add files modified with hook

* Make `IfOperator` return the `else_expression_` in case of `NULL`

* Add gql_behave tests

* Add gql_behave test to specifically check for the case when the test expression itself is null

.clang-tidy

@@ -61,7 +61,9 @@ Checks: '*,
          -readability-magic-numbers,
          -readability-named-parameter,
          -misc-no-recursion,
-         -concurrency-mt-unsafe'
+         -concurrency-mt-unsafe,
+         -bugprone-easily-swappable-parameters'
+
 WarningsAsErrors: ''
 HeaderFilterRegex: 'src/.*'
 AnalyzeTemporaryDtors: false

.github/workflows/diff.yaml

@@ -1,4 +1,7 @@
 name: Diff
+concurrency:
+  group: ${{ github.head_ref || github.sha }}
+  cancel-in-progress: true
 
 on:
   push:
@@ -112,7 +115,7 @@ jobs:
           source /opt/toolchain-v4/activate
 
           # Restrict clang-tidy results only to the modified parts
-          git diff -U0 master... -- src ':!*.hpp' | ./tools/github/clang-tidy/clang-tidy-diff.py -p 1 -j $THREADS -path build | tee ./build/clang_tidy_output.txt
+          git diff -U0 master... -- src | ./tools/github/clang-tidy/clang-tidy-diff.py -p 1 -j $THREADS -path build | tee ./build/clang_tidy_output.txt
 
           # Fail if any warning is reported
           ! cat ./build/clang_tidy_output.txt | ./tools/github/clang-tidy/grep_error_lines.sh > /dev/null

.github/workflows/package_all.yaml

@@ -6,11 +6,11 @@ on: workflow_dispatch
 
 jobs:
   centos-7:
-    runs-on: [self-hosted, DockerMgBuild]
+    runs-on: [self-hosted, DockerMgBuild, X64]
     timeout-minutes: 60
     steps:
       - name: "Set up repository"
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           fetch-depth: 0 # Required because of release/get_version.py
       - name: "Build package"
@@ -22,29 +22,29 @@ jobs:
           name: centos-7
           path: build/output/centos-7/memgraph*.rpm
 
-  centos-8:
-    runs-on: [self-hosted, DockerMgBuild]
+  centos-9:
+    runs-on: [self-hosted, DockerMgBuild, X64]
     timeout-minutes: 60
     steps:
       - name: "Set up repository"
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           fetch-depth: 0 # Required because of release/get_version.py
       - name: "Build package"
         run: |
-          ./release/package/run.sh package centos-8
+          ./release/package/run.sh package centos-9
       - name: "Upload package"
         uses: actions/upload-artifact@v2
         with:
-          name: centos-8
-          path: build/output/centos-8/memgraph*.rpm
+          name: centos-9
+          path: build/output/centos-9/memgraph*.rpm
 
   debian-10:
-    runs-on: [self-hosted, DockerMgBuild]
+    runs-on: [self-hosted, DockerMgBuild, X64]
     timeout-minutes: 60
     steps:
       - name: "Set up repository"
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           fetch-depth: 0 # Required because of release/get_version.py
       - name: "Build package"
@@ -57,11 +57,11 @@ jobs:
           path: build/output/debian-10/memgraph*.deb
 
   debian-11:
-    runs-on: [self-hosted, DockerMgBuild]
+    runs-on: [self-hosted, DockerMgBuild, X64]
     timeout-minutes: 60
     steps:
       - name: "Set up repository"
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           fetch-depth: 0 # Required because of release/get_version.py
       - name: "Build package"
@@ -74,11 +74,11 @@ jobs:
           path: build/output/debian-11/memgraph*.deb
 
   docker:
-    runs-on: [self-hosted, DockerMgBuild]
+    runs-on: [self-hosted, DockerMgBuild, X64]
     timeout-minutes: 60
     steps:
       - name: "Set up repository"
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           fetch-depth: 0 # Required because of release/get_version.py
       - name: "Build package"
@@ -93,11 +93,11 @@ jobs:
           path: build/output/docker/memgraph*.tar.gz
 
   ubuntu-1804:
-    runs-on: [self-hosted, DockerMgBuild]
+    runs-on: [self-hosted, DockerMgBuild, X64]
     timeout-minutes: 60
     steps:
       - name: "Set up repository"
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           fetch-depth: 0 # Required because of release/get_version.py
       - name: "Build package"
@@ -110,11 +110,11 @@ jobs:
           path: build/output/ubuntu-18.04/memgraph*.deb
 
   ubuntu-2004:
-    runs-on: [self-hosted, DockerMgBuild]
+    runs-on: [self-hosted, DockerMgBuild, X64]
     timeout-minutes: 60
     steps:
       - name: "Set up repository"
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           fetch-depth: 0 # Required because of release/get_version.py
       - name: "Build package"
@@ -126,12 +126,29 @@ jobs:
           name: ubuntu-2004
           path: build/output/ubuntu-20.04/memgraph*.deb
 
-  debian-11-platform:
-    runs-on: [self-hosted, DockerMgBuild]
+  ubuntu-2204:
+    runs-on: [self-hosted, DockerMgBuild, X64]
     timeout-minutes: 60
     steps:
       - name: "Set up repository"
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package ubuntu-22.04
+      - name: "Upload package"
+        uses: actions/upload-artifact@v2
+        with:
+          name: ubuntu-2204
+          path: build/output/ubuntu-22.04/memgraph*.deb
+
+  debian-11-platform:
+    runs-on: [self-hosted, DockerMgBuild, X64]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v3
         with:
           fetch-depth: 0 # Required because of release/get_version.py
       - name: "Build package"
@@ -142,3 +159,20 @@ jobs:
         with:
           name: debian-11-platform
           path: build/output/debian-11/memgraph*.deb
+
+  debian-11-arm:
+    runs-on: [self-hosted, DockerMgBuild, ARM64, strange]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package debian-11-arm
+      - name: "Upload package"
+        uses: actions/upload-artifact@v2
+        with:
+          name: debian-11-arm
+          path: build/output/debian-11-arm/memgraph*.deb

.github/workflows/release_docker.yaml

@@ -4,8 +4,12 @@ on:
   workflow_dispatch:
     inputs:
       version:
-        description: "Memgraph binary version to publish on Dockerhub."
+        description: "Memgraph binary version to publish on DockerHub."
         required: true
+      force_release:
+        type: boolean
+        required: false
+        default: false
 
 jobs:
   docker_publish:
@@ -36,6 +40,22 @@ jobs:
           curl -L https://download.memgraph.com/memgraph/v${{ github.event.inputs.version }}/debian-11/memgraph_${{ github.event.inputs.version }}-1_amd64.deb > memgraph-amd64.deb
           curl -L https://download.memgraph.com/memgraph/v${{ github.event.inputs.version }}/debian-11-aarch64/memgraph_${{ github.event.inputs.version }}-1_arm64.deb > memgraph-arm64.deb
 
+      - name: Check if specified version is already pushed
+        run: |
+          EXISTS=$(docker manifest inspect $DOCKER_ORGANIZATION_NAME/$DOCKER_REPOSITORY_NAME:${{ github.event.inputs.version }} > /dev/null; echo $?)
+          echo $EXISTS
+          if [[ ${EXISTS} -eq 0 ]]; then
+              echo 'The specified version has been already released to DockerHub.'
+              if [[ ${{ github.event.inputs.force_release }} = true ]]; then
+                echo 'Forcing the release!'
+              else
+                echo 'Stopping the release!'
+                exit 1
+              fi
+          else
+              echo 'All good the specified version has not been release to DockerHub.'
+          fi
+
       - name: Build & push docker images
         run: |
           cd release/docker

CODEOWNERS

@@ -1 +0,0 @@
-* @antaljanosbenjamin @kostasrim

cmake/FindSodium.cmake

@@ -1,297 +0,0 @@
-# Written in 2016 by Henrik Steffen Gaßmann <henrik@gassmann.onl>
-#
-# To the extent possible under law, the author(s) have dedicated all
-# copyright and related and neighboring rights to this software to the
-# public domain worldwide. This software is distributed without any warranty.
-#
-# You should have received a copy of the CC0 Public Domain Dedication
-# along with this software. If not, see
-#
-#     http://creativecommons.org/publicdomain/zero/1.0/
-#
-########################################################################
-# Tries to find the local libsodium installation.
-#
-# On Windows the sodium_DIR environment variable is used as a default
-# hint which can be overridden by setting the corresponding cmake variable.
-#
-# Once done the following variables will be defined:
-#
-#   sodium_FOUND
-#   sodium_INCLUDE_DIR
-#   sodium_LIBRARY_DEBUG
-#   sodium_LIBRARY_RELEASE
-#
-#
-# Furthermore an imported "sodium" target is created.
-#
-
-if (CMAKE_C_COMPILER_ID STREQUAL "GNU"
-    OR CMAKE_C_COMPILER_ID STREQUAL "Clang")
-    set(_GCC_COMPATIBLE 1)
-endif()
-
-# static library option
-if (NOT DEFINED sodium_USE_STATIC_LIBS)
-    option(sodium_USE_STATIC_LIBS "enable to statically link against sodium" OFF)
-endif()
-if(NOT (sodium_USE_STATIC_LIBS EQUAL sodium_USE_STATIC_LIBS_LAST))
-    unset(sodium_LIBRARY CACHE)
-    unset(sodium_LIBRARY_DEBUG CACHE)
-    unset(sodium_LIBRARY_RELEASE CACHE)
-    unset(sodium_DLL_DEBUG CACHE)
-    unset(sodium_DLL_RELEASE CACHE)
-    set(sodium_USE_STATIC_LIBS_LAST ${sodium_USE_STATIC_LIBS} CACHE INTERNAL "internal change tracking variable")
-endif()
-
-
-########################################################################
-# UNIX
-if (UNIX)
-    # import pkg-config
-    find_package(PkgConfig QUIET)
-    if (PKG_CONFIG_FOUND)
-        pkg_check_modules(sodium_PKG QUIET libsodium)
-    endif()
-
-    if(sodium_USE_STATIC_LIBS)
-        foreach(_libname ${sodium_PKG_STATIC_LIBRARIES})
-            if (NOT _libname MATCHES "^lib.*\\.a$") # ignore strings already ending with .a
-                list(INSERT sodium_PKG_STATIC_LIBRARIES 0 "lib${_libname}.a")
-            endif()
-        endforeach()
-        list(REMOVE_DUPLICATES sodium_PKG_STATIC_LIBRARIES)
-
-        # if pkgconfig for libsodium doesn't provide
-        # static lib info, then override PKG_STATIC here..
-        if (NOT sodium_PKG_STATIC_FOUND)
-            set(sodium_PKG_STATIC_LIBRARIES libsodium.a)
-        endif()
-
-        set(XPREFIX sodium_PKG_STATIC)
-    else()
-        if (NOT sodium_PKG_FOUND)
-            set(sodium_PKG_LIBRARIES sodium)
-        endif()
-
-        set(XPREFIX sodium_PKG)
-    endif()
-
-    find_path(sodium_INCLUDE_DIR sodium.h
-        HINTS ${${XPREFIX}_INCLUDE_DIRS}
-    )
-    find_library(sodium_LIBRARY_DEBUG NAMES ${${XPREFIX}_LIBRARIES}
-        HINTS ${${XPREFIX}_LIBRARY_DIRS}
-    )
-    find_library(sodium_LIBRARY_RELEASE NAMES ${${XPREFIX}_LIBRARIES}
-        HINTS ${${XPREFIX}_LIBRARY_DIRS}
-    )
-
-
-########################################################################
-# Windows
-elseif (WIN32)
-    set(sodium_DIR "$ENV{sodium_DIR}" CACHE FILEPATH "sodium install directory")
-    mark_as_advanced(sodium_DIR)
-
-    find_path(sodium_INCLUDE_DIR sodium.h
-        HINTS ${sodium_DIR}
-        PATH_SUFFIXES include
-    )
-
-    if (MSVC)
-        # detect target architecture
-        file(WRITE "${CMAKE_CURRENT_BINARY_DIR}/arch.cpp" [=[
-            #if defined _M_IX86
-            #error ARCH_VALUE x86_32
-            #elif defined _M_X64
-            #error ARCH_VALUE x86_64
-            #endif
-            #error ARCH_VALUE unknown
-        ]=])
-        try_compile(_UNUSED_VAR "${CMAKE_CURRENT_BINARY_DIR}" "${CMAKE_CURRENT_BINARY_DIR}/arch.cpp"
-            OUTPUT_VARIABLE _COMPILATION_LOG
-        )
-        string(REGEX REPLACE ".*ARCH_VALUE ([a-zA-Z0-9_]+).*" "\\1" _TARGET_ARCH "${_COMPILATION_LOG}")
-
-        # construct library path
-        if (_TARGET_ARCH STREQUAL "x86_32")
-            string(APPEND _PLATFORM_PATH "Win32")
-        elseif(_TARGET_ARCH STREQUAL "x86_64")
-            string(APPEND _PLATFORM_PATH "x64")
-        else()
-            message(FATAL_ERROR "the ${_TARGET_ARCH} architecture is not supported by Findsodium.cmake.")
-        endif()
-        string(APPEND _PLATFORM_PATH "/$$CONFIG$$")
-
-        if (MSVC_VERSION LESS 1900)
-            math(EXPR _VS_VERSION "${MSVC_VERSION} / 10 - 60")
-        else()
-            math(EXPR _VS_VERSION "${MSVC_VERSION} / 10 - 50")
-        endif()
-        string(APPEND _PLATFORM_PATH "/v${_VS_VERSION}")
-
-        if (sodium_USE_STATIC_LIBS)
-            string(APPEND _PLATFORM_PATH "/static")
-        else()
-            string(APPEND _PLATFORM_PATH "/dynamic")
-        endif()
-
-        string(REPLACE "$$CONFIG$$" "Debug" _DEBUG_PATH_SUFFIX "${_PLATFORM_PATH}")
-        string(REPLACE "$$CONFIG$$" "Release" _RELEASE_PATH_SUFFIX "${_PLATFORM_PATH}")
-
-        find_library(sodium_LIBRARY_DEBUG libsodium.lib
-            HINTS ${sodium_DIR}
-            PATH_SUFFIXES ${_DEBUG_PATH_SUFFIX}
-        )
-        find_library(sodium_LIBRARY_RELEASE libsodium.lib
-            HINTS ${sodium_DIR}
-            PATH_SUFFIXES ${_RELEASE_PATH_SUFFIX}
-        )
-        if (NOT sodium_USE_STATIC_LIBS)
-            set(CMAKE_FIND_LIBRARY_SUFFIXES_BCK ${CMAKE_FIND_LIBRARY_SUFFIXES})
-            set(CMAKE_FIND_LIBRARY_SUFFIXES ".dll")
-            find_library(sodium_DLL_DEBUG libsodium
-                HINTS ${sodium_DIR}
-                PATH_SUFFIXES ${_DEBUG_PATH_SUFFIX}
-            )
-            find_library(sodium_DLL_RELEASE libsodium
-                HINTS ${sodium_DIR}
-                PATH_SUFFIXES ${_RELEASE_PATH_SUFFIX}
-            )
-            set(CMAKE_FIND_LIBRARY_SUFFIXES ${CMAKE_FIND_LIBRARY_SUFFIXES_BCK})
-        endif()
-
-    elseif(_GCC_COMPATIBLE)
-        if (sodium_USE_STATIC_LIBS)
-            find_library(sodium_LIBRARY_DEBUG libsodium.a
-                HINTS ${sodium_DIR}
-                PATH_SUFFIXES lib
-            )
-            find_library(sodium_LIBRARY_RELEASE libsodium.a
-                HINTS ${sodium_DIR}
-                PATH_SUFFIXES lib
-            )
-        else()
-            find_library(sodium_LIBRARY_DEBUG libsodium.dll.a
-                HINTS ${sodium_DIR}
-                PATH_SUFFIXES lib
-            )
-            find_library(sodium_LIBRARY_RELEASE libsodium.dll.a
-                HINTS ${sodium_DIR}
-                PATH_SUFFIXES lib
-            )
-
-            file(GLOB _DLL
-                LIST_DIRECTORIES false
-                RELATIVE "${sodium_DIR}/bin"
-                "${sodium_DIR}/bin/libsodium*.dll"
-            )
-            find_library(sodium_DLL_DEBUG ${_DLL} libsodium
-                HINTS ${sodium_DIR}
-                PATH_SUFFIXES bin
-            )
-            find_library(sodium_DLL_RELEASE ${_DLL} libsodium
-                HINTS ${sodium_DIR}
-                PATH_SUFFIXES bin
-            )
-        endif()
-    else()
-        message(FATAL_ERROR "this platform is not supported by FindSodium.cmake")
-    endif()
-
-
-########################################################################
-# unsupported
-else()
-    message(FATAL_ERROR "this platform is not supported by FindSodium.cmake")
-endif()
-
-
-########################################################################
-# common stuff
-
-# extract sodium version
-if (sodium_INCLUDE_DIR)
-    set(_VERSION_HEADER "${_INCLUDE_DIR}/sodium/version.h")
-    if (EXISTS _VERSION_HEADER)
-        file(READ "${_VERSION_HEADER}" _VERSION_HEADER_CONTENT)
-        string(REGEX REPLACE ".*#[ \t]*define[ \t]*SODIUM_VERSION_STRING[ \t]*\"([^\n]*)\".*" "\\1"
-            sodium_VERSION "${_VERSION_HEADER_CONTENT}")
-        set(sodium_VERSION "${sodium_VERSION}" PARENT_SCOPE)
-    endif()
-endif()
-
-# communicate results
-include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(
-    Sodium # The name must be either uppercase or match the filename case.
-    REQUIRED_VARS
-        sodium_LIBRARY_RELEASE
-        sodium_LIBRARY_DEBUG
-        sodium_INCLUDE_DIR
-    VERSION_VAR
-        sodium_VERSION
-)
-
-if(Sodium_FOUND)
-    set(sodium_LIBRARIES
-        optimized ${sodium_LIBRARY_RELEASE} debug ${sodium_LIBRARY_DEBUG})
-endif()
-
-# mark file paths as advanced
-mark_as_advanced(sodium_INCLUDE_DIR)
-mark_as_advanced(sodium_LIBRARY_DEBUG)
-mark_as_advanced(sodium_LIBRARY_RELEASE)
-if (WIN32)
-    mark_as_advanced(sodium_DLL_DEBUG)
-    mark_as_advanced(sodium_DLL_RELEASE)
-endif()
-
-# create imported target
-if(sodium_USE_STATIC_LIBS)
-    set(_LIB_TYPE STATIC)
-else()
-    set(_LIB_TYPE SHARED)
-endif()
-
-if(NOT TARGET sodium)
-    add_library(sodium ${_LIB_TYPE} IMPORTED)
-endif()
-
-set_target_properties(sodium PROPERTIES
-    INTERFACE_INCLUDE_DIRECTORIES "${sodium_INCLUDE_DIR}"
-    IMPORTED_LINK_INTERFACE_LANGUAGES "C"
-)
-
-if (sodium_USE_STATIC_LIBS)
-    set_target_properties(sodium PROPERTIES
-        INTERFACE_COMPILE_DEFINITIONS "SODIUM_STATIC"
-        IMPORTED_LOCATION "${sodium_LIBRARY_RELEASE}"
-        IMPORTED_LOCATION_DEBUG "${sodium_LIBRARY_DEBUG}"
-    )
-else()
-    if (UNIX)
-        set_target_properties(sodium PROPERTIES
-            IMPORTED_LOCATION "${sodium_LIBRARY_RELEASE}"
-            IMPORTED_LOCATION_DEBUG "${sodium_LIBRARY_DEBUG}"
-        )
-    elseif (WIN32)
-        set_target_properties(sodium PROPERTIES
-            IMPORTED_IMPLIB "${sodium_LIBRARY_RELEASE}"
-            IMPORTED_IMPLIB_DEBUG "${sodium_LIBRARY_DEBUG}"
-        )
-        if (NOT (sodium_DLL_DEBUG MATCHES ".*-NOTFOUND"))
-            set_target_properties(sodium PROPERTIES
-                IMPORTED_LOCATION_DEBUG "${sodium_DLL_DEBUG}"
-            )
-        endif()
-        if (NOT (sodium_DLL_RELEASE MATCHES ".*-NOTFOUND"))
-            set_target_properties(sodium PROPERTIES
-                IMPORTED_LOCATION_RELWITHDEBINFO "${sodium_DLL_RELEASE}"
-                IMPORTED_LOCATION_MINSIZEREL "${sodium_DLL_RELEASE}"
-                IMPORTED_LOCATION_RELEASE "${sodium_DLL_RELEASE}"
-            )
-        endif()
-    endif()
-endif()

cmake/MgThrift.cmake

@@ -1,169 +0,0 @@
-find_package(Gflags)
-find_package(Folly)
-find_package(wangle)
-find_package(fizz)
-find_package(proxygen)
-find_package(FBThrift)
-set(THRIFTCPP2 "FBThrift::thriftcpp2")
-set(THRIFT1 ${FBTHRIFT_COMPILER})
-
-include(${FBTHRIFT_INCLUDE_DIR}/thrift/ThriftLibrary.cmake)
-
-set(MG_INTERFACE_TARGET_NAME_PREFIX "mg-interface")
-
-function(_mg_thrift_generate
-  file_name
-  services
-  language
-  options
-  file_path
-  output_path
-  include_prefix
-)
-  cmake_parse_arguments(THRIFT_GENERATE   # Prefix
-    "" # Options
-    "" # One Value args
-    "THRIFT_INCLUDE_DIRECTORIES" # Multi-value args
-    "${ARGN}")
-
-  set(thrift_include_directories)
-  foreach(dir ${THRIFT_GENERATE_THRIFT_INCLUDE_DIRECTORIES})
-    list(APPEND thrift_include_directories "-I" "${dir}")
-  endforeach()
-
-  set("${file_name}-${language}-HEADERS"
-    ${output_path}/gen-${language}/${file_name}_constants.h
-    ${output_path}/gen-${language}/${file_name}_data.h
-    ${output_path}/gen-${language}/${file_name}_metadata.h
-    ${output_path}/gen-${language}/${file_name}_types.h
-    ${output_path}/gen-${language}/${file_name}_types.tcc
-  )
-  set("${file_name}-${language}-SOURCES"
-    ${output_path}/gen-${language}/${file_name}_constants.cpp
-    ${output_path}/gen-${language}/${file_name}_data.cpp
-    ${output_path}/gen-${language}/${file_name}_types.cpp
-  )
-  if(NOT "${options}" MATCHES "no_metadata")
-    set("${file_name}-${language}-SOURCES"
-      ${${file_name}-${language}-SOURCES}
-      ${output_path}/gen-${language}/${file_name}_metadata.cpp
-    )
-  endif()
-  foreach(service ${services})
-    set("${file_name}-${language}-HEADERS"
-      ${${file_name}-${language}-HEADERS}
-      ${output_path}/gen-${language}/${service}.h
-      ${output_path}/gen-${language}/${service}.tcc
-      ${output_path}/gen-${language}/${service}AsyncClient.h
-      ${output_path}/gen-${language}/${service}_custom_protocol.h
-    )
-    set("${file_name}-${language}-SOURCES"
-      ${${file_name}-${language}-SOURCES}
-      ${output_path}/gen-${language}/${service}.cpp
-      ${output_path}/gen-${language}/${service}AsyncClient.cpp
-    )
-  endforeach()
-  if("${include_prefix}" STREQUAL "")
-    set(include_prefix_text "")
-  else()
-    set(include_prefix_text "include_prefix=${include_prefix}")
-    if(NOT "${options}" STREQUAL "")
-      set(include_prefix_text ",${include_prefix_text}")
-    endif()
-  endif()
-  set(gen_language ${language})
-  if("${language}" STREQUAL "cpp2")
-    set(gen_language "mstch_cpp2")
-  elseif("${language}" STREQUAL "py3")
-    set(gen_language "mstch_py3")
-    file(WRITE "${output_path}/gen-${language}/${file_name}/__init__.py")
-  endif()
-  add_custom_command(
-    OUTPUT ${${file_name}-${language}-HEADERS}
-      ${${file_name}-${language}-SOURCES}
-    COMMAND ${THRIFT1}
-      --gen "${gen_language}:${options}${include_prefix_text}"
-      -o ${output_path}
-      ${thrift_include_directories}
-      "${file_path}/${file_name}.thrift"
-    DEPENDS
-      ${THRIFT1}
-      "${file_path}/${file_name}.thrift"
-    COMMENT "Generating ${MG_INTERFACE_TARGET_NAME_PREFIX}-${file_name}-${language} files. Output: ${output_path}"
-  )
-  add_custom_target(
-    ${MG_INTERFACE_TARGET_NAME_PREFIX}-${file_name}-${language}-target ALL
-    DEPENDS ${${language}-${language}-HEADERS}
-      ${${file_name}-${language}-SOURCES}
-  )
-
-  set("${file_name}-${language}-SOURCES" ${${file_name}-${language}-SOURCES} PARENT_SCOPE)
-  install(
-    DIRECTORY gen-${language}
-    DESTINATION include/${include_prefix}
-    FILES_MATCHING PATTERN "*.h")
-  install(
-    DIRECTORY gen-${language}
-    DESTINATION include/${include_prefix}
-    FILES_MATCHING PATTERN "*.tcc")
-endfunction()
-
-
-function(_mg_thrift_object
-  file_name
-  services
-  language
-  options
-  file_path
-  output_path
-  include_prefix
-)
-  _mg_thrift_generate(
-    "${file_name}"
-    "${services}"
-    "${language}"
-    "${options}"
-    "${file_path}"
-    "${output_path}"
-    "${include_prefix}"
-    "${ARGN}"
-  )
-  bypass_source_check(${${file_name}-${language}-SOURCES})
-  add_library(
-    "${MG_INTERFACE_TARGET_NAME_PREFIX}-${file_name}-${language}-obj"
-    OBJECT
-    ${${file_name}-${language}-SOURCES}
-  )
-  add_dependencies(
-    "${MG_INTERFACE_TARGET_NAME_PREFIX}-${file_name}-${language}-obj"
-    "${MG_INTERFACE_TARGET_NAME_PREFIX}-${file_name}-${language}-target"
-  )
-  target_include_directories(${MG_INTERFACE_TARGET_NAME_PREFIX}-${file_name}-${language}-obj PUBLIC ${output_path})
-  message(STATUS "MgThrift will create the Object file : ${MG_INTERFACE_TARGET_NAME_PREFIX}-${file_name}-${language}-obj")
-endfunction()
-
-function(mg_thrift_library
-  file_name
-  services
-  file_path
-  output_path
-  include_prefix
-)
-  _mg_thrift_object(
-    "${file_name}"
-    "${services}"
-    "cpp2"
-    "stack_arguments" # options
-    "${file_path}"
-    "${output_path}"
-    "${include_prefix}"
-    THRIFT_INCLUDE_DIRECTORIES "${FBTHRIFT_INCLUDE_DIR}"
-  )
-  set(LIBRARY_NAME "${MG_INTERFACE_TARGET_NAME_PREFIX}-${file_name}-cpp2")
-  add_library(
-    "${LIBRARY_NAME}"
-    $<TARGET_OBJECTS:${LIBRARY_NAME}-obj>
-  )
-  target_link_libraries("${LIBRARY_NAME}" ${THRIFTCPP2})
-  message("MgThrift will create the library file : ${LIBRARY_NAME}")
-endfunction()

environment/os/centos-7.sh

@@ -5,6 +5,9 @@ set -Eeuo pipefail
 DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 source "$DIR/../util.sh"
 
+check_operating_system "centos-7"
+check_architecture "x86_64"
+
 TOOLCHAIN_BUILD_DEPS=(
     coreutils gcc gcc-c++ make # generic build tools
     wget # used for archive download

environment/os/centos-8.sh

@@ -1,161 +0,0 @@
-#!/bin/bash
-
-set -Eeuo pipefail
-
-DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
-source "$DIR/../util.sh"
-
-TOOLCHAIN_BUILD_DEPS=(
-    coreutils-common gcc gcc-c++ make # generic build tools
-    wget # used for archive download
-    gnupg2 # used for archive signature verification
-    tar gzip bzip2 xz unzip # used for archive unpacking
-    zlib-devel # zlib library used for all builds
-    expat-devel libipt libipt-devel libbabeltrace-devel xz-devel python36-devel texinfo # for gdb
-    libcurl-devel # for cmake
-    curl # snappy
-    readline-devel # for cmake and llvm
-    libffi-devel libxml2-devel # for llvm
-    libedit-devel pcre-devel automake bison # for swig
-    file
-    openssl-devel
-    gmp-devel
-    gperf
-    patch
-)
-
-TOOLCHAIN_RUN_DEPS=(
-    make # generic build tools
-    tar gzip bzip2 xz # used for archive unpacking
-    zlib # zlib library used for all builds
-    expat libipt libbabeltrace xz-libs python36 # for gdb
-    readline # for cmake and llvm
-    libffi libxml2 # for llvm
-    openssl-devel
-)
-
-MEMGRAPH_BUILD_DEPS=(
-    git # source code control
-    make pkgconf-pkg-config # build system
-    curl wget # for downloading libs
-    libuuid-devel java-11-openjdk # required by antlr
-    readline-devel # for memgraph console
-    python36-devel # for query modules
-    openssl-devel
-    libseccomp-devel
-    python36 python3-virtualenv python3-pip nmap-ncat # for qa, macro_benchmark and stress tests
-    #
-    # IMPORTANT: python3-yaml does NOT exist on CentOS
-    # Install it manually using `pip3 install PyYAML`
-    #
-    PyYAML # Package name here does not correspond to the yum package!
-    libcurl-devel # mg-requests
-    rpm-build rpmlint # for RPM package building
-    doxygen graphviz # source documentation generators
-    which mono-complete dotnet-sdk-3.1 nodejs golang zip unzip java-11-openjdk-devel # for driver tests
-    sbcl # for custom Lisp C++ preprocessing
-    autoconf # for jemalloc code generation
-    libtool  # for protobuf code generation
-)
-
-list() {
-    echo "$1"
-}
-
-check() {
-    local missing=""
-    for pkg in $1; do
-        if [ "$pkg" == "PyYAML" ]; then
-            if ! python3 -c "import yaml" >/dev/null 2>/dev/null; then
-                missing="$pkg $missing"
-            fi
-            continue
-        fi
-        if ! yum list installed "$pkg" >/dev/null 2>/dev/null; then
-            missing="$pkg $missing"
-        fi
-    done
-    if [ "$missing" != "" ]; then
-        echo "MISSING PACKAGES: $missing"
-        exit 1
-    fi
-}
-
-install() {
-    cd "$DIR"
-    if [ "$EUID" -ne 0 ]; then
-        echo "Please run as root."
-        exit 1
-    fi
-    # If GitHub Actions runner is installed, append LANG to the environment.
-    # Python related tests doesn't work the LANG export.
-    if [ -d "/home/gh/actions-runner" ]; then
-        echo "LANG=en_US.utf8" >> /home/gh/actions-runner/.env
-    else
-        echo "NOTE: export LANG=en_US.utf8"
-    fi
-    dnf install -y epel-release
-    dnf install -y 'dnf-command(config-manager)'
-    dnf config-manager --set-enabled powertools # Required to install texinfo.
-    dnf update -y
-    dnf install -y wget git python36 python3-pip
-    for pkg in $1; do
-        if [ "$pkg" == libipt ]; then
-            if ! dnf list installed libipt >/dev/null 2>/dev/null; then
-                dnf install -y http://repo.okay.com.mx/centos/8/x86_64/release/libipt-1.6.1-8.el8.x86_64.rpm
-            fi
-            continue
-        fi
-        if [ "$pkg" == libipt-devel ]; then
-            if ! yum list installed libipt-devel >/dev/null 2>/dev/null; then
-                dnf install -y http://repo.okay.com.mx/centos/8/x86_64/release/libipt-devel-1.6.1-8.el8.x86_64.rpm
-            fi
-            continue
-        fi
-        # Install GDB dependencies not present in the standard repos.
-        # https://bugs.centos.org/view.php?id=17068
-        # https://centos.pkgs.org
-	    # Since 2020, there is Babeltrace2 (https://babeltrace.org). Not used
-        # within GDB yet (an assumption).
-        # http://mirror.centos.org/centos/8/PowerTools/x86_64/os/Packages/libbabeltrace-devel-1.5.4-3.el8.x86_64.rpm not working
-        if [ "$pkg" == libbabeltrace-devel ]; then
-            if ! dnf list installed libbabeltrace-devel >/dev/null 2>/dev/null; then
-                dnf install -y https://rpmfind.net/linux/centos/8-stream/PowerTools/x86_64/os/Packages/libbabeltrace-devel-1.5.4-3.el8.x86_64.rpm
-            fi
-            continue
-        fi
-        if [ "$pkg" == sbcl ]; then
-            if ! dnf list installed cl-asdf >/dev/null 2>/dev/null; then
-                dnf install -y 	https://pkgs.dyn.su/el8/base/x86_64/cl-asdf-20101028-18.el8.noarch.rpm
-            fi
-            if ! dnf list installed common-lisp-controller >/dev/null 2>/dev/null; then
-                dnf install -y https://pkgs.dyn.su/el8/base/x86_64/common-lisp-controller-7.4-20.el8.noarch.rpm
-            fi
-            if ! dnf list installed sbcl >/dev/null 2>/dev/null; then
-                dnf install -y https://pkgs.dyn.su/el8/base/x86_64/sbcl-2.0.1-4.el8.x86_64.rpm
-            fi
-            continue
-        fi
-        if [ "$pkg" == dotnet-sdk-3.1 ]; then
-            if ! dnf list installed dotnet-sdk-3.1 >/dev/null 2>/dev/null; then
-                wget -nv https://packages.microsoft.com/config/centos/8/packages-microsoft-prod.rpm -O packages-microsoft-prod.rpm
-                rpm -Uvh https://packages.microsoft.com/config/centos/8/packages-microsoft-prod.rpm
-                dnf update -y
-                dnf install -y dotnet-sdk-3.1
-            fi
-            continue
-        fi
-        if [ "$pkg" == PyYAML ]; then
-            if [ -z ${SUDO_USER+x} ]; then # Running as root (e.g. Docker).
-                pip3 install --user PyYAML
-            else # Running using sudo.
-                sudo -H -u "$SUDO_USER" bash -c "pip3 install --user PyYAML"
-            fi
-            continue
-        fi
-        dnf install -y "$pkg"
-    done
-}
-
-deps=$2"[*]"
-"$1" "${!deps}"

environment/os/centos-9.sh

@@ -5,15 +5,16 @@ set -Eeuo pipefail
 DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 source "$DIR/../util.sh"
 
+check_operating_system "centos-9"
+check_architecture "x86_64"
+
 TOOLCHAIN_BUILD_DEPS=(
-    coreutils gcc gcc-c++ make # generic build tools
+    coreutils-common gcc gcc-c++ make # generic build tools
     wget # used for archive download
     gnupg2 # used for archive signature verification
     tar gzip bzip2 xz unzip # used for archive unpacking
     zlib-devel # zlib library used for all builds
-    expat-devel xz-devel python3-devel texinfo # for gdb
-    libcurl-devel # for cmake
-    curl # snappy
+    expat-devel xz-devel python3-devel texinfo libbabeltrace-devel # for gdb
     readline-devel # for cmake and llvm
     libffi-devel libxml2-devel # for llvm
     libedit-devel pcre-devel automake bison # for swig
@@ -21,6 +22,9 @@ TOOLCHAIN_BUILD_DEPS=(
     openssl-devel
     gmp-devel
     gperf
+    diffutils
+    libipt libipt-devel # intel
+    patch
 )
 
 TOOLCHAIN_RUN_DEPS=(
@@ -31,18 +35,19 @@ TOOLCHAIN_RUN_DEPS=(
     readline # for cmake and llvm
     libffi libxml2 # for llvm
     openssl-devel
+    perl # for openssl
 )
 
 MEMGRAPH_BUILD_DEPS=(
     git # source code control
     make pkgconf-pkg-config # build system
-    curl wget # for downloading libs
+    wget # for downloading libs
     libuuid-devel java-11-openjdk # required by antlr
     readline-devel # for memgraph console
     python3-devel # for query modules
     openssl-devel
     libseccomp-devel
-    python3 python3-virtualenv python3-pip nmap-ncat # for qa, macro_benchmark and stress tests
+    python3 python3-pip python3-virtualenv nmap-ncat # for qa, macro_benchmark and stress tests
     #
     # IMPORTANT: python3-yaml does NOT exist on CentOS
     # Install it manually using `pip3 install PyYAML`
@@ -73,12 +78,6 @@ check() {
         if [ "$pkg" == "python3-virtualenv" ]; then
             continue
         fi
-        if [ "$pkg" == sbcl ]; then
-            if ! sbcl --version &> /dev/null; then
-	        missing="$pkg $missing"
-            fi
-            continue
-        fi
         if ! yum list installed "$pkg" >/dev/null 2>/dev/null; then
             missing="$pkg $missing"
         fi
@@ -105,13 +104,37 @@ install() {
     yum update -y
     yum install -y wget git python3 python3-pip
     for pkg in $1; do
+        # Since there is no support for libipt-devel for CentOS 9 we install
+        # Fedoras version of same libs, they are the same version but released
+        # for different OS
+        # TODO Update when libipt-devel releases for CentOS 9
+        if [ "$pkg" == libipt ]; then
+            if ! dnf list installed libipt >/dev/null 2>/dev/null; then
+                dnf install -y http://repo.okay.com.mx/centos/8/x86_64/release/libipt-1.6.1-8.el8.x86_64.rpm
+            fi
+            continue
+        fi
+        if [ "$pkg" == libipt-devel ]; then
+            if ! dnf list installed libipt-devel >/dev/null 2>/dev/null; then
+                dnf install -y http://repo.okay.com.mx/centos/8/x86_64/release/libipt-devel-1.6.1-8.el8.x86_64.rpm
+            fi
+            continue
+        fi
+        if [ "$pkg" == libbabeltrace-devel ]; then
+            if ! dnf list installed libbabeltrace-devel >/dev/null 2>/dev/null; then
+                dnf install -y http://mirror.stream.centos.org/9-stream/CRB/x86_64/os/Packages/libbabeltrace-devel-1.5.8-10.el9.x86_64.rpm
+            fi
+            continue
+        fi
         if [ "$pkg" == sbcl ]; then
-            if ! sbcl --version &> /dev/null; then
-	        curl -s https://altushost-swe.dl.sourceforge.net/project/sbcl/sbcl/1.4.2/sbcl-1.4.2-arm64-linux-binary.tar.bz2 -o /tmp/sbcl-arm64.tar.bz2
-		tar xvjf /tmp/sbcl-arm64.tar.bz2 -C /tmp
-		pushd /tmp/sbcl-1.4.2-arm64-linux
-		INSTALL_ROOT=/usr/local sh install.sh
-		popd
+            if ! dnf list installed cl-asdf >/dev/null 2>/dev/null; then
+                dnf install -y 	https://pkgs.dyn.su/el8/base/x86_64/cl-asdf-20101028-18.el8.noarch.rpm
+            fi
+            if ! dnf list installed common-lisp-controller >/dev/null 2>/dev/null; then
+                dnf install -y https://pkgs.dyn.su/el8/base/x86_64/common-lisp-controller-7.4-20.el8.noarch.rpm
+            fi
+            if ! dnf list installed sbcl >/dev/null 2>/dev/null; then
+                dnf install -y https://pkgs.dyn.su/el8/base/x86_64/sbcl-2.0.1-4.el8.x86_64.rpm
             fi
             continue
         fi
@@ -125,9 +148,11 @@ install() {
         fi
         if [ "$pkg" == python3-virtualenv ]; then
             if [ -z ${SUDO_USER+x} ]; then # Running as root (e.g. Docker).
-                pip3 install --user virtualenv
+                pip3 install virtualenv
+                pip3 install virtualenvwrapper
             else # Running using sudo.
-                sudo -H -u "$SUDO_USER" bash -c "pip3 install --user virtualenv"
+                sudo -H -u "$SUDO_USER" bash -c "pip3 install virtualenv"
+                sudo -H -u "$SUDO_USER" bash -c "pip3 install virtualenvwrapper"
             fi
             continue
         fi

environment/os/debian-10.sh

@@ -5,6 +5,9 @@ set -Eeuo pipefail
 DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 source "$DIR/../util.sh"
 
+check_operating_system "debian-10"
+check_architecture "x86_64"
+
 TOOLCHAIN_BUILD_DEPS=(
     coreutils gcc g++ build-essential make # generic build tools
     wget # used for archive download

environment/os/debian-11-arm.sh

@@ -5,6 +5,9 @@ set -Eeuo pipefail
 DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 source "$DIR/../util.sh"
 
+check_operating_system "debian-11"
+check_architecture "arm64"
+
 TOOLCHAIN_BUILD_DEPS=(
     coreutils gcc g++ build-essential make # generic build tools
     wget # used for archive download
@@ -87,15 +90,6 @@ EOF
     fi
     apt install -y wget
     for pkg in $1; do
-        if [ "$pkg" == dotnet-sdk-3.1 ]; then
-            if ! dpkg -s "$pkg" 2>/dev/null >/dev/null; then
-                wget -nv https://packages.microsoft.com/config/debian/10/packages-microsoft-prod.deb -O packages-microsoft-prod.deb
-                dpkg -i packages-microsoft-prod.deb
-                apt-get update
-                apt-get install -y apt-transport-https dotnet-sdk-3.1
-            fi
-            continue
-        fi
         apt install -y "$pkg"
     done
 }

environment/os/debian-11.sh

@@ -5,6 +5,9 @@ set -Eeuo pipefail
 DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 source "$DIR/../util.sh"
 
+check_operating_system "debian-11"
+check_architecture "x86_64"
+
 TOOLCHAIN_BUILD_DEPS=(
     coreutils gcc g++ build-essential make # generic build tools
     wget # used for archive download
@@ -87,7 +90,7 @@ EOF
     fi
     apt install -y wget
     for pkg in $1; do
-        if [ "$pkg" == dotnet-sdk-3.1 ]; then
+        if [ "$pkg" == dotnet-sdk-3.1  ]; then
             if ! dpkg -s "$pkg" 2>/dev/null >/dev/null; then
                 wget -nv https://packages.microsoft.com/config/debian/10/packages-microsoft-prod.deb -O packages-microsoft-prod.deb
                 dpkg -i packages-microsoft-prod.deb

environment/os/template.sh

@@ -5,6 +5,8 @@ set -Eeuo pipefail
 DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 source "$DIR/../util.sh"
 
+check_operating_system "todo-os-name"
+
 TOOLCHAIN_BUILD_DEPS=(
     pkg
 )

environment/os/ubuntu-18.04.sh

@@ -5,6 +5,9 @@ set -Eeuo pipefail
 DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 source "$DIR/../util.sh"
 
+check_operating_system "ubuntu-18.04"
+check_architecture "x86_64"
+
 TOOLCHAIN_BUILD_DEPS=(
     coreutils gcc g++ build-essential make # generic build tools
     wget # archive download

environment/os/ubuntu-20.04.sh

@@ -5,6 +5,9 @@ set -Eeuo pipefail
 DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 source "$DIR/../util.sh"
 
+check_operating_system "ubuntu-20.04"
+check_architecture "x86_64"
+
 TOOLCHAIN_BUILD_DEPS=(
     coreutils gcc g++ build-essential make # generic build tools
     wget # used for archive download

environment/os/ubuntu-22.04.sh

@@ -0,0 +1,96 @@
+#!/bin/bash
+
+set -Eeuo pipefail
+
+DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
+source "$DIR/../util.sh"
+
+check_operating_system "ubuntu-22.04"
+check_architecture "x86_64"
+
+TOOLCHAIN_BUILD_DEPS=(
+    coreutils gcc g++ build-essential make # generic build tools
+    wget # used for archive download
+    gnupg # used for archive signature verification
+    tar gzip bzip2 xz-utils unzip # used for archive unpacking
+    zlib1g-dev # zlib library used for all builds
+    libexpat1-dev libipt-dev libbabeltrace-dev liblzma-dev python3-dev texinfo # for gdb
+    libcurl4-openssl-dev # for cmake
+    libreadline-dev # for cmake and llvm
+    libffi-dev libxml2-dev # for llvm
+    curl # snappy
+    file
+    git # for thrift
+    libgmp-dev # for gdb
+    gperf # for proxygen
+    libssl-dev
+    libedit-dev libpcre3-dev automake bison # for swig
+)
+
+TOOLCHAIN_RUN_DEPS=(
+    make # generic build tools
+    tar gzip bzip2 xz-utils # used for archive unpacking
+    zlib1g # zlib library used for all builds
+    libexpat1 libipt2 libbabeltrace1 liblzma5 python3 # for gdb
+    libcurl4 # for cmake
+    libreadline8 # for cmake and llvm
+    libffi7 libxml2 # for llvm
+    libssl-dev # for libevent
+)
+
+MEMGRAPH_BUILD_DEPS=(
+    git # source code control
+    make pkg-config # build system
+    curl wget # for downloading libs
+    uuid-dev default-jre-headless # required by antlr
+    libreadline-dev # for memgraph console
+    libpython3-dev python3-dev # for query modules
+    libssl-dev
+    libseccomp-dev
+    netcat # tests are using nc to wait for memgraph
+    python3 python3-virtualenv python3-pip # for qa, macro_benchmark and stress tests
+    python3-yaml # for the configuration generator
+    libcurl4-openssl-dev # mg-requests
+    sbcl # for custom Lisp C++ preprocessing
+    doxygen graphviz # source documentation generators
+    mono-runtime mono-mcs zip unzip default-jdk-headless # for driver tests
+    dotnet-sdk-6.0 golang nodejs npm
+    autoconf # for jemalloc code generation
+    libtool  # for protobuf code generation
+)
+
+list() {
+    echo "$1"
+}
+
+check() {
+    check_all_dpkg "$1"
+}
+
+install() {
+    cd "$DIR"
+    apt update
+    # If GitHub Actions runner is installed, append LANG to the environment.
+    # Python related tests doesn't work the LANG export.
+    if [ -d "/home/gh/actions-runner" ]; then
+        echo "LANG=en_US.utf8" >> /home/gh/actions-runner/.env
+    else
+        echo "NOTE: export LANG=en_US.utf8"
+    fi
+    apt install -y wget
+    for pkg in $1; do
+        if [ "$pkg" == dotnet-sdk-6.0 ]; then
+            if ! dpkg -s dotnet-sdk-6.0 2>/dev/null >/dev/null; then
+                wget -nv https://packages.microsoft.com/config/ubuntu/22.04/packages-microsoft-prod.deb -O packages-microsoft-prod.deb
+                dpkg -i packages-microsoft-prod.deb
+                apt-get update
+                apt-get install -y apt-transport-https dotnet-sdk-6.0
+            fi
+            continue
+        fi
+        apt install -y "$pkg"
+    done
+}
+
+deps=$2"[*]"
+"$1" "${!deps}"

environment/toolchain/fbthrift.patch

@@ -1,12 +0,0 @@
-diff -ur a/thrift/lib/cpp2/server/IOWorkerContext.h b/thrift/lib/cpp2/server/IOWorkerContext.h
---- a/thrift/lib/cpp2/server/IOWorkerContext.h  2022-06-08 11:50:43.043948657 +0200
-+++ b/thrift/lib/cpp2/server/IOWorkerContext.h  2022-06-08 11:47:33.232695125 +0200
-@@ -59,7 +59,7 @@
-           auto aliveLocked = alive->rlock();
-           if (*aliveLocked) {
-             // IOWorkerContext is still alive and so is replyQueue_
--            queue->startConsumingInternal(&evb);
-+            queue->startConsuming(&evb);
-           }
-         });
-   }

environment/toolchain/v4.sh

@@ -675,7 +675,7 @@ PROXYGEN_SHA256=5360a8ccdfb2f5a6c7b3eed331ec7ab0e2c792d579c6fff499c85c516c11fe14
 SNAPPY_SHA256=75c1fbb3d618dd3a0483bff0e26d0a92b495bbe5059c8b4f1c962b478b6e06e7
 SNAPPY_VERSION=1.1.9
 XZ_VERSION=5.2.5 # for LZMA
-ZLIB_VERSION=1.2.11
+ZLIB_VERSION=1.2.12
 ZSTD_VERSION=1.5.0
 WANGLE_SHA256=1002e9c32b6f4837f6a760016e3b3e22f3509880ef3eaad191c80dc92655f23f
 
@@ -1178,12 +1178,21 @@ popd
 
 # create toolchain archive
 if [ ! -f $NAME-binaries-$DISTRO.tar.gz ]; then
-    DISTRO_FULL_NAME=$DISTRO
-    if [ "$for_arm" = true ]; then
-        DISTRO_FULL_NAME="$DISTRO_FULL_NAME-aarch64"
+    DISTRO_FULL_NAME=${DISTRO}
+    if [[ "${DISTRO}" == centos* ]]; then
+        if [[ "$for_arm" = "true" ]]; then
+            DISTRO_FULL_NAME="$DISTRO_FULL_NAME-aarch64"
+        else
+            DISTRO_FULL_NAME="$DISTRO_FULL_NAME-x86_64"
+        fi
     else
-        DISTRO_FULL_NAME="$DISTRO_FULL_NAME-x86_64"
+        if [[ "$for_arm" = "true" ]]; then
+            DISTRO_FULL_NAME="$DISTRO_FULL_NAME-arm64"
+        else
+            DISTRO_FULL_NAME="$DISTRO_FULL_NAME-amd64"
+        fi
     fi
+
     tar --owner=root --group=root -cpvzf $NAME-binaries-$DISTRO_FULL_NAME.tar.gz -C /opt $NAME
 fi
 

environment/util.sh

@@ -5,10 +5,28 @@ operating_system() {
     sort | cut -d '=' -f 2- | sed 's/"//g' | paste -s -d '-'
 }
 
+check_operating_system() {
+    if [ "$(operating_system)" != "$1" ]; then
+        echo "Not the right operating system!"
+        exit 1
+    else
+        echo "The right operating system."
+    fi
+}
+
 architecture() {
     uname -m
 }
 
+check_architecture() {
+    if [ "$(architecture)" != "$1" ]; then
+        echo "Not the right architecture!"
+        exit 1
+    else
+        echo "The right architecture."
+    fi
+}
+
 check_all_yum() {
     local missing=""
     for pkg in $1; do

init

@@ -24,7 +24,7 @@ function setup_virtualenv () {
     fi
 
     # create new virtualenv
-    virtualenv -p python3 ve3 || exit 1
+    python3 -m virtualenv -p python3 ve3 || exit 1
     source ve3/bin/activate
     pip --timeout 1000 install -r requirements.txt || exit 1
     deactivate
@@ -66,7 +66,7 @@ fi
 
 DISTRO=$(operating_system)
 ARCHITECTURE=$(architecture)
-if [ "${ARCHITECTURE}" = "arm64" ]; then
+if [ "${ARCHITECTURE}" = "arm64" ] || [ "${ARCHITECTURE}" = "aarch64" ]; then
   OS_SCRIPT=$DIR/environment/os/$DISTRO-arm.sh
 else
   OS_SCRIPT=$DIR/environment/os/$DISTRO.sh
@@ -139,3 +139,6 @@ done;
 # Install precommit hook
 python3 -m pip install pre-commit
 python3 -m pre_commit install
+
+# Link `include/mgp.py` with `release/mgp/mgp.py`
+ln -v -f include/mgp.py release/mgp/mgp.py

libs/.gitignore

@@ -4,5 +4,4 @@
 !cleanup.sh
 !CMakeLists.txt
 !__main.cpp
-!jemalloc.cmake
 !pulsar.patch

libs/jemalloc.cmake

@@ -1,55 +0,0 @@
-set(JEMALLOC_DIR "${LIB_DIR}/jemalloc")
-
-set(JEMALLOC_SRCS
-    ${JEMALLOC_DIR}/src/arena.c
-    ${JEMALLOC_DIR}/src/background_thread.c
-    ${JEMALLOC_DIR}/src/base.c
-    ${JEMALLOC_DIR}/src/bin.c
-    ${JEMALLOC_DIR}/src/bitmap.c
-    ${JEMALLOC_DIR}/src/ckh.c
-    ${JEMALLOC_DIR}/src/ctl.c
-    ${JEMALLOC_DIR}/src/div.c
-    ${JEMALLOC_DIR}/src/extent.c
-    ${JEMALLOC_DIR}/src/extent_dss.c
-    ${JEMALLOC_DIR}/src/extent_mmap.c
-    ${JEMALLOC_DIR}/src/hash.c
-    ${JEMALLOC_DIR}/src/hook.c
-    ${JEMALLOC_DIR}/src/jemalloc.c
-    ${JEMALLOC_DIR}/src/large.c
-    ${JEMALLOC_DIR}/src/log.c
-    ${JEMALLOC_DIR}/src/malloc_io.c
-    ${JEMALLOC_DIR}/src/mutex.c
-    ${JEMALLOC_DIR}/src/mutex_pool.c
-    ${JEMALLOC_DIR}/src/nstime.c
-    ${JEMALLOC_DIR}/src/pages.c
-    ${JEMALLOC_DIR}/src/prng.c
-    ${JEMALLOC_DIR}/src/prof.c
-    ${JEMALLOC_DIR}/src/rtree.c
-    ${JEMALLOC_DIR}/src/sc.c
-    ${JEMALLOC_DIR}/src/stats.c
-    ${JEMALLOC_DIR}/src/sz.c
-    ${JEMALLOC_DIR}/src/tcache.c
-    ${JEMALLOC_DIR}/src/test_hooks.c
-    ${JEMALLOC_DIR}/src/ticker.c
-    ${JEMALLOC_DIR}/src/tsd.c
-    ${JEMALLOC_DIR}/src/witness.c
-    ${JEMALLOC_DIR}/src/safety_check.c
-)
-
-add_library(jemalloc ${JEMALLOC_SRCS})
-target_include_directories(jemalloc PUBLIC "${JEMALLOC_DIR}/include")
-
-find_package(Threads REQUIRED)
-target_link_libraries(jemalloc PUBLIC Threads::Threads)
-
-target_compile_definitions(jemalloc PRIVATE -DJEMALLOC_NO_PRIVATE_NAMESPACE)
-
-if (CMAKE_BUILD_TYPE STREQUAL "DEBUG")
-    target_compile_definitions(jemalloc PRIVATE -DJEMALLOC_DEBUG=1 -DJEMALLOC_PROF=1)
-endif()
-
-target_compile_options(jemalloc PRIVATE -Wno-redundant-decls)
-# for RTLD_NEXT
-target_compile_definitions(jemalloc PRIVATE _GNU_SOURCE)
-
-set_property(TARGET jemalloc APPEND PROPERTY INTERFACE_COMPILE_DEFINITIONS USE_JEMALLOC=1)

release/CMakeLists.txt

@@ -67,7 +67,7 @@ It aims to deliver developers the speed, simplicity and scale required to build
 the next generation of applications driver by real-time connected data.")
 # Add `openssl` package to dependencies list. Used to generate SSL certificates.
 # We also depend on `python3` because we embed it in Memgraph.
-set(CPACK_RPM_PACKAGE_REQUIRES "openssl >= 1.0.0, curl >= 7.29.0, python3 >= 3.5.0, libstdc >= 6")
+set(CPACK_RPM_PACKAGE_REQUIRES "openssl >= 1.0.0, curl >= 7.29.0, python3 >= 3.5.0, libstdc >= 6, logrotate")
 
 # All variables must be set before including.
 include(CPack)

release/docker/memgraph_rpm.dockerfile

@@ -1,31 +0,0 @@
-FROM dokken/centos-stream-9
-# NOTE: If you change the base distro update release/package as well.
-
-ARG release
-
-RUN yum update && yum install -y \
-    openssl libcurl libseccomp python3 python3-pip \
-    --nobest --allowerasing \
-  && rm -rf /tmp/* \
-  && yum clean all
-
-RUN pip3 install networkx==2.4 numpy==1.21.4 scipy==1.7.3
-
-COPY ${release} /
-
-# Install memgraph package
-RUN rpm -i ${release}
-
-# Memgraph listens for Bolt Protocol on this port by default.
-EXPOSE 7687
-# Snapshots and logging volumes
-VOLUME /var/log/memgraph
-VOLUME /var/lib/memgraph
-# Configuration volume
-VOLUME /etc/memgraph
-
-USER memgraph
-WORKDIR /usr/lib/memgraph
-
-ENTRYPOINT ["/usr/lib/memgraph/memgraph"]
-CMD [""]

release/mgp/.gitignore

@@ -0,0 +1,3 @@
+.venv
+dist
+mgp.py

release/mgp/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

release/mgp/README.md

@@ -0,0 +1,4 @@
+# mgp
+
+PyPi package used for type hinting when creating MAGE modules. The get started
+using MAGE repository checkout the repository here: https://github.com/memgraph/mage.

release/mgp/_mgp.py

@@ -0,0 +1,255 @@
+from typing import Any
+
+
+class MgpIterable:
+    def get() -> Any:
+        pass
+
+    def next() -> Any:
+        pass
+
+
+class Vertex:
+    def is_valid() -> bool:  # type: ignore
+        pass
+
+    def underlying_graph_is_mutable() -> bool:  # type: ignore
+        pass
+
+    def iter_properties() -> MgpIterable:  # type: ignore
+        pass
+
+    def get_property(self, property_name: str) -> "Property":  # type: ignore
+        pass
+
+    def set_property(self, property_name: str, value: Any) -> "Property":  # type: ignore
+        pass
+
+    def get_id() -> "VertexId":  # type: ignore
+        pass
+
+    def label_at(self, index: int) -> "Label":  # type: ignore
+        pass
+
+    def labels_count() -> int:  # type: ignore
+        pass
+
+    def add_label(self, label: Any):
+        pass
+
+    def remove_label(self, label: Any):
+        pass
+
+    def iter_in_edges() -> MgpIterable:  # type: ignore
+        pass
+
+    def iter_out_edges() -> MgpIterable:  # type: ignore
+        pass
+
+
+class Edge:
+    def is_valid() -> bool:  # type: ignore
+        pass
+
+    def underlying_graph_is_mutable() -> bool:  # type: ignore
+        pass
+
+    def iter_properties() -> MgpIterable:  # type: ignore
+        pass
+
+    def get_property(self, property_name: str) -> "Property":  # type: ignore
+        pass
+
+    def set_property(self, property_name: str, valuse: Any) -> "Property":  # type: ignore
+        pass
+
+    def get_type_name() -> str:  # type: ignore
+        pass
+
+    def get_id() -> "EdgeId":  # type: ignore
+        pass
+
+    def from_vertex() -> Vertex:  # type: ignore
+        pass
+
+    def to_vertex() -> Vertex:  # type: ignore
+        pass
+
+
+class Path:
+    def is_valid() -> bool:  # type: ignore
+        pass
+
+    @staticmethod
+    def make_with_start(vertex: Vertex) -> "Path":  # type: ignore
+        pass
+
+
+class Graph:
+    def is_valid() -> bool:  # type: ignore
+        pass
+
+
+class CypherType:
+    pass
+
+
+class Message:
+    def is_valid() -> bool:  # type: ignore
+        pass
+
+    def source_type() -> str:  # type: ignore
+        pass
+
+    def topic_name() -> str:  # type: ignore
+        pass
+
+    def key() -> bytes:  # type: ignore
+        pass
+
+    def timestamp() -> int:  # type: ignore
+        pass
+
+    def offset() -> int:  # type: ignore
+        pass
+
+    def payload() -> bytes:  # type: ignore
+        pass
+
+
+class Messages:
+    def is_valid() -> bool:  # type: ignore
+        pass
+
+    def message_at(self, id: int) -> Message:  # type: ignore
+        pass
+
+    def total_messages() -> int:  # type: ignore
+        pass
+
+
+class UnknownError(Exception):
+    pass
+
+
+class UnableToAllocateError(Exception):
+    pass
+
+
+class InsufficientBufferError(Exception):
+    pass
+
+
+class OutOfRangeError(Exception):
+    pass
+
+
+class LogicErrorError(Exception):
+
+    pass
+
+
+class DeletedObjectError(Exception):
+    pass
+
+
+class InvalidArgumentError(Exception):
+    pass
+
+
+class KeyAlreadyExistsError(Exception):
+    pass
+
+
+class ImmutableObjectError(Exception):
+    pass
+
+
+class ValueConversionError(Exception):
+    pass
+
+
+class SerializationError(Exception):
+    pass
+
+
+def type_nullable(elem: Any):
+    pass
+
+
+def type_list(elem: Any):
+    pass
+
+
+def type_bool():
+    pass
+
+
+def type_string():
+    pass
+
+
+def type_int():
+    pass
+
+
+def type_float():
+    pass
+
+
+def type_number():
+    pass
+
+
+def type_map():
+    pass
+
+
+def type_node():
+    pass
+
+
+def type_relationship():
+    pass
+
+
+def type_path():
+    pass
+
+
+def type_date():
+    pass
+
+
+def type_local_time():
+    pass
+
+
+def type_local_date_time():
+    pass
+
+
+def type_duration():
+    pass
+
+
+def type_any():
+    pass
+
+
+class _MODULE:
+    @staticmethod
+    def add_read_procedure(wrapper):
+        pass
+
+    @staticmethod
+    def add_write_procedure(wrapper):
+        pass
+
+    @staticmethod
+    def add_transformation(wrapper):
+        pass
+
+    @staticmethod
+    def add_function(wrapper):
+        pass

release/mgp/instructions.md

@@ -0,0 +1,22 @@
+# How to publish new versions
+## Prerequisites
+1. Installed poetry
+```
+pip install poetry
+```
+2. Set up [API tokens](https://pypi.org/help/#apitoken)
+3. Be a collaborator on [pypi](https://pypi.org/project/mgp/)
+
+## Making changes
+1. Make changes to the package
+2. Bump version in `pyproject.tml`
+3. `poetry build`
+4. `poetry publish`
+
+## Why is this not automatized?
+
+Because someone always has to manually bump up the version in `pyproject.toml`
+
+## Why does `_mgp.py` exists?
+Because we are mocking here all the types that are created by Memgraph
+in order to fix typing errors in `mgp.py`.

release/mgp/pyproject.toml

@@ -0,0 +1,23 @@
+[tool.poetry]
+name = "mgp"
+version = "1.0.0"
+description = "Memgraph's module for developing MAGE modules. Used only for type hinting!"
+authors = [
+    "MasterMedo <mislav.vuletic@gmail.com>",
+    "jbajic <jure.bajic@memgraph.io>",
+    "katarinasupe <katarina.supe@memgraph.io>",
+    "antejavor <ante.javor@memgraph.io>",
+    "antaljanosbenjamin <benjamin.antal@memgraph.io>",
+]
+license = "Apache-2.0"
+readme = "README.md"
+include = ["mgp.py", "_mgp.py"]
+
+[tool.poetry.dependencies]
+python = "^3.7"
+
+[tool.poetry.dev-dependencies]
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"

release/package/centos-7/Dockerfile

@@ -7,8 +7,8 @@ RUN yum -y update \
 # Do NOT be smart here and clean the cache because the container is used in the
 # stateful context.
 
-RUN wget -q https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/${TOOLCHAIN_VERSION}/${TOOLCHAIN_VERSION}-binaries-centos-7.tar.gz \
-    -O ${TOOLCHAIN_VERSION}-binaries-centos-7.tar.gz \
-    && tar xzvf ${TOOLCHAIN_VERSION}-binaries-centos-7.tar.gz -C /opt
+RUN wget -q https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/${TOOLCHAIN_VERSION}/${TOOLCHAIN_VERSION}-binaries-centos-7-x86_64.tar.gz \
+    -O ${TOOLCHAIN_VERSION}-binaries-centos-7-x86_64.tar.gz \
+    && tar xzvf ${TOOLCHAIN_VERSION}-binaries-centos-7-x86_64.tar.gz -C /opt
 
 ENTRYPOINT ["sleep", "infinity"]

release/package/centos-8/Dockerfile

@@ -1,14 +0,0 @@
-FROM centos:8
-
-ARG TOOLCHAIN_VERSION
-
-RUN dnf -y update \
-    && dnf install -y wget git
-# Do NOT be smart here and clean the cache because the container is used in the
-# stateful context.
-
-RUN wget -q https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/${TOOLCHAIN_VERSION}/${TOOLCHAIN_VERSION}-binaries-centos-8.tar.gz \
-    -O ${TOOLCHAIN_VERSION}-binaries-centos-8.tar.gz \
-    && tar xzvf ${TOOLCHAIN_VERSION}-binaries-centos-8.tar.gz -C /opt
-
-ENTRYPOINT ["sleep", "infinity"]

release/package/centos-9/Dockerfile

@@ -0,0 +1,14 @@
+FROM quay.io/centos/centos:stream9
+
+ARG TOOLCHAIN_VERSION
+
+RUN yum -y update \
+    && yum install -y wget git
+# Do NOT be smart here and clean the cache because the container is used in the
+# stateful context.
+
+RUN wget -q https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/${TOOLCHAIN_VERSION}/${TOOLCHAIN_VERSION}-binaries-centos-9-x86_64.tar.gz \
+    -O ${TOOLCHAIN_VERSION}-binaries-centos-9-x86_64.tar.gz \
+    && tar xzvf ${TOOLCHAIN_VERSION}-binaries-centos-9-x86_64.tar.gz -C /opt
+
+ENTRYPOINT ["sleep", "infinity"]

release/package/debian-10/Dockerfile

@@ -10,8 +10,8 @@ RUN apt update && apt install -y \
 # Do NOT be smart here and clean the cache because the container is used in the
 # stateful context.
 
-RUN wget -q https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/${TOOLCHAIN_VERSION}/${TOOLCHAIN_VERSION}-binaries-debian-10.tar.gz \
-    -O ${TOOLCHAIN_VERSION}-binaries-debian-10.tar.gz \
-    && tar xzvf ${TOOLCHAIN_VERSION}-binaries-debian-10.tar.gz -C /opt
+RUN wget -q https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/${TOOLCHAIN_VERSION}/${TOOLCHAIN_VERSION}-binaries-debian-10-amd64.tar.gz \
+    -O ${TOOLCHAIN_VERSION}-binaries-debian-10-amd64.tar.gz \
+    && tar xzvf ${TOOLCHAIN_VERSION}-binaries-debian-10-amd64.tar.gz -C /opt
 
 ENTRYPOINT ["sleep", "infinity"]

release/package/debian-11-arm/Dockerfile

@@ -0,0 +1,17 @@
+FROM debian:11
+
+ARG TOOLCHAIN_VERSION
+
+# Stops tzdata interactive configuration.
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN apt update && apt install -y \
+    ca-certificates wget git
+# Do NOT be smart here and clean the cache because the container is used in the
+# stateful context.
+
+RUN wget -q https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/${TOOLCHAIN_VERSION}/${TOOLCHAIN_VERSION}-binaries-debian-11-arm64.tar.gz \
+    -O ${TOOLCHAIN_VERSION}-binaries-debian-11-arm64.tar.gz \
+    && tar xzvf ${TOOLCHAIN_VERSION}-binaries-debian-11-arm64.tar.gz -C /opt
+
+ENTRYPOINT ["sleep", "infinity"]

release/package/debian-11/Dockerfile

@@ -10,8 +10,8 @@ RUN apt update && apt install -y \
 # Do NOT be smart here and clean the cache because the container is used in the
 # stateful context.
 
-RUN wget -q https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/${TOOLCHAIN_VERSION}/${TOOLCHAIN_VERSION}-binaries-debian-11.tar.gz \
-    -O ${TOOLCHAIN_VERSION}-binaries-debian-11.tar.gz \
-    && tar xzvf ${TOOLCHAIN_VERSION}-binaries-debian-11.tar.gz -C /opt
+RUN wget -q https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/${TOOLCHAIN_VERSION}/${TOOLCHAIN_VERSION}-binaries-debian-11-amd64.tar.gz \
+    -O ${TOOLCHAIN_VERSION}-binaries-debian-11-amd64.tar.gz \
+    && tar xzvf ${TOOLCHAIN_VERSION}-binaries-debian-11-amd64.tar.gz -C /opt
 
 ENTRYPOINT ["sleep", "infinity"]

release/package/docker-compose.yml

@@ -4,10 +4,10 @@ services:
     build:
       context: centos-7
     container_name: "mgbuild_centos-7"
-  mgbuild_centos-8:
+  mgbuild_centos-9:
     build:
-      context: centos-8
-    container_name: "mgbuild_centos-8"
+      context: centos-9
+    container_name: "mgbuild_centos-9"
   mgbuild_debian-10:
     build:
       context: debian-10
@@ -24,3 +24,7 @@ services:
     build:
       context: ubuntu-20.04
     container_name: "mgbuild_ubuntu-20.04"
+  mgbuild_ubuntu-22.04:
+    build:
+      context: ubuntu-22.04
+    container_name: "mgbuild_ubuntu-22.04"

release/package/run.sh

@@ -3,7 +3,7 @@
 set -Eeuo pipefail
 
 SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
-SUPPORTED_OS=(centos-7 centos-8 debian-10 debian-11 ubuntu-18.04 ubuntu-20.04)
+SUPPORTED_OS=(centos-7 centos-9 debian-10 debian-11 ubuntu-18.04 ubuntu-20.04 ubuntu-22.04 debian-11-arm)
 PROJECT_ROOT="$SCRIPT_DIR/../.."
 TOOLCHAIN_VERSION="toolchain-v4"
 ACTIVATE_TOOLCHAIN="source /opt/${TOOLCHAIN_VERSION}/activate"
@@ -67,14 +67,18 @@ make_package () {
     # environment/os/{os}.sh does not come within the toolchain package. When
     # migrating to the next version of toolchain do that, and remove the
     # TOOLCHAIN_RUN_DEPS installation from here.
-    echo "Installing dependencies..."
+    echo "Installing dependencies using '/memgraph/environment/os/$os.sh' script..."
     docker exec "$build_container" bash -c "/memgraph/environment/os/$os.sh install TOOLCHAIN_RUN_DEPS"
     docker exec "$build_container" bash -c "/memgraph/environment/os/$os.sh install MEMGRAPH_BUILD_DEPS"
 
     echo "Building targeted package..."
     docker exec "$build_container" bash -c "cd /memgraph && $ACTIVATE_TOOLCHAIN && ./init"
     docker exec "$build_container" bash -c "cd $container_build_dir && rm -rf ./*"
-    docker exec "$build_container" bash -c "cd $container_build_dir && $ACTIVATE_TOOLCHAIN && cmake -DCMAKE_BUILD_TYPE=release $telemetry_id_override_flag .."
+    if [[ "$os" == "debian-11-arm" ]]; then
+        docker exec "$build_container" bash -c "cd $container_build_dir && $ACTIVATE_TOOLCHAIN && cmake -DCMAKE_BUILD_TYPE=release -DMG_ARCH="ARM64" $telemetry_id_override_flag .."
+    else
+        docker exec "$build_container" bash -c "cd $container_build_dir && $ACTIVATE_TOOLCHAIN && cmake -DCMAKE_BUILD_TYPE=release $telemetry_id_override_flag .."
+    fi
     # ' is used instead of " because we need to run make within the allowed
     # container resources.
     # shellcheck disable=SC2016

release/package/ubuntu-18.04/Dockerfile

@@ -10,8 +10,8 @@ RUN apt update && apt install -y \
 # Do NOT be smart here and clean the cache because the container is used in the
 # stateful context.
 
-RUN wget -q https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/${TOOLCHAIN_VERSION}/${TOOLCHAIN_VERSION}-binaries-ubuntu-18.04.tar.gz \
-    -O ${TOOLCHAIN_VERSION}-binaries-ubuntu-18.04.tar.gz \
-    && tar xzvf ${TOOLCHAIN_VERSION}-binaries-ubuntu-18.04.tar.gz -C /opt
+RUN wget -q https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/${TOOLCHAIN_VERSION}/${TOOLCHAIN_VERSION}-binaries-ubuntu-18.04-amd64.tar.gz \
+    -O ${TOOLCHAIN_VERSION}-binaries-ubuntu-18.04-amd64.tar.gz \
+    && tar xzvf ${TOOLCHAIN_VERSION}-binaries-ubuntu-18.04-amd64.tar.gz -C /opt
 
 ENTRYPOINT ["sleep", "infinity"]

release/package/ubuntu-20.04/Dockerfile

@@ -10,8 +10,8 @@ RUN apt update && apt install -y \
 # Do NOT be smart here and clean the cache because the container is used in the
 # stateful context.
 
-RUN wget -q https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/${TOOLCHAIN_VERSION}/${TOOLCHAIN_VERSION}-binaries-ubuntu-20.04.tar.gz \
-    -O ${TOOLCHAIN_VERSION}-binaries-ubuntu-20.04.tar.gz \
-    && tar xzvf ${TOOLCHAIN_VERSION}-binaries-ubuntu-20.04.tar.gz -C /opt
+RUN wget -q https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/${TOOLCHAIN_VERSION}/${TOOLCHAIN_VERSION}-binaries-ubuntu-20.04-amd64.tar.gz \
+    -O ${TOOLCHAIN_VERSION}-binaries-ubuntu-20.04-amd64.tar.gz \
+    && tar xzvf ${TOOLCHAIN_VERSION}-binaries-ubuntu-20.04-amd64.tar.gz -C /opt
 
 ENTRYPOINT ["sleep", "infinity"]

release/package/ubuntu-22.04/Dockerfile

@@ -0,0 +1,17 @@
+FROM ubuntu:22.04
+
+ARG TOOLCHAIN_VERSION
+
+# Stops tzdata interactive configuration.
+ENV DEBIAN_FRONTEND=noninteractive
+
+RUN apt update && apt install -y \
+    ca-certificates wget git
+# Do NOT be smart here and clean the cache because the container is used in the
+# stateful context.
+
+RUN wget -q https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/${TOOLCHAIN_VERSION}/${TOOLCHAIN_VERSION}-binaries-ubuntu-22.04-amd64.tar.gz \
+    -O ${TOOLCHAIN_VERSION}-binaries-ubuntu-22.04-amd64.tar.gz \
+    && tar xzvf ${TOOLCHAIN_VERSION}-binaries-ubuntu-22.04-amd64.tar.gz -C /opt
+
+ENTRYPOINT ["sleep", "infinity"]

src/CMakeLists.txt

@@ -1,7 +1,6 @@
 # CMake configuration for the main memgraph library and executable
 
 # add memgraph sub libraries, ordered by dependency
-add_subdirectory(interface)
 add_subdirectory(lisp)
 add_subdirectory(utils)
 add_subdirectory(requests)
@@ -38,7 +37,7 @@ set(mg_single_node_v2_sources
 )
 
 set(mg_single_node_v2_libs stdc++fs Threads::Threads
-    telemetry_lib mg-query mg-communication mg-memory mg-utils mg-auth mg-license mg-settings mg-interface-storage-cpp2)
+    telemetry_lib mg-query mg-communication mg-memory mg-utils mg-auth mg-license mg-settings)
 if (MG_ENTERPRISE)
   # These are enterprise subsystems
   set(mg_single_node_v2_libs ${mg_single_node_v2_libs} mg-audit)

src/communication/bolt/v1/session.hpp

@@ -1,4 +1,4 @@
-// Copyright 2021 Memgraph Ltd.
+// Copyright 2022 Memgraph Ltd.
 //
 // Use of this software is governed by the Business Source License
 // included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source

src/communication/bolt/v1/states/error.hpp

@@ -1,4 +1,4 @@
-// Copyright 2021 Memgraph Ltd.
+// Copyright 2022 Memgraph Ltd.
 //
 // Use of this software is governed by the Business Source License
 // included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source

src/communication/bolt/v1/states/executing.hpp

@@ -1,4 +1,4 @@
-// Copyright 2021 Memgraph Ltd.
+// Copyright 2022 Memgraph Ltd.
 //
 // Use of this software is governed by the Business Source License
 // included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source

src/communication/bolt/v1/states/handshake.hpp

@@ -1,4 +1,4 @@
-// Copyright 2021 Memgraph Ltd.
+// Copyright 2022 Memgraph Ltd.
 //
 // Use of this software is governed by the Business Source License
 // included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source

src/communication/bolt/v1/states/init.hpp

@@ -1,4 +1,4 @@
-// Copyright 2021 Memgraph Ltd.
+// Copyright 2022 Memgraph Ltd.
 //
 // Use of this software is governed by the Business Source License
 // included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source

src/communication/v2/session.hpp

@@ -105,9 +105,16 @@ class WebsocketSession : public std::enable_shared_from_this<WebsocketSession<TS
     boost::asio::socket_base::keep_alive option(true);
 
     // Set a decorator to change the Server of the handshake
-    ws_.set_option(boost::beast::websocket::stream_base::decorator([](boost::beast::websocket::response_type &res) {
+    ws_.set_option(boost::beast::websocket::stream_base::decorator([&req](boost::beast::websocket::response_type &res) {
       res.set(boost::beast::http::field::server, std::string("Memgraph Bolt WS"));
-      res.set(boost::beast::http::field::sec_websocket_protocol, "binary");
+
+      // We need to do this to support WASM clients, which explicitly send this flag
+      // in their upgrade request
+      // Neo4j client breaks when this flag is sent
+      if (const auto secondary_protocol = req.base().find(boost::beast::http::field::sec_websocket_protocol);
+          secondary_protocol != res.base().end() && secondary_protocol->value() == "binary") {
+        res.set(boost::beast::http::field::sec_websocket_protocol, "binary");
+      }
     }));
     ws_.binary(true);
 
@@ -162,7 +169,7 @@ class WebsocketSession : public std::enable_shared_from_this<WebsocketSession<TS
         boost::asio::bind_executor(strand_, std::bind_front(&WebsocketSession::OnRead, shared_from_this())));
   }
 
-  void OnRead(const boost::system::error_code &ec, [[maybe_unused]] const size_t bytes_transferred) {
+  void OnRead(const boost::system::error_code &ec, const size_t bytes_transferred) {
     // This indicates that the WebsocketSession was closed
     if (ec == boost::beast::websocket::error::closed) {
       return;
@@ -322,7 +329,8 @@ class Session final : public std::enable_shared_from_this<Session<TSession, TSes
       socket.lowest_layer().non_blocking(false);
     });
     timeout_timer_.expires_at(boost::asio::steady_timer::time_point::max());
-    spdlog::info("Accepted a connection from {}:", service_name_, remote_endpoint_.address(), remote_endpoint_.port());
+    spdlog::info("Accepted a connection from {}: {}:{}", service_name_, remote_endpoint_.address(),
+                 remote_endpoint_.port());
   }
 
   void DoRead() {

src/integrations/constants.hpp

@@ -17,6 +17,7 @@
 namespace memgraph::integrations {
 
 inline constexpr int64_t kDefaultCheckBatchLimit{1};
+inline constexpr int64_t kMinimumStartBatchLimit{1};
 inline constexpr std::chrono::milliseconds kDefaultCheckTimeout{30000};
 inline constexpr std::chrono::milliseconds kMinimumInterval{1};
 inline constexpr int64_t kMinimumSize{1};

src/integrations/kafka/consumer.cpp

@@ -74,6 +74,36 @@ utils::BasicResult<std::string, std::vector<Message>> GetBatch(RdKafka::KafkaCon
 
   return std::move(batch);
 }
+
+void CheckAndDestroyLastAssignmentIfNeeded(RdKafka::KafkaConsumer &consumer, const ConsumerInfo &info,
+                                           std::vector<RdKafka::TopicPartition *> &last_assignment) {
+  if (!last_assignment.empty()) {
+    if (const auto err = consumer.assign(last_assignment); err != RdKafka::ERR_NO_ERROR) {
+      throw ConsumerStartFailedException(info.consumer_name,
+                                         fmt::format("Couldn't restore commited offsets: '{}'", RdKafka::err2str(err)));
+    }
+    RdKafka::TopicPartition::destroy(last_assignment);
+  }
+}
+
+void TryToConsumeBatch(RdKafka::KafkaConsumer &consumer, const ConsumerInfo &info,
+                       const ConsumerFunction &consumer_function, const std::vector<Message> &batch) {
+  consumer_function(batch);
+  std::vector<RdKafka::TopicPartition *> partitions;
+  utils::OnScopeExit clear_partitions([&]() { RdKafka::TopicPartition::destroy(partitions); });
+
+  if (const auto err = consumer.assignment(partitions); err != RdKafka::ERR_NO_ERROR) {
+    throw ConsumerCommitFailedException(
+        info.consumer_name, fmt::format("Couldn't get assignment to commit offsets: {}", RdKafka::err2str(err)));
+  }
+  if (const auto err = consumer.position(partitions); err != RdKafka::ERR_NO_ERROR) {
+    throw ConsumerCommitFailedException(info.consumer_name,
+                                        fmt::format("Couldn't get offsets from librdkafka {}", RdKafka::err2str(err)));
+  }
+  if (const auto err = consumer.commitSync(partitions); err != RdKafka::ERR_NO_ERROR) {
+    throw ConsumerCommitFailedException(info.consumer_name, RdKafka::err2str(err));
+  }
+}
 }  // namespace
 
 Message::Message(std::unique_ptr<RdKafka::Message> &&message) : message_{std::move(message)} {
@@ -221,10 +251,21 @@ void Consumer::Start() {
   StartConsuming();
 }
 
-void Consumer::StartIfStopped() {
-  if (!is_running_) {
-    StartConsuming();
+void Consumer::StartWithLimit(const uint64_t limit_batches, std::optional<std::chrono::milliseconds> timeout) const {
+  if (is_running_) {
+    throw ConsumerRunningException(info_.consumer_name);
   }
+  if (limit_batches < kMinimumStartBatchLimit) {
+    throw ConsumerStartFailedException(
+        info_.consumer_name, fmt::format("Batch limit has to be greater than or equal to {}", kMinimumStartBatchLimit));
+  }
+  if (timeout.value_or(kMinimumInterval) < kMinimumInterval) {
+    throw ConsumerStartFailedException(
+        info_.consumer_name,
+        fmt::format("Timeout has to be greater than or equal to {} milliseconds", kMinimumInterval.count()));
+  }
+
+  StartConsumingWithLimit(limit_batches, timeout);
 }
 
 void Consumer::Stop() {
@@ -244,7 +285,7 @@ void Consumer::StopIfRunning() {
   }
 }
 
-void Consumer::Check(std::optional<std::chrono::milliseconds> timeout, std::optional<int64_t> limit_batches,
+void Consumer::Check(std::optional<std::chrono::milliseconds> timeout, std::optional<uint64_t> limit_batches,
                      const ConsumerFunction &check_consumer_function) const {
   // NOLINTNEXTLINE (modernize-use-nullptr)
   if (timeout.value_or(kMinimumInterval) < kMinimumInterval) {
@@ -344,13 +385,7 @@ void Consumer::StartConsuming() {
 
   is_running_.store(true);
 
-  if (!last_assignment_.empty()) {
-    if (const auto err = consumer_->assign(last_assignment_); err != RdKafka::ERR_NO_ERROR) {
-      throw ConsumerStartFailedException(info_.consumer_name,
-                                         fmt::format("Couldn't restore commited offsets: '{}'", RdKafka::err2str(err)));
-    }
-    RdKafka::TopicPartition::destroy(last_assignment_);
-  }
+  CheckAndDestroyLastAssignmentIfNeeded(*consumer_, info_, last_assignment_);
 
   thread_ = std::thread([this] {
     static constexpr auto kMaxThreadNameSize = utils::GetMaxThreadNameSize();
@@ -361,33 +396,18 @@ void Consumer::StartConsuming() {
     while (is_running_) {
       auto maybe_batch = GetBatch(*consumer_, info_, is_running_);
       if (maybe_batch.HasError()) {
-        spdlog::warn("Error happened in consumer {} while fetching messages: {}!", info_.consumer_name,
-                     maybe_batch.GetError());
-        break;
+        throw ConsumerReadMessagesFailedException(info_.consumer_name, maybe_batch.GetError());
       }
       const auto &batch = maybe_batch.GetValue();
 
-      if (batch.empty()) continue;
+      if (batch.empty()) {
+        continue;
+      }
 
       spdlog::info("Kafka consumer {} is processing a batch", info_.consumer_name);
 
       try {
-        consumer_function_(batch);
-        std::vector<RdKafka::TopicPartition *> partitions;
-        utils::OnScopeExit clear_partitions([&]() { RdKafka::TopicPartition::destroy(partitions); });
-
-        if (const auto err = consumer_->assignment(partitions); err != RdKafka::ERR_NO_ERROR) {
-          throw ConsumerCheckFailedException(
-              info_.consumer_name, fmt::format("Couldn't get assignment to commit offsets: {}", RdKafka::err2str(err)));
-        }
-        if (const auto err = consumer_->position(partitions); err != RdKafka::ERR_NO_ERROR) {
-          throw ConsumerCheckFailedException(
-              info_.consumer_name, fmt::format("Couldn't get offsets from librdkafka {}", RdKafka::err2str(err)));
-        }
-        if (const auto err = consumer_->commitSync(partitions); err != RdKafka::ERR_NO_ERROR) {
-          spdlog::warn("Committing offset of consumer {} failed: {}", info_.consumer_name, RdKafka::err2str(err));
-          break;
-        }
+        TryToConsumeBatch(*consumer_, info_, consumer_function_, batch);
       } catch (const std::exception &e) {
         spdlog::warn("Error happened in consumer {} while processing a batch: {}!", info_.consumer_name, e.what());
         break;
@@ -398,6 +418,44 @@ void Consumer::StartConsuming() {
   });
 }
 
+void Consumer::StartConsumingWithLimit(uint64_t limit_batches, std::optional<std::chrono::milliseconds> timeout) const {
+  MG_ASSERT(!is_running_, "Cannot start already running consumer!");
+
+  if (is_running_.exchange(true)) {
+    throw ConsumerRunningException(info_.consumer_name);
+  }
+  utils::OnScopeExit restore_is_running([this] { is_running_.store(false); });
+
+  CheckAndDestroyLastAssignmentIfNeeded(*consumer_, info_, last_assignment_);
+
+  const auto timeout_to_use = timeout.value_or(kDefaultCheckTimeout);
+  const auto start = std::chrono::steady_clock::now();
+
+  for (uint64_t batch_count = 0; batch_count < limit_batches;) {
+    const auto now = std::chrono::steady_clock::now();
+    if (now - start >= timeout_to_use) {
+      throw ConsumerStartFailedException(info_.consumer_name, "Timeout reached");
+    }
+
+    const auto maybe_batch = GetBatch(*consumer_, info_, is_running_);
+    if (maybe_batch.HasError()) {
+      throw ConsumerReadMessagesFailedException(info_.consumer_name, maybe_batch.GetError());
+    }
+    const auto &batch = maybe_batch.GetValue();
+
+    if (batch.empty()) {
+      continue;
+    }
+    ++batch_count;
+
+    spdlog::info("Kafka consumer {} is processing a batch", info_.consumer_name);
+
+    TryToConsumeBatch(*consumer_, info_, consumer_function_, batch);
+
+    spdlog::info("Kafka consumer {} finished processing", info_.consumer_name);
+  }
+}
+
 void Consumer::StopConsuming() {
   is_running_.store(false);
   if (thread_.joinable()) thread_.join();

src/integrations/kafka/consumer.hpp

@@ -113,11 +113,19 @@ class Consumer final : public RdKafka::EventCb {
   /// This method will start a new thread which will poll all the topics for messages.
   ///
   /// @throws ConsumerRunningException if the consumer is already running
+  /// @throws ConsumerStartFailedException if the commited offsets cannot be restored
   void Start();
 
-  /// Starts consuming messages if it is not started already.
+  /// Starts consuming messages.
   ///
-  void StartIfStopped();
+  /// This method will start a new thread which will poll all the topics for messages.
+  ///
+  /// @param limit_batches the consumer will only consume the given number of batches.
+  /// @param timeout the maximum duration during which the command should run.
+  ///
+  /// @throws ConsumerRunningException if the consumer is already running
+  /// @throws ConsumerStartFailedException if the commited offsets cannot be restored
+  void StartWithLimit(uint64_t limit_batches, std::optional<std::chrono::milliseconds> timeout) const;
 
   /// Stops consuming messages.
   ///
@@ -136,9 +144,9 @@ class Consumer final : public RdKafka::EventCb {
   ///                      used.
   /// @param check_consumer_function a function to feed the received messages in, only used during this dry-run.
   ///
-  /// @throws ConsumerRunningException if the consumer is alredy running.
+  /// @throws ConsumerRunningException if the consumer is already running.
   /// @throws ConsumerCheckFailedException if check isn't successful.
-  void Check(std::optional<std::chrono::milliseconds> timeout, std::optional<int64_t> limit_batches,
+  void Check(std::optional<std::chrono::milliseconds> timeout, std::optional<uint64_t> limit_batches,
              const ConsumerFunction &check_consumer_function) const;
 
   /// Returns true if the consumer is actively consuming messages.
@@ -157,6 +165,7 @@ class Consumer final : public RdKafka::EventCb {
   void event_cb(RdKafka::Event &event) override;
 
   void StartConsuming();
+  void StartConsumingWithLimit(uint64_t limit_batches, std::optional<std::chrono::milliseconds> timeout) const;
 
   void StopConsuming();
 
@@ -178,7 +187,6 @@ class Consumer final : public RdKafka::EventCb {
   ConsumerFunction consumer_function_;
   mutable std::atomic<bool> is_running_{false};
   mutable std::vector<RdKafka::TopicPartition *> last_assignment_;  // Protected by is_running_
-  std::optional<int64_t> limit_batches_{std::nullopt};
   std::unique_ptr<RdKafka::KafkaConsumer, std::function<void(RdKafka::KafkaConsumer *)>> consumer_;
   std::thread thread_;
   ConsumerRebalanceCb cb_;

src/integrations/kafka/exceptions.hpp

@@ -64,4 +64,16 @@ class TopicNotFoundException : public KafkaStreamException {
   TopicNotFoundException(const std::string_view consumer_name, const std::string_view topic_name)
       : KafkaStreamException("Kafka consumer {} cannot find topic {}", consumer_name, topic_name) {}
 };
+
+class ConsumerCommitFailedException : public KafkaStreamException {
+ public:
+  ConsumerCommitFailedException(const std::string_view consumer_name, const std::string_view error)
+      : KafkaStreamException("Committing offset of consumer {} failed: {}", consumer_name, error) {}
+};
+
+class ConsumerReadMessagesFailedException : public KafkaStreamException {
+ public:
+  ConsumerReadMessagesFailedException(const std::string_view consumer_name, const std::string_view error)
+      : KafkaStreamException("Error happened in consumer {} while fetching messages: {}", consumer_name, error) {}
+};
 }  // namespace memgraph::integrations::kafka

src/integrations/pulsar/consumer.cpp

@@ -11,13 +11,14 @@
 
 #include "integrations/pulsar/consumer.hpp"
 
+#include <algorithm>
+#include <chrono>
+#include <thread>
+
 #include <fmt/format.h>
 #include <pulsar/Client.h>
 #include <pulsar/InitialPosition.h>
 
-#include <chrono>
-#include <thread>
-
 #include "integrations/constants.hpp"
 #include "integrations/pulsar/exceptions.hpp"
 #include "utils/concepts.hpp"
@@ -33,6 +34,10 @@ namespace {
 template <typename T>
 concept PulsarConsumer = utils::SameAsAnyOf<T, pulsar_client::Consumer, pulsar_client::Reader>;
 
+template <typename TFunc>
+concept PulsarMessageGetter =
+    std::same_as<const pulsar_client::Message &, std::invoke_result_t<TFunc, const Message &>>;
+
 pulsar_client::Result ConsumeMessage(pulsar_client::Consumer &consumer, pulsar_client::Message &message,
                                      int remaining_timeout_in_ms) {
   return consumer.receive(message, remaining_timeout_in_ms);
@@ -97,6 +102,26 @@ pulsar_client::Client CreateClient(const std::string &service_url) {
   conf.setLogger(new SpdlogLoggerFactory);
   return {service_url, conf};
 }
+
+template <PulsarConsumer TConsumer, PulsarMessageGetter TPulsarMessageGetter>
+void TryToConsumeBatch(TConsumer &consumer, const ConsumerInfo &info, const ConsumerFunction &consumer_function,
+                       pulsar_client::MessageId &last_message_id, const std::vector<Message> &batch,
+                       const TPulsarMessageGetter &message_getter) {
+  consumer_function(batch);
+
+  auto has_message_failed = [&consumer, &info, &last_message_id, &message_getter](const auto &message) {
+    if (const auto result = consumer.acknowledge(message_getter(message)); result != pulsar_client::ResultOk) {
+      spdlog::warn("Acknowledging a message of consumer {} failed: {}", info.consumer_name, result);
+      return true;
+    }
+    last_message_id = message_getter(message).getMessageId();
+    return false;
+  };
+
+  if (std::ranges::any_of(batch, has_message_failed)) {
+    throw ConsumerAcknowledgeMessagesFailedException(info.consumer_name);
+  }
+}
 }  // namespace
 
 Message::Message(pulsar_client::Message &&message) : message_{std::move(message)} {}
@@ -137,6 +162,24 @@ void Consumer::Start() {
   StartConsuming();
 }
 
+void Consumer::StartWithLimit(const uint64_t limit_batches,
+                              const std::optional<std::chrono::milliseconds> timeout) const {
+  if (is_running_) {
+    throw ConsumerRunningException(info_.consumer_name);
+  }
+  if (limit_batches < kMinimumStartBatchLimit) {
+    throw ConsumerStartFailedException(
+        info_.consumer_name, fmt::format("Batch limit has to be greater than or equal to {}", kMinimumStartBatchLimit));
+  }
+  if (timeout.value_or(kMinimumInterval) < kMinimumInterval) {
+    throw ConsumerStartFailedException(
+        info_.consumer_name,
+        fmt::format("Timeout has to be greater than or equal to {} milliseconds", kMinimumInterval.count()));
+  }
+
+  StartConsumingWithLimit(limit_batches, timeout);
+}
+
 void Consumer::Stop() {
   if (!is_running_) {
     throw ConsumerStoppedException(info_.consumer_name);
@@ -154,7 +197,7 @@ void Consumer::StopIfRunning() {
   }
 }
 
-void Consumer::Check(std::optional<std::chrono::milliseconds> timeout, std::optional<int64_t> limit_batches,
+void Consumer::Check(std::optional<std::chrono::milliseconds> timeout, std::optional<uint64_t> limit_batches,
                      const ConsumerFunction &check_consumer_function) const {
   // NOLINTNEXTLINE (modernize-use-nullptr)
   if (timeout.value_or(kMinimumInterval) < kMinimumInterval) {
@@ -240,9 +283,7 @@ void Consumer::StartConsuming() {
       auto maybe_batch = GetBatch(consumer_, info_, is_running_, last_message_id_);
 
       if (maybe_batch.HasError()) {
-        spdlog::warn("Error happened in consumer {} while fetching messages: {}!", info_.consumer_name,
-                     maybe_batch.GetError());
-        break;
+        throw ConsumerReadMessagesFailedException(info_.consumer_name, maybe_batch.GetError());
       }
 
       const auto &batch = maybe_batch.GetValue();
@@ -254,18 +295,8 @@ void Consumer::StartConsuming() {
       spdlog::info("Pulsar consumer {} is processing a batch", info_.consumer_name);
 
       try {
-        consumer_function_(batch);
-
-        if (std::any_of(batch.begin(), batch.end(), [&](const auto &message) {
-              if (const auto result = consumer_.acknowledge(message.message_); result != pulsar_client::ResultOk) {
-                spdlog::warn("Acknowledging a message of consumer {} failed: {}", info_.consumer_name, result);
-                return true;
-              }
-              last_message_id_ = message.message_.getMessageId();
-              return false;
-            })) {
-          break;
-        }
+        TryToConsumeBatch(consumer_, info_, consumer_function_, last_message_id_, batch,
+                          [&](const Message &message) -> const pulsar_client::Message & { return message.message_; });
       } catch (const std::exception &e) {
         spdlog::warn("Error happened in consumer {} while processing a batch: {}!", info_.consumer_name, e.what());
         break;
@@ -277,6 +308,43 @@ void Consumer::StartConsuming() {
   });
 }
 
+void Consumer::StartConsumingWithLimit(uint64_t limit_batches, std::optional<std::chrono::milliseconds> timeout) const {
+  if (is_running_.exchange(true)) {
+    throw ConsumerRunningException(info_.consumer_name);
+  }
+  utils::OnScopeExit restore_is_running([this] { is_running_.store(false); });
+
+  const auto timeout_to_use = timeout.value_or(kDefaultCheckTimeout);
+  const auto start = std::chrono::steady_clock::now();
+
+  for (uint64_t batch_count = 0; batch_count < limit_batches;) {
+    const auto now = std::chrono::steady_clock::now();
+    if (now - start >= timeout_to_use) {
+      throw ConsumerCheckFailedException(info_.consumer_name, "Timeout reached");
+    }
+
+    const auto maybe_batch = GetBatch(consumer_, info_, is_running_, last_message_id_);
+
+    if (maybe_batch.HasError()) {
+      throw ConsumerReadMessagesFailedException(info_.consumer_name, maybe_batch.GetError());
+    }
+
+    const auto &batch = maybe_batch.GetValue();
+
+    if (batch.empty()) {
+      continue;
+    }
+    ++batch_count;
+
+    spdlog::info("Pulsar consumer {} is processing a batch", info_.consumer_name);
+
+    TryToConsumeBatch(consumer_, info_, consumer_function_, last_message_id_, batch,
+                      [](const Message &message) -> const pulsar_client::Message & { return message.message_; });
+
+    spdlog::info("Pulsar consumer {} finished processing", info_.consumer_name);
+  }
+}
+
 void Consumer::StopConsuming() {
   is_running_.store(false);
   if (thread_.joinable()) {

src/integrations/pulsar/consumer.hpp

@@ -58,25 +58,27 @@ class Consumer final {
 
   bool IsRunning() const;
   void Start();
+  void StartWithLimit(uint64_t limit_batches, std::optional<std::chrono::milliseconds> timeout) const;
   void Stop();
   void StopIfRunning();
 
-  void Check(std::optional<std::chrono::milliseconds> timeout, std::optional<int64_t> limit_batches,
+  void Check(std::optional<std::chrono::milliseconds> timeout, std::optional<uint64_t> limit_batches,
              const ConsumerFunction &check_consumer_function) const;
 
   const ConsumerInfo &Info() const;
 
  private:
   void StartConsuming();
+  void StartConsumingWithLimit(uint64_t limit_batches, std::optional<std::chrono::milliseconds> timeout) const;
   void StopConsuming();
 
   ConsumerInfo info_;
   mutable pulsar_client::Client client_;
-  pulsar_client::Consumer consumer_;
+  mutable pulsar_client::Consumer consumer_;
   ConsumerFunction consumer_function_;
 
   mutable std::atomic<bool> is_running_{false};
-  pulsar_client::MessageId last_message_id_{pulsar_client::MessageId::earliest()};
+  mutable pulsar_client::MessageId last_message_id_{pulsar_client::MessageId::earliest()};  // Protected by is_running_
   std::thread thread_;
 };
 }  // namespace memgraph::integrations::pulsar

src/integrations/pulsar/exceptions.hpp

@@ -55,4 +55,16 @@ class TopicNotFoundException : public PulsarStreamException {
   TopicNotFoundException(const std::string &consumer_name, const std::string &topic_name)
       : PulsarStreamException("Pulsar consumer {} cannot find topic {}", consumer_name, topic_name) {}
 };
+
+class ConsumerReadMessagesFailedException : public PulsarStreamException {
+ public:
+  ConsumerReadMessagesFailedException(const std::string_view consumer_name, const std::string_view error)
+      : PulsarStreamException("Error happened in consumer {} while fetching messages: {}", consumer_name, error) {}
+};
+
+class ConsumerAcknowledgeMessagesFailedException : public PulsarStreamException {
+ public:
+  explicit ConsumerAcknowledgeMessagesFailedException(const std::string_view consumer_name)
+      : PulsarStreamException("Acknowledging a message of consumer {} has failed!", consumer_name) {}
+};
 }  // namespace memgraph::integrations::pulsar

src/interface/.gitignore

@@ -1 +0,0 @@
-gen-cpp2

src/interface/CMakeLists.txt

@@ -1,27 +0,0 @@
-include(MgThrift)
-
-set(MG_INTERFACE_PATH ${CMAKE_CURRENT_SOURCE_DIR})
-
-mg_thrift_library(
-  "storage" #file_name
-  "Storage" #services
-  "${MG_INTERFACE_PATH}" #file_path
-  "${MG_INTERFACE_PATH}" #output_path
-  "interface" #include_prefix
-)
-
-mg_thrift_library(
-  "meta" #file_name
-  "Meta" #services
-  "${MG_INTERFACE_PATH}" #file_path
-  "${MG_INTERFACE_PATH}" #output_path
-  "interface" #include_prefix
-)
-
-mg_thrift_library(
-  "trial" #file_name
-  "PingPong" #services
-  "${MG_INTERFACE_PATH}" #file_path
-  "${MG_INTERFACE_PATH}" #output_path
-  "interface" #include_prefix
-)

src/interface/meta.thrift

@@ -1,74 +0,0 @@
-namespace cpp2 interface.meta
-
-typedef i64 LabelId
-typedef i64 IndexId
-
-struct Result {
-    1: bool success;
-}
-
-struct CreatePrimaryLabelRequest {
-    1: binary name;
-    2: list<binary> primary_keys;
-}
-
-struct CreateLabelResponse {
-    1: Result result;
-    2: LabelId label_id;
-}
-
-struct GetLabelInfosRequest {
-    //  The empty list means return all of the label infos
-    1: list<binary> label_names;
-}
-
-struct LabelInfo {
-    1: binary name;
-    2: LabelId label_id;
-    3: list<binary> primary_keys;
-}
-
-struct GetLabelInfoResponse {
-    1: Result result;
-    2: LabelInfo label_info;
-}
-
-struct GetLabelInfosResponse {
-    1: Result result;
-    2: list<LabelInfo> label_infos;
-}
-
-struct CreateIndexRequest {
-    1: LabelId label_id;
-    2: list<binary> property_names;
-}
-
-struct CreateIndexResponse {
-    1: Result result;
-    2: IndexId index_id;
-}
-
-struct IndexInfo {
-    1: LabelId label_id;
-    2: list<binary> property_names;
-}
-
-struct GetIndexInfosResponse {
-    1: Result result;
-    2: list<IndexInfo> index_infos;
-}
-
-
-service Meta {
-    CreateLabelResponse createPrimaryLabel(1: CreatePrimaryLabelRequest req);
-    CreateLabelResponse createSecondaryLabel(1: binary label_name);
-    Result dropLabel(1: binary label_name);
-    GetLabelInfoResponse getLabelInfo(1:binary label_name);
-    GetLabelInfosResponse getLabelInfos(1: list<binary> label_names);
-
-    CreateIndexResponse createIndex(1: CreateIndexRequest req);
-    // Don't have index names, and the label doesn't identify the index uniquely, therefore
-    Result dropIndex(1: IndexId index_id);
-    GetIndexInfosResponse getIndexInfos();
-    GetIndexInfosResponse getIndexInfosForLabel(1: LabelId label_id);
-}

src/interface/storage.thrift

@@ -1,273 +0,0 @@
-namespace cpp2 interface.storage
-// https://stackoverflow.com/a/34234874/6639989
-
-cpp_include "storage/v2/view.hpp"
-
-typedef i64 VertexId
-typedef i64 Gid
-
-// TODO(antaljanosbenjamin): Use this after introducing 128 bit vertex ids
-// struct VertexId {
-//     1: i64 upper_half;
-//     2: i64 lower_half;
-// }
-
-struct Label {
-    1: i64 id;
-}
-
-struct EdgeType {
-    1: binary name;
-}
-
-struct EdgeId {
-    1: VertexId src;
-    // QUESTION(antaljanosbenjamin): is it okay to have vertex based (edge id = vertex id + edge id inside vertex)?
-    2: Gid gid;
-}
-
-struct Date {
-    1: i16 year;
-    2: byte month;
-    3: byte day;
-}
-
-struct LocalTime {
-    1: byte hour;
-    2: byte minute;
-    3: byte second;
-    4: i16 millisecond;
-    5: i16 microsecond;
-}
-
-struct LocalDateTime {
-    1: Date date;
-    2: LocalTime local_time;
-}
-
-struct Duration {
-    1: i64 milliseconds;
-}
-
-union Value {
-    1: Null null_v;
-    2: bool bool_v;
-    3: i64 int_v;
-    4: double double_v;
-    5: binary string_v;
-    6: list<Value> list_v;
-    7: map<binary, Value> (cpp.template = "std::unordered_map") map_v (cpp2.ref_type = "unique");
-    8: Vertex vertex_v (cpp2.ref_type = "unique");
-    9: Edge edge_v (cpp2.ref_type = "unique");
-    10: Path path_v (cpp2.ref_type = "unique");
-    11: Date date_v;
-    12: LocalTime local_time_v;
-    13: LocalDateTime local_date_time_v;
-    14: Duration duration_v;
-}
-
-struct Null {
-}
-
-struct Vertex {
-    1: VertexId id;
-    // TODO(antaljanosbenjamin): Change to sperate primary and secondary labels when schema is implemented
-    2: list<Label> labels;
-}
-
-struct Edge {
-    1: VertexId src;
-    2: VertexId dst;
-    3: EdgeType type;
-}
-
-struct PathPart {
-    1: Vertex dst;
-    2: Edge edge;
-}
-
-struct Path {
-    1: Vertex src;
-    2: list<PathPart> parts;
-}
-
-struct ValuesMap {
-    1: map<i64, Value> (cpp.template = "std::unordered_map") values_map;
-}
-
-struct MappedValues {
-    1: list<ValuesMap> properties;
-}
-
-struct ListedValues {
-    1: list<list<Value>> properties;
-}
-
-union Values {
-    // This struct is necessary because depending on the request the response
-    // has two different formats:
-    // 1. When the request specifies the returned properties, then they are
-    //    returned in that order, therefore no extra mapping is necessary.
-    // 2. When the request doesn't specify the returned properties, then all
-    //    of the properties are returned. In this case the `mapped` field is
-    //    used. To extract the <key,value> pairs from this struct the
-    //    mapping of i64 -> property name has to be used.
-    1: ListedValues listed;
-    2: MappedValues mapped;
-}
-
-struct Expression {
-    1: binary alias;
-    2: binary expression;
-}
-
-struct Filter {
-    1: binary filter_expression;
-}
-
-enum OrderingDirection {
-    ASCENDING = 1;
-    DESCENDING = 2;
-}
-
-struct OrderBy {
-    1: Expression expression;
-    2: OrderingDirection direction;
-}
-
-struct Result {
-    // Just placeholder data for now
-    1: bool success;
-}
-
-enum View {
-    OLD = 0,
-    NEW = 1
-}  (cpp.enum_strict, cpp.type = "memgraph::storage::View")
-
-struct ScanVerticesRequest {
-    1: i64 transaction_id;
-    2: optional i64 start_id;
-    // Special values are accepted:
-    // * __mg__id (Vertex, but without labels)
-    // * __mg__labels (Vertex, but without the id)
-    // If both of them is specified, then it will result in a single, fully populated vertex
-    // QUESTION(antaljanosbenjamin): Does the `__mg__labels` is necessary? What about passing the `labels` function
-    //                               as an expression? Maybe it is an optimization. For communicating the vertex id
-    //                               the Vertex struct is really handy.
-    3: optional list<binary> props_to_return;
-    4: list<Expression> expressions;
-    5: optional i64 limit;
-    6: View view;
-    7: optional Filter filter;
-}
-
-struct ScanVerticesResponse {
-    1: Result result;
-    2: Values values;
-    3: optional map<i64, binary> (cpp.template = "std::unordered_map") property_name_map;
-    // contains the next start_id if there is any
-    4: optional VertexId next_start_id;
-}
-
-union VertexOrEdgeIds {
-    1: list<VertexId> vertex_ids;
-    2: list<EdgeId> edge_ids;
-}
-
-struct GetPropertiesRequest {
-    1:  i64 transaction_id;
-    2:  VertexOrEdgeIds vertex_or_edge_ids;
-    3:  list<binary> property_names;
-    4:  list<Expression> expressions;
-    5:  bool only_unique = false;
-    6:  optional list<OrderBy> order_by;
-    7:  optional i64 limit;
-    8:  optional Filter filter;
-}
-
-struct GetPropertiesResponse {
-    1: Values values;
-    2: optional map<i64, binary> (cpp.template = "std::unordered_map") property_name_map;
-}
-
-enum EdgeDirection {
-    OUT = 1;
-    IN = 2;
-    BOTH = 3;
-}
-
-struct ExpandOneRequest {
-    1:  i64 transaction_id;
-    2:  list<VertexId> src_vertices;
-    3:  list<EdgeType> edge_types;
-    4:  EdgeDirection direction;
-    5:  bool only_unique_neighbor_rows = false;
-    //  The empty optional means return all of the properties, while an empty
-    //  list means do not return any properties
-    //  TODO(antaljanosbenjamin): All of the special values should be communicated through a single vertex object
-    //                            after schema is implemented
-    //  Special values are accepted:
-    //  * __mg__labels
-    6:  optional list<binary> src_vertex_properties;
-    //  TODO(antaljanosbenjamin): All of the special values should be communicated through a single vertex object
-    //                            after schema is implemented
-    //  Special values are accepted:
-    //  * __mg__dst_id (Vertex, but without labels)
-    //  * __mg__type (binary)
-    7:  optional list<binary> edge_properties;
-    //  QUESTION(antaljanosbenjamin): Maybe also add possibility to expressions evaluated on the source vertex?
-    //  List of expressions evaluated on edges
-    8:  list<Expression> expressions;
-    9:  optional list<OrderBy> order_by;
-    10:  optional i64 limit;
-    11: optional Filter filter;
-}
-
-struct ExpandOneResultRow {
-    // NOTE: This struct could be a single Values with columns something like this:
-    // src_vertex(Vertex), vertex_prop1(Value), vertex_prop2(Value), edges(list<Value>)
-    // where edges might be a list of:
-    // 1. list<Value> if only a defined list of edge properties are returned
-    // 2. map<binary, Value> if all of the edge properties are returned
-    // The drawback of this is currently the key of the map is always interpreted as a string in Value, not as an
-    // integer, which should be in case of mapped properties.
-    1: Vertex src_vertex;
-    2: optional Values src_vertex_properties;
-    3: Values edges;
-}
-
-struct ExpandOneResponse {
-    // This approach might not suit the expand with per shard parrallelization,
-    // because the property_name_map has to be accessed from multiple threads
-    // in order to avoid duplicated keys (two threads might map the same
-    // property with different numbers) and multiple passes (to unify the
-    // mapping amond result returned from different shards).
-    1: list<ExpandOneResultRow> result;
-    2: optional map<i64, binary>  (cpp.template = "std::unordered_map") property_name_map;
-}
-
-struct NewVertex {
-    1: list<i64> label_ids;
-    2: map<i64, Value> properties;
-}
-
-struct CreateVerticesRequest {
-    1: required i64 transaction_id;
-    2: map<i64, binary> (cpp.template = "std::unordered_map") labels_name_map;
-    3: map<i64, binary> (cpp.template = "std::unordered_map") property_name_map;
-    4: list<NewVertex> new_vertices;
-}
-
-
-service Storage {
-    i64 startTransaction()
-    Result commitTransaction(1: i64 transaction_id)
-    void abortTransaction(1: i64 transaction_id)
-
-    Result createVertices(1: CreateVerticesRequest req)
-    ScanVerticesResponse scanVertices(1: ScanVerticesRequest req)
-    GetPropertiesResponse getProperties(1: GetPropertiesRequest req)
-    ExpandOneResponse expandOne(1: ExpandOneRequest req)
-
-}

src/interface/trial.thrift

@@ -1,11 +0,0 @@
-struct Ping {
-    1: binary message;
-}
-
-struct Pong{
-    1: binary message;
-}
-
-service PingPong {
-    Pong ping(1: Ping req)
-}

src/io/network/epoll.hpp

@@ -1,4 +1,4 @@
-// Copyright 2021 Memgraph Ltd.
+// Copyright 2022 Memgraph Ltd.
 //
 // Use of this software is governed by the Business Source License
 // included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source

src/io/network/socket.cpp

@@ -1,4 +1,4 @@
-// Copyright 2021 Memgraph Ltd.
+// Copyright 2022 Memgraph Ltd.
 //
 // Use of this software is governed by the Business Source License
 // included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source

src/memgraph.cpp

@@ -26,22 +26,16 @@
 #include <thread>
 
 #include <fmt/format.h>
-#include <folly/init/Init.h>
-#include <folly/io/async/AsyncSocket.h>
-#include <folly/io/async/AsyncTransport.h>
-#include <folly/io/async/EventBase.h>
 #include <gflags/gflags.h>
 #include <spdlog/common.h>
 #include <spdlog/sinks/daily_file_sink.h>
 #include <spdlog/sinks/dist_sink.h>
 #include <spdlog/sinks/stdout_color_sinks.h>
-#include <thrift/lib/cpp2/async/HeaderClientChannel.h>
 
 #include "communication/bolt/v1/constants.hpp"
 #include "communication/websocket/auth.hpp"
 #include "communication/websocket/server.hpp"
 #include "helpers.hpp"
-#include "interface/gen-cpp2/Storage.h"
 #include "py/py.hpp"
 #include "query/auth_checker.hpp"
 #include "query/discard_value_stream.hpp"
@@ -222,6 +216,11 @@ DEFINE_bool(telemetry_enabled, false,
             "the database runtime (vertex and edge counts and resource usage) "
             "to allow for easier improvement of the product.");
 
+// NOLINTNEXTLINE(cppcoreguidelines-avoid-non-const-global-variables)
+DEFINE_bool(storage_restore_replicas_on_startup, true,
+            "Controls replicas should be restored automatically.");  // TODO(42jeremy) this must be removed once T0835
+                                                                     // is implemented.
+
 // Streams flags
 // NOLINTNEXTLINE (cppcoreguidelines-avoid-non-const-global-variables)
 DEFINE_uint32(
@@ -1201,7 +1200,8 @@ int main(int argc, char **argv) {
                      .snapshot_retention_count = FLAGS_storage_snapshot_retention_count,
                      .wal_file_size_kibibytes = FLAGS_storage_wal_file_size_kib,
                      .wal_file_flush_every_n_tx = FLAGS_storage_wal_file_flush_every_n_tx,
-                     .snapshot_on_exit = FLAGS_storage_snapshot_on_exit},
+                     .snapshot_on_exit = FLAGS_storage_snapshot_on_exit,
+                     .restore_replicas_on_startup = FLAGS_storage_restore_replicas_on_startup},
       .transaction = {.isolation_level = ParseIsolationLevel()}};
   if (FLAGS_storage_snapshot_interval_sec == 0) {
     if (FLAGS_storage_wal_enabled) {
@@ -1319,19 +1319,8 @@ int main(int argc, char **argv) {
   MG_ASSERT(server.Start(), "Couldn't start the Bolt server!");
   websocket_server.Start();
 
-  folly::init(&argc, &argv);
-  folly::EventBase base;
-  int port = 7779;  // The port on which server is listening
-
-  // Create a async client socket and connect it. Change
-  // the ip address to where the server is listening
-  auto socket(folly::AsyncSocket::newSocket(&base, "127.0.0.1", port));
-
-  // Create a HeaderClientChannel object which is used in creating
-  // client object
-  auto client_channel = apache::thrift::HeaderClientChannel::newChannel(std::move(socket));
-  // Create a client object
-  interface::storage::StorageAsyncClient client(std::move(client_channel));
+  server.AwaitShutdown();
+  websocket_server.AwaitShutdown();
 
   memgraph::query::procedure::gModuleRegistry.UnloadAllModules();
 

src/memory/CMakeLists.txt

@@ -9,4 +9,5 @@ target_link_libraries(mg-memory mg-utils fmt)
 
 if (ENABLE_JEMALLOC)
   target_link_libraries(mg-memory Jemalloc::Jemalloc)
+  target_compile_definitions(mg-memory PRIVATE USE_JEMALLOC=1)
 endif()

src/mg_import_csv.cpp

@@ -170,7 +170,7 @@ enum class CsvParserState {
   EXPECT_DELIMITER,
 };
 
-bool SubstringStartsWith(const std::string_view &str, size_t pos, const std::string_view &what) {
+bool SubstringStartsWith(const std::string_view str, size_t pos, const std::string_view what) {
   return memgraph::utils::StartsWith(memgraph::utils::Substr(str, pos), what);
 }
 

src/query/db_accessor.hpp

@@ -310,11 +310,11 @@ class DbAccessor final {
     return std::make_optional<VertexAccessor>(*value);
   }
 
-  storage::PropertyId NameToProperty(const std::string_view &name) { return accessor_->NameToProperty(name); }
+  storage::PropertyId NameToProperty(const std::string_view name) { return accessor_->NameToProperty(name); }
 
-  storage::LabelId NameToLabel(const std::string_view &name) { return accessor_->NameToLabel(name); }
+  storage::LabelId NameToLabel(const std::string_view name) { return accessor_->NameToLabel(name); }
 
-  storage::EdgeTypeId NameToEdgeType(const std::string_view &name) { return accessor_->NameToEdgeType(name); }
+  storage::EdgeTypeId NameToEdgeType(const std::string_view name) { return accessor_->NameToEdgeType(name); }
 
   const std::string &PropertyToName(storage::PropertyId prop) const { return accessor_->PropertyToName(prop); }
 

src/query/dump.cpp

@@ -46,7 +46,7 @@ const char *kInternalPropertyId = "__mg_id__";
 const char *kInternalVertexLabel = "__mg_vertex__";
 
 /// A helper function that escapes label, edge type and property names.
-std::string EscapeName(const std::string_view &value) {
+std::string EscapeName(const std::string_view value) {
   std::string out;
   out.reserve(value.size() + 2);
   out.append(1, '`');

src/query/frontend/ast/ast.lcp

@@ -2375,10 +2375,7 @@ cpp<#
    (port "Expression *" :initval "nullptr" :scope :public
              :slk-save #'slk-save-ast-pointer
              :slk-load (slk-load-ast-pointer "Expression"))
-   (sync_mode "SyncMode" :scope :public)
-   (timeout "Expression *" :initval "nullptr" :scope :public
-             :slk-save #'slk-save-ast-pointer
-             :slk-load (slk-load-ast-pointer "Expression")))
+   (sync_mode "SyncMode" :scope :public))
 
   (:public
     (lcp:define-enum action
@@ -2391,6 +2388,9 @@ cpp<#
     (lcp:define-enum sync-mode
         (sync async)
       (:serialize))
+    (lcp:define-enum replica-state
+        (ready replicating recovery invalid)
+      (:serialize))
     #>cpp
     ReplicationQuery() = default;
 

src/query/frontend/ast/cypher_main_visitor.cpp

@@ -275,18 +275,7 @@ antlrcpp::Any CypherMainVisitor::visitRegisterReplica(MemgraphCypher::RegisterRe
   replication_query->replica_name_ = ctx->replicaName()->symbolicName()->accept(this).as<std::string>();
   if (ctx->SYNC()) {
     replication_query->sync_mode_ = memgraph::query::ReplicationQuery::SyncMode::SYNC;
-    if (ctx->WITH() && ctx->TIMEOUT()) {
-      if (ctx->timeout->numberLiteral()) {
-        // we accept both double and integer literals
-        replication_query->timeout_ = ctx->timeout->accept(this);
-      } else {
-        throw SemanticException("Timeout should be a integer or double literal!");
-      }
-    }
   } else if (ctx->ASYNC()) {
-    if (ctx->WITH() && ctx->TIMEOUT()) {
-      throw SyntaxException("Timeout can be set only for the SYNC replication mode!");
-    }
     replication_query->sync_mode_ = memgraph::query::ReplicationQuery::SyncMode::ASYNC;
   }
 
@@ -775,6 +764,23 @@ antlrcpp::Any CypherMainVisitor::visitDropStream(MemgraphCypher::DropStreamConte
 antlrcpp::Any CypherMainVisitor::visitStartStream(MemgraphCypher::StartStreamContext *ctx) {
   auto *stream_query = storage_->Create<StreamQuery>();
   stream_query->action_ = StreamQuery::Action::START_STREAM;
+
+  if (ctx->BATCH_LIMIT()) {
+    if (!ctx->batchLimit->numberLiteral() || !ctx->batchLimit->numberLiteral()->integerLiteral()) {
+      throw SemanticException("Batch limit should be an integer literal!");
+    }
+    stream_query->batch_limit_ = ctx->batchLimit->accept(this);
+  }
+  if (ctx->TIMEOUT()) {
+    if (!ctx->timeout->numberLiteral() || !ctx->timeout->numberLiteral()->integerLiteral()) {
+      throw SemanticException("Timeout should be an integer literal!");
+    }
+    if (!ctx->BATCH_LIMIT()) {
+      throw SemanticException("Parameter TIMEOUT can only be defined if BATCH_LIMIT is defined");
+    }
+    stream_query->timeout_ = ctx->timeout->accept(this);
+  }
+
   stream_query->stream_name_ = ctx->streamName()->symbolicName()->accept(this).as<std::string>();
   return stream_query;
 }
@@ -2102,6 +2108,10 @@ antlrcpp::Any CypherMainVisitor::visitFunctionInvocation(MemgraphCypher::Functio
       return static_cast<Expression *>(
           storage_->Create<Aggregation>(expressions[0], nullptr, Aggregation::Op::COLLECT_LIST));
     }
+    if (function_name == Aggregation::kProject) {
+      return static_cast<Expression *>(
+          storage_->Create<Aggregation>(expressions[0], nullptr, Aggregation::Op::PROJECT));
+    }
   }
 
   if (expressions.size() == 2U && function_name == Aggregation::kCollect) {

src/query/frontend/opencypher/grammar/Cypher.g4

@@ -17,6 +17,8 @@
 
 parser grammar Cypher;
 
+options { tokenVocab=CypherLexer; }
+
 cypher : statement ';'? EOF ;
 
 statement : query ;

src/query/frontend/opencypher/grammar/MemgraphCypher.g4

@@ -30,7 +30,7 @@ memgraphCypherKeyword : cypherKeyword
                       | BATCH_SIZE
                       | BEFORE
                       | BOOTSTRAP_SERVERS
-                      | CHECK_
+                      | CHECK
                       | CLEAR
                       | COMMIT
                       | COMMITTED
@@ -276,7 +276,6 @@ replicaName : symbolicName ;
 socketAddress : literal ;
 
 registerReplica : REGISTER REPLICA replicaName ( SYNC | ASYNC )
-                ( WITH TIMEOUT timeout=literal ) ?
                 TO socketAddress ;
 
 dropReplica : DROP REPLICA replicaName ;
@@ -351,7 +350,7 @@ pulsarCreateStream : CREATE PULSAR STREAM streamName ( pulsarCreateStreamConfig
 
 dropStream : DROP STREAM streamName ;
 
-startStream : START STREAM streamName ;
+startStream : START STREAM streamName ( BATCH_LIMIT batchLimit=literal ) ? ( TIMEOUT timeout=literal ) ? ;
 
 startAllStreams : START ALL STREAMS ;
 
@@ -361,7 +360,7 @@ stopAllStreams : STOP ALL STREAMS ;
 
 showStreams : SHOW STREAMS ;
 
-checkStream : CHECK_ STREAM streamName ( BATCH_LIMIT batchLimit=literal ) ? ( TIMEOUT timeout=literal ) ? ;
+checkStream : CHECK STREAM streamName ( BATCH_LIMIT batchLimit=literal ) ? ( TIMEOUT timeout=literal ) ? ;
 
 settingName : literal ;
 

src/query/frontend/opencypher/grammar/MemgraphCypherLexer.g4

@@ -35,8 +35,7 @@ BATCH_LIMIT         : B A T C H UNDERSCORE L I M I T ;
 BATCH_SIZE          : B A T C H UNDERSCORE S I Z E ;
 BEFORE              : B E F O R E ;
 BOOTSTRAP_SERVERS   : B O O T S T R A P UNDERSCORE S E R V E R S ;
-/* This is a workaround to make sure the generated C++ function doesn't conlift with the CHECK macro from glog */
-CHECK_              : C H E C K ;
+CHECK               : C H E C K ;
 CLEAR               : C L E A R ;
 COMMIT              : C O M M I T ;
 COMMITTED           : C O M M I T T E D ;

src/query/interpret/awesome_memgraph_functions.cpp

@@ -882,21 +882,36 @@ TypedValue Id(const TypedValue *args, int64_t nargs, const FunctionContext &ctx)
 }
 
 TypedValue ToString(const TypedValue *args, int64_t nargs, const FunctionContext &ctx) {
-  FType<Or<Null, String, Number, Bool>>("toString", args, nargs);
+  FType<Or<Null, String, Number, Date, LocalTime, LocalDateTime, Duration, Bool>>("toString", args, nargs);
   const auto &arg = args[0];
   if (arg.IsNull()) {
     return TypedValue(ctx.memory);
-  } else if (arg.IsString()) {
+  }
+  if (arg.IsString()) {
     return TypedValue(arg, ctx.memory);
-  } else if (arg.IsInt()) {
+  }
+  if (arg.IsInt()) {
     // TODO: This is making a pointless copy of std::string, we may want to
     // use a different conversion to string
     return TypedValue(std::to_string(arg.ValueInt()), ctx.memory);
-  } else if (arg.IsDouble()) {
-    return TypedValue(std::to_string(arg.ValueDouble()), ctx.memory);
-  } else {
-    return TypedValue(arg.ValueBool() ? "true" : "false", ctx.memory);
   }
+  if (arg.IsDouble()) {
+    return TypedValue(std::to_string(arg.ValueDouble()), ctx.memory);
+  }
+  if (arg.IsDate()) {
+    return TypedValue(arg.ValueDate().ToString(), ctx.memory);
+  }
+  if (arg.IsLocalTime()) {
+    return TypedValue(arg.ValueLocalTime().ToString(), ctx.memory);
+  }
+  if (arg.IsLocalDateTime()) {
+    return TypedValue(arg.ValueLocalDateTime().ToString(), ctx.memory);
+  }
+  if (arg.IsDuration()) {
+    return TypedValue(arg.ValueDuration().ToString(), ctx.memory);
+  }
+
+  return TypedValue(arg.ValueBool() ? "true" : "false", ctx.memory);
 }
 
 TypedValue Timestamp(const TypedValue *args, int64_t nargs, const FunctionContext &ctx) {

src/query/interpret/eval.hpp

@@ -111,7 +111,7 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
   TypedValue Visit(IfOperator &if_operator) override {
     auto condition = if_operator.condition_->Accept(*this);
     if (condition.IsNull()) {
-      return if_operator.then_expression_->Accept(*this);
+      return if_operator.else_expression_->Accept(*this);
     }
     if (condition.type() != TypedValue::Type::Bool) {
       // At the moment IfOperator is used only in CASE construct.
@@ -716,7 +716,7 @@ class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
   }
 
   template <class TRecordAccessor>
-  storage::PropertyValue GetProperty(const TRecordAccessor &record_accessor, const std::string_view &name) {
+  storage::PropertyValue GetProperty(const TRecordAccessor &record_accessor, const std::string_view name) {
     auto maybe_prop = record_accessor.GetProperty(view_, dba_->NameToProperty(name));
     if (maybe_prop.HasError() && maybe_prop.GetError() == storage::Error::NONEXISTENT_OBJECT) {
       // This is a very nasty and temporary hack in order to make MERGE work.

src/query/interpreter.cpp

@@ -44,6 +44,7 @@
 #include "query/trigger.hpp"
 #include "query/typed_value.hpp"
 #include "storage/v2/property_value.hpp"
+#include "storage/v2/replication/enums.hpp"
 #include "utils/algorithm.hpp"
 #include "utils/csv_parsing.hpp"
 #include "utils/event_counter.hpp"
@@ -160,7 +161,7 @@ class ReplQueryHandler final : public query::ReplicationQueryHandler {
 
   /// @throw QueryRuntimeException if an error ocurred.
   void RegisterReplica(const std::string &name, const std::string &socket_address,
-                       const ReplicationQuery::SyncMode sync_mode, const std::optional<double> timeout,
+                       const ReplicationQuery::SyncMode sync_mode,
                        const std::chrono::seconds replica_check_frequency) override {
     if (db_->GetReplicationRole() == storage::ReplicationRole::REPLICA) {
       // replica can't register another replica
@@ -183,9 +184,9 @@ class ReplQueryHandler final : public query::ReplicationQueryHandler {
         io::network::Endpoint::ParseSocketOrIpAddress(socket_address, query::kDefaultReplicationPort);
     if (maybe_ip_and_port) {
       auto [ip, port] = *maybe_ip_and_port;
-      auto ret = db_->RegisterReplica(
-          name, {std::move(ip), port}, repl_mode,
-          {.timeout = timeout, .replica_check_frequency = replica_check_frequency, .ssl = std::nullopt});
+      auto ret = db_->RegisterReplica(name, {std::move(ip), port}, repl_mode,
+                                      storage::replication::RegistrationMode::MUST_BE_INSTANTLY_VALID,
+                                      {.replica_check_frequency = replica_check_frequency, .ssl = std::nullopt});
       if (ret.HasError()) {
         throw QueryRuntimeException(fmt::format("Couldn't register replica '{}'!", name));
       }
@@ -228,8 +229,24 @@ class ReplQueryHandler final : public query::ReplicationQueryHandler {
           replica.sync_mode = ReplicationQuery::SyncMode::ASYNC;
           break;
       }
-      if (repl_info.timeout) {
-        replica.timeout = *repl_info.timeout;
+
+      replica.current_timestamp_of_replica = repl_info.timestamp_info.current_timestamp_of_replica;
+      replica.current_number_of_timestamp_behind_master =
+          repl_info.timestamp_info.current_number_of_timestamp_behind_master;
+
+      switch (repl_info.state) {
+        case storage::replication::ReplicaState::READY:
+          replica.state = ReplicationQuery::ReplicaState::READY;
+          break;
+        case storage::replication::ReplicaState::REPLICATING:
+          replica.state = ReplicationQuery::ReplicaState::REPLICATING;
+          break;
+        case storage::replication::ReplicaState::RECOVERY:
+          replica.state = ReplicationQuery::ReplicaState::RECOVERY;
+          break;
+        case storage::replication::ReplicaState::INVALID:
+          replica.state = ReplicationQuery::ReplicaState::INVALID;
+          break;
       }
 
       return replica;
@@ -468,24 +485,18 @@ Callback HandleReplicationQuery(ReplicationQuery *repl_query, const Parameters &
       const auto &name = repl_query->replica_name_;
       const auto &sync_mode = repl_query->sync_mode_;
       auto socket_address = repl_query->socket_address_->Accept(evaluator);
-      auto timeout = EvaluateOptionalExpression(repl_query->timeout_, &evaluator);
       const auto replica_check_frequency = interpreter_context->config.replication_replica_check_frequency;
-      std::optional<double> maybe_timeout;
-      if (timeout.IsDouble()) {
-        maybe_timeout = timeout.ValueDouble();
-      } else if (timeout.IsInt()) {
-        maybe_timeout = static_cast<double>(timeout.ValueInt());
-      }
+
       callback.fn = [handler = ReplQueryHandler{interpreter_context->db}, name, socket_address, sync_mode,
-                     maybe_timeout, replica_check_frequency]() mutable {
-        handler.RegisterReplica(name, std::string(socket_address.ValueString()), sync_mode, maybe_timeout,
-                                replica_check_frequency);
+                     replica_check_frequency]() mutable {
+        handler.RegisterReplica(name, std::string(socket_address.ValueString()), sync_mode, replica_check_frequency);
         return std::vector<std::vector<TypedValue>>();
       };
       notifications->emplace_back(SeverityLevel::INFO, NotificationCode::REGISTER_REPLICA,
                                   fmt::format("Replica {} is registered.", repl_query->replica_name_));
       return callback;
     }
+
     case ReplicationQuery::Action::DROP_REPLICA: {
       const auto &name = repl_query->replica_name_;
       callback.fn = [handler = ReplQueryHandler{interpreter_context->db}, name]() mutable {
@@ -496,8 +507,11 @@ Callback HandleReplicationQuery(ReplicationQuery *repl_query, const Parameters &
                                   fmt::format("Replica {} is dropped.", repl_query->replica_name_));
       return callback;
     }
+
     case ReplicationQuery::Action::SHOW_REPLICAS: {
-      callback.header = {"name", "socket_address", "sync_mode", "timeout"};
+      callback.header = {
+          "name", "socket_address", "sync_mode", "current_timestamp_of_replica", "number_of_timestamp_behind_master",
+          "state"};
       callback.fn = [handler = ReplQueryHandler{interpreter_context->db}, replica_nfields = callback.header.size()] {
         const auto &replicas = handler.ShowReplicas();
         auto typed_replicas = std::vector<std::vector<TypedValue>>{};
@@ -508,6 +522,7 @@ Callback HandleReplicationQuery(ReplicationQuery *repl_query, const Parameters &
 
           typed_replica.emplace_back(TypedValue(replica.name));
           typed_replica.emplace_back(TypedValue(replica.socket_address));
+
           switch (replica.sync_mode) {
             case ReplicationQuery::SyncMode::SYNC:
               typed_replica.emplace_back(TypedValue("sync"));
@@ -516,10 +531,24 @@ Callback HandleReplicationQuery(ReplicationQuery *repl_query, const Parameters &
               typed_replica.emplace_back(TypedValue("async"));
               break;
           }
-          if (replica.timeout) {
-            typed_replica.emplace_back(TypedValue(*replica.timeout));
-          } else {
-            typed_replica.emplace_back(TypedValue());
+
+          typed_replica.emplace_back(TypedValue(static_cast<int64_t>(replica.current_timestamp_of_replica)));
+          typed_replica.emplace_back(
+              TypedValue(static_cast<int64_t>(replica.current_number_of_timestamp_behind_master)));
+
+          switch (replica.state) {
+            case ReplicationQuery::ReplicaState::READY:
+              typed_replica.emplace_back(TypedValue("ready"));
+              break;
+            case ReplicationQuery::ReplicaState::REPLICATING:
+              typed_replica.emplace_back(TypedValue("replicating"));
+              break;
+            case ReplicationQuery::ReplicaState::RECOVERY:
+              typed_replica.emplace_back(TypedValue("recovery"));
+              break;
+            case ReplicationQuery::ReplicaState::INVALID:
+              typed_replica.emplace_back(TypedValue("invalid"));
+              break;
           }
 
           typed_replicas.emplace_back(std::move(typed_replica));
@@ -655,12 +684,26 @@ Callback HandleStreamQuery(StreamQuery *stream_query, const Parameters &paramete
       return callback;
     }
     case StreamQuery::Action::START_STREAM: {
-      callback.fn = [interpreter_context, stream_name = stream_query->stream_name_]() {
-        interpreter_context->streams.Start(stream_name);
-        return std::vector<std::vector<TypedValue>>{};
-      };
-      notifications->emplace_back(SeverityLevel::INFO, NotificationCode::START_STREAM,
-                                  fmt::format("Started stream {}.", stream_query->stream_name_));
+      const auto batch_limit = GetOptionalValue<int64_t>(stream_query->batch_limit_, evaluator);
+      const auto timeout = GetOptionalValue<std::chrono::milliseconds>(stream_query->timeout_, evaluator);
+
+      if (batch_limit.has_value()) {
+        if (batch_limit.value() < 0) {
+          throw utils::BasicException("Parameter BATCH_LIMIT cannot hold negative value");
+        }
+
+        callback.fn = [interpreter_context, stream_name = stream_query->stream_name_, batch_limit, timeout]() {
+          interpreter_context->streams.StartWithLimit(stream_name, static_cast<uint64_t>(batch_limit.value()), timeout);
+          return std::vector<std::vector<TypedValue>>{};
+        };
+      } else {
+        callback.fn = [interpreter_context, stream_name = stream_query->stream_name_]() {
+          interpreter_context->streams.Start(stream_name);
+          return std::vector<std::vector<TypedValue>>{};
+        };
+        notifications->emplace_back(SeverityLevel::INFO, NotificationCode::START_STREAM,
+                                    fmt::format("Started stream {}.", stream_query->stream_name_));
+      }
       return callback;
     }
     case StreamQuery::Action::START_ALL_STREAMS: {
@@ -729,10 +772,16 @@ Callback HandleStreamQuery(StreamQuery *stream_query, const Parameters &paramete
       return callback;
     }
     case StreamQuery::Action::CHECK_STREAM: {
-      callback.header = {"query", "parameters"};
+      callback.header = {"queries", "raw messages"};
+
+      const auto batch_limit = GetOptionalValue<int64_t>(stream_query->batch_limit_, evaluator);
+      if (batch_limit.has_value() && batch_limit.value() < 0) {
+        throw utils::BasicException("Parameter BATCH_LIMIT cannot hold negative value");
+      }
+
       callback.fn = [interpreter_context, stream_name = stream_query->stream_name_,
                      timeout = GetOptionalValue<std::chrono::milliseconds>(stream_query->timeout_, evaluator),
-                     batch_limit = GetOptionalValue<int64_t>(stream_query->batch_limit_, evaluator)]() mutable {
+                     batch_limit]() mutable {
         return interpreter_context->streams.Check(stream_name, timeout, batch_limit);
       };
       notifications->emplace_back(SeverityLevel::INFO, NotificationCode::CHECK_STREAM,

src/query/interpreter.hpp

@@ -127,6 +127,9 @@ class ReplicationQueryHandler {
     std::string socket_address;
     ReplicationQuery::SyncMode sync_mode;
     std::optional<double> timeout;
+    uint64_t current_timestamp_of_replica;
+    uint64_t current_number_of_timestamp_behind_master;
+    ReplicationQuery::ReplicaState state;
   };
 
   /// @throw QueryRuntimeException if an error ocurred.
@@ -137,7 +140,7 @@ class ReplicationQueryHandler {
 
   /// @throw QueryRuntimeException if an error ocurred.
   virtual void RegisterReplica(const std::string &name, const std::string &socket_address,
-                               const ReplicationQuery::SyncMode sync_mode, const std::optional<double> timeout,
+                               ReplicationQuery::SyncMode sync_mode,
                                const std::chrono::seconds replica_check_frequency) = 0;
 
   /// @throw QueryRuntimeException if an error ocurred.

src/query/plan/operator.cpp

@@ -1,4 +1,4 @@
-// Copyright 2021 Memgraph Ltd.
+// Copyright 2022 Memgraph Ltd.
 //
 // Use of this software is governed by the Business Source License
 // included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
@@ -2109,7 +2109,7 @@ template <typename T>
 concept AccessorWithProperties = requires(T value, storage::PropertyId property_id,
                                           storage::PropertyValue property_value) {
   { value.ClearProperties() } -> std::same_as<storage::Result<std::map<storage::PropertyId, storage::PropertyValue>>>;
-  { value.SetProperty(property_id, property_value) };
+  {value.SetProperty(property_id, property_value)};
 };
 
 /// Helper function that sets the given values on either a Vertex or an Edge.
@@ -2608,9 +2608,10 @@ TypedValue DefaultAggregationOpValue(const Aggregate::Element &element, utils::M
     case Aggregation::Op::AVG:
       return TypedValue(memory);
     case Aggregation::Op::COLLECT_LIST:
-      return TypedValue(TypedValue::TVector(memory));
     case Aggregation::Op::COLLECT_MAP:
       return TypedValue(TypedValue::TMap(memory));
+    case Aggregation::Op::PROJECT:  // add here graph as aggregation value
+      return TypedValue(TypedValue::TVector(memory));
   }
 }
 }  // namespace
@@ -2812,6 +2813,7 @@ class AggregateCursor : public Cursor {
             *value_it = 1;
             break;
           case Aggregation::Op::COLLECT_LIST:
+          case Aggregation::Op::PROJECT:
             value_it->ValueList().push_back(input_value);
             break;
           case Aggregation::Op::COLLECT_MAP:
@@ -2860,6 +2862,7 @@ class AggregateCursor : public Cursor {
           *value_it = *value_it + input_value;
           break;
         case Aggregation::Op::COLLECT_LIST:
+        case Aggregation::Op::PROJECT:
           value_it->ValueList().push_back(input_value);
           break;
         case Aggregation::Op::COLLECT_MAP:
@@ -3697,7 +3700,7 @@ std::unordered_map<std::string, int64_t> CallProcedure::GetAndResetCounters() {
 
 namespace {
 
-void CallCustomProcedure(const std::string_view &fully_qualified_procedure_name, const mgp_proc &proc,
+void CallCustomProcedure(const std::string_view fully_qualified_procedure_name, const mgp_proc &proc,
                          const std::vector<Expression *> &args, mgp_graph &graph, ExpressionEvaluator *evaluator,
                          utils::MemoryResource *memory, std::optional<size_t> memory_limit, mgp_result *result) {
   static_assert(std::uses_allocator_v<mgp_value, utils::Allocator<mgp_value>>,

src/query/plan/profile.cpp

@@ -1,4 +1,4 @@
-// Copyright 2021 Memgraph Ltd.
+// Copyright 2022 Memgraph Ltd.
 //
 // Use of this software is governed by the Business Source License
 // included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source

src/query/plan/scoped_profile.hpp

@@ -1,4 +1,4 @@
-// Copyright 2021 Memgraph Ltd.
+// Copyright 2022 Memgraph Ltd.
 //
 // Use of this software is governed by the Business Source License
 // included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source

src/query/procedure/mg_procedure_impl.cpp

@@ -43,17 +43,6 @@
 // NOLINTNEXTLINE(google-build-using-namespace)
 using namespace memgraph::query::procedure;
 
-#define MG_STATIC_ASSERT_NOEXCEPT(x)                                  \
-  do {                                                                \
-    _Pragma("clang diagnostic push");                                 \
-    _Pragma("clang diagnostic ignored \"-Wunevaluated-expression\""); \
-    static_assert(noexcept(x));                                       \
-    _Pragma("clang diagnostic pop");                                  \
-  } while (false)
-
-#define MG_EXECUTE_NOEXCEPT(x)  \
-  MG_STATIC_ASSERT_NOEXCEPT(x); \
-  x
 namespace {
 
 void *MgpAlignedAllocImpl(memgraph::utils::MemoryResource &memory, const size_t size_in_bytes, const size_t alignment) {
@@ -834,6 +823,7 @@ DEFINE_MGP_VALUE_MAKE_WITH_MEMORY(int, int64_t);
 DEFINE_MGP_VALUE_MAKE_WITH_MEMORY(double, double);
 DEFINE_MGP_VALUE_MAKE_WITH_MEMORY(string, const char *);
 
+// NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
 #define DEFINE_MGP_VALUE_MAKE(type)                                                                             \
   mgp_error mgp_value_make_##type(mgp_##type *val, mgp_value **result) {                                        \
     return WrapExceptions([val] { return NewRawMgpObject<mgp_value>(val->GetMemoryResource(), val); }, result); \
@@ -1697,7 +1687,9 @@ mgp_error mgp_vertex_copy(mgp_vertex *v, mgp_memory *memory, mgp_vertex **result
 void mgp_vertex_destroy(mgp_vertex *v) { DeleteRawMgpObject(v); }
 
 mgp_error mgp_vertex_equal(mgp_vertex *v1, mgp_vertex *v2, int *result) {
-  MG_EXECUTE_NOEXCEPT(*result = *v1 == *v2 ? 1 : 0);
+  // NOLINTNEXTLINE(clang-diagnostic-unevaluated-expression)
+  static_assert(noexcept(*result = *v1 == *v2 ? 1 : 0));
+  *result = *v1 == *v2 ? 1 : 0;
   return mgp_error::MGP_ERROR_NO_ERROR;
 }
 
@@ -1955,7 +1947,9 @@ mgp_error mgp_edge_copy(mgp_edge *e, mgp_memory *memory, mgp_edge **result) {
 void mgp_edge_destroy(mgp_edge *e) { DeleteRawMgpObject(e); }
 
 mgp_error mgp_edge_equal(mgp_edge *e1, mgp_edge *e2, int *result) {
-  MG_EXECUTE_NOEXCEPT(*result = *e1 == *e2 ? 1 : 0);
+  // NOLINTNEXTLINE(clang-diagnostic-unevaluated-expression)
+  static_assert(noexcept(*result = *e1 == *e2 ? 1 : 0));
+  *result = *e1 == *e2 ? 1 : 0;
   return mgp_error::MGP_ERROR_NO_ERROR;
 }
 

src/query/procedure/module.cpp

@@ -1054,7 +1054,7 @@ std::unique_ptr<Module> LoadModuleFromFile(const std::filesystem::path &path) {
 
 }  // namespace
 
-bool ModuleRegistry::RegisterModule(const std::string_view &name, std::unique_ptr<Module> module) {
+bool ModuleRegistry::RegisterModule(const std::string_view name, std::unique_ptr<Module> module) {
   MG_ASSERT(!name.empty(), "Module name cannot be empty");
   MG_ASSERT(module, "Tried to register an invalid module");
   if (modules_.find(name) != modules_.end()) {
@@ -1163,7 +1163,7 @@ void ModuleRegistry::UnloadAndLoadModulesFromDirectories() {
   }
 }
 
-ModulePtr ModuleRegistry::GetModuleNamed(const std::string_view &name) const {
+ModulePtr ModuleRegistry::GetModuleNamed(const std::string_view name) const {
   std::shared_lock<utils::RWLock> guard(lock_);
   auto found_it = modules_.find(name);
   if (found_it == modules_.end()) return nullptr;

src/query/procedure/module.hpp

@@ -77,7 +77,7 @@ class ModuleRegistry final {
   mutable utils::RWLock lock_{utils::RWLock::Priority::WRITE};
   std::unique_ptr<utils::MemoryResource> shared_{std::make_unique<utils::ResourceWithOutOfMemoryException>()};
 
-  bool RegisterModule(const std::string_view &name, std::unique_ptr<Module> module);
+  bool RegisterModule(std::string_view name, std::unique_ptr<Module> module);
 
   void DoUnloadAllModules();
 
@@ -105,7 +105,7 @@ class ModuleRegistry final {
   ///
   /// Return true if the module was loaded or reloaded successfully, false
   /// otherwise.
-  bool LoadOrReloadModuleFromName(const std::string_view name);
+  bool LoadOrReloadModuleFromName(std::string_view name);
 
   /// Atomically unload all modules and then load all possible modules from the
   /// set directories.
@@ -115,7 +115,7 @@ class ModuleRegistry final {
 
   /// Find a module with given name or return nullptr.
   /// Takes a read lock.
-  ModulePtr GetModuleNamed(const std::string_view &name) const;
+  ModulePtr GetModuleNamed(std::string_view name) const;
 
   /// Remove all loaded (non-builtin) modules.
   /// Takes a write lock.
@@ -175,7 +175,7 @@ extern ModuleRegistry gModuleRegistry;
 /// inside this function. ModulePtr must be kept alive to make sure it won't be
 /// unloaded.
 std::optional<std::pair<procedure::ModulePtr, const mgp_proc *>> FindProcedure(
-    const ModuleRegistry &module_registry, const std::string_view fully_qualified_procedure_name,
+    const ModuleRegistry &module_registry, std::string_view fully_qualified_procedure_name,
     utils::MemoryResource *memory);
 
 /// Return the ModulePtr and `mgp_trans *` of the found transformation after resolving
@@ -183,7 +183,7 @@ std::optional<std::pair<procedure::ModulePtr, const mgp_proc *>> FindProcedure(
 /// inside this function. ModulePtr must be kept alive to make sure it won't be
 /// unloaded.
 std::optional<std::pair<procedure::ModulePtr, const mgp_trans *>> FindTransformation(
-    const ModuleRegistry &module_registry, const std::string_view fully_qualified_transformation_name,
+    const ModuleRegistry &module_registry, std::string_view fully_qualified_transformation_name,
     utils::MemoryResource *memory);
 
 /// Return the ModulePtr and `mgp_func *` of the found function after resolving
@@ -191,7 +191,7 @@ std::optional<std::pair<procedure::ModulePtr, const mgp_trans *>> FindTransforma
 /// std::nullopt is returned. `memory` is used for temporary allocations
 /// inside this function. ModulePtr must be kept alive to make sure it won't be unloaded.
 std::optional<std::pair<procedure::ModulePtr, const mgp_func *>> FindFunction(
-    const ModuleRegistry &module_registry, const std::string_view fully_qualified_function_name,
+    const ModuleRegistry &module_registry, std::string_view fully_qualified_function_name,
     utils::MemoryResource *memory);
 
 template <typename T>

src/query/stream/common.hpp

@@ -52,10 +52,11 @@ concept Stream = requires(TStream stream) {
   typename TStream::Message;
   TStream{std::string{""}, typename TStream::StreamInfo{}, ConsumerFunction<typename TStream::Message>{}};
   { stream.Start() } -> std::same_as<void>;
+  { stream.StartWithLimit(uint64_t{}, std::optional<std::chrono::milliseconds>{}) } -> std::same_as<void>;
   { stream.Stop() } -> std::same_as<void>;
   { stream.IsRunning() } -> std::same_as<bool>;
   {
-    stream.Check(std::optional<std::chrono::milliseconds>{}, std::optional<int64_t>{},
+    stream.Check(std::optional<std::chrono::milliseconds>{}, std::optional<uint64_t>{},
                  ConsumerFunction<typename TStream::Message>{})
     } -> std::same_as<void>;
   requires std::same_as<std::decay_t<decltype(std::declval<typename TStream::StreamInfo>().common_info)>,

src/query/stream/sources.cpp

@@ -44,10 +44,13 @@ KafkaStream::StreamInfo KafkaStream::Info(std::string transformation_name) const
 }
 
 void KafkaStream::Start() { consumer_->Start(); }
+void KafkaStream::StartWithLimit(uint64_t batch_limit, std::optional<std::chrono::milliseconds> timeout) const {
+  consumer_->StartWithLimit(batch_limit, timeout);
+}
 void KafkaStream::Stop() { consumer_->Stop(); }
 bool KafkaStream::IsRunning() const { return consumer_->IsRunning(); }
 
-void KafkaStream::Check(std::optional<std::chrono::milliseconds> timeout, std::optional<int64_t> batch_limit,
+void KafkaStream::Check(std::optional<std::chrono::milliseconds> timeout, std::optional<uint64_t> batch_limit,
                         const ConsumerFunction<integrations::kafka::Message> &consumer_function) const {
   consumer_->Check(timeout, batch_limit, consumer_function);
 }
@@ -106,10 +109,12 @@ PulsarStream::StreamInfo PulsarStream::Info(std::string transformation_name) con
 }
 
 void PulsarStream::Start() { consumer_->Start(); }
+void PulsarStream::StartWithLimit(uint64_t batch_limit, std::optional<std::chrono::milliseconds> timeout) const {
+  consumer_->StartWithLimit(batch_limit, timeout);
+}
 void PulsarStream::Stop() { consumer_->Stop(); }
 bool PulsarStream::IsRunning() const { return consumer_->IsRunning(); }
-
-void PulsarStream::Check(std::optional<std::chrono::milliseconds> timeout, std::optional<int64_t> batch_limit,
+void PulsarStream::Check(std::optional<std::chrono::milliseconds> timeout, std::optional<uint64_t> batch_limit,
                          const ConsumerFunction<Message> &consumer_function) const {
   consumer_->Check(timeout, batch_limit, consumer_function);
 }

src/query/stream/sources.hpp

@@ -36,10 +36,11 @@ struct KafkaStream {
   StreamInfo Info(std::string transformation_name) const;
 
   void Start();
+  void StartWithLimit(uint64_t batch_limit, std::optional<std::chrono::milliseconds> timeout) const;
   void Stop();
   bool IsRunning() const;
 
-  void Check(std::optional<std::chrono::milliseconds> timeout, std::optional<int64_t> batch_limit,
+  void Check(std::optional<std::chrono::milliseconds> timeout, std::optional<uint64_t> batch_limit,
              const ConsumerFunction<Message> &consumer_function) const;
 
   utils::BasicResult<std::string> SetStreamOffset(int64_t offset);
@@ -71,10 +72,11 @@ struct PulsarStream {
   StreamInfo Info(std::string transformation_name) const;
 
   void Start();
+  void StartWithLimit(uint64_t batch_limit, std::optional<std::chrono::milliseconds> timeout) const;
   void Stop();
   bool IsRunning() const;
 
-  void Check(std::optional<std::chrono::milliseconds> timeout, std::optional<int64_t> batch_limit,
+  void Check(std::optional<std::chrono::milliseconds> timeout, std::optional<uint64_t> batch_limit,
              const ConsumerFunction<Message> &consumer_function) const;
 
  private:

src/query/stream/streams.cpp

@@ -43,6 +43,7 @@ extern const Event MessagesConsumed;
 namespace memgraph::query::stream {
 namespace {
 inline constexpr auto kExpectedTransformationResultSize = 2;
+inline constexpr auto kCheckStreamResultSize = 2;
 const utils::pmr::string query_param_name{"query", utils::NewDeleteResource()};
 const utils::pmr::string params_param_name{"parameters", utils::NewDeleteResource()};
 
@@ -455,7 +456,7 @@ void Streams::Create(const std::string &stream_name, typename TStream::StreamInf
 
   try {
     std::visit(
-        [&](auto &&stream_data) {
+        [&](const auto &stream_data) {
           const auto stream_source_ptr = stream_data.stream_source->ReadLock();
           Persist(CreateStatus(stream_name, stream_data.transformation_name, stream_data.owner, *stream_source_ptr));
         },
@@ -574,7 +575,7 @@ void Streams::RestoreStreams() {
         auto it = CreateConsumer<T>(*locked_streams_map, stream_name, std::move(status.info), std::move(status.owner));
         if (status.is_running) {
           std::visit(
-              [&](auto &&stream_data) {
+              [&](const auto &stream_data) {
                 auto stream_source_ptr = stream_data.stream_source->Lock();
                 stream_source_ptr->Start();
               },
@@ -616,12 +617,12 @@ void Streams::Drop(const std::string &stream_name) {
   // function can be executing with the consumer, nothing else.
   // By acquiring the write lock here for the consumer, we make sure there is
   // no running Test function for this consumer, therefore it can be erased.
-  std::visit([&](auto &&stream_data) { stream_data.stream_source->Lock(); }, it->second);
+  std::visit([&](const auto &stream_data) { stream_data.stream_source->Lock(); }, it->second);
 
-  locked_streams->erase(it);
   if (!storage_.Delete(stream_name)) {
     throw StreamsException("Couldn't delete stream '{}' from persistent store!", stream_name);
   }
+  locked_streams->erase(it);
 
   // TODO(antaljanosbenjamin) Release the transformation
 }
@@ -631,7 +632,7 @@ void Streams::Start(const std::string &stream_name) {
   auto it = GetStream(*locked_streams, stream_name);
 
   std::visit(
-      [&, this](auto &&stream_data) {
+      [&, this](const auto &stream_data) {
         auto stream_source_ptr = stream_data.stream_source->Lock();
         stream_source_ptr->Start();
         Persist(CreateStatus(stream_name, stream_data.transformation_name, stream_data.owner, *stream_source_ptr));
@@ -639,12 +640,27 @@ void Streams::Start(const std::string &stream_name) {
       it->second);
 }
 
+void Streams::StartWithLimit(const std::string &stream_name, uint64_t batch_limit,
+                             std::optional<std::chrono::milliseconds> timeout) const {
+  std::optional locked_streams{streams_.ReadLock()};
+  auto it = GetStream(**locked_streams, stream_name);
+
+  std::visit(
+      [&](const auto &stream_data) {
+        const auto locked_stream_source = stream_data.stream_source->ReadLock();
+        locked_streams.reset();
+
+        locked_stream_source->StartWithLimit(batch_limit, timeout);
+      },
+      it->second);
+}
+
 void Streams::Stop(const std::string &stream_name) {
   auto locked_streams = streams_.Lock();
   auto it = GetStream(*locked_streams, stream_name);
 
   std::visit(
-      [&, this](auto &&stream_data) {
+      [&, this](const auto &stream_data) {
         auto stream_source_ptr = stream_data.stream_source->Lock();
         stream_source_ptr->Stop();
 
@@ -656,7 +672,7 @@ void Streams::Stop(const std::string &stream_name) {
 void Streams::StartAll() {
   for (auto locked_streams = streams_.Lock(); auto &[stream_name, stream_data] : *locked_streams) {
     std::visit(
-        [&stream_name = stream_name, this](auto &&stream_data) {
+        [&stream_name = stream_name, this](const auto &stream_data) {
           auto locked_stream_source = stream_data.stream_source->Lock();
           if (!locked_stream_source->IsRunning()) {
             locked_stream_source->Start();
@@ -671,7 +687,7 @@ void Streams::StartAll() {
 void Streams::StopAll() {
   for (auto locked_streams = streams_.Lock(); auto &[stream_name, stream_data] : *locked_streams) {
     std::visit(
-        [&stream_name = stream_name, this](auto &&stream_data) {
+        [&stream_name = stream_name, this](const auto &stream_data) {
           auto locked_stream_source = stream_data.stream_source->Lock();
           if (locked_stream_source->IsRunning()) {
             locked_stream_source->Stop();
@@ -688,7 +704,7 @@ std::vector<StreamStatus<>> Streams::GetStreamInfo() const {
   {
     for (auto locked_streams = streams_.ReadLock(); const auto &[stream_name, stream_data] : *locked_streams) {
       std::visit(
-          [&, &stream_name = stream_name](auto &&stream_data) {
+          [&, &stream_name = stream_name](const auto &stream_data) {
             auto locked_stream_source = stream_data.stream_source->ReadLock();
             auto info = locked_stream_source->Info(stream_data.transformation_name);
             result.emplace_back(StreamStatus<>{stream_name, StreamType(*locked_stream_source),
@@ -702,12 +718,12 @@ std::vector<StreamStatus<>> Streams::GetStreamInfo() const {
 }
 
 TransformationResult Streams::Check(const std::string &stream_name, std::optional<std::chrono::milliseconds> timeout,
-                                    std::optional<int64_t> batch_limit) const {
+                                    std::optional<uint64_t> batch_limit) const {
   std::optional locked_streams{streams_.ReadLock()};
   auto it = GetStream(**locked_streams, stream_name);
 
   return std::visit(
-      [&](auto &&stream_data) {
+      [&](const auto &stream_data) {
         // This depends on the fact that Drop will first acquire a write lock to the consumer, and erase it only after
         // that
         const auto locked_stream_source = stream_data.stream_source->ReadLock();
@@ -724,15 +740,27 @@ TransformationResult Streams::Check(const std::string &stream_name, std::optiona
           auto accessor = interpreter_context->db->Access();
           CallCustomTransformation(transformation_name, messages, result, accessor, *memory_resource, stream_name);
 
-          for (auto &row : result.rows) {
-            auto [query, parameters] = ExtractTransformationResult(row.values, transformation_name, stream_name);
-            std::vector<TypedValue> result_row;
-            result_row.reserve(kExpectedTransformationResultSize);
-            result_row.push_back(std::move(query));
-            result_row.push_back(std::move(parameters));
+          auto result_row = std::vector<TypedValue>();
+          result_row.reserve(kCheckStreamResultSize);
 
-            test_result.push_back(std::move(result_row));
-          }
+          auto queries_and_parameters = std::vector<TypedValue>(result.rows.size());
+          std::transform(
+              result.rows.cbegin(), result.rows.cend(), queries_and_parameters.begin(), [&](const auto &row) {
+                auto [query, parameters] = ExtractTransformationResult(row.values, transformation_name, stream_name);
+
+                return std::map<std::string, TypedValue>{{"query", std::move(query)},
+                                                         {"parameters", std::move(parameters)}};
+              });
+          result_row.emplace_back(std::move(queries_and_parameters));
+
+          auto messages_list = std::vector<TypedValue>(messages.size());
+          std::transform(messages.cbegin(), messages.cend(), messages_list.begin(), [](const auto &message) {
+            return std::string_view(message.Payload().data(), message.Payload().size());
+          });
+
+          result_row.emplace_back(std::move(messages_list));
+
+          test_result.emplace_back(std::move(result_row));
         };
 
         locked_stream_source->Check(timeout, batch_limit, consumer_function);

src/query/stream/streams.hpp

@@ -115,6 +115,17 @@ class Streams final {
   /// @throws ConsumerRunningException if the consumer is already running
   void Start(const std::string &stream_name);
 
+  /// Start consuming from a stream.
+  ///
+  /// @param stream_name name of the stream that needs to be started
+  /// @param batch_limit number of batches we want to consume before stopping
+  /// @param timeout the maximum duration during which the command should run.
+  ///
+  /// @throws StreamsException if the stream doesn't exist
+  /// @throws ConsumerRunningException if the consumer is already running
+  void StartWithLimit(const std::string &stream_name, uint64_t batch_limit,
+                      std::optional<std::chrono::milliseconds> timeout) const;
+
   /// Stop consuming from a stream.
   ///
   /// @param stream_name name of the stream that needs to be stopped
@@ -142,6 +153,7 @@ class Streams final {
   ///
   /// @param stream_name name of the stream we want to test
   /// @param batch_limit number of batches we want to test before stopping
+  /// @param timeout the maximum duration during which the command should run.
   ///
   /// @returns A vector of vectors of TypedValue. Each subvector contains two elements, the query string and the
   /// nullable parameters map.
@@ -151,7 +163,7 @@ class Streams final {
   /// @throws ConsumerCheckFailedException if the transformation function throws any std::exception during processing
   TransformationResult Check(const std::string &stream_name,
                              std::optional<std::chrono::milliseconds> timeout = std::nullopt,
-                             std::optional<int64_t> batch_limit = std::nullopt) const;
+                             std::optional<uint64_t> batch_limit = std::nullopt) const;
 
  private:
   template <Stream TStream>
@@ -176,7 +188,7 @@ class Streams final {
   void Persist(StreamStatus<TStream> &&status) {
     const std::string stream_name = status.name;
     if (!storage_.Put(stream_name, nlohmann::json(std::move(status)).dump())) {
-      throw StreamsException{"Couldn't persist steam data for stream '{}'", stream_name};
+      throw StreamsException{"Couldn't persist stream data for stream '{}'", stream_name};
     }
   }
 

src/query/typed_value.cpp

@@ -407,7 +407,7 @@ DEFINE_TYPED_VALUE_COPY_ASSIGNMENT(int, Int, int_v)
 DEFINE_TYPED_VALUE_COPY_ASSIGNMENT(bool, Bool, bool_v)
 DEFINE_TYPED_VALUE_COPY_ASSIGNMENT(int64_t, Int, int_v)
 DEFINE_TYPED_VALUE_COPY_ASSIGNMENT(double, Double, double_v)
-DEFINE_TYPED_VALUE_COPY_ASSIGNMENT(const std::string_view &, String, string_v)
+DEFINE_TYPED_VALUE_COPY_ASSIGNMENT(const std::string_view, String, string_v)
 DEFINE_TYPED_VALUE_COPY_ASSIGNMENT(const TypedValue::TVector &, List, list_v)
 
 TypedValue &TypedValue::operator=(const std::vector<TypedValue> &other) {

src/query/typed_value.hpp

@@ -185,7 +185,7 @@ class TypedValue {
     new (&string_v) TString(value, memory_);
   }
 
-  explicit TypedValue(const std::string_view &value, utils::MemoryResource *memory = utils::NewDeleteResource())
+  explicit TypedValue(const std::string_view value, utils::MemoryResource *memory = utils::NewDeleteResource())
       : memory_(memory), type_(Type::String) {
     new (&string_v) TString(value, memory_);
   }
@@ -420,7 +420,7 @@ class TypedValue {
   TypedValue &operator=(bool);
   TypedValue &operator=(int64_t);
   TypedValue &operator=(double);
-  TypedValue &operator=(const std::string_view &);
+  TypedValue &operator=(std::string_view);
   TypedValue &operator=(const TVector &);
   TypedValue &operator=(const std::vector<TypedValue> &);
   TypedValue &operator=(const TMap &);

src/slk/serialization.hpp

@@ -166,7 +166,7 @@ inline void Save(const char *obj, Builder *builder) {
   builder->Save(reinterpret_cast<const uint8_t *>(obj), size);
 }
 
-inline void Save(const std::string_view &obj, Builder *builder) {
+inline void Save(const std::string_view obj, Builder *builder) {
   uint64_t size = obj.size();
   Save(size, builder);
   builder->Save(reinterpret_cast<const uint8_t *>(obj.data()), size);

src/storage/v2/CMakeLists.txt

@@ -13,7 +13,6 @@ set(storage_v2_src_files
     storage.cpp)
 
 ##### Replication #####
-
 define_add_lcp(add_lcp_storage lcp_storage_cpp_files generated_lcp_storage_files)
 
 add_lcp_storage(replication/rpc.lcp SLK_SERIALIZE)
@@ -26,10 +25,10 @@ set(storage_v2_src_files
     replication/replication_server.cpp
     replication/serialization.cpp
     replication/slk.cpp
+    replication/replication_persistence_helper.cpp
     ${lcp_storage_cpp_files})
 
 #######################
-
 find_package(gflags REQUIRED)
 find_package(Threads REQUIRED)
 

src/storage/v2/config.hpp

@@ -49,7 +49,7 @@ struct Config {
     uint64_t wal_file_flush_every_n_tx{100000};
 
     bool snapshot_on_exit{false};
-
+    bool restore_replicas_on_startup{false};
   } durability;
 
   struct Transaction {

src/storage/v2/durability/paths.hpp

@@ -22,6 +22,7 @@ static const std::string kSnapshotDirectory{"snapshots"};
 static const std::string kWalDirectory{"wal"};
 static const std::string kBackupDirectory{".backup"};
 static const std::string kLockFile{".lock"};
+static const std::string kReplicationDirectory{"replication"};
 
 // This is the prefix used for Snapshot and WAL filenames. It is a timestamp
 // format that equals to: YYYYmmddHHMMSSffffff

src/storage/v2/durability/serialization.cpp

@@ -27,7 +27,7 @@ void WriteSize(Encoder *encoder, uint64_t size) {
 }
 }  // namespace
 
-void Encoder::Initialize(const std::filesystem::path &path, const std::string_view &magic, uint64_t version) {
+void Encoder::Initialize(const std::filesystem::path &path, const std::string_view magic, uint64_t version) {
   file_.Open(path, utils::OutputFile::Mode::OVERWRITE_EXISTING);
   Write(reinterpret_cast<const uint8_t *>(magic.data()), magic.size());
   auto version_encoded = utils::HostToLittleEndian(version);
@@ -73,7 +73,7 @@ void Encoder::WriteDouble(double value) {
   Write(reinterpret_cast<const uint8_t *>(&value_uint), sizeof(value_uint));
 }
 
-void Encoder::WriteString(const std::string_view &value) {
+void Encoder::WriteString(const std::string_view value) {
   WriteMarker(Marker::TYPE_STRING);
   WriteSize(this, value.size());
   Write(reinterpret_cast<const uint8_t *>(value.data()), value.size());

src/storage/v2/durability/serialization.hpp

@@ -34,14 +34,14 @@ class BaseEncoder {
   virtual void WriteBool(bool value) = 0;
   virtual void WriteUint(uint64_t value) = 0;
   virtual void WriteDouble(double value) = 0;
-  virtual void WriteString(const std::string_view &value) = 0;
+  virtual void WriteString(std::string_view value) = 0;
   virtual void WritePropertyValue(const PropertyValue &value) = 0;
 };
 
 /// Encoder that is used to generate a snapshot/WAL.
 class Encoder final : public BaseEncoder {
  public:
-  void Initialize(const std::filesystem::path &path, const std::string_view &magic, uint64_t version);
+  void Initialize(const std::filesystem::path &path, std::string_view magic, uint64_t version);
 
   void OpenExisting(const std::filesystem::path &path);
 
@@ -54,7 +54,7 @@ class Encoder final : public BaseEncoder {
   void WriteBool(bool value) override;
   void WriteUint(uint64_t value) override;
   void WriteDouble(double value) override;
-  void WriteString(const std::string_view &value) override;
+  void WriteString(std::string_view value) override;
   void WritePropertyValue(const PropertyValue &value) override;
 
   uint64_t GetPosition();

src/storage/v2/indices.hpp

@@ -97,10 +97,6 @@ class LabelIndex {
     Iterator begin() { return Iterator(this, index_accessor_.begin()); }
     Iterator end() { return Iterator(this, index_accessor_.end()); }
 
-    Iterator IterateFrom(Vertex *vertex) {
-      return Iterator(this, index_accessor_.find_equal_or_greater(Entry{vertex, 0}));
-    }
-
    private:
     utils::SkipList<Entry>::Accessor index_accessor_;
     LabelId label_;

src/storage/v2/name_id_mapper.hpp

@@ -29,8 +29,8 @@ class NameIdMapper final {
     bool operator<(const MapNameToId &other) { return name < other.name; }
     bool operator==(const MapNameToId &other) { return name == other.name; }
 
-    bool operator<(const std::string_view &other) { return name < other; }
-    bool operator==(const std::string_view &other) { return name == other; }
+    bool operator<(const std::string_view other) const { return name < other; }
+    bool operator==(const std::string_view other) const { return name == other; }
   };
 
   struct MapIdToName {
@@ -46,7 +46,7 @@ class NameIdMapper final {
 
  public:
   /// @throw std::bad_alloc if unable to insert a new mapping
-  uint64_t NameToId(const std::string_view &name) {
+  uint64_t NameToId(const std::string_view name) {
     auto name_to_id_acc = name_to_id_.access();
     auto found = name_to_id_acc.find(name);
     uint64_t id;

src/storage/v2/replication/config.hpp

@@ -10,12 +10,13 @@
 // licenses/APL.txt.
 
 #pragma once
+
+#include <chrono>
 #include <optional>
 #include <string>
 
 namespace memgraph::storage::replication {
 struct ReplicationClientConfig {
-  std::optional<double> timeout;
   // The default delay between main checking/pinging replicas is 1s because
   // that seems like a reasonable timeframe in which main should notice a
   // replica is down.
@@ -24,6 +25,8 @@ struct ReplicationClientConfig {
   struct SSL {
     std::string key_file = "";
     std::string cert_file = "";
+
+    friend bool operator==(const SSL &, const SSL &) = default;
   };
 
   std::optional<SSL> ssl;