diff --git a/.gitmodules b/.gitmodules index 75990fad..917fef43 100644 --- a/.gitmodules +++ b/.gitmodules @@ -7,3 +7,6 @@ [submodule "third_party/tinyxml2"] path = third_party/tinyxml2 url = https://github.com/leethomason/tinyxml2/ +[submodule "third_party/utfcpp"] + path = third_party/utfcpp + url = https://github.com/nemtrif/utfcpp diff --git a/third_party/utfcpp b/third_party/utfcpp new file mode 160000 index 00000000..d8b92208 --- /dev/null +++ b/third_party/utfcpp @@ -0,0 +1 @@ +Subproject commit d8b92208fddde08d628004563a1a3614a32cf8c8 diff --git a/third_party/utfcpp/LICENSE b/third_party/utfcpp/LICENSE deleted file mode 100644 index 36b7cd93..00000000 --- a/third_party/utfcpp/LICENSE +++ /dev/null @@ -1,23 +0,0 @@ -Boost Software License - Version 1.0 - August 17th, 2003 - -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. diff --git a/third_party/utfcpp/source/utf8/core.h b/third_party/utfcpp/source/utf8/core.h deleted file mode 100644 index 244e8923..00000000 --- a/third_party/utfcpp/source/utf8/core.h +++ /dev/null @@ -1,338 +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_CORE_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 -#define UTF8_FOR_CPP_CORE_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 - -#include - -// Determine the C++ standard version. -// If the user defines UTF_CPP_CPLUSPLUS, use that. -// Otherwise, trust the unreliable predefined macro __cplusplus - -#if !defined UTF_CPP_CPLUSPLUS - #define UTF_CPP_CPLUSPLUS __cplusplus -#endif - -#if UTF_CPP_CPLUSPLUS >= 201103L // C++ 11 or later - #define OVERRIDE override - #define NOEXCEPT noexcept -#else // C++ 98/03 - #define OVERRIDE - #define NOEXCEPT throw() -#endif // C++ 11 or later - - -namespace utf8 -{ - // The typedefs for 8-bit, 16-bit and 32-bit unsigned integers - // You may need to change them to match your system. - // These typedefs have the same names as ones from cstdint, or boost/cstdint - typedef unsigned char uint8_t; - typedef unsigned short uint16_t; - typedef unsigned int uint32_t; - -// Helper code - not intended to be directly called by the library users. May be changed at any time -namespace internal -{ - // Unicode constants - // Leading (high) surrogates: 0xd800 - 0xdbff - // Trailing (low) surrogates: 0xdc00 - 0xdfff - const uint16_t LEAD_SURROGATE_MIN = 0xd800u; - const uint16_t LEAD_SURROGATE_MAX = 0xdbffu; - const uint16_t TRAIL_SURROGATE_MIN = 0xdc00u; - const uint16_t TRAIL_SURROGATE_MAX = 0xdfffu; - const uint16_t LEAD_OFFSET = 0xd7c0u; // LEAD_SURROGATE_MIN - (0x10000 >> 10) - const uint32_t SURROGATE_OFFSET = 0xfca02400u; // 0x10000u - (LEAD_SURROGATE_MIN << 10) - TRAIL_SURROGATE_MIN - - // Maximum valid value for a Unicode code point - const uint32_t CODE_POINT_MAX = 0x0010ffffu; - - template - inline uint8_t mask8(octet_type oc) - { - return static_cast(0xff & oc); - } - template - inline uint16_t mask16(u16_type oc) - { - return static_cast(0xffff & oc); - } - template - inline bool is_trail(octet_type oc) - { - return ((utf8::internal::mask8(oc) >> 6) == 0x2); - } - - template - inline bool is_lead_surrogate(u16 cp) - { - return (cp >= LEAD_SURROGATE_MIN && cp <= LEAD_SURROGATE_MAX); - } - - template - inline bool is_trail_surrogate(u16 cp) - { - return (cp >= TRAIL_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX); - } - - template - inline bool is_surrogate(u16 cp) - { - return (cp >= LEAD_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX); - } - - template - inline bool is_code_point_valid(u32 cp) - { - return (cp <= CODE_POINT_MAX && !utf8::internal::is_surrogate(cp)); - } - - template - inline typename std::iterator_traits::difference_type - sequence_length(octet_iterator lead_it) - { - uint8_t lead = utf8::internal::mask8(*lead_it); - if (lead < 0x80) - return 1; - else if ((lead >> 5) == 0x6) - return 2; - else if ((lead >> 4) == 0xe) - return 3; - else if ((lead >> 3) == 0x1e) - return 4; - else - return 0; - } - - template - inline bool is_overlong_sequence(uint32_t cp, octet_difference_type length) - { - if (cp < 0x80) { - if (length != 1) - return true; - } - else if (cp < 0x800) { - if (length != 2) - return true; - } - else if (cp < 0x10000) { - if (length != 3) - return true; - } - - return false; - } - - enum utf_error {UTF8_OK, NOT_ENOUGH_ROOM, INVALID_LEAD, INCOMPLETE_SEQUENCE, OVERLONG_SEQUENCE, INVALID_CODE_POINT}; - - /// Helper for get_sequence_x - template - utf_error increase_safely(octet_iterator& it, octet_iterator end) - { - 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 - 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 - utf_error get_sequence_2(octet_iterator& it, octet_iterator end, uint32_t& code_point) - { - 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 << 6) & 0x7ff) + ((*it) & 0x3f); - - return UTF8_OK; - } - - template - utf_error get_sequence_3(octet_iterator& it, octet_iterator end, uint32_t& code_point) - { - 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 << 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 - utf_error get_sequence_4(octet_iterator& it, octet_iterator end, uint32_t& code_point) - { - 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 UTF8_OK; - } - - #undef UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR - - template - 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; - - uint32_t cp = 0; - // Determine the sequence length based on the lead octet - typedef typename std::iterator_traits::difference_type octet_difference_type; - const octet_difference_type length = utf8::internal::sequence_length(it); - - // Get trail octets and calculate the code point - utf_error err = UTF8_OK; - switch (length) { - case 0: - return INVALID_LEAD; - case 1: - err = utf8::internal::get_sequence_1(it, end, cp); - break; - case 2: - err = utf8::internal::get_sequence_2(it, end, cp); - break; - case 3: - err = utf8::internal::get_sequence_3(it, end, cp); - break; - case 4: - err = utf8::internal::get_sequence_4(it, end, cp); - break; - } - - if (err == UTF8_OK) { - // Decoding succeeded. Now, security checks... - if (utf8::internal::is_code_point_valid(cp)) { - if (!utf8::internal::is_overlong_sequence(cp, length)){ - // Passed! Return here. - code_point = cp; - ++it; - return UTF8_OK; - } - else - err = OVERLONG_SEQUENCE; - } - else - err = INVALID_CODE_POINT; - } - - // Failure branch - restore the original value of the iterator - it = original_it; - return err; - } - - template - inline utf_error validate_next(octet_iterator& it, octet_iterator end) { - uint32_t ignored; - return utf8::internal::validate_next(it, end, ignored); - } - -} // namespace internal - - /// The library API - functions intended to be called by the users - - // Byte order mark - const uint8_t bom[] = {0xef, 0xbb, 0xbf}; - - template - octet_iterator find_invalid(octet_iterator start, octet_iterator end) - { - octet_iterator result = start; - while (result != end) { - utf8::internal::utf_error err_code = utf8::internal::validate_next(result, end); - if (err_code != internal::UTF8_OK) - return result; - } - return result; - } - - template - inline bool is_valid(octet_iterator start, octet_iterator end) - { - return (utf8::find_invalid(start, end) == end); - } - - template - inline bool starts_with_bom (octet_iterator it, octet_iterator end) - { - return ( - ((it != end) && (utf8::internal::mask8(*it++)) == bom[0]) && - ((it != end) && (utf8::internal::mask8(*it++)) == bom[1]) && - ((it != end) && (utf8::internal::mask8(*it)) == bom[2]) - ); - } -} // namespace utf8 - -#endif // header guard - - diff --git a/third_party/utfcpp/source/utf8/unchecked.h b/third_party/utfcpp/source/utf8/unchecked.h deleted file mode 100644 index 0e1b51cc..00000000 --- a/third_party/utfcpp/source/utf8/unchecked.h +++ /dev/null @@ -1,274 +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_UNCHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 -#define UTF8_FOR_CPP_UNCHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 - -#include "core.h" - -namespace utf8 -{ - namespace unchecked - { - template - octet_iterator append(uint32_t cp, octet_iterator result) - { - if (cp < 0x80) // one octet - *(result++) = static_cast(cp); - else if (cp < 0x800) { // two octets - *(result++) = static_cast((cp >> 6) | 0xc0); - *(result++) = static_cast((cp & 0x3f) | 0x80); - } - else if (cp < 0x10000) { // three octets - *(result++) = static_cast((cp >> 12) | 0xe0); - *(result++) = static_cast(((cp >> 6) & 0x3f) | 0x80); - *(result++) = static_cast((cp & 0x3f) | 0x80); - } - else { // four octets - *(result++) = static_cast((cp >> 18) | 0xf0); - *(result++) = static_cast(((cp >> 12) & 0x3f)| 0x80); - *(result++) = static_cast(((cp >> 6) & 0x3f) | 0x80); - *(result++) = static_cast((cp & 0x3f) | 0x80); - } - return result; - } - - template - 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: - 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 - 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::unchecked::replace_invalid(start, end, out, replacement_marker); - } - - template - uint32_t next(octet_iterator& it) - { - uint32_t cp = utf8::internal::mask8(*it); - typename std::iterator_traits::difference_type length = utf8::internal::sequence_length(it); - switch (length) { - case 1: - break; - case 2: - it++; - cp = ((cp << 6) & 0x7ff) + ((*it) & 0x3f); - break; - case 3: - ++it; - cp = ((cp << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff); - ++it; - cp += (*it) & 0x3f; - break; - case 4: - ++it; - cp = ((cp << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff); - ++it; - cp += (utf8::internal::mask8(*it) << 6) & 0xfff; - ++it; - cp += (*it) & 0x3f; - break; - } - ++it; - return cp; - } - - template - uint32_t peek_next(octet_iterator it) - { - return utf8::unchecked::next(it); - } - - template - uint32_t prior(octet_iterator& it) - { - while (utf8::internal::is_trail(*(--it))) ; - octet_iterator temp = it; - return utf8::unchecked::next(temp); - } - - template - void advance (octet_iterator& it, distance_type n) - { - 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 std::iterator_traits::difference_type - distance (octet_iterator first, octet_iterator last) - { - typename std::iterator_traits::difference_type dist; - for (dist = 0; first < last; ++dist) - utf8::unchecked::next(first); - return dist; - } - - template - 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)) { - uint32_t trail_surrogate = utf8::internal::mask16(*start++); - cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET; - } - result = utf8::unchecked::append(cp, result); - } - return result; - } - - template - u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result) - { - while (start < end) { - uint32_t cp = utf8::unchecked::next(start); - if (cp > 0xffff) { //make a surrogate pair - *result++ = static_cast((cp >> 10) + internal::LEAD_OFFSET); - *result++ = static_cast((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN); - } - else - *result++ = static_cast(cp); - } - return result; - } - - template - octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result) - { - while (start != end) - result = utf8::unchecked::append(*(start++), result); - - return result; - } - - template - u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result) - { - while (start < end) - (*result++) = utf8::unchecked::next(start); - - return result; - } - - // The iterator class - template - class iterator { - octet_iterator it; - public: - typedef uint32_t value_type; - typedef uint32_t* pointer; - typedef uint32_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 - { - octet_iterator temp = it; - return utf8::unchecked::next(temp); - } - bool operator == (const iterator& rhs) const - { - return (it == rhs.it); - } - bool operator != (const iterator& rhs) const - { - return !(operator == (rhs)); - } - iterator& operator ++ () - { - ::std::advance(it, utf8::internal::sequence_length(it)); - return *this; - } - iterator operator ++ (int) - { - iterator temp = *this; - ::std::advance(it, utf8::internal::sequence_length(it)); - return temp; - } - iterator& operator -- () - { - utf8::unchecked::prior(it); - return *this; - } - iterator operator -- (int) - { - iterator temp = *this; - utf8::unchecked::prior(it); - return temp; - } - }; // class iterator - - } // namespace utf8::unchecked -} // namespace utf8 - - -#endif // header guard -