upgrade utfcpp to v2.3.5
From https://github.com/nemtrif/utfcpp/releases/tag/v2.3.5 * utf8/utf8.h, utf8/utf8/checked.h, utf8/utf8/core.h, utf8/utf8/unchecked.h: Update. * utf8/doc/utf8cpp.html, utf8/doc/ReleaseNotes: Delete. * utf8/README.md: New file. * Makefile.am: Adjust.
This commit is contained in:
Alexandre Duret-Lutz
parent
b81d7e5839
commit
07e714e14e
8 changed files with 1320 additions and 2061 deletions
|
|
@ -1,4 +1,4 @@
|
|||
// Copyright 2006 Nemanja Trifunovic
|
||||
// Copyright 2006-2016 Nemanja Trifunovic
|
||||
|
||||
/*
|
||||
Permission is hereby granted, free of charge, to any person or organization
|
||||
|
|
@ -34,14 +34,14 @@ DEALINGS IN THE SOFTWARE.
|
|||
namespace utf8
|
||||
{
|
||||
// Base for the exceptions that may be thrown from the library
|
||||
class exception : public std::exception {
|
||||
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) {}
|
||||
invalid_code_point(uint32_t codepoint) : cp(codepoint) {}
|
||||
virtual const char* what() const throw() { return "Invalid code point"; }
|
||||
uint32_t code_point() const {return cp;}
|
||||
};
|
||||
|
|
@ -69,48 +69,10 @@ namespace utf8
|
|||
|
||||
/// 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))
|
||||
if (!utf8::internal::is_code_point_valid(cp))
|
||||
throw invalid_code_point(cp);
|
||||
|
||||
if (cp < 0x80) // one octet
|
||||
|
|
@ -124,7 +86,7 @@ namespace utf8
|
|||
*(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80);
|
||||
*(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80);
|
||||
}
|
||||
else { // 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 >> 6) & 0x3f) | 0x80);
|
||||
|
|
@ -133,11 +95,49 @@ namespace utf8
|
|||
return result;
|
||||
}
|
||||
|
||||
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 = utf8::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:
|
||||
out = utf8::append (replacement, out);
|
||||
++start;
|
||||
break;
|
||||
case internal::INCOMPLETE_SEQUENCE:
|
||||
case internal::OVERLONG_SEQUENCE:
|
||||
case internal::INVALID_CODE_POINT:
|
||||
out = utf8::append (replacement, out);
|
||||
++start;
|
||||
// just one replacement mark for the sequence
|
||||
while (start != end && utf8::internal::is_trail(*start))
|
||||
++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 = utf8::internal::mask16(0xfffd);
|
||||
return utf8::replace_invalid(start, end, out, replacement_marker);
|
||||
}
|
||||
|
||||
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);
|
||||
internal::utf_error err_code = utf8::internal::validate_next(it, end, cp);
|
||||
switch (err_code) {
|
||||
case internal::UTF8_OK :
|
||||
break;
|
||||
|
|
@ -156,22 +156,22 @@ namespace utf8
|
|||
template <typename octet_iterator>
|
||||
uint32_t peek_next(octet_iterator it, octet_iterator end)
|
||||
{
|
||||
return next(it, end);
|
||||
return utf8::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)
|
||||
if (it == start)
|
||||
throw not_enough_room();
|
||||
|
||||
octet_iterator end = it;
|
||||
octet_iterator end = it;
|
||||
// Go back until we hit either a lead octet or start
|
||||
while (internal::is_trail(*(--it)))
|
||||
while (utf8::internal::is_trail(*(--it)))
|
||||
if (it == start)
|
||||
throw invalid_utf8(*it); // error - no lead byte in the sequence
|
||||
return peek_next(it, end);
|
||||
return utf8::peek_next(it, end);
|
||||
}
|
||||
|
||||
/// Deprecated in versions that include "prior"
|
||||
|
|
@ -179,18 +179,18 @@ namespace utf8
|
|||
uint32_t previous(octet_iterator& it, octet_iterator pass_start)
|
||||
{
|
||||
octet_iterator end = it;
|
||||
while (internal::is_trail(*(--it)))
|
||||
while (utf8::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);
|
||||
return utf8::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);
|
||||
utf8::next(it, end);
|
||||
}
|
||||
|
||||
template <typename octet_iterator>
|
||||
|
|
@ -199,7 +199,7 @@ namespace utf8
|
|||
{
|
||||
typename std::iterator_traits<octet_iterator>::difference_type dist;
|
||||
for (dist = 0; first < last; ++dist)
|
||||
next(first, last);
|
||||
utf8::next(first, last);
|
||||
return dist;
|
||||
}
|
||||
|
||||
|
|
@ -207,12 +207,12 @@ namespace utf8
|
|||
octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result)
|
||||
{
|
||||
while (start != end) {
|
||||
uint32_t cp = internal::mask16(*start++);
|
||||
uint32_t cp = utf8::internal::mask16(*start++);
|
||||
// Take care of surrogate pairs first
|
||||
if (internal::is_lead_surrogate(cp)) {
|
||||
if (utf8::internal::is_lead_surrogate(cp)) {
|
||||
if (start != end) {
|
||||
uint32_t trail_surrogate = internal::mask16(*start++);
|
||||
if (internal::is_trail_surrogate(trail_surrogate))
|
||||
uint32_t trail_surrogate = utf8::internal::mask16(*start++);
|
||||
if (utf8::internal::is_trail_surrogate(trail_surrogate))
|
||||
cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET;
|
||||
else
|
||||
throw invalid_utf16(static_cast<uint16_t>(trail_surrogate));
|
||||
|
|
@ -222,10 +222,10 @@ namespace utf8
|
|||
|
||||
}
|
||||
// Lone trail surrogate
|
||||
else if (internal::is_trail_surrogate(cp))
|
||||
else if (utf8::internal::is_trail_surrogate(cp))
|
||||
throw invalid_utf16(static_cast<uint16_t>(cp));
|
||||
|
||||
result = append(cp, result);
|
||||
result = utf8::append(cp, result);
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
|
@ -233,8 +233,8 @@ namespace utf8
|
|||
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);
|
||||
while (start < end) {
|
||||
uint32_t cp = utf8::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);
|
||||
|
|
@ -249,7 +249,7 @@ namespace utf8
|
|||
octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result)
|
||||
{
|
||||
while (start != end)
|
||||
result = append(*(start++), result);
|
||||
result = utf8::append(*(start++), result);
|
||||
|
||||
return result;
|
||||
}
|
||||
|
|
@ -257,8 +257,8 @@ namespace utf8
|
|||
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);
|
||||
while (start < end)
|
||||
(*result++) = utf8::next(start, end);
|
||||
|
||||
return result;
|
||||
}
|
||||
|
|
@ -270,11 +270,11 @@ namespace utf8
|
|||
octet_iterator range_start;
|
||||
octet_iterator range_end;
|
||||
public:
|
||||
iterator () {};
|
||||
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)
|
||||
const octet_iterator& rangestart,
|
||||
const octet_iterator& rangeend) :
|
||||
it(octet_it), range_start(rangestart), range_end(rangeend)
|
||||
{
|
||||
if (it < range_start || it > range_end)
|
||||
throw std::out_of_range("Invalid utf-8 iterator position");
|
||||
|
|
@ -284,7 +284,7 @@ namespace utf8
|
|||
uint32_t operator * () const
|
||||
{
|
||||
octet_iterator temp = it;
|
||||
return next(temp, range_end);
|
||||
return utf8::next(temp, range_end);
|
||||
}
|
||||
bool operator == (const iterator& rhs) const
|
||||
{
|
||||
|
|
@ -298,24 +298,24 @@ namespace utf8
|
|||
}
|
||||
iterator& operator ++ ()
|
||||
{
|
||||
next(it, range_end);
|
||||
utf8::next(it, range_end);
|
||||
return *this;
|
||||
}
|
||||
iterator operator ++ (int)
|
||||
{
|
||||
iterator temp = *this;
|
||||
next(it, range_end);
|
||||
utf8::next(it, range_end);
|
||||
return temp;
|
||||
}
|
||||
iterator& operator -- ()
|
||||
{
|
||||
prior(it, range_start);
|
||||
utf8::prior(it, range_start);
|
||||
return *this;
|
||||
}
|
||||
iterator operator -- (int)
|
||||
{
|
||||
iterator temp = *this;
|
||||
prior(it, range_start);
|
||||
utf8::prior(it, range_start);
|
||||
return temp;
|
||||
}
|
||||
}; // class iterator
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue