diff options
Diffstat (limited to 'dep/utf8cpp/utf8/checked.h')
| -rw-r--r-- | dep/utf8cpp/utf8/checked.h | 118 |
1 files changed, 61 insertions, 57 deletions
diff --git a/dep/utf8cpp/utf8/checked.h b/dep/utf8cpp/utf8/checked.h index a1d2035364d..3b00644444c 100644 --- a/dep/utf8cpp/utf8/checked.h +++ b/dep/utf8cpp/utf8/checked.h @@ -34,7 +34,7 @@ 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. @@ -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); + utf8::append (replacement, out); ++start; break; case internal::INCOMPLETE_SEQUENCE: case internal::OVERLONG_SEQUENCE: case internal::INVALID_CODE_POINT: - append (replacement, 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; @@ -156,18 +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) + throw not_enough_room(); + octet_iterator end = it; - while (internal::is_trail(*(--it))) - if (it < start) + // Go back until we hit either a lead octet or start + while (utf8::internal::is_trail(*(--it))) + if (it == start) throw invalid_utf8(*it); // error - no lead byte in the sequence - octet_iterator temp = it; - return next(temp, end); + return utf8::peek_next(it, end); } /// Deprecated in versions that include "prior" @@ -175,18 +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> @@ -195,7 +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; } @@ -203,12 +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)); @@ -218,10 +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; } @@ -230,7 +234,7 @@ namespace utf8 u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result) { while (start != end) { - uint32_t cp = next(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); @@ -245,7 +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; } @@ -254,7 +258,7 @@ namespace utf8 u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result) { while (start != end) - (*result++) = next(start, end); + (*result++) = utf8::next(start, end); return result; } @@ -280,7 +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 { @@ -294,24 +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 |