Commit 07e714e1 authored by Alexandre Duret-Lutz's avatar Alexandre Duret-Lutz

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.
parent b81d7e58
## -*- coding: utf-8 -*-
## Copyright (C) 2011, 2012, 2013, 2014, 2015, 2016 Laboratoire de
## Recherche et Développement de l'Epita (LRDE).
## Copyright (C) 2011-2017 Laboratoire de Recherche et Développement
## de l'Epita (LRDE).
## Copyright (C) 2003, 2005 Laboratoire d'Informatique de Paris 6 (LIP6),
## département Systèmes Répartis Coopératifs (SRC), Université Pierre
## et Marie Curie.
......@@ -35,7 +35,7 @@ endif
SUBDIRS = picosat buddy lib ltdl spot bin tests $(PYTHON_SUBDIR) doc \
$(NEVER_SUBDIRS)
UTF8 = utf8/doc/ReleaseNotes utf8/doc/utf8cpp.html utf8/utf8.h \
UTF8 = utf8/README.md utf8/utf8.h \
utf8/utf8/checked.h utf8/utf8/core.h utf8/utf8/unchecked.h
DEBIAN = \
......
This diff is collapsed.
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
// 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;}
};
......@@ -69,12 +69,38 @@ namespace utf8
/// The library API - functions intended to be called by the users
template <typename octet_iterator>
octet_iterator append(uint32_t cp, octet_iterator result)
{
if (!utf8::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, 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);
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)
......@@ -83,16 +109,16 @@ namespace utf8
case internal::NOT_ENOUGH_ROOM:
throw not_enough_room();
case internal::INVALID_LEAD:
append (replacement, out);
out = utf8::append (replacement, out);
++start;
break;
case internal::INCOMPLETE_SEQUENCE:
case internal::OVERLONG_SEQUENCE:
case internal::INVALID_CODE_POINT:
append (replacement, out);
out = utf8::append (replacement, out);
++start;
// just one replacement mark for the sequence
while (internal::is_trail(*start) && start != end)
while (start != end && utf8::internal::is_trail(*start))
++start;
break;
}
......@@ -103,41 +129,15 @@ namespace utf8
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;
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;
......@@ -156,7 +156,7 @@ 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>
......@@ -168,10 +168,10 @@ namespace utf8
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
......
......@@ -68,7 +68,7 @@ namespace internal
template<typename octet_type>
inline bool is_trail(octet_type oc)
{
return ((mask8(oc) >> 6) == 0x2);
return ((utf8::internal::mask8(oc) >> 6) == 0x2);
}
template <typename u16>
......@@ -92,14 +92,14 @@ namespace internal
template <typename u32>
inline bool is_code_point_valid(u32 cp)
{
return (cp <= CODE_POINT_MAX && !is_surrogate(cp));
return (cp <= CODE_POINT_MAX && !utf8::internal::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);
uint8_t lead = utf8::internal::mask8(*lead_it);
if (lead < 0x80)
return 1;
else if ((lead >> 5) == 0x6)
......@@ -133,124 +133,98 @@ namespace internal
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
/// Helper for get_sequence_x
template <typename octet_iterator>
utf_error get_sequence_1(octet_iterator& it, octet_iterator end, uint32_t* code_point)
utf_error increase_safely(octet_iterator& it, octet_iterator end)
{
if (it != end) {
if (code_point)
*code_point = mask8(*it);
if (++it == end)
return NOT_ENOUGH_ROOM;
if (!utf8::internal::is_trail(*it))
return INCOMPLETE_SEQUENCE;
return UTF8_OK;
}
#define UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(IT, END) {utf_error ret = increase_safely(IT, END); if (ret != UTF8_OK) return ret;}
/// 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)
return NOT_ENOUGH_ROOM;
code_point = utf8::internal::mask8(*it);
return UTF8_OK;
}
template <typename octet_iterator>
utf_error get_sequence_2(octet_iterator& it, octet_iterator end, uint32_t* code_point)
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)
return NOT_ENOUGH_ROOM;
if (it != end) {
uint32_t cp = mask8(*it);
if (++it != end) {
if (is_trail(*it)) {
cp = ((cp << 6) & 0x7ff) + ((*it) & 0x3f);
code_point = utf8::internal::mask8(*it);
if (code_point)
*code_point = cp;
ret_code = UTF8_OK;
}
else
ret_code = INCOMPLETE_SEQUENCE;
}
else
ret_code = NOT_ENOUGH_ROOM;
}
UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
return ret_code;
code_point = ((code_point << 6) & 0x7ff) + ((*it) & 0x3f);
return UTF8_OK;
}
template <typename octet_iterator>
utf_error get_sequence_3(octet_iterator& it, octet_iterator end, uint32_t* code_point)
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;
}
if (it == end)
return NOT_ENOUGH_ROOM;
code_point = utf8::internal::mask8(*it);
UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
return ret_code;
code_point = ((code_point << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff);
UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
code_point += (*it) & 0x3f;
return UTF8_OK;
}
template <typename octet_iterator>
utf_error get_sequence_4(octet_iterator& it, octet_iterator end, uint32_t* code_point)
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;
}
if (it == end)
return NOT_ENOUGH_ROOM;
code_point = utf8::internal::mask8(*it);
UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
code_point = ((code_point << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff);
UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
code_point += (utf8::internal::mask8(*it) << 6) & 0xfff;
UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)
code_point += (*it) & 0x3f;
return ret_code;
return UTF8_OK;
}
#undef UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR
template <typename octet_iterator>
utf_error validate_next(octet_iterator& it, octet_iterator end, uint32_t* code_point)
utf_error validate_next(octet_iterator& it, octet_iterator end, uint32_t& code_point)
{
if (it == end)
return NOT_ENOUGH_ROOM;
// 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;
......@@ -258,34 +232,33 @@ namespace internal
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;
const octet_difference_type length = utf8::internal::sequence_length(it);
// Now that we have a valid sequence length, get trail octets and calculate the code point
// 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);
err = utf8::internal::get_sequence_1(it, end, cp);
break;
case 2:
err = get_sequence_2(it, end, &cp);
err = utf8::internal::get_sequence_2(it, end, cp);
break;
case 3:
err = get_sequence_3(it, end, &cp);
err = utf8::internal::get_sequence_3(it, end, cp);
break;
case 4:
err = get_sequence_4(it, end, &cp);
err = utf8::internal::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)){
if (utf8::internal::is_code_point_valid(cp)) {
if (!utf8::internal::is_overlong_sequence(cp, length)){
// Passed! Return here.
if (code_point)
*code_point = cp;
code_point = cp;
++it;
return UTF8_OK;
}
......@@ -303,7 +276,8 @@ namespace internal
template <typename octet_iterator>
inline utf_error validate_next(octet_iterator& it, octet_iterator end) {
return validate_next(it, end, nullptr);
uint32_t ignored;
return utf8::internal::validate_next(it, end, ignored);
}
} // namespace internal
......@@ -318,7 +292,7 @@ namespace internal
{
octet_iterator result = start;
while (result != end) {
internal::utf_error err_code = internal::validate_next(result, end);
utf8::internal::utf_error err_code = utf8::internal::validate_next(result, end);
if (err_code != internal::UTF8_OK)
return result;
}
......@@ -328,16 +302,16 @@ namespace internal
template <typename octet_iterator>
inline bool is_valid(octet_iterator start, octet_iterator end)
{
return (find_invalid(start, end) == end);
return (utf8::find_invalid(start, end) == end);
}
template <typename octet_iterator>
inline bool starts_with_bom (octet_iterator it, octet_iterator end)