commit bf22b894f256d34c163ab66f509bfc956a7c63fa Author: Leon Styhre Date: Wed Jan 3 17:24:45 2024 +0100 Squashed 'external/utfcpp/' content from commit 6be08bbea git-subtree-dir: external/utfcpp git-subtree-split: 6be08bbea14ffa0a5c594257fb6285a054395cd7 diff --git a/.github/workflows/cmake-multi-platform.yml b/.github/workflows/cmake-multi-platform.yml new file mode 100644 index 000000000..3ffcf0ca9 --- /dev/null +++ b/.github/workflows/cmake-multi-platform.yml @@ -0,0 +1,75 @@ +# This starter workflow is for a CMake project running on multiple platforms. There is a different starter workflow if you just want a single platform. +# See: https://github.com/actions/starter-workflows/blob/main/ci/cmake-single-platform.yml +name: CMake on multiple platforms + +on: + push: + branches: [ "master" ] + pull_request: + branches: [ "master" ] + +jobs: + build: + runs-on: ${{ matrix.os }} + + strategy: + # Set fail-fast to false to ensure that feedback is delivered for all matrix combinations. Consider changing this to true when your workflow is stable. + fail-fast: false + + # Set up a matrix to run the following 3 configurations: + # 1. + # 2. + # 3. + # + # To add more build types (Release, Debug, RelWithDebInfo, etc.) customize the build_type list. + matrix: + os: [ubuntu-latest, windows-latest] + build_type: [Release] + c_compiler: [gcc, clang, cl] + include: + - os: windows-latest + c_compiler: cl + cpp_compiler: cl + - os: ubuntu-latest + c_compiler: gcc + cpp_compiler: g++ + - os: ubuntu-latest + c_compiler: clang + cpp_compiler: clang++ + exclude: + - os: windows-latest + c_compiler: gcc + - os: windows-latest + c_compiler: clang + - os: ubuntu-latest + c_compiler: cl + + steps: + - uses: actions/checkout@v4 + + - name: Set reusable strings + # Turn repeated input strings (such as the build output directory) into step outputs. These step outputs can be used throughout the workflow file. + id: strings + shell: bash + run: | + echo "build-output-dir=${{ github.workspace }}/tests/build" >> "$GITHUB_OUTPUT" + + - name: Configure CMake + # Configure CMake in a 'build' subdirectory. `CMAKE_BUILD_TYPE` is only required if you are using a single-configuration generator such as make. + # See https://cmake.org/cmake/help/latest/variable/CMAKE_BUILD_TYPE.html?highlight=cmake_build_type + run: > + cmake -B ${{ steps.strings.outputs.build-output-dir }} + -DCMAKE_CXX_COMPILER=${{ matrix.cpp_compiler }} + -DCMAKE_C_COMPILER=${{ matrix.c_compiler }} + -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} + -S ${{ github.workspace }} + + - name: Build + # Build your program with the given configuration. Note that --config is needed because the default Windows generator is a multi-config generator (Visual Studio generator). + run: cmake --build ${{ steps.strings.outputs.build-output-dir }} --config ${{ matrix.build_type }} + + - name: Test + working-directory: ${{ steps.strings.outputs.build-output-dir }} + # Execute tests defined by the CMake configuration. Note that --build-config is needed because the default Windows generator is a multi-config generator (Visual Studio generator). + # See https://cmake.org/cmake/help/latest/manual/ctest.1.html for more detail + run: ctest -VV --build-config ${{ matrix.build_type }} diff --git a/.gitignore b/.gitignore new file mode 100644 index 000000000..488d51dd9 --- /dev/null +++ b/.gitignore @@ -0,0 +1,4 @@ +# VS Code: +.vscode/ +# Often used by CMake +build/ \ No newline at end of file diff --git a/.gitmodules b/.gitmodules new file mode 100644 index 000000000..424f86b76 --- /dev/null +++ b/.gitmodules @@ -0,0 +1,3 @@ +[submodule "extern/ftest"] + path = extern/ftest + url = https://github.com/nemtrif/ftest diff --git a/CMakeLists.txt b/CMakeLists.txt new file mode 100644 index 000000000..f24f9b659 --- /dev/null +++ b/CMakeLists.txt @@ -0,0 +1,53 @@ +# This file is deprecated and will be removed in a future release +# Please see the instructions for installation in README.md file + +cmake_minimum_required (VERSION 3.14...3.27) +project (utf8cpp + VERSION 4.0.4 + LANGUAGES CXX + DESCRIPTION "C++ portable library for working with utf-8 encoding") + +add_library(${PROJECT_NAME} INTERFACE) + +include(GNUInstallDirs) + +target_include_directories(utf8cpp INTERFACE + "$" + $ +) + +include(CMakePackageConfigHelpers) +write_basic_package_version_file( + "${PROJECT_BINARY_DIR}/${PROJECT_NAME}ConfigVersion.cmake" + VERSION ${PROJECT_VERSION} + COMPATIBILITY SameMajorVersion + ARCH_INDEPENDENT +) + +install(TARGETS ${PROJECT_NAME} + EXPORT ${PROJECT_NAME}Targets + LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR} + ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR} + RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR} + PUBLIC_HEADER DESTINATION include COMPONENT Development + BUNDLE DESTINATION bin COMPONENT Runtime +) + +configure_package_config_file( + "${PROJECT_SOURCE_DIR}/${PROJECT_NAME}Config.cmake.in" + "${PROJECT_BINARY_DIR}/${PROJECT_NAME}Config.cmake" + INSTALL_DESTINATION ${CMAKE_INSTALL_DATAROOTDIR}/${PROJECT_NAME}/cmake +) + +install(EXPORT ${PROJECT_NAME}Targets + FILE ${PROJECT_NAME}Targets.cmake + NAMESPACE ${PROJECT_NAME}:: + DESTINATION ${CMAKE_INSTALL_DATAROOTDIR}/${PROJECT_NAME}/cmake) + +install(FILES "${PROJECT_BINARY_DIR}/${PROJECT_NAME}Config.cmake" + "${PROJECT_BINARY_DIR}/${PROJECT_NAME}ConfigVersion.cmake" + DESTINATION ${CMAKE_INSTALL_DATAROOTDIR}/${PROJECT_NAME}/cmake) + +install(FILES ${PROJECT_SOURCE_DIR}/source/utf8.h DESTINATION include/utf8cpp) +install(DIRECTORY ${PROJECT_SOURCE_DIR}/source/utf8 DESTINATION + include/utf8cpp) diff --git a/LICENSE b/LICENSE new file mode 100644 index 000000000..36b7cd93c --- /dev/null +++ b/LICENSE @@ -0,0 +1,23 @@ +Boost Software License - Version 1.0 - August 17th, 2003 + +Permission is hereby granted, free of charge, to any person or organization +obtaining a copy of the software and accompanying documentation covered by +this license (the "Software") to use, reproduce, display, distribute, +execute, and transmit the Software, and to prepare derivative works of the +Software, and to permit third-parties to whom the Software is furnished to +do so, all subject to the following: + +The copyright notices in the Software and this entire statement, including +the above license grant, this restriction and the following disclaimer, +must be included in all copies of the Software, in whole or in part, and +all derivative works of the Software, unless such copies or derivative +works are solely in the form of machine-executable object code generated by +a source language processor. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT +SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE +FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE, +ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER +DEALINGS IN THE SOFTWARE. diff --git a/README.md b/README.md new file mode 100644 index 000000000..37f3de739 --- /dev/null +++ b/README.md @@ -0,0 +1,2131 @@ + + +# UTF8-CPP: UTF-8 with C++ in a Portable Way + + + +## Introduction + +C++ developers still 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. Some progress has been made in the later editions of the standard, but it is still hard to work with Unicode using only the standard facilities. + +I came up with a small, C++98 compatible generic library in order to handle UTF-8 encoded strings. 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 since the first release in 2006 both in commercial and open-source projects and proved to be stable and useful. + +## Table of Contents + +- [UTF8-CPP: UTF-8 with C++ in a Portable Way](#utf8-cpp-utf-8-with-c-in-a-portable-way) + * [Introduction](#introduction) + * [Installation](#installation) + * [Examples of use](#examples-of-use) + + [Introductory Sample](#introductory-sample) + + [Checking if a file contains valid UTF-8 text](#checking-if-a-file-contains-valid-utf-8-text) + + [Ensure that a string contains valid UTF-8 text](#ensure-that-a-string-contains-valid-utf-8-text) + * [Points of interest](#points-of-interest) + - [Design goals and decisions](#design-goals-and-decisions) + - [Alternatives](#alternatives) + * [Reference](#reference) + + [Functions From utf8 Namespace](#functions-from-utf8-namespace) + - [utf8::append](#utf8append) + * [octet_iterator append(utfchar32_t cp, octet_iterator result)](#octet_iterator-appendutfchar32_t-cp-octet_iterator-result) + * [void append(utfchar32_t cp, std::string& s);](#void-appendutfchar32_t-cp-stdstring-s) + - [utf8::append16](#utf8append16) + * [word_iterator append16(utfchar32_t cp, word_iterator result)](#word_iterator-append16utfchar32_t-cp-word_iterator-result) + * [void append(utfchar32_t cp, std::u16string& s)](#void-appendutfchar32_t-cp-stdu16string-s) + - [utf8::next](#utf8next) + - [utf8::next16](#utf8next16) + - [utf8::peek_next](#utf8peek_next) + - [utf8::prior](#utf8prior) + - [utf8::advance](#utf8advance) + - [utf8::distance](#utf8distance) + - [utf8::utf16to8](#utf8utf16to8) + * [octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result)](#octet_iterator-utf16to8-u16bit_iterator-start-u16bit_iterator-end-octet_iterator-result) + * [std::string utf16to8(const std::u16string& s)](#stdstring-utf16to8const-stdu16string-s) + * [std::string utf16to8(std::u16string_view s)](#stdstring-utf16to8stdu16string_view-s) + - [utf8::utf16tou8](#utf8utf16tou8) + * [std::u8string utf16tou8(const std::u16string& s)](#stdu8string-utf16tou8const-stdu16string-s) + * [std::u8string utf16tou8(const std::u16string_view& s)](#stdu8string-utf16tou8const-stdu16string_view-s) + - [utf8::utf8to16](#utf8utf8to16) + * [u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result)](#u16bit_iterator-utf8to16-octet_iterator-start-octet_iterator-end-u16bit_iterator-result) + * [std::u16string utf8to16(const std::string& s)](#stdu16string-utf8to16const-stdstring-s) + * [std::u16string utf8to16(std::string_view s)](#stdu16string-utf8to16stdstring_view-s) + * [std::u16string utf8to16(std::u8string& s)](#stdu16string-utf8to16stdu8string-s) + * [std::u16string utf8to16(std::u8string_view& s)](#stdu16string-utf8to16stdu8string_view-s) + - [utf8::utf32to8](#utf8utf32to8) + * [octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result)](#octet_iterator-utf32to8-u32bit_iterator-start-u32bit_iterator-end-octet_iterator-result) + * [std::string utf32to8(const std::u32string& s)](#stdstring-utf32to8const-stdu32string-s) + * [std::u8string utf32to8(const std::u32string& s)](#stdu8string-utf32to8const-stdu32string-s) + * [std::u8string utf32to8(const std::u32string_view& s)](#stdu8string-utf32to8const-stdu32string_view-s) + * [std::string utf32to8(const std::u32string& s)](#stdstring-utf32to8const-stdu32string-s-1) + * [std::string utf32to8(std::u32string_view s)](#stdstring-utf32to8stdu32string_view-s) + - [utf8::utf8to32](#utf8utf8to32) + * [u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result)](#u32bit_iterator-utf8to32-octet_iterator-start-octet_iterator-end-u32bit_iterator-result) + * [std::u32string utf8to32(const std::u8string& s)](#stdu32string-utf8to32const-stdu8string-s) + * [std::u32string utf8to32(const std::u8string_view& s)](#stdu32string-utf8to32const-stdu8string_view-s) + * [std::u32string utf8to32(const std::string& s)](#stdu32string-utf8to32const-stdstring-s) + * [std::u32string utf8to32(std::string_view s)](#stdu32string-utf8to32stdstring_view-s) + - [utf8::find_invalid](#utf8find_invalid) + * [octet_iterator find_invalid(octet_iterator start, octet_iterator end)](#octet_iterator-find_invalidoctet_iterator-start-octet_iterator-end) + * [const char* find_invalid(const char* str)](#const-char-find_invalidconst-char-str) + * [std::size_t find_invalid(const std::string& s)](#stdsize_t-find_invalidconst-stdstring-s) + * [std::size_t find_invalid(std::string_view s)](#stdsize_t-find_invalidstdstring_view-s) + - [utf8::is_valid](#utf8is_valid) + * [bool is_valid(octet_iterator start, octet_iterator end)](#bool-is_validoctet_iterator-start-octet_iterator-end) + * [bool is_valid(const char* str)](#bool-is_validconst-char-str) + * [bool is_valid(const std::string& s)](#bool-is_validconst-stdstring-s) + * [bool is_valid(std::string_view s)](#bool-is_validstdstring_view-s) + - [utf8::replace_invalid](#utf8replace_invalid) + * [output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, utfchar32_t replacement)](#output_iterator-replace_invalidoctet_iterator-start-octet_iterator-end-output_iterator-out-utfchar32_t-replacement) + * [std::string replace_invalid(const std::string& s, utfchar32_t replacement)](#stdstring-replace_invalidconst-stdstring-s-utfchar32_t-replacement) + * [std::string replace_invalid(std::string_view s, char32_t replacement)](#stdstring-replace_invalidstdstring_view-s-char32_t-replacement) + - [utf8::starts_with_bom](#utf8starts_with_bom) + * [bool starts_with_bom (octet_iterator it, octet_iterator end)](#bool-starts_with_bom-octet_iterator-it-octet_iterator-end) + * [bool starts_with_bom(const std::string& s)](#bool-starts_with_bomconst-stdstring-s) + * [bool starts_with_bom(std::string_view s)](#bool-starts_with_bomstdstring_view-s) + + [Types From utf8 Namespace](#types-from-utf8-namespace) + - [utf8::exception](#utf8exception) + - [utf8::invalid_code_point](#utf8invalid_code_point) + - [utf8::invalid_utf8](#utf8invalid_utf8) + - [utf8::invalid_utf16](#utf8invalid_utf16) + - [utf8::not_enough_room](#utf8not_enough_room) + - [utf8::iterator](#utf8iterator) + * [Member functions](#member-functions) + + [Functions From utf8::unchecked Namespace](#functions-from-utf8unchecked-namespace) + - [utf8::unchecked::append](#utf8uncheckedappend) + - [utf8::unchecked::append16](#utf8uncheckedappend16) + - [utf8::unchecked::next](#utf8uncheckednext) + - [utf8::next16](#utf8next16-1) + - [utf8::unchecked::peek_next](#utf8uncheckedpeek_next) + - [utf8::unchecked::prior](#utf8uncheckedprior) + - [utf8::unchecked::advance](#utf8uncheckedadvance) + - [utf8::unchecked::distance](#utf8uncheckeddistance) + - [utf8::unchecked::utf16to8](#utf8uncheckedutf16to8) + - [utf8::unchecked::utf8to16](#utf8uncheckedutf8to16) + - [utf8::unchecked::utf32to8](#utf8uncheckedutf32to8) + - [utf8::unchecked::utf8to32](#utf8uncheckedutf8to32) + - [utf8::unchecked::replace_invalid](#utf8uncheckedreplace_invalid) + + [Types From utf8::unchecked Namespace](#types-from-utf8unchecked-namespace) + - [utf8::iterator](#utf8iterator-1) + * [Member functions](#member-functions-1) + + + + + +## Installation + +This is a header-only library and the supported way of deploying it is: +- Download a release from https://github.com/nemtrif/utfcpp/releases into a temporary directory +- Unzip the release +- Copy the content of utfcpp/source file into the directory where you keep include files for your project + + +The CMakeList.txt file was originally made for testing purposes only, but unfortunately over time I accepted contributions that added install target. *This is not a supported way of installing the utfcpp library* and I am considering removing the CMakeList.txt in a future release. + + +## Examples of use + + +### Introductory Sample + +To illustrate the use of the library, let's start with a small but complete program that opens a file containing UTF-8 encoded text, reads it line by line, checks each line for invalid UTF-8 byte sequences, and converts it to UTF-16 encoding and back to UTF-8: + +```cpp +#include +#include +#include +#include +#include "utf8.h" +using namespace std; +int main(int argc, char** argv) +{ + if (argc != 2) { + cout << "\nUsage: docsample filename\n"; + return 0; + } + const char* test_file_path = argv[1]; + // 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; + } + + 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) +#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)); +#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: + +```cpp +bool valid_utf8_file(const char* file_name) +{ + ifstream ifs(file_name); + if (!ifs) + return false; // even better, throw here + + istreambuf_iterator it(ifs.rdbuf()); + istreambuf_iterator eos; + + return utf8::is_valid(it, eos); +} +``` + +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: + +```cpp + utf8::utf8to16(it, eos, back_inserter(u16string)); +``` + + +### Ensure that a string contains valid UTF-8 text + +If we have some text that "probably" contains UTF-8 encoded text and we want to replace any invalid UTF-8 sequence with a replacement character, something like the following function may be used: + +```cpp +void fix_utf8_string(std::string& str) +{ + std::string temp; + utf8::replace_invalid(str.begin(), str.end(), back_inserter(temp)); + str = temp; +} +``` + +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 across 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 + +For alternatives and comparisons, I recommend the following article: [The Wonderfully Terrible World of C and C++ Encoding APIs (with Some Rust)](https://thephd.dev/the-c-c++-rust-string-text-encoding-api-landscape), by JeanHeyd Meneide. In the article, this library is compared with: + +- [simdutf](https://github.com/simdutf/simdutf) +- [iconv](https://www.gnu.org/software/libiconv/) +- [boost.text](https://github.com/tzlaine/text) +- [ICU](https://unicode-org.github.io/icu/userguide/conversion/converters.html) +- [encoding_rs](https://github.com/hsivonen/encoding_rs) +- [Windows API functions for converting text between encodings](https://learn.microsoft.com/en-us/windows/win32/api/stringapiset/) +- [ztd.text](https://github.com/soasis/text/) + +The article presents author's view of the quality of the API design, but also some speed benchmarks. + + +## Reference + + +### Functions From utf8 Namespace + + +#### utf8::append + + +##### octet_iterator append(utfchar32_t cp, octet_iterator result) + +Available in version 1.0 and later. + +Encodes a 32 bit code point as a UTF-8 sequence of octets and appends the sequence to a UTF-8 string. + +```cpp +template +octet_iterator append(utfchar32_t cp, octet_iterator result); +``` + +`octet_iterator`: an output iterator. +`cp`: a 32 bit integer representing a code point to append to the sequence. +`result`: an output iterator to the place in the sequence where to append the code point. +Return value: an iterator pointing to the place after the newly appended sequence. + +Example of use: + +```cpp +unsigned char u[5] = {0,0,0,0,0}; +unsigned char* end = append(0x0448, u); +assert (u[0] == 0xd1 && u[1] == 0x88 && u[2] == 0 && u[3] == 0 && u[4] == 0); +``` + +Note that `append` does not allocate any memory - it is the burden of the caller to make sure there is enough memory allocated for the operation. To make things more interesting, `append` can add anywhere between 1 and 4 octets to the sequence. In practice, you would most often want to use `std::back_inserter` to ensure that the necessary memory is allocated. + +In case of an invalid code point, a `utf8::invalid_code_point` exception is thrown. + + + +##### void append(utfchar32_t cp, std::string& s); + +Available in version 3.0 and later. Prior to 4.0 it required a C++ 11 compiler; the requirement is lifted with 4.0. + +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(utfchar32_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::append16 + +##### word_iterator append16(utfchar32_t cp, word_iterator result) + +Available in version 4.0 and later. + +Encodes a 32 bit code point as a UTF-16 sequence of words and appends the sequence to a UTF-16 string. + +```cpp +template +word_iterator append16(utfchar32_t cp, word_iterator result); +``` + +`word_iterator`: an output iterator. +`cp`: a 32 bit integer representing a code point to append to the sequence. +`result`: an output iterator to the place in the sequence where to append the code point. +Return value: an iterator pointing to the place after the newly appended sequence. + +Example of use: + +```cpp +unsigned short u[2] = {0,0}; +unsigned short* end = append16(0x0448, u); +assert (u[0] == 0x0448 && u[1] == 0); +``` + +Note that `append16` does not allocate any memory - it is the burden of the caller to make sure there is enough memory allocated for the operation. To make things more interesting, `append16` can add either one or two words to the sequence. In practice, you would most often want to use `std::back_inserter` to ensure that the necessary memory is allocated. + +In case of an invalid code point, a `utf8::invalid_code_point` exception is thrown. + + + +##### void append(utfchar32_t cp, std::u16string& s) + +Available in version 4.0 and later. Requires a C++11 compliant compiler. + +Encodes a 32 bit code point as a UTF-16 sequence of words and appends the sequence to a UTF-16 string. + +```cpp +void append(utfchar32_t cp, std::u16string& s); +``` + +`cp`: a code point to append to the string. +`s`: a utf-16 encoded string to append the code point to. + +Example of use: + +```cpp +std::u16string u; +append(0x0448, u); +assert (u[0] == 0x0448 && u.length() == 1); +``` + +In case of an invalid code point, a `utf8::invalid_code_point` exception is thrown. + + + +#### utf8::next + +Available in version 1.0 and later. + +Given the iterator to the beginning of the UTF-8 sequence, it returns the code point and moves the iterator to the next position. + +```cpp +template +utfchar32_t next(octet_iterator& it, octet_iterator end); +``` + +`octet_iterator`: an input iterator. +`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 beginning of the next code point. +`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. +Return value: the 32 bit representation of the processed UTF-8 code point. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +char* w = twochars; +int cp = next(w, twochars + 6); +assert (cp == 0x65e5); +assert (w == twochars + 3); +``` + +This function is typically used to iterate through a UTF-8 encoded string. + +In case of an invalid UTF-8 sequence, a `utf8::invalid_utf8` exception is thrown. + + +#### utf8::next16 + +Available in version 4.0 and later. + +Given the iterator to the beginning of the UTF-16 sequence, it returns the code point and moves the iterator to the next position. + +```cpp +template +utfchar32_t next16(word_iterator& it, word_iterator end); +``` + +`word_iterator`: an input iterator. +`it`: a reference to an iterator pointing to the beginning of an UTF-16 encoded code point. After the function returns, it is incremented to point to the beginning of the next code point. +`end`: end of the UTF-16 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. +Return value: the 32 bit representation of the processed UTF-16 code point. + +Example of use: + +```cpp +const unsigned short u[3] = {0x65e5, 0xd800, 0xdf46}; +const unsigned short* w = u; +int cp = next16(w, w + 3); +assert (cp, 0x65e5); +assert (w, u + 1); +``` + +This function is typically used to iterate through a UTF-16 encoded string. + +In case of an invalid UTF-16 sequence, a `utf8::invalid_utf8` exception is thrown. + + + +#### utf8::peek_next + +Available in version 2.1 and later. + +Given the iterator to the beginning of the UTF-8 sequence, it returns the code point for the following sequence without changing the value of the iterator. + +```cpp +template +utfchar32_t peek_next(octet_iterator it, octet_iterator end); +``` + + +`octet_iterator`: an input iterator. +`it`: an iterator pointing to the beginning of an UTF-8 encoded code point. +`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. +Return value: the 32 bit representation of the processed UTF-8 code point. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +char* w = twochars; +int cp = peek_next(w, twochars + 6); +assert (cp == 0x65e5); +assert (w == twochars); +``` + +In case of an invalid UTF-8 sequence, a `utf8::invalid_utf8` exception is thrown. + + +#### utf8::prior + +Available in version 1.02 and later. + +Given a reference to an iterator pointing to an octet in a UTF-8 sequence, 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 +utfchar32_t prior(octet_iterator& it, octet_iterator start); +``` + +`octet_iterator`: a bidirectional 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. +`start`: an iterator to the beginning of the sequence where the search for the beginning of a code point is performed. 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 = prior (w, twochars); +assert (cp == 0x65e5); +assert (w == twochars); +``` + +This function has two purposes: one is two iterate backwards through a UTF-8 encoded string. Note that it is usually a better idea to iterate forward instead, since `utf8::next` is faster. The second purpose is to find a beginning of a UTF-8 sequence if we have a random position within a string. Note that in that case `utf8::prior` may not detect an invalid UTF-8 sequence in some scenarios: for instance if there are superfluous trail octets, it will just skip them. + +`it` will typically point to the beginning of a code point, and `start` will point to 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 `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. + +In case `start` equals `it`, a `not_enough_room` exception is thrown. + + +#### utf8::advance +Available in version 1.0 and later. + +Advances an iterator by the specified number of code points within an UTF-8 sequence. + +```cpp +template +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`: 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: + +```cpp +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); +``` + +In case of an invalid code point, a `utf8::invalid_code_point` exception is thrown. + + +#### utf8::distance + +Available in version 1.0 and later. + +Given the iterators to two UTF-8 encoded code points in a sequence, returns the number of code points between them. + +```cpp +template +typename std::iterator_traits::difference_type distance (octet_iterator first, octet_iterator last); +``` + +`octet_iterator`: an input iterator. +`first`: an iterator to a beginning of a UTF-8 encoded code point. +`last`: an iterator to a "post-end" of the last UTF-8 encoded code point in the sequence we are trying to determine the length. It can be the beginning of a new code point, or not. + Return value the distance between the iterators, in code points. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +size_t dist = utf8::distance(twochars, twochars + 5); +assert (dist == 2); +``` + +This function is used to find the length (in code points) of a UTF-8 encoded string. The reason it is called _distance_, rather than, say, _length_ is mainly because developers are used that _length_ is an O(1) function. Computing the length of an UTF-8 string is a linear operation, and it looked better to model it after `std::distance` algorithm. + +In case of an invalid UTF-8 sequence, a `utf8::invalid_utf8` exception is thrown. If `last` does not point to the past-of-end of a UTF-8 sequence, a `utf8::not_enough_room` exception is thrown. + + +#### utf8::utf16to8 + +##### octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result) + +Available in version 1.0 and later. + +Converts a UTF-16 encoded string to UTF-8. + +```cpp +template +octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result); +``` + +`u16bit_iterator`: an input iterator. +`octet_iterator`: an output iterator. +`start`: an iterator pointing to the beginning of the UTF-16 encoded string to convert. +`end`: an iterator pointing to pass-the-end of the UTF-16 encoded string to convert. +`result`: an output iterator to the place in the UTF-8 string where to append the result of conversion. +Return value: An iterator pointing to the place after the appended UTF-8 string. + +Example of use: + +```cpp +unsigned short utf16string[] = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e}; +vector utf8result; +utf16to8(utf16string, utf16string + 5, back_inserter(utf8result)); +assert (utf8result.size() == 10); +``` + +In case of invalid UTF-16 sequence, a `utf8::invalid_utf16` exception is thrown. + + + +##### std::string utf16to8(const std::u16string& s) + +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. + + +##### std::string utf16to8(std::u16string_view s) + +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::utf16tou8 + +##### std::u8string utf16tou8(const std::u16string& s) + +Available in version 4.0 and later. Requires a C++ 20 compliant compiler. + +Converts a UTF-16 encoded string to UTF-8. + +```cpp +std::u8string utf16tou8(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}; + u8string u = utf16tou8(utf16string); + assert (u.size() == 10); +``` + +In case of invalid UTF-16 sequence, a `utf8::invalid_utf16` exception is thrown. + + +##### std::u8string utf16tou8(const std::u16string_view& s) + +Available in version 4.0 and later. Requires a C++ 20 compliant compiler. + +Converts a UTF-16 encoded string to UTF-8. + +```cpp +std::u8string utf16tou8(const 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); + u8string u = utf16tou8(utf16string); + assert (u.size() == 10); +``` + +In case of invalid UTF-16 sequence, a `utf8::invalid_utf16` exception is thrown. + + +#### utf8::utf8to16 + +##### u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result) + +Available in version 1.0 and later. + +Converts an UTF-8 encoded string to UTF-16 + +```cpp +template +u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result); +``` + +`octet_iterator`: an input iterator. +`u16bit_iterator`: an output iterator. +`start`: an iterator pointing to the beginning of the UTF-8 encoded string to convert. +`end`: an iterator pointing to pass-the-end of the UTF-8 encoded string to convert. +`result`: an output iterator to the place in the UTF-16 string where to append the result of conversion. +Return value: An iterator pointing to the place after the appended UTF-16 string. + +Example of use: + +```cpp +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); +``` + +In case of an invalid UTF-8 sequence, a `utf8::invalid_utf8` exception is thrown. If `end` does not point to the past-of-end of a UTF-8 sequence, a `utf8::not_enough_room` exception is thrown. + + + + +##### std::u16string utf8to16(const std::string& s) + +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 sequence, a `utf8::invalid_utf8` exception is thrown. + + + +##### std::u16string utf8to16(std::string_view s) + +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 sequence, a `utf8::invalid_utf8` exception is thrown. + + + +##### std::u16string utf8to16(std::u8string& s) + +Available in version 4.0 and later. Requires a C++ 20 compliant compiler. + +Converts an UTF-8 encoded string to UTF-16. + +```cpp +std::u16string utf8to16(std::u8string& s); +``` + +`s`: an UTF-8 encoded string to convert. +Return value: A UTF-16 encoded string + +Example of use: + +```cpp +std::u8string utf8_with_surrogates = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"; +std::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 sequence, a `utf8::invalid_utf8` exception is thrown. + + + +##### std::u16string utf8to16(std::u8string_view& s) + +Available in version 4.0 and later. Requires a C++ 20 compliant compiler. + +Converts an UTF-8 encoded string to UTF-16. + +```cpp +std::u16string utf8to16(std::u8string_view& s); +``` + +`s`: an UTF-8 encoded string to convert. +Return value: A UTF-16 encoded string + +Example of use: + +```cpp +std::u8string utf8_with_surrogates = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"; +std::u8string_view utf8stringview {utf8_with_surrogates} +std::u16string utf16result = utf8to16(utf8stringview); +assert (utf16result.length() == 4); +assert (utf16result[2] == 0xd834); +assert (utf16result[3] == 0xdd1e); +``` + +In case of an invalid UTF-8 sequence, a `utf8::invalid_utf8` exception is thrown. + + +#### utf8::utf32to8 + +##### octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result) + +Available in version 1.0 and later. + +Converts a UTF-32 encoded string to UTF-8. + +```cpp +template +octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result); +``` + +`octet_iterator`: an output iterator. +`u32bit_iterator`: an input iterator. +`start`: an iterator pointing to the beginning of the UTF-32 encoded string to convert. +`end`: an iterator pointing to pass-the-end of the UTF-32 encoded string to convert. +`result`: an output iterator to the place in the UTF-8 string where to append the result of conversion. +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)); +assert (utf8result.size() == 9); +``` + +In case of invalid UTF-32 string, a `utf8::invalid_code_point` exception is thrown. + + + +##### std::string utf32to8(const std::u32string& s) + +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. + + +##### std::u8string utf32to8(const std::u32string& s) + +Available in version 4.0 and later. Requires a C++ 20 compliant compiler. + +Converts a UTF-32 encoded string to UTF-8. + +```cpp +std::u8string 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}; +u8string utf8result = utf32to8(utf32string); +assert (utf8result.size() == 9); +``` + +In case of invalid UTF-32 string, a `utf8::invalid_code_point` exception is thrown. + + + +##### std::u8string utf32to8(const std::u32string_view& s) + +Available in version 4.0 and later. Requires a C++ 20 compliant compiler. + +Converts a UTF-32 encoded string to UTF-8. + +```cpp +std::u8string utf32to8(const 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); +u8string utf8result = utf32to8(utf32stringview); +assert (utf8result.size() == 9); +``` + +In case of invalid UTF-32 string, a `utf8::invalid_code_point` exception is thrown. + + + +##### std::string utf32to8(const std::u32string& s) + +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. + + +##### std::string utf32to8(std::u32string_view s) + +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::utf8to32 + +##### u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result) + +Available in version 1.0 and later. + +Converts a UTF-8 encoded string to UTF-32. + +```cpp +template +u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result); +``` + +`octet_iterator`: an input iterator. +`u32bit_iterator`: an output iterator. +`start`: an iterator pointing to the beginning of the UTF-8 encoded string to convert. +`end`: an iterator pointing to pass-the-end of the UTF-8 encoded string to convert. +`result`: an output iterator to the place in the UTF-32 string where to append the result of conversion. +Return value: An iterator pointing to the place after the appended UTF-32 string. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +vector utf32result; +utf8to32(twochars, twochars + 5, back_inserter(utf32result)); +assert (utf32result.size() == 2); +``` + +In case of an invalid UTF-8 sequence, a `utf8::invalid_utf8` exception is thrown. If `end` does not point to the past-of-end of a UTF-8 sequence, a `utf8::not_enough_room` exception is thrown. + + + + +##### std::u32string utf8to32(const std::u8string& s) + +Available in version 4.0 and later. Requires a C++ 20 compliant compiler. + +Converts a UTF-8 encoded string to UTF-32. + +```cpp +std::u32string utf8to32(const std::u8string& s); +``` + +`s`: a UTF-8 encoded string. +Return value: a UTF-32 encoded string. + +Example of use: + +```cpp +const std::u8string* twochars = u8"\xe6\x97\xa5\xd1\x88"; +u32string utf32result = utf8to32(twochars); +assert (utf32result.size() == 2); +``` + +In case of an invalid UTF-8 sequence, a `utf8::invalid_utf8` exception is thrown. + + + +##### std::u32string utf8to32(const std::u8string_view& s) + +Available in version 4.0 and later. Requires a C++ 20 compliant compiler. + +Converts a UTF-8 encoded string to UTF-32. + +```cpp +std::u32string utf8to32(const std::u8string_view& s); +``` + +`s`: a UTF-8 encoded string. +Return value: a UTF-32 encoded string. + +Example of use: + +```cpp +const u8string* twochars = u8"\xe6\x97\xa5\xd1\x88"; +const u8string_view stringview{twochars}; +u32string utf32result = utf8to32(stringview); +assert (utf32result.size() == 2); +``` + +In case of an invalid UTF-8 sequence, a `utf8::invalid_utf8` exception is thrown. + + + +##### std::u32string utf8to32(const std::string& s) + +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 sequence, a `utf8::invalid_utf8` exception is thrown. + + +##### std::u32string utf8to32(std::string_view s) + +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 sequence, a `utf8::invalid_utf8` exception is thrown. + + +#### utf8::find_invalid + +##### octet_iterator find_invalid(octet_iterator start, octet_iterator end) + +Available in version 1.0 and later. + +Detects an invalid sequence within a UTF-8 string. + +```cpp +template +octet_iterator find_invalid(octet_iterator start, octet_iterator end); +``` + +`octet_iterator`: an input iterator. +`start`: an iterator pointing to the beginning of the UTF-8 string to test for validity. +`end`: an iterator pointing to pass-the-end of the UTF-8 string to test for validity. +Return value: an iterator pointing to the first invalid octet in the UTF-8 string. In case none were found, equals `end`. + +Example of use: + +```cpp +char utf_invalid[] = "\xe6\x97\xa5\xd1\x88\xfa"; +char* invalid = find_invalid(utf_invalid, utf_invalid + 6); +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. + + + +##### const char* find_invalid(const char* str) + +Available in version 4.0 and later. + +Detects an invalid sequence within a C-style UTF-8 string. + +```cpp +const char* find_invalid(const char* str); +``` + +`str`: a UTF-8 encoded string. +Return value: a pointer to the first invalid octet in the UTF-8 string. In case none were found, points to the trailing zero byte. + +Example of use: + +```cpp +const char* utf_invalid = "\xe6\x97\xa5\xd1\x88\xfa"; +const char* invalid = find_invalid(utf_invalid); +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. + + +##### std::size_t find_invalid(const std::string& s) + +Available in version 3.0 and later. Prior to 4.0 it required a C++ 11 compiler; the requirement is lifted with 4.0 + +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. + + +##### std::size_t find_invalid(std::string_view s) + +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::is_valid + +##### bool is_valid(octet_iterator start, octet_iterator end) + +Available in version 1.0 and later. + +Checks whether a sequence of octets is a valid UTF-8 string. + +```cpp +template +bool is_valid(octet_iterator start, octet_iterator end); +``` + +`octet_iterator`: an input iterator. +`start`: an iterator pointing to the beginning of the UTF-8 string to test for validity. +`end`: an iterator pointing to pass-the-end of the UTF-8 string to test for validity. +Return value: `true` if the sequence is a valid UTF-8 string; `false` if not. + +Example of use: + +```cpp +char utf_invalid[] = "\xe6\x97\xa5\xd1\x88\xfa"; +bool bvalid = is_valid(utf_invalid, utf_invalid + 6); +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 sequence is a valid UTF-8 string without the need to know where it fails if it is not valid. + + + +##### bool is_valid(const char* str) + +Available in version 4.0 and later. + +Checks whether a C-style string contains valid UTF-8 encoded text. + +```cpp +bool is_valid(const char* str); +``` + +`str`: 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. + + + +##### bool is_valid(const std::string& s) + +Available in version 3.0 and later. Prior to 4.0 it required a C++ 11 compiler; the requirement is lifted with 4.0 + +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. + + +##### bool is_valid(std::string_view s) + +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::replace_invalid + +##### output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, utfchar32_t replacement) + +Available in version 2.0 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, utfchar32_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; +replace_invalid (invalid_sequence, invalid_sequence + sizeof(invalid_sequence), back_inserter(replace_invalid_result), '?'); +bvalid = 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. + + + +##### std::string replace_invalid(const std::string& s, utfchar32_t replacement) + +Available in version 3.0 and later. Prior to 4.0 it required a C++ 11 compiler; the requirement is lifted with 4.0 + +Replaces all invalid UTF-8 sequences within a string with a replacement marker. + +```cpp +std::string replace_invalid(const std::string& s, utfchar32_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); +``` + + +##### std::string replace_invalid(std::string_view s, char32_t replacement) + +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::starts_with_bom + +##### bool starts_with_bom (octet_iterator it, octet_iterator end) + +Available in version 2.3 and later. + +Checks whether an octet sequence starts with a UTF-8 byte order mark (BOM) + +```cpp +template +bool starts_with_bom (octet_iterator it, octet_iterator end); +``` + +`octet_iterator`: an input iterator. +`it`: beginning of the octet sequence to check +`end`: pass-end of the sequence to check +Return value: `true` if the sequence starts with a UTF-8 byte order mark; `false` if not. + +Example of use: + +```cpp +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); +``` + +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. + + + +##### bool starts_with_bom(const std::string& s) + +Available in version 3.0 and later. Prior to 4.0 it required a C++ 11 compiler; the requirement is lifted with 4.0 + +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. + + + +##### bool starts_with_bom(std::string_view s) + +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. + + + +### Types From utf8 Namespace + + +#### utf8::exception + +Available in version 2.3 and later. + +Base class for the exceptions thrown by UTF CPP library functions. + +```cpp +class exception : public std::exception {}; +``` + +Example of use: + +```cpp +try { + code_that_uses_utf_cpp_library(); +} +catch(const utf8::exception& utfcpp_ex) { + cerr << utfcpp_ex.what(); +} +``` + + +#### utf8::invalid_code_point + +Available in version 1.0 and later. + +Thrown by UTF8 CPP functions such as `advance` and `next` if an UTF-8 sequence represents and invalid code point. + +```cpp +class invalid_code_point : public exception { +public: + utfchar32_t code_point() const; +}; +``` + +Member function `code_point()` can be used to determine the invalid code point that caused the exception to be thrown. + + +#### utf8::invalid_utf8 + +Available in version 1.0 and later. + +Thrown by UTF8 CPP functions such as `next` and `prior` if an invalid UTF-8 sequence is detected during decoding. + +```cpp +class invalid_utf8 : public exception { +public: + utfchar8_t utf8_octet() const; +}; +``` + +Member function `utf8_octet()` can be used to determine the beginning of the byte sequence that caused the exception to be thrown. + + +#### utf8::invalid_utf16 + +Available in version 1.0 and later. + +Thrown by UTF8 CPP function `utf16to8` if an invalid UTF-16 sequence is detected during decoding. + +```cpp +class invalid_utf16 : public exception { +public: + utfchar16_t utf16_word() const; +}; +``` + +Member function `utf16_word()` can be used to determine the UTF-16 code unit that caused the exception to be thrown. + + +#### utf8::not_enough_room + +Available in version 1.0 and later. + +Thrown by UTF8 CPP functions such as `next` if the end of the decoded UTF-8 sequence was reached before the code point was decoded. + +```cpp +class not_enough_room : public exception {}; +``` + + +#### utf8::iterator + +Available in version 2.0 and later. + +Adapts the underlying octet iterator to iterate over the sequence of code points, rather than raw octets. + +```cpp +template +class iterator; +``` + + +##### Member functions + +`iterator();` the default 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. + +`utfchar32_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 underlying iterators are equal. + +`bool operator != (const iterator& rhs) const;` returns `true` if the two underlying 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: + +```cpp +char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; +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); +``` + +The purpose of `utf8::iterator` adapter is to enable easy iteration as well as the use of STL algorithms with UTF-8 encoded strings. Increment and decrement operators are implemented in terms of `utf8::next()` and `utf8::prior()` functions. + +Note that `utf8::iterator` adapter is a checked iterator. It operates on the range specified in the constructor; any attempt to go out of that range will result in an exception. Even the comparison operators require both iterator object to be constructed against the same range - otherwise an exception is thrown. Typically, the range will be determined by sequence container functions `begin` and `end`, i.e.: + +```cpp +std::string s = "example"; +utf8::iterator i (s.begin(), s.begin(), s.end()); +``` + + +### Functions From utf8::unchecked Namespace + + +#### utf8::unchecked::append + +Available in version 1.0 and later. + +Encodes a 32 bit code point as a UTF-8 sequence of octets and appends the sequence to a UTF-8 string. + +```cpp +template +octet_iterator append(utfchar32_t cp, octet_iterator result); +``` + +`cp`: A 32 bit integer representing a code point to append to the sequence. +`result`: An output iterator to the place in the sequence where to append the code point. +Return value: An iterator pointing to the place after the newly appended sequence. + +Example of use: + +```cpp +unsigned char u[5] = {0,0,0,0,0}; +unsigned char* end = unchecked::append(0x0448, u); +assert (u[0] == 0xd1 && u[1] == 0x88 && u[2] == 0 && u[3] == 0 && u[4] == 0); +``` + +This is a faster but less safe version of `utf8::append`. It does not check for validity of the supplied code point, and may produce an invalid UTF-8 sequence. + + +#### utf8::unchecked::append16 + +Available in version 4.0 and later. + +Encodes a 32 bit code point as a UTF-16 sequence of words and appends the sequence to a UTF-16 string. + +```cpp +template +word_iterator append16(utfchar32_t cp, word_iterator result) +``` + +`cp`: A 32 bit integer representing a code point to append to the sequence. +`result`: An output iterator to the place in the sequence where to append the code point. +Return value: An iterator pointing to the place after the newly appended sequence. + +Example of use: + +```cpp +unsigned short u[5] = {0,0}; +utf8::unchecked::append16(0x0448, u); +assert(u[0], 0x0448); +assert(u[1], 0x0000); +``` + +This is a faster but less safe version of `utf8::append`. It does not check for validity of the supplied code point, and may produce an invalid UTF-8 sequence. + + + +#### utf8::unchecked::next + +Available in version 1.0 and later. + +Given the iterator to the beginning of a UTF-8 sequence, it returns the code point and moves the iterator to the next position. + +```cpp +template +utfchar32_t next(octet_iterator& it); +``` + +`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 beginning of the next code point. + Return value: the 32 bit representation of the processed UTF-8 code point. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +char* w = twochars; +int cp = unchecked::next(w); +assert (cp == 0x65e5); +assert (w == twochars + 3); +``` + +This is a faster but less safe version of `utf8::next`. It does not check for validity of the supplied UTF-8 sequence. + + +#### utf8::next16 + +Available in version 4.0 and later. + +Given the iterator to the beginning of the UTF-16 sequence, it returns the code point and moves the iterator to the next position. + +```cpp +template +utfchar32_t next16(word_iterator& it); +``` + +`word_iterator`: an input iterator. +`it`: a reference to an iterator pointing to the beginning of an UTF-16 encoded code point. After the function returns, it is incremented to point to the beginning of the next code point. + +Return value: the 32 bit representation of the processed UTF-16 code point. + +Example of use: + +```cpp +const unsigned short u[3] = {0x65e5, 0xd800, 0xdf46}; +const unsigned short* w = u; +int cp = unchecked::next16(w); +assert (cp, 0x65e5); +assert (w, u + 1); +``` + +This function is typically used to iterate through a UTF-16 encoded string. + +This is a faster but less safe version of `utf8::next16`. It does not check for validity of the supplied UTF-8 sequence. + + + +#### utf8::unchecked::peek_next + +Available in version 2.1 and later. + +Given the iterator to the beginning of a UTF-8 sequence, it returns the code point. + +```cpp +template +utfchar32_t peek_next(octet_iterator it); +``` + +`it`: an iterator pointing to the beginning of an UTF-8 encoded code point. +Return value: the 32 bit representation of the processed UTF-8 code point. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +char* w = twochars; +int cp = unchecked::peek_next(w); +assert (cp == 0x65e5); +assert (w == twochars); +``` + +This is a faster but less safe version of `utf8::peek_next`. It does not check for validity of the supplied UTF-8 sequence. + + +#### utf8::unchecked::prior + +Available in version 1.02 and later. + +Given a reference to an iterator pointing to an octet in a UTF-8 sequence, 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 +utfchar32_t prior(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::prior (w); +assert (cp == 0x65e5); +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::advance + +Available in version 1.0 and later. + +Advances an iterator by the specified number of code points within an UTF-8 sequence. + +```cpp +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`: number of code points `it` should be advanced. A negative value means decrement. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +char* w = twochars; +unchecked::advance (w, 2); +assert (w == twochars + 5); +``` + +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 + +Available in version 1.0 and later. + +Given the iterators to two UTF-8 encoded code points in a sequence, returns the number of code points between them. + +```cpp +template +typename std::iterator_traits::difference_type distance (octet_iterator first, octet_iterator last); +``` + +`first`: an iterator to a beginning of a UTF-8 encoded code point. +`last`: an iterator to a "post-end" of the last UTF-8 encoded code point in the sequence we are trying to determine the length. It can be the beginning of a new code point, or not. +Return value: the distance between the iterators, in code points. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +size_t dist = utf8::unchecked::distance(twochars, twochars + 5); +assert (dist == 2); +``` + +This is a faster but less safe version of `utf8::distance`. It does not check for validity of the supplied UTF-8 sequence. + + +#### utf8::unchecked::utf16to8 + +Available in version 1.0 and later. + +Converts a UTF-16 encoded string to UTF-8. + +```cpp +template +octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result); +``` + +`start`: an iterator pointing to the beginning of the UTF-16 encoded string to convert. +`end`: an iterator pointing to pass-the-end of the UTF-16 encoded string to convert. +`result`: an output iterator to the place in the UTF-8 string where to append the result of conversion. +Return value: An iterator pointing to the place after the appended UTF-8 string. + +Example of use: + +```cpp +unsigned short utf16string[] = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e}; +vector utf8result; +unchecked::utf16to8(utf16string, utf16string + 5, back_inserter(utf8result)); +assert (utf8result.size() == 10); +``` + +This is a faster but less safe version of `utf8::utf16to8`. It does not check for validity of the supplied UTF-16 sequence. + + +#### utf8::unchecked::utf8to16 + +Available in version 1.0 and later. + +Converts an UTF-8 encoded string to UTF-16 + +```cpp +template +u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result); +``` + +`start`: an iterator pointing to the beginning of the UTF-8 encoded string to convert. +`end`: an iterator pointing to pass-the-end of the UTF-8 encoded string to convert. +`result`: an output iterator to the place in the UTF-16 string where to append the result of conversion. +Return value: An iterator pointing to the place after the appended UTF-16 string. + +Example of use: + +```cpp +char utf8_with_surrogates[] = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"; +vector utf16result; +unchecked::utf8to16(utf8_with_surrogates, utf8_with_surrogates + 9, back_inserter(utf16result)); +assert (utf16result.size() == 4); +assert (utf16result[2] == 0xd834); +assert (utf16result[3] == 0xdd1e); +``` + +This is a faster but less safe version of `utf8::utf8to16`. It does not check for validity of the supplied UTF-8 sequence. + + +#### utf8::unchecked::utf32to8 + +Available in version 1.0 and later. + +Converts a UTF-32 encoded string to UTF-8. + +```cpp +template +octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result); +``` + +`start`: an iterator pointing to the beginning of the UTF-32 encoded string to convert. +`end`: an iterator pointing to pass-the-end of the UTF-32 encoded string to convert. +`result`: an output iterator to the place in the UTF-8 string where to append the result of conversion. +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)); +assert (utf8result.size() == 9); +``` + +This is a faster but less safe version of `utf8::utf32to8`. It does not check for validity of the supplied UTF-32 sequence. + + +#### utf8::unchecked::utf8to32 + +Available in version 1.0 and later. + +Converts a UTF-8 encoded string to UTF-32. + +```cpp +template +u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result); +``` + +`start`: an iterator pointing to the beginning of the UTF-8 encoded string to convert. +`end`: an iterator pointing to pass-the-end of the UTF-8 encoded string to convert. +`result`: an output iterator to the place in the UTF-32 string where to append the result of conversion. +Return value: An iterator pointing to the place after the appended UTF-32 string. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +vector utf32result; +unchecked::utf8to32(twochars, twochars + 5, back_inserter(utf32result)); +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, utfchar32_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 + +Available in version 2.0 and later. + +Adapts the underlying octet iterator to iterate over the sequence of code points, rather than raw octets. + +```cpp +template +class iterator; +``` + + +##### Member functions + +`iterator();` the default 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`. + +`octet_iterator base () const;` returns the underlying octet_iterator. + +`utfchar32_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 underlying iterators are equal. + +`bool operator != (const iterator& rhs) const;` returns `true` if the two underlying 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: + +```cpp +char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; +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 == 0x0448); +assert (un_it != un_it2); +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); +``` + +This is an unchecked version of `utf8::iterator`. It is faster in many cases, but offers no validity or range checks. + diff --git a/extern/ftest b/extern/ftest new file mode 160000 index 000000000..c4ad4af09 --- /dev/null +++ b/extern/ftest @@ -0,0 +1 @@ +Subproject commit c4ad4af0946b73ce1a40cbc72205d15d196c7e06 diff --git a/source/utf8.h b/source/utf8.h new file mode 100644 index 000000000..b51353093 --- /dev/null +++ b/source/utf8.h @@ -0,0 +1,46 @@ +// Copyright 2006 Nemanja Trifunovic + +/* +Permission is hereby granted, free of charge, to any person or organization +obtaining a copy of the software and accompanying documentation covered by +this license (the "Software") to use, reproduce, display, distribute, +execute, and transmit the Software, and to prepare derivative works of the +Software, and to permit third-parties to whom the Software is furnished to +do so, all subject to the following: + +The copyright notices in the Software and this entire statement, including +the above license grant, this restriction and the following disclaimer, +must be included in all copies of the Software, in whole or in part, and +all derivative works of the Software, unless such copies or derivative +works are solely in the form of machine-executable object code generated by +a source language processor. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT +SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE +FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE, +ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER +DEALINGS IN THE SOFTWARE. +*/ + + +#ifndef UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731 +#define UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731 + +/* +To control the C++ language version used by the library, you can define UTF_CPP_CPLUSPLUS macro +and set it to one of the values used by the __cplusplus predefined macro. + +For instance, + #define UTF_CPP_CPLUSPLUS 199711L +will cause the UTF-8 CPP library to use only types and language features available in the C++ 98 standard. +Some library features will be disabled. + +If you leave UTF_CPP_CPLUSPLUS undefined, it will be internally assigned to __cplusplus. +*/ + +#include "utf8/checked.h" +#include "utf8/unchecked.h" + +#endif // header guard diff --git a/source/utf8/checked.h b/source/utf8/checked.h new file mode 100644 index 000000000..98949f8bc --- /dev/null +++ b/source/utf8/checked.h @@ -0,0 +1,359 @@ +// Copyright 2006-2016 Nemanja Trifunovic + +/* +Permission is hereby granted, free of charge, to any person or organization +obtaining a copy of the software and accompanying documentation covered by +this license (the "Software") to use, reproduce, display, distribute, +execute, and transmit the Software, and to prepare derivative works of the +Software, and to permit third-parties to whom the Software is furnished to +do so, all subject to the following: + +The copyright notices in the Software and this entire statement, including +the above license grant, this restriction and the following disclaimer, +must be included in all copies of the Software, in whole or in part, and +all derivative works of the Software, unless such copies or derivative +works are solely in the form of machine-executable object code generated by +a source language processor. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT +SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE +FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE, +ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER +DEALINGS IN THE SOFTWARE. +*/ + + +#ifndef UTF8_FOR_CPP_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 +#define UTF8_FOR_CPP_CHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 + +#include "core.h" +#include + +namespace utf8 +{ + // Base for the exceptions that may be thrown from the library + class exception : public ::std::exception { + }; + + // Exceptions that may be thrown from the library functions. + class invalid_code_point : public exception { + utfchar32_t cp; + public: + invalid_code_point(utfchar32_t codepoint) : cp(codepoint) {} + virtual const char* what() const UTF_CPP_NOEXCEPT UTF_CPP_OVERRIDE { return "Invalid code point"; } + utfchar32_t code_point() const {return cp;} + }; + + class invalid_utf8 : public exception { + utfchar8_t u8; + public: + invalid_utf8 (utfchar8_t u) : u8(u) {} + invalid_utf8 (char c) : u8(static_cast(c)) {} + virtual const char* what() const UTF_CPP_NOEXCEPT UTF_CPP_OVERRIDE { return "Invalid UTF-8"; } + utfchar8_t utf8_octet() const {return u8;} + }; + + class invalid_utf16 : public exception { + utfchar16_t u16; + public: + invalid_utf16 (utfchar16_t u) : u16(u) {} + virtual const char* what() const UTF_CPP_NOEXCEPT UTF_CPP_OVERRIDE { return "Invalid UTF-16"; } + utfchar16_t utf16_word() const {return u16;} + }; + + class not_enough_room : public exception { + public: + 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 + + template + octet_iterator append(utfchar32_t cp, octet_iterator result) + { + if (!utf8::internal::is_code_point_valid(cp)) + throw invalid_code_point(cp); + + return internal::append(cp, result); + } + + inline void append(utfchar32_t cp, std::string& s) + { + append(cp, std::back_inserter(s)); + } + + template + word_iterator append16(utfchar32_t cp, word_iterator result) + { + if (!utf8::internal::is_code_point_valid(cp)) + throw invalid_code_point(cp); + + return internal::append16(cp, result); + } + + template + output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, utfchar32_t replacement) + { + while (start != end) { + octet_iterator sequence_start = start; + internal::utf_error err_code = utf8::internal::validate_next(start, end); + switch (err_code) { + case internal::UTF8_OK : + for (octet_iterator it = sequence_start; it != start; ++it) + *out++ = *it; + break; + case internal::NOT_ENOUGH_ROOM: + out = utf8::append (replacement, out); + start = end; + break; + case internal::INVALID_LEAD: + out = utf8::append (replacement, out); + ++start; + break; + case internal::INCOMPLETE_SEQUENCE: + case internal::OVERLONG_SEQUENCE: + case internal::INVALID_CODE_POINT: + out = utf8::append (replacement, out); + ++start; + // just one replacement mark for the sequence + while (start != end && utf8::internal::is_trail(*start)) + ++start; + break; + } + } + return out; + } + + template + inline output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out) + { + static const utfchar32_t replacement_marker = utf8::internal::mask16(0xfffd); + return utf8::replace_invalid(start, end, out, replacement_marker); + } + + inline std::string replace_invalid(const std::string& s, utfchar32_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; + } + + template + utfchar32_t next(octet_iterator& it, octet_iterator end) + { + utfchar32_t cp = 0; + internal::utf_error err_code = utf8::internal::validate_next(it, end, cp); + switch (err_code) { + case internal::UTF8_OK : + break; + case internal::NOT_ENOUGH_ROOM : + throw not_enough_room(); + case internal::INVALID_LEAD : + case internal::INCOMPLETE_SEQUENCE : + case internal::OVERLONG_SEQUENCE : + throw invalid_utf8(static_cast(*it)); + case internal::INVALID_CODE_POINT : + throw invalid_code_point(cp); + } + return cp; + } + + template + utfchar32_t next16(word_iterator& it, word_iterator end) + { + utfchar32_t cp = 0; + internal::utf_error err_code = utf8::internal::validate_next16(it, end, cp); + if (err_code == internal::NOT_ENOUGH_ROOM) + throw not_enough_room(); + return cp; + } + + template + utfchar32_t peek_next(octet_iterator it, octet_iterator end) + { + return utf8::next(it, end); + } + + template + utfchar32_t prior(octet_iterator& it, octet_iterator start) + { + // can't do much if it == start + if (it == start) + throw not_enough_room(); + + octet_iterator end = it; + // Go back until we hit either a lead octet or start + while (utf8::internal::is_trail(*(--it))) + if (it == start) + throw invalid_utf8(*it); // error - no lead byte in the sequence + return utf8::peek_next(it, end); + } + + template + void advance (octet_iterator& it, distance_type n, octet_iterator end) + { + const distance_type zero(0); + if (n < zero) { + // backward + for (distance_type i = n; i < zero; ++i) + utf8::prior(it, end); + } else { + // forward + for (distance_type i = zero; i < n; ++i) + utf8::next(it, end); + } + } + + template + typename std::iterator_traits::difference_type + distance (octet_iterator first, octet_iterator last) + { + typename std::iterator_traits::difference_type dist; + for (dist = 0; first < last; ++dist) + utf8::next(first, last); + return dist; + } + + template + octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result) + { + while (start != end) { + utfchar32_t cp = utf8::internal::mask16(*start++); + // Take care of surrogate pairs first + if (utf8::internal::is_lead_surrogate(cp)) { + if (start != end) { + const utfchar32_t trail_surrogate = utf8::internal::mask16(*start++); + if (utf8::internal::is_trail_surrogate(trail_surrogate)) + cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET; + else + throw invalid_utf16(static_cast(trail_surrogate)); + } + else + throw invalid_utf16(static_cast(cp)); + + } + // Lone trail surrogate + else if (utf8::internal::is_trail_surrogate(cp)) + throw invalid_utf16(static_cast(cp)); + + result = utf8::append(cp, result); + } + return result; + } + + template + u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result) + { + while (start < end) { + const utfchar32_t cp = utf8::next(start, end); + if (cp > 0xffff) { //make a surrogate pair + *result++ = static_cast((cp >> 10) + internal::LEAD_OFFSET); + *result++ = static_cast((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN); + } + else + *result++ = static_cast(cp); + } + return result; + } + + template + octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result) + { + while (start != end) + result = utf8::append(*(start++), result); + + return result; + } + + template + u32bit_iterator utf8to32 (octet_iterator start, octet_iterator end, u32bit_iterator result) + { + while (start < end) + (*result++) = utf8::next(start, end); + + return result; + } + + // The iterator class + template + class iterator { + octet_iterator it; + octet_iterator range_start; + octet_iterator range_end; + public: + typedef utfchar32_t value_type; + typedef utfchar32_t* pointer; + typedef utfchar32_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, + const octet_iterator& rangeend) : + it(octet_it), range_start(rangestart), range_end(rangeend) + { + if (it < range_start || it > range_end) + throw std::out_of_range("Invalid utf-8 iterator position"); + } + // the default "big three" are OK + octet_iterator base () const { return it; } + utfchar32_t operator * () const + { + octet_iterator temp = it; + return utf8::next(temp, range_end); + } + bool operator == (const iterator& rhs) const + { + if (range_start != rhs.range_start || range_end != rhs.range_end) + throw std::logic_error("Comparing utf-8 iterators defined with different ranges"); + return (it == rhs.it); + } + bool operator != (const iterator& rhs) const + { + return !(operator == (rhs)); + } + iterator& operator ++ () + { + utf8::next(it, range_end); + return *this; + } + iterator operator ++ (int) + { + iterator temp = *this; + utf8::next(it, range_end); + return temp; + } + iterator& operator -- () + { + utf8::prior(it, range_start); + return *this; + } + iterator operator -- (int) + { + iterator temp = *this; + utf8::prior(it, range_start); + return temp; + } + }; // class iterator + +} // namespace utf8 + +#if UTF_CPP_CPLUSPLUS >= 202002L // C++ 20 or later +#include "cpp20.h" +#elif 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/source/utf8/core.h b/source/utf8/core.h new file mode 100644 index 000000000..4494c538e --- /dev/null +++ b/source/utf8/core.h @@ -0,0 +1,492 @@ +// Copyright 2006 Nemanja Trifunovic + +/* +Permission is hereby granted, free of charge, to any person or organization +obtaining a copy of the software and accompanying documentation covered by +this license (the "Software") to use, reproduce, display, distribute, +execute, and transmit the Software, and to prepare derivative works of the +Software, and to permit third-parties to whom the Software is furnished to +do so, all subject to the following: + +The copyright notices in the Software and this entire statement, including +the above license grant, this restriction and the following disclaimer, +must be included in all copies of the Software, in whole or in part, and +all derivative works of the Software, unless such copies or derivative +works are solely in the form of machine-executable object code generated by +a source language processor. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT +SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE +FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE, +ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER +DEALINGS IN THE SOFTWARE. +*/ + + +#ifndef UTF8_FOR_CPP_CORE_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 +#define UTF8_FOR_CPP_CORE_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 + +#include +#include +#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 code units +#if UTF_CPP_CPLUSPLUS >= 201103L // C++ 11 or later + #if UTF_CPP_CPLUSPLUS >= 202002L // C++ 20 or later + typedef char8_t utfchar8_t; + #else // C++ 11/14/17 + typedef unsigned char utfchar8_t; + #endif + typedef char16_t utfchar16_t; + typedef char32_t utfchar32_t; +#else // C++ 98/03 + typedef unsigned char utfchar8_t; + typedef unsigned short utfchar16_t; + typedef unsigned int utfchar32_t; +#endif // C++ 11 or later + +// Helper code - not intended to be directly called by the library users. May be changed at any time +namespace internal +{ + // Unicode constants + // Leading (high) surrogates: 0xd800 - 0xdbff + // Trailing (low) surrogates: 0xdc00 - 0xdfff + const utfchar16_t LEAD_SURROGATE_MIN = 0xd800u; + const utfchar16_t LEAD_SURROGATE_MAX = 0xdbffu; + const utfchar16_t TRAIL_SURROGATE_MIN = 0xdc00u; + const utfchar16_t TRAIL_SURROGATE_MAX = 0xdfffu; + const utfchar16_t LEAD_OFFSET = 0xd7c0u; // LEAD_SURROGATE_MIN - (0x10000 >> 10) + const utfchar32_t SURROGATE_OFFSET = 0xfca02400u; // 0x10000u - (LEAD_SURROGATE_MIN << 10) - TRAIL_SURROGATE_MIN + + // Maximum valid value for a Unicode code point + const utfchar32_t CODE_POINT_MAX = 0x0010ffffu; + + template + inline utfchar8_t mask8(octet_type oc) + { + return static_cast(0xff & oc); + } + template + inline utfchar16_t mask16(u16_type oc) + { + return static_cast(0xffff & oc); + } + + template + inline bool is_trail(octet_type oc) + { + return ((utf8::internal::mask8(oc) >> 6) == 0x2); + } + + inline bool is_lead_surrogate(utfchar32_t cp) + { + return (cp >= LEAD_SURROGATE_MIN && cp <= LEAD_SURROGATE_MAX); + } + + inline bool is_trail_surrogate(utfchar32_t cp) + { + return (cp >= TRAIL_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX); + } + + inline bool is_surrogate(utfchar32_t cp) + { + return (cp >= LEAD_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX); + } + + inline bool is_code_point_valid(utfchar32_t cp) + { + return (cp <= CODE_POINT_MAX && !utf8::internal::is_surrogate(cp)); + } + + inline bool is_in_bmp(utfchar32_t cp) + { + return cp < utfchar32_t(0x10000); + } + + template + int sequence_length(octet_iterator lead_it) + { + const utfchar8_t lead = utf8::internal::mask8(*lead_it); + if (lead < 0x80) + return 1; + else if ((lead >> 5) == 0x6) + return 2; + else if ((lead >> 4) == 0xe) + return 3; + else if ((lead >> 3) == 0x1e) + return 4; + else + return 0; + } + + inline bool is_overlong_sequence(utfchar32_t cp, int length) + { + if (cp < 0x80) { + if (length != 1) + return true; + } + else if (cp < 0x800) { + if (length != 2) + return true; + } + else if (cp < 0x10000) { + if (length != 3) + return true; + } + return false; + } + + enum utf_error {UTF8_OK, NOT_ENOUGH_ROOM, INVALID_LEAD, INCOMPLETE_SEQUENCE, OVERLONG_SEQUENCE, INVALID_CODE_POINT}; + + /// Helper for get_sequence_x + template + utf_error increase_safely(octet_iterator& it, const octet_iterator end) + { + if (++it == end) + return NOT_ENOUGH_ROOM; + + if (!utf8::internal::is_trail(*it)) + return INCOMPLETE_SEQUENCE; + + return UTF8_OK; + } + + #define UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(IT, END) {utf_error ret = increase_safely(IT, END); if (ret != UTF8_OK) return ret;} + + /// get_sequence_x functions decode utf-8 sequences of the length x + template + utf_error get_sequence_1(octet_iterator& it, octet_iterator end, utfchar32_t& code_point) + { + if (it == end) + return NOT_ENOUGH_ROOM; + + code_point = utf8::internal::mask8(*it); + + return UTF8_OK; + } + + template + utf_error get_sequence_2(octet_iterator& it, octet_iterator end, utfchar32_t& code_point) + { + if (it == end) + return NOT_ENOUGH_ROOM; + + code_point = utf8::internal::mask8(*it); + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point = ((code_point << 6) & 0x7ff) + ((*it) & 0x3f); + + return UTF8_OK; + } + + template + utf_error get_sequence_3(octet_iterator& it, octet_iterator end, utfchar32_t& code_point) + { + if (it == end) + return NOT_ENOUGH_ROOM; + + code_point = utf8::internal::mask8(*it); + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point = ((code_point << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff); + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point += (*it) & 0x3f; + + return UTF8_OK; + } + + template + utf_error get_sequence_4(octet_iterator& it, octet_iterator end, utfchar32_t& code_point) + { + if (it == end) + return NOT_ENOUGH_ROOM; + + code_point = utf8::internal::mask8(*it); + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point = ((code_point << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff); + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point += (utf8::internal::mask8(*it) << 6) & 0xfff; + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point += (*it) & 0x3f; + + return UTF8_OK; + } + + #undef UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR + + template + utf_error validate_next(octet_iterator& it, octet_iterator end, utfchar32_t& code_point) + { + if (it == end) + return NOT_ENOUGH_ROOM; + + // Save the original value of it so we can go back in case of failure + // Of course, it does not make much sense with i.e. stream iterators + octet_iterator original_it = it; + + utfchar32_t cp = 0; + // Determine the sequence length based on the lead octet + const int length = utf8::internal::sequence_length(it); + + // Get trail octets and calculate the code point + utf_error err = UTF8_OK; + switch (length) { + case 0: + return INVALID_LEAD; + case 1: + err = utf8::internal::get_sequence_1(it, end, cp); + break; + case 2: + err = utf8::internal::get_sequence_2(it, end, cp); + break; + case 3: + err = utf8::internal::get_sequence_3(it, end, cp); + break; + case 4: + err = utf8::internal::get_sequence_4(it, end, cp); + break; + } + + if (err == UTF8_OK) { + // Decoding succeeded. Now, security checks... + if (utf8::internal::is_code_point_valid(cp)) { + if (!utf8::internal::is_overlong_sequence(cp, length)){ + // Passed! Return here. + code_point = cp; + ++it; + return UTF8_OK; + } + else + err = OVERLONG_SEQUENCE; + } + else + err = INVALID_CODE_POINT; + } + + // Failure branch - restore the original value of the iterator + it = original_it; + return err; + } + + template + inline utf_error validate_next(octet_iterator& it, octet_iterator end) { + utfchar32_t ignored; + return utf8::internal::validate_next(it, end, ignored); + } + + template + utf_error validate_next16(word_iterator& it, word_iterator end, utfchar32_t& code_point) + { + if (it == end) + return NOT_ENOUGH_ROOM; + // Save the original value of it so we can go back in case of failure + // Of course, it does not make much sense with i.e. stream iterators + word_iterator original_it = it; + + utf_error err = UTF8_OK; + + const utfchar16_t first_word = *it++; + if (!is_surrogate(first_word)) { + code_point = first_word; + return UTF8_OK; + } + else { + if (it == end) + err = NOT_ENOUGH_ROOM; + else if (is_lead_surrogate(first_word)) { + const utfchar16_t second_word = *it++; + if (is_trail_surrogate(second_word)) { + code_point = (first_word << 10) + second_word + SURROGATE_OFFSET; + return UTF8_OK; + } else + err = INCOMPLETE_SEQUENCE; + + } else { + err = INVALID_LEAD; + } + } + // error branch + it = original_it; + return err; + } + + // 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(utfchar32_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(utfchar32_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 + (utfchar32_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 utfchar8_t; that can cause a conversion warning if we are wrong. + template + octet_iterator append(utfchar32_t cp, octet_iterator result) { + return append(cp, result); + } + + // Internal implementation of both checked and unchecked append16() function + // This function will be invoked by the overloads below, as they will know + // the word_type. + template + word_iterator append16(utfchar32_t cp, word_iterator result) { + if (is_in_bmp(cp)) + *(result++) = static_cast(cp); + else { + // Code points from the supplementary planes are encoded via surrogate pairs + *(result++) = static_cast(LEAD_OFFSET + (cp >> 10)); + *(result++) = static_cast(TRAIL_SURROGATE_MIN + (cp & 0x3FF)); + } + return result; + } + + // Hopefully, most common case: the caller uses back_inserter + // i.e. append16(cp, std::back_inserter(str)); + template + std::back_insert_iterator append16 + (utfchar32_t cp, std::back_insert_iterator result) { + return append16, + 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 word_type + // so we assume it's utfchar16_t; that can cause a conversion warning if we are wrong. + template + word_iterator append16(utfchar32_t cp, word_iterator result) { + return append16(cp, result); + } + +} // namespace internal + + /// The library API - functions intended to be called by the users + + // Byte order mark + const utfchar8_t bom[] = {0xef, 0xbb, 0xbf}; + + template + octet_iterator find_invalid(octet_iterator start, octet_iterator end) + { + octet_iterator result = start; + while (result != end) { + utf8::internal::utf_error err_code = utf8::internal::validate_next(result, end); + if (err_code != internal::UTF8_OK) + return result; + } + return result; + } + + inline const char* find_invalid(const char* str) + { + const char* end = str + std::strlen(str); + return find_invalid(str, end); + } + + 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()); + } + + template + inline bool is_valid(octet_iterator start, octet_iterator end) + { + return (utf8::find_invalid(start, end) == end); + } + + inline bool is_valid(const char* str) + { + return (*(utf8::find_invalid(str)) == '\0'); + } + + inline bool is_valid(const std::string& s) + { + return is_valid(s.begin(), s.end()); + } + + + + template + inline bool starts_with_bom (octet_iterator it, octet_iterator end) + { + return ( + ((it != end) && (utf8::internal::mask8(*it++)) == bom[0]) && + ((it != end) && (utf8::internal::mask8(*it++)) == bom[1]) && + ((it != end) && (utf8::internal::mask8(*it)) == bom[2]) + ); + } + + 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/source/utf8/cpp11.h b/source/utf8/cpp11.h new file mode 100644 index 000000000..691633c84 --- /dev/null +++ b/source/utf8/cpp11.h @@ -0,0 +1,70 @@ +// 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" + +namespace utf8 +{ + inline void append16(utfchar32_t cp, std::u16string& s) + { + append16(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; + } +} // namespace utf8 + +#endif // header guard + diff --git a/source/utf8/cpp17.h b/source/utf8/cpp17.h new file mode 100644 index 000000000..6e2fcc238 --- /dev/null +++ b/source/utf8/cpp17.h @@ -0,0 +1,96 @@ +// 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 "cpp11.h" + +namespace utf8 +{ + 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/source/utf8/cpp20.h b/source/utf8/cpp20.h new file mode 100644 index 000000000..07b61d0fb --- /dev/null +++ b/source/utf8/cpp20.h @@ -0,0 +1,124 @@ +// Copyright 2022 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_207e906c01_03a3_4daf_b420_ea7ea952b3c9 +#define UTF8_FOR_CPP_207e906c01_03a3_4daf_b420_ea7ea952b3c9 + +#include "cpp17.h" + +namespace utf8 +{ + inline std::u8string utf16tou8(const std::u16string& s) + { + std::u8string result; + utf16to8(s.begin(), s.end(), std::back_inserter(result)); + return result; + } + + inline std::u8string utf16tou8(std::u16string_view s) + { + std::u8string result; + utf16to8(s.begin(), s.end(), std::back_inserter(result)); + return result; + } + + inline std::u16string utf8to16(const std::u8string& s) + { + std::u16string result; + utf8to16(s.begin(), s.end(), std::back_inserter(result)); + return result; + } + + inline std::u16string utf8to16(const std::u8string_view& s) + { + std::u16string result; + utf8to16(s.begin(), s.end(), std::back_inserter(result)); + return result; + } + + inline std::u8string utf32tou8(const std::u32string& s) + { + std::u8string result; + utf32to8(s.begin(), s.end(), std::back_inserter(result)); + return result; + } + + inline std::u8string utf32tou8(const std::u32string_view& s) + { + std::u8string result; + utf32to8(s.begin(), s.end(), std::back_inserter(result)); + return result; + } + + inline std::u32string utf8to32(const std::u8string& s) + { + std::u32string result; + utf8to32(s.begin(), s.end(), std::back_inserter(result)); + return result; + } + + inline std::u32string utf8to32(const std::u8string_view& s) + { + std::u32string result; + utf8to32(s.begin(), s.end(), std::back_inserter(result)); + return result; + } + + inline std::size_t find_invalid(const std::u8string& s) + { + std::u8string::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(const std::u8string& s) + { + return is_valid(s.begin(), s.end()); + } + + inline std::u8string replace_invalid(const std::u8string& s, char32_t replacement) + { + std::u8string result; + replace_invalid(s.begin(), s.end(), std::back_inserter(result), replacement); + return result; + } + + inline std::u8string replace_invalid(const std::u8string& s) + { + std::u8string result; + replace_invalid(s.begin(), s.end(), std::back_inserter(result)); + return result; + } + + inline bool starts_with_bom(const std::u8string& s) + { + return starts_with_bom(s.begin(), s.end()); + } + +} // namespace utf8 + +#endif // header guard + diff --git a/source/utf8/unchecked.h b/source/utf8/unchecked.h new file mode 100644 index 000000000..65d4948f2 --- /dev/null +++ b/source/utf8/unchecked.h @@ -0,0 +1,287 @@ +// Copyright 2006 Nemanja Trifunovic + +/* +Permission is hereby granted, free of charge, to any person or organization +obtaining a copy of the software and accompanying documentation covered by +this license (the "Software") to use, reproduce, display, distribute, +execute, and transmit the Software, and to prepare derivative works of the +Software, and to permit third-parties to whom the Software is furnished to +do so, all subject to the following: + +The copyright notices in the Software and this entire statement, including +the above license grant, this restriction and the following disclaimer, +must be included in all copies of the Software, in whole or in part, and +all derivative works of the Software, unless such copies or derivative +works are solely in the form of machine-executable object code generated by +a source language processor. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT +SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE +FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE, +ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER +DEALINGS IN THE SOFTWARE. +*/ + + +#ifndef UTF8_FOR_CPP_UNCHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 +#define UTF8_FOR_CPP_UNCHECKED_H_2675DCD0_9480_4c0c_B92A_CC14C027B731 + +#include "core.h" + +namespace utf8 +{ + namespace unchecked + { + template + octet_iterator append(utfchar32_t cp, octet_iterator result) + { + return internal::append(cp, result); + } + + template + word_iterator append16(utfchar32_t cp, word_iterator result) + { + return internal::append16(cp, result); + } + + template + output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, utfchar32_t replacement) + { + while (start != end) { + octet_iterator sequence_start = start; + internal::utf_error err_code = utf8::internal::validate_next(start, end); + switch (err_code) { + case internal::UTF8_OK : + for (octet_iterator it = sequence_start; it != start; ++it) + *out++ = *it; + break; + case internal::NOT_ENOUGH_ROOM: + out = utf8::unchecked::append(replacement, out); + start = end; + break; + case internal::INVALID_LEAD: + out = utf8::unchecked::append(replacement, out); + ++start; + break; + case internal::INCOMPLETE_SEQUENCE: + case internal::OVERLONG_SEQUENCE: + case internal::INVALID_CODE_POINT: + out = utf8::unchecked::append(replacement, out); + ++start; + // just one replacement mark for the sequence + while (start != end && utf8::internal::is_trail(*start)) + ++start; + break; + } + } + return out; + } + + template + inline output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out) + { + static const utfchar32_t replacement_marker = utf8::internal::mask16(0xfffd); + return utf8::unchecked::replace_invalid(start, end, out, replacement_marker); + } + + inline std::string replace_invalid(const std::string& s, utfchar32_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; + } + + template + utfchar32_t next(octet_iterator& it) + { + utfchar32_t cp = utf8::internal::mask8(*it); + switch (utf8::internal::sequence_length(it)) { + case 1: + break; + case 2: + it++; + cp = ((cp << 6) & 0x7ff) + ((*it) & 0x3f); + break; + case 3: + ++it; + cp = ((cp << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff); + ++it; + cp += (*it) & 0x3f; + break; + case 4: + ++it; + cp = ((cp << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff); + ++it; + cp += (utf8::internal::mask8(*it) << 6) & 0xfff; + ++it; + cp += (*it) & 0x3f; + break; + } + ++it; + return cp; + } + + template + utfchar32_t peek_next(octet_iterator it) + { + return utf8::unchecked::next(it); + } + + template + utfchar32_t next16(word_iterator& it) + { + utfchar32_t cp = utf8::internal::mask16(*it++); + if (utf8::internal::is_lead_surrogate(cp)) + return (cp << 10) + *it++ + utf8::internal::SURROGATE_OFFSET; + return cp; + } + + template + utfchar32_t prior(octet_iterator& it) + { + while (utf8::internal::is_trail(*(--it))) ; + octet_iterator temp = it; + return utf8::unchecked::next(temp); + } + + template + void advance(octet_iterator& it, distance_type n) + { + const distance_type zero(0); + if (n < zero) { + // backward + for (distance_type i = n; i < zero; ++i) + utf8::unchecked::prior(it); + } else { + // forward + for (distance_type i = zero; i < n; ++i) + utf8::unchecked::next(it); + } + } + + template + typename std::iterator_traits::difference_type + distance(octet_iterator first, octet_iterator last) + { + typename std::iterator_traits::difference_type dist; + for (dist = 0; first < last; ++dist) + utf8::unchecked::next(first); + return dist; + } + + template + octet_iterator utf16to8(u16bit_iterator start, u16bit_iterator end, octet_iterator result) + { + while (start != end) { + utfchar32_t cp = utf8::internal::mask16(*start++); + // Take care of surrogate pairs first + if (utf8::internal::is_lead_surrogate(cp)) { + if (start == end) + return result; + utfchar32_t trail_surrogate = utf8::internal::mask16(*start++); + cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET; + } + result = utf8::unchecked::append(cp, result); + } + return result; + } + + template + u16bit_iterator utf8to16(octet_iterator start, octet_iterator end, u16bit_iterator result) + { + while (start < end) { + utfchar32_t cp = utf8::unchecked::next(start); + if (cp > 0xffff) { //make a surrogate pair + *result++ = static_cast((cp >> 10) + internal::LEAD_OFFSET); + *result++ = static_cast((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN); + } + else + *result++ = static_cast(cp); + } + return result; + } + + template + octet_iterator utf32to8(u32bit_iterator start, u32bit_iterator end, octet_iterator result) + { + while (start != end) + result = utf8::unchecked::append(*(start++), result); + + return result; + } + + template + u32bit_iterator utf8to32(octet_iterator start, octet_iterator end, u32bit_iterator result) + { + while (start < end) + (*result++) = utf8::unchecked::next(start); + + return result; + } + + // The iterator class + template + class iterator { + octet_iterator it; + public: + typedef utfchar32_t value_type; + typedef utfchar32_t* pointer; + typedef utfchar32_t& reference; + typedef std::ptrdiff_t difference_type; + typedef std::bidirectional_iterator_tag iterator_category; + iterator () {} + explicit iterator (const octet_iterator& octet_it): it(octet_it) {} + // the default "big three" are OK + octet_iterator base () const { return it; } + utfchar32_t operator * () const + { + octet_iterator temp = it; + return utf8::unchecked::next(temp); + } + bool operator == (const iterator& rhs) const + { + return (it == rhs.it); + } + bool operator != (const iterator& rhs) const + { + return !(operator == (rhs)); + } + iterator& operator ++ () + { + ::std::advance(it, utf8::internal::sequence_length(it)); + return *this; + } + iterator operator ++ (int) + { + iterator temp = *this; + ::std::advance(it, utf8::internal::sequence_length(it)); + return temp; + } + iterator& operator -- () + { + utf8::unchecked::prior(it); + return *this; + } + iterator operator -- (int) + { + iterator temp = *this; + utf8::unchecked::prior(it); + return temp; + } + }; // class iterator + + } // namespace utf8::unchecked +} // namespace utf8 + + +#endif // header guard + diff --git a/tests/CMakeLists.txt b/tests/CMakeLists.txt new file mode 100644 index 000000000..8a00a6a08 --- /dev/null +++ b/tests/CMakeLists.txt @@ -0,0 +1,56 @@ +cmake_minimum_required (VERSION 3.5) +project(utfcpptests LANGUAGES CXX) +enable_testing() + +add_library(${PROJECT_NAME} INTERFACE) + +include_directories("${PROJECT_SOURCE_DIR}/../source") + +add_executable(negative negative.cpp) +add_executable(cpp11 test_cpp11.cpp) +add_executable(cpp17 test_cpp17.cpp) +add_executable(cpp20 test_cpp20.cpp) +add_executable(apitests apitests.cpp) + +add_executable(noexceptionstests noexceptionstests.cpp) + + + +target_compile_options(${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) + +set_target_properties(cpp20 + PROPERTIES + CXX_STANDARD 20 + CXX_STANDARD_REQUIRED YES + CXX_EXTENSIONS NO) + + +add_test(negative_test negative ${PROJECT_SOURCE_DIR}/test_data/utf8_invalid.txt) +add_test(cpp11_test cpp11) +add_test(cpp17_test cpp17) +add_test(cpp20_test cpp20) +add_test(api_test apitests) +add_test(noexceptions_test noexceptionstests) + diff --git a/tests/apitests.cpp b/tests/apitests.cpp new file mode 100644 index 000000000..083266d7d --- /dev/null +++ b/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/tests/docker/Dockerfile b/tests/docker/Dockerfile new file mode 100644 index 000000000..dcdd47d1d --- /dev/null +++ b/tests/docker/Dockerfile @@ -0,0 +1,5 @@ +FROM gcc:12.2 + +RUN apt-get update \ + && apt-get install -y make g++ cmake git \ + && rm -rf /var/lib/apt/lists/* diff --git a/tests/negative.cpp b/tests/negative.cpp new file mode 100644 index 000000000..f1bcc993e --- /dev/null +++ b/tests/negative.cpp @@ -0,0 +1,59 @@ +#include "utf8.h" +using namespace utf8; + +#include +#include +#include +#include +using namespace std; + +const unsigned INVALID_LINES[] = { 75, 76, 83, 84, 85, 93, 102, 103, 105, 106, 107, 108, 109, 110, 114, 115, 116, 117, 124, 125, 130, 135, 140, 145, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 169, 175, 176, 177, 207, 208, 209, 210, 211, 220, 221, 222, 223, 224, 232, 233, 234, 235, 236, 247, 248, 249, 250, 251, 252, 253, 257, 258, 259, 260, 261, 262, 263, 264}; +const unsigned* INVALID_LINES_END = INVALID_LINES + sizeof(INVALID_LINES)/sizeof(unsigned); + +int main(int argc, char** argv) +{ + string test_file_path; + if (argc == 2) + test_file_path = argv[1]; + else { + cout << "Wrong number of arguments" << endl; + 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 1; + } + + // 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++; + 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) { + 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())) { + cout << "replace_invalid() resulted in an invalid utf-8 at line " << line_count << '\n'; + return 1; + } + } + else if (!expected_valid) { + cout << "Invalid utf-8 NOT detected at line " << line_count << '\n'; + return 1; + } + } +} diff --git a/tests/noexceptionstests.cpp b/tests/noexceptionstests.cpp new file mode 100644 index 000000000..108ee750c --- /dev/null +++ b/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/tests/test_checked_api.h b/tests/test_checked_api.h new file mode 100644 index 000000000..54e9cf8f0 --- /dev/null +++ b/tests/test_checked_api.h @@ -0,0 +1,233 @@ +#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_append16) +{ + utfchar16_t u[5] = {0,0}; + append16(0x0448, u); + EXPECT_EQ (u[0], 0x0448); + EXPECT_EQ (u[1], 0x0000); + + append16(0x65e5, u); + EXPECT_EQ (u[0], 0x65e5); + EXPECT_EQ (u[1], 0x0000); + + append16(0x10346, u); + EXPECT_EQ (u[0], 0xd800); + EXPECT_EQ (u[1], 0xdf46); +} + +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_next16) +{ + const utfchar16_t u[3] = {0x65e5, 0xd800, 0xdf46}; + const utfchar16_t* w = u; + utf8::utfchar32_t cp = next16(w, w + 3); + EXPECT_EQ (cp, 0x65e5); + EXPECT_EQ (w, u + 1); + + cp = next16(w, w + 2); + EXPECT_EQ (cp, 0x10346); + EXPECT_EQ (w, u + 3); +} + +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"; + const char* invalid = find_invalid(utf_invalid, utf_invalid + 6); + EXPECT_EQ (invalid, utf_invalid + 5); + invalid = find_invalid(utf_invalid); + 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); + bvalid = is_valid(utf_invalid); + 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); + bvalid = is_valid(utf8_with_surrogates); + 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/tests/test_checked_iterator.h b/tests/test_checked_iterator.h new file mode 100644 index 000000000..2829a734e --- /dev/null +++ b/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/tests/test_cpp11.cpp b/tests/test_cpp11.cpp new file mode 100644 index 000000000..e52196682 --- /dev/null +++ b/tests/test_cpp11.cpp @@ -0,0 +1,122 @@ +#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_append16) +{ + u16string u; + append16(0x0448, u); + EXPECT_EQ (u[0], char16_t(0x0448)); + EXPECT_EQ (u.length(), 1); +} + +TEST(CPP11APITests, test_utf16to8) +{ + u16string utf16string = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e}; + string u = utf16to8(utf16string); + EXPECT_EQ (u.size(), 10); + + u16string h16 = u"h!"; + string h8; + utf8::unchecked::utf16to8(h16.begin(), h16.end(), std::back_inserter(h8)); + EXPECT_EQ (h8, "h!"); +} + +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/tests/test_cpp17.cpp b/tests/test_cpp17.cpp new file mode 100644 index 000000000..a38e6f716 --- /dev/null +++ b/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(utf16string); + string u = utf16to8(utf16stringview); + 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/tests/test_cpp20.cpp b/tests/test_cpp20.cpp new file mode 100644 index 000000000..50dbe30ac --- /dev/null +++ b/tests/test_cpp20.cpp @@ -0,0 +1,77 @@ +#include "../extern/ftest/ftest.h" +#define UTF_CPP_CPLUSPLUS 202002L +#include "utf8.h" +#include +using namespace utf8; +using namespace std; + +TEST(CPP20APITests, test_utf16tou8) +{ + u16string utf16string = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e}; + u16string_view utf16stringview{utf16string}; + u8string u = utf16tou8(utf16string); + EXPECT_EQ (u.size(), 10); + u = utf16tou8(utf16stringview); + EXPECT_EQ (u.size(), 10); +} + +TEST(CPP20APITests, tes20t_utf8to16) +{ + u8string utf8_with_surrogates{u8"\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(CPP20APITests, test_utf32tou8) +{ + u32string utf32string = {0x448, 0x65E5, 0x10346}; + u32string_view utf32stringview{utf32string}; + u8string utf8result = utf32tou8(utf32stringview); + EXPECT_EQ (utf8result.size(), 9); +} + +TEST(CPP20APITests, test_utf8to32) +{ + u8string twochars = u8"\xe6\x97\xa5\xd1\x88"; + u32string utf32result = utf8to32(twochars); + EXPECT_EQ (utf32result.size(), 2); +} + +TEST(CPP20APITests, test_find_invalid) +{ + u8string utf_invalid = u8"\xe6\x97\xa5\xd1\x88\xfa"; + auto invalid = find_invalid(utf_invalid); + EXPECT_EQ (invalid, 5); +} + +TEST(CPP20APITests, test_is_valid) +{ + u8string utf_invalid = u8"\xe6\x97\xa5\xd1\x88\xfa"; + bool bvalid = is_valid(utf_invalid); + EXPECT_FALSE (bvalid); + u8string utf8_with_surrogates = u8"\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"; + bvalid = is_valid(utf8_with_surrogates); + EXPECT_TRUE (bvalid); +} + +TEST(CPP20APITests, test_replace_invalid) +{ + u8string invalid_sequence = u8"a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z"; + u8string replace_invalid_result = replace_invalid(invalid_sequence, u8'?'); + bool bvalid = is_valid(replace_invalid_result); + EXPECT_TRUE (bvalid); + const u8string fixed_invalid_sequence = u8"a????z"; + EXPECT_EQ(fixed_invalid_sequence, replace_invalid_result); +} + +TEST(CPP20APITests, test_starts_with_bom) +{ + u8string byte_order_mark = u8"\xef\xbb\xbf"; + bool bbom = starts_with_bom(byte_order_mark); + EXPECT_TRUE (bbom); + u8string threechars = u8"\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; + bool no_bbom = starts_with_bom(threechars); + EXPECT_FALSE (no_bbom); +} diff --git a/tests/test_data/utf8_invalid.txt b/tests/test_data/utf8_invalid.txt new file mode 100644 index 000000000..ae8315932 Binary files /dev/null and b/tests/test_data/utf8_invalid.txt differ diff --git a/tests/test_unchecked_api.h b/tests/test_unchecked_api.h new file mode 100644 index 000000000..aa0cf697b --- /dev/null +++ b/tests/test_unchecked_api.h @@ -0,0 +1,198 @@ +#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_append16) +{ + unsigned short u[5] = {0,0}; + utf8::unchecked::append16(0x0448, u); + EXPECT_EQ (u[0], 0x0448); + EXPECT_EQ (u[1], 0x0000); + + utf8::unchecked::append16(0x65e5, u); + EXPECT_EQ (u[0], 0x65e5); + EXPECT_EQ (u[1], 0x0000); + + utf8::unchecked::append16(0x10346, u); + EXPECT_EQ (u[0], 0xd800); + EXPECT_EQ (u[1], 0xdf46); +} + +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_next16) +{ + const utf8::utfchar16_t u[3] = {0x65e5, 0xd800, 0xdf46}; + const utf8::utfchar16_t* w = u; + utf8::utfchar32_t cp = utf8::unchecked::next16(w); + EXPECT_EQ (cp, 0x65e5); + EXPECT_EQ (w, u + 1); + + cp = utf8::unchecked::next16(w); + EXPECT_EQ (cp, 0x10346); + EXPECT_EQ (w, u + 3); +} + +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); + + utf8result.clear(); + unsigned short highsurrogateonly[] = {0xd800}; + utf8::unchecked::utf16to8(highsurrogateonly, highsurrogateonly + 1, back_inserter(utf8result)); + EXPECT_TRUE(true); // we didn't crash +} + +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/tests/test_unchecked_iterator.h b/tests/test_unchecked_iterator.h new file mode 100644 index 000000000..4294232d6 --- /dev/null +++ b/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/utf8cppConfig.cmake.in b/utf8cppConfig.cmake.in new file mode 100644 index 000000000..4bdb9c419 --- /dev/null +++ b/utf8cppConfig.cmake.in @@ -0,0 +1,8 @@ +@PACKAGE_INIT@ + +include("${CMAKE_CURRENT_LIST_DIR}/@PROJECT_NAME@Targets.cmake") +check_required_components("@PROJECT_NAME@") + +if(NOT TARGET utf8::cpp) + add_library(utf8::cpp ALIAS utf8cpp::utf8cpp) +endif()