From 79835a5fa57271f07a90ed36123e30ae9741178e Mon Sep 17 00:00:00 2001 From: nemtrif Date: Wed, 28 Dec 2022 12:47:32 -0500 Subject: [PATCH 01/10] Remove -Wsign-conversion from test builds. --- tests/CMakeLists.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/CMakeLists.txt b/tests/CMakeLists.txt index 5024470..f3ce258 100644 --- a/tests/CMakeLists.txt +++ b/tests/CMakeLists.txt @@ -13,7 +13,7 @@ target_link_libraries(noexceptionstests PRIVATE utf8::cpp) target_compile_options(${PROJECT_NAME} INTERFACE $<$:/W4> - $<$>:-Wall -Wextra -Wpedantic -Wconversion -Wsign-conversion>) + $<$>:-Wall -Wextra -Wpedantic -Wconversion>) target_compile_options(noexceptionstests PUBLIC -fno-exceptions) From 2ad995746bf1731d5e21cde47c9c3deff56bdbc2 Mon Sep 17 00:00:00 2001 From: spaette <111918424+spaette@users.noreply.github.com> Date: Fri, 13 Jan 2023 13:59:18 -0600 Subject: [PATCH 02/10] typos --- README.md | 40 ++++++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 20 deletions(-) diff --git a/README.md b/README.md index a519cdb..02d9f75 100644 --- a/README.md +++ b/README.md @@ -11,7 +11,7 @@ The purpose of this article is not to offer an introduction to Unicode in genera ## Examples of use -### Introductionary Sample +### Introductory Sample To illustrate the use of the library, let's start with a small but complete program that opens a file containing UTF-8 encoded text, reads it line by line, checks each line for invalid UTF-8 byte sequences, and converts it to UTF-16 encoding and back to UTF-8: @@ -149,7 +149,7 @@ The function will replace any invalid UTF-8 sequence with a Unicode replacement The library was designed to be: 1. Generic: for better or worse, there are many C++ string classes out there, and the library should work with as many of them as possible. -2. Portable: the library should be portable both accross different platforms and compilers. The only non-portable code is a small section that declares unsigned integers of different sizes: three typedefs. They can be changed by the users of the library if they don't match their platform. The default setting should work for Windows (both 32 and 64 bit), and most 32 bit and 64 bit Unix derivatives. Support for post C++03 language features is included for modern compilers at API level only, so the library should work even with pretty old compilers. +2. Portable: the library should be portable both across different platforms and compilers. The only non-portable code is a small section that declares unsigned integers of different sizes: three typedefs. They can be changed by the users of the library if they don't match their platform. The default setting should work for Windows (both 32 and 64 bit), and most 32 bit and 64 bit Unix derivatives. Support for post C++03 language features is included for modern compilers at API level only, so the library should work even with pretty old compilers. 3. Lightweight: follow the "pay only for what you use" guideline. 4. Unintrusive: avoid forcing any particular design or even programming style on the user. This is a library, not a framework. @@ -157,7 +157,7 @@ The library was designed to be: 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. +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 definitely 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. @@ -247,7 +247,7 @@ 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. +In case of an invalid UTF-8 sequence, a `utf8::invalid_utf8` exception is thrown. #### utf8::peek_next @@ -276,7 +276,7 @@ assert (cp == 0x65e5); assert (w == twochars); ``` -In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown. +In case of an invalid UTF-8 sequence, a `utf8::invalid_utf8` exception is thrown. #### utf8::prior @@ -345,7 +345,7 @@ In case of an invalid code point, a `utf8::invalid_code_point` exception is thro 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. +Given the iterators to two UTF-8 encoded code points in a sequence, returns the number of code points between them. ```cpp template @@ -367,7 +367,7 @@ 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. +In case of an invalid UTF-8 sequence, a `utf8::invalid_utf8` exception is thrown. If `last` does not point to the past-of-end of a UTF-8 sequence, a `utf8::not_enough_room` exception is thrown. #### utf8::utf16to8 @@ -469,7 +469,7 @@ assert (utf16result[2] == 0xd834); assert (utf16result[3] == 0xdd1e); ``` -In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown. +In case of an invalid UTF-8 sequence, a `utf8::invalid_utf8` exception is thrown. #### utf8::utf8to16 @@ -494,7 +494,7 @@ assert (utf16result[2] == 0xd834); assert (utf16result[3] == 0xdd1e); ``` -In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown. +In case of an invalid UTF-8 sequence, a `utf8::invalid_utf8` exception is thrown. #### utf8::utf8to16 @@ -525,7 +525,7 @@ 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. +In case of an invalid UTF-8 sequence, a `utf8::invalid_utf8` exception is thrown. If `end` does not point to the past-of-end of a UTF-8 sequence, a `utf8::not_enough_room` exception is thrown. #### utf8::utf32to8 @@ -625,7 +625,7 @@ u32string utf32result = utf8to32(twochars); assert (utf32result.size() == 2); ``` -In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown. +In case of an invalid UTF-8 sequence, a `utf8::invalid_utf8` exception is thrown. #### utf8::utf8to32 @@ -648,7 +648,7 @@ u32string utf32result = utf8to32(twochars); assert (utf32result.size() == 2); ``` -In case of an invalid UTF-8 seqence, a `utf8::invalid_utf8` exception is thrown. +In case of an invalid UTF-8 sequence, a `utf8::invalid_utf8` exception is thrown. #### utf8::utf8to32 @@ -678,7 +678,7 @@ 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. +In case of an invalid UTF-8 sequence, a `utf8::invalid_utf8` exception is thrown. If `end` does not point to the past-of-end of a UTF-8 sequence, a `utf8::not_enough_room` exception is thrown. #### utf8::find_invalid @@ -824,7 +824,7 @@ 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. +`is_valid` is a shorthand for `find_invalid(start, end) == end;`. You may want to use it to make sure that a byte sequence is a valid UTF-8 string without the need to know where it fails if it is not valid. #### utf8::replace_invalid @@ -1094,9 +1094,9 @@ class 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 underlying iterators are equal. -`bool operator != (const iterator& rhs) const;` returns `true` if the two underlaying iterators are not equal. +`bool operator != (const iterator& rhs) const;` returns `true` if the two underlying iterators are not equal. `iterator& operator ++ ();` the prefix increment - moves the iterator to the next UTF-8 encoded code point. @@ -1219,7 +1219,7 @@ This is a faster but less safe version of `utf8::peek_next`. It does not check f 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. +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 @@ -1270,7 +1270,7 @@ This is a faster but less safe version of `utf8::advance`. It does not check for 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. +Given the iterators to two UTF-8 encoded code points in a sequence, returns the number of code points between them. ```cpp template @@ -1460,9 +1460,9 @@ class 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 underlying iterators are equal. -`bool operator != (const iterator& rhs) const;` returns `true` if the two underlaying iterators are not equal. +`bool operator != (const iterator& rhs) const;` returns `true` if the two underlying iterators are not equal. `iterator& operator ++ ();` the prefix increment - moves the iterator to the next UTF-8 encoded code point. From dbb2423248dd5b97acd4125a29bdfbf6b36cd7b1 Mon Sep 17 00:00:00 2001 From: Felix Wang <77263945+topazus@users.noreply.github.com> Date: Tue, 25 Apr 2023 20:05:14 +0800 Subject: [PATCH 03/10] Use ARCH_INDEPENDENT option that is introduced in CMake 3.14 --- CMakeLists.txt | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/CMakeLists.txt b/CMakeLists.txt index c8d4b7a..925165e 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -27,10 +27,15 @@ if(UTF8_INSTALL) set(DEF_INSTALL_CMAKE_DIR ${CMAKE_INSTALL_LIBDIR}/cmake/utf8cpp) endif() + if(${CMAKE_VERSION} VERSION_GREATER "3.14") + set(OPTIONAL_ARCH_INDEPENDENT "ARCH_INDEPENDENT") + endif() + write_basic_package_version_file( ${CMAKE_CURRENT_BINARY_DIR}/utf8cppConfigVersion.cmake VERSION ${PROJECT_VERSION} COMPATIBILITY SameMajorVersion + ${OPTIONAL_ARCH_INDEPENDENT} ) configure_package_config_file( From df857efc5bbc2aa84012d865f7d7e9cccdc08562 Mon Sep 17 00:00:00 2001 From: nemtrif Date: Sun, 6 Aug 2023 07:36:58 -0400 Subject: [PATCH 04/10] Set cmake_minimum_required VERSION to 3.0.2...3.27 Address issue https://github.com/nemtrif/utfcpp/issues/103 --- CMakeLists.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CMakeLists.txt b/CMakeLists.txt index 925165e..af38054 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -1,4 +1,4 @@ -cmake_minimum_required (VERSION 3.0.2) +cmake_minimum_required (VERSION 3.0.2...3.27) project (utf8cpp VERSION 3.2.2 LANGUAGES CXX) if(CMAKE_SOURCE_DIR STREQUAL CMAKE_CURRENT_SOURCE_DIR) From f23474118c5c544c1403883976d78128d17125f9 Mon Sep 17 00:00:00 2001 From: nemtrif Date: Sat, 12 Aug 2023 11:18:39 -0400 Subject: [PATCH 05/10] Version 3.2.4 --- CMakeLists.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CMakeLists.txt b/CMakeLists.txt index af38054..09ecda1 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -1,5 +1,5 @@ cmake_minimum_required (VERSION 3.0.2...3.27) -project (utf8cpp VERSION 3.2.2 LANGUAGES CXX) +project (utf8cpp VERSION 3.2.4 LANGUAGES CXX) if(CMAKE_SOURCE_DIR STREQUAL CMAKE_CURRENT_SOURCE_DIR) set(IS_ROOT_PROJECT ON) From 18026b8ebc2971aaec6ffc0a6d75cf171d2811b1 Mon Sep 17 00:00:00 2001 From: Kai Pastor Date: Thu, 21 Sep 2023 07:20:33 +0200 Subject: [PATCH 06/10] Guard add_library --- utf8cppConfig.cmake.in | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/utf8cppConfig.cmake.in b/utf8cppConfig.cmake.in index 450fe8d..fd3480b 100644 --- a/utf8cppConfig.cmake.in +++ b/utf8cppConfig.cmake.in @@ -3,4 +3,6 @@ include("${CMAKE_CURRENT_LIST_DIR}/utf8cppTargets.cmake") check_required_components( "utf8cpp" ) -add_library(utf8::cpp ALIAS utf8cpp) +if(NOT TARGET utf8::cpp) + add_library(utf8::cpp ALIAS utf8cpp) +endif() From c87f2d39513cb333f39fe7ad828eb8ee4221c42f Mon Sep 17 00:00:00 2001 From: nemtrif Date: Sun, 24 Sep 2023 16:35:27 -0400 Subject: [PATCH 07/10] Re-write the "Alternatives" section of the documentation to point to a third-party article. --- README.md | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 02d9f75..245b6d7 100644 --- a/README.md +++ b/README.md @@ -155,13 +155,17 @@ The library was designed to be: #### 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: +Here is an article I was mada aware of only recently: [The Wonderfully Terrible World of C and C++ Encoding APIs (with Some Rust)](https://thephd.dev/the-c-c++-rust-string-text-encoding-api-landscape), by JeanHeyd Meneide. In the article, this library is compared with: -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 definitely 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. +- [simdutf](https://github.com/simdutf/simdutf) +- [iconv](https://www.gnu.org/software/libiconv/) +- [boost.text](https://github.com/tzlaine/text) +- [ICU](https://unicode-org.github.io/icu/userguide/conversion/converters.html) +- [encoding_rs](https://github.com/hsivonen/encoding_rs) +- [Windows API functions for converting text between encodings](https://learn.microsoft.com/en-us/windows/win32/api/stringapiset/) +- [ztd.text](https://github.com/soasis/text/) +The article presents author's view of the quality of the API design, but also some speed benchmarks. ## Reference From 0c8da664ee30336f7fd13e0aa6a840635380898c Mon Sep 17 00:00:00 2001 From: nemtrif Date: Sun, 24 Sep 2023 16:38:24 -0400 Subject: [PATCH 08/10] Typo in documentation. --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 245b6d7..4f96f65 100644 --- a/README.md +++ b/README.md @@ -155,7 +155,7 @@ The library was designed to be: #### Alternatives -Here is an article I was mada aware of only recently: [The Wonderfully Terrible World of C and C++ Encoding APIs (with Some Rust)](https://thephd.dev/the-c-c++-rust-string-text-encoding-api-landscape), by JeanHeyd Meneide. In the article, this library is compared with: +Here is an article I was made aware of only recently: [The Wonderfully Terrible World of C and C++ Encoding APIs (with Some Rust)](https://thephd.dev/the-c-c++-rust-string-text-encoding-api-landscape), by JeanHeyd Meneide. In the article, this library is compared with: - [simdutf](https://github.com/simdutf/simdutf) - [iconv](https://www.gnu.org/software/libiconv/) From 0ee84daac8bd6c35cbc3b8a144e6a40e0b2fe588 Mon Sep 17 00:00:00 2001 From: nemtrif Date: Sun, 24 Sep 2023 17:17:18 -0400 Subject: [PATCH 09/10] Fix for issue #78: unchecked::utf16to8 reads out of bounds if provided only leading surrogate --- source/utf8/unchecked.h | 4 +++- tests/test_unchecked_api.h | 5 +++++ 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/source/utf8/unchecked.h b/source/utf8/unchecked.h index 8fe83c9..7981839 100644 --- a/source/utf8/unchecked.h +++ b/source/utf8/unchecked.h @@ -155,7 +155,9 @@ namespace utf8 { while (start != end) { uint32_t cp = utf8::internal::mask16(*start++); - // Take care of surrogate pairs first + if (start == end) + return result; + // 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; diff --git a/tests/test_unchecked_api.h b/tests/test_unchecked_api.h index 10c5991..66d0400 100644 --- a/tests/test_unchecked_api.h +++ b/tests/test_unchecked_api.h @@ -137,6 +137,11 @@ TEST(UnCheckedAPITests, test_utf16to8) string utf8result; utf8::unchecked::utf16to8(utf16string, utf16string + 5, back_inserter(utf8result)); EXPECT_EQ (utf8result.size(), 10); + + utf8result.clear(); + unsigned short highsurrogateonly[] = {0xd800}; + utf8::unchecked::utf16to8(highsurrogateonly, highsurrogateonly + 1, back_inserter(utf8result)); + EXPECT_TRUE(true); // we didn't crash } TEST(UnCheckedAPITests, test_utf8to16) From 6f0e7c7865208f2a6b882a7e138584beb1b6b2fd Mon Sep 17 00:00:00 2001 From: nemtrif Date: Sun, 24 Sep 2023 17:20:06 -0400 Subject: [PATCH 10/10] Version 3.2.5 --- CMakeLists.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CMakeLists.txt b/CMakeLists.txt index 09ecda1..7c13109 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -1,5 +1,5 @@ cmake_minimum_required (VERSION 3.0.2...3.27) -project (utf8cpp VERSION 3.2.4 LANGUAGES CXX) +project (utf8cpp VERSION 3.2.5 LANGUAGES CXX) if(CMAKE_SOURCE_DIR STREQUAL CMAKE_CURRENT_SOURCE_DIR) set(IS_ROOT_PROJECT ON)