Add mbstring to KPHP (Package I & II & III -- 26 new functions)

.github/workflows/Dockerfile.buster.install

@@ -0,0 +1,16 @@
+FROM debian:buster
+ARG DEBIAN_FRONTEND=noninteractive
+
+RUN apt-get update && \
+	apt-get install -y --no-install-recommends apt-utils ca-certificates gnupg wget lsb-release && \
+    echo "deb https://deb.debian.org/debian buster-backports main" >> /etc/apt/sources.list && \ 
+    wget -qO /etc/apt/trusted.gpg.d/vkpartner.asc https://artifactory-external.vkpartner.ru/artifactory/api/gpg/key/public && \
+    echo "deb https://artifactory-external.vkpartner.ru/artifactory/kphp buster main" >> /etc/apt/sources.list && \
+    wget -qO - https://packages.sury.org/php/apt.gpg | apt-key add - && \
+    echo "deb https://packages.sury.org/php/ buster main" >> /etc/apt/sources.list.d/php.list
+
+RUN apt-get update && apt-get install -y git cmake make g++ lld gperf netcat php7.4-vkext kphp vk-tl-tools && \
+	mkdir -p /var/www/vkontakte/data/www/vkontakte.com/tl/ && \
+	tl-compiler -e /var/www/vkontakte/data/www/vkontakte.com/tl/scheme.tlo /usr/share/vkontakte/examples/tl-files/common.tl /usr/share/vkontakte/examples/tl-files/tl.tl
+
+RUN useradd -ms /bin/bash kitten

.github/workflows/Dockerfile.focal.install

@@ -0,0 +1,13 @@
+FROM ubuntu:20.04
+ARG DEBIAN_FRONTEND=noninteractive
+
+RUN apt-get update && \
+	apt-get install -y --no-install-recommends apt-utils ca-certificates gnupg wget software-properties-common pkg-config && \
+	wget -qO /etc/apt/trusted.gpg.d/vkpartner.asc https://artifactory-external.vkpartner.ru/artifactory/api/gpg/key/public && \
+	echo "deb https://artifactory-external.vkpartner.ru/artifactory/kphp focal main" >> /etc/apt/sources.list
+
+RUN apt-get update && apt-get install -y git cmake make g++ lld gperf netcat php7.4-vkext kphp vk-tl-tools && \
+	mkdir -p /var/www/vkontakte/data/www/vkontakte.com/tl/ && \
+	tl-compiler -e /var/www/vkontakte/data/www/vkontakte.com/tl/scheme.tlo /usr/share/vkontakte/examples/tl-files/common.tl /usr/share/vkontakte/examples/tl-files/tl.tl
+
+RUN useradd -ms /bin/bash kitten

.github/workflows/Dockerfile.jammy.install

@@ -0,0 +1,17 @@
+FROM ubuntu:22.04
+ARG DEBIAN_FRONTEND=noninteractive
+
+RUN apt update && \
+	apt install -y --no-install-recommends apt-utils ca-certificates gnupg wget software-properties-common pkg-config && \
+	wget -qO /etc/apt/trusted.gpg.d/vkpartner.asc https://artifactory-external.vkpartner.ru/artifactory/api/gpg/key/public && \
+	echo "deb [arch=amd64] https://artifactory-external.vkpartner.ru/artifactory/kphp jammy main" | tee /etc/apt/sources.list.d/vkpartner.list
+
+RUN apt install -y software-properties-common && apt update && \
+	add-apt-repository ppa:ondrej/php -y && \
+	apt update
+
+RUN apt install -y git cmake make g++ lld gperf netcat php7.4-vkext kphp vk-tl-tools && \
+	mkdir -p /var/www/vkontakte/data/www/vkontakte.com/tl/ && \
+	tl-compiler -e /var/www/vkontakte/data/www/vkontakte.com/tl/scheme.tlo /usr/share/vkontakte/examples/tl-files/common.tl /usr/share/vkontakte/examples/tl-files/tl.tl
+
+RUN useradd -ms /bin/bash kitten

.github/workflows/linux-install.yml

@@ -0,0 +1,31 @@
+name: linux-install
+
+on:
+  workflow_dispatch:
+
+env:
+  kphp_root_dir: /home/kitten/kphp
+  kphp_polyfills_dir: /home/kitten/kphp/kphp-polyfills
+  kphp_build_dir: /home/kitten/kphp/build
+
+jobs:
+  install-linux:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        include:
+          - os: buster
+          - os: focal
+          # - os: jammy # TODO: enable after release to artifactory servers
+
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Build and start Docker container
+      run: |
+        docker build -f $GITHUB_WORKSPACE/.github/workflows/Dockerfile.${{matrix.os}}.install $GITHUB_WORKSPACE -t kphp-build-img-${{matrix.os}}-install
+        docker run -dt --name kphp-build-container-${{matrix.os}}-install kphp-build-img-${{matrix.os}}-install
+
+    - name: Run php dummy script
+      run: docker exec -u kitten kphp-build-container-${{matrix.os}}-install bash -c 
+        "cd ${{env.demo_dir}} && echo 'hello world' > demo.php && kphp --mode=cli --cxx=g++ demo.php && ./kphp_out/cli -o --user kitten"

builtin-functions/_functions.txt

@@ -762,14 +762,6 @@ function setlocale ($category ::: int, $locale ::: string) ::: string | false;
 
 function iconv ($input_encoding ::: string, $output_encoding ::: string, $input_str ::: string) ::: string | false;
 
-function mb_check_encoding ($str ::: string, $encoding ::: string = "cp1251") ::: bool;
-function mb_strlen ($str ::: string, $encoding ::: string = "cp1251") ::: int;
-function mb_strpos ($haystack ::: string, $needle ::: string, $offset ::: int = 0, $encoding ::: string = "cp1251") ::: int | false;
-function mb_stripos ($haystack ::: string, $needle ::: string, $offset ::: int = 0, $encoding ::: string = "cp1251") ::: int | false;
-function mb_strtolower ($str ::: string, $encoding ::: string = "cp1251") ::: string;
-function mb_strtoupper ($str ::: string, $encoding ::: string = "cp1251") ::: string;
-function mb_substr ($str ::: string, $start ::: int, $length ::: mixed = PHP_INT_MAX, $encoding ::: string = "cp1251") ::: string;
-
 define('PHP_ROUND_HALF_UP', 123423141);
 define('PHP_ROUND_HALF_DOWN', 123423144);
 define('PHP_ROUND_HALF_EVEN', 123423145);
@@ -1654,3 +1646,31 @@ class DateTimeImmutable implements DateTimeInterface {
 }
 
 function getenv(string $varname = '', bool $local_only = false): mixed;
+
+function mb_check_encoding(array|string $value, ?string $encoding = null): bool;
+function mb_convert_encoding(array|string $string, string $to_encoding, array|string|null $from_encoding = null): array|string|false;
+function mb_encoding_aliases(string $encoding): array;
+function mb_list_encodings(): array;
+function mb_preferred_mime_name(string $encoding): string|false;
+function mb_str_split(string $string, int $length = 1, ?string $encoding = null): array;
+function mb_strcut(string $string, int $start, ?int $length = null, ?string $encoding = null): string;
+function mb_substr(string $string, int $start, ?int $length = null, ?string $encoding = null): string;
+function mb_substitute_character(string|int|null $substitute_character = null): string|int|false;
+function mb_strlen(string $string, ?string $encoding = null): int;
+function mb_substr_count(string $haystack, string $needle, ?string $encoding = null): int;
+function mb_strtolower(string $string, ?string $encoding = null): string;
+function mb_strtoupper(string $string, ?string $encoding = null): string;
+function mb_strwidth(string $string, ?string $encoding = null): int;
+function mb_strpos(string $haystack, string $needle, int $offset = 0, ?string $encoding = null): int|false;
+function mb_stripos(string $haystack, string $needle, int $offset = 0, ?string $encoding = null): int|false;
+function mb_strripos(string $haystack, string $needle, int $offset = 0, ?string $encoding = null): int|false;
+function mb_strrpos(string $haystack, string $needle, int $offset = 0, string $encoding = null): int|false;
+function mb_stristr(string $haystack, string $needle, bool $before_needle = false, ?string $encoding = null): string|false;
+function mb_strrchr(string $haystack, string $needle, bool $before_needle = false, ?string $encoding = null): string|false;
+function mb_strrichr(string $haystack, string $needle, bool $before_needle = false, ?string $encoding = null): string|false;
+function mb_strstr(string $haystack, string $needle, bool $before_needle = false, ?string $encoding = null): string|false;
+function mb_strimwidth(string $string, int $start, int $width, string $trim_marker = "", ?string $encoding = null): string;
+function mb_scrub(string $string, ?string $encoding = null): string;
+function mb_regex_encoding(?string $encoding = null): string|false;
+function mb_regex_set_options(?string $options = null): string;
+function mb_ereg_match(string $pattern, string $string, ?string $options = null): bool;

cmake/external-libraries.cmake

@@ -1,5 +1,7 @@
 option(DOWNLOAD_MISSING_LIBRARIES "download and build missing libraries if needed" OFF)
+option(MBFL "download and build libmbfl" OFF)
 cmake_print_variables(DOWNLOAD_MISSING_LIBRARIES)
+cmake_print_variables(MBFL)
 function(handle_missing_library LIB_NAME)
     message(STATUS "------${LIB_NAME}---------")
     if(DOWNLOAD_MISSING_LIBRARIES)
@@ -9,6 +11,30 @@ function(handle_missing_library LIB_NAME)
     endif()
 endfunction()
 
+if(MBFL)
+    message(STATUS "MBFL=On, libmbfl will be downloaded and built")
+    add_compile_options(-DMBFL)
+    FetchContent_Declare(libmbfl GIT_REPOSITORY https://github.com/andreylzmw/libmbfl)
+    FetchContent_MakeAvailable(libmbfl)
+    include_directories(${libmbfl_SOURCE_DIR}/include)
+    add_definitions(-DLIBMBFL_LIB_DIR="${libmbfl_SOURCE_DIR}/objs")
+    add_link_options(-L${libmbfl_SOURCE_DIR}/objs)
+
+    find_package(onig QUIET)
+    if(NOT onig_FOUND)
+        handle_missing_library("onig")
+        FetchContent_Declare(
+                onig
+                GIT_REPOSITORY https://github.com/kkos/oniguruma/
+                GIT_TAG        v6.9.9
+        )
+        FetchContent_MakeAvailable(onig)
+        include_directories(${onig_SOURCE_DIR}/src)
+        add_definitions(-DONIG_LIB_DIR="${onig_BINARY_DIR}")
+        message(STATUS "---------------------")
+    endif()
+endif()
+
 find_package(fmt QUIET)
 if(NOT fmt_FOUND)
     handle_missing_library("fmtlib")

cmake/init-compilation-flags.cmake

@@ -50,6 +50,41 @@ if(UNDEFINED_SANITIZER)
 endif()
 cmake_print_variables(ADDRESS_SANITIZER UNDEFINED_SANITIZER)
 
+option(PDO_LIBS_STATIC_LINKING "Enable static linking with database libs for PDO")
+if(PDO_LIBS_STATIC_LINKING)
+    add_definitions(-DPDO_LIBS_STATIC_LINKING)
+endif()
+cmake_print_variables(PDO_LIBS_STATIC_LINKING)
+
+option(PDO_DRIVER_MYSQL "Enable MySQL PDO driver")
+if(PDO_DRIVER_MYSQL)
+    add_definitions(-DPDO_DRIVER_MYSQL)
+endif()
+cmake_print_variables(PDO_DRIVER_MYSQL)
+
+option(PDO_DRIVER_PGSQL "Enable pgSQL PDO driver")
+if (PDO_DRIVER_PGSQL)
+    if (APPLE)
+        set(PostgreSQL_ROOT "/usr/local/opt/libpq" CACHE INTERNAL "")
+    else()
+        set(PostgreSQL_ADDITIONAL_VERSIONS "14")
+    endif()
+    find_package(PostgreSQL REQUIRED)
+    include_directories(${PostgreSQL_INCLUDE_DIR})
+    string(FIND ${PostgreSQL_VERSION_STRING} "." PostgreSQL_VERSION_POS)
+    string(SUBSTRING ${PostgreSQL_VERSION_STRING} 0 ${PostgreSQL_VERSION_POS} PostgreSQL_VERSION)
+    add_definitions(-DPDO_DRIVER_PGSQL)
+    add_compile_definitions(PDO_DRIVER_PGSQL_VERSION=${PostgreSQL_VERSION})
+endif()
+
+cmake_print_variables(PDO_DRIVER_PGSQL)
+
+option(KPHP_TESTS "Build the tests" ON)
+cmake_print_variables(KPHP_TESTS)
+
+option(KPHP_CUSTOM_CMAKE "Use CMakeLists.txt of custom php project" OFF)
+cmake_print_variables(KPHP_CUSTOM_CMAKE)
+
 if(NOT CMAKE_BUILD_TYPE AND NOT CMAKE_CONFIGURATION_TYPES)
     message(STATUS "Setting build type to `${DEFAULT_BUILD_TYPE}` as none was specified.")
     set(CMAKE_BUILD_TYPE ${DEFAULT_BUILD_TYPE} CACHE STRING "Build type (default ${DEFAULT_BUILD_TYPE})" FORCE)

compiler/compiler-settings.cpp

@@ -284,6 +284,9 @@ void CompilerSettings::init() {
 
   remove_extra_spaces(extra_cxx_flags.value_);
   std::stringstream ss;
+  #ifdef MBFL
+  ss << " -DMBFL ";
+  #endif
   ss << "-Wall "
      << extra_cxx_flags.get()
      << " -iquote" << kphp_src_path.get()
@@ -334,6 +337,15 @@ void CompilerSettings::init() {
   ld_flags.value_ += " -L /usr/local/lib";
 #endif
 
+#ifdef LIBMBFL_LIB_DIR
+  external_static_libs.emplace_back("libmbfl");
+  ld_flags.value_ += " -L" LIBMBFL_LIB_DIR;
+#endif
+
+#ifdef ONIG_LIB_DIR
+  ld_flags.value_ += " -L " ONIG_LIB_DIR " -lonig";
+#endif
+
 #ifdef KPHP_H3_LIB_DIR
   ld_flags.value_ += " -L" KPHP_H3_LIB_DIR;
 #else