aboutsummaryrefslogtreecommitdiffstats
path: root/lib/charset/utf8/unchecked.h
diff options
context:
space:
mode:
Diffstat (limited to 'lib/charset/utf8/unchecked.h')
-rw-r--r--lib/charset/utf8/unchecked.h163
1 files changed, 111 insertions, 52 deletions
diff --git a/lib/charset/utf8/unchecked.h b/lib/charset/utf8/unchecked.h
index cb24271..65d4948 100644
--- a/lib/charset/utf8/unchecked.h
+++ b/lib/charset/utf8/unchecked.h
@@ -32,37 +32,79 @@ DEALINGS IN THE SOFTWARE.
namespace utf8
{
- namespace unchecked
+ namespace unchecked
{
template <typename octet_iterator>
- octet_iterator append(uint32_t cp, octet_iterator result)
+ octet_iterator append(utfchar32_t cp, octet_iterator result)
{
- 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 internal::append(cp, result);
+ }
+
+ template <typename word_iterator>
+ word_iterator append16(utfchar32_t cp, word_iterator result)
+ {
+ return internal::append16(cp, result);
+ }
+
+ template <typename octet_iterator, typename output_iterator>
+ output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, utfchar32_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:
+ out = utf8::unchecked::append(replacement, out);
+ start = end;
+ break;
+ case internal::INVALID_LEAD:
+ out = utf8::unchecked::append(replacement, out);
+ ++start;
+ break;
+ case internal::INCOMPLETE_SEQUENCE:
+ case internal::OVERLONG_SEQUENCE:
+ case internal::INVALID_CODE_POINT:
+ out = utf8::unchecked::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 utfchar32_t replacement_marker = utf8::internal::mask16(0xfffd);
+ return utf8::unchecked::replace_invalid(start, end, out, replacement_marker);
+ }
+
+ inline std::string replace_invalid(const std::string& s, utfchar32_t replacement)
+ {
+ std::string result;
+ replace_invalid(s.begin(), s.end(), std::back_inserter(result), replacement);
+ return result;
+ }
+
+ inline std::string replace_invalid(const std::string& s)
+ {
+ std::string result;
+ replace_invalid(s.begin(), s.end(), std::back_inserter(result));
return result;
}
template <typename octet_iterator>
- uint32_t next(octet_iterator& it)
+ utfchar32_t next(octet_iterator& it)
{
- uint32_t cp = utf8::internal::mask8(*it);
- typename std::iterator_traits<octet_iterator>::difference_type length = utf8::internal::sequence_length(it);
- switch (length) {
+ utfchar32_t cp = utf8::internal::mask8(*it);
+ switch (utf8::internal::sequence_length(it)) {
case 1:
break;
case 2:
@@ -85,40 +127,50 @@ namespace utf8
break;
}
++it;
- return cp;
+ return cp;
}
template <typename octet_iterator>
- uint32_t peek_next(octet_iterator it)
+ utfchar32_t peek_next(octet_iterator it)
{
- return utf8::unchecked::next(it);
+ return utf8::unchecked::next(it);
}
- template <typename octet_iterator>
- uint32_t prior(octet_iterator& it)
+ template <typename word_iterator>
+ utfchar32_t next16(word_iterator& it)
{
- while (utf8::internal::is_trail(*(--it))) ;
- octet_iterator temp = it;
- return utf8::unchecked::next(temp);
+ utfchar32_t cp = utf8::internal::mask16(*it++);
+ if (utf8::internal::is_lead_surrogate(cp))
+ return (cp << 10) + *it++ + utf8::internal::SURROGATE_OFFSET;
+ return cp;
}
- // Deprecated in versions that include prior, but only for the sake of consistency (see utf8::previous)
template <typename octet_iterator>
- inline uint32_t previous(octet_iterator& it)
+ utfchar32_t prior(octet_iterator& it)
{
- return utf8::unchecked::prior(it);
+ while (utf8::internal::is_trail(*(--it))) ;
+ octet_iterator temp = it;
+ return utf8::unchecked::next(temp);
}
template <typename octet_iterator, typename distance_type>
- void advance (octet_iterator& it, distance_type n)
+ void advance(octet_iterator& it, distance_type n)
{
- for (distance_type i = 0; i < n; ++i)
- utf8::unchecked::next(it);
+ const distance_type zero(0);
+ if (n < zero) {
+ // backward
+ for (distance_type i = n; i < zero; ++i)
+ utf8::unchecked::prior(it);
+ } else {
+ // forward
+ for (distance_type i = zero; i < n; ++i)
+ utf8::unchecked::next(it);
+ }
}
template <typename octet_iterator>
typename std::iterator_traits<octet_iterator>::difference_type
- distance (octet_iterator first, octet_iterator last)
+ distance(octet_iterator first, octet_iterator last)
{
typename std::iterator_traits<octet_iterator>::difference_type dist;
for (dist = 0; first < last; ++dist)
@@ -127,37 +179,39 @@ namespace utf8
}
template <typename u16bit_iterator, typename octet_iterator>
- octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result)
- {
+ octet_iterator utf16to8(u16bit_iterator start, u16bit_iterator end, octet_iterator result)
+ {
while (start != end) {
- uint32_t cp = utf8::internal::mask16(*start++);
- // Take care of surrogate pairs first
+ utfchar32_t cp = utf8::internal::mask16(*start++);
+ // Take care of surrogate pairs first
if (utf8::internal::is_lead_surrogate(cp)) {
- uint32_t trail_surrogate = utf8::internal::mask16(*start++);
+ if (start == end)
+ return result;
+ utfchar32_t trail_surrogate = utf8::internal::mask16(*start++);
cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET;
}
result = utf8::unchecked::append(cp, result);
}
- return result;
+ return result;
}
template <typename u16bit_iterator, typename octet_iterator>
- u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result)
+ u16bit_iterator utf8to16(octet_iterator start, octet_iterator end, u16bit_iterator result)
{
while (start < end) {
- uint32_t cp = utf8::unchecked::next(start);
+ utfchar32_t cp = utf8::unchecked::next(start);
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);
+ *result++ = static_cast<utfchar16_t>((cp >> 10) + internal::LEAD_OFFSET);
+ *result++ = static_cast<utfchar16_t>((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN);
}
else
- *result++ = static_cast<uint16_t>(cp);
+ *result++ = static_cast<utfchar16_t>(cp);
}
return result;
}
template <typename octet_iterator, typename u32bit_iterator>
- octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result)
+ octet_iterator utf32to8(u32bit_iterator start, u32bit_iterator end, octet_iterator result)
{
while (start != end)
result = utf8::unchecked::append(*(start++), result);
@@ -166,7 +220,7 @@ namespace utf8
}
template <typename octet_iterator, typename u32bit_iterator>
- u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result)
+ u32bit_iterator utf8to32(octet_iterator start, octet_iterator end, u32bit_iterator result)
{
while (start < end)
(*result++) = utf8::unchecked::next(start);
@@ -176,14 +230,19 @@ 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;
public:
+ typedef utfchar32_t value_type;
+ typedef utfchar32_t* pointer;
+ typedef utfchar32_t& reference;
+ typedef std::ptrdiff_t difference_type;
+ typedef std::bidirectional_iterator_tag iterator_category;
iterator () {}
explicit iterator (const octet_iterator& octet_it): it(octet_it) {}
// the default "big three" are OK
octet_iterator base () const { return it; }
- uint32_t operator * () const
+ utfchar32_t operator * () const
{
octet_iterator temp = it;
return utf8::unchecked::next(temp);
generated by cgit v1.2.3 (git 2.39.1) at 2024-09-25 21:13:41 +0000