Mirror/TrinityCore
1
0
Fork 0
mirror of https://github.com/TrinityCore/TrinityCore.git synced 2026-01-23 10:26:28 +01:00
Code Issues Packages Projects Releases Wiki Activity

upgrade to new version of utf8cpp

Browse Source 
--HG--
branch : trunk
This commit is contained in:
click
2010-06-07 20:50:02 +02:00
parent 0000768855
commit a3a5697516
6 changed files with 268 additions and 1760 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
externals/utf8cpp/include/doc/ReleaseNotes vendored
View File

@@ -1,9 +0,0 @@
utf8 cpp library
Release 2.1
This is a minor feature release - added the function peek_next.
Changes from version 2.o
- Implemented feature request [ 1770746 ] "Provide a const version of next() (some sort of a peek() )
Files included in the release: utf8.h, core.h, checked.h, unchecked.h, utf8cpp.html, ReleaseNotes

1574
externals/utf8cpp/include/doc/utf8cpp.html vendored
View File

File diff suppressed because it is too large Load Diff

69
externals/utf8cpp/include/utf8.h → externals/utf8cpp/utf8.h vendored
View File

@@ -1,35 +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
// 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

36
externals/utf8cpp/include/utf8/checked.h → externals/utf8cpp/utf8/checked.h vendored
View File

@@ -33,8 +33,12 @@ DEALINGS IN THE SOFTWARE.
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 std::exception {
class invalid_code_point : public exception {
uint32_t cp;
public:
invalid_code_point(uint32_t cp) : cp(cp) {}
@@ -42,7 +46,7 @@ namespace utf8
uint32_t code_point() const {return cp;}
};
class invalid_utf8 : public std::exception {
class invalid_utf8 : public exception {
uint8_t u8;
public:
invalid_utf8 (uint8_t u) : u8(u) {}
@@ -50,7 +54,7 @@ namespace utf8
uint8_t utf8_octet() const {return u8;}
};
class invalid_utf16 : public std::exception {
class invalid_utf16 : public exception {
uint16_t u16;
public:
invalid_utf16 (uint16_t u) : u16(u) {}
@@ -58,7 +62,7 @@ namespace utf8
uint16_t utf16_word() const {return u16;}
};
class not_enough_room : public std::exception {
class not_enough_room : public exception {
public:
virtual const char* what() const throw() { return "Not enough space"; }
};
@@ -72,7 +76,7 @@ namespace utf8
octet_iterator sequence_start = start;
internal::utf_error err_code = internal::validate_next(start, end);
switch (err_code) {
case internal::OK :
case internal::UTF8_OK :
for (octet_iterator it = sequence_start; it != start; ++it)
*out++ = *it;
break;
@@ -120,15 +124,12 @@ namespace utf8
*(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
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 >> 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;
}
@@ -138,7 +139,7 @@ namespace utf8
uint32_t cp = 0;
internal::utf_error err_code = internal::validate_next(it, end, &cp);
switch (err_code) {
case internal::OK :
case internal::UTF8_OK :
break;
case internal::NOT_ENOUGH_ROOM :
throw not_enough_room();
@@ -204,18 +205,22 @@ namespace utf8
while (start != end) {
uint32_t cp = internal::mask16(*start++);
// Take care of surrogate pairs first
if (internal::is_surrogate(cp)) {
if (internal::is_lead_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)
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>(*start));
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;
@@ -248,7 +253,7 @@ namespace utf8
template <typename octet_iterator, typename u32bit_iterator>
u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result)
{
while (start < end)
while (start != end)
(*result++) = next(start, end);
return result;
@@ -316,4 +321,3 @@ namespace utf8
#endif //header guard

297
externals/utf8cpp/include/utf8/core.h → externals/utf8cpp/utf8/core.h vendored
View File

@@ -30,23 +30,14 @@ DEALINGS IN THE SOFTWARE.
#include <iterator>
// use Trinity core types
#include "Platform/Define.h"
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
/* use Trinity alternatives
typedef unsigned char uint8_t;
typedef unsigned short uint16_t;
typedef unsigned int uint32_t;
*/
typedef uint8 uint8_t;
typedef uint16 uint16_t;
typedef uint32 uint32_t;
// Helper code - not intended to be directly called by the library users. May be changed at any time
namespace internal
@@ -80,6 +71,18 @@ namespace internal
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)
{
@@ -109,117 +112,193 @@ namespace internal
return 0;
}
enum utf_error {OK, NOT_ENOUGH_ROOM, INVALID_LEAD, INCOMPLETE_SEQUENCE, OVERLONG_SEQUENCE, INVALID_CODE_POINT};
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)
{
uint32_t cp = mask8(*it);
// Check the lead octet
// 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;
// "Shortcut" for ASCII characters
if (length == 1) {
if (end - it > 0) {
if (code_point)
*code_point = cp;
++it;
return OK;
}
else
return NOT_ENOUGH_ROOM;
}
// Do we have enough memory?
if (std::distance(it, end) < length)
return NOT_ENOUGH_ROOM;
// Check trail octets and calculate the code point
// Now that we have a valid sequence length, get trail octets and calculate the code point
utf_error err = UTF8_OK;
switch (length) {
case 0:
return INVALID_LEAD;
case 1:
err = get_sequence_1(it, end, &cp);
break;
case 2:
if (is_trail(*(++it))) {
cp = ((cp << 6) & 0x7ff) + ((*it) & 0x3f);
}
else {
--it;
return INCOMPLETE_SEQUENCE;
}
err = get_sequence_2(it, end, &cp);
break;
case 3:
if (is_trail(*(++it))) {
cp = ((cp << 12) & 0xffff) + ((mask8(*it) << 6) & 0xfff);
if (is_trail(*(++it))) {
cp += (*it) & 0x3f;
}
else {
std::advance(it, -2);
return INCOMPLETE_SEQUENCE;
}
}
else {
--it;
return INCOMPLETE_SEQUENCE;
}
err = get_sequence_3(it, end, &cp);
break;
case 4:
if (is_trail(*(++it))) {
cp = ((cp << 18) & 0x1fffff) + ((mask8(*it) << 12) & 0x3ffff);
if (is_trail(*(++it))) {
cp += (mask8(*it) << 6) & 0xfff;
if (is_trail(*(++it))) {
cp += (*it) & 0x3f;
}
else {
std::advance(it, -3);
return INCOMPLETE_SEQUENCE;
}
}
else {
std::advance(it, -2);
return INCOMPLETE_SEQUENCE;
}
}
else {
--it;
return INCOMPLETE_SEQUENCE;
}
err = get_sequence_4(it, end, &cp);
break;
}
// Is the code point valid?
if (!is_code_point_valid(cp)) {
for (octet_difference_type i = 0; i < length - 1; ++i)
--it;
return INVALID_CODE_POINT;
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;
}
if (code_point)
*code_point = cp;
if (cp < 0x80) {
if (length != 1) {
std::advance(it, -(length-1));
return OVERLONG_SEQUENCE;
}
}
else if (cp < 0x800) {
if (length != 2) {
std::advance(it, -(length-1));
return OVERLONG_SEQUENCE;
}
}
else if (cp < 0x10000) {
if (length != 3) {
std::advance(it, -(length-1));
return OVERLONG_SEQUENCE;
}
}
++it;
return OK;
// Failure branch - restore the original value of the iterator
it = original_it;
return err;
}
template <typename octet_iterator>
@@ -240,7 +319,7 @@ namespace internal
octet_iterator result = start;
while (result != end) {
internal::utf_error err_code = internal::validate_next(result, end);
if (err_code != internal::OK)
if (err_code != internal::UTF8_OK)
return result;
}
return result;
@@ -252,6 +331,17 @@ namespace internal
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)
{
@@ -266,4 +356,3 @@ namespace internal
#endif // header guard

43
externals/utf8cpp/include/utf8/unchecked.h → externals/utf8cpp/utf8/unchecked.h vendored
View File

@@ -32,26 +32,26 @@ DEALINGS IN THE SOFTWARE.
namespace utf8
{
namespace unchecked
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);
*(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 >> 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 >> 12) & 0x3f)| 0x80);
*(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80);
*(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
}
return result;
@@ -70,28 +70,28 @@ namespace utf8
cp = ((cp << 6) & 0x7ff) + ((*it) & 0x3f);
break;
case 3:
++it;
++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);
cp = ((cp << 18) & 0x1fffff) + ((internal::mask8(*it) << 12) & 0x3ffff);
++it;
cp += (internal::mask8(*it) << 6) & 0xfff;
++it;
cp += (*it) & 0x3f;
cp += (*it) & 0x3f;
break;
}
++it;
return cp;
return cp;
}
template <typename octet_iterator>
uint32_t peek_next(octet_iterator it)
{
return next(it);
return next(it);
}
template <typename octet_iterator>
@@ -121,30 +121,30 @@ namespace utf8
distance (octet_iterator first, octet_iterator last)
{
typename std::iterator_traits<octet_iterator>::difference_type dist;
for (dist = 0; first < last; ++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)) {
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;
return result;
}
template <typename u16bit_iterator, typename octet_iterator>
u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result)
{
while (start != end) {
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);
@@ -176,7 +176,7 @@ namespace utf8
// The iterator class
template <typename octet_iterator>
class iterator : public std::iterator <std::bidirectional_iterator_tag, uint32_t> {
class iterator : public std::iterator <std::bidirectional_iterator_tag, uint32_t> {
octet_iterator it;
public:
iterator () {};
@@ -188,15 +188,15 @@ namespace utf8
octet_iterator temp = it;
return next(temp);
}
bool operator == (const iterator& rhs) const
{
bool operator == (const iterator& rhs) const
{
return (it == rhs.it);
}
bool operator != (const iterator& rhs) const
{
return !(operator == (rhs));
}
iterator& operator ++ ()
iterator& operator ++ ()
{
std::advance(it, internal::sequence_length(it));
return *this;
@@ -206,7 +206,7 @@ namespace utf8
iterator temp = *this;
std::advance(it, internal::sequence_length(it));
return temp;
}
}
iterator& operator -- ()
{
prior(it);
@@ -221,9 +221,8 @@ namespace utf8
}; // class iterator
} // namespace utf8::unchecked
} // namespace utf8
} // namespace utf8
#endif // header guard