commit f7d6a4b00154d30386cb5c559ff5df63e843df4f Author: Daniel Swanson Date: Fri Jun 11 12:40:53 2021 -0500 unbundle utfcpp diff --git a/CMakeLists.txt b/CMakeLists.txt index faf4e38..3f42928 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -102,7 +102,6 @@ if(WIN32) add_definitions(-D_SECURE_SCL=0 -D_ITERATOR_DEBUG_LEVEL=0 -D_CRT_SECURE_NO_DEPRECATE -DWIN32_LEAN_AND_MEAN -DVC_EXTRALEAN -DNOMINMAX) add_definitions(-DSTDC_HEADERS -DREGEX_MALLOC) include_directories("lttoolbox/win32") - include_directories("utf8") else() add_definitions(-D_POSIX_C_SOURCE=200112 -D_GNU_SOURCE) endif() diff --git a/Makefile.am b/Makefile.am index e07e620..13a7779 100644 --- a/Makefile.am +++ b/Makefile.am @@ -10,7 +10,7 @@ endif pkgconfigdir = $(libdir)/pkgconfig pkgconfig_DATA = lttoolbox.pc -EXTRA_DIST=autogen.sh utf8 tests +EXTRA_DIST=autogen.sh tests # TODO: the below will use python3 if you run it on Arch Linux with no python2 installed test: tests/run_tests.py diff --git a/README b/README index d40d0ae..a27e04f 100644 --- a/README +++ b/README @@ -51,6 +51,8 @@ Requirements: * g++ >= 2.95 * GNU make * libxml2 >= 2.6.17 +* ICU +* utfcpp Building & installing: diff --git a/configure.ac b/configure.ac index ab37b3d..a84c06f 100644 --- a/configure.ac +++ b/configure.ac @@ -47,6 +47,7 @@ AC_CHECK_LIB(xml2, xmlReaderForFile) # Checks for header files. AC_HEADER_STDC AC_CHECK_HEADERS([stdlib.h string.h unistd.h stddef.h]) +AC_CHECK_HEADER([utf8.h], [], [AC_MSG_ERROR([You don't have utfcpp installed.])]) # Checks for typedefs, structures, and compiler characteristics. AC_HEADER_STDBOOL diff --git a/lttoolbox/Makefile.am b/lttoolbox/Makefile.am index fa05947..fdb906d 100644 --- a/lttoolbox/Makefile.am +++ b/lttoolbox/Makefile.am @@ -50,7 +50,7 @@ lt_tmxproc_SOURCES = lt_tmxproc.cc man_MANS = lt-comp.1 lt-expand.1 lt-proc.1 lt-tmxcomp.1 lt-tmxproc.1 lt-print.1 lt-trim.1 -INCLUDES = -I$(top_srcdir) -I$(top_srcdir)/utf8 $(LIBXML_CFLAGS) $(ICU_CFLAGS) +INCLUDES = -I$(top_srcdir) $(LIBXML_CFLAGS) $(ICU_CFLAGS) CLEANFILES = *~ EXTRA_DIST = dix.dtd dix.rng dix.rnc acx.rng xsd/dix.xsd xsd/acx.xsd $(man_MANS) diff --git a/lttoolbox/ustring.h b/lttoolbox/ustring.h index fd7ea13..323726f 100644 --- a/lttoolbox/ustring.h +++ b/lttoolbox/ustring.h @@ -20,7 +20,7 @@ #include #include -#include +#include #include #include diff --git a/python/setup.py.in b/python/setup.py.in index 7a9e84c..14f64ab 100644 --- a/python/setup.py.in +++ b/python/setup.py.in @@ -29,7 +29,7 @@ lttoolbox_module = Extension( name='_lttoolbox', sources=get_sources(), swig_opts = ["-c++", "-I@top_srcdir@", "-Wall"], - include_dirs=['@top_srcdir@', '/usr/include/libxml2', '@top_srcdir@/utf8'], + include_dirs=['@top_srcdir@', '/usr/include/libxml2'], library_dirs=['/usr/include/libxml2'], extra_compile_args='@CXXFLAGS@'.split(), extra_link_args=['-lxml2'], diff --git a/utf8/utf8.h b/utf8/utf8.h deleted file mode 100644 index c2c85d6..0000000 --- a/utf8/utf8.h +++ /dev/null @@ -1,38 +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" - -#if __cplusplus >= 201103L // C++ 11 or later -#include "utf8/cpp11.h" -#endif // C++ 11 or later - -#endif // header guard diff --git a/utf8/utf8/checked.h b/utf8/utf8/checked.h deleted file mode 100644 index c31861e..0000000 --- a/utf8/utf8/checked.h +++ /dev/null @@ -1,324 +0,0 @@ -// Copyright 2006-2016 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 codepoint) : cp(codepoint) {} - 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: - out = utf8::append (replacement, out); - start = end; - break; - 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 - 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); - } - - template - void advance (octet_iterator& it, distance_type n, octet_iterator 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 - 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& 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"); - } - // 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/utf8/utf8/core.h b/utf8/utf8/core.h deleted file mode 100644 index b1f1eff..0000000 --- a/utf8/utf8/core.h +++ /dev/null @@ -1,321 +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 = 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/utf8/utf8/cpp11.h b/utf8/utf8/cpp11.h deleted file mode 100644 index 77771ff..0000000 --- a/utf8/utf8/cpp11.h +++ /dev/null @@ -1,103 +0,0 @@ -// 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/utf8/utf8/unchecked.h b/utf8/utf8/unchecked.h deleted file mode 100644 index 5ca6eb7..0000000 --- a/utf8/utf8/unchecked.h +++ /dev/null @@ -1,269 +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 : 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 -