Some changes

Add new dataset for mgbench

.clang-format

@@ -1,10 +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

@@ -1,7 +1,12 @@
 ---
 Checks: '*,
+         -abseil-string-find-str-contains,
+         -altera-id-dependent-backward-branch,
+         -altera-struct-pack-align,
+         -altera-unroll-loops,
          -android-*,
          -cert-err58-cpp,
+         -cert-str34-c,
          -cppcoreguidelines-avoid-c-arrays,
          -cppcoreguidelines-avoid-goto,
          -cppcoreguidelines-avoid-magic-numbers,
@@ -26,6 +31,7 @@ Checks: '*,
          -fuchsia-virtual-inheritance,
          -google-explicit-constructor,
          -google-readability-*,
+         -google-runtime-references,
          -hicpp-avoid-c-arrays,
          -hicpp-avoid-goto,
          -hicpp-braces-around-statements,
@@ -34,15 +40,17 @@ 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-loop-convert,
          -modernize-pass-by-value,
          -modernize-use-equals-default,
          -modernize-use-nodiscard,
@@ -50,11 +58,16 @@ 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,
+         -concurrency-mt-unsafe,
+         -bugprone-easily-swappable-parameters'
+
 WarningsAsErrors: ''
-HeaderFilterRegex: ''
+HeaderFilterRegex: 'src/.*'
 AnalyzeTemporaryDtors: false
 FormatStyle:     none
 CheckOptions:
@@ -79,4 +92,3 @@ CheckOptions:
   - key:             modernize-use-nullptr.NullMacros
     value:           'NULL'
 ...
-

.githooks/pre-commit

@@ -15,7 +15,8 @@ exec 1>&2
 tmpdir=$(mktemp -d repo-XXXXXXXX)
 trap "rm -rf $tmpdir" EXIT INT
 
-modified_files=$(git diff --cached --name-only --diff-filter=AM $against | sed -nE "/.*\.(cpp|cc|cxx|c|h|hpp|lcp)$/p")
+modified_files=$(git diff --cached --name-only --diff-filter=AM $against | sed -nE "/.*\.(cpp|cc|cxx|c|h|hpp)$/p")
+FAIL=0
 for file in $modified_files; do
   echo "Checking $file..."
 
@@ -23,21 +24,13 @@ for file in $modified_files; do
 
   git checkout-index --prefix="$tmpdir/" -- $file
 
-  echo "Running clang-format..."
+  # Do not break header checker
-  $project_folder/tools/git-clang-format $tmpdir/$file
+  echo "Running header checker..."
-  code=$?
+  $project_folder/tools/header-checker.py $tmpdir/$file $file --amend-year
-
+  CODE=$?
-  if [ $code -ne 0 ]; then
+  if [ $CODE -ne 0 ]; then
-    break
+    FAIL=1
-  fi
-
-  echo "Running clang-tidy..."
-  $project_folder/tools/git-clang-tidy $tmpdir/$file
-  code=$?
-
-  if [ $code -ne 0 ]; then
-   break
   fi
 done;
 
-return $code
+return ${FAIL}

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,34 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: "[BUG] "
+labels: bug
+assignees: gitbuda, antonio2368
+
+---
+
+
+**Memgraph version**
+Which version did you use?
+
+**Environment**
+Some information about the environment you are using Memgraph on: operating
+system, how do you connect, with or without docker, which driver etc.
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**To Reproduce**
+Steps to reproduce the behavior:
+1. Run the following query '...'
+2. Click on '....'
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Logs**
+If applicable, add logs of Memgraph, CLI output or screenshots to help explain
+your problem.
+
+**Additional context**
+Add any other context about the problem here.

.github/pull_request_template.md

@@ -0,0 +1,11 @@
+[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
+- [ ] Provide the full content or a guide for the final git message
+
+[master < Task] PR
+- [ ] Check, and update documentation if necessary
+- [ ] Update [changelog](https://docs.memgraph.com/memgraph/changelog)
+- [ ] Provide the full content or a guide for the final git message

.github/workflows/daily_benchmark.yaml

@@ -0,0 +1,82 @@
+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
+      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
+      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
+
+    steps:
+      - name: Set up repository
+        uses: actions/checkout@v3
+        with:
+          # Number of commits to fetch. `0` indicates all history for all
+          # branches and tags. (default: 1)
+          fetch-depth: 0
+
+      - name: Build release binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v4/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build only memgraph release binaries.
+          cd build
+          cmake -DCMAKE_BUILD_TYPE=release ..
+          make -j$THREADS
+
+      - name: Run macro benchmarks
+        run: |
+          cd tests/macro_benchmark
+          ./harness QuerySuite MemgraphRunner \
+            --groups aggregation 1000_create unwind_create dense_expand match \
+            --no-strict
+
+      - name: Get branch name (merge)
+        if: github.event_name != 'pull_request'
+        shell: bash
+        run: echo "BRANCH_NAME=$(echo ${GITHUB_REF#refs/heads/} | tr / -)" >> $GITHUB_ENV
+
+      - name: Get branch name (pull request)
+        if: github.event_name == 'pull_request'
+        shell: bash
+        run: echo "BRANCH_NAME=$(echo ${GITHUB_HEAD_REF} | tr / -)" >> $GITHUB_ENV
+
+      - name: Upload macro benchmark results
+        run: |
+          cd tools/bench-graph-client
+          virtualenv -p python3 ve3
+          source ve3/bin/activate
+          pip install -r requirements.txt
+          ./main.py --benchmark-name "macro_benchmark" \
+                    --benchmark-results-path "../../tests/macro_benchmark/.harness_summary" \
+                    --github-run-id "${{ github.run_id }}" \
+                    --github-run-number "${{ github.run_number }}" \
+                    --head-branch-name "${{ env.BRANCH_NAME }}"
+
+      - name: Run mgbench
+        run: |
+          cd tests/mgbench
+          ./benchmark.py --num-workers-for-benchmark 12 --export-results benchmark_result.json pokec/medium/*/*
+
+      - name: Upload mgbench results
+        run: |
+          cd tools/bench-graph-client
+          virtualenv -p python3 ve3
+          source ve3/bin/activate
+          pip install -r requirements.txt
+          ./main.py --benchmark-name "mgbench" \
+                    --benchmark-results-path "../../tests/mgbench/benchmark_result.json" \
+                    --github-run-id "${{ github.run_id }}" \
+                    --github-run-number "${{ github.run_number }}" \
+                    --head-branch-name "${{ env.BRANCH_NAME }}"

.github/workflows/diff.yaml

@@ -1,21 +1,32 @@
 name: Diff
+concurrency:
+  group: ${{ github.head_ref || github.sha }}
+  cancel-in-progress: true
 
 on:
   push:
+    branches:
+      - master
+  workflow_dispatch:
+  pull_request:
     paths-ignore:
-      - 'docs/**'
+      - "docs/**"
-      - '*.md'
+      - "**/*.md"
+      - ".clang-format"
+      - "CODEOWNERS"
 
 jobs:
   community_build:
     name: "Community build"
-    runs-on: [self-hosted, General, Linux, X64, Debian10]
+    runs-on: [self-hosted, Linux, X64, Diff]
     env:
       THREADS: 24
+      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
+      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -24,7 +35,7 @@ jobs:
       - name: Build community binaries
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Initialize dependencies.
           ./init
@@ -37,57 +48,83 @@ jobs:
       - name: Run unit tests
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Run unit tests.
           cd build
-          ctest -R memgraph__unit --output-on-failure
+          ctest -R memgraph__unit --output-on-failure -j$THREADS
 
-      - name: Run stress test
+  code_analysis:
-        run: |
+    name: "Code analysis"
-          cd tests/stress
+    runs-on: [self-hosted, Linux, X64, Diff]
-          ./continuous_integration
-
-  coverage_build:
-    name: "Coverage build"
-    runs-on: [self-hosted, General, Linux, X64, Debian10]
     env:
       THREADS: 24
+      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
+      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
           fetch-depth: 0
 
-      - name: Build coverage binaries
+        # This is also needed if we want do to comparison against other branches
+        # See https://github.community/t/checkout-code-fails-when-it-runs-lerna-run-test-since-master/17920
+      - name: Fetch all history for all tags and branches
+        run: git fetch
+
+      - name: Initialize deps
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
-
           # Initialize dependencies.
           ./init
 
-          # Build coverage binaries.
+      - name: Set base branch
+        if: ${{ github.event_name == 'pull_request' }}
+        run: |
+          echo "BASE_BRANCH=origin/${{ github.base_ref }}" >> $GITHUB_ENV
+
+      - name: Set base branch # if we manually dispatch or push to master
+        if: ${{ github.event_name != 'pull_request' }}
+        run: |
+          echo "BASE_BRANCH=origin/master" >> $GITHUB_ENV
+
+      - name: Python code analysis
+        run: |
+          CHANGED_FILES=$(git diff -U0 ${{ env.BASE_BRANCH }}... --name-only)
+          for file in ${CHANGED_FILES}; do
+            echo ${file}
+            if [[ ${file} == *.py ]]; then
+              python3 -m black --check --diff ${file}
+              python3 -m isort --check-only --diff ${file}
+            fi
+          done
+
+      - name: Build combined ASAN, UBSAN and coverage binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v4/activate
+
           cd build
-          cmake -DTEST_COVERAGE=ON ..
+          cmake -DTEST_COVERAGE=ON -DASAN=ON -DUBSAN=ON ..
           make -j$THREADS memgraph__unit
 
       - name: Run unit tests
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
-          # Run unit tests.
+          # Run unit tests. It is restricted to 2 threads intentionally, because higher concurrency makes the timing related tests unstable.
           cd build
-          ctest -R memgraph__unit --output-on-failure
+          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-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Compute code coverage.
           cd tools/github
@@ -98,20 +135,42 @@ jobs:
           tar -czf code_coverage.tar.gz coverage.json html report.json summary.rmu
 
       - name: Save code coverage
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: "Code coverage"
           path: tools/github/generated/code_coverage.tar.gz
 
+      - name: Set base branch
+        if: ${{ github.event_name == 'pull_request' }}
+        run: |
+          echo "BASE_BRANCH=origin/${{ github.base_ref }}" >> $GITHUB_ENV
+
+      - name: Set base branch # if we manually dispatch or push to master
+        if: ${{ github.event_name != 'pull_request' }}
+        run: |
+          echo "BASE_BRANCH=origin/master" >> $GITHUB_ENV
+
+      - name: Run clang-tidy
+        run: |
+          source /opt/toolchain-v4/activate
+
+          # Restrict clang-tidy results only to the modified parts
+          git diff -U0 ${{ env.BASE_BRANCH }}... -- src | ./tools/github/clang-tidy/clang-tidy-diff.py -p 1 -j $THREADS -extra-arg="-DMG_CLANG_TIDY_CHECK" -path build | tee ./build/clang_tidy_output.txt
+
+          # Fail if any warning is reported
+          ! cat ./build/clang_tidy_output.txt | ./tools/github/clang-tidy/grep_error_lines.sh > /dev/null
+
   debug_build:
     name: "Debug build"
-    runs-on: [self-hosted, General, Linux, X64, Debian10]
+    runs-on: [self-hosted, Linux, X64, Diff]
     env:
       THREADS: 24
+      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
+      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -120,7 +179,7 @@ jobs:
       - name: Build debug binaries
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Initialize dependencies.
           ./init
@@ -130,86 +189,44 @@ jobs:
           cmake ..
           make -j$THREADS
 
-      - name: Run leftover CTest tests
+      - name: Run simulation tests
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
-          # Run leftover CTest tests (all except unit and benchmark tests).
+          # Run simulation tests.
           cd build
-          ctest -E "(memgraph__unit|memgraph__benchmark)" --output-on-failure
+          ctest -R memgraph__simulation --output-on-failure -j$THREADS
 
-      - name: Run drivers tests
+      - name: Run single benchmark test
-        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-v2/activate
+          source /opt/toolchain-v4/activate
 
-          # Run cppcheck and clang-format.
+          # Run simulation tests.
-          cd tools/github
+          cd tests/mgbench
-          ./cppcheck_and_clang_format diff
+          ./benchmark.py accesscontrol/small --num-workers-for-import 1 --test-system-arg  "split-file splitfiles/accesscontrol_small.shard_configuration bolt-num-workers 1"
-
-      - 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, General, Linux, X64, Debian10]
+    runs-on: [self-hosted, Linux, X64, Diff]
     env:
       THREADS: 24
+      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
+      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
           fetch-depth: 0
 
-      - name: Set up parent
-        run: |
-          # Remove parent folder (if it exists).
-          cd ..
-          if [ -d parent ]; then
-            rm -rf parent
-          fi
-
-          # Copy untouched repository to parent folder.
-          cp -r memgraph parent
-
-          # Checkout previous commit
-          cd parent
-          git checkout HEAD~1
-
       - name: Build release binaries
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Initialize dependencies.
           ./init
@@ -219,72 +236,38 @@ jobs:
           cmake -DCMAKE_BUILD_TYPE=release ..
           make -j$THREADS
 
-      - name: Build parent binaries
+      - name: Run unit tests
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
-          # Initialize dependencies.
+          # Run unit tests.
-          cd ../parent
-          ./init
-
-          # Build parent binaries.
           cd build
-          cmake -DCMAKE_BUILD_TYPE=release ..
+          ctest -R memgraph__unit --output-on-failure -j$THREADS
-          make -j$THREADS memgraph memgraph__macro_benchmark
 
-      - name: Run macro benchmark tests
+      - name: Run simulation tests
         run: |
-          cd tests/macro_benchmark
+          # Activate toolchain.
-          ./harness QuerySuite MemgraphRunner \
+          source /opt/toolchain-v4/activate
-            --groups aggregation 1000_create unwind_create dense_expand match \
-            --no-strict
 
-      - name: Run parent macro benchmark tests
+          # Run simulation tests.
+          cd build
+          ctest -R memgraph__simulation --output-on-failure -j$THREADS
+
+      - name: Run single benchmark test
         run: |
-          cd ../parent/tests/macro_benchmark
+          # Activate toolchain.
-          ./harness QuerySuite MemgraphRunner \
+          source /opt/toolchain-v4/activate
-            --groups aggregation 1000_create unwind_create dense_expand match \
-            --no-strict
 
-      - name: Compute macro benchmark summary
+          # Run simulation tests.
+          cd tests/mgbench
+          ./benchmark.py accesscontrol/small --num-workers-for-import 1 --test-system-arg  "split-file splitfiles/accesscontrol_small.shard_configuration bolt-num-workers 1"
+
+      - name: Run e2e tests
         run: |
-          ./tools/github/macro_benchmark_summary \
+          # TODO(gitbuda): Setup mgclient and pymgclient properly.
-            --current tests/macro_benchmark/.harness_summary \
+          cd tests
-            --previous ../parent/tests/macro_benchmark/.harness_summary \
+          ./setup.sh
-            --output macro_benchmark_summary.txt
-
-      - name: Save macro benchmark summary
-        uses: actions/upload-artifact@v2
-        with:
-          name: "Macro benchmark summary"
-          path: macro_benchmark_summary.txt
-
-      - 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 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
+          cd e2e
+          LD_LIBRARY_PATH=$LD_LIBRARY_PATH:../../libs/mgclient/lib python runner.py --workloads-root-directory ./distributed_queries

.github/workflows/full_clang_tidy.yaml

@@ -0,0 +1,46 @@
+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
+      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
+      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
+
+    steps:
+      - name: Set up repository
+        uses: actions/checkout@v3
+        with:
+          # Number of commits to fetch. `0` indicates all history for all
+          # branches and tags. (default: 1)
+          fetch-depth: 0
+
+      - name: Build debug binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v4/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build debug binaries.
+
+          cd build
+          cmake ..
+          make -j$THREADS
+
+      - name: Run clang-tidy
+        run: |
+          source /opt/toolchain-v4/activate
+
+          # The results are also written to standard output in order to retain them in the logs
+          ./tools/github/clang-tidy/run-clang-tidy.py -p build -j $THREADS -extra-arg="-DMG_CLANG_TIDY_CHECK" -clang-tidy-binary=/opt/toolchain-v4/bin/clang-tidy "$PWD/src/*" |
+            tee ./build/full_clang_tidy_output.txt
+
+      - name: Summarize clang-tidy results
+        run: cat ./build/full_clang_tidy_output.txt | ./tools/github/clang-tidy/count_errors.sh

.github/workflows/package_all.yaml

@@ -0,0 +1,178 @@
+name: Package All
+
+# TODO(gitbuda): Cleanup docker container if GHA job was canceled.
+
+on: workflow_dispatch
+
+jobs:
+  centos-7:
+    runs-on: [self-hosted, DockerMgBuild, X64]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package centos-7
+      - name: "Upload package"
+        uses: actions/upload-artifact@v3
+        with:
+          name: centos-7
+          path: build/output/centos-7/memgraph*.rpm
+
+  centos-9:
+    runs-on: [self-hosted, DockerMgBuild, X64]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package centos-9
+      - name: "Upload package"
+        uses: actions/upload-artifact@v3
+        with:
+          name: centos-9
+          path: build/output/centos-9/memgraph*.rpm
+
+  debian-10:
+    runs-on: [self-hosted, DockerMgBuild, X64]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package debian-10
+      - name: "Upload package"
+        uses: actions/upload-artifact@v3
+        with:
+          name: debian-10
+          path: build/output/debian-10/memgraph*.deb
+
+  debian-11:
+    runs-on: [self-hosted, DockerMgBuild, X64]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package debian-11
+      - name: "Upload package"
+        uses: actions/upload-artifact@v3
+        with:
+          name: debian-11
+          path: build/output/debian-11/memgraph*.deb
+
+  docker:
+    runs-on: [self-hosted, DockerMgBuild, X64]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          cd release/package
+          ./run.sh package debian-11 --for-docker
+          ./run.sh docker
+      - name: "Upload package"
+        uses: actions/upload-artifact@v3
+        with:
+          name: docker
+          path: build/output/docker/memgraph*.tar.gz
+
+  ubuntu-1804:
+    runs-on: [self-hosted, DockerMgBuild, X64]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package ubuntu-18.04
+      - name: "Upload package"
+        uses: actions/upload-artifact@v3
+        with:
+          name: ubuntu-1804
+          path: build/output/ubuntu-18.04/memgraph*.deb
+
+  ubuntu-2004:
+    runs-on: [self-hosted, DockerMgBuild, X64]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package ubuntu-20.04
+      - name: "Upload package"
+        uses: actions/upload-artifact@v3
+        with:
+          name: ubuntu-2004
+          path: build/output/ubuntu-20.04/memgraph*.deb
+
+  ubuntu-2204:
+    runs-on: [self-hosted, DockerMgBuild, X64]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package ubuntu-22.04
+      - name: "Upload package"
+        uses: actions/upload-artifact@v3
+        with:
+          name: ubuntu-2204
+          path: build/output/ubuntu-22.04/memgraph*.deb
+
+  debian-11-platform:
+    runs-on: [self-hosted, DockerMgBuild, X64]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package debian-11 --for-platform
+      - name: "Upload package"
+        uses: actions/upload-artifact@v3
+        with:
+          name: debian-11-platform
+          path: build/output/debian-11/memgraph*.deb
+
+  debian-11-arm:
+    runs-on: [self-hosted, DockerMgBuild, ARM64, strange]
+    timeout-minutes: 60
+    steps:
+      - name: "Set up repository"
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0 # Required because of release/get_version.py
+      - name: "Build package"
+        run: |
+          ./release/package/run.sh package debian-11-arm
+      - name: "Upload package"
+        uses: actions/upload-artifact@v3
+        with:
+          name: debian-11-arm
+          path: build/output/debian-11-arm/memgraph*.deb

.github/workflows/release_centos8.yaml

@@ -1,18 +1,23 @@
-name: Release CentOS
+name: Release CentOS 8
 
-on: [workflow_dispatch]
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: "0 1 * * *"
 
 jobs:
   community_build:
     name: "Community build"
-    runs-on: [self-hosted, General, Linux, X64, CentOS7]
+    runs-on: [self-hosted, Linux, X64, CentOS8]
     env:
       THREADS: 24
+      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
+      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
     timeout-minutes: 960
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -21,7 +26,7 @@ jobs:
       - name: Build community binaries
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Initialize dependencies.
           ./init
@@ -31,51 +36,26 @@ jobs:
           cmake -DCMAKE_BUILD_TYPE=release -DMG_ENTERPRISE=OFF ..
           make -j$THREADS
 
-      - name: Create community RPM package
-        run: |
-          # Activate toolchain.
-          source /opt/toolchain-v2/activate
-
-          # Create community RPM package.
-          cd build
-          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-v2/activate
+          source /opt/toolchain-v4/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, General, Linux, X64, CentOS7]
+    runs-on: [self-hosted, Linux, X64, CentOS8]
     env:
       THREADS: 24
+      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
+      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -84,7 +64,7 @@ jobs:
       - name: Build coverage binaries
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Initialize dependencies.
           ./init
@@ -97,7 +77,7 @@ jobs:
       - name: Run unit tests
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Run unit tests.
           cd build
@@ -106,7 +86,7 @@ jobs:
       - name: Compute code coverage
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Compute code coverage.
           cd tools/github
@@ -117,20 +97,22 @@ jobs:
           tar -czf code_coverage.tar.gz coverage.json html report.json summary.rmu
 
       - name: Save code coverage
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: "Code coverage"
           path: tools/github/generated/code_coverage.tar.gz
 
   debug_build:
     name: "Debug build"
-    runs-on: [self-hosted, General, Linux, X64, CentOS7]
+    runs-on: [self-hosted, Linux, X64, CentOS8]
     env:
       THREADS: 24
+      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
+      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -139,7 +121,7 @@ jobs:
       - name: Build debug binaries
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Initialize dependencies.
           ./init
@@ -152,7 +134,7 @@ jobs:
       - name: Run leftover CTest tests
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Run leftover CTest tests (all except unit and benchmark tests).
           cd build
@@ -184,28 +166,30 @@ jobs:
       - name: Run cppcheck and clang-format
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Run cppcheck and clang-format.
           cd tools/github
           ./cppcheck_and_clang_format diff
 
       - name: Save cppcheck and clang-format errors
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: "Code coverage"
           path: tools/github/cppcheck_and_clang_format.txt
 
   release_build:
     name: "Release build"
-    runs-on: [self-hosted, General, Linux, X64, CentOS7]
+    runs-on: [self-hosted, Linux, X64, CentOS8]
     env:
       THREADS: 24
+      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
+      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
     timeout-minutes: 960
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -214,7 +198,7 @@ jobs:
       - name: Build release binaries
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Initialize dependencies.
           ./init
@@ -227,16 +211,21 @@ jobs:
       - name: Create enterprise RPM package
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
+
+          cd build
+
+          # create mgconsole
+          # we use the -B to force the build
+          make -j$THREADS -B mgconsole
 
           # Create enterprise RPM package.
-          cd build
           mkdir output && cd output
           cpack -G RPM --config ../CPackConfig.cmake
           rpmlint memgraph*.rpm
 
       - name: Save enterprise RPM package
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: "Enterprise RPM package"
           path: build/output/memgraph*.rpm
@@ -244,7 +233,7 @@ jobs:
       - name: Run micro benchmark tests
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Run micro benchmark tests.
           cd build
@@ -273,13 +262,31 @@ jobs:
           ./continuous_integration
 
       - name: Save quality assurance status
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: "GQL Behave Status"
           path: |
             tests/gql_behave/gql_behave_status.csv
             tests/gql_behave/gql_behave_status.html
 
+      - name: Run unit tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v4/activate
+
+          # Run unit tests.
+          cd build
+          ctest -R memgraph__unit --output-on-failure
+
+      - 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

.github/workflows/release_debian10.yaml

@@ -0,0 +1,356 @@
+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
+      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
+      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
+    timeout-minutes: 960
+
+    steps:
+      - name: Set up repository
+        uses: actions/checkout@v3
+        with:
+          # Number of commits to fetch. `0` indicates all history for all
+          # branches and tags. (default: 1)
+          fetch-depth: 0
+
+      - name: Build community binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v4/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build community binaries.
+          cd build
+          cmake -DCMAKE_BUILD_TYPE=release -DMG_ENTERPRISE=OFF ..
+          make -j$THREADS
+
+      - name: Run unit tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v4/activate
+
+          # Run unit tests.
+          cd build
+          ctest -R memgraph__unit --output-on-failure
+
+  coverage_build:
+    name: "Coverage build"
+    runs-on: [self-hosted, Linux, X64, Debian10]
+    env:
+      THREADS: 24
+      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
+      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
+
+    steps:
+      - name: Set up repository
+        uses: actions/checkout@v3
+        with:
+          # Number of commits to fetch. `0` indicates all history for all
+          # branches and tags. (default: 1)
+          fetch-depth: 0
+
+      - name: Build coverage binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v4/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build coverage binaries.
+          cd build
+          cmake -DTEST_COVERAGE=ON ..
+          make -j$THREADS memgraph__unit
+
+      - name: Run unit tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v4/activate
+
+          # Run unit tests.
+          cd build
+          ctest -R memgraph__unit --output-on-failure
+
+      - name: Compute code coverage
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v4/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@v3
+        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
+      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
+      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
+
+    steps:
+      - name: Set up repository
+        uses: actions/checkout@v3
+        with:
+          # Number of commits to fetch. `0` indicates all history for all
+          # branches and tags. (default: 1)
+          fetch-depth: 0
+
+      - name: Build debug binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v4/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build debug binaries.
+          cd build
+          cmake ..
+          make -j$THREADS
+
+      - name: Run leftover CTest tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v4/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-v4/activate
+
+          # Run cppcheck and clang-format.
+          cd tools/github
+          ./cppcheck_and_clang_format diff
+
+      - name: Save cppcheck and clang-format errors
+        uses: actions/upload-artifact@v3
+        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
+      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
+      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
+    timeout-minutes: 960
+
+    steps:
+      - name: Set up repository
+        uses: actions/checkout@v3
+        with:
+          # Number of commits to fetch. `0` indicates all history for all
+          # branches and tags. (default: 1)
+          fetch-depth: 0
+
+      - name: Build release binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v4/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build release binaries.
+          cd build
+          cmake -DCMAKE_BUILD_TYPE=release ..
+          make -j$THREADS
+
+      - name: Create enterprise DEB package
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v4/activate
+
+          cd build
+
+          # create mgconsole
+          # we use the -B to force the build
+          make -j$THREADS -B mgconsole
+
+          # Create enterprise DEB package.
+          mkdir output && cd output
+          cpack -G DEB --config ../CPackConfig.cmake
+
+      - name: Save enterprise DEB package
+        uses: actions/upload-artifact@v3
+        with:
+          name: "Enterprise DEB package"
+          path: build/output/memgraph*.deb
+
+      - name: Run micro benchmark tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v4/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@v3
+        with:
+          name: "GQL Behave Status"
+          path: |
+            tests/gql_behave/gql_behave_status.csv
+            tests/gql_behave/gql_behave_status.html
+
+      - name: Run unit tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v4/activate
+
+          # Run unit tests.
+          cd build
+          ctest -R memgraph__unit --output-on-failure
+
+      - 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
+      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
+      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
+    timeout-minutes: 60
+
+    steps:
+      - name: Set up repository
+        uses: actions/checkout@v3
+        with:
+          # Number of commits to fetch. `0` indicates all history for all
+          # branches and tags. (default: 1)
+          fetch-depth: 0
+
+      - name: Build release binaries
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v4/activate
+
+          # Initialize dependencies.
+          ./init
+
+          # Build only memgraph release binary.
+          cd build
+          cmake -DCMAKE_BUILD_TYPE=release ..
+          make -j$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@v3
+        if: ${{ always() }}
+        with:
+          name: "Jepsen Report"
+          path: tests/jepsen/Jepsen.tar.gz

.github/workflows/release_docker.yaml

@@ -0,0 +1,69 @@
+name: Publish Docker images
+
+on:
+  workflow_dispatch:
+    inputs:
+      version:
+        description: "Memgraph binary version to publish on DockerHub."
+        required: true
+      force_release:
+        type: boolean
+        required: false
+        default: false
+
+jobs:
+  docker_publish:
+    runs-on: ubuntu-latest
+    env:
+      DOCKER_ORGANIZATION_NAME: memgraph
+      DOCKER_REPOSITORY_NAME: memgraph
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v1
+
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v1
+
+      - name: Log in to Docker Hub
+        uses: docker/login-action@v1
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+
+      - name: Download memgraph binary
+        run: |
+          cd release/docker
+          curl -L https://download.memgraph.com/memgraph/v${{ github.event.inputs.version }}/debian-11/memgraph_${{ github.event.inputs.version }}-1_amd64.deb > memgraph-amd64.deb
+          curl -L https://download.memgraph.com/memgraph/v${{ github.event.inputs.version }}/debian-11-aarch64/memgraph_${{ github.event.inputs.version }}-1_arm64.deb > memgraph-arm64.deb
+
+      - name: Check if specified version is already pushed
+        run: |
+          EXISTS=$(docker manifest inspect $DOCKER_ORGANIZATION_NAME/$DOCKER_REPOSITORY_NAME:${{ github.event.inputs.version }} > /dev/null; echo $?)
+          echo $EXISTS
+          if [[ ${EXISTS} -eq 0 ]]; then
+              echo 'The specified version has been already released to DockerHub.'
+              if [[ ${{ github.event.inputs.force_release }} = true ]]; then
+                echo 'Forcing the release!'
+              else
+                echo 'Stopping the release!'
+                exit 1
+              fi
+          else
+              echo 'All good the specified version has not been release to DockerHub.'
+          fi
+
+      - name: Build & push docker images
+        run: |
+          cd release/docker
+          docker buildx build \
+          --build-arg BINARY_NAME="memgraph-" \
+          --build-arg EXTENSION="deb" \
+          --platform linux/amd64,linux/arm64 \
+          --tag $DOCKER_ORGANIZATION_NAME/$DOCKER_REPOSITORY_NAME:${{ github.event.inputs.version }} \
+          --tag $DOCKER_ORGANIZATION_NAME/$DOCKER_REPOSITORY_NAME:latest \
+          --file memgraph_deb.dockerfile \
+          --push .

.github/workflows/release_ubuntu2004.yaml

@@ -1,4 +1,4 @@
-name: Release
+name: Release Ubuntu 20.04
 
 on:
   workflow_dispatch:
@@ -8,14 +8,16 @@ on:
 jobs:
   community_build:
     name: "Community build"
-    runs-on: [self-hosted, General, Linux, X64, Debian10]
+    runs-on: [self-hosted, Linux, X64, Ubuntu20.04]
     env:
       THREADS: 24
+      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
+      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
     timeout-minutes: 960
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -24,7 +26,7 @@ jobs:
       - name: Build community binaries
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Initialize dependencies.
           ./init
@@ -34,50 +36,26 @@ jobs:
           cmake -DCMAKE_BUILD_TYPE=release -DMG_ENTERPRISE=OFF ..
           make -j$THREADS
 
-      - name: Create community DEB package
-        run: |
-          # Activate toolchain.
-          source /opt/toolchain-v2/activate
-
-          # Create community DEB package.
-          cd build
-          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-v2/activate
+          source /opt/toolchain-v4/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, General, Linux, X64, Debian10]
+    runs-on: [self-hosted, Linux, X64, Ubuntu20.04]
     env:
       THREADS: 24
+      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
+      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -86,7 +64,7 @@ jobs:
       - name: Build coverage binaries
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Initialize dependencies.
           ./init
@@ -99,7 +77,7 @@ jobs:
       - name: Run unit tests
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Run unit tests.
           cd build
@@ -108,7 +86,7 @@ jobs:
       - name: Compute code coverage
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Compute code coverage.
           cd tools/github
@@ -119,20 +97,22 @@ jobs:
           tar -czf code_coverage.tar.gz coverage.json html report.json summary.rmu
 
       - name: Save code coverage
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: "Code coverage"
           path: tools/github/generated/code_coverage.tar.gz
 
   debug_build:
     name: "Debug build"
-    runs-on: [self-hosted, General, Linux, X64, Debian10]
+    runs-on: [self-hosted, Linux, X64, Ubuntu20.04]
     env:
       THREADS: 24
+      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
+      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -141,7 +121,7 @@ jobs:
       - name: Build debug binaries
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Initialize dependencies.
           ./init
@@ -154,7 +134,7 @@ jobs:
       - name: Run leftover CTest tests
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Run leftover CTest tests (all except unit and benchmark tests).
           cd build
@@ -186,28 +166,30 @@ jobs:
       - name: Run cppcheck and clang-format
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Run cppcheck and clang-format.
           cd tools/github
           ./cppcheck_and_clang_format diff
 
       - name: Save cppcheck and clang-format errors
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: "Code coverage"
           path: tools/github/cppcheck_and_clang_format.txt
 
   release_build:
     name: "Release build"
-    runs-on: [self-hosted, General, Linux, X64, Debian10]
+    runs-on: [self-hosted, Linux, X64, Ubuntu20.04]
     env:
       THREADS: 24
+      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
+      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
     timeout-minutes: 960
 
     steps:
       - name: Set up repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           # Number of commits to fetch. `0` indicates all history for all
           # branches and tags. (default: 1)
@@ -216,7 +198,7 @@ jobs:
       - name: Build release binaries
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Initialize dependencies.
           ./init
@@ -229,15 +211,20 @@ jobs:
       - name: Create enterprise DEB package
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
+
+          cd build
+
+          # create mgconsole
+          # we use the -B to force the build
+          make -j$THREADS -B mgconsole
 
           # Create enterprise DEB package.
-          cd build
           mkdir output && cd output
           cpack -G DEB --config ../CPackConfig.cmake
 
       - name: Save enterprise DEB package
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: "Enterprise DEB package"
           path: build/output/memgraph*.deb
@@ -245,7 +232,7 @@ jobs:
       - name: Run micro benchmark tests
         run: |
           # Activate toolchain.
-          source /opt/toolchain-v2/activate
+          source /opt/toolchain-v4/activate
 
           # Run micro benchmark tests.
           cd build
@@ -274,13 +261,31 @@ jobs:
           ./continuous_integration
 
       - name: Save quality assurance status
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: "GQL Behave Status"
           path: |
             tests/gql_behave/gql_behave_status.csv
             tests/gql_behave/gql_behave_status.html
 
+      - name: Run unit tests
+        run: |
+          # Activate toolchain.
+          source /opt/toolchain-v4/activate
+
+          # Run unit tests.
+          cd build
+          ctest -R memgraph__unit --output-on-failure
+
+      - 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

.github/workflows/test_all_workers.yaml

@@ -1,116 +0,0 @@
-name: Test All Workers
-
-on: [workflow_dispatch]
-
-jobs:
-  HP-DL360G6-1:
-    name: "HP-DL360G6-1"
-    runs-on: [HP-DL360G6-1]
-    timeout-minutes: 10
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v2
-      - name: Check the system
-        run: |
-          source /opt/toolchain-v2/activate
-          ./tools/check-build-system
-  HP-DL360G6-2:
-    name: "HP-DL360G6-2"
-    runs-on: [HP-DL360G6-2]
-    timeout-minutes: 10
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v2
-      - name: Check the system
-        run: |
-          source /opt/toolchain-v2/activate
-          ./tools/check-build-system
-  HP-DL360G6-3:
-    name: "HP-DL360G6-3"
-    runs-on: [HP-DL360G6-3]
-    timeout-minutes: 10
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v2
-      - name: Check the system
-        run: |
-          source /opt/toolchain-v2/activate
-          ./tools/check-build-system
-
-  HP-DL360G6-v2-1:
-    name: "HP-DL360G6-v2-1"
-    runs-on: [HP-DL360G6-v2-1]
-    timeout-minutes: 10
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v2
-      - name: Check the system
-        run: |
-          source /opt/toolchain-v2/activate
-          ./tools/check-build-system
-  HP-DL360G6-v2-2:
-    name: "HP-DL360G6-v2-2"
-    runs-on: [HP-DL360G6-v2-2]
-    timeout-minutes: 10
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v2
-      - name: Check the system
-        run: |
-          source /opt/toolchain-v2/activate
-          ./tools/check-build-system
-  HP-DL360G6-v2-3:
-    name: "HP-DL360G6-v2-3"
-    runs-on: [HP-DL360G6-v2-3]
-    timeout-minutes: 10
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v2
-      - name: Check the system
-        run: |
-          source /opt/toolchain-v2/activate
-          ./tools/check-build-system
-  HP-DL360G6-v2-4:
-    name: "HP-DL360G6-v2-4"
-    runs-on: [HP-DL360G6-v2-4]
-    timeout-minutes: 10
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v2
-      - name: Check the system
-        run: |
-          source /opt/toolchain-v2/activate
-          ./tools/check-build-system
-  HP-DL360G6-v2-5:
-    name: "HP-DL360G6-v2-5"
-    runs-on: [HP-DL360G6-v2-5]
-    timeout-minutes: 10
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v2
-      - name: Check the system
-        run: |
-          source /opt/toolchain-v2/activate
-          ./tools/check-build-system
-  HP-DL360G6-v2-6:
-    name: "HP-DL360G6-v2-6"
-    runs-on: [HP-DL360G6-v2-6]
-    timeout-minutes: 10
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v2
-      - name: Check the system
-        run: |
-          source /opt/toolchain-v2/activate
-          ./tools/check-build-system
-  HP-DL360G6-v2-7:
-    name: "HP-DL360G6-v2-7"
-    runs-on: [HP-DL360G6-v2-7]
-    timeout-minutes: 10
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v2
-      - name: Check the system
-        run: |
-          source /opt/toolchain-v2/activate
-          ./tools/check-build-system

.gitignore

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

.pre-commit-config.yaml

@@ -0,0 +1,20 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v2.3.0
+    hooks:
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+  - repo: https://github.com/psf/black
+    rev: 22.10.0
+    hooks:
+      - id: black
+  - repo: https://github.com/pycqa/isort
+    rev: 5.10.1
+    hooks:
+      - id: isort
+        name: isort (python)
+  - repo: https://github.com/pre-commit/mirrors-clang-format
+    rev: v13.0.0
+    hooks:
+      - id: clang-format

CHANGELOG.md

@@ -1,413 +1,5 @@
-# Change Log
+Change Log for all versions of Memgraph can be found on-line at
+https://docs.memgraph.com/memgraph/changelog
 
-## v1.2.0
+All the updates to the Change Log can be made in the following repository:
-
+https://github.com/memgraph/docs
-### Breaking Changes
-
-* SSL is disabled by default (`--bolt-cert-file` and `--bolt-key-file` are
-  empty). This change might only affect the client connection configuration.
-
-### Major Features and Improvements
-
-* Added support for Bolt v4.0 and v4.1.
-* Added `mgp_networkx.py` as an alternative implementation of NetworkX graph
-  objects, which is useful to use Memgraph data from NetworkX algorithms
-  optimally.
-* Added `nxalg.py` query module as a proxy to NetworkX algorithms.
-* Added plan optimization to use a label-property index where the property is
-  not null. As a result, the query engine, instead of scanning all elements and
-  applying the filter, performs a label-property index lookup when possible.
-
-### Bug Fixes and Other Changes
-
-* Fixed Cypher `ID` function `Null` handling. When the `ID` function receives
-  `Null`, it will also return `Null`.
-* Fixed bug that caused random crashes in SSL communication on platforms
-  that use older versions of OpenSSL (< 1.1) by adding proper multi-threading
-  handling.
-* Fix `DISCARD` message handling. The query is now executed before discarding
-  the results.
-
-## 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.

CMakeLists.txt

@@ -4,7 +4,6 @@ cmake_minimum_required(VERSION 3.8)
 
 # !! IMPORTANT !! run ./project_root/init.sh before cmake command
 # to download dependencies
-
 if(NOT UNIX)
   message(FATAL_ERROR "Unsupported operating system.")
 endif()
@@ -19,6 +18,7 @@ set_directory_properties(PROPERTIES CLEAN_NO_CUSTOM TRUE)
 find_program(CCACHE_FOUND ccache)
 option(USE_CCACHE "ccache:" ON)
 message(STATUS "CCache: ${USE_CCACHE}")
+
 if(CCACHE_FOUND AND USE_CCACHE)
   set_property(GLOBAL PROPERTY RULE_LAUNCH_COMPILE ccache)
   set_property(GLOBAL PROPERTY RULE_LAUNCH_LINK ccache)
@@ -28,7 +28,8 @@ endif(CCACHE_FOUND AND USE_CCACHE)
 # NOTE: must be choosen before use of project() or enable_language()
 find_program(CLANG_FOUND clang)
 find_program(CLANGXX_FOUND clang++)
-if (CLANG_FOUND AND CLANGXX_FOUND)
+
+if(CLANG_FOUND AND CLANGXX_FOUND)
   set(CMAKE_C_COMPILER ${CLANG_FOUND})
   set(CMAKE_CXX_COMPILER ${CLANGXX_FOUND})
 else()
@@ -36,9 +37,12 @@ else()
 endif()
 
 # -----------------------------------------------------------------------------
-
 project(memgraph)
 
+# Install licenses.
+install(DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}/licenses/
+  DESTINATION share/doc/memgraph)
+
 # For more information about how to release a new version of Memgraph, see
 # `release/README.md`.
 
@@ -57,39 +61,67 @@ set(MEMGRAPH_OVERRIDE_VERSION "")
 set(MEMGRAPH_OVERRIDE_VERSION_SUFFIX "")
 
 # Variables used to generate the versions.
-if (MG_ENTERPRISE)
+if(MG_ENTERPRISE)
-  set(get_version_enterprise "--enterprise")
+  set(get_version_offering "")
 else()
-  set(get_version_enterprise "")
+  set(get_version_offering "--open-source")
 endif()
-set(get_version_script "${CMAKE_SOURCE_DIR}/release/get_version.py")
+
+set(get_version_script "${CMAKE_CURRENT_SOURCE_DIR}/release/get_version.py")
 
 # Get version that should be used in the binary.
 execute_process(
-    OUTPUT_VARIABLE MEMGRAPH_VERSION
+  OUTPUT_VARIABLE MEMGRAPH_VERSION
-    COMMAND "${get_version_script}" ${get_version_enterprise}
+  RESULT_VARIABLE MEMGRAPH_VERSION_RESULT
-                "${MEMGRAPH_OVERRIDE_VERSION}"
+  COMMAND "${get_version_script}" ${get_version_offering}
-                "${MEMGRAPH_OVERRIDE_VERSION_SUFFIX}"
+  "${MEMGRAPH_OVERRIDE_VERSION}"
+  "${MEMGRAPH_OVERRIDE_VERSION_SUFFIX}"
+  "--memgraph-root-dir"
+  "${CMAKE_CURRENT_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: ${MEMGRAPH_VERSION}")
+endif()
+
 # Get version that should be used in the DEB package.
 execute_process(
-    OUTPUT_VARIABLE MEMGRAPH_VERSION_DEB
+  OUTPUT_VARIABLE MEMGRAPH_VERSION_DEB
-    COMMAND "${get_version_script}" ${get_version_enterprise}
+  RESULT_VARIABLE MEMGRAPH_VERSION_DEB_RESULT
-                --variant deb
+  COMMAND "${get_version_script}" ${get_version_offering}
-                "${MEMGRAPH_OVERRIDE_VERSION}"
+  --variant deb
-                "${MEMGRAPH_OVERRIDE_VERSION_SUFFIX}"
+  "${MEMGRAPH_OVERRIDE_VERSION}"
+  "${MEMGRAPH_OVERRIDE_VERSION_SUFFIX}"
+  "--memgraph-root-dir"
+  "${CMAKE_CURRENT_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: ${MEMGRAPH_VERSION_DEB}")
+endif()
+
 # Get version that should be used in the RPM package.
 execute_process(
-    OUTPUT_VARIABLE MEMGRAPH_VERSION_RPM
+  OUTPUT_VARIABLE MEMGRAPH_VERSION_RPM
-    COMMAND "${get_version_script}" ${get_version_enterprise}
+  RESULT_VARIABLE MEMGRAPH_VERSION_RPM_RESULT
-                --variant rpm
+  COMMAND "${get_version_script}" ${get_version_offering}
-                "${MEMGRAPH_OVERRIDE_VERSION}"
+  --variant rpm
-                "${MEMGRAPH_OVERRIDE_VERSION_SUFFIX}"
+  "${MEMGRAPH_OVERRIDE_VERSION}"
+  "${MEMGRAPH_OVERRIDE_VERSION_SUFFIX}"
+  "--memgraph-root-dir"
+  "${CMAKE_CURRENT_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: ${MEMGRAPH_VERSION_RPM}")
+endif()
+
 # We want the above variables to be updated each time something is committed to
 # the repository. That is why we include a dependency on the current git HEAD
 # to trigger a new CMake run when the git repository state changes. This is a
@@ -107,22 +139,24 @@ execute_process(
 # unnecessary recalculations of the release version. The release version only
 # changes on every `git commit` or `git checkout`. That is why we watch the
 # following files for changes:
-#   - `.git/HEAD` -> changes each time a `git checkout` is issued
+# - `.git/HEAD` -> changes each time a `git checkout` is issued
-#   - `.git/refs/heads/...` -> the value in `.git/HEAD` is a branch name (when
+# - `.git/refs/heads/...` -> the value in `.git/HEAD` is a branch name (when
-#     you are on a branch) and you have to monitor the file of the specific
+# you are on a branch) and you have to monitor the file of the specific
-#     branch to detect when a `git commit` was issued
+# branch to detect when a `git commit` was issued
 # More details about the contents of the `.git` directory and the specific
 # files used can be seen here:
 # https://git-scm.com/book/en/v2/Git-Internals-Git-References
 set(git_directory "${CMAKE_SOURCE_DIR}/.git")
-if (EXISTS "${git_directory}")
+
+if(EXISTS "${git_directory}")
   set_property(DIRECTORY APPEND PROPERTY
-      CMAKE_CONFIGURE_DEPENDS "${git_directory}/HEAD")
+    CMAKE_CONFIGURE_DEPENDS "${git_directory}/HEAD")
   file(STRINGS "${git_directory}/HEAD" git_head_data)
-  if (git_head_data MATCHES "^ref: ")
+
+  if(git_head_data MATCHES "^ref: ")
     string(SUBSTRING "${git_head_data}" 5 -1 git_head_ref)
     set_property(DIRECTORY APPEND PROPERTY
-        CMAKE_CONFIGURE_DEPENDS "${git_directory}/${git_head_ref}")
+      CMAKE_CONFIGURE_DEPENDS "${git_directory}/${git_head_ref}")
   endif()
 endif()
 
@@ -131,16 +165,19 @@ endif()
 # setup CMake module path, defines path for include() and find_package()
 # https://cmake.org/cmake/help/latest/variable/CMAKE_MODULE_PATH.html
 set(CMAKE_MODULE_PATH ${CMAKE_MODULE_PATH} ${PROJECT_SOURCE_DIR}/cmake)
+
 # custom function definitions
 include(functions)
+
 # -----------------------------------------------------------------------------
 
 # We want out of source builds, so that cmake generated files don't get mixed
 # with source files. This allows for easier clean up.
 disallow_in_source_build()
 add_custom_target(clean_all
-                  COMMAND ${CMAKE_COMMAND} -P ${PROJECT_SOURCE_DIR}/cmake/clean_all.cmake
+  COMMAND ${CMAKE_COMMAND} -P ${PROJECT_SOURCE_DIR}/cmake/clean_all.cmake
-                  COMMENT "Removing all files in ${CMAKE_BINARY_DIR}")
+  COMMENT "Removing all files in ${CMAKE_BINARY_DIR}")
+
 # -----------------------------------------------------------------------------
 
 # build flags -----------------------------------------------------------------
@@ -151,16 +188,19 @@ set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
 
 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 \
-    -Wno-c99-designator")
+    -Wno-c99-designator \
+    -DBOOST_STACKTRACE_USE_ADDR2LINE \
+    -DBOOST_ASIO_USE_TS_EXECUTOR_AS_DEFAULT")
 
 # Don't omit frame pointer in RelWithDebInfo, for additional callchain debug.
 set(CMAKE_CXX_FLAGS_RELWITHDEBINFO
-    "${CMAKE_CXX_FLAGS_RELWITHDEBINFO} -fno-omit-frame-pointer")
+  "${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-10.2.0/libstdc++/manual/manual/license.html
@@ -176,40 +216,49 @@ set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fuse-ld=gold")
 # release flags
 set(CMAKE_CXX_FLAGS_RELEASE "-O2 -DNDEBUG")
 
-#debug flags
+SET(CMAKE_CXX_LINK_FLAGS "${CMAKE_CXX_LINK_FLAGS} -pthread")
+
+# debug flags
 set(PREFERRED_DEBUGGER "gdb" CACHE STRING
-    "Tunes the debug output for your preferred debugger (gdb or lldb).")
+  "Tunes the debug output for your preferred debugger (gdb or lldb).")
-if ("${PREFERRED_DEBUGGER}" STREQUAL "gdb" AND
+
-    "${CMAKE_CXX_COMPILER_ID}" MATCHES "Clang|GNU")
+if("${PREFERRED_DEBUGGER}" STREQUAL "gdb" AND
-    set(CMAKE_CXX_FLAGS_DEBUG "-ggdb")
+  "${CMAKE_CXX_COMPILER_ID}" MATCHES "Clang|GNU")
-elseif ("${PREFERRED_DEBUGGER}" STREQUAL "lldb" AND
+  set(CMAKE_CXX_FLAGS_DEBUG "-ggdb")
-        "${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang")
+elseif("${PREFERRED_DEBUGGER}" STREQUAL "lldb" AND
-    set(CMAKE_CXX_FLAGS_DEBUG "-glldb")
+  "${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang")
+  set(CMAKE_CXX_FLAGS_DEBUG "-glldb")
 else()
-    message(WARNING "Unable to tune for PREFERRED_DEBUGGER: "
+  message(WARNING "Unable to tune for PREFERRED_DEBUGGER: "
-            "'${PREFERRED_DEBUGGER}' with compiler: '${CMAKE_CXX_COMPILER_ID}'")
+    "'${PREFERRED_DEBUGGER}' with compiler: '${CMAKE_CXX_COMPILER_ID}'")
-    set(CMAKE_CXX_FLAGS_DEBUG "-g")
+  set(CMAKE_CXX_FLAGS_DEBUG "-g")
 endif()
 
 # -----------------------------------------------------------------------------
 
 # default build type is debug
-if (NOT CMAKE_BUILD_TYPE)
+if(NOT CMAKE_BUILD_TYPE)
-    set(CMAKE_BUILD_TYPE "Debug")
+  set(CMAKE_BUILD_TYPE "Debug")
 endif()
+
 message(STATUS "CMake build type: ${CMAKE_BUILD_TYPE}")
+
 # -----------------------------------------------------------------------------
+set(MG_ARCH "x86_64" CACHE STRING "Host architecture to build Memgraph on. Supported values are x86_64 (default), ARM64.")
 
 # setup external dependencies -------------------------------------------------
 
 # threading
 find_package(Threads REQUIRED)
+
 # optional readline
 option(USE_READLINE "Use GNU Readline library if available (default ON). \
 Set this to OFF to prevent linking with Readline even if it is available." ON)
-if (USE_READLINE)
+
+if(USE_READLINE)
   find_package(Readline)
-  if (READLINE_FOUND)
+
+  if(READLINE_FOUND)
     add_definitions(-DHAS_READLINE)
   endif()
 endif()
@@ -225,20 +274,27 @@ option(ASAN "Build with Address Sanitizer. To get a reasonable performance optio
 option(TSAN "Build with Thread Sanitizer. To get a reasonable performance option should be used only in Release or RelWithDebInfo build " OFF)
 option(UBSAN "Build with Undefined Behaviour Sanitizer" OFF)
 
-if (TEST_COVERAGE)
+if(TEST_COVERAGE)
   string(TOLOWER ${CMAKE_BUILD_TYPE} lower_build_type)
-  if (NOT lower_build_type STREQUAL "debug")
+
+  if(NOT lower_build_type STREQUAL "debug")
     message(FATAL_ERROR "Generating test coverage unsupported in non Debug builds. Current build type is '${CMAKE_BUILD_TYPE}'")
   endif()
+
   set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fprofile-instr-generate -fcoverage-mapping")
   set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fprofile-instr-generate -fcoverage-mapping")
 endif()
 
-if (MG_ENTERPRISE)
+if(MG_ENTERPRISE)
   add_definitions(-DMG_ENTERPRISE)
 endif()
 
-if (ASAN)
+set(ENABLE_JEMALLOC ON)
+
+if(ASAN)
+  message(WARNING "Disabling jemalloc as it doesn't work well with ASAN")
+  set(ENABLE_JEMALLOC OFF)
+
   # Enable Addres sanitizer and get nicer stack traces in error messages.
   # NOTE: AddressSanitizer uses llvm-symbolizer binary from the Clang
   # distribution to symbolize the stack traces (note that ideally the
@@ -247,19 +303,20 @@ if (ASAN)
   # provide it in separate ASAN_SYMBOLIZER_PATH environment variable.
   set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsanitize=address -fno-omit-frame-pointer")
   set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fsanitize=address")
+
   # To detect Stack-use-after-return bugs set run-time flag:
-  #   ASAN_OPTIONS=detect_stack_use_after_return=1
+  # ASAN_OPTIONS=detect_stack_use_after_return=1
   # To check initialization order bugs set run-time flag:
-  #   ASAN_OPTIONS=check_initialization_order=true
+  # ASAN_OPTIONS=check_initialization_order=true
-  #     This mode reports an error if initializer for a global variable accesses
+  # This mode reports an error if initializer for a global variable accesses
-  #     dynamically initialized global from another translation unit, which is
+  # dynamically initialized global from another translation unit, which is
-  #     not yet initialized
+  # not yet initialized
-  #   ASAN_OPTIONS=strict_init_order=true
+  # ASAN_OPTIONS=strict_init_order=true
-  #     This mode reports an error if initializer for a global variable accesses
+  # This mode reports an error if initializer for a global variable accesses
-  #     any dynamically initialized global from another translation unit.
+  # any dynamically initialized global from another translation unit.
 endif()
 
-if (TSAN)
+if(TSAN)
   # ThreadSanitizer generally requires all code to be compiled with -fsanitize=thread.
   # If some code (e.g. dynamic libraries) is not compiled with the flag, it can
   # lead to false positive race reports, false negative race reports and/or
@@ -272,23 +329,29 @@ if (TSAN)
   # (unwinding stack on each memory access is too expensive).
   set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsanitize=thread")
   set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fsanitize=thread")
+
   # By default ThreadSanitizer uses addr2line utility to symbolize reports.
   # llvm-symbolizer is faster, consumes less memory and produces much better
   # reports. To use it set runtime flag:
-  #   TSAN_OPTIONS="extern-symbolizer-path=~/llvm-symbolizer"
+  # TSAN_OPTIONS="extern-symbolizer-path=~/llvm-symbolizer"
   # For more runtime flags see: https://github.com/google/sanitizers/wiki/ThreadSanitizerFlags
 endif()
 
-if (UBSAN)
+if(UBSAN)
   # Compile with UBSAN but disable vptr check. This is disabled because it
   # requires linking with clang++ to make sure C++ specific parts of the
   # 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")
+set(MG_PYTHON_PATH "" CACHE STRING "Specify the exact Python path used by the query modules")
+
 # Add subprojects
 include_directories(src)
 add_subdirectory(src)
@@ -296,8 +359,13 @@ add_subdirectory(src)
 # Release configuration
 add_subdirectory(release)
 
-enable_testing()
+option(MG_ENABLE_TESTING "Set this to OFF to disable building test binaries" ON)
-add_subdirectory(tests)
+message(STATUS "MG_ENABLE_TESTING: ${MG_ENABLE_TESTING}")
+
+if(MG_ENABLE_TESTING)
+  enable_testing()
+  add_subdirectory(tests)
+endif()
 
 if(TOOLS)
   add_subdirectory(tools)
@@ -306,3 +374,7 @@ 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

@@ -1,4 +0,0 @@
-/docs/ @gitbuda
-/src/communication/ @antonio2368
-/src/query/ @the-joksim
-/src/storage/ @antonio2368

CODE_OF_CONDUCT.md

@@ -0,0 +1,127 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, caste, color, religion, or sexual
+identity and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+- Demonstrating empathy and kindness toward other people
+- Being respectful of differing opinions, viewpoints, and experiences
+- Giving and gracefully accepting constructive feedback
+- Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+- Focusing on what is best not just for us as individuals, but for the overall
+  community
+
+Examples of unacceptable behavior include:
+
+- The use of sexualized language or imagery, and sexual attention or advances of
+  any kind
+- Trolling, insulting or derogatory comments, and personal or political attacks
+- Public or private harassment
+- Publishing other's private information, such as a physical or email address,
+  without their explicit permission
+- Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+[contact@memgraph.com](contact@memgraph.com). All complaints will be reviewed
+and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series of
+actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or permanent
+ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior, harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within the
+community.
+
+## Attribution
+
+This Code of Conduct is adapted from the Contributor Covenant, version 2.1,
+available at
+[https://www.contributor-covenant.org/version/2/1/code_of_conduct.html](https://www.contributor-covenant.org/version/2/1/code_of_conduct.html).
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct
+enforcement ladder][mozilla coc].
+
+For answers to common questions about this code of conduct, see the FAQ at
+[https://www.contributor-covenant.org/faq](https://www.contributor-covenant.org/faq).
+Translations are available at
+[https://www.contributor-covenant.org/translations](https://www.contributor-covenant.org/translations).

CONTRIBUTING.md

@@ -0,0 +1,121 @@
+# How to contribute?
+
+This is a general purpose guide for contributing to Memgraph. We're still
+working out the kinks to make contributing to this project as easy and
+transparent as possible, but we're not quite there yet. Hopefully, this document
+makes the process for contributing clear and answers some questions that you may
+have.
+
+- [How to contribute?](#how-to-contribute)
+  - [Open development](#open-development)
+  - [Branch organization](#branch-organization)
+  - [Bugs & changes](#bugs--changes)
+    - [Where to find known issues?](#where-to-find-known-issues)
+    - [Proposing a change](#proposing-a-change)
+    - [Your first pull request](#your-first-pull-request)
+    - [Sending a pull request](#sending-a-pull-request)
+    - [Style guide](#style-guide)
+  - [How to get in touch?](#how-to-get-in-touch)
+  - [Code of Conduct](#code-of-conduct)
+  - [License](#license)
+  - [Attribution](#attribution)
+
+## Open development
+
+All work on Memgraph is done via [GitHub](https://github.com/memgraph/memgraph).
+Both core team members and external contributors send pull requests which go
+through the same review process.
+
+## Branch organization
+
+Most pull requests should target the [`master
+branch`](https://github.com/memgraph/memgraph/tree/master). We only use separate
+branches for developing new features and fixing bugs before they are merged with
+`master`. We do our best to keep `master` in good shape, with all tests passing.
+
+Code that lands in `master` must be compatible with the latest stable release.
+It may contain additional features but no breaking changes if it's not
+absolutely necessary. We should be able to release a new minor version from the
+tip of `master` at any time.
+
+## Bugs & changes
+
+### Where to find known issues?
+
+We are using [GitHub Issues](https://github.com/memgraph/memgraph/issues) for
+our public bugs. We keep a close eye on this and try to make it clear when we
+have an internal fix in progress. Before filing a new task, try to make sure
+your problem doesn't already exist.
+
+### Proposing a change
+
+If you intend to change the public API, or make any non-trivial changes to the
+implementation, we recommend [filing an
+issue](https://github.com/memgraph/memgraph/issues/new). This lets us reach an
+agreement on your proposal before you put significant effort into it.
+
+If you're only fixing a bug, it's fine to submit a pull request right away but
+we still recommend to file an issue detailing what you're fixing. This is
+helpful in case we don't accept that specific fix but want to keep track of the
+issue.
+
+### Your first pull request
+
+Working on your first Pull Request? You can learn how from this free video
+series:
+
+**[How to Contribute to an Open Source Project on
+GitHub](https://app.egghead.io/courses/how-to-contribute-to-an-open-source-project-on-github)**
+
+If you decide to fix an issue, please be sure to check the comment thread in
+case somebody is already working on a fix. If nobody is working on it at the
+moment, please leave a comment stating that you intend to work on it so other
+people don't accidentally duplicate your effort.
+
+If somebody claims an issue but doesn't follow up for more than two weeks, it's
+fine to take it over but you should still leave a comment.
+
+### Sending a pull request
+
+The core team is monitoring for pull requests. We will review your pull request
+and either merge it, request changes to it, or close it with an explanation.
+**Before submitting a pull request,** please make sure the following is done:
+
+1. Fork [the repository](https://github.com/memgraph/memgraph) and create your
+   branch from `master`.
+2. If you've fixed a bug or added code that should be tested, add tests!
+3. Use the formatter `clang-format` for C/C++ code and `flake8` for Python code.
+   `clang-format` will automatically detect the `.clang-format` file in the root
+   directory while `flake8` can be used with the default configuration.
+
+### Style guide
+
+Memgraph uses the [Google Style
+Guide](https://google.github.io/styleguide/cppguide.html) for C++ in most of its
+code. You should follow them whenever writing new code.
+
+## How to get in touch?
+
+Aside from communicating directly via Pull Requests and Issues, the Memgraph
+Community [Discord Server](https://discord.gg/memgraph) is the best place for
+conversing with project maintainers and other community members.
+
+## [Code of Conduct](https://github.com/memgraph/memgraph/blob/master/CODE_OF_CONDUCT.md)
+
+Memgraph has adopted the [Contributor
+Covenant](https://www.contributor-covenant.org/) as its Code of Conduct, and we
+expect project participants to adhere to it. Please read [the full
+text](https://github.com/memgraph/memgraph/blob/master/CODE_OF_CONDUCT.md) so
+that you can understand what actions will and will not be tolerated.
+
+## License
+
+By contributing to Memgraph, you agree that your contributions will be licensed
+under the [Memgraph licensing
+scheme](https://github.com/memgraph/memgraph/blob/master/LICENSE).
+
+## Attribution
+
+This Contributing guide is adapted from the **React.js Contributing guide**
+available at
+[https://reactjs.org/docs/how-to-contribute.html](https://reactjs.org/docs/how-to-contribute.html).

LICENSE

@@ -0,0 +1,5 @@
+Source code in this repository is variously licensed under the Business Source
+License 1.1 (BSL), the Memgraph Enterprise License (MEL). A copy of each licence
+can be found in the licences directory. Source code in a given file is licensed
+under the BSL and the copyright belongs to The Memgraph Authors unless
+otherwise noted at th beginning of the file.

README.md

@@ -1,47 +1,148 @@
-# Memgraph
+<p align="center">
+<img width="400px" src="https://uploads-ssl.webflow.com/5e7ceb09657a69bdab054b3a/5e7ceb09657a6937ab054bba_Black_Original%20_Logo.png">
+</p>
 
-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.
 
-## Development Documentation
+<p align="center">
+Build modern, graph-based applications on top of your streaming data in minutes.
+</p>
 
-* [Quick Start](docs/dev/quick-start.md)
+<p align="center">
-* [Workflow](docs/dev/workflow.md)
+  <a href="https://github.com/memgraph/memgraph/blob/master/licenses/APL.txt">
-* [Storage](docs/dev/storage/v2/contents.md)
+    <img src="https://img.shields.io/badge/license-APL-green" alt="license" title="license"/>
-* [Query Engine](docs/dev/query/contents.md)
+  </a>
-* [Communication](docs/dev/communication/contents.md)
+  <a href="https://github.com/memgraph/memgraph/blob/master/licenses/BSL.txt">
-* [Lisp C++ Preprocessor (LCP)](docs/dev/lcp.md)
+    <img src="https://img.shields.io/badge/license-BSL-yellowgreen" alt="license" title="license"/>
+  </a>
+  <a href="https://github.com/memgraph/memgraph/blob/master/licenses/MEL.txt" alt="Documentation">
+    <img src="https://img.shields.io/badge/license-MEL-yellow" alt="license" title="license"/>
+  </a>
+</p>
 
-## Feature Specifications
+<p align="center">
+  <a href="https://github.com/memgraph/memgraph">
+    <img src="https://img.shields.io/github/workflow/status/memgraph/memgraph/Release%20Ubuntu%2020.04/master" alt="build" title="build"/>
+  </a>
+  <a href="https://memgraph.com/docs/" alt="Documentation">
+    <img src="https://img.shields.io/badge/documentation-Memgraph-orange" />
+  </a>
+</p>
 
-Each prominent Memgraph feature requires a feature specification. The purpose
+<p align="center">
-of the feature specification is to have a base for discussing all aspects of
+  <a href="https://memgr.ph/join-discord">
-the feature. Elements of feature specifications should be:
+    <img src="https://img.shields.io/badge/Discord-7289DA?style=for-the-badge&logo=discord&logoColor=white" alt="Discord"/>
+  </a>
+</p>
 
-* High-level context.
+## :clipboard: Description
-* Interface.
-* User stories. Usage from the end-user perspective. In the case of a library,
-  that should be cases on how to use the programming interface. In the case of
-a shell script, that should be cases on how to use flags.
-* Discussion about concurrency, memory management, error management.
-* Any other essential functional or non-functional requirements.
-* Test and benchmark strategy.
-* Possible future changes/improvements/extensions.
-* Security concerns.
-* Additional and/or optional implementation details.
 
-It's crucial to keep feature spec up-to-date with the implementation. Take a
+Memgraph is a streaming graph application platform that helps you wrangle your
-look at the list of [feature specifications](docs/feature_spec/contents.md) to
+streaming data, build sophisticated models that you can query in real-time, and
-learn more about powerful Memgraph features.
+develop graph applications.
 
-## User Documentation
+Memgraph directly connects to your streaming infrastructure. You can ingest data
+from sources like Kafka, SQL, or plain CSV files. Memgraph provides a standard
+interface to query your data with Cypher, a widely-used and declarative query
+language that is easy to write, understand and optimize for performance. This is
+achieved by using the property graph data model, which stores data in terms of
+objects, their attributes, and the relationships that connect them. This is a
+natural and effective way to model many real-world problems without relying on
+complex SQL schemas.
 
-Memgraph user documentation is maintained within
+Memgraph is implemented in C/C++ and leverages an in-memory first architecture
-[docs](https://github.com/memgraph/docs) repository. The documentation is also
+to ensure that you’re getting the best possible performance consistently and
-available on [GitBook](https://docs.memgraph.com).
+without surprises. It’s also ACID-compliant and highly available.
 
-## Licences
+## :video_game: Memgraph Playground
 
-* [Community](release/LICENSE_COMMUNITY.md)
+You don't need to install anything to try out Memgraph. Check out 
-* [Enterprise](release/LICENSE_ENTERPRISE.md)
+our **[Memgraph Playground](https://playground.memgraph.com/)** sandboxes in 
+your browser.
+
+<p align="left">
+  <a href="https://playground.memgraph.com/">
+    <img width="450px" alt="Memgraph Playground" src="https://download.memgraph.com/asset/github/memgraph/memgraph-playground.png">
+  </a>
+</p>
+
+## :floppy_disk: Download & Install
+
+### Windows
+
+[![Windows](https://img.shields.io/badge/Windows-Docker-0078D6?style=for-the-badge&logo=windows&logoColor=white)](https://memgraph.com/docs/memgraph/install-memgraph-on-windows-docker)
+[![Windows](https://img.shields.io/badge/Windows-WSL-0078D6?style=for-the-badge&logo=windows&logoColor=white)](https://memgraph.com/docs/memgraph/install-memgraph-on-windows-wsl)
+
+### macOS
+
+[![macOS](https://img.shields.io/badge/macOS-Docker-000000?style=for-the-badge&logo=macos&logoColor=F0F0F0)](https://memgraph.com/docs/memgraph/install-memgraph-on-macos-docker)
+
+### Linux
+
+[![Linux](https://img.shields.io/badge/Linux-Docker-FCC624?style=for-the-badge&logo=linux&logoColor=black)](https://memgraph.com/docs/memgraph/install-memgraph-on-linux-docker)
+[![Debian](https://img.shields.io/badge/Debian-D70A53?style=for-the-badge&logo=debian&logoColor=white)](https://memgraph.com/docs/memgraph/install-memgraph-on-debian)
+[![Ubuntu](https://img.shields.io/badge/Ubuntu-E95420?style=for-the-badge&logo=ubuntu&logoColor=white)](https://memgraph.com/docs/memgraph/install-memgraph-on-ubuntu)
+[![Cent
+OS](https://img.shields.io/badge/cent%20os-002260?style=for-the-badge&logo=centos&logoColor=F0F0F0)](https://memgraph.com/docs/memgraph/install-memgraph-from-rpm)
+
+You can find the binaries and Docker images on the [Download
+Hub](https://memgraph.com/download) and the installation instructions in the
+[official documentation](https://memgraph.com/docs/memgraph/installation).
+
+## :zap: Features
+
+- Run Python, Rust, and C/C++ code natively, check out the
+  [MAGE](https://github.com/memgraph/mage) graph algorithm library
+- Native support for machine learning
+- Streaming support
+- Replication
+- Authentication and authorization
+- ACID compliance
+
+## :bookmark_tabs: Documentation
+
+The Memgraph documentation is available at
+[memgraph.com/docs](https://memgraph.com/docs).
+
+## :question: Configuration
+
+Command line options that Memgraph accepts are available in the [reference
+guide](https://memgraph.com/docs/memgraph/reference-guide/configuration).
+
+## :trophy: Contributing
+
+The main purpose of this repository is to continue evolving Memgraph, making it
+faster and easier to use. Development of Memgraph happens in the open on GitHub,
+and we are grateful to the community for contributing bug fixes and
+improvements. Read below to learn how you can take part in improving Memgraph.
+
+### Code of Conduct
+
+Memgraph has adopted a Code of Conduct that we expect project participants to
+adhere to. Please read [the full text](CODE_OF_CONDUCT.md) so that you can
+understand what actions will and will not be tolerated.
+
+### Contributing Guide
+
+Read our [contributing guide](CONTRIBUTING.md) to learn about our development
+process and how to propose bug fixes and improvements.
+
+### Internals
+
+Read our
+[internal](https://memgraph.notion.site/Memgraph-Internals-12b69132d67a417898972927d6870bd2)
+docs to learn more about Memgraph's architecture, how to build the project from
+source and how to start contributing. All information related to the database,
+can be found in the aforementioned docs.
+
+### :scroll: License
+
+Memgraph Community is available under the [BSL
+license](./licenses/BSL.txt).</br> Memgraph Enterprise is available under the
+[MEL license](./licenses/MEL.txt).
+
+<p align="center">
+  <a href="#">
+    <img src="https://img.shields.io/badge/⬆️back_to_top_⬆️-white" alt="Back to top" title="Back to top"/>
+  </a>
+</p>

cmake/FindJemalloc.cmake

@@ -0,0 +1,55 @@
+# Try to find jemalloc library
+#
+# Use this module as:
+#   find_package(Jemalloc)
+#
+# or:
+#   find_package(Jemalloc REQUIRED)
+#
+# This will define the following variables:
+#
+#   Jemalloc_FOUND           True if the system has the jemalloc library.
+#   Jemalloc_INCLUDE_DIRS    Include directories needed to use jemalloc.
+#   Jemalloc_LIBRARIES       Libraries needed to link to jemalloc.
+#
+# The following cache variables may also be set:
+#
+# Jemalloc_INCLUDE_DIR     The directory containing jemalloc/jemalloc.h.
+# Jemalloc_LIBRARY         The path to the jemalloc static library.
+
+find_path(Jemalloc_INCLUDE_DIR NAMES jemalloc/jemalloc.h PATH_SUFFIXES include)
+
+find_library(Jemalloc_LIBRARY NAMES libjemalloc.a PATH_SUFFIXES lib)
+
+include(FindPackageHandleStandardArgs)
+find_package_handle_standard_args(Jemalloc
+  FOUND_VAR Jemalloc_FOUND
+  REQUIRED_VARS
+    Jemalloc_LIBRARY
+    Jemalloc_INCLUDE_DIR
+)
+
+if(Jemalloc_FOUND)
+  set(Jemalloc_LIBRARIES ${Jemalloc_LIBRARY})
+  set(Jemalloc_INCLUDE_DIRS ${Jemalloc_INCLUDE_DIR})
+else()
+  if(Jemalloc_FIND_REQUIRED)
+    message(FATAL_ERROR "Cannot find jemalloc!")
+  else()
+    message(WARNING "jemalloc is not found!")
+  endif()
+endif()
+
+if(Jemalloc_FOUND AND NOT TARGET Jemalloc::Jemalloc)
+  add_library(Jemalloc::Jemalloc UNKNOWN IMPORTED)
+  set_target_properties(Jemalloc::Jemalloc
+    PROPERTIES
+      IMPORTED_LOCATION "${Jemalloc_LIBRARY}"
+      INTERFACE_INCLUDE_DIRECTORIES "${Jemalloc_INCLUDE_DIR}"
+  )
+endif()
+
+mark_as_advanced(
+  Jemalloc_INCLUDE_DIR
+  Jemalloc_LIBRARY
+)

config/flags.yaml

@@ -39,10 +39,22 @@ modifications:
     value: "/var/log/memgraph/memgraph.log"
     override: true
 
+  - name: "log_level"
+    value: "WARNING"
+    override: true
+
   - name: "bolt_num_workers"
     value: ""
     override: false
 
+  - name: "bolt_cert_file"
+    value: "/etc/memgraph/ssl/cert.pem"
+    override: false
+
+  - name: "bolt_key_file"
+    value: "/etc/memgraph/ssl/key.pem"
+    override: false
+
   - name: "storage_properties_on_edges"
     value: "true"
     override: true
@@ -71,23 +83,27 @@ modifications:
     value: "true"
     override: true
 
-  - name: "query_modules_directory"
+  # - name: "query_modules_directory"
-    value: "/usr/lib/memgraph/query_modules"
+  #   value: "/usr/lib/memgraph/query_modules"
+  #   override: true
+
+  - name: "memory_limit"
+    value: "0"
     override: true
 
-  - name: "auth_module_executable"
+  - name: "isolation_level"
-    value: "/usr/lib/memgraph/auth_module/example.py"
+    value: "SNAPSHOT_ISOLATION"
+    override: true
+
+  - name: "allow_load_csv"
+    value: "true"
     override: false
 
 undocumented:
   - "flag_file"
-  - "log_file_mode"
+  - "also_log_to_stderr"
-  - "log_link_basename"
-  - "log_prefix"
-  - "max_log_size"
-  - "min_log_level"
   - "help"
   - "help_xml"
-  - "stderr_threshold"
-  - "stop_logging_if_full_disk"
   - "version"
+  - "organization_name"
+  - "license_key"

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/communication/contents.md

@@ -1,5 +0,0 @@
-# Communication
-
-## Bolt
-
-Memgraph implements [Bolt communication protocol](https://7687.org/).

docs/dev/cpp-code-conventions.md

@@ -1,350 +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.
-
-Example of this can be seen while capturing member variables by reference
-inside a lambda.
-Let's define a class that has two members, where one of those members is a
-lambda that captures the other member by reference.
-
-```cpp
-struct S {
-  std::function<void()> foo;
-  int bar;
-
-  S() : foo([&]() { std::cout << bar; })
-  {}
-};
-```
-What would happend if we move an instance of this object? Our lambda
-reference capture will point to the same location as before, i.e. it
-will point to the **old** memory location of `bar`. This means we have
-a dangling reference in our code!
-There are multiple ways to avoid this. The simple solutions would be
-capturing by value or disabling move constructors/assignments.
-Still, if we capture by reference an object that is not a member
-of the struct containing the lambda, we can still have a dangling
-reference if we move that object somewhere in our code and there is
-nothing we can do to prevent that.
-So, be careful with lambda catptures, and remember that references are
-still a pointer under the hood!
-
-[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)
-
-#### Constructors and member variables
-
-One of the most powerful tools in C++ is the move semantics. We won't go into
-detail how it works, but you should know how to utilize it as much as
-possible. In our example we will define a small `struct` called `S` which
-contains only a single member, `text` of type `std::string`.
-```cpp
-struct S {
-  std::string text;
-};
-```
-We want to define a constructor that takes a `std::string`, and saves its
-value in `text`. This is a common situation, where the constructor takes
-a value, and saves it in the object to be constructed.
-
-Our first implementation would look like this:
-```cpp
-S(const std::string &s) : text(s) {}
-```
-
-This is a valid solution but with one downside - we always copy. If we
-construct an object like this:
-```cpp
-S s("some text");
-```
-we would create a temporary `std::string` object and then copy it to our member
-variable.
-
-Of course, we know what to do now - we will capture temporary variables using
-`&&` and move it into our `text` variable.
-```cpp
-S(std::string &&s) : text(std::move(s)) {}
-```
-
-Now let's add an extra member variable of type `std::vector<int>` called
-`words`.  Our constructors accept 2 values now - `std::vector<int>` and
-`std::string`. Those arguments could be passed by value, by reference, or
-as rvalues. To cover all the cases we need to define a dedicated constructor
-for each case.
-Fortunately, there are two simpler options, the first one is writing a
-templated constructor:
-```cpp
-template<typename T1, typename T2>
-S(T1 &&s, T2 &&v) : text(std::forward<T1>(s), words(std::forward<T2>(v) {}
-```
-But don't forget to define `requires` clause so you don't accept any type. This
-solution is optimal but really hard to read AND write. The second solution is
-something you should ALWAYS prefer in these simple cases where we only store
-one of the arguments:
-```cpp
-S(std::string s, std::vector<int> v) : text(std::move(s)), words(std::move(v)) {}
-```
-This way we have an almost optimal solution. The only extra operation we have is
-the extra move when we send an `lvalue`. We would copy the value to the `s`, and
-then move it to the `text` variable. Before, we would copy directly to `text`.
-Also, you should ALWAYS write const-correct code, meaning `s` and `v` cannot be
-`const` as it's not correct here. Why is that? You CANNOT move a const object!
-It would just degrade to copying the object. I would say that this is a small
-price to pay for a much cleaner and more maintainable code.
-
-### 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/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/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

@@ -1,107 +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:
-
-    apt install git
-
-After installing `git`, you are now ready to fetch your own copy of Memgraph
-source code. Run the following command:
-
-    git clone https://github.com/memgraph/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
-
-Dependencies that are required by the codebase should be checked by running the
-`init` script:
-
-    ./init
-
-If the script fails, dependencies installation scripts could be found under
-`environment/os/`. The directory contains dependencies management script for
-each supported operating system. E.g. if your system is **Debian 10**, run the
-following to install all required build packages:
-
-    ./environment/os/debian-10.sh install MEMGRAPH_BUILD_DEPS
-
-Once everything is installed, rerun the `init` script.
-
-Once the `init` script is successfully finished, issue the following commands:
-
-    mkdir -p build
-    ./libs/setup.sh
-
-### Compiling
-
-Memgraph is compiled using our own custom toolchain that can be obtained from
-the toolchain repository. You should read the `environment/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/v1/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/v1/contents.md

@@ -1,6 +0,0 @@
-# Storage v1
-
-* [Accessors](accessors.md)
-* [Indexes](indexes.md)
-* [Property Storage](property-storage.md)
-* [Durability](durability.md)

docs/dev/storage/v1/durability.md

@@ -1,80 +0,0 @@
-# Durability
-
-## 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).
-
-## 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/storage/v1/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/v1/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/storage/v2/contents.md

@@ -1,3 +0,0 @@
-# Storage v2
-
-TODO(gitbuda): Write documentation.

docs/dev/workflow.md

@@ -1,166 +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"
-
-## Github
-
-All of the code in Memgraph needs to go through code review before it can be
-accepted in the codebase. This is done through [Github](https://github.com/).
-You should already have it installed if you followed the steps in [Quick
-Start](quick-start.md).
-
-## 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. There are two branch types, **epic** and **task**
-branches. The epic branch is created when introducing a new feature or any work
-unit requiring more than one commit. More commits are required to split the
-work into chunks to be able to easier review code or find a bug (in each
-commit, there could be various problems, e.g., related to performance or
-concurrency issues, which are the hardest to track down). Each commit on the
-master or epic branch should be a compilable and well-documented set of
-changes. Task branches should be created when a smaller work unit has to be
-integrated into the codebase. The task branch could be branched out of the
-master or an epic branch. We manage epics and tasks on the project management
-tool called [Airtable](https://airtable.com/tblTUqycq8sHTTkBF). Each epic is
-prefixed by `Exyz-MG`, on the other hand, each task has `Tabcd-MG` prefix.
-Examples on how to create branches follow:
-
-```
-git checkout master
-git checkout -b T0025-MG-fix-a-problem
-...
-git checkout master
-git checkout -b E025-MG-huge-feature
-...
-git checkout E025-MG-huge-feature
-git checkout -b T0123-MG-add-feature-part
-```
-
-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.
-
-### 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 by pushing the branch to Github and creating a pull
-request. You can find all PRs
-[here](https://github.com/memgraph/memgraph/pulls).
-
-### Code Integration
-
-When working, you have to integrate some changes to your work or push your work
-to be available for others. To pull changes into a local `branch`, usually run
-the following:
-
-    git checkout {{branch}}
-    git pull origin {{branch}}
-
-To push your changes, usually run the following:
-
-    git checkout {{branch}}
-    git push origin {{branch}}
-
-Sometimes, things could get a little bit more complicated. Diagram below shows
-which git operation should be performed if a piece of code has to be integrated
-from one branch to another. Note, `main_branch` is the **master** branch in our
-case.
-
-```
-      |<---------------------------|
-      |       squash merge         |
-      |--------------------------->|
-      |          merge             |
-      |                            |
-      |<-----------|<--------------|
-      |   merge    | squash merge  |
-      |            |               |
-      |----------->|-------------->|
-      |   rebase   |     merge     |
-      |            | rebase --onto |
-      |            |               |
- main_branch  epic_branch     task_branch
-```
-
-There are a couple of cases:
-
-* If a code has to be integrated from a task branch to the main branch, use
-  **squash merge**. While you were working on a task, you probably committed a
-couple of cleanup commits that are not relevant to the main branch. In the
-other direction, while integrating the main branch to a task branch, the
-**regular merge** is ok because changes from the task branch will later be
-squash merged.
-
-* You should use **squash merge** when integrating changes from task to epic
-  branch (task might have irrelevant commits). On the other hand, you should
-use a **regular merge** when an epic is completed and has to be integrated into
-the main branch. Epic is a more significant piece of work, decoupled in
-compilable and testable commits. All these commits should be preserved to be
-able to find potential issues later on.
-
-* You should use **rebase** when integrating changes from main to an epic
-  branch. The epic branch has to be as clean as possible, avoid pure merge
-commits. Once you rebase epic on main, all commits on the epic branch will
-change the hashes. The implications are: 1) you have to force push your local
-branch to the origin, 2) if you made a task branch out of the epic branch, you
-would have to use **rebase --onto** (please refer to `git help rebase` for
-details). In simple cases, **regular merge** should be sufficient to integrate
-changes from epic to a task branch (that can even be done via GitHub web
-interface).
-
-During any code integration, 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 {{action}} --continue`.

docs/feature_spec/contents.md

@@ -1,3 +0,0 @@
-# Feature Specifications
-
-* [Python Query Modules](python-query-modules.md)

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

@@ -1,44 +0,0 @@
-# Memgraph Build and Run Environments
-
-## Toolchain Installation Procedure
-
-1) Download the toolchain for your operating system from one of the following
-   links (current active toolchain is `toolchain-v2`):
-
-* [CentOS 7](https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/toolchain-v2/toolchain-v2-binaries-centos-7.tar.gz)
-* [CentOS 8](https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/toolchain-v2/toolchain-v2-binaries-centos-8.tar.gz)
-* [Debian 9](https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/toolchain-v2/toolchain-v2-binaries-debian-9.tar.gz)
-* [Debian 10](https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/toolchain-v2/toolchain-v2-binaries-debian-10.tar.gz)
-* [Ubuntu 18.04](https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/toolchain-v2/toolchain-v2-binaries-ubuntu-18.04.tar.gz)
-* [Ubuntu 20.04](https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/toolchain-v2/toolchain-v2-binaries-ubuntu-20.04.tar.gz)
-
-2) Extract the toolchain with the following command:
-
-```bash
-tar xzvf {{toolchain-archive}}.tar.gz -C /opt
-```
-
-3) Check and install required toolchain runtime dependencies by executing
-   (e.g., on **Debian 10**):
-
-```bash
-./environment/os/debian-10.sh check TOOLCHAIN_RUN_DEPS
-./environment/os/debian-10.sh install TOOLCHAIN_RUN_DEPS
-```
-
-4) Activate the toolchain:
-
-```bash
-source /opt/toolchain-v2/activate
-```
-
-## Toolchain Upgrade Procedure
-
-1) Build a new toolchain for each supported OS (latest versions).
-2) If the new toolchain doesn't compile on some supported OS, the last
-   compilable toolchain has to be used instead. In other words, the project has
-   to compile on the oldest active toolchain as well. Suppose some
-   changes/improvements were added when migrating to the latest toolchain; in
-   that case, the maintainer has to ensure that the project still compiles on
-   previous toolchains (everything from `init` script to the actual code has to
-   work on all supported operating systems).

environment/os/centos-7.sh

@@ -5,19 +5,29 @@ set -Eeuo pipefail
 DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 source "$DIR/../util.sh"
 
+check_operating_system "centos-7"
+check_architecture "x86_64"
+
 TOOLCHAIN_BUILD_DEPS=(
     coreutils gcc gcc-c++ make # generic build tools
     wget # used for archive download
     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
+    expat-devel libipt libipt-devel libbabeltrace-devel xz-devel python3-devel # gdb
     texinfo # gdb
     libcurl-devel # cmake
+    curl # snappy
     readline-devel # cmake and llvm
     libffi-devel libxml2-devel perl-Digest-MD5 # llvm
     libedit-devel pcre-devel automake bison # swig
+    file
+    openssl-devel
+    gmp-devel
+    gperf
+    patch
 )
+
 TOOLCHAIN_RUN_DEPS=(
     make # generic build tools
     tar gzip bzip2 xz # used for archive unpacking
@@ -25,9 +35,10 @@ TOOLCHAIN_RUN_DEPS=(
     expat libipt libbabeltrace xz-libs python3 # for gdb
     readline # for cmake and llvm
     libffi libxml2 # for llvm
+    openssl-devel
 )
+
 MEMGRAPH_BUILD_DEPS=(
-    git # source code control
     make pkgconfig # build system
     curl wget # for downloading libs
     libuuid-devel java-11-openjdk # required by antlr
@@ -46,10 +57,14 @@ MEMGRAPH_BUILD_DEPS=(
     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
+    libtool  # for protobuf code generation
 )
+
 list() {
     echo "$1"
 }
+
 check() {
     local missing=""
     for pkg in $1; do
@@ -74,16 +89,13 @@ check() {
         exit 1
     fi
 }
+
 install() {
     cd "$DIR"
     if [ "$EUID" -ne 0 ]; then
         echo "Please run as root."
         exit 1
     fi
-    if [ "$SUDO_USER" == "" ]; then
-        echo "Please run as sudo."
-        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
@@ -92,8 +104,12 @@ install() {
         echo "NOTE: export LANG=en_US.utf8"
     fi
     yum install -y epel-release
+    yum remove -y ius-release
+    yum install -y \
+      https://repo.ius.io/ius-release-el7.rpm
     yum update -y
-    yum install -y wget git python3 python3-pip
+    yum install -y wget python3 python3-pip
+    yum install -y git
     for pkg in $1; do
         if [ "$pkg" == libipt ]; then
             if ! yum list installed libipt >/dev/null 2>/dev/null; then
@@ -117,11 +133,16 @@ install() {
             continue
         fi
         if [ "$pkg" == PyYAML ]; then
-            sudo -H -u "$SUDO_USER" bash -c "pip3 install --user PyYAML"
+            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-9.sh

@@ -5,36 +5,49 @@ set -Eeuo pipefail
 DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 source "$DIR/../util.sh"
 
+check_operating_system "centos-9"
+check_architecture "x86_64"
+
 TOOLCHAIN_BUILD_DEPS=(
-    coreutils gcc gcc-c++ make # generic build tools
+    coreutils-common gcc gcc-c++ make # generic build tools
     wget # used for archive download
     gnupg2 # used for archive signature verification
     tar gzip bzip2 xz unzip # used for archive unpacking
     zlib-devel # zlib library used for all builds
-    expat-devel libipt-devel libbabeltrace-devel xz-devel python36-devel texinfo # for gdb
+    expat-devel xz-devel python3-devel texinfo libbabeltrace-devel # 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
+    file
+    openssl-devel
+    gmp-devel
+    gperf
+    diffutils
+    libipt libipt-devel # intel
+    patch
 )
+
 TOOLCHAIN_RUN_DEPS=(
     make # generic build tools
     tar gzip bzip2 xz # used for archive unpacking
     zlib # zlib library used for all builds
-    expat libipt libbabeltrace xz-libs python36 # for gdb
+    expat xz-libs python3 # for gdb
     readline # for cmake and llvm
     libffi libxml2 # for llvm
+    openssl-devel
+    perl # for openssl
 )
+
 MEMGRAPH_BUILD_DEPS=(
     git # source code control
     make pkgconf-pkg-config # build system
-    curl wget # for downloading libs
+    wget # for downloading libs
     libuuid-devel java-11-openjdk # required by antlr
     readline-devel # for memgraph console
-    python36-devel # for query modules
+    python3-devel # for query modules
     openssl-devel
     libseccomp-devel
-    python36 python3-virtualenv python3-pip nmap-ncat # for qa, macro_benchmark and stress tests
+    python3 python3-pip python3-virtualenv nmap-ncat # for qa, macro_benchmark and stress tests
     #
     # IMPORTANT: python3-yaml does NOT exist on CentOS
     # Install it manually using `pip3 install PyYAML`
@@ -43,12 +56,16 @@ MEMGRAPH_BUILD_DEPS=(
     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
+    which nodejs golang zip unzip java-11-openjdk-devel # for driver tests
     sbcl # for custom Lisp C++ preprocessing
+    autoconf # for jemalloc code generation
+    libtool  # for protobuf code generation
 )
+
 list() {
     echo "$1"
 }
+
 check() {
     local missing=""
     for pkg in $1; do
@@ -58,6 +75,9 @@ check() {
             fi
             continue
         fi
+        if [ "$pkg" == "python3-virtualenv" ]; then
+            continue
+        fi
         if ! yum list installed "$pkg" >/dev/null 2>/dev/null; then
             missing="$pkg $missing"
         fi
@@ -67,16 +87,13 @@ check() {
         exit 1
     fi
 }
+
 install() {
     cd "$DIR"
     if [ "$EUID" -ne 0 ]; then
         echo "Please run as root."
         exit 1
     fi
-    if [ "$SUDO_USER" == "" ]; then
-        echo "Please run as sudo."
-        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
@@ -84,11 +101,13 @@ install() {
     else
         echo "NOTE: export LANG=en_US.utf8"
     fi
-    dnf install -y epel-release
+    yum update -y
-    dnf config-manager --set-enabled PowerTools # Required to install texinfo.
+    yum install -y wget git python3 python3-pip
-    dnf update -y
-    dnf install -y wget git python36 python3-pip
     for pkg in $1; do
+        # Since there is no support for libipt-devel for CentOS 9 we install
+        # Fedoras version of same libs, they are the same version but released
+        # for different OS
+        # TODO Update when libipt-devel releases for CentOS 9
         if [ "$pkg" == libipt ]; then
             if ! dnf list installed libipt >/dev/null 2>/dev/null; then
                 dnf install -y http://repo.okay.com.mx/centos/8/x86_64/release/libipt-1.6.1-8.el8.x86_64.rpm
@@ -96,19 +115,14 @@ install() {
             continue
         fi
         if [ "$pkg" == libipt-devel ]; then
-            if ! yum list installed libipt-devel >/dev/null 2>/dev/null; then
+            if ! dnf list installed libipt-devel >/dev/null 2>/dev/null; then
                 dnf install -y http://repo.okay.com.mx/centos/8/x86_64/release/libipt-devel-1.6.1-8.el8.x86_64.rpm
             fi
             continue
         fi
-        # Install GDB dependencies not present in the standard repos.
-        # https://bugs.centos.org/view.php?id=17068
-        # https://centos.pkgs.org
-	    # Since 2020, there is Babeltrace2 (https://babeltrace.org). Not used
-        # within GDB yet (an assumption).
         if [ "$pkg" == libbabeltrace-devel ]; then
             if ! dnf list installed libbabeltrace-devel >/dev/null 2>/dev/null; then
-                dnf install -y http://repo.okay.com.mx/centos/8/x86_64/release/libbabeltrace-devel-1.5.4-2.el8.x86_64.rpm
+                dnf install -y http://mirror.stream.centos.org/9-stream/CRB/x86_64/os/Packages/libbabeltrace-devel-1.5.8-10.el9.x86_64.rpm
             fi
             continue
         fi
@@ -124,21 +138,27 @@ install() {
             fi
             continue
         fi
-        if [ "$pkg" == dotnet-sdk-3.1 ]; then
+        if [ "$pkg" == PyYAML ]; then
-            if ! dnf list installed dotnet-sdk-3.1 >/dev/null 2>/dev/null; then
+            if [ -z ${SUDO_USER+x} ]; then # Running as root (e.g. Docker).
-                wget -nv https://packages.microsoft.com/config/centos/8/packages-microsoft-prod.rpm -O packages-microsoft-prod.rpm
+                pip3 install --user PyYAML
-                rpm -Uvh https://packages.microsoft.com/config/centos/8/packages-microsoft-prod.rpm
+            else # Running using sudo.
-                dnf update -y
+                sudo -H -u "$SUDO_USER" bash -c "pip3 install --user PyYAML"
-                dnf install -y dotnet-sdk-3.1
             fi
             continue
         fi
-        if [ "$pkg" == PyYAML ]; then
+        if [ "$pkg" == python3-virtualenv ]; then
-            sudo -H -u "$SUDO_USER" bash -c "pip3 install --user PyYAML"
+            if [ -z ${SUDO_USER+x} ]; then # Running as root (e.g. Docker).
+                pip3 install virtualenv
+                pip3 install virtualenvwrapper
+            else # Running using sudo.
+                sudo -H -u "$SUDO_USER" bash -c "pip3 install virtualenv"
+                sudo -H -u "$SUDO_USER" bash -c "pip3 install virtualenvwrapper"
+            fi
             continue
         fi
-        dnf install -y "$pkg"
+        yum install -y "$pkg"
     done
 }
+
 deps=$2"[*]"
 "$1" "${!deps}"

environment/os/debian-10.sh

@@ -5,6 +5,9 @@ set -Eeuo pipefail
 DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 source "$DIR/../util.sh"
 
+check_operating_system "debian-10"
+check_architecture "x86_64"
+
 TOOLCHAIN_BUILD_DEPS=(
     coreutils gcc g++ build-essential make # generic build tools
     wget # used for archive download
@@ -15,8 +18,15 @@ TOOLCHAIN_BUILD_DEPS=(
     libcurl4-openssl-dev # for cmake
     libreadline-dev # for cmake and llvm
     libffi-dev libxml2-dev # for llvm
+    curl # snappy
+    file # for libunwind
+    libssl-dev # for libevent
+    libgmp-dev # for gdb
+    gperf # for proxygen
+    git # for fbthrift
     libedit-dev libpcre3-dev automake bison # for swig
 )
+
 TOOLCHAIN_RUN_DEPS=(
     make # generic build tools
     tar gzip bzip2 xz-utils # used for archive unpacking
@@ -25,7 +35,9 @@ TOOLCHAIN_RUN_DEPS=(
     libcurl4 # for cmake
     libreadline7 # for cmake and llvm
     libffi6 libxml2 # for llvm
+    libssl-dev # for libevent
 )
+
 MEMGRAPH_BUILD_DEPS=(
     git # source code control
     make pkg-config # build system
@@ -43,13 +55,18 @@ MEMGRAPH_BUILD_DEPS=(
     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
+    libtool  # for protobuf code generation
 )
+
 list() {
     echo "$1"
 }
+
 check() {
     check_all_dpkg "$1"
 }
+
 install() {
     cat >/etc/apt/sources.list <<EOF
 deb http://deb.debian.org/debian/ buster main non-free contrib
@@ -60,7 +77,7 @@ deb http://security.debian.org/debian-security buster/updates main contrib non-f
 deb-src http://security.debian.org/debian-security buster/updates main contrib non-free
 EOF
     cd "$DIR"
-    apt update
+    apt --allow-releaseinfo-change 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
@@ -82,5 +99,6 @@ EOF
         apt install -y "$pkg"
     done
 }
+
 deps=$2"[*]"
 "$1" "${!deps}"

environment/os/debian-11-arm.sh

@@ -0,0 +1,98 @@
+#!/bin/bash
+
+set -Eeuo pipefail
+
+DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
+source "$DIR/../util.sh"
+
+check_operating_system "debian-11"
+check_architecture "arm64"
+
+TOOLCHAIN_BUILD_DEPS=(
+    coreutils gcc g++ build-essential make # generic build tools
+    wget # used for archive download
+    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 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
+    curl # snappy
+    file # for libunwind
+    libssl-dev # for libevent
+    libgmp-dev
+    gperf # for proxygen
+    git # for fbthrift
+)
+
+TOOLCHAIN_RUN_DEPS=(
+    make # generic build tools
+    tar gzip bzip2 xz-utils # used for archive unpacking
+    zlib1g # zlib library used for all builds
+    libexpat1 liblzma5 python3 # for gdb
+    libcurl4 # for cmake
+    file # for CPack
+    libreadline8 # for cmake and llvm
+    libffi7 libxml2 # for llvm
+    libssl-dev # for libevent
+)
+
+MEMGRAPH_BUILD_DEPS=(
+    git # source code control
+    make pkg-config # build system
+    curl wget # for downloading libs
+    uuid-dev default-jre-headless # required by antlr
+    libreadline-dev # for memgraph console
+    libpython3-dev python3-dev # for query modules
+    libssl-dev
+    libseccomp-dev
+    netcat # tests are using nc to wait for memgraph
+    python3 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
+    golang nodejs npm
+    autoconf # for jemalloc code generation
+    libtool  # for protobuf code generation
+)
+
+list() {
+    echo "$1"
+}
+
+check() {
+    check_all_dpkg "$1"
+}
+
+install() {
+    cat >/etc/apt/sources.list <<EOF
+deb http://deb.debian.org/debian bullseye main
+deb-src http://deb.debian.org/debian bullseye main
+
+deb http://deb.debian.org/debian-security/ bullseye-security main
+deb-src http://deb.debian.org/debian-security/ bullseye-security main
+
+deb http://deb.debian.org/debian bullseye-updates main
+deb-src http://deb.debian.org/debian bullseye-updates main
+EOF
+    cd "$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 $1; do
+        apt install -y "$pkg"
+    done
+}
+
+deps=$2"[*]"
+"$1" "${!deps}"

environment/os/debian-11.sh

@@ -0,0 +1,107 @@
+#!/bin/bash
+
+set -Eeuo pipefail
+
+DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
+source "$DIR/../util.sh"
+
+check_operating_system "debian-11"
+check_architecture "x86_64"
+
+TOOLCHAIN_BUILD_DEPS=(
+    coreutils gcc g++ build-essential make # generic build tools
+    wget # used for archive download
+    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
+    curl # snappy
+    file # for libunwind
+    libssl-dev # for libevent
+    libgmp-dev
+    gperf # for proxygen
+    git # for fbthrift
+)
+
+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
+    file # for CPack
+    libreadline8 # for cmake and llvm
+    libffi7 libxml2 # for llvm
+    libssl-dev # for libevent
+)
+
+MEMGRAPH_BUILD_DEPS=(
+    git # source code control
+    make pkg-config # build system
+    curl wget # for downloading libs
+    uuid-dev default-jre-headless # required by antlr
+    libreadline-dev # for memgraph console
+    libpython3-dev python3-dev # for query modules
+    libssl-dev
+    libseccomp-dev
+    netcat # tests are using nc to wait for memgraph
+    python3 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
+    libtool  # for protobuf code generation
+)
+
+list() {
+    echo "$1"
+}
+
+check() {
+    check_all_dpkg "$1"
+}
+
+install() {
+    cat >/etc/apt/sources.list <<EOF
+deb http://deb.debian.org/debian bullseye main
+deb-src http://deb.debian.org/debian bullseye main
+
+deb http://deb.debian.org/debian-security/ bullseye-security main
+deb-src http://deb.debian.org/debian-security/ bullseye-security main
+
+deb http://deb.debian.org/debian bullseye-updates main
+deb-src http://deb.debian.org/debian bullseye-updates main
+EOF
+    cd "$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

@@ -1,55 +0,0 @@
-#!/bin/bash
-
-set -Eeuo pipefail
-
-DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
-source "$DIR/../util.sh"
-
-TOOLCHAIN_BUILD_DEPS=(
-    coreutils 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
-)
-list() {
-    echo "$1"
-}
-check() {
-    check_all_dpkg "$1"
-}
-install() {
-    install_all_apt "$1"
-}
-deps=$2"[*]"
-"$1" "${!deps}"

environment/os/template.sh

@@ -5,26 +5,34 @@ set -Eeuo pipefail
 DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 source "$DIR/../util.sh"
 
+check_operating_system "todo-os-name"
+
 TOOLCHAIN_BUILD_DEPS=(
     pkg
 )
+
 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

@@ -5,6 +5,9 @@ set -Eeuo pipefail
 DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 source "$DIR/../util.sh"
 
+check_operating_system "ubuntu-18.04"
+check_architecture "x86_64"
+
 TOOLCHAIN_BUILD_DEPS=(
     coreutils gcc g++ build-essential make # generic build tools
     wget # archive download
@@ -16,8 +19,15 @@ TOOLCHAIN_BUILD_DEPS=(
     libcurl4-openssl-dev # cmake
     libreadline-dev # cmake and llvm
     libffi-dev libxml2-dev # llvm
+    curl # snappy
+    file
+    git # for thrift
+    libgmp-dev # for gdb
+    gperf # for proxygen
+    libssl-dev
     libedit-dev libpcre3-dev automake bison # swig
 )
+
 TOOLCHAIN_RUN_DEPS=(
     make # generic build tools
     tar gzip bzip2 xz-utils # used for archive unpacking
@@ -26,7 +36,9 @@ TOOLCHAIN_RUN_DEPS=(
     libcurl4 # for cmake
     libreadline7 # for cmake and llvm
     libffi6 libxml2 # for llvm
+    libssl-dev # for libevent
 )
+
 MEMGRAPH_BUILD_DEPS=(
     git # source code control
     make pkg-config # build system
@@ -42,15 +54,21 @@ MEMGRAPH_BUILD_DEPS=(
     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
+    libtool  # for protobuf 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

@@ -5,6 +5,9 @@ set -Eeuo pipefail
 DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
 source "$DIR/../util.sh"
 
+check_operating_system "ubuntu-20.04"
+check_architecture "x86_64"
+
 TOOLCHAIN_BUILD_DEPS=(
     coreutils gcc g++ build-essential make # generic build tools
     wget # used for archive download
@@ -15,8 +18,15 @@ TOOLCHAIN_BUILD_DEPS=(
     libcurl4-openssl-dev # for cmake
     libreadline-dev # for cmake and llvm
     libffi-dev libxml2-dev # for llvm
+    curl # snappy
+    file
+    git # for thrift
+    libgmp-dev # for gdb
+    gperf # for proxygen
+    libssl-dev
     libedit-dev libpcre3-dev automake bison # for swig
 )
+
 TOOLCHAIN_RUN_DEPS=(
     make # generic build tools
     tar gzip bzip2 xz-utils # used for archive unpacking
@@ -25,7 +35,9 @@ TOOLCHAIN_RUN_DEPS=(
     libcurl4 # for cmake
     libreadline8 # for cmake and llvm
     libffi7 libxml2 # for llvm
+    libssl-dev # for libevent
 )
+
 MEMGRAPH_BUILD_DEPS=(
     git # source code control
     make pkg-config # build system
@@ -43,13 +55,18 @@ MEMGRAPH_BUILD_DEPS=(
     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
+    libtool  # for protobuf code generation
 )
+
 list() {
     echo "$1"
 }
+
 check() {
     check_all_dpkg "$1"
 }
+
 install() {
     cd "$DIR"
     apt update
@@ -74,5 +91,6 @@ install() {
         apt install -y "$pkg"
     done
 }
+
 deps=$2"[*]"
 "$1" "${!deps}"

environment/os/ubuntu-22.04.sh

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

environment/toolchain/folly.patch

@@ -0,0 +1,41 @@
+diff -ur a/folly/CMakeLists.txt b/folly/CMakeLists.txt
+--- a/folly/CMakeLists.txt	2021-12-12 23:10:42.000000000 +0100
++++ b/folly/CMakeLists.txt	2022-02-03 15:19:41.349693134 +0100
+@@ -28,7 +28,6 @@
+ )
+
+ add_subdirectory(experimental/exception_tracer)
+-add_subdirectory(logging/example)
+
+ if (PYTHON_EXTENSIONS)
+   # Create tree of symbolic links in structure required for successful
+diff -ur a/folly/experimental/exception_tracer/ExceptionTracerLib.cpp b/folly/experimental/exception_tracer/ExceptionTracerLib.cpp
+--- a/folly/experimental/exception_tracer/ExceptionTracerLib.cpp	2021-12-12 23:10:42.000000000 +0100
++++ b/folly/experimental/exception_tracer/ExceptionTracerLib.cpp	2022-02-03 15:19:11.003368891 +0100
+@@ -96,6 +96,7 @@
+ #define __builtin_unreachable()
+ #endif
+
++#if 0
+ namespace __cxxabiv1 {
+
+ void __cxa_throw(
+@@ -154,5 +155,5 @@
+ }
+
+ } // namespace std
+-
++#endif
+ #endif // defined(__GLIBCXX__)
+diff -ur a/folly/Portability.h b/folly/Portability.h
+--- a/folly/Portability.h	2021-12-12 23:10:42.000000000 +0100
++++ b/folly/Portability.h	2022-02-03 15:19:11.003368891 +0100
+@@ -566,7 +566,7 @@
+ #define FOLLY_HAS_COROUTINES 0
+ #elif (__cpp_coroutines >= 201703L || __cpp_impl_coroutine >= 201902L) && \
+     (__has_include(<coroutine>) || __has_include(<experimental/coroutine>))
+-#define FOLLY_HAS_COROUTINES 1
++#define FOLLY_HAS_COROUTINES 0
+ // This is mainly to workaround bugs triggered by LTO, when stack allocated
+ // variables in await_suspend end up on a coroutine frame.
+ #define FOLLY_CORO_AWAIT_SUSPEND_NONTRIVIAL_ATTRIBUTES FOLLY_NOINLINE

environment/toolchain/proxygen.patch

@@ -0,0 +1,11 @@
+diff -ur a/cmake/proxygen-config.cmake.in b/cmake/proxygen-config.cmake.in
+--- a/cmake/proxygen-config.cmake.in	2021-12-13 02:37:05.000000000 +0100
++++ b/cmake/proxygen-config.cmake.in	2022-01-27 17:14:28.284810621 +0100
+@@ -21,7 +21,6 @@
+ find_dependency(folly)
+ find_dependency(wangle)
+ find_dependency(Fizz)
+-find_dependency(mvfst)
+ # For now, anything that depends on Proxygen has to copy its FindZstd.cmake
+ # and issue a `find_package(Zstd)`.  Uncommenting this won't work because
+ # this Zstd module exposes a library called `zstd`.  The right fix is

environment/toolchain/snappy.patch

@@ -0,0 +1,29 @@
+diff -ur a/CMakeLists.txt b/CMakeLists.txt
+--- a/CMakeLists.txt	2021-05-05 00:53:34.000000000 +0200
++++ b/CMakeLists.txt	2022-01-27 17:18:34.758302398 +0100
+@@ -52,9 +52,9 @@
+   set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /EHs-c-")
+   add_definitions(-D_HAS_EXCEPTIONS=0)
+ 
+-  # Disable RTTI.
+-  string(REGEX REPLACE "/GR" "" CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS}")
+-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /GR-")
++  # # Disable RTTI.
++  # string(REGEX REPLACE "/GR" "" CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS}")
++  # set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /GR-")
+ else(CMAKE_CXX_COMPILER_ID STREQUAL "MSVC")
+   # Use -Wall for clang and gcc.
+   if(NOT CMAKE_CXX_FLAGS MATCHES "-Wall")
+@@ -77,9 +77,9 @@
+   string(REGEX REPLACE "-fexceptions" "" CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS}")
+   set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fno-exceptions")
+ 
+-  # Disable RTTI.
+-  string(REGEX REPLACE "-frtti" "" CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS}")
+-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fno-rtti")
++  # # Disable RTTI.
++  # string(REGEX REPLACE "-frtti" "" CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS}")
++  # set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fno-rtti")
+ endif(CMAKE_CXX_COMPILER_ID STREQUAL "MSVC")
+ 
+ # BUILD_SHARED_LIBS is a standard CMake variable, but we declare it here to make

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/toolchain/xz_pgp.txt

@@ -0,0 +1,75 @@
+-----BEGIN PGP PUBLIC KEY BLOCK-----
+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+=asTC
+-----END PGP PUBLIC KEY BLOCK-----

environment/util.sh

@@ -5,6 +5,28 @@ operating_system() {
     sort | cut -d '=' -f 2- | sed 's/"//g' | paste -s -d '-'
 }
 
+check_operating_system() {
+    if [ "$(operating_system)" != "$1" ]; then
+        echo "Not the right operating system!"
+        exit 1
+    else
+        echo "The right operating system."
+    fi
+}
+
+architecture() {
+    uname -m
+}
+
+check_architecture() {
+    if [ "$(architecture)" != "$1" ]; then
+        echo "Not the right architecture!"
+        exit 1
+    else
+        echo "The right architecture."
+    fi
+}
+
 check_all_yum() {
     local missing=""
     for pkg in $1; do
@@ -43,3 +65,8 @@ check_all_dnf() {
         exit 1
     fi
 }
+install_all_apt() {
+    for pkg in $1; do
+        apt install -y "$pkg"
+    done
+}

init

@@ -10,6 +10,8 @@ function print_help () {
     echo -e "Check for missing packages and setup the project.\n"
     echo "Optional arguments:"
     echo -e "  -h\tdisplay this help and exit"
+    echo -e "  --without-libs-setup\tskip the step for setting up libs"
+    echo -e "  --wsl-quicklisp-proxy \"host:port\"\tquicklist HTTP proxy (this flag + HTTP proxy are required on WSL)"
 }
 
 function setup_virtualenv () {
@@ -22,7 +24,7 @@ function setup_virtualenv () {
     fi
 
     # create new virtualenv
-    virtualenv -p python3 ve3 || exit 1
+    python3 -m virtualenv -p python3 ve3 || exit 1
     source ve3/bin/activate
     pip --timeout 1000 install -r requirements.txt || exit 1
     deactivate
@@ -30,26 +32,47 @@ function setup_virtualenv () {
     popd > /dev/null
 }
 
-if [[ $# -gt 1 ]]; then
+wsl_quicklisp_proxy=""
+setup_libs=true
+if [[ $# -eq 1 && "$1" == "-h" ]]; then
     print_help
-    exit 1
+    exit 0
-elif  [[ $# -eq 1 ]]; then
+else
-    case "$1" in
+    while(($#)); do
-      -h)
+        case "$1" in
-          print_help
+          --wsl-quicklisp-proxy)
-          exit 0
+              shift
-      ;;
+              if [[ $# -eq 0 ]]; then
-      *)
+                  echo "Missing proxy URL"
-          # unknown option
+                  print_help
-          print_help
+                  exit 1
-          exit 1
+              fi
-      ;;
+              wsl_quicklisp_proxy=":proxy \"http://$1/\""
-  esac
+              shift
+          ;;
+          --without-libs-setup)
+              shift
+              setup_libs=false
+          ;;
+          *)
+              # unknown option
+              echo "Invalid argument provided: $1"
+              print_help
+              exit 1
+          ;;
+        esac
+    done
 fi
 
 DISTRO=$(operating_system)
-echo "ALL BUILD PACKAGES: $($DIR/environment/os/$DISTRO.sh list MEMGRAPH_BUILD_DEPS)"
+ARCHITECTURE=$(architecture)
-$DIR/environment/os/$DISTRO.sh check MEMGRAPH_BUILD_DEPS
+if [ "${ARCHITECTURE}" = "arm64" ] || [ "${ARCHITECTURE}" = "aarch64" ]; then
+  OS_SCRIPT=$DIR/environment/os/$DISTRO-arm.sh
+else
+  OS_SCRIPT=$DIR/environment/os/$DISTRO.sh
+fi
+echo "ALL BUILD PACKAGES: $($OS_SCRIPT list MEMGRAPH_BUILD_DEPS)"
+$OS_SCRIPT check MEMGRAPH_BUILD_DEPS
 echo "All packages are in-place..."
 
 # create a default build directory
@@ -66,7 +89,7 @@ if [[ ! -f "${quicklisp_install_dir}/setup.lisp" ]]; then
   echo \
   "
   (load \"${DIR}/quicklisp.lisp\")
-  (quicklisp-quickstart:install :path \"${quicklisp_install_dir}\")
+  (quicklisp-quickstart:install $wsl_quicklisp_proxy :path \"${quicklisp_install_dir}\")
   " | sbcl --script || exit 1
   rm -rf quicklisp.lisp || exit 1
 fi
@@ -80,11 +103,13 @@ echo \
   (ql:quickload '(:lcp :lcp/test) :silent t)
   " | sbcl --script
 
-# setup libs (download)
+if [[ "$setup_libs" == "true" ]]; then
-cd libs
+    # Setup libs (download).
-./cleanup.sh
+    cd libs
-./setup.sh
+    ./cleanup.sh
-cd ..
+    ./setup.sh
+    cd ..
+fi
 
 # setup gql_behave dependencies
 setup_virtualenv tests/gql_behave
@@ -95,6 +120,14 @@ 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"
@@ -102,3 +135,17 @@ 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;
+
+# Install precommit hook
+python3 -m pip install pre-commit
+python3 -m pre_commit install
+
+# Install py format tools
+echo "Install black formatter"
+python3 -m pip install black==22.10.*
+echo "Install isort"
+python3 -m pip install isort==5.10.*
+
+
+# Link `include/mgp.py` with `release/mgp/mgp.py`
+ln -v -f include/mgp.py release/mgp/mgp.py

libs/.gitignore

@@ -4,3 +4,5 @@
 !cleanup.sh
 !CMakeLists.txt
 !__main.cpp
+!pulsar.patch
+!antlr4.10.1.patch

libs/CMakeLists.txt

@@ -1,11 +1,24 @@
 include(ExternalProject)
 
+include(GNUInstallDirs)
+
 include(ProcessorCount)
 ProcessorCount(NPROC)
 if (NPROC EQUAL 0)
   set(NPROC 1)
 endif()
 
+find_package(Boost 1.78 REQUIRED)
+find_package(BZip2 1.0.6 REQUIRED)
+find_package(Threads REQUIRED)
+set(GFLAGS_NOTHREADS OFF)
+find_package(gflags REQUIRED)
+find_package(fmt 8.0.1)
+find_package(Jemalloc REQUIRED)
+find_package(ZLIB 1.2.11 REQUIRED)
+
+set(LIB_DIR ${CMAKE_CURRENT_SOURCE_DIR})
+
 # convenience functions
 function(import_header_library name include_dir)
   add_library(${name} INTERFACE IMPORTED GLOBAL)
@@ -44,7 +57,7 @@ endfunction(import_library)
 # INSTALL_COMMAND arguments.
 function(add_external_project name)
   set(options NO_C_COMPILER)
-  set(one_value_kwargs SOURCE_DIR)
+  set(one_value_kwargs SOURCE_DIR BUILD_IN_SOURCE)
   set(multi_value_kwargs CMAKE_ARGS DEPENDS INSTALL_COMMAND BUILD_COMMAND
       CONFIGURE_COMMAND)
   cmake_parse_arguments(KW "${options}" "${one_value_kwargs}" "${multi_value_kwargs}" ${ARGN})
@@ -52,11 +65,16 @@ function(add_external_project name)
   if (KW_SOURCE_DIR)
     set(source_dir ${KW_SOURCE_DIR})
   endif()
+  set(build_in_source 0)
+  if (KW_BUILD_IN_SOURCE)
+    set(build_in_source ${KW_BUILD_IN_SOURCE})
+  endif()
   if (NOT KW_NO_C_COMPILER)
     set(KW_CMAKE_ARGS -DCMAKE_C_COMPILER=${CMAKE_C_COMPILER} ${KW_CMAKE_ARGS})
   endif()
   ExternalProject_Add(${name}-proj DEPENDS ${KW_DEPENDS}
                       PREFIX ${source_dir} SOURCE_DIR ${source_dir}
+                      BUILD_IN_SOURCE ${build_in_source}
                       CONFIGURE_COMMAND ${KW_CONFIGURE_COMMAND}
                       CMAKE_ARGS -DCMAKE_BUILD_TYPE=Release
                                  -DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}
@@ -87,25 +105,19 @@ 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
+             -DANTLR_BUILD_CPP_TESTS=OFF
   BUILD_COMMAND $(MAKE) antlr4_static
-  # Make a License.txt out of thin air, so that antlr4.6 knows how to build.
+  INSTALL_COMMAND $(MAKE) install)
-  # 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)
 
 # Setup google benchmark.
 import_external_library(benchmark STATIC
-  ${CMAKE_CURRENT_SOURCE_DIR}/benchmark/lib/libbenchmark.a
+  ${CMAKE_CURRENT_SOURCE_DIR}/benchmark/${CMAKE_INSTALL_LIBDIR}/libbenchmark.a
   ${CMAKE_CURRENT_SOURCE_DIR}/benchmark/include
   # Skip testing. The tests don't compile with Clang 8.
   CMAKE_ARGS -DBENCHMARK_ENABLE_TESTING=OFF)
 
-# setup fmt format
+include(FetchContent)
-import_external_library(fmt STATIC
-  ${CMAKE_CURRENT_SOURCE_DIR}/fmt/lib/libfmt.a
-  ${CMAKE_CURRENT_SOURCE_DIR}/fmt/include
-  # Skip testing.
-  CMAKE_ARGS -DFMT_TEST=OFF)
 
 # setup rapidcheck (it cannot be external, since it doesn't have install
 # target)
@@ -132,73 +144,19 @@ import_library(gtest_main STATIC ${GTEST_MAIN_LIBRARY} ${GTEST_INCLUDE_DIR} gtes
 import_library(gmock STATIC ${GMOCK_LIBRARY} ${GTEST_INCLUDE_DIR} gtest-proj)
 import_library(gmock_main STATIC ${GMOCK_MAIN_LIBRARY} ${GTEST_INCLUDE_DIR} gtest-proj)
 
-# setup google flags
-set(GFLAGS_NO_FILENAMES "0")
-if ("${CMAKE_BUILD_TYPE}" MATCHES "^(R|r)(E|e)(L|l).+")
-  set(GFLAGS_NO_FILENAMES "1")
-endif()
-
-# setup google flags
-import_external_library(gflags STATIC
-  ${CMAKE_CURRENT_SOURCE_DIR}/gflags/lib/libgflags.a
-  ${CMAKE_CURRENT_SOURCE_DIR}/gflags/include
-  # Not needed, since gflags is C++ only.
-  NO_C_COMPILER
-  # Don't register installation in ~/.cmake
-  CMAKE_ARGS -DREGISTER_INSTALL_PREFIX=OFF
-             -DBUILD_gflags_nothreads_LIB=OFF
-             -DGFLAGS_NO_FILENAMES=${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})
 
 # Setup json
 import_header_library(json ${CMAKE_CURRENT_SOURCE_DIR})
 
-# Setup bzip2
-import_external_library(bzip2 STATIC
-    ${CMAKE_CURRENT_SOURCE_DIR}/bzip2/libbz2.a
-    ${CMAKE_CURRENT_SOURCE_DIR}/bzip2
-    # bzip2's Makefile has -g CFLAG which is redundant
-    CONFIGURE_COMMAND sed -i "s/-Wall -Winline -O2 -g/-Wall -Winline -O2/g" ${CMAKE_CURRENT_SOURCE_DIR}/bzip2/Makefile
-    BUILD_COMMAND make -C ${CMAKE_CURRENT_SOURCE_DIR}/bzip2
-                       CC=${CMAKE_C_COMPILER}
-                       CXX=${CMAKE_CXX_COMPILER}
-    INSTALL_COMMAND true)
-
-# Setup zlib
-import_external_library(zlib STATIC
-    ${CMAKE_CURRENT_SOURCE_DIR}/zlib/lib/libz.a
-    ${CMAKE_CURRENT_SOURCE_DIR}/zlib
-    CMAKE_ARGS -DCMAKE_SKIP_INSTALL_ALL_DEPENDENCY=true
-    BUILD_COMMAND $(MAKE) zlibstatic)
-
 # Setup RocksDB
 import_external_library(rocksdb STATIC
   ${CMAKE_CURRENT_SOURCE_DIR}/rocksdb/lib/librocksdb.a
   ${CMAKE_CURRENT_SOURCE_DIR}/rocksdb/include
-  DEPENDS gflags-proj
+  CMAKE_ARGS -DUSE_RTTI=ON
-  CMAKE_ARGS -Dgflags_DIR=${CMAKE_CURRENT_SOURCE_DIR}/gflags/lib/cmake/gflags
-             -DUSE_RTTI=ON
              -DWITH_TESTS=OFF
+             -DGFLAGS_NOTHREADS=OFF
              -DCMAKE_INSTALL_LIBDIR=lib
              -DCMAKE_SKIP_INSTALL_ALL_DEPENDENCY=true
   BUILD_COMMAND $(MAKE) rocksdb)
@@ -219,6 +177,82 @@ import_external_library(mgclient STATIC
   ${CMAKE_CURRENT_SOURCE_DIR}/mgclient/include
   CMAKE_ARGS -DCMAKE_C_COMPILER=${CMAKE_C_COMPILER}
              -DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}
-             -DBUILD_TESTING=OFF)
+             -DBUILD_TESTING=OFF
+             -DBUILD_CPP_BINDINGS=ON)
 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
+set(SPDLOG_FMT_EXTERNAL ON)
+FetchContent_Declare(spdlog
+  SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/spdlog)
+
+FetchContent_MakeAvailable(spdlog)
+
+# 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
+             -DWITH_ZSTD=OFF
+             -DENABLE_LZ4_EXT=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::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)
+
+set(PROTOBUF_ROOT ${CMAKE_CURRENT_SOURCE_DIR}/protobuf/lib)
+import_external_library(protobuf STATIC
+  ${PROTOBUF_ROOT}/lib/libprotobuf.a
+  ${PROTOBUF_ROOT}/include
+  BUILD_IN_SOURCE 1
+  CONFIGURE_COMMAND true)
+
+import_external_library(pulsar STATIC
+  ${CMAKE_CURRENT_SOURCE_DIR}/pulsar/pulsar-client-cpp/lib/libpulsarwithdeps.a
+  ${CMAKE_CURRENT_SOURCE_DIR}/pulsar/install/include
+  BUILD_IN_SOURCE 1
+  CONFIGURE_COMMAND cmake pulsar-client-cpp
+                            -DCMAKE_INSTALL_PREFIX=${CMAKE_CURRENT_SOURCE_DIR}/pulsar/install
+                            -DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}
+                            -DCMAKE_C_COMPILER=${CMAKE_C_COMPILER}
+                            -DBUILD_DYNAMIC_LIB=OFF
+                            -DBUILD_STATIC_LIB=ON
+                            -DBUILD_TESTS=OFF
+                            -DLINK_STATIC=ON
+                            -DPROTOC_PATH=${PROTOBUF_ROOT}/bin/protoc
+                            -DBOOST_ROOT=${BOOST_ROOT}
+                            -DCMAKE_PREFIX_PATH=${PROTOBUF_ROOT}
+                            -DProtobuf_INCLUDE_DIRS=${PROTOBUF_ROOT}/include
+                            -DBUILD_PYTHON_WRAPPER=OFF
+                            -DBUILD_PERF_TOOLS=OFF
+                            -DUSE_LOG4CXX=OFF
+ BUILD_COMMAND $(MAKE) pulsarStaticWithDeps)
+add_dependencies(pulsar-proj protobuf)
+
+if (${MG_ARCH} STREQUAL "ARM64")
+  set(MG_LIBRDTSC_CMAKE_ARGS -DLIBRDTSC_ARCH_x86=OFF -DLIBRDTSC_ARCH_ARM64=ON)
+endif()
+
+import_external_library(librdtsc STATIC
+  ${CMAKE_CURRENT_SOURCE_DIR}/librdtsc/lib/librdtsc.a
+  ${CMAKE_CURRENT_SOURCE_DIR}/librdtsc/include
+  CMAKE_ARGS ${MG_LIBRDTSC_CMAKE_ARGS}
+  BUILD_COMMAND $(MAKE) rdtsc)

libs/antlr4.10.1.patch

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

libs/librdtsc.patch

@@ -0,0 +1,29 @@
+diff --git a/CMakeLists.txt b/CMakeLists.txt
+index ee9b58c..31359a9 100644
+--- a/CMakeLists.txt
++++ b/CMakeLists.txt
+@@ -48,7 +48,7 @@ option(LIBRDTSC_USE_PMU     "Enables PMU usage on ARM platforms"        OFF)
+ # |          Library Build and Install Properties          |
+ # +--------------------------------------------------------+
+ 
+-add_library(rdtsc SHARED
++add_library(rdtsc
+     src/cycles.c
+     src/common_timer.c
+     src/timer.c
+@@ -72,15 +72,6 @@ target_include_directories(rdtsc
+   PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/include
+ )
+ 
+-# Install directory changes depending on build mode
+-if (CMAKE_BUILD_TYPE MATCHES "^[Dd]ebug")
+-    # During debug, the library will be installed into a local directory
+-    set(CMAKE_INSTALL_PREFIX ${CMAKE_CURRENT_BINARY_DIR}/_install CACHE PATH "" FORCE)
+-else ()
+-    # This will install in /usr/lib and /usr/include
+-    set(CMAKE_INSTALL_PREFIX /usr CACHE PATH "" FORCE)
+-endif ()
+-
+ # Specifying what to export when installing (GNUInstallDirs required)
+ install(TARGETS rdtsc
+         EXPORT librstsc-config

libs/rocksdb.patch

@@ -0,0 +1,21 @@
+diff --git a/CMakeLists.txt b/CMakeLists.txt
+index 6761929..6a369af 100644
+--- a/CMakeLists.txt
++++ b/CMakeLists.txt
+@@ -220,6 +220,7 @@ else()
+       set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -momit-leaf-frame-pointer")
+     endif()
+   endif()
++  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-deprecated-copy -Wno-unused-but-set-variable")
+ endif()
+ 
+ include(CheckCCompilerFlag)
+@@ -997,7 +998,7 @@ if(NOT WIN32 OR ROCKSDB_INSTALL_ON_WINDOWS)
+ 
+   if(ROCKSDB_BUILD_SHARED)
+     install(
+-      TARGETS ${ROCKSDB_SHARED_LIB}
++      TARGETS ${ROCKSDB_SHARED_LIB} OPTIONAL
+       EXPORT RocksDBTargets
+       COMPONENT runtime
+       ARCHIVE DESTINATION "${CMAKE_INSTALL_LIBDIR}"

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.
@@ -12,30 +14,49 @@ clone () {
   local git_repo=$1
   local dir_name=$2
   local checkout_id=$3
-  shift 3
+  local shallow=$4
+  shift 4
   # Clone if there's no repo.
   if [[ ! -d "$dir_name" ]]; then
-    git clone "$git_repo" "$dir_name"
+    echo "Cloning from $git_repo"
+    # If the clone fails, it doesn't make sense to continue with the function
+    # execution but the whole script should continue executing because we might
+    # clone the same repo from a different source.
+
+    if [ "$shallow" = true ]; then
+      git clone --depth 1 --branch "$checkout_id" "$git_repo" "$dir_name" || return 1
+    else
+      git clone "$git_repo" "$dir_name" || return 1
+    fi
   fi
   pushd "$dir_name"
-  # Just fetch new commits from remote repository. Don't merge/pull them in, so
-  # that we don't clobber local modifications.
-  git fetch
   # Check whether we have any local changes which need to be preserved.
   local local_changes=true
   if git diff --no-ext-diff --quiet && git diff --no-ext-diff --cached --quiet; then
     local_changes=false
   fi
-  # Stash regardless of local_changes, so that a user gets a message on stdout.
+
-  git stash
+  if [ "$shallow" = false ]; then
-  # Checkout the primary commit (there's no need to pull/merge).
+    # Stash regardless of local_changes, so that a user gets a message on stdout.
-  git checkout $checkout_id
+    git stash
-  # Apply any optional cherry pick fixes.
+    # Just fetch new commits from remote repository. Don't merge/pull them in, so
-  while [[ $# -ne 0 ]]; do
+    # that we don't clobber local modifications.
-    local cherry_pick_id=$1
+    git fetch
-    shift
+    # Checkout the primary commit (there's no need to pull/merge).
-    git cherry-pick -n $cherry_pick_id
+    # The checkout fail should exit this script immediately because the target
-  done
+    # commit is not there and that will most likely create build-time errors.
+    git checkout "$checkout_id" || exit 1
+    # Apply any optional cherry pick fixes.
+    while [[ $# -ne 0 ]]; do
+      local cherry_pick_id=$1
+      shift
+      # The cherry-pick fail should exit this script immediately because the
+      # target commit is not there and that will most likely create build-time
+      # errors.
+      git cherry-pick -n "$cherry_pick_id" || exit 1
+    done
+  fi
+
   # Reapply any local changes.
   if [[ $local_changes == true ]]; then
     git stash pop
@@ -43,80 +64,177 @@ 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="$4"
+    shallow="${5:-false}"
+    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" "$shallow" || clone "$secondary_url" "$folder_name" "$ref" "$shallow" || exit 1
+    echo ""
+}
+
+# List all dependencies.
+
+# The reason for introducing primary and secondary urls are:
+#   * HTTPS is hard to cache
+#   * Remote development workflow is more flexible if people don't have to connect to VPN
+#   * Direct download from the "source of truth" is slower and unreliable because of the whole internet in-between
+#   * When a new dependency has to be added, both urls could be the same, later someone could optimize if required
+
+# The goal of having primary urls is to have links to the "local" cache of
+# dependencies where these dependencies could be downloaded as fast as
+# possible. The actual cache server could be on your local machine, on a
+# dedicated machine inside the build cluster or on the actual build machine.
+# Download from primary_urls might fail because the cache is not installed.
+declare -A primary_urls=(
+  ["antlr4-code"]="http://$local_cache_host/git/antlr4.git"
+  ["antlr4-generator"]="http://$local_cache_host/file/antlr-4.10.1-complete.jar"
+  ["cppitertools"]="http://$local_cache_host/git/cppitertools.git"
+  ["rapidcheck"]="http://$local_cache_host/git/rapidcheck.git"
+  ["gbenchmark"]="http://$local_cache_host/git/benchmark.git"
+  ["gtest"]="http://$local_cache_host/git/googletest.git"
+  ["libbcrypt"]="http://$local_cache_host/git/libbcrypt.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://$local_cache_host/git/spdlog"
+  ["nlohmann"]="http://$local_cache_host/file/nlohmann/json/9d69186291aca4f0137b69c1dee313b391ff564c/single_include/nlohmann/json.hpp"
+  ["neo4j"]="http://$local_cache_host/file/neo4j-community-3.2.3-unix.tar.gz"
+  ["librdkafka"]="http://$local_cache_host/git/librdkafka.git"
+  ["protobuf"]="http://$local_cache_host/git/protobuf.git"
+  ["pulsar"]="http://$local_cache_host/git/pulsar.git"
+  ["librdtsc"]="http://$local_cache_host/git/librdtsc.git"
+)
+
+# The goal of secondary urls is to have links to the "source of truth" of
+# dependencies, e.g., Github or S3. Download from secondary urls, if happens
+# at all, should never fail. In other words, if it fails, the whole build
+# should fail.
+declare -A secondary_urls=(
+  ["antlr4-code"]="https://github.com/antlr/antlr4.git"
+  ["antlr4-generator"]="https://www.antlr.org/download/antlr-4.10.1-complete.jar"
+  ["cppitertools"]="https://github.com/ryanhaining/cppitertools.git"
+  ["rapidcheck"]="https://github.com/emil-e/rapidcheck.git"
+  ["gbenchmark"]="https://github.com/google/benchmark.git"
+  ["gtest"]="https://github.com/google/googletest.git"
+  ["libbcrypt"]="https://github.com/rg3/libbcrypt"
+  ["rocksdb"]="https://github.com/facebook/rocksdb.git"
+  ["mgclient"]="https://github.com/memgraph/mgclient.git"
+  ["pymgclient"]="https://github.com/memgraph/pymgclient.git"
+  ["mgconsole"]="http://github.com/memgraph/mgconsole.git"
+  ["spdlog"]="https://github.com/gabime/spdlog"
+  ["nlohmann"]="https://raw.githubusercontent.com/nlohmann/json/9d69186291aca4f0137b69c1dee313b391ff564c/single_include/nlohmann/json.hpp"
+  ["neo4j"]="https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/neo4j-community-3.2.3-unix.tar.gz"
+  ["librdkafka"]="https://github.com/edenhill/librdkafka.git"
+  ["protobuf"]="https://github.com/protocolbuffers/protobuf.git"
+  ["pulsar"]="https://github.com/apache/pulsar.git"
+  ["librdtsc"]="https://github.com/gabrieleara/librdtsc.git"
+)
+
 # antlr
-antlr_generator_filename="antlr-4.6-complete.jar"
+file_get_try_double "${primary_urls[antlr4-generator]}" "${secondary_urls[antlr4-generator]}"
-# wget -O ${antlr_generator_filename} http://www.antlr.org/download/${antlr_generator_filename}
+
-wget -nv -O ${antlr_generator_filename} https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/${antlr_generator_filename}
+antlr4_tag="4.10.1" # v4.10.1
-antlr4_tag="aacd2a2c95816d8dc1c05814051d631bfec4cf3e" # v4.6
+repo_clone_try_double "${primary_urls[antlr4-code]}" "${secondary_urls[antlr4-code]}" "antlr4" "$antlr4_tag" true
-clone https://github.com/antlr/antlr4.git antlr4 $antlr4_tag
+pushd antlr4
-# fix missing include
+git apply ../antlr4.10.1.patch
-sed -i 's/^#pragma once/#pragma once\n#include <functional>/' antlr4/runtime/Cpp/runtime/src/support/CPPUtils.h
+popd
-# remove shared library from install dependencies
-sed -i 's/install(TARGETS antlr4_shared/install(TARGETS antlr4_shared OPTIONAL/' antlr4/runtime/Cpp/runtime/CMakeLists.txt
 
 # cppitertools v2.0 2019-12-23
 cppitertools_ref="cb3635456bdb531121b82b4d2e3afc7ae1f56d47"
-clone https://github.com/ryanhaining/cppitertools.git cppitertools $cppitertools_ref
+repo_clone_try_double "${primary_urls[cppitertools]}" "${secondary_urls[cppitertools]}" "cppitertools" "$cppitertools_ref"
-
-# fmt
-fmt_tag="7fa8f8fa48b0903deab5bb42e6760477173ac485" # v3.0.1
-# Commit which fixes an issue when compiling with C++14 and higher.
-fmt_cxx14_fix="b9aaa507fc49680d037fd84c043f747a395bce04"
-clone https://github.com/fmtlib/fmt.git fmt $fmt_tag $fmt_cxx14_fix
 
 # rapidcheck
 rapidcheck_tag="7bc7d302191a4f3d0bf005692677126136e02f60" # (2020-05-04)
-clone https://github.com/emil-e/rapidcheck.git rapidcheck $rapidcheck_tag
+repo_clone_try_double "${primary_urls[rapidcheck]}" "${secondary_urls[rapidcheck]}" "rapidcheck" "$rapidcheck_tag"
 
 # google benchmark
-benchmark_tag="4f8bfeae470950ef005327973f15b0044eceaceb" # v1.1.0
+benchmark_tag="v1.6.0"
-clone https://github.com/google/benchmark.git benchmark $benchmark_tag
+repo_clone_try_double "${primary_urls[gbenchmark]}" "${secondary_urls[gbenchmark]}" "benchmark" "$benchmark_tag" true
 
 # google test
-googletest_tag="ec44c6c1675c25b9827aacd08c02433cccde7780" # v1.8.0
+googletest_tag="release-1.8.0"
-clone https://github.com/google/googletest.git googletest $googletest_tag
+repo_clone_try_double "${primary_urls[gtest]}" "${secondary_urls[gtest]}" "googletest" "$googletest_tag" true
-
-# google logging
-glog_tag="042a21657e79784226babab8b942f7bd0949635f" # custom version (v0.3.5+)
-clone https://github.com/memgraph/glog.git glog $glog_tag
-
-# google flags
-gflags_tag="b37ceb03a0e56c9f15ce80409438a555f8a67b7c" # custom version (May 6, 2017)
-clone https://github.com/memgraph/gflags.git gflags $gflags_tag
 
 # libbcrypt
 libbcrypt_tag="8aa32ad94ebe06b76853b0767c910c9fbf7ccef4" # custom version (Dec 16, 2016)
-clone https://github.com/rg3/libbcrypt libbcrypt $libbcrypt_tag
+repo_clone_try_double "${primary_urls[libbcrypt]}" "${secondary_urls[libbcrypt]}" "libbcrypt" "$libbcrypt_tag"
 
 # neo4j
-wget -nv https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/neo4j-community-3.2.3-unix.tar.gz -O neo4j.tar.gz
+file_get_try_double "${primary_urls[neo4j]}" "${secondary_urls[neo4j]}"
-tar -xzf neo4j.tar.gz
+tar -xzf neo4j-community-3.2.3-unix.tar.gz
-rm -rf neo4j
 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/b3e5cb7f20dcc5c806e418df34324eca60d17d4e/single_include/nlohmann/json.hpp"
+file_get_try_double "${primary_urls[nlohmann]}" "${secondary_urls[nlohmann]}"
 cd ..
 
-bzip2_tag="0405487e2b1de738e7f1c8afb50d19cf44e8d580"  # v1.0.6 (May 26, 2011)
+rocksdb_tag="v6.14.6" # (2020-10-14)
-clone https://github.com/VFR-maniac/bzip2 bzip2 $bzip2_tag
+repo_clone_try_double "${primary_urls[rocksdb]}" "${secondary_urls[rocksdb]}" "rocksdb" "$rocksdb_tag" true
-
+pushd rocksdb
-zlib_tag="cacf7f1d4e3d44d871b605da3b647f07d718623f" # v1.2.11.
+git apply ../rocksdb.patch
-clone https://github.com/madler/zlib.git zlib $zlib_tag
+popd
-# remove shared library from install dependencies
-sed -i 's/install(TARGETS zlib zlibstatic/install(TARGETS zlibstatic/g' zlib/CMakeLists.txt
-
-rocksdb_tag="f3e33549c151f30ac4eb7c22356c6d0331f37652" # (2020-10-14)
-clone https://github.com/facebook/rocksdb.git 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
+mgclient_tag="v1.4.0" # (2022-06-14)
-clone https://github.com/memgraph/mgclient.git mgclient $mgclient_tag
+repo_clone_try_double "${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" "$pymgclient_tag"
+
+# mgconsole
+mgconsole_tag="v1.1.0" # (2021-10-07)
+repo_clone_try_double "${primary_urls[mgconsole]}" "${secondary_urls[mgconsole]}" "mgconsole" "$mgconsole_tag" true
+
+spdlog_tag="v1.9.2" # (2021-08-12)
+repo_clone_try_double "${primary_urls[spdlog]}" "${secondary_urls[spdlog]}" "spdlog" "$spdlog_tag" true
+
+# librdkafka
+librdkafka_tag="v1.7.0" # (2021-05-06)
+repo_clone_try_double "${primary_urls[librdkafka]}" "${secondary_urls[librdkafka]}" "librdkafka" "$librdkafka_tag" true
+
+# protobuf
+protobuf_tag="v3.12.4"
+repo_clone_try_double "${primary_urls[protobuf]}" "${secondary_urls[protobuf]}" "protobuf" "$protobuf_tag" true
+pushd protobuf
+./autogen.sh && ./configure CC=clang CXX=clang++ --prefix=$(pwd)/lib
+popd
+
+#pulsar
+pulsar_tag="v2.8.1"
+repo_clone_try_double "${primary_urls[pulsar]}" "${secondary_urls[pulsar]}" "pulsar" "$pulsar_tag" true
+pushd pulsar
+git apply ../pulsar.patch
+popd
+
+#librdtsc
+librdtsc_tag="v0.3"
+repo_clone_try_double "${primary_urls[librdtsc]}" "${secondary_urls[librdtsc]}" "librdtsc" "$librdtsc_tag" true
+pushd librdtsc
+git apply ../librdtsc.patch
+popd

licenses/APL.txt

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

licenses/BSL.txt

@@ -0,0 +1,84 @@
+MEMGRAPH
+BUSINESS SOURCE LICENSE (BSL) 1.1
+
+PARAMETERS
+
+LICENSOR:               MEMGRAPH LTD
+LICENSED WORK:          MEMGRAPH COMMUNITY EDITION (MCE) version 2.0
+ADDITIONAL USE GRANT:   You may use the Licensed Work in accordance with the
+                        terms of this License solely for any Authorised Purpose,
+                        provided that you may not use the Licensed Work for any
+                        Excluded Purpose.
+
+                        “Authorised Purpose” means any of the following,
+                        provided always that (a) you do not embed or otherwise
+                        distribute the Licensed Work to third parties; and (b)
+                        you do not provide third parties direct access to
+                        operate or control the Licensed Work as a standalone
+                        solution or service:
+                        1. for your internal business purposes;
+                        2. to integrate the Licensed Work with your own
+                        proprietary software, provided that your proprietary
+                        software adds a primary and significant functionality
+                        to the Licensed Work (the “Integrated Solution”);
+                        and/or
+                        3. to host the Integrated Solution and make it available
+                        to third parties on a ‘software-as-a-service’ or an
+                        equivalent distributed model.
+                        “Excluded Purpose” means any of the following:
+                        1. making the Licensed Work accessible to any third
+                        party outside of your organization as a standalone
+                        solution or service;
+                        2. hosting and making the Licensed Work available to
+                        third parties on a ‘database-as-a-service’ or any
+                        equivalent distributed model as a standalone solution or
+                        service; and/or
+                        3. using the Licensed Work to create a work or solution
+                        which competes (or might reasonably be expected to
+                        compete) with the Licensed Work.
+CHANGE DATE:            2026-27-04
+CHANGE LICENSE:         Apache License, Version 2.0
+
+For information about alternative licensing arrangements, please visit: https://memgraph.com/legal.
+The Business Source License (this document, or the “License”) is not an
+‘open source’ license. However, the Licensed Work will eventually be made
+available under an ‘open source’ license, as stated in this License.
+
+TERMS
+The Licensor hereby grants you the right to copy, modify, create derivative works, redistribute, and make non-production
+use of the Licensed Work. The Licensor may make an Additional Use Grant, above, permitting limited production use.
+Effective on the Change Date, or the fourth anniversary of the first publicly available distribution of a specific
+version of the Licensed Work under this License, whichever comes first, the Licensor hereby grants you rights under the
+terms of the Change License, and the rights granted in the paragraph above terminate. If your use of the Licensed Work
+does not comply with the requirements currently in effect as described in thisLicense, you must purchase a commercial
+license from the Licensor, its affiliated entities, or authorized resellers, or you must refrain from using the Licensed
+Work. All copies of the original and modified Licensed Work, and derivative works of the Licensed Work, are subject to
+this License. This License applies separately for each version of the Licensed Work and the Change Date may vary for
+each version of the Licensed Work released by Licensor. You must conspicuously display this License on each original or
+modified copy of the Licensed Work. If you receive the Licensed Work in original or modified form from a third party,
+the terms and conditions set forth in this License apply to your use of that work.Any use of the Licensed Work in
+violation of this License will automatically terminate your rights under this License for the current and all other
+versions of the Licensed Work. This License does not grant you any right in any trademark or logo of Licensor or its
+affiliates (provided that you may use a trademark or logo of Licensor as expressly required by this License).
+TO THE EXTENT PERMITTED BY APPLICABLE LAW, THE LICENSED WORK IS PROVIDED ON AN “AS IS” BASIS. LICENSOR HEREBY DISCLAIMS
+ALL WARRANTIES AND CONDITIONS, EXPRESS OR IMPLIED, INCLUDING (WITHOUT LIMITATION) WARRANTIES OF MERCHANTABILITY, FITNESS
+FOR A PARTICULAR PURPOSE, NON-INFRINGEMENT, AND TITLE.
+MariaDB hereby grants you permission to use this License’s text to license your works, and to refer to it using the
+trademark ‘Business Source License’, as long as you comply with the Covenants of Licensor below.
+Covenants of Licensor
+In consideration of the right to use this License’s text and the ‘Business Source License’ name and trademark, Licensor
+covenants to MariaDB, and to all other recipients of the Licensed Work to be provided by Licensor:
+1.  To specify as the Change License the GPL Version 2.0 or any later version, or a license that is compatible with GPL
+    Version 2.0 or a later version, where “compatible” means that software provided under the Change License can be
+    included in a program with software provided under GPL Version 2.0 or a later version. Licensor may specify
+    additional Change Licenses without limitation.
+
+2.  To either: (a) specify an additional grant of rights to use that does not impose any additional restriction on the
+    right granted in this License, as the Additional Use Grant; or (b) insert the text “None”.
+
+3. To specify a Change Date.
+
+4. Not to modify this License in any other way.
+
+NOTICE
+License text copyright (c) 2017 MariaDB Corporation Ab, All Rights Reserved. ‘Business Source License’ is a trademark of MariaDB Corporation Ab.

licenses/MEL.txt

@@ -0,0 +1,464 @@
+MEMGRAPH
+ENTERPRISE LICENCE AGREEMENT
+
+
+Memgraph Limited is registered in England under registration 10195084 and has its registered office at Suite 4,
+Ironstone House, Ironstone Way, Brixworth, Northampton, NN6 9UD (“Memgraph”).
+
+
+Memgraph agrees to license and/or grant you (the “Customer”) access to the Software ( as defined below) and provide
+support and services to you only if you accept and agree to be bound by the terms and conditions in this Memgraph
+Enterprise Licence Agreement (the “Agreement”). By signing an Order Document (as defined below), which is subject to and
+part of this Agreement, installing and using the Software or by downloading a trial version of the Software, you agree
+to be bound by the terms of this Agreement.
+
+
+Memgraph Enterprise Trial Users: If you receive free of charge trial access to the Software, you are deemed a
+“Customer” for purposes of this Agreement, except that you are subject to the additional restrictions and limitations
+set forth in Section 3.2 below in respect of your use of such Software.
+
+
+1. DEFINITIONS.
+   1.1.  “Applicable Laws” means (i) all applicable laws, statutes and regulations, and (ii) regulatory policies,
+         guidelines and industry codes (in each case having the force of law), which apply to the provisions of the
+         Software and Services and this Agreement.
+   1.2.  “Confidential Information” means all information disclosed by a party (“Disclosing Party”) to the other party
+         (“Receiving Party”), whether orally or in writing, that is designated as confidential or that reasonably should
+         be understood to be confidential given the nature of the information and the circumstances of disclosure.
+         Customer’s Confidential Information includes Customer Data; Memgraph Confidential Information includes the
+         Software and Services; and Confidential Information of each party includes the terms and conditions of this
+         Agreement and all Orders (including pricing), as well as business and marketing plans, technology and technical
+         information, product plans and designs, and business processes disclosed by such party. However, Confidential
+         Information does not include any information that (i) is or becomes generally known to the public without
+         breach of any obligation owed to the Disclosing Party, (ii) was known to the Receiving Party prior to its
+         disclosure by the Disclosing Party without breach of any obligation owed to the Disclosing Party, (iii) is
+         received from a third party without breach of any obligation owed to the Disclosing Party, or (iv) was
+         independently developed by the Receiving Party.
+   1.3.  “Customer Data” means business information or other data loaded by or for Customer and/or processed by the
+         Software.
+   1.4.  “Data Protection Legislation” means all applicable data protection and privacy legislation in force from time
+         to time in the UK including the General Data Protection Regulation ((EU) 2016/679) as it forms part of UK law
+         by virtue of section 3 of the European Union (Withdrawal) Act 2018; the Data
+         Protection Act 2018; the Privacy and Electronic Communications Directive 2002/58/EC (as updated by Directive
+         2009/136/EC); and the Privacy and Electronic Communications Regulations 2003 (SI 2003/2426), in each case as
+         amended.
+   1.5.  “Derivate Work” means any modification or enhancement made by Customer to the Software, whether in source code,
+         binary executable, intermediate or other form.
+   1.6.  “Effective Date” means the date on which you execute this Agreement.
+   1.7.  “Order Document” or “Order” means, as applicable: (i) in the case of a Trial Licence, the Memgraph trial
+         registration form available on Memgraph’s website; or (ii) in any other case, an order form that is submitted
+         by or on behalf of Customer and executed by or on behalf of the parties referencing
+         this Agreement and that specifies the Software and/or Services ordered by Customer, as well as the specific
+         terms and conditions, for that particular transaction.
+   1.8.  “Services” means those services, including Support Services, which may be provided to Customer by Memgraph
+         pursuant to the terms of this Agreement and are expressly limited to those services directly related to
+         Customer’s use of the Software, and expressly exclude any other services.
+   1.9. “Software” means Memgraph’s proprietary downloadable graph database enterprise software known as Memgraph
+         Enterprise Edition (MEE) (“Enterprise Software”) and the associated technical documentation located at
+         https://docs.memgraph.com/ (“Documentation”), as well as software updates, upgrades, bug fixes, or modified
+         versions thereof that Memgraph licenses or provides to Customer directly or indirectly throughout the Subscription
+         Term. For the avoidance of doubt, for the purpose of this Agreement, the term Software excludes Memgraph’s
+         free-to-use software known as Memgraph Community Edition (MCE) which is licensed pursuant to separate terms
+         (including the Business Source Licence (BSL) or Apache 2.0) as indicated here: https://memgraph.com/legal.
+   1.10. “Subscription Term” means the fixed term, of not less than one (1) year, designated in an Order Document
+         beginning on the Effective Date and ending at the end of the period stated therein. If no expiration date is
+         specified in an Order Document, the Subscription Term shall be a one (1) year period (“Minimum Subscription
+         Term”). A “Subscription” is the binding, non-cancellable contract for the use of the Software for the
+         Subscription Term as set forth in an Order Document.
+   1.11. “Support” means the support and maintenance services, including any updates, upgrades, patches, enhancements
+         and bug fixes for the Software that may be provided to Customer by Memgraph pursuant to the terms of this
+         Agreement.
+   1.12. “Users” means employees and Contractors of Customer that Customer has permitted or authorized to access and use
+         of the Software on Customer’s behalf pursuant to the terms of this Agreement.
+
+2. ORDERS, DELIVERY; SUPPORT.
+   2.1.  Delivery. Customer shall access the Software from Memgraph’s website or online repository (as instructed by
+         Memgraph) after the Effective Date. Memgraph shall deliver to Customer the licence key necessary to unlock the
+         Software after Customer accepts an Order. Unless otherwise stated in an Order, Customer is solely responsible
+         for installing Software on Customer’s own computer equipment. In some instances, Customer’s purchasing
+         relationship exists solely between Customer and an authorised reseller of Memgraph’s Software and Services
+         (a “Reseller”), in which case Sections 5.1-5.3 (Fees and Payment) will be inapplicable to such Order(s), and
+         the Reseller shall be responsible for submitting Orders and the appropriate payment method therewith to
+         Memgraph. An Order is not binding until Memgraph accepts and countersigns the Order.
+   2.2.  Support. Memgraph will use commercially reasonable efforts to provide Support to Customer in accordance with
+         Memgraph’s then-current terms and conditions set forth at
+         https://download.memgraph.com/legal/memgraph-support-terms-and-conditions.pdf at the support tier stated in the
+         applicable Order. The Support terms and conditions are subject to change at Memgraph’s discretion; however,
+         Memgraph will not materially reduce the level of Support during a Subscription Term for which Fees have been
+         paid.
+
+3. LICENCE GRANTS; RESTRICTIONS AND PROPRIETARY RIGHTS.
+Customer’s licence and access rights and benefits, and Memgraph’s obligations to Customer, will vary depending on the
+product and the type of licence Memgraph is granting. If you purchased a licence to Memgraph Software, your licence will
+be subject to certain use and/or capacity restrictions, as identified on the applicable Order Document.
+   3.1.  Enterprise Software Licence. In consideration of the Fees paid hereunder and subject to the terms of this
+         Agreement and the applicable Order, Memgraph grants Customer a world-wide, non-exclusive, non-transferable,
+         non-sublicensable, and limited licence during the applicable Subscription Term, to download, access, install
+         and use the Enterprise Software up to the maximum capacity (“Licensed Capacity”), and subject to the usage
+         rules, specified in the applicable Order Document, and to use Documentation solely for Customer’s internal
+         business purposes in connection with the operation of the Enterprise Software.
+   3.2.  Enterprise Trial Licence. If the Customer downloads, accesses, installs or uses the Software under a trial
+         licence (“Trial Licence”), then Customer may use one (1) copy of the Software in accordance with the terms and
+         conditions of this Agreement for a thirty (30) day period, or such longer trial period represented by the
+         applicable licence key issued by or expressly authorised by Memgraph (the “Trial Period”). Trial Licences are
+         permitted solely for Customer’s evaluation use to determine whether to purchase a Subscription to the Software.
+         Customer may not use a Trial Licence for any other purpose. At the end of the Trial Period, the Trial Licence
+         will expire and this Agreement will terminate as to such Trial Licence and continue to apply to any subsequent
+         Subscription or use of the Software. If Customer decides not to obtain a Subscription upon expiration of the
+         Trial Period, it will promptly cease using and will delete the Software from its computer systems. Memgraph has
+         the right to terminate a Trial Licence at any time for any reason.
+   3.3.  Limited right to modify the Software. In consideration of the Fees paid hereunder and subject to the terms of
+         this Agreement and the applicable Order, Memgraph grants Customer a licence to: (i) create, compile and test
+         Derivative Works; (ii) use Derivative Works solely for Customer’s internal business purposes; and (iii)
+         distribute Derivative Works back to Memgraph for potential incorporation into Memgraph’s maintained code base
+         at its sole discretion.
+   3.4.  NO OBLIGATIONS. NOTWITHSTANDING ANYTHING TO THE CONTRARY IN THIS AGREEMENT OR IN ANY ORDER DOCUMENT, MEMGRAPH
+         WILL HAVE NO WARRANTY, INDEMNITY, SUPPORT, OR SERVICE LEVEL, OBLIGATIONS WITH RESPECT TO ANY ENTERPRISE TRIAL,
+         OR OTHER NO-CHARGE SOFTWARE (INCLUDING TOOLS AND UTILITIES) LICENCES.
+   3.5.  General Restrictions. Customer acknowledges that the Software, and its structure, organization, and source code,
+         constitute Memgraph’s and its suppliers’ valuable trade secrets, and that usage of the Software is subject to
+         the following restrictions:
+      3.5.1.   Restrictions. Customer agrees not to, and not to authorize any third party to: (i) allow access or use
+               of the Software by anyone other than its Users; (ii) distribute, embed, sell, rent, transfer, lease,
+               lend, sublicense, loan, assign, pledge, grant a security interest in, or otherwise make the Software
+               accessible or available to any third party; except to the limited extent expressly provided in Section
+               3.5.2, use the Software in any service-bureau, timesharing, outsourcing or similar arrangement; (iii)
+               subject only to the limited rights set out in Section 3.3, modify, adapt, transform, derive, disassemble,
+               decompile, reverse engineer or otherwise attempt to derive the structure, sequence or organization of,
+               the Software or any portion thereof; (iv) remove or alter product identification, copyright, trademark or
+               other proprietary markings contained in or on the Software; (v) conduct any competitive analysis, publish
+               or share with any third party any results of any technical evaluation or tests performed on the Software,
+               or disclose Software features, errors or bugs to a third party without Memgraph’s prior written consent;
+               or (vi) engage in any act designed to circumvent any restriction set forth in this Agreement, in the
+               Software, or in an Order, including but not limited to restrictions related to Licensed Capacity.
+      3.5.2.   Internal Use Licences; Users. The Software is licensed for Customer’s internal business use and not for
+               distribution or use by third parties. For clarity, however, Customer may make available to third parties
+               any Customer-hosted services or other Customer applications or services that make use of or incorporate
+               the Software, provided and solely to the extent that (i) Customer’s application or hosted service adds
+               primary and significant functionality to the Software, (ii) Customer does not embed or otherwise
+               distribute the Software to third parties (iii) Customer does not provide third parties direct access to
+               operate or control the Software itself; and (iv) Customer at all times remains in compliance with the
+               terms of the applicable licence grants under this Agreement. Subject to the terms and conditions of this
+               Agreement, in addition to Customer’s employees, Customer may permit its independent contractors and
+               consultants (“Contractors”) to serve as Users. Customer will remain responsible for compliance by each of
+               its Users (including but not limited to any Contractor Users) with all of the terms and conditions of
+               this Agreement, and any use of the Software by any Contractors must be for the sole benefit of Customer.
+   3.6.  Ownership; Reservation of Rights. This is an agreement for use of Memgraph Software and not an agreement for
+         sale. Customer acknowledges that it is obtaining only a limited right to use the Software on a licensed basis,
+         and that irrespective of any use of the words “purchase”, “sale” or like terms hereunder no ownership rights
+         are being conveyed to Customer. Customer agrees that Memgraph or its suppliers retain all right, title and
+         interest (including all patent, copyright, trade secret and other intellectual property rights) in and to the
+         Memgraph Software. Nothing in this Section shall be deemed as granting Memgraph ownership of Customer Data or
+         in any way impacting Customer’s ownership of Customer Data.
+   3.7.  Third Party Code. The Software may contain or be provided with components which are licensed from third
+         parties, including components subject to the terms and conditions of “open source” software licences
+         (“Open Source Software”). Open Source Software may be identified in the Software, Documentation, or in a list
+         of the Open Source Software provided to you upon your written request. To the extent required by the licence
+         that accompanies the Open Source Software, the terms of such licence will apply in lieu of the terms of this
+         Agreement with respect to such Open Source Software, including, without limitation, any provisions governing
+         access to source code, modification, or reverse engineering.
+   3.8.  IP Ownership. The Parties agree that, save as otherwise provided in this Agreement, neither party shall gain, by
+         virtue of this Agreement, any rights of ownership or any other interest, right or title of copyrights, patents,
+         trade secrets, trademarks, or any other intellectual property rights owned by the other Party. Any and all new
+         works developed in the course of performing obligations pursuant to this Agreement and all new inventions,
+         innovations or ideas developed by a Party in the course of performance of its activities under this Agreement,
+         will belong to that Party who develops the same. Notwithstanding anything to the contrary in this Section, the
+         Parties understand and agree that any and all proprietary materials developed by a Party prior to this
+         Agreement and any modifications, enhancements, improvements or inventions made to such proprietary materials
+         shall be owned by that Party, regardless of which Party prepared or developed such modifications, enhancements,
+         improvements or inventions.
+   3.9.  License-back of Derivate Works. If Customer elects, at its sole discretion, to distribute  Derivative Works
+         back to Memgraph for potential incorporation into Memgraph’s maintained code base, Customer grants Memgraph
+         (without any restrictions, limitations or requirement of remuneration) a worldwide, non-exclusive, fully
+         paid-up, royalty-free, perpetual, irrevocable, transferable and sublicensable licence to use, exploit, modify,
+         make derivative works of, commercialise, distribute and otherwise exploit such Derivative Works.
+
+
+4. CUSTOMER DATA; OBLIGATIONS OF CUSTOMER AND MEMGRAPH.
+   4.1.  Customer shall retain all of its rights, title, and interest in and to its intellectual property rights in
+         Customer Data. Customer grants to Memgraph a non-exclusive, worldwide, limited-term licence solely to host,
+         copy, transmit and display Customer Data as reasonably necessary for Memgraph to support Customer’s use of the
+         Software, to ensure the security of and to administrate the Software, and to deliver Services in accordance
+         with this Agreement or as otherwise outlined in https://memgraph.com/legal/privacy-policy/.
+   4.2.  Protection of Customer Data. Memgraph will maintain appropriate administrative, physical, and technical
+         safeguards, consistent with generally prevailing industry standards, for protection of the security,
+         confidentiality, and integrity of Customer Data, as described in the Documentation. Those safeguards will
+         include, but will not be limited to, measures for preventing access, use, modification, or disclosure of
+         Customer Data by Memgraph personnel, except as permitted by this Agreement.
+   4.3.  Personal data. Both parties will comply with all applicable requirements of the Data Protection Legislation.
+         This section 4.3 is in addition to, and does not relieve, remove or replace, a party’s obligations under the
+         Data Protection Legislation. Notwithstanding the foregoing, the parties acknowledge that, in the ordinary
+         course of providing the Services, Memgraph shall not process personal data (as defined in the Data Protection
+         Legislation) on behalf of the Customer. In the event that the Customer requires Memgraph to process personal
+         data on its behalf, it shall notify Memgraph and the parties shall execute such additional terms as necessary
+         to comply with applicable Data Protection Legislation.
+
+5. FEES AND PAYMENT.
+   5.1.  Fees. Customer will pay Memgraph the fees for the Licences and Services as set forth in the applicable Order (
+         “Fees”). Customer acknowledges and agrees that if Customer’s use of the Software exceeds the Licensed Capacity
+         set forth on the applicable Orders or otherwise requires the payment of additional fees (per the terms of this
+         Agreement), Customer shall be invoiced for such usage and Customer agrees to pay the additional fees in
+         accordance with this Section. Notwithstanding the terms of Section 5.4 below (Reconciliation), Customer
+         acknowledges and agrees that it is obligated to ensure that its Software usage does not exceed the Licensed Capacity
+         and to promptly notify Memgraph of any such excess usage no more than thirty (30) days from the last day of the
+         calendar month during which such excess usage occurred.
+   5.2.  Payment Terms. Except as otherwise specifically set forth on an Order Document, all fees are due and payable
+         within thirty days after the date of invoice. Renewal Fees for any renewal Subscription Term (if purchased by
+         Customer) will be due and payable within thirty (30) days of expiration of the then-current term. If Fees are
+         not paid when due, or in the event of other breach of this Agreement, Customer shall discontinue use of the
+         Software and Memgraph may suspend its performance, including its delivery of technical support of the Software
+         or other Services without further notice and without penalty. All Orders (including multi-year Subscriptions
+         with annual payment schedules) are non-cancellable and all amounts paid are non-refundable, unless otherwise
+         expressly set forth herein. Any invoiced amount not received by the due date will accrue late interest at the
+         rate of 1.5% of the outstanding balance per month, or the maximum rate permitted by applicable law, whichever
+         is lower.
+   5.3.  Taxes. Fees are exclusive of taxes. Customer will pay any sales, use, value added, duties, fees and other
+         governmental assessments or charges arising out of this Agreement and the transactions contemplated herein.
+         Customer will make all payments free and clear of, and without reduction for, any withholding taxes.
+   5.4.  Reconciliation. At Memgraph’s request from time to time, not exceeding once per quarter, Customer will provide
+         Memgraph with a report detailing its use of the Software, including its non-production and/or production use
+         and using the self-monitoring capabilities of the Software or other means, and Memgraph may inspect Customer’s
+         records related to such report not more frequently than annually to ensure payment of Fees. Any on-site review
+         will be conducted during regular business hours at Customer’s offices. The parties will use reasonable efforts
+         to promptly resolve any discrepancies between licensed usage and actual usage.
+
+6. APPLICABLE LAWS.
+   6.1.  Each Party shall perform this Agreement in accordance with all Applicable Laws. Without prejudice to the
+         foregoing, each Party shall:
+      6.1.1.   comply with all Applicable Laws relating to anti-bribery, anti-corruption, anti-slavery and human
+               trafficking, including the Bribery Act 2010 and the Modern Slavery Act 2015
+               (the “Relevant Requirements”);
+      6.1.2.   have and maintain in place throughout the Term its own policies and procedures, including adequate
+               procedures under the Bribery Act 2010, to ensure compliance with the Relevant Requirements, and will
+               enforce them where appropriate;
+      6.1.3.   (if not prohibited by law or regulation from doing so) promptly report to the other Party any request or
+               demand for any undue financial or other advantage of any kind received by the reporting Party in
+               connection with the performance of this Agreement; and
+      6.1.4.   (if not prohibited by law or regulation from doing so) notify the other Party (and email shall be
+               sufficient for this purpose) as soon as it becomes aware of any actual or suspected slavery or human
+               trafficking in a supply chain which has a connection with this Agreement.
+
+7. REPRESENTATIONS AND WARRANTIES.
+   7.1.  Mutual Representations and Warranties. Each Party represents and warrants to the other that: (i) it is a
+         corporation lawfully incorporated and validly existing pursuant to the laws of its place of incorporation;
+         (ii) it has all requisite power and authority, corporate or otherwise, to execute, deliver and perform its
+         obligations under this Agreement; and (iii) this Agreement constitutes its legal, valid and binding obligations
+         and may be enforced against it.
+   7.2. Limited Memgraph Warranty. Memgraph warrants that the Software, when used as permitted hereunder and in
+         accordance with the applicable Documentation, will operate in all material respects as described in the
+         applicable Documentation, and that the Services will be provided in a professional manner consistent with
+         industry standards.
+   7.3.  Limitations; Remedy. Memgraph does not warrant that the Software or the Services will be error-free,
+         uninterrupted or meet Customer’s specific requirements or that performance of the Services will be
+         uninterrupted. Memgraph will have no warranty obligation under Section 7.2 for Customer’s misuse or failure to
+         use the Software in accordance with its Documentation or this Agreement. Customer’s sole and exclusive remedy,
+         and Memgraph’s sole and exclusive obligation, for breach of warranty will be (i) during the thirty (30) day
+         period following initial Delivery of the Software under an Order, Memgraph’s correction of the program errors
+         that cause the breach of warranty, or if Memgraph cannot substantially correct such breach in a commercially
+         reasonable manner, a refund of the fees paid for the nonconforming Software (ii) during the remainder of the
+         relevant Subscription Term, Memgraph’s delivery of Support with respect to any such program errors. In the
+         event of a refund remedy, Customer’s licences and right to use the Software or receive Services will end. In
+         the event of any noticed breach of warranty with respect to Services, Memgraph’s sole and exclusive obligation
+         shall be the re-performance of the deficient Services.
+   7.4.  Disclaimer. THIS SECTION 7 IS A LIMITED WARRANTY AND, EXCEPT EXPRESSLY AS SET FORTH IN SECTION 7.2,
+         THE SOFTWARE, INCLUDING WITHOUT LIMITATION THE THIRD-PARTY CODE, AND ALL SERVICES ARE PROVIDED “AS IS”.
+         MEMGRAPH MAKES NO OTHER WARRANTIES OR REPRESENTATIONS, EXPRESS, IMPLIED, STATUTORY OR OTHERWISE, AND DISCLAIMS
+         ALL IMPLIED WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, TITLE, AND NON-INFRINGEMENT.
+
+8. INDEMNIFICATION.
+   8.1.  By Memgraph. Memgraph will defend against any action against Customer brought by a third party to the extent the
+         action is based on a claim that the Software infringes a third party’s patent, copyright or trademark
+         (a “Claim”) and indemnify Customer from the damages, liabilities, costs and expenses (including reasonable
+         attorneys’ fees) awarded against Customer or agreed in settlement by Customer resulting from such Claim. If
+         your use of the Software is (or in Memgraph’s opinion likely to be) enjoined, then Memgraph may, at its own
+         expense and at its option: (i) substitute substantially similar functionality for the Software which renders
+         it non-infringing; (ii) procure for Customer the right to continue to use the Software; or if (i) and (ii) are
+         not commercially reasonable, terminate this Agreement and refund Customer any prepaid, unused (pro-rated) Fees
+         for the duration of the then-current Subscription Term. The foregoing obligations of Memgraph will not apply:
+         (i) if the Software is modified by any party other than Memgraph, but solely to the extent the alleged
+         infringement is caused by such modification; (ii) if the Software is used in combination with other products or
+         processes not provided or authorized by Memgraph, but solely to the extent the alleged infringement is caused
+         by such combination; (iii) use of any version or release of Software other than the most current version or
+         release made available to Customer by Memgraph, if its use would have avoided the infringement; (iv) any
+         unauthorized use of the Software. THIS SECTION 8.1 SETS FORTH MEMGRAPH’S SOLE LIABILITY AND CUSTOMER’S SOLE
+         AND EXCLUSIVE REMEDY WITH RESPECT TO ANY CLAIM OF INTELLECTUAL PROPERTY INFRINGEMENT.
+   8.2.  By Customer. Customer will indemnify and hold Memgraph and its suppliers harmless against any claims,
+         liabilities, costs, and expenses (including reasonable attorneys’ fees) that Memgraph or its suppliers may
+         incur as a result of a third-party claim arising from or related to Customer Data, or misuse or unauthorised
+         use of the Software by Customer or any User.
+   8.3.  Conditions. All defence and indemnity obligations under Sections 8.1 and 8.2 are conditioned on the indemnitee
+         (i) giving the indemnitor written notice of the relevant claim within thirty (30) days after the indemnitee
+         receives notice of the Claim (or sooner if required by applicable law); (ii) reasonably cooperating with the
+         indemnitor, at the indemnitor’s expense, in the defence of the claim; and (iii) giving the indemnitor sole
+         control of the defence and any settlement negotiations. The indemnitee may participate in the defence at its
+         expense.
+
+9. LIMITATION OF LIABILITY.
+   9.1.  TO THE EXTENT PERMITTED BY LAW, NEITHER MEMGRAPH NOR CUSTOMER SHALL BE LIABLE TO THE OTHER OR ANY THIRD PARTY
+         FOR LOST PROFITS (WHETHER DIRECT OR INDIRECT) OR LOSS OF USE OR DATA, SUBSTITUTE GOODS OR SERVICES, OR FOR
+         INCIDENTAL, CONSEQUENTIAL, PUNITIVE, SPECIAL OR EXEMPLARY DAMAGES (INCLUDING DAMAGE TO BUSINESS, REPUTATION OR
+         GOODWILL), OR INDIRECT DAMAGES OF ANY TYPE HOWEVER CAUSED, WHETHER BY BREACH OF WARRANTY, BREACH OF CONTRACT,
+         IN TORT (INCLUDING NEGLIGENCE) OR ANY OTHER LEGAL OR EQUITABLE CAUSE OF ACTION EVEN IF SUCH PARTY HAS BEEN
+         ADVISED OF SUCH DAMAGES IN ADVANCE OR IF SUCH DAMAGES WERE FORESEEABLE.
+   9.2.  LIMITATIONS ON DIRECT DAMAGES. EXCEPT FOR ANY EXCLUDED CLAIMS AND ANY DAMAGES THAT CANNOT BE LIMITED UNDER
+         APPLICABLE LAW, IN NO EVENT WILL MEMGRAPH’S TOTAL AGGREGATE LIABILITY ARISING FROM OR RELATED TO THIS
+         AGREEMENT, EXCEED AN AMOUNT EQUAL TO THE TOTAL AMOUNT OF FEES PAID OR PAYABLE BY CUSTOMER TO MEMGRAPH UNDER
+         THIS AGREEMENT DURING THE TWELVE MONTHS PRECEDING THE CLAIM. THE FOREGOING LIMITATIONS SHALL NOT APPLY TO: (i)
+         PAYMENTS TO A THIRD PARTY ARISING FROM A PARTY’S OBLIGATIONS UNDER SECTION 8 (INDEMNIFICATION); (ii) BREACH BY
+         A PARTY OF SECTION 10 (CONFIDENTIAL INFORMATION), AND (iii) INFRINGEMENT BY A PARTY OF THE OTHER PARTY’S
+         INTELLECTUAL PROPERTY RIGHTS (COLLECTIVELY EXCLUSIONS (i)-(iii) ARE REFERRED TO AS THE “EXCLUDED CLAIMS”). WITH
+         RESPECT TO ANY EXCLUDED CLAIMS, MEMGRAPH’S TOTAL AGGREGATE LIABILITY SHALL IN NO EVENT EXCEED £1,000,000.
+   9.3.  Nothing in this Agreement excludes the liability of Memgraph for death or personal injury caused by the
+         Supplier’s negligence; or for fraud or fraudulent misrepresentation.
+
+10. CONFIDENTIALITY.
+   10.1. The Receiving Party will use the same degree of care that it uses to protect the confidentiality of its own
+         confidential information of like kind (but not less than reasonable care) to (i) not use any confidential
+         information of the Disclosing Party for any purpose outside the scope of this agreement and (ii) except as
+         otherwise authorized by the Disclosing Party in writing, limit access to confidential information of the
+         Disclosing Party to those of its and its affiliates’ employees and contractors who need that access for
+         purposes consistent with this agreement and who have signed confidentiality agreements with the receiving party
+         containing protections not materially less protective of the confidential information than those herein.
+         Neither party will disclose the terms of this agreement or any Orders to any third-party other than its
+         affiliates, legal counsel, and accountants without the other party’s prior written consent, provided that a
+         party that makes any such disclosure to its affiliate, legal counsel or accountants will remain responsible for
+         such affiliate’s, legal counsel’s, or accountant’s compliance with this “Confidentiality” section.
+   10.2. Compelled Disclosure. The Receiving Party may disclose confidential information of the Disclosing Party to the
+         extent compelled by law to do so, provided the Receiving Party gives the Disclosing Party prior notice of the
+         compelled disclosure (to the extent legally permitted) and reasonable assistance, at the Disclosing Party’s
+         cost, if the Disclosing Party wishes to contest the disclosure. If the receiving party is compelled by law to
+         disclose the Disclosing Party’s confidential information as part of a civil proceeding to which the Disclosing
+         Party is a party, and the Disclosing Party is not contesting the disclosure, the Disclosing Party will
+         reimburse the Receiving Party for its reasonable cost of complying and providing secure access to that
+         confidential information.
+
+
+11. TERMINATION.
+   11.1. Term. The term (“Term”) of this Agreement will commence on the Effective Date and continue until all
+         Subscriptions, licence terms and Orders expire, unless earlier terminated in accordance with this Section 11.
+   11.2. Termination for Cause. In the event of a material breach of this Agreement (excluding any breaches for which an
+         exclusive remedy is expressly provided), the non-breaching party may terminate this Agreement if such breach
+         is not cured within thirty (30) days after written notice thereof (except that for a breach of Section 3.5
+         (“General Restrictions”), there will be no cure period). For clarity, material breach of this Agreement
+         includes, but is not limited to, failure to timely pay amounts due hereunder, exceeding the scope of any
+         Licence granted hereunder (including the Licensed Capacity), violating the Licence restrictions, breach of
+         Section 6.1 and failing to protect the other party’s Confidential Information.
+   11.3. Without affecting any other right or remedy available to it, and to the fullest extent permitted by applicable
+         law, either party may terminate this Agreement with immediate effect by giving written notice to the other
+         party if the other party:
+      11.3.1.  suspends, or threatens to suspend, payment of its debts or is unable to pay its debts as they fall due or
+               admits inability to pay its debts or is deemed unable to pay its debts within the meaning of section 123
+               of the Insolvency Act 1986, as if the words “it is proved to the satisfaction of the court” did not
+               appear in sections 123(1)(e) or 123(2) of the Insolvency Act 1986; or
+      11.3.2.  the other party commences negotiations with all or any class of its creditors with a view to rescheduling
+               any of its debts, or makes a proposal for or enters into any compromise or arrangement with its creditors
+               other than for the sole purpose of a scheme for a solvent amalgamation of that other party with one or
+               more other companies or the solvent reconstruction of that other party; or
+      11.3.3.  a petition is filed, a notice is given, a resolution is passed, or an order is made, for or in connection
+               with the winding up of that other party other than for the sole purpose of a scheme for a solvent
+               amalgamation of that other party with one or more other companies or the solvent reconstruction of that
+               other party; or
+      11.3.4.  an application is made to court, or an order is made, for the appointment of an administrator, or if a
+               notice of intention to appoint an administrator is given or if an administrator is appointed, over the
+               other party; or
+      11.3.5.  the holder of a qualifying floating charge over the assets of that other party has become entitled to
+               appoint or has appointed an administrative receiver; or
+      11.3.6.  a person becomes entitled to appoint a receiver over the assets of the other party or a receiver is
+               appointed over the assets of the other party; or
+      11.3.7.  a creditor or encumbrancer of the other party attaches or takes possession of, or a distress, execution,
+               sequestration or other such process is levied or enforced on or sued against, the whole or any part of
+               the other party’s assets and such attachment or process is not discharged within 30 days; or
+      11.3.8.  any event occurs, or proceeding is taken, with respect to the other party in any jurisdiction to which
+               it is subject that has an effect equivalent or similar to any of the events mentioned in clause 11.3.1 to
+               clause 11.3.7 (inclusive); or
+      11.3.9.  the other party suspends or ceases, or threatens to suspend or cease, carrying on all or a substantial
+               part of its business.
+   11.4. Effect of Termination. Upon the termination of this Agreement: (i) all licences will terminate; (ii) Customer
+         will immediately discontinue all use of the affected Software  and erase all other tangible embodiments of
+         Memgraph Confidential Information in Customer’s possession or control, and promptly certify the same to
+         Memgraph; (iii) Memgraph may immediately cease providing the Services; (iv) (subject to this Section),
+         Memgraph will return or delete all tangible embodiments of Customer Confidential Information in Memgraph’s
+         possession or control; and (v) Sections 1 (“Definitions”), 3.5 (“General Restrictions”), 3.6 (“Ownership;
+         Reservation of Rights”), 5 (“Fees and Payment”), 7.3 (“Limitations”), 7.4 (“Disclaimer”), 8
+         (“Indemnification”), 9 (“Limitation of Liability”), 10 (“Confidentiality”), 11.4 (“Effect of Termination”),
+         and 12 (“Miscellaneous”) will survive. If a party’s file retention policies or a valid legal order provides
+         for backup or archival copies of files to be retained, such party will notify the other party of such policy
+         or order, protect the other party’s Confidential Information as required hereunder, and permanently erase,
+         delete, or destroy such Confidential Information as soon as permissible under such policy or order.
+
+12. MISCELLANEOUS.
+   12.1. Assignment. This Agreement will bind and inure to the benefit of each party’s permitted successors and assigns.
+         Memgraph may assign this Agreement to any affiliate or in connection with a merger, reorganization,
+         acquisition, or other transfer of all or substantially all of Memgraph’s assets or voting securities. Customer
+         may not assign or transfer this Agreement, in whole or in part, without Memgraph’s written consent except that
+         Customer may assign its rights and obligations under this Agreement, in whole but not in part, without
+         Memgraph’s written consent in connection with any merger, consolidation, sale of all or substantially all of
+         Customer’s assets or voting stock, or any other similar transaction provided that: (i) the assignee is not a
+         direct competitor of Memgraph; (ii) Customer provides prompt written notice of such assignment to Memgraph;
+         (iii) the assignee is capable of fully performing Customer’s obligations under this Agreement; and (iv) the
+         assignee agrees to be bound by the terms and conditions of this Agreement. Any attempt to transfer or assign
+         this Agreement without such written consent will be null and void.Force Majeure. Memgraph shall have no
+         liability to the Customer under this Agreement if it is prevented from or delayed in performing its obligations
+         under this Agreement, or from carrying on its business, by acts, events, omissions or accidents beyond its
+         reasonable control, including strikes, lock-outs or other industrial disputes (whether involving the workforce
+         of Memgraph or any other party), failure of a utility service or transport or telecommunications network, act
+         of God, war, pandemic, riot, civil commotion, malicious damage, compliance with any law or governmental order,
+         rule, regulation or direction, accident, breakdown of plant or machinery, fire, flood, storm or default of
+         suppliers or subcontractors, provided that the Customer is notified of such an event and its expected duration.
+   12.2. Governing Law. This Agreement and any dispute or claim arising out of or in connection with it or its subject
+         matter or formation (including non-contractual disputes or claims) shall be governed by and construed in
+         accordance with the law of England and Wales.
+   12.3. Jurisdiction. Each party irrevocably agrees that the courts of England and Wales shall have exclusive
+         jurisdiction to settle any dispute or claim arising out of or in connection with this Agreement or its subject
+         matter or formation (including non-contractual disputes or claims).
+   12.4. Severability; Waiver; Construction. If a court of competent jurisdiction adjudges any provision of this
+         Agreement to be invalid or unenforceable, the remaining provisions of this Agreement, if capable of substantial
+         performance, will continue in full force and effect without being impaired or invalidated in any way. The
+         parties agree to replace any invalid provision with a valid provision that most closely approximates the intent
+         and economic effect of the invalid provision. All waivers must be in writing. A party’s consent to, or waiver
+         of, enforcement of this Agreement on one occasion will not be deemed a waiver of any other provision or such
+         provision on any other occasion. In this Agreement, the word “including” means “including but not limited to.”
+         No presumption will operate in favour of or against any party as a result of its role in drafting this
+         Agreement.
+   12.5. Subcontractors. Memgraph may use the services of subcontractors in connection with its performance of this
+         Agreement, provided that Memgraph remains solely responsible for (i) compliance of any such subcontractor with
+         the terms of this Agreement and (ii) the overall performance of Memgraph as required under this Agreement.
+   12.6. Use of Aggregate Data. Customer agrees that Memgraph may collect, use and disclose quantitative data and
+         metadata derived from the use of the Software (i) for its own internal, statistical analysis, (ii) to develop
+         and improve the Software and (iii) to create and distribute reports and other materials regarding use of the
+         Software. For clarity, any such data collected, used, and disclosed will be in anonymized aggregate form only
+         and shall not identify Customer or its Users, or disclose any Customer Data.Independent Contractors. The
+         parties are independent contractors. No agency, partnership, franchise, joint venture, or employment
+         relationship is intended or created by this Agreement. Neither party has the power or authority to create or
+         assume any obligation, or make any representations or warranties, on behalf of the other party.
+   12.7. Publicity. Memgraph may, in conformity with Customer’s trademark usage guidelines, use Customer’s name and logo
+         in Memgraph’s sales and marketing materials, including in business presentations, Customer lists, and on
+         websites. Neither party will issue a press release regarding this Agreement without the other party’s prior
+         written consent. Neither party will disclose the terms of this Agreement to any third party, except as required
+         by law.
+   12.8. Notice. Any notice, consent, or waiver hereunder must be in writing, addressed to the attention of “Legal
+         Department” at the address set forth above, and delivered by personal delivery, reputable rapid courier, or
+         certified/registered mail, return receipt requested, and will be deemed given upon personal delivery, one (1)
+         day after deposit with an overnight domestic courier, two (2) days after deposit with an international courier,
+         or five (5) days after deposit in the certified or registered mail. A party may specify a new address by
+         providing notice to the other party in accordance with this Section.
+   12.9. Compliance with Law. Each party will comply with all applicable laws, regulations, and orders of any
+         governmental authority of competent jurisdiction in its performance under this Agreement, including but not
+         limited to those applicable to data collection and the privacy and security of personal information, including
+         trans-border data transfers and data breach notification requirements as required of each party by law.
+   12.10.Supremacy; Modification. This Agreement will prevail over any written instrument submitted by Customer; the
+         terms of any purchase order, acknowledgement, or similar document submitted by Customer to Memgraph will have
+         no effect. If the express terms of an Order Document conflict with this Agreement, the terms on the Order
+         Document will prevail, but only with respect to that Order Document. This Agreement cannot be varied or
+         supplemented by course of dealing or by usage of trade. All modifications or amendments to this Agreement must
+         be in writing and signed by both parties, except that subsequent renewals and purchases of additional Licensed
+         Capacity can be procured by payment against an issued invoice as set forth in Section 5 (“Fees and Payment”)
+         above.
+   12.11.No Third Party Beneficiaries. This Agreement is not intended and shall not be construed to give any third party
+         any interest or rights with respect to or in connection with any agreement or provision herein, except as
+         expressly provided for in this Agreement.
+   12.12.Entire Agreement. This Agreement in its original English text, sets forth the complete, exclusive, and final
+         agreement of the parties concerning the subject matter hereof, supersedes, replaces, and merges all prior and
+         contemporaneous agreements, communications, and understandings, both
+         written and oral, between them concerning the subject matter hereof. This Agreement may be executed in
+         counterparts.

licenses/third-party/antlr/LICENSE.txt

@@ -0,0 +1,52 @@
+[The "BSD 3-clause license"]
+Copyright (c) 2012-2017 The ANTLR Project. All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions
+are met:
+
+ 1. Redistributions of source code must retain the above copyright
+    notice, this list of conditions and the following disclaimer.
+ 2. Redistributions in binary form must reproduce the above copyright
+    notice, this list of conditions and the following disclaimer in the
+    documentation and/or other materials provided with the distribution.
+ 3. Neither the name of the copyright holder nor the names of its contributors
+    may be used to endorse or promote products derived from this software
+    without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
+IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
+OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
+IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
+INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+=====
+
+MIT License for codepointat.js from https://git.io/codepointat
+MIT License for fromcodepoint.js from https://git.io/vDW1m
+
+Copyright Mathias Bynens <https://mathiasbynens.be/>
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

licenses/third-party/bzip2/LICENSE

@@ -0,0 +1,42 @@
+
+--------------------------------------------------------------------------
+
+This program, "bzip2", the associated library "libbzip2", and all
+documentation, are copyright (C) 1996-2010 Julian R Seward.  All
+rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions
+are met:
+
+1. Redistributions of source code must retain the above copyright
+   notice, this list of conditions and the following disclaimer.
+
+2. The origin of this software must not be misrepresented; you must 
+   not claim that you wrote the original software.  If you use this 
+   software in a product, an acknowledgment in the product 
+   documentation would be appreciated but is not required.
+
+3. Altered source versions must be plainly marked as such, and must
+   not be misrepresented as being the original software.
+
+4. The name of the author may not be used to endorse or promote 
+   products derived from this software without specific prior written 
+   permission.
+
+THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS
+OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
+DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE
+GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+Julian Seward, jseward@bzip.org
+bzip2/libbzip2 version 1.0.6 of 6 September 2010
+
+--------------------------------------------------------------------------

licenses/third-party/cppitertools/LICENSE.md

@@ -0,0 +1,23 @@
+Copyright (c) 2013, Ryan Haining, Aaron Josephs, Google
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without modification,
+are permitted provided that the following conditions are met:
+
+  Redistributions of source code must retain the above copyright notice, this
+  list of conditions and the following disclaimer.
+
+  Redistributions in binary form must reproduce the above copyright notice, this
+  list of conditions and the following disclaimer in the documentation and/or
+  other materials provided with the distribution.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
+ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR
+ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
+ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

licenses/third-party/fmt/LICENSE.rst

@@ -0,0 +1,27 @@
+Copyright (c) 2012 - present, Victor Zverovich
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+--- Optional exception to the license ---
+
+As an exception, if, as a result of your compiling your source code, portions
+of this Software are embedded into a machine-executable object form of such
+source code, you may redistribute such embedded portions in such object form
+without including the above copyright and permission notices.

licenses/third-party/gflags/COPYING.txt

@@ -0,0 +1,28 @@
+Copyright (c) 2006, Google Inc.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+
+    * Redistributions of source code must retain the above copyright
+notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above
+copyright notice, this list of conditions and the following disclaimer
+in the documentation and/or other materials provided with the
+distribution.
+    * Neither the name of Google Inc. nor the names of its
+contributors may be used to endorse or promote products derived from
+this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

licenses/third-party/jemalloc/COPYING

@@ -0,0 +1,27 @@
+Unless otherwise specified, files in the jemalloc source distribution are
+subject to the following license:
+--------------------------------------------------------------------------------
+Copyright (C) 2002-present Jason Evans <jasone@canonware.com>.
+All rights reserved.
+Copyright (C) 2007-2012 Mozilla Foundation.  All rights reserved.
+Copyright (C) 2009-present Facebook, Inc.  All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+1. Redistributions of source code must retain the above copyright notice(s),
+   this list of conditions and the following disclaimer.
+2. Redistributions in binary form must reproduce the above copyright notice(s),
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDER(S) ``AS IS'' AND ANY EXPRESS
+OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.  IN NO
+EVENT SHALL THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY DIRECT, INDIRECT,
+INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+--------------------------------------------------------------------------------