diff options
Diffstat (limited to 'third-party/utf8cpp')
| -rw-r--r-- | third-party/utf8cpp/.gitignore | 4 | ||||
| -rw-r--r-- | third-party/utf8cpp/CMakeLists.txt | 43 | ||||
| -rw-r--r-- | third-party/utf8cpp/LICENSE | 23 | ||||
| -rw-r--r-- | third-party/utf8cpp/README.md | 1090 | ||||
| -rw-r--r-- | third-party/utf8cpp/samples/docsample.cpp | 52 | ||||
| -rw-r--r-- | third-party/utf8cpp/source/utf8.h | 34 | ||||
| -rw-r--r-- | third-party/utf8cpp/source/utf8/checked.h | 327 | ||||
| -rw-r--r-- | third-party/utf8cpp/source/utf8/core.h | 332 | ||||
| -rw-r--r-- | third-party/utf8cpp/source/utf8/unchecked.h | 228 | ||||
| -rw-r--r-- | third-party/utf8cpp/test_data/negative/utf8_invalid.txt | bin | 0 -> 20010 bytes | |||
| -rw-r--r-- | third-party/utf8cpp/test_data/utf8samples/UTF-8-demo.txt | 212 | ||||
| -rw-r--r-- | third-party/utf8cpp/test_data/utf8samples/Unicode_transcriptions.html | 167 | ||||
| -rw-r--r-- | third-party/utf8cpp/test_data/utf8samples/quickbrown.txt | 126 | ||||
| -rw-r--r-- | third-party/utf8cpp/test_drivers/negative/negative.cpp | 53 | ||||
| -rw-r--r-- | third-party/utf8cpp/test_drivers/smoke_test/test.cpp | 298 | ||||
| -rw-r--r-- | third-party/utf8cpp/test_drivers/utf8reader/utf8reader.cpp | 160 |
16 files changed, 3149 insertions, 0 deletions
diff --git a/third-party/utf8cpp/.gitignore b/third-party/utf8cpp/.gitignore new file mode 100644 index 0000000..488d51d --- /dev/null +++ b/third-party/utf8cpp/.gitignore @@ -0,0 +1,4 @@ +# VS Code: +.vscode/ +# Often used by CMake +build/
\ No newline at end of file diff --git a/third-party/utf8cpp/CMakeLists.txt b/third-party/utf8cpp/CMakeLists.txt new file mode 100644 index 0000000..55073cd --- /dev/null +++ b/third-party/utf8cpp/CMakeLists.txt @@ -0,0 +1,43 @@ +cmake_minimum_required (VERSION 3.0.2) +project (utf8cpp VERSION 2.3.6 LANGUAGES CXX) + +option(UTF8_TESTS "Enable tests for UTF8-CPP" On) +option(UTF8_SAMPLES "Enable building samples for UTF8-CPP" On) + +add_library(utf8cpp INTERFACE) +target_include_directories(utf8cpp INTERFACE + "$<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/source>" + $<INSTALL_INTERFACE:include/utf8cpp> +) +add_library(utf8::cpp ALIAS utf8cpp) + +if(WIN32 AND NOT CYGWIN) + set(DEF_INSTALL_CMAKE_DIR CMake) +else() + include(GNUInstallDirs) # define CMAKE_INSTALL_* + set(DEF_INSTALL_CMAKE_DIR ${CMAKE_INSTALL_LIBDIR}/cmake/utf8cpp) +endif() + +install(DIRECTORY source/ DESTINATION include/utf8cpp) +install(TARGETS utf8cpp EXPORT utf8cppConfig) +install(EXPORT utf8cppConfig DESTINATION ${DEF_INSTALL_CMAKE_DIR}) + +if(UTF8_SAMPLES) + add_executable(utf8reader ${PROJECT_SOURCE_DIR}/test_drivers/utf8reader/utf8reader.cpp) + add_executable(docsample ${PROJECT_SOURCE_DIR}/samples/docsample.cpp) + + target_link_libraries(utf8reader PRIVATE utf8::cpp) + target_link_libraries(docsample PRIVATE utf8::cpp) +endif() + +if(UTF8_TESTS) + add_executable(smoke ${PROJECT_SOURCE_DIR}/test_drivers/smoke_test/test.cpp) + add_executable(negative ${PROJECT_SOURCE_DIR}/test_drivers/negative/negative.cpp) + + target_link_libraries(smoke PRIVATE utf8::cpp) + target_link_libraries(negative PRIVATE utf8::cpp) + + enable_testing() + add_test(smoke_test smoke) + add_test(negative_test negative ${PROJECT_SOURCE_DIR}/test_data/negative/utf8_invalid.txt) +endif() diff --git a/third-party/utf8cpp/LICENSE b/third-party/utf8cpp/LICENSE new file mode 100644 index 0000000..36b7cd9 --- /dev/null +++ b/third-party/utf8cpp/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/third-party/utf8cpp/README.md b/third-party/utf8cpp/README.md new file mode 100644 index 0000000..09996ab --- /dev/null +++ b/third-party/utf8cpp/README.md @@ -0,0 +1,1090 @@ +# UTF8-CPP: UTF-8 with C++ in a Portable Way + + +## Introduction + +Many C++ developers miss an easy and portable way of handling Unicode encoded strings. The original C++ Standard (known as C++98 or C++03) is Unicode agnostic. C++11 provides some support for Unicode on core language and library level: u8, u, and U character and string literals, char16_t and char32_t character types, u16string and u32string library classes, and codecvt support for conversions between Unicode encoding forms. In the meantime, developers use third party libraries like ICU, OS specific capabilities, or simply roll out their own solutions. + +In order to easily handle UTF-8 encoded Unicode strings, I came up with a small, C++98 compatible generic library. For anybody used to work with STL algorithms and iterators, it should be easy and natural to use. The code is freely available for any purpose - check out the [license](./LICENSE). The library has been used a lot in the past ten years both in commercial and open-source projects and is considered feature-complete now. If you run into bugs or performance issues, please let me know and I'll do my best to address them. + +The purpose of this article is not to offer an introduction to Unicode in general, and UTF-8 in particular. If you are not familiar with Unicode, be sure to check out [Unicode Home Page](http://www.unicode.org/) or some other source of information for Unicode. Also, it is not my aim to advocate the use of UTF-8 encoded strings in C++ programs; if you want to handle UTF-8 encoded strings from C++, I am sure you have good reasons for it. + +## Examples of use + +### Introductionary 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 <fstream> +#include <iostream> +#include <string> +#include <vector> +#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 (contains UTF-8 encoded text) + 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) + string::iterator end_it = utf8::find_invalid(line.begin(), line.end()); + 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 + vector<unsigned short> utf16line; + utf8::utf8to16(line.begin(), end_it, back_inserter(utf16line)); + + // And back to utf-8 + string utf8line; + utf8::utf16to8(utf16line.begin(), utf16line.end(), back_inserter(utf8line)); + + // 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`. + +### 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<char> it(ifs.rdbuf()); + istreambuf_iterator<char> 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. + +## Reference + +### Functions From utf8 Namespace + +#### utf8::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 <typename octet_iterator> +octet_iterator append(uint32_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. + +#### 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 <typename octet_iterator> +uint32_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 seqence, 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 <typename octet_iterator> +uint32_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 seqence, 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 <typename octet_iterator> +uint32_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::previous + +Deprecated in version 1.02 and later. + +Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it decreases the iterator until it hits the beginning of the previous UTF-8 encoded code point and returns the 32 bits representation of the code point. + +```cpp +template <typename octet_iterator> +uint32_t previous(octet_iterator& it, octet_iterator pass_start); +``` + +`octet_iterator`: a random access iterator. +`it`: a reference pointing to an octet within a UTF-8 encoded string. After the function returns, it is decremented to point to the beginning of the previous code point. +`pass_start`: an iterator to the point in the sequence where the search for the beginning of a code point is aborted if no result was reached. It is a safety measure to prevent passing the beginning of the string in the search for a UTF-8 lead octet. +Return value: the 32 bit representation of the previous code point. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +unsigned char* w = twochars + 3; +int cp = previous (w, twochars - 1); +assert (cp == 0x65e5); +assert (w == twochars); +``` + + +`utf8::previous` is deprecated, and `utf8::prior` should be used instead, although the existing code can continue using this function. The problem is the parameter `pass_start` that points to the position just before the beginning of the sequence. Standard containers don't have the concept of "pass start" and the function can not be used with their iterators. + +`it` will typically point to the beginning of a code point, and `pass_start` will point to the octet just before the beginning of the string to ensure we don't go backwards too far. `it` is decreased until it points to a lead UTF-8 octet, and then the UTF-8 sequence beginning with that octet is decoded to a 32 bit representation and returned. + +In case `pass_start` is reached before a UTF-8 lead octet is hit, or if an invalid UTF-8 sequence is started by the lead octet, an `invalid_utf8` exception is thrown + +#### utf8::advance +Available in version 1.0 and later. + +Advances an iterator by the specified number of code points within an UTF-8 sequence. + +```cpp +template <typename octet_iterator, typename distance_type> +void advance (octet_iterator& it, distance_type n, octet_iterator end); +``` + +`octet_iterator`: an input iterator. +`distance_type`: an integral type convertible to `octet_iterator`'s difference type. +`it`: a reference to an iterator pointing to the beginning of an UTF-8 encoded code point. After the function returns, it is incremented to point to the nth following code point. +`n`: a positive integer that shows how many code points we want to advance. +`end`: end of the UTF-8 sequence to be processed. If `it` gets equal to `end` during the extraction of a code point, an `utf8::not_enough_room` exception is thrown. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +unsigned char* w = twochars; +advance (w, 2, twochars + 6); +assert (w == twochars + 5); +``` + +This function works only "forward". In case of a negative `n`, there is no effect. + +In case of an invalid code point, a `utf8::invalid_code_point` exception is thrown. + +#### utf8::distance + +Available in version 1.0 and later. + +Given the iterators to two UTF-8 encoded code points in a seqence, returns the number of code points between them. + +```cpp +template <typename octet_iterator> +typename std::iterator_traits<octet_iterator>::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 seqence, a `utf8::invalid_utf8` exception is thrown. If `last` does not point to the past-of-end of a UTF-8 seqence, a `utf8::not_enough_room` exception is thrown. + +#### utf8::utf16to8 + +Available in version 1.0 and later. + +Converts a UTF-16 encoded string to UTF-8. + +```cpp +template <typename u16bit_iterator, typename octet_iterator> +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<unsigned char> 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. + +#### utf8::utf8to16 + +Available in version 1.0 and later. + +Converts an UTF-8 encoded string to UTF-16 + +```cpp +template <typename u16bit_iterator, typename octet_iterator> +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. < br /> `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 <unsigned short> 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 seqence, a `utf8::invalid_utf8` exception is thrown. If `end` does not point to the past-of-end of a UTF-8 seqence, a `utf8::not_enough_room` exception is thrown. + +#### utf8::utf32to8 + +Available in version 1.0 and later. + +Converts a UTF-32 encoded string to UTF-8. + +```cpp +template <typename octet_iterator, typename u32bit_iterator> +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: + +``` +int utf32string[] = {0x448, 0x65E5, 0x10346, 0}; +vector<unsigned char> 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. + +#### utf8::utf8to32 + +Available in version 1.0 and later. + +Converts a UTF-8 encoded string to UTF-32. + +```cpp +template <typename octet_iterator, typename u32bit_iterator> +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<int> utf32result; +utf8to32(twochars, twochars + 5, back_inserter(utf32result)); +assert (utf32result.size() == 2); +``` + +In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown. If `end` does not point to the past-of-end of a UTF-8 seqence, a `utf8::not_enough_room` exception is thrown. + +#### utf8::find_invalid + +Available in version 1.0 and later. + +Detects an invalid sequence within a UTF-8 string. + +```cpp +template <typename octet_iterator> +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. + +#### utf8::is_valid + +Available in version 1.0 and later. + +Checks whether a sequence of octets is a valid UTF-8 string. + +```cpp +template <typename octet_iterator> +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 seqence is a valid UTF-8 string without the need to know where it fails if it is not valid. + +#### utf8::replace_invalid + +Available in version 2.0 and later. + +Replaces all invalid UTF-8 sequences within a string with a replacement marker. + +```cpp +template <typename octet_iterator, typename output_iterator> +output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, uint32_t replacement); +template <typename octet_iterator, typename output_iterator> +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<char> 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. + +If `end` does not point to the past-of-end of a UTF-8 sequence, a `utf8::not_enough_room` exception is thrown. + +#### utf8::starts_with_bom + +Available in version 2.3 and later. Relaces deprecated `is_bom()` function. + +Checks whether an octet sequence starts with a UTF-8 byte order mark (BOM) + +```cpp +template <typename octet_iterator> +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. + +#### utf8::is_bom + +Available in version 1.0 and later. Deprecated in version 2.3\. `starts_with_bom()` should be used instead. + +Checks whether a sequence of three octets is a UTF-8 byte order mark (BOM) + +```cpp +template <typename octet_iterator> +bool is_bom (octet_iterator it); // Deprecated +``` + +`octet_iterator`: an input iterator. +`it`: beginning of the 3-octet sequence to check +Return value: `true` if the sequence is UTF-8 byte order mark; `false` if not. + +Example of use: + +```cpp +unsigned char byte_order_mark[] = {0xef, 0xbb, 0xbf}; +bool bbom = is_bom(byte_order_mark); +assert (bbom == true); +``` + +The typical use of this function is to check the first three bytes of a file. If they form the UTF-8 BOM, we want to skip them before processing the actual UTF-8 encoded text. + +If a sequence is shorter than three bytes, an invalid iterator will be dereferenced. Therefore, this function is deprecated in favor of `starts_with_bom()`that takes the end of sequence as an argument. + +### Types From utf8 Namespace + +#### utf8::exception + +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: + uint32_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: + uint8_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: + uint16_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 <typename octet_iterator> +class iterator; +``` + +##### Member functions + +`iterator();` the deafult constructor; the underlying octet_iterator is constructed with its default constructor. +`explicit iterator (const octet_iterator& octet_it, const octet_iterator& range_start, const octet_iterator& range_end);` a constructor that initializes the underlying octet_iterator with octet_it and sets the range in which the iterator is considered valid. +`octet_iterator base () const;` returns the underlying octet_iterator. +`uint32_t operator * () const;` decodes the utf-8 sequence the underlying octet_iterator is pointing to and returns the code point. +`bool operator == (const iterator& rhs) const;` returns `true` if the two underlaying iterators are equal. +`bool operator != (const iterator& rhs) const;` returns `true` if the two underlaying iterators are not equal. +`iterator& operator ++ ();` the prefix increment - moves the iterator to the next UTF-8 encoded code point. +`iterator operator ++ (int);` the postfix increment - moves the iterator to the next UTF-8 encoded code point and returns the current one. +`iterator& operator -- ();` the prefix decrement - moves the iterator to the previous UTF-8 encoded code point. +`iterator operator -- (int);` the postfix decrement - moves the iterator to the previous UTF-8 encoded code point and returns the current one. + +Example of use: + +```cpp +char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; +utf8::iterator<char*> it(threechars, threechars, threechars + 9); +utf8::iterator<char*> it2 = it; +assert (it2 == it); +assert (*it == 0x10346); +assert (*(++it) == 0x65e5); +assert ((*it++) == 0x65e5); +assert (*it == 0x0448); +assert (it != it2); +utf8::iterator<char*> endit (threechars + 9, threechars, threechars + 9); +assert (++it == endit); +assert (*(--it) == 0x0448); +assert ((*it--) == 0x0448); +assert (*it == 0x65e5); +assert (--it == utf8::iterator<char*>(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 <typename octet_iterator> +octet_iterator append(uint32_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::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 <typename octet_iterator> +uint32_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::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 <typename octet_iterator> +uint32_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 seqence, it decreases the iterator until it hits the beginning of the previous UTF-8 encoded code point and returns the 32 bits representation of the code point. + +```cpp +template <typename octet_iterator> +uint32_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::previous (deprecated, see utf8::unchecked::prior) + +Deprecated in version 1.02 and later. + +Given a reference to an iterator pointing to an octet in a UTF-8 seqence, it decreases the iterator until it hits the beginning of the previous UTF-8 encoded code point and returns the 32 bits representation of the code point. + +```cpp +template <typename octet_iterator> +uint32_t previous(octet_iterator& it); +``` + +`it`: a reference pointing to an octet within a UTF-8 encoded string. After the function returns, it is decremented to point to the beginning of the previous code point. +Return value: the 32 bit representation of the previous code point. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +char* w = twochars + 3; +int cp = unchecked::previous (w); +assert (cp == 0x65e5); +assert (w == twochars); +``` + +The reason this function is deprecated is just the consistency with the "checked" versions, where `prior` should be used instead of `previous`. In fact, `unchecked::previous` behaves exactly the same as `unchecked::prior` + +This is a faster but less safe version of `utf8::previous`. It does not check for validity of the supplied UTF-8 sequence and offers no boundary checking. + +#### utf8::unchecked::advance + +Available in version 1.0 and later. + +Advances an iterator by the specified number of code points within an UTF-8 sequence. + +```cpp +template <typename octet_iterator, typename distance_type> +void advance (octet_iterator& it, distance_type n); +``` + +`it`: a reference to an iterator pointing to the beginning of an UTF-8 encoded code point. After the function returns, it is incremented to point to the nth following code point. +`n`: a positive integer that shows how many code points we want to advance. + +Example of use: + +```cpp +char* twochars = "\xe6\x97\xa5\xd1\x88"; +char* w = twochars; +unchecked::advance (w, 2); +assert (w == twochars + 5); +``` + +This function works only "forward". In case of a negative `n`, there is no effect. + +This is a faster but less safe version of `utf8::advance`. It does not check for validity of the supplied UTF-8 sequence and offers no boundary checking. + +#### utf8::unchecked::distance + +Available in version 1.0 and later. + +Given the iterators to two UTF-8 encoded code points in a seqence, returns the number of code points between them. + +```cpp +template <typename octet_iterator> +typename std::iterator_traits<octet_iterator>::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 <typename u16bit_iterator, typename octet_iterator> +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<unsigned char> 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 <typename u16bit_iterator, typename octet_iterator> +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. < br /> `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 <unsigned short> 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 <typename octet_iterator, typename u32bit_iterator> +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<unsigned char> 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 <typename octet_iterator, typename u32bit_iterator> +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<int> 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. + +### 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 <typename octet_iterator> +class iterator; +``` + +##### Member functions + +`iterator();` the deafult constructor; the underlying octet_iterator is constructed with its default constructor. +`explicit iterator (const octet_iterator& octet_it);` a constructor that initializes the underlying octet_iterator with `octet_it` +`octet_iterator base () const;` returns the underlying octet_iterator. +`uint32_t operator * () const;` decodes the utf-8 sequence the underlying octet_iterator is pointing to and returns the code point. +`bool operator == (const iterator& rhs) const;` returns `true` if the two underlaying iterators are equal. +`bool operator != (const iterator& rhs) const;` returns `true` if the two underlaying iterators are not equal. +`iterator& operator ++ ();` the prefix increment - moves the iterator to the next UTF-8 encoded code point. +`iterator operator ++ (int);` the postfix increment - moves the iterator to the next UTF-8 encoded code point and returns the current one. +`iterator& operator -- ();` the prefix decrement - moves the iterator to the previous UTF-8 encoded code point. +`iterator operator -- (int);` the postfix decrement - moves the iterator to the previous UTF-8 encoded code point and returns the current one. + +Example of use: + +```cpp +char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; +utf8::unchecked::iterator<char*> un_it(threechars); +utf8::unchecked::iterator<char*> 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<char*> 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<char*>(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. + +## Points of interest + +#### Design goals and decisions + +The library was designed to be: + +1. Generic: for better or worse, there are many C++ string classes out there, and the library should work with as many of them as possible. +2. Portable: the library should be portable both accross different platforms and compilers. The only non-portable code is a small section that declares unsigned integers of different sizes: three typedefs. They can be changed by the users of the library if they don't match their platform. The default setting should work for Windows (both 32 and 64 bit), and most 32 bit and 64 bit Unix derivatives. At this point I don't plan to use any post C++03 features, so the library should work even with pretty old compilers. +3. Lightweight: follow the "pay only for what you use" guideline. +4. Unintrusive: avoid forcing any particular design or even programming style on the user. This is a library, not a framework. + +#### Alternatives + +In case you want to look into other means of working with UTF-8 strings from C++, here is the list of solutions I am aware of: + +1. [ICU Library](http://icu.sourceforge.net/). It is very powerful, complete, feature-rich, mature, and widely used. Also big, intrusive, non-generic, and doesn't play well with the Standard Library. I definitelly recommend looking at ICU even if you don't plan to use it. +2. C++11 language and library features. Still far from complete, and not easy to use. +3. [Glib::ustring](http://www.gtkmm.org/gtkmm2/docs/tutorial/html/ch03s04.html). A class specifically made to work with UTF-8 strings, and also feel like `std::string`. If you prefer to have yet another string class in your code, it may be worth a look. Be aware of the licensing issues, though. +4. Platform dependent solutions: Windows and POSIX have functions to convert strings from one encoding to another. That is only a subset of what my library offers, but if that is all you need it may be good enough. + +## Links + +1. [The Unicode Consortium](http://www.unicode.org/). +2. [ICU Library](http://icu.sourceforge.net/). +3. [UTF-8 at Wikipedia](http://en.wikipedia.org/wiki/UTF-8) +4. [UTF-8 and Unicode FAQ for Unix/Linux](http://www.cl.cam.ac.uk/~mgk25/unicode.html) diff --git a/third-party/utf8cpp/samples/docsample.cpp b/third-party/utf8cpp/samples/docsample.cpp new file mode 100644 index 0000000..6f8953b --- /dev/null +++ b/third-party/utf8cpp/samples/docsample.cpp @@ -0,0 +1,52 @@ +#include "../source/utf8.h" +#include <iostream> +#include <fstream> +#include <string> +#include <vector> + + +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) + string::iterator end_it = utf8::find_invalid(line.begin(), line.end()); + 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 + vector<unsigned short> utf16line; + utf8::utf8to16(line.begin(), end_it, back_inserter(utf16line)); + // And back to utf-8; + string utf8line; + utf8::utf16to8(utf16line.begin(), utf16line.end(), back_inserter(utf8line)); + // 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; +} diff --git a/third-party/utf8cpp/source/utf8.h b/third-party/utf8cpp/source/utf8.h new file mode 100644 index 0000000..82b13f5 --- /dev/null +++ b/third-party/utf8cpp/source/utf8.h @@ -0,0 +1,34 @@ +// Copyright 2006 Nemanja Trifunovic + +/* +Permission is hereby granted, free of charge, to any person or organization +obtaining a copy of the software and accompanying documentation covered by +this license (the "Software") to use, reproduce, display, distribute, +execute, and transmit the Software, and to prepare derivative works of the +Software, and to permit third-parties to whom the Software is furnished to +do so, all subject to the following: + +The copyright notices in the Software and this entire statement, including +the above license grant, this restriction and the following disclaimer, +must be included in all copies of the Software, in whole or in part, and +all derivative works of the Software, unless such copies or derivative +works are solely in the form of machine-executable object code generated by +a source language processor. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT +SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE +FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE, +ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER +DEALINGS IN THE SOFTWARE. +*/ + + +#ifndef UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731 +#define UTF8_FOR_CPP_2675DCD0_9480_4c0c_B92A_CC14C027B731 + +#include "utf8/checked.h" +#include "utf8/unchecked.h" + +#endif // header guard diff --git a/third-party/utf8cpp/source/utf8/checked.h b/third-party/utf8cpp/source/utf8/checked.h new file mode 100644 index 0000000..2aef583 --- /dev/null +++ b/third-party/utf8cpp/source/utf8/checked.h @@ -0,0 +1,327 @@ +// 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 <stdexcept> + +namespace utf8 +{ + // Base for the exceptions that may be thrown from the library + class exception : public ::std::exception { + }; + + // Exceptions that may be thrown from the library functions. + class invalid_code_point : public exception { + uint32_t cp; + public: + invalid_code_point(uint32_t codepoint) : cp(codepoint) {} + virtual const char* what() const throw() { return "Invalid code point"; } + uint32_t code_point() const {return cp;} + }; + + class invalid_utf8 : public exception { + uint8_t u8; + public: + invalid_utf8 (uint8_t u) : u8(u) {} + virtual const char* what() const throw() { return "Invalid UTF-8"; } + uint8_t utf8_octet() const {return u8;} + }; + + class invalid_utf16 : public exception { + uint16_t u16; + public: + invalid_utf16 (uint16_t u) : u16(u) {} + virtual const char* what() const throw() { return "Invalid UTF-16"; } + uint16_t utf16_word() const {return u16;} + }; + + class not_enough_room : public exception { + public: + virtual const char* what() const throw() { return "Not enough space"; } + }; + + /// The library API - functions intended to be called by the users + + template <typename octet_iterator> + octet_iterator append(uint32_t cp, octet_iterator result) + { + if (!utf8::internal::is_code_point_valid(cp)) + throw invalid_code_point(cp); + + if (cp < 0x80) // one octet + *(result++) = static_cast<uint8_t>(cp); + else if (cp < 0x800) { // two octets + *(result++) = static_cast<uint8_t>((cp >> 6) | 0xc0); + *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80); + } + else if (cp < 0x10000) { // three octets + *(result++) = static_cast<uint8_t>((cp >> 12) | 0xe0); + *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80); + *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80); + } + else { // four octets + *(result++) = static_cast<uint8_t>((cp >> 18) | 0xf0); + *(result++) = static_cast<uint8_t>(((cp >> 12) & 0x3f) | 0x80); + *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80); + *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80); + } + return result; + } + + template <typename octet_iterator, typename output_iterator> + output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out, uint32_t replacement) + { + while (start != end) { + octet_iterator sequence_start = start; + internal::utf_error err_code = utf8::internal::validate_next(start, end); + switch (err_code) { + case internal::UTF8_OK : + for (octet_iterator it = sequence_start; it != start; ++it) + *out++ = *it; + break; + case internal::NOT_ENOUGH_ROOM: + throw not_enough_room(); + case internal::INVALID_LEAD: + 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 <typename octet_iterator, typename output_iterator> + inline output_iterator replace_invalid(octet_iterator start, octet_iterator end, output_iterator out) + { + static const uint32_t replacement_marker = utf8::internal::mask16(0xfffd); + return utf8::replace_invalid(start, end, out, replacement_marker); + } + + template <typename octet_iterator> + uint32_t next(octet_iterator& it, octet_iterator end) + { + uint32_t cp = 0; + internal::utf_error err_code = utf8::internal::validate_next(it, end, cp); + switch (err_code) { + case internal::UTF8_OK : + break; + case internal::NOT_ENOUGH_ROOM : + throw not_enough_room(); + case internal::INVALID_LEAD : + case internal::INCOMPLETE_SEQUENCE : + case internal::OVERLONG_SEQUENCE : + throw invalid_utf8(*it); + case internal::INVALID_CODE_POINT : + throw invalid_code_point(cp); + } + return cp; + } + + template <typename octet_iterator> + uint32_t peek_next(octet_iterator it, octet_iterator end) + { + return utf8::next(it, end); + } + + template <typename octet_iterator> + uint32_t prior(octet_iterator& it, octet_iterator start) + { + // can't do much if it == start + if (it == start) + throw not_enough_room(); + + octet_iterator end = it; + // Go back until we hit either a lead octet or start + while (utf8::internal::is_trail(*(--it))) + if (it == start) + throw invalid_utf8(*it); // error - no lead byte in the sequence + return utf8::peek_next(it, end); + } + + /// Deprecated in versions that include "prior" + template <typename octet_iterator> + uint32_t previous(octet_iterator& it, octet_iterator pass_start) + { + octet_iterator end = it; + while (utf8::internal::is_trail(*(--it))) + if (it == pass_start) + throw invalid_utf8(*it); // error - no lead byte in the sequence + octet_iterator temp = it; + return utf8::next(temp, end); + } + + template <typename octet_iterator, typename distance_type> + void advance (octet_iterator& it, distance_type n, octet_iterator end) + { + for (distance_type i = 0; i < n; ++i) + utf8::next(it, end); + } + + template <typename octet_iterator> + typename std::iterator_traits<octet_iterator>::difference_type + distance (octet_iterator first, octet_iterator last) + { + typename std::iterator_traits<octet_iterator>::difference_type dist; + for (dist = 0; first < last; ++dist) + utf8::next(first, last); + return dist; + } + + template <typename u16bit_iterator, typename octet_iterator> + octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result) + { + while (start != end) { + uint32_t cp = utf8::internal::mask16(*start++); + // Take care of surrogate pairs first + if (utf8::internal::is_lead_surrogate(cp)) { + if (start != end) { + uint32_t trail_surrogate = utf8::internal::mask16(*start++); + if (utf8::internal::is_trail_surrogate(trail_surrogate)) + cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET; + else + throw invalid_utf16(static_cast<uint16_t>(trail_surrogate)); + } + else + throw invalid_utf16(static_cast<uint16_t>(cp)); + + } + // Lone trail surrogate + else if (utf8::internal::is_trail_surrogate(cp)) + throw invalid_utf16(static_cast<uint16_t>(cp)); + + result = utf8::append(cp, result); + } + return result; + } + + template <typename u16bit_iterator, typename octet_iterator> + u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result) + { + while (start < end) { + uint32_t cp = utf8::next(start, end); + if (cp > 0xffff) { //make a surrogate pair + *result++ = static_cast<uint16_t>((cp >> 10) + internal::LEAD_OFFSET); + *result++ = static_cast<uint16_t>((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN); + } + else + *result++ = static_cast<uint16_t>(cp); + } + return result; + } + + template <typename octet_iterator, typename u32bit_iterator> + octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result) + { + while (start != end) + result = utf8::append(*(start++), result); + + return result; + } + + template <typename octet_iterator, typename u32bit_iterator> + 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 <typename octet_iterator> + class iterator : public std::iterator <std::bidirectional_iterator_tag, uint32_t> { + octet_iterator it; + octet_iterator range_start; + octet_iterator range_end; + public: + iterator () {} + explicit iterator (const octet_iterator& octet_it, + const octet_iterator& rangestart, + const octet_iterator& rangeend) : + it(octet_it), range_start(rangestart), range_end(rangeend) + { + if (it < range_start || it > range_end) + throw std::out_of_range("Invalid utf-8 iterator position"); + } + // the default "big three" are OK + octet_iterator base () const { return it; } + uint32_t operator * () const + { + octet_iterator temp = it; + return utf8::next(temp, range_end); + } + bool operator == (const iterator& rhs) const + { + if (range_start != rhs.range_start || range_end != rhs.range_end) + throw std::logic_error("Comparing utf-8 iterators defined with different ranges"); + return (it == rhs.it); + } + bool operator != (const iterator& rhs) const + { + return !(operator == (rhs)); + } + iterator& operator ++ () + { + utf8::next(it, range_end); + return *this; + } + iterator operator ++ (int) + { + iterator temp = *this; + utf8::next(it, range_end); + return temp; + } + iterator& operator -- () + { + utf8::prior(it, range_start); + return *this; + } + iterator operator -- (int) + { + iterator temp = *this; + utf8::prior(it, range_start); + return temp; + } + }; // class iterator + +} // namespace utf8 + +#endif //header guard + + diff --git a/third-party/utf8cpp/source/utf8/core.h b/third-party/utf8cpp/source/utf8/core.h new file mode 100644 index 0000000..ae0f367 --- /dev/null +++ b/third-party/utf8cpp/source/utf8/core.h @@ -0,0 +1,332 @@ +// 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 <iterator> + +namespace utf8 +{ + // The typedefs for 8-bit, 16-bit and 32-bit unsigned integers + // You may need to change them to match your system. + // These typedefs have the same names as ones from cstdint, or boost/cstdint + typedef unsigned char uint8_t; + typedef unsigned short uint16_t; + typedef unsigned int uint32_t; + +// Helper code - not intended to be directly called by the library users. May be changed at any time +namespace internal +{ + // Unicode constants + // Leading (high) surrogates: 0xd800 - 0xdbff + // Trailing (low) surrogates: 0xdc00 - 0xdfff + const uint16_t LEAD_SURROGATE_MIN = 0xd800u; + const uint16_t LEAD_SURROGATE_MAX = 0xdbffu; + const uint16_t TRAIL_SURROGATE_MIN = 0xdc00u; + const uint16_t TRAIL_SURROGATE_MAX = 0xdfffu; + const uint16_t LEAD_OFFSET = LEAD_SURROGATE_MIN - (0x10000 >> 10); + const uint32_t SURROGATE_OFFSET = 0x10000u - (LEAD_SURROGATE_MIN << 10) - TRAIL_SURROGATE_MIN; + + // Maximum valid value for a Unicode code point + const uint32_t CODE_POINT_MAX = 0x0010ffffu; + + template<typename octet_type> + inline uint8_t mask8(octet_type oc) + { + return static_cast<uint8_t>(0xff & oc); + } + template<typename u16_type> + inline uint16_t mask16(u16_type oc) + { + return static_cast<uint16_t>(0xffff & oc); + } + template<typename octet_type> + inline bool is_trail(octet_type oc) + { + return ((utf8::internal::mask8(oc) >> 6) == 0x2); + } + + template <typename u16> + inline bool is_lead_surrogate(u16 cp) + { + return (cp >= LEAD_SURROGATE_MIN && cp <= LEAD_SURROGATE_MAX); + } + + template <typename u16> + inline bool is_trail_surrogate(u16 cp) + { + return (cp >= TRAIL_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX); + } + + template <typename u16> + inline bool is_surrogate(u16 cp) + { + return (cp >= LEAD_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX); + } + + template <typename u32> + inline bool is_code_point_valid(u32 cp) + { + return (cp <= CODE_POINT_MAX && !utf8::internal::is_surrogate(cp)); + } + + template <typename octet_iterator> + inline typename std::iterator_traits<octet_iterator>::difference_type + sequence_length(octet_iterator lead_it) + { + uint8_t lead = utf8::internal::mask8(*lead_it); + if (lead < 0x80) + return 1; + else if ((lead >> 5) == 0x6) + return 2; + else if ((lead >> 4) == 0xe) + return 3; + else if ((lead >> 3) == 0x1e) + return 4; + else + return 0; + } + + template <typename octet_difference_type> + inline bool is_overlong_sequence(uint32_t cp, octet_difference_type length) + { + if (cp < 0x80) { + if (length != 1) + return true; + } + else if (cp < 0x800) { + if (length != 2) + return true; + } + else if (cp < 0x10000) { + if (length != 3) + return true; + } + + return false; + } + + enum utf_error {UTF8_OK, NOT_ENOUGH_ROOM, INVALID_LEAD, INCOMPLETE_SEQUENCE, OVERLONG_SEQUENCE, INVALID_CODE_POINT}; + + /// Helper for get_sequence_x + template <typename octet_iterator> + utf_error increase_safely(octet_iterator& it, octet_iterator end) + { + if (++it == end) + return NOT_ENOUGH_ROOM; + + if (!utf8::internal::is_trail(*it)) + return INCOMPLETE_SEQUENCE; + + return UTF8_OK; + } + + #define UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(IT, END) {utf_error ret = increase_safely(IT, END); if (ret != UTF8_OK) return ret;} + + /// get_sequence_x functions decode utf-8 sequences of the length x + template <typename octet_iterator> + utf_error get_sequence_1(octet_iterator& it, octet_iterator end, uint32_t& code_point) + { + if (it == end) + return NOT_ENOUGH_ROOM; + + code_point = utf8::internal::mask8(*it); + + return UTF8_OK; + } + + template <typename octet_iterator> + utf_error get_sequence_2(octet_iterator& it, octet_iterator end, uint32_t& code_point) + { + if (it == end) + return NOT_ENOUGH_ROOM; + + code_point = utf8::internal::mask8(*it); + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point = ((code_point << 6) & 0x7ff) + ((*it) & 0x3f); + + return UTF8_OK; + } + + template <typename octet_iterator> + utf_error get_sequence_3(octet_iterator& it, octet_iterator end, uint32_t& code_point) + { + if (it == end) + return NOT_ENOUGH_ROOM; + + code_point = utf8::internal::mask8(*it); + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point = ((code_point << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff); + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point += (*it) & 0x3f; + + return UTF8_OK; + } + + template <typename octet_iterator> + utf_error get_sequence_4(octet_iterator& it, octet_iterator end, uint32_t& code_point) + { + if (it == end) + return NOT_ENOUGH_ROOM; + + code_point = utf8::internal::mask8(*it); + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point = ((code_point << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff); + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point += (utf8::internal::mask8(*it) << 6) & 0xfff; + + UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end) + + code_point += (*it) & 0x3f; + + return UTF8_OK; + } + + #undef UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR + + template <typename octet_iterator> + utf_error validate_next(octet_iterator& it, octet_iterator end, uint32_t& code_point) + { + if (it == end) + return NOT_ENOUGH_ROOM; + + // Save the original value of it so we can go back in case of failure + // Of course, it does not make much sense with i.e. stream iterators + octet_iterator original_it = it; + + uint32_t cp = 0; + // Determine the sequence length based on the lead octet + typedef typename std::iterator_traits<octet_iterator>::difference_type octet_difference_type; + const octet_difference_type length = utf8::internal::sequence_length(it); + + // Get trail octets and calculate the code point + utf_error err = UTF8_OK; + switch (length) { + case 0: + return INVALID_LEAD; + case 1: + err = utf8::internal::get_sequence_1(it, end, cp); + break; + case 2: + err = utf8::internal::get_sequence_2(it, end, cp); + break; + case 3: + err = utf8::internal::get_sequence_3(it, end, cp); + break; + case 4: + err = utf8::internal::get_sequence_4(it, end, cp); + break; + } + + if (err == UTF8_OK) { + // Decoding succeeded. Now, security checks... + if (utf8::internal::is_code_point_valid(cp)) { + if (!utf8::internal::is_overlong_sequence(cp, length)){ + // Passed! Return here. + code_point = cp; + ++it; + return UTF8_OK; + } + else + err = OVERLONG_SEQUENCE; + } + else + err = INVALID_CODE_POINT; + } + + // Failure branch - restore the original value of the iterator + it = original_it; + return err; + } + + template <typename octet_iterator> + inline utf_error validate_next(octet_iterator& it, octet_iterator end) { + uint32_t ignored; + return utf8::internal::validate_next(it, end, ignored); + } + +} // namespace internal + + /// The library API - functions intended to be called by the users + + // Byte order mark + const uint8_t bom[] = {0xef, 0xbb, 0xbf}; + + template <typename octet_iterator> + octet_iterator find_invalid(octet_iterator start, octet_iterator end) + { + octet_iterator result = start; + while (result != end) { + utf8::internal::utf_error err_code = utf8::internal::validate_next(result, end); + if (err_code != internal::UTF8_OK) + return result; + } + return result; + } + + template <typename octet_iterator> + inline bool is_valid(octet_iterator start, octet_iterator end) + { + return (utf8::find_invalid(start, end) == end); + } + + template <typename octet_iterator> + inline bool starts_with_bom (octet_iterator it, octet_iterator end) + { + return ( + ((it != end) && (utf8::internal::mask8(*it++)) == bom[0]) && + ((it != end) && (utf8::internal::mask8(*it++)) == bom[1]) && + ((it != end) && (utf8::internal::mask8(*it)) == bom[2]) + ); + } + + //Deprecated in release 2.3 + template <typename octet_iterator> + inline bool is_bom (octet_iterator it) + { + return ( + (utf8::internal::mask8(*it++)) == bom[0] && + (utf8::internal::mask8(*it++)) == bom[1] && + (utf8::internal::mask8(*it)) == bom[2] + ); + } +} // namespace utf8 + +#endif // header guard + + diff --git a/third-party/utf8cpp/source/utf8/unchecked.h b/third-party/utf8cpp/source/utf8/unchecked.h new file mode 100644 index 0000000..cb24271 --- /dev/null +++ b/third-party/utf8cpp/source/utf8/unchecked.h @@ -0,0 +1,228 @@ +// 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 <typename octet_iterator> + octet_iterator append(uint32_t cp, octet_iterator result) + { + if (cp < 0x80) // one octet + *(result++) = static_cast<uint8_t>(cp); + else if (cp < 0x800) { // two octets + *(result++) = static_cast<uint8_t>((cp >> 6) | 0xc0); + *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80); + } + else if (cp < 0x10000) { // three octets + *(result++) = static_cast<uint8_t>((cp >> 12) | 0xe0); + *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80); + *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80); + } + else { // four octets + *(result++) = static_cast<uint8_t>((cp >> 18) | 0xf0); + *(result++) = static_cast<uint8_t>(((cp >> 12) & 0x3f)| 0x80); + *(result++) = static_cast<uint8_t>(((cp >> 6) & 0x3f) | 0x80); + *(result++) = static_cast<uint8_t>((cp & 0x3f) | 0x80); + } + return result; + } + + template <typename octet_iterator> + uint32_t next(octet_iterator& it) + { + uint32_t cp = utf8::internal::mask8(*it); + typename std::iterator_traits<octet_iterator>::difference_type length = utf8::internal::sequence_length(it); + switch (length) { + case 1: + break; + case 2: + it++; + cp = ((cp << 6) & 0x7ff) + ((*it) & 0x3f); + break; + case 3: + ++it; + cp = ((cp << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff); + ++it; + cp += (*it) & 0x3f; + break; + case 4: + ++it; + cp = ((cp << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff); + ++it; + cp += (utf8::internal::mask8(*it) << 6) & 0xfff; + ++it; + cp += (*it) & 0x3f; + break; + } + ++it; + return cp; + } + + template <typename octet_iterator> + uint32_t peek_next(octet_iterator it) + { + return utf8::unchecked::next(it); + } + + template <typename octet_iterator> + uint32_t prior(octet_iterator& it) + { + while (utf8::internal::is_trail(*(--it))) ; + octet_iterator temp = it; + return utf8::unchecked::next(temp); + } + + // Deprecated in versions that include prior, but only for the sake of consistency (see utf8::previous) + template <typename octet_iterator> + inline uint32_t previous(octet_iterator& it) + { + return utf8::unchecked::prior(it); + } + + template <typename octet_iterator, typename distance_type> + void advance (octet_iterator& it, distance_type n) + { + for (distance_type i = 0; i < n; ++i) + utf8::unchecked::next(it); + } + + template <typename octet_iterator> + typename std::iterator_traits<octet_iterator>::difference_type + distance (octet_iterator first, octet_iterator last) + { + typename std::iterator_traits<octet_iterator>::difference_type dist; + for (dist = 0; first < last; ++dist) + utf8::unchecked::next(first); + return dist; + } + + template <typename u16bit_iterator, typename octet_iterator> + octet_iterator utf16to8 (u16bit_iterator start, u16bit_iterator end, octet_iterator result) + { + while (start != end) { + uint32_t cp = utf8::internal::mask16(*start++); + // Take care of surrogate pairs first + if (utf8::internal::is_lead_surrogate(cp)) { + uint32_t trail_surrogate = utf8::internal::mask16(*start++); + cp = (cp << 10) + trail_surrogate + internal::SURROGATE_OFFSET; + } + result = utf8::unchecked::append(cp, result); + } + return result; + } + + template <typename u16bit_iterator, typename octet_iterator> + u16bit_iterator utf8to16 (octet_iterator start, octet_iterator end, u16bit_iterator result) + { + while (start < end) { + uint32_t cp = utf8::unchecked::next(start); + if (cp > 0xffff) { //make a surrogate pair + *result++ = static_cast<uint16_t>((cp >> 10) + internal::LEAD_OFFSET); + *result++ = static_cast<uint16_t>((cp & 0x3ff) + internal::TRAIL_SURROGATE_MIN); + } + else + *result++ = static_cast<uint16_t>(cp); + } + return result; + } + + template <typename octet_iterator, typename u32bit_iterator> + octet_iterator utf32to8 (u32bit_iterator start, u32bit_iterator end, octet_iterator result) + { + while (start != end) + result = utf8::unchecked::append(*(start++), result); + + return result; + } + + template <typename octet_iterator, typename u32bit_iterator> + 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 <typename octet_iterator> + class iterator : public std::iterator <std::bidirectional_iterator_tag, uint32_t> { + octet_iterator it; + public: + iterator () {} + explicit iterator (const octet_iterator& octet_it): it(octet_it) {} + // the default "big three" are OK + octet_iterator base () const { return it; } + uint32_t operator * () const + { + octet_iterator temp = it; + return utf8::unchecked::next(temp); + } + bool operator == (const iterator& rhs) const + { + return (it == rhs.it); + } + bool operator != (const iterator& rhs) const + { + return !(operator == (rhs)); + } + iterator& operator ++ () + { + ::std::advance(it, utf8::internal::sequence_length(it)); + return *this; + } + iterator operator ++ (int) + { + iterator temp = *this; + ::std::advance(it, utf8::internal::sequence_length(it)); + return temp; + } + iterator& operator -- () + { + utf8::unchecked::prior(it); + return *this; + } + iterator operator -- (int) + { + iterator temp = *this; + utf8::unchecked::prior(it); + return temp; + } + }; // class iterator + + } // namespace utf8::unchecked +} // namespace utf8 + + +#endif // header guard + diff --git a/third-party/utf8cpp/test_data/negative/utf8_invalid.txt b/third-party/utf8cpp/test_data/negative/utf8_invalid.txt Binary files differnew file mode 100644 index 0000000..ae83159 --- /dev/null +++ b/third-party/utf8cpp/test_data/negative/utf8_invalid.txt diff --git a/third-party/utf8cpp/test_data/utf8samples/UTF-8-demo.txt b/third-party/utf8cpp/test_data/utf8samples/UTF-8-demo.txt new file mode 100644 index 0000000..4363f27 --- /dev/null +++ b/third-party/utf8cpp/test_data/utf8samples/UTF-8-demo.txt @@ -0,0 +1,212 @@ + +UTF-8 encoded sample plain-text file +‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾‾ + +Markus Kuhn [ˈmaʳkʊs kuːn] <http://www.cl.cam.ac.uk/~mgk25/> — 2002-07-25 + + +The ASCII compatible UTF-8 encoding used in this plain-text file +is defined in Unicode, ISO 10646-1, and RFC 2279. + + +Using Unicode/UTF-8, you can write in emails and source code things such as + +Mathematics and sciences: + + ∮ E⋅da = Q, n → ∞, ∑ f(i) = ∏ g(i), ⎧⎡⎛┌─────┐⎞⎤⎫ + ⎪⎢⎜│a²+b³ ⎟⎥⎪ + ∀x∈ℝ: ⌈x⌉ = −⌊−x⌋, α ∧ ¬β = ¬(¬α ∨ β), ⎪⎢⎜│───── ⎟⎥⎪ + ⎪⎢⎜⎷ c₈ ⎟⎥⎪ + ℕ ⊆ ℕ₀ ⊂ ℤ ⊂ ℚ ⊂ ℝ ⊂ ℂ, ⎨⎢⎜ ⎟⎥⎬ + ⎪⎢⎜ ∞ ⎟⎥⎪ + ⊥ < a ≠ b ≡ c ≤ d ≪ ⊤ ⇒ (⟦A⟧ ⇔ ⟪B⟫), ⎪⎢⎜ ⎲ ⎟⎥⎪ + ⎪⎢⎜ ⎳aⁱ-bⁱ⎟⎥⎪ + 2H₂ + O₂ ⇌ 2H₂O, R = 4.7 kΩ, ⌀ 200 mm ⎩⎣⎝i=1 ⎠⎦⎭ + +Linguistics and dictionaries: + + ði ıntəˈnæʃənəl fəˈnɛtık əsoʊsiˈeıʃn + Y [ˈʏpsilɔn], Yen [jɛn], Yoga [ˈjoːgɑ] + +APL: + + ((V⍳V)=⍳⍴V)/V←,V ⌷←⍳→⍴∆∇⊃‾⍎⍕⌈ + +Nicer typography in plain text files: + + ╔══════════════════════════════════════════╗ + ║ ║ + ║ • ‘single’ and “double” quotes ║ + ║ ║ + ║ • Curly apostrophes: “We’ve been here” ║ + ║ ║ + ║ • Latin-1 apostrophe and accents: '´` ║ + ║ ║ + ║ • ‚deutsche‘ „Anführungszeichen“ ║ + ║ ║ + ║ • †, ‡, ‰, •, 3–4, —, −5/+5, ™, … ║ + ║ ║ + ║ • ASCII safety test: 1lI|, 0OD, 8B ║ + ║ ╭─────────╮ ║ + ║ • the euro symbol: │ 14.95 € │ ║ + ║ ╰─────────╯ ║ + ╚══════════════════════════════════════════╝ + +Combining characters: + + STARGΛ̊TE SG-1, a = v̇ = r̈, a⃑ ⊥ b⃑ + +Greek (in Polytonic): + + The Greek anthem: + + Σὲ γνωρίζω ἀπὸ τὴν κόψη + τοῦ σπαθιοῦ τὴν τρομερή, + σὲ γνωρίζω ἀπὸ τὴν ὄψη + ποὺ μὲ βία μετράει τὴ γῆ. + + ᾿Απ᾿ τὰ κόκκαλα βγαλμένη + τῶν ῾Ελλήνων τὰ ἱερά + καὶ σὰν πρῶτα ἀνδρειωμένη + χαῖρε, ὦ χαῖρε, ᾿Ελευθεριά! + + From a speech of Demosthenes in the 4th century BC: + + Οὐχὶ ταὐτὰ παρίσταταί μοι γιγνώσκειν, ὦ ἄνδρες ᾿Αθηναῖοι, + ὅταν τ᾿ εἰς τὰ πράγματα ἀποβλέψω καὶ ὅταν πρὸς τοὺς + λόγους οὓς ἀκούω· τοὺς μὲν γὰρ λόγους περὶ τοῦ + τιμωρήσασθαι Φίλιππον ὁρῶ γιγνομένους, τὰ δὲ πράγματ᾿ + εἰς τοῦτο προήκοντα, ὥσθ᾿ ὅπως μὴ πεισόμεθ᾿ αὐτοὶ + πρότερον κακῶς σκέψασθαι δέον. οὐδέν οὖν ἄλλο μοι δοκοῦσιν + οἱ τὰ τοιαῦτα λέγοντες ἢ τὴν ὑπόθεσιν, περὶ ἧς βουλεύεσθαι, + οὐχὶ τὴν οὖσαν παριστάντες ὑμῖν ἁμαρτάνειν. ἐγὼ δέ, ὅτι μέν + ποτ᾿ ἐξῆν τῇ πόλει καὶ τὰ αὑτῆς ἔχειν ἀσφαλῶς καὶ Φίλιππον + τιμωρήσασθαι, καὶ μάλ᾿ ἀκριβῶς οἶδα· ἐπ᾿ ἐμοῦ γάρ, οὐ πάλαι + γέγονεν ταῦτ᾿ ἀμφότερα· νῦν μέντοι πέπεισμαι τοῦθ᾿ ἱκανὸν + προλαβεῖν ἡμῖν εἶναι τὴν πρώτην, ὅπως τοὺς συμμάχους + σώσομεν. ἐὰν γὰρ τοῦτο βεβαίως ὑπάρξῃ, τότε καὶ περὶ τοῦ + τίνα τιμωρήσεταί τις καὶ ὃν τρόπον ἐξέσται σκοπεῖν· πρὶν δὲ + τὴν ἀρχὴν ὀρθῶς ὑποθέσθαι, μάταιον ἡγοῦμαι περὶ τῆς + τελευτῆς ὁντινοῦν ποιεῖσθαι λόγον. + + Δημοσθένους, Γ´ ᾿Ολυνθιακὸς + +Georgian: + + From a Unicode conference invitation: + + გთხოვთ ახლავე გაიაროთ რეგისტრაცია Unicode-ის მეათე საერთაშორისო + კონფერენციაზე დასასწრებად, რომელიც გაიმართება 10-12 მარტს, + ქ. მაინცში, გერმანიაში. კონფერენცია შეჰკრებს ერთად მსოფლიოს + ექსპერტებს ისეთ დარგებში როგორიცაა ინტერნეტი და Unicode-ი, + ინტერნაციონალიზაცია და ლოკალიზაცია, Unicode-ის გამოყენება + ოპერაციულ სისტემებსა, და გამოყენებით პროგრამებში, შრიფტებში, + ტექსტების დამუშავებასა და მრავალენოვან კომპიუტერულ სისტემებში. + +Russian: + + From a Unicode conference invitation: + + Зарегистрируйтесь сейчас на Десятую Международную Конференцию по + Unicode, которая состоится 10-12 марта 1997 года в Майнце в Германии. + Конференция соберет широкий круг экспертов по вопросам глобального + Интернета и Unicode, локализации и интернационализации, воплощению и + применению Unicode в различных операционных системах и программных + приложениях, шрифтах, верстке и многоязычных компьютерных системах. + +Thai (UCS Level 2): + + Excerpt from a poetry on The Romance of The Three Kingdoms (a Chinese + classic 'San Gua'): + + [----------------------------|------------------------] + ๏ แผ่นดินฮั่นเสื่อมโทรมแสนสังเวช พระปกเกศกองบู๊กู้ขึ้นใหม่ + สิบสองกษัตริย์ก่อนหน้าแลถัดไป สององค์ไซร้โง่เขลาเบาปัญญา + ทรงนับถือขันทีเป็นที่พึ่ง บ้านเมืองจึงวิปริตเป็นนักหนา + โฮจิ๋นเรียกทัพทั่วหัวเมืองมา หมายจะฆ่ามดชั่วตัวสำคัญ + เหมือนขับไสไล่เสือจากเคหา รับหมาป่าเข้ามาเลยอาสัญ + ฝ่ายอ้องอุ้นยุแยกให้แตกกัน ใช้สาวนั้นเป็นชนวนชื่นชวนใจ + พลันลิฉุยกุยกีกลับก่อเหตุ ช่างอาเพศจริงหนาฟ้าร้องไห้ + ต้องรบราฆ่าฟันจนบรรลัย ฤๅหาใครค้ำชูกู้บรรลังก์ ฯ + + (The above is a two-column text. If combining characters are handled + correctly, the lines of the second column should be aligned with the + | character above.) + +Ethiopian: + + Proverbs in the Amharic language: + + ሰማይ አይታረስ ንጉሥ አይከሰስ። + ብላ ካለኝ እንደአባቴ በቆመጠኝ። + ጌጥ ያለቤቱ ቁምጥና ነው። + ደሀ በሕልሙ ቅቤ ባይጠጣ ንጣት በገደለው። + የአፍ ወለምታ በቅቤ አይታሽም። + አይጥ በበላ ዳዋ ተመታ። + ሲተረጉሙ ይደረግሙ። + ቀስ በቀስ፥ ዕንቁላል በእግሩ ይሄዳል። + ድር ቢያብር አንበሳ ያስር። + ሰው እንደቤቱ እንጅ እንደ ጉረቤቱ አይተዳደርም። + እግዜር የከፈተውን ጉሮሮ ሳይዘጋው አይድርም። + የጎረቤት ሌባ፥ ቢያዩት ይስቅ ባያዩት ያጠልቅ። + ሥራ ከመፍታት ልጄን ላፋታት። + ዓባይ ማደሪያ የለው፥ ግንድ ይዞ ይዞራል። + የእስላም አገሩ መካ የአሞራ አገሩ ዋርካ። + ተንጋሎ ቢተፉ ተመልሶ ባፉ። + ወዳጅህ ማር ቢሆን ጨርስህ አትላሰው። + እግርህን በፍራሽህ ልክ ዘርጋ። + +Runes: + + ᚻᛖ ᚳᚹᚫᚦ ᚦᚫᛏ ᚻᛖ ᛒᚢᛞᛖ ᚩᚾ ᚦᚫᛗ ᛚᚪᚾᛞᛖ ᚾᚩᚱᚦᚹᛖᚪᚱᛞᚢᛗ ᚹᛁᚦ ᚦᚪ ᚹᛖᛥᚫ + + (Old English, which transcribed into Latin reads 'He cwaeth that he + bude thaem lande northweardum with tha Westsae.' and means 'He said + that he lived in the northern land near the Western Sea.') + +Braille: + + ⡌⠁⠧⠑ ⠼⠁⠒ ⡍⠜⠇⠑⠹⠰⠎ ⡣⠕⠌ + + ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠙⠑⠁⠙⠒ ⠞⠕ ⠃⠑⠛⠔ ⠺⠊⠹⠲ ⡹⠻⠑ ⠊⠎ ⠝⠕ ⠙⠳⠃⠞ + ⠱⠁⠞⠑⠧⠻ ⠁⠃⠳⠞ ⠹⠁⠞⠲ ⡹⠑ ⠗⠑⠛⠊⠌⠻ ⠕⠋ ⠙⠊⠎ ⠃⠥⠗⠊⠁⠇ ⠺⠁⠎ + ⠎⠊⠛⠝⠫ ⠃⠹ ⠹⠑ ⠊⠇⠻⠛⠹⠍⠁⠝⠂ ⠹⠑ ⠊⠇⠻⠅⠂ ⠹⠑ ⠥⠝⠙⠻⠞⠁⠅⠻⠂ + ⠁⠝⠙ ⠹⠑ ⠡⠊⠑⠋ ⠍⠳⠗⠝⠻⠲ ⡎⠊⠗⠕⠕⠛⠑ ⠎⠊⠛⠝⠫ ⠊⠞⠲ ⡁⠝⠙ + ⡎⠊⠗⠕⠕⠛⠑⠰⠎ ⠝⠁⠍⠑ ⠺⠁⠎ ⠛⠕⠕⠙ ⠥⠏⠕⠝ ⠰⡡⠁⠝⠛⠑⠂ ⠋⠕⠗ ⠁⠝⠹⠹⠔⠛ ⠙⠑ + ⠡⠕⠎⠑ ⠞⠕ ⠏⠥⠞ ⠙⠊⠎ ⠙⠁⠝⠙ ⠞⠕⠲ + + ⡕⠇⠙ ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ + + ⡍⠔⠙⠖ ⡊ ⠙⠕⠝⠰⠞ ⠍⠑⠁⠝ ⠞⠕ ⠎⠁⠹ ⠹⠁⠞ ⡊ ⠅⠝⠪⠂ ⠕⠋ ⠍⠹ + ⠪⠝ ⠅⠝⠪⠇⠫⠛⠑⠂ ⠱⠁⠞ ⠹⠻⠑ ⠊⠎ ⠏⠜⠞⠊⠊⠥⠇⠜⠇⠹ ⠙⠑⠁⠙ ⠁⠃⠳⠞ + ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ ⡊ ⠍⠊⠣⠞ ⠙⠁⠧⠑ ⠃⠑⠲ ⠔⠊⠇⠔⠫⠂ ⠍⠹⠎⠑⠇⠋⠂ ⠞⠕ + ⠗⠑⠛⠜⠙ ⠁ ⠊⠕⠋⠋⠔⠤⠝⠁⠊⠇ ⠁⠎ ⠹⠑ ⠙⠑⠁⠙⠑⠌ ⠏⠊⠑⠊⠑ ⠕⠋ ⠊⠗⠕⠝⠍⠕⠝⠛⠻⠹ + ⠔ ⠹⠑ ⠞⠗⠁⠙⠑⠲ ⡃⠥⠞ ⠹⠑ ⠺⠊⠎⠙⠕⠍ ⠕⠋ ⠳⠗ ⠁⠝⠊⠑⠌⠕⠗⠎ + ⠊⠎ ⠔ ⠹⠑ ⠎⠊⠍⠊⠇⠑⠆ ⠁⠝⠙ ⠍⠹ ⠥⠝⠙⠁⠇⠇⠪⠫ ⠙⠁⠝⠙⠎ + ⠩⠁⠇⠇ ⠝⠕⠞ ⠙⠊⠌⠥⠗⠃ ⠊⠞⠂ ⠕⠗ ⠹⠑ ⡊⠳⠝⠞⠗⠹⠰⠎ ⠙⠕⠝⠑ ⠋⠕⠗⠲ ⡹⠳ + ⠺⠊⠇⠇ ⠹⠻⠑⠋⠕⠗⠑ ⠏⠻⠍⠊⠞ ⠍⠑ ⠞⠕ ⠗⠑⠏⠑⠁⠞⠂ ⠑⠍⠏⠙⠁⠞⠊⠊⠁⠇⠇⠹⠂ ⠹⠁⠞ + ⡍⠜⠇⠑⠹ ⠺⠁⠎ ⠁⠎ ⠙⠑⠁⠙ ⠁⠎ ⠁ ⠙⠕⠕⠗⠤⠝⠁⠊⠇⠲ + + (The first couple of paragraphs of "A Christmas Carol" by Dickens) + +Compact font selection example text: + + ABCDEFGHIJKLMNOPQRSTUVWXYZ /0123456789 + abcdefghijklmnopqrstuvwxyz £©µÀÆÖÞßéöÿ + –—‘“”„†•…‰™œŠŸž€ ΑΒΓΔΩαβγδω АБВГДабвгд + ∀∂∈ℝ∧∪≡∞ ↑↗↨↻⇣ ┐┼╔╘░►☺♀ fi�⑀₂ἠḂӥẄɐː⍎אԱა + +Greetings in various languages: + + Hello world, Καλημέρα κόσμε, コンニチハ + +Box drawing alignment tests: █ + ▉ + ╔══╦══╗ ┌──┬──┐ ╭──┬──╮ ╭──┬──╮ ┏━━┳━━┓ ┎┒┏┑ ╷ ╻ ┏┯┓ ┌┰┐ ▊ ╱╲╱╲╳╳╳ + ║┌─╨─┐║ │╔═╧═╗│ │╒═╪═╕│ │╓─╁─╖│ ┃┌─╂─┐┃ ┗╃╄┙ ╶┼╴╺╋╸┠┼┨ ┝╋┥ ▋ ╲╱╲╱╳╳╳ + ║│╲ ╱│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╿ │┃ ┍╅╆┓ ╵ ╹ ┗┷┛ └┸┘ ▌ ╱╲╱╲╳╳╳ + ╠╡ ╳ ╞╣ ├╢ ╟┤ ├┼─┼─┼┤ ├╫─╂─╫┤ ┣┿╾┼╼┿┫ ┕┛┖┚ ┌┄┄┐ ╎ ┏┅┅┓ ┋ ▍ ╲╱╲╱╳╳╳ + ║│╱ ╲│║ │║ ║│ ││ │ ││ │║ ┃ ║│ ┃│ ╽ │┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▎ + ║└─╥─┘║ │╚═╤═╝│ │╘═╪═╛│ │╙─╀─╜│ ┃└─╂─┘┃ ░░▒▒▓▓██ ┊ ┆ ╎ ╏ ┇ ┋ ▏ + ╚══╩══╝ └──┴──┘ ╰──┴──╯ ╰──┴──╯ ┗━━┻━━┛ ▗▄▖▛▀▜ └╌╌┘ ╎ ┗╍╍┛ ┋ ▁▂▃▄▅▆▇█ + ▝▀▘▙▄▟ diff --git a/third-party/utf8cpp/test_data/utf8samples/Unicode_transcriptions.html b/third-party/utf8cpp/test_data/utf8samples/Unicode_transcriptions.html new file mode 100644 index 0000000..69b29ff --- /dev/null +++ b/third-party/utf8cpp/test_data/utf8samples/Unicode_transcriptions.html @@ -0,0 +1,167 @@ +? *Unicode Transcriptions* Notes <#Notes> + +Glyphs <http://www.macchiato.com/unicode/show.html> | Samples +<http://www.macchiato.com/unicode/Unicode_transcriptions.html> | Charts +<http://www.macchiato.com/unicode/charts.html> | UTF +<http://www.macchiato.com/unicode/convert.html> | Forms +<http://www-4.ibm.com/software/developer/library/utfencodingforms/> | +Home <http://www.macchiato.com>. +<http://member.linkexchange.com/cgi-bin/fc/fastcounter-login?750641> + +Name Text Image +Arabic (Arabic) يونِكود ? +Arabic (Persian) یونیکُد / ?/ +Armenian Յունիկօդ +Bengali য়ূনিকোড +Bopomofo ㄊㄨㄥ˅ ㄧˋ ㄇㄚ˅ +ㄨㄢˋ ㄍㄨㄛˊ ㄇㄚ˅ +Braille +Buhid +Canadian Aboriginal ᔫᗂᑰᑦ +Cherokee ᏳᏂᎪᏛ +Cypriot +Cyrillic (Russian) Юникод ? +Deseret (English) ??????? +Devanagari (Hindi) यूनिकोड ? +Ethiopic ዩኒኮድ +Georgian უნიკოდი ? +Gothic +Greek Γιούνικοντ +Gujarati યૂનિકોડ +Gurmukhi ਯੂਨਿਕੋਡ +Han (Chinese) 统一码 ? +統一碼 ? +万国码 ? +萬國碼 ? +Hangul 유니코드 +Hanunoo +Hebrew יוניקוד +Hebrew (pointed) יוּנִיקוׁד +Hebrew (Yiddish) יוניקאָד ? +Hiragana (Japanese) ゆにこおど +Katakana (Japanese) ユニコード ? +Kannada ಯೂನಿಕೋಡ್ +Khmer យូនីគោដ +Lao +Latin Unicode Unicode +Latin (IPA <#English_Pronunciation>) ˈjunɪˌkoːd ? +Latin (Am. Dict. <#American_Dictionary>) Ūnĭcōde̽ ? +Limbu +Linear B +Malayalam യൂനികോഡ് +Mongolian +Myanmar +Ogham ᚔᚒᚅᚔᚉᚑᚇ / / +Old Italic +Oriya ୟୂନିକୋଡ +Osmanya +Runic (Anglo-Saxon) ᛡᚢᚾᛁᚳᚩᛞ +Shavian +Sinhala යණනිකෞද් +Syriac ܝܘܢܝܩܘܕ +Tagbanwa +Tagalog +Tai Le +Tamil யூனிகோட் +Telugu యూనికోడ్ +Thaana +Thai ยูนืโคด +Tibetan (Dzongkha) ཨུ་ནི་ཀོཌྲ། +Ugaritic +Yi + + + Notes: + +There are different ways to transcribe the word “Unicode”, depending on +the language and script. In some cases there is only one language that +customarily uses a given script; in others there are many languages. The +goal here is at a minimum to collect at least one transcription for each +script in a language customarily written in that script, with more +languages if possible. If the transcription is the same for multiple +languages in a script, then a single representative language is used. + +Still missing are transcriptions for the items above in RED (in at least +one language). I would appreciate any other transcriptions, or +corrections for the ones listed here. Send to mark3@macchiato.com +<mailto:mark3@macchiato.com>, using the directions below: + + * *Supplying Missing Items* + o Most Latin-script languages will follow the spelling, and + change the pronunciation. For any that would not, it would + be good to have the alternate spelling. + o For non-Latin scripts the goal is to match the English + pronunciation — /*not*/ spelling. Above is the IPA <#IPA> + (in phonemic transcription) that should be matched as + closely as possible (without sounding affected in the target + language) + o Text would be best in either the UTF-8 text, or the code + points in hex HTML. E.g. either of the following: + + "Юникод" + + "Юникод" + + Note: for / supplementary characters/ + <http://www.unicode.org/glossary/#supplementary_character>, + there should be one hex number per code point, not two + surrogates + <http://www.unicode.org/glossary/#surrogate_code_point>: + # 𐀀 /*not*/ �&xDC00; + o If you have a good font, I'd also appreciate a GIF. It + should be *96 x 24* bits, with the text centered, in black + on white (plus grays if smoothed). + * *Other Comments* + o Because some browsers won't handle the text, both text and + GIF image are supplied. If you can’t read the text columns, + see Display Problems + <http://www.unicode.org/help/display_problems.html>. + o The Chinese versions (inc. Bopomofo) are translations, not + transcriptions, since "transcription in Chinese is pretty + lame" [J. Becker]. + o There are other "translations" of Unicode that may be in + use, such as the Vietnamese "Thống Nhất Mã". + o For sample pages in different languages on the Unicode site, + see What is Unicode? + <http://www.unicode.org/unicode/standard/WhatIsUnicode.html> + o Americans are not generally used to IPA, and find a variety + of different systems in their dictionaries. This one leaves + the base letters as they are, and uses diacritics for + pronunciation. + * *Etymology of /Unicode/* + o Coined by J. Becker. Not related to previous usages, such as: + + A telegraphic code in which one word or set of letters + represents a sentence or phrase; a telegram or message + in this. (late 19th century, OED) + o According to my references, the prefix "uni" is directly + from Latin while the word "code" is through French. + o The original Indo-European apparently would have been + *oino-kau-do ("one strike give"): *kau apparently being + related to such English words as: hew, haggle, hoe, hag, + hay, hack, caudad, caudal, caudate, caudex, coda, codex, + codicil, coward, incus, and Kovač (personal name: "smith"). + + I will leave the exact derivations to the exegetes, + but I like the association with "haggle" myself. + * *Contributions* + o This draws on contributions or comments from: + + Dixon Au + + Joe Becker + + Maurice Bauhahn + + Abel Cheung + + Peter Constable + + Michael Everson + + Christopher John Fynn + + Michael Kaplan + + George Kiraz + + Abdul Malik + + Siva Nataraja + + Roozbeh Pournader + + Jonathan Rosenne + + Jungshik Shin + +------------------------------------------------------------------------ + + +Terms of Use <http://www.macchiato.com/terms_of_use.html>. Last updated: +MED - 04/20/2003 15:30:33. +<http://member.linkexchange.com/cgi-bin/fc/fastcounter-login?750641> + + + diff --git a/third-party/utf8cpp/test_data/utf8samples/quickbrown.txt b/third-party/utf8cpp/test_data/utf8samples/quickbrown.txt new file mode 100644 index 0000000..5db9443 --- /dev/null +++ b/third-party/utf8cpp/test_data/utf8samples/quickbrown.txt @@ -0,0 +1,126 @@ +Sentences that contain all letters commonly used in a language +-------------------------------------------------------------- + +Markus Kuhn <http://www.cl.cam.ac.uk/~mgk25/> -- 2001-09-02 + +This file is UTF-8 encoded. + + +Danish (da) +--------- + + Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen + Wolther spillede på xylofon. + (= Quiz contestants were eating strawbery with cream while Wolther + the circus clown played on xylophone.) + +German (de) +----------- + + Falsches Üben von Xylophonmusik quält jeden größeren Zwerg + (= Wrongful practicing of xylophone music tortures every larger dwarf) + + Zwölf Boxkämpfer jagten Eva quer über den Sylter Deich + (= Twelve boxing fighters hunted Eva across the dike of Sylt) + + Heizölrückstoßabdämpfung + (= fuel oil recoil absorber) + (jqvwxy missing, but all non-ASCII letters in one word) + +English (en) +------------ + + The quick brown fox jumps over the lazy dog + +Spanish (es) +------------ + + El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y + frío, añoraba a su querido cachorro. + (Contains every letter and every accent, but not every combination + of vowel + acute.) + +French (fr) +----------- + + Portez ce vieux whisky au juge blond qui fume sur son île intérieure, à + côté de l'alcôve ovoïde, où les bûches se consument dans l'âtre, ce + qui lui permet de penser à la cænogenèse de l'être dont il est question + dans la cause ambiguë entendue à Moÿ, dans un capharnaüm qui, + pense-t-il, diminue çà et là la qualité de son œuvre. + + l'île exiguë + Où l'obèse jury mûr + Fête l'haï volapük, + Âne ex aéquo au whist, + Ôtez ce vœu déçu. + + Le cœur déçu mais l'âme plutôt naïve, Louÿs rêva de crapaüter en + canoë au delà des îles, près du mälström où brûlent les novæ. + +Irish Gaelic (ga) +----------------- + + D'fhuascail Íosa, Úrmhac na hÓighe Beannaithe, pór Éava agus Ádhaimh + +Hungarian (hu) +-------------- + + Árvíztűrő tükörfúrógép + (= flood-proof mirror-drilling machine, only all non-ASCII letters) + +Icelandic (is) +-------------- + + Kæmi ný öxi hér ykist þjófum nú bæði víl og ádrepa + + Sævör grét áðan því úlpan var ónýt + (some ASCII letters missing) + +Japanese (jp) +------------- + + Hiragana: (Iroha) + + いろはにほへとちりぬるを + わかよたれそつねならむ + うゐのおくやまけふこえて + あさきゆめみしゑひもせす + + Katakana: + + イロハニホヘト チリヌルヲ ワカヨタレソ ツネナラム + ウヰノオクヤマ ケフコエテ アサキユメミシ ヱヒモセスン + +Hebrew (iw) +----------- + + ? דג סקרן שט בים מאוכזב ולפתע מצא לו חברה איך הקליטה + +Polish (pl) +----------- + + Pchnąć w tę łódź jeża lub ośm skrzyń fig + (= To push a hedgehog or eight bins of figs in this boat) + +Russian (ru) +------------ + + В чащах юга жил бы цитрус? Да, но фальшивый экземпляр! + (= Would a citrus live in the bushes of south? Yes, but only a fake one!) + +Thai (th) +--------- + + [--------------------------|------------------------] + ๏ เป็นมนุษย์สุดประเสริฐเลิศคุณค่า กว่าบรรดาฝูงสัตว์เดรัจฉาน + จงฝ่าฟันพัฒนาวิชาการ อย่าล้างผลาญฤๅเข่นฆ่าบีฑาใคร + ไม่ถือโทษโกรธแช่งซัดฮึดฮัดด่า หัดอภัยเหมือนกีฬาอัชฌาสัย + ปฏิบัติประพฤติกฎกำหนดใจ พูดจาให้จ๊ะๆ จ๋าๆ น่าฟังเอย ฯ + + [The copyright for the Thai example is owned by The Computer + Association of Thailand under the Royal Patronage of His Majesty the + King.] + +Please let me know if you find others! Special thanks to the people +from all over the world who contributed these sentences. diff --git a/third-party/utf8cpp/test_drivers/negative/negative.cpp b/third-party/utf8cpp/test_drivers/negative/negative.cpp new file mode 100644 index 0000000..0f1015d --- /dev/null +++ b/third-party/utf8cpp/test_drivers/negative/negative.cpp @@ -0,0 +1,53 @@ +#include "../../source/utf8.h" +using namespace utf8; + +#include <string> +#include <iostream> +#include <fstream> +#include <algorithm> +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; + exit(0); + } + // Open the test file + ifstream fs8(test_file_path.c_str()); + if (!fs8.is_open()) { + cout << "Could not open " << test_file_path << endl; + return 0; + } + + // Read it line by line + unsigned int line_count = 0; + char byte; + while (!fs8.eof()) { + string line; + while ((byte = static_cast<char>(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'; + + // 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'; + } + else if (!expected_valid) + cout << "Invalid utf-8 NOT detected at line " << line_count << '\n'; + } +} diff --git a/third-party/utf8cpp/test_drivers/smoke_test/test.cpp b/third-party/utf8cpp/test_drivers/smoke_test/test.cpp new file mode 100644 index 0000000..4f9fb04 --- /dev/null +++ b/third-party/utf8cpp/test_drivers/smoke_test/test.cpp @@ -0,0 +1,298 @@ +#include <cstring> +#include <cassert> +#include <vector> +#include "../../source/utf8.h" +using namespace utf8; +using namespace std; + +int main() +{ + //append + unsigned char u[5] = {0,0,0,0,0}; + + append(0x0448, u); + assert (u[0] == 0xd1 && u[1] == 0x88 && u[2] == 0 && u[3] == 0 && u[4] == 0); + + append(0x65e5, u); + assert (u[0] == 0xe6 && u[1] == 0x97 && u[2] == 0xa5 && u[3] == 0 && u[4] == 0); + + append(0x3044, u); + assert (u[0] == 0xe3 && u[1] == 0x81 && u[2] == 0x84 && u[3] == 0 && u[4] == 0); + + append(0x10346, u); + assert (u[0] == 0xf0 && u[1] == 0x90 && u[2] == 0x8d && u[3] == 0x86 && u[4] == 0); + + + //next + const char* twochars = "\xe6\x97\xa5\xd1\x88"; + const char* w = twochars; + int cp = next(w, twochars + 6); + assert (cp == 0x65e5); + assert (w == twochars + 3); + + const char* threechars = "\xf0\x90\x8d\x86\xe6\x97\xa5\xd1\x88"; + w = threechars; + cp = next(w, threechars + 9); + assert (cp == 0x10346); + assert (w == threechars + 4); + cp = next(w, threechars + 9); + assert (cp == 0x65e5); + assert (w == threechars + 7); + cp = next(w, threechars + 9); + assert (cp == 0x0448); + assert (w == threechars + 9); + + //peek_next + const char* const cw = twochars; + cp = peek_next(cw, cw + 6); + assert (cp == 0x65e5); + assert (cw == twochars); + + //prior + w = twochars + 3; + cp = prior (w, twochars); + assert (cp == 0x65e5); + assert (w == twochars); + + w = threechars + 9; + cp = prior(w, threechars); + assert (cp == 0x0448); + assert (w == threechars + 7); + cp = prior(w, threechars); + assert (cp == 0x65e5); + assert (w == threechars + 4); + cp = prior(w, threechars); + assert (cp == 0x10346); + assert (w == threechars); + + //previous (deprecated) + w = twochars + 3; + cp = previous (w, twochars - 1); + assert (cp == 0x65e5); + assert (w == twochars); + + w = threechars + 9; + cp = previous(w, threechars - 1); + assert (cp == 0x0448); + assert (w == threechars + 7); + cp = previous(w, threechars -1); + assert (cp == 0x65e5); + assert (w == threechars + 4); + cp = previous(w, threechars - 1); + assert (cp == 0x10346); + assert (w == threechars); + + // advance + w = twochars; + advance (w, 2, twochars + 6); + assert (w == twochars + 5); + + // distance + size_t dist = utf8::distance(twochars, twochars + 5); + assert (dist == 2); + + // utf32to8 + int utf32string[] = {0x448, 0x65E5, 0x10346, 0}; + vector<char> utf8result; + utf32to8(utf32string, utf32string + 3, back_inserter(utf8result)); + assert (utf8result.size() == 9); + // try it with the return value; + char* utf8_end = utf32to8(utf32string, utf32string + 3, &utf8result[0]); + assert (utf8_end == &utf8result[0] + 9); + + //utf8to32 + vector<int> utf32result; + utf8to32(twochars, twochars + 5, back_inserter(utf32result)); + assert (utf32result.size() == 2); + // try it with the return value; + int* utf32_end = utf8to32(twochars, twochars + 5, &utf32result[0]); + assert (utf32_end == &utf32result[0] + 2); + + //utf16to8 + unsigned short utf16string[] = {0x41, 0x0448, 0x65e5, 0xd834, 0xdd1e}; + utf8result.clear(); + utf16to8(utf16string, utf16string + 5, back_inserter(utf8result)); + assert (utf8result.size() == 10); + // try it with the return value; + utf8_end = utf16to8 (utf16string, utf16string + 5, &utf8result[0]); + assert (utf8_end == &utf8result[0] + 10); + + //utf8to16 + char utf8_with_surrogates[] = "\xe6\x97\xa5\xd1\x88\xf0\x9d\x84\x9e"; + vector <unsigned short> utf16result; + utf8to16(utf8_with_surrogates, utf8_with_surrogates + 9, back_inserter(utf16result)); + assert (utf16result.size() == 4); + assert (utf16result[2] == 0xd834); + assert (utf16result[3] == 0xdd1e); + // try it with the return value; + unsigned short* utf16_end = utf8to16 (utf8_with_surrogates, utf8_with_surrogates + 9, &utf16result[0]); + assert (utf16_end == &utf16result[0] + 4); + + //find_invalid + char utf_invalid[] = "\xe6\x97\xa5\xd1\x88\xfa"; + char* invalid = find_invalid(utf_invalid, utf_invalid + 6); + assert (invalid == utf_invalid + 5); + + //is_valid + bool bvalid = is_valid(utf_invalid, utf_invalid + 6); + assert (bvalid == false); + bvalid = is_valid(utf8_with_surrogates, utf8_with_surrogates + 9); + assert (bvalid == true); + + //starts_with_bom + unsigned char byte_order_mark[] = {0xef, 0xbb, 0xbf}; + bool bbom = starts_with_bom(byte_order_mark, byte_order_mark + sizeof(byte_order_mark)); + assert (bbom == true); + bool no_bbom = starts_with_bom(threechars, threechars + sizeof(threechars)); + assert (no_bbom == false); + + //is_bom + bool unsafe_bbom = is_bom(byte_order_mark); + assert (unsafe_bbom == true); + + + //replace_invalid + char invalid_sequence[] = "a\x80\xe0\xa0\xc0\xaf\xed\xa0\x80z"; + vector<char> replace_invalid_result; + replace_invalid (invalid_sequence, invalid_sequence + sizeof(invalid_sequence), std::back_inserter(replace_invalid_result), '?'); + bvalid = is_valid(replace_invalid_result.begin(), replace_invalid_result.end()); + assert (bvalid); + const char fixed_invalid_sequence[] = "a????z"; + assert (sizeof(fixed_invalid_sequence) == replace_invalid_result.size()); + assert (std::equal(replace_invalid_result.begin(), replace_invalid_result.begin() + sizeof(fixed_invalid_sequence), fixed_invalid_sequence)); + + // iterator + utf8::iterator<const char*> it(threechars, threechars, threechars + 9); + utf8::iterator<const char*> it2 = it; + assert (it2 == it); + assert (*it == 0x10346); + assert (*(++it) == 0x65e5); + assert ((*it++) == 0x65e5); + assert (*it == 0x0448); + assert (it != it2); + utf8::iterator<const char*> endit (threechars + 9, threechars, threechars + 9); + assert (++it == endit); + assert (*(--it) == 0x0448); + assert ((*it--) == 0x0448); + assert (*it == 0x65e5); + assert (--it == utf8::iterator<const char*>(threechars, threechars, threechars + 9)); + assert (*it == 0x10346); + + ////////////////////////////////////////////////////////// + //// Unchecked variants + ////////////////////////////////////////////////////////// + + //append + memset(u, 0, 5); + append(0x0448, u); + assert (u[0] == 0xd1 && u[1] == 0x88 && u[2] == 0 && u[3] == 0 && u[4] == 0); + + append(0x65e5, u); + assert (u[0] == 0xe6 && u[1] == 0x97 && u[2] == 0xa5 && u[3] == 0 && u[4] == 0); + + append(0x10346, u); + assert (u[0] == 0xf0 && u[1] == 0x90 && u[2] == 0x8d && u[3] == 0x86 && u[4] == 0); + + //next + w = twochars; + cp = unchecked::next(w); + assert (cp == 0x65e5); + assert (w == twochars + 3); + + w = threechars; + cp = unchecked::next(w); + assert (cp == 0x10346); + assert (w == threechars + 4); + cp = unchecked::next(w); + assert (cp == 0x65e5); + assert (w == threechars + 7); + cp = unchecked::next(w); + assert (cp == 0x0448); + assert (w == threechars + 9); + + //peek_next + cp = unchecked::peek_next(cw); + assert (cp == 0x65e5); + assert (cw == twochars); + + + //previous (calls prior internally) + + w = twochars + 3; + cp = unchecked::previous (w); + assert (cp == 0x65e5); + assert (w == twochars); + + w = threechars + 9; + cp = unchecked::previous(w); + assert (cp == 0x0448); + assert (w == threechars + 7); + cp = unchecked::previous(w); + assert (cp == 0x65e5); + assert (w == threechars + 4); + cp = unchecked::previous(w); + assert (cp == 0x10346); + assert (w == threechars); + + // advance + w = twochars; + unchecked::advance (w, 2); + assert (w == twochars + 5); + + // distance + dist = unchecked::distance(twochars, twochars + 5); + assert (dist == 2); + + // utf32to8 + utf8result.clear(); + unchecked::utf32to8(utf32string, utf32string + 3, back_inserter(utf8result)); + assert (utf8result.size() == 9); + // try it with the return value; + utf8_end = utf32to8(utf32string, utf32string + 3, &utf8result[0]); + assert(utf8_end == &utf8result[0] + 9); + + //utf8to32 + utf32result.clear(); + unchecked::utf8to32(twochars, twochars + 5, back_inserter(utf32result)); + assert (utf32result.size() == 2); + // try it with the return value; + utf32_end = utf8to32(twochars, twochars + 5, &utf32result[0]); + assert (utf32_end == &utf32result[0] + 2); + + //utf16to8 + utf8result.clear(); + unchecked::utf16to8(utf16string, utf16string + 5, back_inserter(utf8result)); + assert (utf8result.size() == 10); + // try it with the return value; + utf8_end = utf16to8 (utf16string, utf16string + 5, &utf8result[0]); + assert (utf8_end == &utf8result[0] + 10); + + //utf8to16 + utf16result.clear(); + unchecked::utf8to16(utf8_with_surrogates, utf8_with_surrogates + 9, back_inserter(utf16result)); + assert (utf16result.size() == 4); + assert (utf16result[2] == 0xd834); + assert (utf16result[3] == 0xdd1e); + // try it with the return value; + utf16_end = utf8to16 (utf8_with_surrogates, utf8_with_surrogates + 9, &utf16result[0]); + assert (utf16_end == &utf16result[0] + 4); + + // iterator + utf8::unchecked::iterator<const char*> un_it(threechars); + utf8::unchecked::iterator<const char*> un_it2 = un_it; + assert (un_it2 == un_it); + assert (*un_it == 0x10346); + assert (*(++un_it) == 0x65e5); + assert ((*un_it++) == 0x65e5); + assert (un_it != un_it2); + assert (*un_it == 0x0448); + utf8::unchecked::iterator<const char*> 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<const char*>(threechars)); + assert (*un_it == 0x10346); +} + + diff --git a/third-party/utf8cpp/test_drivers/utf8reader/utf8reader.cpp b/third-party/utf8cpp/test_drivers/utf8reader/utf8reader.cpp new file mode 100644 index 0000000..c88a5ee --- /dev/null +++ b/third-party/utf8cpp/test_drivers/utf8reader/utf8reader.cpp @@ -0,0 +1,160 @@ +#include "../../source/utf8.h" +using namespace utf8; + +#include <string> +#include <iostream> +#include <fstream> +#include <vector> +using namespace std; + +int main(int argc, char** argv) +{ + if (argc != 2) { + cout << "\nUsage: utfreader filename\n"; + return 0; + } + const char* TEST_FILE_PATH = argv[1]; + // Open the test file + ifstream fs8(TEST_FILE_PATH); + if (!fs8.is_open()) { + cout << "Could not open " << TEST_FILE_PATH << endl; + return 0; + } + + // Read it line by line + unsigned int line_count = 0; + char byte; + while (!fs8.eof()) { + string line; + while ((byte = static_cast<char>(fs8.get())) != '\n' && !fs8.eof()) + line.push_back(byte); + + line_count++; + // Play around with each line and convert it to utf16 + string::iterator line_start = line.begin(); + string::iterator line_end = line.end(); + line_end = find_invalid(line_start, line_end); + if (line_end != line.end()) + cout << "Line " << line_count << ": Invalid utf-8 at byte " << int(line.end() - line_end) << '\n'; + + // Convert it to utf-16 and write to the file + vector<unsigned short> utf16_line; + utf8to16(line_start, line_end, back_inserter(utf16_line)); + + // Back to utf-8 and compare it to the original line. + string back_to_utf8; + utf16to8(utf16_line.begin(), utf16_line.end(), back_inserter(back_to_utf8)); + if (back_to_utf8.compare(string(line_start, line_end)) != 0) + cout << "Line " << line_count << ": Conversion to UTF-16 and back failed" << '\n'; + + // Now, convert it to utf-32, back to utf-8 and compare + vector <unsigned> utf32_line; + utf8to32(line_start, line_end, back_inserter(utf32_line)); + back_to_utf8.clear(); + utf32to8(utf32_line.begin(), utf32_line.end(), back_inserter(back_to_utf8)); + if (back_to_utf8.compare(string(line_start, line_end)) != 0) + cout << "Line " << line_count << ": Conversion to UTF-32 and back failed" << '\n'; + + // Now, iterate and back + unsigned char_count = 0; + string::iterator it = line_start; + while (it != line_end) { + unsigned int next_cp = peek_next(it, line_end); + if (next(it, line_end) != next_cp) + cout << "Line " << line_count << ": Error: peek_next gave a different result than next" << '\n'; + char_count++; + } + if (char_count != utf32_line.size()) + cout << "Line " << line_count << ": Error in iterating with next - wrong number of characters" << '\n'; + + string::iterator adv_it = line_start; + utf8::advance(adv_it, char_count, line_end); + if (adv_it != line_end) + cout << "Line " << line_count << ": Error in advance function" << '\n'; + + if (string::size_type(utf8::distance(line_start, line_end)) != char_count) + cout << "Line " << line_count << ": Error in distance function" << '\n'; + + while (it != line_start) { + previous(it, line.rend().base()); + char_count--; + } + if (char_count != 0) + cout << "Line " << line_count << ": Error in iterating with previous - wrong number of characters" << '\n'; + + // Try utf8::iterator + utf8::iterator<string::iterator> u8it(line_start, line_start, line_end); + if (!utf32_line.empty() && *u8it != utf32_line.at(0)) + cout << "Line " << line_count << ": Error in utf::iterator * operator" << '\n'; + if (std::distance(u8it, utf8::iterator<string::iterator>(line_end, line_start, line_end)) != static_cast<int>(utf32_line.size())) + cout << "Line " << line_count << ": Error in using utf::iterator with std::distance - wrong number of characters" << '\n'; + + std::advance(u8it, utf32_line.size()); + if (u8it != utf8::iterator<string::iterator>(line_end, line_start, line_end)) + cout << "Line " << line_count << ": Error in using utf::iterator with std::advance" << '\n'; + + + //======================== Now, the unchecked versions ====================== + // Convert it to utf-16 and compare to the checked version + vector<unsigned short> utf16_line_unchecked; + unchecked::utf8to16(line_start, line_end, back_inserter(utf16_line_unchecked)); + + if (utf16_line != utf16_line_unchecked) + cout << "Line " << line_count << ": Error in unchecked::utf8to16" << '\n'; + + // Back to utf-8 and compare it to the original line. + back_to_utf8.clear(); + unchecked::utf16to8(utf16_line_unchecked.begin(), utf16_line_unchecked.end(), back_inserter(back_to_utf8)); + if (back_to_utf8.compare(string(line_start, line_end)) != 0) + cout << "Line " << line_count << ": Unchecked conversion to UTF-16 and back failed" << '\n'; + + // Now, convert it to utf-32, back to utf-8 and compare + vector <unsigned> utf32_line_unchecked; + unchecked::utf8to32(line_start, line_end, back_inserter(utf32_line_unchecked)); + if (utf32_line != utf32_line_unchecked) + cout << "Line " << line_count << ": Error in unchecked::utf8to32" << '\n'; + + back_to_utf8.clear(); + unchecked::utf32to8(utf32_line.begin(), utf32_line.end(), back_inserter(back_to_utf8)); + if (back_to_utf8.compare(string(line_start, line_end)) != 0) + cout << "Line " << line_count << ": Unchecked conversion to UTF-32 and back failed" << '\n'; + + // Now, iterate and back + char_count = 0; + it = line_start; + while (it != line_end) { + unsigned int next_cp = unchecked::peek_next(it); + if (unchecked::next(it) != next_cp) + cout << "Line " << line_count << ": Error: unchecked::peek_next gave a different result than unchecked::next" << '\n';; + char_count++; + } + if (char_count != utf32_line.size()) + cout << "Line " << line_count << ": Error in iterating with unchecked::next - wrong number of characters" << '\n'; + + adv_it = line_start; + utf8::unchecked::advance(adv_it, char_count); + if (adv_it != line_end) + cout << "Line " << line_count << ": Error in unchecked::advance function" << '\n'; + + if (string::size_type(utf8::unchecked::distance(line_start, line_end)) != char_count) + cout << "Line " << line_count << ": Error in unchecked::distance function" << '\n'; + + while (it != line_start) { + unchecked::previous(it); + char_count--; + } + if (char_count != 0) + cout << "Line " << line_count << ": Error in iterating with unchecked::previous - wrong number of characters" << '\n'; + + // Try utf8::unchecked::iterator + utf8::unchecked::iterator<string::iterator> un_u8it(line_start); + if (!utf32_line.empty() && *un_u8it != utf32_line.at(0)) + cout << "Line " << line_count << ": Error in utf::unchecked::iterator * operator" << '\n'; + if (std::distance(un_u8it, utf8::unchecked::iterator<string::iterator>(line_end)) != static_cast<int>(utf32_line.size())) + cout << "Line " << line_count << ": Error in using utf::unchecked::iterator with std::distance - wrong number of characters" << '\n'; + + std::advance(un_u8it, utf32_line.size()); + if (un_u8it != utf8::unchecked::iterator<string::iterator>(line_end)) + cout << "Line " << line_count << ": Error in using utf::unchecked::iterator with std::advance" << '\n'; + } +} |