diff --git a/Athena.icns b/Athena.icns new file mode 100644 index 0000000..5a30901 Binary files /dev/null and b/Athena.icns differ diff --git a/Athena.ico b/Athena.ico new file mode 100644 index 0000000..80a7e41 Binary files /dev/null and b/Athena.ico differ diff --git a/AthenaCore.pri b/AthenaCore.pri index 2b43eed..20ccd9f 100644 --- a/AthenaCore.pri +++ b/AthenaCore.pri @@ -56,10 +56,6 @@ HEADERS += \ $$PWD/include/LZ77/LZLookupTable.hpp \ $$PWD/include/LZ77/LZType10.hpp \ $$PWD/include/LZ77/LZType11.hpp \ - $$PWD/include/utf8.h \ - $$PWD/include/utf8/checked.h \ - $$PWD/include/utf8/core.h \ - $$PWD/include/utf8/unchecked.h \ $$PWD/include/Athena/FileInfo.hpp \ $$PWD/include/Athena/Dir.hpp \ $$PWD/include/gekko_support.h \ diff --git a/CMakeLists.txt b/CMakeLists.txt index 3f9eacc..3338265 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -4,7 +4,7 @@ project(Athena) add_subdirectory(extern) file(GLOB ATHENA_HEADERS include/Athena/*.hpp) -include_directories(include) +include_directories(include ${LZO_INCLUDE_DIR} ${ZLIB_INCLUDE_DIR}) set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++11") if(WIN32) @@ -135,7 +135,32 @@ add_library(AthenaZelda ) -install(DIRECTORY include DESTINATION include/Athena) +install(DIRECTORY include/ DESTINATION include/Athena) install(TARGETS AthenaCore AthenaSakura AthenaWiiSave AthenaZelda - DESTINATION lib/Athena) + DESTINATION lib) +if(WIN32 AND NOT UNIX) +install(FILES Athena.ico) +endif() + +# CPack settings +include(InstallRequiredSystemLibraries) +set(CPACK_PACKAGE_DESCRIPTION_SUMMARY "Athena") +set(CPACK_PACKAGE_VENDOR "2015 Antidote / Jackoalan") +set(CPACK_PACKAGE_DESCRIPTION_FILE "${CMAKE_CURRENT_SOURCE_DIR}/README.md") +set(CPACK_RESOURCE_FILE_LICENSE "${CMAKE_CURRENT_SOURCE_DIR}/LICENSE") +set(CPACK_PACKAGE_VERSION_MAJOR "2") +set(CPACK_PACKAGE_VERSION_MINOR "0") +set(CPACK_PACKAGE_VERSION_PATCH "0") +set(CPACK_PACKAGE_INSTALL_DIRECTORY "Athena") +if(WIN32 AND NOT UNIX) + # There is a bug in NSI that does not handle full unix paths properly. Make + # sure there is at least one set of four (4) backlasshes. + set(CPACK_PACKAGE_ICON "${CMAKE_CURRENT_SOURCE_DIR}/Athena.ico") + set(CPACK_NSIS_INSTALLED_ICON_NAME "Athena.ico") + set(CPACK_NSIS_DISPLAY_NAME "Athena") + set(CPACK_NSIS_URL_INFO_ABOUT "http://libathena.github.io") + set(CPACK_NSIS_CONTACT "antidote.crk@gmail.com") + set(CPACK_NSIS_MODIFY_PATH ON) +endif() +include(CPack) diff --git a/PKGBUILD b/PKGBUILD index 5346e5f..3a004e5 100644 --- a/PKGBUILD +++ b/PKGBUILD @@ -5,10 +5,10 @@ pkgver=1.1.0.59.g582d2ce pkgrel=1 pkgdesc="Basic cross platform IO library" arch=('i686' 'x86_64') -source=("${pkgname%-*}::git+https://github.com/libAthena/Athena.git") +source=("${pkgname%-*}::git+https://github.com/libAthena/Athena.git#branch=copy-streamers") options=(staticlibs) license="MIT" -makedepends=('git qt5-base sed') +makedepends=('git cmake sed') md5sums=('SKIP') sha256sums=('SKIP') @@ -19,11 +19,12 @@ pkgver() { build() { cd "$srcdir/$_pkgname" - qmake PREFIX="$pkgdir/usr" && make + cmake -DCMAKE_INSTALL_PREFIX="$pkgdir/usr" + make } package() { cd "$srcdir/$_pkgname" - qmake PREFIX="$pkgdir/usr" && make install + make install } diff --git a/extern/lzo/CMakeLists.txt b/extern/lzo/CMakeLists.txt index cb62a79..e37fa85 100644 --- a/extern/lzo/CMakeLists.txt +++ b/extern/lzo/CMakeLists.txt @@ -1,4 +1,6 @@ -add_library(lzo +find_library(LZO_LIB lzo2) +if(LZO_LIB STREQUAL LZO_LIB-NOTFOUND) +add_library(lzo2 src/lzo1.c src/lzo1_99.c src/lzo1a.c @@ -71,3 +73,7 @@ add_library(lzo include/lzo/lzoconf.h include/lzo/lzodefs.h include/lzo/lzoutil.h) +install(DIRECTORY include/lzo DESTINATION include/lzo) +install(TARGETS lzo2 DESTINATION lib) +set(LZO_INCLUDE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/include CACHE PATH "LZO include path" FORCE) +endif() diff --git a/extern/zlib/CMakeLists.txt b/extern/zlib/CMakeLists.txt index 7b74b52..8859108 100644 --- a/extern/zlib/CMakeLists.txt +++ b/extern/zlib/CMakeLists.txt @@ -1,4 +1,6 @@ -add_library(zlib +find_package(ZLIB) +if(NOT ZLIB_FOUND) +add_library(z adler32.c compress.c crc32.c @@ -20,4 +22,8 @@ add_library(zlib trees.h zconf.h zlib.h - zutil.h) \ No newline at end of file + zutil.h) +install(FILES zconf.h zlib.h DESTINATION include) +install(TARGETS z DESTINATION lib) +set(ZLIB_INCLUDE_DIR ${CMAKE_CURRENT_SOURCE_DIR} CACHE PATH "Zlib include path" FORCE) +endif() diff --git a/include/utf8.h b/include/utf8.h deleted file mode 100644 index 4e44514..0000000 --- a/include/utf8.h +++ /dev/null @@ -1,34 +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_2675DCD0_9480_4c0c_B92A_CC14C027B731 -#define UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731 - -#include "utf8/checked.h" -#include "utf8/unchecked.h" - -#endif // header guard diff --git a/include/utf8/checked.h b/include/utf8/checked.h deleted file mode 100644 index 33ee3ec..0000000 --- a/include/utf8/checked.h +++ /dev/null @@ -1,370 +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 - -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 -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(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: - throw not_enough_room(); - - case internal::INVALID_LEAD: - utf8::append(replacement, out); - ++start; - break; - - case internal::INCOMPLETE_SEQUENCE: - case internal::OVERLONG_SEQUENCE: - case internal::INVALID_CODE_POINT: - 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 -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 -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 -uint32_t peek_next(octet_iterator it, octet_iterator end) -{ - return utf8::next(it, end); -} - -template -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 -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); -} - -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::next(first, last); - - 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)) - { - 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(trail_surrogate)); - } - else - throw invalid_utf16(static_cast(cp)); - - } - // Lone trail surrogate - else if (utf8::internal::is_trail_surrogate(cp)) - throw invalid_utf16(static_cast(cp)); - - result = utf8::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::next(start, end); - - 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::append(*(start++), result); - - return result; -} - -template -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 -class iterator : public std::iterator -{ - 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 - - diff --git a/include/utf8/core.h b/include/utf8/core.h deleted file mode 100644 index f50a25c..0000000 --- a/include/utf8/core.h +++ /dev/null @@ -1,347 +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 - -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 = LEAD_SURROGATE_MIN - (0x10000 >> 10); -const uint32_t SURROGATE_OFFSET = 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) -{ - // 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]) - ); -} - -//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/include/utf8/unchecked.h b/include/utf8/unchecked.h deleted file mode 100644 index 1270994..0000000 --- a/include/utf8/unchecked.h +++ /dev/null @@ -1,251 +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 -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); -} - -// 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); -} - -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 : public std::iterator -{ - octet_iterator it; -public: - 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 -