From 995ab805ff31681c2dfbc2c02d0e142560ee77d2 Mon Sep 17 00:00:00 2001 From: "Arthur (fuj1n) Uzulin" Date: Mon, 17 Aug 2020 17:54:48 +1000 Subject: [PATCH] Update utf8cpp to fix use of C++17 deprecated feature --- contrib/utf8cpp/source/utf8/checked.h | 62 +++++++------- contrib/utf8cpp/source/utf8/core.h | 43 ++++++---- contrib/utf8cpp/source/utf8/cpp11.h | 103 ++++++++++++++++++++++++ contrib/utf8cpp/source/utf8/unchecked.h | 78 ++++++++++++++---- 4 files changed, 225 insertions(+), 61 deletions(-) create mode 100644 contrib/utf8cpp/source/utf8/cpp11.h diff --git a/contrib/utf8cpp/source/utf8/checked.h b/contrib/utf8cpp/source/utf8/checked.h index 133115513..648636e46 100644 --- a/contrib/utf8cpp/source/utf8/checked.h +++ b/contrib/utf8cpp/source/utf8/checked.h @@ -1,4 +1,4 @@ -// Copyright 2006 Nemanja Trifunovic +// Copyright 2006-2016 Nemanja Trifunovic /* Permission is hereby granted, free of charge, to any person or organization @@ -41,8 +41,8 @@ namespace utf8 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"; } + invalid_code_point(uint32_t codepoint) : cp(codepoint) {} + virtual const char* what() const NOEXCEPT OVERRIDE { return "Invalid code point"; } uint32_t code_point() const {return cp;} }; @@ -50,7 +50,7 @@ namespace utf8 uint8_t u8; public: invalid_utf8 (uint8_t u) : u8(u) {} - virtual const char* what() const throw() { return "Invalid UTF-8"; } + virtual const char* what() const NOEXCEPT OVERRIDE { return "Invalid UTF-8"; } uint8_t utf8_octet() const {return u8;} }; @@ -58,13 +58,13 @@ namespace utf8 uint16_t u16; public: invalid_utf16 (uint16_t u) : u16(u) {} - virtual const char* what() const throw() { return "Invalid UTF-16"; } + virtual const char* what() const NOEXCEPT OVERRIDE { 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"; } + virtual const char* what() const NOEXCEPT OVERRIDE { return "Not enough space"; } }; /// The library API - functions intended to be called by the users @@ -107,7 +107,9 @@ namespace utf8 *out++ = *it; break; case internal::NOT_ENOUGH_ROOM: - throw not_enough_room(); + out = utf8::append (replacement, out); + start = end; + break; case internal::INVALID_LEAD: out = utf8::append (replacement, out); ++start; @@ -174,23 +176,19 @@ namespace utf8 return utf8::peek_next(it, end); } - /// Deprecated in versions that include "prior" - template - 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 void advance (octet_iterator& it, distance_type n, octet_iterator end) { - for (distance_type i = 0; i < n; ++i) - utf8::next(it, end); + const distance_type zero(0); + if (n < zero) { + // backward + for (distance_type i = n; i < zero; ++i) + utf8::prior(it, end); + } else { + // forward + for (distance_type i = zero; i < n; ++i) + utf8::next(it, end); + } } template @@ -233,7 +231,7 @@ namespace utf8 template u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result) { - while (start != end) { + while (start < end) { uint32_t cp = utf8::next(start, end); if (cp > 0xffff) { //make a surrogate pair *result++ = static_cast((cp >> 10) + internal::LEAD_OFFSET); @@ -257,7 +255,7 @@ namespace utf8 template u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result) { - while (start != end) + while (start < end) (*result++) = utf8::next(start, end); return result; @@ -265,16 +263,21 @@ namespace utf8 // The iterator class template - class iterator : public std::iterator { + class iterator { octet_iterator it; octet_iterator range_start; octet_iterator range_end; 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, - const octet_iterator& range_start, - const octet_iterator& range_end) : - it(octet_it), range_start(range_start), range_end(range_end) + const octet_iterator& rangestart, + const octet_iterator& rangeend) : + it(octet_it), range_start(rangestart), range_end(rangeend) { if (it < range_start || it > range_end) throw std::out_of_range("Invalid utf-8 iterator position"); @@ -322,6 +325,9 @@ namespace utf8 } // namespace utf8 +#if UTF_CPP_CPLUSPLUS >= 201103L // C++ 11 or later +#include "cpp11.h" +#endif // C++ 11 or later + #endif //header guard - diff --git a/contrib/utf8cpp/source/utf8/core.h b/contrib/utf8cpp/source/utf8/core.h index 693d388c0..244e89231 100644 --- a/contrib/utf8cpp/source/utf8/core.h +++ b/contrib/utf8cpp/source/utf8/core.h @@ -30,6 +30,23 @@ DEALINGS IN THE SOFTWARE. #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 @@ -49,8 +66,8 @@ namespace internal 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 = LEAD_SURROGATE_MIN - (0x10000 >> 10); - const uint32_t SURROGATE_OFFSET = 0x10000u - (LEAD_SURROGATE_MIN << 10) - TRAIL_SURROGATE_MIN; + 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; @@ -142,7 +159,7 @@ namespace internal if (!utf8::internal::is_trail(*it)) return INCOMPLETE_SEQUENCE; - + return UTF8_OK; } @@ -165,7 +182,7 @@ namespace internal { if (it == end) return NOT_ENOUGH_ROOM; - + code_point = utf8::internal::mask8(*it); UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) @@ -222,6 +239,9 @@ namespace internal 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; @@ -234,7 +254,7 @@ namespace internal // Get trail octets and calculate the code point utf_error err = UTF8_OK; switch (length) { - case 0: + case 0: return INVALID_LEAD; case 1: err = utf8::internal::get_sequence_1(it, end, cp); @@ -310,18 +330,7 @@ namespace internal ((it != end) && (utf8::internal::mask8(*it++)) == bom[1]) && ((it != end) && (utf8::internal::mask8(*it)) == bom[2]) ); - } - - //Deprecated in release 2.3 - template - inline bool is_bom (octet_iterator it) - { - return ( - (utf8::internal::mask8(*it++)) == bom[0] && - (utf8::internal::mask8(*it++)) == bom[1] && - (utf8::internal::mask8(*it)) == bom[2] - ); - } + } } // namespace utf8 #endif // header guard diff --git a/contrib/utf8cpp/source/utf8/cpp11.h b/contrib/utf8cpp/source/utf8/cpp11.h new file mode 100644 index 000000000..d93961b04 --- /dev/null +++ b/contrib/utf8cpp/source/utf8/cpp11.h @@ -0,0 +1,103 @@ +// Copyright 2018 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_a184c22c_d012_11e8_a8d5_f2801f1b9fd1 +#define UTF8_FOR_CPP_a184c22c_d012_11e8_a8d5_f2801f1b9fd1 + +#include "checked.h" +#include + +namespace utf8 +{ + + inline void append(char32_t cp, std::string& s) + { + append(uint32_t(cp), std::back_inserter(s)); + } + + inline std::string utf16to8(const std::u16string& s) + { + std::string result; + utf16to8(s.begin(), s.end(), std::back_inserter(result)); + return result; + } + + inline std::u16string utf8to16(const std::string& s) + { + std::u16string result; + utf8to16(s.begin(), s.end(), std::back_inserter(result)); + return result; + } + + inline std::string utf32to8(const std::u32string& s) + { + std::string result; + utf32to8(s.begin(), s.end(), std::back_inserter(result)); + return result; + } + + inline std::u32string utf8to32(const std::string& s) + { + std::u32string result; + utf8to32(s.begin(), s.end(), std::back_inserter(result)); + return result; + } + + inline std::size_t find_invalid(const std::string& s) + { + std::string::const_iterator invalid = find_invalid(s.begin(), s.end()); + return (invalid == s.end()) ? std::string::npos : (invalid - s.begin()); + } + + inline bool is_valid(const std::string& s) + { + return is_valid(s.begin(), s.end()); + } + + inline std::string replace_invalid(const std::string& s, char32_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; + } + + inline bool starts_with_bom(const std::string& s) + { + return starts_with_bom(s.begin(), s.end()); + } + +} // namespace utf8 + +#endif // header guard + diff --git a/contrib/utf8cpp/source/utf8/unchecked.h b/contrib/utf8cpp/source/utf8/unchecked.h index cb2427166..0e1b51cc7 100644 --- a/contrib/utf8cpp/source/utf8/unchecked.h +++ b/contrib/utf8cpp/source/utf8/unchecked.h @@ -32,13 +32,13 @@ DEALINGS IN THE SOFTWARE. namespace utf8 { - namespace unchecked + namespace unchecked { template octet_iterator append(uint32_t cp, octet_iterator result) { if (cp < 0x80) // one octet - *(result++) = static_cast(cp); + *(result++) = static_cast(cp); else if (cp < 0x800) { // two octets *(result++) = static_cast((cp >> 6) | 0xc0); *(result++) = static_cast((cp & 0x3f) | 0x80); @@ -57,6 +57,46 @@ namespace utf8 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) { @@ -85,13 +125,13 @@ namespace utf8 break; } ++it; - return cp; + return cp; } template uint32_t peek_next(octet_iterator it) { - return utf8::unchecked::next(it); + return utf8::unchecked::next(it); } template @@ -102,18 +142,19 @@ namespace utf8 return utf8::unchecked::next(temp); } - // Deprecated in versions that include prior, but only for the sake of consistency (see utf8::previous) - template - inline uint32_t previous(octet_iterator& it) - { - return utf8::unchecked::prior(it); - } - template 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 @@ -128,7 +169,7 @@ namespace utf8 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 @@ -138,7 +179,7 @@ namespace utf8 } result = utf8::unchecked::append(cp, result); } - return result; + return result; } template @@ -176,9 +217,14 @@ namespace utf8 // The iterator class template - class iterator : public std::iterator { + 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