Remove docker volumes in memgraph images

* Make memgraph buildable with new toolchain

* Use toolchain v3 in workflows

.arcconfig

@@ -1,7 +0,0 @@
-{
-  "project_id" : "memgraph",
-  "conduit_uri" : "https://phabricator.memgraph.io",
-  "phabricator_uri" : "https://phabricator.memgraph.io",
-  "git.default-relative-commit": "origin/master",
-  "arc.land.onto.default": "master"
-}

.arclint

@@ -1,16 +0,0 @@
-{
-  "linters": {
-    "clang-tidy": {
-      "type": "script-and-regex",
-      "include": "(\\.(cpp|cc|cxx|c|h|hpp|lcp)$)",
-      "script-and-regex.script": "./tools/arc-clang-tidy",
-      "script-and-regex.regex": "/^(?P<file>.*):(?P<line>\\d+):(?P<char>\\d+): (?P<severity>warning|error): (?P<message>.*)$/m"
-    },
-    "clang-format": {
-      "type": "script-and-regex",
-      "include": "(\\.(cpp|cc|cxx|c|h|hpp)$)",
-      "script-and-regex.script": "./tools/arc-clang-format",
-      "script-and-regex.regex": "/^(?P<severity>warning):(?P<offset>\\d+):(?P<message>.*)$/m"
-    }
-  }
-}

.clang-format

@@ -1,9 +1,10 @@
 ---
 Language:     Cpp
 BasedOnStyle: Google
-Standard:     "C++11"
+Standard:     "c++20"
 UseTab:       Never
 DerivePointerAlignment: false
 PointerAlignment: Right
-ColumnLimit : 80
+ColumnLimit : 120
+IncludeBlocks: Preserve
 ...

.clang-tidy

@@ -1,5 +1,6 @@
 ---
 Checks: '*,
+         -altera-struct-pack-align,
          -android-*,
          -cert-err58-cpp,
          -cppcoreguidelines-avoid-c-arrays,
@@ -26,6 +27,7 @@ Checks: '*,
          -fuchsia-virtual-inheritance,
          -google-explicit-constructor,
          -google-readability-*,
+         -google-runtime-references,
          -hicpp-avoid-c-arrays,
          -hicpp-avoid-goto,
          -hicpp-braces-around-statements,
@@ -34,10 +36,14 @@ Checks: '*,
          -hicpp-no-assembler,
          -hicpp-no-malloc,
          -hicpp-use-equals-default,
+         -hicpp-use-nullptr,
          -hicpp-vararg,
          -llvm-header-guard,
+         -llvm-include-order,
+         -llvmlibc-callee-namespace,
+         -llvmlibc-implementation-in-namespace,
+         -llvmlibc-restrict-system-libc-headers,
          -misc-non-private-member-variables-in-classes,
-         -misc-unused-parameters,
          -modernize-avoid-c-arrays,
          -modernize-concat-nested-namespaces,
          -modernize-pass-by-value,
@@ -47,11 +53,13 @@ Checks: '*,
          -performance-unnecessary-value-param,
          -readability-braces-around-statements,
          -readability-else-after-return,
+         -readability-function-cognitive-complexity,
          -readability-implicit-bool-conversion,
          -readability-magic-numbers,
-         -readability-named-parameter'
+         -readability-named-parameter,
+         -misc-no-recursion'
 WarningsAsErrors: ''
-HeaderFilterRegex: ''
+HeaderFilterRegex: 'src/.*'
 AnalyzeTemporaryDtors: false
 FormatStyle:     none
 CheckOptions:

.githooks/pre-commit

@@ -0,0 +1,35 @@
+#!/bin/sh
+
+project_folder=$(git rev-parse --show-toplevel)
+if git rev-parse --verify HEAD >/dev/null 2>&1
+then
+	against=HEAD
+else
+	# Initial commit: diff against an empty tree object
+	against=$(git hash-object -t tree /dev/null)
+fi
+
+# Redirect output to stderr.
+exec 1>&2
+
+tmpdir=$(mktemp -d repo-XXXXXXXX)
+trap "rm -rf $tmpdir" EXIT INT
+
+modified_files=$(git diff --cached --name-only --diff-filter=AM $against | sed -nE "/.*\.(cpp|cc|cxx|c|h|hpp)$/p")
+for file in $modified_files; do
+  echo "Checking $file..."
+
+  cp $project_folder/.clang-format $project_folder/.clang-tidy $tmpdir
+
+  git checkout-index --prefix="$tmpdir/" -- $file
+
+  echo "Running clang-format..."
+  $project_folder/tools/git-clang-format $tmpdir/$file
+  code=$?
+
+  if [ $code -ne 0 ]; then
+    break
+  fi
+done;
+
+return $code

.github/pull_request_template.md

@@ -0,0 +1,9 @@
+[master < Epic] PR
+- [ ] Check, and update documentation if necessary
+- [ ] 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
+
+[master < Task] PR
+- [ ] Check, and update documentation if necessary
+- [ ] Update [changelog](https://docs.memgraph.com/memgraph/changelog)

.github/workflows/daily_banchmark.yaml

@@ -0,0 +1,68 @@
+name: Daily Benchmark
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: "0 1 * * *"
+
+jobs:
+  release_benchmarks:
+    name: "Release benchmarks"
+    runs-on: [self-hosted, Linux, X64, Diff, Gen7]
+    env:
+      THREADS: 24
+
+    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-v3/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build only memgraph release binaries.
+          cd build
+          cmake -DCMAKE_BUILD_TYPE=release ..
+          make -j$THREADS
+
+      - name: Run macro benchmarks
+        run: |
+          cd tests/macro_benchmark
+          ./harness QuerySuite MemgraphRunner \
+            --groups aggregation 1000_create unwind_create dense_expand match \
+            --no-strict
+
+      - name: Upload macro benchmark results
+        run: |
+          cd tools/bench-graph-client
+          virtualenv -p python3 ve3
+          source ve3/bin/activate
+          pip install -r requirements.txt
+          ./main.py --benchmark-name "macro_benchmark" \
+                    --benchmark-results-path "../../tests/macro_benchmark/.harness_summary" \
+                    --github-run-id "${{ github.run_id }}" \
+                    --github-run-number "${{ github.run_number }}"
+
+      - name: Run mgbench
+        run: |
+          cd tests/mgbench
+          ./benchmark.py --num-workers-for-benchmark 12 --export-results benchmark_result.json pokec/medium/*/*
+
+      - name: Upload mgbench results
+        run: |
+          cd tools/bench-graph-client
+          virtualenv -p python3 ve3
+          source ve3/bin/activate
+          pip install -r requirements.txt
+          ./main.py --benchmark-name "mgbench" \
+                    --benchmark-results-path "../../tests/mgbench/benchmark_result.json" \
+                    --github-run-id "${{ github.run_id }}" \
+                    --github-run-number "${{ github.run_number }}"

.github/workflows/diff.yaml

@@ -0,0 +1,406 @@
+name: Diff
+
+on:
+  push:
+    paths-ignore:
+      - 'docs/**'
+      - '**/*.md'
+      - '.clang-format'
+      - 'CODEOWNERS'
+
+jobs:
+  community_build:
+    name: "Community build"
+    runs-on: [self-hosted, Linux, X64, Diff]
+    env:
+      THREADS: 24
+
+    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 community binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build community binaries.
+          cd build
+          cmake -DCMAKE_BUILD_TYPE=release -DMG_ENTERPRISE=OFF ..
+          make -j$THREADS
+
+      - name: Run unit tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Run unit tests.
+          cd build
+          ctest -R memgraph__unit --output-on-failure -j$THREADS
+
+      - name: Run stress test
+        run: |
+          cd tests/stress
+          ./continuous_integration
+
+      - name: Create community DEB package
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          cd build
+
+          # create mgconsole
+          # we use the -B to force the build
+          make -j$THREADS -B mgconsole
+
+          # Create community DEB package.
+          mkdir output && cd output
+          cpack -G DEB --config ../CPackConfig.cmake
+
+      - name: Save community DEB package
+        uses: actions/upload-artifact@v2
+        with:
+          name: "Community DEB package"
+          path: build/output/memgraph*.deb
+
+  code_analysis:
+    name: "Code analysis"
+    runs-on: [self-hosted, Linux, X64, Diff]
+    env:
+      THREADS: 24
+
+    steps:
+      - name: Set up repository
+        uses: actions/checkout@v2
+        with:
+          # Number of commits to fetch. `0` indicates all history for all
+          # branches and tags. (default: 1)
+          fetch-depth: 0
+
+      - name: Build combined ASAN, UBSAN and coverage binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Initialize dependencies.
+          ./init
+
+          cd build
+          cmake -DTEST_COVERAGE=ON -DASAN=ON -DUBSAN=ON ..
+          make -j$THREADS memgraph__unit
+
+      - name: Run unit tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Run unit tests. It is restricted to 2 threads intentionally, because higher concurrency makes the timing related tests unstable.
+          cd build
+          LSAN_OPTIONS=suppressions=$PWD/../tools/lsan.supp UBSAN_OPTIONS=halt_on_error=1 ctest -R memgraph__unit --output-on-failure -j2
+
+      - name: Compute code coverage
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Compute code coverage.
+          cd tools/github
+          ./coverage_convert
+
+          # Package code coverage.
+          cd generated
+          tar -czf code_coverage.tar.gz coverage.json html report.json summary.rmu
+
+      - name: Save code coverage
+        uses: actions/upload-artifact@v2
+        with:
+          name: "Code coverage"
+          path: tools/github/generated/code_coverage.tar.gz
+
+      - name: Run clang-tidy
+        run: |
+          source /opt/toolchain-v3/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 $THREADS -path build | tee ./build/clang_tidy_output.txt
+
+          # Fail if any warning is reported
+          ! cat ./build/clang_tidy_output.txt | ./tools/github/clang-tidy/grep_error_lines.sh > /dev/null
+
+  debug_build:
+    name: "Debug build"
+    runs-on: [self-hosted, Linux, X64, Diff]
+    env:
+      THREADS: 24
+
+    steps:
+      - name: Set up repository
+        uses: actions/checkout@v2
+        with:
+          # Number of commits to fetch. `0` indicates all history for all
+          # branches and tags. (default: 1)
+          fetch-depth: 0
+
+      - name: Build debug binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build debug binaries.
+          cd build
+          cmake ..
+          make -j$THREADS
+
+      - name: Run leftover CTest tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Run leftover CTest tests (all except unit and benchmark tests).
+          cd build
+          ctest -E "(memgraph__unit|memgraph__benchmark)" --output-on-failure
+
+      - 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: $name"
+            if [ -x prepare.sh ]; then
+              ./prepare.sh
+            fi
+            if [ -x runner.py ]; then
+              ./runner.py
+            elif [ -x runner.sh ]; then
+              ./runner.sh
+            fi
+            echo
+            popd >/dev/null
+          done
+
+      - name: Run cppcheck and clang-format
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Run cppcheck and clang-format.
+          cd tools/github
+          ./cppcheck_and_clang_format diff
+
+      - name: Save cppcheck and clang-format errors
+        uses: actions/upload-artifact@v2
+        with:
+          name: "Code coverage"
+          path: tools/github/cppcheck_and_clang_format.txt
+
+  release_build:
+    name: "Release build"
+    runs-on: [self-hosted, Linux, X64, Diff]
+    env:
+      THREADS: 24
+
+    steps:
+      - name: Set up repository
+        uses: actions/checkout@v2
+        with:
+          # Number of commits to fetch. `0` indicates all history for all
+          # branches and tags. (default: 1)
+          fetch-depth: 0
+
+      - name: Build release binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build release binaries.
+          cd build
+          cmake -DCMAKE_BUILD_TYPE=release ..
+          make -j$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 e2e tests
+        run: |
+          # TODO(gitbuda): Setup mgclient and pymgclient properly.
+          cd tests
+          ./setup.sh
+          source ve3/bin/activate
+          cd e2e
+          LD_LIBRARY_PATH=$LD_LIBRARY_PATH:../../libs/mgclient/lib python runner.py --workloads-root-directory .
+
+      - name: Run stress test (plain)
+        run: |
+          cd tests/stress
+          ./continuous_integration
+
+      - name: Run stress test (SSL)
+        run: |
+          cd tests/stress
+          ./continuous_integration --use-ssl
+
+      - name: Run durability test
+        run: |
+          cd tests/stress
+          source ve3/bin/activate
+          python3 durability --num-steps 5
+
+      - name: Create enterprise DEB package
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          cd build
+
+          # create mgconsole
+          # we use the -B to force the build
+          make -j$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
+
+    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-v3/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: ${{ always() }}
+        with:
+          name: "Jepsen Report"
+          path: tests/jepsen/Jepsen.tar.gz
+
+  release_benchmarks:
+    name: "Release benchmarks"
+    runs-on: [self-hosted, Linux, X64, Diff, Gen7]
+    env:
+      THREADS: 24
+
+    steps:
+      - name: Set up repository
+        uses: actions/checkout@v2
+        with:
+          # Number of commits to fetch. `0` indicates all history for all
+          # branches and tags. (default: 1)
+          fetch-depth: 0
+
+      - name: Build release binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build only memgraph release binaries.
+          cd build
+          cmake -DCMAKE_BUILD_TYPE=release ..
+          make -j$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: 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 }}"
+
+      - 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 }}"

.github/workflows/full_clang_tidy.yaml

@@ -0,0 +1,44 @@
+name: Run clang-tidy on the full codebase
+
+on:
+  workflow_dispatch:
+
+jobs:
+  clang_tidy_check:
+    name: "Clang-tidy check"
+    runs-on: [self-hosted, Linux, X64, Ubuntu20.04]
+    env:
+      THREADS: 24
+
+    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 debug binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build debug binaries.
+
+          cd build
+          cmake ..
+          make -j$THREADS
+
+      - name: Run clang-tidy
+        run: |
+          source /opt/toolchain-v3/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 $THREADS -clang-tidy-binary=/opt/toolchain-v3/bin/clang-tidy "$PWD/src/*" |
+            tee ./build/full_clang_tidy_output.txt
+
+      - name: Summarize clang-tidy results
+        run: cat ./build/full_clang_tidy_output.txt | ./tools/github/clang-tidy/count_errors.sh

.github/workflows/package_all.yaml

@@ -0,0 +1,248 @@
+name: Package All
+
+# TODO(gitbuda): Cleanup docker container if GHA job was canceled.
+
+on: workflow_dispatch
+
+jobs:
+  centos-7_community:
+    runs-on: [self-hosted, DockerMgBuild]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package community centos-7
+      - name: "Upload package"
+        uses: actions/upload-artifact@v2
+        with:
+          name: centos-7_community
+          path: build/output/centos-7/memgraph*.rpm
+
+  centos-8_community:
+    runs-on: [self-hosted, DockerMgBuild]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package community centos-8
+      - name: "Upload package"
+        uses: actions/upload-artifact@v2
+        with:
+          name: centos-8_community
+          path: build/output/centos-8/memgraph*.rpm
+
+  debian-9_community:
+    runs-on: [self-hosted, DockerMgBuild]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package community debian-9
+      - name: "Upload package"
+        uses: actions/upload-artifact@v2
+        with:
+          name: debian-9_community
+          path: build/output/debian-9/memgraph*.deb
+
+  debian-10_community:
+    runs-on: [self-hosted, DockerMgBuild]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package community debian-10
+      - name: "Upload package"
+        uses: actions/upload-artifact@v2
+        with:
+          name: debian-10_community
+          path: build/output/debian-10/memgraph*.deb
+
+  docker_community:
+    runs-on: [self-hosted, DockerMgBuild]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          cd release/package
+          ./run.sh package community debian-10 --for-docker
+          ./run.sh docker
+      - name: "Upload package"
+        uses: actions/upload-artifact@v2
+        with:
+          name: docker_community
+          path: build/output/docker/memgraph*.tar.gz
+
+  ubuntu-1804_community:
+    runs-on: [self-hosted, DockerMgBuild]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package community ubuntu-18.04
+      - name: "Upload package"
+        uses: actions/upload-artifact@v2
+        with:
+          name: ubuntu-1804_community
+          path: build/output/ubuntu-18.04/memgraph*.deb
+
+  ubuntu-2004_community:
+    runs-on: [self-hosted, DockerMgBuild]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package community ubuntu-20.04
+      - name: "Upload package"
+        uses: actions/upload-artifact@v2
+        with:
+          name: ubuntu-2004_community
+          path: build/output/ubuntu-20.04/memgraph*.deb
+
+  centos-7_enterprise:
+    runs-on: [self-hosted, DockerMgBuild]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package enterprise centos-7
+      - name: "Upload package"
+        uses: actions/upload-artifact@v2
+        with:
+          name: centos-7_enterprise
+          path: build/output/centos-7/memgraph*.rpm
+
+  centos-8_enterprise:
+    runs-on: [self-hosted, DockerMgBuild]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package enterprise centos-8
+      - name: "Upload package"
+        uses: actions/upload-artifact@v2
+        with:
+          name: centos-8_enterprise
+          path: build/output/centos-8/memgraph*.rpm
+
+  debian-9_enterprise:
+    runs-on: [self-hosted, DockerMgBuild]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package enterprise debian-9
+      - name: "Upload package"
+        uses: actions/upload-artifact@v2
+        with:
+          name: debian-9_enterprise
+          path: build/output/debian-9/memgraph*.deb
+
+  debian-10_enterprise:
+    runs-on: [self-hosted, DockerMgBuild]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package enterprise debian-10
+      - name: "Upload package"
+        uses: actions/upload-artifact@v2
+        with:
+          name: debian-10_enterprise
+          path: build/output/debian-10/memgraph*.deb
+
+  docker_enterprise:
+    runs-on: [self-hosted, DockerMgBuild]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          cd release/package
+          ./run.sh package enterprise debian-10 --for-docker
+          ./run.sh docker
+      - name: "Upload package"
+        uses: actions/upload-artifact@v2
+        with:
+          name: docker_enterprise
+          path: build/output/docker/memgraph*.tar.gz
+
+  ubuntu-1804_enterprise:
+    runs-on: [self-hosted, DockerMgBuild]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package enterprise ubuntu-18.04
+      - name: "Upload package"
+        uses: actions/upload-artifact@v2
+        with:
+          name: ubuntu-1804_enterprise
+          path: build/output/ubuntu-18.04/memgraph*.deb
+
+  ubuntu-2004_enterprise:
+    runs-on: [self-hosted, DockerMgBuild]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package enterprise ubuntu-20.04
+      - name: "Upload package"
+        uses: actions/upload-artifact@v2
+        with:
+          name: ubuntu-2004_enterprise
+          path: build/output/ubuntu-20.04/memgraph*.deb

.github/workflows/release_centos8.yaml

@@ -0,0 +1,330 @@
+name: Release CentOS 8
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: "0 1 * * *"
+
+jobs:
+  community_build:
+    name: "Community build"
+    runs-on: [self-hosted, Linux, X64, CentOS8]
+    env:
+      THREADS: 24
+    timeout-minutes: 960
+
+    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 community binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build community binaries.
+          cd build
+          cmake -DCMAKE_BUILD_TYPE=release -DMG_ENTERPRISE=OFF ..
+          make -j$THREADS
+
+      - name: Create community RPM package
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          cd build
+
+          # create mgconsole
+          # we use the -B to force the build
+          make -j$THREADS -B mgconsole
+
+          # Create community RPM package.
+          mkdir output && cd output
+          cpack -G RPM --config ../CPackConfig.cmake
+          rpmlint memgraph*.rpm
+
+      - name: Save community RPM package
+        uses: actions/upload-artifact@v2
+        with:
+          name: "Community RPM package"
+          path: build/output/memgraph*.rpm
+
+      - name: Run unit tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Run unit tests.
+          cd build
+          ctest -R memgraph__unit --output-on-failure
+
+      - name: Run stress test (plain)
+        run: |
+          cd tests/stress
+          ./continuous_integration
+
+      - name: Run stress test (large)
+        run: |
+          cd tests/stress
+          ./continuous_integration --large-dataset
+
+  coverage_build:
+    name: "Coverage build"
+    runs-on: [self-hosted, Linux, X64, CentOS8]
+    env:
+      THREADS: 24
+
+    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 coverage binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build coverage binaries.
+          cd build
+          cmake -DTEST_COVERAGE=ON ..
+          make -j$THREADS memgraph__unit
+
+      - name: Run unit tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Run unit tests.
+          cd build
+          ctest -R memgraph__unit --output-on-failure
+
+      - name: Compute code coverage
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Compute code coverage.
+          cd tools/github
+          ./coverage_convert
+
+          # Package code coverage.
+          cd generated
+          tar -czf code_coverage.tar.gz coverage.json html report.json summary.rmu
+
+      - name: Save code coverage
+        uses: actions/upload-artifact@v2
+        with:
+          name: "Code coverage"
+          path: tools/github/generated/code_coverage.tar.gz
+
+  debug_build:
+    name: "Debug build"
+    runs-on: [self-hosted, Linux, X64, CentOS8]
+    env:
+      THREADS: 24
+
+    steps:
+      - name: Set up repository
+        uses: actions/checkout@v2
+        with:
+          # Number of commits to fetch. `0` indicates all history for all
+          # branches and tags. (default: 1)
+          fetch-depth: 0
+
+      - name: Build debug binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build debug binaries.
+          cd build
+          cmake ..
+          make -j$THREADS
+
+      - name: Run leftover CTest tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Run leftover CTest tests (all except unit and benchmark tests).
+          cd build
+          ctest -E "(memgraph__unit|memgraph__benchmark)" --output-on-failure
+
+      - 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: $name"
+            if [ -x prepare.sh ]; then
+              ./prepare.sh
+            fi
+            if [ -x runner.py ]; then
+              ./runner.py
+            elif [ -x runner.sh ]; then
+              ./runner.sh
+            fi
+            echo
+            popd >/dev/null
+          done
+
+      - name: Run cppcheck and clang-format
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Run cppcheck and clang-format.
+          cd tools/github
+          ./cppcheck_and_clang_format diff
+
+      - name: Save cppcheck and clang-format errors
+        uses: actions/upload-artifact@v2
+        with:
+          name: "Code coverage"
+          path: tools/github/cppcheck_and_clang_format.txt
+
+  release_build:
+    name: "Release build"
+    runs-on: [self-hosted, Linux, X64, CentOS8]
+    env:
+      THREADS: 24
+    timeout-minutes: 960
+
+    steps:
+      - name: Set up repository
+        uses: actions/checkout@v2
+        with:
+          # Number of commits to fetch. `0` indicates all history for all
+          # branches and tags. (default: 1)
+          fetch-depth: 0
+
+      - name: Build release binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build release binaries.
+          cd build
+          cmake -DCMAKE_BUILD_TYPE=release ..
+          make -j$THREADS
+
+      - name: Create enterprise RPM package
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          cd build
+
+          # create mgconsole
+          # we use the -B to force the build
+          make -j$THREADS -B mgconsole
+
+          # Create enterprise RPM package.
+          mkdir output && cd output
+          cpack -G RPM --config ../CPackConfig.cmake
+          rpmlint memgraph*.rpm
+
+      - name: Save enterprise RPM package
+        uses: actions/upload-artifact@v2
+        with:
+          name: "Enterprise RPM package"
+          path: build/output/memgraph*.rpm
+
+      - name: Run micro benchmark tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Run micro benchmark tests.
+          cd build
+          # The `eval` benchmark needs a large stack limit.
+          ulimit -s 262144
+          ctest -R memgraph__benchmark -V
+
+      - name: Run macro benchmark tests
+        run: |
+          cd tests/macro_benchmark
+          ./harness QuerySuite MemgraphRunner \
+            --groups aggregation 1000_create unwind_create dense_expand match \
+            --no-strict
+
+      - name: Run parallel macro benchmark tests
+        run: |
+          cd tests/macro_benchmark
+          ./harness QueryParallelSuite MemgraphRunner \
+            --groups aggregation_parallel create_parallel bfs_parallel \
+            --num-database-workers 9 --num-clients-workers 30 \
+            --no-strict
+
+      - name: Run GQL Behave tests
+        run: |
+          cd tests/gql_behave
+          ./continuous_integration
+
+      - name: Save quality assurance status
+        uses: actions/upload-artifact@v2
+        with:
+          name: "GQL Behave Status"
+          path: |
+            tests/gql_behave/gql_behave_status.csv
+            tests/gql_behave/gql_behave_status.html
+
+      - name: Run e2e tests
+        run: |
+          # TODO(gitbuda): Setup mgclient and pymgclient properly.
+          cd tests
+          ./setup.sh
+          source ve3/bin/activate
+          cd e2e
+          LD_LIBRARY_PATH=$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 stress test (large)
+        run: |
+          cd tests/stress
+          ./continuous_integration --large-dataset
+
+      - name: Run durability test (plain)
+        run: |
+          cd tests/stress
+          source ve3/bin/activate
+          python3 durability --num-steps 5
+
+      - name: Run durability test (large)
+        run: |
+          cd tests/stress
+          source ve3/bin/activate
+          python3 durability --num-steps 20

.github/workflows/release_debian10.yaml

@@ -0,0 +1,368 @@
+name: Release Debian 10
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: "0 1 * * *"
+
+jobs:
+  community_build:
+    name: "Community build"
+    runs-on: [self-hosted, Linux, X64, Debian10]
+    env:
+      THREADS: 24
+    timeout-minutes: 960
+
+    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 community binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build community binaries.
+          cd build
+          cmake -DCMAKE_BUILD_TYPE=release -DMG_ENTERPRISE=OFF ..
+          make -j$THREADS
+
+      - name: Create community DEB package
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          cd build
+
+          # create mgconsole
+          # we use the -B to force the build
+          make -j$THREADS -B mgconsole
+
+          # Create community DEB package.
+          mkdir output && cd output
+          cpack -G DEB --config ../CPackConfig.cmake
+
+      - name: Save community DEB package
+        uses: actions/upload-artifact@v2
+        with:
+          name: "Community DEB package"
+          path: build/output/memgraph*.deb
+
+      - name: Run unit tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Run unit tests.
+          cd build
+          ctest -R memgraph__unit --output-on-failure
+
+      - name: Run stress test (plain)
+        run: |
+          cd tests/stress
+          ./continuous_integration
+
+      - name: Run stress test (large)
+        run: |
+          cd tests/stress
+          ./continuous_integration --large-dataset
+
+  coverage_build:
+    name: "Coverage build"
+    runs-on: [self-hosted, Linux, X64, Debian10]
+    env:
+      THREADS: 24
+
+    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 coverage binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build coverage binaries.
+          cd build
+          cmake -DTEST_COVERAGE=ON ..
+          make -j$THREADS memgraph__unit
+
+      - name: Run unit tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Run unit tests.
+          cd build
+          ctest -R memgraph__unit --output-on-failure
+
+      - name: Compute code coverage
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Compute code coverage.
+          cd tools/github
+          ./coverage_convert
+
+          # Package code coverage.
+          cd generated
+          tar -czf code_coverage.tar.gz coverage.json html report.json summary.rmu
+
+      - name: Save code coverage
+        uses: actions/upload-artifact@v2
+        with:
+          name: "Code coverage"
+          path: tools/github/generated/code_coverage.tar.gz
+
+  debug_build:
+    name: "Debug build"
+    runs-on: [self-hosted, Linux, X64, Debian10]
+    env:
+      THREADS: 24
+
+    steps:
+      - name: Set up repository
+        uses: actions/checkout@v2
+        with:
+          # Number of commits to fetch. `0` indicates all history for all
+          # branches and tags. (default: 1)
+          fetch-depth: 0
+
+      - name: Build debug binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build debug binaries.
+          cd build
+          cmake ..
+          make -j$THREADS
+
+      - name: Run leftover CTest tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Run leftover CTest tests (all except unit and benchmark tests).
+          cd build
+          ctest -E "(memgraph__unit|memgraph__benchmark)" --output-on-failure
+
+      - 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: $name"
+            if [ -x prepare.sh ]; then
+              ./prepare.sh
+            fi
+            if [ -x runner.py ]; then
+              ./runner.py
+            elif [ -x runner.sh ]; then
+              ./runner.sh
+            fi
+            echo
+            popd >/dev/null
+          done
+
+      - name: Run cppcheck and clang-format
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Run cppcheck and clang-format.
+          cd tools/github
+          ./cppcheck_and_clang_format diff
+
+      - name: Save cppcheck and clang-format errors
+        uses: actions/upload-artifact@v2
+        with:
+          name: "Code coverage"
+          path: tools/github/cppcheck_and_clang_format.txt
+
+  release_build:
+    name: "Release build"
+    runs-on: [self-hosted, Linux, X64, Debian10]
+    env:
+      THREADS: 24
+    timeout-minutes: 960
+
+    steps:
+      - name: Set up repository
+        uses: actions/checkout@v2
+        with:
+          # Number of commits to fetch. `0` indicates all history for all
+          # branches and tags. (default: 1)
+          fetch-depth: 0
+
+      - name: Build release binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build release binaries.
+          cd build
+          cmake -DCMAKE_BUILD_TYPE=release ..
+          make -j$THREADS
+
+      - name: Create enterprise DEB package
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          cd build
+
+          # create mgconsole
+          # we use the -B to force the build
+          make -j$THREADS -B mgconsole
+
+          # Create enterprise DEB package.
+          mkdir output && cd output
+          cpack -G DEB --config ../CPackConfig.cmake
+
+      - name: Save enterprise DEB package
+        uses: actions/upload-artifact@v2
+        with:
+          name: "Enterprise DEB package"
+          path: build/output/memgraph*.deb
+
+      - name: Run micro benchmark tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Run micro benchmark tests.
+          cd build
+          # The `eval` benchmark needs a large stack limit.
+          ulimit -s 262144
+          ctest -R memgraph__benchmark -V
+
+      - name: Run macro benchmark tests
+        run: |
+          cd tests/macro_benchmark
+          ./harness QuerySuite MemgraphRunner \
+            --groups aggregation 1000_create unwind_create dense_expand match \
+            --no-strict
+
+      - name: Run parallel macro benchmark tests
+        run: |
+          cd tests/macro_benchmark
+          ./harness QueryParallelSuite MemgraphRunner \
+            --groups aggregation_parallel create_parallel bfs_parallel \
+            --num-database-workers 9 --num-clients-workers 30 \
+            --no-strict
+
+      - name: Run GQL Behave tests
+        run: |
+          cd tests/gql_behave
+          ./continuous_integration
+
+      - name: Save quality assurance status
+        uses: actions/upload-artifact@v2
+        with:
+          name: "GQL Behave Status"
+          path: |
+            tests/gql_behave/gql_behave_status.csv
+            tests/gql_behave/gql_behave_status.html
+
+      - name: Run e2e tests
+        run: |
+          # TODO(gitbuda): Setup mgclient and pymgclient properly.
+          cd tests
+          ./setup.sh
+          source ve3/bin/activate
+          cd e2e
+          LD_LIBRARY_PATH=$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 stress test (large)
+        run: |
+          cd tests/stress
+          ./continuous_integration --large-dataset
+
+      - name: Run durability test (plain)
+        run: |
+          cd tests/stress
+          source ve3/bin/activate
+          python3 durability --num-steps 5
+
+      - name: Run durability test (large)
+        run: |
+          cd tests/stress
+          source ve3/bin/activate
+          python3 durability --num-steps 20
+
+  release_jepsen_test:
+    name: "Release Jepsen Test"
+    runs-on: [self-hosted, Linux, X64, Debian10, JepsenControl]
+    env:
+      THREADS: 24
+    timeout-minutes: 60
+
+    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-v3/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build only memgraph release binary.
+          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

.github/workflows/release_ubuntu2004.yaml

@@ -0,0 +1,328 @@
+name: Release Ubuntu 20.04
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: "0 1 * * *"
+
+jobs:
+  community_build:
+    name: "Community build"
+    runs-on: [self-hosted, Linux, X64, Ubuntu20.04]
+    env:
+      THREADS: 24
+    timeout-minutes: 960
+
+    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 community binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build community binaries.
+          cd build
+          cmake -DCMAKE_BUILD_TYPE=release -DMG_ENTERPRISE=OFF ..
+          make -j$THREADS
+
+      - name: Create community DEB package
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          cd build
+
+          # create mgconsole
+          # we use the -B to force the build
+          make -j$THREADS -B mgconsole
+
+          # Create community DEB package.
+          mkdir output && cd output
+          cpack -G DEB --config ../CPackConfig.cmake
+
+      - name: Save community DEB package
+        uses: actions/upload-artifact@v2
+        with:
+          name: "Community DEB package"
+          path: build/output/memgraph*.deb
+
+      - name: Run unit tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Run unit tests.
+          cd build
+          ctest -R memgraph__unit --output-on-failure
+
+      - name: Run stress test (plain)
+        run: |
+          cd tests/stress
+          ./continuous_integration
+
+      - name: Run stress test (large)
+        run: |
+          cd tests/stress
+          ./continuous_integration --large-dataset
+
+  coverage_build:
+    name: "Coverage build"
+    runs-on: [self-hosted, Linux, X64, Ubuntu20.04]
+    env:
+      THREADS: 24
+
+    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 coverage binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build coverage binaries.
+          cd build
+          cmake -DTEST_COVERAGE=ON ..
+          make -j$THREADS memgraph__unit
+
+      - name: Run unit tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Run unit tests.
+          cd build
+          ctest -R memgraph__unit --output-on-failure
+
+      - name: Compute code coverage
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Compute code coverage.
+          cd tools/github
+          ./coverage_convert
+
+          # Package code coverage.
+          cd generated
+          tar -czf code_coverage.tar.gz coverage.json html report.json summary.rmu
+
+      - name: Save code coverage
+        uses: actions/upload-artifact@v2
+        with:
+          name: "Code coverage"
+          path: tools/github/generated/code_coverage.tar.gz
+
+  debug_build:
+    name: "Debug build"
+    runs-on: [self-hosted, Linux, X64, Ubuntu20.04]
+    env:
+      THREADS: 24
+
+    steps:
+      - name: Set up repository
+        uses: actions/checkout@v2
+        with:
+          # Number of commits to fetch. `0` indicates all history for all
+          # branches and tags. (default: 1)
+          fetch-depth: 0
+
+      - name: Build debug binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build debug binaries.
+          cd build
+          cmake ..
+          make -j$THREADS
+
+      - name: Run leftover CTest tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Run leftover CTest tests (all except unit and benchmark tests).
+          cd build
+          ctest -E "(memgraph__unit|memgraph__benchmark)" --output-on-failure
+
+      - 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: $name"
+            if [ -x prepare.sh ]; then
+              ./prepare.sh
+            fi
+            if [ -x runner.py ]; then
+              ./runner.py
+            elif [ -x runner.sh ]; then
+              ./runner.sh
+            fi
+            echo
+            popd >/dev/null
+          done
+
+      - name: Run cppcheck and clang-format
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Run cppcheck and clang-format.
+          cd tools/github
+          ./cppcheck_and_clang_format diff
+
+      - name: Save cppcheck and clang-format errors
+        uses: actions/upload-artifact@v2
+        with:
+          name: "Code coverage"
+          path: tools/github/cppcheck_and_clang_format.txt
+
+  release_build:
+    name: "Release build"
+    runs-on: [self-hosted, Linux, X64, Ubuntu20.04]
+    env:
+      THREADS: 24
+    timeout-minutes: 960
+
+    steps:
+      - name: Set up repository
+        uses: actions/checkout@v2
+        with:
+          # Number of commits to fetch. `0` indicates all history for all
+          # branches and tags. (default: 1)
+          fetch-depth: 0
+
+      - name: Build release binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build release binaries.
+          cd build
+          cmake -DCMAKE_BUILD_TYPE=release ..
+          make -j$THREADS
+
+      - name: Create enterprise DEB package
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          cd build
+
+          # create mgconsole
+          # we use the -B to force the build
+          make -j$THREADS -B mgconsole
+
+          # Create enterprise DEB package.
+          mkdir output && cd output
+          cpack -G DEB --config ../CPackConfig.cmake
+
+      - name: Save enterprise DEB package
+        uses: actions/upload-artifact@v2
+        with:
+          name: "Enterprise DEB package"
+          path: build/output/memgraph*.deb
+
+      - name: Run micro benchmark tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v3/activate
+
+          # Run micro benchmark tests.
+          cd build
+          # The `eval` benchmark needs a large stack limit.
+          ulimit -s 262144
+          ctest -R memgraph__benchmark -V
+
+      - name: Run macro benchmark tests
+        run: |
+          cd tests/macro_benchmark
+          ./harness QuerySuite MemgraphRunner \
+            --groups aggregation 1000_create unwind_create dense_expand match \
+            --no-strict
+
+      - name: Run parallel macro benchmark tests
+        run: |
+          cd tests/macro_benchmark
+          ./harness QueryParallelSuite MemgraphRunner \
+            --groups aggregation_parallel create_parallel bfs_parallel \
+            --num-database-workers 9 --num-clients-workers 30 \
+            --no-strict
+
+      - name: Run GQL Behave tests
+        run: |
+          cd tests/gql_behave
+          ./continuous_integration
+
+      - name: Save quality assurance status
+        uses: actions/upload-artifact@v2
+        with:
+          name: "GQL Behave Status"
+          path: |
+            tests/gql_behave/gql_behave_status.csv
+            tests/gql_behave/gql_behave_status.html
+
+      - name: Run e2e tests
+        run: |
+          # TODO(gitbuda): Setup mgclient and pymgclient properly.
+          cd tests
+          ./setup.sh
+          source ve3/bin/activate
+          cd e2e
+          LD_LIBRARY_PATH=$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 stress test (large)
+        run: |
+          cd tests/stress
+          ./continuous_integration --large-dataset
+
+      - name: Run durability test (plain)
+        run: |
+          cd tests/stress
+          source ve3/bin/activate
+          python3 durability --num-steps 5
+
+      - name: Run durability test (large)
+        run: |
+          cd tests/stress
+          source ve3/bin/activate
+          python3 durability --num-steps 20

.ycm_extra_conf.py

@@ -1,172 +0,0 @@
-import os
-import os.path
-import fnmatch
-import logging
-import ycm_core
-
-BASE_FLAGS = [
-    '-Wall',
-    '-Wextra',
-    '-Werror',
-    '-Wno-long-long',
-    '-Wno-variadic-macros',
-    '-fexceptions',
-    '-ferror-limit=10000',
-    '-std=c++1z',
-    '-xc++',
-    '-I/usr/lib/',
-    '-I/usr/include/',
-    '-I./src',
-    '-I./include',
-    '-I./libs/fmt',
-    '-I./libs/yaml-cpp',
-    '-I./libs/glog/include',
-    '-I./libs/googletest/googletest/include',
-    '-I./libs/googletest/googlemock/include',
-    '-I./libs/benchmark/include',
-    '-I./libs/cereal/include',
-    # We include cppitertools headers directly from libs directory.
-    '-I./libs',
-    '-I./libs/rapidcheck/include',
-    '-I./libs/antlr4/runtime/Cpp/runtime/src',
-    '-I./libs/gflags/include',
-    '-I./experimental/distributed/src',
-    '-I./libs/postgresql/include',
-    '-I./libs/bzip2',
-    '-I./libs/zlib',
-    '-I./libs/rocksdb/include',
-    '-I./libs/librdkafka/include/librdkafka',
-    '-I./build/include'
-]
-
-SOURCE_EXTENSIONS = [
-    '.cpp',
-    '.cxx',
-    '.cc',
-    '.c',
-    '.m',
-    '.mm'
-]
-
-HEADER_EXTENSIONS = [
-    '.h',
-    '.hxx',
-    '.hpp',
-    '.hh'
-]
-
-# set the working directory of YCMD to be this file
-os.chdir(os.path.dirname(os.path.realpath(__file__)))
-
-def IsHeaderFile(filename):
-    extension = os.path.splitext(filename)[1]
-    return extension in HEADER_EXTENSIONS
-
-def GetCompilationInfoForFile(database, filename):
-    if IsHeaderFile(filename):
-        basename = os.path.splitext(filename)[0]
-        for extension in SOURCE_EXTENSIONS:
-            replacement_file = basename + extension
-            if os.path.exists(replacement_file):
-                compilation_info = database.GetCompilationInfoForFile(replacement_file)
-                if compilation_info.compiler_flags_:
-                    return compilation_info
-        return None
-    return database.GetCompilationInfoForFile(filename)
-
-def FindNearest(path, target):
-    candidate = os.path.join(path, target)
-    if(os.path.isfile(candidate) or os.path.isdir(candidate)):
-        logging.info("Found nearest " + target + " at " + candidate)
-        return candidate;
-    else:
-        parent = os.path.dirname(os.path.abspath(path));
-        if(parent == path):
-            raise RuntimeError("Could not find " + target);
-        return FindNearest(parent, target)
-
-def MakeRelativePathsInFlagsAbsolute(flags, working_directory):
-    if not working_directory:
-        return list(flags)
-    new_flags = []
-    make_next_absolute = False
-    path_flags = [ '-isystem', '-I', '-iquote', '--sysroot=' ]
-    for flag in flags:
-        new_flag = flag
-
-        if make_next_absolute:
-            make_next_absolute = False
-            if not flag.startswith('/'):
-                new_flag = os.path.join(working_directory, flag)
-
-        for path_flag in path_flags:
-            if flag == path_flag:
-                make_next_absolute = True
-                break
-
-            if flag.startswith(path_flag):
-                path = flag[ len(path_flag): ]
-                new_flag = path_flag + os.path.join(working_directory, path)
-                break
-
-        if new_flag:
-            new_flags.append(new_flag)
-    return new_flags
-
-
-def FlagsForClangComplete(root):
-    try:
-        clang_complete_path = FindNearest(root, '.clang_complete')
-        clang_complete_flags = open(clang_complete_path, 'r').read().splitlines()
-        return clang_complete_flags
-    except:
-        return None
-
-def FlagsForInclude(root):
-    try:
-        include_path = FindNearest(root, 'include')
-        flags = []
-        for dirroot, dirnames, filenames in os.walk(include_path):
-            for dir_path in dirnames:
-                real_path = os.path.join(dirroot, dir_path)
-                flags = flags + ["-I" + real_path]
-        return flags
-    except:
-        return None
-
-def FlagsForCompilationDatabase(root, filename):
-    try:
-        compilation_db_path = FindNearest(root, 'compile_commands.json')
-        compilation_db_dir = os.path.dirname(compilation_db_path)
-        logging.info("Set compilation database directory to " + compilation_db_dir)
-        compilation_db =  ycm_core.CompilationDatabase(compilation_db_dir)
-        if not compilation_db:
-            logging.info("Compilation database file found but unable to load")
-            return None
-        compilation_info = GetCompilationInfoForFile(compilation_db, filename)
-        if not compilation_info:
-            logging.info("No compilation info for " + filename + " in compilation database")
-            return None
-        return MakeRelativePathsInFlagsAbsolute(
-            compilation_info.compiler_flags_,
-            compilation_info.compiler_working_dir_)
-    except:
-        return None
-
-def FlagsForFile(filename):
-    root = os.path.realpath(filename);
-    compilation_db_flags = FlagsForCompilationDatabase(root, filename)
-    if compilation_db_flags:
-        final_flags = compilation_db_flags
-    else:
-        final_flags = BASE_FLAGS
-        clang_flags = FlagsForClangComplete(root)
-        if clang_flags:
-            final_flags = final_flags + clang_flags
-        include_flags = FlagsForInclude(root)
-        if include_flags:
-            final_flags = final_flags + include_flags
-    return {
-        'flags': final_flags,
-        'do_cache': True
-    }

CHANGELOG.md

@@ -1,385 +1,5 @@
-# Change Log
+Change Log for all versions of Memgraph can be found on-line at
+https://docs.memgraph.com/memgraph/changelog
 
-## v1.1.0
-
-### Major Features and Improvements
-
-* Properties in nodes and edges are now stored encoded and compressed. This
-  change significantly reduces memory usage. Depending on the specific dataset,
-  total memory usage can be reduced up to 50%.
-* Added support for rescanning query modules. Previously, the query modules
-  directory was scanned only upon startup. Now it is scanned each time the user
-  requests to load a query module. The functions used to load the query modules
-  were renamed to `mg.load()` and `mg.load_all()` (from `mg.reload()` and
-  `mg.reload_all()`).
-* Improved execution performance of queries that have an IN list filter by
-  using label+property indices.
-  Example: `MATCH (n:Label) WHERE n.property IN [] ...`
-* Added support for `ANY` and `NONE` openCypher functions. Previously, only
-  `ALL` and `SINGLE` functions were implemented.
-
-### Bug Fixes and Other Changes
-
-* Fixed invalid paths returned by variable expansion when the starting node and
-  destination node used the same symbol.
-  Example: `MATCH path = (n:Person {name: "John"})-[:KNOWS*]->(n) RETURN path`
-* Improved semantics of `ALL` and `SINGLE` functions to be consistent with
-  openCypher when handling lists with `Null`s.
-* `SHOW CONSTRAINT INFO` now returns property names as a list for unique
-  constraints.
-* Escaped label/property/edgetype names in `DUMP DATABASE` to support names
-  with spaces in them.
-* Fixed handling of `DUMP DATABASE` queries in multi-command transactions
-  (`BEGIN`, ..., `COMMIT`).
-* Fixed handling of various query types in explicit transactions. For example,
-  constraints were allowed to be created in multi-command transactions
-  (`BEGIN`, ..., `COMMIT`) but that isn't a transactional operation and as such
-  can't be allowed in multi-command transactions.
-* Fixed integer overflow bugs in `COUNT`, `LIMIT` and `SKIP`.
-* Fixed integer overflow bugs in weighted shortest path expansions.
-* Fixed various other integer overflow bugs in query execution.
-* Added Marvel Comic Universe tutorial.
-* Added FootballTransfers tutorial.
-
-## v1.0.0
-
-### Major Features and Improvements
-
-* [Enterprise Ed.] Exposed authentication username/rolename regex as a flag
-  (`--auth-user-or-role-name-regex`).
-* [Enterprise Ed.] Improved auth module error handling and added support for
-  relative paths.
-* Added support for Python query modules. This release of Memgraph supports
-  query modules written using the already existing C API and the new Python
-  API.
-* Added support for unique constraints. The unique constraint is created with a
-  label and one or more properties.
-* Implemented support for importing CSV files (`mg_import_csv`). The importer
-  is compatible with the Neo4j batch CSV importer.
-* Snapshot and write-ahead log format changed (backward compatible with v0.50).
-* Vertices looked up by their openCypher ID (`MATCH (n) WHERE ID(n) = ...`)
-  will now find the node in O(logn) instead of O(n).
-* Improved planning of BFS expansion, a faster, specific approach is now
-  favored instead of a ScanAll+Filter operation.
-* Added syntax for limiting memory of `CALL`.
-* Exposed server name that should be used for Bolt handshake as flag
-  (`--bolt-server-name-for-init`).
-* Added several more functions to the query module C API.
-* Implemented a storage locking mechanism that prevents the user from
-  concurrently starting two Memgraph instances with the same data directory.
-
-### Bug Fixes and Other Changes
-
-* [Enterprise Ed.] Fixed a bug that crashed the database when granting
-  privileges to a user.
-* [Enterprise Ed.] Improved Louvain algorithm for community detection.
-* Type of variable expansion is now printed in `EXPLAIN` (e.g. ExpandVariable,
-  STShortestPath, BFSExpand, WeightedShortestPath).
-* Correctly display `CALL` in `EXPLAIN` output.
-* Correctly delimit arguments when printing the signature of a query module.
-* Fixed a planning issue when `CALL` preceded filtering.
-* Fixed spelling mistakes in the storage durability module.
-* Fixed storage GC indices/constraints subtle race condition.
-* Reduced memory allocations in storage API and indices.
-* Memgraph version is now outputted to `stdout` when Memgraph is started.
-* Improved RPM packaging.
-* Reduced number of errors reported in production log when loading query
-  modules.
-* Removed `early access` wording from the Community Offering license.
-
-## v0.50.0
-
-### Breaking Changes
-
-* [Enterprise Ed.] Remove support for Kafka streams.
-* Snapshot and write-ahead log format changed (not backward compatible).
-* Removed support for unique constraints.
-* Label indices aren't created automatically, create them explicitly instead.
-* Renamed several database flags. Please see the configuration file for a list of current flags.
-
-### Major Features and Improvements
-
-* [Enterprise Ed.] Add support for auth module.
-* [Enterprise Ed.] LDAP support migrated to auth module.
-* Implemented new graph storage engine.
-* Add support for disabling properties on edges.
-* Add support for existence constraints.
-* Add support for custom openCypher procedures using a C API.
-* Support loading query modules implementing read-only procedures.
-* Add `CALL <procedure> YIELD <result>` syntax for invoking loaded procedures.
-* Add `CREATE INDEX ON :Label` for creating label indices.
-* Add `DROP INDEX ON :Label` for dropping label indices.
-* Add `DUMP DATABASE` clause to openCypher.
-* Add functions for treating character strings as byte strings.
-
-### Bug Fixes and Other Changes
-
-* Fix several memory management bugs.
-* Reduce memory usage in query execution.
-* Fix bug that crashes the database when `EXPLAIN` is used.
-
-## v0.15.0
-
-### Breaking Changes
-
-* Snapshot and write-ahead log format changed (not backward compatible).
-* `indexInfo()` function replaced with `SHOW INDEX INFO` syntax.
-* Removed support for unique index. Use unique constraints instead.
-* `CREATE UNIQUE INDEX ON :label (property)` replaced with `CREATE CONSTRAINT ON (n:label) ASSERT n.property IS UNIQUE`.
-* Changed semantics for `COUNTER` openCypher function.
-
-### Major Features and Improvements
-
-* [Enterprise Ed.] Add new privilege, `STATS` for accessing storage info.
-* [Enterprise Ed.] LDAP authentication and authorization support.
-* [Enterprise Ed.] Add audit logging feature.
-* Add multiple properties unique constraint which replace unique indices.
-* Add `SHOW STORAGE INFO` feature.
-* Add `PROFILE` clause to openCypher.
-* Add `CREATE CONSTRAINT` clause to openCypher.
-* Add `DROP CONSTRAINT` clause to openCypher.
-* Add `SHOW CONSTRAINT INFO` feature.
-* Add `uniformSample` function to openCypher.
-* Add regex matching to openCypher.
-
-### Bug Fixes and Other Changes
-
-* Fix bug in explicit transaction handling.
-* Fix bug in edge filtering by edge type and destination.
-* Fix bug in query comment parsing.
-* Fix bug in query symbol table.
-* Fix OpenSSL memory leaks.
-* Make authentication case insensitive.
-* Remove `COALESCE` function.
-* Add movie tutorial.
-* Add backpacking tutorial.
-
-## v0.14.0
-
-### Breaking Changes
-
-* Write-ahead log format changed (not backward compatible).
-
-### Major Features and Improvements
-
-* [Enterprise Ed.] Reduce memory usage in distributed usage.
-* Add `DROP INDEX` feature.
-* Improve SSL error messages.
-
-### Bug Fixes and Other Changes
-
-* [Enterprise Ed.] Fix issues with reading and writing in a distributed query.
-* Correctly handle an edge case with unique constraint checks.
-* Fix a minor issue with `mg_import_csv`.
-* Fix an issue with `EXPLAIN`.
-
-## v0.13.0
-
-### Breaking Changes
-
-* Write-ahead log format changed (not backward compatible).
-* Snapshot format changed (not backward compatible).
-
-### Major Features and Improvements
-
-* [Enterprise Ed.] Authentication and authorization support.
-* [Enterprise Ed.] Kafka integration.
-* [Enterprise Ed.] Support dynamic worker addition in distributed.
-* Reduce memory usage and improve overall performance.
-* Add `CREATE UNIQUE INDEX` clause to openCypher.
-* Add `EXPLAIN` clause to openCypher.
-* Add `inDegree` and `outDegree` functions to openCypher.
-* Improve BFS performance when both endpoints are known.
-* Add new `node-label`, `relationship-type` and `quote` options to
-  `mg_import_csv` tool.
-* Reduce memory usage of `mg_import_csv`.
-
-### Bug Fixes and Other Changes
-
-* [Enterprise Ed.] Fix an edge case in distributed index creation.
-* [Enterprise Ed.] Fix issues with Cartesian in distributed queries.
-* Correctly handle large messages in Bolt protocol.
-* Fix issues when handling explicitly started transactions in queries.
-* Allow openCypher keywords to be used as variable names.
-* Revise and make user visible error messages consistent.
-* Improve aborting time consuming execution.
-
-## v0.12.0
-
-### Breaking Changes
-
-* Snapshot format changed (not backward compatible).
-
-### Major Features and Improvements
-
-* Improved Id Cypher function.
-* Added string functions to openCypher (`lTrim`, `left`, `rTrim`, `replace`,
- `reverse`, `right`, `split`, `substring`, `toLower`, `toUpper`, `trim`).
-* Added `timestamp` function to openCypher.
-* Added support for dynamic property access with `[]` operator.
-
-## v0.11.0
-
-### Major Features and Improvements
-
-* [Enterprise Ed.] Improve Cartesian support in distributed queries.
-* [Enterprise Ed.] Improve distributed execution of BFS.
-* [Enterprise Ed.] Dynamic graph partitioner added.
-* Static nodes/edges id generators exposed through the Id Cypher function.
-* Properties on disk added.
-* Telemetry added.
-* SSL support added.
-* `toString` function added.
-
-### Bug Fixes and Other Changes
-
-* Document issues with Docker on OS X.
-* Add BFS and Dijkstra's algorithm examples to documentation.
-
-## v0.10.0
-
-### Breaking Changes
-
-* Snapshot format changed (not backward compatible).
-
-### Major Features and Improvements
-
-* [Enterprise Ed.] Distributed storage and execution.
-* `reduce` and `single` functions added to openCypher.
-* `wShortest` edge expansion added to openCypher.
-* Support packaging RPM on CentOS 7.
-
-### Bug Fixes and Other Changes
-
-* Report an error if updating a deleted element.
-* Log an error if reading info on available memory fails.
-* Fix a bug when `MATCH` would stop matching if a result was empty, but later
-  results still contain data to be matched. The simplest case of this was the
-  query: `UNWIND [1,2,3] AS x MATCH (n :Label {prop: x}) RETURN n`. If there
-  was no node `(:Label {prop: 1})`, then the `MATCH` wouldn't even try to find
-  for `x` being 2 or 3.
-* Report an error if trying to compare a property value with something that
-  cannot be stored in a property.
-* Fix crashes in some obscure cases.
-* Commit log automatically garbage collected.
-* Add minor performance improvements.
-
-## v0.9.0
-
-### Breaking Changes
-
-* Snapshot format changed (not backward compatible).
-* Snapshot configuration flags changed, general durability flags added.
-
-### Major Features and Improvements
-
-* Write-ahead log added.
-* `nodes` and `relationships` functions added.
-* `UNION` and `UNION ALL` is implemented.
-* Concurrent index creation is now enabled.
-
-### Bug Fixes and Other Changes
-
-
-## v0.8.0
-
-### Major Features and Improvements
-
-* CASE construct (without aggregations).
-* Named path support added.
-* Maps can now be stored as node/edge properties.
-* Map indexing supported.
-* `rand` function added.
-* `assert` function added.
-* `counter` and `counterSet` functions added.
-* `indexInfo` function added.
-* `collect` aggregation now supports Map collection.
-* Changed the BFS syntax.
-
-### Bug Fixes and Other Changes
-
-* Use \u to specify 4 digit codepoint and \U for 8 digit
-* Keywords appearing in header (named expressions) keep original case.
-* Our Bolt protocol implementation is now completely compatible with the protocol version 1 specification. (https://boltprotocol.org/v1/)
-* Added a log warning when running out of memory and the `memory_warning_threshold` flag
-* Edges are no longer additionally filtered after expansion.
-
-## v0.7.0
-
-### Major Features and Improvements
-
-* Variable length path `MATCH`.
-* Explicitly started transactions (multi-query transactions).
-* Map literal.
-* Query parameters (except for parameters in place of property maps).
-* `all` function in openCypher.
-* `degree` function in openCypher.
-* User specified transaction execution timeout.
-
-### Bug Fixes and Other Changes
-
-* Concurrent `BUILD INDEX` deadlock now returns an error to the client.
-* A `MATCH` preceeded by `OPTIONAL MATCH` expansion inconsistencies.
-* High concurrency Antlr parsing bug.
-* Indexing improvements.
-* Query stripping and caching speedups.
-
-## v0.6.0
-
-### Major Features and Improvements
-
-* AST caching.
-* Label + property index support.
-* Different logging setup & format.
-
-## v0.5.0
-
-### Major Features and Improvements
-
-* Use label indexes to speed up querying.
-* Generate multiple query plans and use the cost estimator to select the best.
-* Snapshots & Recovery.
-* Abandon old yaml configuration and migrate to gflags.
-* Query stripping & AST caching support.
-
-### Bug Fixes and Other Changes
-
-* Fixed race condition in MVCC. Hints exp+aborted race condition prevented.
-* Fixed conceptual bug in MVCC GC. Evaluate old records w.r.t. the oldest.
-  transaction's id AND snapshot.
-* User friendly error messages thrown from the query engine.
-
-## Build 837
-
-### Bug Fixes and Other Changes
-
-* List indexing supported with preceeding IN (for example in query `RETURN 1 IN [[1,2]][0]`).
-
-## Build 825
-
-### Major Features and Improvements
-
-* RETURN *, count(*), OPTIONAL MATCH, UNWIND, DISTINCT (except DISTINCT in aggregate functions), list indexing and slicing, escaped labels, IN LIST operator, range function.
-
-### Bug Fixes and Other Changes
-
-* TCP_NODELAY -> import should be faster.
-* Clear hint bits.
-
-## Build 783
-
-### Major Features and Improvements
-
-* SKIP, LIMIT, ORDER BY.
-* Math functions.
-* Initial support for MERGE clause.
-
-### Bug Fixes and Other Changes
-
-* Unhandled Lock Timeout Exception.
-
-## Build 755
-
-### Major Features and Improvements
-
-* MATCH, CREATE, WHERE, SET, REMOVE, DELETE.
+All the updates to the Change Log can be made in the following repository:
+https://github.com/memgraph/docs

CMakeLists.txt

@@ -35,6 +35,9 @@ else()
   message(FATAL_ERROR "Couldn't find clang and/or clang++!")
 endif()
 
+option(BUILD_FOR_DOCKER "Build Memgraph binary for docker." OFF)
+message(STATUS "BUILD_FOR_DOCKER: ${BUILD_FOR_DOCKER}")
+
 # -----------------------------------------------------------------------------
 
 project(memgraph)
@@ -67,28 +70,52 @@ set(get_version_script "${CMAKE_SOURCE_DIR}/release/get_version.py")
 # Get version that should be used in the binary.
 execute_process(
     OUTPUT_VARIABLE MEMGRAPH_VERSION
+    RESULT_VARIABLE MEMGRAPH_VERSION_RESULT
     COMMAND "${get_version_script}" ${get_version_enterprise}
                 "${MEMGRAPH_OVERRIDE_VERSION}"
                 "${MEMGRAPH_OVERRIDE_VERSION_SUFFIX}"
+                "--memgraph-root-dir"
+                "${CMAKE_SOURCE_DIR}"
 )
+if(MEMGRAPH_VERSION_RESULT AND NOT MEMGRAPH_VERSION_RESULT EQUAL 0)
+    message(FATAL_ERROR "Unable to get Memgraph version.")
+else()
+    MESSAGE(STATUS "Memgraph version: ${MEMGRAPH_VERSION}")
+endif()
 
 # Get version that should be used in the DEB package.
 execute_process(
     OUTPUT_VARIABLE MEMGRAPH_VERSION_DEB
+    RESULT_VARIABLE MEMGRAPH_VERSION_DEB_RESULT
     COMMAND "${get_version_script}" ${get_version_enterprise}
                 --variant deb
                 "${MEMGRAPH_OVERRIDE_VERSION}"
                 "${MEMGRAPH_OVERRIDE_VERSION_SUFFIX}"
+                "--memgraph-root-dir"
+                "${CMAKE_SOURCE_DIR}"
 )
+if(MEMGRAPH_VERSION_DEB_RESULT AND NOT MEMGRAPH_VERSION_DEB_RESULT EQUAL 0)
+    message(FATAL_ERROR "Unable to get Memgraph DEB version.")
+else()
+    MESSAGE(STATUS "Memgraph DEB version: ${MEMGRAPH_VERSION_DEB}")
+endif()
 
 # Get version that should be used in the RPM package.
 execute_process(
     OUTPUT_VARIABLE MEMGRAPH_VERSION_RPM
+    RESULT_VARIABLE MEMGRAPH_VERSION_RPM_RESULT
     COMMAND "${get_version_script}" ${get_version_enterprise}
                 --variant rpm
                 "${MEMGRAPH_OVERRIDE_VERSION}"
                 "${MEMGRAPH_OVERRIDE_VERSION_SUFFIX}"
+                "--memgraph-root-dir"
+                "${CMAKE_SOURCE_DIR}"
 )
+if(MEMGRAPH_VERSION_RPM_RESULT AND NOT MEMGRAPH_VERSION_RPM_RESULT EQUAL 0)
+    message(FATAL_ERROR "Unable to get Memgraph RPM version.")
+else()
+    MESSAGE(STATUS "Memgraph RPM version: ${MEMGRAPH_VERSION_RPM}")
+endif()
 
 # We want the above variables to be updated each time something is committed to
 # the repository. That is why we include a dependency on the current git HEAD
@@ -149,20 +176,23 @@ add_custom_target(clean_all
 # is easier debugging of compilation and linker flags.
 set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
 
-set(CMAKE_CXX_STANDARD 17)
+set(CMAKE_CXX_STANDARD 20)
 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=return-stack-address")
+    -Werror=return-stack-address \
+    -Wno-c99-designator")
 
 # Don't omit frame pointer in RelWithDebInfo, for additional callchain debug.
 set(CMAKE_CXX_FLAGS_RELWITHDEBINFO
     "${CMAKE_CXX_FLAGS_RELWITHDEBINFO} -fno-omit-frame-pointer")
 
 # Statically link libgcc and libstdc++, the GCC allows this according to:
-# https://gcc.gnu.org/onlinedocs/gcc-8.3.0/libstdc++/manual/manual/license.html
+# https://gcc.gnu.org/onlinedocs/gcc-10.2.0/libstdc++/manual/manual/license.html
 # https://www.gnu.org/licenses/gcc-exception-faq.html
-# Last checked for gcc-8.3 which we are using on the build machines.
+# Last checked for gcc-10.2 which we are using on the build machines.
 # ** If we change versions, recheck this! **
 # ** Static linking is allowed only for executables! **
 set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -static-libgcc -static-libstdc++")
@@ -282,10 +312,13 @@ if (UBSAN)
   # runtime library and c++ standard libraries are present.
   set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsanitize=undefined -fno-omit-frame-pointer -fno-sanitize=vptr")
   set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fsanitize=undefined -fno-sanitize=vptr")
-  # Run program with environment variable UBSAN_OPTIONS=print_stacktrace=1
-  # Make sure llvm-symbolizer binary is in path
+  # Run program with environment variable UBSAN_OPTIONS=print_stacktrace=1.
+  # Make sure llvm-symbolizer binary is in path.
+  # To make the program abort on undefined behavior, use UBSAN_OPTIONS=halt_on_error=1.
 endif()
 
+set(MG_PYTHON_VERSION "" CACHE STRING "Specify the exact python version used by the query modules")
+
 # Add subprojects
 include_directories(src)
 add_subdirectory(src)
@@ -303,3 +336,7 @@ endif()
 if(QUERY_MODULES)
   add_subdirectory(query_modules)
 endif()
+
+install(FILES ${CMAKE_BINARY_DIR}/bin/mgconsole
+  PERMISSIONS OWNER_EXECUTE OWNER_READ OWNER_WRITE GROUP_READ GROUP_EXECUTE WORLD_READ WORLD_EXECUTE
+  TYPE BIN)

CODEOWNERS

@@ -0,0 +1 @@
+* @gitbuda @antonio2368 @antaljanosbenjamin @kostasrim @jbajic

Doxyfile

@@ -51,7 +51,7 @@ PROJECT_BRIEF          = "The World's Most Powerful Graph Database"
 # pixels and the maximum width should not exceed 200 pixels. Doxygen will copy
 # the logo to the output directory.
 
-PROJECT_LOGO           = Doxylogo.png
+PROJECT_LOGO           = docs/doxygen/memgraph_logo.png
 
 # The OUTPUT_DIRECTORY tag is used to specify the (relative or absolute) path
 # into which the generated documentation will be written. If a relative path is

README.md

@@ -1,24 +1,21 @@
-# memgraph
+# Memgraph
 
 Memgraph is an ACID compliant high performance transactional distributed
 in-memory graph database featuring runtime native query compiling, lock free
 data structures, multi-version concurrency control and asynchronous IO.
 
-## dependencies
+## Development Documentation
 
-Memgraph can be compiled using any modern c++ compiler. It mostly relies on
-the standard template library, however, some things do require external
-libraries.
+Please continue in
+[Notion](https://www.notion.so/memgraph/memgraph-0428591638604c8385550e214ea9f3e6).
 
-Some code contains linux-specific libraries and the build is only supported
-on a 64 bit linux kernel.
+## User Documentation
 
-* linux
-* clang 3.8 (good c++11 support, especially lock free atomics)
-* antlr (compiler frontend)
-* cppitertools
-* fmt format
-* google benchmark
-* google test
-* glog
-* gflags
+Memgraph user documentation is maintained within
+[docs](https://github.com/memgraph/docs) repository. The documentation is also
+available on [GitBook](https://docs.memgraph.com).
+
+## Licences
+
+* [Community](release/LICENSE_COMMUNITY.md)
+* [Enterprise](release/LICENSE_ENTERPRISE.md)

apollo_archives.py

@@ -1,29 +0,0 @@
-#!/usr/bin/env python3
-import json
-import os
-
-SCRIPT_DIR = os.path.dirname(os.path.realpath(__file__))
-
-
-def find_packages(build_output_dir):
-    ret = []
-    output_dir = os.path.join(SCRIPT_DIR, build_output_dir)
-    if os.path.exists(output_dir):
-        for fname in os.listdir(output_dir):
-            if fname.startswith("memgraph") and fname.endswith(".deb"):
-                path = os.path.join(build_output_dir, fname)
-                ret.append({
-                    "name": "Release " + fname.split("_")[1] +
-                            " (deb package)",
-                    "archive": path,
-                })
-    return ret
-
-
-archives = []
-# Find enterprise package(s).
-archives += find_packages(os.path.join("build_release", "output"))
-# Find community package(s).
-archives += find_packages(os.path.join("build_community", "output"))
-
-print(json.dumps(archives, indent=4, sort_keys=True))

apollo_archives.yaml

@@ -1,17 +0,0 @@
-- name: Binaries
-  archive:
-    - build_debug/memgraph
-    - build_debug/config/memgraph.conf
-    - build_release/memgraph
-    - build_release/config/memgraph.conf
-    - build_release/tools/src/mg_client
-    - build_community/memgraph
-    - build_community/config/memgraph.conf
-  filename: binaries.tar.gz
-
-- name: Doxygen documentation
-  cd: docs/doxygen/html
-  archive:
-    - .
-  filename: documentation.tar.gz
-  host: true

apollo_build.yaml

@@ -1,110 +0,0 @@
-- name: Diff build
-  project: ^mg-master-diff$
-  commands: |
-    # Activate toolchain
-    export PATH=/opt/toolchain-v1/bin:$PATH
-    export LD_LIBRARY_PATH=/opt/toolchain-v1/lib:/opt/toolchain-v1/lib64
-
-    # Copy untouched repository to parent folder.
-    cd ..
-    cp -r memgraph parent
-    cd memgraph
-
-    # Initialize and create documentation.
-    TIMEOUT=1200 ./init
-    doxygen Doxyfile
-
-    # Remove default build directory.
-    rm -r build
-
-    # Build debug binaries.
-    mkdir build_debug
-    cd build_debug
-    cmake ..
-    TIMEOUT=1200 make -j$THREADS
-
-    # Build coverage binaries.
-    cd ..
-    mkdir build_coverage
-    cd build_coverage
-    cmake -DTEST_COVERAGE=ON ..
-    TIMEOUT=1200 make -j$THREADS memgraph__unit
-
-    # Build release binaries.
-    cd ..
-    mkdir build_release
-    cd build_release
-    cmake -DCMAKE_BUILD_TYPE=release ..
-    TIMEOUT=1200 make -j$THREADS
-
-    # Build community binaries.
-    cd ..
-    mkdir build_community
-    cd build_community
-    cmake -DCMAKE_BUILD_TYPE=release -DMG_ENTERPRISE=OFF ..
-    TIMEOUT=1200 make -j$THREADS
-    cd ..
-
-    # Checkout to parent commit and initialize.
-    cd ../parent
-    git checkout HEAD~1
-    TIMEOUT=1200 ./init
-
-    # Build parent release binaries.
-    mkdir build_release
-    cd build_release
-    cmake -DCMAKE_BUILD_TYPE=release ..
-    TIMEOUT=1200 make -j$THREADS memgraph memgraph__macro_benchmark
-
-
-# release build is the default one
-- name: Release build
-  commands: |
-    # Activate toolchain
-    export PATH=/opt/toolchain-v1/bin:$PATH
-    export LD_LIBRARY_PATH=/opt/toolchain-v1/lib:/opt/toolchain-v1/lib64
-
-    # Initialize and create documentation.
-    TIMEOUT=1200 ./init
-    doxygen Doxyfile
-
-    # Remove default build directory.
-    rm -r build
-
-    # Build debug binaries.
-    mkdir build_debug
-    cd build_debug
-    cmake ..
-    TIMEOUT=1200 make -j$THREADS
-
-    # Build coverage binaries.
-    cd ..
-    mkdir build_coverage
-    cd build_coverage
-    cmake -DTEST_COVERAGE=ON ..
-    TIMEOUT=1200 make -j$THREADS memgraph__unit
-
-    # Build release binaries.
-    cd ..
-    mkdir build_release
-    cd build_release
-    cmake -DCMAKE_BUILD_TYPE=Release -DUSE_READLINE=OFF ..
-    TIMEOUT=1200 make -j$THREADS
-
-    # Create Debian package.
-    mkdir output
-    cd output
-    cpack -G DEB --config ../CPackConfig.cmake
-    cd ..
-
-    # Build community binaries.
-    cd ..
-    mkdir build_community
-    cd build_community
-    cmake -DCMAKE_BUILD_TYPE=Release -DUSE_READLINE=OFF -DMG_ENTERPRISE=OFF ..
-    TIMEOUT=1200 make -j$THREADS
-
-    # Create Debian package.
-    mkdir output
-    cd output
-    cpack -G DEB --config ../CPackConfig.cmake

config/flags.yaml

@@ -39,12 +39,8 @@ modifications:
     value: "/var/log/memgraph/memgraph.log"
     override: true
 
-  - name: "bolt_cert_file"
-    value: "/etc/memgraph/ssl/cert.pem"
-    override: true
-
-  - name: "bolt_key_file"
-    value: "/etc/memgraph/ssl/key.pem"
+  - name: "log_level"
+    value: "WARNING"
     override: true
 
   - name: "bolt_num_workers"
@@ -87,15 +83,21 @@ modifications:
     value: "/usr/lib/memgraph/auth_module/example.py"
     override: false
 
+  - name: "memory_limit"
+    value: "0"
+    override: true
+
+  - name: "isolation_level"
+    value: "SNAPSHOT_ISOLATION"
+    override: true
+
+  - name: "allow_load_csv"
+    value: "true"
+    override: false
+
 undocumented:
   - "flag_file"
-  - "log_file_mode"
-  - "log_link_basename"
-  - "log_prefix"
-  - "max_log_size"
-  - "min_log_level"
+  - "also_log_to_stderr"
   - "help"
   - "help_xml"
-  - "stderr_threshold"
-  - "stop_logging_if_full_disk"
   - "version"

docs/dev/code-review.md

@@ -1,269 +0,0 @@
-# Code Review Guidelines
-
-This chapter describes some of the things you should be on the lookout when
-reviewing someone else's code.
-
-## Exceptions
-
-Although the Google C++ Style Guide forbids exceptions, we do allow them in
-our codebase. As a reviewer you should watch out for the following.
-
-The documentation of throwing functions needs to be in-sync with the
-implementation. This must be enforced recursively. I.e. if a function A now
-throws a new exception, and the function B uses A, then B needs to handle that
-exception or have its documentation updated and so on. Naturally, the same
-applies when an exception is removed.
-
-Transitive callers of the function which throws a new exception must be OK
-with that. This ties into the previous point. You need to check that all users
-of the new exception either handle it correctly or propagate it.
-
-Exceptions should not escape out of class destructors, because that will
-terminate the program. The code should be changed so that such cases are not
-possible.
-
-Exceptions being thrown in class constructors. Although this is well defined
-in C++, it usually implies that a constructor is doing too much work and the
-class construction & initialization should be redesigned. Usual approaches are
-using the (Static) Factory Method pattern or having some sort of an
-initialization method that needs to be called after the construction is done.
-Prefer the Factory Method.
-
-Don't forget that STL functions may also throw!
-
-## Pointers & References
-
-In cases when some code passes a pointer or reference, or if a code stores a
-pointer or reference you should take a careful look at the following.
-
-  * Lifetime of the pointed to value (this includes both ownership and
-    multithreaded access).
-  * In case of a class, check validity of destructor and move/copy
-    constructors.
-  * Is the pointed to value mutated, if not it should be `const` (`const Type
-    *` or `const Type &`).
-
-## Allocators & Memory Resources
-
-With the introduction of polymorphic allocators (C++17 `<memory_resource>` and
-our `utils/memory.hpp`) we get a more convenient type signatures for
-containers so as to keep the outward facing API nice. This convenience comes
-at a cost of less static checks on the type level due to type erasure.
-
-For example:
-
-    std::pmr::vector<int> first_vec(std::pmr::null_memory_resource());
-    std::pmr::vector<int> second_vec(std::pmr::new_delete_resource());
-
-    second_vec = first_vec  // What happens here?
-
-    // Or with our implementation
-    utils::MonotonicBufferResource monotonic_memory(1024);
-    std::vector<int, utils::Allocator<int>> first_vec(&monotonic_memory);
-    std::vector<int, utils::Allocator<int>> second_vec(utils::NewDeleteResource());
-
-    second_vec = first_vec  // What happens here?
-
-In the above, both `first_vec` and `second_vec` have the same type, but have
-*different* allocators! This can lead to ambiguity when moving or copying
-elements between them.
-
-You need to watch out for the following.
-
-  * Swapping can lead to undefined behaviour if the allocators are not equal.
-  * Is the move construction done with the right allocator.
-  * Is the move assignment done correctly, also it may throw an exception.
-  * Is the copy construction done with the right allocator.
-  * Is the copy assignment done correctly.
-  * Using `auto` makes allocator propagation rules rather ambiguous.
-
-## Classes & Object Oriented Programming
-
-A common mistake is to use classes, inheritance and "OOP" when it's not
-needed. This sections shows examples of encountered cases.
-
-### Classes without (Meaningful) Members
-
-    class MyCoolClass {
-     public:
-      int BeCool(int a, int b) { return a + b; }
-
-      void SaySomethingCool() { std::cout << "Hello!"; }
-    };
-
-The above class has no members (i.e. state) which affect the behaviour of
-methods. This class should need not exist, it can be easily replaced with a
-more modular (and shorter) design -- top level functions.
-
-    int BeCool(int a, int b) { return a + b; }
-
-    void SaySomethingCool() { std::cout << "Hello!"; }
-
-### Classes with a Single Public Method
-
-    clas MyAwesomeClass {
-     public:
-      MyAwesomeClass(int state) : state_(state) {}
-
-      int GetAwesome() { return GetAwesomeImpl() + 1; }
-
-     private:
-      int state_;
-
-      int GetAwesomeImpl() { return state_; }
-    };
-
-The above class has a `state_` and even a private method, but there's only one
-public method -- `GetAwesome`.
-
-You should check "Does the stored state have any meaningful influence on the
-public method?", similarly to the previous point.
-
-In the above case it doesn't, and the class should be replaced with a public
-function in `.hpp` while the private method should become a private function
-in `.cpp` (static or in anonymous namespace).
-
-    // hpp
-    int GetAwesome(int state);
-
-    // cpp
-    namespace {
-      int GetAwesomeImpl(int state) { return state; }
-    }
-    int GetAwesome(int state) { return GetAwesomeImpl(state) + 1; }
-
-A counterexample is when the state is meaningful.
-
-    class Counter {
-     public:
-      Counter(int state) : state_(state) {}
-
-      int Get() { return state_++; }
-
-     private:
-      int state_;
-    };
-
-But even that could be replaced with a closure.
-
-    auto MakeCounter(int state) {
-      return [state]() mutable { return state++; };
-    }
-
-### Private Methods
-
-Instead of private methods, top level functions should be preferred. The
-reasoning is completely explained in "Effective C++" Item 23 by Scott Meyers.
-In our codebase, even improvements to compilation times can be noticed if
-private methods in interface (`.hpp`) files are replaced with top level
-functions in implementation (`.cpp`) files.
-
-### Inheritance
-
-The rule is simple -- if there are no virtual methods (but maybe destructor),
-then the class should be marked as `final` and never inherited.
-
-If there are virtual methods (i.e. class is meant to be inherited), make sure
-that either a public virtual destructor or a protected non-virtual destructor
-exist. See "Effective C++" Item 7 by Scott Meyers. Also take a look at
-"Effective C++" Items 32---39 by Scott Meyers.
-
-An example of how inheritance with no virtual methods is replaced with
-composition.
-
-    class MyBase {
-     public:
-      virtual ~MyBase() {}
-
-      void DoSomethingBase() { ... }
-    };
-
-    class MyDerived final : public MyBase {
-     public:
-      void DoSomethingNew() { ... DoSomethingBase(); ... }
-    };
-
-With composition, the above becomes.
-
-    class MyBase final {
-     public:
-      void DoSomethingBase() { ... }
-    };
-
-    class MyDerived final {
-      MyBase base_;
-
-     public:
-      void DoSomethingNew() { ... base_.DoSomethingBase(); ... }
-    };
-
-The composition approach is preferred as it encapsulates the fact that
-`MyBase` is used for the implementation and users only interact with the
-public interface of `MyDerived`. Additionally, you can easily replace `MyBase
-base_;` with a C++ PIMPL idiom (`std::unique_ptr<MyBase> base_;`) to make the
-code more modular with regards to compilation.
-
-More advanced C++ users will recognize that the encapsulation feature of the
-non-PIMPL composition can be replaced with private inheritance.
-
-    class MyDerived final : private MyBase {
-     public:
-      void DoSomethingNew() { ... MyBase::DoSomethingBase(); ... }
-    };
-
-One of the common "counterexample" is the ability to store objects of
-different type in a container or pass them to a function. Unfortunately, this
-is not that good of a design. For example.
-
-    class MyBase {
-      ... // No virtual methods (but the destructor)
-    };
-
-    class MyFirstClass final : public MyBase { ...  };
-
-    class MySecondClass final : public MyBase { ... };
-
-    std::vector<std::unique_ptr<MyBase>> first_and_second_classes;
-    first_and_second_classes.push_back(std::make_unique<MyFirstClass>());
-    first_and_second_classes.push_back(std::make_unique<MySecondClass>());
-
-    void FunctionOnFirstOrSecond(const MyBase &first_or_second, ...) { ... }
-
-With C++17, the containers for different types should be implemented with
-`std::variant`, and as before the functions can be templated.
-
-    class MyFirstClass final { ... };
-
-    class MySecondClass final { ... };
-
-    std::vector<std::variant<MyFirstClass, MySecondClass>> first_and_second_classes;
-    // Notice no heap allocation, since we don't store a pointer
-    first_and_second_classes.emplace_back(MyFirstClass());
-    first_and_second_classes.emplace_back(MySecondClass());
-
-    // You can also use `std::variant` here instead of template
-    template <class TFirstOrSecond>
-    void FunctionOnFirstOrSecond(const TFirstOrSecond &first_or_second, ...) { ... }
-
-Naturally, if the base class has meaningful virtual methods (i.e. other than
-destructor) it maybe is OK to use inheritance but also consider alternatives.
-See "Effective C++" Items 32---39 by Scott Meyers.
-
-### Multiple Inheritance
-
-Multiple inheritance should not be used unless all base classes are pure
-interface classes. This decision is inherited from [Google C++ Style
-Guide](https://google.github.io/styleguide/cppguide.html#Inheritance). For
-example on how to design with and around multiple inheritance refer to
-"Effective C++" Item 40 by Scott Meyers.
-
-Naturally, if there *really* is no better design, then multiple inheritance is
-allowed. An example of this can be found in our codebase when inheriting
-Visitor classes (though even that could be replaced with `std::variant` for
-example).
-
-## Code Format & Style
-
-If something doesn't conform to our code formatting and style, just refer the
-author to either [C++ Style](cpp-code-conventions.md) or [Other Code
-Conventions](other-code-conventions.md).

docs/dev/cpp-code-conventions.md

@@ -1,263 +0,0 @@
-# C++ Code Conventions
-
-This chapter describes code conventions which should be followed when writing
-C++ code.
-
-## Code Style
-
-Memgraph uses the
-[Google Style Guide for C++](https://google.github.io/styleguide/cppguide.html)
-in most of its code.  You should follow them whenever writing new code.
-Besides following the style guide, take a look at
-[Code Review Guidelines](code-review.md) for common design issues and pitfalls
-with C++ as well as [Required Reading](required-reading.md).
-
-### Often Overlooked Style Conventions
-
-#### Pointers & References
-
-References provide a shorter syntax for accessing members and better declare
-the intent that a pointer *should* not be `nullptr`. They do not prevent
-accessing a `nullptr` and obfuscate the client/calling code because the
-reference argument is passed just like a value. Errors with such code have
-been very difficult to debug. Therefore, pointers are always used. They will
-not prevent bugs but will make some of them more obvious when reading code.
-
-The only time a reference can be used is if it is `const`. Note that this
-kind of reference is not allowed if it is stored somewhere, i.e. in a class.
-You should use a pointer to `const` then. The primary reason being is that
-references obscure the semantics of moving an object, thus making bugs with
-references pointing to invalid memory harder to track down.
-
-[Style guide reference](https://google.github.io/styleguide/cppguide.html#Reference_Arguments)
-
-#### Constructors & RAII
-
-RAII (Resource Acquisition is Initialization) is a nice mechanism for managing
-resources. It is especially useful when exceptions are used, such as in our
-code. Unfortunately, they do have 2 major downsides.
-
-  * Only exceptions can be used for to signal failure.
-  * Calls to virtual methods are not resolved as expected.
-
-For those reasons the style guide recommends minimal work that cannot fail.
-Using virtual methods or doing a lot more should be delegated to some form of
-`Init` method, possibly coupled with static factory methods. Similar rules
-apply to destructors, which are not allowed to even throw exceptions.
-
-[Style guide reference](https://google.github.io/styleguide/cppguide.html#Doing_Work_in_Constructors)
-
-### Additional Style Conventions
-
-Old code may have broken Google C++ Style accidentally, but the new code
-should adhere to it as close as possible. We do have some exceptions
-to Google style as well as additions for unspecified conventions.
-
-#### Using C++ Exceptions
-
-Unlike Google, we do not forbid using exceptions.
-
-But, you should be very careful when using them and introducing new ones. They
-are indeed handy, but cause problems with understanding the control flow since
-exceptions are another form of `goto`. It also becomes very hard to determine
-that the program is in correct state after the stack is unwound and the thrown
-exception handled. Other than those issues, throwing exceptions in destructors
-will terminate the program. The same will happen if a thread doesn't handle an
-exception even though it is not the main thread.
-
-[Style guide reference](https://google.github.io/styleguide/cppguide.html#Exceptions)
-
-In general, when introducing a new exception, either via `throw` statement or
-calling a function which throws, you must examine all transitive callers and
-update their implementation and/or documentation.
-
-#### Assertions
-
-We use `CHECK` and `DCHECK` macros from glog library. You are encouraged to
-use them as often as possible to both document and validate various pre and
-post conditions of a function.
-
-`CHECK` remains even in release build and should be preferred over it's cousin
-`DCHECK` which only exists in debug builds. The primary reason is that you
-want to trigger assertions in release builds in case the tests didn't
-completely validate all code paths. It is better to fail fast and crash the
-program, than to leave it in undefined state and potentially corrupt end
-user's work. In cases when profiling shows that `CHECK` is causing visible
-slowdown you should switch to `DCHECK`.
-
-#### Template Parameter Naming
-
-Template parameter names should start with capital letter 'T' followed by a
-short descriptive name. For example:
-
-```cpp
-template <typename TKey, typename TValue>
-class KeyValueStore
-```
-
-## Code Formatting
-
-You should install `clang-format` and run it on code you change or add. The
-root of Memgraph's project contains the `.clang-format` file, which specifies
-how formatting should behave. Running `clang-format -style=file` in the
-project's root will read the file and behave as expected. For ease of use, you
-should integrate formatting with your favourite editor.
-
-The code formatting isn't enforced, because sometimes manual formatting may
-produce better results. Though, running `clang-format` is strongly encouraged.
-
-## Documentation
-
-Besides following the comment guidelines from [Google Style
-Guide](https://google.github.io/styleguide/cppguide.html#Comments), your
-documentation of the public API should be
-[Doxygen](https://github.com/doxygen/doxygen) compatible. For private parts of
-the code or for comments accompanying the implementation, you are free to
-break doxygen compatibility. In both cases, you should write your
-documentation as full sentences, correctly written in English.
-
-## Doxygen
-
-To start a Doxygen compatible documentation string, you should open your
-comment with either a JavaDoc style block comment (`/**`) or a line comment
-containing 3 slashes (`///`). Take a look at the 2 examples below.
-
-### Block Comment
-
-```cpp
-/**
- * One sentence, brief description.
- *
- * Long form description.
- */
-```
-
-### Line Comment
-
-```cpp
-/// One sentence, brief description.
-///
-/// Long form description.
-```
-
-If you only have a brief description, you may collapse the documentation into
-a single line.
-
-### Block Comment
-
-```cpp
-/** Brief description. */
-```
-
-### Line Comment
-
-```cpp
-/// Brief description.
-```
-
-Whichever style you choose, keep it consistent across the whole file.
-
-Doxygen supports various commands in comments, such as `@file` and `@param`.
-These help Doxygen to render specified things differently or to track them for
-cross referencing. If you want to learn more, take a look at these two links:
-
-  * http://www.stack.nl/~dimitri/doxygen/manual/docblocks.html
-  * http://www.stack.nl/~dimitri/doxygen/manual/commands.html
-
-## Examples
-
-Below are a few examples of documentation from the codebase.
-
-### Function
-
-```cpp
-/**
- * Removes whitespace characters from the start and from the end of a string.
- *
- * @param s String that is going to be trimmed.
- *
- * @return Trimmed string.
- */
-inline std::string Trim(const std::string &s);
-```
-
-### Class
-
-```cpp
-/** Base class for logical operators.
- *
- *  Each operator describes an operation, which is to be performed on the
- *  database. Operators are iterated over using a @c Cursor. Various operators
- *  can serve as inputs to others and thus a sequence of operations is formed.
- */
-class LogicalOperator
-    : public ::utils::Visitable<HierarchicalLogicalOperatorVisitor> {
- public:
-  /** Constructs a @c Cursor which is used to run this operator.
-   *
-   *  @param GraphDbAccessor Used to perform operations on the database.
-   */
-  virtual std::unique_ptr<Cursor> MakeCursor(GraphDbAccessor &db) const = 0;
-
-  /** Return @c Symbol vector where the results will be stored.
-   *
-   *  Currently, outputs symbols are only generated in @c Produce operator.
-   *  @c Skip, @c Limit and @c OrderBy propagate the symbols from @c Produce (if
-   *  it exists as input operator). In the future, we may want this method to
-   *  return the symbols that will be set in this operator.
-   *
-   *  @param SymbolTable used to find symbols for expressions.
-   *  @return std::vector<Symbol> used for results.
-   */
-  virtual std::vector<Symbol> OutputSymbols(const SymbolTable &) const {
-    return std::vector<Symbol>();
-  }
-
-  virtual ~LogicalOperator() {}
-};
-```
-
-### File Header
-
-```cpp
-/// @file visitor.hpp
-///
-/// This file contains the generic implementation of visitor pattern.
-///
-/// There are 2 approaches to the pattern:
-///
-///   * classic visitor pattern using @c Accept and @c Visit methods, and
-///   * hierarchical visitor which also uses @c PreVisit and @c PostVisit
-///   methods.
-///
-/// Classic Visitor
-/// ===============
-///
-/// Explanation on the classic visitor pattern can be found from many
-/// sources, but here is the link to hopefully most easily accessible
-/// information: https://en.wikipedia.org/wiki/Visitor_pattern
-///
-/// The idea behind the generic implementation of classic visitor pattern is to
-/// allow returning any type via @c Accept and @c Visit methods. Traversing the
-/// class hierarchy is relegated to the visitor classes. Therefore, visitor
-/// should call @c Accept on children when visiting their parents. To implement
-/// such a visitor refer to @c Visitor and @c Visitable classes.
-///
-/// Hierarchical Visitor
-/// ====================
-///
-/// Unlike the classic visitor, the intent of this design is to allow the
-/// visited structure itself to control the traversal. This way the internal
-/// children structure of classes can remain private. On the other hand,
-/// visitors may want to differentiate visiting composite types from leaf types.
-/// Composite types are those which contain visitable children, unlike the leaf
-/// nodes. Differentiation is accomplished by providing @c PreVisit and @c
-/// PostVisit methods, which should be called inside @c Accept of composite
-/// types. Regular @c Visit is only called inside @c Accept of leaf types.
-/// To implement such a visitor refer to @c CompositeVisitor, @c LeafVisitor and
-/// @c Visitable classes.
-///
-/// Implementation of hierarchical visiting is modelled after:
-/// http://wiki.c2.com/?HierarchicalVisitorPattern
-```
-

docs/dev/durability/snapshots.md

@@ -1,22 +0,0 @@
-# Snapshots
-
-A "snapshot" is a record of the current database state stored in permanent
-storage. Note that the term "snapshot" is used also in the context of
-the transaction engine to denote a set of running transactions.
-
-A snapshot is written to the file by Memgraph periodically if so
-configured. The snapshot creation  process is done within a transaction created
-specifically for that purpose. The transaction is needed to ensure that
-the stored state is internally consistent.
-
-The database state can be recovered from the snapshot during startup, if
-so configured. This recovery works in conjunction with write-ahead log
-recovery.
-
-A single snapshot contains all the data needed to recover a database. In
-that sense snapshots are independent of each other and old snapshots can
-be deleted once the new ones are safely stored, if it is not necessary
-to revert the database to some older state.
-
-The exact format of the snapshot file is defined inline in the snapshot
-creation code.

docs/dev/durability/wal.md

@@ -1,55 +0,0 @@
-# Write-ahead logging
-
-Typically WAL denotes the process of writing a "log" of database
-operations (state changes) to persistent storage before committing the
-transaction, thus ensuring that the state can be recovered (in the case
-of a crash) for all the transactions which the database committed.
-
-The WAL is a fine-grained durability format. It's purpose is to store
-database changes fast. It's primary purpose is not to provide
-space-efficient storage, nor to support fast recovery. For that reason
-it's often used in combination with a different persistence mechanism
-(in Memgraph's case the "snapshot") that has complementary
-characteristics.
-
-### Guarantees
-
-Ensuring that the log is written before the transaction is committed can
-slow down the database. For that reason this guarantee is most often
-configurable in databases.
-
-Memgraph offers two options for the WAL. The default option, where the WAL is
-flushed to the disk periodically and transactions do not wait for this to
-complete, introduces the risk of database inconsistency because an operating
-system or hardware crash might lead to missing transactions in the WAL. Memgraph
-will handle this as if those transactions never happened. The second option,
-called synchronous commit, will instruct Memgraph to wait for the WAL to be
-flushed to the disk when a transactions completes and the transaction will wait
-for this to complete. This option can be turned on with the
-`--synchronous-commit` command line flag.
-
-### Format
-
-The WAL file contains a series of DB state changes called `StateDelta`s.
-Each of them describes what the state change is and in which transaction
-it happened. Also some kinds of meta-information needed to ensure proper
-state recovery are recorded (transaction beginnings and commits/abort).
-
-The following is guaranteed w.r.t. `StateDelta` ordering in
-a single WAL file:
-- For two ops in the same transaction, if op A happened before B in the
-  database, that ordering is preserved in the log.
-- Transaction begin/commit/abort messages also appear in exactly the
-  same order as they were executed in the transactional engine.
-
-### Recovery
-
-The database can recover from the WAL on startup. This works in
-conjunction with snapshot recovery. The database attempts to recover from
-the latest snapshot and then apply as much as possible from the WAL
-files. Only those transactions that were not recovered from the snapshot
-are recovered from the WAL, for speed efficiency. It is possible (but
-inefficient) to recover the database from WAL only, provided all the WAL
-files created from DB start are available. It is not possible to recover
-partial database state (i.e. from some suffix of WAL files, without the
-preceding snapshot).

docs/dev/other-code-conventions.md

@@ -1,15 +0,0 @@
-# Other Code Conventions
-
-While we are mainly programming in C++, we do use other programming languages
-when appropriate. This chapter describes conventions for such code.
-
-## Python
-
-Code written in Python should adhere to
-[PEP 8](https://www.python.org/dev/peps/pep-0008/). You should run `flake8` on
-your code to automatically check compliance.
-
-## Common Lisp
-
-Code written in Common Lisp should adhere to
-[Google Common Lisp Style](https://google.github.io/styleguide/lispguide.xml).

docs/dev/query/.gitignore

@@ -1 +0,0 @@
-html/

docs/dev/query/build-html

@@ -1,16 +0,0 @@
-#!/bin/bash
-
-script_dir="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
-
-mkdir -p $script_dir/html
-
-for markdown_file in $(find $script_dir -name '*.md'); do
-  name=$(basename -s .md $markdown_file)
-  sed -e 's/.md/.html/' $markdown_file | \
-    pandoc -s -f markdown -t html -o $script_dir/html/$name.html
-done
-
-for dot_file in $(find $script_dir -name '*.dot'); do
-  name=$(basename -s .dot $dot_file)
-  dot -Tpng $dot_file -o $script_dir/html/$name.png
-done

docs/dev/query/contents.md

@@ -1,34 +0,0 @@
-# Query Parsing, Planning and Execution
-
-This part of the documentation deals with query execution.
-
-Memgraph currently supports only query interpretation. Each new query is
-parsed, analysed and translated into a sequence of operations which are then
-executed on the main database storage. Query execution is organized into the
-following phases:
-
-  1.  [Lexical Analysis (Tokenization)](parsing.md)
-  2.  [Syntactic Analysis (Parsing)](parsing.md)
-  3.  [Semantic Analysis and Symbol Generation](semantic.md)
-  4.  [Logical Planning](planning.md)
-  5.  [Logical Plan Execution](execution.md)
-
-The main entry point is `Interpreter::operator()`, which takes a query text
-string and produces a `Results` object. To instantiate the object,
-`Interpreter` needs to perform the above steps from 1 to 4. If any of the
-steps fail, a `QueryException` is thrown. The complete `LogicalPlan` is
-wrapped into a `CachedPlan` and stored for reuse. This way we can skip the
-whole process of analysing a query if it appears to be the same as before.
-
-When we have valid plan, the client code can invoke `Results::PullAll` with a
-stream object. The `Results` instance will then execute the plan and fill the
-stream with the obtained results.
-
-Since we want to optionally run Memgraph as a distributed database, we have
-hooks for creating a different plan of logical operators.
-`DistributedInterpreter` inherits from `Interpreter` and overrides
-`MakeLogicalPlan` method. This method needs to return a concrete instance of
-`LogicalPlan`, and in case of distributed database that will be
-`DistributedLogicalPlan`.
-
-![Intepreter Class Diagram](interpreter-class.png)

docs/dev/query/execution.md

@@ -1,373 +0,0 @@
-# Logical Plan Execution
-
-We implement classical iterator style operators. Logical operators define
-operations on database. They encapsulate the following info: what the input is
-(another `LogicalOperator`), what to do with the data, and how to do it.
-
-Currently logical operators can have zero or more input operations, and thus a
-`LogicalOperator` tree is formed. Most `LogicalOperator` types have only one
-input, so we are mostly working with chains instead of full fledged trees.
-You can find information on each operator in `src/query/plan/operator.lcp`.
-
-## Cursor
-
-Logical operators do not perform database work themselves. Instead they create
-`Cursor` objects that do the actual work, based on the info in the operator.
-Cursors expose a `Pull` method that gets called by the cursor's consumer. The
-consumer keeps pulling as long as the `Pull` returns `true` (indicating it
-successfully performed some work and might be eligible for another `Pull`).
-Most cursors will call the `Pull` function of their input provided cursor, so
-typically a cursor chain is created that is analogue to the logical operator
-chain it's created from.
-
-## Frame
-
-The `Frame` object contains all the data of the current `Pull` chain. It
-serves for communicating data between cursors.
-
-For example, in a `MATCH (n) RETURN n` query the `ScanAllCursor` places a
-vertex on the `Frame` for each `Pull`. It places it on the place reserved for
-the `n` symbol. Then the `ProduceCursor` can take that same value from the
-`Frame` because it knows the appropriate symbol. `Frame` positions are indexed
-by `Symbol` objects.
-
-## ExpressionEvaluator
-
-Expressions results are not placed on the `Frame` since they do not need to be
-communicated between different `Cursors`. Instead, expressions are evaluated
-using an instance of `ExpressionEvaluator`. Since generally speaking an
-expression can be defined by a tree of subexpressions, the
-`ExpressionEvaluator` is implemented as a tree visitor. There is a performance
-sub-optimality here because a stack is used to communicate intermediary
-expression results between elements of the tree. This is one of the reasons
-why it's planned to use `Frame` for intermediary expression results as well.
-The other reason is that it might facilitate compilation later on.
-
-## Cypher Execution Semantics
-
-Cypher query execution has *mostly* well-defined semantics. Some are
-explicitly defined by openCypher and its TCK, while others are implicitly
-defined by Neo4j's implementation of Cypher that we want to be generally
-compatible with.
-
-These semantics can in short be described as follows: a Cypher query consists
-of multiple clauses some of which modify it. Generally, every clause in the
-query, when reading it left to right, operates on a consistent state of the
-property graph, untouched by subsequent clauses. This means that a `MATCH`
-clause in the beginning operates on a graph-state in which modifications by
-the subsequent `SET` are not visible.
-
-The stated semantics feel very natural to the end-user, and Neo seems to
-implement them well. For Memgraph the situation is complex because
-`LogicalOperator` execution (through a `Cursor`) happens one `Pull` at a time
-(generally meaning all the query clauses get executed for every top-level
-`Pull`). This is not inherently consistent with Cypher semantics because a
-`SET` clause can modify data, and the `MATCH` clause that precedes it might
-see the modification in a subsequent `Pull`. Also, the `RETURN` clause might
-want to stream results to the user before all `SET` clauses have been
-executed, so the user might see some intermediate graph state. There are many
-edge-cases that Memgraph does its best to avoid to stay true to Cypher
-semantics, while at the same time using a high-performance streaming approach.
-The edge-cases are enumerated in this document along with the implementation
-details they imply.
-
-## Implementation Peculiarities
-
-### Once
-
-An operator that does nothing but whose `Cursor::Pull` returns `true` on the
-first `Pull` and `false` on subsequent ones. This operator is used when
-another operator has an optional input, because in Cypher a clause will
-typically execute once for every input from the preceding clauses, or just
-once if there was no preceding input. For example, consider the `CREATE`
-clause. In the query `CREATE (n)` only one node is created, while in the query
-`MATCH (n) CREATE (m)` a node is created for each existing node. Thus in our
-`CreateNode` logical operator the input is either a `ScanAll` operator, or a
-`Once` operator.
-
-### storage::View
-
-In the previous section, [Cypher Execution
-Semantics](#cypher-execution-semantics), we mentioned how the preceding
-clauses should not see changes made in subsequent ones. For that reason, some
-operators take a `storage::View` enum value. This value determines which state of
-the graph an operator sees.
-
-Consider the query `MATCH (n)--(m) WHERE n.x = 0 SET m.x = 1`. Naive streaming
-could match a vertex `n` on the given criteria, expand to `m`, update it's
-property, and in the next iteration consider the vertex previously matched to
-`m` and skip it because it's newly set property value does not qualify. This
-is not how Cypher works. To handle this issue properly, Memgraph designed the
-`VertexAccessor` class that tracks two versions of data: one that was visible
-before the current transaction+command, and the optional other that was
-created in the current transaction+command. The `MATCH` clause will be planned
-as `ScanAll` and `Expand` operations using `storage::View::OLD` value. This
-will ensure modifications performed in the same query do not affect it. The
-same applies to edges and the `EdgeAccessor` class.
-
-### Existing Record Detection
-
-It's possible that a pattern element has already been declared in the same
-pattern, or a preceding pattern. For example `MATCH (n)--(m), (n)--(l)` or a
-cycle-detection match `MATCH (n)-->(n) RETURN n`. Implementation-wise,
-existing record detection just checks that the expanded record is equal to the
-one already on the frame.
-
-### Why Not Use Separate Expansion Ops for Edges and Vertices?
-
-Expanding an edge and a vertex in separate ops is not feasible when matching a
-cycle in bi-directional expansions. Consider the query `MATCH (n)--(n) RETURN
-n`. Let's try to expand first the edge in one op, and vertex in the next. The
-vertex expansion consumes the edge expansion input. It takes the expanded edge
-from the frame. It needs to detect a cycle by comparing the vertex existing on
-the frame with one of the edge vertices (`from` or `to`). But which one? It
-doesn't know, and can't ensure correct cycle detection.
-
-### Data Visibility During and After SET
-
-In Cypher, setting values always works on the latest version of data (from
-preceding or current clause). That means that within a `SET` clause all the
-changes from previous clauses must be visible, as well as changes done by the
-current `SET` clause. Also, if there is a clause after `SET` it must see *all*
-the changes performed by the preceding `SET`. Both these things are best
-illustrated with the following queries executed on an empty database:
-
-    CREATE (n:A {x:0})-[:EdgeType]->(m:B {x:0})
-    MATCH (n)--(m) SET m.x = n.x + 1 RETURN labels(n), n.x, labels(m), m.x
-
-This returns:
-
-+---------+---+---------+---+
-|labels(n)|n.x|labels(m)|m.x|
-+:=======:+:=:+:=======:+:=:+
-|[A]      |2  |[B]      |1  |
-+---------+---+---------+---+
-|[B]      |1  |[A]      |2  |
-+---------+---+---------+---+
-
-The obtained result implies the following operations:
-
-  1. In the first iteration set the value of the `B.x` to 1
-  2. In the second iteration the we observe `B.x` with the value of 1 and set
-     `A.x` to 2
-  3. In `RETURN` we see all the changes made in both iterations
-
-To implement the desired behavior Memgraph utilizes two techniques. First is
-the already mentioned tracking of two versions of data in vertex accessors.
-Using this approach ensures that the second iteration in the example query
-sees the data modification performed by the preceding iteration. The second
-technique is the `Accumulate` operation that accumulates all the iterations
-from the preceding logical op before passing them to the next logical op. In
-the example query, `Accumulate` ensures that the results returned to the user
-reflect changes performed in all iterations of the query (naive streaming
-could stream results at the end of first iteration producing inconsistent
-results). Note that `Accumulate` is demanding regarding memory and slows down
-query execution. For that reason it should be used only when necessary, for
-example it does not have to be used in a query that has `MATCH` and `SET` but
-no `RETURN`.
-
-### Neo4j Inconsistency on Multiple SET Clauses
-
-Considering the preceding example it could be expected that when a query has
-multiple `SET` clauses all the changes from those preceding one are visible.
-This is not the case in Neo4j's implementation. Consider the following queries
-executed on an empty database:
-
-    CREATE (n:A {x:0})-[:EdgeType]->(m:B {x:0})
-    MATCH (n)--(m) SET n.x = n.x + 1 SET m.x = m.x * 2
-    RETURN labels(n), n.x, labels(m), m.x
-
-This returns:
-
-+---------+---+---------+---+
-|labels(n)|n.x|labels(m)|m.x|
-+:=======:+:=:+:=======:+:=:+
-|[A]      |2  |[B]      |1  |
-+---------+---+---------+---+
-|[B]      |1  |[A]      |2  |
-+---------+---+---------+---+
-
-If all the iterations of the first `SET` clause were executed before executing
-the second, all the resulting values would be 2. This not being the case, we
-conclude that Neo4j does not use a barrier-like mechanism between `SET`
-clauses.  It is Memgraph's current vision that this is inconsistent and we
-plan to reduce Neo4j compliance in favour of operation consistency.
-
-### Double Deletion
-
-It's possible to match the same graph element multiple times in a single query
-and delete it. Neo supports this, and so do we. The relevant implementation
-detail is in the `GraphDbAccessor` class, where the record deletion functions
-reside, and not in the logical plan execution. It comes down to checking if a
-record has already been deleted in the current transaction+command and not
-attempting to do it again (results in a crash).
-
-### Set + Delete Edge-case
-
-It's legal for a query to combine `SET` and `DELETE` clauses. Consider the
-following queries executed on an empty database:
-
-
-    CREATE ()-[:T]->()
-    MATCH (n)--(m) SET n.x = 42 DETACH DELETE m
-
-Due to the `MATCH` being undirected the second pull will attempt to set data
-on a deleted vertex. This is not a legal operation in Memgraph storage
-implementation. For that reason the logical operator for `SET` must check if
-the record it's trying to set something on has been deleted by the current
-transaction+command. If so, the modification is not executed.
-
-### Deletion Accumulation
-
-Sometimes it's necessary to accumulate deletions of all the matches before
-attempting to execute them. Consider this the following. Start with an empty
-database and execute queries:
-
-    CREATE ()-[:T]->()-[:T]->()
-    MATCH (a)-[r1]-(b)-[r2]-(c) DELETE r1, b, c
-
-Note that the `DELETE` clause attempts to delete node `c`, but it does not
-detach it by deleting edge `r2`. However, due to undirected edge in the
-`MATCH`, both edges get pulled and deleted.
-
-Currently Memgraph does not support this behavior, Neo does. There are a few
-ways that we could do this.
-
- * Accumulate on deletion (that sucks because we have to keep track of
-   everything that gets returned after the deletion).
- * Maybe we could stream through the deletion op, but defer actual deletion
-   until plan-execution end.
- * Ignore this because it's very edgy (this is the currently selected option).
-
-### Aggregation Without Input
-
-It is necessary to define what aggregation ops return when they receive no
-input. Following is a table that shows what Neo4j's Cypher implementation and
-SQL produce.
-
-
-+-------------+------------------------+---------------------+---------------------+------------------+
-|    \<OP\>   | 1. Cypher, no group-by | 2. Cypher, group-by | 3. SQL, no group-by | 4. SQL, group-by |
-+=============+:======================:+:===================:+:===================:+:================:+
-| Count(\*)   | 0                      | \<NO\_ROWS>         | 0                   | \<NO\_ROWS>      |
-+-------------+------------------------+---------------------+---------------------+------------------+
-| Count(prop) | 0                      | \<NO\_ROWS>         | 0                   | \<NO\_ROWS>      |
-+-------------+------------------------+---------------------+---------------------+------------------+
-| Sum         | 0                      | \<NO\_ROWS>         | NULL                | \<NO\_ROWS>      |
-+-------------+------------------------+---------------------+---------------------+------------------+
-| Avg         | NULL                   | \<NO\_ROWS>         | NULL                | \<NO\_ROWS>      |
-+-------------+------------------------+---------------------+---------------------+------------------+
-| Min         | NULL                   | \<NO\_ROWS>         | NULL                | \<NO\_ROWS>      |
-+-------------+------------------------+---------------------+---------------------+------------------+
-| Max         | NULL                   | \<NO\_ROWS>         | NULL                | \<NO\_ROWS>      |
-+-------------+------------------------+---------------------+---------------------+------------------+
-| Collect     | []                     | \<NO\_ROWS>         | N/A                 | N/A              |
-+-------------+------------------------+---------------------+---------------------+------------------+
-
-Where:
-
-    1. `MATCH (n) RETURN <OP>(n.prop)`
-    2. `MATCH (n) RETURN <OP>(n.prop), (n.prop2)`
-    3. `SELECT <OP>(prop) FROM Table`
-    4. `SELECT <OP>(prop), prop2 FROM Table GROUP BY prop2`
-
-Neo's Cypher implementation diverges from SQL only when performing `SUM`.
-Memgraph implements SQL-like behavior. It is considered that `SUM` of
-arbitrary elements should not be implicitly 0, especially in a property graph
-without a strict schema (the property in question can contain values of
-arbitrary types, or no values at all).
-
-### OrderBy
-
-The `OrderBy` logical operator sorts the results in the desired order. It
-occurs in Cypher as part of a `WITH` or `RETURN` clause. Both the concept and
-the implementation are straightforward. It's necessary for the logical op to
-`Pull` everything from its input so it can be sorted. It's not necessary to
-keep the whole `Frame` state of each input, it is sufficient to keep a list of
-`TypedValues` on which the results will be sorted, and another list of values
-that need to be remembered and recreated on the `Frame` when yielding.
-
-The sorting itself is made to reflect that of Neo's implementation which comes
-down to these points.
-
-  * `Null` comes last (as if it's greater than anything).
-  * Primitive types compare naturally, with no implicit casting except from
-    `int` to `double`.
-  * Complex types are not comparable.
-  * Every unsupported comparison results in an exception that gets propagated
-    to the end user.
-
-### Limit in Write Queries
-
-`Limit` can be used as part of a write query, in which case it will *not*
-reduce the amount of performed updates. For example, consider a database that
-has 10 vertices. The query `MATCH (n) SET n.x = 1 RETURN n LIMIT 3` will
-result in all vertices having their property value changed, while returning
-only the first to the client. This makes sense from the implementation
-standpoint, because `Accumulate` is planned after `SetProperty` but before
-`Produce` and `Limit` operations. Note that this behavior can be
-non-deterministic in some queries, since it relies on the order of iteration
-over nodes which is undefined when not explicitly specified.
-
-### Merge
-
-`MERGE` in Cypher attempts to match a pattern. If it already exists, it does
-nothing and subsequent clauses like `RETURN` can use the matched pattern
-elements. If the pattern can't match to any data, it creates it. For detailed
-information see Neo4j's [merge
-documentation.](https://neo4j.com/docs/developer-manual/current/cypher/clauses/merge/)
-
-An important thing about `MERGE` is visibility of modified data. `MERGE` takes
-an input (typically a `MATCH`) and has two additional *phases*: the merging
-part, and the subsequent set parts (`ON MATCH SET` and `ON CREATE SET`).
-Analysis of Neo4j's behavior indicates that each of these three phases (input,
-merge, set) does not see changes to the graph state done by subsequent phase.
-The input phase does not see data created by the merge phase, nor the set
-phase. This is consistent with what seems like the general Cypher philosophy
-that query clause effects aren't visible in the preceding clauses.
-
-We define the `Merge` logical operator as a *routing* operator that uses three
-logical operator branches.
-
-  1. The input from a preceding clause.
-
-     For example in `MATCH (n), (m) MERGE (n)-[:T]-(m)`. This input is
-     optional because `MERGE` is allowed to be the first clause in a query.
-
-  2. The `merge_match` branch.
-
-     This logical operator branch is `Pull`-ed from until exhausted for each
-     successful `Pull` from the input branch.
-
-  3. The `merge_create` branch.
-
-     This branch is `Pull`ed when the `merge_match` branch does not match
-     anything (no successful `Pull`s) for an input `Pull`. It is `Pull`ed only
-     once in such a situation, since only one creation needs to occur for a
-     failed match.
-
-The `ON MATCH SET` and `ON CREATE SET` parts of the `MERGE` clause are
-included in the `merge_match` and `merge_create` branches respectively. They
-are placed on the end of their branches so that they execute only when those
-branches succeed.
-
-Memgraph strives to be consistent with Neo in its `MERGE` implementation,
-while at the same time keeping performance as good as possible. Consistency
-with Neo w.r.t. graph state visibility is not trivial. Documentation for
-`Expand` and `Set` describe how Memgraph keeps track of both the updated
-version of an edge/vertex and the old one, as it was before the current
-transaction+command. This technique is also used in `Merge`. The input
-phase/branch of `Merge` always looks at the old data. The merge phase needs to
-see the new data so it doesn't create more data then necessary.
-
-For example, consider the query.
-
-    MATCH (p:Person) MERGE (c:City {name: p.lives_in})
-
-This query needs to create a city node only once for each unique `p.lives_in`.
-Finally the set phase of a `MERGE` clause should not affect the merge phase.
-To achieve this the `merge_match` branch of the `Merge` operator should see
-the latest created nodes, but filter them on their old state (if those nodes
-were not created by the `create_branch`).  Implementation-wise that means that
-`ScanAll` and `Expand` operators in the `merge_branch` need to look at the new
-graph state, while `Filter` operators the old, if available.

docs/dev/query/interpreter-class.dot

@@ -1,23 +0,0 @@
-digraph interpreter {
-  node [fontname="dejavusansmono"]
-  edge [fontname="dejavusansmono"]
-  node [shape=record]
-  edge [dir=back,arrowtail=empty,arrowsize=1.5]
-  Interpreter [label="{\N|+ operator(query : string, ...) : Results\l|
-                      # MakeLogicalPlan(...) : LogicalPlan\l|
-                      - plan_cache_ : Map(QueryHash, CachedPlan)\l}"]
-  Interpreter -> DistributedInterpreter
-  Results [label="{\N|+ PullAll(stream) : void\l|- plan_ : CachedPlan\l}"]
-  Interpreter -> Results
-    [dir=forward,style=dashed,arrowhead=open,label="<<create>>"]
-  CachedPlan -> Results
-    [dir=forward,arrowhead=odiamond,taillabel="1",headlabel="*"]
-  Interpreter -> CachedPlan [arrowtail=diamond,taillabel="1",headlabel="*"]
-  CachedPlan -> LogicalPlan [arrowtail=diamond]
-  LogicalPlan [label="{\N|+ GetRoot() : LogicalOperator
-                      \l+ GetCost() : double\l}"]
-  LogicalPlan -> SingleNodeLogicalPlan [style=dashed]
-  LogicalPlan -> DistributedLogicalPlan [style=dashed]
-  DistributedInterpreter -> DistributedLogicalPlan
-    [dir=forward,style=dashed,arrowhead=open,label="<<create>>"]
-}

docs/dev/query/parsing.md

@@ -1,62 +0,0 @@
-# Lexical and Syntactic Analysis
-
-## Antlr
-
-We use Antlr for lexical and syntax analysis of Cypher queries. Antrl uses
-grammar file `Cypher.g4` downloaded from http://www.opencypher.org to generate
-the parser and the visitor for the Cypher parse tree. Even though the provided
-grammar is not very pleasant to work with we decided not to do any drastic
-changes to it so that our transition to newly published versions of
-`Cypher.g4` would be easier. Nevertheless, we had to fix some bugs and add
-features, so our version is not completely the same.
-
-In addition to using `Cypher.g4`, we have `MemgraphCypher.g4`. This grammar
-file defines Memgraph specific extensions to the original grammar. Most
-notable example is the inclusion of syntax for handling authorization. At the
-moment, some extensions are also found in `Cypher.g4`. For example, the syntax
-for using a lambda function in relationship patterns. These extensions should
-be moved out of `Cypher.g4`, so that it remains as close to the original
-grammar as possible. Additionally, having `MemgraphCypher.g4` may not be
-enough if we wish to split the functionality for community and enterprise
-editions of Memgraph.
-
-## Abstract Syntax Tree (AST)
-
-Since Antlr generated visitor and the official openCypher grammar are not very
-practical to use, we translate the Antlr's AST to our own AST. Currently there
-are ~40 types of nodes in our AST. Their definitions can be found in
-`src/query/frontend/ast/ast.lcp`.
-
-Major groups of types can be found under the following base types.
-
-  * `Expression` --- types corresponding to Cypher expressions.
-  * `Clause` --- types corresponding to Cypher clauses.
-  * `PatternAtom` --- node or edge related information.
-  * `Query` --- different kinds of queries, allows extending the language with
-    Memgraph specific query syntax.
-
-Memory management of created AST nodes is done with `AstStorage`. Each type
-must be created by invoking `AstStorage::Create` method. This way all of the
-pointers to nodes and their children are raw pointers. The only owner of
-allocated memory is the `AstStorage`. When the storage goes out of scope, the
-pointers become invalid. It may be more natural to handle tree ownership via
-`unique_ptr`, i.e. each node owns its children. But there are some benefits to
-having a custom storage and allocation scheme.
-
-The primary reason we opted for not using `unique_ptr` is the requirement of
-Antlr's base visitor class that the resulting values must by copyable. The
-result is wrapped in `antlr::Any` so that the derived visitor classes may
-return any type they wish when visiting Antlr's AST. Unfortunately,
-`antlr::Any` does not work with non-copyable types.
-
-Another benefit of having `AstStorage` is that we can easily add a different
-allocation scheme for AST nodes. The interface of node creation would not
-change.
-
-### AST Translation
-
-The translation process is done via `CypherMainVisitor` class, which is
-derived from Antlr generated visitor. Besides instancing our AST types, a
-minimal number of syntactic checks are done on a query. These checks handle
-the cases which were valid in original openCypher grammar, but may be invalid
-when combined with other syntax elements.

docs/dev/query/planning.md

@@ -1,526 +0,0 @@
-# Logical Planning
-
-After the semantic analysis and symbol generation, the AST is converted to a
-tree of logical operators. This conversion is called *planning* and the tree
-of logical operators is called a *plan*. The whole planning process is done in
-the following steps.
-
-  1. [AST Preprocessing](#ast-preprocessing)
-
-     The first step is to preprocess the AST by collecting
-     information on filters, divide the query into parts, normalize patterns
-     in `MATCH` clauses, etc.
-
-  2. [Logical Operator Planning](#logical-operator-planning)
-
-     After the preprocess step, the planning can be done via 2 planners:
-     `VariableStartPlanner` and `RuleBasedPlanner`. The first planner will
-     generate multiple plans where each plan has different starting points for
-     searching the patterns in `MATCH` clauses. The second planner produces a
-     single plan by mapping the query parts as they are to logical operators.
-
-  3. [Logical Plan Postprocessing](#logical-plan-postprocessing)
-
-     In this stage, we perform various transformations on the generated logical
-     plan. Here we want to optimize the operations in order to improve
-     performance during the execution. Naturally, transformations need to
-     preserve the semantic behaviour of the original plan.
-
-  4. [Cost Estimation](#cost-estimation)
-
-     After the generation, the execution cost of each plan is estimated. This
-     estimation is used to select the best plan which will be executed.
-
-The implementation can be found in the `query/plan` directory, with the public
-entry point being `query/plan/planner.hpp`.
-
-## AST Preprocessing
-
-Each openCypher query consists of at least 1 **single query**. Multiple single
-queries are chained together using a **query combinator**. Currently, there is
-only one combinator, `UNION`. The preprocessing step starts in the
-`CollectQueryParts` function. This function will take a look at each single
-query and divide it into parts. Each part is separated with `RETURN` and
-`WITH` clauses. For example:
-
-    MATCH (n) CREATE (m) WITH m MATCH (l)-[]-(m) RETURN l
-    |                          |                        |
-    |------- part 1 -----------+-------- part 2 --------|
-    |                                                   |
-    |-------------------- single query -----------------|
-
-Each part is created by collecting all `MATCH` clauses and *normalizing* their
-patterns. Pattern normalization is the process of converting an arbitrarily
-long pattern chain of nodes and edges into a list of triplets `(start node,
-edge, end node)`. The triplets should preserve the semantics of the match. For
-example:
-
-    MATCH (a)-[p]-(b)-[q]-(c)-[r]-(d)
-
-is equivalent to:
-
-    MATCH (a)-[p]-(b), (b)-[q]-(c), (c)-[r]-(d)
-
-With this representation, it becomes easier to reorder the triplets and choose
-different strategies for pattern matching.
-
-In addition to normalizing patterns, all of the filter expressions in patterns
-and inside of the `WHERE` clause (of the accompanying `MATCH`) are extracted
-and stored separately. During the extraction, symbols used in the filter
-expression are collected. This allows for planning filters in a valid order,
-as the matching for triplets is being done. Another important benefit of
-having extra information on filters, is to recognize when a database index
-could be used.
-
-After each `MATCH` is processed, they are all grouped, so that even the whole
-`MATCH` clauses may be reordered. The important thing is to remember which
-symbols were used to name edges in each `MATCH`. With those symbols we can
-plan for *cyphermorphism*, i.e. ensure different edges in the search pattern
-of a single `MATCH` map to different edges in the graph. This preserves the
-semantic of the query, even though we may have reordered the matching. The
-same steps are done for `OPTIONAL MATCH`.
-
-Another clause which needs processing is `MERGE`. Here we normalize the
-pattern, since the `MERGE` is a bit like `MATCH` and `CREATE` in one.
-
-All the other clauses are left as is.
-
-In the end, each query part consists of:
-
-  * processed and grouped `MATCH` clauses;
-  * processed and grouped `OPTIONAL MATCH` clauses;
-  * processed `MERGE` matching pattern and
-  * unchanged remaining clauses.
-
-The last stored clause is guaranteed to be either `WITH` or `RETURN`.
-
-## Logical Operator Planning
-
-### Variable Start Planner
-
-The `VariableStartPlanner` generates multiple plans for a single query. Each
-plan is generated by selecting a different starting point for pattern
-matching.
-
-The algorithm works as follows.
-
-  1. For each query part:
-     1. For each node in triplets of collected `MATCH` clauses:
-        i. Add the node to a set of `expanded` nodes
-        ii. Select a triplet `(start node, edge, end node)` whose `start node` is
-            in the `expanded` set
-        iii. If no triplet was selected, choose a new starting node that isn't in
-             `expanded` and continue expanding
-        iv. Repeat steps ii. -- iii. until all triplets have been selected
-            and store that as a variation of the `MATCH` clauses
-     2. Do step 1.1. for `OPTIONAL MATCH` and `MERGE` clauses
-     3. Take all combinations of the generated `MATCH`, `OPTIONAL MATCH` and
-        `MERGE` and store them as variations of the query part.
-  2. For each combination of query part variations:
-     1. Generate a plan using the rule based planner
-
-###  Rule Based Planner
-
-The `RuleBasedPlanner` generates a single plan for a single query. A plan is
-generated by following hardcoded rules for producing logical operators. The
-following sections are an overview on how each openCypher clause is converted
-to a `LogicalOperator`.
-
-####  MATCH
-
-`MATCH` clause is used to specify which patterns need to be searched for in
-the database. These patterns are normalized in the preprocess step to be
-represented as triplets `(start node, edge, end node)`. When there is no edge,
-then the triplet is reduced only to the `start node`. Generating the operators
-is done by looping over these triplets.
-
-##### Searching for Nodes
-
-The simplest search is finding standalone nodes. For example, `MATCH (n)`
-will find all the nodes in the graph. This is accomplished by generating a
-`ScanAll` operator and forwarding the node symbol which should store the
-results. In this case, all the nodes will be referenced by `n`.
-
-Multiple nodes can be specified in a single match, e.g. `MATCH (n), (m)`.
-Planning is done by repeating the same steps for each sub pattern (separated
-by a comma). In this case, we would get 2 `ScanAll` operators chained one
-after the other. An optimization can be obtained if the node in the pattern is
-already searched for. In `MATCH (n), (n)` we can drop the second `ScanAll`
-operator since we have already generated it for the first node.
-
-##### Searching for Relationships
-
-A more advanced search includes finding nodes with relationships. For example,
-`MATCH (n)-[r]-(m)` should find every pair of connected nodes in the database.
-This means, that if a single node has multiple connections, it will be
-repeated for each combination of pairs. The generation of operators starts
-from the first node in the pattern. If we are referencing a new starting node,
-we need to generate a `ScanAll` which finds all the nodes and stores them
-into `n`. Then, we generate an `Expand` operator which reads the `n` and
-traverses all the edges of that node. The edge is stored into `r`, while the
-destination node is stored in `m`.
-
-Matching multiple relationships proceeds similarly, by repeating the same
-steps. The only difference is that we need to ensure different edges in the
-search pattern, map to different edges in the graph. This means that after each
-`Expand` operator, we need to generate an `EdgeUniquenessFilter`. We provide
-this operator with a list of symbols for the previously matched edges and the
-symbol for the current edge.
-
-For example.
-
-    MATCH (n)-[r1]-(m)-[r2]-(l)
-
-The above is preprocessed into
-
-    MATCH (n)-[r1]-(m), (m)-[r2]-(l)
-
-Then we look at each triplet in order and perform the described steps. This
-way, we would generate:
-
-    ScanAll (n) > Expand (n, r1, m) > Expand (m, r2, l) >
-        EdgeUniquenessFilter ([r1], r2)
-
-Note that we don't need to make `EdgeUniquenessFilter` after the first
-`Expand`, since there are no edges to compare to. This filtering needs to work
-across multiple pattern, but inside a *single* `MATCH` clause.
-
-Let's take a look at the following.
-
-    MATCH (n)-[r1]-(m), (m)-[r2]-(l)
-
-We would also generate the exact same operators.
-
-    ScanAll (n) > Expand (n, r1, m) > Expand (m, r2, l) >
-        EdgeUniquenessFilter ([r1], r2)
-
-On the other hand,
-
-    MATCH (n)-[r1]-(m) MATCH (m)-[r2]-(l)-[r3]-(i)
-
-would reset the uniqueness filtering at the start of the second match. This
-would mean that we output the following:
-
-    ScanAll (n) > Expand (n, r1, m) > Expand (m, r2, l) > Expand (l, r3, i) >
-        EdgeUniquenessFilter ([r2], r3)
-
-There is a difference in how we handle edge uniqueness compared to Neo4j.
-Neo4j does not allow searching for a single edge multiple times, but we've
-decided to support that.
-
-For example, the user can say the following.
-
-    MATCH (n)-[r]-(m)-[r]-l
-
-We would ensure that both `r` variables match to the same edge. In our
-terminology, we call this the *edge cycle*. For the above example, we would
-generate this plan.
-
-    ScanAll (n) > Expand (n, r, m) > Expand (m, r, l)
-
-We do not put an `EdgeUniquenessFilter` operator between 2 `Expand`
-operators and we tell the 2nd `Expand` that it is an edge cycle. This, 2nd
-`Expand` will ensure we have matched both the same edges.
-
-##### Filtering
-
-To narrow the search down, the patterns in `MATCH` can have filtered labels
-and properties. A more general filtering is done using the accompanying
-`WHERE` clause. During the preprocess step, all filters are collected and
-extracted into expressions. Additional information on which symbols are used
-is also stored. This way, each time we generate a `ScanAll` or `Expand`, we
-look at all the filters to see if any of them can be used. I.e. if the symbols
-they use have been bound by a newly produced operator. If a filter expression
-can be used, we immediately add a `Filter` operator with that expression.
-
-For example.
-
-    MATCH (n)-[r]-(m :label) WHERE n.prop = 42
-
-We would produce:
-
-    ScanAll (n) > Filter (n.prop) > Expand (n, r, m) > Filter (m :label)
-
-This means that the same plan is generated for the query:
-
-    MATCH (n {prop: 42})-[r]-(m :label)
-
-#### OPTIONAL
-
-If a `MATCH` clause is preceded by `OPTIONAL`, then we need to generate a plan
-such that we produce results even if we fail to match anything. This is
-accomplished by generating an `Optional` operator, which takes 2 operator
-trees:
-
-  * input operation and
-  * optional operation.
-
-The input is the operation we generated for the part of the query before
-`OPTIONAL MATCH`. For the optional operation, we simply generate the `OPTIONAL
-MATCH` part just like we would for regular `MATCH`. In addition to operations,
-we need to send the symbols which are set during optional matching to the
-`Optional` operator. The operator will reset values of those symbols to
-`null`, when the optional part fails to match.
-
-#### RETURN & WITH
-
-`RETURN` and `WITH` clauses are very similar to each other. The only
-difference is that `WITH` separates parts of the query and can be paired with
-`WHERE` clause.
-
-The common part is generating operators for the body of the clause. Separation
-of query parts is mostly done in semantic analysis, which checks that only the
-symbols exposed through `WITH` are visible in the query parts after the
-clause. The minor part is done in planning.
-
-##### Named Results
-
-Both clauses contain multiple named expressions (`expr AS name`) which are
-used to generate `Produce` operator.
-
-##### Aggregations
-
-If an expression contains an aggregation operator (`sum`, `avg`, ...) we need
-to plan the `Aggregate` operator as input to `Produce`. This case is more
-complex, because aggregation in openCypher can perform implicit grouping of
-results used for aggregation.
-
-For example, `WITH/RETURN sum(n.x) AS s, n.y AS group` will implicitly group
-by `n.y` expression.
-
-Another, obscure grouping can be achieved with `RETURN sum(n.a) + n.b AS s`.
-Here, the `n.b` will be used for grouping, even though both the `sum` and
-`n.b` are in the same named expression.
-
-Therefore, we need to collect all expressions which do not contain
-aggregations and use them for grouping. You may have noticed that in the last
-example `sum` is actually a sub-expression of `+`. `Aggregate` operator does
-not see that (nor it should), so the responsibility of evaluating that falls
-on `Produce`. One way is for `Aggregate` to store results of grouping
-expressions on the frame in addition to aggregation results. Unfortunately,
-this would require rewiring named expressions in `Produce` to reference
-already evaluated expressions. In the current implementation, we opted for
-`Aggregate` to store only aggregation results on the frame, while `Produce`
-will re-evaluate all the other (grouping) expressions. To handle that, symbols
-which are used in expressions are passed to `Aggregate`, so that they can be
-remembered. `Produce` will read those symbols from the frame and use it to
-re-evaluate the needed expressions.
-
-##### Accumulation
-
-After we have `Produce` and potentially `Aggregate`, we need to handle a
-special case when the part of the query before `RETURN` or `WITH` performs
-updates. For that, we want to run that part of the query fully, so that we get
-the latest results. This is accomplished by adding `Accumulate` operator as
-input to `Aggregate` or `Produce` (if there is no aggregation). Accumulation
-will store all the values for all the used symbols inside `RETURN` and `WITH`,
-so that they can be used in the operator which follows. This way, only parts
-of the frame are copied, instead of the whole frame. Here is a minor
-difference between planning `WITH`, compared to `RETURN`. Since `WITH` can
-separate writing from reading, we need to advance the transaction command.
-This enables the later, read parts of the query to obtain the newest changes.
-This is supported by passing `advance_command` flag to `Accumulate` operator.
-
-In the simplest case, common to both clauses, we have `Accumulate > Aggregate
-> Produce` operators, where `Accumulate` and `Aggregate` may be left out.
-
-##### Ordering
-
-Planning `ORDER BY` is simple enough. Since it may see new symbols (filled in
-`Produce`), we add the `OrderBy` operator at the end. The operator will change
-the order of produced results, so we pass it the ordering expressions and the
-output symbols of named expressions.
-
-##### Filtering
-
-A final difference in `WITH`, is when it contains a `WHERE` clause. For that,
-we simply generate the `Filter` operator, appended after `Produce` or
-`OrderBy` (depending which operator is last).
-
-##### Skipping and Limiting
-
-If we have `SKIP` or `LIMIT`, we generate `Skip` or `Limit` operators,
-respectively. These operators are put at the end of the clause.
-
-This placement may have some unexpected behaviour when combined with
-operations that update the graph. For example.
-
-    MATCH (n) SET n.x = n.x + 1 RETURN n LIMIT 1
-
-The above query may be interpreted as if the `SET` will be done only once.
-Since this is a write query, we need to accumulate results, so the part before
-`RETURN` will execute completely. The accumulated results will be yielded up
-to the given limit, and the user would get only the first `n` that was
-updated.  This may confuse the user because in reality, every node in the
-database had been updated.
-
-Note that `Skip` always comes before `Limit`. In the current implementation,
-they are generated directly one after the other.
-
-#### CREATE
-
-`CREATE` clause is used to create nodes and edges (relationships).
-
-For multiple `CREATE` clauses or multiple creation patterns in a single
-clause, we perform the same, following steps.
-
-##### Creating a Single Node
-
-A node is created by simply specifying a node pattern.
-
-For example `CREATE (n :label {property: "value"}), ()` would create 2 nodes.
-The 1st one would be created with a label and a property. This node could be
-referenced later in the query, by using the variable `n`. The 2nd node cannot
-be referenced and it would be created without any labels nor properties. For
-node creation, we generate a `CreateNode` operator and pass it all the details
-of node creation: variable symbol, labels and properties. In the mentioned
-example, we would have `CreateNode > CreateNode`.
-
-##### Creating a Relationship
-
-To create a relationship, the `CREATE` clause must contain a pattern with a
-directed edge. Compared to creating a single node, this case is a bit more
-complicated, because either side of the edge may not exist. By exist, we mean
-that the endpoint is a variable which already references a node.
-
-For example, `MATCH (n) CREATE (n)-[r]->(m)` would create an edge `r` and a
-node `m` for each matched node `n`. If we focus on the `CREATE` part, we
-generate `CreateExpand (n, r, m)` where `n` already exists (refers to matched
-node) and `m` would be newly created along with edge `r`. If we had only
-`CREATE (n)-[r]->(m)`, then we would need to create both nodes of the edge
-`r`. This is done by generating `CreateNode (n) > CreateExpand(n, r, m)`. The
-final case is when both endpoints refer to an existing node. For example, when
-adding a node with a cyclical connection `CREATE (n)-[r]->(n)`. In this case,
-we would generate `CreateNode (n) > CreateExpand (n, r, n)`. We would tell
-`CreateExpand` to only create the edge `r` between the already created `n`.
-
-#### MERGE
-
-Although the merge operation is complex, planning turns out to be relatively
-simple. The pattern inside the `MERGE` clause is used for both matching and
-creating. Therefore, we create 2 operator trees, one for each action.
-
-For example.
-
-    MERGE (n)-[r:r]-(m)
-
-We would generate a single `Merge` operator which has the following.
-
-  * No input operation (since it is not preceded by any other clause).
-
-  * On match operation
-
-    `ScanAll (n) > Expand (n, r, m) > Filter (r)`
-
-  * On create operation
-
-    `CreateNode (n) > CreateExpand (n, r, m)`
-
-In cases when `MERGE` contains `ON MATCH` and `ON CREATE` parts, we simply
-append their operations to the respective operator trees.
-
-Observe the following example.
-
-    MERGE (n)-[r:r]-(m) ON MATCH SET n.x = 42 ON CREATE SET m :label
-
-The `Merge` would be generated with the following.
-
-  * No input operation (again, since there is no clause preceding it).
-
-  * On match operation
-
-    `ScanAll (n) > Expand (n, r, m) > Filter (r) > SetProperty (n.x, 42)`
-
-  * On create operation
-
-    `CreateNode (n) > CreateExpand (n, r, m) > SetLabels (n, :label)`
-
-When we have preceding clauses, we simply put their operator as input to
-`Merge`.
-
-    MATCH (n) MERGE (n)-[r:r]-(m)
-
-The above would be generated as
-
-    ScanAll (n) > Merge (on_match_operation, on_create_operation)
-
-Here we need to be careful to recognize which symbols are already declared.
-But, since the `on_match_operation` uses the same algorithm for generating a
-`Match`, that problem is handled there. The same should hold for
-`on_create_operation`, which uses the process of generating a `Create`. So,
-finally for this example, the `Merge` would have:
-
-  * Input operation
-
-    `ScanAll (n)`
-
-  * On match operation
-
-    `Expand (n, r, m) > Filter (r)`
-
-    Note that `ScanAll` is not needed since we get the nodes from input.
-
-  * On create operation
-
-    `CreateExpand (n, r, m)`
-
-    Note that `CreateNode` is dropped, since we want to expand the existing one.
-
-## Logical Plan Postprocessing
-
-Postprocessing of a logical plan is done by rewriting the original plan into
-a more efficient one while preserving the original semantic of operations.
-The rewriters are found in `query/plan/rewrite` directory, and currently we
-only have one -- `IndexLookupRewriter`.
-
-### IndexLookupRewriter
-
-The job of this rewriter is to merge `Filter` and `ScanAll` operations into
-equivalent `ScanAllBy<Index>` operations. In almost all cases using indexed
-lookup will be faster than regular lookup, so `IndexLookupRewriter` simply
-does the transformations whenever possible. The simplest case being the
-following, assuming we have an index over `id`.
-
-  * Original Plan
-
-    `ScanAll (n) > Filter (id(n) == 42) > Produce (n)`
-
-  * Rewritten Plan
-
-    `ScanAllById (n, id=42) > Produce (n)`
-
-Naturally, there are some cases we need to be careful about.
-
-  1. Operators with Multiple Branches
-
-     Here we may not carry `Filter` operations outside of the operator into
-     its branches, so the branches are rewritten as stand alone plans with a
-     branch new `IndexLookupRewriter`. Some of the operators with multiple
-     branches are `Merge`, `Optional`, `Cartesian` and `Union`.
-
-  2. Expand Operators
-
-     Expand operations aren't that tricky to handle, but they have a special
-     case where we want to use an indexed lookup of the destination so that the
-     expansion is performed between known nodes. This decision may depend on
-     various parameters which may need further tweaking as we encounter more
-     use-cases of Cypher queries.
-
-## Cost Estimation
-
-Cost estimation is the final step of processing a logical plan. The
-implementation can be found in `query/plan/cost_estimator.hpp`. We give each
-operator a cost based on the estimated cardinality of results of that operator
-and on the preset coefficient of the runtime performance of that operator.
-
-This scheme is rather simple and works quite well, but there are couple of
-improvements we may want to do at some point.
-
-  * Track more information about the stored graph and use that to improve the
-    estimates.
-  * Do a quick, partial run of the plan and tweak the estimation based on how
-    much each operator produced results. This may require us having some kind
-    of representative subset of the stored graph.
-  * Write micro benchmarks for each operator and based on the results create
-    sensible preset coefficients. This would replace the current coefficients
-    which are just assumptions on how each operator implementation performs.

docs/dev/query/semantic.md

@@ -1,134 +0,0 @@
-# Semantic Analysis and Symbol Generation
-
-In this phase, various semantic and variable type checks are performed.
-Additionally, we generate symbols which map AST nodes to stored values
-computed from evaluated expressions.
-
-## Symbol Generation
-
-Implementation can be found in `query/frontend/semantic/symbol_generator.cpp`.
-
-Symbols are generated for each AST node that represents data that needs to
-have storage. Currently, these are:
-
-  * `NamedExpression`
-  * `CypherUnion`
-  * `Identifier`
-  * `Aggregation`
-
-You may notice that the above AST nodes may not correspond to something named
-by a user. For example, `Aggregation` can be a part of larger expression and
-thus remain unnamed. The reason we still generate symbols is to have a uniform
-behaviour when executing a query as well as allow for caching the results of
-expression evaluation.
-
-AST nodes do not actually store a `Symbol` instance, instead they have a
-`int32_t` index identifying the symbol in the `SymbolTable` class. This is
-done to minimize the size of AST types as well as allow easier sharing of same
-symbols with multiple instances of AST nodes.
-
-The storage for evaluated data is represented by the `Frame` class. Each
-symbol determines a unique position in the frame. During interpretation,
-evaluation of expressions which have a symbol will either read or store values
-in the frame. For example, instance of an `Identifier` will use the symbol to
-find and read the value from `Frame`. On the other hand, `NamedExpression`
-will take the result of evaluating its own expression and store it in the
-`Frame`.
-
-When a symbol is created, context of creation is used to assign a type to that
-symbol. This type is used for simple type checking operations. For example,
-`MATCH (n)` will create a symbol for variable `n`. Since the `MATCH (n)`
-represents finding a vertex in the graph, we can set `Symbol::Type::Vertex`
-for that symbol. Later, for example in `MATCH ()-[n]-()` we see that variable
-`n` is used as an edge. Since we already have a symbol for that variable, we
-detect this type mismatch and raise a `SemanticException`.
-
-Basic rule of symbol generation, is that variables inside `MATCH`, `CREATE`,
-`MERGE`, `WITH ... AS` and `RETURN ... AS` clauses establish new symbols.
-
-### Symbols in Patterns
-
-Inside `MATCH`, symbols are created only if they didn't exist before. For
-example, patterns in `MATCH (n {a: 5})--(m {b: 5}) RETURN n, m` will create 2
-symbols: one for `n` and one for `m`. `RETURN` clause will, in turn, reference
-those symbols. Symbols established in a part of pattern are immediately bound
-and visible in later parts. For example, `MATCH (n)--(n)` will create a symbol
-for variable `n` for 1st `(n)`. That symbol is referenced in 2nd `(n)`. Note
-that the symbol is not bound inside 1st `(n)` itself. What this means is that,
-for example, `MATCH (n {a: n.b})` should raise an error, because `n` is not
-yet bound when encountering `n.b`. On the other hand,
-`MATCH (n)--(n {a: n.b})` is fine.
-
-The `CREATE` is similar to `MATCH`, but it *always* establishes symbols for
-variables which create graph elements. What this means is that, for example
-`MATCH (n) CREATE (n)` is not allowed. `CREATE` wants to create a new node,
-for which we already have a symbol. In such a case, we need to throw an error
-that the variable `n` is being redeclared. On the other hand `MATCH (n) CREATE
-(n)-[r :r]->(n)` is fine, because `CREATE` will only create the edge `r`,
-connecting the already existing node `n`. Remaining behaviour is the same as
-in `MATCH`. This means that we can simplify `CREATE` to be like `MATCH` with 2
-special cases.
-
-  1. Are we creating a node, i.e. `CREATE (n)`? If yes, then the symbol for
-     `n` must not have been created before. Otherwise, we reference the
-     existing symbol.
-  2. Are we creating an edge, i.e. we encounter a variable for an edge inside
-     `CREATE`? If yes, then that variable must not reference a symbol.
-
-The `MERGE` clause is treated the same as `CREATE` with regards to symbol
-generation. The only difference is that we allow bidirectional edges in the
-pattern. When creating such a pattern, the direction of the created edge is
-arbitrarily determined.
-
-### Symbols in WITH and RETURN
-
-In addition to patterns, new symbols are established in the `WITH` clause.
-This clause makes the new symbols visible *only* to the rest of the query.
-For example, `MATCH (old) WITH old AS new RETURN new, old` should raise an
-error that `old` is unbound inside `RETURN`.
-
-There is a special case with symbol visibility in `WHERE` and `ORDER BY`. They
-need to see both the old and the new symbols. Therefore `MATCH (old) RETURN
-old AS new ORDER BY old.prop` needs to work. On the other hand, if we perform
-aggregations inside `WITH` or `RETURN`, then the old symbols should not be
-visible neither in `WHERE` nor in `ORDER BY`. Since the aggregation has to go
-through all the results in order to generate the final value, it makes no
-sense to store old symbols and their values. A query like `MATCH (old) WITH
-SUM(old.prop) AS sum WHERE old.prop = 42 RETURN sum` needs to raise an error
-that `old` is unbound inside `WHERE`.
-
-For cases when `SKIP` and `LIMIT` appear, we disallow any identifiers from
-appearing in their expressions. Basically, `SKIP` and `LIMIT` can only be
-constant expressions[^1]. For example, `MATCH (old) RETURN old AS new SKIP
-new.prop` needs to raise that variables are not allowed in `SKIP`. It makes no
-sense to allow variables, since their values may vary on each iteration. On
-the other hand, we could support variables to constant expressions, but for
-simplicity we do not. For example, `MATCH (old) RETURN old, 2 AS limit_var
-LIMIT limit_var` would still throw an error.
-
-Finally, we generate symbols for names created in `RETURN` clause. These
-symbols are used for the final results of a query.
-
-NOTE: New symbols in `WITH` and `RETURN` should be unique. This means that
-`WITH a AS same, b AS same` is not allowed, neither is a construct like
-`RETURN 2, 2`
-
-### Symbols in Functions which Establish New Scope
-
-Symbols can also be created in some functions. These functions usually take an
-expression, bind a single variable and run the expression inside the newly
-established scope.
-
-The `all` function takes a list, creates a variable for list element and runs
-the predicate expression. For example:
-
-    MATCH (n) RETURN n, all(n IN n.prop_list WHERE n < 42)
-
-We create a new symbol for use inside `all`, this means that the `WHERE n <
-42` uses the `n` which takes values from a `n.prop_list` elements. The
-original `n` bound by `MATCH` is not visible inside the `all` function, but it
-is visible outside. Therefore, the `RETURN n` and `n.prop_list` reference the
-`n` from `MATCH`.
-
-[^1]: Constant expressions are expressions for which the result can be
-  computed at compile time.

docs/dev/quick-start.md

@@ -1,108 +0,0 @@
-# Quick Start
-
-A short chapter on downloading the Memgraph source, compiling and running.
-
-## Obtaining the Source Code
-
-Memgraph uses `git` for source version control. You will need to install `git`
-on your machine before you can download the source code.
-
-On Debian systems, you can do it inside a terminal with the following
-command:
-
-    sudo apt-get install git
-
-On ArchLinux or Gentoo, you probably already know what to do.
-
-After installing `git`, you are now ready to fetch your own copy of Memgraph
-source code. Run the following command:
-
-    git clone https://phabricator.memgraph.io/diffusion/MG/memgraph.git
-
-The above will create a `memgraph` directory and put all source code there.
-
-## Compiling Memgraph
-
-With the source code, you are now ready to compile Memgraph. Well... Not
-quite. You'll need to download Memgraph's dependencies first.
-
-In your terminal, position yourself in the obtained memgraph directory.
-
-    cd memgraph
-
-### Installing Dependencies
-
-On Debian systems, dependencies that are required by the codebase should be
-setup by running the `init` script:
-
-    ./init -s
-
-Currently, other systems aren't supported in the `init` script. But you can
-issue the needed steps manually. First run the `init` script.
-
-    ./init
-
-The script will output the required packages, which you should be able to
-install via your favorite package manager. For example, `pacman` on ArchLinux.
-After installing the packages, issue the following commands:
-
-    mkdir -p build
-    ./libs/setup.sh
-
-### Compiling
-
-Memgraph is compiled using our own custom toolchain that can be obtained from
-[Toolchain repository](https://deps.memgraph.io/toolchain).  You should read
-the `README.txt` file in the repository and install the apropriate toolchain
-for your distribution.  After you have installed the toolchain you should read
-the instructions for the toolchain in the toolchain install directory
-(`/opt/toolchain-vXYZ/README.md`) and install dependencies that are necessary
-to run the toolchain.
-
-When you want to compile Memgraph you should activate the toolchain using the
-prepared toolchain activation script that is also described in the toolchain
-`README`.
-
-NOTE: You *must* activate the toolchain every time you want to compile
-Memgraph!
-
-You should now activate the toolchain in your console.
-
-    source /opt/toolchain-vXYZ/activate
-
-With all of the dependencies installed and the build environment set-up, you
-need to configure the build system. To do that, execute the following:
-
-    cd build
-    cmake ..
-
-If everything went OK, you can now, finally, compile Memgraph.
-
-    make -j$(nproc)
-
-### Running
-
-After the compilation verify that Memgraph works:
-
-    ./memgraph --version
-
-To make extra sure, run the unit tests:
-
-    ctest -R unit -j$(nproc)
-
-## Problems
-
-If you have any trouble running the above commands, contact your nearest
-developer who successfully built Memgraph. Ask for help and insist on getting
-this document updated with correct steps!
-
-## Next Steps
-
-Familiarise yourself with our code conventions and guidelines:
-
-  * [C++ Code](cpp-code-conventions.md)
-  * [Other Code](other-code-conventions.md)
-  * [Code Review Guidelines](code-review.md)
-
-Take a look at the list of [required reading](required-reading.md) for
-brushing up on technical skills.

docs/dev/required-reading.md

@@ -1,129 +0,0 @@
-# Required Reading
-
-This chapter lists a few books that should be read by everyone working on
-Memgraph. Since Memgraph is developed primarily with C++, Python and Common
-Lisp, books are oriented around those languages. Of course, there are plenty
-of general books which will help you improve your technical skills (such as
-"The Pragmatic Programmer", "The Mythical Man-Month", etc.), but they are not
-listed here. This way the list should be kept short and the *required* part in
-"Required Reading" more easily honored.
-
-Some of these books you may find in our office, so feel free to pick them up.
-If any are missing and you would like a physical copy, don't be afraid to
-request the book for our office shelves.
-
-Besides reading, don't get stuck in a rut and be a
-[Blub Programmer](http://www.paulgraham.com/avg.html).
-
-## Effective C++ by Scott Meyers
-
-Required for C++ developers.
-
-The book is a must-read as it explains most common gotchas of using C++. After
-reading this book, you are good to write competent C++ which will pass code
-reviews easily.
-
-## Effective Modern C++ by Scott Meyers
-
-Required for C++ developers.
-
-This is a continuation of the previous book, it covers updates to C++ which
-came with C++11 and later. The book isn't as imperative as the previous one,
-but it will make you aware of modern features we are using in our codebase.
-
-## Practical Common Lisp by Peter Siebel
-
-Required for Common Lisp developers.
-
-Free: http://www.gigamonkeys.com/book/
-
-We use Common Lisp to generate C++ code and make our lives easier.
-Unfortunately, not many developers are familiar with the language. This book
-will make you familiar very quickly as it has tons of very practical
-exercises. E.g. implementing unit testing library, serialization library and
-bundling all that to create a mp3 music server.
-
-## Effective Python by Brett Slatkin
-
-(Almost) required reading for Python developers.
-
-Why the "almost"? Well, Python is relatively easy to pick up and you will
-probably learn all the gotchas during code review from someone more
-experienced. This makes the book less necessary for a newcomer to Memgraph,
-but the book is not advanced enough to delegate it to
-[Advanced Reading](#advanced-reading). The book is written in similar vein as
-the "Effective C++" ones and will make you familiar with nifty Python features
-that make everyone's lives easier.
-
-# Advanced Reading
-
-The books listed below are not required reading, but you may want to read them
-at some point when you feel comfortable enough.
-
-## Design Patterns by Gamma et. al.
-
-Recommended for C++ developers.
-
-This book is highly divisive because it introduced a culture centered around
-design patterns. The main issues is overuse of patterns which complicates the
-code. This has made many Java programs to serve as examples of highly
-complicated, "enterprise" code.
-
-Unfortunately, design patterns are pretty much missing
-language features. This is most evident in dynamic languages such as Python
-and Lisp, as demonstrated by
-[Peter Norvig](http://www.norvig.com/design-patterns/).
-
-Or as [Paul Graham](http://www.paulgraham.com/icad.html) put it:
-
-```
-This practice is not only common, but institutionalized. For example, in the
-OO world you hear a good deal about "patterns". I wonder if these patterns are
-not sometimes evidence of case (c), the human compiler, at work. When I see
-patterns in my programs, I consider it a sign of trouble. The shape of a
-program should reflect only the problem it needs to solve. Any other
-regularity in the code is a sign, to me at least, that I'm using abstractions
-that aren't powerful enough-- often that I'm generating by hand the expansions
-of some macro that I need to write
-```
-
-After presenting the book so negatively, why you should even read it then?
-Well, it is good to be aware of those design patterns and use them when
-appropriate. They can improve modularity and reuse of the code. You will also
-find examples of such patterns in our code, primarily Strategy and Visitor
-patterns. The book is also a good stepping stone to more advanced reading
-about software design.
-
-## Modern C++ Design by Andrei Alexandrescu
-
-Recommended for C++ developers.
-
-This book can be treated as a continuation of the previous "Design Patterns"
-book. It introduced "dark arts of template meta-programming" to the world.
-Many of the patterns are converted to use C++ templates which makes them even
-better for reuse. But, like the previous book, there are downsides if used too
-much. You should approach it with a critical eye and it will help you
-understand ideas that are used in some parts of our codebase.
-
-## Large Scale C++ Software Design by John Lakos
-
-Recommended for C++ developers.
-
-An old book, but well worth the read. Lakos presents a very pragmatic view of
-writing modular software and how it affects both development time as well as
-program runtime. Some things are outdated or controversial, but it will help
-you understand how the whole C++ process of working in a large team, compiling
-and linking affects development.
-
-## On Lisp by Paul Graham
-
-Recommended for Common Lisp developers.
-
-Free: http://www.paulgraham.com/onlisp.html
-
-An excellent continuation to "Practical Common Lisp". It starts of slow, as if
-introducing the language, but very quickly picks up speed. The main meat of
-the book are macros and their uses. From using macros to define cooperative
-concurrency to including Prolog as if it's part of Common Lisp. The book will
-help you understand more advanced macros that are occasionally used in our
-Lisp C++ Preprocessor (LCP).

docs/dev/storage/accessors.md

@@ -1,110 +0,0 @@
-# DatabaseAccessor
-
-A `DatabaseAccessor` actually wraps a transactional access to database
-data, for a single transaction. In that sense the naming is bad. It
-encapsulates references to the database and the transaction object.
-
-It contains logic for working with database content (graph element
-data) in the context of a single transaction. All CRUD operations are
-performed within a single transaction (as Memgraph is a transactional
-database), and therefore iteration over data, finding a specific graph
-element etc are all functionalities of a `GraphDbAccessor`.
-
-In single-node Memgraph the database accessor also defined the lifetime
-of a transaction. Even though a `Transaction` object was owned by the
-transactional engine, it was `GraphDbAccessor`'s lifetime that object
-was bound to (the transaction was implicitly aborted in
-`GraphDbAccessor`'s destructor, if it was not explicitly ended before
-that).
-
-# RecordAccessor
-
-It is important to understand data organization and access in the
-storage layer. This discussion pertains to vertices and edges as graph
-elements that the end client works with.
-
-Memgraph uses MVCC (documented on it's own page). This means that for
-each graph element there could be different versions visible to
-different currently executing transactions. When we talk about a
-`Vertex` or `Edge` as a data structure we typically mean one of those
-versions. In code this semantic is implemented so that both those classes
-inherit `mvcc::Record`, which in turn inherits `mvcc::Version`.
-
-Handling MVCC and visibility is not in itself trivial. Next to that,
-there is other book-keeping to be performed when working with data. For
-that reason, Memgraph uses "accessors" to define an API of working with
-data in a safe way. Most of the code in Memgraph (for example the
-interpretation code) should work with accessors. There is a
-`RecordAccessor` as a base class for `VertexAccessor` and
-`EdgeAccessor`. Following is an enumeration of their purpose.
-
-### Data access
-
-The client interacts with Memgraph using the Cypher query language. That
-language has certain semantics which imply that multiple versions of the
-data need to be visible during the execution of a single query. For
-example: expansion over the graph is always done over the graph state as
-it was at the beginning of the transaction.
-
-The `RecordAccessor` exposes functions to switch between the old and the new
-versions of the same graph element (intelligently named `SwitchOld` and
-`SwitchNew`) within a single transaction. In that way the client code
-(mostly the interpreter) can avoid dealing with the underlying MVCC
-version concepts.
-
-### Updates
-
-Data updates are also done through accessors. Meaning: there are methods
-on the accessors that modify data, the client code should almost never
-interact directly with `Vertex` or `Edge` objects.
-
-The accessor layer takes care of creating version in the MVCC layer and
-performing updates on appropriate versions.
-
-Next, for many kinds of updates it is necessary to update the relevant
-indexes. There are implicit indexes for vertex labels, as
-well as user-created indexes for (label, property) pairs. The accessor
-layer takes care of updating the indexes when these values are changed.
-
-Each update also triggers a log statement in the write-ahead log. This
-is also handled by the accessor layer.
-
-### Distributed
-
-In distributed Memgraph accessors also contain a lot of the remote graph
-element handling logic. More info on that is available in the
-documentation for distributed.
-
-### Deferred MVCC data lookup for Edges
-
-Vertices and edges are versioned using MVCC. This means that for each
-transaction an MVCC lookup needs to be done to determine which version
-is visible to that transaction. This tends to slow things down due to
-cache invalidations (version lists and versions are stored in arbitrary
-locations on the heap).
-
-However, for edges, only the properties are mutable. The edge endpoints
-and type are fixed once the edge is created. For that reason both edge
-endpoints and type are available in vertex data, so that when expanding
-it is not mandatory to do MVCC lookups of versioned, mutable data. This
-logic is implemented in `RecordAccessor` and `EdgeAccessor`.
-
-### Exposure
-
-The original idea and implementation of graph element accessors was that
-they'd prevent client code from ever interacting with raw `Vertex` or
-`Edge` data. This however turned out to be impractical when implementing
-distributed Memgraph and the raw data members have since been exposed
-(through getters to old and new version pointers). However, refrain from
-working with that data directly whenever possible! Always consider the
-accessors to be the first go-to for interacting with data, especially
-when in the context of a transaction.
-
-# Skiplist accessor
-
-The term "accessor" is also used in the context of a skiplist. Every
-operation on a skiplist must be performed within on an
-accessor. The skiplist ensures that there will be no physical deletions
-of an object during the lifetime of an accessor. This mechanism is used
-to ensure deletion correctness in a highly concurrent container.
-We only mention that here to avoid confusion regarding terminology.

docs/dev/storage/indexes.md

@@ -1,116 +0,0 @@
-# Label indexes
-
-These are unsorted indexes that contain all the vertices that have the label
-the indexes are for (one index per label). These kinds of indexes get
-automatically generated for each label used in the database.
-
-### Updating the indexes
-
-Whenever something gets added to the record we update the index (add that
-record to index). We keep an index which might contain garbage (not relevant
-records, because the value got removed or something similar) but we will
-filter it out when querying the index. We do it like this because we don't
-have to do bookkeeping and deciding if we update the index on the end of the
-transaction (commit/abort phase), moreover current interpreter advances the
-command in transaction and as such assumes that the indexes now contain
-objects added in the previous command inside this transaction, so we need to
-update over the whole scope of transaction (whenever something is added to the
-record).
-
-### Index Entries Label
-
-These kinds of indexes are internally keeping track of pair (record, vlist).
-Why do we need to keep track of exactly those two things?
-
-Problems with two different approaches
-
-1) Keep track of just the record:
-
-  - We need the `VersionList` for creating an accessor (this in itself is a
-    deal-breaker).
-  - Semantically it makes sense. An edge/vertex maps bijectionally to a
-    `VersionList`.
-  - We might try to access some members of record while the record is being
-    modified from another thread.
-  - A vertex/edge could get updated, thus expiring the record in the index.
-    The newly created record should be present in the index, but it's not.
-    Without the `VersionList` we can't reach the newly created record.
-  - Probably there are even more reasons... It should be obvious by now that
-    we need the `VersionList` in the index.
-
-2) Keep track of just the version list:
-
-  - Removing from an index is a problem for two major reasons. First, if we
-    only have the `VersionList`, checking if it should be removed implies
-    checking all the reachable records, which is not thread-safe. Second,
-    there are issues with concurrent removal and insertion. The cleanup thread
-    could determine the vertex/edge should be removed from the index and
-    remove it, while in between those ops another thread attempts to insert
-    the `VersionList` into the index. The insertion does nothing because the
-    `VersionList` is already in, but it gets removed immediately after.
-
-Because of inability to keep track of just the record, or value, we need to
-keep track of both of them.  Resolution of problems mentioned above, in the
-same order, with (record, vlist) pair
-
-  - simple `vlist.find(current transaction)` will get us the newest visible
-    record
-  - we'll never try to access some record if it's still being written since we
-    will always operate on vlist.find returned record
-  - newest record will contain that label
-  - since we have (record, vlist) pair as the key in the index when we update
-    and delete in the same time we will never delete the same record, vlist
-    pair we are adding because the record, vlist pair we are deleting is
-    already superseded by a newer record and as such won't be inserted while
-    it's being deleted
-
-### Querying the index
-
-We run through the index for the given label and do `vlist.find` operation for
-the current transaction, and check if the newest return record has that
-label. If it has it then we return it. By now you are probably wondering
-aren't we sometimes returning duplicate vlist entries? And you are wondering
-correctly, we would be returning them, but we are making sure that the entires
-in the index are sorted by their `vlist*` and as such we can filter consecutive
-duplicate `vlist*` to only return one of those while still being able to create
-an iterator to index.
-
-### Cleaning the index
-
-Cleaning the index is not as straightforward as it seems as a lot of garbage
-can accumulate, but it's hard to know when exactly can we delete some (record,
-vlist) pair. First, let's assume that we are doing the cleaning process at
-some `transaction_id`, `id` such that there doesn't exist an active transaction
-with an id lower than `id`.
-
-We scan through the whole index and for each (record, vlist) pair we first
-check if it was deleted before the id (i.e. no transaction with an id >= `id`
-will ever again see that record), if it was deleted before we might naively
-say that it's safe to delete it, but, we must take into account that when some
-new record is created from this record (update operation), that record still
-contains the label but by deleting this record we won't be able to see that
-vlist because that new record won't add again to index because we didn't
-explicitly add that label again to it.
-
-Because of this we have to 'update' this index (record, vlist) pair. We have
-to update the record to now point to a newer record in vlist, the one that is
-not deleted yet. We can do that by querying the `version_list` for the last
-record inside (oldest it has — remember that `mvcc_gc` will re-link not
-visible records so the last record will be visible for the current GC id).
-When updating the record inside the index, it's not okay to just update the
-pointer and leave the index as it is, because with updating the `record*` we
-might change the relative order of entries inside the index. We first have to
-re-insert it with new `record*`, and then delete the old entry. And we need to
-do insertion before the remove operation! Otherwise it could happen that the
-vlist with a newer record with that label won't exist while some transaction
-is querying the index.
-
-Records which we added as a consequence of deleting older records will be
-eventually removed from the index if they don't contain label because if we
-see that the record is not deleted we try to check if that record still
-contains the label. We also need to be careful here because we can't check
-that while the record is being potentially updated by some transaction (race
-condition), so we need can check if records still contain label if it's
-creation id is smaller than our `id`, as that implies that the creating
-transaction either aborted or committed as our `id` is equal to the oldest
-active transaction in time of starting the GC.

docs/dev/storage/property-storage.md

@@ -1,131 +0,0 @@
-# Property storage
-
-Although the reader is probably familiar with properties in *Memgraph*, let's
-briefly recap. 
-
-Both vertices and edges can store an arbitrary number of properties. Properties
-are, in essence, ordered pairs of property names and property values. Each
-property name within a single graph element (edge/node) can store a single
-property value. Property names are represented as strings, while property values
-must be one of the following types:
-
- Type      | Description
------------|------------
- `Null`    | Denotes that the property has no value. This is the same as if the property does not exist.
- `String`  | A character string, i.e. text.
- `Boolean` | A boolean value, either `true` or `false`.
- `Integer` | An integer number.
- `Float`   | A floating-point number, i.e. a real number.
- `List`    | A list containing any number of property values of any supported type. It can be used to store multiple values under a single property name.
- `Map`     | A mapping of string keys to values of any supported type.
-
-Property values are modeled in a class conveniently called `PropertyValue`.
-
-## Mapping between property names and property keys.
-
-Although users think of property names in terms of descriptive strings 
-(e.g. "location" or "department"), *Memgraph* internally converts those names
-into property keys which are, essentially, unsigned 16-bit integers.
-
-Property keys are modelled by a not-so-conveniently named class called
-`Property` which can be found in `storage/types.hpp`. The actual conversion
-between property names and property keys is done within the `ConcurrentIdMapper`
-but the internals of that implementation are out of scope for understanding
-property storage.
-
-## PropertyValueStore
-
-Both `Edge` and `Vertex` objects contain an instance of `PropertyValueStore`
-object which is responsible for storing properties of a corresponding graph
-element.
-
-An interface of `PropertyValueStore` is as follows:
-
- Method    | Description
------------|------------
- `at`      | Returns the `PropertyValue` for a given `Property` (key).
- `set`     | Stores a given `PropertyValue` under a given `Property` (key).
- `erase`   | Deletes a given `Property` (key) alongside its corresponding `PropertyValue`.
- `clear`   | Clears the storage.
- `iterator`| Provides an extension of `std::input_iterator` that iterates over storage.
-
-## Storage location
-
-By default, *Memgraph* is an in-memory database and all properties are therefore
-stored in working memory unless specified otherwise by the user. User has an
-option to specify via the command line which properties they wish to be stored
-on disk.
-
-Storage location of each property is encapsulated within a `Property` object
-which is ensured by the `ConcurrentIdMapper`. More precisely, the unsigned 16-bit
-property key has the following format:
-
-```
-|---location--|------id------|
-|-Memory|Disk-|-----2^15-----|
-``` 
-
-In other words, the most significant bit determines the location where the
-property will be stored. 
-
-### In-memory storage
-
-The underlying implementation of in-memory storage for the time being is
-`std::vector<std::pair<Property, PropertyValue>>`. Implementations of`at`, `set`
-and `erase` are linear in time. This implementation is arguably more efficient
-than `std::map` or `std::unordered_map` when the average number of properties of
-a record is relatively small (up to 10) which seems to be the case.
-
-### On-disk storage
-
-#### KVStore
-
-Disk storage is modeled by an abstraction of key-value storage as implemented in
-`storage/kvstore.hpp'. An interface of this abstraction is as follows:
-
- Method         | Description
-----------------|------------
- `Put`          | Stores the given value under the given key.
- `Get`          | Obtains the given value stored under the given key.
- `Delete`       | Deletes a given (key, value) pair from storage..
- `DeletePrefix` | Deletes all (key, value) pairs where key begins with a given prefix.
- `Size`         | Returns the size of the storage or, optionally, the number of stored pairs that begin with a given prefix.
- `iterator`     | Provides an extension of `std::input_iterator` that iterates over storage.
-
-Keys and values in this context are of type `std::string`.
-
-The actual underlying implementation of this abstraction uses
-[RocksDB]{https://rocksdb.org} &mdash; a persistent key-value store for fast
-storage.
-
-It is worthy to note that the custom iterator implementation allows the user
-to iterate over a given prefix. Otherwise, the implementation follows familiar
-c++ constructs and can be used as follows:
-
-```
-KVStore storage = ...;
-for (auto it = storage.begin(); it != storage.end(); ++it) {}
-for (auto kv : storage) {}
-for (auto it = storage.begin("prefix"); it != storage.end("prefix"); ++it) {}
-```
-
-Note that it is not possible to scan over multiple prefixes. For instance, one
-might assume that you can scan over all keys that fall in a certain
-lexicographical range. Unfortunately, that is not the case and running the
-following code will result in an infinite loop with a touch of undefined
-behavior.
-
-```
-KVStore storage = ...;
-for (auto it = storage.begin("alpha"); it != storage.end("omega"); ++it) {}
-```
-
-#### Data organization on disk
-
-Each `PropertyValueStore` instance can access a static `KVStore` object that can
-store `(key, value)` pairs on disk. The key of each property on disk consists of
-two parts &mdash; a unique identifier (unsigned 64-bit integer) of the current
-record version (see mvcc docummentation for further clarification) and a 
-property key as described above. The actual value of the property is serialized
-into a bytestring using bolt `BaseEncoder`. Similarly, deserialization is
-performed by bolt `Decoder`.

docs/dev/toolchain-bootstrap.md

@@ -1,152 +0,0 @@
-# Bootstrapping Compilation Toolchain for Memgraph
-
-Requirements:
-
-  * libstdc++ shipped with gcc-6.3 or gcc-6.4
-  * cmake >= 3.1, Debian Stretch uses cmake-3.7.2
-  * clang-3.9
-
-## Installing gcc-6.4
-
-gcc-6.3 has a bug, so use the 6.4 version which is just a bugfix release.
-
-Requirements on CentOS 7:
-
-  * wget
-  * make
-  * gcc (bootstrap)
-  * gcc-c++ (bootstrap)
-  * gmp-devel (bootstrap)
-  * mpfr-devel (bootstrap)
-  * libmpc-devel (bootstrap)
-  * zip
-  * perl
-  * dejagnu (testing)
-  * expect (testing)
-  * tcl (testing)
-
-```
-wget ftp://ftp.mpi-sb.mpg.de/pub/gnu/mirror/gcc.gnu.org/pub/gcc/releases/gcc-6.4.0/gcc-6.4.0.tar.gz
-tar xf gcc-6.4.0.tar.gz
-cd gcc-6.4.0
-mkdir build
-cd build
-../configure --disable-multilib --prefix=<install-dst>
-make
-# Testing
-make -k check
-make install
-```
-
-*Do not put gcc + libs on PATH* (unless you know what you are doing).
-
-## Installing cmake-3.7.2
-
-Requirements on CentOS 7:
-
-  * wget
-  * make
-  * gcc
-  * gcc-c++
-  * ncurses-devel (optional, for ccmake)
-
-```
-wget https://cmake.org/files/v3.7/cmake-3.7.2.tar.gz
-tar xf cmake-3.7.2.tar.gz
-cd cmake-3.7.2.tar.gz
-./bootstrap --prefix<install-dst>
-make
-make install
-```
-
-Put cmake on PATH (if appropriate)
-
-**Fix the bug in CpackRPM**
-
-`"<path-to-cmake>/share/cmake-3.7/Modules/CPackRPM.cmake" line 2273 of 2442`
-
-The line
-
-```
-set(RPMBUILD_FLAGS "-bb")
-```
-needs to be before
-
-```
-if(CPACK_RPM_GENERATE_USER_BINARY_SPECFILE_TEMPLATE OR NOT CPACK_RPM_USER_BINARY_SPECFILE)
-```
-
-It was probably accidentally placed after, and is fixed in later cmake
-releases.
-
-## Installing clang-3.9
-
-Requirements on CentOS 7:
-
-  * wget
-  * make
-  * cmake
-
-```
-wget http://releases.llvm.org/3.9.1/llvm-3.9.1.src.tar.xz
-tar xf llvm-3.9.1.src.tar.xz
-mv llvm-3.9.1.src llvm
-
-wget http://releases.llvm.org/3.9.1/cfe-3.9.1.src.tar.xz
-tar xf cfe-3.9.1.src.tar.xz
-mv cfe-3.9.1.src llvm/tools/clang
-
-cd llvm
-mkdir build
-cd build
-cmake -DCMAKE_BUILD_TYPE="Release" -DGCC_INSTALL_PREFIX=<gcc-dir> \
--DCMAKE_C_COMPILER=<gcc> -DCMAKE_CXX_COMPILER=<g++> \
--DCMAKE_CXX_LINK_FLAGS="-L<gcc-dir>/lib64 -Wl,-rpath,<gcc-dir>/lib64" \
--DCMAKE_INSTALL_PREFIX=<install-dst> ..
-make
-# Testing
-make check-clang
-make install
-```
-
-Put clang on PATH (if appropriate)
-
-## Memgraph
-
-Requirements on CentOS 7:
-
-  * libuuid-devel (antlr4)
-  * java-1.8.0-openjdk (antlr4)
-  * boost-static (too low version --- compile manually)
-  * rpm-build (RPM)
-  * python3 (tests, ...)
-  * which (required for rocksdb)
-  * sbcl (lisp C++ preprocessing)
-
-### Boost 1.62
-
-```
-wget https://netix.dl.sourceforge.net/project/boost/boost/1.62.0/boost_1_62_0.tar.gz
-tar xf boost_1_62_0.tar.gz
-cd boost_1_62_0
-./bootstrap.sh --with-toolset=clang --with-libraries=iostreams,serialization --prefix=<install-dst>
-./b2
-# Default installs to /usr/local/
-./b2 install
-```
-
-### Building Memgraph
-
-clang is *required* to be findable by cmake, i.e. it should be on PATH.
-cmake isn't required to be on the path, since you run it manually, so can use
-the full path to executable in order to run it. Obviously, it is convenient to
-put cmake also on PATH.
-
-Building is done as explained in [Quick Start](quick-start.md), but each
-`make` invocation needs to be prepended with:
-
-`LD_RUN_PATH=<gcc-dir>/lib64 make ...`
-
-### RPM
-
-Name format: `memgraph-<version>-<pkg-version>.<arch>.rpm`

docs/dev/workflow.md

@@ -1,177 +0,0 @@
-# Memgraph Workflow
-
-This chapter describes the usual workflow for working on Memgraph.
-
-## Git
-
-Memgraph uses [git](https://git-scm.com/) for source version control. If you
-obtained the source, you probably already have it installed. Before you can
-track new changes, you need to setup some basic information.
-
-First, tell git your name:
-
-    git config --global user.name "FirstName LastName"
-
-Then, set your Memgraph email:
-
-    git config --global user.email "my.email@memgraph.com"
-
-Finally, make git aware of your favourite editor:
-
-    git config --global core.editor "vim"
-
-## Phabricator
-
-All of the code in Memgraph needs to go through code review before it can be
-accepted in the codebase. This is done through
-[Phabricator](https://phacility.com/phabricator/). The command line tool for
-interfacing with Phabricator is
-[arcanist](https://phacility.com/phabricator/arcanist/). You should already
-have it installed if you followed the steps in [Quick Start](quick-start.md).
-
-The only required setup is to go in the root of Memgraph's project and run:
-
-    arc install-certificate
-
-## Working on Your Feature Branch
-
-Git has a concept of source code *branches*. The `master` branch contains all
-of the changes which were reviewed and accepted in Memgraph's code base. The
-`master` branch is selected by default.
-
-### Creating a Branch
-
-When working on a new feature or fixing a bug, you should create a new branch
-out of the `master` branch. For example, let's say you are adding static type
-checking to the query language compiler. You would create a branch called
-`mg_query_static_typing` with the following command:
-
-    git branch mg_query_static_typing
-
-To switch to that branch, type:
-
-    git checkout mg_query_static_typing
-
-Since doing these two steps will happen often, you can use a shortcut command:
-
-    git checkout -b mg_query_static_typing
-
-Note that a branch is created from the currently selected branch. So, if you
-wish to create another branch from `master` you need to switch to `master`
-first.
-
-The usual convention for naming your branches is `mg_<feature_name>`, you may
-switch underscores ('\_') for hyphens ('-').
-
-Do take care not to mix the case of your branch names! Certain operating
-systems (like Windows) don't distinguish the casing in git branches. This may
-cause hard to track down issues when trying to switch branches. Therefore, you
-should always name your branches with lowercase letters.
-
-### Making and Committing Changes
-
-When you have a branch for your new addition, you can now actually start
-implementing it. After some amount of time, you may have created new files,
-modified others and maybe even deleted unused files. You need to tell git to
-track those changes. This is accomplished with `git add` and `git rm`
-commands.
-
-    git add path-to-new-file path-to-modified-file
-    git rm path-to-deleted-file
-
-To check that everything is correctly tracked, you may use the `git status`
-command. It will also print the name of the currently selected branch.
-
-If everything seems OK, you should commit these changes to git.
-
-    git commit
-
-You will be presented with an editor where you need to type the commit
-message. Writing a good commit message is an art in itself. You should take a
-look at the links below. We try to follow these conventions as much as
-possible.
-
-  * [How to Write a Git Commit Message](http://chris.beams.io/posts/git-commit/)
-  * [A Note About Git Commit Messages](http://tbaggery.com/2008/04/19/a-note-about-git-commit-messages.html)
-  * [stopwritingramblingcommitmessages](http://stopwritingramblingcommitmessages.com/)
-
-### Sending Changes on a Review
-
-After finishing your work on your feature branch, you will want to send it on
-code review. This is done through Arcanist. To do that, run the following
-command:
-
-    arc diff
-
-You will, once again, be presented with an editor where you need to describe
-your whole work. `arc` will by default fill that description with your commit
-messages. The title and summary of your work should also follow the
-conventions of git messages as described above. If you followed the
-guidelines, the message filled by `arc` should be fine.
-
-In addition to the message, you need to fill the `Reviewers:` line with
-usernames of people who should do the code review.
-
-You changes will be visible on Phabricator as a so called "diff". You can find
-the default view of active diffs
-[here](https://phabricator.memgraph.io/differential/)
-
-### Updating Changes Based on Review
-
-When you get comments in the code review, you will want to make additional
-modifications to your work. The same workflow as before applies: [Making and
-Committing Changes](#making-and-committing-changes)
-
-After making those changes, send them back on code review:
-
-    arc diff
-
-
-### Updating From New Master
-
-Let's say that, while you were working, someone else added some new features
-to the codebase that you would like to use in your current work. To obtain
-those changes you should update your `master` branch:
-
-    git checkout master
-    git pull origin master
-
-Now, these changes are on `master`, but you want them in your local branch. To
-do that, use `git rebase`:
-
-    git checkout mg_query_static_typing
-    git rebase master
-
-During `git rebase`, you may get reports that some files have conflicting
-changes. If you need help resolving them, don't be afraid to ask around! After
-you've resolved them, mark them as done with `git add` command. You may
-then continue with `git rebase --continue`.
-
-After the `git rebase` is done, you will now have new changes from `master` on
-your feature branch as if you just created and started working on that branch.
-You may continue with the usual workflow of [Making and Committing
-Changes](#making-and-committing-changes) and [Sending Changes on a
-Review](#sending-changes-on-a-review).
-
-### Sending Your Changes on Master Branch
-
-When your changes pass the code review, you are ready to integrate them in the
-`master` branch. To do that, run the following command:
-
-    arc land
-
-Arcanist will take care of obtaining the latest changes from `master` and
-merging your changes on top. If the `land` was successful, Arcanist will
-delete your local branch and you will be back on `master`. Continuing from the
-examples above, the deleted branch would be `mg_query_static_typing`.
-
-This marks the completion of your changes, and you are ready to work on
-something else.
-
-### Note For People Familiar With Git
-
-Since Arcanist takes care of merging your git commits and pushing them on
-`master`, you should *never* have to call `git merge` and `git push`. If you
-find yourself typing those commands, check that you are doing the right thing.
-The most common mistake is to use `git merge` instead of `git rebase` for the
-case described in [Updating From New Master](#updating-from-new-master).

docs/doxygen/README.md

@@ -1,7 +1,6 @@
 # Memgraph Code Documentation
 
-IMPORTANT: auto-generated (run doxygen Doxyfile in the project root)
+IMPORTANT: Auto-generated (run doxygen Doxyfile in the project root).
 
-* HTML - just open docs/doxygen/html/index.html
-
-* Latex - run make inside docs/doxygen/latex
+* HTML - Open docs/doxygen/html/index.html.
+* Latex - Run make inside docs/doxygen/latex.

docs/feature_spec/distributed.md

@@ -1,78 +0,0 @@
-# Distributed Memgraph specs
-This document describes reasnonings behind Memgraphs distributed concepts.
-
-## Distributed state machine
-Memgraphs distributed mode introduces two states of the cluster, recovering and
-working. The change between states shouldn't happen often, but when it happens
-it can take a while to make a transition from one to another.
-
-### Recovering
-This state is the default state for Memgraph when the cluster starts with
-recovery flags. If the recovery finishes successfully, the state changes to
-working. If recovery fails, the user will be presented with a message that
-explains what happened and what are the next steps.
-
-Another way to enter this state is failure. If the cluster encounters a failure,
-the master will enter the Recovering mode. This time, it will wait for all
-workers to respond with a message saying they are alive and well, and making
-sure they all have consistent state.
-
-### Working
-This state should be the default state of Memgraph most of the time. When in
-this state, Memgraph accepts connections from Bolt clients and allows query
-execution.
-
-If distributed execution fails for a transaction, that transaction, and all
-other active transactions will be aborted and the cluster will enter the
-Recovering state.
-
-## Durability
-One of the important concepts in distributed Memgraph is durability.
-
-### Cluster configuration
-When running Memgraph in distributed mode, the master will store cluster
-metadata in a persistent store. If fore some reason the cluster shuts down,
-recovering Memgraph from durability files shouldn't require any additional
-flags.
-
-### Database ID
-Each new and clean run of Memgraph should generate a new globally unique
-database id.  This id will associate all files that have persisted with this
-run. Adding the database id to snapshots, write-ahead logs and cluster metadata
-files ties them a specific Memgraph run, and it makes recovery easier to reason
-about.
-
-When recovering, the cluster won't generate a new id, but will reuse the one
-from the snapshot/wal that it was able to recover from.
-
-### Durability files
-Memgraph uses snapshots and write-ahead logs for durability.
-
-When Memgraph recovers it has to make sure all machines in the cluster recover
-to the same recovery point. This is done by finding a common snapshot and
-finding common transactions in per-machine available write-ahead logs.
-
-Since we can not be sure that each machine persisted durability files, we need
-to be able to negotiate a common recovery point in the cluster. Possible
-durability file failures could require to start the cluster from scratch,
-purging everything from storage and recovering from existing durability files.
-
-We need to ensure that we keep wal files containing information about
-transactions between all existing snapshots. This will provide better durability
-in the case of a random machine durability file failure, where the cluster can
-find a common recovery point that all machines in the cluster have.
-
-Also, we should suggest and make clear docs that anything less than two
-snapshots isn't considered safe for recovery.
-
-### Recovery
-The recovery happens in following steps:
-* Master enables worker registration.
-* Master recovers cluster metadata from the persisted storage.
-* Master waits all required workers to register.
-* Master broadcasts a recovery request to all workers.
-* Workers respond with with a set of possible recovery points.
-* Master finds a common recovery point for the whole cluster.
-* Master broadcasts a recovery request with the common recovery point.
-* Master waits for the cluster to recover.
-* After a successful cluster recovery, master can enter Working state.

docs/feature_spec/dynamic_graph_partitioning.md

@@ -1,75 +0,0 @@
-# Dynamic Graph Partitioning (abbr. DGP)
-
-## Implementation
-
-Take a look under `dev/memgraph/distributed/dynamic_graph_partitioning.md`.
-
-### Implemented parameters
-
---dynamic-graph-partitioner-enabled (If the dynamic graph partitioner should be
-  enabled.) type: bool default: false (start time)
---dgp-improvement-threshold (How much better should specific node score be
-  to consider a migration to another worker. This represents the minimal
-  difference between new score that the vertex will have when migrated
-  and the old one such that it's migrated.) type: int32 default: 10
-  (start time)
---dgp-max-batch-size (Maximal amount of vertices which should be migrated
-  in one dynamic graph partitioner step.) type: int32 default: 2000
-  (start time)
-
-## Planning
-
-### Design decisions
-
-* Each partitioning session has to be a new transaction.
-* When and how does an instance perform the moves?
-  * Periodically.
-  * Token sharing (round robin, exactly one instance at a time has an
-    opportunity to perform the moves).
-* On server-side serialization error (when DGP receives an error).
-  -> Quit partitioning and wait for the next turn.
-* On client-side serialization error (when end client receives an error).
-  -> The client should never receive an error because of any
-     internal operation.
-  -> For the first implementation, it's good enough to wait until data becomes
-     available again.
-  -> It would be nice to achieve that DGP has lower priority than end client
-     operations.
-
-### End-user parameters
-
-* --dynamic-graph-partitioner-enabled (execution time)
-* --dgp-improvement-threshold (execution time)
-* --dgp-max-batch-size (execution time)
-* --dgp-min-batch-size (execution time)
-  -> Minimum number of nodes that will be moved in each step.
-* --dgp-fitness-threshold (execution time)
-  -> Do not perform moves if partitioning is good enough.
-* --dgp-delta-turn-time (execution time)
-  -> Time between each turn.
-* --dgp-delta-step-time (execution time)
-  -> Time between each step.
-* --dgp-step-time (execution time)
-  -> Time limit per each step.
-
-### Testing
-
-The implementation has to provide good enough results in terms of:
-  * How good the partitioning is (numeric value), aka goodness.
-  * Workload execution time.
-  * Stress test correctness.
-
-Test cases:
-  * N not connected subgraphs
-    -> shuffle nodes to N instances
-    -> run partitioning
-    -> test perfect partitioning.
-  * N connected subgraph
-    -> shuffle nodes to N instance
-    -> run partitioning
-    -> test partitioning.
-  * Take realistic workload (Long Running, LDBC1, LDBC2, Card Fraud, BFS, WSP)
-    -> measure exec time
-    -> run partitioning
-    -> test partitioning
-    -> measure exec time (during and after partitioning).

docs/feature_spec/high_availability.md

@@ -1,275 +0,0 @@
-# High Availability (abbr. HA)
-
-## High Level Context
-
-High availability is a characteristic of a system which aims to ensure a
-certain level of operational performance for a higher-than-normal period.
-Although there are multiple ways to design highly available systems, Memgraph
-strives to achieve HA by elimination of single points of failure. In essence,
-this implies adding redundancy to the system so that a failure of a component
-does not imply the failure of the entire system. To ensure this, HA Memgraph
-implements the [Raft consensus algorithm](https://raft.github.io/).
-
-Correct implementation of the algorithm guarantees that the cluster will be
-fully functional (available) as long as any strong majority of the servers are
-operational and can communicate with each other and with clients. For example,
-clusters of three or four machines can tolerate the failure of a single server,
-clusters of five and six machines can tolerate the failure of any two servers,
-and so on. Therefore, we strongly recommend a setup of an odd-sized cluster.
-
-### Performance Implications
-
-Internally, Raft achieves high availability by keeping a consistent replicated
-log on each server within the cluster. Therefore, we must successfully replicate
-a transaction on the majority of servers within the cluster before we actually
-commit it and report the result back to the client. This operation represents
-a significant performance hit when compared with single node version of
-Memgraph.
-
-Luckily, the algorithm can be tweaked in a way which allows read-only
-transactions to perform significantly better than those which modify the
-database state. That being said, the performance of read-only operations
-is still not going to be on par with single node Memgraph.
-
-This section will be updated with exact numbers once we integrate HA with
-new storage.
-
-With the old storage, write throughput was almost five times lower than read
-throughput (~30000 reads per second vs ~6000 writes per second).
-
-## User Facing Setup
-
-### How to Setup HA Memgraph Cluster?
-
-First, the user needs to install `memgraph_ha` package on each machine
-in their cluster. HA Memgraph should be available as a Debian package,
-so its installation on each machine should be as simple as:
-
-```plaintext
-dpkg -i /path/to/memgraph_ha_<version>.deb
-```
-
-After successful installation of the `memgraph_ha` package, the user should
-finish its configuration before attempting to start the cluster.
-
-There are two main things that need to be configured on every node in order for
-the cluster to be able to run:
-
-1. The user has to edit the main configuration file and specify the unique node
-   ID to each server in the cluster
-2. The user has to create a file that describes all IP addresses of all servers
-   that will be used in the cluster
-
-The `memgraph_ha` binary loads all main configuration parameters from
-`/etc/memgraph/memgraph_ha.conf`. On each node of the cluster, the user should
-uncomment the `--server-id=0` parameter and change its value to the `server_id`
-of that node.
-
-The last step before starting the server is to create a `coordination`
-configuration file. That file is already present as an example in
-`/etc/memgraph/coordination.json.example` and you have to copy it to
-`/etc/memgraph/coordination.json` and edit it according to your cluster
-configuration. The file contains coordination info consisting of a list of
-`server_id`, `ip_address` and `rpc_port` lists. The assumed contents of the
-`coordination.json` file are:
-
-```plaintext
-[
-  [1, "192.168.0.1", 10000],
-  [2, "192.168.0.2", 10000],
-  [3, "192.168.0.3", 10000]
-]
-```
-Here, each line corresponds to coordination of one server. The first entry is
-that server's ID, the second is its IP address and the third is the RPC port it
-listens to. This port should not be confused with the port used for client
-interaction via the Bolt protocol.
-
-The `ip_address` entered for each `server_id` *must* match the exact IP address
-that belongs to that server and that will be used to communicate to other nodes
-in the cluster. The coordination configuration file *must* be identical on all
-nodes in the cluster.
-
-After the user has set the `server_id` on each node in
-`/etc/memgraph/memgraph_ha.conf` and provided the same
-`/etc/memgraph/coordination.json` file to each node in the cluster, they can
-start the Memgraph HA service by issuing the following command on each node in
-the cluster:
-
-```plaintext
-systemctl start memgraph_ha
-```
-
-### How to Configure Raft Parameters?
-
-All Raft configuration parameters can be controlled by modifying
-`/etc/memgraph/raft.json`.  The assumed contents of the `raft.json` file are:
-
-```plaintext
-{
-  "election_timeout_min": 750,
-  "election_timeout_max": 1000,
-  "heartbeat_interval": 100,
-  "replication_timeout": 20000,
-  "log_size_snapshot_threshold": 50000
-}
-```
-
-The meaning behind each entry is demystified in the following table:
-
-Flag                          | Description
-------------------------------|------------
-`election_timeout_min`        | Lower bound for the randomly sampled reelection timer given in milliseconds
-`election_timeout_max`        | Upper bound for the randomly sampled reelection timer given in milliseconds
-`heartbeat_interval`          | Time interval between consecutive heartbeats given in milliseconds
-`replication_timeout`         | Time interval allowed for data replication given in milliseconds
-`log_size_snapshot_threshold` | Allowed number of entries in Raft log before its compaction
-
-### How to Query HA Memgraph via Proxy?
-
-This chapter describes how to query HA Memgraph using our proxy server.
-Note that this is not intended to be a long-term solution. Instead, we will
-implement a proper Memgraph HA client which is capable of communicating with
-the HA cluster. Once our own client is implemented, it will no longer be
-possible to query HA Memgraph using other clients (such as neo4j client).
-
-The Bolt protocol that is exposed by each Memgraph HA node is an extended
-version of the standard Bolt protocol. In order to be able to communicate with
-the highly available cluster of Memgraph HA nodes, the client must have some
-logic implemented in itself so that it can communicate correctly with all nodes
-in the cluster. To facilitate a faster start with the HA cluster we will build
-the Memgraph HA proxy binary that communicates with all nodes in the HA cluster
-using the extended Bolt protocol and itself exposes a standard Bolt protocol to
-the user. All standard Bolt clients (libraries and custom systems) can
-communicate with the Memgraph HA proxy without any code modifications.
-
-The HA proxy should be deployed on each client machine that is used to
-communicate with the cluster. It can't be deployed on the Memgraph HA nodes!
-
-When using the Memgraph HA proxy, the communication flow is described in the
-following diagram:
-
-```plaintext
-Memgraph HA node 1 -----+
-                        |
-Memgraph HA node 2 -----+ Memgraph HA proxy <---> any standard Bolt client (C, Java, PHP, Python, etc.)
-                        |
-Memgraph HA node 3 -----+
-```
-
-To setup the Memgraph HA proxy the user should install the `memgraph_ha_proxy`
-package.
-
-After its successful installation, the user should enter all endpoints of the
-HA Memgraph cluster servers into the configuration before attempting to start
-the HA Memgraph proxy server.
-
-The HA Memgraph proxy server loads all of its configuration from
-`/etc/memgraph/memgraph_ha_proxy.conf`. Assuming that the cluster is set up
-like in the previous examples, the user should uncomment and enter the following
-value into the `--endpoints` parameter:
-
-```plaintext
---endpoints=192.168.0.1:7687,192.168.0.2:7687,192.168.0.3:7687
-```
-
-Note that the IP addresses used in the example match the individual cluster
-nodes IP addresses, but the ports used are the Bolt server ports exposed by
-each node (currently the default value of `7687`).
-
-The user can now start the proxy by using the following command:
-
-```plaintext
-systemctl start memgraph_ha_proxy
-```
-
-After the proxy has been started, the user can query the HA cluster by
-connecting to the HA Memgraph proxy IP address using their favorite Bolt
-client.
-
-## Integration with Memgraph
-
-The first thing that should be defined is a single instruction within the
-context of Raft (i.e. a single entry in a replicated log).
-These instructions should be completely deterministic when applied
-to the state machine. We have therefore decided that the appropriate level
-of abstraction within Memgraph corresponds to `Delta`s (data structures
-which describe a single change to the Memgraph state, used for durability
-in WAL). Moreover, a single instruction in a replicated log will consist of a
-batch of `Delta`s which correspond to a single transaction that's about
-to be **committed**.
-
-Apart from `Delta`s, there are certain operations within the storage called
-`StorageGlobalOperations` which do not conform to usual transactional workflow
-(e.g. Creating indices).  Since our storage engine implementation guarantees
-that at the moment of their execution no other transactions are active, we can
-safely replicate them as well. In other words, no additional logic needs to be
-implemented because of them.
-
-Therefore, we will introduce a new `RaftDelta` object which can be constructed
-both from storage `Delta` and `StorageGlobalOperation`. Instead of appending
-these to WAL (as we do in single node), we will start to replicate them across
-our cluster. Once we have replicated the corresponding Raft log entry on
-majority of the cluster, we are able to safely commit the transaction or execute
-a global operation. If for any reason the replication fails (leadership change,
-worker failures, etc.) the transaction will be aborted.
-
-In the follower mode, we need to be able to apply `RaftDelta`s we got from
-the leader when the protocol allows us to do so. In that case, we will use the
-same concepts from durability in storage v2, i.e., applying deltas maps
-completely to recovery from WAL in storage v2.
-
-## Test and Benchmark Strategy
-
-We have already implemented some integration and stress tests. These are:
-
-1. leader election -- Tests whether leader election works properly.
-2. basic test -- Tests basic leader election and log replication.
-3. term updates test -- Tests a specific corner case (which used to fail)
-                        regarding term updates.
-4. log compaction test -- Tests whether log compaction works properly.
-5. large log entries -- Tests whether we can successfully replicate relatively
-                        large log entries.
-6. index test -- Tests whether index creation works in HA.
-7. normal operation stress test -- Long running concurrent stress test under
-                                   normal conditions (no failures).
-8. read benchmark -- Measures read throughput in HA.
-9. write benchmark -- Measures write throughput in HA.
-
-At the moment, our main goal is to pass existing tests and have a stable version
-on our stress test. We should also implement a stress test which occasionally
-introduces different types of failures in our cluster (we did this kind of
-testing manually thus far). Passing these tests should convince us that we have
-a "stable enough" version which we can start pushing to our customers.
-
-Additional (proper) testing should probably involve some ideas from
-[here](https://jepsen.io/analyses/dgraph-1-0-2)
-
-## Possible Future Changes/Improvements/Extensions
-
-There are two general directions in which we can alter HA Memgraph. The first
-direction assumes we are going to stick with the Raft protocol. In that case
-there are a few known ways to extend the basic algorithm in order to gain
-better performance or achieve extra functionality. In no particular order,
-these are:
-
-1. Improving read performance using leader leases [Section 6.4 from Raft thesis]
-2. Introducing cluster membership changes [Chapter 4 from Raft thesis]
-3. Introducing a [learner mode](https://etcd.io/docs/v3.3.12/learning/learner/).
-4. Consider different log compaction strategies [Chapter 5 from Raft thesis]
-5. Removing HA proxy and implementing our own HA Memgraph client.
-
-On the other hand, we might decide in the future to base our HA implementation
-on a completely different protocol which might even offer different guarantees.
-In that case we probably need to do a bit more of market research and weigh the
-trade-offs of different solutions.
-[This](https://www.postgresql.org/docs/9.5/different-replication-solutions.html)
-might be a good starting point.
-
-## Reading materials
-
-1. [Raft paper](https://raft.github.io/raft.pdf)
-2. [Raft thesis](https://github.com/ongardie/dissertation) (book.pdf)
-3. [Raft playground](https://raft.github.io/)
-4. [Leader Leases](https://blog.yugabyte.com/low-latency-reads-in-geo-distributed-sql-with-raft-leader-leases/)
-5. [Improving Raft ETH](https://pub.tik.ee.ethz.ch/students/2017-FS/SA-2017-80.pdf)

docs/feature_spec/kafka/opencypher.md

@@ -1,80 +0,0 @@
-# Kafka - openCypher clause
-
-One must be able to specify the following when importing data from Kafka:
-
-* Kafka URI
-* Kafka topic
-* Transform [script](transform.md) URI
-
-
-Minimum required syntax looks like:
-```opencypher
-CREATE STREAM stream_name AS LOAD DATA KAFKA 'URI'
-  WITH TOPIC 'topic'
-  WITH TRANSFORM 'URI';
-```
-
-
-The full openCypher clause for creating a stream is:
-```opencypher
-CREATE STREAM stream_name AS
-  LOAD DATA KAFKA 'URI'
-  WITH TOPIC 'topic'
-  WITH TRANSFORM 'URI'
-  [BATCH_INTERVAL milliseconds]
-  [BATCH_SIZE count]
-```
-The `CREATE STREAM` clause happens in a transaction.
-
-`WITH TOPIC` parameter specifies the Kafka topic from which we'll stream
-data.
-
-`WITH TRANSFORM` parameter should contain a URI of the transform script.
-
-`BATCH_INTERVAL` parameter defines the time interval in milliseconds
-which is the time between two successive stream importing operations.
-
-`BATCH_SIZE` parameter defines the count of Kafka messages that will be
-batched together before import.
-
-If both `BATCH_INTERVAL` and `BATCH_SIZE` parameters are given, the condition
-that is satisfied first will trigger the batched import.
-
-Default value for `BATCH_INTERVAL` is 100 milliseconds, and the default value
-for `BATCH_SIZE` is 10;
-
-The `DROP` clause deletes a stream:
-```opencypher
-DROP STREAM stream_name;
-```
-
-The `SHOW` clause enables you to see all configured streams:
-```opencypher
-SHOW STREAMS;
-```
-
-You can also start/stop streams with the `START` and `STOP` clauses:
-```opencypher
-START STREAM stream_name [LIMIT count BATCHES];
-STOP STREAM stream_name;
-```
-A stream needs to be stopped in order to start it and it needs to be started in
-order to stop it. Starting a started or stopping a stopped stream will not
-affect that stream.
-
-There are also convenience clauses to start and stop all streams:
-```opencypher
-START ALL STREAMS;
-STOP ALL STREAMS;
-```
-
-Before the actual import, you can also test the stream with the `TEST
-STREAM` clause:
-```opencypher
-TEST STREAM stream_name [LIMIT count BATCHES];
-```
-When a stream is tested, data extraction and transformation occurs, but no
-output is inserted in the graph.
-
-A stream needs to be stopped in order to test it. When the batch limit is
-omitted, `TEST STREAM` will run for only one batch by default.

docs/feature_spec/kafka/transform.md

@@ -1,34 +0,0 @@
-# Kafka - data transform
-
-The transform script is a user defined script written in Python.  The script
-should be aware of the data format in the Kafka message.
-
-Each Kafka message is byte length encoded, which means that the first eight
-bytes of each message contain the length of the message.
-
-A sample code for a streaming transform script could look like this:
-
-```python
-def create_vertex(vertex_id):
-  return ("CREATE (:Node {id: $id})", {"id": vertex_id})
-
-
-def create_edge(from_id, to_id):
-  return ("MATCH (n:Node {id: $from_id}), (m:Node {id: $to_id}) "\
-          "CREATE (n)-[:Edge]->(m)", {"from_id": from_id, "to_id": to_id})
-
-
-def stream(batch):
-    result = []
-    for item in batch:
-        message = item.decode('utf-8').strip().split()
-        if len(message) == 1:
-          result.append(create_vertex(message[0])))
-        else:
-          result.append(create_edge(message[0], message[1]))
-    return result
-
-```
-
-The script should output openCypher query strings based on the type of the
-records.

docs/feature_spec/python-query-modules.md

@@ -1,185 +0,0 @@
-# Python 3 Query Modules
-
-## Introduction
-
-Memgraph exposes a C API for writing the so called Query Modules. These
-modules contain definitions of procedures which can be invoked through the
-query language using the `CALL ... YIELD ...` syntax. This mechanism allows
-database users to extend Memgraph with their own algorithms and
-functionalities.
-
-Using a low level language like C can be quite cumbersome for writing modules,
-so it seems natural to add support for a higher level language on top of the
-existing C API.
-
-There are languages written exactly for this purpose of extending C with high
-level constructs, for example Lua and Guile. Instead of those, we have chosen
-Python 3 to be the first high level language we will support. The primary reason
-being that it's very popular, so more people should be able to write modules.
-Another benefit of Python which comes out of its popularity is the large
-ecosystem of libraries, especially graph algorithm related ones like NetworkX.
-Python does have significant performance and implementation downsides compared
-to Lua and Guile, but these are described in more detail later in this
-document.
-
-## Python 3 API Overview
-
-The Python 3 API should be as user friendly as possible as well as look
-Pythonic. This implies that some functions from the C API will not map to the
-exact same functions. The most obvious case for a Pythonic approach is
-registering procedures of a query module. Let's take a look at the C example
-and its transformation to Python.
-
-```c
-static void procedure(const struct mgp_list *args,
-                      const struct mgp_graph *graph, struct mgp_result *result,
-                      struct mgp_memory *memory);
-
-int mgp_init_module(struct mgp_module *module, struct mgp_memory *memory) {
-  struct mgp_proc *proc =
-      mgp_module_add_read_procedure(module, "procedure", procedure);
-  if (!proc) return 1;
-  if (!mgp_proc_add_arg(proc, "required_arg",
-                        mgp_type_nullable(mgp_type_any())))
-    return 1;
-  struct mgp_value *null_value = mgp_value_make_null(memory);
-  if (!mgp_proc_add_opt_arg(proc, "optional_arg",
-                            mgp_type_nullable(mgp_type_any()), null_value)) {
-    mgp_value_destroy(null_value);
-    return 1;
-  }
-  mgp_value_destroy(null_value);
-  if (!mgp_proc_add_result(proc, "result", mgp_type_string())) return 1;
-  if (!mgp_proc_add_result(proc, "args",
-                           mgp_type_list(mgp_type_nullable(mgp_type_any()))))
-    return 1;
-  return 0;
-}
-```
-
-In Python things should be a lot simpler.
-
-```Python
-# mgp.read_proc obtains the procedure name via __name__ attribute of a function.
-@mgp.read_proc(# Arguments passed to multiple mgp_proc_add_arg calls
-               (('required_arg', mgp.Nullable(mgp.Any)), ('optional_arg', mgp.Nullable(mgp.Any), None)),
-               # Result fields passed to multiple mgp_proc_add_result calls
-               (('result', str), ('args', mgp.List(mgp.Nullable(mgp.Any)))))
-def procedure(args, graph, result, memory):
-    pass
-```
-
-Here we have replaced `mgp_module_*` and `mgp_proc_*` C API with a much
-simpler decorator function in Python -- `mgp.read_proc`. The types of
-arguments and result fields can both be our types as well as Python builtin
-types which can map to supported `mgp_value` types. The expected builtin types
-we ought to support are: `bool`, `str`, `int`, `float` and `map`. While the
-rest of the types are provided via our Python API. Optionally, we can add
-convenience support for `object` type which would map to
-`mgp.Nullable(mgp.Any)` and `list` which would map to
-`mgp.List(mgp.Nullable(mgp.Any))`. Also, it makes sense to take a look if we
-can leverage Python's `typing` module here.
-
-Another Pythonic change is to remove `mgp_value` C API from Python altogether.
-This means that the arguments a Python procedure receives are not `mgp_value`
-instances but rather `PyObject` instances. In other words, our implementation
-would immediately marshal `mgp_value` to corresponding type in Python.
-Obviously we would need to provide our own Python types for non-builtin
-things like `mgp.Vertex` (equivalent to `mgp_vertex`) and other.
-
-Continuing from our example above, let's say the procedure was invoked through
-Cypher using the following query.
-
-    MATCH (n) CALL py_module.procedure(42, n) YIELD *;
-
-The Python procedure could then do the following and complete without throwing
-neither the AssertionError nor the ValueError.
-
-```Python
-def procedure(args, graph, result, memory):
-    assert isinstance(args, list)
-    # Unpacking throws ValueError if args does not contain exactly 2 values.
-    required_arg, optional_arg = args
-    assert isintance(required_arg, int)
-    assert isinstance(optional_arg, mgp.Vertex)
-```
-
-The rest of the C API should naturally map to either top level functions or
-class methods as appropriate.
-
-## Loading Python Query Modules
-
-Our current mechanism for loading the modules is to look for `.so` files in
-the directory specified by `--query-modules` flag. This is done when Memgraph
-is started. We can extend this mechanism to look for `.py` files in addition
-to `.so` files in the same directory and import them in the embedded Python
-interpreter. The only issue is embedding the interpreter in Memgraph.  There
-are multiple choices:
-
-  1. Building Memgraph and statically linking to Python.
-  2. Building Memgraph and dynamically linking to Python, and distributing
-     Python with Memgraph's installation.
-  3. Building Memgraph and dynamically linking to Python, but without
-     distributing the Python library.
-  4. Building Memgraph and optionally loading Python library by trying to
-     `dlopen` it.
-
-The first two options are only viable if the Python license allows, and this
-will need further investigation.
-
-The third option adds Python as an installation dependency for Memgraph, and
-without it Memgraph will not run. This is problematic for users which cannot
-or do not want to install Python 3.
-
-The fourth option avoids all of the issues present in the first 3 options, but
-comes at a higher implementation cost. We would need to try to `dlopen` the
-Python library and setup function pointers. If we succeed we would import
-`.py` files from the `--query-modules` directory. On the other hand, if the
-user does not have Python, `dlopen` would fail and Memgraph would run without
-Python support.
-
-After live discussion, we've decided to go with option 3. This way we don't
-have to worry about mismatching Python versions we support and what the users
-expect. Also, we should target Python 3.5 as that should be common between
-Debian and CentOS for which we ship installation packages.
-
-## Performance and Implementation Problems
-
-As previously mentioned, embedding Python introduces usability issues compared
-to other embeddable languages.
-
-The first, major issue is Global Interpreter Lock (GIL). Initializing Python
-will start a single global interpreter and running multiple threads will
-require acquiring GIL. In practice, this means that when multiple users run a
-procedure written in Python in parallel the execution will not actually be
-parallel. Python's interpreter will jump between executing one user's
-procedure and the other's. This can be quite an issue for long running
-procedures when multiple users are querying Memgraph. The solution for this
-issue is Python's API for sub-interpreters. Unfortunately, the support for
-them is rather poor and the API contains a lot of critical bugs when we tried
-to use them. For the time being, we will have to accept GIL and its downsides.
-Perhaps in the future we will gain more knowledge on how we could reduce the
-acquire rate of GIL or the sub-interpreter API will get improved.
-
-Another major issue is memory allocation. Python's C API does not have support
-for setting up a temporary allocator during execution of a single function.
-It only has support for setting up a global heap allocator. This obviously
-impacts our control of memory during a query procedure invocation. Besides
-potential performance penalty, a procedure could allocate much more memory
-than we would actually allow for execution of a single query. This means that
-options controlling the memory limit during query execution are useless. On
-the bright side, Python does use block style allocators and reference
-counting, so the performance penalty and global memory usage should not be
-that terrible.
-
-The final issue that isn't as major as the ones above is the global state of
-the interpreter. In practice this means that any registered procedure and
-imported module has access to any other procedure and module. This may pollute
-the namespace for other users, but it should not be much of a problem because
-Python always has things under a module scope. The other, slightly bigger
-downside is that a malicious user could use this knowledge to modify other
-modules and procedures. This seems like a major issue, but if we take the
-bigger picture into consideration, we already have a security issue in general
-by invoking `dlopen` on `.so` and potentially running arbitrary code. This was
-the trade off we chose to allow users to extend Memgraph. It's up to the users
-to write sane extensions and protect their servers from access.

docs/feature_spec/tensorflow_op/technicalities.md

@@ -1,61 +0,0 @@
-# Tensorflow Op - Technicalities
-
-The final result should be a shared object (".so") file that can be
-dynamically loaded by the Tensorflow runtime in order to directly
-access the bolt client.
-
-## About Tensorflow
-
-Tensorflow is usually used with Python such that the Python code is used
-to define a directed acyclic computation graph. Basically no computation
-is done in Python. Instead, values from Python are copied into the graph
-structure as constants to be used by other Ops. The directed acyclic graph
-naturally ends up with two sets of border nodes, one for inputs, one for
-outputs. These are sometimes called "feeds".
-
-Following the Python definition of the graph, during training, the entire
-data processing graph/pipeline is called from Python as a single expression.
-This leads to lazy evaluation since the called result has already been
-defined for a while.
-
-Tensorflow internally works with tensors, i.e. n-dimensional arrays. That
-means all of its inputs need to be matrices as well as its outputs. While
-it is possible to feed data directly from Python's numpy matrices straight
-into Tensorflow, this is less desirable than using the Tensorflow data API
-(which defines data input and processing as a Tensorflow graph) because:
-
-  1. The data API is written in C++ and entirely avoids Python and as such
-  is faster
-  2. The data API, unlike Python is available in "Tensorflow serving". The
-  default way to serve Tensorflow models in production.
-
-Once the entire input pipeline is defined via the tf.data API, its input
-is basically a list of node IDs the model is supposed to work with. The
-model, through the data API knows how to connect to Memgraph and execute
-openCypher queries in order to get the remaining data it needs.
-(For example features of neighbouring nodes.)
-
-## The Interface
-
-I think it's best you read the official guide...  
-<https://www.tensorflow.org/extend/adding_an_op>  
-And especially the addition that specifies how data ops are special  
-<https://www.tensorflow.org/extend/new_data_formats>  
-
-## Compiling the TF Op
-
-There are two options for compiling a custom op.  
-One of them involves pulling the TF source, adding your code to it and
-compiling via bazel.  
-This is probably awkward to do for us and would
-significantly slow down compilation.  
-
-The other method involves installing Tensorflow as a Python package and
-pulling the required headers from for example:  
-`/usr/local/lib/python3.6/site-packages/tensorflow/include`  
-We can then compile our Op with our regular build system.
-
-This is practical since we can copy the required headers to our repo.
-If necessary, we can have several versions of the headers to build several
-versions of our Op for every TF version which we want to support.
-(But this is unlikely to be required as the API should be stable).

docs/feature_spec/tensorflow_op/usage_example.md

@@ -1,142 +0,0 @@
-# Example for Using the Bolt Client Tensorflow Op
-
-## Dynamic Loading
-
-``` python3
-import tensorflow as tf
-
-mg_ops = tf.load_op_library('/usr/bin/memgraph/tensorflow_ops.so')
-```
-
-## Basic Usage
-
-``` python3
-dataset = mg_ops.OpenCypherDataset(
-            # This is probably unfortunate as the username and password
-            # get hardcoded into the graph, but for the simple case it's fine
-            "hostname:7687", auth=("user", "pass"),
-
-            # Our query
-            '''
-            MATCH (n:Train) RETURN n.id, n.features
-            ''',
-
-            # Cast return values to these types
-            (tf.string, tf.float32))
-
-# Some Tensorflow data api boilerplate
-iterator = dataset.make_one_shot_iterator()
-next_element = iterator.get_next()
-
-# Up to now we have only defined our computation graph which basically
-# just connects to Memgraph
-# `next_element` is not really data but a handle to a node in the Tensorflow
-# graph, which we can and do evaluate
-# It is a Tensorflow tensor with shape=(None, 2)
-# and dtype=(tf.string, tf.float)
-# shape `None` means the shape of the tensor is unknown at definition time
-# and is dynamic and will only be known once the tensor has been evaluated
-
-with tf.Session() as sess:
-    node_ids = sess.run(next_element)
-    # `node_ids` contains IDs and features of all the nodes 
-    # in the graph with the label "Train"
-    # It is a numpy.ndarray with a shape ($n_matching_nodes, 2)
-```
-
-## Memgraph Client as a Generic Tensorflow Op
-
-Other than the Tensorflow Data Op, we'll want to support a generic Tensorflow
-Op which can be put anywhere in the Tensorflow computation Graph. It takes in
-an arbitrary tensor and produces a tensor. This would be used in the GraphSage
-algorithm to fetch the lowest level features into Tensorflow
-
-```python3
-requested_ids = np.array([1, 2, 3])
-ids_placeholder = tf.placeholder(tf.int32)
-
-model = mg_ops.OpenCypher()
-    "hostname:7687", auth=("user", "pass"),
-    """
-    UNWIND $node_ids as nid
-    MATCH (n:Train {id: nid})
-    RETURN n.features
-    """,
-
-    # What to call the input tensor as an openCypher parameter
-    parameter_name="node_ids",
-
-    # Type of our resulting tensor
-    dtype=(tf.float32)
-)
-
-features = model(ids_placeholder)
-
-with tf.Session() as sess:
-    result = sess.run(features,
-                    feed_dict={ids_placeholder: requested_ids})
-```
-
-This is probably easier to implement than the Data Op, so it might be a good
-idea to start with.
-
-## Production Usage
-
-During training, in the GraphSage algorithm at least, Memgraph is at the
-beginning and at the end of the Tensorflow computation graph.  
-At the beginning, the Data Op provides the node IDs which are fed into the
-generic Tensorflow Op to find their neighbours and their neighbours and
-their features.
-
-Production usage differs in that we don't use the Data Op. The Data Op is
-effectively cut off and the initial input is fed by Tensorflow serving,
-with the data found in the request.
-
-For example a JSON request to classify a node might look like:
-
-`POST http://host:port/v1/models/GraphSage/versions/v1:classify`
-
-With the contents:
-
-```json
-{
-    "examples": [
-        {"node_id": 1},
-        {"node_id": 2}
-    ],
-}
-```
-
-Every element of the "examples" list is an example to be computed. Each is
-represented by a dict with keys matching names of feeds in the Tensorflow
-graph and values being the values we want fed in for each example
-
-The REST API then replies in kind with the classification result in JSON
-
-Note about adding our custom Op to Tensorflow serving.  
-Our Ops .so can be added into the Bazel build to link with Tensorflow serving
-or it can be dynamically loaded by starting Tensorflow serving with a flag
-`--custom_op_paths`
-
-## Considerations
-
-There might be issues here that the url to connect to Memgraph is
-hardcoded into the op and would thus be wrong when moved to production,
-requiring some type of a hack to make work. We probably want to solve
-this by having the client op take in another tf.Variable as an input
-which would contain a connection url and username/password.  
-We have to research whether this makes it easy enough to move to
-production, as the connection string variable is still a part of the
-graph, but maybe easier to replace.  
-
-It is probably the best idea to utilize openCypher parameters to make
-our queries flexible. The exact API as to how to declare the parameters
-in Python is open to discussion.
-
-The Data Op might not even be necessary to implement as it is not
-key for production use. It can be replaced in training mode with
-feed dicts and either
-
- 1. Getting the initial list of nodes via a Python Bolt client
- 2. Creating a separate Tensorflow computation graph that gets all the
- relevant node IDs into Python

docs/presentation/latex-template/README.md

@@ -1,22 +0,0 @@
-# Memgraph LaTeX Beamer Template
-
-This folder contains all of the needed files for creating a presentation with
-Memgraph styling. You should use this style for any public presentations.
-
-Feel free to improve it according to style guidelines and raise issues if you
-find any.
-
-## Usage
-
-Copy the contents of this folder (excluding this README file) to where you
-want to write your own presentation. After copying, you can start editing the
-`template.tex` with your content.
-
-To compile the presentation to a PDF, run `latexmk -pdf -xelatex`. Some
-directives require XeLaTeX, so you need to pass `-xelatex` as the final option
-of `latexmk`. You may also need to install some packages if the compilation
-complains about missing packages.
-
-To clean up the generated files, use `latexmk -C`. This will also delete the
-generated PDF. If you wish to remove generated files except the PDF, use
-`latexmk -c`.

docs/presentation/latex-template/mg-beamer.cls

@@ -1,82 +0,0 @@
-\NeedsTeXFormat{LaTeX2e}
-\ProvidesClass{mg-beamer}[2018/03/26 Memgraph Beamer]
-
-\DeclareOption*{\PassOptionsToClass{\CurrentOption}{beamer}}
-
-\ProcessOptions \relax
-
-\LoadClass{beamer}
-
-\usetheme{Pittsburgh}
-
-% Memgraph color palette
-\definecolor{mg-purple}{HTML}{720096}
-\definecolor{mg-red}{HTML}{DD2222}
-\definecolor{mg-orange}{HTML}{FB6E00}
-\definecolor{mg-yellow}{HTML}{FFC500}
-\definecolor{mg-gray}{HTML}{857F87}
-\definecolor{mg-black}{HTML}{231F20}
-
-\RequirePackage{fontspec}
-% Title fonts
-\setbeamerfont{frametitle}{family={\fontspec[Path = ./mg-style/fonts/]{EncodeSansSemiCondensed-Regular.ttf}}}
-\setbeamerfont{title}{family={\fontspec[Path = ./mg-style/fonts/]{EncodeSansSemiCondensed-Regular.ttf}}}
-% Body font
-\RequirePackage[sfdefault,light]{roboto}
-% Roboto is pretty bad for monospace font. We will find a replacement.
-% \setmonofont{RobotoMono-Regular.ttf}[Path = ./mg-style/fonts/]
-
-% Title slide styles
-% \setbeamerfont{frametitle}{size=\huge}
-% \setbeamerfont{title}{size=\huge}
-% \setbeamerfont{date}{size=\tiny}
-
-% Other typography styles
-\setbeamertemplate{frametitle}[default][center]
-\setbeamercolor{frametitle}{fg=mg-black}
-\setbeamercolor{title}{fg=mg-black}
-\setbeamercolor{section in toc}{fg=mg-black}
-\setbeamercolor{local structure}{fg=mg-orange}
-\setbeamercolor{alert text}{fg=mg-red}
-
-% Commands
-\newcommand{\mgalert}[1]{{\usebeamercolor[fg]{alert text}#1}}
-\newcommand{\titleframe}{\frame[plain]{\titlepage}}
-\newcommand{\mgtexttt}[1]{{\textcolor{mg-gray}{\texttt{#1}}}}
-
-% Title slide background
-\RequirePackage{tikz,calc}
-% Use title-slide-169 if aspect ration is 16:9
-\pgfdeclareimage[interpolate=true,width=\paperwidth,height=\paperheight]{logo}{mg-style/title-slide-169}
-\setbeamertemplate{background}{
-  \begin{tikzpicture}
-  \useasboundingbox (0,0) rectangle (\the\paperwidth,\the\paperheight);
-    \pgftext[at=\pgfpoint{0}{0},left,base]{\pgfuseimage{logo}};
-  \ifnum\thepage>1\relax
-  \useasboundingbox (0,0) rectangle (\the\paperwidth,\the\paperheight);
-      \fill[white, opacity=1](0,\the\paperheight)--(\the\paperwidth,\the\paperheight)--(\the\paperwidth,0)--(0,0)--(0,\the\paperheight);
-  \fi
-  \end{tikzpicture}
-}
-
-% Footline content
-\setbeamertemplate{navigation symbols}{}%remove navigation symbols
- \setbeamertemplate{footline}{
-  \begin{beamercolorbox}[ht=1.6cm,wd=\paperwidth]{footlinecolor}
-    \vspace{0.1cm}
-    \hfill
-    \begin{minipage}[c]{3cm}
-      \begin{center}
-       \includegraphics[height=0.8cm]{mg-style/memgraph-logo.png}
-      \end{center}
-    \end{minipage}
-    \begin{minipage}[c]{7cm}
-         \insertshorttitle\ --- \insertsection
-    \end{minipage}
-    \begin{minipage}[c]{2cm}
-        \tiny{\insertframenumber{} of \inserttotalframenumber}
-    \end{minipage}
-   \end{beamercolorbox}
-}
-
-\endinput

docs/presentation/latex-template/template.tex

@@ -1,40 +0,0 @@
-% Set 16:9 aspect ratio
-\documentclass[aspectratio=169]{mg-beamer}
-% Default directive sets the regular 4:3 aspect ratio
-% \documentclass{mg-beamer}
-\mode<presentation>
-
-% requires xelatex
-\usepackage{ccicons}
-
-\title{Insert Presentation Title}
-\titlegraphic{\ccbyncnd}
-\author{Insert Name}
-
-% Institute doesn't look good in our current styling class.
-% \institute[Memgraph Ltd.]{\pgfimage[height=1.5cm]{mg-logo.png}}
-
-% Date is autogenerated on compilation, so no need to set it explicitly,
-% unless you wish to override it with a different date.
-% \date{March 23, 2018}
-
-\begin{document}
-
-\titleframe
-
-\section{Intro}
-
-\begin{frame}{Contents}
-  \tableofcontents
-\end{frame}
-
-\begin{frame}{Memgraph Markup Test}
-  \begin{itemize}
-    \item \mgtexttt{Prefer \\mgtexttt for monospace}
-    \item Replace this slide with your own
-    \item Add even more slides in different sections
-    \item Make sure you spellcheck your presentation
-  \end{itemize}
-\end{frame}
-
-\end{document}

environment/README.md

@@ -0,0 +1,4 @@
+# Memgraph Build and Run Environments
+
+Please continue in
+[Notion](https://www.notion.so/memgraph/Tools-05e0baafb78a49b386e0063b4833d23d).

environment/os/.gitignore

@@ -0,0 +1,3 @@
+*.deb
+*.rpm
+*.tar.gz

environment/os/centos-7.sh

@@ -0,0 +1,134 @@
+#!/bin/bash
+
+set -Eeuo pipefail
+
+DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
+source "$DIR/../util.sh"
+
+TOOLCHAIN_BUILD_DEPS=(
+    coreutils 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-devel libbabeltrace-devel xz-devel python3-devel # gdb
+    texinfo # gdb
+    libcurl-devel # cmake
+    readline-devel # cmake and llvm
+    libffi-devel libxml2-devel perl-Digest-MD5 # llvm
+    libedit-devel pcre-devel automake bison # swig
+)
+
+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 python3 # for gdb
+    readline # for cmake and llvm
+    libffi libxml2 # for llvm
+)
+
+MEMGRAPH_BUILD_DEPS=(
+    git # source code control
+    make pkgconfig # build system
+    curl 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 python-virtualenv python3-pip nmap-ncat # for qa, macro_benchmark and stress tests
+    #
+    # IMPORTANT: python3-yaml does NOT exist on CentOS
+    # Install it using `pip3 install PyYAML`
+    #
+    PyYAML # Package name here does not correspond to the yum package!
+    libcurl-devel # mg-requests
+    sbcl # for custom Lisp C++ preprocessing
+    rpm-build rpmlint # for RPM package building
+    doxygen graphviz # source documentation generators
+    which mono-complete dotnet-sdk-3.1 golang nodejs zip unzip java-11-openjdk-devel # for driver tests
+    autoconf # for jemalloc code generation
+)
+
+list() {
+    echo "$1"
+}
+
+check() {
+    local missing=""
+    for pkg in $1; do
+        if [ "$pkg" == git ]; then
+            if ! which "git" >/dev/null; then
+                missing="git $missing"
+            fi
+            continue
+        fi
+        if [ "$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
+    yum install -y epel-release
+    yum update -y
+    yum install -y wget git python3 python3-pip
+    for pkg in $1; do
+        if [ "$pkg" == libipt ]; then
+            if ! yum list installed libipt >/dev/null 2>/dev/null; then
+                yum 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 [ "$pkg" == libipt-devel ]; then
+            if ! yum list installed libipt-devel >/dev/null 2>/dev/null; then
+                yum install -y http://repo.okay.com.mx/centos/8/x86_64/release/libipt-devel-1.6.1-8.el8.x86_64.rpm
+            fi
+            continue
+        fi
+        if [ "$pkg" == dotnet-sdk-3.1 ]; then
+            if ! yum list installed dotnet-sdk-3.1 >/dev/null 2>/dev/null; then
+                wget -nv https://packages.microsoft.com/config/centos/7/packages-microsoft-prod.rpm -O packages-microsoft-prod.rpm
+                rpm -Uvh https://packages.microsoft.com/config/centos/7/packages-microsoft-prod.rpm
+                yum update -y
+                yum 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
+        yum install -y "$pkg"
+    done
+}
+
+deps=$2"[*]"
+"$1" "${!deps}"

environment/os/centos-8.sh

@@ -0,0 +1,152 @@
+#!/bin/bash
+
+set -Eeuo pipefail
+
+DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
+source "$DIR/../util.sh"
+
+TOOLCHAIN_BUILD_DEPS=(
+    coreutils 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-devel libbabeltrace-devel xz-devel python36-devel texinfo # for gdb
+    libcurl-devel # for cmake
+    readline-devel # for cmake and llvm
+    libffi-devel libxml2-devel # for llvm
+    libedit-devel pcre-devel automake bison # for swig
+)
+
+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
+)
+
+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
+)
+
+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 [ "$pkg" == libipt-devel ]; then
+            if ! yum list installed libipt-devel >/dev/null 2>/dev/null; then
+                dnf install -y http://repo.okay.com.mx/centos/8/x86_64/release/libipt-devel-1.6.1-8.el8.x86_64.rpm
+            fi
+            continue
+        fi
+        # Install GDB dependencies not present in the standard repos.
+        # https://bugs.centos.org/view.php?id=17068
+        # https://centos.pkgs.org
+	    # Since 2020, there is Babeltrace2 (https://babeltrace.org). Not used
+        # within GDB yet (an assumption).
+        if [ "$pkg" == libbabeltrace-devel ]; then
+            if ! dnf list installed libbabeltrace-devel >/dev/null 2>/dev/null; then
+                dnf install -y http://mirror.centos.org/centos/8/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/debian-10.sh

@@ -0,0 +1,93 @@
+#!/bin/bash
+
+set -Eeuo pipefail
+
+DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
+source "$DIR/../util.sh"
+
+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
+    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
+    libreadline7 # for cmake and llvm
+    libffi6 libxml2 # for llvm
+)
+
+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 virtualenv 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-3.1 golang nodejs npm
+    autoconf # for jemalloc code generation
+)
+
+list() {
+    echo "$1"
+}
+
+check() {
+    check_all_dpkg "$1"
+}
+
+install() {
+    cat >/etc/apt/sources.list <<EOF
+deb http://deb.debian.org/debian/ buster main non-free contrib
+deb-src http://deb.debian.org/debian/ buster main non-free contrib
+deb http://deb.debian.org/debian/ buster-updates main contrib non-free
+deb-src http://deb.debian.org/debian/ buster-updates main contrib non-free
+deb http://security.debian.org/debian-security buster/updates main contrib non-free
+deb-src http://security.debian.org/debian-security buster/updates main contrib non-free
+EOF
+    cd "$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-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
+}
+
+deps=$2"[*]"
+"$1" "${!deps}"

environment/os/debian-9.sh

@@ -0,0 +1,62 @@
+#!/bin/bash
+
+set -Eeuo pipefail
+
+DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
+source "$DIR/../util.sh"
+
+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 libbabeltrace-ctf-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
+    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 libipt1 libbabeltrace1 libbabeltrace-ctf1 liblzma5 python3 # for gdb
+    libcurl3 # for cmake
+    libreadline7 # for cmake and llvm
+    libffi6 libxml2 # for llvm
+)
+
+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
+    python3 python-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 nodejs zip unzip default-jdk-headless # for driver tests
+    autoconf # for jemalloc code generation
+)
+
+list() {
+    echo "$1"
+}
+
+check() {
+    check_all_dpkg "$1"
+}
+
+install() {
+    install_all_apt "$1"
+}
+
+deps=$2"[*]"
+"$1" "${!deps}"

environment/os/template.sh

@@ -0,0 +1,36 @@
+#!/bin/bash
+
+set -Eeuo pipefail
+
+DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
+source "$DIR/../util.sh"
+
+TOOLCHAIN_BUILD_DEPS=(
+    pkg
+)
+
+TOOLCHAIN_RUN_DEPS=(
+    pkg
+)
+
+MEMGRAPH_BUILD_DEPS=(
+    pkg
+)
+
+list() {
+    echo "$1"
+}
+
+check() {
+    echo "TODO: Implement ${FUNCNAME[0]}."
+    exit 1
+}
+
+install() {
+    echo "TODO: Implement ${FUNCNAME[0]}."
+    exit 1
+}
+
+# http://ahmed.amayem.com/bash-indirect-expansion-exploration
+deps=$2"[*]"
+"$1" "${!deps}"

environment/os/ubuntu-18.04.sh

@@ -0,0 +1,63 @@
+#!/bin/bash
+
+set -Eeuo pipefail
+
+DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
+source "$DIR/../util.sh"
+
+TOOLCHAIN_BUILD_DEPS=(
+    coreutils gcc g++ build-essential make # generic build tools
+    wget # archive download
+    gnupg # archive signature verification
+    tar gzip bzip2 xz-utils unzip # archive unpacking
+    zlib1g-dev # zlib library used for all builds
+    libexpat1-dev libipt-dev libbabeltrace-dev liblzma-dev python3-dev # gdb
+    texinfo # gdb
+    libcurl4-openssl-dev # cmake
+    libreadline-dev # cmake and llvm
+    libffi-dev libxml2-dev # llvm
+    libedit-dev libpcre3-dev automake bison # 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 libipt1 libbabeltrace1 liblzma5 python3 # for gdb
+    libcurl4 # for cmake
+    libreadline7 # for cmake and llvm
+    libffi6 libxml2 # for llvm
+)
+
+MEMGRAPH_BUILD_DEPS=(
+    git # source code control
+    make pkg-config # build system
+    curl wget # downloading libs
+    uuid-dev default-jre-headless # required by antlr
+    libreadline-dev # memgraph console
+    libpython3-dev python3-dev # for query modules
+    libssl-dev
+    libseccomp-dev
+    python3 virtualenv python3-virtualenv python3-pip # qa, macro bench and stress tests
+    python3-yaml # the configuration generator
+    libcurl4-openssl-dev # mg-requests
+    sbcl # custom Lisp C++ preprocessing
+    doxygen graphviz # source documentation generators
+    mono-runtime mono-mcs nodejs zip unzip default-jdk-headless # driver tests
+    autoconf # for jemalloc code generation
+)
+
+list() {
+    echo "$1"
+}
+
+check() {
+    check_all_dpkg "$1"
+}
+
+install() {
+    apt install -y $1
+}
+
+deps=$2"[*]"
+"$1" "${!deps}"

environment/os/ubuntu-20.04.sh

@@ -0,0 +1,85 @@
+#!/bin/bash
+
+set -Eeuo pipefail
+
+DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
+source "$DIR/../util.sh"
+
+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
+    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
+)
+
+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-3.1 golang nodejs npm
+    autoconf # for jemalloc 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-3.1 ]; then
+            if ! dpkg -s dotnet-sdk-3.1 2>/dev/null >/dev/null; then
+                wget -nv https://packages.microsoft.com/config/ubuntu/20.04/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-3.1
+            fi
+            continue
+        fi
+        apt install -y "$pkg"
+    done
+}
+
+deps=$2"[*]"
+"$1" "${!deps}"

environment/toolchain/v1.sh

@@ -105,7 +105,8 @@ case "$DISTRO" in
             gnupg2 # used for archive signature verification
             tar gzip bzip2 xz unzip # used for archive unpacking
             zlib-devel # zlib library used for all builds
-            expat-devel libipt-devel libbabeltrace-devel xz-devel python36-devel texinfo # for gdb
+            expat-devel libipt-devel libbabeltrace-devel xz-devel python3-devel texinfo # for gdb
+            libcurl-devel # for cmake
             readline-devel # for cmake and llvm
             libffi-devel libxml2-devel # for llvm
             libedit-devel pcre-devel automake bison # for swig
@@ -114,7 +115,7 @@ case "$DISTRO" in
             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
+            expat libipt libbabeltrace xz-libs python3 # for gdb
             readline # for cmake and llvm
             libffi libxml2 # for llvm
         )
@@ -203,6 +204,7 @@ if [ ! -f llvm-$LLVM_VERSION.src.tar.xz ]; then
     wget https://releases.llvm.org/$LLVM_VERSION/llvm-$LLVM_VERSION.src.tar.xz
     wget https://releases.llvm.org/$LLVM_VERSION/cfe-$LLVM_VERSION.src.tar.xz
     wget https://releases.llvm.org/$LLVM_VERSION/lld-$LLVM_VERSION.src.tar.xz
+    wget https://releases.llvm.org/$LLVM_VERSION/compiler-rt-$LLVM_VERSION.src.tar.xz
     wget https://releases.llvm.org/$LLVM_VERSION/clang-tools-extra-$LLVM_VERSION.src.tar.xz
 fi
 if [ ! -f pahole-gdb-master.zip ]; then
@@ -223,7 +225,7 @@ if [ ! -f gcc-$GCC_VERSION.tar.gz.sig ]; then
     wget https://ftp.gnu.org/gnu/gcc/gcc-$GCC_VERSION/gcc-$GCC_VERSION.tar.gz.sig
 fi
 # list of valid gcc gnupg keys: https://gcc.gnu.org/mirrors.html
-$GPG --keyserver $KEYSERVER --recv-keys 0xC3C45C06
+$GPG --keyserver $KEYSERVER --recv-keys 0xA328C3A2C3C45C06
 $GPG --verify gcc-$GCC_VERSION.tar.gz.sig gcc-$GCC_VERSION.tar.gz
 # verify binutils
 if [ ! -f binutils-$BINUTILS_VERSION.tar.gz.sig ]; then
@@ -245,7 +247,7 @@ if [ ! -f cmake-$CMAKE_VERSION-SHA-256.txt ] || [ ! -f cmake-$CMAKE_VERSION-SHA-
     # we filter out the missing files from the sums here manually.
     cat cmake-$CMAKE_VERSION-SHA-256.txt | grep "cmake-$CMAKE_VERSION.tar.gz" > cmake-$CMAKE_VERSION-SHA-256-filtered.txt
 fi
-$GPG --keyserver $KEYSERVER --recv-keys 0x7BFB4EDA
+$GPG --keyserver $KEYSERVER --recv-keys 0xC6C265324BBEBDC350B513D02D2CEF1034921684
 sha256sum -c cmake-$CMAKE_VERSION-SHA-256-filtered.txt
 $GPG --verify cmake-$CMAKE_VERSION-SHA-256.txt.asc cmake-$CMAKE_VERSION-SHA-256.txt
 # verify llvm, cfe, lld, clang-tools-extra
@@ -253,6 +255,7 @@ if [ ! -f llvm-$LLVM_VERSION.src.tar.xz.sig ]; then
     wget https://releases.llvm.org/$LLVM_VERSION/llvm-$LLVM_VERSION.src.tar.xz.sig
     wget https://releases.llvm.org/$LLVM_VERSION/cfe-$LLVM_VERSION.src.tar.xz.sig
     wget https://releases.llvm.org/$LLVM_VERSION/lld-$LLVM_VERSION.src.tar.xz.sig
+    wget https://releases.llvm.org/$LLVM_VERSION/compiler-rt-$LLVM_VERSION.src.tar.xz.sig
     wget https://releases.llvm.org/$LLVM_VERSION/clang-tools-extra-$LLVM_VERSION.src.tar.xz.sig
 fi
 # list of valid llvm gnupg keys: https://releases.llvm.org/download.html
@@ -260,6 +263,7 @@ $GPG --keyserver $KEYSERVER --recv-keys 0x345AD05D
 $GPG --verify llvm-$LLVM_VERSION.src.tar.xz.sig llvm-$LLVM_VERSION.src.tar.xz
 $GPG --verify cfe-$LLVM_VERSION.src.tar.xz.sig cfe-$LLVM_VERSION.src.tar.xz
 $GPG --verify lld-$LLVM_VERSION.src.tar.xz.sig lld-$LLVM_VERSION.src.tar.xz
+$GPG --verify compiler-rt-$LLVM_VERSION.src.tar.xz.sig compiler-rt-$LLVM_VERSION.src.tar.xz
 $GPG --verify clang-tools-extra-$LLVM_VERSION.src.tar.xz.sig clang-tools-extra-$LLVM_VERSION.src.tar.xz
 popd
 
@@ -500,6 +504,8 @@ if [ ! -f $PREFIX/bin/clang ]; then
     mv cfe-$LLVM_VERSION.src llvm-$LLVM_VERSION/tools/clang
     tar -xvf ../archives/lld-$LLVM_VERSION.src.tar.xz
     mv lld-$LLVM_VERSION.src/ llvm-$LLVM_VERSION/tools/lld
+    tar -xvf ../archives/compiler-rt-$LLVM_VERSION.src.tar.xz
+    mv compiler-rt-$LLVM_VERSION.src/ llvm-$LLVM_VERSION/projects/compiler-rt
     tar -xvf ../archives/clang-tools-extra-$LLVM_VERSION.src.tar.xz
     mv clang-tools-extra-$LLVM_VERSION.src/ llvm-$LLVM_VERSION/tools/clang/tools/extra
     pushd llvm-$LLVM_VERSION
@@ -546,7 +552,7 @@ if [ ! -f $PREFIX/README.md ]; then
  - GDB $GDB_VERSION
  - CMake $CMAKE_VERSION
  - Cppcheck $CPPCHECK_VERSION
- - LLVM (Clang, LLD, Clang tools extra) $LLVM_VERSION
+ - LLVM (Clang, LLD, compiler-rt, Clang tools extra) $LLVM_VERSION
 
 ## Required libraries
 

environment/toolchain/v2.sh

@@ -0,0 +1,533 @@
+#!/bin/bash -e
+
+# helpers
+pushd () { command pushd "$@" > /dev/null; }
+popd () { command popd "$@" > /dev/null; }
+DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
+CPUS=$( grep -c processor < /proc/cpuinfo )
+cd "$DIR"
+
+source "$DIR/../util.sh"
+DISTRO="$(operating_system)"
+
+# toolchain version
+TOOLCHAIN_VERSION=2
+
+# package versions used
+GCC_VERSION=10.2.0
+BINUTILS_VERSION=2.35.1
+case "$DISTRO" in
+    centos-7) # because GDB >= 9 does NOT compile with readline6.
+        GDB_VERSION=8.3
+    ;;
+    *)
+        GDB_VERSION=10.1
+    ;;
+esac
+CMAKE_VERSION=3.18.4
+CPPCHECK_VERSION=2.2
+LLVM_VERSION=11.0.0
+SWIG_VERSION=4.0.2 # used only for LLVM compilation
+
+# Check for the dependencies.
+echo "ALL BUILD PACKAGES: $($DIR/../os/$DISTRO.sh list TOOLCHAIN_BUILD_DEPS)"
+$DIR/../os/$DISTRO.sh check TOOLCHAIN_BUILD_DEPS
+echo "ALL RUN PACKAGES: $($DIR/../os/$DISTRO.sh list TOOLCHAIN_RUN_DEPS)"
+$DIR/../os/$DISTRO.sh check TOOLCHAIN_RUN_DEPS
+
+# check installation directory
+NAME=toolchain-v$TOOLCHAIN_VERSION
+PREFIX=/opt/$NAME
+mkdir -p $PREFIX >/dev/null 2>/dev/null || true
+if [ ! -d $PREFIX ] || [ ! -w $PREFIX ]; then
+    echo "Please make sure that the directory '$PREFIX' exists and is writable by the current user!"
+    echo
+    echo "If unsure, execute these commands as root:"
+    echo "    mkdir $PREFIX && chown $USER:$USER $PREFIX"
+    echo
+    echo "Press <return> when you have created the directory and granted permissions."
+    # wait for the directory to be created
+    while true; do
+        read
+        if [ ! -d $PREFIX ] || [ ! -w $PREFIX ]; then
+            echo
+            echo "You can't continue before you have created the directory and granted permissions!"
+            echo
+            echo "Press <return> when you have created the directory and granted permissions."
+        else
+            break
+        fi
+    done
+fi
+
+# create archives directory
+mkdir -p archives
+
+# download all archives
+pushd archives
+if [ ! -f gcc-$GCC_VERSION.tar.gz ]; then
+    wget https://ftp.gnu.org/gnu/gcc/gcc-$GCC_VERSION/gcc-$GCC_VERSION.tar.gz
+fi
+if [ ! -f binutils-$BINUTILS_VERSION.tar.gz ]; then
+    wget https://ftp.gnu.org/gnu/binutils/binutils-$BINUTILS_VERSION.tar.gz
+fi
+if [ ! -f gdb-$GDB_VERSION.tar.gz ]; then
+    wget https://ftp.gnu.org/gnu/gdb/gdb-$GDB_VERSION.tar.gz
+fi
+if [ ! -f cmake-$CMAKE_VERSION.tar.gz ]; then
+    wget https://github.com/Kitware/CMake/releases/download/v$CMAKE_VERSION/cmake-$CMAKE_VERSION.tar.gz
+fi
+if [ ! -f swig-$SWIG_VERSION.tar.gz ]; then
+    wget https://github.com/swig/swig/archive/rel-$SWIG_VERSION.tar.gz -O swig-$SWIG_VERSION.tar.gz
+fi
+if [ ! -f cppcheck-$CPPCHECK_VERSION.tar.gz ]; then
+    wget https://github.com/danmar/cppcheck/archive/$CPPCHECK_VERSION.tar.gz -O cppcheck-$CPPCHECK_VERSION.tar.gz
+fi
+if [ ! -f llvm-$LLVM_VERSION.src.tar.xz ]; then
+    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION/llvm-$LLVM_VERSION.src.tar.xz
+    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION/clang-$LLVM_VERSION.src.tar.xz
+    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION/lld-$LLVM_VERSION.src.tar.xz
+    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION/clang-tools-extra-$LLVM_VERSION.src.tar.xz
+    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION/compiler-rt-$LLVM_VERSION.src.tar.xz
+fi
+if [ ! -f pahole-gdb-master.zip ]; then
+    wget https://github.com/PhilArmstrong/pahole-gdb/archive/master.zip -O pahole-gdb-master.zip
+fi
+
+# verify all archives
+# NOTE: Verification can fail if the archive is signed by another developer. I
+# haven't added commands to download all developer GnuPG keys because the
+# download is very slow. If the verification fails for you, figure out who has
+# signed the archive and download their public key instead.
+GPG="gpg --homedir .gnupg"
+KEYSERVER="hkp://keyserver.ubuntu.com"
+mkdir -p .gnupg
+chmod 700 .gnupg
+# verify gcc
+if [ ! -f gcc-$GCC_VERSION.tar.gz.sig ]; then
+    wget https://ftp.gnu.org/gnu/gcc/gcc-$GCC_VERSION/gcc-$GCC_VERSION.tar.gz.sig
+fi
+# list of valid gcc gnupg keys: https://gcc.gnu.org/mirrors.html
+$GPG --keyserver $KEYSERVER --recv-keys 0x3AB00996FC26A641
+$GPG --verify gcc-$GCC_VERSION.tar.gz.sig gcc-$GCC_VERSION.tar.gz
+# verify binutils
+if [ ! -f binutils-$BINUTILS_VERSION.tar.gz.sig ]; then
+    wget https://ftp.gnu.org/gnu/binutils/binutils-$BINUTILS_VERSION.tar.gz.sig
+fi
+$GPG --keyserver $KEYSERVER --recv-keys 0xDD9E3C4F
+$GPG --verify binutils-$BINUTILS_VERSION.tar.gz.sig binutils-$BINUTILS_VERSION.tar.gz
+# verify gdb
+if [ ! -f gdb-$GDB_VERSION.tar.gz.sig ]; then
+    wget https://ftp.gnu.org/gnu/gdb/gdb-$GDB_VERSION.tar.gz.sig
+fi
+$GPG --keyserver $KEYSERVER --recv-keys 0xFF325CF3
+$GPG --verify gdb-$GDB_VERSION.tar.gz.sig gdb-$GDB_VERSION.tar.gz
+# verify cmake
+if [ ! -f cmake-$CMAKE_VERSION-SHA-256.txt ] || [ ! -f cmake-$CMAKE_VERSION-SHA-256.txt.asc ]; then
+    wget https://github.com/Kitware/CMake/releases/download/v$CMAKE_VERSION/cmake-$CMAKE_VERSION-SHA-256.txt
+    wget https://github.com/Kitware/CMake/releases/download/v$CMAKE_VERSION/cmake-$CMAKE_VERSION-SHA-256.txt.asc
+    # Because CentOS 7 doesn't have the `--ignore-missing` flag for `sha256sum`
+    # we filter out the missing files from the sums here manually.
+    cat cmake-$CMAKE_VERSION-SHA-256.txt | grep "cmake-$CMAKE_VERSION.tar.gz" > cmake-$CMAKE_VERSION-SHA-256-filtered.txt
+fi
+$GPG --keyserver $KEYSERVER --recv-keys 0xC6C265324BBEBDC350B513D02D2CEF1034921684
+sha256sum -c cmake-$CMAKE_VERSION-SHA-256-filtered.txt
+$GPG --verify cmake-$CMAKE_VERSION-SHA-256.txt.asc cmake-$CMAKE_VERSION-SHA-256.txt
+# verify llvm, cfe, lld, clang-tools-extra
+if [ ! -f llvm-$LLVM_VERSION.src.tar.xz.sig ]; then
+    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION/llvm-$LLVM_VERSION.src.tar.xz.sig
+    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION/clang-$LLVM_VERSION.src.tar.xz.sig
+    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION/lld-$LLVM_VERSION.src.tar.xz.sig
+    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION/clang-tools-extra-$LLVM_VERSION.src.tar.xz.sig
+    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION/compiler-rt-$LLVM_VERSION.src.tar.xz.sig
+fi
+# list of valid llvm gnupg keys: https://releases.llvm.org/download.html
+$GPG --keyserver $KEYSERVER --recv-keys 0x345AD05D
+$GPG --verify llvm-$LLVM_VERSION.src.tar.xz.sig llvm-$LLVM_VERSION.src.tar.xz
+$GPG --verify clang-$LLVM_VERSION.src.tar.xz.sig clang-$LLVM_VERSION.src.tar.xz
+$GPG --verify lld-$LLVM_VERSION.src.tar.xz.sig lld-$LLVM_VERSION.src.tar.xz
+$GPG --verify clang-tools-extra-$LLVM_VERSION.src.tar.xz.sig clang-tools-extra-$LLVM_VERSION.src.tar.xz
+$GPG --verify compiler-rt-$LLVM_VERSION.src.tar.xz.sig compiler-rt-$LLVM_VERSION.src.tar.xz
+popd
+
+# create build directory
+mkdir -p build
+pushd build
+
+# compile gcc
+if [ ! -f $PREFIX/bin/gcc ]; then
+    if [ -d gcc-$GCC_VERSION ]; then
+        rm -rf gcc-$GCC_VERSION
+    fi
+    tar -xvf ../archives/gcc-$GCC_VERSION.tar.gz
+    pushd gcc-$GCC_VERSION
+    ./contrib/download_prerequisites
+    mkdir build && pushd build
+    # influenced by: https://buildd.debian.org/status/fetch.php?pkg=gcc-8&arch=amd64&ver=8.3.0-6&stamp=1554588545
+    ../configure -v \
+        --build=x86_64-linux-gnu \
+        --host=x86_64-linux-gnu \
+        --target=x86_64-linux-gnu \
+        --prefix=$PREFIX \
+        --disable-multilib \
+        --with-system-zlib \
+        --enable-checking=release \
+        --enable-languages=c,c++,fortran \
+        --enable-gold=yes \
+        --enable-ld=yes \
+        --enable-lto \
+        --enable-bootstrap \
+        --disable-vtable-verify \
+        --disable-werror \
+        --without-included-gettext \
+        --enable-threads=posix \
+        --enable-nls \
+        --enable-clocale=gnu \
+        --enable-libstdcxx-debug \
+        --enable-libstdcxx-time=yes \
+        --enable-gnu-unique-object \
+        --enable-libmpx \
+        --enable-plugin \
+        --enable-default-pie \
+        --with-target-system-zlib \
+        --with-tune=generic \
+        --without-cuda-driver
+        #--program-suffix=$( printf "$GCC_VERSION" | cut -d '.' -f 1,2 ) \
+    make -j$CPUS
+    # make -k check # run test suite
+    make install
+    popd && popd
+fi
+
+# activate toolchain
+export PATH=$PREFIX/bin:$PATH
+export LD_LIBRARY_PATH=$PREFIX/lib64
+
+# compile binutils
+if [ ! -f $PREFIX/bin/ld.gold ]; then
+    if [ -d binutils-$BINUTILS_VERSION ]; then
+        rm -rf binutils-$BINUTILS_VERSION
+    fi
+    tar -xvf ../archives/binutils-$BINUTILS_VERSION.tar.gz
+    pushd binutils-$BINUTILS_VERSION
+    mkdir build && pushd build
+    # influenced by: https://buildd.debian.org/status/fetch.php?pkg=binutils&arch=amd64&ver=2.32-7&stamp=1553247092
+    env \
+        CC=gcc \
+        CXX=g++ \
+        CFLAGS="-g -O2" \
+        CXXFLAGS="-g -O2" \
+        LDFLAGS="" \
+        ../configure \
+            --build=x86_64-linux-gnu \
+            --host=x86_64-linux-gnu \
+            --prefix=$PREFIX \
+            --enable-ld=default \
+            --enable-gold \
+            --enable-lto \
+            --enable-plugins \
+            --enable-shared \
+            --enable-threads \
+            --with-system-zlib \
+            --enable-deterministic-archives \
+            --disable-compressed-debug-sections \
+            --enable-new-dtags \
+            --disable-werror
+    make -j$CPUS
+    # make -k check # run test suite
+    make install
+    popd && popd
+fi
+
+# compile gdb
+if [ ! -f $PREFIX/bin/gdb ]; then
+    if [ -d gdb-$GDB_VERSION ]; then
+        rm -rf gdb-$GDB_VERSION
+    fi
+    tar -xvf ../archives/gdb-$GDB_VERSION.tar.gz
+    pushd gdb-$GDB_VERSION
+    mkdir build && pushd build
+    # https://buildd.debian.org/status/fetch.php?pkg=gdb&arch=amd64&ver=8.2.1-2&stamp=1550831554&raw=0
+    env \
+        CC=gcc \
+        CXX=g++ \
+        CFLAGS="-g -O2 -fstack-protector-strong -Wformat -Werror=format-security" \
+        CXXFLAGS="-g -O2 -fstack-protector-strong -Wformat -Werror=format-security" \
+        CPPFLAGS="-Wdate-time -D_FORTIFY_SOURCE=2 -fPIC" \
+        LDFLAGS="-Wl,-z,relro" \
+        PYTHON="" \
+        ../configure \
+            --build=x86_64-linux-gnu \
+            --host=x86_64-linux-gnu \
+            --prefix=$PREFIX \
+            --disable-maintainer-mode \
+            --disable-dependency-tracking \
+            --disable-silent-rules \
+            --disable-gdbtk \
+            --disable-shared \
+            --without-guile \
+            --with-system-gdbinit=$PREFIX/etc/gdb/gdbinit \
+            --with-system-readline \
+            --with-expat \
+            --with-system-zlib \
+            --with-lzma \
+            --with-babeltrace \
+            --with-intel-pt \
+            --enable-tui \
+            --with-python=python3
+    make -j$CPUS
+    make install
+    popd && popd
+fi
+
+# install pahole
+if [ ! -d $PREFIX/share/pahole-gdb ]; then
+    unzip ../archives/pahole-gdb-master.zip
+    mv pahole-gdb-master $PREFIX/share/pahole-gdb
+fi
+
+# setup system gdbinit
+if [ ! -f $PREFIX/etc/gdb/gdbinit ]; then
+    mkdir -p $PREFIX/etc/gdb
+    cat >$PREFIX/etc/gdb/gdbinit <<EOF
+# improve formatting
+set print pretty on
+set print object on
+set print static-members on
+set print vtbl on
+set print demangle on
+set demangle-style gnu-v3
+set print sevenbit-strings off
+
+# load libstdc++ pretty printers
+add-auto-load-scripts-directory $PREFIX/lib64
+add-auto-load-safe-path $PREFIX
+
+# load pahole
+python
+sys.path.insert(0, "$PREFIX/share/pahole-gdb")
+import offsets
+import pahole
+end
+EOF
+fi
+
+# compile cmake
+if [ ! -f $PREFIX/bin/cmake ]; then
+    if [ -d cmake-$CMAKE_VERSION ]; then
+        rm -rf cmake-$CMAKE_VERSION
+    fi
+    tar -xvf ../archives/cmake-$CMAKE_VERSION.tar.gz
+    pushd cmake-$CMAKE_VERSION
+    # influenced by: https://buildd.debian.org/status/fetch.php?pkg=cmake&arch=amd64&ver=3.13.4-1&stamp=1549799837
+    echo 'set(CMAKE_SKIP_RPATH ON CACHE BOOL "Skip rpath" FORCE)' >> build-flags.cmake
+    echo 'set(CMAKE_USE_RELATIVE_PATHS ON CACHE BOOL "Use relative paths" FORCE)' >> build-flags.cmake
+    echo 'set(CMAKE_C_FLAGS "-g -O2 -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2" CACHE STRING "C flags" FORCE)' >> build-flags.cmake
+    echo 'set(CMAKE_CXX_FLAGS "-g -O2 -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2" CACHE STRING "C++ flags" FORCE)' >> build-flags.cmake
+    echo 'set(CMAKE_SKIP_BOOTSTRAP_TEST ON CACHE BOOL "Skip BootstrapTest" FORCE)' >> build-flags.cmake
+    echo 'set(BUILD_CursesDialog ON CACHE BOOL "Build curses GUI" FORCE)' >> build-flags.cmake
+    mkdir build && pushd build
+    ../bootstrap \
+        --prefix=$PREFIX \
+        --init=../build-flags.cmake \
+        --parallel=$CPUS \
+        --system-curl
+    make -j$CPUS
+    # make test # run test suite
+    make install
+    popd && popd
+fi
+
+# compile cppcheck
+if [ ! -f $PREFIX/bin/cppcheck ]; then
+    if [ -d cppcheck-$CPPCHECK_VERSION ]; then
+        rm -rf cppcheck-$CPPCHECK_VERSION
+    fi
+    tar -xvf ../archives/cppcheck-$CPPCHECK_VERSION.tar.gz
+    pushd cppcheck-$CPPCHECK_VERSION
+    env \
+        CC=gcc \
+        CXX=g++ \
+        PREFIX=$PREFIX \
+        FILESDIR=$PREFIX/share/cppcheck \
+        CFGDIR=$PREFIX/share/cppcheck/cfg \
+            make -j$CPUS
+    env \
+        CC=gcc \
+        CXX=g++ \
+        PREFIX=$PREFIX \
+        FILESDIR=$PREFIX/share/cppcheck \
+        CFGDIR=$PREFIX/share/cppcheck/cfg \
+            make install
+    popd
+fi
+
+# compile swig
+if [ ! -d swig-$SWIG_VERSION/install ]; then
+    if [ -d swig-$SWIG_VERSION ]; then
+        rm -rf swig-$SWIG_VERSION
+    fi
+    tar -xvf ../archives/swig-$SWIG_VERSION.tar.gz
+    mv swig-rel-$SWIG_VERSION swig-$SWIG_VERSION
+    pushd swig-$SWIG_VERSION
+    ./autogen.sh
+    mkdir build && pushd build
+    ../configure --prefix=$DIR/build/swig-$SWIG_VERSION/install
+    make -j$CPUS
+    make install
+    popd && popd
+fi
+
+# compile llvm
+if [ ! -f $PREFIX/bin/clang ]; then
+    if [ -d llvm-$LLVM_VERSION ]; then
+        rm -rf llvm-$LLVM_VERSION
+    fi
+    tar -xvf ../archives/llvm-$LLVM_VERSION.src.tar.xz
+    mv llvm-$LLVM_VERSION.src llvm-$LLVM_VERSION
+    tar -xvf ../archives/clang-$LLVM_VERSION.src.tar.xz
+    mv clang-$LLVM_VERSION.src llvm-$LLVM_VERSION/tools/clang
+    tar -xvf ../archives/lld-$LLVM_VERSION.src.tar.xz
+    mv lld-$LLVM_VERSION.src/ llvm-$LLVM_VERSION/tools/lld
+    tar -xvf ../archives/clang-tools-extra-$LLVM_VERSION.src.tar.xz
+    mv clang-tools-extra-$LLVM_VERSION.src/ llvm-$LLVM_VERSION/tools/clang/tools/extra
+    tar -xvf ../archives/compiler-rt-$LLVM_VERSION.src.tar.xz
+    mv compiler-rt-$LLVM_VERSION.src/ llvm-$LLVM_VERSION/projects/compiler-rt
+    pushd llvm-$LLVM_VERSION
+    mkdir build && pushd build
+    # activate swig
+    export PATH=$DIR/build/swig-$SWIG_VERSION/install/bin:$PATH
+    # influenced by: https://buildd.debian.org/status/fetch.php?pkg=llvm-toolchain-7&arch=amd64&ver=1%3A7.0.1%7E%2Brc2-1%7Eexp1&stamp=1541506173&raw=0
+    cmake .. \
+        -DCMAKE_C_COMPILER=$PREFIX/bin/gcc \
+        -DCMAKE_CXX_COMPILER=$PREFIX/bin/g++ \
+        -DCMAKE_CXX_LINK_FLAGS="-L$PREFIX/lib64 -Wl,-rpath,$PREFIX/lib64" \
+        -DCMAKE_INSTALL_PREFIX=$PREFIX \
+        -DCMAKE_BUILD_TYPE=RelWithDebInfo \
+        -DCMAKE_CXX_FLAGS_RELWITHDEBINFO="-O2 -DNDEBUG" \
+        -DCMAKE_CXX_FLAGS=' -fuse-ld=gold -fPIC -Wno-unused-command-line-argument -Wno-unknown-warning-option' \
+        -DCMAKE_C_FLAGS=' -fuse-ld=gold -fPIC -Wno-unused-command-line-argument -Wno-unknown-warning-option' \
+        -DLLVM_LINK_LLVM_DYLIB=ON \
+        -DLLVM_INSTALL_UTILS=ON \
+        -DLLVM_VERSION_SUFFIX= \
+        -DLLVM_BUILD_LLVM_DYLIB=ON \
+        -DLLVM_ENABLE_RTTI=ON \
+        -DLLVM_ENABLE_FFI=ON \
+        -DLLVM_BINUTILS_INCDIR=$PREFIX/include/ \
+        -DLLVM_USE_PERF=yes
+    make -j$CPUS
+    make -j$CPUS check-clang # run clang test suite
+    make -j$CPUS check-lld # run lld test suite
+    make install
+    popd && popd
+fi
+
+# create README
+if [ ! -f $PREFIX/README.md ]; then
+    cat >$PREFIX/README.md <<EOF
+# Memgraph Toolchain v$TOOLCHAIN_VERSION
+
+## Included tools
+
+ - GCC $GCC_VERSION
+ - Binutils $BINUTILS_VERSION
+ - GDB $GDB_VERSION
+ - CMake $CMAKE_VERSION
+ - Cppcheck $CPPCHECK_VERSION
+ - LLVM (Clang, LLD, compiler-rt, Clang tools extra) $LLVM_VERSION
+
+## Required libraries
+
+In order to be able to run all of these tools you should install the following
+packages:
+
+\`\`\`
+$($DIR/../os/$DISTRO.sh list TOOLCHAIN_RUN_DEPS)
+\`\`\`
+
+## Usage
+
+In order to use the toolchain you just have to source the activation script:
+
+\`\`\`
+source $PREFIX/activate
+\`\`\`
+EOF
+fi
+
+# create activation script
+if [ ! -f $PREFIX/activate ]; then
+    cat >$PREFIX/activate <<EOF
+# This file must be used with "source $PREFIX/activate" *from bash*
+# You can't run it directly!
+
+# check for active virtual environments
+if [ "\$( type -t deactivate )" != "" ]; then
+    echo "You already have an active virtual environment!"
+    return 0
+fi
+
+# check that we aren't root
+if [ "\$USER" == "root" ]; then
+    echo "You shouldn't use the toolchan as root!"
+    return 0
+fi
+
+# save original environment
+export ORIG_PATH=\$PATH
+export ORIG_PS1=\$PS1
+export ORIG_LD_LIBRARY_PATH=\$LD_LIBRARY_PATH
+
+# activate new environment
+export PATH=$PREFIX/bin:\$PATH
+export PS1="($NAME) \$PS1"
+export LD_LIBRARY_PATH=$PREFIX/lib:$PREFIX/lib64
+
+# disable root
+function su () {
+    echo "You don't want to use root functions while using the toolchain!"
+    return 1
+}
+function sudo () {
+    echo "You don't want to use root functions while using the toolchain!"
+    return 1
+}
+
+# create deactivation function
+function deactivate() {
+    export PATH=\$ORIG_PATH
+    export PS1=\$ORIG_PS1
+    export LD_LIBRARY_PATH=\$ORIG_LD_LIBRARY_PATH
+    unset ORIG_PATH ORIG_PS1 ORIG_LD_LIBRARY_PATH
+    unset -f su sudo deactivate
+}
+EOF
+fi
+
+# create toolchain archive
+if [ ! -f $NAME-binaries-$DISTRO.tar.gz ]; then
+    tar --owner=root --group=root -cpvzf $NAME-binaries-$DISTRO.tar.gz -C /opt $NAME
+fi
+
+# output final instructions
+echo -e "\n\n"
+echo "All tools have been built. They are installed in '$PREFIX'."
+echo "In order to distribute the tools to someone else, an archive with the toolchain was created in the 'build' directory."
+echo "If you want to install the packed tools you should execute the following command:"
+echo
+echo "    tar -xvzf build/$NAME-binaries.tar.gz -C /opt"
+echo
+echo "Because the tools were built on this machine, you should probably change the permissions of the installation directory using:"
+echo
+echo "    OPTIONAL: chown -R root:root $PREFIX"
+echo
+echo "In order to use all of the newly compiled tools you should use the prepared activation script:"
+echo
+echo "    source $PREFIX/activate"
+echo
+echo "Or, for more advanced uses, you can add the following lines to your script:"
+echo
+echo "    export PATH=$PREFIX/bin:\$PATH"
+echo "    export LD_LIBRARY_PATH=$PREFIX/lib:$PREFIX/lib64"
+echo
+echo "Enjoy!"

environment/toolchain/v3.sh

@@ -0,0 +1,556 @@
+#!/bin/bash -e
+
+# helpers
+pushd () { command pushd "$@" > /dev/null; }
+popd () { command popd "$@" > /dev/null; }
+DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
+CPUS=$( grep -c processor < /proc/cpuinfo )
+cd "$DIR"
+
+source "$DIR/../util.sh"
+DISTRO="$(operating_system)"
+
+# toolchain version
+TOOLCHAIN_VERSION=3
+
+# package versions used
+GCC_VERSION=11.1.0
+BINUTILS_VERSION=2.36.1
+case "$DISTRO" in
+    centos-7) # because GDB >= 9 does NOT compile with readline6.
+        GDB_VERSION=8.3
+    ;;
+    *)
+        GDB_VERSION=10.2
+    ;;
+esac
+CMAKE_VERSION=3.20.5
+CPPCHECK_VERSION=2.4.1
+LLVM_VERSION=12.0.1rc4
+LLVM_VERSION_LONG=12.0.1-rc4
+SWIG_VERSION=4.0.2 # used only for LLVM compilation
+
+# Check for the dependencies.
+echo "ALL BUILD PACKAGES: $($DIR/../os/$DISTRO.sh list TOOLCHAIN_BUILD_DEPS)"
+$DIR/../os/$DISTRO.sh check TOOLCHAIN_BUILD_DEPS
+echo "ALL RUN PACKAGES: $($DIR/../os/$DISTRO.sh list TOOLCHAIN_RUN_DEPS)"
+$DIR/../os/$DISTRO.sh check TOOLCHAIN_RUN_DEPS
+
+# check installation directory
+NAME=toolchain-v$TOOLCHAIN_VERSION
+PREFIX=/opt/$NAME
+mkdir -p $PREFIX >/dev/null 2>/dev/null || true
+if [ ! -d $PREFIX ] || [ ! -w $PREFIX ]; then
+    echo "Please make sure that the directory '$PREFIX' exists and is writable by the current user!"
+    echo
+    echo "If unsure, execute these commands as root:"
+    echo "    mkdir $PREFIX && chown $USER:$USER $PREFIX"
+    echo
+    echo "Press <return> when you have created the directory and granted permissions."
+    # wait for the directory to be created
+    while true; do
+        read
+        if [ ! -d $PREFIX ] || [ ! -w $PREFIX ]; then
+            echo
+            echo "You can't continue before you have created the directory and granted permissions!"
+            echo
+            echo "Press <return> when you have created the directory and granted permissions."
+        else
+            break
+        fi
+    done
+fi
+
+# create archives directory
+mkdir -p archives
+
+# download all archives
+pushd archives
+if [ ! -f gcc-$GCC_VERSION.tar.gz ]; then
+    wget https://ftp.gnu.org/gnu/gcc/gcc-$GCC_VERSION/gcc-$GCC_VERSION.tar.gz
+fi
+if [ ! -f binutils-$BINUTILS_VERSION.tar.gz ]; then
+    wget https://ftp.gnu.org/gnu/binutils/binutils-$BINUTILS_VERSION.tar.gz
+fi
+if [ ! -f gdb-$GDB_VERSION.tar.gz ]; then
+    wget https://ftp.gnu.org/gnu/gdb/gdb-$GDB_VERSION.tar.gz
+fi
+if [ ! -f cmake-$CMAKE_VERSION.tar.gz ]; then
+    wget https://github.com/Kitware/CMake/releases/download/v$CMAKE_VERSION/cmake-$CMAKE_VERSION.tar.gz
+fi
+if [ ! -f swig-$SWIG_VERSION.tar.gz ]; then
+    wget https://github.com/swig/swig/archive/rel-$SWIG_VERSION.tar.gz -O swig-$SWIG_VERSION.tar.gz
+fi
+if [ ! -f cppcheck-$CPPCHECK_VERSION.tar.gz ]; then
+    wget https://github.com/danmar/cppcheck/archive/$CPPCHECK_VERSION.tar.gz -O cppcheck-$CPPCHECK_VERSION.tar.gz
+fi
+if [ ! -f llvm-$LLVM_VERSION.src.tar.xz ]; then
+    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION_LONG/llvm-$LLVM_VERSION.src.tar.xz
+    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION_LONG/clang-$LLVM_VERSION.src.tar.xz
+    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION_LONG/lld-$LLVM_VERSION.src.tar.xz
+    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION_LONG/clang-tools-extra-$LLVM_VERSION.src.tar.xz
+    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION_LONG/compiler-rt-$LLVM_VERSION.src.tar.xz
+    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION_LONG/libunwind-$LLVM_VERSION.src.tar.xz
+fi
+if [ ! -f pahole-gdb-master.zip ]; then
+    wget https://github.com/PhilArmstrong/pahole-gdb/archive/master.zip -O pahole-gdb-master.zip
+fi
+
+# verify all archives
+# NOTE: Verification can fail if the archive is signed by another developer. I
+# haven't added commands to download all developer GnuPG keys because the
+# download is very slow. If the verification fails for you, figure out who has
+# signed the archive and download their public key instead.
+GPG="gpg --homedir .gnupg"
+KEYSERVER="hkp://keyserver.ubuntu.com"
+
+mkdir -p .gnupg
+chmod 700 .gnupg
+# verify gcc
+if [ ! -f gcc-$GCC_VERSION.tar.gz.sig ]; then
+    wget https://ftp.gnu.org/gnu/gcc/gcc-$GCC_VERSION/gcc-$GCC_VERSION.tar.gz.sig
+fi
+# list of valid gcc gnupg keys: https://gcc.gnu.org/mirrors.html
+$GPG --keyserver $KEYSERVER --recv-keys 0x6C35B99309B5FA62
+$GPG --verify gcc-$GCC_VERSION.tar.gz.sig gcc-$GCC_VERSION.tar.gz
+# verify binutils
+if [ ! -f binutils-$BINUTILS_VERSION.tar.gz.sig ]; then
+    wget https://ftp.gnu.org/gnu/binutils/binutils-$BINUTILS_VERSION.tar.gz.sig
+fi
+$GPG --keyserver $KEYSERVER --recv-keys 0xDD9E3C4F
+$GPG --verify binutils-$BINUTILS_VERSION.tar.gz.sig binutils-$BINUTILS_VERSION.tar.gz
+# verify gdb
+if [ ! -f gdb-$GDB_VERSION.tar.gz.sig ]; then
+    wget https://ftp.gnu.org/gnu/gdb/gdb-$GDB_VERSION.tar.gz.sig
+fi
+$GPG --keyserver $KEYSERVER --recv-keys 0xFF325CF3
+$GPG --verify gdb-$GDB_VERSION.tar.gz.sig gdb-$GDB_VERSION.tar.gz
+# verify cmake
+if [ ! -f cmake-$CMAKE_VERSION-SHA-256.txt ] || [ ! -f cmake-$CMAKE_VERSION-SHA-256.txt.asc ]; then
+    wget https://github.com/Kitware/CMake/releases/download/v$CMAKE_VERSION/cmake-$CMAKE_VERSION-SHA-256.txt
+    wget https://github.com/Kitware/CMake/releases/download/v$CMAKE_VERSION/cmake-$CMAKE_VERSION-SHA-256.txt.asc
+    # Because CentOS 7 doesn't have the `--ignore-missing` flag for `sha256sum`
+    # we filter out the missing files from the sums here manually.
+    cat cmake-$CMAKE_VERSION-SHA-256.txt | grep "cmake-$CMAKE_VERSION.tar.gz" > cmake-$CMAKE_VERSION-SHA-256-filtered.txt
+fi
+$GPG --keyserver $KEYSERVER --recv-keys 0xC6C265324BBEBDC350B513D02D2CEF1034921684
+sha256sum -c cmake-$CMAKE_VERSION-SHA-256-filtered.txt
+$GPG --verify cmake-$CMAKE_VERSION-SHA-256.txt.asc cmake-$CMAKE_VERSION-SHA-256.txt
+# verify llvm, cfe, lld, clang-tools-extra
+if [ ! -f llvm-$LLVM_VERSION.src.tar.xz.sig ]; then
+    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION_LONG/llvm-$LLVM_VERSION.src.tar.xz.sig
+    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION_LONG/clang-$LLVM_VERSION.src.tar.xz.sig
+    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION_LONG/lld-$LLVM_VERSION.src.tar.xz.sig
+    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION_LONG/clang-tools-extra-$LLVM_VERSION.src.tar.xz.sig
+    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION_LONG/compiler-rt-$LLVM_VERSION.src.tar.xz.sig
+    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION_LONG/libunwind-$LLVM_VERSION.src.tar.xz.sig
+fi
+# list of valid llvm gnupg keys: https://releases.llvm.org/download.html
+$GPG --keyserver $KEYSERVER --recv-keys 0x474E22316ABF4785A88C6E8EA2C794A986419D8A
+$GPG --verify llvm-$LLVM_VERSION.src.tar.xz.sig llvm-$LLVM_VERSION.src.tar.xz
+$GPG --verify clang-$LLVM_VERSION.src.tar.xz.sig clang-$LLVM_VERSION.src.tar.xz
+$GPG --verify lld-$LLVM_VERSION.src.tar.xz.sig lld-$LLVM_VERSION.src.tar.xz
+$GPG --verify clang-tools-extra-$LLVM_VERSION.src.tar.xz.sig clang-tools-extra-$LLVM_VERSION.src.tar.xz
+$GPG --verify compiler-rt-$LLVM_VERSION.src.tar.xz.sig compiler-rt-$LLVM_VERSION.src.tar.xz
+$GPG --verify libunwind-$LLVM_VERSION.src.tar.xz.sig libunwind-$LLVM_VERSION.src.tar.xz
+popd
+
+# create build directory
+mkdir -p build
+pushd build
+
+# compile gcc
+if [ ! -f $PREFIX/bin/gcc ]; then
+    if [ -d gcc-$GCC_VERSION ]; then
+        rm -rf gcc-$GCC_VERSION
+    fi
+    tar -xvf ../archives/gcc-$GCC_VERSION.tar.gz
+    pushd gcc-$GCC_VERSION
+    ./contrib/download_prerequisites
+    mkdir build && pushd build
+    # influenced by: https://buildd.debian.org/status/fetch.php?pkg=gcc-8&arch=amd64&ver=8.3.0-6&stamp=1554588545
+    ../configure -v \
+        --build=x86_64-linux-gnu \
+        --host=x86_64-linux-gnu \
+        --target=x86_64-linux-gnu \
+        --prefix=$PREFIX \
+        --disable-multilib \
+        --with-system-zlib \
+        --enable-checking=release \
+        --enable-languages=c,c++,fortran \
+        --enable-gold=yes \
+        --enable-ld=yes \
+        --enable-lto \
+        --enable-bootstrap \
+        --disable-vtable-verify \
+        --disable-werror \
+        --without-included-gettext \
+        --enable-threads=posix \
+        --enable-nls \
+        --enable-clocale=gnu \
+        --enable-libstdcxx-debug \
+        --enable-libstdcxx-time=yes \
+        --enable-gnu-unique-object \
+        --enable-libmpx \
+        --enable-plugin \
+        --enable-default-pie \
+        --with-target-system-zlib \
+        --with-tune=generic \
+        --without-cuda-driver
+        #--program-suffix=$( printf "$GCC_VERSION" | cut -d '.' -f 1,2 ) \
+    make -j$CPUS
+    # make -k check # run test suite
+    make install
+    popd && popd
+fi
+
+# activate toolchain
+export PATH=$PREFIX/bin:$PATH
+export LD_LIBRARY_PATH=$PREFIX/lib64
+
+# compile binutils
+if [ ! -f $PREFIX/bin/ld.gold ]; then
+    if [ -d binutils-$BINUTILS_VERSION ]; then
+        rm -rf binutils-$BINUTILS_VERSION
+    fi
+    tar -xvf ../archives/binutils-$BINUTILS_VERSION.tar.gz
+    pushd binutils-$BINUTILS_VERSION
+    mkdir build && pushd build
+    # influenced by: https://buildd.debian.org/status/fetch.php?pkg=binutils&arch=amd64&ver=2.32-7&stamp=1553247092
+    env \
+        CC=gcc \
+        CXX=g++ \
+        CFLAGS="-g -O2" \
+        CXXFLAGS="-g -O2" \
+        LDFLAGS="" \
+        ../configure \
+            --build=x86_64-linux-gnu \
+            --host=x86_64-linux-gnu \
+            --prefix=$PREFIX \
+            --enable-ld=default \
+            --enable-gold \
+            --enable-lto \
+            --enable-plugins \
+            --enable-shared \
+            --enable-threads \
+            --with-system-zlib \
+            --enable-deterministic-archives \
+            --disable-compressed-debug-sections \
+            --enable-new-dtags \
+            --disable-werror
+    make -j$CPUS
+    # make -k check # run test suite
+    make install
+    popd && popd
+fi
+
+# compile gdb
+if [ ! -f $PREFIX/bin/gdb ]; then
+    if [ -d gdb-$GDB_VERSION ]; then
+        rm -rf gdb-$GDB_VERSION
+    fi
+    tar -xvf ../archives/gdb-$GDB_VERSION.tar.gz
+    pushd gdb-$GDB_VERSION
+    mkdir build && pushd build
+    # https://buildd.debian.org/status/fetch.php?pkg=gdb&arch=amd64&ver=8.2.1-2&stamp=1550831554&raw=0
+    env \
+        CC=gcc \
+        CXX=g++ \
+        CFLAGS="-g -O2 -fstack-protector-strong -Wformat -Werror=format-security" \
+        CXXFLAGS="-g -O2 -fstack-protector-strong -Wformat -Werror=format-security" \
+        CPPFLAGS="-Wdate-time -D_FORTIFY_SOURCE=2 -fPIC" \
+        LDFLAGS="-Wl,-z,relro" \
+        PYTHON="" \
+        ../configure \
+            --build=x86_64-linux-gnu \
+            --host=x86_64-linux-gnu \
+            --prefix=$PREFIX \
+            --disable-maintainer-mode \
+            --disable-dependency-tracking \
+            --disable-silent-rules \
+            --disable-gdbtk \
+            --disable-shared \
+            --without-guile \
+            --with-system-gdbinit=$PREFIX/etc/gdb/gdbinit \
+            --with-system-readline \
+            --with-expat \
+            --with-system-zlib \
+            --with-lzma \
+            --with-babeltrace \
+            --with-intel-pt \
+            --enable-tui \
+            --with-python=python3
+    make -j$CPUS
+    make install
+    popd && popd
+fi
+
+# install pahole
+if [ ! -d $PREFIX/share/pahole-gdb ]; then
+    unzip ../archives/pahole-gdb-master.zip
+    mv pahole-gdb-master $PREFIX/share/pahole-gdb
+fi
+
+# setup system gdbinit
+if [ ! -f $PREFIX/etc/gdb/gdbinit ]; then
+    mkdir -p $PREFIX/etc/gdb
+    cat >$PREFIX/etc/gdb/gdbinit <<EOF
+# improve formatting
+set print pretty on
+set print object on
+set print static-members on
+set print vtbl on
+set print demangle on
+set demangle-style gnu-v3
+set print sevenbit-strings off
+
+# load libstdc++ pretty printers
+add-auto-load-scripts-directory $PREFIX/lib64
+add-auto-load-safe-path $PREFIX
+
+# load pahole
+python
+sys.path.insert(0, "$PREFIX/share/pahole-gdb")
+import offsets
+import pahole
+end
+EOF
+fi
+
+# compile cmake
+if [ ! -f $PREFIX/bin/cmake ]; then
+    if [ -d cmake-$CMAKE_VERSION ]; then
+        rm -rf cmake-$CMAKE_VERSION
+    fi
+    tar -xvf ../archives/cmake-$CMAKE_VERSION.tar.gz
+    pushd cmake-$CMAKE_VERSION
+    # influenced by: https://buildd.debian.org/status/fetch.php?pkg=cmake&arch=amd64&ver=3.13.4-1&stamp=1549799837
+    echo 'set(CMAKE_SKIP_RPATH ON CACHE BOOL "Skip rpath" FORCE)' >> build-flags.cmake
+    echo 'set(CMAKE_USE_RELATIVE_PATHS ON CACHE BOOL "Use relative paths" FORCE)' >> build-flags.cmake
+    echo 'set(CMAKE_C_FLAGS "-g -O2 -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2" CACHE STRING "C flags" FORCE)' >> build-flags.cmake
+    echo 'set(CMAKE_CXX_FLAGS "-g -O2 -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2" CACHE STRING "C++ flags" FORCE)' >> build-flags.cmake
+    echo 'set(CMAKE_SKIP_BOOTSTRAP_TEST ON CACHE BOOL "Skip BootstrapTest" FORCE)' >> build-flags.cmake
+    echo 'set(BUILD_CursesDialog ON CACHE BOOL "Build curses GUI" FORCE)' >> build-flags.cmake
+    mkdir build && pushd build
+    ../bootstrap \
+        --prefix=$PREFIX \
+        --init=../build-flags.cmake \
+        --parallel=$CPUS \
+        --system-curl
+    make -j$CPUS
+    # make test # run test suite
+    make install
+    popd && popd
+fi
+
+# compile cppcheck
+if [ ! -f $PREFIX/bin/cppcheck ]; then
+    if [ -d cppcheck-$CPPCHECK_VERSION ]; then
+        rm -rf cppcheck-$CPPCHECK_VERSION
+    fi
+    tar -xvf ../archives/cppcheck-$CPPCHECK_VERSION.tar.gz
+    pushd cppcheck-$CPPCHECK_VERSION
+    # this was fixed in cppcheck 2.5, remove this in toolchain-v4 after the lib is updated
+    # to 2.5+ version.
+    sed -i '/#include <iostream>/ a #include <limits>' lib/symboldatabase.cpp
+    env \
+        CC=gcc \
+        CXX=g++ \
+        PREFIX=$PREFIX \
+        FILESDIR=$PREFIX/share/cppcheck \
+        CFGDIR=$PREFIX/share/cppcheck/cfg \
+            make -j$CPUS
+    env \
+        CC=gcc \
+        CXX=g++ \
+        PREFIX=$PREFIX \
+        FILESDIR=$PREFIX/share/cppcheck \
+        CFGDIR=$PREFIX/share/cppcheck/cfg \
+            make install
+    popd
+fi
+
+# compile swig
+if [ ! -d swig-$SWIG_VERSION/install ]; then
+    if [ -d swig-$SWIG_VERSION ]; then
+        rm -rf swig-$SWIG_VERSION
+    fi
+    tar -xvf ../archives/swig-$SWIG_VERSION.tar.gz
+    mv swig-rel-$SWIG_VERSION swig-$SWIG_VERSION
+    pushd swig-$SWIG_VERSION
+    ./autogen.sh
+    mkdir build && pushd build
+    ../configure --prefix=$DIR/build/swig-$SWIG_VERSION/install
+    make -j$CPUS
+    make install
+    popd && popd
+fi
+
+# compile llvm
+if [ ! -f $PREFIX/bin/clang ]; then
+    if [ -d llvm-$LLVM_VERSION ]; then
+        rm -rf llvm-$LLVM_VERSION
+    fi
+    tar -xvf ../archives/llvm-$LLVM_VERSION.src.tar.xz
+    mv llvm-$LLVM_VERSION.src llvm-$LLVM_VERSION
+    tar -xvf ../archives/clang-$LLVM_VERSION.src.tar.xz
+    mv clang-$LLVM_VERSION.src llvm-$LLVM_VERSION/tools/clang
+    tar -xvf ../archives/lld-$LLVM_VERSION.src.tar.xz
+    mv lld-$LLVM_VERSION.src/ llvm-$LLVM_VERSION/tools/lld
+    tar -xvf ../archives/clang-tools-extra-$LLVM_VERSION.src.tar.xz
+    mv clang-tools-extra-$LLVM_VERSION.src/ llvm-$LLVM_VERSION/tools/clang/tools/extra
+    tar -xvf ../archives/compiler-rt-$LLVM_VERSION.src.tar.xz
+    mv compiler-rt-$LLVM_VERSION.src/ llvm-$LLVM_VERSION/projects/compiler-rt
+    tar -xvf ../archives/libunwind-$LLVM_VERSION.src.tar.xz
+    mv libunwind-$LLVM_VERSION.src/include/mach-o llvm-$LLVM_VERSION/tools/lld/include
+    pushd llvm-$LLVM_VERSION
+    mkdir build && pushd build
+    # activate swig
+    export PATH=$DIR/build/swig-$SWIG_VERSION/install/bin:$PATH
+    # influenced by: https://buildd.debian.org/status/fetch.php?pkg=llvm-toolchain-7&arch=amd64&ver=1%3A7.0.1%7E%2Brc2-1%7Eexp1&stamp=1541506173&raw=0
+    cmake .. \
+        -DCMAKE_C_COMPILER=$PREFIX/bin/gcc \
+        -DCMAKE_CXX_COMPILER=$PREFIX/bin/g++ \
+        -DCMAKE_CXX_LINK_FLAGS="-L$PREFIX/lib64 -Wl,-rpath,$PREFIX/lib64" \
+        -DCMAKE_INSTALL_PREFIX=$PREFIX \
+        -DCMAKE_BUILD_TYPE=RelWithDebInfo \
+        -DCMAKE_CXX_FLAGS_RELWITHDEBINFO="-O2 -DNDEBUG" \
+        -DCMAKE_CXX_FLAGS=' -fuse-ld=gold -fPIC -Wno-unused-command-line-argument -Wno-unknown-warning-option' \
+        -DCMAKE_C_FLAGS=' -fuse-ld=gold -fPIC -Wno-unused-command-line-argument -Wno-unknown-warning-option' \
+        -DLLVM_LINK_LLVM_DYLIB=ON \
+        -DLLVM_INSTALL_UTILS=ON \
+        -DLLVM_VERSION_SUFFIX= \
+        -DLLVM_BUILD_LLVM_DYLIB=ON \
+        -DLLVM_ENABLE_RTTI=ON \
+        -DLLVM_ENABLE_FFI=ON \
+        -DLLVM_BINUTILS_INCDIR=$PREFIX/include/ \
+        -DLLVM_USE_PERF=yes
+    make -j$CPUS
+    make -j$CPUS check-clang # run clang test suite
+    make -j$CPUS check-lld # run lld test suite
+    make install
+    popd && popd
+fi
+
+# create README
+if [ ! -f $PREFIX/README.md ]; then
+    cat >$PREFIX/README.md <<EOF
+# Memgraph Toolchain v$TOOLCHAIN_VERSION
+
+## Included tools
+
+ - GCC $GCC_VERSION
+ - Binutils $BINUTILS_VERSION
+ - GDB $GDB_VERSION
+ - CMake $CMAKE_VERSION
+ - Cppcheck $CPPCHECK_VERSION
+ - LLVM (Clang, LLD, compiler-rt, Clang tools extra) $LLVM_VERSION
+
+## Required libraries
+
+In order to be able to run all of these tools you should install the following
+packages:
+
+\`\`\`
+$($DIR/../os/$DISTRO.sh list TOOLCHAIN_RUN_DEPS)
+\`\`\`
+
+## Usage
+
+In order to use the toolchain you just have to source the activation script:
+
+\`\`\`
+source $PREFIX/activate
+\`\`\`
+EOF
+fi
+
+# create activation script
+if [ ! -f $PREFIX/activate ]; then
+    cat >$PREFIX/activate <<EOF
+# This file must be used with "source $PREFIX/activate" *from bash*
+# You can't run it directly!
+
+env_error="You already have an active virtual environment!"
+
+# zsh does not recognize the option -t of the command type
+# therefore we use the alternative whence -w
+if [[ "\$ZSH_NAME" == "zsh" ]]; then
+    # check for active virtual environments
+    if [ "\$( whence -w deactivate )" != "deactivate: none" ]; then
+        echo \$env_error
+        return 0;
+    fi
+# any other shell
+else
+    # check for active virtual environments
+    if [ "\$( type -t deactivate )" != "" ]; then
+        echo \$env_error
+        return 0
+    fi
+fi
+
+# check that we aren't root
+if [[ "\$USER" == "root" ]]; then
+    echo "You shouldn't use the toolchain as root!"
+    return 0
+fi
+
+# save original environment
+export ORIG_PATH=\$PATH
+export ORIG_PS1=\$PS1
+export ORIG_LD_LIBRARY_PATH=\$LD_LIBRARY_PATH
+
+# activate new environment
+export PATH=$PREFIX/bin:\$PATH
+export PS1="($NAME) \$PS1"
+export LD_LIBRARY_PATH=$PREFIX/lib:$PREFIX/lib64
+
+# disable root
+function su () {
+    echo "You don't want to use root functions while using the toolchain!"
+    return 1
+}
+function sudo () {
+    echo "You don't want to use root functions while using the toolchain!"
+    return 1
+}
+
+# create deactivation function
+function deactivate() {
+    export PATH=\$ORIG_PATH
+    export PS1=\$ORIG_PS1
+    export LD_LIBRARY_PATH=\$ORIG_LD_LIBRARY_PATH
+    unset ORIG_PATH ORIG_PS1 ORIG_LD_LIBRARY_PATH
+    unset -f su sudo deactivate
+}
+EOF
+fi
+
+# create toolchain archive
+if [ ! -f $NAME-binaries-$DISTRO.tar.gz ]; then
+    tar --owner=root --group=root -cpvzf $NAME-binaries-$DISTRO.tar.gz -C /opt $NAME
+fi
+
+# output final instructions
+echo -e "\n\n"
+echo "All tools have been built. They are installed in '$PREFIX'."
+echo "In order to distribute the tools to someone else, an archive with the toolchain was created in the 'build' directory."
+echo "If you want to install the packed tools you should execute the following command:"
+echo
+echo "    tar -xvzf build/$NAME-binaries.tar.gz -C /opt"
+echo
+echo "Because the tools were built on this machine, you should probably change the permissions of the installation directory using:"
+echo
+echo "    OPTIONAL: chown -R root:root $PREFIX"
+echo
+echo "In order to use all of the newly compiled tools you should use the prepared activation script:"
+echo
+echo "    source $PREFIX/activate"
+echo
+echo "Or, for more advanced uses, you can add the following lines to your script:"
+echo
+echo "    export PATH=$PREFIX/bin:\$PATH"
+echo "    export LD_LIBRARY_PATH=$PREFIX/lib:$PREFIX/lib64"
+echo
+echo "Enjoy!"

environment/util.sh

@@ -0,0 +1,50 @@
+#!/bin/bash
+
+operating_system() {
+    grep -E '^(VERSION_)?ID=' /etc/os-release | \
+    sort | cut -d '=' -f 2- | sed 's/"//g' | paste -s -d '-'
+}
+
+check_all_yum() {
+    local missing=""
+    for pkg in $1; do
+        if ! yum list installed "$pkg" >/dev/null 2>/dev/null; then
+            missing="$pkg $missing"
+        fi
+    done
+    if [ "$missing" != "" ]; then
+        echo "MISSING PACKAGES: $missing"
+        exit 1
+    fi
+}
+
+check_all_dpkg() {
+    local missing=""
+    for pkg in $1; do
+        if ! dpkg -s "$pkg" >/dev/null 2>/dev/null; then
+            missing="$pkg $missing"
+        fi
+    done
+    if [ "$missing" != "" ]; then
+        echo "MISSING PACKAGES: $missing"
+        exit 1
+    fi
+}
+
+check_all_dnf() {
+    local missing=""
+    for pkg in $1; do
+        if ! dnf list installed "$pkg" >/dev/null 2>/dev/null; then
+            missing="$pkg $missing"
+        fi
+    done
+    if [ "$missing" != "" ]; then
+        echo "MISSING PACKAGES: $missing"
+        exit 1
+    fi
+}
+install_all_apt() {
+    for pkg in $1; do
+        apt install -y "$pkg"
+    done
+}

include/mgp.py

@@ -64,6 +64,13 @@ class Properties:
         self._len = None
         self._vertex_or_edge = vertex_or_edge
 
+    def __deepcopy__(self, memo):
+        # This is the same as the shallow copy, as the underlying C API should
+        # not support deepcopy. Besides, it doesn't make much sense to actually
+        # copy _mgp.Edge and _mgp.Vertex types as they are actually references
+        # to graph elements and not proper values.
+        return Properties(self._vertex_or_edge)
+
     def get(self, property_name: str, default=None) -> object:
         '''Get the value of a property with the given name or return default.
 
@@ -183,7 +190,8 @@ class Edge:
 
     def __init__(self, edge):
         if not isinstance(edge, _mgp.Edge):
-            raise TypeError("Expected '_mgp.Edge', got '{}'".format(type(edge)))
+            raise TypeError(
+                "Expected '_mgp.Edge', got '{}'".format(type(edge)))
         self._edge = edge
 
     def __deepcopy__(self, memo):
@@ -236,6 +244,8 @@ class Edge:
         '''Raise InvalidContextError.'''
         if not self.is_valid():
             raise InvalidContextError()
+        if not isinstance(other, Edge):
+            return NotImplemented
         return self._edge == other._edge
 
     def __hash__(self) -> int:
@@ -259,7 +269,8 @@ class Vertex:
 
     def __init__(self, vertex):
         if not isinstance(vertex, _mgp.Vertex):
-            raise TypeError("Expected '_mgp.Vertex', got '{}'".format(type(vertex)))
+            raise TypeError(
+                "Expected '_mgp.Vertex', got '{}'".format(type(vertex)))
         self._vertex = vertex
 
     def __deepcopy__(self, memo):
@@ -325,6 +336,8 @@ class Vertex:
         '''Raise InvalidContextError'''
         if not self.is_valid():
             raise InvalidContextError()
+        if not isinstance(other, Vertex):
+            return NotImplemented
         return self._vertex == other._vertex
 
     def __hash__(self) -> int:
@@ -372,8 +385,8 @@ class Path:
             pass
         # This is the same as the shallow copy, as the underlying C API should
         # not support deepcopy. Besides, it doesn't make much sense to actually
-        # copy Edge and Vertex types as they are actually references to graph
-        # elements and not proper values.
+        # copy _mgp.Edge and _mgp.Vertex types as they are actually references
+        # to graph elements and not proper values.
         path = self.__copy__()
         memo[id(self._path)] = path._path
         return path
@@ -393,7 +406,8 @@ class Path:
         passed in edge is invalid.
         '''
         if not isinstance(edge, Edge):
-            raise TypeError("Expected '_mgp.Edge', got '{}'".format(type(edge)))
+            raise TypeError(
+                "Expected '_mgp.Edge', got '{}'".format(type(edge)))
         if not self.is_valid() or not edge.is_valid():
             raise InvalidContextError()
         self._path.expand(edge._edge)
@@ -443,7 +457,8 @@ class Vertices:
 
     def __init__(self, graph):
         if not isinstance(graph, _mgp.Graph):
-            raise TypeError("Expected '_mgp.Graph', got '{}'".format(type(graph)))
+            raise TypeError(
+                "Expected '_mgp.Graph', got '{}'".format(type(graph)))
         self._graph = graph
         self._len = None
 
@@ -471,7 +486,7 @@ class Vertices:
 
     def __contains__(self, vertex):
         try:
-            _ = self.graph.get_vertex_by_id(vertex.id)
+            _ = self._graph.get_vertex_by_id(vertex.id)
             return True
         except IndexError:
             return False
@@ -488,7 +503,8 @@ class Graph:
 
     def __init__(self, graph):
         if not isinstance(graph, _mgp.Graph):
-            raise TypeError("Expected '_mgp.Graph', got '{}'".format(type(graph)))
+            raise TypeError(
+                "Expected '_mgp.Graph', got '{}'".format(type(graph)))
         self._graph = graph
 
     def __deepcopy__(self, memo):
@@ -546,7 +562,8 @@ class ProcCtx:
 
     def __init__(self, graph):
         if not isinstance(graph, _mgp.Graph):
-            raise TypeError("Expected '_mgp.Graph', got '{}'".format(type(graph)))
+            raise TypeError(
+                "Expected '_mgp.Graph', got '{}'".format(type(graph)))
         self._graph = Graph(graph)
 
     def is_valid(self) -> bool:
@@ -616,8 +633,11 @@ def _typing_to_cypher_type(type_):
         if complex_type == typing.Union:
             # If we have a Union with NoneType inside, it means we are building
             # a nullable type.
-            if isinstance(None, type_args):
-                types = tuple(t for t in type_args if not isinstance(None, t))
+            # isinstance doesn't work here because subscripted generics cannot
+            # be used with class and instance checks. type comparison should be
+            # fine because subclasses are not used.
+            if type(None) in type_args:
+                types = tuple(t for t in type_args if t is not type(None))  # noqa E721
                 if len(types) == 1:
                     type_arg, = types
                 else:
@@ -662,17 +682,27 @@ def _typing_to_cypher_type(type_):
                 type_args_as_str = parse_type_args(type_as_str)
                 none_type_as_str = type(None).__name__
                 if none_type_as_str in type_args_as_str:
-                    types = tuple(t for t in type_args_as_str if t != none_type_as_str)
+                    types = tuple(
+                        t for t in type_args_as_str if t != none_type_as_str)
                     if len(types) == 1:
                         type_arg_as_str, = types
                     else:
-                        type_arg_as_str = 'typing.Union[' + ', '.join(types) + ']'
+                        type_arg_as_str = 'typing.Union[' + \
+                            ', '.join(types) + ']'
                     simple_type = get_simple_type(type_arg_as_str)
                     if simple_type is not None:
                         return _mgp.type_nullable(simple_type)
                     return _mgp.type_nullable(parse_typing(type_arg_as_str))
             elif type_as_str.startswith('typing.List'):
-                type_arg_as_str, = parse_type_args(type_as_str)
+                type_arg_as_str = parse_type_args(type_as_str)
+
+                if len(type_arg_as_str) > 1:
+                    # Nested object could be a type consisting of a list of types (e.g. mgp.Map)
+                    # so we need to join the parts.
+                    type_arg_as_str = ', '.join(type_arg_as_str)
+                else:
+                    type_arg_as_str = type_arg_as_str[0]
+
                 simple_type = get_simple_type(type_arg_as_str)
                 if simple_type is not None:
                     return _mgp.type_list(simple_type)
@@ -692,6 +722,19 @@ class Deprecated:
         self.field_type = type_
 
 
+def raise_if_does_not_meet_requirements(func: typing.Callable[..., Record]):
+    if not callable(func):
+        raise TypeError("Expected a callable object, got an instance of '{}'"
+                        .format(type(func)))
+    if inspect.iscoroutinefunction(func):
+        raise TypeError("Callable must not be 'async def' function")
+    if sys.version_info >= (3, 6):
+        if inspect.isasyncgenfunction(func):
+            raise TypeError("Callable must not be 'async def' function")
+    if inspect.isgeneratorfunction(func):
+        raise NotImplementedError("Generator functions are not supported")
+
+
 def read_proc(func: typing.Callable[..., Record]):
     '''
     Register `func` as a a read-only procedure of the current module.
@@ -732,16 +775,7 @@ def read_proc(func: typing.Callable[..., Record]):
       CALL example.procedure(1) YIELD args, result;
     Naturally, you may pass in different arguments or yield less fields.
     '''
-    if not callable(func):
-        raise TypeError("Expected a callable object, got an instance of '{}'"
-                        .format(type(func)))
-    if inspect.iscoroutinefunction(func):
-        raise TypeError("Callable must not be 'async def' function")
-    if sys.version_info >= (3, 6):
-        if inspect.isasyncgenfunction(func):
-            raise TypeError("Callable must not be 'async def' function")
-    if inspect.isgeneratorfunction(func):
-        raise NotImplementedError("Generator functions are not supported")
+    raise_if_does_not_meet_requirements(func)
     sig = inspect.signature(func)
     params = tuple(sig.parameters.values())
     if params and params[0].annotation is ProcCtx:
@@ -777,3 +811,133 @@ def read_proc(func: typing.Callable[..., Record]):
             else:
                 mgp_proc.add_result(name, _typing_to_cypher_type(type_))
     return func
+
+
+class InvalidMessageError(Exception):
+    '''Signals using a message instance outside of the registered transformation.'''
+    pass
+
+
+class Message:
+    '''Represents a message from a stream.'''
+    __slots__ = ('_message',)
+
+    def __init__(self, message):
+        if not isinstance(message, _mgp.Message):
+            raise TypeError(
+                "Expected '_mgp.Message', got '{}'".format(type(message)))
+        self._message = message
+
+    def __deepcopy__(self, memo):
+        # This is the same as the shallow copy, because we want to share the
+        # underlying C struct. Besides, it doesn't make much sense to actually
+        # copy _mgp.Messages as that always references all the messages.
+        return Message(self._message)
+
+    def is_valid(self) -> bool:
+        '''Return True if `self` is in valid context and may be used.'''
+        return self._message.is_valid()
+
+    def payload(self) -> bytes:
+        if not self.is_valid():
+            raise InvalidMessageError()
+        return self._message.payload()
+
+    def topic_name(self) -> str:
+        if not self.is_valid():
+            raise InvalidMessageError()
+        return self._message.topic_name()
+
+    def key(self) -> bytes:
+        if not self.is_valid():
+            raise InvalidMessageError()
+        return self._message.key()
+
+    def timestamp(self) -> int:
+        if not self.is_valid():
+            raise InvalidMessageError()
+        return self._message.timestamp()
+
+
+class InvalidMessagesError(Exception):
+    '''Signals using a messages instance outside of the registered transformation.'''
+    pass
+
+
+class Messages:
+    '''Represents a list of messages from a stream.'''
+    __slots__ = ('_messages',)
+
+    def __init__(self, messages):
+        if not isinstance(messages, _mgp.Messages):
+            raise TypeError(
+                "Expected '_mgp.Messages', got '{}'".format(type(messages)))
+        self._messages = messages
+
+    def __deepcopy__(self, memo):
+        # This is the same as the shallow copy, because we want to share the
+        # underlying C struct. Besides, it doesn't make much sense to actually
+        # copy _mgp.Messages as that always references all the messages.
+        return Messages(self._messages)
+
+    def is_valid(self) -> bool:
+        '''Return True if `self` is in valid context and may be used.'''
+        return self._messages.is_valid()
+
+    def message_at(self, id: int) -> Message:
+        '''Raise InvalidMessagesError if context is invalid.'''
+        if not self.is_valid():
+            raise InvalidMessagesError()
+        return Message(self._messages.message_at(id))
+
+    def total_messages(self) -> int:
+        '''Raise InvalidContextError if context is invalid.'''
+        if not self.is_valid():
+            raise InvalidMessagesError()
+        return self._messages.total_messages()
+
+
+class TransCtx:
+    '''Context of a transformation being executed.
+
+    Access to a TransCtx is only valid during a single execution of a transformation.
+    You should not globally store a TransCtx instance.
+    '''
+    __slots__ = ('_graph')
+
+    def __init__(self, graph):
+        if not isinstance(graph, _mgp.Graph):
+            raise TypeError(
+                "Expected '_mgp.Graph', got '{}'".format(type(graph)))
+        self._graph = Graph(graph)
+
+    def is_valid(self) -> bool:
+        return self._graph.is_valid()
+
+    @property
+    def graph(self) -> Graph:
+        '''Raise InvalidContextError if context is invalid.'''
+        if not self.is_valid():
+            raise InvalidContextError()
+        return self._graph
+
+
+def transformation(func: typing.Callable[..., Record]):
+    raise_if_does_not_meet_requirements(func)
+    sig = inspect.signature(func)
+    params = tuple(sig.parameters.values())
+    if not params or not params[0].annotation is Messages:
+        if not len(params) == 2 or not params[1].annotation is Messages:
+            raise NotImplementedError(
+                "Valid signatures for transformations are (TransCtx, Messages) or (Messages)")
+    if params[0].annotation is TransCtx:
+        @functools.wraps(func)
+        def wrapper(graph, messages):
+            return func(TransCtx(graph), messages)
+        _mgp._MODULE.add_transformation(wrapper)
+    else:
+        @functools.wraps(func)
+        def wrapper(graph, messages):
+            return func(messages)
+        _mgp._MODULE.add_transformation(wrapper)
+    return func

init

@@ -1,35 +1,14 @@
 #!/bin/bash -e
 
-required_pkgs=(git arcanist # 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
-               libssl-dev
-               libseccomp-dev
-               python3 python-virtualenv python3-pip # for qa, macro_benchmark and stress tests
-               python3-yaml # for the configuration generator
-               uuid-dev # mg-utils
-               libcurl4-openssl-dev # mg-requests
-               sbcl # for custom Lisp C++ preprocessing
-               php-xml # for arcanist linters
-              )
-
-optional_pkgs=(doxygen graphviz # source documentation generators
-               php-cli # for user technical documentation generators
-               mono-runtime mono-mcs nodejs # for driver tests
-              )
-
-use_sudo=0
-
 DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
 cd "$DIR"
 
+source "$DIR/environment/util.sh"
+
 function print_help () {
     echo "Usage: $0 [OPTION]"
-    echo -e "Check for missing packages and install them if possible.\n"
+    echo -e "Check for missing packages and setup the project.\n"
     echo "Optional arguments:"
-    echo -e "  -s\tuse sudo apt-get for installing packages"
     echo -e "  -h\tdisplay this help and exit"
 }
 
@@ -45,10 +24,7 @@ function setup_virtualenv () {
     # create new virtualenv
     virtualenv -p python3 ve3 || exit 1
     source ve3/bin/activate
-    # we need to increase the timeout for pip because our local cache server
-    # can sometimes be stupid, see: https://github.com/devpi/devpi/issues/208
-    pip --timeout 1000 install -i http://deps.memgraph.io:3141/root/pypi \
-                --trusted-host deps.memgraph.io -r requirements.txt || exit 1
+    pip --timeout 1000 install -r requirements.txt || exit 1
     deactivate
 
     popd > /dev/null
@@ -59,9 +35,6 @@ if [[ $# -gt 1 ]]; then
     exit 1
 elif  [[ $# -eq 1 ]]; then
     case "$1" in
-      -s)
-          use_sudo=1
-      ;;
       -h)
           print_help
           exit 0
@@ -74,39 +47,10 @@ elif  [[ $# -eq 1 ]]; then
   esac
 fi
 
-echo "Started installing dependencies for Memgraph"
-
-required_missing=0
-
-# install all dependencies on debian based operating systems
-for pkg in ${required_pkgs[@]}; do
-    if dpkg -s $pkg 2>/dev/null >/dev/null; then
-        echo "Found $pkg"
-    elif (( $use_sudo )); then
-        echo "Installing $pkg"
-        if [[ ! `sudo apt-get -y install $pkg` ]]; then
-            echo "Didn't install $pkg [required]"
-            required_missing=1
-        fi
-    else
-        echo "Missing $pkg [required]"
-        required_missing=1
-    fi
-done
-
-for pkg in ${optional_pkgs[@]}; do
-    if dpkg -s $pkg 2>/dev/null >/dev/null; then
-        echo "Found $pkg [optional]"
-    else
-        echo "Missing $pkg [optional]"
-    fi
-done
-
-if (( $required_missing )); then
-    echo "Missing required packages. EXITING!"
-    echo "Please, install required packages and rerun $0 again."
-    exit 2
-fi
+DISTRO=$(operating_system)
+echo "ALL BUILD PACKAGES: $($DIR/environment/os/$DISTRO.sh list MEMGRAPH_BUILD_DEPS)"
+$DIR/environment/os/$DISTRO.sh check MEMGRAPH_BUILD_DEPS
+echo "All packages are in-place..."
 
 # create a default build directory
 mkdir -p ./build
@@ -136,14 +80,14 @@ echo \
   (ql:quickload '(:lcp :lcp/test) :silent t)
   " | sbcl --script
 
-# setup libs (download)
+# Setup libs (download).
 cd libs
 ./cleanup.sh
 ./setup.sh
 cd ..
 
-# setup qa dependencies
-setup_virtualenv tests/qa
+# setup gql_behave dependencies
+setup_virtualenv tests/gql_behave
 
 # setup stress dependencies
 setup_virtualenv tests/stress
@@ -151,4 +95,18 @@ setup_virtualenv tests/stress
 # setup integration/ldap dependencies
 setup_virtualenv tests/integration/ldap
 
+# Setup tests dependencies.
+# cd tests
+# ./setup.sh
+# cd ..
+# TODO(gitbuda): Remove setup_virtualenv, replace it with tests/ve3. Take care
+# of the build order because tests/setup.py builds pymgclient which depends on
+# mgclient which is build after this script by calling make.
+
 echo "Done installing dependencies for Memgraph"
+
+echo "Linking git hooks"
+for hook in $(find $DIR/.githooks -type f -printf "%f\n"); do
+  ln -s -f "$DIR/.githooks/$hook" "$DIR/.git/hooks/$hook"
+  echo "Added $hook hook"
+done;

libs/.gitignore

@@ -4,3 +4,4 @@
 !cleanup.sh
 !CMakeLists.txt
 !__main.cpp
+!jemalloc.cmake

libs/CMakeLists.txt

@@ -1,11 +1,15 @@
 include(ExternalProject)
 
+include(GNUInstallDirs)
+
 include(ProcessorCount)
 ProcessorCount(NPROC)
 if (NPROC EQUAL 0)
   set(NPROC 1)
 endif()
 
+set(LIB_DIR ${CMAKE_CURRENT_SOURCE_DIR})
+
 # convenience functions
 function(import_header_library name include_dir)
   add_library(${name} INTERFACE IMPORTED GLOBAL)
@@ -87,11 +91,9 @@ import_external_library(antlr4 STATIC
   CMAKE_ARGS # http://stackoverflow.com/questions/37096062/get-a-basic-c-program-to-compile-using-clang-on-ubuntu-16/38385967#38385967
              -DWITH_LIBCXX=OFF # because of debian bug
              -DCMAKE_SKIP_INSTALL_ALL_DEPENDENCY=true
+             -DCMAKE_CXX_STANDARD=20
   BUILD_COMMAND $(MAKE) antlr4_static
-  # Make a License.txt out of thin air, so that antlr4.6 knows how to build.
-  # When we upgrade antlr, this will no longer be needed.
-  INSTALL_COMMAND touch ${CMAKE_CURRENT_SOURCE_DIR}/antlr4/runtime/Cpp/License.txt
-  COMMAND $(MAKE) install)
+  INSTALL_COMMAND $(MAKE) install)
 
 # Setup google benchmark.
 import_external_library(benchmark STATIC
@@ -102,7 +104,7 @@ import_external_library(benchmark STATIC
 
 # setup fmt format
 import_external_library(fmt STATIC
-  ${CMAKE_CURRENT_SOURCE_DIR}/fmt/lib/libfmt.a
+  ${CMAKE_CURRENT_SOURCE_DIR}/fmt/${CMAKE_INSTALL_LIBDIR}/libfmt.a
   ${CMAKE_CURRENT_SOURCE_DIR}/fmt/include
   # Skip testing.
   CMAKE_ARGS -DFMT_TEST=OFF)
@@ -149,24 +151,6 @@ import_external_library(gflags STATIC
              -DBUILD_gflags_nothreads_LIB=OFF
              -DGFLAGS_NO_FILENAMES=${GFLAGS_NO_FILENAMES})
 
-# Setup google logging after gflags (so that glog can use it).
-set(GLOG_DISABLE_OPTIONS "0")
-if ("${CMAKE_BUILD_TYPE}" MATCHES "^(R|r)(E|e)(L|l).+")
-  set(GLOG_DISABLE_OPTIONS "1")
-endif()
-
-# Setup google logging after gflags (so that glog can use it).
-import_external_library(glog STATIC
-  ${CMAKE_CURRENT_SOURCE_DIR}/glog/lib/libglog.a
-  ${CMAKE_CURRENT_SOURCE_DIR}/glog/include
-  DEPENDS gflags-proj
-  CMAKE_ARGS -Dgflags_DIR=${CMAKE_CURRENT_SOURCE_DIR}/gflags/lib/cmake/gflags
-             -DBUILD_TESTING=OFF
-             -DGLOG_NO_FILENAMES=${GLOG_DISABLE_OPTIONS}
-             -DGLOG_NO_STACKTRACE=${GLOG_DISABLE_OPTIONS}
-             -DGLOG_NO_BUFFER_SETTINGS=${GLOG_DISABLE_OPTIONS}
-             -DGLOG_NO_TIME_PID_FILENAME=${GLOG_DISABLE_OPTIONS})
-
 # Setup cppitertools
 import_header_library(cppitertools ${CMAKE_CURRENT_SOURCE_DIR})
 
@@ -195,7 +179,9 @@ import_external_library(zlib STATIC
 import_external_library(rocksdb STATIC
   ${CMAKE_CURRENT_SOURCE_DIR}/rocksdb/lib/librocksdb.a
   ${CMAKE_CURRENT_SOURCE_DIR}/rocksdb/include
-  CMAKE_ARGS -DUSE_RTTI=ON
+  DEPENDS gflags-proj
+  CMAKE_ARGS -Dgflags_DIR=${CMAKE_CURRENT_SOURCE_DIR}/gflags/lib/cmake/gflags
+             -DUSE_RTTI=ON
              -DWITH_TESTS=OFF
              -DCMAKE_INSTALL_LIBDIR=lib
              -DCMAKE_SKIP_INSTALL_ALL_DEPENDENCY=true
@@ -220,3 +206,38 @@ import_external_library(mgclient STATIC
              -DBUILD_TESTING=OFF)
 find_package(OpenSSL REQUIRED)
 target_link_libraries(mgclient INTERFACE ${OPENSSL_LIBRARIES})
+
+add_external_project(mgconsole
+  SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/mgconsole
+  CMAKE_ARGS
+    -DCMAKE_INSTALL_PREFIX:PATH=${CMAKE_BINARY_DIR}
+  BUILD_COMMAND $(MAKE) mgconsole)
+
+add_custom_target(mgconsole DEPENDS mgconsole-proj)
+
+# Setup spdlog
+import_external_library(spdlog STATIC
+  ${CMAKE_CURRENT_SOURCE_DIR}/spdlog/${CMAKE_INSTALL_LIBDIR}/libspdlog.a
+  ${CMAKE_CURRENT_SOURCE_DIR}/spdlog/include
+  BUILD_COMMAND $(MAKE) spdlog)
+
+include(jemalloc.cmake)
+
+# Setup librdkafka.
+import_external_library(librdkafka STATIC
+  ${CMAKE_CURRENT_SOURCE_DIR}/librdkafka/lib/librdkafka.a
+  ${CMAKE_CURRENT_SOURCE_DIR}/librdkafka/include
+  CMAKE_ARGS -DRDKAFKA_BUILD_STATIC=ON
+             -DRDKAFKA_BUILD_EXAMPLES=OFF
+             -DRDKAFKA_BUILD_TESTS=OFF
+             -DCMAKE_INSTALL_LIBDIR=lib
+             -DWITH_SSL=ON
+             # If we want SASL, we need to install it on build machines
+             -DWITH_SASL=OFF)
+target_link_libraries(librdkafka INTERFACE ${OPENSSL_LIBRARIES} zlib)
+
+import_library(librdkafka++ STATIC
+  ${CMAKE_CURRENT_SOURCE_DIR}/librdkafka/lib/librdkafka++.a
+  ${CMAKE_CURRENT_SOURCE_DIR}/librdkafka/include
+)
+target_link_libraries(librdkafka++ INTERFACE librdkafka)

libs/jemalloc.cmake

@@ -0,0 +1,55 @@
+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

@@ -1,9 +1,11 @@
 #!/bin/bash -e
 
 # Download external dependencies.
+# Don't forget to add/update the license in release/third-party-licenses of added/updated libs!
 
+local_cache_host=${MGDEPS_CACHE_HOST_PORT:-mgdeps-cache:8000}
 working_dir="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
-cd ${working_dir}
+cd "${working_dir}"
 
 # Clones a git repository and optionally cherry picks additional commits. The
 # function will try to preserve any local changes in the repo.
@@ -15,7 +17,11 @@ clone () {
   shift 3
   # Clone if there's no repo.
   if [[ ! -d "$dir_name" ]]; then
-    git clone "$git_repo" "$dir_name"
+    echo "Cloning from $git_repo"
+    # If the clone fails, it doesn't make sense to continue with the function
+    # execution but the whole script should continue executing because we might
+    # clone the same repo from a different source.
+    git clone "$git_repo" "$dir_name" || return 1
   fi
   pushd "$dir_name"
   # Just fetch new commits from remote repository. Don't merge/pull them in, so
@@ -29,12 +35,17 @@ clone () {
   # Stash regardless of local_changes, so that a user gets a message on stdout.
   git stash
   # Checkout the primary commit (there's no need to pull/merge).
-  git checkout $checkout_id
+  # The checkout fail should exit this script immediately because the target
+  # commit is not there and that will most likely create build-time errors.
+  git checkout "$checkout_id" || exit 1
   # Apply any optional cherry pick fixes.
   while [[ $# -ne 0 ]]; do
     local cherry_pick_id=$1
     shift
-    git cherry-pick -n $cherry_pick_id
+    # The cherry-pick fail should exit this script immediately because the
+    # target commit is not there and that will most likely create build-time
+    # errors.
+    git cherry-pick -n "$cherry_pick_id" || exit 1
   done
   # Reapply any local changes.
   if [[ $local_changes == true ]]; then
@@ -43,96 +54,198 @@ clone () {
   popd
 }
 
+file_get_try_double () {
+    primary_url="$1"
+    secondary_url="$2"
+    echo "Download primary from $primary_url secondary from $secondary_url"
+    if [ -z "$primary_url" ]; then echo "Primary should not be empty." && exit 1; fi
+    if [ -z "$secondary_url" ]; then echo "Secondary should not be empty." && exit 1; fi
+    filename="$(basename "$secondary_url")"
+    wget -nv "$primary_url" -O "$filename" || wget -nv "$secondary_url" -O "$filename" || exit 1
+    echo ""
+}
+
+repo_clone_try_double () {
+    primary_url="$1"
+    secondary_url="$2"
+    folder_name="$3"
+    ref="$4"
+    echo "Cloning primary from $primary_url secondary from $secondary_url"
+    if [ -z "$primary_url" ]; then echo "Primary should not be empty." && exit 1; fi
+    if [ -z "$secondary_url" ]; then echo "Secondary should not be empty." && exit 1; fi
+    if [ -z "$folder_name" ]; then echo "Clone folder should not be empty." && exit 1; fi
+    if [ -z "$ref" ]; then echo "Git clone ref should not be empty." && exit 1; fi
+    clone "$primary_url" "$folder_name" "$ref" || clone "$secondary_url" "$folder_name" "$ref" || exit 1
+    echo ""
+}
+
+# List all dependencies.
+
+# The reason for introducing primary and secondary urls are:
+#   * HTTPS is hard to cache
+#   * Remote development workflow is more flexible if people don't have to connect to VPN
+#   * Direct download from the "source of truth" is slower and unreliable because of the whole internet in-between
+#   * When a new dependency has to be added, both urls could be the same, later someone could optimize if required
+
+# The goal of having primary urls is to have links to the "local" cache of
+# dependencies where these dependencies could be downloaded as fast as
+# possible. The actual cache server could be on your local machine, on a
+# dedicated machine inside the build cluster or on the actual build machine.
+# Download from primary_urls might fail because the cache is not installed.
+declare -A primary_urls=(
+  ["antlr4-code"]="http://$local_cache_host/git/antlr4.git"
+  ["antlr4-generator"]="http://$local_cache_host/file/antlr-4.9.2-complete.jar"
+  ["cppitertools"]="http://$local_cache_host/git/cppitertools.git"
+  ["fmt"]="http://$local_cache_host/git/fmt.git"
+  ["rapidcheck"]="http://$local_cache_host/git/rapidcheck.git"
+  ["gbenchmark"]="http://$local_cache_host/git/benchmark.git"
+  ["gtest"]="http://$local_cache_host/git/googletest.git"
+  ["gflags"]="http://$local_cache_host/git/gflags.git"
+  ["libbcrypt"]="http://$local_cache_host/git/libbcrypt.git"
+  ["bzip2"]="http://$local_cache_host/git/bzip2.git"
+  ["zlib"]="http://$local_cache_host/git/zlib.git"
+  ["rocksdb"]="http://$local_cache_host/git/rocksdb.git"
+  ["mgclient"]="http://$local_cache_host/git/mgclient.git"
+  ["pymgclient"]="http://$local_cache_host/git/pymgclient.git"
+  ["mgconsole"]="http://$local_cache_host/git/mgconsole.git"
+  ["spdlog"]="http://$local_cache_host/git/spdlog"
+  ["jemalloc"]="http://$local_cache_host/git/jemalloc.git"
+  ["nlohmann"]="http://$local_cache_host/file/nlohmann/json/b3e5cb7f20dcc5c806e418df34324eca60d17d4e/single_include/nlohmann/json.hpp"
+  ["neo4j"]="http://$local_cache_host/file/neo4j-community-3.2.3-unix.tar.gz"
+  ["librdkafka"]="http://$local_cache_host/git/librdkafka.git"
+)
+
+# The goal of secondary urls is to have links to the "source of truth" of
+# dependencies, e.g., Github or S3. Download from secondary urls, if happens
+# at all, should never fail. In other words, if it fails, the whole build
+# 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"
+  ["cppitertools"]="https://github.com/ryanhaining/cppitertools.git"
+  ["fmt"]="https://github.com/fmtlib/fmt.git"
+  ["rapidcheck"]="https://github.com/emil-e/rapidcheck.git"
+  ["gbenchmark"]="https://github.com/google/benchmark.git"
+  ["gtest"]="https://github.com/google/googletest.git"
+  ["gflags"]="https://github.com/memgraph/gflags.git"
+  ["libbcrypt"]="https://github.com/rg3/libbcrypt"
+  ["bzip2"]="https://github.com/VFR-maniac/bzip2"
+  ["zlib"]="https://github.com/madler/zlib.git"
+  ["rocksdb"]="https://github.com/facebook/rocksdb.git"
+  ["mgclient"]="https://github.com/memgraph/mgclient.git"
+  ["pymgclient"]="https://github.com/memgraph/pymgclient.git"
+  ["mgconsole"]="http://github.com/memgraph/mgconsole.git"
+  ["spdlog"]="https://github.com/gabime/spdlog"
+  ["jemalloc"]="https://github.com/jemalloc/jemalloc.git"
+  ["nlohmann"]="https://raw.githubusercontent.com/nlohmann/json/b3e5cb7f20dcc5c806e418df34324eca60d17d4e/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"
+)
+
 # antlr
-antlr_generator_filename="antlr-4.6-complete.jar"
-# wget -O ${antlr_generator_filename} http://www.antlr.org/download/${antlr_generator_filename}
-wget -nv -O ${antlr_generator_filename} http://deps.memgraph.io/${antlr_generator_filename}
-# git clone https://github.com/antlr/antlr4.git
-antlr4_tag="aacd2a2c95816d8dc1c05814051d631bfec4cf3e" # v4.6
-clone git://deps.memgraph.io/antlr4.git antlr4 $antlr4_tag
-# fix missing include
-sed -i 's/^#pragma once/#pragma once\n#include <functional>/' antlr4/runtime/Cpp/runtime/src/support/CPPUtils.h
+file_get_try_double "${primary_urls[antlr4-generator]}" "${secondary_urls[antlr4-generator]}"
+
+antlr4_tag="5e5b6d35b4183fd330102c40947b95c4b5c6abb5" # v4.9.2
+repo_clone_try_double "${primary_urls[antlr4-code]}" "${secondary_urls[antlr4-code]}" "antlr4" "$antlr4_tag"
 # remove shared library from install dependencies
 sed -i 's/install(TARGETS antlr4_shared/install(TARGETS antlr4_shared OPTIONAL/' antlr4/runtime/Cpp/runtime/CMakeLists.txt
+# fix issue https://github.com/antlr/antlr4/issues/3194 - should update Antlr commit once the PR related to the issue gets merged
+sed -i 's/std::is_nothrow_copy_constructible/std::is_copy_constructible/' antlr4/runtime/Cpp/runtime/src/support/Any.h
+# replace the utf8cpp version which is used because the older one uses gtest that doesn't 
+# compile with the newer compilers because of uninitialized variable
+# the newer utf8cpp switched to ftest
+sed -i 's/v3.1.1/v3.2.1/' antlr4/runtime/Cpp/runtime/CMakeLists.txt
 
-# cppitertools
-# Use our fork that uses experimental/optional instead of unique_ptr in
-# DerefHolder. Once we move memgraph to c++17 we can use cpp17 branch from
-# original repo.
-# git clone https://github.com/memgraph/cppitertools.git
-cppitertools_tag="4231e0bc6fba2737b2a7a8a1576cf06186b0de6a" # experimental_optional 17 Aug 2017
-clone git://deps.memgraph.io/cppitertools.git cppitertools $cppitertools_tag
+# cppitertools v2.0 2019-12-23
+cppitertools_ref="cb3635456bdb531121b82b4d2e3afc7ae1f56d47"
+repo_clone_try_double "${primary_urls[cppitertools]}" "${secondary_urls[cppitertools]}" "cppitertools" "$cppitertools_ref"
 
 # fmt
-# git clone https://github.com/fmtlib/fmt.git
-fmt_tag="7fa8f8fa48b0903deab5bb42e6760477173ac485" # v3.0.1
-# Commit which fixes an issue when compiling with C++14 and higher.
-fmt_cxx14_fix="b9aaa507fc49680d037fd84c043f747a395bce04"
-clone git://deps.memgraph.io/fmt.git fmt $fmt_tag $fmt_cxx14_fix
+fmt_tag="7bdf0628b1276379886c7f6dda2cef2b3b374f0b" # (2020-11-25)
+repo_clone_try_double "${primary_urls[fmt]}" "${secondary_urls[fmt]}" "fmt" "$fmt_tag"
 
 # rapidcheck
-# git clone https://github.com/emil-e/rapidcheck.git
-rapidcheck_tag="853e14f0f4313a9eb3c71e24848373e7b843dfd1" # Jun 23, 2017
-clone git://deps.memgraph.io/rapidcheck.git rapidcheck $rapidcheck_tag
+rapidcheck_tag="7bc7d302191a4f3d0bf005692677126136e02f60" # (2020-05-04)
+repo_clone_try_double "${primary_urls[rapidcheck]}" "${secondary_urls[rapidcheck]}" "rapidcheck" "$rapidcheck_tag"
 
 # google benchmark
-# git clone https://github.com/google/benchmark.git
 benchmark_tag="4f8bfeae470950ef005327973f15b0044eceaceb" # v1.1.0
-clone git://deps.memgraph.io/benchmark.git benchmark $benchmark_tag
+repo_clone_try_double "${primary_urls[gbenchmark]}" "${secondary_urls[gbenchmark]}" "benchmark" "$benchmark_tag"
 
 # google test
-# git clone https://github.com/google/googletest.git
 googletest_tag="ec44c6c1675c25b9827aacd08c02433cccde7780" # v1.8.0
-clone git://deps.memgraph.io/googletest.git googletest $googletest_tag
-
-# google logging
-# git clone https://github.com/memgraph/glog.git
-glog_tag="042a21657e79784226babab8b942f7bd0949635f" # custom version (v0.3.5+)
-clone git://deps.memgraph.io/glog.git glog $glog_tag
+repo_clone_try_double "${primary_urls[gtest]}" "${secondary_urls[gtest]}" "googletest" "$googletest_tag"
 
 # google flags
-# git clone https://github.com/memgraph/gflags.git
 gflags_tag="b37ceb03a0e56c9f15ce80409438a555f8a67b7c" # custom version (May 6, 2017)
-clone git://deps.memgraph.io/gflags.git gflags $gflags_tag
+repo_clone_try_double "${primary_urls[gflags]}" "${secondary_urls[gflags]}" "gflags" "$gflags_tag"
 
 # libbcrypt
-# git clone https://github.com/rg3/libbcrypt
 libbcrypt_tag="8aa32ad94ebe06b76853b0767c910c9fbf7ccef4" # custom version (Dec 16, 2016)
-clone git://deps.memgraph.io/libbcrypt.git libbcrypt $libbcrypt_tag
+repo_clone_try_double "${primary_urls[libbcrypt]}" "${secondary_urls[libbcrypt]}" "libbcrypt" "$libbcrypt_tag"
 
 # neo4j
-wget -nv http://deps.memgraph.io/neo4j-community-3.2.3-unix.tar.gz -O neo4j.tar.gz
-tar -xzf neo4j.tar.gz
-rm -rf neo4j
+file_get_try_double "${primary_urls[neo4j]}" "${secondary_urls[neo4j]}"
+tar -xzf neo4j-community-3.2.3-unix.tar.gz
 mv neo4j-community-3.2.3 neo4j
-rm neo4j.tar.gz
+rm neo4j-community-3.2.3-unix.tar.gz
 
 # nlohmann json
 # We wget header instead of cloning repo since repo is huge (lots of test data).
 # We use head on Sep 1, 2017 instead of last release since it was long time ago.
 mkdir -p json
 cd json
-# wget "https://raw.githubusercontent.com/nlohmann/json/91e003285312167ad8365f387438ea371b465a7e/src/json.hpp"
-wget -nv http://deps.memgraph.io/json.hpp
+file_get_try_double "${primary_urls[nlohmann]}" "${secondary_urls[nlohmann]}"
 cd ..
 
 bzip2_tag="0405487e2b1de738e7f1c8afb50d19cf44e8d580"  # v1.0.6 (May 26, 2011)
-clone git://deps.memgraph.io/bzip2.git bzip2 $bzip2_tag
+repo_clone_try_double "${primary_urls[bzip2]}" "${secondary_urls[bzip2]}" "bzip2" "$bzip2_tag"
 
 zlib_tag="cacf7f1d4e3d44d871b605da3b647f07d718623f" # v1.2.11.
-clone git://deps.memgraph.io/zlib.git zlib $zlib_tag
+repo_clone_try_double "${primary_urls[zlib]}" "${secondary_urls[zlib]}" "zlib" "$zlib_tag"
 # remove shared library from install dependencies
 sed -i 's/install(TARGETS zlib zlibstatic/install(TARGETS zlibstatic/g' zlib/CMakeLists.txt
 
-rocksdb_tag="641fae60f63619ed5d0c9d9e4c4ea5a0ffa3e253" # v5.18.3 Feb 11, 2019
-clone git://deps.memgraph.io/rocksdb.git rocksdb $rocksdb_tag
-# fix compilation flags to work with clang 8
-sed -i 's/-Wshadow/-Wno-defaulted-function-deleted/' rocksdb/CMakeLists.txt
+rocksdb_tag="f3e33549c151f30ac4eb7c22356c6d0331f37652" # (2020-10-14)
+repo_clone_try_double "${primary_urls[rocksdb]}" "${secondary_urls[rocksdb]}" "rocksdb" "$rocksdb_tag"
 # remove shared library from install dependencies
 sed -i 's/TARGETS ${ROCKSDB_SHARED_LIB}/TARGETS ${ROCKSDB_SHARED_LIB} OPTIONAL/' rocksdb/CMakeLists.txt
 
 # mgclient
-mgclient_tag="fe94b3631385ef5dbe40a3d8458860dbcc33e6ea" # May 27, 2019
-# git clone https://github.com/memgraph/mgclient.git
-clone git://deps.memgraph.io/mgclient.git mgclient $mgclient_tag
+mgclient_tag="v1.2.0" # (2021-01-14)
+repo_clone_try_double "${primary_urls[mgclient]}" "${secondary_urls[mgclient]}" "mgclient" "$mgclient_tag"
 sed -i 's/\${CMAKE_INSTALL_LIBDIR}/lib/' mgclient/src/CMakeLists.txt
+
+# pymgclient
+pymgclient_tag="4f85c179e56302d46a1e3e2cf43509db65f062b3" # (2021-01-15)
+repo_clone_try_double "${primary_urls[pymgclient]}" "${secondary_urls[pymgclient]}" "pymgclient" "$pymgclient_tag"
+
+# mgconsole
+mgconsole_tag="01ae99bfce772e540e75c076ba03cf06c0c2ac7d" # (2021-05-26)
+repo_clone_try_double "${primary_urls[mgconsole]}" "${secondary_urls[mgconsole]}" "mgconsole" "$mgconsole_tag"
+
+spdlog_tag="46d418164dd4cd9822cf8ca62a116a3f71569241" # (2020-12-01)
+repo_clone_try_double "${primary_urls[spdlog]}" "${secondary_urls[spdlog]}" "spdlog" "$spdlog_tag"
+
+jemalloc_tag="ea6b3e973b477b8061e0076bb257dbd7f3faa756" # (2021-02-11)
+repo_clone_try_double "${primary_urls[jemalloc]}" "${secondary_urls[jemalloc]}" "jemalloc" "$jemalloc_tag"
+pushd jemalloc
+# ThreadPool select job randomly, and there can be some threads that had been
+# performed some memory heavy task before and will be inactive for some time,
+# but until it will became active again, the memory will not be freed since by
+# default each thread has it's own arena, but there should be not more then
+# 4*CPU arenas (see opt.nareans description).
+#
+# By enabling percpu_arena number of arenas limited to number of CPUs and hence
+# this problem should go away.
+#
+# muzzy_decay_ms -- use MADV_FREE when available on newer Linuxes, to
+# avoid spurious latencies and additional work associated with
+# MADV_DONTNEED. See
+# https://github.com/ClickHouse/ClickHouse/issues/11121 for motivation.
+./autogen.sh --with-malloc-conf="percpu_arena:percpu,oversize_threshold:0,muzzy_decay_ms:5000,dirty_decay_ms:5000"
+popd
+
+# librdkafka
+librdkafka_tag="v1.7.0" # (2021-05-06)
+repo_clone_try_double "${primary_urls[librdkafka]}" "${secondary_urls[librdkafka]}" "librdkafka" "$librdkafka_tag"

query_modules/CMakeLists.txt

@@ -32,10 +32,6 @@ install(FILES example.py DESTINATION lib/memgraph/query_modules RENAME py_exampl
 
 # Install the Python modules
 install(FILES graph_analyzer.py DESTINATION lib/memgraph/query_modules)
-install(FILES pagerank.py DESTINATION lib/memgraph/query_modules)
+install(FILES mgp_networkx.py DESTINATION lib/memgraph/query_modules)
+install(FILES nxalg.py DESTINATION lib/memgraph/query_modules)
 install(FILES wcc.py DESTINATION lib/memgraph/query_modules)
-
-if (MG_ENTERPRISE)
-  add_subdirectory(louvain)
-  add_subdirectory(connectivity)
-endif()

query_modules/connectivity/CMakeLists.txt

@@ -1,18 +0,0 @@
-set(MODULE src/connectivity_module.cpp)
-
-include_directories(src)
-
-add_library(connectivity SHARED ${MODULE})
-target_include_directories(connectivity PRIVATE ${CMAKE_SOURCE_DIR}/include)
-
-# Strip the library in release build.
-string(TOLOWER ${CMAKE_BUILD_TYPE} lower_build_type)
-if (lower_build_type STREQUAL "release")
-  add_custom_command(TARGET connectivity POST_BUILD
-                     COMMAND strip -s $<TARGET_FILE:connectivity>
-                     COMMENT "Stripping symbols and sections from connectivity module")
-endif()
-
-install(PROGRAMS $<TARGET_FILE:connectivity>
-        DESTINATION lib/memgraph/query_modules
-        RENAME connectivity.so)

query_modules/connectivity/src/connectivity_module.cpp

@@ -1,131 +0,0 @@
-#include "mg_procedure.h"
-
-#include <queue>
-#include <unordered_map>
-
-// Finds weakly connected components of a graph.
-// Time complexity: O(|V|+|E|)
-static void weak(const mgp_list *args, const mgp_graph *graph,
-                 mgp_result *result, mgp_memory *memory) {
-  std::unordered_map<int64_t, int64_t> vertex_component;
-  mgp_vertices_iterator *vertices_iterator =
-      mgp_graph_iter_vertices(graph, memory);
-  if (vertices_iterator == nullptr) {
-    mgp_result_set_error_msg(result, "Not enough memory");
-    return;
-  }
-
-  int64_t curr_component = 0;
-  for (const mgp_vertex *vertex = mgp_vertices_iterator_get(vertices_iterator);
-       vertex != nullptr;
-       vertex = mgp_vertices_iterator_next(vertices_iterator)) {
-    mgp_vertex_id vertex_id = mgp_vertex_get_id(vertex);
-    if (vertex_component.find(vertex_id.as_int) != vertex_component.end())
-      continue;
-
-    // run bfs from current vertex
-    std::queue<int64_t> q;
-    q.push(vertex_id.as_int);
-    vertex_component[vertex_id.as_int] = curr_component;
-    while (!q.empty()) {
-      mgp_vertex *v = mgp_graph_get_vertex_by_id(graph, {q.front()}, memory);
-      if (v == nullptr) {
-        mgp_vertices_iterator_destroy(vertices_iterator);
-        mgp_result_set_error_msg(result, "Not enough memory");
-        return;
-      }
-
-      q.pop();
-
-      // iterate over inbound edges
-      mgp_edges_iterator *edges_iterator = mgp_vertex_iter_in_edges(v, memory);
-      if (edges_iterator == nullptr) {
-        mgp_vertex_destroy(v);
-        mgp_vertices_iterator_destroy(vertices_iterator);
-        mgp_result_set_error_msg(result, "Not enough memory");
-        return;
-      }
-
-      for (const mgp_edge *edge = mgp_edges_iterator_get(edges_iterator);
-           edge != nullptr; edge = mgp_edges_iterator_next(edges_iterator)) {
-        mgp_vertex_id next_id = mgp_vertex_get_id(mgp_edge_get_from(edge));
-        if (vertex_component.find(next_id.as_int) != vertex_component.end())
-          continue;
-        vertex_component[next_id.as_int] = curr_component;
-        q.push(next_id.as_int);
-      }
-
-      // iterate over outbound edges
-      mgp_edges_iterator_destroy(edges_iterator);
-      edges_iterator = mgp_vertex_iter_out_edges(v, memory);
-      if (edges_iterator == nullptr) {
-        mgp_vertex_destroy(v);
-        mgp_vertices_iterator_destroy(vertices_iterator);
-        mgp_result_set_error_msg(result, "Not enough memory");
-        return;
-      }
-
-      for (const mgp_edge *edge = mgp_edges_iterator_get(edges_iterator);
-           edge != nullptr; edge = mgp_edges_iterator_next(edges_iterator)) {
-        mgp_vertex_id next_id = mgp_vertex_get_id(mgp_edge_get_to(edge));
-        if (vertex_component.find(next_id.as_int) != vertex_component.end())
-          continue;
-        vertex_component[next_id.as_int] = curr_component;
-        q.push(next_id.as_int);
-      }
-
-      mgp_vertex_destroy(v);
-      mgp_edges_iterator_destroy(edges_iterator);
-    }
-
-    ++curr_component;
-  }
-
-  mgp_vertices_iterator_destroy(vertices_iterator);
-
-  for (const auto &p : vertex_component) {
-    mgp_result_record *record = mgp_result_new_record(result);
-    if (record == nullptr) {
-      mgp_result_set_error_msg(result, "Not enough memory");
-      return;
-    }
-
-    mgp_value *mem_id_value = mgp_value_make_int(p.first, memory);
-    if (mem_id_value == nullptr) {
-      mgp_result_set_error_msg(result, "Not enough memory");
-      return;
-    }
-
-    mgp_value *comp_value = mgp_value_make_int(p.second, memory);
-    if (comp_value == nullptr) {
-      mgp_value_destroy(mem_id_value);
-      mgp_result_set_error_msg(result, "Not enough memory");
-      return;
-    }
-
-    int mem_id_inserted = mgp_result_record_insert(record, "id", mem_id_value);
-    int comp_inserted =
-        mgp_result_record_insert(record, "component", comp_value);
-
-    mgp_value_destroy(mem_id_value);
-    mgp_value_destroy(comp_value);
-
-    if (!mem_id_inserted || !comp_inserted) {
-      mgp_result_set_error_msg(result, "Not enough memory");
-      return;
-    }
-  }
-}
-
-extern "C" int mgp_init_module(struct mgp_module *module,
-                               struct mgp_memory *memory) {
-  struct mgp_proc *wcc_proc =
-      mgp_module_add_read_procedure(module, "weak", weak);
-  if (!mgp_proc_add_result(wcc_proc, "id", mgp_type_int())) return 1;
-  if (!mgp_proc_add_result(wcc_proc, "component", mgp_type_int())) return 1;
-  return 0;
-}
-
-extern "C" int mgp_shutdown_module() {
-  return 0;
-}

query_modules/example.c

@@ -16,61 +16,101 @@
 //   CALL example.procedure(1, 2) YIELD args, result;
 //   CALL example.procedure(1) YIELD args, result;
 // Naturally, you may pass in different arguments or yield less fields.
-static void procedure(const struct mgp_list *args,
-                      const struct mgp_graph *graph, struct mgp_result *result,
+static void procedure(const struct mgp_list *args, const struct mgp_graph *graph, struct mgp_result *result,
                       struct mgp_memory *memory) {
-  struct mgp_list *args_copy = mgp_list_make_empty(mgp_list_size(args), memory);
-  if (args_copy == NULL) goto error_memory;
-  for (size_t i = 0; i < mgp_list_size(args); ++i) {
-    int success = mgp_list_append(args_copy, mgp_list_at(args, i));
-    if (!success) goto error_free_list;
+  size_t args_size = 0;
+  if (mgp_list_size(args, &args_size) != MGP_ERROR_NO_ERROR) {
+    goto error_something_went_wrong;
+  }
+  struct mgp_list *args_copy = NULL;
+  if (mgp_list_make_empty(args_size, memory, &args_copy) != MGP_ERROR_NO_ERROR) {
+    goto error_something_went_wrong;
+  }
+  for (size_t i = 0; i < args_size; ++i) {
+    const struct mgp_value *value = NULL;
+    if (mgp_list_at(args, i, &value) != MGP_ERROR_NO_ERROR) {
+      goto error_free_list;
+    }
+    if (mgp_list_append(args_copy, value) != MGP_ERROR_NO_ERROR) {
+      goto error_free_list;
+    }
+  }
+  struct mgp_result_record *record = NULL;
+  if (mgp_result_new_record(result, &record) != MGP_ERROR_NO_ERROR) {
+    goto error_free_list;
   }
-  struct mgp_result_record *record = mgp_result_new_record(result);
-  if (record == NULL) goto error_free_list;
   // Transfer ownership of args_copy to mgp_value.
-  struct mgp_value *args_value = mgp_value_make_list(args_copy);
-  if (args_value == NULL) goto error_free_list;
-  int args_inserted = mgp_result_record_insert(record, "args", args_value);
+  struct mgp_value *args_value = NULL;
+  if (mgp_value_make_list(args_copy, &args_value) != MGP_ERROR_NO_ERROR) {
+    goto error_free_list;
+  }
   // Release `args_value` and contained `args_copy`.
+  if (mgp_result_record_insert(record, "args", args_value) != MGP_ERROR_NO_ERROR) {
+    mgp_value_destroy(args_value);
+    goto error_something_went_wrong;
+  }
   mgp_value_destroy(args_value);
-  if (!args_inserted) goto error_memory;
-  struct mgp_value *hello_world_value =
-      mgp_value_make_string("Hello World!", memory);
-  if (hello_world_value == NULL) goto error_memory;
-  int result_inserted =
-      mgp_result_record_insert(record, "result", hello_world_value);
+  struct mgp_value *hello_world_value = NULL;
+  if (mgp_value_make_string("Hello World!", memory, &hello_world_value) != MGP_ERROR_NO_ERROR) {
+    goto error_something_went_wrong;
+  }
+  enum mgp_error insert_result = mgp_result_record_insert(record, "result", hello_world_value);
   mgp_value_destroy(hello_world_value);
-  if (!result_inserted) goto error_memory;
+  if (insert_result != MGP_ERROR_NO_ERROR) {
+    goto error_something_went_wrong;
+  }
   // We have successfully finished, so return without error reporting.
   return;
 
 error_free_list:
   mgp_list_destroy(args_copy);
-error_memory:
-  mgp_result_set_error_msg(result, "Not enough memory!");
+error_something_went_wrong:
+  mgp_result_set_error_msg(result, "Something went wrong!");
   return;
 }
 
 // Each module needs to define mgp_init_module function.
 // Here you can register multiple procedures your module supports.
 int mgp_init_module(struct mgp_module *module, struct mgp_memory *memory) {
-  struct mgp_proc *proc =
-      mgp_module_add_read_procedure(module, "procedure", procedure);
-  if (!proc) return 1;
-  if (!mgp_proc_add_arg(proc, "required_arg",
-                        mgp_type_nullable(mgp_type_any())))
+  struct mgp_proc *proc = NULL;
+  if (mgp_module_add_read_procedure(module, "procedure", procedure, &proc) != MGP_ERROR_NO_ERROR) {
     return 1;
-  struct mgp_value *null_value = mgp_value_make_null(memory);
-  if (!mgp_proc_add_opt_arg(proc, "optional_arg",
-                            mgp_type_nullable(mgp_type_any()), null_value)) {
+  }
+  const struct mgp_type *any_type = NULL;
+  if (mgp_type_any(&any_type) != MGP_ERROR_NO_ERROR) {
+    return 1;
+  }
+  const struct mgp_type *nullable_any_type = NULL;
+  if (mgp_type_nullable(any_type, &nullable_any_type) != MGP_ERROR_NO_ERROR) {
+    return 1;
+  }
+  if (mgp_proc_add_arg(proc, "required_arg", nullable_any_type) != MGP_ERROR_NO_ERROR) {
+    return 1;
+  }
+
+  struct mgp_value *null_value = NULL;
+  if (mgp_value_make_null(memory, &null_value) != MGP_ERROR_NO_ERROR) {
+    return 1;
+  }
+  if (mgp_proc_add_opt_arg(proc, "optional_arg", nullable_any_type, null_value) != MGP_ERROR_NO_ERROR) {
     mgp_value_destroy(null_value);
     return 1;
   }
   mgp_value_destroy(null_value);
-  if (!mgp_proc_add_result(proc, "result", mgp_type_string())) return 1;
-  if (!mgp_proc_add_result(proc, "args",
-                           mgp_type_list(mgp_type_nullable(mgp_type_any()))))
+  const struct mgp_type *string = NULL;
+  if (mgp_type_string(&string) != MGP_ERROR_NO_ERROR) {
     return 1;
+  }
+  if (mgp_proc_add_result(proc, "result", string) != MGP_ERROR_NO_ERROR) {
+    return 1;
+  }
+  const struct mgp_type *list_of_anything = NULL;
+  if (mgp_type_list(nullable_any_type, &list_of_anything) != MGP_ERROR_NO_ERROR) {
+    return 1;
+  }
+  if (mgp_proc_add_result(proc, "args", list_of_anything)) {
+    return 1;
+  }
   return 0;
 }
 

query_modules/graph_analyzer.py

@@ -1,10 +1,21 @@
+import sys
 import mgp
-
 from collections import OrderedDict
 from itertools import chain, repeat
 from inspect import cleandoc
-from typing import List, Tuple, Optional
-import networkx as nx
+from typing import List, Tuple
+try:
+    import networkx as nx
+except ImportError as import_error:
+    sys.stderr.write((
+        '\n'
+        'NOTE: Please install networkx to be able to use graph_analyzer '
+        'module. Using Python:\n'
+        + sys.version +
+        '\n'))
+    raise import_error
+# Imported last because it also depends on networkx.
+from mgp_networkx import MemgraphMultiDiGraph  # noqa E402
 
 
 _MAX_LIST_SIZE = 10
@@ -47,7 +58,7 @@ def analyze(context: mgp.ProcCtx,
     Example call (with parameter):
         CALL graph_analyzer.analyze(['nodes', 'edges']) YIELD *;
     '''
-    g = _convert_to_multidigraph(context)
+    g = MemgraphMultiDiGraph(ctx=context)
     recs = _analyze_graph(context, g, analyses)
     return [mgp.Record(name=name, value=value) for name, value in recs]
 
@@ -81,7 +92,11 @@ def analyze_subgraph(context: mgp.ProcCtx,
         YIELD *
         RETURN name, value;
     '''
-    g = _convert_to_subgraph_multidigraph(context, vertices, edges)
+    vertices, edges = map(set, [vertices, edges])
+    g = nx.subgraph_view(
+        MemgraphMultiDiGraph(ctx=context),
+        lambda n: n in vertices,
+        lambda n1, n2, e: e in edges)
     recs = _analyze_graph(context, g, analyses)
     return [mgp.Record(name=name, value=value) for name, value in recs]
 
@@ -263,36 +278,3 @@ def _strongly_components(g: nx.MultiDiGraph):
     '''Returns number of strongly connected components.'''
     comps = nx.algorithms.components.number_strongly_connected_components(g)
     return 'Number of strongly connected components', comps
-
-
-def _convert_to_multidigraph(context: mgp.ProcCtx,
-                             ) -> Optional[nx.MultiDiGraph]:
-    g = nx.MultiDiGraph()
-
-    for v in context.graph.vertices:
-        context.check_must_abort()
-        g.add_node(v.id)
-
-    for v in context.graph.vertices:
-        context.check_must_abort()
-        for e in v.out_edges:
-            g.add_edge(e.from_vertex.id, e.to_vertex.id)
-
-    return g
-
-
-def _convert_to_subgraph_multidigraph(context: mgp.ProcCtx,
-                                      vertices: mgp.List[mgp.Vertex],
-                                      edges: mgp.List[mgp.Edge]
-                                      ) -> Optional[nx.MultiDiGraph]:
-    g = nx.MultiDiGraph()
-
-    for v in vertices:
-        context.check_must_abort()
-        g.add_node(v.id)
-
-    for e in edges:
-        context.check_must_abort()
-        g.add_edge(e.from_vertex.id, e.to_vertex.id)
-
-    return g

query_modules/louvain/CMakeLists.txt

@@ -1,33 +0,0 @@
-set(MAIN src/main.cpp)
-set(MODULE src/louvain_module.cpp)
-set(SOURCES src/algorithms/louvain.cpp
-            src/data_structures/graph.cpp)
-
-include_directories(src)
-
-add_library(louvain-core STATIC ${SOURCES})
-set_target_properties(louvain-core PROPERTIES POSITION_INDEPENDENT_CODE ON)
-
-add_executable(louvain-main ${MAIN})
-target_link_libraries(louvain-main louvain-core)
-
-enable_testing()
-add_subdirectory(test)
-
-add_library(louvain SHARED ${MODULE})
-target_link_libraries(louvain louvain-core)
-target_include_directories(louvain PRIVATE ${CMAKE_SOURCE_DIR}/include)
-
-# Strip the library in release build.
-string(TOLOWER ${CMAKE_BUILD_TYPE} lower_build_type)
-if (lower_build_type STREQUAL "release")
-  add_custom_command(TARGET louvain POST_BUILD
-                     COMMAND strip -s $<TARGET_FILE:louvain>
-                     COMMENT "Stripping symbols and sections from louvain module")
-endif()
-
-if (NOT MG_COMMUNITY)
-  install(PROGRAMS $<TARGET_FILE:louvain>
-          DESTINATION lib/memgraph/query_modules
-          RENAME louvain.so)
-endif()

query_modules/louvain/src/algorithms/algorithms.hpp

@@ -1,18 +0,0 @@
-/// @file
-///
-/// The file contains function declarations of several community-detection
-/// graph algorithms.
-
-#pragma once
-
-#include "data_structures/graph.hpp"
-
-namespace algorithms {
-  /// Detects communities of an unidrected, weighted graph using the Louvain
-  /// algorithm. The algorithm attempts to maximze the modularity of a weighted
-  /// graph.
-  ///
-  /// @param graph pointer to an undirected, weighted graph which may contain
-  ///              self-loops.
-  void Louvain(comdata::Graph *graph);
-} // namespace algorithms

query_modules/louvain/src/algorithms/louvain.cpp

@@ -1,163 +0,0 @@
-#include "algorithms/algorithms.hpp"
-
-#include <algorithm>
-#include <map>
-#include <random>
-#include <unordered_map>
-
-namespace {
-
-void OptimizeLocally(comdata::Graph *graph) {
-  // We will consider local optimizations uniformly at random.
-  std::random_device rd;
-  std::mt19937 g(rd());
-  std::vector<uint32_t> p(graph->Size());
-  std::iota(p.begin(), p.end(), 0);
-  std::shuffle(p.begin(), p.end(), g);
-
-  // Modularity of a graph can be expressed as:
-  //
-  // Q = 1 / (2m) * sum_over_pairs_of_nodes[(Aij - ki * kj / 2m) * delta(ci, cj)]
-  //
-  // where m is the sum of all weights in the graph,
-  //       Aij is the weight on edge that connects i and j (i=j for a self-loop)
-  //       ki is the sum of weights incident to node i
-  //       ci is the community of node i
-  //       delta(a, b) is the Kronecker delta function.
-  //
-  // With some simple algebraic manipulations, we can transform the formula into:
-  //
-  // Q = sum_over_components[M * ((sum_over_pairs(Aij + M * ki * kj)))] =
-  //   = sum_over_components[M * (sum_over_pairs(Aij) + M * sum_over_nodes^2(ki))] =
-  //   = sum_over_components[M * (w_contrib(ci) + M * k_contrib^2(ci))]
-  //
-  // where M = 1 / (2m)
-  //
-  // Therefore, we could store for each community the following:
-  //    * Weight contribution (w_contrib)
-  //    * Weighted degree contribution (k_contrib)
-  //
-  // This allows us to efficiently remove a node from one community and insert
-  // it into a community of its neighbour without the need to recalculate
-  // modularity from scratch.
-
-  std::unordered_map<uint32_t, double> w_contrib;
-  std::unordered_map<uint32_t, double> k_contrib;
-
-  for (uint32_t node_id = 0; node_id < graph->Size(); ++node_id) {
-    k_contrib[graph->Community(node_id)] += graph->IncidentWeight(node_id);
-    for (const auto &neigh : graph->Neighbours(node_id)) {
-      uint32_t nxt_id = neigh.dest;
-      double w = neigh.weight;
-      if (graph->Community(node_id) == graph->Community(nxt_id))
-        w_contrib[graph->Community(node_id)] += w;
-    }
-  }
-
-  bool stable = false;
-  double total_w = graph->TotalWeight();
-
-  while (!stable) {
-    stable = true;
-    for (uint32_t node_id : p) {
-      std::unordered_map<uint32_t, double> sum_w;
-      double self_loop = 0;
-      sum_w[graph->Community(node_id)] = 0;
-      for (const auto &neigh : graph->Neighbours(node_id)) {
-        uint32_t nxt_id = neigh.dest;
-        double weight = neigh.weight;
-        if (nxt_id == node_id) {
-          self_loop += weight;
-          continue;
-        }
-        sum_w[graph->Community(nxt_id)] += weight;
-      }
-
-      uint32_t my_c = graph->Community(node_id);
-
-      uint32_t best_c = my_c;
-      double best_dq = 0;
-
-      for (const auto &p : sum_w) {
-        if (p.first == my_c) continue;
-        uint32_t nxt_c = p.first;
-        double dq = 0;
-
-        // contributions before swap (dq = d_after - d_before)
-        for (uint32_t c : {my_c, nxt_c})
-          dq -= w_contrib[c] - k_contrib[c] * k_contrib[c] / (2.0 * total_w);
-
-        // leave the current community
-        dq += (w_contrib[my_c] - 2.0 * sum_w[my_c] - self_loop) -
-              (k_contrib[my_c] - graph->IncidentWeight(node_id)) *
-                  (k_contrib[my_c] - graph->IncidentWeight(node_id)) /
-                  (2.0 * total_w);
-
-        // join a new community
-        dq += (w_contrib[nxt_c] + 2.0 * sum_w[nxt_c] + self_loop) -
-              (k_contrib[nxt_c] + graph->IncidentWeight(node_id)) *
-                  (k_contrib[nxt_c] + graph->IncidentWeight(node_id)) /
-                  (2.0 * total_w);
-
-        if (dq > best_dq) {
-          best_dq = dq;
-          best_c = nxt_c;
-        }
-      }
-
-      if (best_c != my_c) {
-        graph->SetCommunity(node_id, best_c);
-        w_contrib[my_c] -= 2.0 * sum_w[my_c] + self_loop;
-        k_contrib[my_c] -= graph->IncidentWeight(node_id);
-        w_contrib[best_c] += 2.0 * sum_w[best_c] + self_loop;
-        k_contrib[best_c] += graph->IncidentWeight(node_id);
-        stable = false;
-      }
-    }
-  }
-}
-
-} // anonymous namespace
-
-namespace algorithms {
-
-void Louvain(comdata::Graph *graph) {
-  OptimizeLocally(graph);
-
-  // Collapse the locally optimized graph.
-  uint32_t collapsed_nodes = graph->NormalizeCommunities();
-  if (collapsed_nodes == graph->Size()) return;
-  comdata::Graph collapsed_graph(collapsed_nodes);
-  std::map<std::pair<uint32_t, uint32_t>, double> collapsed_edges;
-
-  for (uint32_t node_id = 0; node_id < graph->Size(); ++node_id) {
-    std::unordered_map<uint32_t, double> edges;
-    for (const auto &neigh : graph->Neighbours(node_id)) {
-      uint32_t nxt_id = neigh.dest;
-      double weight = neigh.weight;
-      if (graph->Community(nxt_id) < graph->Community(node_id)) continue;
-      edges[graph->Community(nxt_id)] += weight;
-    }
-    for (const auto &neigh : edges) {
-      uint32_t a = std::min(graph->Community(node_id), neigh.first);
-      uint32_t b = std::max(graph->Community(node_id), neigh.first);
-      collapsed_edges[{a, b}] += neigh.second;
-    }
-  }
-
-  for (const auto &p : collapsed_edges)
-    collapsed_graph.AddEdge(p.first.first, p.first.second, p.second);
-
-  // Repeat until no local optimizations can be found.
-  Louvain(&collapsed_graph);
-
-  // Propagate results from collapsed graph.
-  for (uint32_t node_id = 0; node_id < graph->Size(); ++node_id) {
-    graph->SetCommunity(node_id,
-                        collapsed_graph.Community(graph->Community(node_id)));
-  }
-
-  graph->NormalizeCommunities();
-}
-
-} // namespace algorithms

query_modules/louvain/src/data_structures/graph.cpp

@@ -1,105 +0,0 @@
-#include "data_structures/graph.hpp"
-
-#include <exception>
-#include <numeric>
-#include <unordered_map>
-#include <unordered_set>
-#include <vector>
-
-namespace comdata {
-
-Graph::Graph(uint32_t n_nodes) : n_nodes_(n_nodes), total_w_(0) {
-  adj_list_.resize(n_nodes, {});
-  inc_w_.resize(n_nodes, 0);
-
-  // each node starts as its own separate community.
-  community_.resize(n_nodes);
-  std::iota(community_.begin(), community_.end(), 0);
-}
-
-uint32_t Graph::Size() const {
-  return n_nodes_;
-}
-
-uint32_t Graph::Community(uint32_t node) const { return community_.at(node); }
-
-void Graph::SetCommunity(uint32_t node, uint32_t c) { community_.at(node) = c; }
-
-uint32_t Graph::NormalizeCommunities() {
-  std::set<uint32_t> c_id(community_.begin(), community_.end());
-  std::unordered_map<uint32_t, uint32_t> cmap;
-  uint32_t id = 0;
-  for (uint32_t c : c_id) {
-    cmap[c] = id;
-    ++id;
-  }
-  for (uint32_t node_id = 0; node_id < n_nodes_; ++node_id)
-    community_[node_id] = cmap[community_[node_id]];
-  return id;
-}
-
-void Graph::AddEdge(uint32_t node1, uint32_t node2, double weight) {
-  if (node1 >= n_nodes_ || node2 >= n_nodes_)
-    throw std::out_of_range("Node index out of range");
-  if (weight <= 0) throw std::out_of_range("Weights must be positive");
-  if (edges_.find({node1, node2}) != edges_.end())
-    throw std::invalid_argument("Edge already exists");
-
-  edges_.emplace(node1, node2);
-  edges_.emplace(node2, node1);
-
-  total_w_ += weight;
-
-  adj_list_[node1].emplace_back(node2, weight);
-  inc_w_[node1] += weight;
-
-  if (node1 != node2) {
-    adj_list_[node2].emplace_back(node1, weight);
-    inc_w_[node2] += weight;
-  }
-}
-
-uint32_t Graph::Degree(uint32_t node) const {
-  return static_cast<uint32_t>(adj_list_.at(node).size());
-}
-
-double Graph::IncidentWeight(uint32_t node) const {
-  return inc_w_.at(node);
-}
-
-double Graph::TotalWeight() const {
-  return total_w_;
-}
-
-double Graph::Modularity() const {
-  double ret = 0;
-  // Since all weights should be positive, this implies that our graph has
-  // no edges.
-  if (total_w_ == 0)
-    return 0;
-
-  std::unordered_map<uint32_t, double> weight_c;
-  std::unordered_map<uint32_t, double> degree_c;
-
-  for (uint32_t i = 0; i < n_nodes_; ++i) {
-    degree_c[Community(i)] += IncidentWeight(i);
-    for (const auto &neigh : adj_list_[i]) {
-      uint32_t j = neigh.dest;
-      double w = neigh.weight;
-      if (Community(i) != Community(j)) continue;
-      weight_c[Community(i)] += w;
-    }
-  }
-
-  for (const auto &p : degree_c)
-    ret += weight_c[p.first] - (p.second * p.second) / (2 * total_w_);
-
-  ret /= 2 * total_w_;
-  return ret;
-}
-
-const std::vector<Neighbour> &Graph::Neighbours(uint32_t node) const {
-  return adj_list_.at(node);
-}
-
-} // namespace comdata

query_modules/louvain/src/data_structures/graph.hpp

@@ -1,125 +0,0 @@
-/// @file
-
-#pragma once
-
-#include <cstdint>
-#include <set>
-#include <vector>
-
-namespace comdata {
-
-struct Neighbour {
-  uint32_t dest;
-  double weight;
-  Neighbour(uint32_t d, double w) : dest(d), weight(w) {}
-};
-
-/// Class which models a weighted, undirected graph with necessary
-/// functionalities for community detection algorithms.
-class Graph {
-public:
-  /// Constructs a new graph with a given number of nodes and no edges between
-  /// them.
-  ///
-  /// The implementation assumes (and enforces) that all nodes
-  /// are indexed from 0 to n_nodes.
-  ///
-  /// @param n_nodes Number of nodes in the graph.
-  explicit Graph(uint32_t n_nodes);
-
-  /// @return number of nodes in the graph.
-  uint32_t Size() const;
-
-  /// Adds a bidirectional, weighted edge to the graph between the given
-  /// nodes. If both given nodes are the same, the method inserts a weighted
-  /// self-loop.
-  ///
-  /// There should be no edges between the given nodes when before invoking
-  /// this method.
-  ///
-  /// @param node1 index of an incident node.
-  /// @param node2 index of an incident node.
-  /// @param weight real value which represents the weight of the edge.
-  ///
-  /// @throw std::out_of_range
-  /// @throw std::invalid_argument
-  void AddEdge(uint32_t node1, uint32_t node2, double weight);
-
-  /// @param node index of node.
-  ///
-  /// @return community where the node belongs to.
-  ///
-  /// @throw std::out_of_range
-  uint32_t Community(uint32_t node) const;
-
-  /// Adds a given node to a given community.
-  ///
-  /// @param node index of node.
-  /// @param c community where the given node should go in.
-  ///
-  /// @throw std::out_of_range
-  void SetCommunity(uint32_t node, uint32_t c);
-
-  /// Normalizes the values of communities. More precisely, after invoking this
-  /// method communities will be indexed by successive integers starting from 0.
-  ///
-  /// Note: this method is computationally expensive and takes O(|V|)
-  ///       time, i.e., it traverses all nodes in the graph.
-  ///
-  /// @return number of communities in the graph
-  uint32_t NormalizeCommunities();
-
-  /// Returns the number of incident edges to a given node. Self-loops
-  /// contribute a single edge to the degree.
-  ///
-  /// @param node index of node.
-  ///
-  /// @return degree of given node.
-  ///
-  /// @throw std::out_of_range
-  uint32_t Degree(uint32_t node) const;
-
-  /// Returns the total weight of incident edges to a given node. Weight
-  /// of a self loop contributes once to the total sum.
-  ///
-  /// @param node index of node.
-  ///
-  /// @return total incident weight of a given node.
-  ///
-  /// @throw std::out_of_range
-  double IncidentWeight(uint32_t node) const;
-
-  /// @return total weight of all edges in a graph.
-  double TotalWeight() const;
-
-  /// Calculates the modularity of the graph which is defined as a real value
-  /// between -1 and 1 that measures the density of links inside communities
-  /// compared to links between communities.
-  ///
-  /// Note: this method is computationally expensive and takes O(|V| + |E|)
-  ///       time, i.e., it traverses the entire graph.
-  ///
-  /// @return modularity of the graph.
-  double Modularity() const;
-
-  /// Returns nodes adjacent to a given node.
-  ///
-  /// @param node index of node.
-  ///
-  /// @return list of neighbouring nodes.
-  ///
-  /// @throw std::out_of_range
-  const std::vector<Neighbour>& Neighbours(uint32_t node) const;
-
-private:
-  uint32_t n_nodes_;
-  double total_w_;
-
-  std::vector<std::vector<Neighbour>> adj_list_;
-  std::set<std::pair<uint32_t, uint32_t>> edges_;
-
-  std::vector<double> inc_w_;
-  std::vector<uint32_t> community_;
-};
-
-} // namespace comdata

query_modules/louvain/src/louvain_module.cpp

@@ -1,228 +0,0 @@
-#include "mg_procedure.h"
-
-#include <exception>
-#include <unordered_map>
-
-#include "algorithms/algorithms.hpp"
-#include "data_structures/graph.hpp"
-
-namespace {
-
-std::optional<std::unordered_map<int64_t, uint32_t>> NormalizeVertexIds(
-    const mgp_graph *graph, mgp_result *result, mgp_memory *memory) {
-  std::unordered_map<int64_t, uint32_t> mem_to_louv_id;
-  mgp_vertices_iterator *vertices_iterator =
-      mgp_graph_iter_vertices(graph, memory);
-  if (vertices_iterator == nullptr) {
-    mgp_result_set_error_msg(result, "Not enough memory!");
-    return std::nullopt;
-  }
-
-  uint32_t louv_id = 0;
-  for (const mgp_vertex *vertex = mgp_vertices_iterator_get(vertices_iterator);
-       vertex != nullptr;
-       vertex = mgp_vertices_iterator_next(vertices_iterator)) {
-    mgp_vertex_id mem_id = mgp_vertex_get_id(vertex);
-    mem_to_louv_id[mem_id.as_int] = louv_id;
-    ++louv_id;
-  }
-
-  mgp_vertices_iterator_destroy(vertices_iterator);
-  return mem_to_louv_id;
-}
-
-std::optional<comdata::Graph> RunLouvain(
-    const mgp_graph *graph, mgp_result *result, mgp_memory *memory,
-    const std::unordered_map<int64_t, uint32_t> &mem_to_louv_id) {
-  comdata::Graph louvain_graph(mem_to_louv_id.size());
-  // Extract the graph structure
-  // TODO(ipaljak): consider filtering nodes and edges by labels.
-  for (const auto &p : mem_to_louv_id) {
-    mgp_vertex *vertex = mgp_graph_get_vertex_by_id(graph, {p.first}, memory);
-    if (!vertex) {
-      mgp_result_set_error_msg(result, "Not enough memory!");
-      return std::nullopt;
-    }
-
-    // iterate over inbound edges. This is enough because we will eventually
-    // iterate over outbound edges in another direction.
-    mgp_edges_iterator *edges_iterator =
-        mgp_vertex_iter_in_edges(vertex, memory);
-    if (edges_iterator == nullptr) {
-      mgp_vertex_destroy(vertex);
-      mgp_result_set_error_msg(result, "Not enough memory!");
-      return std::nullopt;
-    }
-
-    for (const mgp_edge *edge = mgp_edges_iterator_get(edges_iterator);
-         edge != nullptr; edge = mgp_edges_iterator_next(edges_iterator)) {
-      const mgp_vertex *next_vertex = mgp_edge_get_from(edge);
-      mgp_vertex_id next_mem_id = mgp_vertex_get_id(next_vertex);
-      uint32_t next_louv_id;
-      try {
-        next_louv_id = mem_to_louv_id.at(next_mem_id.as_int);
-      } catch (const std::exception &e) {
-        const auto msg = std::string("[Internal error] ") + e.what();
-        mgp_result_set_error_msg(result, msg.c_str());
-        return std::nullopt;
-      }
-
-      // retrieve edge weight (default to 1)
-      mgp_value *weight_prop = mgp_edge_get_property(edge, "weight", memory);
-      if (!weight_prop) {
-        mgp_vertex_destroy(vertex);
-        mgp_edges_iterator_destroy(edges_iterator);
-        mgp_result_set_error_msg(result, "Not enough memory");
-      }
-
-      double weight = 1;
-      if (mgp_value_is_double(weight_prop))
-        weight = mgp_value_get_double(weight_prop);
-      if (mgp_value_is_int(weight_prop))
-        weight = static_cast<double>(mgp_value_get_int(weight_prop));
-
-      mgp_value_destroy(weight_prop);
-
-      try {
-        louvain_graph.AddEdge(p.second, next_louv_id, weight);
-      } catch (const std::exception &e) {
-        mgp_vertex_destroy(vertex);
-        mgp_edges_iterator_destroy(edges_iterator);
-        mgp_result_set_error_msg(result, e.what());
-        return std::nullopt;
-      }
-    }
-
-    mgp_vertex_destroy(vertex);
-    mgp_edges_iterator_destroy(edges_iterator);
-  }
-
-  try {
-    algorithms::Louvain(&louvain_graph);
-  } catch (const std::exception &e) {
-    const auto msg = std::string("[Internal error] ") + e.what();
-    mgp_result_set_error_msg(result, msg.c_str());
-    return std::nullopt;
-  }
-
-  return louvain_graph;
-}
-
-void communities(const mgp_list *args, const mgp_graph *graph,
-                        mgp_result *result, mgp_memory *memory) {
-  try {
-    // Normalize vertex ids
-    auto mem_to_louv_id = NormalizeVertexIds(graph, result, memory);
-    if (!mem_to_louv_id) return;
-
-    // Run louvain
-    auto louvain_graph = RunLouvain(graph, result, memory, *mem_to_louv_id);
-    if (!louvain_graph) return;
-
-    // Return node ids and their corresponding communities.
-    for (const auto &p : *mem_to_louv_id) {
-      mgp_result_record *record = mgp_result_new_record(result);
-      if (record == nullptr) {
-        mgp_result_set_error_msg(result, "Not enough memory!");
-        return;
-      }
-
-      mgp_value *mem_id_value = mgp_value_make_int(p.first, memory);
-      if (mem_id_value == nullptr) {
-        mgp_result_set_error_msg(result, "Not enough memory!");
-        return;
-      }
-
-      mgp_value *com_value =
-          mgp_value_make_int(louvain_graph->Community(p.second), memory);
-      if (com_value == nullptr) {
-        mgp_value_destroy(mem_id_value);
-        mgp_result_set_error_msg(result, "Not enough memory!");
-        return;
-      }
-
-      int mem_id_inserted =
-          mgp_result_record_insert(record, "id", mem_id_value);
-      int com_inserted =
-          mgp_result_record_insert(record, "community", com_value);
-
-      mgp_value_destroy(mem_id_value);
-      mgp_value_destroy(com_value);
-
-      if (!mem_id_inserted || !com_inserted) {
-        mgp_result_set_error_msg(result, "Not enough memory!");
-        return;
-      }
-    }
-  } catch (const std::exception &e) {
-    mgp_result_set_error_msg(result, e.what());
-    return;
-  }
-}
-
-void modularity(const mgp_list *args, const mgp_graph *graph,
-                       mgp_result *result, mgp_memory *memory) {
-  try {
-    // Normalize vertex ids
-    auto mem_to_louv_id = NormalizeVertexIds(graph, result, memory);
-    if (!mem_to_louv_id) return;
-
-    // Run louvain
-    auto louvain_graph = RunLouvain(graph, result, memory, *mem_to_louv_id);
-    if (!louvain_graph) return;
-
-    // Return graph modularity after Louvain
-    // TODO(ipaljak) - consider allowing the user to specify seed communities and
-    //                 yield modularity values both before and after running
-    //                 louvain.
-    mgp_result_record *record = mgp_result_new_record(result);
-    if (record == nullptr) {
-      mgp_result_set_error_msg(result, "Not enough memory!");
-      return;
-    }
-
-    mgp_value *modularity_value =
-        mgp_value_make_double(louvain_graph->Modularity(), memory);
-    if (modularity_value == nullptr) {
-      mgp_result_set_error_msg(result, "Not enough memory!");
-      return;
-    }
-
-    int value_inserted =
-        mgp_result_record_insert(record, "modularity", modularity_value);
-
-    mgp_value_destroy(modularity_value);
-
-    if (!value_inserted) {
-      mgp_result_set_error_msg(result, "Not enough memory!");
-      return;
-    }
-  } catch (const std::exception &e) {
-    mgp_result_set_error_msg(result, e.what());
-    return;
-  }
-}
-
-} // namespace
-
-extern "C" int mgp_init_module(struct mgp_module *module,
-                               struct mgp_memory *memory) {
-  struct mgp_proc *community_proc =
-      mgp_module_add_read_procedure(module, "communities", communities);
-  if (!community_proc) return 1;
-  if (!mgp_proc_add_result(community_proc, "id", mgp_type_int())) return 1;
-  if (!mgp_proc_add_result(community_proc, "community", mgp_type_int()))
-    return 1;
-
-  struct mgp_proc *modularity_proc =
-    mgp_module_add_read_procedure(module, "modularity", modularity);
-  if (!modularity_proc) return 1;
-  if (!mgp_proc_add_result(modularity_proc, "modularity", mgp_type_float()))
-    return 1;
-
-  return 0;
-}
-
-extern "C" int mgp_shutdown_module() {
-  return 0;
-}

query_modules/louvain/src/main.cpp

@@ -1,28 +0,0 @@
-#include <iostream>
-
-#include "algorithms/algorithms.hpp"
-#include "data_structures/graph.hpp"
-
-// A simple program that reads the graph from STDIN and
-// outputs the detected communities from louvain along with
-// its modularity measure on STDOUT.
-int main() {
-  int n;
-  int m;
-  std::cin >> n >> m;
-  comdata::Graph graph(n);
-  for (int i = 0; i < m; ++i) {
-    int a;
-    int b;
-    double c;
-    std::cin >> a >> b >> c;
-    graph.AddEdge(a, b, c);
-  }
-
-  algorithms::Louvain(&graph);
-
-  for (int i = 0; i < n; ++i)
-    std::cout << i << " " << graph.Community(i) << "\n";
-  std::cout << graph.Modularity() << "\n";
-  return 0;
-}

query_modules/louvain/test/.clang-tidy

@@ -1,80 +0,0 @@
----
-Checks: '*,
-         -android-*,
-         -cert-err58-cpp,
-         -cppcoreguidelines-avoid-c-arrays,
-         -cppcoreguidelines-avoid-goto,
-         -cppcoreguidelines-avoid-magic-numbers,
-         -cppcoreguidelines-macro-usage,
-         -cppcoreguidelines-no-malloc,
-         -cppcoreguidelines-non-private-member-variables-in-classes,
-         -cppcoreguidelines-owning-memory,
-         -cppcoreguidelines-pro-bounds-array-to-pointer-decay,
-         -cppcoreguidelines-pro-bounds-constant-array-index,
-         -cppcoreguidelines-pro-bounds-pointer-arithmetic,
-         -cppcoreguidelines-pro-type-member-init,
-         -cppcoreguidelines-pro-type-reinterpret-cast,
-         -cppcoreguidelines-pro-type-static-cast-downcast,
-         -cppcoreguidelines-pro-type-union-access,
-         -cppcoreguidelines-pro-type-vararg,
-         -cppcoreguidelines-special-member-functions,
-         -fuchsia-default-arguments,
-         -fuchsia-default-arguments-calls,
-         -fuchsia-default-arguments-declarations,
-         -fuchsia-overloaded-operator,
-         -fuchsia-statically-constructed-objects,
-         -fuchsia-trailing-return,
-         -fuchsia-virtual-inheritance,
-         -google-explicit-constructor,
-         -google-readability-*,
-         -hicpp-avoid-c-arrays,
-         -hicpp-avoid-goto,
-         -hicpp-braces-around-statements,
-         -hicpp-member-init,
-         -hicpp-no-array-decay,
-         -hicpp-no-assembler,
-         -hicpp-no-malloc,
-         -hicpp-special-member-functions,
-         -hicpp-use-equals-default,
-         -hicpp-vararg,
-         -llvm-header-guard,
-         -misc-non-private-member-variables-in-classes,
-         -misc-unused-parameters,
-         -modernize-avoid-c-arrays,
-         -modernize-concat-nested-namespaces,
-         -modernize-pass-by-value,
-         -modernize-use-equals-default,
-         -modernize-use-nodiscard,
-         -modernize-use-trailing-return-type,
-         -performance-unnecessary-value-param,
-         -readability-braces-around-statements,
-         -readability-else-after-return,
-         -readability-implicit-bool-conversion,
-         -readability-magic-numbers,
-         -readability-named-parameter'
-WarningsAsErrors: ''
-HeaderFilterRegex: ''
-AnalyzeTemporaryDtors: false
-FormatStyle:     none
-CheckOptions:
-  - key:             google-readability-braces-around-statements.ShortStatementLines
-    value:           '1'
-  - key:             google-readability-function-size.StatementThreshold
-    value:           '800'
-  - key:             google-readability-namespace-comments.ShortNamespaceLines
-    value:           '10'
-  - key:             google-readability-namespace-comments.SpacesBeforeComments
-    value:           '2'
-  - key:             modernize-loop-convert.MaxCopySize
-    value:           '16'
-  - key:             modernize-loop-convert.MinConfidence
-    value:           reasonable
-  - key:             modernize-loop-convert.NamingStyle
-    value:           CamelCase
-  - key:             modernize-pass-by-value.IncludeStyle
-    value:           llvm
-  - key:             modernize-replace-auto-ptr.IncludeStyle
-    value:           llvm
-  - key:             modernize-use-nullptr.NullMacros
-    value:           'NULL'
-...

query_modules/louvain/test/CMakeLists.txt

@@ -1,3 +0,0 @@
-include_directories(${GTEST_INCLUDE_DIR})
-
-add_subdirectory(unit)

query_modules/louvain/test/unit/CMakeLists.txt

@@ -1,28 +0,0 @@
-set(test_prefix louvain__unit__)
-
-add_custom_target(louvain__unit)
-
-add_library(louvain-test STATIC utils.cpp)
-set_target_properties(louvain-test PROPERTIES POSITION_INDEPENDENT_CODE ON)
-
-function(add_unit_test test_cpp)
-  # get exec name (remove extension from the abs path)
-  get_filename_component(exec_name ${test_cpp} NAME_WE)
-  set(target_name ${test_prefix}${exec_name})
-  add_executable(${target_name} ${test_cpp})
-  # OUTPUT_NAME sets the real name of a target when it is built and can be
-  # used to help create two targets of the same name even though CMake
-  # requires unique logical target names
-  set_target_properties(${target_name} PROPERTIES OUTPUT_NAME ${exec_name})
-  # TODO: this is a temporary workaround the test build warnings
-  target_compile_options(${target_name} PRIVATE -Wno-comment -Wno-sign-compare
-                                                -Wno-unused-variable)
-  target_link_libraries(${target_name} glog gflags gtest gtest_main Threads::Threads
-                                       louvain-core louvain-test)
-  # register test
-  add_test(${target_name} ${exec_name})
-  # add to unit target
-  add_dependencies(louvain__unit ${target_name})
-endfunction(add_unit_test)
-
-add_unit_test(graph.cpp)

query_modules/louvain/test/unit/graph.cpp

@@ -1,365 +0,0 @@
-#include <glog/logging.h>
-#include <gtest/gtest.h>
-
-#include "data_structures/graph.hpp"
-#include "utils.hpp"
-
-// Checks if commmunities of nodes in graph correspond to a given community
-// vector.
-bool CommunityCheck(const comdata::Graph &graph,
-                    const std::vector<uint32_t> &c) {
-  if (graph.Size() != c.size()) return false;
-  for (uint32_t node_id = 0; node_id < graph.Size(); ++node_id)
-    if (graph.Community(node_id) != c[node_id])
-      return false;
-  return true;
-}
-
-// Checks if degrees of nodes in graph correspond to a given degree vector.
-bool DegreeCheck(const comdata::Graph &graph,
-                 const std::vector<uint32_t> &deg) {
-  if (graph.Size() != deg.size()) return false;
-  for (uint32_t node_id = 0; node_id < graph.Size(); ++node_id)
-    if (graph.Degree(node_id) != deg[node_id])
-      return false;
-  return true;
-}
-
-// Checks if incident weights of nodes in graph correspond to a given weight
-// vector.
-bool IncidentWeightCheck(const comdata::Graph &graph,
-                         const std::vector<double> &inc_w) {
-  if (graph.Size() != inc_w.size()) return false;
-  for (uint32_t node_id = 0; node_id < graph.Size(); ++node_id)
-    if (std::abs(graph.IncidentWeight(node_id) - inc_w[node_id]) > 1e-6)
-      return false;
-  return true;
-}
-
-// Sets communities of nodes in graph. Returns true on success.
-bool SetCommunities(comdata::Graph *graph, const std::vector<uint32_t> &c) {
-  if (graph->Size() != c.size()) return false;
-  for (uint32_t node_id = 0; node_id < graph->Size(); ++node_id)
-    graph->SetCommunity(node_id, c[node_id]);
-  return true;
-}
-
-TEST(Graph, Constructor) {
-  uint32_t nodes = 100;
-  comdata::Graph graph(nodes);
-  ASSERT_EQ(graph.Size(), nodes);
-  for (uint32_t node_id = 0; node_id < nodes; ++node_id) {
-    ASSERT_EQ(graph.IncidentWeight(node_id), 0);
-    ASSERT_EQ(graph.Community(node_id), node_id);
-  }
-}
-
-TEST(Graph, Size) {
-  comdata::Graph graph1 = GenRandomUnweightedGraph(0, 0);
-  comdata::Graph graph2 = GenRandomUnweightedGraph(42, 41);
-  comdata::Graph graph3 = GenRandomUnweightedGraph(100, 250);
-  ASSERT_EQ(graph1.Size(), 0);
-  ASSERT_EQ(graph2.Size(), 42);
-  ASSERT_EQ(graph3.Size(), 100);
-}
-
-TEST(Graph, Communities) {
-  comdata::Graph graph = GenRandomUnweightedGraph(100, 250);
-
-  for (int i = 0; i < 100; ++i) graph.SetCommunity(i, i % 5);
-  for (int i = 0; i < 100; ++i) ASSERT_EQ(graph.Community(i), i % 5);
-
-  // Try to set communities on non-existing nodes
-  EXPECT_THROW({ graph.SetCommunity(100, 2); }, std::out_of_range);
-  EXPECT_THROW({ graph.SetCommunity(150, 0); }, std::out_of_range);
-
-  // Try to get a the community of a non-existing node
-  EXPECT_THROW({ graph.Community(100); }, std::out_of_range);
-  EXPECT_THROW({ graph.Community(150); }, std::out_of_range);
-}
-
-TEST(Graph, CommunityNormalization) {
-  // Communities are already normalized.
-  comdata::Graph graph = GenRandomUnweightedGraph(5, 10);
-  std::vector<uint32_t> init_c = {0, 2, 1, 3, 4};
-  std::vector<uint32_t> final_c = {0, 2, 1, 3, 4};
-  ASSERT_TRUE(SetCommunities(&graph, init_c));
-  graph.NormalizeCommunities();
-  ASSERT_TRUE(CommunityCheck(graph, final_c));
-
-  // Each node in its own community.
-  graph = GenRandomUnweightedGraph(5, 10);
-  init_c = {20, 30, 10, 40, 50};
-  final_c = {1, 2, 0, 3, 4};
-  ASSERT_TRUE(SetCommunities(&graph, init_c));
-  graph.NormalizeCommunities();
-  ASSERT_TRUE(CommunityCheck(graph, final_c));
-
-  // Multiple nodes in the same community
-  graph = GenRandomUnweightedGraph(7, 10);
-  init_c = {13, 99, 13, 13, 1, 99, 1};
-  final_c = {1, 2, 1, 1, 0, 2, 0};
-  ASSERT_TRUE(SetCommunities(&graph, init_c));
-  graph.NormalizeCommunities();
-  ASSERT_TRUE(CommunityCheck(graph, final_c));
-}
-
-TEST(Graph, AddEdge) {
-  comdata::Graph graph = GenRandomUnweightedGraph(5, 0);
-
-  // Node out of bounds.
-  EXPECT_THROW({ graph.AddEdge(1, 5, 7); }, std::out_of_range);
-
-  // Repeated edge
-  graph.AddEdge(1, 2, 1);
-  EXPECT_THROW({ graph.AddEdge(1, 2, 7); }, std::invalid_argument);
-
-  // Non-positive edge weight
-  EXPECT_THROW({ graph.AddEdge(2, 3, -7); }, std::out_of_range);
-  EXPECT_THROW({ graph.AddEdge(3, 4, 0); }, std::out_of_range);
-}
-
-TEST(Graph, Degrees) {
-  // Graph without edges
-  comdata::Graph graph = GenRandomUnweightedGraph(5, 0);
-  std::vector<uint32_t> deg = {0, 0, 0, 0, 0};
-  ASSERT_TRUE(DegreeCheck(graph, deg));
-
-  // Chain
-  // (0)--(1)--(2)--(3)--(4)
-  graph = BuildGraph(5, {{0, 1, 1},
-                     {1, 2, 1},
-                     {2, 3, 1},
-                     {3, 4, 1}});
-  deg = {1, 2, 2, 2, 1};
-  ASSERT_TRUE(DegreeCheck(graph, deg));
-
-  // Tree
-  //      (0)--(3)
-  //     /   \
-  //   (1)   (2)
-  //    |   /   \
-  //   (4) (5)  (6)
-  graph = BuildGraph(7, {{0, 1, 1},
-                     {0, 2, 1},
-                     {0, 3, 1},
-                     {1, 4, 1},
-                     {2, 5, 1},
-                     {2, 6, 1}});
-  deg = {3, 2, 3, 1, 1, 1, 1};
-  ASSERT_TRUE(DegreeCheck(graph, deg));
-
-  // Graph without self-loops
-  // (0)--(1)
-  //  | \  | \
-  //  |  \ |  \
-  // (2)--(3)-(4)
-  graph = BuildGraph(5, {{0, 1, 1},
-                     {0, 2, 1},
-                     {0, 3, 1},
-                     {1, 3, 1},
-                     {1, 4, 1},
-                     {2, 3, 1},
-                     {3, 4, 1}});
-  deg = {3, 3, 2, 4, 2};
-  ASSERT_TRUE(DegreeCheck(graph, deg));
-
-  // Graph with self loop [*nodes have self loops]
-  // (0)--(1*)
-  //  | \  | \
-  //  |  \ |  \
-  // (2*)--(3)-(4*)
-  graph = BuildGraph(5, {{0, 1, 1},
-                     {0, 2, 1},
-                     {0, 3, 1},
-                     {1, 3, 1},
-                     {1, 4, 1},
-                     {2, 3, 1},
-                     {3, 4, 1},
-                     {1, 1, 1},
-                     {2, 2, 2},
-                     {4, 4, 4}});
-  deg = {3, 4, 3, 4, 3};
-  ASSERT_TRUE(DegreeCheck(graph, deg));
-
-  // Try to get degree of non-existing nodes
-  EXPECT_THROW({ graph.Degree(5); }, std::out_of_range);
-  EXPECT_THROW({ graph.Degree(100); }, std::out_of_range);
-}
-
-TEST(Graph, Weights) {
-  // Graph without edges
-  comdata::Graph graph = GenRandomUnweightedGraph(5, 0);
-  std::vector<double> inc_w = {0, 0, 0, 0, 0};
-  ASSERT_TRUE(IncidentWeightCheck(graph, inc_w));
-  ASSERT_EQ(graph.TotalWeight(), 0);
-
-  // Chain
-  // (0)--(1)--(2)--(3)--(4)
-  graph = BuildGraph(5, {{0, 1, 0.1},
-                     {1, 2, 0.5},
-                     {2, 3, 2.3},
-                     {3, 4, 4.2}});
-  inc_w = {0.1, 0.6, 2.8, 6.5, 4.2};
-  ASSERT_TRUE(IncidentWeightCheck(graph, inc_w));
-  ASSERT_NEAR(graph.TotalWeight(), 7.1, 1e-6);
-
-  // Tree
-  //      (0)--(3)
-  //     /   \
-  //   (1)   (2)
-  //    |   /   \
-  //   (4) (5)  (6)
-  graph = BuildGraph(7, {{0, 1, 1.3},
-                     {0, 2, 0.2},
-                     {0, 3, 1},
-                     {1, 4, 3.2},
-                     {2, 5, 4.2},
-                     {2, 6, 0.7}});
-  inc_w = {2.5, 4.5, 5.1, 1, 3.2, 4.2, 0.7};
-  ASSERT_TRUE(IncidentWeightCheck(graph, inc_w));
-  EXPECT_NEAR(graph.TotalWeight(), 10.6, 1e-6);
-
-  // Graph without self-loops
-  // (0)--(1)
-  //  | \  | \
-  //  |  \ |  \
-  // (2)--(3)-(4)
-  graph = BuildGraph(5, {{0, 1, 0.1},
-                     {0, 2, 0.2},
-                     {0, 3, 0.3},
-                     {1, 3, 0.4},
-                     {1, 4, 0.5},
-                     {2, 3, 0.6},
-                     {3, 4, 0.7}});
-  inc_w = {0.6, 1, 0.8, 2, 1.2};
-  ASSERT_TRUE(IncidentWeightCheck(graph, inc_w));
-  EXPECT_NEAR(graph.TotalWeight(), 2.8, 1e-6);
-
-  // Graph with self loop [*nodes have self loops]
-  // (0)--(1*)
-  //  | \  | \
-  //  |  \ |  \
-  // (2*)--(3)-(4*)
-  graph = BuildGraph(5, {{0, 1, 0.1},
-                     {0, 2, 0.2},
-                     {0, 3, 0.3},
-                     {1, 3, 0.4},
-                     {1, 4, 0.5},
-                     {2, 3, 0.6},
-                     {3, 4, 0.7},
-                     {1, 1, 0.8},
-                     {2, 2, 0.9},
-                     {4, 4, 1}});
-  inc_w = {0.6, 1.8, 1.7, 2, 2.2};
-  ASSERT_TRUE(IncidentWeightCheck(graph, inc_w));
-  EXPECT_NEAR(graph.TotalWeight(), 5.5, 1e-6);
-
-  // Try to get incident weight of non-existing node
-  EXPECT_THROW({ graph.IncidentWeight(5); }, std::out_of_range);
-  EXPECT_THROW({ graph.IncidentWeight(100); }, std::out_of_range);
-}
-
-TEST(Graph, Modularity) {
-  // Graph without edges
-  comdata::Graph graph = GenRandomUnweightedGraph(5, 0);
-  ASSERT_EQ(graph.Modularity(), 0);
-
-  // Chain
-  // (0)--(1)--(2)--(3)--(4)
-  graph = BuildGraph(5, {{0, 1, 0.1},
-                     {1, 2, 0.5},
-                     {2, 3, 2.3},
-                     {3, 4, 4.2}});
-  std::vector<uint32_t> c = {0, 1, 1, 2, 2};
-  SetCommunities(&graph, c);
-  EXPECT_NEAR(graph.Modularity(), 0.036798254314620096, 1e-6);
-
-  // Tree
-  //      (0)--(3)
-  //     /   \
-  //   (1)   (2)
-  //    |   /   \
-  //   (4) (5)  (6)
-  graph = BuildGraph(7, {{0, 1, 1.3},
-                     {0, 2, 0.2},
-                     {0, 3, 1},
-                     {1, 4, 3.2},
-                     {2, 5, 4.2},
-                     {2, 6, 0.7}});
-  c = {0, 0, 1, 0, 0, 1, 2};
-  SetCommunities(&graph, c);
-  EXPECT_NEAR(graph.Modularity(), 0.4424617301530794, 1e-6);
-
-  // Graph without self-loops
-  // (0)--(1)
-  //  | \  | \
-  //  |  \ |  \
-  // (2)--(3)-(4)
-  graph = BuildGraph(5, {{0, 1, 0.1},
-                     {0, 2, 0.2},
-                     {0, 3, 0.3},
-                     {1, 3, 0.4},
-                     {1, 4, 0.5},
-                     {2, 3, 0.6},
-                     {3, 4, 0.7}});
-  c = {0, 1, 1, 1, 1};
-  SetCommunities(&graph, c);
-  EXPECT_NEAR(graph.Modularity(), -0.022959183673469507, 1e-6);
-
-  // Graph with self loop [*nodes have self loops]
-  // (0)--(1*)
-  //  | \  | \
-  //  |  \ |  \
-  // (2*)--(3)-(4*)
-  graph = BuildGraph(5, {{0, 1, 0.1},
-                     {0, 2, 0.2},
-                     {0, 3, 0.3},
-                     {1, 3, 0.4},
-                     {1, 4, 0.5},
-                     {2, 3, 0.6},
-                     {3, 4, 0.7},
-                     {1, 1, 0.8},
-                     {2, 2, 0.9},
-                     {4, 4, 1}});
-  c = {0, 0, 0, 0, 1};
-  SetCommunities(&graph, c);
-  EXPECT_NEAR(graph.Modularity(), 0.188842975206611, 1e-6);
-
-  // Neo4j example graph
-  // (0)--(1)---(3)--(4)
-  //   \  /       \ /
-  //    (2)       (5)
-  graph = BuildGraph(6, {{0, 1, 1},
-                         {1, 2, 1},
-                         {0, 2, 1},
-                         {1, 3, 1},
-                         {3, 5, 1},
-                         {5, 4, 1},
-                         {3, 4, 1}});
-  c = {0, 0, 0, 1, 1, 1};
-  SetCommunities(&graph, c);
-  EXPECT_NEAR(graph.Modularity(), 0.3571428571428571, 1e-6);
-
-  // Example graph from wikipedia
-  // (0)--(1)--(3)--(4)--(5)
-  //   \  /     |      \ /
-  //    (2)    (7)     (6)
-  //          /   \
-  //         (8)--(9)
-  graph = BuildGraph(10, {{0, 1, 1},
-                          {1, 2, 1},
-                          {0, 2, 1},
-                          {1, 3, 1},
-                          {3, 4, 1},
-                          {4, 5, 1},
-                          {5, 6, 1},
-                          {6, 4, 1},
-                          {3, 7, 1},
-                          {7, 8, 1},
-                          {7, 9, 1},
-                          {8, 9, 1}});
-  c = {0, 0, 0, 0, 1, 1, 1, 2, 2, 2};
-  SetCommunities(&graph, c);
-  EXPECT_NEAR(graph.Modularity(), 0.4896, 1e-4);
-}

query_modules/louvain/test/unit/utils.cpp

@@ -1,32 +0,0 @@
-#include "utils.hpp"
-
-#include <random>
-
-comdata::Graph BuildGraph(
-    uint32_t nodes, std::vector<std::tuple<uint32_t, uint32_t, double>> edges) {
-  comdata::Graph G(nodes);
-  for (auto &edge : edges)
-    G.AddEdge(std::get<0>(edge), std::get<1>(edge), std::get<2>(edge));
-  return G;
-}
-
-comdata::Graph GenRandomUnweightedGraph(uint32_t nodes, uint32_t edges) {
-  auto seed =
-      std::chrono::high_resolution_clock::now().time_since_epoch().count();
-  std::mt19937 rng(seed);
-  std::uniform_int_distribution<uint32_t> dist(0, nodes - 1);
-  std::set<std::tuple<uint32_t, uint32_t, double>> E;
-  for (uint32_t i = 0; i < edges; ++i) {
-    int u;
-    int v;
-    do {
-      u = dist(rng);
-      v = dist(rng);
-      if (u > v) std::swap(u, v);
-    } while (u == v || E.find({u, v, 1}) != E.end());
-    E.insert({u, v, 1});
-  }
-  return BuildGraph(nodes, std::vector<std::tuple<uint32_t, uint32_t, double>>(
-                               E.begin(), E.end()));
-}
-

query_modules/louvain/test/unit/utils.hpp

@@ -1,18 +0,0 @@
-#pragma once
-
-#include <chrono>
-#include <random>
-#include <set>
-#include <tuple>
-
-#include "data_structures/graph.hpp"
-
-/// Builds the graph from a given number of nodes and a list of edges.
-/// Nodes should be 0-indexed and each edge should be provided only once.
-comdata::Graph BuildGraph(
-    uint32_t nodes, std::vector<std::tuple<uint32_t, uint32_t, double>> edges);
-
-/// Generates random undirected graph with a given number of nodes and edges.
-/// The generated graph is not picked out of a uniform distribution. All weights
-/// are the same and equal to one.
-comdata::Graph GenRandomUnweightedGraph(uint32_t nodes, uint32_t edges);

query_modules/mgp_networkx.py

@@ -0,0 +1,289 @@
+import sys
+import mgp
+import collections
+try:
+    import networkx as nx
+except ImportError as import_error:
+    sys.stderr.write((
+        '\n'
+        'NOTE: Please install networkx to be able to use Memgraph NetworkX '
+        'wrappers. Using Python:\n'
+        + sys.version +
+        '\n'))
+    raise import_error
+
+
+class MemgraphAdjlistOuterDict(collections.abc.Mapping):
+    __slots__ = ('_ctx', '_succ', '_multi')
+
+    def __init__(self, ctx, succ=True, multi=True):
+        self._ctx = ctx
+        self._succ = succ
+        self._multi = multi
+
+    def __getitem__(self, key):
+        if key not in self:
+            raise KeyError
+        return MemgraphAdjlistInnerDict(key, succ=self._succ,
+                                        multi=self._multi)
+
+    def __iter__(self):
+        return iter(self._ctx.graph.vertices)
+
+    def __len__(self):
+        return len(self._ctx.graph.vertices)
+
+    def __contains__(self, key):
+        if not isinstance(key, mgp.Vertex):
+            raise TypeError
+        return key in self._ctx.graph.vertices
+
+
+class MemgraphAdjlistInnerDict(collections.abc.Mapping):
+    __slots__ = ('_node', '_succ', '_multi', '_neighbors')
+
+    def __init__(self, node, succ=True, multi=True):
+        self._node = node
+        self._succ = succ
+        self._multi = multi
+        self._neighbors = None
+
+    def __getitem__(self, key):
+        # NOTE: NetworkX 2.4, classes/coreviews.py:143. UnionAtlas expects a
+        # KeyError when indexing with a vertex that is not a neighbor.
+        if key not in self:
+            raise KeyError
+        if not self._multi:
+            return UnhashableProperties(self._get_edge(key).properties)
+        return MemgraphEdgeKeyDict(self._node, key, self._succ)
+
+    def __iter__(self):
+        yield from self._get_neighbors()
+
+    def __len__(self):
+        return len(self._get_neighbors())
+
+    def __contains__(self, key):
+        if not isinstance(key, mgp.Vertex):
+            raise TypeError
+        return key in self._get_neighbors()
+
+    def _get_neighbors(self):
+        if not self._neighbors:
+            if self._succ:
+                self._neighbors = set(
+                    e.to_vertex for e in self._node.out_edges)
+            else:
+                self._neighbors = set(
+                    e.from_vertex for e in self._node.in_edges)
+        return self._neighbors
+
+    def _get_edge(self, neighbor):
+        if self._succ:
+            edge = list(filter(lambda e: e.to_vertex == neighbor,
+                               self._node.out_edges))
+        else:
+            edge = list(filter(lambda e: e.from_vertex == neighbor,
+                               self._node.in_edges))
+
+        assert len(edge) >= 1
+        if len(edge) > 1:
+            raise RuntimeError('Graph contains multiedges but '
+                               'is of non-multigraph type: {}'.format(edge))
+
+        return edge[0]
+
+
+class MemgraphEdgeKeyDict(collections.abc.Mapping):
+    __slots__ = ('_node', '_neighbor', '_succ', '_edges')
+
+    def __init__(self, node, neighbor, succ=True):
+        self._node = node
+        self._neighbor = neighbor
+        self._succ = succ
+        self._edges = None
+
+    def __getitem__(self, key):
+        if key not in self:
+            raise KeyError
+        return UnhashableProperties(key.properties)
+
+    def __iter__(self):
+        yield from self._get_edges()
+
+    def __len__(self):
+        return len(self._get_edges())
+
+    def __contains__(self, key):
+        if not isinstance(key, mgp.Edge):
+            raise TypeError
+        return key in self._get_edges()
+
+    def _get_edges(self):
+        if not self._edges:
+            if self._succ:
+                self._edges = list(filter(
+                    lambda e: e.to_vertex == self._neighbor,
+                    self._node.out_edges))
+            else:
+                self._edges = list(filter(
+                    lambda e: e.from_vertex == self._neighbor,
+                    self._node.in_edges))
+        return self._edges
+
+
+class UnhashableProperties(collections.abc.Mapping):
+    __slots__ = ('_properties')
+
+    def __init__(self, properties):
+        self._properties = properties
+
+    def __getitem__(self, key):
+        return self._properties[key]
+
+    def __iter__(self):
+        yield from self._properties
+
+    def __len__(self):
+        return len(self._properties)
+
+    def __contains__(self, key):
+        return key in self._properties
+
+    # NOTE: Explicitly disable hashing. See the comment in MemgraphNodeDict.
+    __hash__ = None
+
+
+class MemgraphNodeDict(collections.abc.Mapping):
+    __slots__ = ('_ctx',)
+
+    def __init__(self, ctx):
+        self._ctx = ctx
+
+    def __getitem__(self, key):
+        if key not in self:
+            raise KeyError
+        # NOTE: NetworkX 2.4, classes/digraph.py:484. NetworkX expects the
+        # tuples provided to add_nodes_from to be unhashable and cause a
+        # TypeError when trying to index the node dictionary. This happens
+        # because the data dictionary element of the tuple is unhashable. We do
+        # the same thing by returning an unhashable data dictionary.
+        return UnhashableProperties(key.properties)
+
+    def __iter__(self):
+        return iter(self._ctx.graph.vertices)
+
+    def __len__(self):
+        return len(self._ctx.graph.vertices)
+
+    def __contains__(self, key):
+        # NOTE: NetworkX 2.4, graph.py:425. Graph.__contains__ relies on
+        # self._node's (i.e. the dictionary produced by node_dict_factory)
+        # __contains__ to raise a TypeError when indexing with something weird,
+        # e.g. with sets. This is the behavior of dict.
+        if not isinstance(key, mgp.Vertex):
+            raise TypeError
+        return key in self._ctx.graph.vertices
+
+
+class MemgraphDiGraphBase:
+    def __init__(self, incoming_graph_data=None, ctx=None, multi=True,
+                 **kwargs):
+        # NOTE: We assume that our graph will never be given any initial data
+        # because we already pull our data from the Memgraph database. This
+        # assert is triggered by certain NetworkX procedures because they
+        # create a new instance of our class and try to populate it with their
+        # own data.
+        assert incoming_graph_data is None
+
+        # NOTE: We allow for ctx to be None in order to allow certain NetworkX
+        # procedures (such as `subgraph`) to work. Such procedures directly
+        # modify the graph's internal attributes and don't try to populate it
+        # with initial data or modify it.
+
+        self.node_dict_factory = lambda: MemgraphNodeDict(ctx) \
+            if ctx else self._error
+        self.node_attr_dict_factory = self._error
+
+        self.adjlist_outer_dict_factory = \
+            lambda: MemgraphAdjlistOuterDict(ctx, multi=multi) \
+            if ctx else self._error
+        self.adjlist_inner_dict_factory = self._error
+        self.edge_key_dict_factory = self._error
+        self.edge_attr_dict_factory = self._error
+
+        # NOTE: We forbid any mutating operations because our graph is
+        # immutable and pulls its data from the Memgraph database.
+        for f in ['add_node', 'add_nodes_from', 'remove_node',
+                  'remove_nodes_from', 'add_edge', 'add_edges_from',
+                  'add_weighted_edges_from', 'new_edge_key', 'remove_edge',
+                  'remove_edges_from', 'update', 'clear']:
+            setattr(self, f, lambda *args, **kwargs: self._error())
+
+        super().__init__(None, **kwargs)
+
+        # NOTE: This is a necessary hack because NetworkX assumes that the
+        # customizable factory functions will only ever return *empty*
+        # dictionaries. In our case, the factory functions return our custom,
+        # already populated, dictionaries. Because self._pred and self._end are
+        # initialized by the same factory function, they end up storing the
+        # same adjacency lists which is not good. We correct that here.
+        self._pred = MemgraphAdjlistOuterDict(ctx, succ=False, multi=multi)
+
+    def _error(self):
+        raise RuntimeError('Modification operations are not supported')
+
+
+class MemgraphMultiDiGraph(MemgraphDiGraphBase, nx.MultiDiGraph):
+    def __init__(self, incoming_graph_data=None, ctx=None, **kwargs):
+        super().__init__(incoming_graph_data=incoming_graph_data,
+                         ctx=ctx, multi=True, **kwargs)
+
+
+def MemgraphMultiGraph(incoming_graph_data=None, ctx=None, **kwargs):
+    return MemgraphMultiDiGraph(incoming_graph_data=incoming_graph_data,
+                                ctx=ctx, **kwargs).to_undirected(as_view=True)
+
+
+class MemgraphDiGraph(MemgraphDiGraphBase, nx.DiGraph):
+    def __init__(self, incoming_graph_data=None, ctx=None, **kwargs):
+        super().__init__(incoming_graph_data=incoming_graph_data,
+                         ctx=ctx, multi=False, **kwargs)
+
+
+def MemgraphGraph(incoming_graph_data=None, ctx=None, **kwargs):
+    return MemgraphDiGraph(incoming_graph_data=incoming_graph_data,
+                           ctx=ctx, **kwargs).to_undirected(as_view=True)
+
+
+class PropertiesDictionary(collections.abc.Mapping):
+    __slots__ = ('_ctx', '_prop', '_len')
+
+    def __init__(self, ctx, prop):
+        self._ctx = ctx
+        self._prop = prop
+        self._len = None
+
+    def __getitem__(self, vertex):
+        if vertex not in self:
+            raise KeyError
+        try:
+            return vertex.properties[self._prop]
+        except KeyError:
+            raise KeyError(("{} doesn\t have the required " +
+                            "property '{}'").format(vertex, self._prop))
+
+    def __iter__(self):
+        for v in self._ctx.graph.vertices:
+            if self._prop in v.properties:
+                yield v
+
+    def __len__(self):
+        if not self._len:
+            self._len = sum(1 for _ in self)
+        return self._len
+
+    def __contains__(self, vertex):
+        if not isinstance(vertex, mgp.Vertex):
+            raise TypeError
+        return self._prop in vertex.properties