Commit 403170f5 authored by Alexandre Duret-Lutz's avatar Alexandre Duret-Lutz
Browse files

Distribute UTF8-for-cpp.

* utf8/doc/ReleaseNotes, utf8/doc/utf8cpp.html, utf8/utf8.h,
utf8/utf8/checked.h, utf8/utf8/core.h, utf8/utf8/unchecked.h:
New files.
* Makefile.am (EXTRA_DIST): Distribute them.
parent 80a9c3e2
......@@ -38,8 +38,11 @@ endif
SUBDIRS = $(MAYBE_BUDDY) $(MAYBE_LBTT) $(NEVER_BENCH) doc src wrap ltdl iface
UTF8 = utf8/doc/ReleaseNotes utf8/doc/utf8cpp.html utf8/utf8.h \
utf8/utf8/checked.h utf8/utf8/core.h utf8/utf8/unchecked.h
ACLOCAL_AMFLAGS = -I m4
EXTRA_DIST = HACKING ChangeLog.1 tools/gitlog-to-changelog
EXTRA_DIST = HACKING ChangeLog.1 tools/gitlog-to-changelog $(UTF8)
dist-hook: gen-ChangeLog
......
utf8 cpp library
Release 2.3.1
A bug fix release. Special thanks to dalle and Ivan Sorokin who reported the bugs.
Changes from version 2.3
- Bug fix [3025042]: is_bom documentation issue.
- Bug fix [3083640]: is_code_point_valid incorrectly returns false.
- Bug fix [3167987]: prior moves it before start.
- Bug fix [3185087]: utf8::prior and utf8::previous documentation issue.
Files included in the release: utf8.h, core.h, checked.h, unchecked.h, utf8cpp.html, ReleaseNotes
This diff is collapsed.
// 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_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
// 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