diff --git a/third-party/utf8cpp/.circleci/config.yml b/third-party/utf8cpp/.circleci/config.yml new file mode 100644 index 000000000..2588646d4 --- /dev/null +++ b/third-party/utf8cpp/.circleci/config.yml @@ -0,0 +1,13 @@ +version: 2 + +jobs: + build: + docker: + - image: nemtrif/utf8cpp:3.1.3 + steps: + - checkout + - run: git submodule update --init --recursive --remote + - run: mkdir build + - run: cd build && cmake .. + - run: cd build && cmake --build . + - run: cd build && ctest -VV diff --git a/third-party/utf8cpp/.gitmodules b/third-party/utf8cpp/.gitmodules new file mode 100644 index 000000000..424f86b76 --- /dev/null +++ b/third-party/utf8cpp/.gitmodules @@ -0,0 +1,3 @@ +[submodule "extern/ftest"] + path = extern/ftest + url = https://github.com/nemtrif/ftest diff --git a/third-party/utf8cpp/CMakeLists.txt b/third-party/utf8cpp/CMakeLists.txt index 55073cdaa..c8d4b7a3c 100644 --- a/third-party/utf8cpp/CMakeLists.txt +++ b/third-party/utf8cpp/CMakeLists.txt @@ -1,43 +1,62 @@ cmake_minimum_required (VERSION 3.0.2) -project (utf8cpp VERSION 2.3.6 LANGUAGES CXX) +project (utf8cpp VERSION 3.2.2 LANGUAGES CXX) -option(UTF8_TESTS "Enable tests for UTF8-CPP" On) -option(UTF8_SAMPLES "Enable building samples for UTF8-CPP" On) +if(CMAKE_SOURCE_DIR STREQUAL CMAKE_CURRENT_SOURCE_DIR) + set(IS_ROOT_PROJECT ON) +else() + set(IS_ROOT_PROJECT OFF) +endif() + +option(UTF8_TESTS "Enable tests for UTF8-CPP" ${IS_ROOT_PROJECT}) +option(UTF8_INSTALL "Enable installation for UTF8-CPP" ${IS_ROOT_PROJECT}) +option(UTF8_SAMPLES "Enable building samples for UTF8-CPP" ${IS_ROOT_PROJECT}) add_library(utf8cpp INTERFACE) target_include_directories(utf8cpp INTERFACE - "$" - $ + "$" + $ ) add_library(utf8::cpp ALIAS utf8cpp) -if(WIN32 AND NOT CYGWIN) - set(DEF_INSTALL_CMAKE_DIR CMake) -else() - include(GNUInstallDirs) # define CMAKE_INSTALL_* - set(DEF_INSTALL_CMAKE_DIR ${CMAKE_INSTALL_LIBDIR}/cmake/utf8cpp) +if(UTF8_INSTALL) + include(CMakePackageConfigHelpers) + if(MSVC) + set(DEF_INSTALL_CMAKE_DIR CMake) + else() + include(GNUInstallDirs) # define CMAKE_INSTALL_* + set(DEF_INSTALL_CMAKE_DIR ${CMAKE_INSTALL_LIBDIR}/cmake/utf8cpp) + endif() + + write_basic_package_version_file( + ${CMAKE_CURRENT_BINARY_DIR}/utf8cppConfigVersion.cmake + VERSION ${PROJECT_VERSION} + COMPATIBILITY SameMajorVersion + ) + + configure_package_config_file( + ${PROJECT_SOURCE_DIR}/utf8cppConfig.cmake.in + ${CMAKE_CURRENT_BINARY_DIR}/utf8cppConfig.cmake + INSTALL_DESTINATION ${DEF_INSTALL_CMAKE_DIR} + ) + + install(DIRECTORY source/ DESTINATION include/utf8cpp) + install(TARGETS utf8cpp EXPORT utf8cppTargets) + install(EXPORT utf8cppTargets DESTINATION ${DEF_INSTALL_CMAKE_DIR}) + install( + FILES + ${CMAKE_CURRENT_BINARY_DIR}/utf8cppConfig.cmake + ${CMAKE_CURRENT_BINARY_DIR}/utf8cppConfigVersion.cmake + DESTINATION + ${DEF_INSTALL_CMAKE_DIR} + ) endif() -install(DIRECTORY source/ DESTINATION include/utf8cpp) -install(TARGETS utf8cpp EXPORT utf8cppConfig) -install(EXPORT utf8cppConfig DESTINATION ${DEF_INSTALL_CMAKE_DIR}) - if(UTF8_SAMPLES) - add_executable(utf8reader ${PROJECT_SOURCE_DIR}/test_drivers/utf8reader/utf8reader.cpp) - add_executable(docsample ${PROJECT_SOURCE_DIR}/samples/docsample.cpp) - - target_link_libraries(utf8reader PRIVATE utf8::cpp) - target_link_libraries(docsample PRIVATE utf8::cpp) + add_executable(docsample ${PROJECT_SOURCE_DIR}/samples/docsample.cpp) + target_link_libraries(docsample PRIVATE utf8::cpp) endif() if(UTF8_TESTS) - add_executable(smoke ${PROJECT_SOURCE_DIR}/test_drivers/smoke_test/test.cpp) - add_executable(negative ${PROJECT_SOURCE_DIR}/test_drivers/negative/negative.cpp) - - target_link_libraries(smoke PRIVATE utf8::cpp) - target_link_libraries(negative PRIVATE utf8::cpp) - - enable_testing() - add_test(smoke_test smoke) - add_test(negative_test negative ${PROJECT_SOURCE_DIR}/test_data/negative/utf8_invalid.txt) + enable_testing() + add_subdirectory(tests) endif() diff --git a/third-party/utf8cpp/README.md b/third-party/utf8cpp/README.md index 09996abc8..a519cdb96 100644 --- a/third-party/utf8cpp/README.md +++ b/third-party/utf8cpp/README.md @@ -3,7 +3,7 @@ ## Introduction -Many C++ developers miss an easy and portable way of handling Unicode encoded strings. The original C++ Standard (known as C++98 or C++03) is Unicode agnostic. C++11 provides some support for Unicode on core language and library level: u8, u, and U character and string literals, char16_t and char32_t character types, u16string and u32string library classes, and codecvt support for conversions between Unicode encoding forms. In the meantime, developers use third party libraries like ICU, OS specific capabilities, or simply roll out their own solutions. +C++ developers miss an easy and portable way of handling Unicode encoded strings. The original C++ Standard (known as C++98 or C++03) is Unicode agnostic. C++11 provides some support for Unicode on core language and library level: u8, u, and U character and string literals, char16_t and char32_t character types, u16string and u32string library classes, and codecvt support for conversions between Unicode encoding forms. In the meantime, developers use third party libraries like ICU, OS specific capabilities, or simply roll out their own solutions. In order to easily handle UTF-8 encoded Unicode strings, I came up with a small, C++98 compatible generic library. For anybody used to work with STL algorithms and iterators, it should be easy and natural to use. The code is freely available for any purpose - check out the [license](./LICENSE). The library has been used a lot in the past ten years both in commercial and open-source projects and is considered feature-complete now. If you run into bugs or performance issues, please let me know and I'll do my best to address them. @@ -28,50 +28,78 @@ int main(int argc, char** argv) cout << "\nUsage: docsample filename\n"; return 0; } - const char* test_file_path = argv[1]; - // Open the test file (contains UTF-8 encoded text) + // Open the test file (must be UTF-8 encoded) ifstream fs8(test_file_path); if (!fs8.is_open()) { - cout << "Could not open " << test_file_path << endl; - return 0; + cout << "Could not open " << test_file_path << endl; + return 0; } unsigned line_count = 1; string line; // Play with all the lines in the file while (getline(fs8, line)) { - // check for invalid utf-8 (for a simple yes/no check, there is also utf8::is_valid function) + // check for invalid utf-8 (for a simple yes/no check, there is also utf8::is_valid function) +#if __cplusplus >= 201103L // C++ 11 or later + auto end_it = utf8::find_invalid(line.begin(), line.end()); +#else string::iterator end_it = utf8::find_invalid(line.begin(), line.end()); +#endif // C++ 11 if (end_it != line.end()) { cout << "Invalid UTF-8 encoding detected at line " << line_count << "\n"; cout << "This part is fine: " << string(line.begin(), end_it) << "\n"; } - // Get the line length (at least for the valid part) int length = utf8::distance(line.begin(), end_it); cout << "Length of line " << line_count << " is " << length << "\n"; // Convert it to utf-16 +#if __cplusplus >= 201103L // C++ 11 or later + u16string utf16line = utf8::utf8to16(line); +#else vector utf16line; utf8::utf8to16(line.begin(), end_it, back_inserter(utf16line)); - - // And back to utf-8 +#endif // C++ 11 + // And back to utf-8; +#if __cplusplus >= 201103L // C++ 11 or later + string utf8line = utf8::utf16to8(utf16line); +#else string utf8line; utf8::utf16to8(utf16line.begin(), utf16line.end(), back_inserter(utf8line)); - +#endif // C++ 11 // Confirm that the conversion went OK: if (utf8line != string(line.begin(), end_it)) cout << "Error in UTF-16 conversion at line: " << line_count << "\n"; line_count++; - } + } + return 0; } ``` In the previous code sample, for each line we performed a detection of invalid UTF-8 sequences with `find_invalid`; the number of characters (more precisely - the number of Unicode code points, including the end of line and even BOM if there is one) in each line was determined with a use of `utf8::distance`; finally, we have converted each line to UTF-16 encoding with `utf8to16` and back to UTF-8 with `utf16to8`. +Note a different pattern of usage for old compilers. For instance, this is how we convert +a UTF-8 encoded string to a UTF-16 encoded one with a pre - C++11 compiler: +```cpp + vector utf16line; + utf8::utf8to16(line.begin(), end_it, back_inserter(utf16line)); +``` + +With a more modern compiler, the same operation would look like: +```cpp + u16string utf16line = utf8::utf8to16(line); +``` +If `__cplusplus` macro points to a C++ 11 or later, the library exposes API that takes into +account C++ standard Unicode strings and move semantics. With an older compiler, it is still +possible to use the same functionality, just in a little less convenient way + +In case you do not trust the `__cplusplus` macro or, for instance, do not want to include +the C++ 11 helper functions even with a modern compiler, define `UTF_CPP_CPLUSPLUS` macro +before including `utf8.h` and assign it a value for the standard you want to use - the values are the same as for the `__cplusplus` macro. This can be also useful with compilers that are conservative in setting the `__cplusplus` macro even if they have a good support for a recent standard edition - Microsoft's Visual C++ is one example. + ### Checking if a file contains valid UTF-8 text Here is a function that checks whether the content of a file is valid UTF-8 encoded text without reading the content into the memory: @@ -90,7 +118,7 @@ bool valid_utf8_file(const char* file_name) } ``` -Because the function `utf8::is_valid()` works with input iterators, we were able to pass an `istreambuf_iterator` to it and read the content of the file directly without loading it to the memory first. +Because the function `utf8::is_valid()` works with input iterators, we were able to pass an `istreambuf_iterator` to `it` and read the content of the file directly without loading it to the memory first. Note that other functions that take input iterator arguments can be used in a similar way. For instance, to read the content of a UTF-8 encoded text file and convert the text to UTF-16, just do something like: @@ -113,10 +141,56 @@ void fix_utf8_string(std::string& str) The function will replace any invalid UTF-8 sequence with a Unicode replacement character. There is an overloaded function that enables the caller to supply their own replacement character. + +## Points of interest + +#### Design goals and decisions + +The library was designed to be: + +1. Generic: for better or worse, there are many C++ string classes out there, and the library should work with as many of them as possible. +2. Portable: the library should be portable both accross different platforms and compilers. The only non-portable code is a small section that declares unsigned integers of different sizes: three typedefs. They can be changed by the users of the library if they don't match their platform. The default setting should work for Windows (both 32 and 64 bit), and most 32 bit and 64 bit Unix derivatives. Support for post C++03 language features is included for modern compilers at API level only, so the library should work even with pretty old compilers. +3. Lightweight: follow the "pay only for what you use" guideline. +4. Unintrusive: avoid forcing any particular design or even programming style on the user. This is a library, not a framework. + +#### Alternatives + +In case you want to look into other means of working with UTF-8 strings from C++, here is the list of solutions I am aware of: + +1. [ICU Library](http://icu.sourceforge.net/). It is very powerful, complete, feature-rich, mature, and widely used. Also big, intrusive, non-generic, and doesn't play well with the Standard Library. I definitelly recommend looking at ICU even if you don't plan to use it. +2. C++11 language and library features. Still far from complete, and not easy to use. +3. [Glib::ustring](http://www.gtkmm.org/gtkmm2/docs/tutorial/html/ch03s04.html). A class specifically made to work with UTF-8 strings, and also feel like `std::string`. If you prefer to have yet another string class in your code, it may be worth a look. Be aware of the licensing issues, though. +4. Platform dependent solutions: Windows and POSIX have functions to convert strings from one encoding to another. That is only a subset of what my library offers, but if that is all you need it may be good enough. + + ## Reference ### Functions From utf8 Namespace +#### utf8::append + +Available in version 3.0 and later. Requires a C++ 11 compliant compiler. + +Encodes a 32 bit code point as a UTF-8 sequence of octets and appends the sequence to a UTF-8 string. + +```cpp +void append(char32_t cp, std::string& s); +``` + +`cp`: a code point to append to the string. +`s`: a utf-8 encoded string to append the code point to. + +Example of use: + +```cpp +std::string u; +append(0x0448, u); +assert (u[0] == char(0xd1) && u[1] == char(0x88) && u.length() == 2); +``` + +In case of an invalid code point, a `utf8::invalid_code_point` exception is thrown. + + #### utf8::append Available in version 1.0 and later. @@ -238,39 +312,6 @@ In case `start` is reached before a UTF-8 lead octet is hit, or if an invalid UT In case `start` equals `it`, a `not_enough_room` exception is thrown. -#### utf8::previous - -Deprecated in version 1.02 and later. - -Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it decreases the iterator until it hits the beginning of the previous UTF-8 encoded code point and returns the 32 bits representation of the code point. - -```cpp -template -uint32_t previous(octet_iterator& it, octet_iterator pass_start); -``` - -`octet_iterator`: a random access iterator. -`it`: a reference pointing to an octet within a UTF-8 encoded string. After the function returns, it is decremented to point to the beginning of the previous code point. -`pass_start`: an iterator to the point in the sequence where the search for the beginning of a code point is aborted if no result was reached. It is a safety measure to prevent passing the beginning of the string in the search for a UTF-8 lead octet. -Return value: the 32 bit representation of the previous code point. - -Example of use: - -```cpp -char* twochars = "\xe6\x97\xa5\xd1\x88"; -unsigned char* w = twochars + 3; -int cp = previous (w, twochars - 1); -assert (cp == 0x65e5); -assert (w == twochars); -``` - - -`utf8::previous` is deprecated, and `utf8::prior` should be used instead, although the existing code can continue using this function. The problem is the parameter `pass_start` that points to the position just before the beginning of the sequence. Standard containers don't have the concept of "pass start" and the function can not be used with their iterators. - -`it` will typically point to the beginning of a code point, and `pass_start` will point to the octet just before the beginning of the string to ensure we don't go backwards too far. `it` is decreased until it points to a lead UTF-8 octet, and then the UTF-8 sequence beginning with that octet is decoded to a 32 bit representation and returned. - -In case `pass_start` is reached before a UTF-8 lead octet is hit, or if an invalid UTF-8 sequence is started by the lead octet, an `invalid_utf8` exception is thrown - #### utf8::advance Available in version 1.0 and later. @@ -284,8 +325,8 @@ void advance (octet_iterator& it, distance_type n, octet_iterator end); `octet_iterator`: an input iterator. `distance_type`: an integral type convertible to `octet_iterator`'s difference type. `it`: a reference to an iterator pointing to the beginning of an UTF-8 encoded code point. After the function returns, it is incremented to point to the nth following code point. -`n`: a positive integer that shows how many code points we want to advance. -`end`: end of the UTF-8 sequence to be processed. If `it` gets equal to `end` during the extraction of a code point, an `utf8::not_enough_room` exception is thrown. +`n`: number of code points `it` should be advanced. A negative value means decrement. +`end`: limit of the UTF-8 sequence to be processed. If `n` is positive and `it` gets equal to `end` during the extraction of a code point, an `utf8::not_enough_room` exception is thrown. If `n` is negative and `it` reaches `end` while `it` points t a trail byte of a UTF-8 sequence, a `utf8::invalid_code_point` exception is thrown. Example of use: @@ -294,10 +335,10 @@ char* twochars = "\xe6\x97\xa5\xd1\x88"; unsigned char* w = twochars; advance (w, 2, twochars + 6); assert (w == twochars + 5); +advance (w, -2, twochars); +assert (w == twochars); ``` -This function works only "forward". In case of a negative `n`, there is no effect. - In case of an invalid code point, a `utf8::invalid_code_point` exception is thrown. #### utf8::distance @@ -328,6 +369,54 @@ This function is used to find the length (in code points) of a UTF-8 encoded str In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown. If `last` does not point to the past-of-end of a UTF-8 seqence, a `utf8::not_enough_room` exception is thrown. +#### utf8::utf16to8 + +Available in version 3.0 and later. Requires a C++ 11 compliant compiler. + +Converts a UTF-16 encoded string to UTF-8. + +```cpp +std::string utf16to8(const std::u16string& s); +``` + +`s`: a UTF-16 encoded string. +Return value: A UTF-8 encoded string. + +Example of use: + +```cpp + u16string utf16string = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e}; + string u = utf16to8(utf16string); + assert (u.size() == 10); +``` + +In case of invalid UTF-16 sequence, a `utf8::invalid_utf16` exception is thrown. + +#### utf8::utf16to8 + +Available in version 3.2 and later. Requires a C++ 17 compliant compiler. + +Converts a UTF-16 encoded string to UTF-8. + +```cpp +std::string utf16to8(std::u16string_view s); +``` + +`s`: a UTF-16 encoded string. +Return value: A UTF-8 encoded string. + +Example of use: + +```cpp + u16string utf16string = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e}; + u16string_view utf16stringview(u16string); + string u = utf16to8(utf16string); + assert (u.size() == 10); +``` + +In case of invalid UTF-16 sequence, a `utf8::invalid_utf16` exception is thrown. + + #### utf8::utf16to8 Available in version 1.0 and later. @@ -357,6 +446,57 @@ assert (utf8result.size() == 10); In case of invalid UTF-16 sequence, a `utf8::invalid_utf16` exception is thrown. +#### utf8::utf8to16 + +Available in version 3.0 and later. Requires a C++ 11 compliant compiler. + +Converts an UTF-8 encoded string to UTF-16. + +```cpp +std::u16string utf8to16(const std::string& s); +``` + +`s`: an UTF-8 encoded string to convert. +Return value: A UTF-16 encoded string + +Example of use: + +```cpp +string utf8_with_surrogates = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"; +u16string utf16result = utf8to16(utf8_with_surrogates); +assert (utf16result.length() == 4); +assert (utf16result[2] == 0xd834); +assert (utf16result[3] == 0xdd1e); +``` + +In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown. + +#### utf8::utf8to16 + +Available in version 3.2 and later. Requires a C++ 17 compliant compiler. + +Converts an UTF-8 encoded string to UTF-16. + +```cpp +std::u16string utf8to16(std::string_view s); +``` + +`s`: an UTF-8 encoded string to convert. +Return value: A UTF-16 encoded string + +Example of use: + +```cpp +string_view utf8_with_surrogates = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"; +u16string utf16result = utf8to16(utf8_with_surrogates); +assert (utf16result.length() == 4); +assert (utf16result[2] == 0xd834); +assert (utf16result[3] == 0xdd1e); +``` + +In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown. + + #### utf8::utf8to16 Available in version 1.0 and later. @@ -387,6 +527,54 @@ assert (utf16result[3] == 0xdd1e); In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown. If `end` does not point to the past-of-end of a UTF-8 seqence, a `utf8::not_enough_room` exception is thrown. +#### utf8::utf32to8 + +Available in version 3.0 and later. Requires a C++ 11 compliant compiler. + +Converts a UTF-32 encoded string to UTF-8. + +```cpp +std::string utf32to8(const std::u32string& s); +``` + +`s`: a UTF-32 encoded string. +Return value: a UTF-8 encoded string. + +Example of use: + +```cpp +u32string utf32string = {0x448, 0x65E5, 0x10346}; +string utf8result = utf32to8(utf32string); +assert (utf8result.size() == 9); +``` + +In case of invalid UTF-32 string, a `utf8::invalid_code_point` exception is thrown. + +#### utf8::utf32to8 + +Available in version 3.2 and later. Requires a C++ 17 compliant compiler. + +Converts a UTF-32 encoded string to UTF-8. + +```cpp +std::string utf32to8(std::u32string_view s); +``` + +`s`: a UTF-32 encoded string. +Return value: a UTF-8 encoded string. + +Example of use: + +```cpp +u32string utf32string = {0x448, 0x65E5, 0x10346}; +u32string_view utf32stringview(utf32string); +string utf8result = utf32to8(utf32stringview); +assert (utf8result.size() == 9); +``` + +In case of invalid UTF-32 string, a `utf8::invalid_code_point` exception is thrown. + + #### utf8::utf32to8 Available in version 1.0 and later. @@ -407,7 +595,7 @@ Return value: An iterator pointing to the place after the appended UTF-8 string. Example of use: -``` +```cpp int utf32string[] = {0x448, 0x65E5, 0x10346, 0}; vector utf8result; utf32to8(utf32string, utf32string + 3, back_inserter(utf8result)); @@ -416,6 +604,53 @@ assert (utf8result.size() == 9); In case of invalid UTF-32 string, a `utf8::invalid_code_point` exception is thrown. +#### utf8::utf8to32 + +Available in version 3.0 and later. Requires a C++ 11 compliant compiler. + +Converts a UTF-8 encoded string to UTF-32. + +```cpp +std::u32string utf8to32(const std::string& s); +``` + +`s`: a UTF-8 encoded string. +Return value: a UTF-32 encoded string. + +Example of use: + +```cpp +const char* twochars = "\xe6\x97\xa5\xd1\x88"; +u32string utf32result = utf8to32(twochars); +assert (utf32result.size() == 2); +``` + +In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown. + +#### utf8::utf8to32 + +Available in version 3.2 and later. Requires a C++ 17 compliant compiler. + +Converts a UTF-8 encoded string to UTF-32. + +```cpp +std::u32string utf8to32(std::string_view s); +``` + +`s`: a UTF-8 encoded string. +Return value: a UTF-32 encoded string. + +Example of use: + +```cpp +string_view twochars = "\xe6\x97\xa5\xd1\x88"; +u32string utf32result = utf8to32(twochars); +assert (utf32result.size() == 2); +``` + +In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown. + + #### utf8::utf8to32 Available in version 1.0 and later. @@ -445,6 +680,53 @@ assert (utf32result.size() == 2); In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown. If `end` does not point to the past-of-end of a UTF-8 seqence, a `utf8::not_enough_room` exception is thrown. +#### utf8::find_invalid + +Available in version 3.0 and later. Requires a C++ 11 compliant compiler. + +Detects an invalid sequence within a UTF-8 string. + +```cpp +std::size_t find_invalid(const std::string& s); +``` + +`s`: a UTF-8 encoded string. +Return value: the index of the first invalid octet in the UTF-8 string. In case none were found, equals `std::string::npos`. + +Example of use: + +```cpp +string utf_invalid = "\xe6\x97\xa5\xd1\x88\xfa"; +auto invalid = find_invalid(utf_invalid); +assert (invalid == 5); +``` + +This function is typically used to make sure a UTF-8 string is valid before processing it with other functions. It is especially important to call it if before doing any of the _unchecked_ operations on it. + +#### utf8::find_invalid + +Available in version 3.2 and later. Requires a C++ 17 compliant compiler. + +Detects an invalid sequence within a UTF-8 string. + +```cpp +std::size_t find_invalid(std::string_view s); +``` + +`s`: a UTF-8 encoded string. +Return value: the index of the first invalid octet in the UTF-8 string. In case none were found, equals `std::string_view::npos`. + +Example of use: + +```cpp +string_view utf_invalid = "\xe6\x97\xa5\xd1\x88\xfa"; +auto invalid = find_invalid(utf_invalid); +assert (invalid == 5); +``` + +This function is typically used to make sure a UTF-8 string is valid before processing it with other functions. It is especially important to call it if before doing any of the _unchecked_ operations on it. + + #### utf8::find_invalid Available in version 1.0 and later. @@ -471,6 +753,53 @@ assert (invalid == utf_invalid + 5); This function is typically used to make sure a UTF-8 string is valid before processing it with other functions. It is especially important to call it if before doing any of the _unchecked_ operations on it. +#### utf8::is_valid + +Available in version 3.0 and later. Requires a C++ 11 compliant compiler. + +Checks whether a string object contains valid UTF-8 encoded text. + +```cpp +bool is_valid(const std::string& s); +``` + +`s`: a UTF-8 encoded string. +Return value: `true` if the string contains valid UTF-8 encoded text; `false` if not. + +Example of use: + +```cpp +char utf_invalid[] = "\xe6\x97\xa5\xd1\x88\xfa"; +bool bvalid = is_valid(utf_invalid); +assert (bvalid == false); +``` + +You may want to use `is_valid` to make sure that a string contains valid UTF-8 text without the need to know where it fails if it is not valid. + +#### utf8::is_valid + +Available in version 3.2 and later. Requires a C++ 17 compliant compiler. + +Checks whether a string object contains valid UTF-8 encoded text. + +```cpp +bool is_valid(std::string_view s); +``` + +`s`: a UTF-8 encoded string. +Return value: `true` if the string contains valid UTF-8 encoded text; `false` if not. + +Example of use: + +```cpp +string_view utf_invalid = "\xe6\x97\xa5\xd1\x88\xfa"; +bool bvalid = is_valid(utf_invalid); +assert (bvalid == false); +``` + +You may want to use `is_valid` to make sure that a string contains valid UTF-8 text without the need to know where it fails if it is not valid. + + #### utf8::is_valid Available in version 1.0 and later. @@ -497,6 +826,59 @@ assert (bvalid == false); `is_valid` is a shorthand for `find_invalid(start, end) == end;`. You may want to use it to make sure that a byte seqence is a valid UTF-8 string without the need to know where it fails if it is not valid. +#### utf8::replace_invalid + +Available in version 3.0 and later. Requires a C++ 11 compliant compiler. + +Replaces all invalid UTF-8 sequences within a string with a replacement marker. + +```cpp +std::string replace_invalid(const std::string& s, char32_t replacement); +std::string replace_invalid(const std::string& s); +``` + +`s`: a UTF-8 encoded string. +`replacement`: A Unicode code point for the replacement marker. The version without this parameter assumes the value `0xfffd` +Return value: A UTF-8 encoded string with replaced invalid sequences. + +Example of use: + +```cpp +string invalid_sequence = "a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z"; +string replace_invalid_result = replace_invalid(invalid_sequence, '?'); +bvalid = is_valid(replace_invalid_result); +assert (bvalid); +const string fixed_invalid_sequence = "a????z"; +assert (fixed_invalid_sequence == replace_invalid_result); +``` + +#### utf8::replace_invalid + +Available in version 3.2 and later. Requires a C++ 17 compliant compiler. + +Replaces all invalid UTF-8 sequences within a string with a replacement marker. + +```cpp +std::string replace_invalid(std::string_view s, char32_t replacement); +std::string replace_invalid(std::string_view s); +``` + +`s`: a UTF-8 encoded string. +`replacement`: A Unicode code point for the replacement marker. The version without this parameter assumes the value `0xfffd` +Return value: A UTF-8 encoded string with replaced invalid sequences. + +Example of use: + +```cpp +string_view invalid_sequence = "a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z"; +string replace_invalid_result = replace_invalid(invalid_sequence, '?'); +bool bvalid = is_valid(replace_invalid_result); +assert (bvalid); +const string fixed_invalid_sequence = "a????z"; +assert(fixed_invalid_sequence, replace_invalid_result); +``` + + #### utf8::replace_invalid Available in version 2.0 and later. @@ -532,11 +914,64 @@ assert (std::equal(replace_invalid_result.begin(), replace_invalid_result.end(), `replace_invalid` does not perform in-place replacement of invalid sequences. Rather, it produces a copy of the original string with the invalid sequences replaced with a replacement marker. Therefore, `out` must not be in the `[start, end]` range. -If `end` does not point to the past-of-end of a UTF-8 sequence, a `utf8::not_enough_room` exception is thrown. +#### utf8::starts_with_bom + +Available in version 3.0 and later. Requires a C++ 11 compliant compiler. + +Checks whether a string starts with a UTF-8 byte order mark (BOM) + +```cpp +bool starts_with_bom(const std::string& s); +``` + +`s`: a UTF-8 encoded string. +Return value: `true` if the string starts with a UTF-8 byte order mark; `false` if not. + +Example of use: + +```cpp +string byte_order_mark = {char(0xef), char(0xbb), char(0xbf)}; +bool bbom = starts_with_bom(byte_order_mark); +assert (bbom == true); +string threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; +bool no_bbom = starts_with_bom(threechars); +assert (no_bbom == false); + ``` + +The typical use of this function is to check the first three bytes of a file. If they form the UTF-8 BOM, we want to skip them before processing the actual UTF-8 encoded text. + #### utf8::starts_with_bom -Available in version 2.3 and later. Relaces deprecated `is_bom()` function. +Available in version 3.2 and later. Requires a C++ 17 compliant compiler. + +Checks whether a string starts with a UTF-8 byte order mark (BOM) + +```cpp +bool starts_with_bom(std::string_view s); +``` + +`s`: a UTF-8 encoded string. +Return value: `true` if the string starts with a UTF-8 byte order mark; `false` if not. + +Example of use: + +```cpp +string byte_order_mark = {char(0xef), char(0xbb), char(0xbf)}; +string_view byte_order_mark_view(byte_order_mark); +bool bbom = starts_with_bom(byte_order_mark_view); +assert (bbom); +string_view threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; +bool no_bbom = starts_with_bom(threechars); +assert (!no_bbom); + ``` + +The typical use of this function is to check the first three bytes of a file. If they form the UTF-8 BOM, we want to skip them before processing the actual UTF-8 encoded text. + + +#### utf8::starts_with_bom + +Available in version 2.3 and later. Checks whether an octet sequence starts with a UTF-8 byte order mark (BOM) @@ -560,33 +995,6 @@ assert (bbom == true); The typical use of this function is to check the first three bytes of a file. If they form the UTF-8 BOM, we want to skip them before processing the actual UTF-8 encoded text. -#### utf8::is_bom - -Available in version 1.0 and later. Deprecated in version 2.3\. `starts_with_bom()` should be used instead. - -Checks whether a sequence of three octets is a UTF-8 byte order mark (BOM) - -```cpp -template -bool is_bom (octet_iterator it); // Deprecated -``` - -`octet_iterator`: an input iterator. -`it`: beginning of the 3-octet sequence to check -Return value: `true` if the sequence is UTF-8 byte order mark; `false` if not. - -Example of use: - -```cpp -unsigned char byte_order_mark[] = {0xef, 0xbb, 0xbf}; -bool bbom = is_bom(byte_order_mark); -assert (bbom == true); -``` - -The typical use of this function is to check the first three bytes of a file. If they form the UTF-8 BOM, we want to skip them before processing the actual UTF-8 encoded text. - -If a sequence is shorter than three bytes, an invalid iterator will be dereferenced. Therefore, this function is deprecated in favor of `starts_with_bom()`that takes the end of sequence as an argument. - ### Types From utf8 Namespace #### utf8::exception @@ -678,15 +1086,24 @@ class iterator; ##### Member functions -`iterator();` the deafult constructor; the underlying octet_iterator is constructed with its default constructor. +`iterator();` the deafult constructor; the underlying octet_iterator is constructed with its default constructor. + `explicit iterator (const octet_iterator& octet_it, const octet_iterator& range_start, const octet_iterator& range_end);` a constructor that initializes the underlying octet_iterator with octet_it and sets the range in which the iterator is considered valid. + `octet_iterator base () const;` returns the underlying octet_iterator. + `uint32_t operator * () const;` decodes the utf-8 sequence the underlying octet_iterator is pointing to and returns the code point. + `bool operator == (const iterator& rhs) const;` returns `true` if the two underlaying iterators are equal. + `bool operator != (const iterator& rhs) const;` returns `true` if the two underlaying iterators are not equal. + `iterator& operator ++ ();` the prefix increment - moves the iterator to the next UTF-8 encoded code point. + `iterator operator ++ (int);` the postfix increment - moves the iterator to the next UTF-8 encoded code point and returns the current one. + `iterator& operator -- ();` the prefix decrement - moves the iterator to the previous UTF-8 encoded code point. + `iterator operator -- (int);` the postfix decrement - moves the iterator to the previous UTF-8 encoded code point and returns the current one. Example of use: @@ -824,34 +1241,6 @@ assert (w == twochars); This is a faster but less safe version of `utf8::prior`. It does not check for validity of the supplied UTF-8 sequence and offers no boundary checking. -#### utf8::unchecked::previous (deprecated, see utf8::unchecked::prior) - -Deprecated in version 1.02 and later. - -Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it decreases the iterator until it hits the beginning of the previous UTF-8 encoded code point and returns the 32 bits representation of the code point. - -```cpp -template -uint32_t previous(octet_iterator& it); -``` - -`it`: a reference pointing to an octet within a UTF-8 encoded string. After the function returns, it is decremented to point to the beginning of the previous code point. -Return value: the 32 bit representation of the previous code point. - -Example of use: - -```cpp -char* twochars = "\xe6\x97\xa5\xd1\x88"; -char* w = twochars + 3; -int cp = unchecked::previous (w); -assert (cp == 0x65e5); -assert (w == twochars); -``` - -The reason this function is deprecated is just the consistency with the "checked" versions, where `prior` should be used instead of `previous`. In fact, `unchecked::previous` behaves exactly the same as `unchecked::prior` - -This is a faster but less safe version of `utf8::previous`. It does not check for validity of the supplied UTF-8 sequence and offers no boundary checking. - #### utf8::unchecked::advance Available in version 1.0 and later. @@ -863,8 +1252,8 @@ template void advance (octet_iterator& it, distance_type n); ``` -`it`: a reference to an iterator pointing to the beginning of an UTF-8 encoded code point. After the function returns, it is incremented to point to the nth following code point. -`n`: a positive integer that shows how many code points we want to advance. +`it`: a reference to an iterator pointing to the beginning of an UTF-8 encoded code point. After the function returns, it is incremented to point to the nth following code point. +`n`: number of code points `it` should be advanced. A negative value means decrement. Example of use: @@ -875,8 +1264,6 @@ unchecked::advance (w, 2); assert (w == twochars + 5); ``` -This function works only "forward". In case of a negative `n`, there is no effect. - This is a faster but less safe version of `utf8::advance`. It does not check for validity of the supplied UTF-8 sequence and offers no boundary checking. #### utf8::unchecked::distance @@ -1013,6 +1400,43 @@ assert (utf32result.size() == 2); This is a faster but less safe version of `utf8::utf8to32`. It does not check for validity of the supplied UTF-8 sequence. +#### utf8::unchecked::replace_invalid + +Available in version 3.1 and later. + +Replaces all invalid UTF-8 sequences within a string with a replacement marker. + +```cpp +template +output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, uint32_t replacement); +template +output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out); +``` + +`octet_iterator`: an input iterator. +`output_iterator`: an output iterator. +`start`: an iterator pointing to the beginning of the UTF-8 string to look for invalid UTF-8 sequences. +`end`: an iterator pointing to pass-the-end of the UTF-8 string to look for invalid UTF-8 sequences. +`out`: An output iterator to the range where the result of replacement is stored. +`replacement`: A Unicode code point for the replacement marker. The version without this parameter assumes the value `0xfffd` +Return value: An iterator pointing to the place after the UTF-8 string with replaced invalid sequences. + +Example of use: + +```cpp +char invalid_sequence[] = "a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z"; +vector replace_invalid_result; +unchecked::replace_invalid (invalid_sequence, invalid_sequence + sizeof(invalid_sequence), back_inserter(replace_invalid_result), '?'); +bvalid = utf8::is_valid(replace_invalid_result.begin(), replace_invalid_result.end()); +assert (bvalid); +char* fixed_invalid_sequence = "a????z"; +assert (std::equal(replace_invalid_result.begin(), replace_invalid_result.end(), fixed_invalid_sequence)); +``` + +`replace_invalid` does not perform in-place replacement of invalid sequences. Rather, it produces a copy of the original string with the invalid sequences replaced with a replacement marker. Therefore, `out` must not be in the `[start, end]` range. + +Unlike `utf8::replace_invalid`, this function does not verify validity of the replacement marker. + ### Types From utf8::unchecked Namespace #### utf8::iterator @@ -1029,14 +1453,23 @@ class iterator; ##### Member functions `iterator();` the deafult constructor; the underlying octet_iterator is constructed with its default constructor. -`explicit iterator (const octet_iterator& octet_it);` a constructor that initializes the underlying octet_iterator with `octet_it` + +`explicit iterator (const octet_iterator& octet_it);` a constructor that initializes the underlying octet_iterator with `octet_it`. + `octet_iterator base () const;` returns the underlying octet_iterator. + `uint32_t operator * () const;` decodes the utf-8 sequence the underlying octet_iterator is pointing to and returns the code point. + `bool operator == (const iterator& rhs) const;` returns `true` if the two underlaying iterators are equal. + `bool operator != (const iterator& rhs) const;` returns `true` if the two underlaying iterators are not equal. + `iterator& operator ++ ();` the prefix increment - moves the iterator to the next UTF-8 encoded code point. + `iterator operator ++ (int);` the postfix increment - moves the iterator to the next UTF-8 encoded code point and returns the current one. + `iterator& operator -- ();` the prefix decrement - moves the iterator to the previous UTF-8 encoded code point. + `iterator operator -- (int);` the postfix decrement - moves the iterator to the previous UTF-8 encoded code point and returns the current one. Example of use: @@ -1062,26 +1495,6 @@ assert (*un_it == 0x10346); This is an unchecked version of `utf8::iterator`. It is faster in many cases, but offers no validity or range checks. -## Points of interest - -#### Design goals and decisions - -The library was designed to be: - -1. Generic: for better or worse, there are many C++ string classes out there, and the library should work with as many of them as possible. -2. Portable: the library should be portable both accross different platforms and compilers. The only non-portable code is a small section that declares unsigned integers of different sizes: three typedefs. They can be changed by the users of the library if they don't match their platform. The default setting should work for Windows (both 32 and 64 bit), and most 32 bit and 64 bit Unix derivatives. At this point I don't plan to use any post C++03 features, so the library should work even with pretty old compilers. -3. Lightweight: follow the "pay only for what you use" guideline. -4. Unintrusive: avoid forcing any particular design or even programming style on the user. This is a library, not a framework. - -#### Alternatives - -In case you want to look into other means of working with UTF-8 strings from C++, here is the list of solutions I am aware of: - -1. [ICU Library](http://icu.sourceforge.net/). It is very powerful, complete, feature-rich, mature, and widely used. Also big, intrusive, non-generic, and doesn't play well with the Standard Library. I definitelly recommend looking at ICU even if you don't plan to use it. -2. C++11 language and library features. Still far from complete, and not easy to use. -3. [Glib::ustring](http://www.gtkmm.org/gtkmm2/docs/tutorial/html/ch03s04.html). A class specifically made to work with UTF-8 strings, and also feel like `std::string`. If you prefer to have yet another string class in your code, it may be worth a look. Be aware of the licensing issues, though. -4. Platform dependent solutions: Windows and POSIX have functions to convert strings from one encoding to another. That is only a subset of what my library offers, but if that is all you need it may be good enough. - ## Links 1. [The Unicode Consortium](http://www.unicode.org/). diff --git a/third-party/utf8cpp/extern/ftest b/third-party/utf8cpp/extern/ftest new file mode 160000 index 000000000..c4ad4af09 --- /dev/null +++ b/third-party/utf8cpp/extern/ftest @@ -0,0 +1 @@ +Subproject commit c4ad4af0946b73ce1a40cbc72205d15d196c7e06 diff --git a/third-party/utf8cpp/samples/docsample.cpp b/third-party/utf8cpp/samples/docsample.cpp index 6f8953b99..653388725 100644 --- a/third-party/utf8cpp/samples/docsample.cpp +++ b/third-party/utf8cpp/samples/docsample.cpp @@ -17,8 +17,8 @@ int main(int argc, char** argv) // Open the test file (must be UTF-8 encoded) ifstream fs8(test_file_path); if (!fs8.is_open()) { - cout << "Could not open " << test_file_path << endl; - return 0; + cout << "Could not open " << test_file_path << endl; + return 0; } unsigned line_count = 1; @@ -26,21 +26,33 @@ int main(int argc, char** argv) // Play with all the lines in the file while (getline(fs8, line)) { // check for invalid utf-8 (for a simple yes/no check, there is also utf8::is_valid function) +#if __cplusplus >= 201103L // C++ 11 or later + auto end_it = utf8::find_invalid(line.begin(), line.end()); +#else string::iterator end_it = utf8::find_invalid(line.begin(), line.end()); +#endif // C++ 11 if (end_it != line.end()) { cout << "Invalid UTF-8 encoding detected at line " << line_count << "\n"; cout << "This part is fine: " << string(line.begin(), end_it) << "\n"; } // Get the line length (at least for the valid part) - int length = utf8::distance(line.begin(), end_it); + ptrdiff_t length = utf8::distance(line.begin(), end_it); cout << "Length of line " << line_count << " is " << length << "\n"; // Convert it to utf-16 +#if __cplusplus >= 201103L // C++ 11 or later + u16string utf16line = utf8::utf8to16(line); +#else vector utf16line; utf8::utf8to16(line.begin(), end_it, back_inserter(utf16line)); +#endif // C++ 11 // And back to utf-8; +#if __cplusplus >= 201103L // C++ 11 or later + string utf8line = utf8::utf16to8(utf16line); +#else string utf8line; utf8::utf16to8(utf16line.begin(), utf16line.end(), back_inserter(utf8line)); +#endif // C++ 11 // Confirm that the conversion went OK: if (utf8line != string(line.begin(), end_it)) cout << "Error in UTF-16 conversion at line: " << line_count << "\n"; diff --git a/third-party/utf8cpp/source/utf8/checked.h b/third-party/utf8cpp/source/utf8/checked.h index 2aef5838d..512dcc2fb 100644 --- a/third-party/utf8cpp/source/utf8/checked.h +++ b/third-party/utf8cpp/source/utf8/checked.h @@ -42,7 +42,7 @@ namespace utf8 uint32_t cp; public: invalid_code_point(uint32_t codepoint) : cp(codepoint) {} - virtual const char* what() const throw() { return "Invalid code point"; } + virtual const char* what() const UTF_CPP_NOEXCEPT UTF_CPP_OVERRIDE { return "Invalid code point"; } uint32_t code_point() const {return cp;} }; @@ -50,7 +50,8 @@ namespace utf8 uint8_t u8; public: invalid_utf8 (uint8_t u) : u8(u) {} - virtual const char* what() const throw() { return "Invalid UTF-8"; } + invalid_utf8 (char c) : u8(static_cast(c)) {} + virtual const char* what() const UTF_CPP_NOEXCEPT UTF_CPP_OVERRIDE { return "Invalid UTF-8"; } uint8_t utf8_octet() const {return u8;} }; @@ -58,13 +59,13 @@ 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 UTF_CPP_NOEXCEPT UTF_CPP_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 UTF_CPP_NOEXCEPT UTF_CPP_OVERRIDE { return "Not enough space"; } }; /// The library API - functions intended to be called by the users @@ -75,24 +76,7 @@ namespace utf8 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; + return internal::append(cp, result); } template @@ -107,7 +91,9 @@ 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; @@ -146,7 +132,7 @@ namespace utf8 case internal::INVALID_LEAD : case internal::INCOMPLETE_SEQUENCE : case internal::OVERLONG_SEQUENCE : - throw invalid_utf8(*it); + throw invalid_utf8(static_cast(*it)); case internal::INVALID_CODE_POINT : throw invalid_code_point(cp); } @@ -174,23 +160,19 @@ 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 @@ -265,11 +247,16 @@ 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& rangestart, @@ -322,6 +309,11 @@ namespace utf8 } // namespace utf8 +#if UTF_CPP_CPLUSPLUS >= 201703L // C++ 17 or later +#include "cpp17.h" +#elif UTF_CPP_CPLUSPLUS >= 201103L // C++ 11 or later +#include "cpp11.h" +#endif // C++ 11 or later + #endif //header guard - diff --git a/third-party/utf8cpp/source/utf8/core.h b/third-party/utf8cpp/source/utf8/core.h index ae0f367db..34371ee31 100644 --- a/third-party/utf8cpp/source/utf8/core.h +++ b/third-party/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 UTF_CPP_OVERRIDE override + #define UTF_CPP_NOEXCEPT noexcept +#else // C++ 98/03 + #define UTF_CPP_OVERRIDE + #define UTF_CPP_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) @@ -222,7 +239,7 @@ namespace internal template utf_error validate_next(octet_iterator& it, octet_iterator end, uint32_t& code_point) { - if (it == end) + if (it == end) return NOT_ENOUGH_ROOM; // Save the original value of it so we can go back in case of failure @@ -237,7 +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); @@ -280,6 +297,55 @@ namespace internal return utf8::internal::validate_next(it, end, ignored); } + // Internal implementation of both checked and unchecked append() function + // This function will be invoked by the overloads below, as they will know + // the octet_type. + 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; + } + + // One of the following overloads will be invoked from the API calls + + // A simple (but dangerous) case: the caller appends byte(s) to a char array + inline char* append(uint32_t cp, char* result) { + return append(cp, result); + } + + // Hopefully, most common case: the caller uses back_inserter + // i.e. append(cp, std::back_inserter(str)); + template + std::back_insert_iterator append + (uint32_t cp, std::back_insert_iterator result) { + return append, + typename container_type::value_type>(cp, result); + } + + // The caller uses some other kind of output operator - not covered above + // Note that in this case we are not able to determine octet_type + // so we assume it's uint_8; that can cause a conversion warning if we are wrong. + template + octet_iterator append(uint32_t cp, octet_iterator result) { + return append(cp, result); + } + } // namespace internal /// The library API - functions intended to be called by the users @@ -313,18 +379,7 @@ 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/third-party/utf8cpp/source/utf8/cpp11.h b/third-party/utf8cpp/source/utf8/cpp11.h new file mode 100644 index 000000000..2366f1291 --- /dev/null +++ b/third-party/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 : static_cast(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/third-party/utf8cpp/source/utf8/cpp17.h b/third-party/utf8cpp/source/utf8/cpp17.h new file mode 100644 index 000000000..32a77ce30 --- /dev/null +++ b/third-party/utf8cpp/source/utf8/cpp17.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_7e906c01_03a3_4daf_b420_ea7ea952b3c9 +#define UTF8_FOR_CPP_7e906c01_03a3_4daf_b420_ea7ea952b3c9 + +#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(std::u16string_view s) + { + std::string result; + utf16to8(s.begin(), s.end(), std::back_inserter(result)); + return result; + } + + inline std::u16string utf8to16(std::string_view s) + { + std::u16string result; + utf8to16(s.begin(), s.end(), std::back_inserter(result)); + return result; + } + + inline std::string utf32to8(std::u32string_view s) + { + std::string result; + utf32to8(s.begin(), s.end(), std::back_inserter(result)); + return result; + } + + inline std::u32string utf8to32(std::string_view s) + { + std::u32string result; + utf8to32(s.begin(), s.end(), std::back_inserter(result)); + return result; + } + + inline std::size_t find_invalid(std::string_view s) + { + std::string_view::const_iterator invalid = find_invalid(s.begin(), s.end()); + return (invalid == s.end()) ? std::string_view::npos : static_cast(invalid - s.begin()); + } + + inline bool is_valid(std::string_view s) + { + return is_valid(s.begin(), s.end()); + } + + inline std::string replace_invalid(std::string_view 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(std::string_view s) + { + std::string result; + replace_invalid(s.begin(), s.end(), std::back_inserter(result)); + return result; + } + + inline bool starts_with_bom(std::string_view s) + { + return starts_with_bom(s.begin(), s.end()); + } + +} // namespace utf8 + +#endif // header guard + diff --git a/third-party/utf8cpp/source/utf8/unchecked.h b/third-party/utf8cpp/source/utf8/unchecked.h index cb2427166..8fe83c9ec 100644 --- a/third-party/utf8cpp/source/utf8/unchecked.h +++ b/third-party/utf8cpp/source/utf8/unchecked.h @@ -32,29 +32,52 @@ 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); - else if (cp < 0x800) { // two octets - *(result++) = static_cast((cp >> 6) | 0xc0); - *(result++) = static_cast((cp & 0x3f) | 0x80); + return internal::append(cp, 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; + } } - 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; + 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 @@ -85,13 +108,13 @@ 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 +125,19 @@ 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 +152,7 @@ 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 +162,7 @@ namespace utf8 } result = utf8::unchecked::append(cp, result); } - return result; + return result; } template @@ -176,9 +200,14 @@ 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 diff --git a/third-party/utf8cpp/test_data/utf8samples/UTF-8-demo.txt b/third-party/utf8cpp/test_data/utf8samples/UTF-8-demo.txt deleted file mode 100644 index 4363f27bd..000000000 --- a/third-party/utf8cpp/test_data/utf8samples/UTF-8-demo.txt +++ /dev/null @@ -1,212 +0,0 @@ - -UTF-8 encoded sample plain-text file -‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ - -Markus Kuhn [ˈmaʳkʊs kuːn] — 2002-07-25 - - -The ASCII compatible UTF-8 encoding used in this plain-text file -is defined in Unicode, ISO 10646-1, and RFC 2279. - - -Using Unicode/UTF-8, you can write in emails and source code things such as - -Mathematics and sciences: - - ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ - ⎪⎢⎜│a²+b³ ⎟⎥⎪ - ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ - ⎪⎢⎜⎷ c₈ ⎟⎥⎪ - ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ - ⎪⎢⎜ ∞ ⎟⎥⎪ - ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ - ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ - 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ - -Linguistics and dictionaries: - - ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn - Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] - -APL: - - ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ - -Nicer typography in plain text files: - - ╔══════════════════════════════════════════╗ - ║ ║ - ║ • ‘single’ and “double” quotes ║ - ║ ║ - ║ • Curly apostrophes: “We’ve been here” ║ - ║ ║ - ║ • Latin-1 apostrophe and accents: '´` ║ - ║ ║ - ║ • ‚deutsche‘ „Anführungszeichen“ ║ - ║ ║ - ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ - ║ ║ - ║ • ASCII safety test: 1lI|, 0OD, 8B ║ - ║ ╭─────────╮ ║ - ║ • the euro symbol: │ 14.95 € │ ║ - ║ ╰─────────╯ ║ - ╚══════════════════════════════════════════╝ - -Combining characters: - - STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ - -Greek (in Polytonic): - - The Greek anthem: - - Σὲ γνωρίζω ἀπὸ τὴν κόψη - τοῦ σπαθιοῦ τὴν τρομερή, - σὲ γνωρίζω ἀπὸ τὴν ὄψη - ποὺ μὲ βία μετράει τὴ γῆ. - - ᾿Απ᾿ τὰ κόκκαλα βγαλμένη - τῶν ῾Ελλήνων τὰ ἱερά - καὶ σὰν πρῶτα ἀνδρειωμένη - χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! - - From a speech of Demosthenes in the 4th century BC: - - Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, - ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς - λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ - τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ - εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ - πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν - οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, - οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν - ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον - τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι - γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν - προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους - σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ - τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ - τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς - τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. - - Δημοσθένους, Γ´ ᾿Ολυνθιακὸς - -Georgian: - - From a Unicode conference invitation: - - გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო - კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, - ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს - ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, - ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება - ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, - ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. - -Russian: - - From a Unicode conference invitation: - - Зарегистрируйтесь сейчас на Десятую Международную Конференцию по - Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. - Конференция соберет широкий круг экспертов по вопросам глобального - Интернета и Unicode, локализации и интернационализации, воплощению и - применению Unicode в различных операционных системах и программных - приложениях, шрифтах, верстке и многоязычных компьютерных системах. - -Thai (UCS Level 2): - - Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese - classic 'San Gua'): - - [----------------------------|------------------------] - ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ - สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา - ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา - โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ - เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ - ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ - พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ - ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ - - (The above is a two-column text. If combining characters are handled - correctly, the lines of the second column should be aligned with the - | character above.) - -Ethiopian: - - Proverbs in the Amharic language: - - ሰማይ አይታረስ ንጉሥ አይከሰስ። - ብላ ካለኝ እንደአባቴ በቆመጠኝ። - ጌጥ ያለቤቱ ቁምጥና ነው። - ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። - የአፍ ወለምታ በቅቤ አይታሽም። - አይጥ በበላ ዳዋ ተመታ። - ሲተረጉሙ ይደረግሙ። - ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። - ድር ቢያብር አንበሳ ያስር። - ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። - እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። - የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። - ሥራ ከመፍታት ልጄን ላፋታት። - ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። - የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። - ተንጋሎ ቢተፉ ተመልሶ ባፉ። - ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። - እግርህን በፍራሽህ ልክ ዘርጋ። - -Runes: - - ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ - - (Old English, which transcribed into Latin reads 'He cwaeth that he - bude thaem lande northweardum with tha Westsae.' and means 'He said - that he lived in the northern land near the Western Sea.') - -Braille: - - ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ - - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ - ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ - ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ - ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ - ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ - ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ - - ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ - ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ - ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ - ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ - ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ - ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ - ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ - ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ - ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ - - (The first couple of paragraphs of "A Christmas Carol" by Dickens) - -Compact font selection example text: - - ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 - abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ - –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд - ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა - -Greetings in various languages: - - Hello world, Καλημέρα κόσμε, コンニチハ - -Box drawing alignment tests: █ - ▉ - ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ - ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ - ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ - ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ - ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ - ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ - ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ - ▝▀▘▙▄▟ diff --git a/third-party/utf8cpp/test_data/utf8samples/Unicode_transcriptions.html b/third-party/utf8cpp/test_data/utf8samples/Unicode_transcriptions.html deleted file mode 100644 index 69b29ffa5..000000000 --- a/third-party/utf8cpp/test_data/utf8samples/Unicode_transcriptions.html +++ /dev/null @@ -1,167 +0,0 @@ -? *Unicode Transcriptions* Notes <#Notes> - -Glyphs | Samples - | Charts - | UTF - | Forms - | -Home . - - -Name Text Image -Arabic (Arabic) يونِكود ? -Arabic (Persian) یونی‌کُد / ?/ -Armenian Յունիկօդ -Bengali য়ূনিকোড -Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ -ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ -Braille -Buhid -Canadian Aboriginal ᔫᗂᑰᑦ -Cherokee ᏳᏂᎪᏛ -Cypriot -Cyrillic (Russian) Юникод ? -Deseret (English) ??????? -Devanagari (Hindi) यूनिकोड ? -Ethiopic ዩኒኮድ -Georgian უნიკოდი ? -Gothic -Greek Γιούνικοντ -Gujarati યૂનિકોડ -Gurmukhi ਯੂਨਿਕੋਡ -Han (Chinese) 统一码 ? -統一碼 ? -万国码 ? -萬國碼 ? -Hangul 유니코드 -Hanunoo -Hebrew יוניקוד -Hebrew (pointed) יוּנִיקוׁד -Hebrew (Yiddish) יוניקאָד ? -Hiragana (Japanese) ゆにこおど -Katakana (Japanese) ユニコード ? -Kannada ಯೂನಿಕೋಡ್ -Khmer យូនីគោដ -Lao -Latin Unicode Unicode -Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? -Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? -Limbu -Linear B -Malayalam യൂനികോഡ് -Mongolian -Myanmar -Ogham ᚔᚒᚅᚔᚉᚑᚇ / / -Old Italic -Oriya ୟୂନିକୋଡ -Osmanya -Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ -Shavian -Sinhala යණනිකෞද් -Syriac ܝܘܢܝܩܘܕ -Tagbanwa -Tagalog -Tai Le -Tamil யூனிகோட் -Telugu యూనికోడ్ -Thaana -Thai ยูนืโคด -Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། -Ugaritic -Yi - - - Notes: - -There are different ways to transcribe the word “Unicode”, depending on -the language and script. In some cases there is only one language that -customarily uses a given script; in others there are many languages. The -goal here is at a minimum to collect at least one transcription for each -script in a language customarily written in that script, with more -languages if possible. If the transcription is the same for multiple -languages in a script, then a single representative language is used. - -Still missing are transcriptions for the items above in RED (in at least -one language). I would appreciate any other transcriptions, or -corrections for the ones listed here. Send to mark3@macchiato.com -, using the directions below: - - * *Supplying Missing Items* - o Most Latin-script languages will follow the spelling, and - change the pronunciation. For any that would not, it would - be good to have the alternate spelling. - o For non-Latin scripts the goal is to match the English - pronunciation — /*not*/ spelling. Above is the IPA <#IPA> - (in phonemic transcription) that should be matched as - closely as possible (without sounding affected in the target - language) - o Text would be best in either the UTF-8 text, or the code - points in hex HTML. E.g. either of the following: - + "Юникод" - + "Юникод" - + Note: for / supplementary characters/ - , - there should be one hex number per code point, not two - surrogates - : - # 𐀀 /*not*/ �&xDC00; - o If you have a good font, I'd also appreciate a GIF. It - should be *96 x 24* bits, with the text centered, in black - on white (plus grays if smoothed). - * *Other Comments* - o Because some browsers won't handle the text, both text and - GIF image are supplied. If you can’t read the text columns, - see Display Problems - . - o The Chinese versions (inc. Bopomofo) are translations, not - transcriptions, since "transcription in Chinese is pretty - lame" [J. Becker]. - o There are other "translations" of Unicode that may be in - use, such as the Vietnamese "Thống Nhất Mã". - o For sample pages in different languages on the Unicode site, - see What is Unicode? - - o Americans are not generally used to IPA, and find a variety - of different systems in their dictionaries. This one leaves - the base letters as they are, and uses diacritics for - pronunciation. - * *Etymology of /Unicode/* - o Coined by J. Becker. Not related to previous usages, such as: - + A telegraphic code in which one word or set of letters - represents a sentence or phrase; a telegram or message - in this. (late 19th century, OED) - o According to my references, the prefix "uni" is directly - from Latin while the word "code" is through French. - o The original Indo-European apparently would have been - *oino-kau-do ("one strike give"): *kau apparently being - related to such English words as: hew, haggle, hoe, hag, - hay, hack, caudad, caudal, caudate, caudex, coda, codex, - codicil, coward, incus, and Kovač (personal name: "smith"). - + I will leave the exact derivations to the exegetes, - but I like the association with "haggle" myself. - * *Contributions* - o This draws on contributions or comments from: - + Dixon Au - + Joe Becker - + Maurice Bauhahn - + Abel Cheung - + Peter Constable - + Michael Everson - + Christopher John Fynn - + Michael Kaplan - + George Kiraz - + Abdul Malik - + Siva Nataraja - + Roozbeh Pournader - + Jonathan Rosenne - + Jungshik Shin - ------------------------------------------------------------------------- - - -Terms of Use . Last updated: -MED - 04/20/2003 15:30:33. - - - - diff --git a/third-party/utf8cpp/test_data/utf8samples/quickbrown.txt b/third-party/utf8cpp/test_data/utf8samples/quickbrown.txt deleted file mode 100644 index 5db944343..000000000 --- a/third-party/utf8cpp/test_data/utf8samples/quickbrown.txt +++ /dev/null @@ -1,126 +0,0 @@ -Sentences that contain all letters commonly used in a language --------------------------------------------------------------- - -Markus Kuhn -- 2001-09-02 - -This file is UTF-8 encoded. - - -Danish (da) ---------- - - Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen - Wolther spillede på xylofon. - (= Quiz contestants were eating strawbery with cream while Wolther - the circus clown played on xylophone.) - -German (de) ------------ - - Falsches Üben von Xylophonmusik quält jeden größeren Zwerg - (= Wrongful practicing of xylophone music tortures every larger dwarf) - - Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich - (= Twelve boxing fighters hunted Eva across the dike of Sylt) - - Heizölrückstoßabdämpfung - (= fuel oil recoil absorber) - (jqvwxy missing, but all non-ASCII letters in one word) - -English (en) ------------- - - The quick brown fox jumps over the lazy dog - -Spanish (es) ------------- - - El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y - frío, añoraba a su querido cachorro. - (Contains every letter and every accent, but not every combination - of vowel + acute.) - -French (fr) ------------ - - Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à - côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce - qui lui permet de penser à la cænogenèse de l'être dont il est question - dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, - pense-t-il, diminue çà et là la qualité de son œuvre. - - l'île exiguë - Où l'obèse jury mûr - Fête l'haï volapük, - Âne ex aéquo au whist, - Ôtez ce vœu déçu. - - Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en - canoë au delà des îles, près du mälström où brûlent les novæ. - -Irish Gaelic (ga) ------------------ - - D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh - -Hungarian (hu) --------------- - - Árvíztűrő tükörfúrógép - (= flood-proof mirror-drilling machine, only all non-ASCII letters) - -Icelandic (is) --------------- - - Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa - - Sævör grét áðan því úlpan var ónýt - (some ASCII letters missing) - -Japanese (jp) -------------- - - Hiragana: (Iroha) - - いろはにほへとちりぬるを - わかよたれそつねならむ - うゐのおくやまけふこえて - あさきゆめみしゑひもせす - - Katakana: - - イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム - ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン - -Hebrew (iw) ------------ - - ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה - -Polish (pl) ------------ - - Pchnąć w tę łódź jeża lub ośm skrzyń fig - (= To push a hedgehog or eight bins of figs in this boat) - -Russian (ru) ------------- - - В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! - (= Would a citrus live in the bushes of south? Yes, but only a fake one!) - -Thai (th) ---------- - - [--------------------------|------------------------] - ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน - จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร - ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย - ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ - - [The copyright for the Thai example is owned by The Computer - Association of Thailand under the Royal Patronage of His Majesty the - King.] - -Please let me know if you find others! Special thanks to the people -from all over the world who contributed these sentences. diff --git a/third-party/utf8cpp/test_drivers/smoke_test/test.cpp b/third-party/utf8cpp/test_drivers/smoke_test/test.cpp deleted file mode 100644 index 4f9fb0485..000000000 --- a/third-party/utf8cpp/test_drivers/smoke_test/test.cpp +++ /dev/null @@ -1,298 +0,0 @@ -#include -#include -#include -#include "../../source/utf8.h" -using namespace utf8; -using namespace std; - -int main() -{ - //append - unsigned char u[5] = {0,0,0,0,0}; - - append(0x0448, u); - assert (u[0] == 0xd1 && u[1] == 0x88 && u[2] == 0 && u[3] == 0 && u[4] == 0); - - append(0x65e5, u); - assert (u[0] == 0xe6 && u[1] == 0x97 && u[2] == 0xa5 && u[3] == 0 && u[4] == 0); - - append(0x3044, u); - assert (u[0] == 0xe3 && u[1] == 0x81 && u[2] == 0x84 && u[3] == 0 && u[4] == 0); - - append(0x10346, u); - assert (u[0] == 0xf0 && u[1] == 0x90 && u[2] == 0x8d && u[3] == 0x86 && u[4] == 0); - - - //next - const char* twochars = "\xe6\x97\xa5\xd1\x88"; - const char* w = twochars; - int cp = next(w, twochars + 6); - assert (cp == 0x65e5); - assert (w == twochars + 3); - - const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; - w = threechars; - cp = next(w, threechars + 9); - assert (cp == 0x10346); - assert (w == threechars + 4); - cp = next(w, threechars + 9); - assert (cp == 0x65e5); - assert (w == threechars + 7); - cp = next(w, threechars + 9); - assert (cp == 0x0448); - assert (w == threechars + 9); - - //peek_next - const char* const cw = twochars; - cp = peek_next(cw, cw + 6); - assert (cp == 0x65e5); - assert (cw == twochars); - - //prior - w = twochars + 3; - cp = prior (w, twochars); - assert (cp == 0x65e5); - assert (w == twochars); - - w = threechars + 9; - cp = prior(w, threechars); - assert (cp == 0x0448); - assert (w == threechars + 7); - cp = prior(w, threechars); - assert (cp == 0x65e5); - assert (w == threechars + 4); - cp = prior(w, threechars); - assert (cp == 0x10346); - assert (w == threechars); - - //previous (deprecated) - w = twochars + 3; - cp = previous (w, twochars - 1); - assert (cp == 0x65e5); - assert (w == twochars); - - w = threechars + 9; - cp = previous(w, threechars - 1); - assert (cp == 0x0448); - assert (w == threechars + 7); - cp = previous(w, threechars -1); - assert (cp == 0x65e5); - assert (w == threechars + 4); - cp = previous(w, threechars - 1); - assert (cp == 0x10346); - assert (w == threechars); - - // advance - w = twochars; - advance (w, 2, twochars + 6); - assert (w == twochars + 5); - - // distance - size_t dist = utf8::distance(twochars, twochars + 5); - assert (dist == 2); - - // utf32to8 - int utf32string[] = {0x448, 0x65E5, 0x10346, 0}; - vector utf8result; - utf32to8(utf32string, utf32string + 3, back_inserter(utf8result)); - assert (utf8result.size() == 9); - // try it with the return value; - char* utf8_end = utf32to8(utf32string, utf32string + 3, &utf8result[0]); - assert (utf8_end == &utf8result[0] + 9); - - //utf8to32 - vector utf32result; - utf8to32(twochars, twochars + 5, back_inserter(utf32result)); - assert (utf32result.size() == 2); - // try it with the return value; - int* utf32_end = utf8to32(twochars, twochars + 5, &utf32result[0]); - assert (utf32_end == &utf32result[0] + 2); - - //utf16to8 - unsigned short utf16string[] = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e}; - utf8result.clear(); - utf16to8(utf16string, utf16string + 5, back_inserter(utf8result)); - assert (utf8result.size() == 10); - // try it with the return value; - utf8_end = utf16to8 (utf16string, utf16string + 5, &utf8result[0]); - assert (utf8_end == &utf8result[0] + 10); - - //utf8to16 - char utf8_with_surrogates[] = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"; - vector utf16result; - utf8to16(utf8_with_surrogates, utf8_with_surrogates + 9, back_inserter(utf16result)); - assert (utf16result.size() == 4); - assert (utf16result[2] == 0xd834); - assert (utf16result[3] == 0xdd1e); - // try it with the return value; - unsigned short* utf16_end = utf8to16 (utf8_with_surrogates, utf8_with_surrogates + 9, &utf16result[0]); - assert (utf16_end == &utf16result[0] + 4); - - //find_invalid - char utf_invalid[] = "\xe6\x97\xa5\xd1\x88\xfa"; - char* invalid = find_invalid(utf_invalid, utf_invalid + 6); - assert (invalid == utf_invalid + 5); - - //is_valid - bool bvalid = is_valid(utf_invalid, utf_invalid + 6); - assert (bvalid == false); - bvalid = is_valid(utf8_with_surrogates, utf8_with_surrogates + 9); - assert (bvalid == true); - - //starts_with_bom - unsigned char byte_order_mark[] = {0xef, 0xbb, 0xbf}; - bool bbom = starts_with_bom(byte_order_mark, byte_order_mark + sizeof(byte_order_mark)); - assert (bbom == true); - bool no_bbom = starts_with_bom(threechars, threechars + sizeof(threechars)); - assert (no_bbom == false); - - //is_bom - bool unsafe_bbom = is_bom(byte_order_mark); - assert (unsafe_bbom == true); - - - //replace_invalid - char invalid_sequence[] = "a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z"; - vector replace_invalid_result; - replace_invalid (invalid_sequence, invalid_sequence + sizeof(invalid_sequence), std::back_inserter(replace_invalid_result), '?'); - bvalid = is_valid(replace_invalid_result.begin(), replace_invalid_result.end()); - assert (bvalid); - const char fixed_invalid_sequence[] = "a????z"; - assert (sizeof(fixed_invalid_sequence) == replace_invalid_result.size()); - assert (std::equal(replace_invalid_result.begin(), replace_invalid_result.begin() + sizeof(fixed_invalid_sequence), fixed_invalid_sequence)); - - // iterator - utf8::iterator it(threechars, threechars, threechars + 9); - utf8::iterator it2 = it; - assert (it2 == it); - assert (*it == 0x10346); - assert (*(++it) == 0x65e5); - assert ((*it++) == 0x65e5); - assert (*it == 0x0448); - assert (it != it2); - utf8::iterator endit (threechars + 9, threechars, threechars + 9); - assert (++it == endit); - assert (*(--it) == 0x0448); - assert ((*it--) == 0x0448); - assert (*it == 0x65e5); - assert (--it == utf8::iterator(threechars, threechars, threechars + 9)); - assert (*it == 0x10346); - - ////////////////////////////////////////////////////////// - //// Unchecked variants - ////////////////////////////////////////////////////////// - - //append - memset(u, 0, 5); - append(0x0448, u); - assert (u[0] == 0xd1 && u[1] == 0x88 && u[2] == 0 && u[3] == 0 && u[4] == 0); - - append(0x65e5, u); - assert (u[0] == 0xe6 && u[1] == 0x97 && u[2] == 0xa5 && u[3] == 0 && u[4] == 0); - - append(0x10346, u); - assert (u[0] == 0xf0 && u[1] == 0x90 && u[2] == 0x8d && u[3] == 0x86 && u[4] == 0); - - //next - w = twochars; - cp = unchecked::next(w); - assert (cp == 0x65e5); - assert (w == twochars + 3); - - w = threechars; - cp = unchecked::next(w); - assert (cp == 0x10346); - assert (w == threechars + 4); - cp = unchecked::next(w); - assert (cp == 0x65e5); - assert (w == threechars + 7); - cp = unchecked::next(w); - assert (cp == 0x0448); - assert (w == threechars + 9); - - //peek_next - cp = unchecked::peek_next(cw); - assert (cp == 0x65e5); - assert (cw == twochars); - - - //previous (calls prior internally) - - w = twochars + 3; - cp = unchecked::previous (w); - assert (cp == 0x65e5); - assert (w == twochars); - - w = threechars + 9; - cp = unchecked::previous(w); - assert (cp == 0x0448); - assert (w == threechars + 7); - cp = unchecked::previous(w); - assert (cp == 0x65e5); - assert (w == threechars + 4); - cp = unchecked::previous(w); - assert (cp == 0x10346); - assert (w == threechars); - - // advance - w = twochars; - unchecked::advance (w, 2); - assert (w == twochars + 5); - - // distance - dist = unchecked::distance(twochars, twochars + 5); - assert (dist == 2); - - // utf32to8 - utf8result.clear(); - unchecked::utf32to8(utf32string, utf32string + 3, back_inserter(utf8result)); - assert (utf8result.size() == 9); - // try it with the return value; - utf8_end = utf32to8(utf32string, utf32string + 3, &utf8result[0]); - assert(utf8_end == &utf8result[0] + 9); - - //utf8to32 - utf32result.clear(); - unchecked::utf8to32(twochars, twochars + 5, back_inserter(utf32result)); - assert (utf32result.size() == 2); - // try it with the return value; - utf32_end = utf8to32(twochars, twochars + 5, &utf32result[0]); - assert (utf32_end == &utf32result[0] + 2); - - //utf16to8 - utf8result.clear(); - unchecked::utf16to8(utf16string, utf16string + 5, back_inserter(utf8result)); - assert (utf8result.size() == 10); - // try it with the return value; - utf8_end = utf16to8 (utf16string, utf16string + 5, &utf8result[0]); - assert (utf8_end == &utf8result[0] + 10); - - //utf8to16 - utf16result.clear(); - unchecked::utf8to16(utf8_with_surrogates, utf8_with_surrogates + 9, back_inserter(utf16result)); - assert (utf16result.size() == 4); - assert (utf16result[2] == 0xd834); - assert (utf16result[3] == 0xdd1e); - // try it with the return value; - utf16_end = utf8to16 (utf8_with_surrogates, utf8_with_surrogates + 9, &utf16result[0]); - assert (utf16_end == &utf16result[0] + 4); - - // iterator - utf8::unchecked::iterator un_it(threechars); - utf8::unchecked::iterator un_it2 = un_it; - assert (un_it2 == un_it); - assert (*un_it == 0x10346); - assert (*(++un_it) == 0x65e5); - assert ((*un_it++) == 0x65e5); - assert (un_it != un_it2); - assert (*un_it == 0x0448); - utf8::unchecked::iterator un_endit (threechars + 9); - assert (++un_it == un_endit); - assert (*(--un_it) == 0x0448); - assert ((*un_it--) == 0x0448); - assert (*un_it == 0x65e5); - assert (--un_it == utf8::unchecked::iterator(threechars)); - assert (*un_it == 0x10346); -} - - diff --git a/third-party/utf8cpp/test_drivers/utf8reader/utf8reader.cpp b/third-party/utf8cpp/test_drivers/utf8reader/utf8reader.cpp deleted file mode 100644 index c88a5ee1b..000000000 --- a/third-party/utf8cpp/test_drivers/utf8reader/utf8reader.cpp +++ /dev/null @@ -1,160 +0,0 @@ -#include "../../source/utf8.h" -using namespace utf8; - -#include -#include -#include -#include -using namespace std; - -int main(int argc, char** argv) -{ - if (argc != 2) { - cout << "\nUsage: utfreader filename\n"; - return 0; - } - const char* TEST_FILE_PATH = argv[1]; - // Open the test file - ifstream fs8(TEST_FILE_PATH); - if (!fs8.is_open()) { - cout << "Could not open " << TEST_FILE_PATH << endl; - return 0; - } - - // Read it line by line - unsigned int line_count = 0; - char byte; - while (!fs8.eof()) { - string line; - while ((byte = static_cast(fs8.get())) != '\n' && !fs8.eof()) - line.push_back(byte); - - line_count++; - // Play around with each line and convert it to utf16 - string::iterator line_start = line.begin(); - string::iterator line_end = line.end(); - line_end = find_invalid(line_start, line_end); - if (line_end != line.end()) - cout << "Line " << line_count << ": Invalid utf-8 at byte " << int(line.end() - line_end) << '\n'; - - // Convert it to utf-16 and write to the file - vector utf16_line; - utf8to16(line_start, line_end, back_inserter(utf16_line)); - - // Back to utf-8 and compare it to the original line. - string back_to_utf8; - utf16to8(utf16_line.begin(), utf16_line.end(), back_inserter(back_to_utf8)); - if (back_to_utf8.compare(string(line_start, line_end)) != 0) - cout << "Line " << line_count << ": Conversion to UTF-16 and back failed" << '\n'; - - // Now, convert it to utf-32, back to utf-8 and compare - vector utf32_line; - utf8to32(line_start, line_end, back_inserter(utf32_line)); - back_to_utf8.clear(); - utf32to8(utf32_line.begin(), utf32_line.end(), back_inserter(back_to_utf8)); - if (back_to_utf8.compare(string(line_start, line_end)) != 0) - cout << "Line " << line_count << ": Conversion to UTF-32 and back failed" << '\n'; - - // Now, iterate and back - unsigned char_count = 0; - string::iterator it = line_start; - while (it != line_end) { - unsigned int next_cp = peek_next(it, line_end); - if (next(it, line_end) != next_cp) - cout << "Line " << line_count << ": Error: peek_next gave a different result than next" << '\n'; - char_count++; - } - if (char_count != utf32_line.size()) - cout << "Line " << line_count << ": Error in iterating with next - wrong number of characters" << '\n'; - - string::iterator adv_it = line_start; - utf8::advance(adv_it, char_count, line_end); - if (adv_it != line_end) - cout << "Line " << line_count << ": Error in advance function" << '\n'; - - if (string::size_type(utf8::distance(line_start, line_end)) != char_count) - cout << "Line " << line_count << ": Error in distance function" << '\n'; - - while (it != line_start) { - previous(it, line.rend().base()); - char_count--; - } - if (char_count != 0) - cout << "Line " << line_count << ": Error in iterating with previous - wrong number of characters" << '\n'; - - // Try utf8::iterator - utf8::iterator u8it(line_start, line_start, line_end); - if (!utf32_line.empty() && *u8it != utf32_line.at(0)) - cout << "Line " << line_count << ": Error in utf::iterator * operator" << '\n'; - if (std::distance(u8it, utf8::iterator(line_end, line_start, line_end)) != static_cast(utf32_line.size())) - cout << "Line " << line_count << ": Error in using utf::iterator with std::distance - wrong number of characters" << '\n'; - - std::advance(u8it, utf32_line.size()); - if (u8it != utf8::iterator(line_end, line_start, line_end)) - cout << "Line " << line_count << ": Error in using utf::iterator with std::advance" << '\n'; - - - //======================== Now, the unchecked versions ====================== - // Convert it to utf-16 and compare to the checked version - vector utf16_line_unchecked; - unchecked::utf8to16(line_start, line_end, back_inserter(utf16_line_unchecked)); - - if (utf16_line != utf16_line_unchecked) - cout << "Line " << line_count << ": Error in unchecked::utf8to16" << '\n'; - - // Back to utf-8 and compare it to the original line. - back_to_utf8.clear(); - unchecked::utf16to8(utf16_line_unchecked.begin(), utf16_line_unchecked.end(), back_inserter(back_to_utf8)); - if (back_to_utf8.compare(string(line_start, line_end)) != 0) - cout << "Line " << line_count << ": Unchecked conversion to UTF-16 and back failed" << '\n'; - - // Now, convert it to utf-32, back to utf-8 and compare - vector utf32_line_unchecked; - unchecked::utf8to32(line_start, line_end, back_inserter(utf32_line_unchecked)); - if (utf32_line != utf32_line_unchecked) - cout << "Line " << line_count << ": Error in unchecked::utf8to32" << '\n'; - - back_to_utf8.clear(); - unchecked::utf32to8(utf32_line.begin(), utf32_line.end(), back_inserter(back_to_utf8)); - if (back_to_utf8.compare(string(line_start, line_end)) != 0) - cout << "Line " << line_count << ": Unchecked conversion to UTF-32 and back failed" << '\n'; - - // Now, iterate and back - char_count = 0; - it = line_start; - while (it != line_end) { - unsigned int next_cp = unchecked::peek_next(it); - if (unchecked::next(it) != next_cp) - cout << "Line " << line_count << ": Error: unchecked::peek_next gave a different result than unchecked::next" << '\n';; - char_count++; - } - if (char_count != utf32_line.size()) - cout << "Line " << line_count << ": Error in iterating with unchecked::next - wrong number of characters" << '\n'; - - adv_it = line_start; - utf8::unchecked::advance(adv_it, char_count); - if (adv_it != line_end) - cout << "Line " << line_count << ": Error in unchecked::advance function" << '\n'; - - if (string::size_type(utf8::unchecked::distance(line_start, line_end)) != char_count) - cout << "Line " << line_count << ": Error in unchecked::distance function" << '\n'; - - while (it != line_start) { - unchecked::previous(it); - char_count--; - } - if (char_count != 0) - cout << "Line " << line_count << ": Error in iterating with unchecked::previous - wrong number of characters" << '\n'; - - // Try utf8::unchecked::iterator - utf8::unchecked::iterator un_u8it(line_start); - if (!utf32_line.empty() && *un_u8it != utf32_line.at(0)) - cout << "Line " << line_count << ": Error in utf::unchecked::iterator * operator" << '\n'; - if (std::distance(un_u8it, utf8::unchecked::iterator(line_end)) != static_cast(utf32_line.size())) - cout << "Line " << line_count << ": Error in using utf::unchecked::iterator with std::distance - wrong number of characters" << '\n'; - - std::advance(un_u8it, utf32_line.size()); - if (un_u8it != utf8::unchecked::iterator(line_end)) - cout << "Line " << line_count << ": Error in using utf::unchecked::iterator with std::advance" << '\n'; - } -} diff --git a/third-party/utf8cpp/tests/CMakeLists.txt b/third-party/utf8cpp/tests/CMakeLists.txt new file mode 100644 index 000000000..f3ce2584c --- /dev/null +++ b/third-party/utf8cpp/tests/CMakeLists.txt @@ -0,0 +1,43 @@ +add_executable(negative ${PROJECT_SOURCE_DIR}/tests/negative.cpp) +add_executable(cpp11 ${PROJECT_SOURCE_DIR}/tests/test_cpp11.cpp) +add_executable(cpp17 ${PROJECT_SOURCE_DIR}/tests/test_cpp17.cpp) +add_executable(apitests ${PROJECT_SOURCE_DIR}/tests/apitests.cpp) + +add_executable(noexceptionstests ${PROJECT_SOURCE_DIR}/tests/noexceptionstests.cpp) + +target_link_libraries(negative PRIVATE utf8::cpp) +target_link_libraries(cpp11 PRIVATE utf8::cpp) +target_link_libraries(cpp17 PRIVATE utf8::cpp) +target_link_libraries(apitests PRIVATE utf8::cpp) +target_link_libraries(noexceptionstests PRIVATE utf8::cpp) + +target_compile_options(${PROJECT_NAME} INTERFACE + $<$:/W4> + $<$>:-Wall -Wextra -Wpedantic -Wconversion>) + +target_compile_options(noexceptionstests PUBLIC -fno-exceptions) + +set_target_properties(negative apitests noexceptionstests + PROPERTIES + CXX_STANDARD 98 + CXX_STANDARD_REQUIRED YES + CXX_EXTENSIONS NO) + +set_target_properties(cpp11 + PROPERTIES + CXX_STANDARD 11 + CXX_STANDARD_REQUIRED YES + CXX_EXTENSIONS NO) + +set_target_properties(cpp17 + PROPERTIES + CXX_STANDARD 17 + CXX_STANDARD_REQUIRED YES + CXX_EXTENSIONS NO) + +add_test(negative_test negative ${PROJECT_SOURCE_DIR}/tests/test_data/utf8_invalid.txt) +add_test(cpp11_test cpp11) +add_test(cpp17_test cpp17) +add_test(api_test apitests) +add_test(noexceptions_test noexceptionstests) + diff --git a/third-party/utf8cpp/tests/apitests.cpp b/third-party/utf8cpp/tests/apitests.cpp new file mode 100644 index 000000000..083266d7d --- /dev/null +++ b/third-party/utf8cpp/tests/apitests.cpp @@ -0,0 +1,6 @@ +#include "../extern/ftest/ftest.h" + +#include "test_checked_api.h" +#include "test_checked_iterator.h" +#include "test_unchecked_api.h" +#include "test_unchecked_iterator.h" diff --git a/third-party/utf8cpp/tests/docker/Dockerfile b/third-party/utf8cpp/tests/docker/Dockerfile new file mode 100644 index 000000000..9df3717a1 --- /dev/null +++ b/third-party/utf8cpp/tests/docker/Dockerfile @@ -0,0 +1,5 @@ +FROM debian:buster-slim + +RUN apt-get update \ + && apt-get install -y make g++ cmake git \ + && rm -rf /var/lib/apt/lists/* diff --git a/third-party/utf8cpp/test_drivers/negative/negative.cpp b/third-party/utf8cpp/tests/negative.cpp similarity index 88% rename from third-party/utf8cpp/test_drivers/negative/negative.cpp rename to third-party/utf8cpp/tests/negative.cpp index 0f1015d0e..f1bcc993e 100644 --- a/third-party/utf8cpp/test_drivers/negative/negative.cpp +++ b/third-party/utf8cpp/tests/negative.cpp @@ -1,4 +1,4 @@ -#include "../../source/utf8.h" +#include "utf8.h" using namespace utf8; #include @@ -17,13 +17,13 @@ int main(int argc, char** argv) test_file_path = argv[1]; else { cout << "Wrong number of arguments" << endl; - exit(0); + return 1; } // Open the test file ifstream fs8(test_file_path.c_str()); if (!fs8.is_open()) { cout << "Could not open " << test_file_path << endl; - return 0; + return 1; } // Read it line by line @@ -38,16 +38,22 @@ int main(int argc, char** argv) bool expected_valid = (find(INVALID_LINES, INVALID_LINES_END, line_count) == INVALID_LINES_END); // Print out lines that contain unexpected invalid UTF-8 if (!is_valid(line.begin(), line.end())) { - if (expected_valid) + if (expected_valid) { cout << "Unexpected invalid utf-8 at line " << line_count << '\n'; + return 1; + } // try fixing it: string fixed_line; replace_invalid(line.begin(), line.end(), back_inserter(fixed_line)); - if (!is_valid(fixed_line.begin(), fixed_line.end())) + if (!is_valid(fixed_line.begin(), fixed_line.end())) { cout << "replace_invalid() resulted in an invalid utf-8 at line " << line_count << '\n'; + return 1; + } } - else if (!expected_valid) + else if (!expected_valid) { cout << "Invalid utf-8 NOT detected at line " << line_count << '\n'; + return 1; + } } } diff --git a/third-party/utf8cpp/tests/noexceptionstests.cpp b/third-party/utf8cpp/tests/noexceptionstests.cpp new file mode 100644 index 000000000..108ee750c --- /dev/null +++ b/third-party/utf8cpp/tests/noexceptionstests.cpp @@ -0,0 +1,4 @@ +#include "../extern/ftest/ftest.h" + +#include "test_unchecked_api.h" +#include "test_unchecked_iterator.h" diff --git a/third-party/utf8cpp/tests/test_checked_api.h b/third-party/utf8cpp/tests/test_checked_api.h new file mode 100644 index 000000000..3a7067b76 --- /dev/null +++ b/third-party/utf8cpp/tests/test_checked_api.h @@ -0,0 +1,198 @@ +#ifndef UTF8_FOR_CPP_TEST_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 +#define UTF8_FOR_CPP_TEST_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 + +#include "utf8.h" + +#include +#include +using namespace utf8; +using namespace std; + + +TEST(CheckedAPITests, test_append) +{ + unsigned char u[5] = {0,0,0,0,0}; + append(0x0448, u); + EXPECT_EQ (u[0], 0xd1); + EXPECT_EQ (u[1], 0x88); + EXPECT_EQ (u[2], 0); + EXPECT_EQ (u[3], 0); + EXPECT_EQ (u[4], 0); + + append(0x65e5, u); + EXPECT_EQ (u[0], 0xe6); + EXPECT_EQ (u[1], 0x97); + EXPECT_EQ (u[2], 0xa5); + EXPECT_EQ (u[3], 0); + EXPECT_EQ (u[4], 0); + + append(0x3044, u); + EXPECT_EQ (u[0], 0xe3); + EXPECT_EQ (u[1], 0x81); + EXPECT_EQ (u[2], 0x84); + EXPECT_EQ (u[3], 0); + EXPECT_EQ (u[4], 0); + + append(0x10346, u); + EXPECT_EQ (u[0], 0xf0); + EXPECT_EQ (u[1], 0x90); + EXPECT_EQ (u[2], 0x8d); + EXPECT_EQ (u[3], 0x86); + EXPECT_EQ (u[4], 0); + + // Ensure no warnings with plain char + char c[2] = {0,0}; + append('a', c); + EXPECT_EQ (c[0], 'a'); + EXPECT_EQ (c[1], 0); +} + +TEST(CheckedAPITests, test_next) +{ + const char* twochars = "\xe6\x97\xa5\xd1\x88"; + const char* w = twochars; + unsigned int cp = next(w, twochars + 6); + EXPECT_EQ (cp, 0x65e5); + EXPECT_EQ (w, twochars + 3); + + const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; + w = threechars; + + cp = next(w, threechars + 9); + EXPECT_EQ (cp, 0x10346); + EXPECT_EQ (w, threechars + 4); + + cp = next(w, threechars + 9); + EXPECT_EQ (cp, 0x65e5); + EXPECT_EQ (w, threechars + 7); + + cp = next(w, threechars + 9); + EXPECT_EQ (cp, 0x0448); + EXPECT_EQ (w, threechars + 9); +} + +TEST(CheckedAPITests, test_peek_next) +{ + const char* const cw = "\xe6\x97\xa5\xd1\x88"; + unsigned int cp = peek_next(cw, cw + 6); + EXPECT_EQ (cp, 0x65e5); +} + +TEST(CheckedAPITests, test_prior) +{ + const char* twochars = "\xe6\x97\xa5\xd1\x88"; + const char* w = twochars + 3; + unsigned int cp = prior (w, twochars); + EXPECT_EQ (cp, 0x65e5); + EXPECT_EQ (w, twochars); + + const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; + w = threechars + 9; + cp = prior(w, threechars); + EXPECT_EQ (cp, 0x0448); + EXPECT_EQ (w, threechars + 7); + cp = prior(w, threechars); + EXPECT_EQ (cp, 0x65e5); + EXPECT_EQ (w, threechars + 4); + cp = prior(w, threechars); + EXPECT_EQ (cp, 0x10346); + EXPECT_EQ (w, threechars); +} + +TEST(CheckedAPITests, test_advance) +{ + const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; + const char* w = threechars; + advance(w, 2, threechars + 9); + EXPECT_EQ(w, threechars + 7); + advance(w, -2, threechars); + EXPECT_EQ(w, threechars); + advance(w, 3, threechars + 9); + EXPECT_EQ(w, threechars + 9); + advance(w, -2, threechars); + EXPECT_EQ(w, threechars + 4); + advance(w, -1, threechars); + EXPECT_EQ(w, threechars); +} + +TEST(CheckedAPITests, test_distance) +{ + const char* twochars = "\xe6\x97\xa5\xd1\x88"; + size_t dist = static_cast(utf8::distance(twochars, twochars + 5)); + EXPECT_EQ (dist, 2); +} + +TEST(CheckedAPITests, test_utf32to8) +{ + unsigned int utf32string[] = {0x448, 0x65E5, 0x10346, 0}; + string utf8result; + utf32to8(utf32string, utf32string + 3, back_inserter(utf8result)); + EXPECT_EQ (utf8result.size(), 9); +} + +TEST(CheckedAPITests, test_utf8to32) +{ + const char* twochars = "\xe6\x97\xa5\xd1\x88"; + vector utf32result; + utf8to32(twochars, twochars + 5, back_inserter(utf32result)); + EXPECT_EQ (utf32result.size(), 2); +} + +TEST(CheckedAPITests, test_utf16to8) +{ + unsigned short utf16string[] = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e}; + string utf8result; + utf16to8(utf16string, utf16string + 5, back_inserter(utf8result)); + EXPECT_EQ (utf8result.size(), 10); +} + +TEST(CheckedAPITests, test_utf8to16) +{ + char utf8_with_surrogates[] = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"; + vector utf16result; + utf8to16(utf8_with_surrogates, utf8_with_surrogates + 9, back_inserter(utf16result)); + EXPECT_EQ (utf16result.size(), 4); + EXPECT_EQ (utf16result[2], 0xd834); + EXPECT_EQ (utf16result[3], 0xdd1e); +} + +TEST(CheckedAPITests, test_replace_invalid) +{ + char invalid_sequence[] = "a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z"; + vector replace_invalid_result; + replace_invalid (invalid_sequence, invalid_sequence + sizeof(invalid_sequence), std::back_inserter(replace_invalid_result), '?'); + bool bvalid = is_valid(replace_invalid_result.begin(), replace_invalid_result.end()); + EXPECT_TRUE (bvalid); + const char fixed_invalid_sequence[] = "a????z"; + EXPECT_EQ (sizeof(fixed_invalid_sequence), replace_invalid_result.size()); + EXPECT_TRUE (std::equal(replace_invalid_result.begin(), replace_invalid_result.begin() + sizeof(fixed_invalid_sequence), fixed_invalid_sequence)); +} + +TEST(CheckedAPITests, test_find_invalid) +{ + char utf_invalid[] = "\xe6\x97\xa5\xd1\x88\xfa"; + char* invalid = find_invalid(utf_invalid, utf_invalid + 6); + EXPECT_EQ (invalid, utf_invalid + 5); +} + +TEST(CheckedAPITests, test_is_valid) +{ + char utf_invalid[] = "\xe6\x97\xa5\xd1\x88\xfa"; + bool bvalid = is_valid(utf_invalid, utf_invalid + 6); + EXPECT_FALSE (bvalid); + char utf8_with_surrogates[] = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"; + bvalid = is_valid(utf8_with_surrogates, utf8_with_surrogates + 9); + EXPECT_TRUE (bvalid); +} + +TEST(CheckedAPITests, test_starts_with_bom) +{ + unsigned char byte_order_mark[] = {0xef, 0xbb, 0xbf}; + bool bbom = starts_with_bom(byte_order_mark, byte_order_mark + sizeof(byte_order_mark)); + EXPECT_TRUE (bbom); + const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; + bool no_bbom = starts_with_bom(threechars, threechars + sizeof(threechars)); + EXPECT_FALSE (no_bbom); +} + +#endif diff --git a/third-party/utf8cpp/tests/test_checked_iterator.h b/third-party/utf8cpp/tests/test_checked_iterator.h new file mode 100644 index 000000000..2829a734e --- /dev/null +++ b/third-party/utf8cpp/tests/test_checked_iterator.h @@ -0,0 +1,35 @@ +#ifndef UTF8_FOR_CPP_TEST_CHECKED_ITERATOR_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 +#define UTF8_FOR_CPP_TEST_CHECKED_ITERATOR_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 + +#include "utf8.h" + +using namespace utf8; + + +TEST(CheckedIteratrTests, test_increment) +{ + const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; + utf8::iterator it(threechars, threechars, threechars + 9); + utf8::iterator it2 = it; + EXPECT_EQ (it2, it); + EXPECT_EQ (*it, 0x10346); + EXPECT_EQ (*(++it), 0x65e5); + EXPECT_EQ ((*it++), 0x65e5); + EXPECT_EQ (*it, 0x0448); + EXPECT_NE (it, it2); + utf8::iterator endit (threechars + 9, threechars, threechars + 9); + EXPECT_EQ (++it, endit); +} + +TEST(CheckedIteratrTests, test_decrement) +{ + const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; + utf8::iterator it(threechars+9, threechars, threechars + 9); + EXPECT_EQ (*(--it), 0x0448); + EXPECT_EQ ((*it--), 0x0448); + EXPECT_EQ (*it, 0x65e5); + EXPECT_EQ (--it, utf8::iterator(threechars, threechars, threechars + 9)); + EXPECT_EQ (*it, 0x10346); +} + +#endif diff --git a/third-party/utf8cpp/tests/test_cpp11.cpp b/third-party/utf8cpp/tests/test_cpp11.cpp new file mode 100644 index 000000000..ee4ddd8fd --- /dev/null +++ b/third-party/utf8cpp/tests/test_cpp11.cpp @@ -0,0 +1,109 @@ +#include "../extern/ftest/ftest.h" +#include "utf8.h" +#include +using namespace utf8; +using namespace std; + +#if __cplusplus >= 201103L // C++ 11 or later + +TEST(CPP11APITests, test_append) +{ + string u; + append(0x0448, u); + EXPECT_EQ (u[0], char(0xd1)); + EXPECT_EQ (u[1], char(0x88)); + EXPECT_EQ (u.length(), 2); + + u.clear(); + append(0x65e5, u); + EXPECT_EQ (u[0], char(0xe6)); + EXPECT_EQ (u[1], char(0x97)); + EXPECT_EQ (u[2], char(0xa5)); + EXPECT_EQ (u.length(), 3); + + u.clear(); + append(0x3044, u); + EXPECT_EQ (u[0], char(0xe3)); + EXPECT_EQ (u[1], char(0x81)); + EXPECT_EQ (u[2], char(0x84)); + EXPECT_EQ (u.length(), 3); + + u.clear(); + append(0x10346, u); + EXPECT_EQ (u[0], char(0xf0)); + EXPECT_EQ (u[1], char(0x90)); + EXPECT_EQ (u[2], char(0x8d)); + EXPECT_EQ (u[3], char(0x86)); + EXPECT_EQ (u.length(), 4); +} + +TEST(CPP11APITests, test_utf16to8) +{ + u16string utf16string = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e}; + string u = utf16to8(utf16string); + EXPECT_EQ (u.size(), 10); +} + +TEST(CPP11APITests, test_utf8to16) +{ + string utf8_with_surrogates = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"; + u16string utf16result = utf8to16(utf8_with_surrogates); + EXPECT_EQ (utf16result.size(), 4); + EXPECT_EQ (utf16result[2], 0xd834); + EXPECT_EQ (utf16result[3], 0xdd1e); + // Just to make sure it compiles with string literals + utf8to16(u8"simple"); + utf8to16("simple"); +} + +TEST(CPP11APITests, test_utf32to8) +{ + u32string utf32string = {0x448, 0x65E5, 0x10346}; + string utf8result = utf32to8(utf32string); + EXPECT_EQ (utf8result.size(), 9); +} + +TEST(CPP11APITests, test_utf8to32) +{ + const char* twochars = "\xe6\x97\xa5\xd1\x88"; + u32string utf32result = utf8to32(twochars); + EXPECT_EQ (utf32result.size(), 2); +} + +TEST(CPP11APITests, test_find_invalid) +{ + string utf_invalid = "\xe6\x97\xa5\xd1\x88\xfa"; + auto invalid = find_invalid(utf_invalid); + EXPECT_EQ (invalid, 5); +} + +TEST(CPP11APITests, test_is_valid) +{ + string utf_invalid = "\xe6\x97\xa5\xd1\x88\xfa"; + bool bvalid = is_valid(utf_invalid); + EXPECT_FALSE (bvalid); + string utf8_with_surrogates = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"; + bvalid = is_valid(utf8_with_surrogates); + EXPECT_TRUE (bvalid); +} + +TEST(CPP11APITests, test_replace_invalid) +{ + string invalid_sequence = "a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z"; + string replace_invalid_result = replace_invalid(invalid_sequence, '?'); + bool bvalid = is_valid(replace_invalid_result); + EXPECT_TRUE (bvalid); + const string fixed_invalid_sequence = "a????z"; + EXPECT_EQ(fixed_invalid_sequence, replace_invalid_result); +} + +TEST(CPP11APITests, test_starts_with_bom) +{ + string byte_order_mark = {char(0xef), char(0xbb), char(0xbf)}; + bool bbom = starts_with_bom(byte_order_mark); + EXPECT_TRUE (bbom); + string threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; + bool no_bbom = starts_with_bom(threechars); + EXPECT_FALSE (no_bbom); +} +#endif // C++ 11 or later diff --git a/third-party/utf8cpp/tests/test_cpp17.cpp b/third-party/utf8cpp/tests/test_cpp17.cpp new file mode 100644 index 000000000..4b87816b1 --- /dev/null +++ b/third-party/utf8cpp/tests/test_cpp17.cpp @@ -0,0 +1,88 @@ +#include "../extern/ftest/ftest.h" +#include "utf8.h" +#include +using namespace utf8; +using namespace std; + +#if __cplusplus >= 201703L // C++ 17 or later + + +TEST(CPP17APITests, test_utf16to8) +{ + u16string utf16string = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e}; + u16string_view utf16stringview(u16string); + string u = utf16to8(utf16string); + EXPECT_EQ (u.size(), 10); +} + +TEST(CPP17APITests, test_utf8to16) +{ + string_view utf8_with_surrogates = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"; + u16string utf16result = utf8to16(utf8_with_surrogates); + EXPECT_EQ (utf16result.size(), 4); + EXPECT_EQ (utf16result[2], 0xd834); + EXPECT_EQ (utf16result[3], 0xdd1e); +} + +TEST(CPP17APITests, test_utf32to8) +{ + u32string utf32string = {0x448, 0x65E5, 0x10346}; + u32string_view utf32stringview(utf32string); + string utf8result = utf32to8(utf32stringview); + EXPECT_EQ (utf8result.size(), 9); +} + +TEST(CPP17APITests, test_utf8to32) +{ + string_view twochars = "\xe6\x97\xa5\xd1\x88"; + u32string utf32result = utf8to32(twochars); + EXPECT_EQ (utf32result.size(), 2); +} + +TEST(CPP17APITests, test_find_invalid) +{ + string_view utf_invalid = "\xe6\x97\xa5\xd1\x88\xfa"; + auto invalid = find_invalid(utf_invalid); + EXPECT_EQ (invalid, 5); +} + +TEST(CPP17APITests, test_is_valid) +{ + string_view utf_invalid = "\xe6\x97\xa5\xd1\x88\xfa"; + bool bvalid = is_valid(utf_invalid); + EXPECT_FALSE (bvalid); + string_view utf8_with_surrogates = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"; + bvalid = is_valid(utf8_with_surrogates); + EXPECT_TRUE (bvalid); +} + +TEST(CPP17APITests, test_replace_invalid) +{ + string_view invalid_sequence = "a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z"; + string replace_invalid_result = replace_invalid(invalid_sequence, '?'); + bool bvalid = is_valid(replace_invalid_result); + EXPECT_TRUE (bvalid); + const string fixed_invalid_sequence = "a????z"; + EXPECT_EQ(fixed_invalid_sequence, replace_invalid_result); +} + +TEST(CPP17APITests, test_starts_with_bom) +{ + string byte_order_mark = {char(0xef), char(0xbb), char(0xbf)}; + string_view byte_order_mark_view(byte_order_mark); + bool bbom = starts_with_bom(byte_order_mark_view); + EXPECT_TRUE (bbom); + string_view threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; + bool no_bbom = starts_with_bom(threechars); + EXPECT_FALSE (no_bbom); +} + +TEST(CPP17APITests, string_class_and_literals) +{ + const char* twochars = u8"ab"; + EXPECT_TRUE (is_valid(twochars)); + const string two_chars_string(twochars); + EXPECT_TRUE (is_valid(two_chars_string)); +} + +#endif // C++ 11 or later diff --git a/third-party/utf8cpp/test_data/negative/utf8_invalid.txt b/third-party/utf8cpp/tests/test_data/utf8_invalid.txt similarity index 100% rename from third-party/utf8cpp/test_data/negative/utf8_invalid.txt rename to third-party/utf8cpp/tests/test_data/utf8_invalid.txt diff --git a/third-party/utf8cpp/tests/test_unchecked_api.h b/third-party/utf8cpp/tests/test_unchecked_api.h new file mode 100644 index 000000000..10c5991ed --- /dev/null +++ b/third-party/utf8cpp/tests/test_unchecked_api.h @@ -0,0 +1,164 @@ +#ifndef UTF8_FOR_CPP_TEST_UNCHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 +#define UTF8_FOR_CPP_TEST_UNCHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 + +#include "utf8/unchecked.h" + +#include +#include + +using namespace std; + +TEST(UnCheckedAPITests, test_append) +{ + unsigned char u[5] = {0,0,0,0,0}; + utf8::unchecked::append(0x0448, u); + EXPECT_EQ (u[0], 0xd1); + EXPECT_EQ (u[1], 0x88); + EXPECT_EQ (u[2], 0); + EXPECT_EQ (u[3], 0); + EXPECT_EQ (u[4], 0); + + utf8::unchecked::append(0x65e5, u); + EXPECT_EQ (u[0], 0xe6); + EXPECT_EQ (u[1], 0x97); + EXPECT_EQ (u[2], 0xa5); + EXPECT_EQ (u[3], 0); + EXPECT_EQ (u[4], 0); + + utf8::unchecked::append(0x3044, u); + EXPECT_EQ (u[0], 0xe3); + EXPECT_EQ (u[1], 0x81); + EXPECT_EQ (u[2], 0x84); + EXPECT_EQ (u[3], 0); + EXPECT_EQ (u[4], 0); + + utf8::unchecked::append(0x10346, u); + EXPECT_EQ (u[0], 0xf0); + EXPECT_EQ (u[1], 0x90); + EXPECT_EQ (u[2], 0x8d); + EXPECT_EQ (u[3], 0x86); + EXPECT_EQ (u[4], 0); +} + +TEST(UnCheckedAPITests, test_next) +{ + const char* twochars = "\xe6\x97\xa5\xd1\x88"; + const char* w = twochars; + unsigned int cp = utf8::unchecked::next(w); + EXPECT_EQ (cp, 0x65e5); + EXPECT_EQ (w, twochars + 3); + + const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; + w = threechars; + + cp = utf8::unchecked::next(w); + EXPECT_EQ (cp, 0x10346); + EXPECT_EQ (w, threechars + 4); + + cp = utf8::unchecked::next(w); + EXPECT_EQ (cp, 0x65e5); + EXPECT_EQ (w, threechars + 7); + + cp = utf8::unchecked::next(w); + EXPECT_EQ (cp, 0x0448); + EXPECT_EQ (w, threechars + 9); +} + +TEST(UnCheckedAPITests, test_peek_next) +{ + const char* const cw = "\xe6\x97\xa5\xd1\x88"; + unsigned int cp = utf8::unchecked::peek_next(cw); + EXPECT_EQ (cp, 0x65e5); +} + +TEST(UnCheckedAPITests, test_prior) +{ + const char* twochars = "\xe6\x97\xa5\xd1\x88"; + const char* w = twochars + 3; + unsigned int cp = utf8::unchecked::prior (w); + EXPECT_EQ (cp, 0x65e5); + EXPECT_EQ (w, twochars); + + const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; + w = threechars + 9; + cp = utf8::unchecked::prior(w); + EXPECT_EQ (cp, 0x0448); + EXPECT_EQ (w, threechars + 7); + cp = utf8::unchecked::prior(w); + EXPECT_EQ (cp, 0x65e5); + EXPECT_EQ (w, threechars + 4); + cp = utf8::unchecked::prior(w); + EXPECT_EQ (cp, 0x10346); + EXPECT_EQ (w, threechars); +} + +TEST(UnCheckedAPITests, test_advance) +{ + const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; + const char* w = threechars; + utf8::unchecked::advance(w, 2); + EXPECT_EQ(w, threechars + 7); + utf8::unchecked::advance(w, -2); + EXPECT_EQ(w, threechars); + utf8::unchecked::advance(w, 3); + EXPECT_EQ(w, threechars + 9); + utf8::unchecked::advance(w, -2); + EXPECT_EQ(w, threechars + 4); + utf8::unchecked::advance(w, -1); + EXPECT_EQ(w, threechars); +} + +TEST(UnCheckedAPITests, test_distance) +{ + const char* twochars = "\xe6\x97\xa5\xd1\x88"; + size_t dist = static_cast(utf8::unchecked::distance(twochars, twochars + 5)); + EXPECT_EQ (dist, 2); +} + +TEST(UnCheckedAPITests, test_utf32to8) +{ + unsigned int utf32string[] = {0x448, 0x65E5, 0x10346, 0}; + string utf8result; + utf8::unchecked::utf32to8(utf32string, utf32string + 3, back_inserter(utf8result)); + EXPECT_EQ (utf8result.size(), 9); +} + +TEST(UnCheckedAPITests, test_utf8to32) +{ + const char* twochars = "\xe6\x97\xa5\xd1\x88"; + vector utf32result; + utf8::unchecked::utf8to32(twochars, twochars + 5, back_inserter(utf32result)); + EXPECT_EQ (utf32result.size(), 2); +} + +TEST(UnCheckedAPITests, test_utf16to8) +{ + unsigned short utf16string[] = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e}; + string utf8result; + utf8::unchecked::utf16to8(utf16string, utf16string + 5, back_inserter(utf8result)); + EXPECT_EQ (utf8result.size(), 10); +} + +TEST(UnCheckedAPITests, test_utf8to16) +{ + char utf8_with_surrogates[] = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"; + vector utf16result; + utf8::unchecked::utf8to16(utf8_with_surrogates, utf8_with_surrogates + 9, back_inserter(utf16result)); + EXPECT_EQ (utf16result.size(), 4); + EXPECT_EQ (utf16result[2], 0xd834); + EXPECT_EQ (utf16result[3], 0xdd1e); +} + +TEST(UnCheckedAPITests, test_replace_invalid) +{ + char invalid_sequence[] = "a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z"; + vector replace_invalid_result; + utf8::unchecked::replace_invalid (invalid_sequence, invalid_sequence + sizeof(invalid_sequence), std::back_inserter(replace_invalid_result), '?'); + bool bvalid = utf8::is_valid(replace_invalid_result.begin(), replace_invalid_result.end()); + EXPECT_TRUE (bvalid); + const char fixed_invalid_sequence[] = "a????z"; + EXPECT_EQ (sizeof(fixed_invalid_sequence), replace_invalid_result.size()); + EXPECT_TRUE (std::equal(replace_invalid_result.begin(), replace_invalid_result.begin() + sizeof(fixed_invalid_sequence), fixed_invalid_sequence)); +} + +#endif diff --git a/third-party/utf8cpp/tests/test_unchecked_iterator.h b/third-party/utf8cpp/tests/test_unchecked_iterator.h new file mode 100644 index 000000000..4294232d6 --- /dev/null +++ b/third-party/utf8cpp/tests/test_unchecked_iterator.h @@ -0,0 +1,36 @@ +#ifndef UTF8_FOR_CPP_TEST_UNCHECKED_ITERATOR_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 +#define UTF8_FOR_CPP_TEST_UNCHECKED_ITERATOR_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 + +#include "utf8/unchecked.h" + +using namespace utf8::unchecked; + + +TEST(UnCheckedIteratrTests, test_increment) +{ + const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; + utf8::unchecked::iterator it(threechars); + utf8::unchecked::iterator it2 = it; + EXPECT_EQ (it2, it); + EXPECT_EQ (*it, 0x10346); + EXPECT_EQ (*(++it), 0x65e5); + EXPECT_EQ ((*it++), 0x65e5); + EXPECT_EQ (*it, 0x0448); + EXPECT_NE (it, it2); + utf8::unchecked::iterator endit (threechars + 9); + EXPECT_EQ (++it, endit); +} + +TEST(UnCheckedIteratrTests, test_decrement) +{ + const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; + utf8::unchecked::iterator it(threechars+9); + EXPECT_EQ (*(--it), 0x0448); + EXPECT_EQ ((*it--), 0x0448); + EXPECT_EQ (*it, 0x65e5); + EXPECT_EQ (--it, utf8::unchecked::iterator(threechars)); + EXPECT_EQ (*it, 0x10346); + +} + +#endif diff --git a/third-party/utf8cpp/utf8cppConfig.cmake.in b/third-party/utf8cpp/utf8cppConfig.cmake.in new file mode 100644 index 000000000..450fe8d18 --- /dev/null +++ b/third-party/utf8cpp/utf8cppConfig.cmake.in @@ -0,0 +1,6 @@ +@PACKAGE_INIT@ + +include("${CMAKE_CURRENT_LIST_DIR}/utf8cppTargets.cmake") +check_required_components( "utf8cpp" ) + +add_library(utf8::cpp ALIAS utf8cpp)