UtfIterator<C> str_find_last_not_of(const UtfIterator<C>& b, const UtfIterator<C>& e,
const basic_string<C>& target) {
auto u_target = to_utf32(target);
auto i = e;
while (i != b) {
--i;
if (u_target.find(*i) == npos)
return i;
}
return e;
}
std::pair<Iterator, boost::optional<char32_t>> decode(Iterator p, Iterator pe)
{
return to_utf32(p, pe);
}
std::u32string read_with_bom(std::istream & src)
{
enum encoding {
encoding_utf32be = 0,
encoding_utf32le,
encoding_utf16be,
encoding_utf16le,
encoding_utf8,
encoding_ascii,
};
std::vector<std::string> boms = {
std::string("\x00\x00\xFE\xFF", 4),
std::string("\xFF\xFE\x00\x00", 4),
std::string("\xFE\xFF", 2),
std::string("\xFF\xFE", 2),
std::string("\xEF\xBB\xBF", 3)
};
std::string buffer((std::istreambuf_iterator<char>(src)), std::istreambuf_iterator<char>());
encoding enc = encoding_ascii;
for (unsigned int i = 0; i < boms.size(); ++i) {
std::string testBom = boms[i];
if (buffer.compare(0, testBom.length(), testBom) == 0) {
enc = encoding(i);
buffer = buffer.substr(testBom.length());
break;
}
}
switch (enc) {
case encoding_utf32be:
{
if (buffer.length() % 4 != 0) {
throw std::logic_error("size in bytes must be a multiple of 4");
}
int count = buffer.length() / 4;
std::u32string temp = std::u32string(count, 0);
for (int i = 0; i < count; ++i) {
temp[i] = static_cast<char32_t>(buffer[i * 4 + 3] << 0 | buffer[i * 4 + 2] << 8 | buffer[i * 4 + 1] << 16 | buffer[i * 4 + 0] << 24);
}
return temp;
}
case encoding_utf32le:
{
if (buffer.length() % 4 != 0) {
throw std::logic_error("size in bytes must be a multiple of 4");
}
int count = buffer.length() / 4;
std::u32string temp = std::u32string(count, 0);
for (int i = 0; i < count; ++i) {
temp[i] = static_cast<char32_t>(buffer[i * 4 + 0] << 0 | buffer[i * 4 + 1] << 8 | buffer[i * 4 + 2] << 16 | buffer[i * 4 + 3] << 24);
}
return temp;
}
case encoding_utf16be:
{
if (buffer.length() % 2 != 0) {
throw std::logic_error("size in bytes must be a multiple of 2");
}
int count = buffer.length() / 2;
std::u16string temp = std::u16string(count, 0);
for (int i = 0; i < count; ++i) {
temp[i] = static_cast<char16_t>(buffer[i * 2 + 1] << 0 | buffer[i * 2 + 0] << 8);
}
return to_utf32(temp);
}
case encoding_utf16le:
{
if (buffer.length() % 2 != 0) {
throw std::logic_error("size in bytes must be a multiple of 2");
}
int count = buffer.length() / 2;
std::u16string temp = std::u16string(count, 0);
for (int i = 0; i < count; ++i) {
temp[i] = static_cast<char16_t>(buffer[i * 2 + 0] << 0 | buffer[i * 2 + 1] << 8);
}
return to_utf32(temp);
}
default:
return to_utf32(buffer);
}
}
std::u32string to_utf32(const std::u16string &s) {
return to_utf32(to_utf8(s));
}
UtfIterator<C> str_find_first_of(const UtfIterator<C>& b, const UtfIterator<C>& e,
const basic_string<C>& target) {
auto u_target = to_utf32(target);
return std::find_if(b, e,
[&] (char32_t c) { return u_target.find(c) != npos; });
}
UtfIterator<C> str_search(const UtfIterator<C>& b, const UtfIterator<C>& e,
const basic_string<C>& target) {
auto u_target = to_utf32(target);
return std::search(b, e, u_target.begin(), u_target.end());
}
