utf8: Update to match current version

* utf8/LICENSE, utf8/utf8/cpp11.h, utf8/utf8/cpp17.h: New files.
* Makefile.am: Distribute them.
* utf8/README.md, utf8/utf8/checked.h, utf8/utf8/core.h,
utf8/utf8/unchecked.h: Update to the current version of utfcpp.
* README: Add a link to the upstream github.
This commit is contained in:
Alexandre Duret-Lutz 2022-07-05 10:56:57 +02:00
parent efee1c4130
commit ff89601306
9 changed files with 897 additions and 194 deletions

View file

@ -42,7 +42,7 @@ namespace utf8
uint32_t cp;
public:
invalid_code_point(uint32_t codepoint) : cp(codepoint) {}
virtual const char* what() const throw() { return "Invalid code point"; }
virtual const char* what() const UTF_CPP_NOEXCEPT UTF_CPP_OVERRIDE { return "Invalid code point"; }
uint32_t code_point() const {return cp;}
};
@ -50,7 +50,7 @@ namespace utf8
uint8_t u8;
public:
invalid_utf8 (uint8_t u) : u8(u) {}
virtual const char* what() const throw() { return "Invalid UTF-8"; }
virtual const char* what() const UTF_CPP_NOEXCEPT UTF_CPP_OVERRIDE { return "Invalid UTF-8"; }
uint8_t utf8_octet() const {return u8;}
};
@ -58,13 +58,13 @@ namespace utf8
uint16_t u16;
public:
invalid_utf16 (uint16_t u) : u16(u) {}
virtual const char* what() const throw() { return "Invalid UTF-16"; }
virtual const char* what() const UTF_CPP_NOEXCEPT UTF_CPP_OVERRIDE { 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"; }
virtual const char* what() const UTF_CPP_NOEXCEPT UTF_CPP_OVERRIDE { return "Not enough space"; }
};
/// The library API - functions intended to be called by the users
@ -107,7 +107,9 @@ namespace utf8
*out++ = *it;
break;
case internal::NOT_ENOUGH_ROOM:
throw not_enough_room();
out = utf8::append (replacement, out);
start = end;
break;
case internal::INVALID_LEAD:
out = utf8::append (replacement, out);
++start;
@ -174,23 +176,19 @@ namespace utf8
return utf8::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 (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 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)
utf8::next(it, end);
const distance_type zero(0);
if (n < zero) {
// backward
for (distance_type i = n; i < zero; ++i)
utf8::prior(it, end);
} else {
// forward
for (distance_type i = zero; i < n; ++i)
utf8::next(it, end);
}
}
template <typename octet_iterator>
@ -265,11 +263,16 @@ namespace utf8
// The iterator class
template <typename octet_iterator>
class iterator : public std::iterator <std::bidirectional_iterator_tag, uint32_t> {
class iterator {
octet_iterator it;
octet_iterator range_start;
octet_iterator range_end;
public:
typedef uint32_t value_type;
typedef uint32_t* pointer;
typedef uint32_t& reference;
typedef std::ptrdiff_t difference_type;
typedef std::bidirectional_iterator_tag iterator_category;
iterator () {}
explicit iterator (const octet_iterator& octet_it,
const octet_iterator& rangestart,
@ -322,6 +325,11 @@ namespace utf8
} // namespace utf8
#if UTF_CPP_CPLUSPLUS >= 201703L // C++ 17 or later
#include "cpp17.h"
#elif UTF_CPP_CPLUSPLUS >= 201103L // C++ 11 or later
#include "cpp11.h"
#endif // C++ 11 or later
#endif //header guard