_dictionary.translate("Loading");
//printf("'%s'\n", test.c_str());
// This one is just for the xgettext parser to pick up
#define ignore(X)
ignore(_(" Is this a RTL language?"));
//I18N: Do NOT literally translate this string!! Please enter Y as the translation if your language is a RTL (right-to-left) language, N (or nothing) otherwise
const char* isRtl = gettext(" Is this a RTL language?");
const wchar_t* isRtlW = reinterpret_cast<const wchar_t*>(isRtl);
const std::string isRtl = m_dictionary.translate(" Is this a RTL language?");
const wchar_t* isRtlW = reinterpret_cast<const wchar_t*>(isRtl.c_str());
m_rtl = false;
@ -236,7 +352,7 @@ const wchar_t* Translations::w_gettext(const char* original)
#endif
#if ENABLE_NLS
const char* original_t = gettext(original);
const std::string& original_t = m_dictionary.translate(original);
#else
m_converted_string = core::stringw(original);
return m_converted_string.c_str();
@ -259,7 +375,7 @@ const wchar_t* Translations::w_gettext(const char* original)
}
}*/
if(original_t==original)
if (original_t == original)
{
m_converted_string = core::stringw(original);
@ -272,7 +388,9 @@ const wchar_t* Translations::w_gettext(const char* original)
// print
//for (int n=0;; n+=4)
wchar_t* out_ptr = (wchar_t*)original_t;
wchar_t* original_tw = utf8_to_wide(original_t.c_str());
wchar_t* out_ptr = original_tw;
if (REMOVE_BOM) out_ptr++;
#if TRANSLATE_VERBOSE

9
src/utils/translation.hpp
View File

@ -26,11 +26,7 @@
#include "utils/string_utils.hpp"
#if ENABLE_NLS
# ifdef __APPLE__
# include <libintl/libintl.h>
# else
# include <libintl.h>
# endif
# include "tinygettext/tinygettext.hpp"
# define _(String, ...) (translations->fribidize(StringUtils::insertValues(translations->w_gettext(String), ##__VA_ARGS__)))
# define _LTR(String, ...) (StringUtils::insertValues(translations->w_gettext(String), ##__VA_ARGS__))
@ -50,6 +46,9 @@
class Translations
{
private:
tinygettext::DictionaryManager m_dictionary_manager;
tinygettext::Dictionary m_dictionary;
irr::core::stringw m_converted_string;
bool m_rtl;

34
src/utils/utf8.h Normal file
View File

@ -0,0 +1,34 @@
// Copyright 2006 Nemanja Trifunovic
/*
Permission is hereby granted, free of charge, to any person or organization
obtaining a copy of the software and accompanying documentation covered by
this license (the "Software") to use, reproduce, display, distribute,
execute, and transmit the Software, and to prepare derivative works of the
Software, and to permit third-parties to whom the Software is furnished to
do so, all subject to the following:
The copyright notices in the Software and this entire statement, including
the above license grant, this restriction and the following disclaimer,
must be included in all copies of the Software, in whole or in part, and
all derivative works of the Software, unless such copies or derivative
works are solely in the form of machine-executable object code generated by
a source language processor.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
DEALINGS IN THE SOFTWARE.
*/
#ifndef UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731
#define UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731
#include "utf8/checked.h"
#include "utf8/unchecked.h"
#endif // header guard

327
src/utils/utf8/checked.h Normal file
View File

@ -0,0 +1,327 @@
// Copyright 2006 Nemanja Trifunovic
/*
Permission is hereby granted, free of charge, to any person or organization
obtaining a copy of the software and accompanying documentation covered by
this license (the "Software") to use, reproduce, display, distribute,
execute, and transmit the Software, and to prepare derivative works of the
Software, and to permit third-parties to whom the Software is furnished to
do so, all subject to the following:
The copyright notices in the Software and this entire statement, including
the above license grant, this restriction and the following disclaimer,
must be included in all copies of the Software, in whole or in part, and
all derivative works of the Software, unless such copies or derivative
works are solely in the form of machine-executable object code generated by
a source language processor.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
DEALINGS IN THE SOFTWARE.
*/
#ifndef UTF8_FOR_CPP_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
#define UTF8_FOR_CPP_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
#include "core.h"
#include <stdexcept>
namespace utf8
{
// Base for the exceptions that may be thrown from the library
class exception : public std::exception {
};
// Exceptions that may be thrown from the library functions.
class invalid_code_point : public exception {
uint32_t cp;
public:
invalid_code_point(uint32_t cp) : cp(cp) {}
virtual const char* what() const throw() { return "Invalid code point"; }
uint32_t code_point() const {return cp;}
};
class invalid_utf8 : public exception {
uint8_t u8;
public:
invalid_utf8 (uint8_t u) : u8(u) {}
virtual const char* what() const throw() { return "Invalid UTF-8"; }
uint8_t utf8_octet() const {return u8;}
};
class invalid_utf16 : public exception {
uint16_t u16;
public:
invalid_utf16 (uint16_t u) : u16(u) {}
virtual const char* what() const throw() { return "Invalid UTF-16"; }
uint16_t utf16_word() const {return u16;}
};
class not_enough_room : public exception {
public:
virtual const char* what() const throw() { return "Not enough space"; }
};
/// The library API - functions intended to be called by the users
template <typename octet_iterator, typename output_iterator>
output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, uint32_t replacement)
{
while (start != end) {
octet_iterator sequence_start = start;
internal::utf_error err_code = internal::validate_next(start, end);
switch (err_code) {
case internal::UTF8_OK :
for (octet_iterator it = sequence_start; it != start; ++it)
*out++ = *it;
break;
case internal::NOT_ENOUGH_ROOM:
throw not_enough_room();
case internal::INVALID_LEAD:
append (replacement, out);
++start;
break;
case internal::INCOMPLETE_SEQUENCE:
case internal::OVERLONG_SEQUENCE:
case internal::INVALID_CODE_POINT:
append (replacement, out);
++start;
// just one replacement mark for the sequence
while (internal::is_trail(*start) && start != end)
++start;
break;
}
}
return out;
}
template <typename octet_iterator, typename output_iterator>
inline output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out)
{
static const uint32_t replacement_marker = internal::mask16(0xfffd);
return replace_invalid(start, end, out, replacement_marker);
}
template <typename octet_iterator>
octet_iterator append(uint32_t cp, octet_iterator result)
{
if (!internal::is_code_point_valid(cp))
throw invalid_code_point(cp);
if (cp < 0x80) // one octet
*(result++) = static_cast<uint8_t>(cp);
else if (cp < 0x800) { // two octets
*(result++) = static_cast<uint8_t>((cp >> 6) | 0xc0);
*(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
}
else if (cp < 0x10000) { // three octets
*(result++) = static_cast<uint8_t>((cp >> 12) | 0xe0);
*(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80);
*(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
}
else { // four octets
*(result++) = static_cast<uint8_t>((cp >> 18) | 0xf0);
*(result++) = static_cast<uint8_t>(((cp >> 12) & 0x3f) | 0x80);
*(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80);
*(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
}
return result;
}
template <typename octet_iterator>
uint32_t next(octet_iterator& it, octet_iterator end)
{
uint32_t cp = 0;
internal::utf_error err_code = internal::validate_next(it, end, &cp);
switch (err_code) {
case internal::UTF8_OK :
break;
case internal::NOT_ENOUGH_ROOM :
throw not_enough_room();
case internal::INVALID_LEAD :
case internal::INCOMPLETE_SEQUENCE :
case internal::OVERLONG_SEQUENCE :
throw invalid_utf8(*it);
case internal::INVALID_CODE_POINT :
throw invalid_code_point(cp);
}
return cp;
}
template <typename octet_iterator>
uint32_t peek_next(octet_iterator it, octet_iterator end)
{
return next(it, end);
}
template <typename octet_iterator>
uint32_t prior(octet_iterator& it, octet_iterator start)
{
// can't do much if it == start
if (it == start)
throw not_enough_room();
octet_iterator end = it;
// Go back until we hit either a lead octet or start
while (internal::is_trail(*(--it)))
if (it == start)
throw invalid_utf8(*it); // error - no lead byte in the sequence
return peek_next(it, end);
}
/// Deprecated in versions that include "prior"
template <typename octet_iterator>
uint32_t previous(octet_iterator& it, octet_iterator pass_start)
{
octet_iterator end = it;
while (internal::is_trail(*(--it)))
if (it == pass_start)
throw invalid_utf8(*it); // error - no lead byte in the sequence
octet_iterator temp = it;
return next(temp, end);
}
template <typename octet_iterator, typename distance_type>
void advance (octet_iterator& it, distance_type n, octet_iterator end)
{
for (distance_type i = 0; i < n; ++i)
next(it, end);
}
template <typename octet_iterator>
typename std::iterator_traits<octet_iterator>::difference_type
distance (octet_iterator first, octet_iterator last)
{
typename std::iterator_traits<octet_iterator>::difference_type dist;
for (dist = 0; first < last; ++dist)
next(first, last);
return dist;
}
template <typename u16bit_iterator, typename octet_iterator>
octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result)
{
while (start != end) {
uint32_t cp = internal::mask16(*start++);
// Take care of surrogate pairs first
if (internal::is_lead_surrogate(cp)) {
if (start != end) {
uint32_t trail_surrogate = internal::mask16(*start++);
if (internal::is_trail_surrogate(trail_surrogate))
cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET;
else
throw invalid_utf16(static_cast<uint16_t>(trail_surrogate));
}
else
throw invalid_utf16(static_cast<uint16_t>(cp));
}
// Lone trail surrogate
else if (internal::is_trail_surrogate(cp))
throw invalid_utf16(static_cast<uint16_t>(cp));
result = append(cp, result);
}
return result;
}
template <typename u16bit_iterator, typename octet_iterator>
u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result)
{
while (start != end) {
uint32_t cp = next(start, end);
if (cp > 0xffff) { //make a surrogate pair
*result++ = static_cast<uint16_t>((cp >> 10) + internal::LEAD_OFFSET);
*result++ = static_cast<uint16_t>((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN);
}
else
*result++ = static_cast<uint16_t>(cp);
}
return result;
}
template <typename octet_iterator, typename u32bit_iterator>
octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result)
{
while (start != end)
result = append(*(start++), result);
return result;
}
template <typename octet_iterator, typename u32bit_iterator>
u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result)
{
while (start != end)
(*result++) = next(start, end);
return result;
}
// The iterator class
template <typename octet_iterator>
class iterator : public std::iterator <std::bidirectional_iterator_tag, uint32_t> {
octet_iterator it;
octet_iterator range_start;
octet_iterator range_end;
public:
iterator () {};
explicit iterator (const octet_iterator& octet_it,
const octet_iterator& range_start,
const octet_iterator& range_end) :
it(octet_it), range_start(range_start), range_end(range_end)
{
if (it < range_start || it > range_end)
throw std::out_of_range("Invalid utf-8 iterator position");
}
// the default "big three" are OK
octet_iterator base () const { return it; }
uint32_t operator * () const
{
octet_iterator temp = it;
return next(temp, range_end);
}
bool operator == (const iterator& rhs) const
{
if (range_start != rhs.range_start || range_end != rhs.range_end)
throw std::logic_error("Comparing utf-8 iterators defined with different ranges");
return (it == rhs.it);
}
bool operator != (const iterator& rhs) const
{
return !(operator == (rhs));
}
iterator& operator ++ ()
{
next(it, range_end);
return *this;
}
iterator operator ++ (int)
{
iterator temp = *this;
next(it, range_end);
return temp;
}
iterator& operator -- ()
{
prior(it, range_start);
return *this;
}
iterator operator -- (int)
{
iterator temp = *this;
prior(it, range_start);
return temp;
}
}; // class iterator
} // namespace utf8
#endif //header guard

358
src/utils/utf8/core.h Executable file
View File

@ -0,0 +1,358 @@
// Copyright 2006 Nemanja Trifunovic
/*
Permission is hereby granted, free of charge, to any person or organization
obtaining a copy of the software and accompanying documentation covered by
this license (the "Software") to use, reproduce, display, distribute,
execute, and transmit the Software, and to prepare derivative works of the
Software, and to permit third-parties to whom the Software is furnished to
do so, all subject to the following:
The copyright notices in the Software and this entire statement, including
the above license grant, this restriction and the following disclaimer,
must be included in all copies of the Software, in whole or in part, and
all derivative works of the Software, unless such copies or derivative
works are solely in the form of machine-executable object code generated by
a source language processor.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
DEALINGS IN THE SOFTWARE.
*/
#ifndef UTF8_FOR_CPP_CORE_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
#define UTF8_FOR_CPP_CORE_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
#include <iterator>
namespace utf8
{
// The typedefs for 8-bit, 16-bit and 32-bit unsigned integers
// You may need to change them to match your system.
// These typedefs have the same names as ones from cstdint, or boost/cstdint
typedef unsigned char uint8_t;
typedef unsigned short uint16_t;
typedef unsigned int uint32_t;
// Helper code - not intended to be directly called by the library users. May be changed at any time
namespace internal
{
// Unicode constants
// Leading (high) surrogates: 0xd800 - 0xdbff
// Trailing (low) surrogates: 0xdc00 - 0xdfff
const uint16_t LEAD_SURROGATE_MIN = 0xd800u;
const uint16_t LEAD_SURROGATE_MAX = 0xdbffu;
const uint16_t TRAIL_SURROGATE_MIN = 0xdc00u;
const uint16_t TRAIL_SURROGATE_MAX = 0xdfffu;
const uint16_t LEAD_OFFSET = LEAD_SURROGATE_MIN - (0x10000 >> 10);
const uint32_t SURROGATE_OFFSET = 0x10000u - (LEAD_SURROGATE_MIN << 10) - TRAIL_SURROGATE_MIN;
// Maximum valid value for a Unicode code point
const uint32_t CODE_POINT_MAX = 0x0010ffffu;
template<typename octet_type>
inline uint8_t mask8(octet_type oc)
{
return static_cast<uint8_t>(0xff & oc);
}
template<typename u16_type>
inline uint16_t mask16(u16_type oc)
{
return static_cast<uint16_t>(0xffff & oc);
}
template<typename octet_type>
inline bool is_trail(octet_type oc)
{
return ((mask8(oc) >> 6) == 0x2);
}
template <typename u16>
inline bool is_lead_surrogate(u16 cp)
{
return (cp >= LEAD_SURROGATE_MIN && cp <= LEAD_SURROGATE_MAX);
}
template <typename u16>
inline bool is_trail_surrogate(u16 cp)
{
return (cp >= TRAIL_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX);
}
template <typename u16>
inline bool is_surrogate(u16 cp)
{
return (cp >= LEAD_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX);
}
template <typename u32>
inline bool is_code_point_valid(u32 cp)
{
return (cp <= CODE_POINT_MAX && !is_surrogate(cp));
}
template <typename octet_iterator>
inline typename std::iterator_traits<octet_iterator>::difference_type
sequence_length(octet_iterator lead_it)
{
uint8_t lead = mask8(*lead_it);
if (lead < 0x80)
return 1;
else if ((lead >> 5) == 0x6)
return 2;
else if ((lead >> 4) == 0xe)
return 3;
else if ((lead >> 3) == 0x1e)
return 4;
else
return 0;
}
template <typename octet_difference_type>
inline bool is_overlong_sequence(uint32_t cp, octet_difference_type length)
{
if (cp < 0x80) {
if (length != 1)
return true;
}
else if (cp < 0x800) {
if (length != 2)
return true;
}
else if (cp < 0x10000) {
if (length != 3)
return true;
}
return false;
}
enum utf_error {UTF8_OK, NOT_ENOUGH_ROOM, INVALID_LEAD, INCOMPLETE_SEQUENCE, OVERLONG_SEQUENCE, INVALID_CODE_POINT};
/// get_sequence_x functions decode utf-8 sequences of the length x
template <typename octet_iterator>
utf_error get_sequence_1(octet_iterator& it, octet_iterator end, uint32_t* code_point)
{
if (it != end) {
if (code_point)
*code_point = mask8(*it);
return UTF8_OK;
}
return NOT_ENOUGH_ROOM;
}
template <typename octet_iterator>
utf_error get_sequence_2(octet_iterator& it, octet_iterator end, uint32_t* code_point)
{
utf_error ret_code = NOT_ENOUGH_ROOM;
if (it != end) {
uint32_t cp = mask8(*it);
if (++it != end) {
if (is_trail(*it)) {
cp = ((cp << 6) & 0x7ff) + ((*it) & 0x3f);
if (code_point)
*code_point = cp;
ret_code = UTF8_OK;
}
else
ret_code = INCOMPLETE_SEQUENCE;
}
else
ret_code = NOT_ENOUGH_ROOM;
}
return ret_code;
}
template <typename octet_iterator>
utf_error get_sequence_3(octet_iterator& it, octet_iterator end, uint32_t* code_point)
{
utf_error ret_code = NOT_ENOUGH_ROOM;
if (it != end) {
uint32_t cp = mask8(*it);
if (++it != end) {
if (is_trail(*it)) {
cp = ((cp << 12) & 0xffff) + ((mask8(*it) << 6) & 0xfff);
if (++it != end) {
if (is_trail(*it)) {
cp += (*it) & 0x3f;
if (code_point)
*code_point = cp;
ret_code = UTF8_OK;
}
else
ret_code = INCOMPLETE_SEQUENCE;
}
else
ret_code = NOT_ENOUGH_ROOM;
}
else
ret_code = INCOMPLETE_SEQUENCE;
}
else
ret_code = NOT_ENOUGH_ROOM;
}
return ret_code;
}
template <typename octet_iterator>
utf_error get_sequence_4(octet_iterator& it, octet_iterator end, uint32_t* code_point)
{
utf_error ret_code = NOT_ENOUGH_ROOM;
if (it != end) {
uint32_t cp = mask8(*it);
if (++it != end) {
if (is_trail(*it)) {
cp = ((cp << 18) & 0x1fffff) + ((mask8(*it) << 12) & 0x3ffff);
if (++it != end) {
if (is_trail(*it)) {
cp += (mask8(*it) << 6) & 0xfff;
if (++it != end) {
if (is_trail(*it)) {
cp += (*it) & 0x3f;
if (code_point)
*code_point = cp;
ret_code = UTF8_OK;
}
else
ret_code = INCOMPLETE_SEQUENCE;
}
else
ret_code = NOT_ENOUGH_ROOM;
}
else
ret_code = INCOMPLETE_SEQUENCE;
}
else
ret_code = NOT_ENOUGH_ROOM;
}
else
ret_code = INCOMPLETE_SEQUENCE;
}
else
ret_code = NOT_ENOUGH_ROOM;
}
return ret_code;
}
template <typename octet_iterator>
utf_error validate_next(octet_iterator& it, octet_iterator end, uint32_t* code_point)
{
// Save the original value of it so we can go back in case of failure
// Of course, it does not make much sense with i.e. stream iterators
octet_iterator original_it = it;
uint32_t cp = 0;
// Determine the sequence length based on the lead octet
typedef typename std::iterator_traits<octet_iterator>::difference_type octet_difference_type;
octet_difference_type length = sequence_length(it);
if (length == 0)
return INVALID_LEAD;
// Now that we have a valid sequence length, get trail octets and calculate the code point
utf_error err = UTF8_OK;
switch (length) {
case 1:
err = get_sequence_1(it, end, &cp);
break;
case 2:
err = get_sequence_2(it, end, &cp);
break;
case 3:
err = get_sequence_3(it, end, &cp);
break;
case 4:
err = get_sequence_4(it, end, &cp);
break;
}
if (err == UTF8_OK) {
// Decoding succeeded. Now, security checks...
if (is_code_point_valid(cp)) {
if (!is_overlong_sequence(cp, length)){
// Passed! Return here.
if (code_point)
*code_point = cp;
++it;
return UTF8_OK;
}
else
err = OVERLONG_SEQUENCE;
}
else
err = INVALID_CODE_POINT;
}
// Failure branch - restore the original value of the iterator
it = original_it;
return err;
}
template <typename octet_iterator>
inline utf_error validate_next(octet_iterator& it, octet_iterator end) {
return validate_next(it, end, 0);
}
} // namespace internal
/// The library API - functions intended to be called by the users
// Byte order mark
const uint8_t bom[] = {0xef, 0xbb, 0xbf};
template <typename octet_iterator>
octet_iterator find_invalid(octet_iterator start, octet_iterator end)
{
octet_iterator result = start;
while (result != end) {
internal::utf_error err_code = internal::validate_next(result, end);
if (err_code != internal::UTF8_OK)
return result;
}
return result;
}
template <typename octet_iterator>
inline bool is_valid(octet_iterator start, octet_iterator end)
{
return (find_invalid(start, end) == end);
}
template <typename octet_iterator>
inline bool starts_with_bom (octet_iterator it, octet_iterator end)
{
return (
((it != end) && (internal::mask8(*it++)) == bom[0]) &&
((it != end) && (internal::mask8(*it++)) == bom[1]) &&
((it != end) && (internal::mask8(*it)) == bom[2])
);
}
//Deprecated in release 2.3
template <typename octet_iterator>
inline bool is_bom (octet_iterator it)
{
return (
(internal::mask8(*it++)) == bom[0] &&
(internal::mask8(*it++)) == bom[1] &&
(internal::mask8(*it)) == bom[2]
);
}
} // namespace utf8
#endif // header guard

228
src/utils/utf8/unchecked.h Executable file
View File

@ -0,0 +1,228 @@
// Copyright 2006 Nemanja Trifunovic
/*
Permission is hereby granted, free of charge, to any person or organization
obtaining a copy of the software and accompanying documentation covered by
this license (the "Software") to use, reproduce, display, distribute,
execute, and transmit the Software, and to prepare derivative works of the
Software, and to permit third-parties to whom the Software is furnished to
do so, all subject to the following:
The copyright notices in the Software and this entire statement, including
the above license grant, this restriction and the following disclaimer,
must be included in all copies of the Software, in whole or in part, and
all derivative works of the Software, unless such copies or derivative
works are solely in the form of machine-executable object code generated by
a source language processor.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
DEALINGS IN THE SOFTWARE.
*/
#ifndef UTF8_FOR_CPP_UNCHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
#define UTF8_FOR_CPP_UNCHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
#include "core.h"
namespace utf8
{
namespace unchecked
{
template <typename octet_iterator>
octet_iterator append(uint32_t cp, octet_iterator result)
{
if (cp < 0x80) // one octet
*(result++) = static_cast<uint8_t>(cp);
else if (cp < 0x800) { // two octets
*(result++) = static_cast<uint8_t>((cp >> 6) | 0xc0);
*(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
}
else if (cp < 0x10000) { // three octets
*(result++) = static_cast<uint8_t>((cp >> 12) | 0xe0);
*(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80);
*(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
}
else { // four octets
*(result++) = static_cast<uint8_t>((cp >> 18) | 0xf0);
*(result++) = static_cast<uint8_t>(((cp >> 12) & 0x3f)| 0x80);
*(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80);
*(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
}
return result;
}
template <typename octet_iterator>
uint32_t next(octet_iterator& it)
{
uint32_t cp = internal::mask8(*it);
typename std::iterator_traits<octet_iterator>::difference_type length = utf8::internal::sequence_length(it);
switch (length) {
case 1:
break;
case 2:
it++;
cp = ((cp << 6) & 0x7ff) + ((*it) & 0x3f);
break;
case 3:
++it;
cp = ((cp << 12) & 0xffff) + ((internal::mask8(*it) << 6) & 0xfff);
++it;
cp += (*it) & 0x3f;
break;
case 4:
++it;
cp = ((cp << 18) & 0x1fffff) + ((internal::mask8(*it) << 12) & 0x3ffff);
++it;
cp += (internal::mask8(*it) << 6) & 0xfff;
++it;
cp += (*it) & 0x3f;
break;
}
++it;
return cp;
}
template <typename octet_iterator>
uint32_t peek_next(octet_iterator it)
{
return next(it);
}
template <typename octet_iterator>
uint32_t prior(octet_iterator& it)
{
while (internal::is_trail(*(--it))) ;
octet_iterator temp = it;
return next(temp);
}
// Deprecated in versions that include prior, but only for the sake of consistency (see utf8::previous)
template <typename octet_iterator>
inline uint32_t previous(octet_iterator& it)
{
return prior(it);
}
template <typename octet_iterator, typename distance_type>
void advance (octet_iterator& it, distance_type n)
{
for (distance_type i = 0; i < n; ++i)
next(it);
}
template <typename octet_iterator>
typename std::iterator_traits<octet_iterator>::difference_type
distance (octet_iterator first, octet_iterator last)
{
typename std::iterator_traits<octet_iterator>::difference_type dist;
for (dist = 0; first < last; ++dist)
next(first);
return dist;
}
template <typename u16bit_iterator, typename octet_iterator>
octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result)
{
while (start != end) {
uint32_t cp = internal::mask16(*start++);
// Take care of surrogate pairs first
if (internal::is_lead_surrogate(cp)) {
uint32_t trail_surrogate = internal::mask16(*start++);
cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET;
}
result = append(cp, result);
}
return result;
}
template <typename u16bit_iterator, typename octet_iterator>
u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result)
{
while (start < end) {
uint32_t cp = next(start);
if (cp > 0xffff) { //make a surrogate pair
*result++ = static_cast<uint16_t>((cp >> 10) + internal::LEAD_OFFSET);
*result++ = static_cast<uint16_t>((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN);
}
else
*result++ = static_cast<uint16_t>(cp);
}
return result;
}
template <typename octet_iterator, typename u32bit_iterator>
octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result)
{
while (start != end)
result = append(*(start++), result);
return result;
}
template <typename octet_iterator, typename u32bit_iterator>
u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result)
{
while (start < end)
(*result++) = next(start);
return result;
}
// The iterator class
template <typename octet_iterator>
class iterator : public std::iterator <std::bidirectional_iterator_tag, uint32_t> {
octet_iterator it;
public:
iterator () {};
explicit iterator (const octet_iterator& octet_it): it(octet_it) {}
// the default "big three" are OK
octet_iterator base () const { return it; }
uint32_t operator * () const
{
octet_iterator temp = it;
return next(temp);
}
bool operator == (const iterator& rhs) const
{
return (it == rhs.it);
}
bool operator != (const iterator& rhs) const
{
return !(operator == (rhs));
}
iterator& operator ++ ()
{
std::advance(it, internal::sequence_length(it));
return *this;
}
iterator operator ++ (int)
{
iterator temp = *this;
std::advance(it, internal::sequence_length(it));
return temp;
}
iterator& operator -- ()
{
prior(it);
return *this;
}
iterator operator -- (int)
{
iterator temp = *this;
prior(it);
return temp;
}
}; // class iterator
} // namespace utf8::unchecked
} // namespace utf8
#endif // header guard