Prepare release v0.50.0

Subscribers: pullbot

Differential Revision: https://phabricator.memgraph.io/D2598

.arcconfig

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

.arclint

@@ -0,0 +1,9 @@
+{
+  "linters": {
+    "clang-tidy": {
+      "type": "script-and-regex",
+      "script-and-regex.script": "./tools/arc-clang-tidy",
+      "script-and-regex.regex": "/^(?P<file>.*):(?P<line>\\d+):(?P<char>\\d+): (?P<severity>warning|error): (?P<message>.*)$/m"
+    }
+  }
+}

.clang-format

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

.clang-tidy

@@ -1,12 +1,7 @@
 ---
 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,
@@ -31,7 +26,6 @@ Checks: '*,
          -fuchsia-virtual-inheritance,
          -google-explicit-constructor,
          -google-readability-*,
-         -google-runtime-references,
          -hicpp-avoid-c-arrays,
          -hicpp-avoid-goto,
          -hicpp-braces-around-statements,
@@ -40,17 +34,12 @@ 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,
@@ -58,16 +47,11 @@ 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,
-         -misc-no-recursion,
-         -concurrency-mt-unsafe,
-         -bugprone-easily-swappable-parameters'
-
+         -readability-named-parameter'
 WarningsAsErrors: ''
-HeaderFilterRegex: 'src/.*'
+HeaderFilterRegex: ''
 AnalyzeTemporaryDtors: false
 FormatStyle:     none
 CheckOptions:
@@ -92,3 +76,4 @@ CheckOptions:
   - key:             modernize-use-nullptr.NullMacros
     value:           'NULL'
 ...
+

.githooks/pre-commit

@@ -1,36 +0,0 @@
-#!/bin/sh
-
-project_folder=$(git rev-parse --show-toplevel)
-if git rev-parse --verify HEAD >/dev/null 2>&1
-then
-	against=HEAD
-else
-	# Initial commit: diff against an empty tree object
-	against=$(git hash-object -t tree /dev/null)
-fi
-
-# Redirect output to stderr.
-exec 1>&2
-
-tmpdir=$(mktemp -d repo-XXXXXXXX)
-trap "rm -rf $tmpdir" EXIT INT
-
-modified_files=$(git diff --cached --name-only --diff-filter=AM $against | sed -nE "/.*\.(cpp|cc|cxx|c|h|hpp)$/p")
-FAIL=0
-for file in $modified_files; do
-  echo "Checking $file..."
-
-  cp $project_folder/.clang-format $project_folder/.clang-tidy $tmpdir
-
-  git checkout-index --prefix="$tmpdir/" -- $file
-
-  # Do not break header checker
-  echo "Running header checker..."
-  $project_folder/tools/header-checker.py $tmpdir/$file $file --amend-year
-  CODE=$?
-  if [ $CODE -ne 0 ]; then
-    FAIL=1
-  fi
-done;
-
-return ${FAIL}

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,34 +0,0 @@
----
-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

@@ -1,11 +0,0 @@
-[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

@@ -1,82 +0,0 @@
-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

@@ -1,273 +0,0 @@
-name: Diff
-concurrency:
-  group: ${{ github.head_ref || github.sha }}
-  cancel-in-progress: true
-
-on:
-  push:
-    branches:
-      - master
-  workflow_dispatch:
-  pull_request:
-    paths-ignore:
-      - "docs/**"
-      - "**/*.md"
-      - ".clang-format"
-      - "CODEOWNERS"
-
-jobs:
-  community_build:
-    name: "Community build"
-    runs-on: [self-hosted, Linux, X64, Diff]
-    env:
-      THREADS: 24
-      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
-      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
-
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v3
-        with:
-          # Number of commits to fetch. `0` indicates all history for all
-          # branches and tags. (default: 1)
-          fetch-depth: 0
-
-      - name: Build community binaries
-        run: |
-          # Activate toolchain.
-          source /opt/toolchain-v4/activate
-
-          # Initialize dependencies.
-          ./init
-
-          # Build community binaries.
-          cd build
-          cmake -DCMAKE_BUILD_TYPE=release -DMG_ENTERPRISE=OFF ..
-          make -j$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 -j$THREADS
-
-  code_analysis:
-    name: "Code analysis"
-    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@v3
-        with:
-          # Number of commits to fetch. `0` indicates all history for all
-          # branches and tags. (default: 1)
-          fetch-depth: 0
-
-        # This is also needed if we want do to comparison against other branches
-        # See https://github.community/t/checkout-code-fails-when-it-runs-lerna-run-test-since-master/17920
-      - name: Fetch all history for all tags and branches
-        run: git fetch
-
-      - name: Initialize deps
-        run: |
-          # Activate toolchain.
-          source /opt/toolchain-v4/activate
-          # Initialize dependencies.
-          ./init
-
-      - name: Set base branch
-        if: ${{ github.event_name == 'pull_request' }}
-        run: |
-          echo "BASE_BRANCH=origin/${{ github.base_ref }}" >> $GITHUB_ENV
-
-      - name: Set base branch # if we manually dispatch or push to master
-        if: ${{ github.event_name != 'pull_request' }}
-        run: |
-          echo "BASE_BRANCH=origin/master" >> $GITHUB_ENV
-
-      - name: Python code analysis
-        run: |
-          CHANGED_FILES=$(git diff -U0 ${{ env.BASE_BRANCH }}... --name-only)
-          for file in ${CHANGED_FILES}; do
-            echo ${file}
-            if [[ ${file} == *.py ]]; then
-              python3 -m black --check --diff ${file}
-              python3 -m isort --check-only --profile "black" --diff ${file}
-            fi
-          done
-
-      - name: Build combined ASAN, UBSAN and coverage binaries
-        run: |
-          # Activate toolchain.
-          source /opt/toolchain-v4/activate
-
-          cd build
-          cmake -DTEST_COVERAGE=ON -DASAN=ON -DUBSAN=ON ..
-          make -j$THREADS memgraph__unit
-
-      - name: Run unit tests
-        run: |
-          # Activate toolchain.
-          source /opt/toolchain-v4/activate
-
-          # Run unit tests. It is restricted to 2 threads intentionally, because higher concurrency makes the timing related tests unstable.
-          cd build
-          LSAN_OPTIONS=suppressions=$PWD/../tools/lsan.supp UBSAN_OPTIONS=halt_on_error=1 ctest -R memgraph__unit --output-on-failure -j2
-
-      - name: Compute code coverage
-        run: |
-          # Activate toolchain.
-          source /opt/toolchain-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
-
-      - 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, Linux, X64, Diff]
-    env:
-      THREADS: 24
-      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
-      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
-
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v3
-        with:
-          # Number of commits to fetch. `0` indicates all history for all
-          # branches and tags. (default: 1)
-          fetch-depth: 0
-
-      - name: Build debug binaries
-        run: |
-          # Activate toolchain.
-          source /opt/toolchain-v4/activate
-
-          # Initialize dependencies.
-          ./init
-
-          # Build debug binaries.
-          cd build
-          cmake ..
-          make -j$THREADS
-
-      - name: Run simulation tests
-        run: |
-          # Activate toolchain.
-          source /opt/toolchain-v4/activate
-
-          # Run simulation tests.
-          cd build
-          ctest -R memgraph__simulation --output-on-failure -j$THREADS
-
-      - name: Run single benchmark test
-        run: |
-          # Activate toolchain.
-          source /opt/toolchain-v4/activate
-
-          # Run simulation tests.
-          cd tests/mgbench
-          ./benchmark.py accesscontrol/small --num-workers-for-import 1 --test-system-arg  "split-file splitfiles/accesscontrol_small.shard_configuration bolt-num-workers 1"
-
-  release_build:
-    name: "Release build"
-    runs-on: [self-hosted, Linux, X64, Diff]
-    env:
-      THREADS: 24
-      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
-      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
-
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v3
-        with:
-          # Number of commits to fetch. `0` indicates all history for all
-          # branches and tags. (default: 1)
-          fetch-depth: 0
-
-      - name: Build release binaries
-        run: |
-          # Activate toolchain.
-          source /opt/toolchain-v4/activate
-
-          # Initialize dependencies.
-          ./init
-
-          # Build release binaries.
-          cd build
-          cmake -DCMAKE_BUILD_TYPE=release ..
-          make -j$THREADS
-
-      - name: Run unit tests
-        run: |
-          # Activate toolchain.
-          source /opt/toolchain-v4/activate
-
-          # Run unit tests.
-          cd build
-          ctest -R memgraph__unit --output-on-failure -j$THREADS
-
-      - name: Run simulation tests
-        run: |
-          # Activate toolchain.
-          source /opt/toolchain-v4/activate
-
-          # Run simulation tests.
-          cd build
-          ctest -R memgraph__simulation --output-on-failure -j$THREADS
-
-      - name: Run single benchmark test
-        run: |
-          # Activate toolchain.
-          source /opt/toolchain-v4/activate
-
-          # Run simulation tests.
-          cd tests/mgbench
-          ./benchmark.py accesscontrol/small --num-workers-for-import 1 --test-system-arg  "split-file splitfiles/accesscontrol_small.shard_configuration bolt-num-workers 1"
-
-      - name: Run e2e tests
-        run: |
-          # TODO(gitbuda): Setup mgclient and pymgclient properly.
-          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 ./distributed_queries

.github/workflows/full_clang_tidy.yaml

@@ -1,46 +0,0 @@
-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

@@ -1,178 +0,0 @@
-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

@@ -1,315 +0,0 @@
-name: Release CentOS 8
-
-on:
-  workflow_dispatch:
-  schedule:
-    - cron: "0 1 * * *"
-
-jobs:
-  community_build:
-    name: "Community build"
-    runs-on: [self-hosted, Linux, X64, CentOS8]
-    env:
-      THREADS: 24
-      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, CentOS8]
-    env:
-      THREADS: 24
-      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
-      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
-
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v3
-        with:
-          # Number of commits to fetch. `0` indicates all history for all
-          # branches and tags. (default: 1)
-          fetch-depth: 0
-
-      - name: Build coverage binaries
-        run: |
-          # Activate toolchain.
-          source /opt/toolchain-v4/activate
-
-          # Initialize dependencies.
-          ./init
-
-          # Build coverage binaries.
-          cd build
-          cmake -DTEST_COVERAGE=ON ..
-          make -j$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, CentOS8]
-    env:
-      THREADS: 24
-      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
-      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
-
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v3
-        with:
-          # Number of commits to fetch. `0` indicates all history for all
-          # branches and tags. (default: 1)
-          fetch-depth: 0
-
-      - name: Build debug binaries
-        run: |
-          # Activate toolchain.
-          source /opt/toolchain-v4/activate
-
-          # Initialize dependencies.
-          ./init
-
-          # Build debug binaries.
-          cd build
-          cmake ..
-          make -j$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, CentOS8]
-    env:
-      THREADS: 24
-      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
-      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
-    timeout-minutes: 960
-
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v3
-        with:
-          # Number of commits to fetch. `0` indicates all history for all
-          # branches and tags. (default: 1)
-          fetch-depth: 0
-
-      - name: Build release binaries
-        run: |
-          # Activate toolchain.
-          source /opt/toolchain-v4/activate
-
-          # Initialize dependencies.
-          ./init
-
-          # Build release binaries.
-          cd build
-          cmake -DCMAKE_BUILD_TYPE=release ..
-          make -j$THREADS
-
-      - name: Create enterprise RPM 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 RPM package.
-          mkdir output && cd output
-          cpack -G RPM --config ../CPackConfig.cmake
-          rpmlint memgraph*.rpm
-
-      - name: Save enterprise RPM package
-        uses: actions/upload-artifact@v3
-        with:
-          name: "Enterprise RPM package"
-          path: build/output/memgraph*.rpm
-
-      - 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

.github/workflows/release_debian10.yaml

@@ -1,356 +0,0 @@
-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

@@ -1,69 +0,0 @@
-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

@@ -1,314 +0,0 @@
-name: Release Ubuntu 20.04
-
-on:
-  workflow_dispatch:
-  schedule:
-    - cron: "0 1 * * *"
-
-jobs:
-  community_build:
-    name: "Community build"
-    runs-on: [self-hosted, Linux, X64, Ubuntu20.04]
-    env:
-      THREADS: 24
-      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, Ubuntu20.04]
-    env:
-      THREADS: 24
-      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
-      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
-
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v3
-        with:
-          # Number of commits to fetch. `0` indicates all history for all
-          # branches and tags. (default: 1)
-          fetch-depth: 0
-
-      - name: Build coverage binaries
-        run: |
-          # Activate toolchain.
-          source /opt/toolchain-v4/activate
-
-          # Initialize dependencies.
-          ./init
-
-          # Build coverage binaries.
-          cd build
-          cmake -DTEST_COVERAGE=ON ..
-          make -j$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, 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 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, Ubuntu20.04]
-    env:
-      THREADS: 24
-      MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
-      MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
-    timeout-minutes: 960
-
-    steps:
-      - name: Set up repository
-        uses: actions/checkout@v3
-        with:
-          # Number of commits to fetch. `0` indicates all history for all
-          # branches and tags. (default: 1)
-          fetch-depth: 0
-
-      - name: Build release binaries
-        run: |
-          # Activate toolchain.
-          source /opt/toolchain-v4/activate
-
-          # Initialize dependencies.
-          ./init
-
-          # Build release binaries.
-          cd build
-          cmake -DCMAKE_BUILD_TYPE=release ..
-          make -j$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

.gitignore

@@ -23,8 +23,6 @@ cmake-build-*
 cmake/DownloadProject/
 dist/
 src/query/frontend/opencypher/generated/
-src/query/v2/frontend/opencypher/generated/
-src/parser/opencypher/generated
 tags
 ve/
 ve3/
@@ -52,25 +50,15 @@ 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

@@ -1,21 +0,0 @@
-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)
-        args: ["--profile", "black"]
-  - repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v13.0.0
-    hooks:
-      - id: clang-format

.ycm_extra_conf.py

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

CHANGELOG.md

@@ -1,5 +1,298 @@
-Change Log for all versions of Memgraph can be found on-line at
-https://docs.memgraph.com/memgraph/changelog
+# Change Log
 
-All the updates to the Change Log can be made in the following repository:
-https://github.com/memgraph/docs
+## 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

@@ -35,125 +35,16 @@ else()
   message(FATAL_ERROR "Couldn't find clang and/or clang++!")
 endif()
 
+# Get current commit hash.
+execute_process(
+    OUTPUT_VARIABLE COMMIT_HASH
+    COMMAND git rev-parse --short HEAD
+)
+string(STRIP ${COMMIT_HASH} COMMIT_HASH)
+
 # -----------------------------------------------------------------------------
 
-project(memgraph)
-
-# Install licenses.
-install(DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}/licenses/
-        DESTINATION share/doc/memgraph)
-
-# For more information about how to release a new version of Memgraph, see
-# `release/README.md`.
-
-# Option that is used to specify which version of Memgraph should be built. The
-# default is `ON` which causes the build system to build Memgraph Enterprise.
-# Memgraph Community is built if explicitly set to `OFF`.
-option(MG_ENTERPRISE "Build Memgraph Enterprise Edition" ON)
-
-# Set the current version here to override the automatic version detection. The
-# version must be specified as `X.Y.Z`. Primarily used when building new patch
-# versions.
-set(MEMGRAPH_OVERRIDE_VERSION "")
-
-# Custom suffix that this version should have. The suffix can be any arbitrary
-# string. Primarily used when building a version for a specific customer.
-set(MEMGRAPH_OVERRIDE_VERSION_SUFFIX "")
-
-# Variables used to generate the versions.
-if (MG_ENTERPRISE)
-  set(get_version_offering "")
-else()
-  set(get_version_offering "--open-source")
-endif()
-set(get_version_script "${CMAKE_CURRENT_SOURCE_DIR}/release/get_version.py")
-
-# Get version that should be used in the binary.
-execute_process(
-    OUTPUT_VARIABLE MEMGRAPH_VERSION
-    RESULT_VARIABLE MEMGRAPH_VERSION_RESULT
-    COMMAND "${get_version_script}" ${get_version_offering}
-                "${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: ${MEMGRAPH_VERSION}")
-endif()
-
-# Get version that should be used in the DEB package.
-execute_process(
-    OUTPUT_VARIABLE MEMGRAPH_VERSION_DEB
-    RESULT_VARIABLE MEMGRAPH_VERSION_DEB_RESULT
-    COMMAND "${get_version_script}" ${get_version_offering}
-                --variant deb
-                "${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: ${MEMGRAPH_VERSION_DEB}")
-endif()
-
-# Get version that should be used in the RPM package.
-execute_process(
-    OUTPUT_VARIABLE MEMGRAPH_VERSION_RPM
-    RESULT_VARIABLE MEMGRAPH_VERSION_RPM_RESULT
-    COMMAND "${get_version_script}" ${get_version_offering}
-                --variant rpm
-                "${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: ${MEMGRAPH_VERSION_RPM}")
-endif()
-
-# We want the above variables to be updated each time something is committed to
-# the repository. That is why we include a dependency on the current git HEAD
-# to trigger a new CMake run when the git repository state changes. This is a
-# hack, as CMake doesn't have a mechanism to regenerate variables when
-# something changes (only files can be regenerated).
-# https://cmake.org/pipermail/cmake/2018-October/068389.html
-#
-# The hack in the above link is nearly correct but it has a fatal flaw. The
-# `CMAKE_CONFIGURE_DEPENDS` isn't a `GLOBAL` property, it is instead a
-# `DIRECTORY` property and as such must be set in the `DIRECTORY` scope.
-# https://cmake.org/cmake/help/v3.14/manual/cmake-properties.7.html
-#
-# Unlike the above mentioned hack, we don't use the `.git/index` file. That
-# file changes on every `git add` (even on `git status`) so it triggers
-# unnecessary recalculations of the release version. The release version only
-# changes on every `git commit` or `git checkout`. That is why we watch the
-# following files for changes:
-#   - `.git/HEAD` -> changes each time a `git checkout` is issued
-#   - `.git/refs/heads/...` -> the value in `.git/HEAD` is a branch name (when
-#     you are on a branch) and you have to monitor the file of the specific
-#     branch to detect when a `git commit` was issued
-# More details about the contents of the `.git` directory and the specific
-# files used can be seen here:
-# https://git-scm.com/book/en/v2/Git-Internals-Git-References
-set(git_directory "${CMAKE_SOURCE_DIR}/.git")
-if (EXISTS "${git_directory}")
-  set_property(DIRECTORY APPEND PROPERTY
-      CMAKE_CONFIGURE_DEPENDS "${git_directory}/HEAD")
-  file(STRINGS "${git_directory}/HEAD" git_head_data)
-  if (git_head_data MATCHES "^ref: ")
-    string(SUBSTRING "${git_head_data}" 5 -1 git_head_ref)
-    set_property(DIRECTORY APPEND PROPERTY
-        CMAKE_CONFIGURE_DEPENDS "${git_directory}/${git_head_ref}")
-  endif()
-endif()
-
+project(memgraph VERSION 0.50.0)
 # -----------------------------------------------------------------------------
 
 # setup CMake module path, defines path for include() and find_package()
@@ -177,25 +68,20 @@ add_custom_target(clean_all
 # is easier debugging of compilation and linker flags.
 set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
 
-set(CMAKE_CXX_STANDARD 20)
+set(CMAKE_CXX_STANDARD 17)
 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=implicit-fallthrough \
-    -Werror=return-type \
-    -Werror=return-stack-address \
-    -Wno-c99-designator \
-    -DBOOST_ASIO_USE_TS_EXECUTOR_AS_DEFAULT")
+    -Werror=switch -Werror=switch-bool -Werror=return-type \
+    -Werror=return-stack-address")
 
 # Don't omit frame pointer in RelWithDebInfo, for additional callchain debug.
 set(CMAKE_CXX_FLAGS_RELWITHDEBINFO
     "${CMAKE_CXX_FLAGS_RELWITHDEBINFO} -fno-omit-frame-pointer")
 
 # Statically link libgcc and libstdc++, the GCC allows this according to:
-# https://gcc.gnu.org/onlinedocs/gcc-10.2.0/libstdc++/manual/manual/license.html
+# https://gcc.gnu.org/onlinedocs/gcc-8.3.0/libstdc++/manual/manual/license.html
 # https://www.gnu.org/licenses/gcc-exception-faq.html
-# Last checked for gcc-10.2 which we are using on the build machines.
+# Last checked for gcc-8.3 which we are using on the build machines.
 # ** If we change versions, recheck this! **
 # ** Static linking is allowed only for executables! **
 set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -static-libgcc -static-libstdc++")
@@ -206,8 +92,6 @@ set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fuse-ld=gold")
 # release flags
 set(CMAKE_CXX_FLAGS_RELEASE "-O2 -DNDEBUG")
 
-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).")
@@ -223,6 +107,13 @@ else()
     set(CMAKE_CXX_FLAGS_DEBUG "-g")
 endif()
 
+# ndebug
+option(NDEBUG "No debug" OFF)
+message(STATUS "NDEBUG: ${NDEBUG} (be careful CMAKE_BUILD_TYPE can also \
+append this flag)")
+if(NDEBUG)
+    add_definitions( -DNDEBUG )
+endif()
 # -----------------------------------------------------------------------------
 
 # default build type is debug
@@ -232,12 +123,15 @@ 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 Ltalloc
+option(USE_LTALLOC "Use Ltalloc instead of default allocator (default OFF). \
+Set this to ON to link with Ltalloc." OFF)
+
 # 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)
@@ -248,16 +142,68 @@ if (USE_READLINE)
   endif()
 endif()
 
+# OpenSSL
+find_package(OpenSSL REQUIRED)
+
 set(libs_dir ${CMAKE_SOURCE_DIR}/libs)
 add_subdirectory(libs EXCLUDE_FROM_ALL)
 
+include_directories(SYSTEM ${GFLAGS_INCLUDE_DIR})
+include_directories(SYSTEM ${GLOG_INCLUDE_DIR})
+include_directories(SYSTEM ${FMT_INCLUDE_DIR})
+include_directories(SYSTEM ${ANTLR4_INCLUDE_DIR})
+include_directories(SYSTEM ${BZIP2_INCLUDE_DIR})
+include_directories(SYSTEM ${ZLIB_INCLUDE_DIR})
+include_directories(SYSTEM ${ROCKSDB_INCLUDE_DIR})
+include_directories(SYSTEM ${LIBRDKAFKA_INCLUDE_DIR})
+# -----------------------------------------------------------------------------
+
+# openCypher parser -----------------------------------------------------------
+set(opencypher_frontend ${CMAKE_SOURCE_DIR}/src/query/frontend/opencypher)
+set(opencypher_generated ${opencypher_frontend}/generated)
+set(opencypher_lexer_grammar ${opencypher_frontend}/grammar/MemgraphCypherLexer.g4)
+set(opencypher_parser_grammar ${opencypher_frontend}/grammar/MemgraphCypher.g4)
+
+# enumerate all files that are generated from antlr
+set(antlr_opencypher_generated_src
+   ${opencypher_generated}/MemgraphCypherLexer.cpp
+   ${opencypher_generated}/MemgraphCypher.cpp
+   ${opencypher_generated}/MemgraphCypherBaseVisitor.cpp
+   ${opencypher_generated}/MemgraphCypherVisitor.cpp
+)
+
+# Provide a command to generate sources if missing. If this were a
+# custom_target, it would always run and we don't want that.
+add_custom_command(OUTPUT ${antlr_opencypher_generated_src}
+  COMMAND
+  ${CMAKE_COMMAND} -E make_directory ${opencypher_generated}
+  COMMAND
+  java -jar ${CMAKE_SOURCE_DIR}/libs/antlr-4.6-complete.jar -Dlanguage=Cpp -visitor -o ${opencypher_generated} -package antlropencypher ${opencypher_lexer_grammar} ${opencypher_parser_grammar}
+  WORKING_DIRECTORY "${CMAKE_BINARY_DIR}"
+  DEPENDS ${opencypher_lexer_grammar} ${opencypher_parser_grammar}
+          ${opencypher_frontend}/grammar/CypherLexer.g4
+          ${opencypher_frontend}/grammar/Cypher.g4)
+
+# add custom target for generation
+add_custom_target(generate_opencypher_parser
+  DEPENDS ${antlr_opencypher_generated_src})
+
+add_library(antlr_opencypher_parser_lib STATIC ${antlr_opencypher_generated_src})
+target_link_libraries(antlr_opencypher_parser_lib antlr4)
+# -----------------------------------------------------------------------------
+
 # Optional subproject configuration -------------------------------------------
+option(POC "Build proof of concept binaries" OFF)
+option(EXPERIMENTAL "Build experimental binaries" OFF)
+option(CUSTOMERS "Build customer binaries" OFF)
 option(TEST_COVERAGE "Generate coverage reports from running memgraph" OFF)
 option(TOOLS "Build tools binaries" ON)
 option(QUERY_MODULES "Build query modules containing custom procedures" ON)
+option(MG_COMMUNITY "Build Memgraph Community Edition" OFF)
 option(ASAN "Build with Address Sanitizer. To get a reasonable performance option should be used only in Release or RelWithDebInfo build " OFF)
 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)
+option(THIN_LTO "Build with link time optimization" OFF)
 
 if (TEST_COVERAGE)
   string(TOLOWER ${CMAKE_BUILD_TYPE} lower_build_type)
@@ -268,15 +214,11 @@ if (TEST_COVERAGE)
   set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fprofile-instr-generate -fcoverage-mapping")
 endif()
 
-if (MG_ENTERPRISE)
-  add_definitions(-DMG_ENTERPRISE)
+if (MG_COMMUNITY)
+  add_definitions(-DMG_COMMUNITY)
 endif()
 
-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
@@ -323,29 +265,34 @@ if (UBSAN)
   # runtime library and c++ standard libraries are present.
   set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsanitize=undefined -fno-omit-frame-pointer -fno-sanitize=vptr")
   set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fsanitize=undefined -fno-sanitize=vptr")
-  # Run program with environment variable UBSAN_OPTIONS=print_stacktrace=1.
-  # Make sure llvm-symbolizer binary is in path.
-  # To make the program abort on undefined behavior, use UBSAN_OPTIONS=halt_on_error=1.
+  # Run program with environment variable UBSAN_OPTIONS=print_stacktrace=1
+  # Make sure llvm-symbolizer binary is in path
 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")
+if (THIN_LTO)
+  set(CMAKE_CXX_FLAGS"${CMAKE_CXX_FLAGS} -flto=thin")
+  set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -flto=thin")
+endif()
 
 # Add subprojects
 include_directories(src)
 add_subdirectory(src)
 
-# Release configuration
-add_subdirectory(release)
-
-option(MG_ENABLE_TESTING "Set this to OFF to disable building test binaries" ON)
-message(STATUS "MG_ENABLE_TESTING: ${MG_ENABLE_TESTING}")
-
-if (MG_ENABLE_TESTING)
-  enable_testing()
-  add_subdirectory(tests)
+if(POC)
+  add_subdirectory(poc)
 endif()
 
+if(EXPERIMENTAL)
+  add_subdirectory(experimental)
+endif()
+
+if(CUSTOMERS)
+  add_subdirectory(customers)
+endif()
+
+enable_testing()
+add_subdirectory(tests)
+
 if(TOOLS)
   add_subdirectory(tools)
 endif()
@@ -354,6 +301,58 @@ 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)
+# -----------------------------------------------------------------------------
+
+# ---- Setup CPack --------
+# General setup
+set(CPACK_PACKAGE_NAME memgraph)
+set(CPACK_PACKAGE_VENDOR "Memgraph Ltd.")
+set(CPACK_PACKAGE_DESCRIPTION_SUMMARY
+    "High performance, in-memory, transactional graph database")
+set(CPACK_PACKAGE_VERSION_MAJOR ${memgraph_VERSION_MAJOR})
+set(CPACK_PACKAGE_VERSION_MINOR ${memgraph_VERSION_MINOR})
+set(CPACK_PACKAGE_VERSION_PATCH ${memgraph_VERSION_PATCH})
+set(CPACK_PACKAGE_VERSION_TWEAK ${memgraph_VERSION_TWEAK})
+set(CPACK_PACKAGE_FILE_NAME ${CPACK_PACKAGE_NAME}-${memgraph_VERSION}-${COMMIT_HASH}${CPACK_SYSTEM_NAME})
+
+# DEB specific
+# Instead of using "name <email>" format, we use "email (name)" to prevent
+# errors due to full stop, '.' at the end of "Ltd". (See: RFC 822)
+set(CPACK_DEBIAN_PACKAGE_MAINTAINER "tech@memgraph.com (Memgraph Ltd.)")
+set(CPACK_DEBIAN_PACKAGE_SECTION non-free/database)
+set(CPACK_DEBIAN_PACKAGE_HOMEPAGE https://memgraph.com)
+set(CPACK_DEBIAN_PACKAGE_CONTROL_EXTRA
+    "${CMAKE_SOURCE_DIR}/release/debian/conffiles;"
+    "${CMAKE_SOURCE_DIR}/release/debian/copyright;"
+    "${CMAKE_SOURCE_DIR}/release/debian/prerm;"
+    "${CMAKE_SOURCE_DIR}/release/debian/postrm;"
+    "${CMAKE_SOURCE_DIR}/release/debian/postinst;")
+set(CPACK_DEBIAN_PACKAGE_SHLIBDEPS ON)
+# Description formatting is important, summary must be followed with a newline and 1 space.
+set(CPACK_DEBIAN_PACKAGE_DESCRIPTION "${CPACK_PACKAGE_DESCRIPTION_SUMMARY}
+ Contains Memgraph, the graph database. It aims to deliver developers the
+ speed, simplicity and scale required to build the next generation of
+ applications driver by real-time connected data.")
+# Add `openssl` package to dependencies list. Used to generate SSL certificates.
+set(CPACK_DEBIAN_PACKAGE_DEPENDS "openssl (>= 1.1.0)")
+
+# RPM specific
+set(CPACK_RPM_PACKAGE_URL https://memgraph.com)
+set(CPACK_RPM_EXCLUDE_FROM_AUTO_FILELIST_ADDITION
+  /var /var/lib /var/log /etc/logrotate.d
+  /lib /lib/systemd /lib/systemd/system /lib/systemd/system/memgraph.service)
+set(CPACK_RPM_PACKAGE_REQUIRES_PRE "shadow-utils")
+# NOTE: user specfile has a bug in cmake 3.7.2, this needs to be patched
+# manually in: ~/cmake/share/cmake-3.7/Modules/CPackRPM.cmake line 2273
+# Or newer cmake version used
+set(CPACK_RPM_USER_BINARY_SPECFILE "${CMAKE_SOURCE_DIR}/release/rpm/memgraph.spec.in")
+# Description formatting is important, no line must be greater than 80 characters.
+set(CPACK_RPM_PACKAGE_DESCRIPTION "Contains Memgraph, the graph database.
+It aims to deliver developers the speed, simplicity and scale required to build
+the next generation of applications driver by real-time connected data.")
+# Add `openssl` package to dependencies list. Used to generate SSL certificates.
+set(CPACK_RPM_PACKAGE_REQUIRES "openssl >= 1.0.0, curl >= 7.29.0")
+
+# All variables must be set before including.
+include(CPack)
+# ---- End Setup CPack ----

CODE_OF_CONDUCT.md

@@ -1,127 +0,0 @@
-# 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

@@ -1,121 +0,0 @@
-# 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).

Doxyfile

@@ -51,7 +51,7 @@ PROJECT_BRIEF          = "The World's Most Powerful Graph Database"
 # pixels and the maximum width should not exceed 200 pixels. Doxygen will copy
 # the logo to the output directory.
 
-PROJECT_LOGO           = docs/doxygen/memgraph_logo.png
+PROJECT_LOGO           = Doxylogo.png
 
 # The OUTPUT_DIRECTORY tag is used to specify the (relative or absolute) path
 # into which the generated documentation will be written. If a relative path is
@@ -839,6 +839,7 @@ EXCLUDE_PATTERNS      += */Testing/*
 EXCLUDE_PATTERNS      += */tests/*
 EXCLUDE_PATTERNS      += */dist/*
 EXCLUDE_PATTERNS      += */tools/*
+EXCLUDE_PATTERNS      += */customers/*
 
 # The EXCLUDE_SYMBOLS tag can be used to specify one or more symbol names
 # (namespaces, classes, functions, etc.) that should be excluded from the

LICENSE

@@ -1,5 +0,0 @@
-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

@@ -1,148 +1,24 @@
-<p align="center">
-<img width="400px" src="https://uploads-ssl.webflow.com/5e7ceb09657a69bdab054b3a/5e7ceb09657a6937ab054bba_Black_Original%20_Logo.png">
-</p>
+# memgraph
 
----
+Memgraph is an ACID compliant high performance transactional distributed
+in-memory graph database featuring runtime native query compiling, lock free
+data structures, multi-version concurrency control and asynchronous IO.
 
-<p align="center">
-Build modern, graph-based applications on top of your streaming data in minutes.
-</p>
+## dependencies
 
-<p align="center">
-  <a href="https://github.com/memgraph/memgraph/blob/master/licenses/APL.txt">
-    <img src="https://img.shields.io/badge/license-APL-green" alt="license" title="license"/>
-  </a>
-  <a href="https://github.com/memgraph/memgraph/blob/master/licenses/BSL.txt">
-    <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>
+Memgraph can be compiled using any modern c++ compiler. It mostly relies on
+the standard template library, however, some things do require external
+libraries.
 
-<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>
+Some code contains linux-specific libraries and the build is only supported
+on a 64 bit linux kernel.
 
-<p align="center">
-  <a href="https://memgr.ph/join-discord">
-    <img src="https://img.shields.io/badge/Discord-7289DA?style=for-the-badge&logo=discord&logoColor=white" alt="Discord"/>
-  </a>
-</p>
-
-## :clipboard: Description
-
-Memgraph is a streaming graph application platform that helps you wrangle your
-streaming data, build sophisticated models that you can query in real-time, and
-develop graph applications.
-
-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 is implemented in C/C++ and leverages an in-memory first architecture
-to ensure that you’re getting the best possible performance consistently and
-without surprises. It’s also ACID-compliant and highly available.
-
-## :video_game: Memgraph Playground
-
-You don't need to install anything to try out Memgraph. Check out 
-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>
+* linux
+* clang 3.8 (good c++11 support, especially lock free atomics)
+* antlr (compiler frontend)
+* cppitertools
+* fmt format
+* google benchmark
+* google test
+* glog
+* gflags

apollo_archives.py

@@ -0,0 +1,39 @@
+#!/usr/bin/env python3
+import json
+import os
+import re
+import subprocess
+import sys
+
+# paths
+SCRIPT_DIR = os.path.dirname(os.path.realpath(__file__))
+BUILD_OUTPUT_DIR = os.path.normpath(os.path.join(SCRIPT_DIR, "build_release", "output"))
+
+# helpers
+def run_cmd(cmd, cwd):
+    return subprocess.run(cmd, cwd=cwd, check=True,
+        stdout=subprocess.PIPE).stdout.decode("utf-8")
+
+# check project
+if re.search(r"release", os.environ.get("PROJECT", "")) is None:
+    print(json.dumps([]))
+    sys.exit(0)
+
+# generate archive
+deb_name = run_cmd(["find", ".", "-maxdepth", "1", "-type", "f",
+        "-name", "memgraph*.deb"], BUILD_OUTPUT_DIR).split("\n")[0][2:]
+arch = run_cmd(["dpkg", "--print-architecture"], BUILD_OUTPUT_DIR).split("\n")[0]
+version = deb_name.split("-")[1]
+# generate Debian package file name as expected by Debian Policy
+standard_deb_name = "memgraph_{}-1_{}.deb".format(version, arch)
+
+archive_path = os.path.relpath(os.path.join(BUILD_OUTPUT_DIR,
+        deb_name), SCRIPT_DIR)
+
+archives = [{
+    "name": "Release (deb package)",
+    "archive": archive_path,
+    "filename": standard_deb_name,
+}]
+
+print(json.dumps(archives, indent=4, sort_keys=True))

apollo_archives.yaml

@@ -0,0 +1,15 @@
+- name: Binaries
+  archive:
+    - build_debug/memgraph
+    - build_release/memgraph
+    - build_release/tools/src/mg_client
+    - build_release/tools/src/mg_import_csv
+    - config
+  filename: binaries.tar.gz
+
+- name: Doxygen documentation
+  cd: docs/doxygen/html
+  archive:
+    - .
+  filename: documentation.tar.gz
+  host: true

apollo_build.yaml

@@ -0,0 +1,94 @@
+- name: Diff build
+  project: ^mg-master-diff$
+  commands: |
+    # Activate toolchain
+    export PATH=/opt/toolchain-v1/bin:$PATH
+    export LD_LIBRARY_PATH=/opt/toolchain-v1/lib:/opt/toolchain-v1/lib64
+
+    # Copy untouched repository to parent folder.
+    cd ..
+    cp -r memgraph parent
+    cd memgraph
+
+    # Initialize and create documentation.
+    TIMEOUT=1200 ./init
+    doxygen Doxyfile
+
+    # Remove default build directory.
+    rm -r build
+
+    # Build debug binaries.
+    mkdir build_debug
+    cd build_debug
+    cmake ..
+    TIMEOUT=1200 make -j$THREADS
+
+    # Build coverage binaries.
+    cd ..
+    # TODO: uncomment this build once single node and ha are split
+    # mkdir build_coverage
+    # cd build_coverage
+    # cmake -DTEST_COVERAGE=ON ..
+    # TIMEOUT=1200 make -j$THREADS memgraph__unit
+    ln -s build_debug build_coverage
+
+    # Build release binaries.
+    # cd ..
+    mkdir build_release
+    cd build_release
+    cmake -DCMAKE_BUILD_TYPE=release ..
+    TIMEOUT=1200 make -j$THREADS
+    cd ..
+
+    # Checkout to parent commit and initialize.
+    cd ../parent
+    git checkout HEAD~1
+    TIMEOUT=1200 ./init
+
+    # Build parent release binaries.
+    mkdir build_release
+    cd build_release
+    cmake -DCMAKE_BUILD_TYPE=release ..
+    TIMEOUT=1200 make -j$THREADS memgraph memgraph__macro_benchmark
+
+
+# release build is the default one
+- name: Release build
+  commands: |
+    # Activate toolchain
+    export PATH=/opt/toolchain-v1/bin:$PATH
+    export LD_LIBRARY_PATH=/opt/toolchain-v1/lib:/opt/toolchain-v1/lib64
+
+    # Initialize and create documentation.
+    TIMEOUT=1200 ./init
+    doxygen Doxyfile
+
+    # Remove default build directory.
+    rm -r build
+
+    # Build debug binaries.
+    mkdir build_debug
+    cd build_debug
+    cmake ..
+    TIMEOUT=1200 make -j$THREADS
+
+    # Build coverage binaries.
+    cd ..
+    # TODO: uncomment this build once single node and ha are split
+    # mkdir build_coverage
+    # cd build_coverage
+    # cmake -DTEST_COVERAGE=ON ..
+    # TIMEOUT=1200 make -j$THREADS memgraph__unit
+    ln -s build_debug build_coverage
+
+    # Build release binaries.
+    # cd ..
+    mkdir build_release
+    cd build_release
+    cmake -DCMAKE_BUILD_TYPE=Release -DUSE_READLINE=OFF ..
+    TIMEOUT=1200 make -j$THREADS
+
+    # Create Debian package.
+    mkdir output
+    cd output
+    cpack -G DEB --config ../CPackConfig.cmake

cmake/FindJemalloc.cmake

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

@@ -39,22 +39,18 @@ modifications:
     value: "/var/log/memgraph/memgraph.log"
     override: true
 
-  - name: "log_level"
-    value: "WARNING"
+  - name: "bolt_cert_file"
+    value: "/etc/memgraph/ssl/cert.pem"
+    override: true
+
+  - name: "bolt_key_file"
+    value: "/etc/memgraph/ssl/key.pem"
     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
@@ -83,27 +79,23 @@ modifications:
     value: "true"
     override: true
 
-  # - name: "query_modules_directory"
-  #   value: "/usr/lib/memgraph/query_modules"
-  #   override: true
-
-  - name: "memory_limit"
-    value: "0"
+  - name: "query_modules_directory"
+    value: "/usr/lib/memgraph/query_modules"
     override: true
 
-  - name: "isolation_level"
-    value: "SNAPSHOT_ISOLATION"
-    override: true
-
-  - name: "allow_load_csv"
-    value: "true"
+  - name: "auth_module_executable"
+    value: "/usr/lib/memgraph/auth_module/example.py"
     override: false
 
 undocumented:
   - "flag_file"
-  - "also_log_to_stderr"
+  - "log_file_mode"
+  - "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"

customers/CMakeLists.txt

@@ -0,0 +1,2 @@
+project(mg_customers)
+add_subdirectory(otto)

customers/elliott/README_internal.md

@@ -0,0 +1,70 @@
+DISCLAIMER: this is just an initial test, graph might not resemble
+the graph in the use case at all and the data might be completely
+irrelevant.
+
+We tried generating a few sample graphs from the vague description
+given in the use case doc. Then we tried writing queries that would
+solve the problem of updating nodes when a leaf value changes,
+assuming all the internal nodes compute only the sum function.
+
+We start by creating an index on `id` property to improve initial lookup
+performance:
+
+    CREATE INDEX ON :Leaf(id)
+
+Set values of all leafs to 1:
+
+    MATCH (u:Leaf) SET u.value = 1
+
+Now we initialize the values of all other nodes in the graph:
+
+    MATCH (u) WHERE NOT u:Leaf SET u.value = 0
+
+    MATCH (u) WITH u
+    ORDER BY u.topological_index DESC
+    MATCH (u)-->(v) SET u.value = u.value + v.value
+
+Change the value of a leaf:
+
+    MATCH (u:Leaf {id: "18"}) SET u.value = 10
+
+We have to reset all the updated nodes to a neutral element:
+
+    MATCH (u:Leaf {id: "18"})<-[* bfs]-(v)
+    WHERE NOT v:Leaf SET v.value = 0
+
+Finally, we recalculate their values in topological order:
+
+    MATCH (u:Leaf {id: "18"})<-[* bfs]-(v)
+    WITH v ORDER BY v.topological_index DESC
+    MATCH (v)-->(w) SET v.value = v.value + w.value
+
+There are a few assumptions made worth pointing out.
+
+* We are able to efficiently maintain topological order
+  of vertices in the graph.
+
+* It is possible to accumulate the value of the function.  Formally: 
+  $$f(x_1, x_2, ..., x_n) = g(...(g(g(x_1, x_2), x_3), ...), x_n)$$
+
+* There is a neutral element for the operation. However, this
+  assumption can be dropped by introducing an artificial neutral element.
+
+Number of operations required is proportional to the sum of degrees of affected
+nodes.
+
+We generated graph with $10^5$ nodes ($20\ 000$ nodes in each layer),  varied the
+degree distribution in node layers and measured time for the query to execute:
+
+| # |  Root-Category-Group degree | Group-CustomGroup-Leaf degree |   Time    |
+|:-:|:---------------------------:|:-----------------------------:|:---------:|
+| 1 |            [1, 10]          |           [20, 40]            |   ~1.1s   |
+| 2 |            [1, 10]          |          [50, 100]            |   ~2.5s   |
+| 3 |           [10, 50]          |          [50, 100]            |   ~3.3s   |
+
+Due to the structure of the graph, update of a leaf required update of almost
+all the nodes in the graph so we don't show times required for initial graph
+update and update after leaf change separately.
+
+However, there is not enough info on the use case to make the test more
+sophisticated.

customers/elliott/README_public.md

@@ -0,0 +1,71 @@
+---
+title: "Elliott Management"
+subtitle: "Proof of Concept Report"
+header-title: "Elliott Management POC"
+date: 2017-10-28
+copyright: "©2017 Memgraph Ltd. All rights reserved."
+titlepage: true
+titlepage-color: FFFFFF
+titlepage-text-color: 101010
+titlepage-rule-color: 101010
+titlepage-rule-height: 1
+...
+
+# Introduction
+
+We tried generating a few sample graphs from the description given at
+the in-person meetings.  Then, we tried writing queries that would solve
+the problem of updating nodes when a leaf value changes, assuming all the
+internal nodes compute only the sum function.
+
+# Technical details
+
+We started by creating an index on `id` property to improve initial lookup
+performance:
+
+    CREATE INDEX ON :Leaf(id)
+
+Afther that, we set values of all leafs to 1:
+
+    MATCH (u:Leaf) SET u.value = 1
+
+We then initialized the values of all other nodes in the graph:
+
+    MATCH (u) WHERE NOT u:Leaf SET u.value = 0
+
+    MATCH (u) WITH u
+    ORDER BY u.topological_index DESC
+    MATCH (u)-->(v) SET u.value = u.value + v.value
+
+Leaf value change and update of affected values in the graph can
+be done using three queries. To change the value of a leaf:
+
+    MATCH (u:Leaf {id: "18"}) SET u.value = 10
+
+Then we had to reset all the affected nodes to the neutral element:
+
+    MATCH (u:Leaf {id: "18"})<-[* bfs]-(v)
+    WHERE NOT v:Leaf SET v.value = 0
+
+Finally, we recalculated their values in topological order:
+
+    MATCH (u:Leaf {id: "18"})<-[* bfs]-(v)
+    WITH v ORDER BY v.topological_index DESC
+    MATCH (v)-->(w) SET v.value = v.value + w.value
+
+There are a few assumptions necessary for the approach above to work.
+
+* We are able to maintain topological order of vertices during graph
+  structure changes.  
+
+* It is possible to accumulate the value of the function.  Formally: 
+  $$f(x_1, x_2, ..., x_n) = g(...(g(g(x_1, x_2), x_3), ...), x_n)$$
+
+* There is a neutral element for the operation. However, this
+  assumption can be dropped by introducing an artificial neutral element.
+
+Above assumptions could be changed, relaxed or dropped, depending on the
+specifics of the use case.
+
+Number of operations required is proportional to the sum of degrees of affected
+nodes. 

customers/elliott/commands.txt

@@ -0,0 +1,12 @@
+CREATE INDEX ON :Leaf(id);
+MATCH (u:Leaf) SET u.value = 1;
+MATCH (u) WHERE NOT u:Leaf SET u.value = 0;
+MATCH (u) WITH u 
+ORDER BY u.topological_index DESC
+MATCH (u)-->(v) SET u.value = u.value + v.value;
+MATCH (u:Leaf {id: "85000"}) SET u.value = 10;
+MATCH (u:Leaf {id: "85000"})<-[* bfs]-(v) 
+WHERE NOT v:Leaf SET v.value = 0;
+MATCH (u:Leaf {id: "85000"})<-[* bfs]-(v)
+WITH v ORDER BY v.topological_index DESC
+MATCH (v)-->(w) SET v.value = v.value + w.value;

customers/elliott/generate_dag

@@ -0,0 +1,125 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""Generates a DAG from JSON spec in [config] and outputs nodes to
+[filename]_nodes, and edges to [filename]_edges in format convertible
+to Memgraph snapshot.
+
+Here's an example JSON spec:
+
+    {
+        "layers": [
+            {
+                "name": "A",
+                "sublayers": 1,
+                "degree_lo": 1,
+                "degree_hi": 3,
+                "nodes": 4
+            },
+            {
+                "name": "B",
+                "sublayers": 3,
+                "degree_lo": 2,
+                "degree_hi": 3,
+                "nodes": 10
+            },
+            {
+                "name": "C",
+                "sublayers": 1,
+                "degree_lo": 1,
+                "degree_hi": 1,
+                "nodes": 5
+            }
+        ]
+    }
+
+Nodes from each layer will be randomly divided into sublayers.  A node can
+only have edges pointing to nodes in lower sublayers of the same layer, or
+to nodes from the layer directly below it. Out-degree is chosen uniformly
+random from [degree_lo, degree_hi] interval."""
+
+import argparse
+from itertools import accumulate
+import json
+import random
+
+
+def _split_into_sum(n, k):
+    assert 1 <= n, "n should be at least 1"
+    assert k <= n, "k shouldn't be greater than n"
+    xs = [0] + sorted(random.sample(range(1, n), k-1)) + [n]
+    return [b - a for a, b in zip(xs, xs[1:])]
+
+
+def generate_dag(graph_config, seed=None):
+    random.seed(seed)
+
+    nodes = []
+    edges = []
+
+    layer_lo = 1
+    for layer in graph_config:
+        sublayers = _split_into_sum(layer['nodes'], layer['sublayers'])
+        sub_range = accumulate([layer_lo] + sublayers)
+        layer['sublayer_range'] = list(sub_range)
+        nodes.extend([
+            (u, layer['name'])
+            for u in range(layer_lo, layer_lo + layer['nodes'])
+        ])
+        layer_lo += layer['nodes']
+
+    edges = []
+
+    for layer, next_layer in zip(graph_config, graph_config[1:]):
+        degree_lo = layer['degree_lo']
+        degree_hi = layer['degree_hi']
+
+        sub_range = layer['sublayer_range']
+        sub_range_next = next_layer['sublayer_range']
+
+        layer_lo = sub_range[0]
+        next_layer_hi = sub_range_next[-1]
+
+        for sub_lo, sub_hi in zip(sub_range, sub_range[1:]):
+            for u in range(sub_lo, sub_hi):
+                num_edges = random.randint(degree_lo, degree_hi)
+                for _ in range(num_edges):
+                    v = random.randint(sub_hi, next_layer_hi - 1)
+                    edges.append((u, v))
+
+        for sub_lo, sub_hi in zip(sub_range_next, sub_range_next[1:]):
+            for u in range(sub_lo, sub_hi):
+                v = random.randint(layer_lo, sub_lo - 1)
+                edges.append((v, u))
+
+    return nodes, edges
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        description=__doc__)
+    parser.add_argument('config', type=str, help='graph config JSON file')
+    parser.add_argument('filename', type=str,
+                        help='nodes will be stored to filename_nodes, '
+                        'edges to filename_edges')
+    parser.add_argument('--seed', type=int,
+                        help='seed for the random generator (default = '
+                        'current system time)')
+    args = parser.parse_args()
+
+    with open(args.config, 'r') as f:
+        graph_config = json.loads(f.read())['layers']
+
+    nodes, edges = generate_dag(graph_config, seed=args.seed)
+
+    #  print nodes into CSV file
+    with open('{}_nodes'.format(args.filename), 'w') as out:
+        out.write('nodeId:ID(Node),name,topological_index:Int,:LABEL\n')
+        for node_id, layer in nodes:
+            out.write('{0},{1}{0},{0},{1}\n'.format(node_id, layer))
+
+    # print edges into CSV file
+    with open('{}_edges'.format(args.filename), 'w') as out:
+        out.write(':START_ID(Node),:END_ID(Node),:TYPE\n')
+        for u, v in edges:
+            out.write('{},{},child\n'.format(u, v))

customers/elliott/graph1.json

@@ -0,0 +1,39 @@
+{
+    "layers": [
+        { 
+            "name": "Root",
+            "sublayers": 1,
+            "degree_lo": 1,
+            "degree_hi": 10,
+            "nodes": 20000
+        },
+        { 
+            "name": "Category",
+            "sublayers": 5,
+            "degree_lo": 1,
+            "degree_hi": 10,
+            "nodes": 20000
+        },
+        {   
+            "name": "Group",
+            "sublayers": 1,
+            "degree_lo": 20,
+            "degree_hi": 40,
+            "nodes": 20000
+        },
+        {
+            "name": "CustomGroup",
+            "sublayers": 15,
+            "degree_lo": 20,
+            "degree_hi": 40,
+            "nodes": 20000
+        },
+        { 
+            "name": "Leaf",
+            "sublayers": 1,
+            "degree_lo": 1,
+            "degree_hi": 1,
+            "nodes": 20000
+        }
+    ]
+}

customers/elliott/graph2.json

@@ -0,0 +1,39 @@
+{
+    "layers": [
+        { 
+            "name": "Root",
+            "sublayers": 1,
+            "degree_lo": 1,
+            "degree_hi": 10,
+            "nodes": 20000
+        },
+        { 
+            "name": "Category",
+            "sublayers": 5,
+            "degree_lo": 1,
+            "degree_hi": 10,
+            "nodes": 20000
+        },
+        {   
+            "name": "Group",
+            "sublayers": 1,
+            "degree_lo": 50,
+            "degree_hi": 100,
+            "nodes": 20000
+        },
+        {
+            "name": "CustomGroup",
+            "sublayers": 15,
+            "degree_lo": 50,
+            "degree_hi": 100,
+            "nodes": 20000
+        },
+        { 
+            "name": "Leaf",
+            "sublayers": 1,
+            "degree_lo": 50,
+            "degree_hi": 100,
+            "nodes": 20000
+        }
+    ]
+}

customers/elliott/graph3.json

@@ -0,0 +1,39 @@
+{
+    "layers": [
+        { 
+            "name": "Root",
+            "sublayers": 1,
+            "degree_lo": 10,
+            "degree_hi": 50,
+            "nodes": 20000
+        },
+        { 
+            "name": "Category",
+            "sublayers": 5,
+            "degree_lo": 10,
+            "degree_hi": 50,
+            "nodes": 20000
+        },
+        {   
+            "name": "Group",
+            "sublayers": 1,
+            "degree_lo": 50,
+            "degree_hi": 100,
+            "nodes": 20000
+        },
+        {
+            "name": "CustomGroup",
+            "sublayers": 15,
+            "degree_lo": 50,
+            "degree_hi": 100,
+            "nodes": 20000
+        },
+        { 
+            "name": "Leaf",
+            "sublayers": 1,
+            "degree_lo": 50,
+            "degree_hi": 100,
+            "nodes": 20000
+        }
+    ]
+}

customers/otto/CMakeLists.txt

@@ -0,0 +1,3 @@
+set(exec_name customers_otto_parallel_connected_components)
+add_executable(${exec_name} parallel_connected_components.cpp)
+target_link_libraries(${exec_name} memgraph_lib)

customers/otto/connected_components_test.py

@@ -0,0 +1,118 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+"""
+This script attempts to evaluate the feasibility of using Memgraph for
+Otto group's usecase. The usecase is finding connected componentes in
+a large, very sparse graph (cca 220M nodes, 250M edges), based on a dynamic
+inclusion / exclusion of edges (w.r.t variable parameters and the source node
+type).
+
+This implementation defines a random graph with the given number of nodes
+and edges and looks for connected components using breadth-first expansion.
+Edges are included / excluded based on a simple expression, only demonstrating
+possible usage.
+"""
+
+from argparse import ArgumentParser
+import logging
+from time import time
+from collections import defaultdict
+from math import log2
+from random import randint
+
+from neo4j.v1 import GraphDatabase
+
+log = logging.getLogger(__name__)
+
+
+def generate_graph(sess, node_count, edge_count):
+    # An index that will speed-up edge creation.
+    sess.run("CREATE INDEX ON :Node(id)").consume()
+
+    # Create the given number of nodes with a randomly selected type from:
+    # [0.5, 1.5, 2.5].
+    sess.run(("UNWIND range(0, {} - 1) AS id CREATE "
+              "(:Node {{id: id, type: 0.5 + tointeger(rand() * 3)}})").format(
+                 node_count)).consume()
+
+    # Create the given number of edges, each with a 'value' property of
+    # a random [0, 3.0) float. Each edge connects two random nodes, so the
+    # expected node degree is (edge_count * 2 / node_count). Generate edges
+    # so the connectivity is non-uniform (to produce connected components of
+    # various sizes).
+    sess.run(("UNWIND range(0, {0} - 1) AS id WITH id "
+              "MATCH (from:Node {{id: tointeger(rand() * {1})}}), "
+              "(to:Node {{id: tointeger(rand() * {1} * id / {0})}}) "
+              "CREATE (from)-[:Edge {{value: 3 * rand()}}]->(to)").format(
+                 edge_count, node_count)).consume()
+
+
+def get_connected_ids(sess, node_id):
+    # Matches a node with the given ID and returns the IDs of all the nodes
+    # it is connected to. Note that within the BFS lambda expression there
+    # is an expression used to filter out edges expanded over.
+    return sess.run((
+        "MATCH (from:Node {{id: {}}})-"
+        "[*bfs (e, n | abs(from.type - e.value) < 0.80)]-(d) "
+        "RETURN count(*) AS c").format(node_id)).data()[0]['c']
+
+
+def parse_args():
+    parser = ArgumentParser(description=__doc__)
+    parser.add_argument('--endpoint', type=str, default='localhost:7687',
+                        help='Memgraph instance endpoint. ')
+    parser.add_argument('--node-count', type=int, default=1000,
+                        help='The number of nodes in the graph')
+    parser.add_argument('--edge-count', type=int, default=1000,
+                        help='The number of edges in the graph')
+    parser.add_argument('--sample-count', type=int, default=None,
+                        help='The number of samples to take')
+    return parser.parse_args()
+
+
+def main():
+    args = parse_args()
+    logging.basicConfig(level=logging.INFO)
+    log.info("Memgraph - Otto test database generator")
+    logging.getLogger("neo4j").setLevel(logging.WARNING)
+
+    driver = GraphDatabase.driver(
+        'bolt://' + args.endpoint,
+        auth=("ignored", "ignored"),
+        encrypted=False)
+    sess = driver.session()
+
+    sess.run("MATCH (n) DETACH DELETE n").consume()
+
+    log.info("Generating graph with %s nodes and %s edges...",
+             args.node_count, args.edge_count)
+    generate_graph(sess, args.node_count, args.edge_count)
+
+    # Track which vertices have been found as part of a component.
+    start_time = time()
+    max_query_time = 0
+    log.info("Looking for connected components...")
+    # Histogram of log2 sizes of connected components found.
+    histogram = defaultdict(int)
+    sample_count = args.sample_count if args.sample_count else args.node_count
+    for i in range(sample_count):
+        node_id = randint(0, args.node_count - 1)
+        query_start_time = time()
+        log2_size = int(log2(1 + get_connected_ids(sess, node_id)))
+        max_query_time = max(max_query_time, time() - query_start_time)
+        histogram[log2_size] += 1
+    elapsed = time() - start_time
+    log.info("Connected components found in %.2f sec (avg %.2fms, max %.2fms)",
+             elapsed, elapsed / sample_count * 1000, max_query_time * 1000)
+    log.info("Component size histogram (count | range)")
+    for log2_size, count in sorted(histogram.items()):
+        log.info("\t%5d | %d - %d", count, 2 ** log2_size,
+                 2 ** (log2_size + 1) - 1)
+
+    sess.close()
+    driver.close()
+
+
+if __name__ == '__main__':
+    main()

customers/otto/parallel_connected_components.cpp

@@ -0,0 +1,207 @@
+#include <algorithm>
+#include <limits>
+#include <mutex>
+#include <random>
+#include <set>
+#include <stack>
+#include <thread>
+
+#include "gflags/gflags.h"
+#include "glog/logging.h"
+
+#include "data_structures/union_find.hpp"
+#include "database/graph_db.hpp"
+#include "database/graph_db_accessor.hpp"
+#include "storage/property_value.hpp"
+#include "threading/sync/spinlock.hpp"
+#include "utils/bound.hpp"
+#include "utils/timer.hpp"
+
+DEFINE_int32(thread_count, 1, "Number of threads");
+DEFINE_int32(vertex_count, 1000, "Number of vertices");
+DEFINE_int32(edge_count, 1000, "Number of edges");
+DECLARE_int32(gc_cycle_sec);
+
+static const std::string kLabel{"kLabel"};
+static const std::string kProperty{"kProperty"};
+
+void GenerateGraph(database::GraphDb &db) {
+  {
+    database::GraphDbAccessor dba{db};
+    dba.BuildIndex(dba.Label(kLabel), dba.Property(kProperty));
+    dba.Commit();
+  }
+
+  // Randomize the sequence of IDs of created vertices and edges to simulate
+  // real-world lack of locality.
+  auto make_id_vector = [](size_t size) {
+    gid::Generator generator{0};
+    std::vector<gid::Gid> ids(size);
+    for (size_t i = 0; i < size; ++i)
+      ids[i] = generator.Next(std::experimental::nullopt);
+    std::random_shuffle(ids.begin(), ids.end());
+    return ids;
+  };
+
+  std::vector<VertexAccessor> vertices;
+  vertices.reserve(FLAGS_vertex_count);
+  {
+    CHECK(FLAGS_vertex_count % FLAGS_thread_count == 0)
+        << "Thread count must be a factor of vertex count";
+    LOG(INFO) << "Generating " << FLAGS_vertex_count << " vertices...";
+    utils::Timer timer;
+    auto vertex_ids = make_id_vector(FLAGS_vertex_count);
+
+    std::vector<std::thread> threads;
+    SpinLock vertices_lock;
+    for (int i = 0; i < FLAGS_thread_count; ++i) {
+      threads.emplace_back([&db, &vertex_ids, &vertices, &vertices_lock, i]() {
+        database::GraphDbAccessor dba{db};
+        auto label = dba.Label(kLabel);
+        auto property = dba.Property(kProperty);
+        auto batch_size = FLAGS_vertex_count / FLAGS_thread_count;
+        for (int j = i * batch_size; j < (i + 1) * batch_size; ++j) {
+          auto vertex = dba.InsertVertex(vertex_ids[j]);
+          vertex.add_label(label);
+          vertex.PropsSet(property, static_cast<int64_t>(vertex_ids[j]));
+          vertices_lock.lock();
+          vertices.emplace_back(vertex);
+          vertices_lock.unlock();
+        }
+        dba.Commit();
+      });
+    }
+    for (auto &t : threads) t.join();
+    LOG(INFO) << "Generated " << FLAGS_vertex_count << " vertices in "
+              << timer.Elapsed().count() << " seconds.";
+  }
+  {
+    database::GraphDbAccessor dba{db};
+    for (int i = 0; i < FLAGS_vertex_count; ++i)
+      vertices[i] = *dba.Transfer(vertices[i]);
+
+    LOG(INFO) << "Generating " << FLAGS_edge_count << " edges...";
+    auto edge_ids = make_id_vector(FLAGS_edge_count);
+    std::mt19937 pseudo_rand_gen{std::random_device{}()};
+    std::uniform_int_distribution<> rand_dist{0, FLAGS_vertex_count - 1};
+    auto edge_type = dba.EdgeType("edge");
+    utils::Timer timer;
+    for (int i = 0; i < FLAGS_edge_count; ++i)
+      dba.InsertEdge(vertices[rand_dist(pseudo_rand_gen)],
+                     vertices[rand_dist(pseudo_rand_gen)], edge_type,
+                     edge_ids[i]);
+    dba.Commit();
+    LOG(INFO) << "Generated " << FLAGS_edge_count << " edges in "
+              << timer.Elapsed().count() << " seconds.";
+  }
+}
+
+auto EdgeIteration(database::GraphDb &db) {
+  database::GraphDbAccessor dba{db};
+  int64_t sum{0};
+  for (auto edge : dba.Edges(false)) sum += edge.from().gid() + edge.to().gid();
+  return sum;
+}
+
+auto VertexIteration(database::GraphDb &db) {
+  database::GraphDbAccessor dba{db};
+  int64_t sum{0};
+  for (auto v : dba.Vertices(false))
+    for (auto e : v.out()) sum += e.gid() + e.to().gid();
+  return sum;
+}
+
+auto ConnectedComponentsEdges(database::GraphDb &db) {
+  UnionFind<int64_t> connectivity{FLAGS_vertex_count};
+  database::GraphDbAccessor dba{db};
+  for (auto edge : dba.Edges(false))
+    connectivity.Connect(edge.from().gid(), edge.to().gid());
+  return connectivity.Size();
+}
+
+auto ConnectedComponentsVertices(database::GraphDb &db) {
+  UnionFind<int64_t> connectivity{FLAGS_vertex_count};
+  database::GraphDbAccessor dba{db};
+  for (auto from : dba.Vertices(false)) {
+    for (auto out_edge : from.out())
+      connectivity.Connect(from.gid(), out_edge.to().gid());
+  }
+  return connectivity.Size();
+}
+
+auto ConnectedComponentsVerticesParallel(database::GraphDb &db) {
+  UnionFind<int64_t> connectivity{FLAGS_vertex_count};
+  SpinLock connectivity_lock;
+
+  // Define bounds of vertex IDs for each thread to use.
+  std::vector<PropertyValue> bounds;
+  for (int64_t i = 0; i < FLAGS_thread_count; ++i)
+    bounds.emplace_back(i * FLAGS_vertex_count / FLAGS_thread_count);
+  bounds.emplace_back(std::numeric_limits<int64_t>::max());
+
+  std::vector<std::thread> threads;
+  for (int i = 0; i < FLAGS_thread_count; ++i) {
+    threads.emplace_back(
+        [&connectivity, &connectivity_lock, &bounds, &db, i]() {
+          database::GraphDbAccessor dba{db};
+          for (auto from :
+               dba.Vertices(dba.Label(kLabel), dba.Property(kProperty),
+                            utils::MakeBoundInclusive(bounds[i]),
+                            utils::MakeBoundExclusive(bounds[i + 1]), false)) {
+            for (auto out_edge : from.out()) {
+              std::lock_guard<SpinLock> lock{connectivity_lock};
+              connectivity.Connect(from.gid(), out_edge.to().gid());
+            }
+          }
+        });
+  }
+  for (auto &t : threads) t.join();
+  return connectivity.Size();
+}
+
+auto Expansion(database::GraphDb &db) {
+  std::vector<int> component_ids(FLAGS_vertex_count, -1);
+  int next_component_id{0};
+  std::stack<VertexAccessor> expansion_stack;
+  database::GraphDbAccessor dba{db};
+  for (auto v : dba.Vertices(false)) {
+    if (component_ids[v.gid()] != -1) continue;
+    auto component_id = next_component_id++;
+    expansion_stack.push(v);
+    while (!expansion_stack.empty()) {
+      auto next_v = expansion_stack.top();
+      expansion_stack.pop();
+      if (component_ids[next_v.gid()] != -1) continue;
+      component_ids[next_v.gid()] = component_id;
+      for (auto e : next_v.out()) expansion_stack.push(e.to());
+      for (auto e : next_v.in()) expansion_stack.push(e.from());
+    }
+  }
+
+  return next_component_id;
+}
+
+int main(int argc, char **argv) {
+  gflags::ParseCommandLineFlags(&argc, &argv, true);
+  google::InitGoogleLogging(argv[0]);
+  FLAGS_gc_cycle_sec = -1;
+
+  database::SingleNode db;
+  GenerateGraph(db);
+  auto timed_call = [&db](auto callable, const std::string &descr) {
+    LOG(INFO) << "Running " << descr << "...";
+    utils::Timer timer;
+    auto result = callable(db);
+    LOG(INFO) << "\tDone in " << timer.Elapsed().count()
+              << " seconds, result: " << result;
+  };
+  timed_call(EdgeIteration, "Edge iteration");
+  timed_call(VertexIteration, "Vertex iteration");
+  timed_call(ConnectedComponentsEdges, "Connected components - Edges");
+  timed_call(ConnectedComponentsVertices, "Connected components - Vertices");
+  timed_call(ConnectedComponentsVerticesParallel,
+             "Parallel connected components - Vertices");
+  timed_call(Expansion, "Expansion");
+
+  return 0;
+}

customers/ravelin/fraud_detection.oc

@@ -0,0 +1,5 @@
+WITH tointeger(rand() * 40000000) AS from_id
+MATCH (from:Node {id : from_id}) WITH from
+MATCH path = (from)-[*bfs..50 (e, n | degree(n) < 50)]->(to) WITH path LIMIT 10000 WHERE to.fraudulent
+RETURN path, size(path)
+

customers/ravelin/snapshot_gen_config.json

@@ -0,0 +1,31 @@
+{
+   "indexes":[
+      "Node.id"
+   ],
+   "nodes":[
+      {
+         "count":40000000,
+         "labels":[
+            "Node"
+         ],
+         "properties":{
+            "id":{
+               "type":"counter",
+               "param":"Node.id"
+            },
+            "fraudulent":{
+               "type":"bernoulli",
+               "param":0.0005
+            }
+         }
+      }
+   ],
+   "edges":[
+      {
+         "count":80000000,
+         "from":"Node",
+         "to":"Node",
+         "type":"Edge"
+      }
+   ]
+}

customers/strata2018/card_fraud_config.json

@@ -0,0 +1,20 @@
+{
+  "indexes" : ["Card.id", "Pos.id", "Transaction.fraud_reported"],
+  "nodes" : [
+    {
+      "count_per_worker" : 1250000,
+      "label" : "Card"
+    },
+    {
+      "count_per_worker" : 1250000,
+      "label" : "Pos"
+    },
+    {
+      "count_per_worker" : 2500000,
+      "label" : "Transaction"
+    }
+  ],
+  "compromised_pos_probability" : 0.2,
+  "fraud_reported_probability" : 0.1,
+  "hop_probability" : 0.1
+}

docs/dev/code-review.md

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

docs/dev/cpp-code-conventions.md

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

docs/dev/diagram/dependencies.dot

@@ -0,0 +1,288 @@
+// dot -Tpng dependencies.dot -o /path/to/output.png
+
+// TODO (buda): Put PropertyValueStore to storage namespace
+
+digraph {
+  // At the beginning of each block there is a default style for that block
+  label="Memgraph Dependencies Diagram"; fontname="Roboto Bold"; fontcolor=black;
+    fontsize=26; labelloc=top; labeljust=right;
+  compound=true; // If true, allow edges between clusters
+  rankdir=TB; // Alternatives: LR
+  node [shape=record fontname="Roboto", fontsize=12, fontcolor=white];
+  edge [color="#B5AFB7"];
+
+  // -- Legend --
+  // dir=both arrowtail=diamond arrowhead=vee -> group ownership
+  // dir=both arrowtail=none, arrowhead=vee -> ownership; stack or uptr
+
+  subgraph cluster_tcp_end_client_communication {
+    label="TCP End Client Communication"; fontsize=14;
+    node [style=filled, color="#DD2222" fillcolor="#DD2222"];
+
+    // Owned elements
+    "communication::Server";
+    "io::network::Socket";
+
+    // Intracluster connections
+    "communication::Server" -> "io::network::Socket"
+      [label="socket_" dir=both arrowtail=none arrowhead=vee];
+  }
+
+  subgraph cluster_bolt_server {
+    label="Bolt Server"; fontsize=14;
+    node [style=filled, color="#62A2CA" fillcolor="#62A2CA"];
+
+    // Owned elements
+    "communication::bolt::SessionData";
+    "communication::bolt::Session";
+    "communication::bolt::Encoder";
+    "communication::bolt::Decoder";
+
+    // Intracluster connections
+    "communication::bolt::Session" -> "communication::bolt::Encoder"
+      [label="encoder_", dir=both arrowtail=none, arrowhead=vee];
+    "communication::bolt::Session" -> "communication::bolt::Decoder"
+      [label="decoder_", dir=both arrowtail=none, arrowhead=vee];
+  }
+
+  subgraph cluster_opencypher_engine {
+    label="openCypher Engine"; fontsize=14;
+    node [style=filled, color="#68BDF6" fillcolor="#68BDF6"];
+
+    // Owned Elements
+    "query::Interpreter";
+    "query::AstTreeStorage";
+    "query::TypedValue"
+    "query::Path";
+    "query::Simbol";
+    "query::Context";
+    "query::ExpressionEvaluator";
+    "query::Frame";
+    "query::SymbolTable";
+    "query::plan::LogicalOperator";
+    "query::plan::Cursor";
+    "query::plan::CostEstimator";
+
+    // Intracluster connections
+    "query::Interpreter" -> "query::AstTreeStorage"
+      [label="ast_cache" dir=both arrowtail=diamond arrowhead=vee];
+    "query::TypedValue" -> "query::Path";
+    "query::plan::Cursor" -> "query::Frame";
+    "query::plan::Cursor" -> "query::Context";
+    "query::plan::LogicalOperator" -> "query::Symbol";
+    "query::plan::LogicalOperator" -> "query::SymbolTable";
+    "query::plan::LogicalOperator" -> "query::plan::Cursor";
+  }
+
+
+  subgraph cluster_storage {
+    label="Storage" fontsize=14;
+    node [style=filled, color="#FB6E00" fillcolor="#FB6E00"];
+
+    // Owned Elements
+    "database::GraphDb";
+    "database::GraphDbAccessor";
+    "storage::Record";
+    "storage::Vertex";
+    "storage::Edge";
+    "storage::RecordAccessor";
+    "storage::VertexAccessor";
+    "storage::EdgeAccessor";
+    "storage::Common";
+    "storage::Label";
+    "storage::EdgeType";
+    "storage::Property";
+    "storage::compression";
+    "storage::SingleNodeConcurrentIdMapper";
+    "storage::Location";
+    "storage::StorageTypesLocation";
+    "PropertyValueStore";
+    "storage::RecordLock";
+    "mvcc::Version";
+    "mvcc::Record";
+    "mvcc::VersionList";
+
+    // Intracluster connections
+    "storage::VertexAccessor" -> "storage::RecordAccessor"
+      [arrowhead=onormal];
+    "storage::EdgeAccessor" -> "storage::RecordAccessor"
+      [arrowhead=onormal];
+    "storage::RecordAccessor" -> "database::GraphDbAccessor"
+      [style=dashed arrowhead=vee];
+    "storage::Vertex" -> "mvcc::Record"
+      [arrowhead=onormal];
+    "storage::Edge" -> "mvcc::Record"
+      [arrowhead=onormal];
+    "storage::Edge" -> "PropertyValueStore"
+      [arrowhead=vee];
+    "storage::Vertex" -> "PropertyValueStore"
+      [arrowhead=vee];
+    "storage::Edge" -> "mvcc::VersionList"
+      [label="from,to" arrowhead=vee style=dashed];
+    "storage::VertexAccessor" -> "storage::Vertex"
+      [arrowhead=vee];
+    "storage::EdgeAccessor" -> "storage::Edge"
+      [arrowhead=vee];
+    "storage::SingleNodeConcurrentIdMapper" -> "storage::StorageTypesLocation"
+      [arrowhead=vee];
+    "storage::StorageTypesLocation" -> "storage::Location"
+      [arrowhead=vee];
+    "storage::Storage" -> "storage::StorageTypesLocation"
+      [arrowhead=vee];
+    "storage::Property" -> "storage::Common"
+      [arrowhead=onormal];
+    "storage::Label" -> "storage::Common"
+      [arrowhead=onormal];
+    "storage::EdgeType" -> "storage::Common"
+      [arrowhead=onormal];
+    "storage::Property" -> "storage::Location"
+      [arrowhead=vee];
+    "PropertyValueStore" -> "storage::Property"
+      [arrowhead=vee];
+    "PropertyValueStore" -> "storage::Location"
+      [arrowhead=vee];
+    "database::GraphDbAccessor" -> "database::GraphDb"
+      [arrowhead=vee];
+    "database::GraphDbAccessor" -> "tx::TransactionId"
+      [arrowhead=vee];
+    "mvcc::VersionList" -> "storge::RecordLock"
+      [label="lock" arrowhead=vee];
+    "mvcc::VersionList" -> "mvcc::Record"
+      [label="head" arrowhead=vee];
+    "mvcc::Record" -> "mvcc::Version"
+      [arrowhead=onormal];
+
+    // Explicit positioning
+    {rank=same;
+        "database::GraphDbAccessor";
+        "storage::VertexAccessor";
+        "storage::EdgeAccessor";}
+    {rank=same;
+        "storage::Common";
+        "storage::compression";}
+  }
+
+  subgraph cluster_properties_on_disk {
+    label="Properties on Disk" fontsize=14;
+    node [style=filled, color="#102647" fillcolor="#102647"];
+
+    // Owned Elements
+    "storage::KVStore";
+    "rocksdb";
+
+    // Intracluster connections
+    "storage::KVStore" -> "rocksdb";
+  }
+
+  subgraph cluster_distributed {
+    label="Distributed" fontsize=14;
+    node [style=filled, color="#FFC500" fillcolor="#FFC500"];
+
+    // Owned Elements
+    "distributed::DataManager";
+    "distributed::DataRpcClients";
+
+    // Intracluster connections
+    "distributed::DataManager" -> "distributed::DataRpcClients"
+      [arrowhead=vee];
+    "storage::RecordAccessor" -> "distributed::DataManager"
+      [style=dashed arrowhead=vee];
+  }
+
+  subgraph cluster_dynamic_partitioning {
+    label="Dynamic Partitioning" fontsize=14;
+    node [style=filled, color="#720096" fillcolor="#720096"];
+
+    // Owned Elements
+    "DynamicPartitioner";
+  }
+
+  subgraph cluster_security {
+    label="Security" fontsize=14;
+    node [style=filled, color="#857F87" fillcolor="#857F87"];
+
+    // Owned Elements
+    "Communication Encryption";
+    "Data Encryption";
+    "Access Control";
+    "Audit Logging";
+  }
+
+  subgraph cluster_web_dashboard {
+    label="Dashaboard" fontsize=14;
+    node [style=filled, color="#FF0092" fillcolor="#FF0092"];
+
+    // Owned Elements
+    "Memgraph Ops / Memgraph Cockpit";
+  }
+
+  subgraph cluster_rpc {
+    label="RPC" fontsize=14;
+    node [style=filled, color="#857F87" fillcolor="#857F87"];
+
+    // Owned Elements
+    "communication::rpc::Server";
+    "communication::rpc::Client";
+  }
+
+  subgraph cluster_ingestion {
+    label="Ingestion" fontsize=14;
+    node [style=filled, color="#0B6D88" fillcolor="#0B6D88"];
+
+    // Owned Elements
+    "Extract";
+    "Transform";
+    "Load";
+    "Amazon S3";
+    "Kafka";
+
+    // Intracluster connections
+    "Extract" -> "Amazon S3";
+    "Extract" -> "Kafka";
+
+    // Explicit positioning
+    {rank=same;"Extract";"Transform";"Load";}
+  }
+
+  // -- Intercluster connections --
+  // cluster_tcp_end_client_communication -- cluster_bolt_server
+  "communication::Server" -> "communication::bolt::SessionData" [color=black];
+  "communication::Server" -> "communication::bolt::Session" [color=black];
+  // cluster_bolt_server -> cluster_storage
+  "communication::bolt::SessionData" -> "database::GraphDb" [color=red];
+  "communication::bolt::Session" -> "database::GraphDbAccessor" [color=red];
+  // cluster_bolt_server -> cluster_opencypher_engine
+  "communication::bolt::SessionData" -> "query::Interpreter" [color=red];
+  // cluster_opencypher_engine -- cluster_storage
+  "query::Interpreter" -> "database::GraphDbAccessor" [color=black];
+  "query::Interpreter" -> "storage::VertexAccessor" [color=black];
+  "query::Interpreter" -> "storage::EdgeAccessor" [color=black];
+  "query::TypedValue" -> "storage::VertexAccessor" [color=black];
+  "query::TypedValue" -> "storage::EdgeAccessor" [color=black];
+  "query::Path" -> "storage::VertexAccessor"
+    [label="vertices" dir=both arrowtail=diamond arrowhead=vee color=black];
+  "query::Path" -> "storage::EdgeAccessor"
+    [label="edges" dir=both arrowtail=diamond arrowhead=vee color=black];
+  "query::plan::LogicalOperator" -> "database::GraphDbAccessor"
+    [color=black arrowhead=vee];
+  // cluster_distributed -- cluster_storage
+  "distributed::DataManager" -> "database::GraphDb"
+    [arrowhead=vee style=dashed color=red];
+  "distributed::DataManager" -> "tx::TransactionId"
+    [label="ves_caches_key" dir=both arrowhead=none arrowtail=diamond
+     color=red];
+  "distributed::DataManager" -> "storage::Vertex"
+    [label="vertices_caches" dir=both arrowhead=none arrowtail=diamond
+     color=red];
+  "distributed::DataManager" -> "storage::Edge"
+    [label="edges_caches" dir=both arrowhead=none arrowtail=diamond
+     color=red];
+  // cluster_storage -- cluster_properties_on_disk
+  "PropertyValueStore" -> "storage::KVStore"
+    [label="static" arrowhead=vee color=black];
+  // cluster_dynamic_partitioning -- cluster_storage
+  "database::GraphDb" -> "DynamicPartitioner"
+    [arrowhead=vee color=red];
+  "DynamicPartitioner" -> "database::GraphDbAccessor"
+    [arrowhead=vee color=black];
+}

docs/dev/diagram/dgp/logical.dot

@@ -0,0 +1,22 @@
+digraph {
+  // label="Dynamig Graph Partitioning";
+  fontname="Roboto Bold"; fontcolor=black;
+    fontsize=26; labelloc=top; labeljust=center;
+  compound=true; // If true, allow edges between clusters
+  rankdir=TB; // Alternatives: LR
+  node [shape=record fontname="Roboto", fontsize=12, fontcolor=white
+        style=filled, color="#FB6E00" fillcolor="#FB6E00"];
+  edge [color="#B5AFB7"];
+
+  "distributed::DistributedGraphDb" -> "distributed::TokenSharingRpcServer";
+
+  "distributed::TokenSharingRpcServer" -> "communication::rpc::Server";
+  "distributed::TokenSharingRpcServer" -> "distributed::Coordination";
+  "distributed::TokenSharingRpcServer" -> "distributed::TokenSharingRpcClients";
+  "distributed::TokenSharingRpcServer" -> "distributed::dgp::Partitioner";
+
+  "distributed::dgp::Partitioner" -> "distributed::DistributedGraphDb" [style=dashed];
+
+  "distributed::dgp::Partitioner" -> "distributed::dgp::VertexMigrator";
+  "distributed::dgp::VertexMigrator" -> "database::GraphDbAccessor" [style=dashed];
+}

docs/dev/distributed/addressing.md

@@ -0,0 +1,43 @@
+# Distributed addressing
+
+In distributed Memgraph a single graph element must be owned by exactly
+one worker. It is possible that multiple workers have cached copies of
+a single graph element (which is inevitable), but there is only one
+owner.
+
+The owner of a graph element can change. This is not yet implemented,
+but is intended. Graph partitioning is intended to be dynamic.
+
+Graph elements refer to other graph elements that are possibly on some
+other worker. Even though each graph element is identified with a unique
+ID, that ID does not contain the information about where that element
+currently resides (which worker is the owner).
+
+Thus we introduce the concept of a global address. It indicates both
+which graph element is referred to (it's global ID), and where it
+resides. Semantically it's a pair of two elements, but for efficiency
+it's stored in 64 bits.
+
+The global address is efficient for usage in a cluster: it indicates
+where something can be found. However, finding a graph element based on
+it's ID is still not a free operation (in the current implementation
+it's a skiplist lookup). So, whenever possible, it's better to use local
+addresses (pointers).
+
+Succinctly, the requirements for addressing are:
+- global addressing containing location info
+- fast local addressing
+- storage of both types in the same location efficiently
+- translation between the two
+
+The `storage::Address` class handles the enumerated storage
+requirements. It stores either a local or global address in the size of
+a local pointer (typically 8 bytes).
+
+Conversion between the two is done in multiple places. The general
+approach is to use local addresses (when possible) only for local
+in-memory handling. All the communication and persistence uses global
+addresses. Also, when receiving address from another worker, attempt to
+localize addresses as soon as possible, so that least code has to worry
+about potential inefficiency of using a global address for a local graph
+element.

docs/dev/distributed/durability.md

@@ -0,0 +1,50 @@
+# Distributed durability
+
+Durability in distributed is slightly different then in single-node as
+the state itself is shared between multiple workers and none of those
+states are independent.
+
+Note that recovering from persistent storage must result in a stable
+database state. This means that across the cluster the state
+modification of every transaction that was running is either recovered
+fully or not at all. Also, if transaction A committed before transaction B,
+then if B is recovered so must A.
+
+## Snapshots
+
+It is possibly avoidable but highly desirable that the database can be
+recovered from snapshot only, without relying on WAL files. For this to
+be possible in distributed, it must be ensured that the same
+transactions are recovered on all the workers (including master) in the
+cluster. Since the snapshot does not contain information about which
+state change happened in which transaction, the only way to achieve this
+is to have synchronized snapshots. This means that the process of
+creating a snapshot, which is in itself transactional (it happens within
+a transaction and thus observes some consistent database state), must
+happen in the same transaction. This is achieved by the master starting
+a snapshot generating transaction and triggering the process on all
+workers in the cluster.
+
+## WAL
+
+Unlike the snapshot, write-ahead logs contain the information on which
+transaction made which state change. This makes it possible to include
+or exclude transactions during the recovery process. What is necessary
+however is a global consensus on which of the transactions should be
+recovered and which not, to ensure recovery into a consistent state.
+
+It would be possible to achieve this with some kind of synchronized
+recovery process, but it would impose constraints on cluster startup and
+would not be trivial.
+
+A simpler alternative is that the consensus is achieved beforehand,
+while the database (to be recovered) is still operational. What is
+necessary is to keep track of which transactions are guaranteed to
+have been flushed to the WAL files on all the workers in the cluster. It
+makes sense to keep this record on the master, so a mechanism is
+introduced which periodically pings all the workers, telling them to
+flush their WALs, and writes some sort of a log indicating that this has
+been confirmed. The downside of this is a periodic broadcast must be
+done, and that potentially slightly less data can be recovered in the
+case of a crash then if using a post-crash consensus. It is however much
+simpler to implement.

docs/dev/distributed/dynamic_graph_partitioning.md

@@ -0,0 +1,51 @@
+## Dynamic Graph Partitioning
+
+Memgraph supports dynamic graph partitioning similar to the Spinner algorithm, 
+mentioned in this paper: [https://arxiv.org/pdf/1404.3861.pdf].
+
+Dgp is useful because it tries to group `local` date on the same worker, i.e. 
+it tries to keep closely connected data on one worker. It tries to avoid jumps 
+across workers when querying/traversing the distributed graph.
+
+### Our implementation
+
+It works independently on each worker but it is always running the migration 
+on only one worker at the same time. It achieves that by sharing a token 
+between workers, and the token ownership is transferred to the next worker 
+when the current worker finishes its migration step. 
+
+The reason that we want workers to work in  disjoint time slots is it avoid 
+serialization errors caused by creating/removing edges of vertices during 
+migrations, which might cause an update of some vertex from two or more 
+different transactions.
+
+### Migrations
+
+For each vertex and workerid (label in the context of Dgp algorithm) we define  
+a score function. Score function takes into account labels of surrounding 
+endpoints of vertex edges (in/out) and the capacity of the worker with said 
+label. Score function loosely looks like this 
+```
+locality(v, l) = 
+count endpoints of edges of vertex `v` with label `l` / degree of `v`
+
+capacity(l) = 
+number of vertices on worker `l` divided by the worker capacity 
+(usually equal to the average number of vertices per worker)
+
+score(v, l) = locality(v, l) - capacity(l)
+```
+We also define two flags alongside ```dynamic_graph_partitioner_enabled```, 
+   ```dgp_improvement_threshold``` and ```dgp_max_batch_size```.
+
+These two flags are used during the migration phase.
+When deciding if we need to migrate some vertex `v` from worker `l1` to worker 
+`l2` we examine the difference in scores, i.e.
+if score(v, l1) - dgp_improvement_threshold / 100 < score(v, l2) then we 
+migrate the vertex. 
+
+Max batch size flag limits the number of vertices we can transfer in one batch 
+(one migration step). 
+Setting this value to a too large value will probably cause
+a lot of interference with client queries, and having it a small value
+will slow down convergence of the algorithm.

docs/dev/distributed/general_concepts.md

@@ -0,0 +1,54 @@
+# Memgraph distributed
+
+This chapter describes some of the concepts used in distributed
+Memgraph. By "distributed" here we mean the sharding of a single graph
+onto multiple processing units (servers).
+
+## Conceptual organization
+
+There is a single master and multiple workers. The master contains all
+the global sources of truth (transaction engine,
+[label|edge-type|property] to name mappings). Also, in the current
+organization it is the only one that contains a Bolt server (for
+communication with the end client) and an interpretation engine. Workers
+contain the data and means of subquery interpretation (query plans
+recieved from the master) and means of communication with the master and
+other workers.
+
+In many query plans the load on the master is much larger then the load
+on the workers. For that reason it might be beneficial to make the
+master contain less data (or none at all), and/or having multiple
+interpretation masters.
+
+## Logic organization
+
+Both the distributed and the single node Memgraph use the same codebase.
+In cases where the behavior in single-node differs from that in
+distributed, some kind of dynamic behavior change is implemented (either
+through inheritance or conditional logic).
+
+### GraphDb
+
+The `database::GraphDb` is an "umbrella" object for parts of the
+database such as storage, garbage collection, transaction engine etc.
+There is a class heirarchy of `GraphDb` implementations, as well as a
+base interface object. There are subclasses for single-node, master and
+worker deplotyments. Which implementation is used depends on the
+configuration processed in the `main` entry point of memgraph.
+
+The `GraphDb` interface exposes getters to base classes of
+other similar heirarchies (for example to `tx::Engine`). In that way
+much of the code that uses those objects (for example query plan
+interpretation) is agnostic to the type of deployment.
+
+### RecordAccessors
+
+The functionality of `RecordAccessors` and it's subclasses is already
+documented. It's important to note that the same implementation of
+accessors is used in all deployments, with internal changes of behavior
+depending on the locality of the graph element (vertex or edge) the
+accessor represents. For example, if the graph element is local, an
+update operation on an accessor will make the necessary MVCC ops, update
+local data, indexes, the write-ahead log etc. However, if the accessor
+represents a remote graph element, an update will trigger an RPC message
+to the owner about the update and a change in the local cache.

docs/dev/distributed/updates.md

@@ -0,0 +1,103 @@
+# Distributed updates
+
+Operations that modify the graph state are somewhat more complex in the
+distributed system, as opposed to a single-node Memgraph deployment. The
+complexity arises from two factors.
+
+First, the data being modified is not necessarily owned by the worker
+performing the modification. This situation is completely valid workers
+execute parts of the query plan and parts must be executed by the
+master.
+
+Second, there are less guarantees regarding multi-threaded access. In
+single-node Memgraph it was guaranteed that only one transaction will be
+performing database work in a single transaction. This implied that
+per-version storage could be thread-unsafe. In distributed Memgraph it
+is possible that multiple threads could be performing work in the same
+transaction as a consequence of the query being executed at the same
+time on multiple workers and those executions interacting with the
+globally partitioned database state.
+
+## Deferred state modification
+
+Making the per-version data storage thread-safe would most likely have a
+performance impact very undesirable in a transactional database intended
+for high throughput.
+
+An alternative is that state modification over unsafe structures is not
+performed immediately when requested, but postponed until it is safe to
+do (there is is a guarantee of no concurrent access).
+
+Since local query plan execution is done the same way on local data as
+it is in single-node Memgraph, it is not possible to deffer that part of
+the modification story. What can be deferred are modifications requested
+by other workers. Since local query plan execution still is
+single-threaded, this approach is safe.
+
+At the same time those workers requesting the remote update can update
+local copies (caches) of the not-owned data since that cache is only
+being used by the single, local-execution thread.
+
+### Visibility
+
+Since updates are deferred the question arises: when do the updates
+become visible? The above described process offers the following
+visibility guarantees:
+- updates done on the local state are visible to the owner
+- updates done on the local state are NOT visible to anyone else during
+  the same (transaction + command)
+- updates done on remote state are deferred on the owner and not
+  visible to the owner until applied
+- updates done on the remote state are applied immediately to the local
+  caches and thus visible locally
+
+This implies an inconsistent view of the database state. In a concurrent
+execution of a single query this can hardly be avoided and is accepted
+as such. It does not change the Cypher query execution semantic in any
+of the well-defined scenarios. It possibly changes some of the behaviors
+in which the semantic is not well defined even in single-node execution.
+
+### Synchronization, update application
+
+In many queries it is mandatory to observe the latest global graph state
+(typically when returning it to the client). That means that before that
+happens all the deferred updates need to be applied, and all the caches
+to remote data invalidated. Exactly this happens when executing queries
+that modify the graph state. At some point a global synchronization
+point is reached. First it is waited that all workers finish the
+execution of query plan parts performing state modifications. After that
+all the workers are told to apply the deferred updates they received to
+their graph state. Since there is no concurrent query plan execution,
+this is safe. Once that is done all the local caches are cleared and the
+requested data can be returned to the client.
+
+### Command advancement
+
+In complex queries where a read part follows a state modification part
+the synchronization process after the state modification part is
+followed by command advancement, like in single-node execution.
+
+## Creation
+
+Graph element creation is not deferred. This is practical because the
+response to a creation is the global ID of the newly created element. At
+the same time it is safe because no other worker (including the owner)
+will be using the newly added graph element.
+
+## Updating
+
+Updating is deferred, as described. Note that this also means that
+record locking conflicts are deferred and serialization errors
+(including lock timeouts) are postponed until the deferred update
+application phase. In certain scenarios it might be beneficial to force
+these errors to happen earlier, when the deferred update request is
+processed.
+
+## Deletion
+
+Deletion is also deferred. Deleting an edge implies a modification of
+it's endpoint vertices, which must be deferred as those data structures
+are not thread-safe. Deleting a vertex is either with detaching, in
+which case an arbitrary number of updates are implied in the vertex's
+neighborhood, or without detaching which relies on checking the current
+state of the graph which is generally impossible in distributed.

docs/dev/durability/snapshots.md

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

docs/dev/durability/wal.md

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

docs/dev/other-code-conventions.md

@@ -0,0 +1,15 @@
+# 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

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

docs/dev/query/build-html

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

docs/dev/query/contents.md

@@ -0,0 +1,34 @@
+# 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

@@ -0,0 +1,373 @@
+# 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

@@ -0,0 +1,23 @@
+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

@@ -0,0 +1,62 @@
+# 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

@@ -0,0 +1,487 @@
+# 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.
+
+  5. [Distributed Planning](#distributed-planning)
+
+     In case we are running distributed Memgraph, the final plan is adapted
+     for distributed execution. NOTE: This appears to be an error in the
+     workflow. Distributed planning should be moved before step 3. or
+     integrated with it. With the workflow ordered as is now, cost estimation
+     doesn't consider the distributed plan.
+
+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
+
+NOTE: TODO
+
+## Cost Estimation
+
+NOTE: TODO
+
+## Distributed Planning
+
+NOTE: TODO

docs/dev/query/semantic.md

@@ -0,0 +1,134 @@
+# 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

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

docs/dev/required-reading.md

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

docs/dev/storage/accessors.md

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

docs/dev/storage/indexes.md

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

docs/dev/storage/property-storage.md

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

docs/dev/toolchain-bootstrap.md

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

docs/dev/workflow.md

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

docs/doxygen/README.md

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

docs/feature_ref/dynamic_graph_partitioning.md

@@ -0,0 +1,20 @@
+## Dynamic Graph Partitioner
+
+Memgraph supports dynamic graph partitioning which dynamically improves
+performance on badly partitioned dataset over workers. To enable it, the user
+should use the following flag when firing up the *master* node:
+
+```plaintext
+--dynamic_graph_partitioner_enable
+```
+
+### Parameters
+
+| Name | Default Value | Description | Range |
+|------|---------------|-------------|-------|
+|--dgp_improvement_threshold | 10 | 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. | Min: 1, Max: 100
+|--dgp_max_batch_size | 2000 | Maximal amount of vertices which should be
+migrated in one dynamic graph partitioner step. | Min: 1, Max: MaxInt32 |

docs/feature_spec/distributed.md

@@ -0,0 +1,78 @@
+# 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

@@ -0,0 +1,75 @@
+# 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

@@ -0,0 +1,214 @@
+# High Availability (abbr. HA)
+
+## Introduction
+
+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.
+
+## Theoretical Background
+
+The following chapter serves as an introduction into some theoretical aspects
+of Memgraph's high availability implementation. If the reader is solely
+interested in design decisions around HA implementation, they can skip this
+chapter.
+
+An important implication of any HA implementation stems from Eric Brewer's
+[CAP Theorem](https://fenix.tecnico.ulisboa.pt/downloadFile/1126518382178117/10.e-CAP-3.pdf)
+which states that it is impossible for a distributed system to simultaneously
+achieve:
+
+  * Consistency (C - every read receives the most recent write or an error)
+  * Availability (A - every request receives a response that is not an error)
+  * Partition tolerance (P - The system continues to operate despite an
+                             arbitrary number of messages being dropped by the
+                             network between nodes)
+
+In the context of HA, Memgraph should strive to achieve CA.
+
+### Consensus
+
+Implications of the CAP theorem naturally lead us towards introducing a
+cluster of machines which will have identical internal states. When a designated
+machine for handling client requests fails, it can simply be replaced with
+another.
+
+Well... turns out this is not as easy as it sounds :(
+
+Keeping around a cluster of machines with consistent internal state is an
+inherently difficult problem. More precisely, this problem is as hard as
+getting a cluster of machines to agree on a single value, which is a highly
+researched area in distributed systems. Our research of state of the art
+consensus algorithms lead us to Diego Ongaro's
+[Raft algorithm](https://raft.github.io/raft.pdf).
+
+#### Raft
+
+As you might have guessed, analyzing each subtle detail of Raft goes way
+beyond the scope of this document. In the remainder of the chapter we will
+outline only the most important ideas and implications, leaving all further
+analysis to the reader. Detailed explanation can be found either in Diego's
+[dissertation](https://ramcloud.stanford.edu/~ongaro/thesis.pdf) \[1\] or the
+Raft [paper](https://raft.github.io/raft.pdf) \[2\].
+
+In essence, Raft allows us to implement the previously mentioned idea of
+managing a cluster of machines with identical internal states. In other
+words, the Raft protocol allows us to manage a cluster of replicated
+state machines which is fully functional as long as the *majority* of
+the machines in the cluster operate correctly.
+
+Another important fact is that those state machines must be *deterministic*.
+In other words, the same command on two different machines with the same
+internal state must yield the same result. This is important because Memgraph,
+as a black box, is not entirely deterministic. Non-determinism can easily be
+introduced by the user (e.g. by using the `rand` function) or by algorithms
+behind query execution (e.g. introducing fuzzy logic in the planner could yield
+a different order of results). Luckily, once we enter the storage level,
+everything should be fully deterministic.
+
+To summarize, Raft is a protocol which achieves consensus in a cluster of
+deterministic state machines via log replication. The cluster is fully
+functional if the majority of the machines work correctly. The reader
+is strongly encouraged to gain a deeper understanding (at least read through
+the paper) of Raft before reading the rest of this document.
+
+## 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). As mentioned
+before, 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 `StateDelta`-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 `StateDelta`s which correspond to a single **committed** transaction.
+This decision both improves performance and handles some special cases that
+present themselves otherwise by leveraging the knowledge that the transaction
+should be committed.
+
+"What happens with aborted transactions?"
+
+A great question, they are handled solely by the leader which is the only
+machine that communicates with the client. Aborted transactions do not alter
+the state of the database and there is no need to replicate it to other machines
+in the cluster. If, for instance, the leader dies before returning the result
+of some read operation in an aborted transaction, the client will notice that
+the leader has crashed. A new leader will be elected in the next term and the
+client should retry the transaction.
+
+"OK, that makes sense! But, wait a minute, this is broken by design! Merely
+generating `StateDelta`s on the leader for any transaction will taint its
+internal storage before sending the first RPC to some follower. This deviates
+from Raft and will crash the universe!"
+
+Another great observation. It is indeed true that applying `StateDelta`s makes
+changes to local storage, but only a single type of `StateDelta` makes that
+  change durable. That `StateDelta` type is called `TRANSACTION_COMMIT` and we
+will change its behaviour when working as a HA instance. More precisely, we
+must not allow the transaction engine to modify the commit log saying that
+the transaction has been committed. That action should be delayed until those
+`StateDelta`s have been applied to the majority of the cluster. At that point
+the commit log can be safely modified leaving it up to Raft to ensure the
+durability of the transaction.
+
+We should also address one subtle detail that arises in this case. Consider
+the following scenario:
+
+  * The leader starts working on a transaction which creates a new record in the
+    database. Suppose that record is stored in the leader's internal storage
+    but the transaction was not committed (i.e. no such entry in the commit log).
+  * The leader should start replicating those `StateDelta`s to its followers
+    but, suddenly, it's cut off from the rest of the cluster.
+  * Due to timeout, a new election is held and a new leader has been elected.
+  * Our old leader comes back to life and becomes a follower.
+  * The new leader receives a transaction which creates that same record, but
+    this transaction is successfully replicated and committed by the new leader.
+
+The problem lies in the fact that there is still a record within the internal
+storage of our old leader with the same transaction ID and GID as the recently
+committed record by the new leader. Obviously, this is broken. As a solution, on
+each transition from `Leader` to `Follower`, we will reinitialize storage, reset
+the transaction engine and recover data from the Raft log. This will ensure all
+ongoing transactions which have "polluted" the storage will be gone.
+
+"When will followers append that transaction to their commit logs?"
+
+When the leader deduces that the transaction is safe to commit, it will include
+the relevant information in all further heartbeats which will alert the
+followers that it is safe to commit those entries from their raft logs.
+Naturally, the followers need not to delay appending data to the commit log
+as they know that the transaction has already been committed (from the clusters
+point of view). If this sounds really messed up, seriously, read the Raft paper.
+
+"How does the raft log differ from WAL"
+
+Conceptually, it doesn't. When operating in HA, we don't really need the
+recovery mechanisms implemented in Memgraph thus far. When a dead machine
+comes back to life, it will eventually come in sync with the rest of the
+cluster and everything will be done using the machine's raft log as well
+as the messages received from the cluster leader.
+
+"Those logs will become huge, isn't that recovery going to be painfully slow?"
+
+True, but there are mechanisms for making raft logs more compact. The most
+popular method is, wait for it, making snapshots :)
+Although the process of bringing an old machine back to life is a long one,
+it doesn't really affect the performance of the cluster in a great degree.
+The cluster will work perfectly fine with that machine being way out of sync.
+
+"I don't know, everything seems to be a lot slower than before!"
+
+Absolutely true, the user should be aware that they will suffer dire
+consequences on the performance side if they choose to be highly available.
+As Frankie says, "That's life!".
+
+"Also, I didn't really care about most of the things you've said. I'm
+not a part of the storage team and couldn't care less about the issues you
+face, how does HA affect 'my part of the codebase'?"
+
+Answer for query execution: That's ok, you'll be able to use the same beloved
+API (when we implement it, he he :) towards storage and continue to
+make fun of us when you find a bug.
+
+Answer for infrastructure: We'll talk. Some changes will surely need to
+be made on the Memgraph client. There is a chapter in Diego's dissertation
+called 'Client interaction', but we'll cross that bridge when we get there.
+There will also be the whole 'integration with Jepsen tests' thing going on.
+
+Answer for analytics: I'm astonished you've read this article. Wanna join
+storage?
+
+### Subtlety Regarding Reads
+
+As we have hinted in the previous chapter, we would like to bypass log
+replication for operations which do not alter the internal state of Memgraph.
+Those operations should therefore be handled only by the leader, which is not
+as trivial as it seems. The subtlety arises from the fact that a (newly-elected)
+leader can have an entry in its log which was committed by the previous leader
+that has crashed but that entry is not yet committed in its internal storage
+by the current leader. Moreover, the rule about safely committing logs that are
+replicated on the majority of the cluster only applies for entries replicated in
+the leaders current term. Therefore, we are faced with two issues:
+
+  * We cannot simply perform read operations if the leader has a non-committed
+    entry in its log (breaks consistency).
+  * Replicating those entries onto the majority of the cluster is not enough
+    to guarantee that they can be safely committed.
+
+This can be solved by introducing a blank no-op operation which the new leader
+will try to replicate at the start of its term. Once that operation is
+replicated and committed, the leader can safely perform those non-altering
+operations on its own.
+
+For further information about these issues, you should check out section
+5.4.2 from the raft paper \[1\] which hints as to why its not safe to commit
+entries from previous terms. Also, you should check out section 6.4 from
+the thesis \[2\] which goes into more details around efficiently processing
+read-only queries.
+
+## How do we test HA
+
+[Check this out](https://jepsen.io/analyses/dgraph-1-0-2)

docs/feature_spec/kafka/opencypher.md

@@ -0,0 +1,80 @@
+# 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

@@ -0,0 +1,34 @@
+# 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/tensorflow_op/technicalities.md

@@ -0,0 +1,61 @@
+# 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

@@ -0,0 +1,142 @@
+# 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

@@ -0,0 +1,22 @@
+# 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

@@ -0,0 +1,82 @@
+\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

@@ -0,0 +1,40 @@
+% 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/os/.gitignore

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

environment/os/centos-7.sh

@@ -1,148 +0,0 @@
-#!/bin/bash
-
-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 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
-    zlib # zlib library used for all builds
-    expat libipt libbabeltrace xz-libs python3 # for gdb
-    readline # for cmake and llvm
-    libffi libxml2 # for llvm
-    openssl-devel
-)
-
-MEMGRAPH_BUILD_DEPS=(
-    make pkgconfig # build system
-    curl wget # for downloading libs
-    libuuid-devel java-11-openjdk # required by antlr
-    readline-devel # for memgraph console
-    python3-devel # for query modules
-    openssl-devel
-    libseccomp-devel
-    python3 python-virtualenv python3-pip nmap-ncat # for qa, macro_benchmark and stress tests
-    #
-    # IMPORTANT: python3-yaml does NOT exist on CentOS
-    # Install it using `pip3 install PyYAML`
-    #
-    PyYAML # Package name here does not correspond to the yum package!
-    libcurl-devel # mg-requests
-    sbcl # for custom Lisp C++ preprocessing
-    rpm-build rpmlint # for RPM package building
-    doxygen graphviz # source documentation generators
-    which mono-complete dotnet-sdk-3.1 golang nodejs zip unzip java-11-openjdk-devel # for driver tests
-    autoconf # for jemalloc code generation
-    libtool  # for protobuf code generation
-)
-
-list() {
-    echo "$1"
-}
-
-check() {
-    local missing=""
-    for pkg in $1; do
-        if [ "$pkg" == git ]; then
-            if ! which "git" >/dev/null; then
-                missing="git $missing"
-            fi
-            continue
-        fi
-        if [ "$pkg" == "PyYAML" ]; then
-            if ! python3 -c "import yaml" >/dev/null 2>/dev/null; then
-                missing="$pkg $missing"
-            fi
-            continue
-        fi
-        if ! yum list installed "$pkg" >/dev/null 2>/dev/null; then
-            missing="$pkg $missing"
-        fi
-    done
-    if [ "$missing" != "" ]; then
-        echo "MISSING PACKAGES: $missing"
-        exit 1
-    fi
-}
-
-install() {
-    cd "$DIR"
-    if [ "$EUID" -ne 0 ]; then
-        echo "Please run as root."
-        exit 1
-    fi
-    # If GitHub Actions runner is installed, append LANG to the environment.
-    # Python related tests doesn't work the LANG export.
-    if [ -d "/home/gh/actions-runner" ]; then
-        echo "LANG=en_US.utf8" >> /home/gh/actions-runner/.env
-    else
-        echo "NOTE: export LANG=en_US.utf8"
-    fi
-    yum install -y epel-release
-    yum remove -y ius-release
-    yum install -y \
-      https://repo.ius.io/ius-release-el7.rpm
-    yum update -y
-    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
-                yum install -y http://repo.okay.com.mx/centos/8/x86_64/release/libipt-1.6.1-8.el8.x86_64.rpm
-            fi
-            continue
-        fi
-        if [ "$pkg" == libipt-devel ]; then
-            if ! yum list installed libipt-devel >/dev/null 2>/dev/null; then
-                yum install -y http://repo.okay.com.mx/centos/8/x86_64/release/libipt-devel-1.6.1-8.el8.x86_64.rpm
-            fi
-            continue
-        fi
-        if [ "$pkg" == dotnet-sdk-3.1 ]; then
-            if ! yum list installed dotnet-sdk-3.1 >/dev/null 2>/dev/null; then
-                wget -nv https://packages.microsoft.com/config/centos/7/packages-microsoft-prod.rpm -O packages-microsoft-prod.rpm
-                rpm -Uvh https://packages.microsoft.com/config/centos/7/packages-microsoft-prod.rpm
-                yum update -y
-                yum install -y dotnet-sdk-3.1
-            fi
-            continue
-        fi
-        if [ "$pkg" == PyYAML ]; then
-            if [ -z ${SUDO_USER+x} ]; then # Running as root (e.g. Docker).
-                pip3 install --user PyYAML
-            else # Running using sudo.
-                sudo -H -u "$SUDO_USER" bash -c "pip3 install --user PyYAML"
-            fi
-            continue
-        fi
-        yum install -y "$pkg"
-    done
-}
-
-deps=$2"[*]"
-"$1" "${!deps}"

environment/os/centos-9.sh

@@ -1,164 +0,0 @@
-#!/bin/bash
-
-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-common gcc gcc-c++ make # generic build tools
-    wget # used for archive download
-    gnupg2 # used for archive signature verification
-    tar gzip bzip2 xz unzip # used for archive unpacking
-    zlib-devel # zlib library used for all builds
-    expat-devel xz-devel python3-devel texinfo libbabeltrace-devel # for gdb
-    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 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
-    wget # for downloading libs
-    libuuid-devel java-11-openjdk # required by antlr
-    readline-devel # for memgraph console
-    python3-devel # for query modules
-    openssl-devel
-    libseccomp-devel
-    python3 python3-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`
-    #
-    PyYAML # Package name here does not correspond to the yum package!
-    libcurl-devel # mg-requests
-    rpm-build rpmlint # for RPM package building
-    doxygen graphviz # source documentation generators
-    which nodejs golang zip unzip java-11-openjdk-devel # for driver tests
-    sbcl # for custom Lisp C++ preprocessing
-    autoconf # for jemalloc code generation
-    libtool  # for protobuf code generation
-)
-
-list() {
-    echo "$1"
-}
-
-check() {
-    local missing=""
-    for pkg in $1; do
-        if [ "$pkg" == "PyYAML" ]; then
-            if ! python3 -c "import yaml" >/dev/null 2>/dev/null; then
-                missing="$pkg $missing"
-            fi
-            continue
-        fi
-        if [ "$pkg" == "python3-virtualenv" ]; then
-            continue
-        fi
-        if ! yum list installed "$pkg" >/dev/null 2>/dev/null; then
-            missing="$pkg $missing"
-        fi
-    done
-    if [ "$missing" != "" ]; then
-        echo "MISSING PACKAGES: $missing"
-        exit 1
-    fi
-}
-
-install() {
-    cd "$DIR"
-    if [ "$EUID" -ne 0 ]; then
-        echo "Please run as root."
-        exit 1
-    fi
-    # If GitHub Actions runner is installed, append LANG to the environment.
-    # Python related tests doesn't work the LANG export.
-    if [ -d "/home/gh/actions-runner" ]; then
-        echo "LANG=en_US.utf8" >> /home/gh/actions-runner/.env
-    else
-        echo "NOTE: export LANG=en_US.utf8"
-    fi
-    yum update -y
-    yum install -y wget git python3 python3-pip
-    for pkg in $1; do
-        # Since there is no support for libipt-devel for CentOS 9 we install
-        # Fedoras version of same libs, they are the same version but released
-        # for different OS
-        # TODO Update when libipt-devel releases for CentOS 9
-        if [ "$pkg" == libipt ]; then
-            if ! dnf list installed libipt >/dev/null 2>/dev/null; then
-                dnf install -y http://repo.okay.com.mx/centos/8/x86_64/release/libipt-1.6.1-8.el8.x86_64.rpm
-            fi
-            continue
-        fi
-        if [ "$pkg" == libipt-devel ]; then
-            if ! dnf list installed libipt-devel >/dev/null 2>/dev/null; then
-                dnf install -y http://repo.okay.com.mx/centos/8/x86_64/release/libipt-devel-1.6.1-8.el8.x86_64.rpm
-            fi
-            continue
-        fi
-        if [ "$pkg" == libbabeltrace-devel ]; then
-            if ! dnf list installed libbabeltrace-devel >/dev/null 2>/dev/null; then
-                dnf install -y http://mirror.stream.centos.org/9-stream/CRB/x86_64/os/Packages/libbabeltrace-devel-1.5.8-10.el9.x86_64.rpm
-            fi
-            continue
-        fi
-        if [ "$pkg" == sbcl ]; then
-            if ! dnf list installed cl-asdf >/dev/null 2>/dev/null; then
-                dnf install -y 	https://pkgs.dyn.su/el8/base/x86_64/cl-asdf-20101028-18.el8.noarch.rpm
-            fi
-            if ! dnf list installed common-lisp-controller >/dev/null 2>/dev/null; then
-                dnf install -y https://pkgs.dyn.su/el8/base/x86_64/common-lisp-controller-7.4-20.el8.noarch.rpm
-            fi
-            if ! dnf list installed sbcl >/dev/null 2>/dev/null; then
-                dnf install -y https://pkgs.dyn.su/el8/base/x86_64/sbcl-2.0.1-4.el8.x86_64.rpm
-            fi
-            continue
-        fi
-        if [ "$pkg" == PyYAML ]; then
-            if [ -z ${SUDO_USER+x} ]; then # Running as root (e.g. Docker).
-                pip3 install --user PyYAML
-            else # Running using sudo.
-                sudo -H -u "$SUDO_USER" bash -c "pip3 install --user PyYAML"
-            fi
-            continue
-        fi
-        if [ "$pkg" == python3-virtualenv ]; then
-            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 "$SUDO_USER" bash -c "pip3 install virtualenvwrapper"
-            fi
-            continue
-        fi
-        yum install -y "$pkg"
-    done
-}
-
-deps=$2"[*]"
-"$1" "${!deps}"

environment/os/debian-10.sh

@@ -1,104 +0,0 @@
-#!/bin/bash
-
-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
-    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 # 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
-    zlib1g # zlib library used for all builds
-    libexpat1 libipt2 libbabeltrace1 liblzma5 python3 # for gdb
-    libcurl4 # for cmake
-    libreadline7 # for cmake and llvm
-    libffi6 libxml2 # for llvm
-    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 "$1"
-}
-
-install() {
-    cat >/etc/apt/sources.list <<EOF
-deb http://deb.debian.org/debian/ buster main non-free contrib
-deb-src http://deb.debian.org/debian/ buster main non-free contrib
-deb http://deb.debian.org/debian/ buster-updates main contrib non-free
-deb-src http://deb.debian.org/debian/ buster-updates main contrib non-free
-deb http://security.debian.org/debian-security buster/updates main contrib non-free
-deb-src http://security.debian.org/debian-security buster/updates main contrib non-free
-EOF
-    cd "$DIR"
-    apt --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
-        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-11-arm.sh

@@ -1,98 +0,0 @@
-#!/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

@@ -1,107 +0,0 @@
-#!/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/template.sh

@@ -1,38 +0,0 @@
-#!/bin/bash
-
-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

@@ -1,74 +0,0 @@
-#!/bin/bash
-
-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
-    gnupg # archive signature verification
-    tar gzip bzip2 xz-utils unzip # archive unpacking
-    zlib1g-dev # zlib library used for all builds
-    libexpat1-dev libipt-dev libbabeltrace-dev liblzma-dev python3-dev # gdb
-    texinfo # gdb
-    libcurl4-openssl-dev # cmake
-    libreadline-dev # cmake and llvm
-    libffi-dev libxml2-dev # llvm
-    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
-    zlib1g # zlib library used for all builds
-    libexpat1 libipt1 libbabeltrace1 liblzma5 python3 # for gdb
-    libcurl4 # for cmake
-    libreadline7 # for cmake and llvm
-    libffi6 libxml2 # for llvm
-    libssl-dev # for libevent
-)
-
-MEMGRAPH_BUILD_DEPS=(
-    git # source code control
-    make pkg-config # build system
-    curl wget # downloading libs
-    uuid-dev default-jre-headless # required by antlr
-    libreadline-dev # memgraph console
-    libpython3-dev python3-dev # for query modules
-    libssl-dev
-    libseccomp-dev
-    python3 virtualenv python3-virtualenv python3-pip # qa, macro bench and stress tests
-    python3-yaml # the configuration generator
-    libcurl4-openssl-dev # mg-requests
-    sbcl # custom Lisp C++ preprocessing
-    doxygen graphviz # source documentation generators
-    mono-runtime mono-mcs nodejs zip unzip default-jdk-headless # driver tests
-    autoconf # for jemalloc code generation
-    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

@@ -1,96 +0,0 @@
-#!/bin/bash
-
-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
-    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-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
-    # If GitHub Actions runner is installed, append LANG to the environment.
-    # Python related tests doesn't work the LANG export.
-    if [ -d "/home/gh/actions-runner" ]; then
-        echo "LANG=en_US.utf8" >> /home/gh/actions-runner/.env
-    else
-        echo "NOTE: export LANG=en_US.utf8"
-    fi
-    apt install -y wget
-    for pkg in $1; do
-        if [ "$pkg" == dotnet-sdk-3.1 ]; then
-            if ! dpkg -s dotnet-sdk-3.1 2>/dev/null >/dev/null; then
-                wget -nv https://packages.microsoft.com/config/ubuntu/20.04/packages-microsoft-prod.deb -O packages-microsoft-prod.deb
-                dpkg -i packages-microsoft-prod.deb
-                apt-get update
-                apt-get install -y apt-transport-https dotnet-sdk-3.1
-            fi
-            continue
-        fi
-        apt install -y "$pkg"
-    done
-}
-
-deps=$2"[*]"
-"$1" "${!deps}"

environment/os/ubuntu-22.04.sh

@@ -1,96 +0,0 @@
-#!/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/setup.sh

@@ -4,36 +4,88 @@
 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 )
+CPUS=$( cat /proc/cpuinfo | grep processor | wc -l )
 cd "$DIR"
 
-source "$DIR/../util.sh"
-DISTRO="$(operating_system)"
-
 # toolchain version
-TOOLCHAIN_VERSION=2
+TOOLCHAIN_VERSION=1
 
 # package versions used
-GCC_VERSION=10.2.0
-BINUTILS_VERSION=2.35.1
-case "$DISTRO" in
-    centos-7) # because GDB >= 9 does NOT compile with readline6.
-        GDB_VERSION=8.3
-    ;;
-    *)
-        GDB_VERSION=10.1
-    ;;
-esac
-CMAKE_VERSION=3.18.4
-CPPCHECK_VERSION=2.2
-LLVM_VERSION=11.0.0
-SWIG_VERSION=4.0.2 # used only for LLVM compilation
+GCC_VERSION=8.3.0
+BINUTILS_VERSION=2.32
+GDB_VERSION=8.2.1
+CMAKE_VERSION=3.14.2
+CPPCHECK_VERSION=1.87
+LLVM_VERSION=8.0.0
+SWIG_VERSION=3.0.12 # 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/$DISTRO.sh check TOOLCHAIN_RUN_DEPS
+# check for installed dependencies
+DISTRO="$( egrep '^(VERSION_)?ID=' /etc/os-release | sort | cut -d '=' -f 2- | sed 's/"//g' | paste -s -d '-' )"
+if [ "$DISTRO" == "debian-9" ] || [ "$DISTRO" == "ubuntu-18.04" ]; then
+    DEPS_MANAGER=apt-get
+    DEPS_COMPILE=(
+        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 # 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
+        libreadline-dev # for cmake and llvm
+        libffi-dev libxml2-dev # for llvm
+        libedit-dev libpcre3-dev automake bison # for swig
+    )
+    DEPS_RUN=(
+        make # generic build tools
+        tar gzip bzip2 xz-utils # used for archive unpacking
+        zlib1g # zlib library used for all builds
+        libexpat1 libipt1 libbabeltrace1 liblzma5 python3 # for gdb
+        libreadline7 # for cmake and llvm
+        libffi6 libxml2 # for llvm
+    )
+elif [ "$DISTRO" == "centos-7" ]; then
+    DEPS_MANAGER=yum
+    DEPS_COMPILE=(
+        coreutils gcc gcc-c++ make # generic build tools
+        wget # used for archive download
+        gnupg2 # used for archive signature verification
+        tar gzip bzip2 xz # 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
+        readline-devel # for cmake and llvm
+        libffi-devel libxml2-devel # for llvm
+        libedit-devel pcre-devel automake bison # for swig
+    )
+    DEPS_RUN=(
+        make # generic build tools
+        tar gzip bzip2 xz # used for archive unpacking
+        zlib # zlib library used for all builds
+        expat libipt libbabeltrace xz-libs python36 # for gdb
+        readline # for cmake and llvm
+        libffi libxml2 # for llvm
+    )
+else
+    echo "Unknown distribution: $DISTRO!"
+    exit 1
+fi
+missing=""
+for dep in ${DEPS_COMPILE[@]}; do
+    if [ "$DEPS_MANAGER" == "apt-get" ]; then
+        if ! dpkg -s $dep >/dev/null 2>/dev/null; then
+            missing="$dep $missing"
+        fi
+    elif [ "$DEPS_MANAGER" == "yum" ]; then
+        if ! yum list installed $dep >/dev/null 2>/dev/null; then
+            missing="$dep $missing"
+        fi
+    else
+        echo "Invalid package manager: $DEPS_MANAGER!"
+        exit 1
+    fi
+done
+if [ "$missing" != "" ]; then
+    echo "Missing dependencies: $missing"
+    exit 1
+fi
 
 # check installation directory
 NAME=toolchain-v$TOOLCHAIN_VERSION
@@ -84,14 +136,10 @@ if [ ! -f cppcheck-$CPPCHECK_VERSION.tar.gz ]; then
     wget https://github.com/danmar/cppcheck/archive/$CPPCHECK_VERSION.tar.gz -O cppcheck-$CPPCHECK_VERSION.tar.gz
 fi
 if [ ! -f llvm-$LLVM_VERSION.src.tar.xz ]; then
-    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION/llvm-$LLVM_VERSION.src.tar.xz
-    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION/clang-$LLVM_VERSION.src.tar.xz
-    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION/lld-$LLVM_VERSION.src.tar.xz
-    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION/clang-tools-extra-$LLVM_VERSION.src.tar.xz
-    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION/compiler-rt-$LLVM_VERSION.src.tar.xz
-fi
-if [ ! -f pahole-gdb-master.zip ]; then
-    wget https://github.com/PhilArmstrong/pahole-gdb/archive/master.zip -O pahole-gdb-master.zip
+    wget http://releases.llvm.org/$LLVM_VERSION/llvm-$LLVM_VERSION.src.tar.xz
+    wget http://releases.llvm.org/$LLVM_VERSION/cfe-$LLVM_VERSION.src.tar.xz
+    wget http://releases.llvm.org/$LLVM_VERSION/lld-$LLVM_VERSION.src.tar.xz
+    wget http://releases.llvm.org/$LLVM_VERSION/clang-tools-extra-$LLVM_VERSION.src.tar.xz
 fi
 
 # verify all archives
@@ -108,7 +156,7 @@ if [ ! -f gcc-$GCC_VERSION.tar.gz.sig ]; then
     wget https://ftp.gnu.org/gnu/gcc/gcc-$GCC_VERSION/gcc-$GCC_VERSION.tar.gz.sig
 fi
 # list of valid gcc gnupg keys: https://gcc.gnu.org/mirrors.html
-$GPG --keyserver $KEYSERVER --recv-keys 0x3AB00996FC26A641
+$GPG --keyserver $KEYSERVER --recv-keys 0xC3C45C06
 $GPG --verify gcc-$GCC_VERSION.tar.gz.sig gcc-$GCC_VERSION.tar.gz
 # verify binutils
 if [ ! -f binutils-$BINUTILS_VERSION.tar.gz.sig ]; then
@@ -126,28 +174,23 @@ $GPG --verify gdb-$GDB_VERSION.tar.gz.sig gdb-$GDB_VERSION.tar.gz
 if [ ! -f cmake-$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 --keyserver $KEYSERVER --recv-keys 0x7BFB4EDA
+sha256sum --ignore-missing -c cmake-$CMAKE_VERSION-SHA-256.txt
 $GPG --verify cmake-$CMAKE_VERSION-SHA-256.txt.asc cmake-$CMAKE_VERSION-SHA-256.txt
 # verify llvm, cfe, lld, clang-tools-extra
 if [ ! -f llvm-$LLVM_VERSION.src.tar.xz.sig ]; then
-    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION/llvm-$LLVM_VERSION.src.tar.xz.sig
-    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION/clang-$LLVM_VERSION.src.tar.xz.sig
-    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION/lld-$LLVM_VERSION.src.tar.xz.sig
-    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION/clang-tools-extra-$LLVM_VERSION.src.tar.xz.sig
-    wget https://github.com/llvm/llvm-project/releases/download/llvmorg-$LLVM_VERSION/compiler-rt-$LLVM_VERSION.src.tar.xz.sig
+    wget http://releases.llvm.org/$LLVM_VERSION/llvm-$LLVM_VERSION.src.tar.xz.sig
+    wget http://releases.llvm.org/$LLVM_VERSION/cfe-$LLVM_VERSION.src.tar.xz.sig
+    wget http://releases.llvm.org/$LLVM_VERSION/lld-$LLVM_VERSION.src.tar.xz.sig
+    wget http://releases.llvm.org/$LLVM_VERSION/clang-tools-extra-$LLVM_VERSION.src.tar.xz.sig
 fi
 # list of valid llvm gnupg keys: https://releases.llvm.org/download.html
 $GPG --keyserver $KEYSERVER --recv-keys 0x345AD05D
 $GPG --verify llvm-$LLVM_VERSION.src.tar.xz.sig llvm-$LLVM_VERSION.src.tar.xz
-$GPG --verify clang-$LLVM_VERSION.src.tar.xz.sig clang-$LLVM_VERSION.src.tar.xz
+$GPG --verify cfe-$LLVM_VERSION.src.tar.xz.sig cfe-$LLVM_VERSION.src.tar.xz
 $GPG --verify lld-$LLVM_VERSION.src.tar.xz.sig lld-$LLVM_VERSION.src.tar.xz
 $GPG --verify clang-tools-extra-$LLVM_VERSION.src.tar.xz.sig clang-tools-extra-$LLVM_VERSION.src.tar.xz
-$GPG --verify compiler-rt-$LLVM_VERSION.src.tar.xz.sig compiler-rt-$LLVM_VERSION.src.tar.xz
 popd
 
 # create build directory
@@ -266,7 +309,6 @@ if [ ! -f $PREFIX/bin/gdb ]; then
             --disable-gdbtk \
             --disable-shared \
             --without-guile \
-            --with-system-gdbinit=$PREFIX/etc/gdb/gdbinit \
             --with-system-readline \
             --with-expat \
             --with-system-zlib \
@@ -280,38 +322,6 @@ if [ ! -f $PREFIX/bin/gdb ]; then
     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
@@ -330,8 +340,7 @@ if [ ! -f $PREFIX/bin/cmake ]; then
     ../bootstrap \
         --prefix=$PREFIX \
         --init=../build-flags.cmake \
-        --parallel=$CPUS \
-        --system-curl
+        --parallel=$CPUS
     make -j$CPUS
     # make test # run test suite
     make install
@@ -349,14 +358,12 @@ if [ ! -f $PREFIX/bin/cppcheck ]; then
         CC=gcc \
         CXX=g++ \
         PREFIX=$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
@@ -385,20 +392,19 @@ if [ ! -f $PREFIX/bin/clang ]; then
     fi
     tar -xvf ../archives/llvm-$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-$LLVM_VERSION/tools/clang
+    tar -xvf ../archives/cfe-$LLVM_VERSION.src.tar.xz
+    mv cfe-$LLVM_VERSION.src llvm-$LLVM_VERSION/tools/clang
     tar -xvf ../archives/lld-$LLVM_VERSION.src.tar.xz
     mv lld-$LLVM_VERSION.src/ llvm-$LLVM_VERSION/tools/lld
     tar -xvf ../archives/clang-tools-extra-$LLVM_VERSION.src.tar.xz
     mv clang-tools-extra-$LLVM_VERSION.src/ llvm-$LLVM_VERSION/tools/clang/tools/extra
-    tar -xvf ../archives/compiler-rt-$LLVM_VERSION.src.tar.xz
-    mv compiler-rt-$LLVM_VERSION.src/ llvm-$LLVM_VERSION/projects/compiler-rt
     pushd llvm-$LLVM_VERSION
     mkdir build && pushd build
     # activate swig
     export PATH=$DIR/build/swig-$SWIG_VERSION/install/bin:$PATH
     # influenced by: https://buildd.debian.org/status/fetch.php?pkg=llvm-toolchain-7&arch=amd64&ver=1%3A7.0.1%7E%2Brc2-1%7Eexp1&stamp=1541506173&raw=0
     cmake .. \
+        -DGCC_INSTALL_PREFIX=$PREFIX \
         -DCMAKE_C_COMPILER=$PREFIX/bin/gcc \
         -DCMAKE_CXX_COMPILER=$PREFIX/bin/g++ \
         -DCMAKE_CXX_LINK_FLAGS="-L$PREFIX/lib64 -Wl,-rpath,$PREFIX/lib64" \
@@ -414,7 +420,9 @@ if [ ! -f $PREFIX/bin/clang ]; then
         -DLLVM_ENABLE_RTTI=ON \
         -DLLVM_ENABLE_FFI=ON \
         -DLLVM_BINUTILS_INCDIR=$PREFIX/include/ \
-        -DLLVM_USE_PERF=yes
+        -DLLVM_USE_PERF=yes \
+        -DLIBCLANG_LIBRARY_VERSION=1 \
+        -DCLANG_ENABLE_BOOTSTRAP=ON
     make -j$CPUS
     make -j$CPUS check-clang # run clang test suite
     make -j$CPUS check-lld # run lld test suite
@@ -434,7 +442,7 @@ if [ ! -f $PREFIX/README.md ]; then
  - GDB $GDB_VERSION
  - CMake $CMAKE_VERSION
  - Cppcheck $CPPCHECK_VERSION
- - LLVM (Clang, LLD, compiler-rt, Clang tools extra) $LLVM_VERSION
+ - LLVM (Clang, LLD, Clang tools extra) $LLVM_VERSION
 
 ## Required libraries
 
@@ -442,7 +450,7 @@ In order to be able to run all of these tools you should install the following
 packages:
 
 \`\`\`
-$($DIR/../os/$DISTRO.sh list TOOLCHAIN_RUN_DEPS)
+$DEPS_MANAGER install ${DEPS_RUN[@]}
 \`\`\`
 
 ## Usage
@@ -480,7 +488,7 @@ export ORIG_LD_LIBRARY_PATH=\$LD_LIBRARY_PATH
 
 # activate new environment
 export PATH=$PREFIX/bin:\$PATH
-export PS1="($NAME) \$PS1"
+export PS1="(TOOLCHAIN) \$PS1"
 export LD_LIBRARY_PATH=$PREFIX/lib:$PREFIX/lib64
 
 # disable root