Revert "sdl_ttf, utf8"

This reverts commit 33683a9471.
This commit is contained in:
aurhat
2015-02-14 16:12:45 +01:00
parent f640b23a95
commit 6b27825a52
8 changed files with 0 additions and 1148 deletions
Binary file not shown.
Binary file not shown.
-234
View File
@@ -1,234 +0,0 @@
/*
SDL_ttf: A companion library to SDL for working with TrueType (tm) fonts
Copyright (C) 1997-2004 Sam Lantinga
This library is free software; you can redistribute it and/or
modify it under the terms of the GNU Library General Public
License as published by the Free Software Foundation; either
version 2 of the License, or (at your option) any later version.
This library 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
Library General Public License for more details.
You should have received a copy of the GNU Library General Public
License along with this library; if not, write to the Free
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
Sam Lantinga
[email protected]
*/
/* $Id: SDL_ttf.h 3282 2007-07-15 06:02:48Z slouken $ */
/* This library is a wrapper around the excellent FreeType 2.0 library,
available at:
http://www.freetype.org/
*/
#ifndef _SDL_TTF_H
#define _SDL_TTF_H
#include "SDL.h"
#include "begin_code.h"
/* Set up for C function definitions, even when using C++ */
#ifdef __cplusplus
extern "C" {
#endif
/* Printable format: "%d.%d.%d", MAJOR, MINOR, PATCHLEVEL
*/
#define SDL_TTF_MAJOR_VERSION 2
#define SDL_TTF_MINOR_VERSION 0
#define SDL_TTF_PATCHLEVEL 9
/* This macro can be used to fill a version structure with the compile-time
* version of the SDL_ttf library.
*/
#define SDL_TTF_VERSION(X) \
{ \
(X)->major = SDL_TTF_MAJOR_VERSION; \
(X)->minor = SDL_TTF_MINOR_VERSION; \
(X)->patch = SDL_TTF_PATCHLEVEL; \
}
/* Backwards compatibility */
#define TTF_MAJOR_VERSION SDL_TTF_MAJOR_VERSION
#define TTF_MINOR_VERSION SDL_TTF_MINOR_VERSION
#define TTF_PATCHLEVEL SDL_TTF_PATCHLEVEL
#define TTF_VERSION(X) SDL_TTF_VERSION(X)
/* This function gets the version of the dynamically linked SDL_ttf library.
it should NOT be used to fill a version structure, instead you should
use the SDL_TTF_VERSION() macro.
*/
extern DECLSPEC const SDL_version * SDLCALL TTF_Linked_Version(void);
/* ZERO WIDTH NO-BREAKSPACE (Unicode byte order mark) */
#define UNICODE_BOM_NATIVE 0xFEFF
#define UNICODE_BOM_SWAPPED 0xFFFE
/* This function tells the library whether UNICODE text is generally
byteswapped. A UNICODE BOM character in a string will override
this setting for the remainder of that string.
*/
extern DECLSPEC void SDLCALL TTF_ByteSwappedUNICODE(int swapped);
/* The internal structure containing font information */
typedef struct _TTF_Font TTF_Font;
/* Initialize the TTF engine - returns 0 if successful, -1 on error */
extern DECLSPEC int SDLCALL TTF_Init(void);
/* Open a font file and create a font of the specified point size.
* Some .fon fonts will have several sizes embedded in the file, so the
* point size becomes the index of choosing which size. If the value
* is too high, the last indexed size will be the default. */
extern DECLSPEC TTF_Font * SDLCALL TTF_OpenFont(const char *file, int ptsize);
extern DECLSPEC TTF_Font * SDLCALL TTF_OpenFontIndex(const char *file, int ptsize, long index);
extern DECLSPEC TTF_Font * SDLCALL TTF_OpenFontRW(SDL_RWops *src, int freesrc, int ptsize);
extern DECLSPEC TTF_Font * SDLCALL TTF_OpenFontIndexRW(SDL_RWops *src, int freesrc, int ptsize, long index);
/* Set and retrieve the font style
This font style is implemented by modifying the font glyphs, and
doesn't reflect any inherent properties of the truetype font file.
*/
#define TTF_STYLE_NORMAL 0x00
#define TTF_STYLE_BOLD 0x01
#define TTF_STYLE_ITALIC 0x02
#define TTF_STYLE_UNDERLINE 0x04
extern DECLSPEC int SDLCALL TTF_GetFontStyle(const TTF_Font *font);
extern DECLSPEC void SDLCALL TTF_SetFontStyle(TTF_Font *font, int style);
/* Get the total height of the font - usually equal to point size */
extern DECLSPEC int SDLCALL TTF_FontHeight(const TTF_Font *font);
/* Get the offset from the baseline to the top of the font
This is a positive value, relative to the baseline.
*/
extern DECLSPEC int SDLCALL TTF_FontAscent(const TTF_Font *font);
/* Get the offset from the baseline to the bottom of the font
This is a negative value, relative to the baseline.
*/
extern DECLSPEC int SDLCALL TTF_FontDescent(const TTF_Font *font);
/* Get the recommended spacing between lines of text for this font */
extern DECLSPEC int SDLCALL TTF_FontLineSkip(const TTF_Font *font);
/* Get the number of faces of the font */
extern DECLSPEC long SDLCALL TTF_FontFaces(const TTF_Font *font);
/* Get the font face attributes, if any */
extern DECLSPEC int SDLCALL TTF_FontFaceIsFixedWidth(const TTF_Font *font);
extern DECLSPEC char * SDLCALL TTF_FontFaceFamilyName(const TTF_Font *font);
extern DECLSPEC char * SDLCALL TTF_FontFaceStyleName(const TTF_Font *font);
/* Get the metrics (dimensions) of a glyph
To understand what these metrics mean, here is a useful link:
http://freetype.sourceforge.net/freetype2/docs/tutorial/step2.html
*/
extern DECLSPEC int SDLCALL TTF_GlyphMetrics(TTF_Font *font, Uint16 ch,
int *minx, int *maxx,
int *miny, int *maxy, int *advance);
/* Get the dimensions of a rendered string of text */
extern DECLSPEC int SDLCALL TTF_SizeText(TTF_Font *font, const char *text, int *w, int *h);
extern DECLSPEC int SDLCALL TTF_SizeUTF8(TTF_Font *font, const char *text, int *w, int *h);
extern DECLSPEC int SDLCALL TTF_SizeUNICODE(TTF_Font *font, const Uint16 *text, int *w, int *h);
/* Create an 8-bit palettized surface and render the given text at
fast quality with the given font and color. The 0 pixel is the
colorkey, giving a transparent background, and the 1 pixel is set
to the text color.
This function returns the new surface, or NULL if there was an error.
*/
extern DECLSPEC SDL_Surface * SDLCALL TTF_RenderText_Solid(TTF_Font *font,
const char *text, SDL_Color fg);
extern DECLSPEC SDL_Surface * SDLCALL TTF_RenderUTF8_Solid(TTF_Font *font,
const char *text, SDL_Color fg);
extern DECLSPEC SDL_Surface * SDLCALL TTF_RenderUNICODE_Solid(TTF_Font *font,
const Uint16 *text, SDL_Color fg);
/* Create an 8-bit palettized surface and render the given glyph at
fast quality with the given font and color. The 0 pixel is the
colorkey, giving a transparent background, and the 1 pixel is set
to the text color. The glyph is rendered without any padding or
centering in the X direction, and aligned normally in the Y direction.
This function returns the new surface, or NULL if there was an error.
*/
extern DECLSPEC SDL_Surface * SDLCALL TTF_RenderGlyph_Solid(TTF_Font *font,
Uint16 ch, SDL_Color fg);
/* Create an 8-bit palettized surface and render the given text at
high quality with the given font and colors. The 0 pixel is background,
while other pixels have varying degrees of the foreground color.
This function returns the new surface, or NULL if there was an error.
*/
extern DECLSPEC SDL_Surface * SDLCALL TTF_RenderText_Shaded(TTF_Font *font,
const char *text, SDL_Color fg, SDL_Color bg);
extern DECLSPEC SDL_Surface * SDLCALL TTF_RenderUTF8_Shaded(TTF_Font *font,
const char *text, SDL_Color fg, SDL_Color bg);
extern DECLSPEC SDL_Surface * SDLCALL TTF_RenderUNICODE_Shaded(TTF_Font *font,
const Uint16 *text, SDL_Color fg, SDL_Color bg);
/* Create an 8-bit palettized surface and render the given glyph at
high quality with the given font and colors. The 0 pixel is background,
while other pixels have varying degrees of the foreground color.
The glyph is rendered without any padding or centering in the X
direction, and aligned normally in the Y direction.
This function returns the new surface, or NULL if there was an error.
*/
extern DECLSPEC SDL_Surface * SDLCALL TTF_RenderGlyph_Shaded(TTF_Font *font,
Uint16 ch, SDL_Color fg, SDL_Color bg);
/* Create a 32-bit ARGB surface and render the given text at high quality,
using alpha blending to dither the font with the given color.
This function returns the new surface, or NULL if there was an error.
*/
extern DECLSPEC SDL_Surface * SDLCALL TTF_RenderText_Blended(TTF_Font *font,
const char *text, SDL_Color fg);
extern DECLSPEC SDL_Surface * SDLCALL TTF_RenderUTF8_Blended(TTF_Font *font,
const char *text, SDL_Color fg);
extern DECLSPEC SDL_Surface * SDLCALL TTF_RenderUNICODE_Blended(TTF_Font *font,
const Uint16 *text, SDL_Color fg);
/* Create a 32-bit ARGB surface and render the given glyph at high quality,
using alpha blending to dither the font with the given color.
The glyph is rendered without any padding or centering in the X
direction, and aligned normally in the Y direction.
This function returns the new surface, or NULL if there was an error.
*/
extern DECLSPEC SDL_Surface * SDLCALL TTF_RenderGlyph_Blended(TTF_Font *font,
Uint16 ch, SDL_Color fg);
/* For compatibility with previous versions, here are the old functions */
#define TTF_RenderText(font, text, fg, bg) \
TTF_RenderText_Shaded(font, text, fg, bg)
#define TTF_RenderUTF8(font, text, fg, bg) \
TTF_RenderUTF8_Shaded(font, text, fg, bg)
#define TTF_RenderUNICODE(font, text, fg, bg) \
TTF_RenderUNICODE_Shaded(font, text, fg, bg)
/* Close an opened font file */
extern DECLSPEC void SDLCALL TTF_CloseFont(TTF_Font *font);
/* De-initialize the TTF engine */
extern DECLSPEC void SDLCALL TTF_Quit(void);
/* Check if the TTF engine is initialized */
extern DECLSPEC int SDLCALL TTF_WasInit(void);
/* We'll use SDL for reporting errors */
#define TTF_SetError SDL_SetError
#define TTF_GetError SDL_GetError
/* Ends C function definitions when using C++ */
#ifdef __cplusplus
}
#endif
#include "close_code.h"
#endif /* _SDL_TTF_H */
-34
View File
@@ -1,34 +0,0 @@
// 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
-318
View File
@@ -1,318 +0,0 @@
// 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
{
// Exceptions that may be thrown from the library functions.
class invalid_code_point : public std::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 std::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 std::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 std::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 if (cp <= internal::CODE_POINT_MAX) { // 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);
}
else
throw invalid_code_point(cp);
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)
{
octet_iterator end = it;
while (internal::is_trail(*(--it)))
if (it < start)
throw invalid_utf8(*it); // error - no lead byte in the sequence
octet_iterator temp = it;
return next(temp, 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_surrogate(cp)) {
if (start != end) {
uint32_t trail_surrogate = internal::mask16(*start++);
if (trail_surrogate >= internal::TRAIL_SURROGATE_MIN && trail_surrogate <= internal::TRAIL_SURROGATE_MAX)
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>(*start));
}
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
-334
View File
@@ -1,334 +0,0 @@
// 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_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) && cp != 0xfffe && cp != 0xffff);
}
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;
}
inline bool is_overlong_sequence(uint32_t cp, int 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 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
View File
@@ -1,228 +0,0 @@
// 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_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
Binary file not shown.