diff options
Diffstat (limited to 'utf8/checked.h')
| -rw-r--r-- | utf8/checked.h | 327 |
1 files changed, 0 insertions, 327 deletions
diff --git a/utf8/checked.h b/utf8/checked.h deleted file mode 100644 index 1331155..0000000 --- a/utf8/checked.h +++ /dev/null @@ -1,327 +0,0 @@ -// Copyright 2006 Nemanja Trifunovic - -/* -Permission is hereby granted, free of charge, to any person or organization -obtaining a copy of the software and accompanying documentation covered by -this license (the "Software") to use, reproduce, display, distribute, -execute, and transmit the Software, and to prepare derivative works of the -Software, and to permit third-parties to whom the Software is furnished to -do so, all subject to the following: - -The copyright notices in the Software and this entire statement, including -the above license grant, this restriction and the following disclaimer, -must be included in all copies of the Software, in whole or in part, and -all derivative works of the Software, unless such copies or derivative -works are solely in the form of machine-executable object code generated by -a source language processor. - -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT -SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE -FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE, -ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER -DEALINGS IN THE SOFTWARE. -*/ - - -#ifndef UTF8_FOR_CPP_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 -#define UTF8_FOR_CPP_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 - -#include "core.h" -#include <stdexcept> - -namespace utf8 -{ - // Base for the exceptions that may be thrown from the library - 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) {} - virtual const char* what() const throw() { return "Invalid code point"; } - uint32_t code_point() const {return cp;} - }; - - class invalid_utf8 : public exception { - uint8_t u8; - public: - invalid_utf8 (uint8_t u) : u8(u) {} - virtual const char* what() const throw() { return "Invalid UTF-8"; } - uint8_t utf8_octet() const {return u8;} - }; - - class invalid_utf16 : public exception { - uint16_t u16; - public: - invalid_utf16 (uint16_t u) : u16(u) {} - virtual const char* what() const throw() { 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"; } - }; - - /// 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 = 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: - throw not_enough_room(); - case internal::INVALID_LEAD: - out = utf8::append (replacement, out); - ++start; - break; - case internal::INCOMPLETE_SEQUENCE: - case internal::OVERLONG_SEQUENCE: - case internal::INVALID_CODE_POINT: - out = utf8::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 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 = utf8::internal::validate_next(it, end, cp); - switch (err_code) { - case internal::UTF8_OK : - break; - case internal::NOT_ENOUGH_ROOM : - throw not_enough_room(); - case internal::INVALID_LEAD : - case internal::INCOMPLETE_SEQUENCE : - case internal::OVERLONG_SEQUENCE : - throw invalid_utf8(*it); - case internal::INVALID_CODE_POINT : - throw invalid_code_point(cp); - } - return cp; - } - - template <typename octet_iterator> - uint32_t peek_next(octet_iterator it, octet_iterator 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; - // 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 - 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); - } - - template <typename octet_iterator> - typename std::iterator_traits<octet_iterator>::difference_type - distance (octet_iterator first, octet_iterator last) - { - typename std::iterator_traits<octet_iterator>::difference_type dist; - for (dist = 0; first < last; ++dist) - utf8::next(first, last); - return dist; - } - - template <typename u16bit_iterator, typename octet_iterator> - 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 - if (utf8::internal::is_lead_surrogate(cp)) { - if (start != end) { - 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)); - } - else - throw invalid_utf16(static_cast<uint16_t>(cp)); - - } - // Lone trail surrogate - else if (utf8::internal::is_trail_surrogate(cp)) - throw invalid_utf16(static_cast<uint16_t>(cp)); - - result = utf8::append(cp, result); - } - return result; - } - - 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 = 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); - } - else - *result++ = static_cast<uint16_t>(cp); - } - return result; - } - - template <typename octet_iterator, typename u32bit_iterator> - octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result) - { - while (start != end) - result = utf8::append(*(start++), result); - - return result; - } - - template <typename octet_iterator, typename u32bit_iterator> - u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result) - { - while (start != end) - (*result++) = utf8::next(start, end); - - return result; - } - - // The iterator class - template <typename octet_iterator> - class iterator : public std::iterator <std::bidirectional_iterator_tag, uint32_t> { - octet_iterator it; - octet_iterator range_start; - octet_iterator range_end; - public: - 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) - { - if (it < range_start || it > range_end) - throw std::out_of_range("Invalid utf-8 iterator position"); - } - // the default "big three" are OK - octet_iterator base () const { return it; } - uint32_t operator * () const - { - octet_iterator temp = it; - return utf8::next(temp, range_end); - } - bool operator == (const iterator& rhs) const - { - if (range_start != rhs.range_start || range_end != rhs.range_end) - throw std::logic_error("Comparing utf-8 iterators defined with different ranges"); - return (it == rhs.it); - } - bool operator != (const iterator& rhs) const - { - return !(operator == (rhs)); - } - iterator& operator ++ () - { - utf8::next(it, range_end); - return *this; - } - iterator operator ++ (int) - { - iterator temp = *this; - utf8::next(it, range_end); - return temp; - } - iterator& operator -- () - { - utf8::prior(it, range_start); - return *this; - } - iterator operator -- (int) - { - iterator temp = *this; - utf8::prior(it, range_start); - return temp; - } - }; // class iterator - -} // namespace utf8 - -#endif //header guard - - |