mirror-games/glest-source
1
0
Fork 0
mirror of https://github.com/glest/glest-source.git synced 2025-08-12 11:24:00 +02:00
Code Issues Projects Releases Wiki Activity

- added some bug fixes to check if lng files are utf-8 or not and deal with it appropriately

Browse Source
This commit is contained in:
Mark Vejvoda
2011-06-08 07:18:06 +00:00
parent bf9702cdca
commit f65bfe8710
29 changed files with 3072 additions and 83 deletions
Download Patch File Download Diff File Expand all files Collapse all files

615
source/shared_lib/include/util/string_utils.h Normal file
View File

@@ -0,0 +1,615 @@
/* TA3D, a remake of Total Annihilation
Copyright (C) 2005 Roland BROCHARD
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA*/
#ifndef _SHARED_UTIL_W_STRING_H__
#define _SHARED_UTIL_W_STRING_H__
# include <sstream>
# include <list>
# include <vector>
# include <cstdarg>
# include <string>
#include "types.h"
/*!
** \brief Force the Use of the Boost functions
*/
# define TA3D_USE_BOOST 0
//! \name Macros for Shared::Util::String
//@{
//! Macro to append some data to the string
# define TA3D_WSTR_APPEND std::stringstream out; \
out << v; \
append(out.str());\
return *this
//! Macro to convert the string into a given type
# define TA3D_WSTR_CAST_OP(X) X v; \
fromString<X>(v, *this); \
return v;
//! Macro to append the value of a boolean (true -> "true", false -> "false")
# define TA3D_WSTR_APPEND_BOOL(X) append(X ? "true" : "false")
//@} // Macros for Shared::Util::String
# define TA3D_WSTR_SEPARATORS " \t\r\n"
using namespace Shared::Platform;
namespace Shared { namespace Util {
/*! \class String
** \brief A String implementation for `TA3D`
**
** \code
** Shared::Util::String a("abcd");
** std::cout << a << std::endl; // display: `abcd`
** Shared::Util::String b(10 + 2);
** std::cout << b << std::endl; // display: `12`
** Shared::Util::String c(10.3);
** std::cout << c << std::endl; // display: `10.3`
**
** // The same with the operator `<<`
** Shared::Util::String d;
** d << "Value : " << 42;
** std::cout << d << std::endl; // display: `Value : 42`
** \endcode
**
** Here is an example to show when to use static methods :
** \code
** Shared::Util::String s = "HelLo wOrLd";
** std::cout << Shared::Util::String::ToLower(s) << std::endl; // `hello world`
** std::cout << s << std::endl; // `HelLo wOrLd`
** std::cout << s.toLower() << std::endl; // `hello world`
** std::cout << s << std::endl; // `hello world`
** \endcode
*/
class String : public std::string
{
public:
//! A String list
typedef std::list<String> List;
//! A String vector
typedef std::vector<String> Vector;
//! Char Case
enum CharCase
{
//! The string should remain untouched
soCaseSensitive,
//! The string should be converted to lowercase
soIgnoreCase
};
public:
/*!
** \brief Copy then Convert the case (lower case) of characters in the string using the UTF8 charset
** \param s The string to convert
** \return A new string
*/
static String ToLower(const char* s) {return String(s).toLower();}
/*!
** \brief Copy then Convert the case (lower case) of characters in the string using the UTF8 charset
** \param s The string to convert
** \return A new string
*/
static String ToLower(const wchar_t* s) {return String(s).toLower();}
/*!
** \brief Copy then Convert the case (lower case) of characters in the string using the UTF8 charset
** \param s The string to convert
** \return A new string
*/
static String ToLower(const String& s) {return String(s).toLower();}
/*!
** \brief Copy then Convert the case (upper case) of characters in the string using the UTF8 charset
** \param s The string to convert
** \return A new string
*/
static String ToUpper(const char* s) {return String(s).toUpper();}
/*!
** \brief Copy then Convert the case (upper case) of characters in the string using the UTF8 charset
** \param s The string to convert
** \return A new string
*/
static String ToUpper(const wchar_t* s) {return String(s).toUpper();}
/*!
** \brief Copy then Convert the case (upper case) of characters in the string using the UTF8 charset
** \param s The string to convert
** \return A new string
*/
static String ToUpper(const String& s) {return String(s).toUpper();}
/*!
** \brief Remove trailing and leading spaces
** \param s The string to convert
** \param trimChars The chars to remove
** \return A new string
*/
static String Trim(const char* s, const String& trimChars = TA3D_WSTR_SEPARATORS) {return String(s).trim(trimChars);}
/*!
** \brief Remove trailing and leading spaces
** \param s The string to convert
** \param trimChars The chars to remove
** \return A new string
*/
static String Trim(const wchar_t* s, const String& trimChars = TA3D_WSTR_SEPARATORS) {return String(s).trim(trimChars);}
/*!
** \brief Remove trailing and leading spaces
** \param s The string to convert
** \param trimChars The chars to remove
** \return A new string
*/
static String Trim(const String& s, const String& trimChars = TA3D_WSTR_SEPARATORS) {return String(s).trim(trimChars);}
/*!
** \brief Convert all antislashes into slashes
** \param s The string to convert
** \return A new string
*/
static String ConvertAntiSlashesIntoSlashes(const String& s) {return String(s).convertAntiSlashesIntoSlashes();}
/*!
** \brief Convert all slashes into antislashes
** \param s The string to convert
** \return A new string
*/
static String ConvertSlashesIntoAntiSlashes(const String& s) {return String(s).convertSlashesIntoAntiSlashes();}
/*!
** \brief Extract the key and its value from a string (mainly provided by TDF files)
**
** \param s A line (ex: ` category=core vtol ctrl_v level1 weapon notsub ;`)
** \param[out] key The key that has been found
** \param[out] value The associated value
** \param chcase The key will be converted to lowercase if equals to `soIgnoreCase`
**
** \code
** String k, v;
**
** // -> k='category'
** // -> v='core vtol ctrl_v level1 weapon notsub'
** String::ToKeyValue(" category=core vtol ctrl_v level1 weapon notsub ;", k, v)
**
** // -> k='foo'
** // -> v='bar'
** String::ToKeyValue(" foo = bar ; ");
**
** // -> k='}' v=''
** String::ToKeyValue(" } ", k, v);
**
** // -> k='[' v='Example of Section'
** String::ToKeyValue(" [Example of Section] ", k, v);
**
** // -> k='foo' v='bar'
** String::ToKeyValue(" foo=bar; // comment", k, v);
**
** // -> k='foo' v='bar'
** String::ToKeyValue(" foo=bar; // comments here; ", k, v);
** \endcode
*/
static void ToKeyValue(const String& s, String& key, String& value, const enum CharCase chcase = soCaseSensitive);
/*!
** \brief Find the index of a string in a vector
** \param l The vector
** \param s The string to look for
** \return The index of the string found, -1 otherwise
*/
static int FindInList(const String::Vector& l, const char* s);
static int FindInList(const String::Vector& l, const String& s);
/*!
** \brief Convert a string from ASCII to UTF8
** \param s The string to convert
** \return A new Null-terminated String (must be deleted with the keyword `delete[]`), even if s is NULL
*/
static char* ConvertToUTF8(const char* s);
/*!
** \brief Convert a string from ASCII to UTF8
** \param s The string to convert
** \param len The length of the string
** \param[out] The new size
** \return A new Null-terminated String (must be deleted with the keyword `delete[]`), even if s is NULL
*/
static char* ConvertToUTF8(const char* s, const uint32 len);
static char* ConvertToUTF8(const char* s, const uint32 len, uint32& newSize);
/*!
** \brief Convert a string from ASCII to UTF8
** \param s The string to convert
** \return A new String
*/
static String ConvertToUTF8(const String& s);
/*!
** \brief Formatted string
** \param format The format of the new string
** \return A new string
*/
static String Format(const String& f, ...);
static String Format(const char* f, ...);
public:
//! \name Constructors and Destructor
//@{
//! Default constructor
String() :std::string() {}
//! Constructor by copy
String(const String& v, size_type pos = 0, size_type n = npos) :std::string(v, pos, n) {}
//! Constructor with a default value from a std::string
String(const std::string& v) :std::string(v) {}
//! Constructor with a default value from a wide string (wchar_t*)
String(const wchar_t* v) :std::string() {if (v) *this << v;}
//! Constructor with a default value from a string (char*)
String(const char* v) :std::string() { if (v) append(v); }
//! Constructor with a default value from a string (char*) and a length
String(const char* v, String::size_type n) :std::string(v, n) {}
//! Constructor with a default value from a single char
String(const char v) :std::string() {*this += v;}
//! Constructor with a default value from an int (8 bits)
String(const int8_t v) :std::string() {*this << v;}
//! Constructor with a default value from an int (16 bits)
String(const int16_t v) :std::string() {*this << v;}
//! Constructor with a default value from an int (32 bits)
String(const int32_t v) :std::string() {*this << v;}
//! Constructor with a default value from an int (64 bits)
String(const int64_t v) :std::string() {*this << v;}
//! Constructor with a default value from an unsigned int (8 bits)
String(const uint8_t v) :std::string() {*this << v;}
//! Constructor with a default value from an unsigned int (16 bits)
String(const uint16_t v) :std::string() {*this << v;}
//! Constructor with a default value from an unsigned int (32 bits)
String(const uint32_t v) :std::string() {*this << v;}
//! Constructor with a default value from an unsigned int (64 bits)
String(const uint64_t v) :std::string() {*this << v;}
//! Constructor with a default value from a float
String(const float v) :std::string() {*this << v;}
//! Constructor with a default value from a double
String(const double v) :std::string() {*this << v;}
//! Destructor
~String() {}
//@}
//! \name The operator `<<`
//@{
//! Append a string (char*)
String& operator << (const char* v) {append(v);return *this;}
//! Append a string (stl)
String& operator << (const std::string& v) {append(v);return *this;}
//! Append a string (Shared::Util::String)
String& operator << (const String& v) {append(v);return *this;}
//! Append a single char
String& operator << (const char v) {*(static_cast<std::string*>(this)) += v; return *this;}
//! Append a wide string (wchar_t*)
String& operator << (const wchar_t* v);
//! Append an int (8 bits)
String& operator << (const int8_t v) {TA3D_WSTR_APPEND;}
//! Append an unsigned int (8 bits)
String& operator << (const uint8_t v) {TA3D_WSTR_APPEND;}
//! Append an int (16 bits)
String& operator << (const int16_t v) {TA3D_WSTR_APPEND;}
//! Append an unsigned int (16 bits)
String& operator << (const uint16_t v) {TA3D_WSTR_APPEND;}
//! Append an int (32 bits)
String& operator << (const int32_t v) {TA3D_WSTR_APPEND;}
//! Append an unsigned int (32 bits)
String& operator << (const uint32_t v) {TA3D_WSTR_APPEND;}
//! Append an int (64 bits)
String& operator << (const int64_t v) {TA3D_WSTR_APPEND;}
//! Append an unsigned int (64 bits)
String& operator << (const uint64_t v) {TA3D_WSTR_APPEND;}
//! Convert then Append a float
String& operator << (const float v) {TA3D_WSTR_APPEND;}
//! Convert then Append a double
String& operator << (const double v) {TA3D_WSTR_APPEND;}
//! Convert then Append a boolean (will be converted into "true" or "false")
String& operator << (const bool v) {TA3D_WSTR_APPEND_BOOL(v);return *this;}
//@}
//! \name Convertions
//@{
//! Convert this string into an int (8 bits)
int8_t toInt8() const {TA3D_WSTR_CAST_OP(int8_t);}
//! Convert this string into an int (16 bits)
int16_t toInt16() const {TA3D_WSTR_CAST_OP(int16_t);}
//! Convert this string into an int (32 bits)
int32_t toInt32() const {TA3D_WSTR_CAST_OP(int32_t);}
//! Convert this string into an int (64 bits)
int64_t toInt64() const {TA3D_WSTR_CAST_OP(int64_t);}
//! Convert this string into an unsigned int (8 bits)
uint8_t toUInt8() const {TA3D_WSTR_CAST_OP(uint8_t);}
//! Convert this string into an unsigned int (16 bits)
uint16_t toUInt16() const {TA3D_WSTR_CAST_OP(uint16_t);}
//! Convert this string into an unsigned int (32 bits)
uint32_t toUInt32() const {TA3D_WSTR_CAST_OP(uint32_t);}
//! Convert this string into an unsigned int (64 bits)
uint64_t toUInt64() const {TA3D_WSTR_CAST_OP(uint64_t);}
//! Convert this string into a float
float toFloat() const {TA3D_WSTR_CAST_OP(float);}
//! Convert this string into a float with a default value if empty
float toFloat(const float def) const {if (empty()) return def;TA3D_WSTR_CAST_OP(float);}
//! Convert this string into a double
double toDouble() const {TA3D_WSTR_CAST_OP(double);}
//! Convert this string into a bool (true if the lower case value is equals to "true", "1" or "on")
bool toBool() const;
//! \name The operator `+=` (with the same abilities than the operator `<<`)
//@{
//! Append a string (char*)
String& operator += (const char* v) {append(v); return *this;}
//! Append a string (stl)
String& operator += (const std::string& v) {append(v); return *this;}
//! Append a string (Shared::Util::String)
String& operator += (const Shared::Util::String& v) {append(v); return *this; }
//! Append a single char
String& operator += (const char v) {*(static_cast<std::string*>(this)) += (char)v; return *this;}
//! Append a wide string (wchar_t*)
String& operator += (const wchar_t* v) {*this << v; return *this;}
//! Append an int (8 bits)
String& operator += (const int8_t v) {*this << v; return *this;}
//! Append an unsigned int (8 bits)
String& operator += (const uint8_t v) {*this << v; return *this;}
//! Append an int (16 bits)
String& operator += (const int16_t v) {*this << v; return *this; }
//! Append an unsigned int (16 bits)
String& operator += (const uint16_t v) {*this << v; return *this; }
//! Append an int (32 bits)
String& operator += (const int32_t v) {*this << v; return *this; }
//! Append an unsigned int (32 bits)
String& operator += (const uint32_t v) {*this << v; return *this; }
//! Append an int (64 bits)
String& operator += (const int64_t v) {*this << v; return *this; }
//! Append an unsigned int (64 bits)
String& operator += (const uint64_t v) {*this << v; return *this; }
//! Convert then Append a float
String& operator += (const float v) {*this << v; return *this; }
//! Convert then Append a double
String& operator += (const double v) {*this << v; return *this; }
//! Convert then Append a boolean (will be converted into "true" or "false")
String& operator += (const bool v) {TA3D_WSTR_APPEND_BOOL(v); return *this; }
//@}
//! \name The operator `+`
//@{
//! Create a new String from the concatenation of *this and a string
const String operator + (const String& rhs) { return String(*this) += rhs; }
//! Create a new String from the concatenation of *this and a char
const String operator + (const char rhs) { return String(*this) += rhs; }
//! Create a new String from the concatenation of *this and a widechar
const String operator + (const wchar_t rhs) { return String(*this) += rhs; }
//! Create a new String from the concatenation of *this and a const char*
const String operator + (const char* rhs) { return String(*this) += rhs; }
//! Create a new String from the concatenation of *this and a wide string
const String operator + (const wchar_t* rhs) { return String(*this) += rhs; }
//! Create a new String from the concatenation of *this and a signed int (8 bits)
const String operator + (const int8_t rhs) { return String(*this) += rhs; }
//! Create a new String from the concatenation of *this and a signed int (16 bits)
const String operator + (const int16_t rhs) { return String(*this) += rhs; }
//! Create a new String from the concatenation of *this and a signed int (32 bits)
const String operator + (const int32_t rhs) { return String(*this) += rhs; }
//! Create a new String from the concatenation of *this and a signed int (64 bits)
const String operator + (const int64_t rhs) { return String(*this) += rhs; }
//! Create a new String from the concatenation of *this and an unsigned int (8 bits)
const String operator + (const uint8_t rhs) { return String(*this) += rhs; }
//! Create a new String from the concatenation of *this and an unsigned int (16 bits)
const String operator + (const uint16_t rhs) { return String(*this) += rhs; }
//! Create a new String from the concatenation of *this and an unsigned int (32 bits)
const String operator + (const uint32_t rhs) { return String(*this) += rhs; }
//! Create a new String from the concatenation of *this and an unsigned int (64 bits)
const String operator + (const uint64_t rhs) { return String(*this) += rhs; }
//! Create a new String from the concatenation of *this and a float
const String operator + (const float rhs) { return String(*this) += rhs; }
//! Create a new String from the concatenation of *this and a double
const String operator + (const double rhs) { return String(*this) += rhs; }
//@}
//! \name Case convertion
//@{
/*!
** \brief Convert the case (lower case) of characters in the string using the UTF8 charset
** \return Returns *this
*/
String& toLower();
/*!
** \brief Convert the case (upper case) of characters in the string using the UTF8 charset
** \return Returns *this
*/
String& toUpper();
//@} Case convertion
/*!
** \brief Remove trailing and leading spaces
** \param trimChars The chars to remove
** \return Returns *this
*/
String& trim(const String& trimChars = TA3D_WSTR_SEPARATORS);
//! \name Split
//@{
/*!
** \brief Divide a string into several parts
** \param[out] All found parts
** \param sepearators Sequence of chars considered as a separator
** \param emptyBefore True to clear the vector before fulfill it
** \warning Do not take care of string representation (with `'` or `"`)
*/
void split(String::Vector& out, const String& separators = TA3D_WSTR_SEPARATORS, const bool emptyBefore = true) const;
/*!
** \brief Divide a string into several parts
** \param[out] All found parts
** \param sepearators Sequence of chars considered as a separator
** \param emptyBefore True to clear the list before fulfill it
** \warning Do not take care of string representation (with `'` or `"`)
*/
void split(String::List& out, const String& separators = TA3D_WSTR_SEPARATORS, const bool emptyBefore = true) const;
//@} Split
/*!
** \brief Extract the key and its value from a string (mainly provided by TDF files)
**
** \param[out] key The key that has been found
** \param[out] value The associated value
**
** \see String::ToKeyValue()
*/
void toKeyValue(String& key, String& value, const enum CharCase chcase = soCaseSensitive) const
{ToKeyValue(*this, key, value, chcase);}
/*!
** \brief Convert all antislashes into slashes
** \return Returns *this
*/
String& convertAntiSlashesIntoSlashes();
/*!
** \brief Convert all slashes into antislashes
** \return Returns *this
*/
String& convertSlashesIntoAntiSlashes();
/*!
** \brief Get the hash value of this string
*/
uint32 hashValue() const;
/*!
** \brief Convert the string from ASCII to UTF8
** \return Always *this
*/
String& convertToUTF8() {*this = ConvertToUTF8(*this); return *this;}
/*!
** \brief Replace a substr by another one
** \param toSearch The string to look for
** \param replaceWith The string replacement
** \param option Option when looking for the string `toSearch`
** \return Always *this
*/
String& findAndReplace(const String& toSearch, const String& replaceWith, const enum String::CharCase option = soCaseSensitive);
String& findAndReplace(char toSearch, const char replaceWith, const enum String::CharCase option = soCaseSensitive);
/*!
** \brief Reset the current value with a formatted string
** \param f The format of the new string
** \return Always *this
*/
String& format(const String& f, ...);
String& format(const char* f, ...);
/*!
** \brief Append a formatted string
** \param f The format of the new string
** \return Always *this
*/
String& appendFormat(const String& f, ...);
String& appendFormat(const char* f, ...);
String& vappendFormat(const char* f, va_list parg);
/*!
** \brief Detect if the string matches the given pattern
** \param pattern
** \return true if match
*/
bool match(const String &pattern);
/*!
** \brief returns a substring assuming current string is an UTF8 String
** \param pos
** \param len
** \return the substring
*/
String substrUTF8(int pos = 0, int len = -1) const;
/*!
** \brief returns the String size assuming it's in UTF8
** \return the number of UTF8 symbols
*/
int sizeUTF8() const;
private:
/*!
** \brief Convert a string into another type, given by the template parameter `T`
** \param[out] t The destination variable
** \param s The string to convert
** \param f The base to use for the convertion (std::hex, std::dec, ...)
** \return True if the operation succeeded, False otherwise
*/
template <class T>
bool fromString(T& t, const String& s) const
{
std::istringstream iss(s);
if (s.size() > 2)
{
if(s[0] == '0' && (s[1] == 'x' || s[1] == 'X'))
iss >> std::hex;
else if (s[0] == '0' && s[1] != 'x' && s[1] != 'X')
iss >> std::oct;
else
iss >> std::dec;
}
else
iss >> std::dec;
return !(iss >> t).fail();
}
static int ASCIItoUTF8(const byte c, byte *out);
}; // class String
//int ASCIItoUTF8(const byte c, byte *out);
/*!
** \brief Convert an UTF-8 String into a WideChar String
** \todo This class must be removed as soon as possible and is only here to prevent against
** stange bugs with the previous implementation
*/
struct WString
{
public:
WString(const char* s);
WString(const String& str);
void fromUtf8(const char* s, size_t length);
const wchar_t* cw_str() const {return pBuffer;}
private:
wchar_t pBuffer[5120];
};
}} // namespace TA3D
#endif // _SHARED_UTIL_W_STRING_H__

34
source/shared_lib/include/util/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
source/shared_lib/include/util/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
source/shared_lib/include/util/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
source/shared_lib/include/util/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