Merge branch 'project-pineapples' into add-gnuplot-example

[🍍 < MG] Fix mgbench access control benchmark

.clang-tidy

@@ -6,6 +6,7 @@ Checks: '*,
          -altera-unroll-loops,
          -android-*,
          -cert-err58-cpp,
+         -cert-str34-c,
          -cppcoreguidelines-avoid-c-arrays,
          -cppcoreguidelines-avoid-goto,
          -cppcoreguidelines-avoid-magic-numbers,
@@ -49,6 +50,7 @@ Checks: '*,
          -misc-non-private-member-variables-in-classes,
          -modernize-avoid-c-arrays,
          -modernize-concat-nested-namespaces,
+         -modernize-loop-convert,
          -modernize-pass-by-value,
          -modernize-use-equals-default,
          -modernize-use-nodiscard,
@@ -61,7 +63,9 @@ 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/pull_request_template.md

@@ -3,7 +3,9 @@
 - [ ] Update [changelog](https://docs.memgraph.com/memgraph/changelog)
 - [ ] Write E2E tests
 - [ ] Compare the [benchmarking results](https://bench-graph.memgraph.com/) between the master branch and the Epic branch
+- [ ] Provide the full content or a guide for the final git message
 
 [master < Task] PR
 - [ ] Check, and update documentation if necessary
 - [ ] Update [changelog](https://docs.memgraph.com/memgraph/changelog)
+- [ ] Provide the full content or a guide for the final git message

.github/workflows/daily_benchmark.yaml

@@ -16,7 +16,7 @@ jobs:
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)

.github/workflows/diff.yaml

@@ -1,4 +1,7 @@
 name: Diff
+concurrency:
+  group: ${{ github.head_ref || github.sha }}
+  cancel-in-progress: true
 
 on:
   push:
@@ -23,7 +26,7 @@ jobs:
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -61,20 +64,50 @@ jobs:
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
           fetch-depth: 0
 
+        # This is also needed if we want do to comparison against other branches
+        # See https://github.community/t/checkout-code-fails-when-it-runs-lerna-run-test-since-master/17920
+      - name: Fetch all history for all tags and branches
+        run: git fetch
+
+      - name: Initialize deps
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v4/activate
+          # Initialize dependencies.
+          ./init
+
+      - name: Set base branch
+        if: ${{ github.event_name == 'pull_request' }}
+        run: |
+          echo "BASE_BRANCH=origin/${{ github.base_ref }}" >> $GITHUB_ENV
+
+      - name: Set base branch # if we manually dispatch or push to master
+        if: ${{ github.event_name != 'pull_request' }}
+        run: |
+          echo "BASE_BRANCH=origin/master" >> $GITHUB_ENV
+
+      - name: Python code analysis
+        run: |
+          CHANGED_FILES=$(git diff -U0 ${{ env.BASE_BRANCH }}... --name-only)
+          for file in ${CHANGED_FILES}; do
+            echo ${file}
+            if [[ ${file} == *.py ]]; then
+              python3 -m black --check --diff ${file}
+              python3 -m isort --check-only --profile "black" --diff ${file}
+            fi
+          done
+
       - name: Build combined ASAN, UBSAN and coverage binaries
         run: |
           # Activate toolchain.
           source /opt/toolchain-v4/activate
 
-          # Initialize dependencies.
-          ./init
-
           cd build
           cmake -DTEST_COVERAGE=ON -DASAN=ON -DUBSAN=ON ..
           make -j$THREADS memgraph__unit
@@ -102,17 +135,27 @@ jobs:
           tar -czf code_coverage.tar.gz coverage.json html report.json summary.rmu
 
       - name: Save code coverage
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: "Code coverage"
           path: tools/github/generated/code_coverage.tar.gz
 
+      - name: Set base branch
+        if: ${{ github.event_name == 'pull_request' }}
+        run: |
+          echo "BASE_BRANCH=origin/${{ github.base_ref }}" >> $GITHUB_ENV
+
+      - name: Set base branch # if we manually dispatch or push to master
+        if: ${{ github.event_name != 'pull_request' }}
+        run: |
+          echo "BASE_BRANCH=origin/master" >> $GITHUB_ENV
+
       - name: Run clang-tidy
         run: |
           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 ${{ env.BASE_BRANCH }}... -- src | ./tools/github/clang-tidy/clang-tidy-diff.py -p 1 -j $THREADS -extra-arg="-DMG_CLANG_TIDY_CHECK" -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
@@ -127,7 +170,7 @@ jobs:
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -146,52 +189,23 @@ jobs:
           cmake ..
           make -j$THREADS
 
-      - name: Run leftover CTest tests
+      - name: Run simulation tests
         run: |
           # Activate toolchain.
           source /opt/toolchain-v4/activate
 
-          # Run leftover CTest tests (all except unit and benchmark tests).
+          # Run simulation tests.
           cd build
-          ctest -E "(memgraph__unit|memgraph__benchmark)" --output-on-failure
+          ctest -R memgraph__simulation --output-on-failure -j$THREADS
 
-      - name: Run drivers tests
-        run: |
-          ./tests/drivers/run.sh
-
-      - name: Run integration tests
-        run: |
-          cd tests/integration
-          for name in *; do
-            if [ ! -d $name ]; then continue; fi
-            pushd $name >/dev/null
-            echo "Running: $name"
-            if [ -x prepare.sh ]; then
-              ./prepare.sh
-            fi
-            if [ -x runner.py ]; then
-              ./runner.py
-            elif [ -x runner.sh ]; then
-              ./runner.sh
-            fi
-            echo
-            popd >/dev/null
-          done
-
-      - name: Run cppcheck and clang-format
+      - name: Run single benchmark test
         run: |
           # Activate toolchain.
           source /opt/toolchain-v4/activate
 
-          # Run cppcheck and clang-format.
-          cd tools/github
-          ./cppcheck_and_clang_format diff
-
-      - name: Save cppcheck and clang-format errors
-        uses: actions/upload-artifact@v2
-        with:
-          name: "Code coverage"
-          path: tools/github/cppcheck_and_clang_format.txt
+          # Run simulation tests.
+          cd tests/mgbench
+          ./benchmark.py accesscontrol/small --num-workers-for-import 1 --test-system-arg  "split-file splitfiles/accesscontrol_small.shard_configuration bolt-num-workers 1"
 
   release_build:
     name: "Release build"
@@ -203,7 +217,7 @@ jobs:
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -222,19 +236,6 @@ jobs:
           cmake -DCMAKE_BUILD_TYPE=release ..
           make -j$THREADS
 
-      - name: Run GQL Behave tests
-        run: |
-          cd tests/gql_behave
-          ./continuous_integration
-
-      - name: Save quality assurance status
-        uses: actions/upload-artifact@v2
-        with:
-          name: "GQL Behave Status"
-          path: |
-            tests/gql_behave/gql_behave_status.csv
-            tests/gql_behave/gql_behave_status.html
-
       - name: Run unit tests
         run: |
           # Activate toolchain.
@@ -244,6 +245,24 @@ jobs:
           cd build
           ctest -R memgraph__unit --output-on-failure -j$THREADS
 
+      - name: Run simulation tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v4/activate
+
+          # Run simulation tests.
+          cd build
+          ctest -R memgraph__simulation --output-on-failure -j$THREADS
+
+      - name: Run single benchmark test
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v4/activate
+
+          # Run simulation tests.
+          cd tests/mgbench
+          ./benchmark.py accesscontrol/small --num-workers-for-import 1 --test-system-arg  "split-file splitfiles/accesscontrol_small.shard_configuration bolt-num-workers 1"
+
       - name: Run e2e tests
         run: |
           # TODO(gitbuda): Setup mgclient and pymgclient properly.
@@ -251,167 +270,4 @@ jobs:
           ./setup.sh
           source ve3/bin/activate
           cd e2e
-          LD_LIBRARY_PATH=$LD_LIBRARY_PATH:../../libs/mgclient/lib python runner.py --workloads-root-directory .
-
-      - name: Run stress test (plain)
-        run: |
-          cd tests/stress
-          ./continuous_integration
-
-      - name: Run stress test (SSL)
-        run: |
-          cd tests/stress
-          ./continuous_integration --use-ssl
-
-      - name: Run durability test
-        run: |
-          cd tests/stress
-          source ve3/bin/activate
-          python3 durability --num-steps 5
-
-      - name: Create enterprise DEB package
-        run: |
-          # Activate toolchain.
-          source /opt/toolchain-v4/activate
-
-          cd build
-
-          # create mgconsole
-          # we use the -B to force the build
-          make -j$THREADS -B mgconsole
-
-          # Create enterprise DEB package.
-          mkdir output && cd output
-          cpack -G DEB --config ../CPackConfig.cmake
-
-      - name: Save enterprise DEB package
-        uses: actions/upload-artifact@v2
-        with:
-          name: "Enterprise DEB package"
-          path: build/output/memgraph*.deb
-
-      - name: Save test data
-        uses: actions/upload-artifact@v2
-        if: always()
-        with:
-          name: "Test data"
-          path: |
-            # multiple paths could be defined
-            build/logs
-
-  release_jepsen_test:
-    name: "Release Jepsen Test"
-    runs-on: [self-hosted, Linux, X64, Debian10, JepsenControl]
-    #continue-on-error: true
-    env:
-      THREADS: 24
-      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
-      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
-
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v2
-        with:
-          # Number of commits to fetch. `0` indicates all history for all
-          # branches and tags. (default: 1)
-          fetch-depth: 0
-
-      - name: Build release binaries
-        run: |
-          # Activate toolchain.
-          source /opt/toolchain-v4/activate
-
-          # Initialize dependencies.
-          ./init
-
-          # Build only memgraph release binarie.
-          cd build
-          cmake -DCMAKE_BUILD_TYPE=release ..
-          make -j$THREADS memgraph
-
-      - name: Run Jepsen tests
-        run: |
-          cd tests/jepsen
-          ./run.sh test --binary ../../build/memgraph --run-args "test-all --node-configs resources/node-config.edn" --ignore-run-stdout-logs --ignore-run-stderr-logs
-
-      - name: Save Jepsen report
-        uses: actions/upload-artifact@v2
-        if: ${{ always() }}
-        with:
-          name: "Jepsen Report"
-          path: tests/jepsen/Jepsen.tar.gz
-
-  release_benchmarks:
-    name: "Release benchmarks"
-    runs-on: [self-hosted, Linux, X64, Diff, Gen7]
-    env:
-      THREADS: 24
-      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
-      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
-
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v2
-        with:
-          # Number of commits to fetch. `0` indicates all history for all
-          # branches and tags. (default: 1)
-          fetch-depth: 0
-
-      - name: Build release binaries
-        run: |
-          # Activate toolchain.
-          source /opt/toolchain-v4/activate
-
-          # Initialize dependencies.
-          ./init
-
-          # Build only memgraph release binaries.
-          cd build
-          cmake -DCMAKE_BUILD_TYPE=release ..
-          make -j$THREADS
-
-      - name: Run macro benchmarks
-        run: |
-          cd tests/macro_benchmark
-          ./harness QuerySuite MemgraphRunner \
-            --groups aggregation 1000_create unwind_create dense_expand match \
-            --no-strict
-
-      - name: Get branch name (merge)
-        if: github.event_name != 'pull_request'
-        shell: bash
-        run: echo "BRANCH_NAME=$(echo ${GITHUB_REF#refs/heads/} | tr / -)" >> $GITHUB_ENV
-
-      - name: Get branch name (pull request)
-        if: github.event_name == 'pull_request'
-        shell: bash
-        run: echo "BRANCH_NAME=$(echo ${GITHUB_HEAD_REF} | tr / -)" >> $GITHUB_ENV
-
-      - name: Upload macro benchmark results
-        run: |
-          cd tools/bench-graph-client
-          virtualenv -p python3 ve3
-          source ve3/bin/activate
-          pip install -r requirements.txt
-          ./main.py --benchmark-name "macro_benchmark" \
-                    --benchmark-results-path "../../tests/macro_benchmark/.harness_summary" \
-                    --github-run-id "${{ github.run_id }}" \
-                    --github-run-number "${{ github.run_number }}" \
-                    --head-branch-name "${{ env.BRANCH_NAME }}"
-
-      - name: Run mgbench
-        run: |
-          cd tests/mgbench
-          ./benchmark.py --num-workers-for-benchmark 12 --export-results benchmark_result.json pokec/medium/*/*
-
-      - name: Upload mgbench results
-        run: |
-          cd tools/bench-graph-client
-          virtualenv -p python3 ve3
-          source ve3/bin/activate
-          pip install -r requirements.txt
-          ./main.py --benchmark-name "mgbench" \
-                    --benchmark-results-path "../../tests/mgbench/benchmark_result.json" \
-                    --github-run-id "${{ github.run_id }}" \
-                    --github-run-number "${{ github.run_number }}" \
-                    --head-branch-name "${{ env.BRANCH_NAME }}"
+          LD_LIBRARY_PATH=$LD_LIBRARY_PATH:../../libs/mgclient/lib python runner.py --workloads-root-directory ./distributed_queries

.github/workflows/full_clang_tidy.yaml

@@ -14,7 +14,7 @@ jobs:
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -39,7 +39,7 @@ jobs:
           source /opt/toolchain-v4/activate
 
           # The results are also written to standard output in order to retain them in the logs
-          ./tools/github/clang-tidy/run-clang-tidy.py -p build -j $THREADS -clang-tidy-binary=/opt/toolchain-v4/bin/clang-tidy "$PWD/src/*" |
+          ./tools/github/clang-tidy/run-clang-tidy.py -p build -j $THREADS -extra-arg="-DMG_CLANG_TIDY_CHECK" -clang-tidy-binary=/opt/toolchain-v4/bin/clang-tidy "$PWD/src/*" |
             tee ./build/full_clang_tidy_output.txt
 
       - name: Summarize clang-tidy results

.github/workflows/package_all.yaml

@@ -6,79 +6,79 @@ 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"
         run: |
           ./release/package/run.sh package centos-7
       - name: "Upload package"
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           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
+        uses: actions/upload-artifact@v3
         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"
         run: |
           ./release/package/run.sh package debian-10
       - name: "Upload package"
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: debian-10
           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"
         run: |
           ./release/package/run.sh package debian-11
       - name: "Upload package"
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: debian-11
           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"
@@ -87,58 +87,92 @@ jobs:
           ./run.sh package debian-11 --for-docker
           ./run.sh docker
       - name: "Upload package"
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: docker
           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"
         run: |
           ./release/package/run.sh package ubuntu-18.04
       - name: "Upload package"
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: ubuntu-1804
           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"
         run: |
           ./release/package/run.sh package ubuntu-20.04
       - name: "Upload package"
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           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@v3
+        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"
         run: |
           ./release/package/run.sh package debian-11 --for-platform
       - name: "Upload package"
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         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@v3
+        with:
+          name: debian-11-arm
+          path: build/output/debian-11-arm/memgraph*.deb

.github/workflows/release_centos8.yaml

@@ -17,7 +17,7 @@ jobs:
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -55,7 +55,7 @@ jobs:
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -97,7 +97,7 @@ jobs:
           tar -czf code_coverage.tar.gz coverage.json html report.json summary.rmu
 
       - name: Save code coverage
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: "Code coverage"
           path: tools/github/generated/code_coverage.tar.gz
@@ -112,7 +112,7 @@ jobs:
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -173,7 +173,7 @@ jobs:
           ./cppcheck_and_clang_format diff
 
       - name: Save cppcheck and clang-format errors
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: "Code coverage"
           path: tools/github/cppcheck_and_clang_format.txt
@@ -189,7 +189,7 @@ jobs:
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -225,7 +225,7 @@ jobs:
           rpmlint memgraph*.rpm
 
       - name: Save enterprise RPM package
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: "Enterprise RPM package"
           path: build/output/memgraph*.rpm
@@ -262,7 +262,7 @@ jobs:
           ./continuous_integration
 
       - name: Save quality assurance status
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: "GQL Behave Status"
           path: |

.github/workflows/release_debian10.yaml

@@ -17,7 +17,7 @@ jobs:
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -55,7 +55,7 @@ jobs:
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -97,7 +97,7 @@ jobs:
           tar -czf code_coverage.tar.gz coverage.json html report.json summary.rmu
 
       - name: Save code coverage
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: "Code coverage"
           path: tools/github/generated/code_coverage.tar.gz
@@ -112,7 +112,7 @@ jobs:
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -173,7 +173,7 @@ jobs:
           ./cppcheck_and_clang_format diff
 
       - name: Save cppcheck and clang-format errors
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: "Code coverage"
           path: tools/github/cppcheck_and_clang_format.txt
@@ -189,7 +189,7 @@ jobs:
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -224,7 +224,7 @@ jobs:
           cpack -G DEB --config ../CPackConfig.cmake
 
       - name: Save enterprise DEB package
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: "Enterprise DEB package"
           path: build/output/memgraph*.deb
@@ -261,7 +261,7 @@ jobs:
           ./continuous_integration
 
       - name: Save quality assurance status
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: "GQL Behave Status"
           path: |
@@ -324,7 +324,7 @@ jobs:
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -349,7 +349,7 @@ jobs:
           ./run.sh test --binary ../../build/memgraph --run-args "test-all --node-configs resources/node-config.edn" --ignore-run-stdout-logs --ignore-run-stderr-logs
 
       - name: Save Jepsen report
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         if: ${{ always() }}
         with:
           name: "Jepsen Report"

.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:
@@ -15,7 +19,7 @@ jobs:
       DOCKER_REPOSITORY_NAME: memgraph
     steps:
       - name: Checkout
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
 
       - name: Set up QEMU
         uses: docker/setup-qemu-action@v1
@@ -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

.github/workflows/release_ubuntu2004.yaml

@@ -17,7 +17,7 @@ jobs:
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -55,7 +55,7 @@ jobs:
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -97,7 +97,7 @@ jobs:
           tar -czf code_coverage.tar.gz coverage.json html report.json summary.rmu
 
       - name: Save code coverage
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: "Code coverage"
           path: tools/github/generated/code_coverage.tar.gz
@@ -112,7 +112,7 @@ jobs:
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -173,7 +173,7 @@ jobs:
           ./cppcheck_and_clang_format diff
 
       - name: Save cppcheck and clang-format errors
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: "Code coverage"
           path: tools/github/cppcheck_and_clang_format.txt
@@ -189,7 +189,7 @@ jobs:
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -224,7 +224,7 @@ jobs:
           cpack -G DEB --config ../CPackConfig.cmake
 
       - name: Save enterprise DEB package
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: "Enterprise DEB package"
           path: build/output/memgraph*.deb
@@ -261,7 +261,7 @@ jobs:
           ./continuous_integration
 
       - name: Save quality assurance status
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: "GQL Behave Status"
           path: |

.gitignore

@@ -23,6 +23,8 @@ cmake-build-*
 cmake/DownloadProject/
 dist/
 src/query/frontend/opencypher/generated/
+src/query/v2/frontend/opencypher/generated/
+src/parser/opencypher/generated
 tags
 ve/
 ve3/
@@ -50,15 +52,25 @@ src/distributed/pull_produce_rpc_messages.hpp
 src/distributed/storage_gc_rpc_messages.hpp
 src/distributed/token_sharing_rpc_messages.hpp
 src/distributed/updates_rpc_messages.hpp
+src/query/v2/frontend/ast/ast.hpp
 src/query/frontend/ast/ast.hpp
+src/storage/v3/bindings/ast/ast.hpp
 src/query/distributed/frontend/ast/ast_serialization.hpp
+src/query/v2/distributed/frontend/ast/ast_serialization.hpp
 src/durability/distributed/state_delta.hpp
 src/durability/single_node/state_delta.hpp
 src/durability/single_node_ha/state_delta.hpp
 src/query/frontend/semantic/symbol.hpp
+src/query/v2/frontend/semantic/symbol.hpp
+src/expr/semantic/symbol.hpp
 src/query/distributed/frontend/semantic/symbol_serialization.hpp
+src/query/v2/distributed/frontend/semantic/symbol_serialization.hpp
 src/query/distributed/plan/ops.hpp
+src/query/v2/distributed/plan/ops.hpp
 src/query/plan/operator.hpp
+src/query/v2/plan/operator.hpp
+src/parser/opencypher/generated
+src/expr/semantic/symbol.hpp
 src/raft/log_entry.hpp
 src/raft/raft_rpc_messages.hpp
 src/raft/snapshot_metadata.hpp

.pre-commit-config.yaml

@@ -6,18 +6,15 @@ repos:
       - id: end-of-file-fixer
       - id: trailing-whitespace
   - repo: https://github.com/psf/black
-    rev: 22.3.0
+    rev: 22.10.0
     hooks:
       - id: black
-        args: # arguments to configure black
-          - --line-length=120
-          - --include='\.pyi?$'
-          # these folders wont be formatted by black
-          - --exclude="""\.git |
-            \.__pycache__|
-            build|
-            libs|
-            .cache"""
+  - repo: https://github.com/pycqa/isort
+    rev: 5.10.1
+    hooks:
+      - id: isort
+        name: isort (python)
+        args: ["--profile", "black"]
   - repo: https://github.com/pre-commit/mirrors-clang-format
     rev: v13.0.0
     hooks:

CMakeLists.txt

@@ -182,7 +182,8 @@ set(CMAKE_CXX_STANDARD_REQUIRED ON)
 # c99-designator is disabled because of required mixture of designated and
 # non-designated initializers in Python Query Module code (`py_module.cpp`).
 set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wall \
-    -Werror=switch -Werror=switch-bool -Werror=return-type \
+    -Werror=switch -Werror=switch-bool -Werror=implicit-fallthrough \
+    -Werror=return-type \
     -Werror=return-stack-address \
     -Wno-c99-designator \
     -DBOOST_ASIO_USE_TS_EXECUTOR_AS_DEFAULT")

CODEOWNERS

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

config/flags.yaml

@@ -83,13 +83,9 @@ modifications:
     value: "true"
     override: true
 
-  - name: "query_modules_directory"
-    value: "/usr/lib/memgraph/query_modules"
-    override: true
-
-  - name: "auth_module_executable"
-    value: "/usr/lib/memgraph/auth_module/example.py"
-    override: false
+  # - name: "query_modules_directory"
+  #   value: "/usr/lib/memgraph/query_modules"
+  #   override: true
 
   - name: "memory_limit"
     value: "0"

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/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 +139,13 @@ done;
 # Install precommit hook
 python3 -m pip install pre-commit
 python3 -m pre_commit install
+
+# Install py format tools
+echo "Install black formatter"
+python3 -m pip install black==22.10.*
+echo "Install isort"
+python3 -m pip install isort==5.10.*
+
+
+# Link `include/mgp.py` with `release/mgp/mgp.py`
+ln -v -f include/mgp.py release/mgp/mgp.py

libs/.gitignore

@@ -4,5 +4,5 @@
 !cleanup.sh
 !CMakeLists.txt
 !__main.cpp
-!jemalloc.cmake
 !pulsar.patch
+!antlr4.10.1.patch

libs/CMakeLists.txt

@@ -106,6 +106,7 @@ import_external_library(antlr4 STATIC
              -DWITH_LIBCXX=OFF # because of debian bug
              -DCMAKE_SKIP_INSTALL_ALL_DEPENDENCY=true
              -DCMAKE_CXX_STANDARD=20
+             -DANTLR_BUILD_CPP_TESTS=OFF
   BUILD_COMMAND $(MAKE) antlr4_static
   INSTALL_COMMAND $(MAKE) install)
 

libs/antlr4.10.1.patch

@@ -0,0 +1,13 @@
+diff --git a/runtime/Cpp/runtime/CMakeLists.txt b/runtime/Cpp/runtime/CMakeLists.txt
+index baf46cac9..2e7756de8 100644
+--- a/runtime/Cpp/runtime/CMakeLists.txt
++++ b/runtime/Cpp/runtime/CMakeLists.txt
+@@ -134,7 +134,7 @@ set_target_properties(antlr4_static
+                                  ARCHIVE_OUTPUT_DIRECTORY ${LIB_OUTPUT_DIR}
+                                  COMPILE_FLAGS "${disabled_compile_warnings} ${extra_static_compile_flags}")
+
+-install(TARGETS antlr4_shared
++install(TARGETS antlr4_shared OPTIONAL
+         EXPORT antlr4-targets
+         ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR}
+         LIBRARY DESTINATION ${CMAKE_INSTALL_LIBDIR}

libs/antlr4.patch

@@ -1,43 +0,0 @@
-diff --git a/runtime/Cpp/runtime/CMakeLists.txt b/runtime/Cpp/runtime/CMakeLists.txt
-index a8503bb..11362cf 100644
---- a/runtime/Cpp/runtime/CMakeLists.txt
-+++ b/runtime/Cpp/runtime/CMakeLists.txt
-@@ -5,8 +5,8 @@ set(THIRDPARTY_DIR ${CMAKE_BINARY_DIR}/runtime/thirdparty)
- set(UTFCPP_DIR ${THIRDPARTY_DIR}/utfcpp)
- ExternalProject_Add(
-   utfcpp
--  GIT_REPOSITORY        "git://github.com/nemtrif/utfcpp"
--  GIT_TAG               "v3.1.1"
-+  GIT_REPOSITORY        "https://github.com/nemtrif/utfcpp"
-+  GIT_TAG               "v3.2.1"
-   SOURCE_DIR            ${UTFCPP_DIR}
-   UPDATE_DISCONNECTED   1
-   CMAKE_ARGS            -DCMAKE_INSTALL_PREFIX=${UTFCPP_DIR}/install -Dgtest_force_shared_crt=ON
-@@ -118,7 +118,7 @@ set_target_properties(antlr4_static
-                                  ARCHIVE_OUTPUT_DIRECTORY ${LIB_OUTPUT_DIR}
-                                  COMPILE_FLAGS "${disabled_compile_warnings} ${extra_static_compile_flags}")
- 
--install(TARGETS antlr4_shared
-+install(TARGETS antlr4_shared OPTIONAL
-         DESTINATION lib
-         EXPORT antlr4-targets)
- install(TARGETS antlr4_static
-diff --git a/runtime/Cpp/runtime/src/support/Any.h b/runtime/Cpp/runtime/src/support/Any.h
-index 468db98..65a473b 100644
---- a/runtime/Cpp/runtime/src/support/Any.h
-+++ b/runtime/Cpp/runtime/src/support/Any.h
-@@ -122,12 +122,12 @@ private:
-     }
- 
-   private:
--    template<int N = 0, typename std::enable_if<N == N && std::is_nothrow_copy_constructible<T>::value, int>::type = 0>
-+    template<int N = 0, typename std::enable_if<N == N && std::is_copy_constructible<T>::value, int>::type = 0>
-     Base* clone() const {
-       return new Derived<T>(value);
-     }
- 
--    template<int N = 0, typename std::enable_if<N == N && !std::is_nothrow_copy_constructible<T>::value, int>::type = 0>
-+    template<int N = 0, typename std::enable_if<N == N && !std::is_copy_constructible<T>::value, int>::type = 0>
-     Base* clone() const {
-       return nullptr;
-     }

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)

libs/setup.sh

@@ -105,7 +105,7 @@ repo_clone_try_double () {
 # Download from primary_urls might fail because the cache is not installed.
 declare -A primary_urls=(
   ["antlr4-code"]="http://$local_cache_host/git/antlr4.git"
-  ["antlr4-generator"]="http://$local_cache_host/file/antlr-4.9.2-complete.jar"
+  ["antlr4-generator"]="http://$local_cache_host/file/antlr-4.10.1-complete.jar"
   ["cppitertools"]="http://$local_cache_host/git/cppitertools.git"
   ["rapidcheck"]="http://$local_cache_host/git/rapidcheck.git"
   ["gbenchmark"]="http://$local_cache_host/git/benchmark.git"
@@ -116,7 +116,7 @@ declare -A primary_urls=(
   ["pymgclient"]="http://$local_cache_host/git/pymgclient.git"
   ["mgconsole"]="http://$local_cache_host/git/mgconsole.git"
   ["spdlog"]="http://$local_cache_host/git/spdlog"
-  ["nlohmann"]="http://$local_cache_host/file/nlohmann/json/4f8fba14066156b73f1189a2b8bd568bde5284c5/single_include/nlohmann/json.hpp"
+  ["nlohmann"]="http://$local_cache_host/file/nlohmann/json/9d69186291aca4f0137b69c1dee313b391ff564c/single_include/nlohmann/json.hpp"
   ["neo4j"]="http://$local_cache_host/file/neo4j-community-3.2.3-unix.tar.gz"
   ["librdkafka"]="http://$local_cache_host/git/librdkafka.git"
   ["protobuf"]="http://$local_cache_host/git/protobuf.git"
@@ -130,7 +130,7 @@ declare -A primary_urls=(
 # should fail.
 declare -A secondary_urls=(
   ["antlr4-code"]="https://github.com/antlr/antlr4.git"
-  ["antlr4-generator"]="http://www.antlr.org/download/antlr-4.9.2-complete.jar"
+  ["antlr4-generator"]="https://www.antlr.org/download/antlr-4.10.1-complete.jar"
   ["cppitertools"]="https://github.com/ryanhaining/cppitertools.git"
   ["rapidcheck"]="https://github.com/emil-e/rapidcheck.git"
   ["gbenchmark"]="https://github.com/google/benchmark.git"
@@ -141,7 +141,7 @@ declare -A secondary_urls=(
   ["pymgclient"]="https://github.com/memgraph/pymgclient.git"
   ["mgconsole"]="http://github.com/memgraph/mgconsole.git"
   ["spdlog"]="https://github.com/gabime/spdlog"
-  ["nlohmann"]="https://raw.githubusercontent.com/nlohmann/json/4f8fba14066156b73f1189a2b8bd568bde5284c5/single_include/nlohmann/json.hpp"
+  ["nlohmann"]="https://raw.githubusercontent.com/nlohmann/json/9d69186291aca4f0137b69c1dee313b391ff564c/single_include/nlohmann/json.hpp"
   ["neo4j"]="https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/neo4j-community-3.2.3-unix.tar.gz"
   ["librdkafka"]="https://github.com/edenhill/librdkafka.git"
   ["protobuf"]="https://github.com/protocolbuffers/protobuf.git"
@@ -152,10 +152,10 @@ declare -A secondary_urls=(
 # antlr
 file_get_try_double "${primary_urls[antlr4-generator]}" "${secondary_urls[antlr4-generator]}"
 
-antlr4_tag="4.9.2" # v4.9.2
+antlr4_tag="4.10.1" # v4.10.1
 repo_clone_try_double "${primary_urls[antlr4-code]}" "${secondary_urls[antlr4-code]}" "antlr4" "$antlr4_tag" true
 pushd antlr4
-git apply ../antlr4.patch
+git apply ../antlr4.10.1.patch
 popd
 
 # cppitertools v2.0 2019-12-23
@@ -171,7 +171,7 @@ benchmark_tag="v1.6.0"
 repo_clone_try_double "${primary_urls[gbenchmark]}" "${secondary_urls[gbenchmark]}" "benchmark" "$benchmark_tag" true
 
 # google test
-googletest_tag="release-1.8.0"
+googletest_tag="release-1.12.1"
 repo_clone_try_double "${primary_urls[gtest]}" "${secondary_urls[gtest]}" "googletest" "$googletest_tag" true
 
 # libbcrypt
@@ -199,7 +199,7 @@ git apply ../rocksdb.patch
 popd
 
 # mgclient
-mgclient_tag="96e95c6845463cbe88948392be58d26da0d5ffd3" # (2022-02-08)
+mgclient_tag="v1.4.0" # (2022-06-14)
 repo_clone_try_double "${primary_urls[mgclient]}" "${secondary_urls[mgclient]}" "mgclient" "$mgclient_tag"
 sed -i 's/\${CMAKE_INSTALL_LIBDIR}/lib/' mgclient/src/CMakeLists.txt
 

pyproject.toml

@@ -0,0 +1,12 @@
+[tool.black]
+line-length = 120
+include = '\.pyi?$'
+extend-exclude = '''
+/(
+    | .git
+    | .__pycache__
+    | build
+    | libs
+    | .cache
+)/
+'''

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

@@ -5,16 +5,23 @@ add_subdirectory(lisp)
 add_subdirectory(utils)
 add_subdirectory(requests)
 add_subdirectory(io)
+add_subdirectory(io/simulator)
 add_subdirectory(kvstore)
 add_subdirectory(telemetry)
 add_subdirectory(communication)
 add_subdirectory(memory)
 add_subdirectory(storage/v2)
+add_subdirectory(storage/v3)
 add_subdirectory(integrations)
 add_subdirectory(query)
+add_subdirectory(query/v2)
 add_subdirectory(slk)
 add_subdirectory(rpc)
 add_subdirectory(auth)
+add_subdirectory(parser)
+add_subdirectory(expr)
+add_subdirectory(coordinator)
+add_subdirectory(functions)
 
 if (MG_ENTERPRISE)
   add_subdirectory(audit)
@@ -31,13 +38,13 @@ include_directories(${CMAKE_CURRENT_BINARY_DIR})
 # Memgraph Single Node v2 Executable
 # ----------------------------------------------------------------------------
 set(mg_single_node_v2_sources
-    glue/communication.cpp
-    memgraph.cpp
-    glue/auth.cpp
+        glue/v2/communication.cpp
+        memgraph.cpp
+        glue/v2/auth.cpp
 )
 
 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)
+    telemetry_lib mg-query-v2 mg-communication mg-memory mg-utils mg-auth mg-license mg-settings mg-io mg-coordinator)
 if (MG_ENTERPRISE)
   # These are enterprise subsystems
   set(mg_single_node_v2_libs ${mg_single_node_v2_libs} mg-audit)
@@ -120,19 +127,3 @@ install(CODE "file(MAKE_DIRECTORY \$ENV{DESTDIR}/var/log/memgraph
 # ----------------------------------------------------------------------------
 # Memgraph CSV Import Tool Executable
 # ----------------------------------------------------------------------------
-
-add_executable(mg_import_csv mg_import_csv.cpp)
-target_link_libraries(mg_import_csv mg-storage-v2)
-
-# Strip the executable in release build.
-if (lower_build_type STREQUAL "release")
-  add_custom_command(TARGET mg_import_csv POST_BUILD
-                     COMMAND strip -s mg_import_csv
-                     COMMENT "Stripping symbols and sections from mg_import_csv")
-endif()
-
-install(TARGETS mg_import_csv RUNTIME DESTINATION bin)
-
-# ----------------------------------------------------------------------------
-# Memgraph CSV Import Tool Executable
-# ----------------------------------------------------------------------------

src/auth/models.cpp

@@ -37,7 +37,7 @@ const std::vector<Permission> kPermissionsAll = {
     Permission::CONSTRAINT, Permission::DUMP,      Permission::AUTH,        Permission::REPLICATION,
     Permission::DURABILITY, Permission::READ_FILE, Permission::FREE_MEMORY, Permission::TRIGGER,
     Permission::CONFIG,     Permission::STREAM,    Permission::MODULE_READ, Permission::MODULE_WRITE,
-    Permission::WEBSOCKET};
+    Permission::WEBSOCKET,  Permission::SCHEMA};
 }  // namespace
 
 std::string PermissionToString(Permission permission) {
@@ -84,6 +84,8 @@ std::string PermissionToString(Permission permission) {
       return "MODULE_WRITE";
     case Permission::WEBSOCKET:
       return "WEBSOCKET";
+    case Permission::SCHEMA:
+      return "SCHEMA";
   }
 }
 

src/auth/models.hpp

@@ -38,7 +38,8 @@ enum class Permission : uint64_t {
   STREAM       = 1U << 17U,
   MODULE_READ  = 1U << 18U,
   MODULE_WRITE = 1U << 19U,
-  WEBSOCKET    = 1U << 20U
+  WEBSOCKET    = 1U << 20U,
+  SCHEMA       = 1U << 21U
 };
 // clang-format on
 

src/common/errors.hpp

@@ -0,0 +1,68 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+#pragma once
+
+#include <cstdint>
+#include <string_view>
+
+namespace memgraph::common {
+
+enum class ErrorCode : uint8_t {
+  SERIALIZATION_ERROR,
+  NONEXISTENT_OBJECT,
+  DELETED_OBJECT,
+  VERTEX_HAS_EDGES,
+  PROPERTIES_DISABLED,
+  VERTEX_ALREADY_INSERTED,
+  // Schema Violations
+  SCHEMA_NO_SCHEMA_DEFINED_FOR_LABEL,
+  SCHEMA_VERTEX_PROPERTY_WRONG_TYPE,
+  SCHEMA_VERTEX_UPDATE_PRIMARY_KEY,
+  SCHEMA_VERTEX_UPDATE_PRIMARY_LABEL,
+  SCHEMA_VERTEX_SECONDARY_LABEL_IS_PRIMARY,
+  SCHEMA_VERTEX_PRIMARY_PROPERTIES_UNDEFINED,
+
+  OBJECT_NOT_FOUND,
+};
+
+constexpr std::string_view ErrorCodeToString(const ErrorCode code) {
+  switch (code) {
+    case ErrorCode::SERIALIZATION_ERROR:
+      return "SERIALIZATION_ERROR";
+    case ErrorCode::NONEXISTENT_OBJECT:
+      return "NONEXISTENT_OBJECT";
+    case ErrorCode::DELETED_OBJECT:
+      return "DELETED_OBJECT";
+    case ErrorCode::VERTEX_HAS_EDGES:
+      return "VERTEX_HAS_EDGES";
+    case ErrorCode::PROPERTIES_DISABLED:
+      return "PROPERTIES_DISABLED";
+    case ErrorCode::VERTEX_ALREADY_INSERTED:
+      return "VERTEX_ALREADY_INSERTED";
+    case ErrorCode::SCHEMA_NO_SCHEMA_DEFINED_FOR_LABEL:
+      return "SCHEMA_NO_SCHEMA_DEFINED_FOR_LABEL";
+    case ErrorCode::SCHEMA_VERTEX_PROPERTY_WRONG_TYPE:
+      return "SCHEMA_VERTEX_PROPERTY_WRONG_TYPE";
+    case ErrorCode::SCHEMA_VERTEX_UPDATE_PRIMARY_KEY:
+      return "SCHEMA_VERTEX_UPDATE_PRIMARY_KEY";
+    case ErrorCode::SCHEMA_VERTEX_UPDATE_PRIMARY_LABEL:
+      return "SCHEMA_VERTEX_UPDATE_PRIMARY_LABEL";
+    case ErrorCode::SCHEMA_VERTEX_SECONDARY_LABEL_IS_PRIMARY:
+      return "SCHEMA_VERTEX_SECONDARY_LABEL_IS_PRIMARY";
+    case ErrorCode::SCHEMA_VERTEX_PRIMARY_PROPERTIES_UNDEFINED:
+      return "SCHEMA_VERTEX_PRIMARY_PROPERTIES_UNDEFINED";
+    case ErrorCode::OBJECT_NOT_FOUND:
+      return "OBJECT_NOT_FOUND";
+  }
+}
+
+}  // namespace memgraph::common

src/common/types.hpp

@@ -0,0 +1,19 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+#pragma once
+
+#include <cstdint>
+
+namespace memgraph::common {
+enum class SchemaType : uint8_t { BOOL, INT, STRING, DATE, LOCALTIME, LOCALDATETIME, DURATION };
+
+}  // namespace memgraph::common

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

@@ -74,7 +74,7 @@ State RunHandlerV4(Signature signature, TSession &session, State state, Marker m
     }
     case Signature::Route: {
       if constexpr (bolt_minor >= 3) {
-        if (signature == Signature::Route) return HandleRoute<TSession>(session);
+        return HandleRoute<TSession>(session);
       } else {
         spdlog::trace("Supported only in bolt v4.3");
         return State::Close;

src/communication/v2/listener.hpp

@@ -30,6 +30,7 @@
 #include "communication/context.hpp"
 #include "communication/v2/pool.hpp"
 #include "communication/v2/session.hpp"
+#include "utils/message.hpp"
 #include "utils/spin_lock.hpp"
 #include "utils/synchronized.hpp"
 
@@ -58,10 +59,10 @@ class Listener final : public std::enable_shared_from_this<Listener<TSession, TS
   bool IsRunning() const noexcept { return alive_.load(std::memory_order_relaxed); }
 
  private:
-  Listener(boost::asio::io_context &io_context, TSessionData *data, ServerContext *server_context,
+  Listener(boost::asio::io_context &io_context, TSessionData &data, ServerContext *server_context,
            tcp::endpoint &endpoint, const std::string_view service_name, const uint64_t inactivity_timeout_sec)
       : io_context_(io_context),
-        data_(data),
+        data_(&data),
         server_context_(server_context),
         acceptor_(io_context_),
         endpoint_{endpoint},
@@ -110,7 +111,7 @@ class Listener final : public std::enable_shared_from_this<Listener<TSession, TS
       return OnError(ec, "accept");
     }
 
-    auto session = SessionHandler::Create(std::move(socket), data_, *server_context_, endpoint_, inactivity_timeout_,
+    auto session = SessionHandler::Create(std::move(socket), *data_, *server_context_, endpoint_, inactivity_timeout_,
                                           service_name_);
     session->Start();
     DoAccept();

src/communication/v2/server.hpp

@@ -72,7 +72,7 @@ class Server final {
    * Constructs and binds server to endpoint, operates on session data and
    * invokes workers_count workers
    */
-  Server(ServerEndpoint &endpoint, TSessionData *session_data, ServerContext *server_context,
+  Server(ServerEndpoint &endpoint, TSessionData &session_data, ServerContext *server_context,
          const int inactivity_timeout_sec, const std::string_view service_name,
          size_t workers_count = std::thread::hardware_concurrency())
       : endpoint_{endpoint},

src/communication/v2/session.hpp

@@ -41,6 +41,7 @@
 #include <boost/beast/websocket/rfc6455.hpp>
 #include <boost/system/detail/error_code.hpp>
 
+#include "communication/buffer.hpp"
 #include "communication/context.hpp"
 #include "communication/exceptions.hpp"
 #include "utils/logging.hpp"
@@ -105,9 +106,16 @@ 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);
 
@@ -132,7 +140,7 @@ class WebsocketSession : public std::enable_shared_from_this<WebsocketSession<TS
 
  private:
   // Take ownership of the socket
-  explicit WebsocketSession(tcp::socket &&socket, TSessionData *data, tcp::endpoint endpoint,
+  explicit WebsocketSession(tcp::socket &&socket, TSessionData &data, tcp::endpoint endpoint,
                             std::string_view service_name)
       : ws_(std::move(socket)),
         strand_{boost::asio::make_strand(ws_.get_executor())},
@@ -162,7 +170,7 @@ 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;
@@ -304,13 +312,13 @@ class Session final : public std::enable_shared_from_this<Session<TSession, TSes
   }
 
  private:
-  explicit Session(tcp::socket &&socket, TSessionData *data, ServerContext &server_context, tcp::endpoint endpoint,
+  explicit Session(tcp::socket &&socket, TSessionData &data, ServerContext &server_context, tcp::endpoint endpoint,
                    const std::chrono::seconds inactivity_timeout_sec, std::string_view service_name)
       : socket_(CreateSocket(std::move(socket), server_context)),
         strand_{boost::asio::make_strand(GetExecutor())},
         output_stream_([this](const uint8_t *data, size_t len, bool have_more) { return Write(data, len, have_more); }),
         session_(data, endpoint, input_buffer_.read_end(), &output_stream_),
-        data_{data},
+        data_{&data},
         endpoint_{endpoint},
         remote_endpoint_{GetRemoteEndpoint()},
         service_name_{service_name},
@@ -322,7 +330,8 @@ 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() {
@@ -365,7 +374,7 @@ class Session final : public std::enable_shared_from_this<Session<TSession, TSes
         spdlog::info("Switching {} to websocket connection", remote_endpoint_);
         if (std::holds_alternative<TCPSocket>(socket_)) {
           auto sock = std::get<TCPSocket>(std::move(socket_));
-          WebsocketSession<TSession, TSessionData>::Create(std::move(sock), data_, endpoint_, service_name_)
+          WebsocketSession<TSession, TSessionData>::Create(std::move(sock), *data_, endpoint_, service_name_)
               ->DoAccept(parser.release());
           execution_active_ = false;
           return;
@@ -457,7 +466,7 @@ class Session final : public std::enable_shared_from_this<Session<TSession, TSes
     if (timeout_timer_.expiry() <= boost::asio::steady_timer::clock_type::now()) {
       // The deadline has passed. Stop the session. The other actors will
       // terminate as soon as possible.
-      spdlog::info("Shutting down session after {} of inactivity", timeout_seconds_);
+      spdlog::info("Shutting down session after {} of inactivity", timeout_seconds_.count());
       DoShutdown();
     } else {
       // Put the actor back to sleep.

src/coordinator/CMakeLists.txt

@@ -0,0 +1,9 @@
+set(coordinator_src_files
+    coordinator.cpp
+    shard_map.cpp)
+
+find_package(fmt REQUIRED)
+find_package(Threads REQUIRED)
+
+add_library(mg-coordinator STATIC ${coordinator_src_files})
+target_link_libraries(mg-coordinator stdc++fs Threads::Threads fmt::fmt mg-utils mg-storage-v3)

src/coordinator/coordinator.cpp

@@ -0,0 +1,129 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+#include <coordinator/coordinator.hpp>
+
+namespace memgraph::coordinator {
+
+CoordinatorWriteResponses Coordinator::ApplyWrite(HeartbeatRequest &&heartbeat_request) {
+  spdlog::info("Coordinator handling HeartbeatRequest");
+
+  // add this storage engine to any under-replicated shards that it is not already a part of
+
+  auto initializing_rsms_for_shard_manager =
+      shard_map_.AssignShards(heartbeat_request.from_storage_manager, heartbeat_request.initialized_rsms);
+
+  return HeartbeatResponse{
+      .shards_to_initialize = initializing_rsms_for_shard_manager,
+  };
+}
+
+CoordinatorWriteResponses Coordinator::ApplyWrite(HlcRequest &&hlc_request) {
+  HlcResponse res{};
+
+  auto hlc_shard_map = shard_map_.GetHlc();
+
+  MG_ASSERT(!(hlc_request.last_shard_map_version.logical_id > hlc_shard_map.logical_id));
+
+  res.new_hlc = Hlc{
+      .logical_id = ++highest_allocated_timestamp_,
+      // TODO(tyler) probably pass some more context to the Coordinator here
+      // so that we can use our wall clock and enforce monotonicity.
+      // .coordinator_wall_clock = io_.Now(),
+  };
+
+  // Allways return fresher shard_map for now.
+  res.fresher_shard_map = std::make_optional(shard_map_);
+
+  return res;
+}
+
+CoordinatorWriteResponses Coordinator::ApplyWrite(AllocateEdgeIdBatchRequest &&ahr) {
+  AllocateEdgeIdBatchResponse res{};
+
+  uint64_t low = highest_allocated_edge_id_;
+
+  highest_allocated_edge_id_ += ahr.batch_size;
+
+  uint64_t high = highest_allocated_edge_id_;
+
+  res.low = low;
+  res.high = high;
+
+  return res;
+}
+
+/// This splits the shard immediately beneath the provided
+/// split key, keeping the assigned peers identical for now,
+/// but letting them be gradually migrated over time.
+CoordinatorWriteResponses Coordinator::ApplyWrite(SplitShardRequest &&split_shard_request) {
+  SplitShardResponse res{};
+
+  if (split_shard_request.previous_shard_map_version != shard_map_.shard_map_version) {
+    res.success = false;
+  } else {
+    res.success = shard_map_.SplitShard(split_shard_request.previous_shard_map_version, split_shard_request.label_id,
+                                        split_shard_request.split_key);
+  }
+
+  return res;
+}
+
+/// This adds the provided storage engine to the standby storage engine pool,
+/// which can be used to rebalance storage over time.
+CoordinatorWriteResponses Coordinator::ApplyWrite(
+    RegisterStorageEngineRequest && /* register_storage_engine_request */) {
+  RegisterStorageEngineResponse res{};
+  // TODO
+
+  return res;
+}
+
+/// This begins the process of draining the provided storage engine from all raft
+/// clusters that it might be participating in.
+CoordinatorWriteResponses Coordinator::ApplyWrite(
+    DeregisterStorageEngineRequest && /* register_storage_engine_request */) {
+  DeregisterStorageEngineResponse res{};
+  // TODO
+
+  return res;
+}
+
+CoordinatorWriteResponses Coordinator::ApplyWrite(InitializeLabelRequest &&initialize_label_request) {
+  InitializeLabelResponse res{};
+
+  std::optional<LabelId> new_label_id = shard_map_.InitializeNewLabel(
+      initialize_label_request.label_name, initialize_label_request.schema, initialize_label_request.replication_factor,
+      initialize_label_request.last_shard_map_version);
+
+  if (new_label_id) {
+    res.new_label_id = new_label_id.value();
+    res.fresher_shard_map = std::nullopt;
+    res.success = true;
+  } else {
+    res.fresher_shard_map = shard_map_;
+    res.success = false;
+  }
+
+  return res;
+}
+
+CoordinatorWriteResponses Coordinator::ApplyWrite(AllocatePropertyIdsRequest &&allocate_property_ids_request) {
+  AllocatePropertyIdsResponse res{};
+
+  auto property_ids = shard_map_.AllocatePropertyIds(allocate_property_ids_request.property_names);
+
+  res.property_ids = property_ids;
+
+  return res;
+}
+
+}  // namespace memgraph::coordinator

src/coordinator/coordinator.hpp

@@ -0,0 +1,196 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+#pragma once
+
+#include <optional>
+#include <set>
+#include <string>
+#include <unordered_set>
+#include <variant>
+#include <vector>
+
+#include <boost/uuid/uuid.hpp>
+
+#include <coordinator/hybrid_logical_clock.hpp>
+#include <coordinator/shard_map.hpp>
+#include <io/simulator/simulator.hpp>
+#include <io/time.hpp>
+#include <io/transport.hpp>
+#include <storage/v3/id_types.hpp>
+#include <storage/v3/schemas.hpp>
+
+namespace memgraph::coordinator {
+
+using memgraph::io::Address;
+using memgraph::storage::v3::LabelId;
+using memgraph::storage::v3::PropertyId;
+using memgraph::storage::v3::SchemaProperty;
+using SimT = memgraph::io::simulator::SimulatorTransport;
+using PrimaryKey = std::vector<PropertyValue>;
+
+struct HlcRequest {
+  Hlc last_shard_map_version;
+};
+
+struct HlcResponse {
+  Hlc new_hlc;
+  std::optional<ShardMap> fresher_shard_map;
+};
+
+struct GetShardMapRequest {
+  // No state
+};
+
+struct GetShardMapResponse {
+  ShardMap shard_map;
+};
+
+struct AllocateHlcBatchRequest {
+  Hlc low;
+  Hlc high;
+};
+
+struct AllocateHlcBatchResponse {
+  bool success;
+  Hlc low;
+  Hlc high;
+};
+
+struct AllocateEdgeIdBatchRequest {
+  size_t batch_size;
+};
+
+struct AllocateEdgeIdBatchResponse {
+  uint64_t low;
+  uint64_t high;
+};
+
+struct AllocatePropertyIdsRequest {
+  std::vector<std::string> property_names;
+};
+
+struct AllocatePropertyIdsResponse {
+  std::map<std::string, PropertyId> property_ids;
+};
+
+struct SplitShardRequest {
+  Hlc previous_shard_map_version;
+  LabelId label_id;
+  PrimaryKey split_key;
+};
+
+struct SplitShardResponse {
+  bool success;
+};
+
+struct RegisterStorageEngineRequest {
+  Address address;
+};
+
+struct RegisterStorageEngineResponse {
+  bool success;
+};
+
+struct DeregisterStorageEngineRequest {
+  Address address;
+};
+
+struct DeregisterStorageEngineResponse {
+  bool success;
+};
+
+struct InitializeLabelRequest {
+  std::string label_name;
+  std::vector<SchemaProperty> schema;
+  size_t replication_factor;
+  Hlc last_shard_map_version;
+};
+
+struct InitializeLabelResponse {
+  bool success;
+  LabelId new_label_id;
+  std::optional<ShardMap> fresher_shard_map;
+};
+
+struct HeartbeatRequest {
+  Address from_storage_manager;
+  std::set<boost::uuids::uuid> initialized_rsms;
+};
+
+struct HeartbeatResponse {
+  std::vector<ShardToInitialize> shards_to_initialize;
+};
+
+using CoordinatorWriteRequests =
+    std::variant<HlcRequest, AllocateEdgeIdBatchRequest, SplitShardRequest, RegisterStorageEngineRequest,
+                 DeregisterStorageEngineRequest, InitializeLabelRequest, AllocatePropertyIdsRequest, HeartbeatRequest>;
+using CoordinatorWriteResponses = std::variant<HlcResponse, AllocateEdgeIdBatchResponse, SplitShardResponse,
+                                               RegisterStorageEngineResponse, DeregisterStorageEngineResponse,
+                                               InitializeLabelResponse, AllocatePropertyIdsResponse, HeartbeatResponse>;
+
+using CoordinatorReadRequests = std::variant<GetShardMapRequest>;
+using CoordinatorReadResponses = std::variant<GetShardMapResponse>;
+
+class Coordinator {
+ public:
+  explicit Coordinator(ShardMap sm) : shard_map_{std::move(sm)} {}
+
+  // NOLINTNEXTLINE(readability-convert-member-functions-to-static
+  CoordinatorReadResponses Read(CoordinatorReadRequests requests) {
+    return std::visit([&](auto &&request) { return HandleRead(std::forward<decltype(request)>(request)); },
+                      std::move(requests));  // NOLINT(hicpp-move-const-arg,performance-move-const-arg)
+  }
+
+  // NOLINTNEXTLINE(readability-convert-member-functions-to-static
+  CoordinatorWriteResponses Apply(CoordinatorWriteRequests requests) {
+    return std::visit([&](auto &&request) mutable { return ApplyWrite(std::forward<decltype(request)>(request)); },
+                      std::move(requests));
+  }
+
+ private:
+  ShardMap shard_map_;
+  uint64_t highest_allocated_timestamp_{0};
+
+  /// Query engines need to periodically request batches of unique edge IDs.
+  uint64_t highest_allocated_edge_id_{0};
+
+  CoordinatorReadResponses HandleRead(GetShardMapRequest && /* get_shard_map_request */) {
+    GetShardMapResponse res;
+    res.shard_map = shard_map_;
+    return res;
+  }
+
+  CoordinatorWriteResponses ApplyWrite(HeartbeatRequest &&heartbeat_request);
+
+  CoordinatorWriteResponses ApplyWrite(HlcRequest &&hlc_request);
+
+  CoordinatorWriteResponses ApplyWrite(AllocateEdgeIdBatchRequest &&ahr);
+
+  /// This splits the shard immediately beneath the provided
+  /// split key, keeping the assigned peers identical for now,
+  /// but letting them be gradually migrated over time.
+  CoordinatorWriteResponses ApplyWrite(SplitShardRequest &&split_shard_request);
+
+  /// This adds the provided storage engine to the standby storage engine pool,
+  /// which can be used to rebalance storage over time.
+  static CoordinatorWriteResponses ApplyWrite(RegisterStorageEngineRequest && /* register_storage_engine_request */);
+
+  /// This begins the process of draining the provided storage engine from all raft
+  /// clusters that it might be participating in.
+  static CoordinatorWriteResponses ApplyWrite(DeregisterStorageEngineRequest && /* register_storage_engine_request */);
+
+  CoordinatorWriteResponses ApplyWrite(InitializeLabelRequest &&initialize_label_request);
+
+  CoordinatorWriteResponses ApplyWrite(AllocatePropertyIdsRequest &&allocate_property_ids_request);
+};
+
+}  // namespace memgraph::coordinator

src/coordinator/coordinator_client.hpp

@@ -0,0 +1,24 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+#pragma once
+
+#include "coordinator/coordinator.hpp"
+#include "io/rsm/rsm_client.hpp"
+
+namespace memgraph::coordinator {
+
+using memgraph::io::rsm::RsmClient;
+
+template <typename IoImpl>
+using CoordinatorClient = RsmClient<IoImpl, CoordinatorWriteRequests, CoordinatorWriteResponses,
+                                    CoordinatorReadRequests, CoordinatorReadResponses>;
+}  // namespace memgraph::coordinator

src/coordinator/coordinator_rsm.hpp

@@ -0,0 +1,23 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+#pragma once
+
+#include "coordinator/coordinator.hpp"
+#include "io/rsm/raft.hpp"
+
+namespace memgraph::coordinator {
+
+template <typename IoImpl>
+using CoordinatorRsm = memgraph::io::rsm::Raft<IoImpl, Coordinator, CoordinatorWriteRequests, CoordinatorWriteResponses,
+                                               CoordinatorReadRequests, CoordinatorReadResponses>;
+
+}  // namespace memgraph::coordinator

src/coordinator/coordinator_worker.hpp

@@ -0,0 +1,168 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+#pragma once
+
+#include <chrono>
+#include <deque>
+#include <memory>
+#include <queue>
+#include <variant>
+
+#include "coordinator/coordinator.hpp"
+#include "coordinator/coordinator_rsm.hpp"
+#include "coordinator/shard_map.hpp"
+#include "io/address.hpp"
+#include "io/future.hpp"
+#include "io/messages.hpp"
+#include "io/rsm/raft.hpp"
+#include "io/time.hpp"
+#include "io/transport.hpp"
+#include "query/v2/requests.hpp"
+
+namespace memgraph::coordinator::coordinator_worker {
+
+/// Obligations:
+/// * ShutDown
+/// * Cron
+/// * RouteMessage
+
+using coordinator::Coordinator;
+using coordinator::CoordinatorRsm;
+using io::Address;
+using io::RequestId;
+using io::Time;
+using io::messages::CoordinatorMessages;
+using msgs::ReadRequests;
+using msgs::ReadResponses;
+using msgs::WriteRequests;
+using msgs::WriteResponses;
+
+struct ShutDown {};
+
+struct Cron {};
+
+struct RouteMessage {
+  CoordinatorMessages message;
+  RequestId request_id;
+  Address to;
+  Address from;
+};
+
+using Message = std::variant<RouteMessage, Cron, ShutDown>;
+
+struct QueueInner {
+  std::mutex mu{};
+  std::condition_variable cv;
+  // TODO(tyler) handle simulator communication std::shared_ptr<std::atomic<int>> blocked;
+
+  // TODO(tyler) investigate using a priority queue that prioritizes messages in a way that
+  // improves overall QoS. For example, maybe we want to schedule raft Append messages
+  // ahead of Read messages or generally writes before reads for lowering the load on the
+  // overall system faster etc... When we do this, we need to make sure to avoid
+  // starvation by sometimes randomizing priorities, rather than following a strict
+  // prioritization.
+  std::deque<Message> queue;
+
+  uint64_t submitted = 0;
+  uint64_t calls_to_pop = 0;
+};
+
+/// There are two reasons to implement our own Queue instead of using
+/// one off-the-shelf:
+/// 1. we will need to know in the simulator when all threads are waiting
+/// 2. we will want to implement our own priority queue within this for QoS
+class Queue {
+  std::shared_ptr<QueueInner> inner_ = std::make_shared<QueueInner>();
+
+ public:
+  void Push(Message &&message) {
+    {
+      MG_ASSERT(inner_.use_count() > 0);
+      std::unique_lock<std::mutex> lock(inner_->mu);
+
+      inner_->submitted++;
+
+      inner_->queue.emplace_back(std::move(message));
+    }  // lock dropped before notifying condition variable
+
+    inner_->cv.notify_all();
+  }
+
+  Message Pop() {
+    MG_ASSERT(inner_.use_count() > 0);
+    std::unique_lock<std::mutex> lock(inner_->mu);
+
+    inner_->calls_to_pop++;
+    inner_->cv.notify_all();
+
+    while (inner_->queue.empty()) {
+      inner_->cv.wait(lock);
+    }
+
+    Message message = std::move(inner_->queue.front());
+    inner_->queue.pop_front();
+
+    return message;
+  }
+
+  void BlockOnQuiescence() const {
+    MG_ASSERT(inner_.use_count() > 0);
+    std::unique_lock<std::mutex> lock(inner_->mu);
+
+    while (inner_->calls_to_pop <= inner_->submitted) {
+      inner_->cv.wait(lock);
+    }
+  }
+};
+
+/// A CoordinatorWorker owns Raft<CoordinatorRsm> instances. receives messages from the MachineManager.
+template <typename IoImpl>
+class CoordinatorWorker {
+  io::Io<IoImpl> io_;
+  Queue queue_;
+  CoordinatorRsm<IoImpl> coordinator_;
+
+  bool Process(ShutDown && /*shut_down*/) { return false; }
+
+  bool Process(Cron && /* cron */) {
+    coordinator_.Cron();
+    return true;
+  }
+
+  bool Process(RouteMessage &&route_message) {
+    coordinator_.Handle(std::move(route_message.message), route_message.request_id, route_message.from);
+
+    return true;
+  }
+
+ public:
+  CoordinatorWorker(io::Io<IoImpl> io, Queue queue, Coordinator coordinator)
+      : io_(std::move(io)), queue_(std::move(queue)), coordinator_{std::move(io_), {}, std::move(coordinator)} {}
+
+  CoordinatorWorker(CoordinatorWorker &&) noexcept = default;
+  CoordinatorWorker &operator=(CoordinatorWorker &&) noexcept = default;
+  CoordinatorWorker(const CoordinatorWorker &) = delete;
+  CoordinatorWorker &operator=(const CoordinatorWorker &) = delete;
+  ~CoordinatorWorker() = default;
+
+  void Run() {
+    bool should_continue = true;
+    while (should_continue) {
+      Message message = queue_.Pop();
+
+      should_continue = std::visit([this](auto &&msg) { return this->Process(std::forward<decltype(msg)>(msg)); },
+                                   std::move(message));
+    }
+  }
+};
+
+}  // namespace memgraph::coordinator::coordinator_worker

src/coordinator/hybrid_logical_clock.hpp

@@ -0,0 +1,48 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+#pragma once
+
+#include <chrono>
+#include <compare>
+#include <ctime>
+#include <iomanip>
+
+#include "io/time.hpp"
+
+namespace memgraph::coordinator {
+
+using Time = memgraph::io::Time;
+
+/// Hybrid-logical clock
+struct Hlc {
+  uint64_t logical_id = 0;
+  Time coordinator_wall_clock = Time::min();
+
+  auto operator<=>(const Hlc &other) const { return logical_id <=> other.logical_id; }
+
+  bool operator==(const Hlc &other) const = default;
+  bool operator<(const Hlc &other) const = default;
+  bool operator==(const uint64_t other) const { return logical_id == other; }
+  bool operator<(const uint64_t other) const { return logical_id < other; }
+  bool operator>=(const uint64_t other) const { return logical_id >= other; }
+
+  friend std::ostream &operator<<(std::ostream &in, const Hlc &hlc) {
+    auto wall_clock = std::chrono::system_clock::to_time_t(hlc.coordinator_wall_clock);
+    in << "Hlc { logical_id: " << hlc.logical_id;
+    in << ", coordinator_wall_clock: " << std::put_time(std::localtime(&wall_clock), "%F %T");
+    in << " }";
+
+    return in;
+  }
+};
+
+}  // namespace memgraph::coordinator

src/coordinator/shard_map.cpp

@@ -0,0 +1,576 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+#include <optional>
+#include <unordered_map>
+#include <vector>
+
+#include "common/types.hpp"
+#include "coordinator/shard_map.hpp"
+#include "spdlog/spdlog.h"
+#include "storage/v3/schemas.hpp"
+#include "storage/v3/temporal.hpp"
+#include "utils/cast.hpp"
+#include "utils/exceptions.hpp"
+#include "utils/string.hpp"
+
+namespace memgraph::coordinator {
+
+using memgraph::common::SchemaType;
+using memgraph::storage::v3::TemporalData;
+using memgraph::storage::v3::TemporalType;
+
+PrimaryKey SchemaToMinKey(const std::vector<SchemaProperty> &schema) {
+  PrimaryKey ret{};
+
+  const int64_t min_int = std::numeric_limits<int64_t>::min();
+
+  const TemporalData date{TemporalType::Date, min_int};
+  const TemporalData local_time{TemporalType::LocalTime, min_int};
+  const TemporalData local_date_time{TemporalType::LocalDateTime, min_int};
+  const TemporalData duration{TemporalType::Duration, min_int};
+
+  for (const auto &schema_property : schema) {
+    switch (schema_property.type) {
+      case SchemaType::BOOL:
+        ret.emplace_back(PropertyValue(false));
+        break;
+      case SchemaType::INT:
+        ret.emplace_back(PropertyValue(min_int));
+        break;
+      case SchemaType::STRING:
+        ret.emplace_back(PropertyValue(""));
+        break;
+      case SchemaType::DATE:
+        ret.emplace_back(PropertyValue(date));
+        break;
+      case SchemaType::LOCALTIME:
+        ret.emplace_back(PropertyValue(local_time));
+        break;
+      case SchemaType::LOCALDATETIME:
+        ret.emplace_back(PropertyValue(local_date_time));
+        break;
+      case SchemaType::DURATION:
+        ret.emplace_back(PropertyValue(duration));
+        break;
+    }
+  }
+
+  return ret;
+}
+
+ShardMap ShardMap::Parse(std::istream &input_stream) {
+  ShardMap shard_map;
+  const auto read_size = [&input_stream] {
+    size_t size{0};
+    input_stream >> size;
+    return size;
+  };
+
+  // Reads a string until the next whitespace
+  const auto read_word = [&input_stream] {
+    std::string word;
+    input_stream >> word;
+    return word;
+  };
+
+  const auto read_names = [&read_size, &read_word] {
+    const auto number_of_names = read_size();
+    spdlog::trace("Reading {} names", number_of_names);
+    std::vector<std::string> names;
+    names.reserve(number_of_names);
+
+    for (auto name_index = 0; name_index < number_of_names; ++name_index) {
+      names.push_back(read_word());
+      spdlog::trace("Read '{}'", names.back());
+    }
+    return names;
+  };
+
+  const auto read_line = [&input_stream] {
+    std::string line;
+    std::getline(input_stream, line);
+    return line;
+  };
+
+  const auto parse_type = [](const std::string &type) {
+    static const auto type_map = std::unordered_map<std::string, common::SchemaType>{
+        {"string", common::SchemaType::STRING}, {"int", common::SchemaType::INT}, {"bool", common::SchemaType::BOOL}};
+    const auto lower_case_type = utils::ToLowerCase(type);
+    auto it = type_map.find(lower_case_type);
+    MG_ASSERT(it != type_map.end(), "Invalid type in split files: {}", type);
+    return it->second;
+  };
+
+  const auto parse_property_value = [](std::string text, const common::SchemaType type) {
+    if (type == common::SchemaType::STRING) {
+      return storage::v3::PropertyValue{std::move(text)};
+    }
+    if (type == common::SchemaType::INT) {
+      size_t processed{0};
+      int64_t value = std::stoll(text, &processed);
+      MG_ASSERT(processed == text.size() || text[processed] == ' ', "Invalid integer format: '{}'", text);
+      return storage::v3::PropertyValue{value};
+    }
+    LOG_FATAL("Not supported type: {}", utils::UnderlyingCast(type));
+  };
+
+  spdlog::debug("Reading properties");
+  const auto properties = read_names();
+  MG_ASSERT(shard_map.AllocatePropertyIds(properties).size() == properties.size(),
+            "Unexpected number of properties created!");
+
+  spdlog::debug("Reading edge types");
+  const auto edge_types = read_names();
+  MG_ASSERT(shard_map.AllocateEdgeTypeIds(edge_types).size() == edge_types.size(),
+            "Unexpected number of properties created!");
+
+  spdlog::debug("Reading primary labels");
+  const auto number_of_primary_labels = read_size();
+  spdlog::debug("Reading {} primary labels", number_of_primary_labels);
+
+  for (auto label_index = 0; label_index < number_of_primary_labels; ++label_index) {
+    const auto primary_label = read_word();
+    spdlog::debug("Reading primary label named '{}'", primary_label);
+    const auto number_of_primary_properties = read_size();
+    spdlog::debug("Reading {} primary properties", number_of_primary_properties);
+    std::vector<std::string> pp_names;
+    std::vector<common::SchemaType> pp_types;
+    pp_names.reserve(number_of_primary_properties);
+    pp_types.reserve(number_of_primary_properties);
+    for (auto property_index = 0; property_index < number_of_primary_properties; ++property_index) {
+      pp_names.push_back(read_word());
+      spdlog::debug("Reading primary property named '{}'", pp_names.back());
+      pp_types.push_back(parse_type(read_word()));
+    }
+    auto pp_mapping = shard_map.AllocatePropertyIds(pp_names);
+    std::vector<SchemaProperty> schema;
+    schema.reserve(number_of_primary_properties);
+
+    for (auto property_index = 0; property_index < number_of_primary_properties; ++property_index) {
+      schema.push_back(storage::v3::SchemaProperty{pp_mapping.at(pp_names[property_index]), pp_types[property_index]});
+    }
+    const auto hlc = shard_map.GetHlc();
+    MG_ASSERT(shard_map.InitializeNewLabel(primary_label, schema, 1, hlc).has_value(),
+              "Cannot initialize new label: {}", primary_label);
+
+    const auto number_of_split_points = read_size();
+    spdlog::debug("Reading {} split points", number_of_split_points);
+
+    [[maybe_unused]] const auto remainder_from_last_line = read_line();
+    for (auto split_point_index = 0; split_point_index < number_of_split_points; ++split_point_index) {
+      const auto line = read_line();
+      spdlog::debug("Read split point '{}'", line);
+      MG_ASSERT(line.front() == '[', "Invalid split file format!");
+      MG_ASSERT(line.back() == ']', "Invalid split file format!");
+      std::string_view line_view{line};
+      line_view.remove_prefix(1);
+      line_view.remove_suffix(1);
+      static constexpr std::string_view kDelimiter{","};
+      auto pk_values_as_text = utils::Split(line_view, kDelimiter);
+      std::vector<PropertyValue> pk;
+      pk.reserve(number_of_primary_properties);
+      MG_ASSERT(pk_values_as_text.size() == number_of_primary_properties,
+                "Split point contains invalid number of values '{}'", line);
+
+      for (auto property_index = 0; property_index < number_of_primary_properties; ++property_index) {
+        pk.push_back(parse_property_value(std::move(pk_values_as_text[property_index]), schema[property_index].type));
+      }
+      shard_map.SplitShard(shard_map.GetHlc(), shard_map.labels.at(primary_label), pk);
+    }
+  }
+
+  return shard_map;
+}
+
+std::ostream &operator<<(std::ostream &in, const ShardMap &shard_map) {
+  using utils::print_helpers::operator<<;
+
+  in << "ShardMap { shard_map_version: " << shard_map.shard_map_version;
+  in << ", max_property_id: " << shard_map.max_property_id;
+  in << ", max_edge_type_id: " << shard_map.max_edge_type_id;
+  in << ", properties: " << shard_map.properties;
+  in << ", edge_types: " << shard_map.edge_types;
+  in << ", max_label_id: " << shard_map.max_label_id;
+  in << ", labels: " << shard_map.labels;
+  in << ", label_spaces: " << shard_map.label_spaces;
+  in << ", schemas: " << shard_map.schemas;
+  in << "}";
+  return in;
+}
+
+Shards ShardMap::GetShardsForLabel(const LabelName &label) const {
+  const auto id = labels.at(label);
+  const auto &shards = label_spaces.at(id).shards;
+  return shards;
+}
+
+std::vector<Shards> ShardMap::GetAllShards() const {
+  std::vector<Shards> all_shards;
+  all_shards.reserve(label_spaces.size());
+  std::transform(label_spaces.begin(), label_spaces.end(), std::back_inserter(all_shards),
+                 [](const auto &label_space) { return label_space.second.shards; });
+  return all_shards;
+}
+
+// TODO(gabor) later we will want to update the wallclock time with
+// the given Io<impl>'s time as well
+Hlc ShardMap::IncrementShardMapVersion() noexcept {
+  ++shard_map_version.logical_id;
+  return shard_map_version;
+}
+
+// TODO(antaljanosbenjamin) use a single map for all name id
+// mapping and a single counter to maintain the next id
+std::unordered_map<uint64_t, std::string> ShardMap::IdToNames() {
+  std::unordered_map<uint64_t, std::string> id_to_names;
+
+  const auto map_type_ids = [&id_to_names](const auto &name_to_id_type) {
+    for (const auto &[name, id] : name_to_id_type) {
+      id_to_names.emplace(id.AsUint(), name);
+    }
+  };
+
+  map_type_ids(edge_types);
+  map_type_ids(labels);
+  map_type_ids(properties);
+
+  return id_to_names;
+}
+
+Hlc ShardMap::GetHlc() const noexcept { return shard_map_version; }
+
+boost::uuids::uuid NewShardUuid(uint64_t shard_id) {
+  return boost::uuids::uuid{0,
+                            0,
+                            0,
+                            0,
+                            0,
+                            0,
+                            0,
+                            0,
+                            static_cast<unsigned char>(shard_id >> 56U),
+                            static_cast<unsigned char>(shard_id >> 48U),
+                            static_cast<unsigned char>(shard_id >> 40U),
+                            static_cast<unsigned char>(shard_id >> 32U),
+                            static_cast<unsigned char>(shard_id >> 24U),
+                            static_cast<unsigned char>(shard_id >> 16U),
+                            static_cast<unsigned char>(shard_id >> 8U),
+                            static_cast<unsigned char>(shard_id)};
+}
+
+std::vector<ShardToInitialize> ShardMap::AssignShards(Address storage_manager,
+                                                      std::set<boost::uuids::uuid> initialized) {
+  std::vector<ShardToInitialize> ret{};
+
+  bool mutated = false;
+
+  for (auto &[label_id, label_space] : label_spaces) {
+    for (auto it = label_space.shards.begin(); it != label_space.shards.end(); it++) {
+      auto &[low_key, shard] = *it;
+      std::optional<PrimaryKey> high_key;
+      if (const auto next_it = std::next(it); next_it != label_space.shards.end()) {
+        high_key = next_it->first;
+      }
+      // TODO(tyler) avoid these triple-nested loops by having the heartbeat include better info
+      bool machine_contains_shard = false;
+
+      for (auto &aas : shard.peers) {
+        if (initialized.contains(aas.address.unique_id)) {
+          machine_contains_shard = true;
+          if (aas.status != Status::CONSENSUS_PARTICIPANT) {
+            mutated = true;
+            spdlog::info("marking shard as full consensus participant: {}", aas.address.unique_id);
+            aas.status = Status::CONSENSUS_PARTICIPANT;
+          }
+        } else {
+          const bool same_machine = aas.address.last_known_ip == storage_manager.last_known_ip &&
+                                    aas.address.last_known_port == storage_manager.last_known_port;
+          if (same_machine) {
+            machine_contains_shard = true;
+            spdlog::info("reminding shard manager that they should begin participating in shard");
+
+            ret.push_back(ShardToInitialize{
+                .uuid = aas.address.unique_id,
+                .label_id = label_id,
+                .min_key = low_key,
+                .max_key = high_key,
+                .schema = schemas[label_id],
+                .config = Config{},
+                .id_to_names = IdToNames(),
+            });
+          }
+        }
+      }
+
+      if (!machine_contains_shard && shard.peers.size() < label_space.replication_factor) {
+        // increment version for each new uuid for deterministic creation
+        IncrementShardMapVersion();
+
+        Address address = storage_manager;
+
+        // TODO(tyler) use deterministic UUID so that coordinators don't diverge here
+        address.unique_id = NewShardUuid(shard_map_version.logical_id);
+
+        spdlog::info("assigning shard manager to shard");
+
+        ret.push_back(ShardToInitialize{
+            .uuid = address.unique_id,
+            .label_id = label_id,
+            .min_key = low_key,
+            .max_key = high_key,
+            .schema = schemas[label_id],
+            .config = Config{},
+            .id_to_names = IdToNames(),
+        });
+
+        AddressAndStatus aas = {
+            .address = address,
+            .status = Status::INITIALIZING,
+        };
+
+        shard.peers.emplace_back(aas);
+      }
+    }
+  }
+
+  if (mutated) {
+    IncrementShardMapVersion();
+  }
+  return ret;
+}
+
+bool ShardMap::SplitShard(Hlc previous_shard_map_version, LabelId label_id, const PrimaryKey &key) {
+  if (previous_shard_map_version != shard_map_version) {
+    return false;
+  }
+
+  auto &label_space = label_spaces.at(label_id);
+  auto &shards_in_map = label_space.shards;
+
+  MG_ASSERT(!shards_in_map.empty());
+  MG_ASSERT(!shards_in_map.contains(key));
+  MG_ASSERT(label_spaces.contains(label_id));
+
+  // Finding the ShardMetadata that the new PrimaryKey should map to.
+  auto prev = std::prev(shards_in_map.upper_bound(key));
+  ShardMetadata duplicated_shard = prev->second;
+
+  // Apply the split
+  shards_in_map[key] = duplicated_shard;
+
+  IncrementShardMapVersion();
+
+  return true;
+}
+
+std::optional<LabelId> ShardMap::InitializeNewLabel(std::string label_name, std::vector<SchemaProperty> schema,
+                                                    size_t replication_factor, Hlc last_shard_map_version) {
+  if (shard_map_version != last_shard_map_version || labels.contains(label_name)) {
+    return std::nullopt;
+  }
+
+  const LabelId label_id = LabelId::FromUint(++max_label_id);
+
+  labels.emplace(std::move(label_name), label_id);
+
+  PrimaryKey initial_key = SchemaToMinKey(schema);
+  ShardMetadata empty_shard = {};
+
+  Shards shards = {
+      {initial_key, empty_shard},
+  };
+
+  LabelSpace label_space{
+      .schema = schema,
+      .shards = shards,
+      .replication_factor = replication_factor,
+  };
+  schemas[label_id] = std::move(schema);
+
+  label_spaces.emplace(label_id, label_space);
+
+  IncrementShardMapVersion();
+
+  return label_id;
+}
+
+void ShardMap::AddServer(Address server_address) {
+  // Find a random place for the server to plug in
+}
+
+std::optional<LabelId> ShardMap::GetLabelId(const std::string &label) const {
+  if (const auto it = labels.find(label); it != labels.end()) {
+    return it->second;
+  }
+  return std::nullopt;
+}
+
+const std::string &ShardMap::GetLabelName(const LabelId label) const {
+  if (const auto it =
+          std::ranges::find_if(labels, [label](const auto &name_id_pair) { return name_id_pair.second == label; });
+      it != labels.end()) {
+    return it->first;
+  }
+  throw utils::BasicException("GetLabelName fails on the given label id!");
+}
+
+std::optional<PropertyId> ShardMap::GetPropertyId(const std::string &property_name) const {
+  if (const auto it = properties.find(property_name); it != properties.end()) {
+    return it->second;
+  }
+  return std::nullopt;
+}
+
+const std::string &ShardMap::GetPropertyName(const PropertyId property) const {
+  if (const auto it = std::ranges::find_if(
+          properties, [property](const auto &name_id_pair) { return name_id_pair.second == property; });
+      it != properties.end()) {
+    return it->first;
+  }
+  throw utils::BasicException("PropertyId not found!");
+}
+
+std::optional<EdgeTypeId> ShardMap::GetEdgeTypeId(const std::string &edge_type) const {
+  if (const auto it = edge_types.find(edge_type); it != edge_types.end()) {
+    return it->second;
+  }
+  return std::nullopt;
+}
+
+const std::string &ShardMap::GetEdgeTypeName(const EdgeTypeId property) const {
+  if (const auto it = std::ranges::find_if(
+          edge_types, [property](const auto &name_id_pair) { return name_id_pair.second == property; });
+      it != edge_types.end()) {
+    return it->first;
+  }
+  throw utils::BasicException("EdgeTypeId not found!");
+}
+
+Shards ShardMap::GetShardsForRange(const LabelName &label_name, const PrimaryKey &start_key,
+                                   const PrimaryKey &end_key) const {
+  MG_ASSERT(start_key <= end_key);
+  MG_ASSERT(labels.contains(label_name));
+
+  LabelId label_id = labels.at(label_name);
+
+  const auto &label_space = label_spaces.at(label_id);
+
+  const auto &shards_for_label = label_space.shards;
+
+  MG_ASSERT(shards_for_label.begin()->first <= start_key,
+            "the ShardMap must always contain a minimal key that is less than or equal to any requested key");
+
+  auto it = std::prev(shards_for_label.upper_bound(start_key));
+  const auto end_it = shards_for_label.upper_bound(end_key);
+
+  Shards shards{};
+
+  std::copy(it, end_it, std::inserter(shards, shards.end()));
+
+  return shards;
+}
+
+ShardMetadata ShardMap::GetShardForKey(const LabelName &label_name, const PrimaryKey &key) const {
+  MG_ASSERT(labels.contains(label_name));
+
+  LabelId label_id = labels.at(label_name);
+
+  const auto &label_space = label_spaces.at(label_id);
+
+  MG_ASSERT(label_space.shards.begin()->first <= key,
+            "the ShardMap must always contain a minimal key that is less than or equal to any requested key");
+
+  return std::prev(label_space.shards.upper_bound(key))->second;
+}
+
+ShardMetadata ShardMap::GetShardForKey(const LabelId &label_id, const PrimaryKey &key) const {
+  MG_ASSERT(label_spaces.contains(label_id));
+
+  const auto &label_space = label_spaces.at(label_id);
+
+  MG_ASSERT(label_space.shards.begin()->first <= key,
+            "the ShardMap must always contain a minimal key that is less than or equal to any requested key");
+
+  return std::prev(label_space.shards.upper_bound(key))->second;
+}
+
+PropertyMap ShardMap::AllocatePropertyIds(const std::vector<PropertyName> &new_properties) {
+  PropertyMap ret{};
+
+  bool mutated = false;
+
+  for (const auto &property_name : new_properties) {
+    if (properties.contains(property_name)) {
+      auto property_id = properties.at(property_name);
+      ret.emplace(property_name, property_id);
+    } else {
+      mutated = true;
+
+      const PropertyId property_id = PropertyId::FromUint(++max_property_id);
+      ret.emplace(property_name, property_id);
+      properties.emplace(property_name, property_id);
+    }
+  }
+
+  if (mutated) {
+    IncrementShardMapVersion();
+  }
+
+  return ret;
+}
+
+EdgeTypeIdMap ShardMap::AllocateEdgeTypeIds(const std::vector<EdgeTypeName> &new_edge_types) {
+  EdgeTypeIdMap ret;
+
+  bool mutated = false;
+
+  for (const auto &edge_type_name : new_edge_types) {
+    if (edge_types.contains(edge_type_name)) {
+      auto edge_type_id = edge_types.at(edge_type_name);
+      ret.emplace(edge_type_name, edge_type_id);
+    } else {
+      mutated = true;
+
+      const EdgeTypeId edge_type_id = EdgeTypeId::FromUint(++max_edge_type_id);
+      ret.emplace(edge_type_name, edge_type_id);
+      edge_types.emplace(edge_type_name, edge_type_id);
+    }
+  }
+
+  if (mutated) {
+    IncrementShardMapVersion();
+  }
+
+  return ret;
+}
+
+bool ShardMap::ClusterInitialized() const {
+  for (const auto &[label_id, label_space] : label_spaces) {
+    for (const auto &[low_key, shard] : label_space.shards) {
+      if (shard.peers.size() < label_space.replication_factor) {
+        spdlog::info("label_space below desired replication factor");
+        return false;
+      }
+
+      for (const auto &aas : shard.peers) {
+        if (aas.status != Status::CONSENSUS_PARTICIPANT) {
+          spdlog::info("shard member not yet a CONSENSUS_PARTICIPANT");
+          return false;
+        }
+      }
+    }
+  }
+
+  return true;
+}
+
+}  // namespace memgraph::coordinator

src/coordinator/shard_map.hpp

@@ -0,0 +1,204 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+#pragma once
+
+#include <algorithm>
+#include <limits>
+#include <map>
+#include <set>
+#include <vector>
+
+#include <boost/uuid/uuid.hpp>
+#include <boost/uuid/uuid_generators.hpp>
+
+#include "common/types.hpp"
+#include "coordinator/hybrid_logical_clock.hpp"
+#include "io/address.hpp"
+#include "storage/v3/config.hpp"
+#include "storage/v3/id_types.hpp"
+#include "storage/v3/name_id_mapper.hpp"
+#include "storage/v3/property_value.hpp"
+#include "storage/v3/schemas.hpp"
+#include "storage/v3/temporal.hpp"
+#include "utils/exceptions.hpp"
+#include "utils/print_helpers.hpp"
+
+namespace memgraph::coordinator {
+
+constexpr int64_t kNotExistingId{0};
+
+using memgraph::io::Address;
+using memgraph::storage::v3::Config;
+using memgraph::storage::v3::EdgeTypeId;
+using memgraph::storage::v3::LabelId;
+using memgraph::storage::v3::PropertyId;
+using memgraph::storage::v3::PropertyValue;
+using memgraph::storage::v3::SchemaProperty;
+
+enum class Status : uint8_t {
+  CONSENSUS_PARTICIPANT,
+  INITIALIZING,
+  // TODO(tyler) this will possibly have more states,
+  // depending on the reconfiguration protocol that we
+  // implement.
+};
+
+struct AddressAndStatus {
+  memgraph::io::Address address;
+  Status status;
+
+  friend bool operator<(const AddressAndStatus &lhs, const AddressAndStatus &rhs) { return lhs.address < rhs.address; }
+
+  friend std::ostream &operator<<(std::ostream &in, const AddressAndStatus &address_and_status) {
+    in << "AddressAndStatus { address: ";
+    in << address_and_status.address;
+    if (address_and_status.status == Status::CONSENSUS_PARTICIPANT) {
+      in << ", status: CONSENSUS_PARTICIPANT }";
+    } else {
+      in << ", status: INITIALIZING }";
+    }
+
+    return in;
+  }
+
+  friend bool operator==(const AddressAndStatus &lhs, const AddressAndStatus &rhs) {
+    return lhs.address == rhs.address;
+  }
+};
+
+using PrimaryKey = std::vector<PropertyValue>;
+
+struct ShardMetadata {
+  std::vector<AddressAndStatus> peers;
+  uint64_t version;
+
+  friend std::ostream &operator<<(std::ostream &in, const ShardMetadata &shard) {
+    using utils::print_helpers::operator<<;
+
+    in << "ShardMetadata { peers: ";
+    in << shard.peers;
+    in << " version: ";
+    in << shard.version;
+    in << " }";
+
+    return in;
+  }
+
+  friend bool operator==(const ShardMetadata &lhs, const ShardMetadata &rhs) = default;
+
+  friend bool operator<(const ShardMetadata &lhs, const ShardMetadata &rhs) {
+    if (lhs.peers != rhs.peers) {
+      return lhs.peers < rhs.peers;
+    }
+
+    return lhs.version < rhs.version;
+  }
+};
+
+using Shards = std::map<PrimaryKey, ShardMetadata>;
+using LabelName = std::string;
+using PropertyName = std::string;
+using EdgeTypeName = std::string;
+using PropertyMap = std::map<PropertyName, PropertyId>;
+using EdgeTypeIdMap = std::map<EdgeTypeName, EdgeTypeId>;
+
+struct ShardToInitialize {
+  boost::uuids::uuid uuid;
+  LabelId label_id;
+  PrimaryKey min_key;
+  std::optional<PrimaryKey> max_key;
+  std::vector<SchemaProperty> schema;
+  Config config;
+  std::unordered_map<uint64_t, std::string> id_to_names;
+};
+
+PrimaryKey SchemaToMinKey(const std::vector<SchemaProperty> &schema);
+
+struct LabelSpace {
+  std::vector<SchemaProperty> schema;
+  // Maps between the smallest primary key stored in the shard and the shard
+  std::map<PrimaryKey, ShardMetadata> shards;
+  size_t replication_factor;
+
+  friend std::ostream &operator<<(std::ostream &in, const LabelSpace &label_space) {
+    using utils::print_helpers::operator<<;
+
+    in << "LabelSpace { schema: ";
+    in << label_space.schema;
+    in << ", shards: ";
+    in << label_space.shards;
+    in << ", replication_factor: " << label_space.replication_factor << "}";
+
+    return in;
+  }
+};
+
+struct ShardMap {
+  Hlc shard_map_version;
+  uint64_t max_property_id{kNotExistingId};
+  uint64_t max_edge_type_id{kNotExistingId};
+  std::map<PropertyName, PropertyId> properties;
+  std::map<EdgeTypeName, EdgeTypeId> edge_types;
+  uint64_t max_label_id{kNotExistingId};
+  std::map<LabelId, LabelSpace> label_spaces;
+  std::map<LabelId, std::vector<SchemaProperty>> schemas;
+  std::map<LabelName, LabelId> labels;
+
+  [[nodiscard]] static ShardMap Parse(std::istream &input_stream);
+  friend std::ostream &operator<<(std::ostream &in, const ShardMap &shard_map);
+
+  Shards GetShardsForLabel(const LabelName &label) const;
+
+  std::vector<Shards> GetAllShards() const;
+
+  // TODO(gabor) later we will want to update the wallclock time with
+  // the given Io<impl>'s time as well
+  Hlc IncrementShardMapVersion() noexcept;
+  Hlc GetHlc() const noexcept;
+
+  std::unordered_map<uint64_t, std::string> IdToNames();
+
+  // Returns the shard UUIDs that have been assigned but not yet acknowledged for this storage manager
+  std::vector<ShardToInitialize> AssignShards(Address storage_manager, std::set<boost::uuids::uuid> initialized);
+
+  bool SplitShard(Hlc previous_shard_map_version, LabelId label_id, const PrimaryKey &key);
+
+  std::optional<LabelId> InitializeNewLabel(std::string label_name, std::vector<SchemaProperty> schema,
+                                            size_t replication_factor, Hlc last_shard_map_version);
+
+  void AddServer(Address server_address);
+
+  std::optional<LabelId> GetLabelId(const std::string &label) const;
+  // TODO(antaljanosbenjamin): Remove this and instead use NameIdMapper
+  const std::string &GetLabelName(LabelId label) const;
+  std::optional<PropertyId> GetPropertyId(const std::string &property_name) const;
+  const std::string &GetPropertyName(PropertyId property) const;
+  std::optional<EdgeTypeId> GetEdgeTypeId(const std::string &edge_type) const;
+  const std::string &GetEdgeTypeName(EdgeTypeId property) const;
+
+  Shards GetShardsForRange(const LabelName &label_name, const PrimaryKey &start_key, const PrimaryKey &end_key) const;
+
+  ShardMetadata GetShardForKey(const LabelName &label_name, const PrimaryKey &key) const;
+
+  ShardMetadata GetShardForKey(const LabelId &label_id, const PrimaryKey &key) const;
+
+  PropertyMap AllocatePropertyIds(const std::vector<PropertyName> &new_properties);
+
+  EdgeTypeIdMap AllocateEdgeTypeIds(const std::vector<EdgeTypeName> &new_edge_types);
+
+  /// Returns true if all shards have the desired number of replicas and they are in
+  /// the CONSENSUS_PARTICIPANT state. Note that this does not necessarily mean that
+  /// there is also an active leader for each shard.
+  bool ClusterInitialized() const;
+};
+
+}  // namespace memgraph::coordinator

src/expr/CMakeLists.txt

@@ -0,0 +1,20 @@
+define_add_lcp(add_lcp_expr lcp_expr_cpp_files generated_lcp_expr_files)
+
+add_lcp_expr(semantic/symbol.lcp)
+
+add_custom_target(generate_lcp_expr DEPENDS ${generated_lcp_expr_files})
+
+set(mg_expr_sources
+    ${lcp_expr_cpp_files}
+    parsing.cpp)
+
+find_package(Boost REQUIRED)
+
+add_library(mg-expr STATIC ${mg_expr_sources})
+add_dependencies(mg-expr generate_lcp_expr)
+target_include_directories(mg-expr PUBLIC ${CMAKE_SOURCE_DIR}/include)
+target_include_directories(mg-expr PUBLIC ${CMAKE_CURRENT_SOURCE_DIR})
+target_include_directories(mg-expr PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/ast)
+target_include_directories(mg-expr PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/interpret)
+target_include_directories(mg-expr PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/semantic)
+target_link_libraries(mg-expr cppitertools Boost::headers mg-utils mg-parser mg-functions)

src/expr/ast.hpp

@@ -0,0 +1,33 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+#pragma once
+
+#ifndef MG_AST_INCLUDE_PATH
+#ifdef MG_CLANG_TIDY_CHECK
+// NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
+#include "query/v2/bindings/bindings.hpp"
+#else
+#error Missing AST include path
+#endif
+#endif
+
+#ifndef MG_INJECTED_NAMESPACE_NAME
+#ifdef MG_CLANG_TIDY_CHECK
+#else
+#error Missing AST namespace
+#endif
+#endif
+
+#include MG_AST_INCLUDE_PATH
+
+namespace memgraph::expr {
+using namespace MG_INJECTED_NAMESPACE_NAME;  // NOLINT(google-build-using-namespace)
+}  // namespace memgraph::expr

src/expr/ast/ast_visitor.hpp

@@ -0,0 +1,135 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+#pragma once
+
+#include "utils/visitor.hpp"
+
+namespace MG_INJECTED_NAMESPACE_NAME {
+
+// Forward declares for Tree visitors.
+class CypherQuery;
+class SingleQuery;
+class CypherUnion;
+class NamedExpression;
+class Identifier;
+class PropertyLookup;
+class LabelsTest;
+class Aggregation;
+class Function;
+class Reduce;
+class Coalesce;
+class Extract;
+class All;
+class Single;
+class Any;
+class None;
+class ParameterLookup;
+class CallProcedure;
+class Create;
+class Match;
+class Return;
+class With;
+class Pattern;
+class NodeAtom;
+class EdgeAtom;
+class PrimitiveLiteral;
+class ListLiteral;
+class MapLiteral;
+class OrOperator;
+class XorOperator;
+class AndOperator;
+class NotOperator;
+class AdditionOperator;
+class SubtractionOperator;
+class MultiplicationOperator;
+class DivisionOperator;
+class ModOperator;
+class UnaryPlusOperator;
+class UnaryMinusOperator;
+class IsNullOperator;
+class NotEqualOperator;
+class EqualOperator;
+class LessOperator;
+class GreaterOperator;
+class LessEqualOperator;
+class GreaterEqualOperator;
+class InListOperator;
+class SubscriptOperator;
+class ListSlicingOperator;
+class IfOperator;
+class Delete;
+class Where;
+class SetProperty;
+class SetProperties;
+class SetLabels;
+class RemoveProperty;
+class RemoveLabels;
+class Merge;
+class Unwind;
+class AuthQuery;
+class ExplainQuery;
+class ProfileQuery;
+class IndexQuery;
+class InfoQuery;
+class ConstraintQuery;
+class RegexMatch;
+class DumpQuery;
+class ReplicationQuery;
+class LockPathQuery;
+class LoadCsv;
+class FreeMemoryQuery;
+class TriggerQuery;
+class IsolationLevelQuery;
+class CreateSnapshotQuery;
+class StreamQuery;
+class SettingQuery;
+class VersionQuery;
+class Foreach;
+class SchemaQuery;
+
+using TreeCompositeVisitor = memgraph::utils::CompositeVisitor<
+    SingleQuery, CypherUnion, NamedExpression, OrOperator, XorOperator, AndOperator, NotOperator, AdditionOperator,
+    SubtractionOperator, MultiplicationOperator, DivisionOperator, ModOperator, NotEqualOperator, EqualOperator,
+    LessOperator, GreaterOperator, LessEqualOperator, GreaterEqualOperator, InListOperator, SubscriptOperator,
+    ListSlicingOperator, IfOperator, UnaryPlusOperator, UnaryMinusOperator, IsNullOperator, ListLiteral, MapLiteral,
+    PropertyLookup, LabelsTest, Aggregation, Function, Reduce, Coalesce, Extract, All, Single, Any, None, CallProcedure,
+    Create, Match, Return, With, Pattern, NodeAtom, EdgeAtom, Delete, Where, SetProperty, SetProperties, SetLabels,
+    RemoveProperty, RemoveLabels, Merge, Unwind, RegexMatch, LoadCsv, Foreach>;
+
+using TreeLeafVisitor = memgraph::utils::LeafVisitor<Identifier, PrimitiveLiteral, ParameterLookup>;
+
+class HierarchicalTreeVisitor : public TreeCompositeVisitor, public TreeLeafVisitor {
+ public:
+  using TreeCompositeVisitor::PostVisit;
+  using TreeCompositeVisitor::PreVisit;
+  using TreeLeafVisitor::Visit;
+  using typename TreeLeafVisitor::ReturnType;
+};
+
+template <class TResult>
+class ExpressionVisitor
+    : public memgraph::utils::Visitor<
+          TResult, NamedExpression, OrOperator, XorOperator, AndOperator, NotOperator, AdditionOperator,
+          SubtractionOperator, MultiplicationOperator, DivisionOperator, ModOperator, NotEqualOperator, EqualOperator,
+          LessOperator, GreaterOperator, LessEqualOperator, GreaterEqualOperator, InListOperator, SubscriptOperator,
+          ListSlicingOperator, IfOperator, UnaryPlusOperator, UnaryMinusOperator, IsNullOperator, ListLiteral,
+          MapLiteral, PropertyLookup, LabelsTest, Aggregation, Function, Reduce, Coalesce, Extract, All, Single, Any,
+          None, ParameterLookup, Identifier, PrimitiveLiteral, RegexMatch> {};
+
+template <class TResult>
+class QueryVisitor
+    : public memgraph::utils::Visitor<TResult, CypherQuery, ExplainQuery, ProfileQuery, IndexQuery, AuthQuery,
+                                      InfoQuery, ConstraintQuery, DumpQuery, ReplicationQuery, LockPathQuery,
+                                      FreeMemoryQuery, TriggerQuery, IsolationLevelQuery, CreateSnapshotQuery,
+                                      StreamQuery, SettingQuery, VersionQuery, SchemaQuery> {};
+
+}  // namespace MG_INJECTED_NAMESPACE_NAME

src/expr/ast/pretty_print.hpp

@@ -0,0 +1,271 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+#pragma once
+
+#include <iostream>
+#include <type_traits>
+
+#include "expr/ast.hpp"
+#include "expr/typed_value.hpp"
+#include "utils/algorithm.hpp"
+#include "utils/logging.hpp"
+#include "utils/string.hpp"
+
+namespace memgraph::expr {
+namespace detail {
+template <typename T>
+void PrintObject(std::ostream *out, const T &arg) {
+  static_assert(!std::is_convertible<T, Expression *>::value,
+                "This overload shouldn't be called with pointers convertible "
+                "to Expression *. This means your other PrintObject overloads aren't "
+                "being called for certain AST nodes when they should (or perhaps such "
+                "overloads don't exist yet).");
+  *out << arg;
+}
+
+inline void PrintObject(std::ostream *out, const std::string &str) { *out << utils::Escape(str); }
+
+inline void PrintObject(std::ostream *out, Aggregation::Op op) { *out << Aggregation::OpToString(op); }
+
+inline void PrintObject(std::ostream *out, Expression *expr);
+
+inline void PrintObject(std::ostream *out, Identifier *expr) { PrintObject(out, static_cast<Expression *>(expr)); }
+
+template <typename T>
+void PrintObject(std::ostream *out, const std::vector<T> &vec) {
+  *out << "[";
+  utils::PrintIterable(*out, vec, ", ", [](auto &stream, const auto &item) { PrintObject(&stream, item); });
+  *out << "]";
+}
+
+template <typename T>
+void PrintObject(std::ostream *out, const std::vector<T, utils::Allocator<T>> &vec) {
+  *out << "[";
+  utils::PrintIterable(*out, vec, ", ", [](auto &stream, const auto &item) { PrintObject(&stream, item); });
+  *out << "]";
+}
+
+template <typename K, typename V>
+void PrintObject(std::ostream *out, const std::map<K, V> &map) {
+  *out << "{";
+  utils::PrintIterable(*out, map, ", ", [](auto &stream, const auto &item) {
+    PrintObject(&stream, item.first);
+    stream << ": ";
+    PrintObject(&stream, item.second);
+  });
+  *out << "}";
+}
+
+template <typename T>
+void PrintObject(std::ostream *out, const utils::pmr::map<utils::pmr::string, T> &map) {
+  *out << "{";
+  utils::PrintIterable(*out, map, ", ", [](auto &stream, const auto &item) {
+    PrintObject(&stream, item.first);
+    stream << ": ";
+    PrintObject(&stream, item.second);
+  });
+  *out << "}";
+}
+
+template <typename T1, typename T2, typename T3>
+inline void PrintObject(std::ostream *out, const TypedValueT<T1, T2, T3> &value) {
+  using TypedValue = TypedValueT<T1, T2, T3>;
+  switch (value.type()) {
+    case TypedValue::Type::Null:
+      *out << "null";
+      break;
+    case TypedValue::Type::String:
+      PrintObject(out, value.ValueString());
+      break;
+    case TypedValue::Type::Bool:
+      *out << (value.ValueBool() ? "true" : "false");
+      break;
+    case TypedValue::Type::Int:
+      PrintObject(out, value.ValueInt());
+      break;
+    case TypedValue::Type::Double:
+      PrintObject(out, value.ValueDouble());
+      break;
+    case TypedValue::Type::List:
+      PrintObject(out, value.ValueList());
+      break;
+    case TypedValue::Type::Map:
+      PrintObject(out, value.ValueMap());
+      break;
+    case TypedValue::Type::Date:
+      PrintObject(out, value.ValueDate());
+      break;
+    case TypedValue::Type::Duration:
+      PrintObject(out, value.ValueDuration());
+      break;
+    case TypedValue::Type::LocalTime:
+      PrintObject(out, value.ValueLocalTime());
+      break;
+    case TypedValue::Type::LocalDateTime:
+      PrintObject(out, value.ValueLocalDateTime());
+      break;
+    default:
+      MG_ASSERT(false, "PrintObject(std::ostream *out, const TypedValue &value) should not reach here");
+  }
+}
+
+template <typename T>
+void PrintOperatorArgs(std::ostream *out, const T &arg) {
+  *out << " ";
+  PrintObject(out, arg);
+  *out << ")";
+}
+
+template <typename T, typename... Ts>
+void PrintOperatorArgs(std::ostream *out, const T &arg, const Ts &...args) {
+  *out << " ";
+  PrintObject(out, arg);
+  PrintOperatorArgs(out, args...);
+}
+
+template <typename... Ts>
+void PrintOperator(std::ostream *out, const std::string &name, const Ts &...args) {
+  *out << "(" << name;
+  PrintOperatorArgs(out, args...);
+}
+}  // namespace detail
+
+class ExpressionPrettyPrinter : public ExpressionVisitor<void> {
+ public:
+  explicit ExpressionPrettyPrinter(std::ostream *out) : out_(out) {}
+
+  // Unary operators
+  // NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
+#define UNARY_OPERATOR_VISIT(OP_NODE, OP_STR)      \
+  /* NOLINTNEXTLINE(bugprone-macro-parentheses) */ \
+  void Visit(OP_NODE &op) override { detail::PrintOperator(out_, OP_STR, op.expression_); }
+
+  UNARY_OPERATOR_VISIT(NotOperator, "Not");
+  UNARY_OPERATOR_VISIT(UnaryPlusOperator, "+");
+  UNARY_OPERATOR_VISIT(UnaryMinusOperator, "-");
+  UNARY_OPERATOR_VISIT(IsNullOperator, "IsNull");
+
+#undef UNARY_OPERATOR_VISIT
+
+  // Binary operators
+// NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
+#define BINARY_OPERATOR_VISIT(OP_NODE, OP_STR)     \
+  /* NOLINTNEXTLINE(bugprone-macro-parentheses) */ \
+  void Visit(OP_NODE &op) override { detail::PrintOperator(out_, OP_STR, op.expression1_, op.expression2_); }
+
+  BINARY_OPERATOR_VISIT(OrOperator, "Or");
+  BINARY_OPERATOR_VISIT(XorOperator, "Xor");
+  BINARY_OPERATOR_VISIT(AndOperator, "And");
+  BINARY_OPERATOR_VISIT(AdditionOperator, "+");
+  BINARY_OPERATOR_VISIT(SubtractionOperator, "-");
+  BINARY_OPERATOR_VISIT(MultiplicationOperator, "*");
+  BINARY_OPERATOR_VISIT(DivisionOperator, "/");
+  BINARY_OPERATOR_VISIT(ModOperator, "%");
+  BINARY_OPERATOR_VISIT(NotEqualOperator, "!=");
+  BINARY_OPERATOR_VISIT(EqualOperator, "==");
+  BINARY_OPERATOR_VISIT(LessOperator, "<");
+  BINARY_OPERATOR_VISIT(GreaterOperator, ">");
+  BINARY_OPERATOR_VISIT(LessEqualOperator, "<=");
+  BINARY_OPERATOR_VISIT(GreaterEqualOperator, ">=");
+  BINARY_OPERATOR_VISIT(InListOperator, "In");
+  BINARY_OPERATOR_VISIT(SubscriptOperator, "Subscript");
+
+#undef BINARY_OPERATOR_VISIT
+
+  // Other
+  void Visit(ListSlicingOperator &op) override {
+    detail::PrintOperator(out_, "ListSlicing", op.list_, op.lower_bound_, op.upper_bound_);
+  }
+
+  void Visit(IfOperator &op) override {
+    detail::PrintOperator(out_, "If", op.condition_, op.then_expression_, op.else_expression_);
+  }
+
+  void Visit(ListLiteral &op) override { detail::PrintOperator(out_, "ListLiteral", op.elements_); }
+
+  void Visit(MapLiteral &op) override {
+    std::map<std::string, Expression *> map;
+    for (const auto &kv : op.elements_) {
+      map[kv.first.name] = kv.second;
+    }
+    detail::PrintObject(out_, map);
+  }
+
+  void Visit(LabelsTest &op) override { detail::PrintOperator(out_, "LabelsTest", op.expression_); }
+
+  void Visit(Aggregation &op) override { detail::PrintOperator(out_, "Aggregation", op.op_); }
+
+  void Visit(Function &op) override { detail::PrintOperator(out_, "Function", op.function_name_, op.arguments_); }
+
+  void Visit(Reduce &op) override {
+    detail::PrintOperator(out_, "Reduce", op.accumulator_, op.initializer_, op.identifier_, op.list_, op.expression_);
+  }
+
+  void Visit(Coalesce &op) override { detail::PrintOperator(out_, "Coalesce", op.expressions_); }
+
+  void Visit(Extract &op) override { detail::PrintOperator(out_, "Extract", op.identifier_, op.list_, op.expression_); }
+
+  void Visit(All &op) override {
+    detail::PrintOperator(out_, "All", op.identifier_, op.list_expression_, op.where_->expression_);
+  }
+
+  void Visit(Single &op) override {
+    detail::PrintOperator(out_, "Single", op.identifier_, op.list_expression_, op.where_->expression_);
+  }
+
+  void Visit(Any &op) override {
+    detail::PrintOperator(out_, "Any", op.identifier_, op.list_expression_, op.where_->expression_);
+  }
+
+  void Visit(None &op) override {
+    detail::PrintOperator(out_, "None", op.identifier_, op.list_expression_, op.where_->expression_);
+  }
+
+  void Visit(Identifier &op) override { detail::PrintOperator(out_, "Identifier", op.name_); }
+
+  void Visit(PrimitiveLiteral &op) override { detail::PrintObject(out_, op.value_); }
+
+  void Visit(PropertyLookup &op) override {
+    detail::PrintOperator(out_, "PropertyLookup", op.expression_, op.property_.name);
+  }
+
+  void Visit(ParameterLookup &op) override { detail::PrintOperator(out_, "ParameterLookup", op.token_position_); }
+
+  void Visit(NamedExpression &op) override { detail::PrintOperator(out_, "NamedExpression", op.name_, op.expression_); }
+
+  void Visit(RegexMatch &op) override { detail::PrintOperator(out_, "=~", op.string_expr_, op.regex_); }
+
+ private:
+  std::ostream *out_;
+};
+
+namespace detail {
+inline void PrintObject(std::ostream *out, Expression *expr) {
+  if (expr) {
+    ExpressionPrettyPrinter printer{out};
+    expr->Accept(printer);
+  } else {
+    *out << "<null>";
+  }
+}
+}  // namespace detail
+
+inline void PrintExpression(Expression *expr, std::ostream *out) {
+  ExpressionPrettyPrinter printer{out};
+  expr->Accept(printer);
+}
+
+inline void PrintExpression(NamedExpression *expr, std::ostream *out) {
+  ExpressionPrettyPrinter printer{out};
+  expr->Accept(printer);
+}
+}  // namespace memgraph::expr

src/expr/ast/pretty_print_ast_to_original_expression.hpp

@@ -0,0 +1,279 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+#pragma once
+
+#include <iostream>
+#include <type_traits>
+
+#include "expr/ast.hpp"
+#include "expr/typed_value.hpp"
+#include "utils/algorithm.hpp"
+#include "utils/logging.hpp"
+#include "utils/string.hpp"
+
+namespace memgraph::expr {
+inline constexpr const char *identifier_node_symbol = "MG_SYMBOL_NODE";
+inline constexpr const char *identifier_edge_symbol = "MG_SYMBOL_EDGE";
+
+namespace detail {
+template <typename T>
+void PrintObject(std::ostream *out, const T &arg) {
+  static_assert(!std::is_convertible<T, Expression *>::value,
+                "This overload shouldn't be called with pointers convertible "
+                "to Expression *. This means your other PrintObject overloads aren't "
+                "being called for certain AST nodes when they should (or perhaps such "
+                "overloads don't exist yet).");
+  *out << arg;
+}
+
+inline void PrintObject(std::ostream *out, const std::string &str) { *out << str; }
+
+inline void PrintObject(std::ostream * /*out*/, Aggregation::Op /*op*/) {
+  throw utils::NotYetImplemented("PrintObject: Aggregation::Op");
+}
+
+inline void PrintObject(std::ostream * /*out*/, Expression * /*expr*/);
+
+inline void PrintObject(std::ostream *out, Identifier *expr) { PrintObject(out, static_cast<Expression *>(expr)); }
+
+template <typename T>
+void PrintObject(std::ostream * /*out*/, const std::vector<T> & /*vec*/) {
+  throw utils::NotYetImplemented("PrintObject: vector<T>");
+}
+
+template <typename T>
+void PrintObject(std::ostream * /*out*/, const std::vector<T, utils::Allocator<T>> & /*vec*/) {
+  throw utils::NotYetImplemented("PrintObject: vector<T, utils::Allocator<T>>");
+}
+
+template <typename K, typename V>
+void PrintObject(std::ostream * /*out*/, const std::map<K, V> & /*map*/) {
+  throw utils::NotYetImplemented("PrintObject: map<K, V>");
+}
+
+template <typename T>
+void PrintObject(std::ostream * /*out*/, const utils::pmr::map<utils::pmr::string, T> & /*map*/) {
+  throw utils::NotYetImplemented("PrintObject: map<utils::pmr::string, V>");
+}
+
+template <typename T1, typename T2, typename T3>
+inline void PrintObject(std::ostream *out, const TypedValueT<T1, T2, T3> &value) {
+  using TypedValue = TypedValueT<T1, T2, T3>;
+  switch (value.type()) {
+    case TypedValue::Type::Null:
+      *out << "null";
+      break;
+    case TypedValue::Type::String:
+      PrintObject(out, value.ValueString());
+      break;
+    case TypedValue::Type::Bool:
+      *out << (value.ValueBool() ? "true" : "false");
+      break;
+    case TypedValue::Type::Int:
+      PrintObject(out, value.ValueInt());
+      break;
+    case TypedValue::Type::Double:
+      PrintObject(out, value.ValueDouble());
+      break;
+    case TypedValue::Type::List:
+      PrintObject(out, value.ValueList());
+      break;
+    case TypedValue::Type::Map:
+      PrintObject(out, value.ValueMap());
+      break;
+    case TypedValue::Type::Date:
+      PrintObject(out, value.ValueDate());
+      break;
+    case TypedValue::Type::Duration:
+      PrintObject(out, value.ValueDuration());
+      break;
+    case TypedValue::Type::LocalTime:
+      PrintObject(out, value.ValueLocalTime());
+      break;
+    case TypedValue::Type::LocalDateTime:
+      PrintObject(out, value.ValueLocalDateTime());
+      break;
+    default:
+      MG_ASSERT(false, "PrintObject(std::ostream *out, const TypedValue &value) should not reach here");
+  }
+}
+
+template <typename T>
+void PrintOperatorArgs(const std::string & /*name*/, std::ostream *out, bool with_parenthesis, const T &arg) {
+  PrintObject(out, arg);
+  if (with_parenthesis) {
+    *out << ")";
+  }
+}
+
+template <typename T, typename... Ts>
+void PrintOperatorArgs(const std::string &name, std::ostream *out, bool with_parenthesis, const T &arg,
+                       const Ts &...args) {
+  PrintObject(out, arg);
+  *out << " " << name << " ";
+  PrintOperatorArgs(name, out, with_parenthesis, args...);
+}
+
+template <typename... Ts>
+void PrintOperator(const std::string &name, std::ostream *out, bool with_parenthesis, const Ts &...args) {
+  if (with_parenthesis) {
+    *out << "(";
+  }
+  PrintOperatorArgs(name, out, with_parenthesis, args...);
+}
+
+// new
+template <typename T>
+void PrintOperatorArgs(std::ostream *out, const T &arg) {
+  PrintObject(out, arg);
+}
+
+template <typename T, typename... Ts>
+void PrintOperatorArgs(std::ostream *out, const T &arg, const Ts &...args) {
+  PrintObject(out, arg);
+  PrintOperatorArgs(out, args...);
+}
+
+template <typename... Ts>
+void PrintOperator(std::ostream *out, const Ts &...args) {
+  PrintOperatorArgs(out, args...);
+}
+}  // namespace detail
+
+class ExpressionPrettyPrinter : public ExpressionVisitor<void> {
+ public:
+  explicit ExpressionPrettyPrinter(std::ostream *out) : out_(out) {}
+
+  // Unary operators
+  // NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
+#define UNARY_OPERATOR_VISIT(OP_NODE, OP_STR)      \
+  /* NOLINTNEXTLINE(bugprone-macro-parentheses) */ \
+  void Visit(OP_NODE &op) override { detail::PrintOperator(OP_STR, out_, false /*with_parenthesis*/, op.expression_); }
+
+  UNARY_OPERATOR_VISIT(NotOperator, "Not");
+  UNARY_OPERATOR_VISIT(UnaryPlusOperator, "+");
+  UNARY_OPERATOR_VISIT(UnaryMinusOperator, "-");
+  UNARY_OPERATOR_VISIT(IsNullOperator, "IsNull");
+
+#undef UNARY_OPERATOR_VISIT
+
+  // Binary operators
+// NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
+#define BINARY_OPERATOR_VISIT(OP_NODE, OP_STR)                                                        \
+  /* NOLINTNEXTLINE(bugprone-macro-parentheses) */                                                    \
+  void Visit(OP_NODE &op) override {                                                                  \
+    detail::PrintOperator(OP_STR, out_, true /*with_parenthesis*/, op.expression1_, op.expression2_); \
+  }
+// NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
+#define BINARY_OPERATOR_VISIT_NOT_IMPL(OP_NODE, OP_STR) \
+  /* NOLINTNEXTLINE(bugprone-macro-parentheses) */      \
+  void Visit(OP_NODE & /*op*/) override { throw utils::NotYetImplemented("OP_NODE"); }
+
+  BINARY_OPERATOR_VISIT(OrOperator, "Or");
+  BINARY_OPERATOR_VISIT(XorOperator, "Xor");
+  BINARY_OPERATOR_VISIT(AndOperator, "And");
+  BINARY_OPERATOR_VISIT(AdditionOperator, "+");
+  BINARY_OPERATOR_VISIT(SubtractionOperator, "-");
+  BINARY_OPERATOR_VISIT(MultiplicationOperator, "*");
+  BINARY_OPERATOR_VISIT(DivisionOperator, "/");
+  BINARY_OPERATOR_VISIT(ModOperator, "%");
+  BINARY_OPERATOR_VISIT(NotEqualOperator, "!=");
+  BINARY_OPERATOR_VISIT(EqualOperator, "=");
+  BINARY_OPERATOR_VISIT(LessOperator, "<");
+  BINARY_OPERATOR_VISIT(GreaterOperator, ">");
+  BINARY_OPERATOR_VISIT(LessEqualOperator, "<=");
+  BINARY_OPERATOR_VISIT(GreaterEqualOperator, ">=");
+  BINARY_OPERATOR_VISIT_NOT_IMPL(InListOperator, "In");
+  BINARY_OPERATOR_VISIT_NOT_IMPL(SubscriptOperator, "Subscript");
+
+#undef BINARY_OPERATOR_VISIT
+#undef BINARY_OPERATOR_VISIT_NOT_IMPL
+
+  // Other
+  void Visit(ListSlicingOperator & /*op*/) override { throw utils::NotYetImplemented("ListSlicingOperator"); }
+
+  void Visit(IfOperator & /*op*/) override { throw utils::NotYetImplemented("IfOperator"); }
+
+  void Visit(ListLiteral & /*op*/) override { throw utils::NotYetImplemented("ListLiteral"); }
+
+  void Visit(MapLiteral & /*op*/) override { throw utils::NotYetImplemented("MapLiteral"); }
+
+  void Visit(LabelsTest & /*op*/) override { throw utils::NotYetImplemented("LabelsTest"); }
+
+  void Visit(Aggregation & /*op*/) override { throw utils::NotYetImplemented("Aggregation"); }
+
+  void Visit(Function & /*op*/) override { throw utils::NotYetImplemented("Function"); }
+
+  void Visit(Reduce & /*op*/) override { throw utils::NotYetImplemented("Reduce"); }
+
+  void Visit(Coalesce & /*op*/) override { throw utils::NotYetImplemented("Coalesce"); }
+
+  void Visit(Extract & /*op*/) override { throw utils::NotYetImplemented("Extract"); }
+
+  void Visit(All & /*op*/) override { throw utils::NotYetImplemented("All"); }
+
+  void Visit(Single & /*op*/) override { throw utils::NotYetImplemented("Single"); }
+
+  void Visit(Any & /*op*/) override { throw utils::NotYetImplemented("Any"); }
+
+  void Visit(None & /*op*/) override { throw utils::NotYetImplemented("None"); }
+
+  void Visit(Identifier &op) override {
+    auto is_node = true;
+    auto is_edge = false;
+    auto is_other = false;
+    if (is_node) {
+      detail::PrintOperator(out_, identifier_node_symbol);
+    } else if (is_edge) {
+      detail::PrintOperator(out_, identifier_edge_symbol);
+    } else {
+      MG_ASSERT(is_other);
+      detail::PrintOperator(out_, op.name_);
+    }
+  }
+
+  void Visit(PrimitiveLiteral &op) override { detail::PrintObject(out_, op.value_); }
+
+  void Visit(PropertyLookup &op) override { detail::PrintOperator(out_, op.expression_, ".", op.property_.name); }
+
+  void Visit(ParameterLookup & /*op*/) override { throw utils::NotYetImplemented("ParameterLookup"); }
+
+  void Visit(NamedExpression & /*op*/) override { throw utils::NotYetImplemented("NamedExpression"); }
+
+  void Visit(RegexMatch & /*op*/) override { throw utils::NotYetImplemented("RegexMatch"); }
+
+ private:
+  std::ostream *out_;
+};
+
+namespace detail {
+inline void PrintObject(std::ostream *out, Expression *expr) {
+  if (expr) {
+    ExpressionPrettyPrinter printer{out};
+    expr->Accept(printer);
+  } else {
+    *out << "<null>";
+  }
+}
+}  // namespace detail
+
+inline void PrintExpressionToOriginalAndReplaceNodeAndEdgeSymbols(Expression *expr, std::ostream *out) {
+  ExpressionPrettyPrinter printer{out};
+  expr->Accept(printer);
+}
+
+inline std::string ExpressiontoStringWhileReplacingNodeAndEdgeSymbols(Expression *expr) {
+  std::ostringstream ss;
+  expr::PrintExpressionToOriginalAndReplaceNodeAndEdgeSymbols(expr, &ss);
+  return ss.str();
+}
+}  // namespace memgraph::expr

src/expr/exceptions.hpp

@@ -0,0 +1,52 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+#pragma once
+
+#include "utils/exceptions.hpp"
+
+namespace memgraph::expr {
+
+class SyntaxException : public utils::BasicException {
+ public:
+  using utils::BasicException::BasicException;
+  SyntaxException() : SyntaxException("") {}
+};
+
+class SemanticException : public utils::BasicException {
+ public:
+  using utils::BasicException::BasicException;
+  SemanticException() : BasicException("") {}
+};
+
+class ExpressionRuntimeException : public utils::BasicException {
+ public:
+  using utils::BasicException::BasicException;
+};
+
+class RedeclareVariableError : public SemanticException {
+ public:
+  explicit RedeclareVariableError(const std::string &name) : SemanticException("Redeclaring variable: " + name + ".") {}
+};
+
+class UnboundVariableError : public SemanticException {
+ public:
+  explicit UnboundVariableError(const std::string &name) : SemanticException("Unbound variable: " + name + ".") {}
+};
+
+class TypeMismatchError : public SemanticException {
+ public:
+  TypeMismatchError(const std::string &name, const std::string &datum, const std::string &expected)
+      : SemanticException(fmt::format("Type mismatch: {} already defined as {}, expected {}.", name, datum, expected)) {
+  }
+};
+
+}  // namespace memgraph::expr

src/expr/interpret/eval.hpp

@@ -0,0 +1,821 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+/// @file
+#pragma once
+
+#include <algorithm>
+#include <limits>
+#include <map>
+#include <optional>
+#include <regex>
+#include <type_traits>
+#include <vector>
+
+#include "expr/ast.hpp"
+#include "expr/exceptions.hpp"
+#include "expr/interpret/frame.hpp"
+#include "expr/semantic/symbol_table.hpp"
+#include "functions/awesome_memgraph_functions.hpp"
+#include "utils/exceptions.hpp"
+
+namespace memgraph::expr {
+
+struct StorageTag {};
+struct QueryEngineTag {};
+
+template <typename TypedValue, typename EvaluationContext, typename DbAccessor, typename StorageView, typename LabelId,
+          typename PropertyValue, typename ConvFunctor, typename Error, typename Tag = StorageTag>
+class ExpressionEvaluator : public ExpressionVisitor<TypedValue> {
+ public:
+  ExpressionEvaluator(Frame *frame, const SymbolTable &symbol_table, const EvaluationContext &ctx, DbAccessor *dba,
+                      StorageView view)
+      : frame_(frame), symbol_table_(&symbol_table), ctx_(&ctx), dba_(dba), view_(view) {}
+
+  using ExpressionVisitor<TypedValue>::Visit;
+
+  utils::MemoryResource *GetMemoryResource() const { return ctx_->memory; }
+
+  TypedValue Visit(NamedExpression &named_expression) override {
+    const auto &symbol = symbol_table_->at(named_expression);
+    auto value = named_expression.expression_->Accept(*this);
+    frame_->at(symbol) = value;
+    return value;
+  }
+
+  TypedValue Visit(Identifier &ident) override {
+    return TypedValue(frame_->at(symbol_table_->at(ident)), ctx_->memory);
+  }
+
+  // NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
+#define BINARY_OPERATOR_VISITOR(OP_NODE, CPP_OP, CYPHER_OP)                                                         \
+  /* NOLINTNEXTLINE(bugprone-macro-parentheses) */                                                                  \
+  TypedValue Visit(OP_NODE &op) override {                                                                          \
+    auto val1 = op.expression1_->Accept(*this);                                                                     \
+    auto val2 = op.expression2_->Accept(*this);                                                                     \
+    try {                                                                                                           \
+      return val1 CPP_OP val2;                                                                                      \
+    } catch (const TypedValueException &) {                                                                         \
+      throw ExpressionRuntimeException("Invalid types: {} and {} for '{}'.", val1.type(), val2.type(), #CYPHER_OP); \
+    }                                                                                                               \
+  }
+
+  // NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
+#define UNARY_OPERATOR_VISITOR(OP_NODE, CPP_OP, CYPHER_OP)                                   \
+  /* NOLINTNEXTLINE(bugprone-macro-parentheses) */                                           \
+  TypedValue Visit(OP_NODE &op) override {                                                   \
+    auto val = op.expression_->Accept(*this);                                                \
+    try {                                                                                    \
+      return CPP_OP val;                                                                     \
+    } catch (const TypedValueException &) {                                                  \
+      throw ExpressionRuntimeException("Invalid type {} for '{}'.", val.type(), #CYPHER_OP); \
+    }                                                                                        \
+  }
+
+  BINARY_OPERATOR_VISITOR(OrOperator, ||, OR);
+  BINARY_OPERATOR_VISITOR(XorOperator, ^, XOR);
+  BINARY_OPERATOR_VISITOR(AdditionOperator, +, +);
+  BINARY_OPERATOR_VISITOR(SubtractionOperator, -, -);
+  BINARY_OPERATOR_VISITOR(MultiplicationOperator, *, *);
+  BINARY_OPERATOR_VISITOR(DivisionOperator, /, /);
+  BINARY_OPERATOR_VISITOR(ModOperator, %, %);
+  BINARY_OPERATOR_VISITOR(NotEqualOperator, !=, <>);
+  BINARY_OPERATOR_VISITOR(EqualOperator, ==, =);
+  BINARY_OPERATOR_VISITOR(LessOperator, <, <);
+  BINARY_OPERATOR_VISITOR(GreaterOperator, >, >);
+  BINARY_OPERATOR_VISITOR(LessEqualOperator, <=, <=);
+  BINARY_OPERATOR_VISITOR(GreaterEqualOperator, >=, >=);
+
+  UNARY_OPERATOR_VISITOR(NotOperator, !, NOT);
+  UNARY_OPERATOR_VISITOR(UnaryPlusOperator, +, +);
+  UNARY_OPERATOR_VISITOR(UnaryMinusOperator, -, -);
+
+#undef BINARY_OPERATOR_VISITOR
+#undef UNARY_OPERATOR_VISITOR
+
+  void HandleObjectAccessError(Error &shard_error, const std::string_view accessed_object) {
+    switch (shard_error) {
+      case Error::DELETED_OBJECT:
+        throw ExpressionRuntimeException("Trying to access {} on a deleted object.", accessed_object);
+      case Error::NONEXISTENT_OBJECT:
+        throw ExpressionRuntimeException("Trying to access {} from a node object doesn't exist.", accessed_object);
+      case Error::SERIALIZATION_ERROR:
+      case Error::VERTEX_HAS_EDGES:
+      case Error::PROPERTIES_DISABLED:
+      case Error::VERTEX_ALREADY_INSERTED:
+      case Error::OBJECT_NOT_FOUND:
+        throw ExpressionRuntimeException("Unexpected error when accessing {}.", accessed_object);
+      case Error::SCHEMA_NO_SCHEMA_DEFINED_FOR_LABEL:
+      case Error::SCHEMA_VERTEX_PROPERTY_WRONG_TYPE:
+      case Error::SCHEMA_VERTEX_UPDATE_PRIMARY_KEY:
+      case Error::SCHEMA_VERTEX_UPDATE_PRIMARY_LABEL:
+      case Error::SCHEMA_VERTEX_SECONDARY_LABEL_IS_PRIMARY:
+      case Error::SCHEMA_VERTEX_PRIMARY_PROPERTIES_UNDEFINED:
+        throw ExpressionRuntimeException("Unexpected schema violation when accessing {}.", accessed_object);
+    }
+  }
+
+  TypedValue Visit(AndOperator &op) override {
+    auto value1 = op.expression1_->Accept(*this);
+    if (value1.IsBool() && !value1.ValueBool()) {
+      // If first expression is false, don't evaluate the second one.
+      return value1;
+    }
+    auto value2 = op.expression2_->Accept(*this);
+    try {
+      return value1 && value2;
+    } catch (const TypedValueException &) {
+      throw ExpressionRuntimeException("Invalid types: {} and {} for AND.", value1.type(), value2.type());
+    }
+  }
+
+  TypedValue Visit(IfOperator &if_operator) override {
+    auto condition = if_operator.condition_->Accept(*this);
+    if (condition.IsNull()) {
+      return if_operator.else_expression_->Accept(*this);
+    }
+    if (condition.type() != TypedValue::Type::Bool) {
+      // At the moment IfOperator is used only in CASE construct.
+      throw ExpressionRuntimeException("CASE expected boolean expression, got {}.", condition.type());
+    }
+    if (condition.ValueBool()) {
+      return if_operator.then_expression_->Accept(*this);
+    }
+    return if_operator.else_expression_->Accept(*this);
+  }
+
+  TypedValue Visit(InListOperator &in_list) override {
+    auto literal = in_list.expression1_->Accept(*this);
+    auto _list = in_list.expression2_->Accept(*this);
+    if (_list.IsNull()) {
+      return TypedValue(ctx_->memory);
+    }
+    // Exceptions have higher priority than returning nulls when list expression
+    // is not null.
+    if (_list.type() != TypedValue::Type::List) {
+      throw ExpressionRuntimeException("IN expected a list, got {}.", _list.type());
+    }
+    const auto &list = _list.ValueList();
+
+    // If literal is NULL there is no need to try to compare it with every
+    // element in the list since result of every comparison will be NULL. There
+    // is one special case that we must test explicitly: if list is empty then
+    // result is false since no comparison will be performed.
+    if (list.empty()) return TypedValue(false, ctx_->memory);
+    if (literal.IsNull()) return TypedValue(ctx_->memory);
+
+    auto has_null = false;
+    for (const auto &element : list) {
+      auto result = literal == element;
+      if (result.IsNull()) {
+        has_null = true;
+      } else if (result.ValueBool()) {
+        return TypedValue(true, ctx_->memory);
+      }
+    }
+    if (has_null) {
+      return TypedValue(ctx_->memory);
+    }
+    return TypedValue(false, ctx_->memory);
+  }
+
+  TypedValue Visit(SubscriptOperator &list_indexing) override {
+    auto lhs = list_indexing.expression1_->Accept(*this);
+    auto index = list_indexing.expression2_->Accept(*this);
+    if (!lhs.IsList() && !lhs.IsMap() && !lhs.IsVertex() && !lhs.IsEdge() && !lhs.IsNull())
+      throw ExpressionRuntimeException(
+          "Expected a list, a map, a node or an edge to index with '[]', got "
+          "{}.",
+          lhs.type());
+    if (lhs.IsNull() || index.IsNull()) return TypedValue(ctx_->memory);
+    if (lhs.IsList()) {
+      if (!index.IsInt())
+        throw ExpressionRuntimeException("Expected an integer as a list index, got {}.", index.type());
+      auto index_int = index.ValueInt();
+      // NOTE: Take non-const reference to list, so that we can move out the
+      // indexed element as the result.
+      auto &list = lhs.ValueList();
+      if (index_int < 0) {
+        index_int += static_cast<int64_t>(list.size());
+      }
+      if (index_int >= static_cast<int64_t>(list.size()) || index_int < 0) return TypedValue(ctx_->memory);
+      // NOTE: Explicit move is needed, so that we return the move constructed
+      // value and preserve the correct MemoryResource.
+      return std::move(list[index_int]);
+    }
+
+    if (lhs.IsMap()) {
+      if (!index.IsString())
+        throw ExpressionRuntimeException("Expected a string as a map index, got {}.", index.type());
+      // NOTE: Take non-const reference to map, so that we can move out the
+      // looked-up element as the result.
+      auto &map = lhs.ValueMap();
+      auto found = map.find(index.ValueString());
+      if (found == map.end()) return TypedValue(ctx_->memory);
+      // NOTE: Explicit move is needed, so that we return the move constructed
+      // value and preserve the correct MemoryResource.
+      return std::move(found->second);
+    }
+
+    if (lhs.IsVertex()) {
+      if (!index.IsString())
+        throw ExpressionRuntimeException("Expected a string as a property name, got {}.", index.type());
+      return TypedValue(GetProperty(lhs.ValueVertex(), index.ValueString()), ctx_->memory);
+    }
+
+    if (lhs.IsEdge()) {
+      if (!index.IsString())
+        throw ExpressionRuntimeException("Expected a string as a property name, got {}.", index.type());
+      return TypedValue(GetProperty(lhs.ValueEdge(), index.ValueString()), ctx_->memory);
+    }
+
+    // lhs is Null
+    return TypedValue(ctx_->memory);
+  }
+
+  TypedValue Visit(ListSlicingOperator &op) override {
+    // If some type is null we can't return null, because throwing exception
+    // on illegal type has higher priority.
+    auto is_null = false;
+    auto get_bound = [&](Expression *bound_expr, int64_t default_value) {
+      if (bound_expr) {
+        auto bound = bound_expr->Accept(*this);
+        if (bound.type() == TypedValue::Type::Null) {
+          is_null = true;
+        } else if (bound.type() != TypedValue::Type::Int) {
+          throw ExpressionRuntimeException("Expected an integer for a bound in list slicing, got {}.", bound.type());
+        }
+        return bound;
+      }
+      return TypedValue(default_value, ctx_->memory);
+    };
+    auto _upper_bound = get_bound(op.upper_bound_, std::numeric_limits<int64_t>::max());
+    auto _lower_bound = get_bound(op.lower_bound_, 0);
+
+    auto _list = op.list_->Accept(*this);
+    if (_list.type() == TypedValue::Type::Null) {
+      is_null = true;
+    } else if (_list.type() != TypedValue::Type::List) {
+      throw ExpressionRuntimeException("Expected a list to slice, got {}.", _list.type());
+    }
+
+    if (is_null) {
+      return TypedValue(ctx_->memory);
+    }
+    const auto &list = _list.ValueList();
+    auto normalise_bound = [&](int64_t bound) {
+      if (bound < 0) {
+        bound = static_cast<int64_t>(list.size()) + bound;
+      }
+      return std::max(static_cast<int64_t>(0), std::min(bound, static_cast<int64_t>(list.size())));
+    };
+    auto lower_bound = normalise_bound(_lower_bound.ValueInt());
+    auto upper_bound = normalise_bound(_upper_bound.ValueInt());
+    if (upper_bound <= lower_bound) {
+      return TypedValue(typename TypedValue::TVector(ctx_->memory), ctx_->memory);
+    }
+    return TypedValue(
+        typename TypedValue::TVector(list.begin() + lower_bound, list.begin() + upper_bound, ctx_->memory));
+  }
+
+  TypedValue Visit(IsNullOperator &is_null) override {
+    auto value = is_null.expression_->Accept(*this);
+    return TypedValue(value.IsNull(), ctx_->memory);
+  }
+
+  TypedValue Visit(PropertyLookup &property_lookup) override {
+    auto expression_result = property_lookup.expression_->Accept(*this);
+    auto maybe_date = [this](const auto &date, const auto &prop_name) -> std::optional<TypedValue> {
+      if (prop_name == "year") {
+        return TypedValue(date.year, ctx_->memory);
+      }
+      if (prop_name == "month") {
+        return TypedValue(date.month, ctx_->memory);
+      }
+      if (prop_name == "day") {
+        return TypedValue(date.day, ctx_->memory);
+      }
+      return std::nullopt;
+    };
+    auto maybe_local_time = [this](const auto &lt, const auto &prop_name) -> std::optional<TypedValue> {
+      if (prop_name == "hour") {
+        return TypedValue(lt.hour, ctx_->memory);
+      }
+      if (prop_name == "minute") {
+        return TypedValue(lt.minute, ctx_->memory);
+      }
+      if (prop_name == "second") {
+        return TypedValue(lt.second, ctx_->memory);
+      }
+      if (prop_name == "millisecond") {
+        return TypedValue(lt.millisecond, ctx_->memory);
+      }
+      if (prop_name == "microsecond") {
+        return TypedValue(lt.microsecond, ctx_->memory);
+      }
+      return std::nullopt;
+    };
+    auto maybe_duration = [this](const auto &dur, const auto &prop_name) -> std::optional<TypedValue> {
+      if (prop_name == "day") {
+        return TypedValue(dur.Days(), ctx_->memory);
+      }
+      if (prop_name == "hour") {
+        return TypedValue(dur.SubDaysAsHours(), ctx_->memory);
+      }
+      if (prop_name == "minute") {
+        return TypedValue(dur.SubDaysAsMinutes(), ctx_->memory);
+      }
+      if (prop_name == "second") {
+        return TypedValue(dur.SubDaysAsSeconds(), ctx_->memory);
+      }
+      if (prop_name == "millisecond") {
+        return TypedValue(dur.SubDaysAsMilliseconds(), ctx_->memory);
+      }
+      if (prop_name == "microsecond") {
+        return TypedValue(dur.SubDaysAsMicroseconds(), ctx_->memory);
+      }
+      if (prop_name == "nanosecond") {
+        return TypedValue(dur.SubDaysAsNanoseconds(), ctx_->memory);
+      }
+      return std::nullopt;
+    };
+    switch (expression_result.type()) {
+      case TypedValue::Type::Null:
+        return TypedValue(ctx_->memory);
+      case TypedValue::Type::Vertex:
+        return GetProperty(expression_result.ValueVertex(), property_lookup.property_);
+      case TypedValue::Type::Edge:
+        return GetProperty(expression_result.ValueEdge(), property_lookup.property_);
+      case TypedValue::Type::Map: {
+        // NOTE: Take non-const reference to map, so that we can move out the
+        // looked-up element as the result.
+        auto &map = expression_result.ValueMap();
+        auto found = map.find(property_lookup.property_.name.c_str());
+        if (found == map.end()) return TypedValue(ctx_->memory);
+        // NOTE: Explicit move is needed, so that we return the move constructed
+        // value and preserve the correct MemoryResource.
+        return std::move(found->second);
+      }
+      case TypedValue::Type::Duration: {
+        const auto &prop_name = property_lookup.property_.name;
+        const auto &dur = expression_result.ValueDuration();
+        if (auto dur_field = maybe_duration(dur, prop_name); dur_field) {
+          return std::move(*dur_field);
+        }
+        throw ExpressionRuntimeException("Invalid property name {} for Duration", prop_name);
+      }
+      case TypedValue::Type::Date: {
+        const auto &prop_name = property_lookup.property_.name;
+        const auto &date = expression_result.ValueDate();
+        if (auto date_field = maybe_date(date, prop_name); date_field) {
+          return std::move(*date_field);
+        }
+        throw ExpressionRuntimeException("Invalid property name {} for Date", prop_name);
+      }
+      case TypedValue::Type::LocalTime: {
+        const auto &prop_name = property_lookup.property_.name;
+        const auto &lt = expression_result.ValueLocalTime();
+        if (auto lt_field = maybe_local_time(lt, prop_name); lt_field) {
+          return std::move(*lt_field);
+        }
+        throw ExpressionRuntimeException("Invalid property name {} for LocalTime", prop_name);
+      }
+      case TypedValue::Type::LocalDateTime: {
+        const auto &prop_name = property_lookup.property_.name;
+        const auto &ldt = expression_result.ValueLocalDateTime();
+        if (auto date_field = maybe_date(ldt.date, prop_name); date_field) {
+          return std::move(*date_field);
+        }
+        if (auto lt_field = maybe_local_time(ldt.local_time, prop_name); lt_field) {
+          return std::move(*lt_field);
+        }
+        throw ExpressionRuntimeException("Invalid property name {} for LocalDateTime", prop_name);
+      }
+      default:
+        throw ExpressionRuntimeException("Only nodes, edges, maps and temporal types have properties to be looked-up.");
+    }
+  }
+
+  template <typename VertexAccessor, typename TTag = Tag,
+            typename TReturnType = std::enable_if_t<std::is_same_v<TTag, StorageTag>, bool>>
+  TReturnType HasLabelImpl(const VertexAccessor &vertex, const LabelIx &label, StorageTag /*tag*/) {
+    auto has_label = vertex.HasLabel(view_, GetLabel(label));
+    if (has_label.HasError() && has_label.GetError() == Error::NONEXISTENT_OBJECT) {
+      // This is a very nasty and temporary hack in order to make MERGE
+      // work. The old storage had the following logic when returning an
+      // `OLD` view: `return old ? old : new`. That means that if the
+      // `OLD` view didn't exist, it returned the NEW view. With this hack
+      // we simulate that behavior.
+      // TODO (mferencevic, teon.banek): Remove once MERGE is
+      // reimplemented.
+      has_label = vertex.HasLabel(StorageView::NEW, GetLabel(label));
+    }
+    if (has_label.HasError()) {
+      HandleObjectAccessError(has_label.GetError().code, "labels");
+    }
+    return *has_label;
+  }
+
+  template <typename VertexAccessor, typename TTag = Tag,
+            typename TReturnType = std::enable_if_t<std::is_same_v<TTag, QueryEngineTag>, bool>>
+  TReturnType HasLabelImpl(const VertexAccessor &vertex, const LabelIx &label_ix, QueryEngineTag /*tag*/) {
+    auto label = typename VertexAccessor::Label{LabelId::FromUint(label_ix.ix)};
+    return vertex.HasLabel(label);
+  }
+
+  TypedValue Visit(LabelsTest &labels_test) override {
+    auto expression_result = labels_test.expression_->Accept(*this);
+    switch (expression_result.type()) {
+      case TypedValue::Type::Null:
+        return TypedValue(ctx_->memory);
+      case TypedValue::Type::Vertex: {
+        const auto &vertex = expression_result.ValueVertex();
+        if (std::ranges::all_of(labels_test.labels_, [&vertex, this](const auto label_test) {
+              return this->HasLabelImpl(vertex, label_test, Tag{});
+            })) {
+          return TypedValue(true, ctx_->memory);
+        }
+        return TypedValue(false, ctx_->memory);
+      }
+      default:
+        throw ExpressionRuntimeException("Only nodes have labels.");
+    }
+  }
+
+  TypedValue Visit(PrimitiveLiteral &literal) override {
+    // TODO: no need to evaluate constants, we can write it to frame in one
+    // of the previous phases.
+    return TypedValue(literal.value_, ctx_->memory);
+  }
+
+  TypedValue Visit(ListLiteral &literal) override {
+    typename TypedValue::TVector result(ctx_->memory);
+    result.reserve(literal.elements_.size());
+    for (const auto &expression : literal.elements_) result.emplace_back(expression->Accept(*this));
+    return TypedValue(result, ctx_->memory);
+  }
+
+  TypedValue Visit(MapLiteral &literal) override {
+    typename TypedValue::TMap result(ctx_->memory);
+    for (const auto &pair : literal.elements_) result.emplace(pair.first.name, pair.second->Accept(*this));
+    return TypedValue(result, ctx_->memory);
+  }
+
+  TypedValue Visit(Aggregation &aggregation) override {
+    return TypedValue(frame_->at(symbol_table_->at(aggregation)), ctx_->memory);
+  }
+
+  TypedValue Visit(Coalesce &coalesce) override {
+    auto &exprs = coalesce.expressions_;
+
+    if (exprs.size() == 0) {
+      throw ExpressionRuntimeException("'coalesce' requires at least one argument.");
+    }
+
+    for (int64_t i = 0; i < exprs.size(); ++i) {
+      TypedValue val(exprs[i]->Accept(*this), ctx_->memory);
+      if (!val.IsNull()) {
+        return val;
+      }
+    }
+
+    return TypedValue(ctx_->memory);
+  }
+
+  TypedValue Visit(Function &function) override {
+    functions::FunctionContext<DbAccessor> function_ctx{dba_, ctx_->memory, ctx_->timestamp, &ctx_->counters, view_};
+    // Stack allocate evaluated arguments when there's a small number of them.
+    if (function.arguments_.size() <= 8) {
+      TypedValue arguments[8] = {TypedValue(ctx_->memory), TypedValue(ctx_->memory), TypedValue(ctx_->memory),
+                                 TypedValue(ctx_->memory), TypedValue(ctx_->memory), TypedValue(ctx_->memory),
+                                 TypedValue(ctx_->memory), TypedValue(ctx_->memory)};
+      for (size_t i = 0; i < function.arguments_.size(); ++i) {
+        arguments[i] = function.arguments_[i]->Accept(*this);
+      }
+      auto res = function.function_(arguments, function.arguments_.size(), function_ctx);
+      MG_ASSERT(res.GetMemoryResource() == ctx_->memory);
+      return res;
+    } else {
+      typename TypedValue::TVector arguments(ctx_->memory);
+      arguments.reserve(function.arguments_.size());
+      for (const auto &argument : function.arguments_) {
+        arguments.emplace_back(argument->Accept(*this));
+      }
+      auto res = function.function_(arguments.data(), arguments.size(), function_ctx);
+      MG_ASSERT(res.GetMemoryResource() == ctx_->memory);
+      return res;
+    }
+  }
+
+  TypedValue Visit(Reduce &reduce) override {
+    auto list_value = reduce.list_->Accept(*this);
+    if (list_value.IsNull()) {
+      return TypedValue(ctx_->memory);
+    }
+    if (list_value.type() != TypedValue::Type::List) {
+      throw ExpressionRuntimeException("REDUCE expected a list, got {}.", list_value.type());
+    }
+    const auto &list = list_value.ValueList();
+    const auto &element_symbol = symbol_table_->at(*reduce.identifier_);
+    const auto &accumulator_symbol = symbol_table_->at(*reduce.accumulator_);
+    auto accumulator = reduce.initializer_->Accept(*this);
+    for (const auto &element : list) {
+      frame_->at(accumulator_symbol) = accumulator;
+      frame_->at(element_symbol) = element;
+      accumulator = reduce.expression_->Accept(*this);
+    }
+    return accumulator;
+  }
+
+  TypedValue Visit(Extract &extract) override {
+    auto list_value = extract.list_->Accept(*this);
+    if (list_value.IsNull()) {
+      return TypedValue(ctx_->memory);
+    }
+    if (list_value.type() != TypedValue::Type::List) {
+      throw ExpressionRuntimeException("EXTRACT expected a list, got {}.", list_value.type());
+    }
+    const auto &list = list_value.ValueList();
+    const auto &element_symbol = symbol_table_->at(*extract.identifier_);
+    typename TypedValue::TVector result(ctx_->memory);
+    result.reserve(list.size());
+    for (const auto &element : list) {
+      if (element.IsNull()) {
+        result.emplace_back();
+      } else {
+        frame_->at(element_symbol) = element;
+        result.emplace_back(extract.expression_->Accept(*this));
+      }
+    }
+    return TypedValue(result, ctx_->memory);
+  }
+
+  TypedValue Visit(All &all) override {
+    auto list_value = all.list_expression_->Accept(*this);
+    if (list_value.IsNull()) {
+      return TypedValue(ctx_->memory);
+    }
+    if (list_value.type() != TypedValue::Type::List) {
+      throw ExpressionRuntimeException("ALL expected a list, got {}.", list_value.type());
+    }
+    const auto &list = list_value.ValueList();
+    const auto &symbol = symbol_table_->at(*all.identifier_);
+    bool has_null_elements = false;
+    bool has_value = false;
+    for (const auto &element : list) {
+      frame_->at(symbol) = element;
+      auto result = all.where_->expression_->Accept(*this);
+      if (!result.IsNull() && result.type() != TypedValue::Type::Bool) {
+        throw ExpressionRuntimeException("Predicate of ALL must evaluate to boolean, got {}.", result.type());
+      }
+      if (!result.IsNull()) {
+        has_value = true;
+        if (!result.ValueBool()) {
+          return TypedValue(false, ctx_->memory);
+        }
+      } else {
+        has_null_elements = true;
+      }
+    }
+    if (!has_value) {
+      return TypedValue(ctx_->memory);
+    }
+    if (has_null_elements) {
+      return TypedValue(false, ctx_->memory);
+    } else {
+      return TypedValue(true, ctx_->memory);
+    }
+  }
+
+  TypedValue Visit(Single &single) override {
+    auto list_value = single.list_expression_->Accept(*this);
+    if (list_value.IsNull()) {
+      return TypedValue(ctx_->memory);
+    }
+    if (list_value.type() != TypedValue::Type::List) {
+      throw ExpressionRuntimeException("SINGLE expected a list, got {}.", list_value.type());
+    }
+    const auto &list = list_value.ValueList();
+    const auto &symbol = symbol_table_->at(*single.identifier_);
+    bool has_value = false;
+    bool predicate_satisfied = false;
+    for (const auto &element : list) {
+      frame_->at(symbol) = element;
+      auto result = single.where_->expression_->Accept(*this);
+      if (!result.IsNull() && result.type() != TypedValue::Type::Bool) {
+        throw ExpressionRuntimeException("Predicate of SINGLE must evaluate to boolean, got {}.", result.type());
+      }
+      if (result.type() == TypedValue::Type::Bool) {
+        has_value = true;
+      }
+      if (result.IsNull() || !result.ValueBool()) {
+        continue;
+      }
+      // Return false if more than one element satisfies the predicate.
+      if (predicate_satisfied) {
+        return TypedValue(false, ctx_->memory);
+      } else {
+        predicate_satisfied = true;
+      }
+    }
+    if (!has_value) {
+      return TypedValue(ctx_->memory);
+    } else {
+      return TypedValue(predicate_satisfied, ctx_->memory);
+    }
+  }
+
+  TypedValue Visit(Any &any) override {
+    auto list_value = any.list_expression_->Accept(*this);
+    if (list_value.IsNull()) {
+      return TypedValue(ctx_->memory);
+    }
+    if (list_value.type() != TypedValue::Type::List) {
+      throw ExpressionRuntimeException("ANY expected a list, got {}.", list_value.type());
+    }
+    const auto &list = list_value.ValueList();
+    const auto &symbol = symbol_table_->at(*any.identifier_);
+    bool has_value = false;
+    for (const auto &element : list) {
+      frame_->at(symbol) = element;
+      auto result = any.where_->expression_->Accept(*this);
+      if (!result.IsNull() && result.type() != TypedValue::Type::Bool) {
+        throw ExpressionRuntimeException("Predicate of ANY must evaluate to boolean, got {}.", result.type());
+      }
+      if (!result.IsNull()) {
+        has_value = true;
+        if (result.ValueBool()) {
+          return TypedValue(true, ctx_->memory);
+        }
+      }
+    }
+    // Return Null if all elements are Null
+    if (!has_value) {
+      return TypedValue(ctx_->memory);
+    } else {
+      return TypedValue(false, ctx_->memory);
+    }
+  }
+
+  TypedValue Visit(None &none) override {
+    auto list_value = none.list_expression_->Accept(*this);
+    if (list_value.IsNull()) {
+      return TypedValue(ctx_->memory);
+    }
+    if (list_value.type() != TypedValue::Type::List) {
+      throw ExpressionRuntimeException("NONE expected a list, got {}.", list_value.type());
+    }
+    const auto &list = list_value.ValueList();
+    const auto &symbol = symbol_table_->at(*none.identifier_);
+    bool has_value = false;
+    for (const auto &element : list) {
+      frame_->at(symbol) = element;
+      auto result = none.where_->expression_->Accept(*this);
+      if (!result.IsNull() && result.type() != TypedValue::Type::Bool) {
+        throw ExpressionRuntimeException("Predicate of NONE must evaluate to boolean, got {}.", result.type());
+      }
+      if (!result.IsNull()) {
+        has_value = true;
+        if (result.ValueBool()) {
+          return TypedValue(false, ctx_->memory);
+        }
+      }
+    }
+    // Return Null if all elements are Null
+    if (!has_value) {
+      return TypedValue(ctx_->memory);
+    } else {
+      return TypedValue(true, ctx_->memory);
+    }
+  }
+
+  TypedValue Visit(ParameterLookup &param_lookup) override {
+    return TypedValue(conv_(ctx_->parameters.AtTokenPosition(param_lookup.token_position_)), ctx_->memory);
+  }
+
+  TypedValue Visit(RegexMatch &regex_match) override {
+    auto target_string_value = regex_match.string_expr_->Accept(*this);
+    auto regex_value = regex_match.regex_->Accept(*this);
+    if (target_string_value.IsNull() || regex_value.IsNull()) {
+      return TypedValue(ctx_->memory);
+    }
+    if (regex_value.type() != TypedValue::Type::String) {
+      throw ExpressionRuntimeException("Regular expression must evaluate to a string, got {}.", regex_value.type());
+    }
+    if (target_string_value.type() != TypedValue::Type::String) {
+      // Instead of error, we return Null which makes it compatible in case we
+      // use indexed lookup which filters out any non-string properties.
+      // Assuming a property lookup is the target_string_value.
+      return TypedValue(ctx_->memory);
+    }
+    const auto &target_string = target_string_value.ValueString();
+    try {
+      std::regex regex(regex_value.ValueString());
+      return TypedValue(std::regex_match(target_string, regex), ctx_->memory);
+    } catch (const std::regex_error &e) {
+      throw ExpressionRuntimeException("Regex error in '{}': {}", regex_value.ValueString(), e.what());
+    }
+  }
+
+ private:
+  template <class TRecordAccessor, class TTag = Tag,
+            class TReturnType = std::enable_if_t<std::is_same_v<TTag, QueryEngineTag>, TypedValue>>
+  TReturnType GetProperty(const TRecordAccessor &record_accessor, PropertyIx prop) {
+    auto maybe_prop = record_accessor.GetProperty(prop.name);
+    // Handler non existent property
+    return conv_(maybe_prop, dba_);
+  }
+
+  template <class TRecordAccessor, class TTag = Tag,
+            class TReturnType = std::enable_if_t<std::is_same_v<TTag, QueryEngineTag>, TypedValue>>
+  TReturnType GetProperty(const TRecordAccessor &record_accessor, const std::string_view name) {
+    auto maybe_prop = record_accessor.GetProperty(std::string(name));
+    // Handler non existent property
+    return conv_(maybe_prop, dba_);
+  }
+
+  template <class TRecordAccessor, class TTag = Tag,
+            class TReturnType = std::enable_if_t<std::is_same_v<TTag, StorageTag>, TypedValue>>
+  TypedValue GetProperty(const TRecordAccessor &record_accessor, PropertyIx prop) {
+    auto maybe_prop = record_accessor.GetProperty(view_, ctx_->properties[prop.ix]);
+    if (maybe_prop.HasError() && maybe_prop.GetError() == Error::NONEXISTENT_OBJECT) {
+      // This is a very nasty and temporary hack in order to make MERGE work.
+      // The old storage had the following logic when returning an `OLD` view:
+      // `return old ? old : new`. That means that if the `OLD` view didn't
+      // exist, it returned the NEW view. With this hack we simulate that
+      // behavior.
+      // TODO (mferencevic, teon.banek): Remove once MERGE is reimplemented.
+      maybe_prop = record_accessor.GetProperty(StorageView::NEW, ctx_->properties[prop.ix]);
+    }
+    if (maybe_prop.HasError()) {
+      HandleObjectAccessError(maybe_prop.GetError().code, "property");
+    }
+    return conv_(*maybe_prop, ctx_->memory);
+  }
+
+  template <class TRecordAccessor, class TTag = Tag,
+            class TReturnType = std::enable_if_t<std::is_same_v<TTag, StorageTag>, TypedValue>>
+  TypedValue 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() == Error::NONEXISTENT_OBJECT) {
+      // This is a very nasty and temporary hack in order to make MERGE work.
+      // The old storage had the following logic when returning an `OLD` view:
+      // `return old ? old : new`. That means that if the `OLD` view didn't
+      // exist, it returned the NEW view. With this hack we simulate that
+      // behavior.
+      // TODO (mferencevic, teon.banek): Remove once MERGE is reimplemented.
+      maybe_prop = record_accessor.GetProperty(view_, dba_->NameToProperty(name));
+    }
+    if (maybe_prop.HasError()) {
+      HandleObjectAccessError(maybe_prop.GetError().code, "property");
+    }
+    return conv_(*maybe_prop, ctx_->memory);
+  }
+
+  LabelId GetLabel(LabelIx label) { return ctx_->labels[label.ix]; }
+
+  Frame *frame_;
+  const SymbolTable *symbol_table_;
+  const EvaluationContext *ctx_;
+  DbAccessor *dba_;
+  // which switching approach should be used when evaluating
+  StorageView view_;
+  ConvFunctor conv_;
+};
+
+/// A helper function for evaluating an expression that's an int.
+///
+/// @param what - Name of what's getting evaluated. Used for user feedback (via
+///               exception) when the evaluated value is not an int.
+/// @throw ExpressionRuntimeException if expression doesn't evaluate to an int.
+template <typename ExpressionEvaluator>
+int64_t EvaluateInt(ExpressionEvaluator *evaluator, Expression *expr, const std::string &what) {
+  TypedValue value = expr->Accept(*evaluator);
+  try {
+    return value.ValueInt();
+  } catch (TypedValueException &e) {
+    throw ExpressionRuntimeException(what + " must be an int");
+  }
+}
+
+template <typename ExpressionEvaluator>
+std::optional<size_t> EvaluateMemoryLimit(ExpressionEvaluator *eval, Expression *memory_limit, size_t memory_scale) {
+  if (!memory_limit) return std::nullopt;
+  auto limit_value = memory_limit->Accept(*eval);
+  if (!limit_value.IsInt() || limit_value.ValueInt() <= 0)
+    throw ExpressionRuntimeException("Memory limit must be a non-negative integer.");
+  size_t limit = limit_value.ValueInt();
+  if (std::numeric_limits<size_t>::max() / memory_scale < limit)
+    throw ExpressionRuntimeException("Memory limit overflow.");
+  return limit * memory_scale;
+}
+
+}  // namespace memgraph::expr

src/expr/interpret/frame.hpp

@@ -0,0 +1,59 @@
+// Copyright 2023 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+#pragma once
+
+#include <vector>
+
+#include "expr/semantic/symbol_table.hpp"
+#include "utils/logging.hpp"
+#include "utils/memory.hpp"
+#include "utils/pmr/vector.hpp"
+
+namespace memgraph::expr {
+
+class Frame {
+ public:
+  /// Create a Frame of given size backed by a utils::NewDeleteResource()
+  explicit Frame(size_t size) : elems_(size, utils::NewDeleteResource()) { MG_ASSERT(size >= 0); }
+
+  Frame(size_t size, utils::MemoryResource *memory) : elems_(size, memory) { MG_ASSERT(size >= 0); }
+
+  TypedValue &operator[](const Symbol &symbol) { return elems_[symbol.position()]; }
+  const TypedValue &operator[](const Symbol &symbol) const { return elems_[symbol.position()]; }
+
+  TypedValue &at(const Symbol &symbol) { return elems_.at(symbol.position()); }
+  const TypedValue &at(const Symbol &symbol) const { return elems_.at(symbol.position()); }
+
+  auto &elems() { return elems_; }
+  const auto &elems() const { return elems_; }
+
+  utils::MemoryResource *GetMemoryResource() const { return elems_.get_allocator().GetMemoryResource(); }
+
+ private:
+  utils::pmr::vector<TypedValue> elems_;
+};
+
+class FrameWithValidity final : public Frame {
+ public:
+  explicit FrameWithValidity(size_t size) : Frame(size), is_valid_(false) {}
+
+  FrameWithValidity(size_t size, utils::MemoryResource *memory) : Frame(size, memory), is_valid_(false) {}
+
+  bool IsValid() const noexcept { return is_valid_; }
+  void MakeValid() noexcept { is_valid_ = true; }
+  void MakeInvalid() noexcept { is_valid_ = false; }
+
+ private:
+  bool is_valid_;
+};
+
+}  // namespace memgraph::expr

src/expr/parsing.cpp

@@ -0,0 +1,184 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+#include "expr/parsing.hpp"
+
+#include <cctype>
+#include <codecvt>
+#include <locale>
+#include <stdexcept>
+
+#include "expr/exceptions.hpp"
+#include "utils/logging.hpp"
+#include "utils/string.hpp"
+
+namespace memgraph::expr {
+
+int64_t ParseIntegerLiteral(const std::string &s) {
+  try {
+    // Not really correct since long long can have a bigger range than int64_t.
+    return static_cast<int64_t>(std::stoll(s, 0, 0));
+  } catch (const std::out_of_range &) {
+    throw SemanticException("Integer literal exceeds 64 bits.");
+  }
+}
+
+std::string ParseStringLiteral(const std::string &s) {
+  // These functions is declared as lambda since its semantics is highly
+  // specific for this conxtext and shouldn't be used elsewhere.
+  auto EncodeEscapedUnicodeCodepointUtf32 = [](const std::string &s, int &i) {
+    const int kLongUnicodeLength = 8;
+    int j = i + 1;
+    while (j < static_cast<int>(s.size()) - 1 && j < i + kLongUnicodeLength + 1 && isxdigit(s[j])) {
+      ++j;
+    }
+    if (j - i == kLongUnicodeLength + 1) {
+      char32_t t = stoi(s.substr(i + 1, kLongUnicodeLength), 0, 16);
+      i += kLongUnicodeLength;
+      std::wstring_convert<std::codecvt_utf8<char32_t>, char32_t> converter;
+      return converter.to_bytes(t);
+    }
+    throw SyntaxException(
+        "Expected 8 hex digits as unicode codepoint started with \\U. "
+        "Use \\u for 4 hex digits format.");
+  };
+  auto EncodeEscapedUnicodeCodepointUtf16 = [](const std::string &s, int &i) {
+    const int kShortUnicodeLength = 4;
+    int j = i + 1;
+    while (j < static_cast<int>(s.size()) - 1 && j < i + kShortUnicodeLength + 1 && isxdigit(s[j])) {
+      ++j;
+    }
+    if (j - i >= kShortUnicodeLength + 1) {
+      char16_t t = stoi(s.substr(i + 1, kShortUnicodeLength), 0, 16);
+      if (t >= 0xD800 && t <= 0xDBFF) {
+        // t is high surrogate pair. Expect one more utf16 codepoint.
+        j = i + kShortUnicodeLength + 1;
+        if (j >= static_cast<int>(s.size()) - 1 || s[j] != '\\') {
+          throw SemanticException("Invalid UTF codepoint.");
+        }
+        ++j;
+        if (j >= static_cast<int>(s.size()) - 1 || (s[j] != 'u' && s[j] != 'U')) {
+          throw SemanticException("Invalid UTF codepoint.");
+        }
+        ++j;
+        int k = j;
+        while (k < static_cast<int>(s.size()) - 1 && k < j + kShortUnicodeLength && isxdigit(s[k])) {
+          ++k;
+        }
+        if (k != j + kShortUnicodeLength) {
+          throw SemanticException("Invalid UTF codepoint.");
+        }
+        char16_t surrogates[3] = {t, static_cast<char16_t>(stoi(s.substr(j, kShortUnicodeLength), 0, 16)), 0};
+        i += kShortUnicodeLength + 2 + kShortUnicodeLength;
+        std::wstring_convert<std::codecvt_utf8_utf16<char16_t>, char16_t> converter;
+        return converter.to_bytes(surrogates);
+      } else {
+        i += kShortUnicodeLength;
+        std::wstring_convert<std::codecvt_utf8_utf16<char16_t>, char16_t> converter;
+        return converter.to_bytes(t);
+      }
+    }
+    throw SyntaxException(
+        "Expected 4 hex digits as unicode codepoint started with \\u. "
+        "Use \\U for 8 hex digits format.");
+  };
+
+  std::string unescaped;
+  bool escape = false;
+
+  // First and last char is quote, we don't need to look at them.
+  for (int i = 1; i < static_cast<int>(s.size()) - 1; ++i) {
+    if (escape) {
+      switch (s[i]) {
+        case '\\':
+          unescaped += '\\';
+          break;
+        case '\'':
+          unescaped += '\'';
+          break;
+        case '"':
+          unescaped += '"';
+          break;
+        case 'B':
+        case 'b':
+          unescaped += '\b';
+          break;
+        case 'F':
+        case 'f':
+          unescaped += '\f';
+          break;
+        case 'N':
+        case 'n':
+          unescaped += '\n';
+          break;
+        case 'R':
+        case 'r':
+          unescaped += '\r';
+          break;
+        case 'T':
+        case 't':
+          unescaped += '\t';
+          break;
+        case 'U':
+          try {
+            unescaped += EncodeEscapedUnicodeCodepointUtf32(s, i);
+          } catch (const std::range_error &) {
+            throw SemanticException("Invalid UTF codepoint.");
+          }
+          break;
+        case 'u':
+          try {
+            unescaped += EncodeEscapedUnicodeCodepointUtf16(s, i);
+          } catch (const std::range_error &) {
+            throw SemanticException("Invalid UTF codepoint.");
+          }
+          break;
+        default:
+          // This should never happen, except grammar changes and we don't
+          // notice change in this production.
+          DLOG_FATAL("can't happen");
+          throw std::exception();
+      }
+      escape = false;
+    } else if (s[i] == '\\') {
+      escape = true;
+    } else {
+      unescaped += s[i];
+    }
+  }
+  return unescaped;
+}
+
+double ParseDoubleLiteral(const std::string &s) {
+  try {
+    return utils::ParseDouble(s);
+  } catch (const utils::BasicException &) {
+    throw SemanticException("Couldn't parse string to double.");
+  }
+}
+
+std::string ParseParameter(const std::string &s) {
+  DMG_ASSERT(s[0] == '$', "Invalid string passed as parameter name");
+  if (s[1] != '`') return s.substr(1);
+  // If parameter name is escaped symbolic name then symbolic name should be
+  // unescaped and leading and trailing backquote should be removed.
+  DMG_ASSERT(s.size() > 3U && s.back() == '`', "Invalid string passed as parameter name");
+  std::string out;
+  for (int i = 2; i < static_cast<int>(s.size()) - 1; ++i) {
+    if (s[i] == '`') {
+      ++i;
+    }
+    out.push_back(s[i]);
+  }
+  return out;
+}
+
+}  // namespace memgraph::expr

src/expr/parsing.hpp

@@ -0,0 +1,27 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+/// @file
+#pragma once
+
+#include <cstdint>
+#include <string>
+
+namespace memgraph::expr {
+
+// These are the functions for parsing literals and parameter names from
+// opencypher query.
+int64_t ParseIntegerLiteral(const std::string &s);
+std::string ParseStringLiteral(const std::string &s);
+double ParseDoubleLiteral(const std::string &s);
+std::string ParseParameter(const std::string &s);
+
+}  // namespace memgraph::expr

src/expr/semantic/symbol.lcp

@@ -0,0 +1,87 @@
+;; 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
+;; License, and you may not use this file except in compliance with the Business Source License.
+;;
+;; As of the Change Date specified in that file, in accordance with
+;; the Business Source License, use of this software will be governed
+;; by the Apache License, Version 2.0, included in the file
+;; licenses/APL.txt.
+
+#>cpp
+#pragma once
+
+#include <string>
+
+#include "utils/typeinfo.hpp"
+cpp<#
+
+(lcp:namespace memgraph)
+(lcp:namespace expr)
+
+(lcp:define-class symbol ()
+  ((name "std::string" :scope :public)
+   (position :int64_t :scope :public)
+   (user-declared :bool :initval "true" :scope :public)
+   (type "Type" :initval "Type::ANY" :scope :public)
+   (token-position :int64_t :initval "-1" :scope :public))
+  (:public
+    ;; This is similar to TypedValue::Type, but this has `Any` type.
+    ;; TODO: Make a better Type structure which can store a generic List.
+    (lcp:define-enum type (any vertex edge path number edge-list)
+      (:serialize))
+    #>cpp
+    // TODO: Generate enum to string conversion from LCP. Note, that this is
+    // displayed to the end user, so we may want to have a pretty name of each
+    // value.
+    static std::string TypeToString(Type type) {
+      const char *enum_string[] = {"Any",  "Vertex", "Edge",
+                                   "Path", "Number", "EdgeList"};
+      return enum_string[static_cast<int>(type)];
+    }
+
+    Symbol() {}
+    Symbol(const std::string &name, int position, bool user_declared,
+           Type type = Type::ANY, int token_position = -1)
+        : name_(name),
+          position_(position),
+          user_declared_(user_declared),
+          type_(type),
+          token_position_(token_position) {}
+
+    bool operator==(const Symbol &other) const {
+      return position_ == other.position_ && name_ == other.name_ &&
+             type_ == other.type_;
+    }
+    bool operator!=(const Symbol &other) const { return !operator==(other); }
+
+    // TODO: Remove these since members are public
+    const auto &name() const { return name_; }
+    int position() const { return position_; }
+    Type type() const { return type_; }
+    bool user_declared() const { return user_declared_; }
+    int token_position() const { return token_position_; }
+    cpp<#)
+  (:serialize (:slk)))
+
+(lcp:pop-namespace) ;; expr
+(lcp:pop-namespace) ;; memgraph
+
+#>cpp
+namespace std {
+
+template <>
+struct hash<memgraph::expr::Symbol> {
+  size_t operator()(const memgraph::expr::Symbol &symbol) const {
+    size_t prime = 265443599u;
+    size_t hash = std::hash<int>{}(symbol.position());
+    hash ^= prime * std::hash<std::string>{}(symbol.name());
+    hash ^= prime * std::hash<int>{}(static_cast<int>(symbol.type()));
+    return hash;
+  }
+};
+
+}  // namespace std
+
+cpp<#

src/expr/semantic/symbol_generator.hpp

@@ -0,0 +1,712 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+// Copyright 2017 Memgraph
+//
+// Created by Teon Banek on 11-03-2017
+
+#pragma once
+
+#include <algorithm>
+#include <optional>
+#include <ranges>
+#include <unordered_map>
+#include <unordered_set>
+#include <variant>
+#include <vector>
+
+#include "expr/ast.hpp"
+#include "expr/ast/ast_visitor.hpp"
+#include "expr/exceptions.hpp"
+#include "expr/semantic/symbol_table.hpp"
+
+namespace memgraph::expr {
+namespace detail {
+inline std::unordered_map<std::string, Identifier *> GeneratePredefinedIdentifierMap(
+    const std::vector<Identifier *> &predefined_identifiers) {
+  std::unordered_map<std::string, Identifier *> identifier_map;
+  for (const auto &identifier : predefined_identifiers) {
+    identifier_map.emplace(identifier->name_, identifier);
+  }
+
+  return identifier_map;
+}
+}  // namespace detail
+
+/// Visits the AST and generates symbols for variables.
+///
+/// During the process of symbol generation, simple semantic checks are
+/// performed. Such as, redeclaring a variable or conflicting expectations of
+/// variable types.
+class SymbolGenerator : public HierarchicalTreeVisitor {
+ public:
+  explicit SymbolGenerator(SymbolTable *symbol_table, const std::vector<Identifier *> &predefined_identifiers)
+      : symbol_table_(symbol_table),
+        predefined_identifiers_{detail::GeneratePredefinedIdentifierMap(predefined_identifiers)},
+        scopes_(1, Scope()) {}
+
+  using HierarchicalTreeVisitor::PostVisit;
+  using HierarchicalTreeVisitor::PreVisit;
+  using HierarchicalTreeVisitor::Visit;
+  using typename HierarchicalTreeVisitor::ReturnType;
+
+  // Query
+  bool PreVisit(SingleQuery & /*unused*/) override {
+    prev_return_names_ = curr_return_names_;
+    curr_return_names_.clear();
+    return true;
+  }
+
+  // Union
+  bool PreVisit(CypherUnion & /*unused*/) override {
+    scopes_.back() = Scope();
+    return true;
+  }
+
+  bool PostVisit(CypherUnion &cypher_union) override {
+    if (prev_return_names_ != curr_return_names_) {
+      throw SemanticException("All subqueries in an UNION must have the same column names.");
+    }
+
+    // create new symbols for the result of the union
+    for (const auto &name : curr_return_names_) {
+      auto symbol = CreateSymbol(name, false);
+      cypher_union.union_symbols_.push_back(symbol);
+    }
+
+    return true;
+  }
+
+  // Clauses
+  bool PreVisit(Create & /*unused*/) override {
+    scopes_.back().in_create = true;
+    return true;
+  }
+
+  bool PostVisit(Create & /*unused*/) override {
+    scopes_.back().in_create = false;
+    return true;
+  }
+
+  bool PreVisit(CallProcedure &call_proc) override {
+    for (auto *expr : call_proc.arguments_) {
+      expr->Accept(*this);
+    }
+    return false;
+  }
+
+  bool PostVisit(CallProcedure &call_proc) override {
+    for (auto *ident : call_proc.result_identifiers_) {
+      if (HasSymbolLocalScope(ident->name_)) {
+        throw RedeclareVariableError(ident->name_);
+      }
+      ident->MapTo(CreateSymbol(ident->name_, true));
+    }
+    return true;
+  }
+
+  bool PreVisit(LoadCsv & /*unused*/) override { return false; }
+
+  bool PostVisit(LoadCsv &load_csv) override {
+    if (HasSymbolLocalScope(load_csv.row_var_->name_)) {
+      throw RedeclareVariableError(load_csv.row_var_->name_);
+    }
+    load_csv.row_var_->MapTo(CreateSymbol(load_csv.row_var_->name_, true));
+    return true;
+  }
+
+  bool PreVisit(Return &ret) override {
+    auto &scope = scopes_.back();
+    scope.in_return = true;
+    VisitReturnBody(ret.body_);
+    scope.in_return = false;
+    return false;  // We handled the traversal ourselves.
+  }
+
+  bool PostVisit(Return & /*unused*/) override {
+    for (const auto &name_symbol : scopes_.back().symbols) curr_return_names_.insert(name_symbol.first);
+    return true;
+  }
+
+  bool PreVisit(With &with) override {
+    auto &scope = scopes_.back();
+    scope.in_with = true;
+    VisitReturnBody(with.body_, with.where_);
+    scope.in_with = false;
+    return false;  // We handled the traversal ourselves.
+  }
+
+  bool PreVisit(Where & /*unused*/) override {
+    scopes_.back().in_where = true;
+    return true;
+  }
+
+  bool PostVisit(Where & /*unused*/) override {
+    scopes_.back().in_where = false;
+    return true;
+  }
+
+  bool PreVisit(Merge & /*unused*/) override {
+    scopes_.back().in_merge = true;
+    return true;
+  }
+
+  bool PostVisit(Merge & /*unused*/) override {
+    scopes_.back().in_merge = false;
+    return true;
+  }
+
+  bool PostVisit(Unwind &unwind) override {
+    const auto &name = unwind.named_expression_->name_;
+    if (HasSymbolLocalScope(name)) {
+      throw RedeclareVariableError(name);
+    }
+    unwind.named_expression_->MapTo(CreateSymbol(name, true));
+    return true;
+  }
+
+  bool PreVisit(Match & /*unused*/) override {
+    scopes_.back().in_match = true;
+    return true;
+  }
+
+  bool PostVisit(Match & /*unused*/) override {
+    auto &scope = scopes_.back();
+    scope.in_match = false;
+    // Check variables in property maps after visiting Match, so that they can
+    // reference symbols out of bind order.
+    for (auto &ident : scope.identifiers_in_match) {
+      if (!HasSymbolLocalScope(ident->name_) && !ConsumePredefinedIdentifier(ident->name_))
+        throw UnboundVariableError(ident->name_);
+      ident->MapTo(scope.symbols[ident->name_]);
+    }
+    scope.identifiers_in_match.clear();
+    return true;
+  }
+
+  bool PreVisit(Foreach &for_each) override {
+    const auto &name = for_each.named_expression_->name_;
+    scopes_.emplace_back(Scope());
+    scopes_.back().in_foreach = true;
+    for_each.named_expression_->MapTo(
+        CreateSymbol(name, true, Symbol::Type::ANY, for_each.named_expression_->token_position_));
+    return true;
+  }
+
+  bool PostVisit(Foreach & /*unused*/) override {
+    scopes_.pop_back();
+    return true;
+  }
+
+  // Expressions
+  ReturnType Visit(Identifier &ident) override {
+    auto &scope = scopes_.back();
+    if (scope.in_skip || scope.in_limit) {
+      throw SemanticException("Variables are not allowed in {}.", scope.in_skip ? "SKIP" : "LIMIT");
+    }
+    Symbol symbol;
+    if (scope.in_pattern && !(scope.in_node_atom || scope.visiting_edge)) {
+      // If we are in the pattern, and outside of a node or an edge, the
+      // identifier is the pattern name.
+      symbol = GetOrCreateSymbolLocalScope(ident.name_, ident.user_declared_, Symbol::Type::PATH);
+    } else if (scope.in_pattern && scope.in_pattern_atom_identifier) {
+      //  Patterns used to create nodes and edges cannot redeclare already
+      //  established bindings. Declaration only happens in single node
+      //  patterns and in edge patterns. OpenCypher example,
+      //  `MATCH (n) CREATE (n)` should throw an error that `n` is already
+      //  declared. While `MATCH (n) CREATE (n) -[:R]-> (n)` is allowed,
+      //  since `n` now references the bound node instead of declaring it.
+      if ((scope.in_create_node || scope.in_create_edge) && HasSymbolLocalScope(ident.name_)) {
+        throw RedeclareVariableError(ident.name_);
+      }
+      auto type = Symbol::Type::VERTEX;
+      if (scope.visiting_edge) {
+        // Edge referencing is not allowed (like in Neo4j):
+        // `MATCH (n) - [r] -> (n) - [r] -> (n) RETURN r` is not allowed.
+        if (HasSymbolLocalScope(ident.name_)) {
+          throw RedeclareVariableError(ident.name_);
+        }
+        type = scope.visiting_edge->IsVariable() ? Symbol::Type::EDGE_LIST : Symbol::Type::EDGE;
+      }
+      symbol = GetOrCreateSymbolLocalScope(ident.name_, ident.user_declared_, type);
+    } else if (scope.in_pattern && !scope.in_pattern_atom_identifier && scope.in_match) {
+      if (scope.in_edge_range && scope.visiting_edge->identifier_->name_ == ident.name_) {
+        // Prevent variable path bounds to reference the identifier which is bound
+        // by the variable path itself.
+        throw UnboundVariableError(ident.name_);
+      }
+      // Variables in property maps or bounds of variable length path during MATCH
+      // can reference symbols bound later in the same MATCH. We collect them
+      // here, so that they can be checked after visiting Match.
+      scope.identifiers_in_match.emplace_back(&ident);
+    } else {
+      // Everything else references a bound symbol.
+      if (!HasSymbol(ident.name_) && !ConsumePredefinedIdentifier(ident.name_)) throw UnboundVariableError(ident.name_);
+      symbol = GetOrCreateSymbol(ident.name_, ident.user_declared_, Symbol::Type::ANY);
+    }
+    ident.MapTo(symbol);
+    return true;
+  }
+
+  ReturnType Visit(PrimitiveLiteral & /*unused*/) override { return true; }
+
+  ReturnType Visit(ParameterLookup & /*unused*/) override { return true; }
+
+  bool PreVisit(Aggregation &aggr) override {
+    auto &scope = scopes_.back();
+    // Check if the aggregation can be used in this context. This check should
+    // probably move to a separate phase, which checks if the query is well
+    // formed.
+    if ((!scope.in_return && !scope.in_with) || scope.in_order_by || scope.in_skip || scope.in_limit ||
+        scope.in_where) {
+      throw SemanticException("Aggregation functions are only allowed in WITH and RETURN.");
+    }
+    if (scope.in_aggregation) {
+      throw SemanticException(
+          "Using aggregation functions inside aggregation functions is not "
+          "allowed.");
+    }
+    if (scope.num_if_operators) {
+      // Neo allows aggregations here and produces very interesting behaviors.
+      // To simplify implementation at this moment we decided to completely
+      // disallow aggregations inside of the CASE.
+      // However, in some cases aggregation makes perfect sense, for example:
+      //    CASE count(n) WHEN 10 THEN "YES" ELSE "NO" END.
+      // TODO: Rethink of allowing aggregations in some parts of the CASE
+      // construct.
+      throw SemanticException("Using aggregation functions inside of CASE is not allowed.");
+    }
+    // Create a virtual symbol for aggregation result.
+    // Currently, we only have aggregation operators which return numbers.
+    auto aggr_name = Aggregation::OpToString(aggr.op_) + std::to_string(aggr.symbol_pos_);
+    aggr.MapTo(CreateSymbol(aggr_name, false, Symbol::Type::NUMBER));
+    scope.in_aggregation = true;
+    scope.has_aggregation = true;
+    return true;
+  }
+
+  bool PostVisit(Aggregation & /*unused*/) override {
+    scopes_.back().in_aggregation = false;
+    return true;
+  }
+
+  bool PreVisit(IfOperator & /*unused*/) override {
+    ++scopes_.back().num_if_operators;
+    return true;
+  }
+
+  bool PostVisit(IfOperator & /*unused*/) override {
+    --scopes_.back().num_if_operators;
+    return true;
+  }
+
+  bool PreVisit(All &all) override {
+    all.list_expression_->Accept(*this);
+    VisitWithIdentifiers(all.where_->expression_, {all.identifier_});
+    return false;
+  }
+
+  bool PreVisit(Single &single) override {
+    single.list_expression_->Accept(*this);
+    VisitWithIdentifiers(single.where_->expression_, {single.identifier_});
+    return false;
+  }
+
+  bool PreVisit(Any &any) override {
+    any.list_expression_->Accept(*this);
+    VisitWithIdentifiers(any.where_->expression_, {any.identifier_});
+    return false;
+  }
+
+  bool PreVisit(None &none) override {
+    none.list_expression_->Accept(*this);
+    VisitWithIdentifiers(none.where_->expression_, {none.identifier_});
+    return false;
+  }
+
+  bool PreVisit(Reduce &reduce) override {
+    reduce.initializer_->Accept(*this);
+    reduce.list_->Accept(*this);
+    VisitWithIdentifiers(reduce.expression_, {reduce.accumulator_, reduce.identifier_});
+    return false;
+  }
+
+  bool PreVisit(Extract &extract) override {
+    extract.list_->Accept(*this);
+    VisitWithIdentifiers(extract.expression_, {extract.identifier_});
+    return false;
+  }
+
+  // Pattern and its subparts.
+  bool PreVisit(Pattern &pattern) override {
+    auto &scope = scopes_.back();
+    scope.in_pattern = true;
+    if ((scope.in_create || scope.in_merge) && pattern.atoms_.size() == 1U) {
+      MG_ASSERT(utils::IsSubtype(*pattern.atoms_[0], NodeAtom::kType), "Expected a single NodeAtom in Pattern");
+      scope.in_create_node = true;
+    }
+    return true;
+  }
+
+  bool PostVisit(Pattern & /*unused*/) override {
+    auto &scope = scopes_.back();
+    scope.in_pattern = false;
+    scope.in_create_node = false;
+    return true;
+  }
+
+  bool PreVisit(NodeAtom &node_atom) override {
+    auto &scope = scopes_.back();
+    auto check_node_semantic = [&node_atom, &scope, this](const bool props_or_labels) {
+      const auto &node_name = node_atom.identifier_->name_;
+      if ((scope.in_create || scope.in_merge) && props_or_labels && HasSymbolLocalScope(node_name)) {
+        throw SemanticException("Cannot create node '" + node_name +
+                                "' with labels or properties, because it is already declared.");
+      }
+      scope.in_pattern_atom_identifier = true;
+      node_atom.identifier_->Accept(*this);
+      scope.in_pattern_atom_identifier = false;
+    };
+
+    scope.in_node_atom = true;
+    if (auto *properties = std::get_if<std::unordered_map<PropertyIx, Expression *>>(&node_atom.properties_)) {
+      bool props_or_labels = !properties->empty() || !node_atom.labels_.empty();
+
+      check_node_semantic(props_or_labels);
+      for (auto kv : *properties) {
+        kv.second->Accept(*this);
+      }
+
+      return false;
+    }
+    auto &properties_parameter = std::get<ParameterLookup *>(node_atom.properties_);
+    bool props_or_labels = !properties_parameter || !node_atom.labels_.empty();
+
+    check_node_semantic(props_or_labels);
+    properties_parameter->Accept(*this);
+    return false;
+  }
+
+  bool PostVisit(NodeAtom & /*unused*/) override {
+    scopes_.back().in_node_atom = false;
+    return true;
+  }
+
+  bool PreVisit(EdgeAtom &edge_atom) override {
+    auto &scope = scopes_.back();
+    scope.visiting_edge = &edge_atom;
+    if (scope.in_create || scope.in_merge) {
+      scope.in_create_edge = true;
+      if (edge_atom.edge_types_.size() != 1U) {
+        throw SemanticException(
+            "A single relationship type must be specified "
+            "when creating an edge.");
+      }
+      if (scope.in_create &&  // Merge allows bidirectionality
+          edge_atom.direction_ == EdgeAtom::Direction::BOTH) {
+        throw SemanticException(
+            "Bidirectional relationship are not supported "
+            "when creating an edge");
+      }
+      if (edge_atom.IsVariable()) {
+        throw SemanticException(
+            "Variable length relationships are not supported when creating an "
+            "edge.");
+      }
+    }
+    if (auto *properties = std::get_if<std::unordered_map<PropertyIx, Expression *>>(&edge_atom.properties_)) {
+      for (auto kv : *properties) {
+        kv.second->Accept(*this);
+      }
+    } else {
+      std::get<ParameterLookup *>(edge_atom.properties_)->Accept(*this);
+    }
+    if (edge_atom.IsVariable()) {
+      scope.in_edge_range = true;
+      if (edge_atom.lower_bound_) {
+        edge_atom.lower_bound_->Accept(*this);
+      }
+      if (edge_atom.upper_bound_) {
+        edge_atom.upper_bound_->Accept(*this);
+      }
+      scope.in_edge_range = false;
+      scope.in_pattern = false;
+      if (edge_atom.filter_lambda_.expression) {
+        VisitWithIdentifiers(edge_atom.filter_lambda_.expression,
+                             {edge_atom.filter_lambda_.inner_edge, edge_atom.filter_lambda_.inner_node});
+      } else {
+        // Create inner symbols, but don't bind them in scope, since they are to
+        // be used in the missing filter expression.
+        auto *inner_edge = edge_atom.filter_lambda_.inner_edge;
+        inner_edge->MapTo(
+            symbol_table_->CreateSymbol(inner_edge->name_, inner_edge->user_declared_, Symbol::Type::EDGE));
+        auto *inner_node = edge_atom.filter_lambda_.inner_node;
+        inner_node->MapTo(
+            symbol_table_->CreateSymbol(inner_node->name_, inner_node->user_declared_, Symbol::Type::VERTEX));
+      }
+      if (edge_atom.weight_lambda_.expression) {
+        VisitWithIdentifiers(edge_atom.weight_lambda_.expression,
+                             {edge_atom.weight_lambda_.inner_edge, edge_atom.weight_lambda_.inner_node});
+      }
+      scope.in_pattern = true;
+    }
+    scope.in_pattern_atom_identifier = true;
+    edge_atom.identifier_->Accept(*this);
+    scope.in_pattern_atom_identifier = false;
+    if (edge_atom.total_weight_) {
+      if (HasSymbolLocalScope(edge_atom.total_weight_->name_)) {
+        throw RedeclareVariableError(edge_atom.total_weight_->name_);
+      }
+      edge_atom.total_weight_->MapTo(GetOrCreateSymbolLocalScope(
+          edge_atom.total_weight_->name_, edge_atom.total_weight_->user_declared_, Symbol::Type::NUMBER));
+    }
+    return false;
+  }
+
+  bool PostVisit(EdgeAtom & /*unused*/) override {
+    auto &scope = scopes_.back();
+    scope.visiting_edge = nullptr;
+    scope.in_create_edge = false;
+    return true;
+  }
+
+ private:
+  // Scope stores the state of where we are when visiting the AST and a map of
+  // names to symbols.
+  struct Scope {
+    bool in_pattern{false};
+    bool in_merge{false};
+    bool in_create{false};
+    // in_create_node is true if we are creating or merging *only* a node.
+    // Therefore, it is *not* equivalent to (in_create || in_merge) &&
+    // in_node_atom.
+    bool in_create_node{false};
+    // True if creating an edge;
+    // shortcut for (in_create || in_merge) && visiting_edge.
+    bool in_create_edge{false};
+    bool in_node_atom{false};
+    EdgeAtom *visiting_edge{nullptr};
+    bool in_aggregation{false};
+    bool in_return{false};
+    bool in_with{false};
+    bool in_skip{false};
+    bool in_limit{false};
+    bool in_order_by{false};
+    bool in_where{false};
+    bool in_match{false};
+    bool in_foreach{false};
+    // True when visiting a pattern atom (node or edge) identifier, which can be
+    // reused or created in the pattern itself.
+    bool in_pattern_atom_identifier{false};
+    // True when visiting range bounds of a variable path.
+    bool in_edge_range{false};
+    // True if the return/with contains an aggregation in any named expression.
+    bool has_aggregation{false};
+    // Map from variable names to symbols.
+    std::map<std::string, Symbol> symbols;
+    // Identifiers found in property maps of patterns or as variable length path
+    // bounds in a single Match clause. They need to be checked after visiting
+    // Match. Identifiers created by naming vertices, edges and paths are *not*
+    // stored in here.
+    std::vector<Identifier *> identifiers_in_match;
+    // Number of nested IfOperators.
+    int num_if_operators{0};
+  };
+
+  inline static std::optional<Symbol> FindSymbolInScope(const std::string &name, const Scope &scope,
+                                                        Symbol::Type type) {
+    if (auto it = scope.symbols.find(name); it != scope.symbols.end()) {
+      const auto &symbol = it->second;
+      // Unless we have `ANY` type, check that types match.
+      if (type != Symbol::Type::ANY && symbol.type() != Symbol::Type::ANY && type != symbol.type()) {
+        throw TypeMismatchError(name, Symbol::TypeToString(symbol.type()), Symbol::TypeToString(type));
+      }
+      return symbol;
+    }
+    return std::nullopt;
+  }
+
+  bool HasSymbol(const std::string &name) const {
+    return std::ranges::any_of(scopes_, [&name](const auto &scope) { return scope.symbols.contains(name); });
+  }
+
+  bool HasSymbolLocalScope(const std::string &name) const { return scopes_.back().symbols.contains(name); }
+
+  // @return true if it added a predefined identifier with that name
+  bool ConsumePredefinedIdentifier(const std::string &name) {
+    auto it = predefined_identifiers_.find(name);
+
+    if (it == predefined_identifiers_.end()) {
+      return false;
+    }
+
+    // we can only use the predefined identifier in a single scope so we remove it after creating
+    // a symbol for it
+    auto &identifier = it->second;
+    MG_ASSERT(!identifier->user_declared_, "Predefined symbols cannot be user declared!");
+    identifier->MapTo(CreateSymbol(identifier->name_, identifier->user_declared_));
+    predefined_identifiers_.erase(it);
+    return true;
+  }
+
+  // Returns a freshly generated symbol. Previous mapping of the same name to a
+  // different symbol is replaced with the new one.
+  Symbol CreateSymbol(const std::string &name, bool user_declared, Symbol::Type type = Symbol::Type::ANY,
+                      int token_position = -1) {
+    auto symbol = symbol_table_->CreateSymbol(name, user_declared, type, token_position);
+    scopes_.back().symbols[name] = symbol;
+    return symbol;
+  }
+
+  Symbol GetOrCreateSymbol(const std::string &name, bool user_declared, Symbol::Type type = Symbol::Type::ANY) {
+    // NOLINTNEXTLINE
+    for (auto scope = scopes_.rbegin(); scope != scopes_.rend(); ++scope) {
+      if (auto maybe_symbol = FindSymbolInScope(name, *scope, type); maybe_symbol) {
+        return *maybe_symbol;
+      }
+    }
+    return CreateSymbol(name, user_declared, type);
+  }
+
+  // Returns the symbol by name. If the mapping already exists, checks if the
+  // types match. Otherwise, returns a new symbol.
+  Symbol GetOrCreateSymbolLocalScope(const std::string &name, bool user_declared,
+                                     Symbol::Type type = Symbol::Type::ANY) {
+    auto &scope = scopes_.back();
+    if (auto maybe_symbol = FindSymbolInScope(name, scope, type); maybe_symbol) {
+      return *maybe_symbol;
+    }
+    return CreateSymbol(name, user_declared, type);
+  }
+
+  void VisitReturnBody(ReturnBody &body, Where *where = nullptr) {
+    auto &scope = scopes_.back();
+    for (auto &expr : body.named_expressions) {
+      expr->Accept(*this);
+    }
+    std::vector<Symbol> user_symbols;
+    if (body.all_identifiers) {
+      // Carry over user symbols because '*' appeared.
+      for (const auto &sym_pair : scope.symbols) {
+        if (!sym_pair.second.user_declared()) {
+          continue;
+        }
+        user_symbols.emplace_back(sym_pair.second);
+      }
+      if (user_symbols.empty()) {
+        throw SemanticException("There are no variables in scope to use for '*'.");
+      }
+    }
+    // WITH/RETURN clause removes declarations of all the previous variables and
+    // declares only those established through named expressions. New declarations
+    // must not be visible inside named expressions themselves.
+    bool removed_old_names = false;
+    if ((!where && body.order_by.empty()) || scope.has_aggregation) {
+      // WHERE and ORDER BY need to see both the old and new symbols, unless we
+      // have an aggregation. Therefore, we can clear the symbols immediately if
+      // there is neither ORDER BY nor WHERE, or we have an aggregation.
+      scope.symbols.clear();
+      removed_old_names = true;
+    }
+    // Create symbols for named expressions.
+    std::unordered_set<std::string> new_names;
+    for (const auto &user_sym : user_symbols) {
+      new_names.insert(user_sym.name());
+      scope.symbols[user_sym.name()] = user_sym;
+    }
+    for (auto &named_expr : body.named_expressions) {
+      const auto &name = named_expr->name_;
+      if (!new_names.insert(name).second) {
+        throw SemanticException("Multiple results with the same name '{}' are not allowed.", name);
+      }
+      // An improvement would be to infer the type of the expression, so that the
+      // new symbol would have a more specific type.
+      named_expr->MapTo(CreateSymbol(name, true, Symbol::Type::ANY, named_expr->token_position_));
+    }
+    scope.in_order_by = true;
+    for (const auto &order_pair : body.order_by) {
+      order_pair.expression->Accept(*this);
+    }
+    scope.in_order_by = false;
+    if (body.skip) {
+      scope.in_skip = true;
+      body.skip->Accept(*this);
+      scope.in_skip = false;
+    }
+    if (body.limit) {
+      scope.in_limit = true;
+      body.limit->Accept(*this);
+      scope.in_limit = false;
+    }
+    if (where) where->Accept(*this);
+    if (!removed_old_names) {
+      // We have an ORDER BY or WHERE, but no aggregation, which means we didn't
+      // clear the old symbols, so do it now. We cannot just call clear, because
+      // we've added new symbols.
+      for (auto sym_it = scope.symbols.begin(); sym_it != scope.symbols.end();) {
+        if (new_names.find(sym_it->first) == new_names.end()) {
+          sym_it = scope.symbols.erase(sym_it);
+        } else {
+          sym_it++;
+        }
+      }
+    }
+    scopes_.back().has_aggregation = false;
+  }
+
+  void VisitWithIdentifiers(Expression *expr, const std::vector<Identifier *> &identifiers) {
+    auto &scope = scopes_.back();
+    std::vector<std::pair<std::optional<Symbol>, Identifier *>> prev_symbols;
+    // Collect previous symbols if they exist.
+    for (const auto &identifier : identifiers) {
+      std::optional<Symbol> prev_symbol;
+      auto prev_symbol_it = scope.symbols.find(identifier->name_);
+      if (prev_symbol_it != scope.symbols.end()) {
+        prev_symbol = prev_symbol_it->second;
+      }
+      identifier->MapTo(CreateSymbol(identifier->name_, identifier->user_declared_));
+      prev_symbols.emplace_back(prev_symbol, identifier);
+    }
+    // Visit the expression with the new symbols bound.
+    expr->Accept(*this);
+    // Restore back to previous symbols.
+    for (const auto &prev : prev_symbols) {
+      const auto &prev_symbol = prev.first;
+      const auto &identifier = prev.second;
+      if (prev_symbol) {
+        scope.symbols[identifier->name_] = *prev_symbol;
+      } else {
+        scope.symbols.erase(identifier->name_);
+      }
+    }
+  }
+
+  SymbolTable *symbol_table_;
+
+  // Identifiers which are injected from outside the query. Each identifier
+  // is mapped by its name.
+  std::unordered_map<std::string, Identifier *> predefined_identifiers_;
+  std::vector<Scope> scopes_;
+  std::unordered_set<std::string> prev_return_names_;
+  std::unordered_set<std::string> curr_return_names_;
+};
+
+inline SymbolTable MakeSymbolTable(CypherQuery *query, const std::vector<Identifier *> &predefined_identifiers = {}) {
+  SymbolTable symbol_table;
+  SymbolGenerator symbol_generator(&symbol_table, predefined_identifiers);
+  query->single_query_->Accept(symbol_generator);
+  for (auto *cypher_union : query->cypher_unions_) {
+    cypher_union->Accept(symbol_generator);
+  }
+  return symbol_table;
+}
+
+}  // namespace memgraph::expr

src/expr/semantic/symbol_table.hpp

@@ -0,0 +1,64 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+#pragma once
+
+#include <map>
+#include <string>
+
+#include "expr/ast.hpp"
+#include "expr/semantic/symbol.hpp"
+#include "utils/logging.hpp"
+
+namespace memgraph::expr {
+
+class SymbolTable final {
+ public:
+  SymbolTable() {}
+  const Symbol &CreateSymbol(const std::string &name, bool user_declared, Symbol::Type type = Symbol::Type::ANY,
+                             int32_t token_position = -1) {
+    MG_ASSERT(table_.size() <= std::numeric_limits<int32_t>::max(),
+              "SymbolTable size doesn't fit into 32-bit integer!");
+    auto got = table_.emplace(position_, Symbol(name, position_, user_declared, type, token_position));
+    MG_ASSERT(got.second, "Duplicate symbol ID!");
+    position_++;
+    return got.first->second;
+  }
+
+  // TODO(buda): This is the same logic as in the cypher_main_visitor. During
+  // parsing phase symbol table doesn't exist. Figure out a better solution.
+  const Symbol &CreateAnonymousSymbol(Symbol::Type type = Symbol::Type::ANY) {
+    int id = 1;
+    while (true) {
+      static const std::string &kAnonPrefix = "anon";
+      std::string name_candidate = kAnonPrefix + std::to_string(id++);
+      if (std::find_if(std::begin(table_), std::end(table_), [&name_candidate](const auto &item) -> bool {
+            return item.second.name_ == name_candidate;
+          }) == std::end(table_)) {
+        return CreateSymbol(name_candidate, false, type);
+      }
+    }
+  }
+
+  const Symbol &at(const Identifier &ident) const { return table_.at(ident.symbol_pos_); }
+  const Symbol &at(const NamedExpression &nexpr) const { return table_.at(nexpr.symbol_pos_); }
+  const Symbol &at(const Aggregation &aggr) const { return table_.at(aggr.symbol_pos_); }
+
+  // TODO: Remove these since members are public
+  int32_t max_position() const { return static_cast<int32_t>(table_.size()); }
+
+  const auto &table() const { return table_; }
+
+  int32_t position_{0};
+  std::map<int32_t, Symbol> table_;
+};
+
+}  // namespace memgraph::expr

src/expr/typed_value_exception.hpp

@@ -0,0 +1,26 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+#pragma once
+
+#include "utils/exceptions.hpp"
+
+namespace memgraph::expr {
+/**
+ * An exception raised by the TypedValue system. Typically when
+ * trying to perform operations (such as addition) on TypedValues
+ * of incompatible Types.
+ */
+class TypedValueException : public utils::BasicException {
+ public:
+  using utils::BasicException::BasicException;
+};
+}  // namespace memgraph::expr

src/functions/CMakeLists.txt

@@ -0,0 +1 @@
+add_library(mg-functions INTERFACE)

src/glue/v2/auth.cpp

@@ -0,0 +1,64 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+#include "glue/v2/auth.hpp"
+
+namespace memgraph::glue::v2 {
+
+auth::Permission PrivilegeToPermission(query::v2::AuthQuery::Privilege privilege) {
+  switch (privilege) {
+    case query::v2::AuthQuery::Privilege::MATCH:
+      return auth::Permission::MATCH;
+    case query::v2::AuthQuery::Privilege::CREATE:
+      return auth::Permission::CREATE;
+    case query::v2::AuthQuery::Privilege::MERGE:
+      return auth::Permission::MERGE;
+    case query::v2::AuthQuery::Privilege::DELETE:
+      return auth::Permission::DELETE;
+    case query::v2::AuthQuery::Privilege::SET:
+      return auth::Permission::SET;
+    case query::v2::AuthQuery::Privilege::REMOVE:
+      return auth::Permission::REMOVE;
+    case query::v2::AuthQuery::Privilege::INDEX:
+      return auth::Permission::INDEX;
+    case query::v2::AuthQuery::Privilege::STATS:
+      return auth::Permission::STATS;
+    case query::v2::AuthQuery::Privilege::CONSTRAINT:
+      return auth::Permission::CONSTRAINT;
+    case query::v2::AuthQuery::Privilege::DUMP:
+      return auth::Permission::DUMP;
+    case query::v2::AuthQuery::Privilege::REPLICATION:
+      return auth::Permission::REPLICATION;
+    case query::v2::AuthQuery::Privilege::DURABILITY:
+      return auth::Permission::DURABILITY;
+    case query::v2::AuthQuery::Privilege::READ_FILE:
+      return auth::Permission::READ_FILE;
+    case query::v2::AuthQuery::Privilege::FREE_MEMORY:
+      return auth::Permission::FREE_MEMORY;
+    case query::v2::AuthQuery::Privilege::TRIGGER:
+      return auth::Permission::TRIGGER;
+    case query::v2::AuthQuery::Privilege::CONFIG:
+      return auth::Permission::CONFIG;
+    case query::v2::AuthQuery::Privilege::AUTH:
+      return auth::Permission::AUTH;
+    case query::v2::AuthQuery::Privilege::STREAM:
+      return auth::Permission::STREAM;
+    case query::v2::AuthQuery::Privilege::MODULE_READ:
+      return auth::Permission::MODULE_READ;
+    case query::v2::AuthQuery::Privilege::MODULE_WRITE:
+      return auth::Permission::MODULE_WRITE;
+    case query::v2::AuthQuery::Privilege::WEBSOCKET:
+      return auth::Permission::WEBSOCKET;
+    case query::v2::AuthQuery::Privilege::SCHEMA:
+      return auth::Permission::SCHEMA;
+  }
+}
+}  // namespace memgraph::glue::v2

src/glue/v2/auth.hpp

@@ -0,0 +1,23 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+#include "auth/models.hpp"
+#include "query/v2/frontend/ast/ast.hpp"
+
+namespace memgraph::glue::v2 {
+
+/**
+ * This function converts query::AuthQuery::Privilege to its corresponding
+ * auth::Permission.
+ */
+auth::Permission PrivilegeToPermission(query::v2::AuthQuery::Privilege privilege);
+
+}  // namespace memgraph::glue::v2

src/glue/v2/communication.cpp

@@ -0,0 +1,297 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+#include "glue/v2/communication.hpp"
+
+#include <map>
+#include <string>
+#include <vector>
+
+#include "common/errors.hpp"
+#include "coordinator/shard_map.hpp"
+#include "query/v2/accessors.hpp"
+#include "query/v2/request_router.hpp"
+#include "query/v2/requests.hpp"
+#include "storage/v3/edge_accessor.hpp"
+#include "storage/v3/id_types.hpp"
+#include "storage/v3/shard.hpp"
+#include "storage/v3/vertex_accessor.hpp"
+#include "storage/v3/view.hpp"
+#include "utils/exceptions.hpp"
+#include "utils/temporal.hpp"
+
+using memgraph::communication::bolt::Value;
+
+namespace memgraph::glue::v2 {
+
+query::v2::TypedValue ToTypedValue(const Value &value) {
+  switch (value.type()) {
+    case Value::Type::Null:
+      return {};
+    case Value::Type::Bool:
+      return query::v2::TypedValue(value.ValueBool());
+    case Value::Type::Int:
+      return query::v2::TypedValue(value.ValueInt());
+    case Value::Type::Double:
+      return query::v2::TypedValue(value.ValueDouble());
+    case Value::Type::String:
+      return query::v2::TypedValue(value.ValueString());
+    case Value::Type::List: {
+      std::vector<query::v2::TypedValue> list;
+      list.reserve(value.ValueList().size());
+      for (const auto &v : value.ValueList()) list.push_back(ToTypedValue(v));
+      return query::v2::TypedValue(std::move(list));
+    }
+    case Value::Type::Map: {
+      std::map<std::string, query::v2::TypedValue> map;
+      for (const auto &kv : value.ValueMap()) map.emplace(kv.first, ToTypedValue(kv.second));
+      return query::v2::TypedValue(std::move(map));
+    }
+    case Value::Type::Vertex:
+    case Value::Type::Edge:
+    case Value::Type::UnboundedEdge:
+    case Value::Type::Path:
+      throw communication::bolt::ValueException("Unsupported conversion from Value to TypedValue");
+    case Value::Type::Date:
+      return query::v2::TypedValue(value.ValueDate());
+    case Value::Type::LocalTime:
+      return query::v2::TypedValue(value.ValueLocalTime());
+    case Value::Type::LocalDateTime:
+      return query::v2::TypedValue(value.ValueLocalDateTime());
+    case Value::Type::Duration:
+      return query::v2::TypedValue(value.ValueDuration());
+  }
+}
+
+communication::bolt::Vertex ToBoltVertex(const query::v2::accessors::VertexAccessor &vertex,
+                                         const query::v2::RequestRouterInterface *request_router,
+                                         storage::v3::View /*view*/) {
+  auto id = communication::bolt::Id::FromUint(0);
+
+  auto labels = vertex.Labels();
+  std::vector<std::string> new_labels;
+  new_labels.reserve(labels.size());
+  for (const auto &label : labels) {
+    new_labels.push_back(request_router->LabelToName(label.id));
+  }
+
+  auto properties = vertex.Properties();
+  std::map<std::string, Value> new_properties;
+  for (const auto &[prop, property_value] : properties) {
+    new_properties[request_router->PropertyToName(prop)] = ToBoltValue(property_value);
+  }
+  return communication::bolt::Vertex{id, new_labels, new_properties};
+}
+
+communication::bolt::Edge ToBoltEdge(const query::v2::accessors::EdgeAccessor &edge,
+                                     const query::v2::RequestRouterInterface *request_router,
+                                     storage::v3::View /*view*/) {
+  // TODO(jbajic) Fix bolt communication
+  auto id = communication::bolt::Id::FromUint(0);
+  auto from = communication::bolt::Id::FromUint(0);
+  auto to = communication::bolt::Id::FromUint(0);
+  const auto &type = request_router->EdgeTypeToName(edge.EdgeType());
+
+  auto properties = edge.Properties();
+  std::map<std::string, Value> new_properties;
+  for (const auto &[prop, property_value] : properties) {
+    new_properties[request_router->PropertyToName(prop)] = ToBoltValue(property_value);
+  }
+  return communication::bolt::Edge{id, from, to, type, new_properties};
+}
+
+communication::bolt::Path ToBoltPath(const query::v2::accessors::Path & /*edge*/,
+                                     const query::v2::RequestRouterInterface * /*request_router*/,
+                                     storage::v3::View /*view*/) {
+  // TODO(jbajic) Fix bolt communication
+  MG_ASSERT(false, "Path is unimplemented!");
+  return {};
+}
+
+Value ToBoltValue(const query::v2::TypedValue &value, const query::v2::RequestRouterInterface *request_router,
+                  storage::v3::View view) {
+  switch (value.type()) {
+    case query::v2::TypedValue::Type::Null:
+      return {};
+    case query::v2::TypedValue::Type::Bool:
+      return {value.ValueBool()};
+    case query::v2::TypedValue::Type::Int:
+      return {value.ValueInt()};
+    case query::v2::TypedValue::Type::Double:
+      return {value.ValueDouble()};
+    case query::v2::TypedValue::Type::String:
+      return {std::string(value.ValueString())};
+    case query::v2::TypedValue::Type::List: {
+      std::vector<Value> values;
+      values.reserve(value.ValueList().size());
+      for (const auto &v : value.ValueList()) {
+        auto value = ToBoltValue(v, request_router, view);
+        values.emplace_back(std::move(value));
+      }
+      return {std::move(values)};
+    }
+    case query::v2::TypedValue::Type::Map: {
+      std::map<std::string, Value> map;
+      for (const auto &kv : value.ValueMap()) {
+        auto value = ToBoltValue(kv.second, request_router, view);
+        map.emplace(kv.first, std::move(value));
+      }
+      return {std::move(map)};
+    }
+    case query::v2::TypedValue::Type::Vertex: {
+      auto vertex = ToBoltVertex(value.ValueVertex(), request_router, view);
+      return {std::move(vertex)};
+    }
+    case query::v2::TypedValue::Type::Edge: {
+      auto edge = ToBoltEdge(value.ValueEdge(), request_router, view);
+      return {std::move(edge)};
+    }
+    case query::v2::TypedValue::Type::Path: {
+      auto path = ToBoltPath(value.ValuePath(), request_router, view);
+      return {std::move(path)};
+    }
+    case query::v2::TypedValue::Type::Date:
+      return {value.ValueDate()};
+    case query::v2::TypedValue::Type::LocalTime:
+      return {value.ValueLocalTime()};
+    case query::v2::TypedValue::Type::LocalDateTime:
+      return {value.ValueLocalDateTime()};
+    case query::v2::TypedValue::Type::Duration:
+      return {value.ValueDuration()};
+  }
+}
+
+Value ToBoltValue(msgs::Value value) {
+  switch (value.type) {
+    case msgs::Value::Type::Null:
+      return {};
+    case msgs::Value::Type::Bool:
+      return {value.bool_v};
+    case msgs::Value::Type::Int64:
+      return {value.int_v};
+    case msgs::Value::Type::Double:
+      return {value.double_v};
+    case msgs::Value::Type::String:
+      return {std::string(value.string_v)};
+    case msgs::Value::Type::List: {
+      std::vector<Value> values;
+      values.reserve(value.list_v.size());
+      for (const auto &v : value.list_v) {
+        auto maybe_value = ToBoltValue(v);
+        values.emplace_back(std::move(maybe_value));
+      }
+      return Value{std::move(values)};
+    }
+    case msgs::Value::Type::Map: {
+      std::map<std::string, Value> map;
+      for (const auto &kv : value.map_v) {
+        auto maybe_value = ToBoltValue(kv.second);
+        map.emplace(kv.first, std::move(maybe_value));
+      }
+      return Value{std::move(map)};
+    }
+    case msgs::Value::Type::Vertex:
+    case msgs::Value::Type::Edge: {
+      throw utils::BasicException("Vertex and Edge not supported!");
+    }
+      // TODO Value to Date types not supported
+  }
+}
+
+storage::v3::PropertyValue ToPropertyValue(const Value &value) {
+  switch (value.type()) {
+    case Value::Type::Null:
+      return {};
+    case Value::Type::Bool:
+      return storage::v3::PropertyValue(value.ValueBool());
+    case Value::Type::Int:
+      return storage::v3::PropertyValue(value.ValueInt());
+    case Value::Type::Double:
+      return storage::v3::PropertyValue(value.ValueDouble());
+    case Value::Type::String:
+      return storage::v3::PropertyValue(value.ValueString());
+    case Value::Type::List: {
+      std::vector<storage::v3::PropertyValue> vec;
+      vec.reserve(value.ValueList().size());
+      for (const auto &value : value.ValueList()) vec.emplace_back(ToPropertyValue(value));
+      return storage::v3::PropertyValue(std::move(vec));
+    }
+    case Value::Type::Map: {
+      std::map<std::string, storage::v3::PropertyValue> map;
+      for (const auto &kv : value.ValueMap()) map.emplace(kv.first, ToPropertyValue(kv.second));
+      return storage::v3::PropertyValue(std::move(map));
+    }
+    case Value::Type::Vertex:
+    case Value::Type::Edge:
+    case Value::Type::UnboundedEdge:
+    case Value::Type::Path:
+      throw communication::bolt::ValueException("Unsupported conversion from Value to PropertyValue");
+    case Value::Type::Date:
+      return storage::v3::PropertyValue(
+          storage::v3::TemporalData(storage::v3::TemporalType::Date, value.ValueDate().MicrosecondsSinceEpoch()));
+    case Value::Type::LocalTime:
+      return storage::v3::PropertyValue(storage::v3::TemporalData(storage::v3::TemporalType::LocalTime,
+                                                                  value.ValueLocalTime().MicrosecondsSinceEpoch()));
+    case Value::Type::LocalDateTime:
+      return storage::v3::PropertyValue(storage::v3::TemporalData(storage::v3::TemporalType::LocalDateTime,
+                                                                  value.ValueLocalDateTime().MicrosecondsSinceEpoch()));
+    case Value::Type::Duration:
+      return storage::v3::PropertyValue(
+          storage::v3::TemporalData(storage::v3::TemporalType::Duration, value.ValueDuration().microseconds));
+  }
+}
+
+Value ToBoltValue(const storage::v3::PropertyValue &value) {
+  switch (value.type()) {
+    case storage::v3::PropertyValue::Type::Null:
+      return {};
+    case storage::v3::PropertyValue::Type::Bool:
+      return {value.ValueBool()};
+    case storage::v3::PropertyValue::Type::Int:
+      return {value.ValueInt()};
+      break;
+    case storage::v3::PropertyValue::Type::Double:
+      return {value.ValueDouble()};
+    case storage::v3::PropertyValue::Type::String:
+      return {value.ValueString()};
+    case storage::v3::PropertyValue::Type::List: {
+      const auto &values = value.ValueList();
+      std::vector<Value> vec;
+      vec.reserve(values.size());
+      for (const auto &v : values) {
+        vec.push_back(ToBoltValue(v));
+      }
+      return {std::move(vec)};
+    }
+    case storage::v3::PropertyValue::Type::Map: {
+      const auto &map = value.ValueMap();
+      std::map<std::string, Value> dv_map;
+      for (const auto &kv : map) {
+        dv_map.emplace(kv.first, ToBoltValue(kv.second));
+      }
+      return {std::move(dv_map)};
+    }
+    case storage::v3::PropertyValue::Type::TemporalData:
+      const auto &type = value.ValueTemporalData();
+      switch (type.type) {
+        case storage::v3::TemporalType::Date:
+          return {utils::Date(type.microseconds)};
+        case storage::v3::TemporalType::LocalTime:
+          return {utils::LocalTime(type.microseconds)};
+        case storage::v3::TemporalType::LocalDateTime:
+          return {utils::LocalDateTime(type.microseconds)};
+        case storage::v3::TemporalType::Duration:
+          return {utils::Duration(type.microseconds)};
+      }
+  }
+}
+
+}  // namespace memgraph::glue::v2

src/glue/v2/communication.hpp

@@ -0,0 +1,78 @@
+// 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
+// License, and you may not use this file except in compliance with the Business Source License.
+//
+// As of the Change Date specified in that file, in accordance with
+// the Business Source License, use of this software will be governed
+// by the Apache License, Version 2.0, included in the file
+// licenses/APL.txt.
+
+/// @file Conversion functions between Value and other memgraph types.
+#pragma once
+
+#include "communication/bolt/v1/value.hpp"
+#include "coordinator/shard_map.hpp"
+#include "query/v2/bindings/typed_value.hpp"
+#include "query/v2/request_router.hpp"
+#include "storage/v3/property_value.hpp"
+#include "storage/v3/result.hpp"
+#include "storage/v3/shard.hpp"
+#include "storage/v3/view.hpp"
+#include "utils/result.hpp"
+
+namespace memgraph::storage::v3 {
+class EdgeAccessor;
+class Storage;
+class VertexAccessor;
+}  // namespace memgraph::storage::v3
+
+namespace memgraph::glue::v2 {
+
+/// @param storage::v3::VertexAccessor for converting to
+///        communication::bolt::Vertex.
+/// @param query::v2::RequestRouterInterface *request_router getting label and property names.
+/// @param storage::v3::View for deciding which vertex attributes are visible.
+///
+/// @throw std::bad_alloc
+communication::bolt::Vertex ToBoltVertex(const storage::v3::VertexAccessor &vertex,
+                                         const query::v2::RequestRouterInterface *request_router,
+                                         storage::v3::View view);
+
+/// @param storage::v3::EdgeAccessor for converting to communication::bolt::Edge.
+/// @param query::v2::RequestRouterInterface *request_router getting edge type and property names.
+/// @param storage::v3::View for deciding which edge attributes are visible.
+///
+/// @throw std::bad_alloc
+communication::bolt::Edge ToBoltEdge(const storage::v3::EdgeAccessor &edge,
+                                     const query::v2::RequestRouterInterface *request_router, storage::v3::View view);
+
+/// @param query::v2::Path for converting to communication::bolt::Path.
+/// @param query::v2::RequestRouterInterface *request_router ToBoltVertex and ToBoltEdge.
+/// @param storage::v3::View for ToBoltVertex and ToBoltEdge.
+///
+/// @throw std::bad_alloc
+communication::bolt::Path ToBoltPath(const query::v2::accessors::Path &path,
+                                     const query::v2::RequestRouterInterface *request_router, storage::v3::View view);
+
+/// @param query::v2::TypedValue for converting to communication::bolt::Value.
+/// @param query::v2::RequestRouterInterface *request_router ToBoltVertex and ToBoltEdge.
+/// @param storage::v3::View for ToBoltVertex and ToBoltEdge.
+///
+/// @throw std::bad_alloc
+communication::bolt::Value ToBoltValue(const query::v2::TypedValue &value,
+                                       const query::v2::RequestRouterInterface *request_router, storage::v3::View view);
+
+query::v2::TypedValue ToTypedValue(const communication::bolt::Value &value);
+
+communication::bolt::Value ToBoltValue(const storage::v3::PropertyValue &value);
+
+storage::v3::PropertyValue ToPropertyValue(const communication::bolt::Value &value);
+
+communication::bolt::Value ToBoltValue(msgs::Value value);
+
+communication::bolt::Value ToBoltValue(msgs::Value value, const query::v2::RequestRouterInterface *request_router,
+                                       storage::v3::View view);
+
+}  // namespace memgraph::glue::v2

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()) {