Compare commits

..

13 Commits

Author SHA1 Message Date
jbajic
e36784b5e5 Throw exception not assert 2022-08-04 11:18:21 +02:00
jbajic
7c01957295 Enable memgraph with new version of storage and query engine 2022-08-03 16:52:41 +02:00
jbajic
794046309a Change temp dir name 2022-08-02 10:19:36 +02:00
jbajic
05b4e86f49 Fix clang tidy errors 2022-08-02 09:58:02 +02:00
jbajic
6188d6fdec Fix interpreter test 2022-08-01 22:00:15 +02:00
jbajic
fbec252324 Fix typo in CMake 2022-08-01 17:20:45 +02:00
jbajic
943a0f05e9 Move schema related tests to newer versions of query and storage 2022-08-01 15:58:10 +02:00
jbajic
73fb8cc141 Make glue v2 2022-08-01 15:46:52 +02:00
jbajic
4244b91f17 Remove schema from query v1 2022-08-01 13:18:24 +02:00
jbajic
867a4075ae Move schema to query v2 2022-08-01 13:10:54 +02:00
jbajic
7a699a02a3 Merge branch 'E112-MG-implement-partial-schema' into T0950-MG-move-schema-to-storage-v3-and-query-v2 2022-08-01 10:47:08 +02:00
jbajic
6f0010004f Remove schema from v2 2022-08-01 10:14:41 +02:00
jbajic
30c213815b Move schema to storage v3 2022-08-01 10:08:15 +02:00
381 changed files with 51675 additions and 48099 deletions

View File

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

View File

@@ -26,7 +26,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v3
uses: actions/checkout@v2
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
@@ -64,7 +64,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v3
uses: actions/checkout@v2
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
@@ -75,39 +75,14 @@ jobs:
- name: Fetch all history for all tags and branches
run: git fetch
- name: Initialize deps
run: |
# Activate toolchain.
source /opt/toolchain-v4/activate
# Initialize dependencies.
./init
- name: Set base branch
if: ${{ github.event_name == 'pull_request' }}
run: |
echo "BASE_BRANCH=origin/${{ github.base_ref }}" >> $GITHUB_ENV
- name: Set base branch # if we manually dispatch or push to master
if: ${{ github.event_name != 'pull_request' }}
run: |
echo "BASE_BRANCH=origin/master" >> $GITHUB_ENV
- name: Python code analysis
run: |
CHANGED_FILES=$(git diff -U0 ${{ env.BASE_BRANCH }}... --name-only)
for file in ${CHANGED_FILES}; do
echo ${file}
if [[ ${file} == *.py ]]; then
python3 -m black --check --diff ${file}
python3 -m isort --check-only --profile "black" --diff ${file}
fi
done
- name: Build combined ASAN, UBSAN and coverage binaries
run: |
# Activate toolchain.
source /opt/toolchain-v4/activate
# Initialize dependencies.
./init
cd build
cmake -DTEST_COVERAGE=ON -DASAN=ON -DUBSAN=ON ..
make -j$THREADS memgraph__unit
@@ -135,7 +110,7 @@ jobs:
tar -czf code_coverage.tar.gz coverage.json html report.json summary.rmu
- name: Save code coverage
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v2
with:
name: "Code coverage"
path: tools/github/generated/code_coverage.tar.gz
@@ -155,7 +130,7 @@ jobs:
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
git diff -U0 ${{ env.BASE_BRANCH }}... -- src | ./tools/github/clang-tidy/clang-tidy-diff.py -p 1 -j $THREADS -path build | tee ./build/clang_tidy_output.txt
# Fail if any warning is reported
! cat ./build/clang_tidy_output.txt | ./tools/github/clang-tidy/grep_error_lines.sh > /dev/null
@@ -170,7 +145,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v3
uses: actions/checkout@v2
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
@@ -189,23 +164,52 @@ jobs:
cmake ..
make -j$THREADS
- name: Run simulation tests
- name: Run leftover CTest tests
run: |
# Activate toolchain.
source /opt/toolchain-v4/activate
# Run simulation tests.
# Run leftover CTest tests (all except unit and benchmark tests).
cd build
ctest -R memgraph__simulation --output-on-failure -j$THREADS
ctest -E "(memgraph__unit|memgraph__benchmark)" --output-on-failure
- name: Run single benchmark test
- 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: $name"
if [ -x prepare.sh ]; then
./prepare.sh
fi
if [ -x runner.py ]; then
./runner.py
elif [ -x runner.sh ]; then
./runner.sh
fi
echo
popd >/dev/null
done
- name: Run cppcheck and clang-format
run: |
# Activate toolchain.
source /opt/toolchain-v4/activate
# Run simulation tests.
cd tests/mgbench
./benchmark.py accesscontrol/small --num-workers-for-import 1 --test-system-arg "split-file splitfiles/accesscontrol_small.shard_configuration bolt-num-workers 1"
# Run cppcheck and clang-format.
cd tools/github
./cppcheck_and_clang_format diff
- name: Save cppcheck and clang-format errors
uses: actions/upload-artifact@v2
with:
name: "Code coverage"
path: tools/github/cppcheck_and_clang_format.txt
release_build:
name: "Release build"
@@ -217,7 +221,7 @@ jobs:
steps:
- name: Set up repository
uses: actions/checkout@v3
uses: actions/checkout@v2
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
@@ -236,6 +240,19 @@ jobs:
cmake -DCMAKE_BUILD_TYPE=release ..
make -j$THREADS
- name: Run GQL Behave tests
run: |
cd tests/gql_behave
./continuous_integration
- name: Save quality assurance status
uses: actions/upload-artifact@v2
with:
name: "GQL Behave Status"
path: |
tests/gql_behave/gql_behave_status.csv
tests/gql_behave/gql_behave_status.html
- name: Run unit tests
run: |
# Activate toolchain.
@@ -245,24 +262,6 @@ jobs:
cd build
ctest -R memgraph__unit --output-on-failure -j$THREADS
- name: Run simulation tests
run: |
# Activate toolchain.
source /opt/toolchain-v4/activate
# Run simulation tests.
cd build
ctest -R memgraph__simulation --output-on-failure -j$THREADS
- name: Run single benchmark test
run: |
# Activate toolchain.
source /opt/toolchain-v4/activate
# Run simulation tests.
cd tests/mgbench
./benchmark.py accesscontrol/small --num-workers-for-import 1 --test-system-arg "split-file splitfiles/accesscontrol_small.shard_configuration bolt-num-workers 1"
- name: Run e2e tests
run: |
# TODO(gitbuda): Setup mgclient and pymgclient properly.
@@ -270,4 +269,167 @@ jobs:
./setup.sh
source ve3/bin/activate
cd e2e
LD_LIBRARY_PATH=$LD_LIBRARY_PATH:../../libs/mgclient/lib python runner.py --workloads-root-directory ./distributed_queries
LD_LIBRARY_PATH=$LD_LIBRARY_PATH:../../libs/mgclient/lib python runner.py --workloads-root-directory .
- name: Run stress test (plain)
run: |
cd tests/stress
./continuous_integration
- name: Run stress test (SSL)
run: |
cd tests/stress
./continuous_integration --use-ssl
- name: Run durability test
run: |
cd tests/stress
source ve3/bin/activate
python3 durability --num-steps 5
- name: Create enterprise DEB package
run: |
# Activate toolchain.
source /opt/toolchain-v4/activate
cd build
# create mgconsole
# we use the -B to force the build
make -j$THREADS -B mgconsole
# Create enterprise DEB package.
mkdir output && cd output
cpack -G DEB --config ../CPackConfig.cmake
- name: Save enterprise DEB package
uses: actions/upload-artifact@v2
with:
name: "Enterprise DEB package"
path: build/output/memgraph*.deb
- name: Save test data
uses: actions/upload-artifact@v2
if: always()
with:
name: "Test data"
path: |
# multiple paths could be defined
build/logs
release_jepsen_test:
name: "Release Jepsen Test"
runs-on: [self-hosted, Linux, X64, Debian10, JepsenControl]
#continue-on-error: true
env:
THREADS: 24
MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
steps:
- name: Set up repository
uses: actions/checkout@v2
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
fetch-depth: 0
- name: Build release binaries
run: |
# Activate toolchain.
source /opt/toolchain-v4/activate
# Initialize dependencies.
./init
# Build only memgraph release binarie.
cd build
cmake -DCMAKE_BUILD_TYPE=release ..
make -j$THREADS memgraph
- name: Run Jepsen tests
run: |
cd tests/jepsen
./run.sh test --binary ../../build/memgraph --run-args "test-all --node-configs resources/node-config.edn" --ignore-run-stdout-logs --ignore-run-stderr-logs
- name: Save Jepsen report
uses: actions/upload-artifact@v2
if: ${{ always() }}
with:
name: "Jepsen Report"
path: tests/jepsen/Jepsen.tar.gz
release_benchmarks:
name: "Release benchmarks"
runs-on: [self-hosted, Linux, X64, Diff, Gen7]
env:
THREADS: 24
MEMGRAPH_ENTERPRISE_LICENSE: ${{ secrets.MEMGRAPH_ENTERPRISE_LICENSE }}
MEMGRAPH_ORGANIZATION_NAME: ${{ secrets.MEMGRAPH_ORGANIZATION_NAME }}
steps:
- name: Set up repository
uses: actions/checkout@v2
with:
# Number of commits to fetch. `0` indicates all history for all
# branches and tags. (default: 1)
fetch-depth: 0
- name: Build release binaries
run: |
# Activate toolchain.
source /opt/toolchain-v4/activate
# Initialize dependencies.
./init
# Build only memgraph release binaries.
cd build
cmake -DCMAKE_BUILD_TYPE=release ..
make -j$THREADS
- name: Run macro benchmarks
run: |
cd tests/macro_benchmark
./harness QuerySuite MemgraphRunner \
--groups aggregation 1000_create unwind_create dense_expand match \
--no-strict
- name: Get branch name (merge)
if: github.event_name != 'pull_request'
shell: bash
run: echo "BRANCH_NAME=$(echo ${GITHUB_REF#refs/heads/} | tr / -)" >> $GITHUB_ENV
- name: Get branch name (pull request)
if: github.event_name == 'pull_request'
shell: bash
run: echo "BRANCH_NAME=$(echo ${GITHUB_HEAD_REF} | tr / -)" >> $GITHUB_ENV
- name: Upload macro benchmark results
run: |
cd tools/bench-graph-client
virtualenv -p python3 ve3
source ve3/bin/activate
pip install -r requirements.txt
./main.py --benchmark-name "macro_benchmark" \
--benchmark-results-path "../../tests/macro_benchmark/.harness_summary" \
--github-run-id "${{ github.run_id }}" \
--github-run-number "${{ github.run_number }}" \
--head-branch-name "${{ env.BRANCH_NAME }}"
- name: Run mgbench
run: |
cd tests/mgbench
./benchmark.py --num-workers-for-benchmark 12 --export-results benchmark_result.json pokec/medium/*/*
- name: Upload mgbench results
run: |
cd tools/bench-graph-client
virtualenv -p python3 ve3
source ve3/bin/activate
pip install -r requirements.txt
./main.py --benchmark-name "mgbench" \
--benchmark-results-path "../../tests/mgbench/benchmark_result.json" \
--github-run-id "${{ github.run_id }}" \
--github-run-number "${{ github.run_number }}" \
--head-branch-name "${{ env.BRANCH_NAME }}"

View File

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

View File

@@ -17,7 +17,7 @@ jobs:
run: |
./release/package/run.sh package centos-7
- name: "Upload package"
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v2
with:
name: centos-7
path: build/output/centos-7/memgraph*.rpm
@@ -34,7 +34,7 @@ jobs:
run: |
./release/package/run.sh package centos-9
- name: "Upload package"
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v2
with:
name: centos-9
path: build/output/centos-9/memgraph*.rpm
@@ -51,7 +51,7 @@ jobs:
run: |
./release/package/run.sh package debian-10
- name: "Upload package"
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v2
with:
name: debian-10
path: build/output/debian-10/memgraph*.deb
@@ -68,7 +68,7 @@ jobs:
run: |
./release/package/run.sh package debian-11
- name: "Upload package"
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v2
with:
name: debian-11
path: build/output/debian-11/memgraph*.deb
@@ -87,7 +87,7 @@ jobs:
./run.sh package debian-11 --for-docker
./run.sh docker
- name: "Upload package"
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v2
with:
name: docker
path: build/output/docker/memgraph*.tar.gz
@@ -104,7 +104,7 @@ jobs:
run: |
./release/package/run.sh package ubuntu-18.04
- name: "Upload package"
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v2
with:
name: ubuntu-1804
path: build/output/ubuntu-18.04/memgraph*.deb
@@ -121,7 +121,7 @@ jobs:
run: |
./release/package/run.sh package ubuntu-20.04
- name: "Upload package"
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v2
with:
name: ubuntu-2004
path: build/output/ubuntu-20.04/memgraph*.deb
@@ -138,7 +138,7 @@ jobs:
run: |
./release/package/run.sh package ubuntu-22.04
- name: "Upload package"
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v2
with:
name: ubuntu-2204
path: build/output/ubuntu-22.04/memgraph*.deb
@@ -155,7 +155,7 @@ jobs:
run: |
./release/package/run.sh package debian-11 --for-platform
- name: "Upload package"
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v2
with:
name: debian-11-platform
path: build/output/debian-11/memgraph*.deb
@@ -172,7 +172,7 @@ jobs:
run: |
./release/package/run.sh package debian-11-arm
- name: "Upload package"
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v2
with:
name: debian-11-arm
path: build/output/debian-11-arm/memgraph*.deb

View File

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

View File

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

View File

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

View File

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

5
.gitignore vendored
View File

@@ -24,7 +24,6 @@ cmake/DownloadProject/
dist/
src/query/frontend/opencypher/generated/
src/query/v2/frontend/opencypher/generated/
src/parser/opencypher/generated
tags
ve/
ve3/
@@ -54,7 +53,6 @@ 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
@@ -62,15 +60,12 @@ 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

View File

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

View File

@@ -182,8 +182,7 @@ 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=switch -Werror=switch-bool -Werror=return-type \
-Werror=return-stack-address \
-Wno-c99-designator \
-DBOOST_ASIO_USE_TS_EXECUTOR_AS_DEFAULT")

View File

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

7
init
View File

@@ -140,12 +140,5 @@ done;
python3 -m pip install pre-commit
python3 -m pre_commit install
# Install py format tools
echo "Install black formatter"
python3 -m pip install black==22.10.*
echo "Install isort"
python3 -m pip install isort==5.10.*
# Link `include/mgp.py` with `release/mgp/mgp.py`
ln -v -f include/mgp.py release/mgp/mgp.py

View File

@@ -116,7 +116,7 @@ declare -A primary_urls=(
["pymgclient"]="http://$local_cache_host/git/pymgclient.git"
["mgconsole"]="http://$local_cache_host/git/mgconsole.git"
["spdlog"]="http://$local_cache_host/git/spdlog"
["nlohmann"]="http://$local_cache_host/file/nlohmann/json/9d69186291aca4f0137b69c1dee313b391ff564c/single_include/nlohmann/json.hpp"
["nlohmann"]="http://$local_cache_host/file/nlohmann/json/4f8fba14066156b73f1189a2b8bd568bde5284c5/single_include/nlohmann/json.hpp"
["neo4j"]="http://$local_cache_host/file/neo4j-community-3.2.3-unix.tar.gz"
["librdkafka"]="http://$local_cache_host/git/librdkafka.git"
["protobuf"]="http://$local_cache_host/git/protobuf.git"
@@ -141,7 +141,7 @@ declare -A secondary_urls=(
["pymgclient"]="https://github.com/memgraph/pymgclient.git"
["mgconsole"]="http://github.com/memgraph/mgconsole.git"
["spdlog"]="https://github.com/gabime/spdlog"
["nlohmann"]="https://raw.githubusercontent.com/nlohmann/json/9d69186291aca4f0137b69c1dee313b391ff564c/single_include/nlohmann/json.hpp"
["nlohmann"]="https://raw.githubusercontent.com/nlohmann/json/4f8fba14066156b73f1189a2b8bd568bde5284c5/single_include/nlohmann/json.hpp"
["neo4j"]="https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/neo4j-community-3.2.3-unix.tar.gz"
["librdkafka"]="https://github.com/edenhill/librdkafka.git"
["protobuf"]="https://github.com/protocolbuffers/protobuf.git"
@@ -171,7 +171,7 @@ benchmark_tag="v1.6.0"
repo_clone_try_double "${primary_urls[gbenchmark]}" "${secondary_urls[gbenchmark]}" "benchmark" "$benchmark_tag" true
# google test
googletest_tag="release-1.12.1"
googletest_tag="release-1.8.0"
repo_clone_try_double "${primary_urls[gtest]}" "${secondary_urls[gtest]}" "googletest" "$googletest_tag" true
# libbcrypt

View File

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

View File

@@ -5,7 +5,6 @@ add_subdirectory(lisp)
add_subdirectory(utils)
add_subdirectory(requests)
add_subdirectory(io)
add_subdirectory(io/simulator)
add_subdirectory(kvstore)
add_subdirectory(telemetry)
add_subdirectory(communication)
@@ -18,10 +17,6 @@ add_subdirectory(query/v2)
add_subdirectory(slk)
add_subdirectory(rpc)
add_subdirectory(auth)
add_subdirectory(parser)
add_subdirectory(expr)
add_subdirectory(coordinator)
add_subdirectory(functions)
if (MG_ENTERPRISE)
add_subdirectory(audit)
@@ -38,13 +33,13 @@ include_directories(${CMAKE_CURRENT_BINARY_DIR})
# Memgraph Single Node v2 Executable
# ----------------------------------------------------------------------------
set(mg_single_node_v2_sources
glue/v2/communication.cpp
memgraph.cpp
glue/v2/auth.cpp
glue/v2/communication.cpp
memgraph.cpp
glue/v2/auth.cpp
)
set(mg_single_node_v2_libs stdc++fs Threads::Threads
telemetry_lib mg-query-v2 mg-communication mg-memory mg-utils mg-auth mg-license mg-settings mg-io mg-coordinator)
telemetry_lib mg-query-v2 mg-communication mg-memory mg-utils mg-auth mg-license mg-settings)
if (MG_ENTERPRISE)
# These are enterprise subsystems
set(mg_single_node_v2_libs ${mg_single_node_v2_libs} mg-audit)
@@ -127,3 +122,19 @@ install(CODE "file(MAKE_DIRECTORY \$ENV{DESTDIR}/var/log/memgraph
# ----------------------------------------------------------------------------
# Memgraph CSV Import Tool Executable
# ----------------------------------------------------------------------------
add_executable(mg_import_csv mg_import_csv.cpp)
target_link_libraries(mg_import_csv mg-storage-v3)
# Strip the executable in release build.
if (lower_build_type STREQUAL "release")
add_custom_command(TARGET mg_import_csv POST_BUILD
COMMAND strip -s mg_import_csv
COMMENT "Stripping symbols and sections from mg_import_csv")
endif()
install(TARGETS mg_import_csv RUNTIME DESTINATION bin)
# ----------------------------------------------------------------------------
# Memgraph CSV Import Tool Executable
# ----------------------------------------------------------------------------

View File

@@ -5,4 +5,4 @@ find_package(gflags REQUIRED)
add_library(mg-audit STATIC ${audit_src_files})
target_link_libraries(mg-audit json gflags fmt::fmt)
target_link_libraries(mg-audit mg-utils mg-storage-v2)
target_link_libraries(mg-audit mg-utils mg-storage-v3)

View File

@@ -1,68 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <cstdint>
#include <string_view>
namespace memgraph::common {
enum class ErrorCode : uint8_t {
SERIALIZATION_ERROR,
NONEXISTENT_OBJECT,
DELETED_OBJECT,
VERTEX_HAS_EDGES,
PROPERTIES_DISABLED,
VERTEX_ALREADY_INSERTED,
// Schema Violations
SCHEMA_NO_SCHEMA_DEFINED_FOR_LABEL,
SCHEMA_VERTEX_PROPERTY_WRONG_TYPE,
SCHEMA_VERTEX_UPDATE_PRIMARY_KEY,
SCHEMA_VERTEX_UPDATE_PRIMARY_LABEL,
SCHEMA_VERTEX_SECONDARY_LABEL_IS_PRIMARY,
SCHEMA_VERTEX_PRIMARY_PROPERTIES_UNDEFINED,
OBJECT_NOT_FOUND,
};
constexpr std::string_view ErrorCodeToString(const ErrorCode code) {
switch (code) {
case ErrorCode::SERIALIZATION_ERROR:
return "SERIALIZATION_ERROR";
case ErrorCode::NONEXISTENT_OBJECT:
return "NONEXISTENT_OBJECT";
case ErrorCode::DELETED_OBJECT:
return "DELETED_OBJECT";
case ErrorCode::VERTEX_HAS_EDGES:
return "VERTEX_HAS_EDGES";
case ErrorCode::PROPERTIES_DISABLED:
return "PROPERTIES_DISABLED";
case ErrorCode::VERTEX_ALREADY_INSERTED:
return "VERTEX_ALREADY_INSERTED";
case ErrorCode::SCHEMA_NO_SCHEMA_DEFINED_FOR_LABEL:
return "SCHEMA_NO_SCHEMA_DEFINED_FOR_LABEL";
case ErrorCode::SCHEMA_VERTEX_PROPERTY_WRONG_TYPE:
return "SCHEMA_VERTEX_PROPERTY_WRONG_TYPE";
case ErrorCode::SCHEMA_VERTEX_UPDATE_PRIMARY_KEY:
return "SCHEMA_VERTEX_UPDATE_PRIMARY_KEY";
case ErrorCode::SCHEMA_VERTEX_UPDATE_PRIMARY_LABEL:
return "SCHEMA_VERTEX_UPDATE_PRIMARY_LABEL";
case ErrorCode::SCHEMA_VERTEX_SECONDARY_LABEL_IS_PRIMARY:
return "SCHEMA_VERTEX_SECONDARY_LABEL_IS_PRIMARY";
case ErrorCode::SCHEMA_VERTEX_PRIMARY_PROPERTIES_UNDEFINED:
return "SCHEMA_VERTEX_PRIMARY_PROPERTIES_UNDEFINED";
case ErrorCode::OBJECT_NOT_FOUND:
return "OBJECT_NOT_FOUND";
}
}
} // namespace memgraph::common

View File

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

View File

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

View File

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

View File

@@ -41,7 +41,6 @@
#include <boost/beast/websocket/rfc6455.hpp>
#include <boost/system/detail/error_code.hpp>
#include "communication/buffer.hpp"
#include "communication/context.hpp"
#include "communication/exceptions.hpp"
#include "utils/logging.hpp"
@@ -140,7 +139,7 @@ class WebsocketSession : public std::enable_shared_from_this<WebsocketSession<TS
private:
// Take ownership of the socket
explicit WebsocketSession(tcp::socket &&socket, TSessionData &data, tcp::endpoint endpoint,
explicit WebsocketSession(tcp::socket &&socket, TSessionData *data, tcp::endpoint endpoint,
std::string_view service_name)
: ws_(std::move(socket)),
strand_{boost::asio::make_strand(ws_.get_executor())},
@@ -312,13 +311,13 @@ class Session final : public std::enable_shared_from_this<Session<TSession, TSes
}
private:
explicit Session(tcp::socket &&socket, TSessionData &data, ServerContext &server_context, tcp::endpoint endpoint,
explicit Session(tcp::socket &&socket, TSessionData *data, ServerContext &server_context, tcp::endpoint endpoint,
const std::chrono::seconds inactivity_timeout_sec, std::string_view service_name)
: socket_(CreateSocket(std::move(socket), server_context)),
strand_{boost::asio::make_strand(GetExecutor())},
output_stream_([this](const uint8_t *data, size_t len, bool have_more) { return Write(data, len, have_more); }),
session_(data, endpoint, input_buffer_.read_end(), &output_stream_),
data_{&data},
data_{data},
endpoint_{endpoint},
remote_endpoint_{GetRemoteEndpoint()},
service_name_{service_name},
@@ -374,7 +373,7 @@ class Session final : public std::enable_shared_from_this<Session<TSession, TSes
spdlog::info("Switching {} to websocket connection", remote_endpoint_);
if (std::holds_alternative<TCPSocket>(socket_)) {
auto sock = std::get<TCPSocket>(std::move(socket_));
WebsocketSession<TSession, TSessionData>::Create(std::move(sock), *data_, endpoint_, service_name_)
WebsocketSession<TSession, TSessionData>::Create(std::move(sock), data_, endpoint_, service_name_)
->DoAccept(parser.release());
execution_active_ = false;
return;
@@ -466,7 +465,7 @@ class Session final : public std::enable_shared_from_this<Session<TSession, TSes
if (timeout_timer_.expiry() <= boost::asio::steady_timer::clock_type::now()) {
// The deadline has passed. Stop the session. The other actors will
// terminate as soon as possible.
spdlog::info("Shutting down session after {} of inactivity", timeout_seconds_.count());
spdlog::info("Shutting down session after {} of inactivity", timeout_seconds_);
DoShutdown();
} else {
// Put the actor back to sleep.

View File

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

View File

@@ -1,129 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#include <coordinator/coordinator.hpp>
namespace memgraph::coordinator {
CoordinatorWriteResponses Coordinator::ApplyWrite(HeartbeatRequest &&heartbeat_request) {
spdlog::info("Coordinator handling HeartbeatRequest");
// add this storage engine to any under-replicated shards that it is not already a part of
auto initializing_rsms_for_shard_manager =
shard_map_.AssignShards(heartbeat_request.from_storage_manager, heartbeat_request.initialized_rsms);
return HeartbeatResponse{
.shards_to_initialize = initializing_rsms_for_shard_manager,
};
}
CoordinatorWriteResponses Coordinator::ApplyWrite(HlcRequest &&hlc_request) {
HlcResponse res{};
auto hlc_shard_map = shard_map_.GetHlc();
MG_ASSERT(!(hlc_request.last_shard_map_version.logical_id > hlc_shard_map.logical_id));
res.new_hlc = Hlc{
.logical_id = ++highest_allocated_timestamp_,
// TODO(tyler) probably pass some more context to the Coordinator here
// so that we can use our wall clock and enforce monotonicity.
// .coordinator_wall_clock = io_.Now(),
};
// Allways return fresher shard_map for now.
res.fresher_shard_map = std::make_optional(shard_map_);
return res;
}
CoordinatorWriteResponses Coordinator::ApplyWrite(AllocateEdgeIdBatchRequest &&ahr) {
AllocateEdgeIdBatchResponse res{};
uint64_t low = highest_allocated_edge_id_;
highest_allocated_edge_id_ += ahr.batch_size;
uint64_t high = highest_allocated_edge_id_;
res.low = low;
res.high = high;
return res;
}
/// This splits the shard immediately beneath the provided
/// split key, keeping the assigned peers identical for now,
/// but letting them be gradually migrated over time.
CoordinatorWriteResponses Coordinator::ApplyWrite(SplitShardRequest &&split_shard_request) {
SplitShardResponse res{};
if (split_shard_request.previous_shard_map_version != shard_map_.shard_map_version) {
res.success = false;
} else {
res.success = shard_map_.SplitShard(split_shard_request.previous_shard_map_version, split_shard_request.label_id,
split_shard_request.split_key);
}
return res;
}
/// This adds the provided storage engine to the standby storage engine pool,
/// which can be used to rebalance storage over time.
CoordinatorWriteResponses Coordinator::ApplyWrite(
RegisterStorageEngineRequest && /* register_storage_engine_request */) {
RegisterStorageEngineResponse res{};
// TODO
return res;
}
/// This begins the process of draining the provided storage engine from all raft
/// clusters that it might be participating in.
CoordinatorWriteResponses Coordinator::ApplyWrite(
DeregisterStorageEngineRequest && /* register_storage_engine_request */) {
DeregisterStorageEngineResponse res{};
// TODO
return res;
}
CoordinatorWriteResponses Coordinator::ApplyWrite(InitializeLabelRequest &&initialize_label_request) {
InitializeLabelResponse res{};
std::optional<LabelId> new_label_id = shard_map_.InitializeNewLabel(
initialize_label_request.label_name, initialize_label_request.schema, initialize_label_request.replication_factor,
initialize_label_request.last_shard_map_version);
if (new_label_id) {
res.new_label_id = new_label_id.value();
res.fresher_shard_map = std::nullopt;
res.success = true;
} else {
res.fresher_shard_map = shard_map_;
res.success = false;
}
return res;
}
CoordinatorWriteResponses Coordinator::ApplyWrite(AllocatePropertyIdsRequest &&allocate_property_ids_request) {
AllocatePropertyIdsResponse res{};
auto property_ids = shard_map_.AllocatePropertyIds(allocate_property_ids_request.property_names);
res.property_ids = property_ids;
return res;
}
} // namespace memgraph::coordinator

View File

@@ -1,196 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <optional>
#include <set>
#include <string>
#include <unordered_set>
#include <variant>
#include <vector>
#include <boost/uuid/uuid.hpp>
#include <coordinator/hybrid_logical_clock.hpp>
#include <coordinator/shard_map.hpp>
#include <io/simulator/simulator.hpp>
#include <io/time.hpp>
#include <io/transport.hpp>
#include <storage/v3/id_types.hpp>
#include <storage/v3/schemas.hpp>
namespace memgraph::coordinator {
using memgraph::io::Address;
using memgraph::storage::v3::LabelId;
using memgraph::storage::v3::PropertyId;
using memgraph::storage::v3::SchemaProperty;
using SimT = memgraph::io::simulator::SimulatorTransport;
using PrimaryKey = std::vector<PropertyValue>;
struct HlcRequest {
Hlc last_shard_map_version;
};
struct HlcResponse {
Hlc new_hlc;
std::optional<ShardMap> fresher_shard_map;
};
struct GetShardMapRequest {
// No state
};
struct GetShardMapResponse {
ShardMap shard_map;
};
struct AllocateHlcBatchRequest {
Hlc low;
Hlc high;
};
struct AllocateHlcBatchResponse {
bool success;
Hlc low;
Hlc high;
};
struct AllocateEdgeIdBatchRequest {
size_t batch_size;
};
struct AllocateEdgeIdBatchResponse {
uint64_t low;
uint64_t high;
};
struct AllocatePropertyIdsRequest {
std::vector<std::string> property_names;
};
struct AllocatePropertyIdsResponse {
std::map<std::string, PropertyId> property_ids;
};
struct SplitShardRequest {
Hlc previous_shard_map_version;
LabelId label_id;
PrimaryKey split_key;
};
struct SplitShardResponse {
bool success;
};
struct RegisterStorageEngineRequest {
Address address;
};
struct RegisterStorageEngineResponse {
bool success;
};
struct DeregisterStorageEngineRequest {
Address address;
};
struct DeregisterStorageEngineResponse {
bool success;
};
struct InitializeLabelRequest {
std::string label_name;
std::vector<SchemaProperty> schema;
size_t replication_factor;
Hlc last_shard_map_version;
};
struct InitializeLabelResponse {
bool success;
LabelId new_label_id;
std::optional<ShardMap> fresher_shard_map;
};
struct HeartbeatRequest {
Address from_storage_manager;
std::set<boost::uuids::uuid> initialized_rsms;
};
struct HeartbeatResponse {
std::vector<ShardToInitialize> shards_to_initialize;
};
using CoordinatorWriteRequests =
std::variant<HlcRequest, AllocateEdgeIdBatchRequest, SplitShardRequest, RegisterStorageEngineRequest,
DeregisterStorageEngineRequest, InitializeLabelRequest, AllocatePropertyIdsRequest, HeartbeatRequest>;
using CoordinatorWriteResponses = std::variant<HlcResponse, AllocateEdgeIdBatchResponse, SplitShardResponse,
RegisterStorageEngineResponse, DeregisterStorageEngineResponse,
InitializeLabelResponse, AllocatePropertyIdsResponse, HeartbeatResponse>;
using CoordinatorReadRequests = std::variant<GetShardMapRequest>;
using CoordinatorReadResponses = std::variant<GetShardMapResponse>;
class Coordinator {
public:
explicit Coordinator(ShardMap sm) : shard_map_{std::move(sm)} {}
// NOLINTNEXTLINE(readability-convert-member-functions-to-static
CoordinatorReadResponses Read(CoordinatorReadRequests requests) {
return std::visit([&](auto &&request) { return HandleRead(std::forward<decltype(request)>(request)); },
std::move(requests)); // NOLINT(hicpp-move-const-arg,performance-move-const-arg)
}
// NOLINTNEXTLINE(readability-convert-member-functions-to-static
CoordinatorWriteResponses Apply(CoordinatorWriteRequests requests) {
return std::visit([&](auto &&request) mutable { return ApplyWrite(std::forward<decltype(request)>(request)); },
std::move(requests));
}
private:
ShardMap shard_map_;
uint64_t highest_allocated_timestamp_{0};
/// Query engines need to periodically request batches of unique edge IDs.
uint64_t highest_allocated_edge_id_{0};
CoordinatorReadResponses HandleRead(GetShardMapRequest && /* get_shard_map_request */) {
GetShardMapResponse res;
res.shard_map = shard_map_;
return res;
}
CoordinatorWriteResponses ApplyWrite(HeartbeatRequest &&heartbeat_request);
CoordinatorWriteResponses ApplyWrite(HlcRequest &&hlc_request);
CoordinatorWriteResponses ApplyWrite(AllocateEdgeIdBatchRequest &&ahr);
/// This splits the shard immediately beneath the provided
/// split key, keeping the assigned peers identical for now,
/// but letting them be gradually migrated over time.
CoordinatorWriteResponses ApplyWrite(SplitShardRequest &&split_shard_request);
/// This adds the provided storage engine to the standby storage engine pool,
/// which can be used to rebalance storage over time.
static CoordinatorWriteResponses ApplyWrite(RegisterStorageEngineRequest && /* register_storage_engine_request */);
/// This begins the process of draining the provided storage engine from all raft
/// clusters that it might be participating in.
static CoordinatorWriteResponses ApplyWrite(DeregisterStorageEngineRequest && /* register_storage_engine_request */);
CoordinatorWriteResponses ApplyWrite(InitializeLabelRequest &&initialize_label_request);
CoordinatorWriteResponses ApplyWrite(AllocatePropertyIdsRequest &&allocate_property_ids_request);
};
} // namespace memgraph::coordinator

View File

@@ -1,24 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "coordinator/coordinator.hpp"
#include "io/rsm/rsm_client.hpp"
namespace memgraph::coordinator {
using memgraph::io::rsm::RsmClient;
template <typename IoImpl>
using CoordinatorClient = RsmClient<IoImpl, CoordinatorWriteRequests, CoordinatorWriteResponses,
CoordinatorReadRequests, CoordinatorReadResponses>;
} // namespace memgraph::coordinator

View File

@@ -1,23 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "coordinator/coordinator.hpp"
#include "io/rsm/raft.hpp"
namespace memgraph::coordinator {
template <typename IoImpl>
using CoordinatorRsm = memgraph::io::rsm::Raft<IoImpl, Coordinator, CoordinatorWriteRequests, CoordinatorWriteResponses,
CoordinatorReadRequests, CoordinatorReadResponses>;
} // namespace memgraph::coordinator

View File

@@ -1,168 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <chrono>
#include <deque>
#include <memory>
#include <queue>
#include <variant>
#include "coordinator/coordinator.hpp"
#include "coordinator/coordinator_rsm.hpp"
#include "coordinator/shard_map.hpp"
#include "io/address.hpp"
#include "io/future.hpp"
#include "io/messages.hpp"
#include "io/rsm/raft.hpp"
#include "io/time.hpp"
#include "io/transport.hpp"
#include "query/v2/requests.hpp"
namespace memgraph::coordinator::coordinator_worker {
/// Obligations:
/// * ShutDown
/// * Cron
/// * RouteMessage
using coordinator::Coordinator;
using coordinator::CoordinatorRsm;
using io::Address;
using io::RequestId;
using io::Time;
using io::messages::CoordinatorMessages;
using msgs::ReadRequests;
using msgs::ReadResponses;
using msgs::WriteRequests;
using msgs::WriteResponses;
struct ShutDown {};
struct Cron {};
struct RouteMessage {
CoordinatorMessages message;
RequestId request_id;
Address to;
Address from;
};
using Message = std::variant<RouteMessage, Cron, ShutDown>;
struct QueueInner {
std::mutex mu{};
std::condition_variable cv;
// TODO(tyler) handle simulator communication std::shared_ptr<std::atomic<int>> blocked;
// TODO(tyler) investigate using a priority queue that prioritizes messages in a way that
// improves overall QoS. For example, maybe we want to schedule raft Append messages
// ahead of Read messages or generally writes before reads for lowering the load on the
// overall system faster etc... When we do this, we need to make sure to avoid
// starvation by sometimes randomizing priorities, rather than following a strict
// prioritization.
std::deque<Message> queue;
uint64_t submitted = 0;
uint64_t calls_to_pop = 0;
};
/// There are two reasons to implement our own Queue instead of using
/// one off-the-shelf:
/// 1. we will need to know in the simulator when all threads are waiting
/// 2. we will want to implement our own priority queue within this for QoS
class Queue {
std::shared_ptr<QueueInner> inner_ = std::make_shared<QueueInner>();
public:
void Push(Message &&message) {
{
MG_ASSERT(inner_.use_count() > 0);
std::unique_lock<std::mutex> lock(inner_->mu);
inner_->submitted++;
inner_->queue.emplace_back(std::move(message));
} // lock dropped before notifying condition variable
inner_->cv.notify_all();
}
Message Pop() {
MG_ASSERT(inner_.use_count() > 0);
std::unique_lock<std::mutex> lock(inner_->mu);
inner_->calls_to_pop++;
inner_->cv.notify_all();
while (inner_->queue.empty()) {
inner_->cv.wait(lock);
}
Message message = std::move(inner_->queue.front());
inner_->queue.pop_front();
return message;
}
void BlockOnQuiescence() const {
MG_ASSERT(inner_.use_count() > 0);
std::unique_lock<std::mutex> lock(inner_->mu);
while (inner_->calls_to_pop <= inner_->submitted) {
inner_->cv.wait(lock);
}
}
};
/// A CoordinatorWorker owns Raft<CoordinatorRsm> instances. receives messages from the MachineManager.
template <typename IoImpl>
class CoordinatorWorker {
io::Io<IoImpl> io_;
Queue queue_;
CoordinatorRsm<IoImpl> coordinator_;
bool Process(ShutDown && /*shut_down*/) { return false; }
bool Process(Cron && /* cron */) {
coordinator_.Cron();
return true;
}
bool Process(RouteMessage &&route_message) {
coordinator_.Handle(std::move(route_message.message), route_message.request_id, route_message.from);
return true;
}
public:
CoordinatorWorker(io::Io<IoImpl> io, Queue queue, Coordinator coordinator)
: io_(std::move(io)), queue_(std::move(queue)), coordinator_{std::move(io_), {}, std::move(coordinator)} {}
CoordinatorWorker(CoordinatorWorker &&) noexcept = default;
CoordinatorWorker &operator=(CoordinatorWorker &&) noexcept = default;
CoordinatorWorker(const CoordinatorWorker &) = delete;
CoordinatorWorker &operator=(const CoordinatorWorker &) = delete;
~CoordinatorWorker() = default;
void Run() {
bool should_continue = true;
while (should_continue) {
Message message = queue_.Pop();
should_continue = std::visit([this](auto &&msg) { return this->Process(std::forward<decltype(msg)>(msg)); },
std::move(message));
}
}
};
} // namespace memgraph::coordinator::coordinator_worker

View File

@@ -1,48 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <chrono>
#include <compare>
#include <ctime>
#include <iomanip>
#include "io/time.hpp"
namespace memgraph::coordinator {
using Time = memgraph::io::Time;
/// Hybrid-logical clock
struct Hlc {
uint64_t logical_id = 0;
Time coordinator_wall_clock = Time::min();
auto operator<=>(const Hlc &other) const { return logical_id <=> other.logical_id; }
bool operator==(const Hlc &other) const = default;
bool operator<(const Hlc &other) const = default;
bool operator==(const uint64_t other) const { return logical_id == other; }
bool operator<(const uint64_t other) const { return logical_id < other; }
bool operator>=(const uint64_t other) const { return logical_id >= other; }
friend std::ostream &operator<<(std::ostream &in, const Hlc &hlc) {
auto wall_clock = std::chrono::system_clock::to_time_t(hlc.coordinator_wall_clock);
in << "Hlc { logical_id: " << hlc.logical_id;
in << ", coordinator_wall_clock: " << std::put_time(std::localtime(&wall_clock), "%F %T");
in << " }";
return in;
}
};
} // namespace memgraph::coordinator

View File

@@ -1,576 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#include <optional>
#include <unordered_map>
#include <vector>
#include "common/types.hpp"
#include "coordinator/shard_map.hpp"
#include "spdlog/spdlog.h"
#include "storage/v3/schemas.hpp"
#include "storage/v3/temporal.hpp"
#include "utils/cast.hpp"
#include "utils/exceptions.hpp"
#include "utils/string.hpp"
namespace memgraph::coordinator {
using memgraph::common::SchemaType;
using memgraph::storage::v3::TemporalData;
using memgraph::storage::v3::TemporalType;
PrimaryKey SchemaToMinKey(const std::vector<SchemaProperty> &schema) {
PrimaryKey ret{};
const int64_t min_int = std::numeric_limits<int64_t>::min();
const TemporalData date{TemporalType::Date, min_int};
const TemporalData local_time{TemporalType::LocalTime, min_int};
const TemporalData local_date_time{TemporalType::LocalDateTime, min_int};
const TemporalData duration{TemporalType::Duration, min_int};
for (const auto &schema_property : schema) {
switch (schema_property.type) {
case SchemaType::BOOL:
ret.emplace_back(PropertyValue(false));
break;
case SchemaType::INT:
ret.emplace_back(PropertyValue(min_int));
break;
case SchemaType::STRING:
ret.emplace_back(PropertyValue(""));
break;
case SchemaType::DATE:
ret.emplace_back(PropertyValue(date));
break;
case SchemaType::LOCALTIME:
ret.emplace_back(PropertyValue(local_time));
break;
case SchemaType::LOCALDATETIME:
ret.emplace_back(PropertyValue(local_date_time));
break;
case SchemaType::DURATION:
ret.emplace_back(PropertyValue(duration));
break;
}
}
return ret;
}
ShardMap ShardMap::Parse(std::istream &input_stream) {
ShardMap shard_map;
const auto read_size = [&input_stream] {
size_t size{0};
input_stream >> size;
return size;
};
// Reads a string until the next whitespace
const auto read_word = [&input_stream] {
std::string word;
input_stream >> word;
return word;
};
const auto read_names = [&read_size, &read_word] {
const auto number_of_names = read_size();
spdlog::trace("Reading {} names", number_of_names);
std::vector<std::string> names;
names.reserve(number_of_names);
for (auto name_index = 0; name_index < number_of_names; ++name_index) {
names.push_back(read_word());
spdlog::trace("Read '{}'", names.back());
}
return names;
};
const auto read_line = [&input_stream] {
std::string line;
std::getline(input_stream, line);
return line;
};
const auto parse_type = [](const std::string &type) {
static const auto type_map = std::unordered_map<std::string, common::SchemaType>{
{"string", common::SchemaType::STRING}, {"int", common::SchemaType::INT}, {"bool", common::SchemaType::BOOL}};
const auto lower_case_type = utils::ToLowerCase(type);
auto it = type_map.find(lower_case_type);
MG_ASSERT(it != type_map.end(), "Invalid type in split files: {}", type);
return it->second;
};
const auto parse_property_value = [](std::string text, const common::SchemaType type) {
if (type == common::SchemaType::STRING) {
return storage::v3::PropertyValue{std::move(text)};
}
if (type == common::SchemaType::INT) {
size_t processed{0};
int64_t value = std::stoll(text, &processed);
MG_ASSERT(processed == text.size() || text[processed] == ' ', "Invalid integer format: '{}'", text);
return storage::v3::PropertyValue{value};
}
LOG_FATAL("Not supported type: {}", utils::UnderlyingCast(type));
};
spdlog::debug("Reading properties");
const auto properties = read_names();
MG_ASSERT(shard_map.AllocatePropertyIds(properties).size() == properties.size(),
"Unexpected number of properties created!");
spdlog::debug("Reading edge types");
const auto edge_types = read_names();
MG_ASSERT(shard_map.AllocateEdgeTypeIds(edge_types).size() == edge_types.size(),
"Unexpected number of properties created!");
spdlog::debug("Reading primary labels");
const auto number_of_primary_labels = read_size();
spdlog::debug("Reading {} primary labels", number_of_primary_labels);
for (auto label_index = 0; label_index < number_of_primary_labels; ++label_index) {
const auto primary_label = read_word();
spdlog::debug("Reading primary label named '{}'", primary_label);
const auto number_of_primary_properties = read_size();
spdlog::debug("Reading {} primary properties", number_of_primary_properties);
std::vector<std::string> pp_names;
std::vector<common::SchemaType> pp_types;
pp_names.reserve(number_of_primary_properties);
pp_types.reserve(number_of_primary_properties);
for (auto property_index = 0; property_index < number_of_primary_properties; ++property_index) {
pp_names.push_back(read_word());
spdlog::debug("Reading primary property named '{}'", pp_names.back());
pp_types.push_back(parse_type(read_word()));
}
auto pp_mapping = shard_map.AllocatePropertyIds(pp_names);
std::vector<SchemaProperty> schema;
schema.reserve(number_of_primary_properties);
for (auto property_index = 0; property_index < number_of_primary_properties; ++property_index) {
schema.push_back(storage::v3::SchemaProperty{pp_mapping.at(pp_names[property_index]), pp_types[property_index]});
}
const auto hlc = shard_map.GetHlc();
MG_ASSERT(shard_map.InitializeNewLabel(primary_label, schema, 1, hlc).has_value(),
"Cannot initialize new label: {}", primary_label);
const auto number_of_split_points = read_size();
spdlog::debug("Reading {} split points", number_of_split_points);
[[maybe_unused]] const auto remainder_from_last_line = read_line();
for (auto split_point_index = 0; split_point_index < number_of_split_points; ++split_point_index) {
const auto line = read_line();
spdlog::debug("Read split point '{}'", line);
MG_ASSERT(line.front() == '[', "Invalid split file format!");
MG_ASSERT(line.back() == ']', "Invalid split file format!");
std::string_view line_view{line};
line_view.remove_prefix(1);
line_view.remove_suffix(1);
static constexpr std::string_view kDelimiter{","};
auto pk_values_as_text = utils::Split(line_view, kDelimiter);
std::vector<PropertyValue> pk;
pk.reserve(number_of_primary_properties);
MG_ASSERT(pk_values_as_text.size() == number_of_primary_properties,
"Split point contains invalid number of values '{}'", line);
for (auto property_index = 0; property_index < number_of_primary_properties; ++property_index) {
pk.push_back(parse_property_value(std::move(pk_values_as_text[property_index]), schema[property_index].type));
}
shard_map.SplitShard(shard_map.GetHlc(), shard_map.labels.at(primary_label), pk);
}
}
return shard_map;
}
std::ostream &operator<<(std::ostream &in, const ShardMap &shard_map) {
using utils::print_helpers::operator<<;
in << "ShardMap { shard_map_version: " << shard_map.shard_map_version;
in << ", max_property_id: " << shard_map.max_property_id;
in << ", max_edge_type_id: " << shard_map.max_edge_type_id;
in << ", properties: " << shard_map.properties;
in << ", edge_types: " << shard_map.edge_types;
in << ", max_label_id: " << shard_map.max_label_id;
in << ", labels: " << shard_map.labels;
in << ", label_spaces: " << shard_map.label_spaces;
in << ", schemas: " << shard_map.schemas;
in << "}";
return in;
}
Shards ShardMap::GetShardsForLabel(const LabelName &label) const {
const auto id = labels.at(label);
const auto &shards = label_spaces.at(id).shards;
return shards;
}
std::vector<Shards> ShardMap::GetAllShards() const {
std::vector<Shards> all_shards;
all_shards.reserve(label_spaces.size());
std::transform(label_spaces.begin(), label_spaces.end(), std::back_inserter(all_shards),
[](const auto &label_space) { return label_space.second.shards; });
return all_shards;
}
// TODO(gabor) later we will want to update the wallclock time with
// the given Io<impl>'s time as well
Hlc ShardMap::IncrementShardMapVersion() noexcept {
++shard_map_version.logical_id;
return shard_map_version;
}
// TODO(antaljanosbenjamin) use a single map for all name id
// mapping and a single counter to maintain the next id
std::unordered_map<uint64_t, std::string> ShardMap::IdToNames() {
std::unordered_map<uint64_t, std::string> id_to_names;
const auto map_type_ids = [&id_to_names](const auto &name_to_id_type) {
for (const auto &[name, id] : name_to_id_type) {
id_to_names.emplace(id.AsUint(), name);
}
};
map_type_ids(edge_types);
map_type_ids(labels);
map_type_ids(properties);
return id_to_names;
}
Hlc ShardMap::GetHlc() const noexcept { return shard_map_version; }
boost::uuids::uuid NewShardUuid(uint64_t shard_id) {
return boost::uuids::uuid{0,
0,
0,
0,
0,
0,
0,
0,
static_cast<unsigned char>(shard_id >> 56U),
static_cast<unsigned char>(shard_id >> 48U),
static_cast<unsigned char>(shard_id >> 40U),
static_cast<unsigned char>(shard_id >> 32U),
static_cast<unsigned char>(shard_id >> 24U),
static_cast<unsigned char>(shard_id >> 16U),
static_cast<unsigned char>(shard_id >> 8U),
static_cast<unsigned char>(shard_id)};
}
std::vector<ShardToInitialize> ShardMap::AssignShards(Address storage_manager,
std::set<boost::uuids::uuid> initialized) {
std::vector<ShardToInitialize> ret{};
bool mutated = false;
for (auto &[label_id, label_space] : label_spaces) {
for (auto it = label_space.shards.begin(); it != label_space.shards.end(); it++) {
auto &[low_key, shard] = *it;
std::optional<PrimaryKey> high_key;
if (const auto next_it = std::next(it); next_it != label_space.shards.end()) {
high_key = next_it->first;
}
// TODO(tyler) avoid these triple-nested loops by having the heartbeat include better info
bool machine_contains_shard = false;
for (auto &aas : shard.peers) {
if (initialized.contains(aas.address.unique_id)) {
machine_contains_shard = true;
if (aas.status != Status::CONSENSUS_PARTICIPANT) {
mutated = true;
spdlog::info("marking shard as full consensus participant: {}", aas.address.unique_id);
aas.status = Status::CONSENSUS_PARTICIPANT;
}
} else {
const bool same_machine = aas.address.last_known_ip == storage_manager.last_known_ip &&
aas.address.last_known_port == storage_manager.last_known_port;
if (same_machine) {
machine_contains_shard = true;
spdlog::info("reminding shard manager that they should begin participating in shard");
ret.push_back(ShardToInitialize{
.uuid = aas.address.unique_id,
.label_id = label_id,
.min_key = low_key,
.max_key = high_key,
.schema = schemas[label_id],
.config = Config{},
.id_to_names = IdToNames(),
});
}
}
}
if (!machine_contains_shard && shard.peers.size() < label_space.replication_factor) {
// increment version for each new uuid for deterministic creation
IncrementShardMapVersion();
Address address = storage_manager;
// TODO(tyler) use deterministic UUID so that coordinators don't diverge here
address.unique_id = NewShardUuid(shard_map_version.logical_id);
spdlog::info("assigning shard manager to shard");
ret.push_back(ShardToInitialize{
.uuid = address.unique_id,
.label_id = label_id,
.min_key = low_key,
.max_key = high_key,
.schema = schemas[label_id],
.config = Config{},
.id_to_names = IdToNames(),
});
AddressAndStatus aas = {
.address = address,
.status = Status::INITIALIZING,
};
shard.peers.emplace_back(aas);
}
}
}
if (mutated) {
IncrementShardMapVersion();
}
return ret;
}
bool ShardMap::SplitShard(Hlc previous_shard_map_version, LabelId label_id, const PrimaryKey &key) {
if (previous_shard_map_version != shard_map_version) {
return false;
}
auto &label_space = label_spaces.at(label_id);
auto &shards_in_map = label_space.shards;
MG_ASSERT(!shards_in_map.empty());
MG_ASSERT(!shards_in_map.contains(key));
MG_ASSERT(label_spaces.contains(label_id));
// Finding the ShardMetadata that the new PrimaryKey should map to.
auto prev = std::prev(shards_in_map.upper_bound(key));
ShardMetadata duplicated_shard = prev->second;
// Apply the split
shards_in_map[key] = duplicated_shard;
IncrementShardMapVersion();
return true;
}
std::optional<LabelId> ShardMap::InitializeNewLabel(std::string label_name, std::vector<SchemaProperty> schema,
size_t replication_factor, Hlc last_shard_map_version) {
if (shard_map_version != last_shard_map_version || labels.contains(label_name)) {
return std::nullopt;
}
const LabelId label_id = LabelId::FromUint(++max_label_id);
labels.emplace(std::move(label_name), label_id);
PrimaryKey initial_key = SchemaToMinKey(schema);
ShardMetadata empty_shard = {};
Shards shards = {
{initial_key, empty_shard},
};
LabelSpace label_space{
.schema = schema,
.shards = shards,
.replication_factor = replication_factor,
};
schemas[label_id] = std::move(schema);
label_spaces.emplace(label_id, label_space);
IncrementShardMapVersion();
return label_id;
}
void ShardMap::AddServer(Address server_address) {
// Find a random place for the server to plug in
}
std::optional<LabelId> ShardMap::GetLabelId(const std::string &label) const {
if (const auto it = labels.find(label); it != labels.end()) {
return it->second;
}
return std::nullopt;
}
const std::string &ShardMap::GetLabelName(const LabelId label) const {
if (const auto it =
std::ranges::find_if(labels, [label](const auto &name_id_pair) { return name_id_pair.second == label; });
it != labels.end()) {
return it->first;
}
throw utils::BasicException("GetLabelName fails on the given label id!");
}
std::optional<PropertyId> ShardMap::GetPropertyId(const std::string &property_name) const {
if (const auto it = properties.find(property_name); it != properties.end()) {
return it->second;
}
return std::nullopt;
}
const std::string &ShardMap::GetPropertyName(const PropertyId property) const {
if (const auto it = std::ranges::find_if(
properties, [property](const auto &name_id_pair) { return name_id_pair.second == property; });
it != properties.end()) {
return it->first;
}
throw utils::BasicException("PropertyId not found!");
}
std::optional<EdgeTypeId> ShardMap::GetEdgeTypeId(const std::string &edge_type) const {
if (const auto it = edge_types.find(edge_type); it != edge_types.end()) {
return it->second;
}
return std::nullopt;
}
const std::string &ShardMap::GetEdgeTypeName(const EdgeTypeId property) const {
if (const auto it = std::ranges::find_if(
edge_types, [property](const auto &name_id_pair) { return name_id_pair.second == property; });
it != edge_types.end()) {
return it->first;
}
throw utils::BasicException("EdgeTypeId not found!");
}
Shards ShardMap::GetShardsForRange(const LabelName &label_name, const PrimaryKey &start_key,
const PrimaryKey &end_key) const {
MG_ASSERT(start_key <= end_key);
MG_ASSERT(labels.contains(label_name));
LabelId label_id = labels.at(label_name);
const auto &label_space = label_spaces.at(label_id);
const auto &shards_for_label = label_space.shards;
MG_ASSERT(shards_for_label.begin()->first <= start_key,
"the ShardMap must always contain a minimal key that is less than or equal to any requested key");
auto it = std::prev(shards_for_label.upper_bound(start_key));
const auto end_it = shards_for_label.upper_bound(end_key);
Shards shards{};
std::copy(it, end_it, std::inserter(shards, shards.end()));
return shards;
}
ShardMetadata ShardMap::GetShardForKey(const LabelName &label_name, const PrimaryKey &key) const {
MG_ASSERT(labels.contains(label_name));
LabelId label_id = labels.at(label_name);
const auto &label_space = label_spaces.at(label_id);
MG_ASSERT(label_space.shards.begin()->first <= key,
"the ShardMap must always contain a minimal key that is less than or equal to any requested key");
return std::prev(label_space.shards.upper_bound(key))->second;
}
ShardMetadata ShardMap::GetShardForKey(const LabelId &label_id, const PrimaryKey &key) const {
MG_ASSERT(label_spaces.contains(label_id));
const auto &label_space = label_spaces.at(label_id);
MG_ASSERT(label_space.shards.begin()->first <= key,
"the ShardMap must always contain a minimal key that is less than or equal to any requested key");
return std::prev(label_space.shards.upper_bound(key))->second;
}
PropertyMap ShardMap::AllocatePropertyIds(const std::vector<PropertyName> &new_properties) {
PropertyMap ret{};
bool mutated = false;
for (const auto &property_name : new_properties) {
if (properties.contains(property_name)) {
auto property_id = properties.at(property_name);
ret.emplace(property_name, property_id);
} else {
mutated = true;
const PropertyId property_id = PropertyId::FromUint(++max_property_id);
ret.emplace(property_name, property_id);
properties.emplace(property_name, property_id);
}
}
if (mutated) {
IncrementShardMapVersion();
}
return ret;
}
EdgeTypeIdMap ShardMap::AllocateEdgeTypeIds(const std::vector<EdgeTypeName> &new_edge_types) {
EdgeTypeIdMap ret;
bool mutated = false;
for (const auto &edge_type_name : new_edge_types) {
if (edge_types.contains(edge_type_name)) {
auto edge_type_id = edge_types.at(edge_type_name);
ret.emplace(edge_type_name, edge_type_id);
} else {
mutated = true;
const EdgeTypeId edge_type_id = EdgeTypeId::FromUint(++max_edge_type_id);
ret.emplace(edge_type_name, edge_type_id);
edge_types.emplace(edge_type_name, edge_type_id);
}
}
if (mutated) {
IncrementShardMapVersion();
}
return ret;
}
bool ShardMap::ClusterInitialized() const {
for (const auto &[label_id, label_space] : label_spaces) {
for (const auto &[low_key, shard] : label_space.shards) {
if (shard.peers.size() < label_space.replication_factor) {
spdlog::info("label_space below desired replication factor");
return false;
}
for (const auto &aas : shard.peers) {
if (aas.status != Status::CONSENSUS_PARTICIPANT) {
spdlog::info("shard member not yet a CONSENSUS_PARTICIPANT");
return false;
}
}
}
}
return true;
}
} // namespace memgraph::coordinator

View File

@@ -1,204 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <algorithm>
#include <limits>
#include <map>
#include <set>
#include <vector>
#include <boost/uuid/uuid.hpp>
#include <boost/uuid/uuid_generators.hpp>
#include "common/types.hpp"
#include "coordinator/hybrid_logical_clock.hpp"
#include "io/address.hpp"
#include "storage/v3/config.hpp"
#include "storage/v3/id_types.hpp"
#include "storage/v3/name_id_mapper.hpp"
#include "storage/v3/property_value.hpp"
#include "storage/v3/schemas.hpp"
#include "storage/v3/temporal.hpp"
#include "utils/exceptions.hpp"
#include "utils/print_helpers.hpp"
namespace memgraph::coordinator {
constexpr int64_t kNotExistingId{0};
using memgraph::io::Address;
using memgraph::storage::v3::Config;
using memgraph::storage::v3::EdgeTypeId;
using memgraph::storage::v3::LabelId;
using memgraph::storage::v3::PropertyId;
using memgraph::storage::v3::PropertyValue;
using memgraph::storage::v3::SchemaProperty;
enum class Status : uint8_t {
CONSENSUS_PARTICIPANT,
INITIALIZING,
// TODO(tyler) this will possibly have more states,
// depending on the reconfiguration protocol that we
// implement.
};
struct AddressAndStatus {
memgraph::io::Address address;
Status status;
friend bool operator<(const AddressAndStatus &lhs, const AddressAndStatus &rhs) { return lhs.address < rhs.address; }
friend std::ostream &operator<<(std::ostream &in, const AddressAndStatus &address_and_status) {
in << "AddressAndStatus { address: ";
in << address_and_status.address;
if (address_and_status.status == Status::CONSENSUS_PARTICIPANT) {
in << ", status: CONSENSUS_PARTICIPANT }";
} else {
in << ", status: INITIALIZING }";
}
return in;
}
friend bool operator==(const AddressAndStatus &lhs, const AddressAndStatus &rhs) {
return lhs.address == rhs.address;
}
};
using PrimaryKey = std::vector<PropertyValue>;
struct ShardMetadata {
std::vector<AddressAndStatus> peers;
uint64_t version;
friend std::ostream &operator<<(std::ostream &in, const ShardMetadata &shard) {
using utils::print_helpers::operator<<;
in << "ShardMetadata { peers: ";
in << shard.peers;
in << " version: ";
in << shard.version;
in << " }";
return in;
}
friend bool operator==(const ShardMetadata &lhs, const ShardMetadata &rhs) = default;
friend bool operator<(const ShardMetadata &lhs, const ShardMetadata &rhs) {
if (lhs.peers != rhs.peers) {
return lhs.peers < rhs.peers;
}
return lhs.version < rhs.version;
}
};
using Shards = std::map<PrimaryKey, ShardMetadata>;
using LabelName = std::string;
using PropertyName = std::string;
using EdgeTypeName = std::string;
using PropertyMap = std::map<PropertyName, PropertyId>;
using EdgeTypeIdMap = std::map<EdgeTypeName, EdgeTypeId>;
struct ShardToInitialize {
boost::uuids::uuid uuid;
LabelId label_id;
PrimaryKey min_key;
std::optional<PrimaryKey> max_key;
std::vector<SchemaProperty> schema;
Config config;
std::unordered_map<uint64_t, std::string> id_to_names;
};
PrimaryKey SchemaToMinKey(const std::vector<SchemaProperty> &schema);
struct LabelSpace {
std::vector<SchemaProperty> schema;
// Maps between the smallest primary key stored in the shard and the shard
std::map<PrimaryKey, ShardMetadata> shards;
size_t replication_factor;
friend std::ostream &operator<<(std::ostream &in, const LabelSpace &label_space) {
using utils::print_helpers::operator<<;
in << "LabelSpace { schema: ";
in << label_space.schema;
in << ", shards: ";
in << label_space.shards;
in << ", replication_factor: " << label_space.replication_factor << "}";
return in;
}
};
struct ShardMap {
Hlc shard_map_version;
uint64_t max_property_id{kNotExistingId};
uint64_t max_edge_type_id{kNotExistingId};
std::map<PropertyName, PropertyId> properties;
std::map<EdgeTypeName, EdgeTypeId> edge_types;
uint64_t max_label_id{kNotExistingId};
std::map<LabelId, LabelSpace> label_spaces;
std::map<LabelId, std::vector<SchemaProperty>> schemas;
std::map<LabelName, LabelId> labels;
[[nodiscard]] static ShardMap Parse(std::istream &input_stream);
friend std::ostream &operator<<(std::ostream &in, const ShardMap &shard_map);
Shards GetShardsForLabel(const LabelName &label) const;
std::vector<Shards> GetAllShards() const;
// TODO(gabor) later we will want to update the wallclock time with
// the given Io<impl>'s time as well
Hlc IncrementShardMapVersion() noexcept;
Hlc GetHlc() const noexcept;
std::unordered_map<uint64_t, std::string> IdToNames();
// Returns the shard UUIDs that have been assigned but not yet acknowledged for this storage manager
std::vector<ShardToInitialize> AssignShards(Address storage_manager, std::set<boost::uuids::uuid> initialized);
bool SplitShard(Hlc previous_shard_map_version, LabelId label_id, const PrimaryKey &key);
std::optional<LabelId> InitializeNewLabel(std::string label_name, std::vector<SchemaProperty> schema,
size_t replication_factor, Hlc last_shard_map_version);
void AddServer(Address server_address);
std::optional<LabelId> GetLabelId(const std::string &label) const;
// TODO(antaljanosbenjamin): Remove this and instead use NameIdMapper
const std::string &GetLabelName(LabelId label) const;
std::optional<PropertyId> GetPropertyId(const std::string &property_name) const;
const std::string &GetPropertyName(PropertyId property) const;
std::optional<EdgeTypeId> GetEdgeTypeId(const std::string &edge_type) const;
const std::string &GetEdgeTypeName(EdgeTypeId property) const;
Shards GetShardsForRange(const LabelName &label_name, const PrimaryKey &start_key, const PrimaryKey &end_key) const;
ShardMetadata GetShardForKey(const LabelName &label_name, const PrimaryKey &key) const;
ShardMetadata GetShardForKey(const LabelId &label_id, const PrimaryKey &key) const;
PropertyMap AllocatePropertyIds(const std::vector<PropertyName> &new_properties);
EdgeTypeIdMap AllocateEdgeTypeIds(const std::vector<EdgeTypeName> &new_edge_types);
/// Returns true if all shards have the desired number of replicas and they are in
/// the CONSENSUS_PARTICIPANT state. Note that this does not necessarily mean that
/// there is also an active leader for each shard.
bool ClusterInitialized() const;
};
} // namespace memgraph::coordinator

View File

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

View File

@@ -1,33 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#ifndef MG_AST_INCLUDE_PATH
#ifdef MG_CLANG_TIDY_CHECK
// NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
#include "query/v2/bindings/bindings.hpp"
#else
#error Missing AST include path
#endif
#endif
#ifndef MG_INJECTED_NAMESPACE_NAME
#ifdef MG_CLANG_TIDY_CHECK
#else
#error Missing AST namespace
#endif
#endif
#include MG_AST_INCLUDE_PATH
namespace memgraph::expr {
using namespace MG_INJECTED_NAMESPACE_NAME; // NOLINT(google-build-using-namespace)
} // namespace memgraph::expr

File diff suppressed because it is too large Load Diff

View File

@@ -1,271 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <iostream>
#include <type_traits>
#include "expr/ast.hpp"
#include "expr/typed_value.hpp"
#include "utils/algorithm.hpp"
#include "utils/logging.hpp"
#include "utils/string.hpp"
namespace memgraph::expr {
namespace detail {
template <typename T>
void PrintObject(std::ostream *out, const T &arg) {
static_assert(!std::is_convertible<T, Expression *>::value,
"This overload shouldn't be called with pointers convertible "
"to Expression *. This means your other PrintObject overloads aren't "
"being called for certain AST nodes when they should (or perhaps such "
"overloads don't exist yet).");
*out << arg;
}
inline void PrintObject(std::ostream *out, const std::string &str) { *out << utils::Escape(str); }
inline void PrintObject(std::ostream *out, Aggregation::Op op) { *out << Aggregation::OpToString(op); }
inline void PrintObject(std::ostream *out, Expression *expr);
inline void PrintObject(std::ostream *out, Identifier *expr) { PrintObject(out, static_cast<Expression *>(expr)); }
template <typename T>
void PrintObject(std::ostream *out, const std::vector<T> &vec) {
*out << "[";
utils::PrintIterable(*out, vec, ", ", [](auto &stream, const auto &item) { PrintObject(&stream, item); });
*out << "]";
}
template <typename T>
void PrintObject(std::ostream *out, const std::vector<T, utils::Allocator<T>> &vec) {
*out << "[";
utils::PrintIterable(*out, vec, ", ", [](auto &stream, const auto &item) { PrintObject(&stream, item); });
*out << "]";
}
template <typename K, typename V>
void PrintObject(std::ostream *out, const std::map<K, V> &map) {
*out << "{";
utils::PrintIterable(*out, map, ", ", [](auto &stream, const auto &item) {
PrintObject(&stream, item.first);
stream << ": ";
PrintObject(&stream, item.second);
});
*out << "}";
}
template <typename T>
void PrintObject(std::ostream *out, const utils::pmr::map<utils::pmr::string, T> &map) {
*out << "{";
utils::PrintIterable(*out, map, ", ", [](auto &stream, const auto &item) {
PrintObject(&stream, item.first);
stream << ": ";
PrintObject(&stream, item.second);
});
*out << "}";
}
template <typename T1, typename T2, typename T3>
inline void PrintObject(std::ostream *out, const TypedValueT<T1, T2, T3> &value) {
using TypedValue = TypedValueT<T1, T2, T3>;
switch (value.type()) {
case TypedValue::Type::Null:
*out << "null";
break;
case TypedValue::Type::String:
PrintObject(out, value.ValueString());
break;
case TypedValue::Type::Bool:
*out << (value.ValueBool() ? "true" : "false");
break;
case TypedValue::Type::Int:
PrintObject(out, value.ValueInt());
break;
case TypedValue::Type::Double:
PrintObject(out, value.ValueDouble());
break;
case TypedValue::Type::List:
PrintObject(out, value.ValueList());
break;
case TypedValue::Type::Map:
PrintObject(out, value.ValueMap());
break;
case TypedValue::Type::Date:
PrintObject(out, value.ValueDate());
break;
case TypedValue::Type::Duration:
PrintObject(out, value.ValueDuration());
break;
case TypedValue::Type::LocalTime:
PrintObject(out, value.ValueLocalTime());
break;
case TypedValue::Type::LocalDateTime:
PrintObject(out, value.ValueLocalDateTime());
break;
default:
MG_ASSERT(false, "PrintObject(std::ostream *out, const TypedValue &value) should not reach here");
}
}
template <typename T>
void PrintOperatorArgs(std::ostream *out, const T &arg) {
*out << " ";
PrintObject(out, arg);
*out << ")";
}
template <typename T, typename... Ts>
void PrintOperatorArgs(std::ostream *out, const T &arg, const Ts &...args) {
*out << " ";
PrintObject(out, arg);
PrintOperatorArgs(out, args...);
}
template <typename... Ts>
void PrintOperator(std::ostream *out, const std::string &name, const Ts &...args) {
*out << "(" << name;
PrintOperatorArgs(out, args...);
}
} // namespace detail
class ExpressionPrettyPrinter : public ExpressionVisitor<void> {
public:
explicit ExpressionPrettyPrinter(std::ostream *out) : out_(out) {}
// Unary operators
// NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
#define UNARY_OPERATOR_VISIT(OP_NODE, OP_STR) \
/* NOLINTNEXTLINE(bugprone-macro-parentheses) */ \
void Visit(OP_NODE &op) override { detail::PrintOperator(out_, OP_STR, op.expression_); }
UNARY_OPERATOR_VISIT(NotOperator, "Not");
UNARY_OPERATOR_VISIT(UnaryPlusOperator, "+");
UNARY_OPERATOR_VISIT(UnaryMinusOperator, "-");
UNARY_OPERATOR_VISIT(IsNullOperator, "IsNull");
#undef UNARY_OPERATOR_VISIT
// Binary operators
// NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
#define BINARY_OPERATOR_VISIT(OP_NODE, OP_STR) \
/* NOLINTNEXTLINE(bugprone-macro-parentheses) */ \
void Visit(OP_NODE &op) override { detail::PrintOperator(out_, OP_STR, op.expression1_, op.expression2_); }
BINARY_OPERATOR_VISIT(OrOperator, "Or");
BINARY_OPERATOR_VISIT(XorOperator, "Xor");
BINARY_OPERATOR_VISIT(AndOperator, "And");
BINARY_OPERATOR_VISIT(AdditionOperator, "+");
BINARY_OPERATOR_VISIT(SubtractionOperator, "-");
BINARY_OPERATOR_VISIT(MultiplicationOperator, "*");
BINARY_OPERATOR_VISIT(DivisionOperator, "/");
BINARY_OPERATOR_VISIT(ModOperator, "%");
BINARY_OPERATOR_VISIT(NotEqualOperator, "!=");
BINARY_OPERATOR_VISIT(EqualOperator, "==");
BINARY_OPERATOR_VISIT(LessOperator, "<");
BINARY_OPERATOR_VISIT(GreaterOperator, ">");
BINARY_OPERATOR_VISIT(LessEqualOperator, "<=");
BINARY_OPERATOR_VISIT(GreaterEqualOperator, ">=");
BINARY_OPERATOR_VISIT(InListOperator, "In");
BINARY_OPERATOR_VISIT(SubscriptOperator, "Subscript");
#undef BINARY_OPERATOR_VISIT
// Other
void Visit(ListSlicingOperator &op) override {
detail::PrintOperator(out_, "ListSlicing", op.list_, op.lower_bound_, op.upper_bound_);
}
void Visit(IfOperator &op) override {
detail::PrintOperator(out_, "If", op.condition_, op.then_expression_, op.else_expression_);
}
void Visit(ListLiteral &op) override { detail::PrintOperator(out_, "ListLiteral", op.elements_); }
void Visit(MapLiteral &op) override {
std::map<std::string, Expression *> map;
for (const auto &kv : op.elements_) {
map[kv.first.name] = kv.second;
}
detail::PrintObject(out_, map);
}
void Visit(LabelsTest &op) override { detail::PrintOperator(out_, "LabelsTest", op.expression_); }
void Visit(Aggregation &op) override { detail::PrintOperator(out_, "Aggregation", op.op_); }
void Visit(Function &op) override { detail::PrintOperator(out_, "Function", op.function_name_, op.arguments_); }
void Visit(Reduce &op) override {
detail::PrintOperator(out_, "Reduce", op.accumulator_, op.initializer_, op.identifier_, op.list_, op.expression_);
}
void Visit(Coalesce &op) override { detail::PrintOperator(out_, "Coalesce", op.expressions_); }
void Visit(Extract &op) override { detail::PrintOperator(out_, "Extract", op.identifier_, op.list_, op.expression_); }
void Visit(All &op) override {
detail::PrintOperator(out_, "All", op.identifier_, op.list_expression_, op.where_->expression_);
}
void Visit(Single &op) override {
detail::PrintOperator(out_, "Single", op.identifier_, op.list_expression_, op.where_->expression_);
}
void Visit(Any &op) override {
detail::PrintOperator(out_, "Any", op.identifier_, op.list_expression_, op.where_->expression_);
}
void Visit(None &op) override {
detail::PrintOperator(out_, "None", op.identifier_, op.list_expression_, op.where_->expression_);
}
void Visit(Identifier &op) override { detail::PrintOperator(out_, "Identifier", op.name_); }
void Visit(PrimitiveLiteral &op) override { detail::PrintObject(out_, op.value_); }
void Visit(PropertyLookup &op) override {
detail::PrintOperator(out_, "PropertyLookup", op.expression_, op.property_.name);
}
void Visit(ParameterLookup &op) override { detail::PrintOperator(out_, "ParameterLookup", op.token_position_); }
void Visit(NamedExpression &op) override { detail::PrintOperator(out_, "NamedExpression", op.name_, op.expression_); }
void Visit(RegexMatch &op) override { detail::PrintOperator(out_, "=~", op.string_expr_, op.regex_); }
private:
std::ostream *out_;
};
namespace detail {
inline void PrintObject(std::ostream *out, Expression *expr) {
if (expr) {
ExpressionPrettyPrinter printer{out};
expr->Accept(printer);
} else {
*out << "<null>";
}
}
} // namespace detail
inline void PrintExpression(Expression *expr, std::ostream *out) {
ExpressionPrettyPrinter printer{out};
expr->Accept(printer);
}
inline void PrintExpression(NamedExpression *expr, std::ostream *out) {
ExpressionPrettyPrinter printer{out};
expr->Accept(printer);
}
} // namespace memgraph::expr

View File

@@ -1,279 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <iostream>
#include <type_traits>
#include "expr/ast.hpp"
#include "expr/typed_value.hpp"
#include "utils/algorithm.hpp"
#include "utils/logging.hpp"
#include "utils/string.hpp"
namespace memgraph::expr {
inline constexpr const char *identifier_node_symbol = "MG_SYMBOL_NODE";
inline constexpr const char *identifier_edge_symbol = "MG_SYMBOL_EDGE";
namespace detail {
template <typename T>
void PrintObject(std::ostream *out, const T &arg) {
static_assert(!std::is_convertible<T, Expression *>::value,
"This overload shouldn't be called with pointers convertible "
"to Expression *. This means your other PrintObject overloads aren't "
"being called for certain AST nodes when they should (or perhaps such "
"overloads don't exist yet).");
*out << arg;
}
inline void PrintObject(std::ostream *out, const std::string &str) { *out << str; }
inline void PrintObject(std::ostream * /*out*/, Aggregation::Op /*op*/) {
throw utils::NotYetImplemented("PrintObject: Aggregation::Op");
}
inline void PrintObject(std::ostream * /*out*/, Expression * /*expr*/);
inline void PrintObject(std::ostream *out, Identifier *expr) { PrintObject(out, static_cast<Expression *>(expr)); }
template <typename T>
void PrintObject(std::ostream * /*out*/, const std::vector<T> & /*vec*/) {
throw utils::NotYetImplemented("PrintObject: vector<T>");
}
template <typename T>
void PrintObject(std::ostream * /*out*/, const std::vector<T, utils::Allocator<T>> & /*vec*/) {
throw utils::NotYetImplemented("PrintObject: vector<T, utils::Allocator<T>>");
}
template <typename K, typename V>
void PrintObject(std::ostream * /*out*/, const std::map<K, V> & /*map*/) {
throw utils::NotYetImplemented("PrintObject: map<K, V>");
}
template <typename T>
void PrintObject(std::ostream * /*out*/, const utils::pmr::map<utils::pmr::string, T> & /*map*/) {
throw utils::NotYetImplemented("PrintObject: map<utils::pmr::string, V>");
}
template <typename T1, typename T2, typename T3>
inline void PrintObject(std::ostream *out, const TypedValueT<T1, T2, T3> &value) {
using TypedValue = TypedValueT<T1, T2, T3>;
switch (value.type()) {
case TypedValue::Type::Null:
*out << "null";
break;
case TypedValue::Type::String:
PrintObject(out, value.ValueString());
break;
case TypedValue::Type::Bool:
*out << (value.ValueBool() ? "true" : "false");
break;
case TypedValue::Type::Int:
PrintObject(out, value.ValueInt());
break;
case TypedValue::Type::Double:
PrintObject(out, value.ValueDouble());
break;
case TypedValue::Type::List:
PrintObject(out, value.ValueList());
break;
case TypedValue::Type::Map:
PrintObject(out, value.ValueMap());
break;
case TypedValue::Type::Date:
PrintObject(out, value.ValueDate());
break;
case TypedValue::Type::Duration:
PrintObject(out, value.ValueDuration());
break;
case TypedValue::Type::LocalTime:
PrintObject(out, value.ValueLocalTime());
break;
case TypedValue::Type::LocalDateTime:
PrintObject(out, value.ValueLocalDateTime());
break;
default:
MG_ASSERT(false, "PrintObject(std::ostream *out, const TypedValue &value) should not reach here");
}
}
template <typename T>
void PrintOperatorArgs(const std::string & /*name*/, std::ostream *out, bool with_parenthesis, const T &arg) {
PrintObject(out, arg);
if (with_parenthesis) {
*out << ")";
}
}
template <typename T, typename... Ts>
void PrintOperatorArgs(const std::string &name, std::ostream *out, bool with_parenthesis, const T &arg,
const Ts &...args) {
PrintObject(out, arg);
*out << " " << name << " ";
PrintOperatorArgs(name, out, with_parenthesis, args...);
}
template <typename... Ts>
void PrintOperator(const std::string &name, std::ostream *out, bool with_parenthesis, const Ts &...args) {
if (with_parenthesis) {
*out << "(";
}
PrintOperatorArgs(name, out, with_parenthesis, args...);
}
// new
template <typename T>
void PrintOperatorArgs(std::ostream *out, const T &arg) {
PrintObject(out, arg);
}
template <typename T, typename... Ts>
void PrintOperatorArgs(std::ostream *out, const T &arg, const Ts &...args) {
PrintObject(out, arg);
PrintOperatorArgs(out, args...);
}
template <typename... Ts>
void PrintOperator(std::ostream *out, const Ts &...args) {
PrintOperatorArgs(out, args...);
}
} // namespace detail
class ExpressionPrettyPrinter : public ExpressionVisitor<void> {
public:
explicit ExpressionPrettyPrinter(std::ostream *out) : out_(out) {}
// Unary operators
// NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
#define UNARY_OPERATOR_VISIT(OP_NODE, OP_STR) \
/* NOLINTNEXTLINE(bugprone-macro-parentheses) */ \
void Visit(OP_NODE &op) override { detail::PrintOperator(OP_STR, out_, false /*with_parenthesis*/, op.expression_); }
UNARY_OPERATOR_VISIT(NotOperator, "Not");
UNARY_OPERATOR_VISIT(UnaryPlusOperator, "+");
UNARY_OPERATOR_VISIT(UnaryMinusOperator, "-");
UNARY_OPERATOR_VISIT(IsNullOperator, "IsNull");
#undef UNARY_OPERATOR_VISIT
// Binary operators
// NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
#define BINARY_OPERATOR_VISIT(OP_NODE, OP_STR) \
/* NOLINTNEXTLINE(bugprone-macro-parentheses) */ \
void Visit(OP_NODE &op) override { \
detail::PrintOperator(OP_STR, out_, true /*with_parenthesis*/, op.expression1_, op.expression2_); \
}
// NOLINTNEXTLINE(cppcoreguidelines-macro-usage)
#define BINARY_OPERATOR_VISIT_NOT_IMPL(OP_NODE, OP_STR) \
/* NOLINTNEXTLINE(bugprone-macro-parentheses) */ \
void Visit(OP_NODE & /*op*/) override { throw utils::NotYetImplemented("OP_NODE"); }
BINARY_OPERATOR_VISIT(OrOperator, "Or");
BINARY_OPERATOR_VISIT(XorOperator, "Xor");
BINARY_OPERATOR_VISIT(AndOperator, "And");
BINARY_OPERATOR_VISIT(AdditionOperator, "+");
BINARY_OPERATOR_VISIT(SubtractionOperator, "-");
BINARY_OPERATOR_VISIT(MultiplicationOperator, "*");
BINARY_OPERATOR_VISIT(DivisionOperator, "/");
BINARY_OPERATOR_VISIT(ModOperator, "%");
BINARY_OPERATOR_VISIT(NotEqualOperator, "!=");
BINARY_OPERATOR_VISIT(EqualOperator, "=");
BINARY_OPERATOR_VISIT(LessOperator, "<");
BINARY_OPERATOR_VISIT(GreaterOperator, ">");
BINARY_OPERATOR_VISIT(LessEqualOperator, "<=");
BINARY_OPERATOR_VISIT(GreaterEqualOperator, ">=");
BINARY_OPERATOR_VISIT_NOT_IMPL(InListOperator, "In");
BINARY_OPERATOR_VISIT_NOT_IMPL(SubscriptOperator, "Subscript");
#undef BINARY_OPERATOR_VISIT
#undef BINARY_OPERATOR_VISIT_NOT_IMPL
// Other
void Visit(ListSlicingOperator & /*op*/) override { throw utils::NotYetImplemented("ListSlicingOperator"); }
void Visit(IfOperator & /*op*/) override { throw utils::NotYetImplemented("IfOperator"); }
void Visit(ListLiteral & /*op*/) override { throw utils::NotYetImplemented("ListLiteral"); }
void Visit(MapLiteral & /*op*/) override { throw utils::NotYetImplemented("MapLiteral"); }
void Visit(LabelsTest & /*op*/) override { throw utils::NotYetImplemented("LabelsTest"); }
void Visit(Aggregation & /*op*/) override { throw utils::NotYetImplemented("Aggregation"); }
void Visit(Function & /*op*/) override { throw utils::NotYetImplemented("Function"); }
void Visit(Reduce & /*op*/) override { throw utils::NotYetImplemented("Reduce"); }
void Visit(Coalesce & /*op*/) override { throw utils::NotYetImplemented("Coalesce"); }
void Visit(Extract & /*op*/) override { throw utils::NotYetImplemented("Extract"); }
void Visit(All & /*op*/) override { throw utils::NotYetImplemented("All"); }
void Visit(Single & /*op*/) override { throw utils::NotYetImplemented("Single"); }
void Visit(Any & /*op*/) override { throw utils::NotYetImplemented("Any"); }
void Visit(None & /*op*/) override { throw utils::NotYetImplemented("None"); }
void Visit(Identifier &op) override {
auto is_node = true;
auto is_edge = false;
auto is_other = false;
if (is_node) {
detail::PrintOperator(out_, identifier_node_symbol);
} else if (is_edge) {
detail::PrintOperator(out_, identifier_edge_symbol);
} else {
MG_ASSERT(is_other);
detail::PrintOperator(out_, op.name_);
}
}
void Visit(PrimitiveLiteral &op) override { detail::PrintObject(out_, op.value_); }
void Visit(PropertyLookup &op) override { detail::PrintOperator(out_, op.expression_, ".", op.property_.name); }
void Visit(ParameterLookup & /*op*/) override { throw utils::NotYetImplemented("ParameterLookup"); }
void Visit(NamedExpression & /*op*/) override { throw utils::NotYetImplemented("NamedExpression"); }
void Visit(RegexMatch & /*op*/) override { throw utils::NotYetImplemented("RegexMatch"); }
private:
std::ostream *out_;
};
namespace detail {
inline void PrintObject(std::ostream *out, Expression *expr) {
if (expr) {
ExpressionPrettyPrinter printer{out};
expr->Accept(printer);
} else {
*out << "<null>";
}
}
} // namespace detail
inline void PrintExpressionToOriginalAndReplaceNodeAndEdgeSymbols(Expression *expr, std::ostream *out) {
ExpressionPrettyPrinter printer{out};
expr->Accept(printer);
}
inline std::string ExpressiontoStringWhileReplacingNodeAndEdgeSymbols(Expression *expr) {
std::ostringstream ss;
expr::PrintExpressionToOriginalAndReplaceNodeAndEdgeSymbols(expr, &ss);
return ss.str();
}
} // namespace memgraph::expr

View File

@@ -1,52 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "utils/exceptions.hpp"
namespace memgraph::expr {
class SyntaxException : public utils::BasicException {
public:
using utils::BasicException::BasicException;
SyntaxException() : SyntaxException("") {}
};
class SemanticException : public utils::BasicException {
public:
using utils::BasicException::BasicException;
SemanticException() : BasicException("") {}
};
class ExpressionRuntimeException : public utils::BasicException {
public:
using utils::BasicException::BasicException;
};
class RedeclareVariableError : public SemanticException {
public:
explicit RedeclareVariableError(const std::string &name) : SemanticException("Redeclaring variable: " + name + ".") {}
};
class UnboundVariableError : public SemanticException {
public:
explicit UnboundVariableError(const std::string &name) : SemanticException("Unbound variable: " + name + ".") {}
};
class TypeMismatchError : public SemanticException {
public:
TypeMismatchError(const std::string &name, const std::string &datum, const std::string &expected)
: SemanticException(fmt::format("Type mismatch: {} already defined as {}, expected {}.", name, datum, expected)) {
}
};
} // namespace memgraph::expr

View File

@@ -1,712 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
// Copyright 2017 Memgraph
//
// Created by Teon Banek on 11-03-2017
#pragma once
#include <algorithm>
#include <optional>
#include <ranges>
#include <unordered_map>
#include <unordered_set>
#include <variant>
#include <vector>
#include "expr/ast.hpp"
#include "expr/ast/ast_visitor.hpp"
#include "expr/exceptions.hpp"
#include "expr/semantic/symbol_table.hpp"
namespace memgraph::expr {
namespace detail {
inline std::unordered_map<std::string, Identifier *> GeneratePredefinedIdentifierMap(
const std::vector<Identifier *> &predefined_identifiers) {
std::unordered_map<std::string, Identifier *> identifier_map;
for (const auto &identifier : predefined_identifiers) {
identifier_map.emplace(identifier->name_, identifier);
}
return identifier_map;
}
} // namespace detail
/// Visits the AST and generates symbols for variables.
///
/// During the process of symbol generation, simple semantic checks are
/// performed. Such as, redeclaring a variable or conflicting expectations of
/// variable types.
class SymbolGenerator : public HierarchicalTreeVisitor {
public:
explicit SymbolGenerator(SymbolTable *symbol_table, const std::vector<Identifier *> &predefined_identifiers)
: symbol_table_(symbol_table),
predefined_identifiers_{detail::GeneratePredefinedIdentifierMap(predefined_identifiers)},
scopes_(1, Scope()) {}
using HierarchicalTreeVisitor::PostVisit;
using HierarchicalTreeVisitor::PreVisit;
using HierarchicalTreeVisitor::Visit;
using typename HierarchicalTreeVisitor::ReturnType;
// Query
bool PreVisit(SingleQuery & /*unused*/) override {
prev_return_names_ = curr_return_names_;
curr_return_names_.clear();
return true;
}
// Union
bool PreVisit(CypherUnion & /*unused*/) override {
scopes_.back() = Scope();
return true;
}
bool PostVisit(CypherUnion &cypher_union) override {
if (prev_return_names_ != curr_return_names_) {
throw SemanticException("All subqueries in an UNION must have the same column names.");
}
// create new symbols for the result of the union
for (const auto &name : curr_return_names_) {
auto symbol = CreateSymbol(name, false);
cypher_union.union_symbols_.push_back(symbol);
}
return true;
}
// Clauses
bool PreVisit(Create & /*unused*/) override {
scopes_.back().in_create = true;
return true;
}
bool PostVisit(Create & /*unused*/) override {
scopes_.back().in_create = false;
return true;
}
bool PreVisit(CallProcedure &call_proc) override {
for (auto *expr : call_proc.arguments_) {
expr->Accept(*this);
}
return false;
}
bool PostVisit(CallProcedure &call_proc) override {
for (auto *ident : call_proc.result_identifiers_) {
if (HasSymbolLocalScope(ident->name_)) {
throw RedeclareVariableError(ident->name_);
}
ident->MapTo(CreateSymbol(ident->name_, true));
}
return true;
}
bool PreVisit(LoadCsv & /*unused*/) override { return false; }
bool PostVisit(LoadCsv &load_csv) override {
if (HasSymbolLocalScope(load_csv.row_var_->name_)) {
throw RedeclareVariableError(load_csv.row_var_->name_);
}
load_csv.row_var_->MapTo(CreateSymbol(load_csv.row_var_->name_, true));
return true;
}
bool PreVisit(Return &ret) override {
auto &scope = scopes_.back();
scope.in_return = true;
VisitReturnBody(ret.body_);
scope.in_return = false;
return false; // We handled the traversal ourselves.
}
bool PostVisit(Return & /*unused*/) override {
for (const auto &name_symbol : scopes_.back().symbols) curr_return_names_.insert(name_symbol.first);
return true;
}
bool PreVisit(With &with) override {
auto &scope = scopes_.back();
scope.in_with = true;
VisitReturnBody(with.body_, with.where_);
scope.in_with = false;
return false; // We handled the traversal ourselves.
}
bool PreVisit(Where & /*unused*/) override {
scopes_.back().in_where = true;
return true;
}
bool PostVisit(Where & /*unused*/) override {
scopes_.back().in_where = false;
return true;
}
bool PreVisit(Merge & /*unused*/) override {
scopes_.back().in_merge = true;
return true;
}
bool PostVisit(Merge & /*unused*/) override {
scopes_.back().in_merge = false;
return true;
}
bool PostVisit(Unwind &unwind) override {
const auto &name = unwind.named_expression_->name_;
if (HasSymbolLocalScope(name)) {
throw RedeclareVariableError(name);
}
unwind.named_expression_->MapTo(CreateSymbol(name, true));
return true;
}
bool PreVisit(Match & /*unused*/) override {
scopes_.back().in_match = true;
return true;
}
bool PostVisit(Match & /*unused*/) override {
auto &scope = scopes_.back();
scope.in_match = false;
// Check variables in property maps after visiting Match, so that they can
// reference symbols out of bind order.
for (auto &ident : scope.identifiers_in_match) {
if (!HasSymbolLocalScope(ident->name_) && !ConsumePredefinedIdentifier(ident->name_))
throw UnboundVariableError(ident->name_);
ident->MapTo(scope.symbols[ident->name_]);
}
scope.identifiers_in_match.clear();
return true;
}
bool PreVisit(Foreach &for_each) override {
const auto &name = for_each.named_expression_->name_;
scopes_.emplace_back(Scope());
scopes_.back().in_foreach = true;
for_each.named_expression_->MapTo(
CreateSymbol(name, true, Symbol::Type::ANY, for_each.named_expression_->token_position_));
return true;
}
bool PostVisit(Foreach & /*unused*/) override {
scopes_.pop_back();
return true;
}
// Expressions
ReturnType Visit(Identifier &ident) override {
auto &scope = scopes_.back();
if (scope.in_skip || scope.in_limit) {
throw SemanticException("Variables are not allowed in {}.", scope.in_skip ? "SKIP" : "LIMIT");
}
Symbol symbol;
if (scope.in_pattern && !(scope.in_node_atom || scope.visiting_edge)) {
// If we are in the pattern, and outside of a node or an edge, the
// identifier is the pattern name.
symbol = GetOrCreateSymbolLocalScope(ident.name_, ident.user_declared_, Symbol::Type::PATH);
} else if (scope.in_pattern && scope.in_pattern_atom_identifier) {
// Patterns used to create nodes and edges cannot redeclare already
// established bindings. Declaration only happens in single node
// patterns and in edge patterns. OpenCypher example,
// `MATCH (n) CREATE (n)` should throw an error that `n` is already
// declared. While `MATCH (n) CREATE (n) -[:R]-> (n)` is allowed,
// since `n` now references the bound node instead of declaring it.
if ((scope.in_create_node || scope.in_create_edge) && HasSymbolLocalScope(ident.name_)) {
throw RedeclareVariableError(ident.name_);
}
auto type = Symbol::Type::VERTEX;
if (scope.visiting_edge) {
// Edge referencing is not allowed (like in Neo4j):
// `MATCH (n) - [r] -> (n) - [r] -> (n) RETURN r` is not allowed.
if (HasSymbolLocalScope(ident.name_)) {
throw RedeclareVariableError(ident.name_);
}
type = scope.visiting_edge->IsVariable() ? Symbol::Type::EDGE_LIST : Symbol::Type::EDGE;
}
symbol = GetOrCreateSymbolLocalScope(ident.name_, ident.user_declared_, type);
} else if (scope.in_pattern && !scope.in_pattern_atom_identifier && scope.in_match) {
if (scope.in_edge_range && scope.visiting_edge->identifier_->name_ == ident.name_) {
// Prevent variable path bounds to reference the identifier which is bound
// by the variable path itself.
throw UnboundVariableError(ident.name_);
}
// Variables in property maps or bounds of variable length path during MATCH
// can reference symbols bound later in the same MATCH. We collect them
// here, so that they can be checked after visiting Match.
scope.identifiers_in_match.emplace_back(&ident);
} else {
// Everything else references a bound symbol.
if (!HasSymbol(ident.name_) && !ConsumePredefinedIdentifier(ident.name_)) throw UnboundVariableError(ident.name_);
symbol = GetOrCreateSymbol(ident.name_, ident.user_declared_, Symbol::Type::ANY);
}
ident.MapTo(symbol);
return true;
}
ReturnType Visit(PrimitiveLiteral & /*unused*/) override { return true; }
ReturnType Visit(ParameterLookup & /*unused*/) override { return true; }
bool PreVisit(Aggregation &aggr) override {
auto &scope = scopes_.back();
// Check if the aggregation can be used in this context. This check should
// probably move to a separate phase, which checks if the query is well
// formed.
if ((!scope.in_return && !scope.in_with) || scope.in_order_by || scope.in_skip || scope.in_limit ||
scope.in_where) {
throw SemanticException("Aggregation functions are only allowed in WITH and RETURN.");
}
if (scope.in_aggregation) {
throw SemanticException(
"Using aggregation functions inside aggregation functions is not "
"allowed.");
}
if (scope.num_if_operators) {
// Neo allows aggregations here and produces very interesting behaviors.
// To simplify implementation at this moment we decided to completely
// disallow aggregations inside of the CASE.
// However, in some cases aggregation makes perfect sense, for example:
// CASE count(n) WHEN 10 THEN "YES" ELSE "NO" END.
// TODO: Rethink of allowing aggregations in some parts of the CASE
// construct.
throw SemanticException("Using aggregation functions inside of CASE is not allowed.");
}
// Create a virtual symbol for aggregation result.
// Currently, we only have aggregation operators which return numbers.
auto aggr_name = Aggregation::OpToString(aggr.op_) + std::to_string(aggr.symbol_pos_);
aggr.MapTo(CreateSymbol(aggr_name, false, Symbol::Type::NUMBER));
scope.in_aggregation = true;
scope.has_aggregation = true;
return true;
}
bool PostVisit(Aggregation & /*unused*/) override {
scopes_.back().in_aggregation = false;
return true;
}
bool PreVisit(IfOperator & /*unused*/) override {
++scopes_.back().num_if_operators;
return true;
}
bool PostVisit(IfOperator & /*unused*/) override {
--scopes_.back().num_if_operators;
return true;
}
bool PreVisit(All &all) override {
all.list_expression_->Accept(*this);
VisitWithIdentifiers(all.where_->expression_, {all.identifier_});
return false;
}
bool PreVisit(Single &single) override {
single.list_expression_->Accept(*this);
VisitWithIdentifiers(single.where_->expression_, {single.identifier_});
return false;
}
bool PreVisit(Any &any) override {
any.list_expression_->Accept(*this);
VisitWithIdentifiers(any.where_->expression_, {any.identifier_});
return false;
}
bool PreVisit(None &none) override {
none.list_expression_->Accept(*this);
VisitWithIdentifiers(none.where_->expression_, {none.identifier_});
return false;
}
bool PreVisit(Reduce &reduce) override {
reduce.initializer_->Accept(*this);
reduce.list_->Accept(*this);
VisitWithIdentifiers(reduce.expression_, {reduce.accumulator_, reduce.identifier_});
return false;
}
bool PreVisit(Extract &extract) override {
extract.list_->Accept(*this);
VisitWithIdentifiers(extract.expression_, {extract.identifier_});
return false;
}
// Pattern and its subparts.
bool PreVisit(Pattern &pattern) override {
auto &scope = scopes_.back();
scope.in_pattern = true;
if ((scope.in_create || scope.in_merge) && pattern.atoms_.size() == 1U) {
MG_ASSERT(utils::IsSubtype(*pattern.atoms_[0], NodeAtom::kType), "Expected a single NodeAtom in Pattern");
scope.in_create_node = true;
}
return true;
}
bool PostVisit(Pattern & /*unused*/) override {
auto &scope = scopes_.back();
scope.in_pattern = false;
scope.in_create_node = false;
return true;
}
bool PreVisit(NodeAtom &node_atom) override {
auto &scope = scopes_.back();
auto check_node_semantic = [&node_atom, &scope, this](const bool props_or_labels) {
const auto &node_name = node_atom.identifier_->name_;
if ((scope.in_create || scope.in_merge) && props_or_labels && HasSymbolLocalScope(node_name)) {
throw SemanticException("Cannot create node '" + node_name +
"' with labels or properties, because it is already declared.");
}
scope.in_pattern_atom_identifier = true;
node_atom.identifier_->Accept(*this);
scope.in_pattern_atom_identifier = false;
};
scope.in_node_atom = true;
if (auto *properties = std::get_if<std::unordered_map<PropertyIx, Expression *>>(&node_atom.properties_)) {
bool props_or_labels = !properties->empty() || !node_atom.labels_.empty();
check_node_semantic(props_or_labels);
for (auto kv : *properties) {
kv.second->Accept(*this);
}
return false;
}
auto &properties_parameter = std::get<ParameterLookup *>(node_atom.properties_);
bool props_or_labels = !properties_parameter || !node_atom.labels_.empty();
check_node_semantic(props_or_labels);
properties_parameter->Accept(*this);
return false;
}
bool PostVisit(NodeAtom & /*unused*/) override {
scopes_.back().in_node_atom = false;
return true;
}
bool PreVisit(EdgeAtom &edge_atom) override {
auto &scope = scopes_.back();
scope.visiting_edge = &edge_atom;
if (scope.in_create || scope.in_merge) {
scope.in_create_edge = true;
if (edge_atom.edge_types_.size() != 1U) {
throw SemanticException(
"A single relationship type must be specified "
"when creating an edge.");
}
if (scope.in_create && // Merge allows bidirectionality
edge_atom.direction_ == EdgeAtom::Direction::BOTH) {
throw SemanticException(
"Bidirectional relationship are not supported "
"when creating an edge");
}
if (edge_atom.IsVariable()) {
throw SemanticException(
"Variable length relationships are not supported when creating an "
"edge.");
}
}
if (auto *properties = std::get_if<std::unordered_map<PropertyIx, Expression *>>(&edge_atom.properties_)) {
for (auto kv : *properties) {
kv.second->Accept(*this);
}
} else {
std::get<ParameterLookup *>(edge_atom.properties_)->Accept(*this);
}
if (edge_atom.IsVariable()) {
scope.in_edge_range = true;
if (edge_atom.lower_bound_) {
edge_atom.lower_bound_->Accept(*this);
}
if (edge_atom.upper_bound_) {
edge_atom.upper_bound_->Accept(*this);
}
scope.in_edge_range = false;
scope.in_pattern = false;
if (edge_atom.filter_lambda_.expression) {
VisitWithIdentifiers(edge_atom.filter_lambda_.expression,
{edge_atom.filter_lambda_.inner_edge, edge_atom.filter_lambda_.inner_node});
} else {
// Create inner symbols, but don't bind them in scope, since they are to
// be used in the missing filter expression.
auto *inner_edge = edge_atom.filter_lambda_.inner_edge;
inner_edge->MapTo(
symbol_table_->CreateSymbol(inner_edge->name_, inner_edge->user_declared_, Symbol::Type::EDGE));
auto *inner_node = edge_atom.filter_lambda_.inner_node;
inner_node->MapTo(
symbol_table_->CreateSymbol(inner_node->name_, inner_node->user_declared_, Symbol::Type::VERTEX));
}
if (edge_atom.weight_lambda_.expression) {
VisitWithIdentifiers(edge_atom.weight_lambda_.expression,
{edge_atom.weight_lambda_.inner_edge, edge_atom.weight_lambda_.inner_node});
}
scope.in_pattern = true;
}
scope.in_pattern_atom_identifier = true;
edge_atom.identifier_->Accept(*this);
scope.in_pattern_atom_identifier = false;
if (edge_atom.total_weight_) {
if (HasSymbolLocalScope(edge_atom.total_weight_->name_)) {
throw RedeclareVariableError(edge_atom.total_weight_->name_);
}
edge_atom.total_weight_->MapTo(GetOrCreateSymbolLocalScope(
edge_atom.total_weight_->name_, edge_atom.total_weight_->user_declared_, Symbol::Type::NUMBER));
}
return false;
}
bool PostVisit(EdgeAtom & /*unused*/) override {
auto &scope = scopes_.back();
scope.visiting_edge = nullptr;
scope.in_create_edge = false;
return true;
}
private:
// Scope stores the state of where we are when visiting the AST and a map of
// names to symbols.
struct Scope {
bool in_pattern{false};
bool in_merge{false};
bool in_create{false};
// in_create_node is true if we are creating or merging *only* a node.
// Therefore, it is *not* equivalent to (in_create || in_merge) &&
// in_node_atom.
bool in_create_node{false};
// True if creating an edge;
// shortcut for (in_create || in_merge) && visiting_edge.
bool in_create_edge{false};
bool in_node_atom{false};
EdgeAtom *visiting_edge{nullptr};
bool in_aggregation{false};
bool in_return{false};
bool in_with{false};
bool in_skip{false};
bool in_limit{false};
bool in_order_by{false};
bool in_where{false};
bool in_match{false};
bool in_foreach{false};
// True when visiting a pattern atom (node or edge) identifier, which can be
// reused or created in the pattern itself.
bool in_pattern_atom_identifier{false};
// True when visiting range bounds of a variable path.
bool in_edge_range{false};
// True if the return/with contains an aggregation in any named expression.
bool has_aggregation{false};
// Map from variable names to symbols.
std::map<std::string, Symbol> symbols;
// Identifiers found in property maps of patterns or as variable length path
// bounds in a single Match clause. They need to be checked after visiting
// Match. Identifiers created by naming vertices, edges and paths are *not*
// stored in here.
std::vector<Identifier *> identifiers_in_match;
// Number of nested IfOperators.
int num_if_operators{0};
};
inline static std::optional<Symbol> FindSymbolInScope(const std::string &name, const Scope &scope,
Symbol::Type type) {
if (auto it = scope.symbols.find(name); it != scope.symbols.end()) {
const auto &symbol = it->second;
// Unless we have `ANY` type, check that types match.
if (type != Symbol::Type::ANY && symbol.type() != Symbol::Type::ANY && type != symbol.type()) {
throw TypeMismatchError(name, Symbol::TypeToString(symbol.type()), Symbol::TypeToString(type));
}
return symbol;
}
return std::nullopt;
}
bool HasSymbol(const std::string &name) const {
return std::ranges::any_of(scopes_, [&name](const auto &scope) { return scope.symbols.contains(name); });
}
bool HasSymbolLocalScope(const std::string &name) const { return scopes_.back().symbols.contains(name); }
// @return true if it added a predefined identifier with that name
bool ConsumePredefinedIdentifier(const std::string &name) {
auto it = predefined_identifiers_.find(name);
if (it == predefined_identifiers_.end()) {
return false;
}
// we can only use the predefined identifier in a single scope so we remove it after creating
// a symbol for it
auto &identifier = it->second;
MG_ASSERT(!identifier->user_declared_, "Predefined symbols cannot be user declared!");
identifier->MapTo(CreateSymbol(identifier->name_, identifier->user_declared_));
predefined_identifiers_.erase(it);
return true;
}
// Returns a freshly generated symbol. Previous mapping of the same name to a
// different symbol is replaced with the new one.
Symbol CreateSymbol(const std::string &name, bool user_declared, Symbol::Type type = Symbol::Type::ANY,
int token_position = -1) {
auto symbol = symbol_table_->CreateSymbol(name, user_declared, type, token_position);
scopes_.back().symbols[name] = symbol;
return symbol;
}
Symbol GetOrCreateSymbol(const std::string &name, bool user_declared, Symbol::Type type = Symbol::Type::ANY) {
// NOLINTNEXTLINE
for (auto scope = scopes_.rbegin(); scope != scopes_.rend(); ++scope) {
if (auto maybe_symbol = FindSymbolInScope(name, *scope, type); maybe_symbol) {
return *maybe_symbol;
}
}
return CreateSymbol(name, user_declared, type);
}
// Returns the symbol by name. If the mapping already exists, checks if the
// types match. Otherwise, returns a new symbol.
Symbol GetOrCreateSymbolLocalScope(const std::string &name, bool user_declared,
Symbol::Type type = Symbol::Type::ANY) {
auto &scope = scopes_.back();
if (auto maybe_symbol = FindSymbolInScope(name, scope, type); maybe_symbol) {
return *maybe_symbol;
}
return CreateSymbol(name, user_declared, type);
}
void VisitReturnBody(ReturnBody &body, Where *where = nullptr) {
auto &scope = scopes_.back();
for (auto &expr : body.named_expressions) {
expr->Accept(*this);
}
std::vector<Symbol> user_symbols;
if (body.all_identifiers) {
// Carry over user symbols because '*' appeared.
for (const auto &sym_pair : scope.symbols) {
if (!sym_pair.second.user_declared()) {
continue;
}
user_symbols.emplace_back(sym_pair.second);
}
if (user_symbols.empty()) {
throw SemanticException("There are no variables in scope to use for '*'.");
}
}
// WITH/RETURN clause removes declarations of all the previous variables and
// declares only those established through named expressions. New declarations
// must not be visible inside named expressions themselves.
bool removed_old_names = false;
if ((!where && body.order_by.empty()) || scope.has_aggregation) {
// WHERE and ORDER BY need to see both the old and new symbols, unless we
// have an aggregation. Therefore, we can clear the symbols immediately if
// there is neither ORDER BY nor WHERE, or we have an aggregation.
scope.symbols.clear();
removed_old_names = true;
}
// Create symbols for named expressions.
std::unordered_set<std::string> new_names;
for (const auto &user_sym : user_symbols) {
new_names.insert(user_sym.name());
scope.symbols[user_sym.name()] = user_sym;
}
for (auto &named_expr : body.named_expressions) {
const auto &name = named_expr->name_;
if (!new_names.insert(name).second) {
throw SemanticException("Multiple results with the same name '{}' are not allowed.", name);
}
// An improvement would be to infer the type of the expression, so that the
// new symbol would have a more specific type.
named_expr->MapTo(CreateSymbol(name, true, Symbol::Type::ANY, named_expr->token_position_));
}
scope.in_order_by = true;
for (const auto &order_pair : body.order_by) {
order_pair.expression->Accept(*this);
}
scope.in_order_by = false;
if (body.skip) {
scope.in_skip = true;
body.skip->Accept(*this);
scope.in_skip = false;
}
if (body.limit) {
scope.in_limit = true;
body.limit->Accept(*this);
scope.in_limit = false;
}
if (where) where->Accept(*this);
if (!removed_old_names) {
// We have an ORDER BY or WHERE, but no aggregation, which means we didn't
// clear the old symbols, so do it now. We cannot just call clear, because
// we've added new symbols.
for (auto sym_it = scope.symbols.begin(); sym_it != scope.symbols.end();) {
if (new_names.find(sym_it->first) == new_names.end()) {
sym_it = scope.symbols.erase(sym_it);
} else {
sym_it++;
}
}
}
scopes_.back().has_aggregation = false;
}
void VisitWithIdentifiers(Expression *expr, const std::vector<Identifier *> &identifiers) {
auto &scope = scopes_.back();
std::vector<std::pair<std::optional<Symbol>, Identifier *>> prev_symbols;
// Collect previous symbols if they exist.
for (const auto &identifier : identifiers) {
std::optional<Symbol> prev_symbol;
auto prev_symbol_it = scope.symbols.find(identifier->name_);
if (prev_symbol_it != scope.symbols.end()) {
prev_symbol = prev_symbol_it->second;
}
identifier->MapTo(CreateSymbol(identifier->name_, identifier->user_declared_));
prev_symbols.emplace_back(prev_symbol, identifier);
}
// Visit the expression with the new symbols bound.
expr->Accept(*this);
// Restore back to previous symbols.
for (const auto &prev : prev_symbols) {
const auto &prev_symbol = prev.first;
const auto &identifier = prev.second;
if (prev_symbol) {
scope.symbols[identifier->name_] = *prev_symbol;
} else {
scope.symbols.erase(identifier->name_);
}
}
}
SymbolTable *symbol_table_;
// Identifiers which are injected from outside the query. Each identifier
// is mapped by its name.
std::unordered_map<std::string, Identifier *> predefined_identifiers_;
std::vector<Scope> scopes_;
std::unordered_set<std::string> prev_return_names_;
std::unordered_set<std::string> curr_return_names_;
};
inline SymbolTable MakeSymbolTable(CypherQuery *query, const std::vector<Identifier *> &predefined_identifiers = {}) {
SymbolTable symbol_table;
SymbolGenerator symbol_generator(&symbol_table, predefined_identifiers);
query->single_query_->Accept(symbol_generator);
for (auto *cypher_union : query->cypher_unions_) {
cypher_union->Accept(symbol_generator);
}
return symbol_table;
}
} // namespace memgraph::expr

File diff suppressed because it is too large Load Diff

View File

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

File diff suppressed because it is too large Load Diff

View File

@@ -15,17 +15,9 @@
#include <string>
#include <vector>
#include "common/errors.hpp"
#include "coordinator/shard_map.hpp"
#include "query/v2/accessors.hpp"
#include "query/v2/request_router.hpp"
#include "query/v2/requests.hpp"
#include "storage/v3/edge_accessor.hpp"
#include "storage/v3/id_types.hpp"
#include "storage/v3/shard.hpp"
#include "storage/v3/storage.hpp"
#include "storage/v3/vertex_accessor.hpp"
#include "storage/v3/view.hpp"
#include "utils/exceptions.hpp"
#include "utils/temporal.hpp"
using memgraph::communication::bolt::Value;
@@ -71,139 +63,125 @@ query::v2::TypedValue ToTypedValue(const Value &value) {
}
}
communication::bolt::Vertex ToBoltVertex(const query::v2::accessors::VertexAccessor &vertex,
const query::v2::RequestRouterInterface *request_router,
storage::v3::View /*view*/) {
auto id = communication::bolt::Id::FromUint(0);
auto labels = vertex.Labels();
std::vector<std::string> new_labels;
new_labels.reserve(labels.size());
for (const auto &label : labels) {
new_labels.push_back(request_router->LabelToName(label.id));
}
auto properties = vertex.Properties();
std::map<std::string, Value> new_properties;
for (const auto &[prop, property_value] : properties) {
new_properties[request_router->PropertyToName(prop)] = ToBoltValue(property_value);
}
return communication::bolt::Vertex{id, new_labels, new_properties};
storage::v3::Result<communication::bolt::Vertex> ToBoltVertex(const query::v2::VertexAccessor &vertex,
const storage::v3::Storage &db, storage::v3::View view) {
return ToBoltVertex(vertex.impl_, db, view);
}
communication::bolt::Edge ToBoltEdge(const query::v2::accessors::EdgeAccessor &edge,
const query::v2::RequestRouterInterface *request_router,
storage::v3::View /*view*/) {
// TODO(jbajic) Fix bolt communication
auto id = communication::bolt::Id::FromUint(0);
auto from = communication::bolt::Id::FromUint(0);
auto to = communication::bolt::Id::FromUint(0);
const auto &type = request_router->EdgeTypeToName(edge.EdgeType());
auto properties = edge.Properties();
std::map<std::string, Value> new_properties;
for (const auto &[prop, property_value] : properties) {
new_properties[request_router->PropertyToName(prop)] = ToBoltValue(property_value);
}
return communication::bolt::Edge{id, from, to, type, new_properties};
storage::v3::Result<communication::bolt::Edge> ToBoltEdge(const query::v2::EdgeAccessor &edge,
const storage::v3::Storage &db, storage::v3::View view) {
return ToBoltEdge(edge.impl_, db, view);
}
communication::bolt::Path ToBoltPath(const query::v2::accessors::Path & /*edge*/,
const query::v2::RequestRouterInterface * /*request_router*/,
storage::v3::View /*view*/) {
// TODO(jbajic) Fix bolt communication
MG_ASSERT(false, "Path is unimplemented!");
return {};
}
Value ToBoltValue(const query::v2::TypedValue &value, const query::v2::RequestRouterInterface *request_router,
storage::v3::View view) {
storage::v3::Result<Value> ToBoltValue(const query::v2::TypedValue &value, const storage::v3::Storage &db,
storage::v3::View view) {
switch (value.type()) {
case query::v2::TypedValue::Type::Null:
return {};
return Value();
case query::v2::TypedValue::Type::Bool:
return {value.ValueBool()};
return Value(value.ValueBool());
case query::v2::TypedValue::Type::Int:
return {value.ValueInt()};
return Value(value.ValueInt());
case query::v2::TypedValue::Type::Double:
return {value.ValueDouble()};
return Value(value.ValueDouble());
case query::v2::TypedValue::Type::String:
return {std::string(value.ValueString())};
return Value(std::string(value.ValueString()));
case query::v2::TypedValue::Type::List: {
std::vector<Value> values;
values.reserve(value.ValueList().size());
for (const auto &v : value.ValueList()) {
auto value = ToBoltValue(v, request_router, view);
values.emplace_back(std::move(value));
auto maybe_value = ToBoltValue(v, db, view);
if (maybe_value.HasError()) return maybe_value.GetError();
values.emplace_back(std::move(*maybe_value));
}
return {std::move(values)};
return Value(std::move(values));
}
case query::v2::TypedValue::Type::Map: {
std::map<std::string, Value> map;
for (const auto &kv : value.ValueMap()) {
auto value = ToBoltValue(kv.second, request_router, view);
map.emplace(kv.first, std::move(value));
auto maybe_value = ToBoltValue(kv.second, db, view);
if (maybe_value.HasError()) return maybe_value.GetError();
map.emplace(kv.first, std::move(*maybe_value));
}
return {std::move(map)};
return Value(std::move(map));
}
case query::v2::TypedValue::Type::Vertex: {
auto vertex = ToBoltVertex(value.ValueVertex(), request_router, view);
return {std::move(vertex)};
auto maybe_vertex = ToBoltVertex(value.ValueVertex(), db, view);
if (maybe_vertex.HasError()) return maybe_vertex.GetError();
return Value(std::move(*maybe_vertex));
}
case query::v2::TypedValue::Type::Edge: {
auto edge = ToBoltEdge(value.ValueEdge(), request_router, view);
return {std::move(edge)};
auto maybe_edge = ToBoltEdge(value.ValueEdge(), db, view);
if (maybe_edge.HasError()) return maybe_edge.GetError();
return Value(std::move(*maybe_edge));
}
case query::v2::TypedValue::Type::Path: {
auto path = ToBoltPath(value.ValuePath(), request_router, view);
return {std::move(path)};
auto maybe_path = ToBoltPath(value.ValuePath(), db, view);
if (maybe_path.HasError()) return maybe_path.GetError();
return Value(std::move(*maybe_path));
}
case query::v2::TypedValue::Type::Date:
return {value.ValueDate()};
return Value(value.ValueDate());
case query::v2::TypedValue::Type::LocalTime:
return {value.ValueLocalTime()};
return Value(value.ValueLocalTime());
case query::v2::TypedValue::Type::LocalDateTime:
return {value.ValueLocalDateTime()};
return Value(value.ValueLocalDateTime());
case query::v2::TypedValue::Type::Duration:
return {value.ValueDuration()};
return Value(value.ValueDuration());
}
}
Value ToBoltValue(msgs::Value value) {
switch (value.type) {
case msgs::Value::Type::Null:
return {};
case msgs::Value::Type::Bool:
return {value.bool_v};
case msgs::Value::Type::Int64:
return {value.int_v};
case msgs::Value::Type::Double:
return {value.double_v};
case msgs::Value::Type::String:
return {std::string(value.string_v)};
case msgs::Value::Type::List: {
std::vector<Value> values;
values.reserve(value.list_v.size());
for (const auto &v : value.list_v) {
auto maybe_value = ToBoltValue(v);
values.emplace_back(std::move(maybe_value));
}
return Value{std::move(values)};
}
case msgs::Value::Type::Map: {
std::map<std::string, Value> map;
for (const auto &kv : value.map_v) {
auto maybe_value = ToBoltValue(kv.second);
map.emplace(kv.first, std::move(maybe_value));
}
return Value{std::move(map)};
}
case msgs::Value::Type::Vertex:
case msgs::Value::Type::Edge: {
throw utils::BasicException("Vertex and Edge not supported!");
}
// TODO Value to Date types not supported
storage::v3::Result<communication::bolt::Vertex> ToBoltVertex(const storage::v3::VertexAccessor &vertex,
const storage::v3::Storage &db, storage::v3::View view) {
auto id = communication::bolt::Id::FromUint(vertex.Gid().AsUint());
auto maybe_labels = vertex.Labels(view);
if (maybe_labels.HasError()) return maybe_labels.GetError();
std::vector<std::string> labels;
labels.reserve(maybe_labels->size());
for (const auto &label : *maybe_labels) {
labels.push_back(db.LabelToName(label));
}
auto maybe_properties = vertex.Properties(view);
if (maybe_properties.HasError()) return maybe_properties.GetError();
std::map<std::string, Value> properties;
for (const auto &prop : *maybe_properties) {
properties[db.PropertyToName(prop.first)] = ToBoltValue(prop.second);
}
return communication::bolt::Vertex{id, labels, properties};
}
storage::v3::Result<communication::bolt::Edge> ToBoltEdge(const storage::v3::EdgeAccessor &edge,
const storage::v3::Storage &db, storage::v3::View view) {
auto id = communication::bolt::Id::FromUint(edge.Gid().AsUint());
auto from = communication::bolt::Id::FromUint(edge.FromVertex().Gid().AsUint());
auto to = communication::bolt::Id::FromUint(edge.ToVertex().Gid().AsUint());
const auto &type = db.EdgeTypeToName(edge.EdgeType());
auto maybe_properties = edge.Properties(view);
if (maybe_properties.HasError()) return maybe_properties.GetError();
std::map<std::string, Value> properties;
for (const auto &prop : *maybe_properties) {
properties[db.PropertyToName(prop.first)] = ToBoltValue(prop.second);
}
return communication::bolt::Edge{id, from, to, type, properties};
}
storage::v3::Result<communication::bolt::Path> ToBoltPath(const query::v2::Path &path, const storage::v3::Storage &db,
storage::v3::View view) {
std::vector<communication::bolt::Vertex> vertices;
vertices.reserve(path.vertices().size());
for (const auto &v : path.vertices()) {
auto maybe_vertex = ToBoltVertex(v, db, view);
if (maybe_vertex.HasError()) return maybe_vertex.GetError();
vertices.emplace_back(std::move(*maybe_vertex));
}
std::vector<communication::bolt::Edge> edges;
edges.reserve(path.edges().size());
for (const auto &e : path.edges()) {
auto maybe_edge = ToBoltEdge(e, db, view);
if (maybe_edge.HasError()) return maybe_edge.GetError();
edges.emplace_back(std::move(*maybe_edge));
}
return communication::bolt::Path(vertices, edges);
}
storage::v3::PropertyValue ToPropertyValue(const Value &value) {

View File

@@ -13,14 +13,10 @@
#pragma once
#include "communication/bolt/v1/value.hpp"
#include "coordinator/shard_map.hpp"
#include "query/v2/bindings/typed_value.hpp"
#include "query/v2/request_router.hpp"
#include "query/v2/typed_value.hpp"
#include "storage/v3/property_value.hpp"
#include "storage/v3/result.hpp"
#include "storage/v3/shard.hpp"
#include "storage/v3/view.hpp"
#include "utils/result.hpp"
namespace memgraph::storage::v3 {
class EdgeAccessor;
@@ -32,37 +28,36 @@ namespace memgraph::glue::v2 {
/// @param storage::v3::VertexAccessor for converting to
/// communication::bolt::Vertex.
/// @param query::v2::RequestRouterInterface *request_router getting label and property names.
/// @param storage::v3::Storage for getting label and property names.
/// @param storage::v3::View for deciding which vertex attributes are visible.
///
/// @throw std::bad_alloc
communication::bolt::Vertex ToBoltVertex(const storage::v3::VertexAccessor &vertex,
const query::v2::RequestRouterInterface *request_router,
storage::v3::View view);
storage::v3::Result<communication::bolt::Vertex> ToBoltVertex(const storage::v3::VertexAccessor &vertex,
const storage::v3::Storage &db, storage::v3::View view);
/// @param storage::v3::EdgeAccessor for converting to communication::bolt::Edge.
/// @param query::v2::RequestRouterInterface *request_router getting edge type and property names.
/// @param storage::v3::Storage for getting edge type and property names.
/// @param storage::v3::View for deciding which edge attributes are visible.
///
/// @throw std::bad_alloc
communication::bolt::Edge ToBoltEdge(const storage::v3::EdgeAccessor &edge,
const query::v2::RequestRouterInterface *request_router, storage::v3::View view);
storage::v3::Result<communication::bolt::Edge> ToBoltEdge(const storage::v3::EdgeAccessor &edge,
const storage::v3::Storage &db, storage::v3::View view);
/// @param query::v2::Path for converting to communication::bolt::Path.
/// @param query::v2::RequestRouterInterface *request_router ToBoltVertex and ToBoltEdge.
/// @param storage::v3::Storage for ToBoltVertex and ToBoltEdge.
/// @param storage::v3::View for ToBoltVertex and ToBoltEdge.
///
/// @throw std::bad_alloc
communication::bolt::Path ToBoltPath(const query::v2::accessors::Path &path,
const query::v2::RequestRouterInterface *request_router, storage::v3::View view);
storage::v3::Result<communication::bolt::Path> ToBoltPath(const query::v2::Path &path, const storage::v3::Storage &db,
storage::v3::View view);
/// @param query::v2::TypedValue for converting to communication::bolt::Value.
/// @param query::v2::RequestRouterInterface *request_router ToBoltVertex and ToBoltEdge.
/// @param storage::v3::Storage for ToBoltVertex and ToBoltEdge.
/// @param storage::v3::View for ToBoltVertex and ToBoltEdge.
///
/// @throw std::bad_alloc
communication::bolt::Value ToBoltValue(const query::v2::TypedValue &value,
const query::v2::RequestRouterInterface *request_router, storage::v3::View view);
storage::v3::Result<communication::bolt::Value> ToBoltValue(const query::v2::TypedValue &value,
const storage::v3::Storage &db, storage::v3::View view);
query::v2::TypedValue ToTypedValue(const communication::bolt::Value &value);
@@ -70,9 +65,4 @@ communication::bolt::Value ToBoltValue(const storage::v3::PropertyValue &value);
storage::v3::PropertyValue ToPropertyValue(const communication::bolt::Value &value);
communication::bolt::Value ToBoltValue(msgs::Value value);
communication::bolt::Value ToBoltValue(msgs::Value value, const query::v2::RequestRouterInterface *request_router,
storage::v3::View view);
} // namespace memgraph::glue::v2

View File

@@ -1,163 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <compare>
#include <fmt/format.h>
#include <boost/asio/ip/tcp.hpp>
#include <boost/functional/hash.hpp>
#include <boost/uuid/uuid.hpp>
#include <boost/uuid/uuid_generators.hpp>
#include <boost/uuid/uuid_io.hpp>
#include "utils/logging.hpp"
namespace memgraph::io {
struct PartialAddress {
boost::asio::ip::address ip;
uint16_t port;
friend bool operator==(const PartialAddress &lhs, const PartialAddress &rhs) = default;
/// unique_id is most dominant for ordering, then ip, then port
friend bool operator<(const PartialAddress &lhs, const PartialAddress &rhs) {
if (lhs.ip != rhs.ip) {
return lhs.ip < rhs.ip;
}
return lhs.port < rhs.port;
}
std::string ToString() const { return fmt::format("PartialAddress {{ ip: {}, port: {} }}", ip.to_string(), port); }
friend std::ostream &operator<<(std::ostream &in, const PartialAddress &partial_address) {
in << partial_address.ToString();
return in;
}
};
struct Address {
// It's important for all participants to have a
// unique identifier - IP and port alone are not
// enough, and may change over the lifecycle of
// the nodes. Particularly storage nodes may change
// their IP addresses over time, and the system
// should gracefully update its information
// about them.
boost::uuids::uuid unique_id;
boost::asio::ip::address last_known_ip;
uint16_t last_known_port;
static Address TestAddress(uint16_t port) {
MG_ASSERT(port <= 255);
return Address{
.unique_id = boost::uuids::uuid{0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, static_cast<unsigned char>(port)},
.last_known_port = port,
};
}
// NB: don't use this in test code because it is non-deterministic
static Address UniqueLocalAddress() {
return Address{
.unique_id = boost::uuids::uuid{boost::uuids::random_generator()()},
};
}
/// `Coordinator`s have constant UUIDs because there is at most one per ip/port pair.
Address ForkLocalCoordinator() {
return Address{
.unique_id = boost::uuids::uuid{1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
.last_known_ip = last_known_ip,
.last_known_port = last_known_port,
};
}
/// `ShardManager`s have constant UUIDs because there is at most one per ip/port pair.
Address ForkLocalShardManager() {
return Address{
.unique_id = boost::uuids::uuid{2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
.last_known_ip = last_known_ip,
.last_known_port = last_known_port,
};
}
/// Returns a new ID with the same IP and port but a unique UUID.
Address ForkUniqueAddress() {
return Address{
.unique_id = boost::uuids::uuid{boost::uuids::random_generator()()},
.last_known_ip = last_known_ip,
.last_known_port = last_known_port,
};
}
PartialAddress ToPartialAddress() const {
return PartialAddress{
.ip = last_known_ip,
.port = last_known_port,
};
}
friend bool operator==(const Address &lhs, const Address &rhs) = default;
/// unique_id is most dominant for ordering, then last_known_ip, then last_known_port
friend bool operator<(const Address &lhs, const Address &rhs) {
if (lhs.unique_id != rhs.unique_id) {
return lhs.unique_id < rhs.unique_id;
}
if (lhs.last_known_ip != rhs.last_known_ip) {
return lhs.last_known_ip < rhs.last_known_ip;
}
return lhs.last_known_port < rhs.last_known_port;
}
std::string ToString() const {
return fmt::format("Address {{ unique_id: {}, last_known_ip: {}, last_known_port: {} }}",
boost::uuids::to_string(unique_id), last_known_ip.to_string(), last_known_port);
}
friend std::ostream &operator<<(std::ostream &in, const Address &address) {
in << address.ToString();
return in;
}
};
}; // namespace memgraph::io
namespace std {
template <>
struct hash<memgraph::io::PartialAddress> {
size_t operator()(const memgraph::io::PartialAddress &pa) const {
using boost::hash_combine;
using boost::hash_value;
// Start with a hash value of 0 .
std::size_t seed = 0;
if (pa.ip.is_v4()) {
auto h = std::hash<boost::asio::ip::address_v4>()(pa.ip.to_v4());
hash_combine(seed, h);
} else {
auto h = std::hash<boost::asio::ip::address_v6>()(pa.ip.to_v6());
hash_combine(seed, h);
}
hash_combine(seed, hash_value(pa.port));
// Return the result.
return seed;
}
};
} // namespace std

View File

@@ -1,26 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
namespace memgraph::io {
// Signifies that a retriable operation was unable to
// complete after a configured number of retries.
struct RetriesExhausted {};
// Signifies that a request was unable to receive a response
// within some configured timeout duration. It is important
// to remember that in distributed systems, a timeout does
// not signify that a request was not received or processed.
// It may be the case that the request was fully processed
// but that the response was not received.
struct TimedOut {};
}; // namespace memgraph::io

View File

@@ -1,275 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <condition_variable>
#include <memory>
#include <mutex>
#include <optional>
#include <thread>
#include <utility>
#include "io/errors.hpp"
#include "utils/logging.hpp"
namespace memgraph::io {
// Shared is in an anonymous namespace, and the only way to
// construct a Promise or Future is to pass a Shared in. This
// ensures that Promises and Futures can only be constructed
// in this translation unit.
namespace details {
template <typename T>
class Shared {
mutable std::condition_variable cv_;
mutable std::mutex mu_;
std::optional<T> item_;
bool consumed_ = false;
bool waiting_ = false;
bool filled_ = false;
std::function<bool()> wait_notifier_ = nullptr;
std::function<void()> fill_notifier_ = nullptr;
public:
explicit Shared(std::function<bool()> wait_notifier, std::function<void()> fill_notifier)
: wait_notifier_(wait_notifier), fill_notifier_(fill_notifier) {}
Shared() = default;
Shared(Shared &&) = delete;
Shared &operator=(Shared &&) = delete;
Shared(const Shared &) = delete;
Shared &operator=(const Shared &) = delete;
~Shared() = default;
/// Takes the item out of our optional item_ and returns it.
T Take() {
MG_ASSERT(item_, "Take called without item_ being present");
MG_ASSERT(!consumed_, "Take called on already-consumed Future");
T ret = std::move(item_).value();
item_.reset();
consumed_ = true;
return ret;
}
T Wait() {
std::unique_lock<std::mutex> lock(mu_);
waiting_ = true;
while (!item_) {
if (wait_notifier_) [[unlikely]] {
// We can't hold our own lock while notifying
// the simulator because notifying the simulator
// involves acquiring the simulator's mutex
// to guarantee that our notification linearizes
// with the simulator's condition variable.
// However, the simulator may acquire our
// mutex to check if we are being awaited,
// while determining system quiescence,
// so we have to get out of its way to avoid
// a cyclical deadlock.
lock.unlock();
std::invoke(wait_notifier_);
lock.lock();
if (item_) {
// item may have been filled while we
// had dropped our mutex while notifying
// the simulator of our waiting_ status.
break;
}
} else {
cv_.wait(lock);
}
MG_ASSERT(!consumed_, "Future consumed twice!");
}
waiting_ = false;
return Take();
}
bool IsReady() const {
std::unique_lock<std::mutex> lock(mu_);
return item_.has_value();
}
std::optional<T> TryGet() {
std::unique_lock<std::mutex> lock(mu_);
if (item_) {
return Take();
}
return std::nullopt;
}
void Fill(T item) {
{
std::unique_lock<std::mutex> lock(mu_);
MG_ASSERT(!consumed_, "Promise filled after it was already consumed!");
MG_ASSERT(!filled_, "Promise filled twice!");
item_ = item;
filled_ = true;
} // lock released before condition variable notification
if (fill_notifier_) {
spdlog::trace("calling fill notifier");
std::invoke(fill_notifier_);
} else {
spdlog::trace("not calling fill notifier");
}
cv_.notify_all();
}
bool IsAwaited() const {
std::unique_lock<std::mutex> lock(mu_);
return waiting_;
}
};
} // namespace details
template <typename T>
class Future {
bool consumed_or_moved_ = false;
std::shared_ptr<details::Shared<T>> shared_;
public:
explicit Future(std::shared_ptr<details::Shared<T>> shared) : shared_(shared) {}
Future() = delete;
Future(Future &&old) noexcept {
MG_ASSERT(!old.consumed_or_moved_, "Future moved from after already being moved from or consumed.");
shared_ = std::move(old.shared_);
consumed_or_moved_ = old.consumed_or_moved_;
old.consumed_or_moved_ = true;
}
Future &operator=(Future &&old) noexcept {
MG_ASSERT(!old.consumed_or_moved_, "Future moved from after already being moved from or consumed.");
shared_ = std::move(old.shared_);
consumed_or_moved_ = old.consumed_or_moved_;
old.consumed_or_moved_ = true;
return *this;
}
Future(const Future &) = delete;
Future &operator=(const Future &) = delete;
~Future() = default;
/// Returns true if the Future is ready to
/// be consumed using TryGet or Wait (prefer Wait
/// if you know it's ready, because it doesn't
/// return an optional.
bool IsReady() {
MG_ASSERT(!consumed_or_moved_, "Called IsReady after Future already consumed!");
return shared_->IsReady();
}
/// Non-blocking method that returns the inner
/// item if it's already ready, or std::nullopt
/// if it is not ready yet.
std::optional<T> TryGet() {
MG_ASSERT(!consumed_or_moved_, "Called TryGet after Future already consumed!");
std::optional<T> ret = shared_->TryGet();
if (ret) {
consumed_or_moved_ = true;
}
return ret;
}
/// Block on the corresponding promise to be filled,
/// returning the inner item when ready.
T Wait() && {
MG_ASSERT(!consumed_or_moved_, "Future should only be consumed with Wait once!");
T ret = shared_->Wait();
consumed_or_moved_ = true;
return ret;
}
/// Marks this Future as canceled.
void Cancel() {
MG_ASSERT(!consumed_or_moved_, "Future::Cancel called on a future that was already moved or consumed!");
consumed_or_moved_ = true;
}
};
template <typename T>
class Promise {
std::shared_ptr<details::Shared<T>> shared_;
bool filled_or_moved_{false};
public:
explicit Promise(std::shared_ptr<details::Shared<T>> shared) : shared_(shared) {}
Promise() = delete;
Promise(Promise &&old) noexcept {
MG_ASSERT(!old.filled_or_moved_, "Promise moved from after already being moved from or filled.");
shared_ = std::move(old.shared_);
old.filled_or_moved_ = true;
}
Promise &operator=(Promise &&old) noexcept {
MG_ASSERT(!old.filled_or_moved_, "Promise moved from after already being moved from or filled.");
shared_ = std::move(old.shared_);
old.filled_or_moved_ = true;
}
Promise(const Promise &) = delete;
Promise &operator=(const Promise &) = delete;
// NOLINTNEXTLINE(clang-analyzer-core.uninitialized.Branch)
~Promise() { MG_ASSERT(filled_or_moved_, "Promise destroyed before its associated Future was filled!"); }
// Fill the expected item into the Future.
void Fill(T item) {
MG_ASSERT(!filled_or_moved_, "Promise::Fill called on a promise that is already filled or moved!");
shared_->Fill(item);
filled_or_moved_ = true;
}
bool IsAwaited() { return shared_->IsAwaited(); }
/// Moves this Promise into a unique_ptr.
std::unique_ptr<Promise<T>> ToUnique() && {
std::unique_ptr<Promise<T>> up = std::make_unique<Promise<T>>(std::move(shared_));
filled_or_moved_ = true;
return up;
}
};
template <typename T>
std::pair<Future<T>, Promise<T>> FuturePromisePair() {
std::shared_ptr<details::Shared<T>> shared = std::make_shared<details::Shared<T>>();
Future<T> future = Future<T>(shared);
Promise<T> promise = Promise<T>(shared);
return std::make_pair(std::move(future), std::move(promise));
}
template <typename T>
std::pair<Future<T>, Promise<T>> FuturePromisePairWithNotifications(std::function<bool()> wait_notifier,
std::function<void()> fill_notifier) {
std::shared_ptr<details::Shared<T>> shared = std::make_shared<details::Shared<T>>(wait_notifier, fill_notifier);
Future<T> future = Future<T>(shared);
Promise<T> promise = Promise<T>(shared);
return std::make_pair(std::move(future), std::move(promise));
}
}; // namespace memgraph::io

View File

@@ -1,35 +0,0 @@
// Copyright 2023 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <random>
#include "io/address.hpp"
#include "io/local_transport/local_transport.hpp"
#include "io/local_transport/local_transport_handle.hpp"
#include "io/transport.hpp"
namespace memgraph::io::local_transport {
class LocalSystem {
std::shared_ptr<LocalTransportHandle> local_transport_handle_ = std::make_shared<LocalTransportHandle>();
public:
Io<LocalTransport> Register(Address address) {
LocalTransport local_transport(local_transport_handle_);
return Io{local_transport, address};
}
void ShutDown() { local_transport_handle_->ShutDown(); }
};
} // namespace memgraph::io::local_transport

View File

@@ -1,62 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <chrono>
#include <memory>
#include <random>
#include <utility>
#include "io/address.hpp"
#include "io/local_transport/local_transport_handle.hpp"
#include "io/time.hpp"
#include "io/transport.hpp"
namespace memgraph::io::local_transport {
class LocalTransport {
std::shared_ptr<LocalTransportHandle> local_transport_handle_;
public:
explicit LocalTransport(std::shared_ptr<LocalTransportHandle> local_transport_handle)
: local_transport_handle_(std::move(local_transport_handle)) {}
template <Message RequestT, Message ResponseT>
ResponseFuture<ResponseT> Request(Address to_address, Address from_address, RequestT request,
std::function<void()> fill_notifier, Duration timeout) {
return local_transport_handle_->template SubmitRequest<RequestT, ResponseT>(
to_address, from_address, std::move(request), timeout, fill_notifier);
}
template <Message... Ms>
requires(sizeof...(Ms) > 0) RequestResult<Ms...> Receive(Address receiver_address, Duration timeout) {
return local_transport_handle_->template Receive<Ms...>(receiver_address, timeout);
}
template <Message M>
void Send(Address to_address, Address from_address, RequestId request_id, M &&message) {
return local_transport_handle_->template Send<M>(to_address, from_address, request_id, std::forward<M>(message));
}
Time Now() const { return local_transport_handle_->Now(); }
bool ShouldShutDown() const { return local_transport_handle_->ShouldShutDown(); }
template <class D = std::poisson_distribution<>, class Return = uint64_t>
Return Rand(D distrib) {
std::random_device rng;
return distrib(rng);
}
LatencyHistogramSummaries ResponseLatencies() { return local_transport_handle_->ResponseLatencies(); }
};
}; // namespace memgraph::io::local_transport

View File

@@ -1,177 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <chrono>
#include <condition_variable>
#include <iostream>
#include <map>
#include <mutex>
#include "io/errors.hpp"
#include "io/message_conversion.hpp"
#include "io/message_histogram_collector.hpp"
#include "io/time.hpp"
#include "io/transport.hpp"
namespace memgraph::io::local_transport {
class LocalTransportHandle {
mutable std::mutex mu_{};
mutable std::condition_variable cv_;
bool should_shut_down_ = false;
MessageHistogramCollector histograms_;
RequestId request_id_counter_ = 0;
// the responses to requests that are being waited on
std::map<PromiseKey, DeadlineAndOpaquePromise> promises_;
// messages that are sent to servers that may later receive them
std::vector<OpaqueMessage> can_receive_;
public:
~LocalTransportHandle() {
for (auto &&[pk, promise] : promises_) {
std::move(promise.promise).TimeOut();
}
promises_.clear();
}
void ShutDown() {
std::unique_lock<std::mutex> lock(mu_);
should_shut_down_ = true;
cv_.notify_all();
}
bool ShouldShutDown() const {
std::unique_lock<std::mutex> lock(mu_);
return should_shut_down_;
}
LatencyHistogramSummaries ResponseLatencies() {
std::unique_lock<std::mutex> lock(mu_);
return histograms_.ResponseLatencies();
}
static Time Now() {
auto nano_time = std::chrono::system_clock::now();
return std::chrono::time_point_cast<std::chrono::microseconds>(nano_time);
}
template <Message... Ms>
requires(sizeof...(Ms) > 0) RequestResult<Ms...> Receive(Address /* receiver_address */, Duration timeout) {
std::unique_lock lock(mu_);
Time before = Now();
spdlog::info("can_receive_ size: {}", can_receive_.size());
while (can_receive_.empty()) {
Time now = Now();
// protection against non-monotonic timesources
auto maxed_now = std::max(now, before);
auto elapsed = maxed_now - before;
if (timeout < elapsed) {
return TimedOut{};
}
Duration relative_timeout = timeout - elapsed;
std::cv_status cv_status_value = cv_.wait_for(lock, relative_timeout);
if (cv_status_value == std::cv_status::timeout) {
return TimedOut{};
}
}
auto current_message = std::move(can_receive_.back());
can_receive_.pop_back();
auto m_opt = std::move(current_message).Take<Ms...>();
return std::move(m_opt).value();
}
template <Message M>
void Send(Address to_address, Address from_address, RequestId request_id, M &&message) {
auto type_info = TypeInfoFor(message);
std::any message_any(std::forward<M>(message));
OpaqueMessage opaque_message{.to_address = to_address,
.from_address = from_address,
.request_id = request_id,
.message = std::move(message_any),
.type_info = type_info};
PromiseKey promise_key{.requester_address = to_address, .request_id = opaque_message.request_id};
{
std::unique_lock<std::mutex> lock(mu_);
if (promises_.contains(promise_key)) {
spdlog::info("using message to fill promise");
// complete waiting promise if it's there
DeadlineAndOpaquePromise dop = std::move(promises_.at(promise_key));
promises_.erase(promise_key);
Duration response_latency = Now() - dop.requested_at;
dop.promise.Fill(std::move(opaque_message), response_latency);
histograms_.Measure(type_info, response_latency);
} else {
spdlog::info("placing message in can_receive_");
can_receive_.emplace_back(std::move(opaque_message));
}
} // lock dropped
cv_.notify_all();
}
template <Message RequestT, Message ResponseT>
ResponseFuture<ResponseT> SubmitRequest(Address to_address, Address from_address, RequestT &&request,
Duration timeout, std::function<void()> fill_notifier) {
auto [future, promise] = memgraph::io::FuturePromisePairWithNotifications<ResponseResult<ResponseT>>(
// set null notifier for when the Future::Wait is called
nullptr,
// set notifier for when Promise::Fill is called
std::forward<std::function<void()>>(fill_notifier));
const bool port_matches = to_address.last_known_port == from_address.last_known_port;
const bool ip_matches = to_address.last_known_ip == from_address.last_known_ip;
MG_ASSERT(port_matches && ip_matches);
const auto now = Now();
const Time deadline = now + timeout;
RequestId request_id = 0;
{
std::unique_lock<std::mutex> lock(mu_);
request_id = ++request_id_counter_;
PromiseKey promise_key{.requester_address = from_address, .request_id = request_id};
OpaquePromise opaque_promise(std::move(promise).ToUnique());
DeadlineAndOpaquePromise dop{.requested_at = now, .deadline = deadline, .promise = std::move(opaque_promise)};
MG_ASSERT(!promises_.contains(promise_key));
promises_.emplace(std::move(promise_key), std::move(dop));
} // lock dropped
Send(to_address, from_address, request_id, std::forward<RequestT>(request));
return std::move(future);
}
};
} // namespace memgraph::io::local_transport

View File

@@ -1,236 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <boost/core/demangle.hpp>
#include "io/transport.hpp"
#include "utils/type_info_ref.hpp"
namespace memgraph::io {
struct PromiseKey {
Address requester_address;
uint64_t request_id;
public:
friend bool operator<(const PromiseKey &lhs, const PromiseKey &rhs) {
if (lhs.requester_address != rhs.requester_address) {
return lhs.requester_address < rhs.requester_address;
}
return lhs.request_id < rhs.request_id;
}
};
struct OpaqueMessage {
Address to_address;
Address from_address;
uint64_t request_id;
std::any message;
utils::TypeInfoRef type_info;
/// Recursively tries to match a specific type from the outer
/// variant's parameter pack against the type of the std::any,
/// and if it matches, make it concrete and return it. Otherwise,
/// move on and compare the any with the next type from the
/// parameter pack.
///
/// Return is the full std::variant<Ts...> type that holds the
/// full parameter pack without interfering with recursive
/// narrowing expansion.
template <typename Return, Message Head, Message... Rest>
std::optional<Return> Unpack(std::any &&a) {
if (typeid(Head) == a.type()) {
Head concrete = std::any_cast<Head>(std::move(a));
return concrete;
}
if constexpr (sizeof...(Rest) > 0) {
return Unpack<Return, Rest...>(std::move(a));
} else {
return std::nullopt;
}
}
/// High level "user-facing" conversion function that lets
/// people interested in conversion only supply a single
/// parameter pack for the types that they want to compare
/// with the any and potentially include in the returned
/// variant.
template <Message... Ms>
requires(sizeof...(Ms) > 0) std::optional<std::variant<Ms...>> VariantFromAny(std::any &&a) {
return Unpack<std::variant<Ms...>, Ms...>(std::move(a));
}
template <Message... Ms>
requires(sizeof...(Ms) > 0) std::optional<RequestEnvelope<Ms...>> Take() && {
std::optional<std::variant<Ms...>> m_opt = VariantFromAny<Ms...>(std::move(message));
if (m_opt) {
return RequestEnvelope<Ms...>{
.message = std::move(*m_opt),
.request_id = request_id,
.to_address = to_address,
.from_address = from_address,
};
}
std::string demangled_name = "\"" + boost::core::demangle(message.type().name()) + "\"";
spdlog::error("failed to cast message of type {} to expected request type (probably in Receive argument types)",
demangled_name);
return std::nullopt;
}
};
class OpaquePromiseTraitBase {
public:
virtual const std::type_info *TypeInfo() const = 0;
virtual bool IsAwaited(void *ptr) const = 0;
virtual void Fill(void *ptr, OpaqueMessage &&, Duration) const = 0;
virtual void TimeOut(void *ptr) const = 0;
virtual ~OpaquePromiseTraitBase() = default;
OpaquePromiseTraitBase() = default;
OpaquePromiseTraitBase(const OpaquePromiseTraitBase &) = delete;
OpaquePromiseTraitBase &operator=(const OpaquePromiseTraitBase &) = delete;
OpaquePromiseTraitBase(OpaquePromiseTraitBase &&old) = delete;
OpaquePromiseTraitBase &operator=(OpaquePromiseTraitBase &&) = delete;
};
template <typename T>
class OpaquePromiseTrait : public OpaquePromiseTraitBase {
public:
const std::type_info *TypeInfo() const override { return &typeid(T); };
bool IsAwaited(void *ptr) const override { return static_cast<ResponsePromise<T> *>(ptr)->IsAwaited(); };
void Fill(void *ptr, OpaqueMessage &&opaque_message, Duration response_latency) const override {
T message = std::any_cast<T>(std::move(opaque_message.message));
auto response_envelope = ResponseEnvelope<T>{.message = std::move(message),
.request_id = opaque_message.request_id,
.to_address = opaque_message.to_address,
.from_address = opaque_message.from_address,
.response_latency = response_latency};
auto promise = static_cast<ResponsePromise<T> *>(ptr);
auto unique_promise = std::unique_ptr<ResponsePromise<T>>(promise);
unique_promise->Fill(std::move(response_envelope));
};
void TimeOut(void *ptr) const override {
auto promise = static_cast<ResponsePromise<T> *>(ptr);
auto unique_promise = std::unique_ptr<ResponsePromise<T>>(promise);
ResponseResult<T> result = TimedOut{};
unique_promise->Fill(std::move(result));
}
};
class OpaquePromise {
void *ptr_;
std::unique_ptr<OpaquePromiseTraitBase> trait_;
public:
OpaquePromise(OpaquePromise &&old) noexcept : ptr_(old.ptr_), trait_(std::move(old.trait_)) {
MG_ASSERT(old.ptr_ != nullptr);
old.ptr_ = nullptr;
}
OpaquePromise &operator=(OpaquePromise &&old) noexcept {
MG_ASSERT(ptr_ == nullptr);
MG_ASSERT(old.ptr_ != nullptr);
MG_ASSERT(this != &old);
ptr_ = old.ptr_;
trait_ = std::move(old.trait_);
old.ptr_ = nullptr;
return *this;
}
OpaquePromise(const OpaquePromise &) = delete;
OpaquePromise &operator=(const OpaquePromise &) = delete;
template <typename T>
std::unique_ptr<ResponsePromise<T>> Take() && {
MG_ASSERT(typeid(T) == *trait_->TypeInfo());
MG_ASSERT(ptr_ != nullptr);
auto ptr = static_cast<ResponsePromise<T> *>(ptr_);
ptr_ = nullptr;
return std::unique_ptr<T>(ptr);
}
template <typename T>
explicit OpaquePromise(std::unique_ptr<ResponsePromise<T>> promise)
: ptr_(static_cast<void *>(promise.release())), trait_(std::make_unique<OpaquePromiseTrait<T>>()) {}
bool IsAwaited() {
MG_ASSERT(ptr_ != nullptr);
return trait_->IsAwaited(ptr_);
}
void TimeOut() {
MG_ASSERT(ptr_ != nullptr);
trait_->TimeOut(ptr_);
ptr_ = nullptr;
}
void Fill(OpaqueMessage &&opaque_message, Duration response_latency) {
MG_ASSERT(ptr_ != nullptr);
trait_->Fill(ptr_, std::move(opaque_message), response_latency);
ptr_ = nullptr;
}
~OpaquePromise() {
MG_ASSERT(ptr_ == nullptr, "OpaquePromise destroyed without being explicitly timed out or filled");
}
};
struct DeadlineAndOpaquePromise {
Time requested_at;
Time deadline;
OpaquePromise promise;
};
template <class From>
std::type_info const &TypeInfoForVariant(From const &from) {
return std::visit([](auto &&x) -> decltype(auto) { return typeid(x); }, from);
}
template <class T>
utils::TypeInfoRef TypeInfoFor(const T & /* t */) {
return typeid(T);
}
template <typename From, typename Return, typename Head, typename... Rest>
std::optional<Return> ConvertVariantInner(From &&a) {
if (typeid(Head) == TypeInfoForVariant(a)) {
Head concrete = std::get<Head>(std::forward<From>(a));
return concrete;
}
if constexpr (sizeof...(Rest) > 0) {
return ConvertVariantInner<From, Return, Rest...>(std::forward<From>(a));
} else {
return std::nullopt;
}
}
/// This function converts a variant to another variant holding a subset OR superset of
/// possible types.
template <class From, class... Ms>
requires(sizeof...(Ms) > 0) std::optional<std::variant<Ms...>> ConvertVariant(From &&from) {
return ConvertVariantInner<From, std::variant<Ms...>, Ms...>(std::forward<From>(from));
}
} // namespace memgraph::io

View File

@@ -1,132 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <chrono>
#include <cmath>
#include <compare>
#include <unordered_map>
#include <boost/core/demangle.hpp>
#include "io/time.hpp"
#include "utils/histogram.hpp"
#include "utils/logging.hpp"
#include "utils/print_helpers.hpp"
#include "utils/type_info_ref.hpp"
namespace memgraph::io {
struct LatencyHistogramSummary {
uint64_t count;
Duration p0;
Duration p50;
Duration p75;
Duration p90;
Duration p95;
Duration p975;
Duration p99;
Duration p999;
Duration p9999;
Duration p100;
Duration sum;
friend bool operator==(const LatencyHistogramSummary &lhs, const LatencyHistogramSummary &rhs) = default;
friend std::ostream &operator<<(std::ostream &in, const LatencyHistogramSummary &histo) {
in << "{ \"count\": " << histo.count;
in << ", \"p0\": " << histo.p0.count();
in << ", \"p50\": " << histo.p50.count();
in << ", \"p75\": " << histo.p75.count();
in << ", \"p90\": " << histo.p90.count();
in << ", \"p95\": " << histo.p95.count();
in << ", \"p975\": " << histo.p975.count();
in << ", \"p99\": " << histo.p99.count();
in << ", \"p999\": " << histo.p999.count();
in << ", \"p9999\": " << histo.p9999.count();
in << ", \"p100\": " << histo.p100.count();
in << ", \"sum\": " << histo.sum.count();
in << " }";
return in;
}
};
struct LatencyHistogramSummaries {
std::unordered_map<std::string, LatencyHistogramSummary> latencies;
std::string SummaryTable() {
std::string output;
const auto row = [&output](const auto &c1, const auto &c2, const auto &c3, const auto &c4, const auto &c5,
const auto &c6, const auto &c7) {
output +=
fmt::format("{: >50} | {: >8} | {: >8} | {: >8} | {: >8} | {: >8} | {: >8}\n", c1, c2, c3, c4, c5, c6, c7);
};
row("name", "count", "min (μs)", "med (μs)", "p99 (μs)", "max (μs)", "sum (ms)");
for (const auto &[name, histo] : latencies) {
row(name, histo.count, histo.p0.count(), histo.p50.count(), histo.p99.count(), histo.p100.count(),
histo.sum.count() / 1000);
}
output += "\n";
return output;
}
friend bool operator==(const LatencyHistogramSummaries &lhs, const LatencyHistogramSummaries &rhs) = default;
friend std::ostream &operator<<(std::ostream &in, const LatencyHistogramSummaries &histo) {
using memgraph::utils::print_helpers::operator<<;
in << histo.latencies;
return in;
}
};
class MessageHistogramCollector {
std::unordered_map<utils::TypeInfoRef, utils::Histogram, utils::TypeInfoHasher, utils::TypeInfoEqualTo> histograms_;
public:
void Measure(const std::type_info &type_info, const Duration &duration) {
auto &histo = histograms_[type_info];
histo.Measure(duration.count());
}
LatencyHistogramSummaries ResponseLatencies() {
std::unordered_map<std::string, LatencyHistogramSummary> ret{};
for (const auto &[type_id, histo] : histograms_) {
std::string demangled_name = "\"" + boost::core::demangle(type_id.get().name()) + "\"";
LatencyHistogramSummary latency_histogram_summary{
.count = histo.Count(),
.p0 = Duration(static_cast<int64_t>(histo.Percentile(0.0))),
.p50 = Duration(static_cast<int64_t>(histo.Percentile(50.0))),
.p75 = Duration(static_cast<int64_t>(histo.Percentile(75.0))),
.p90 = Duration(static_cast<int64_t>(histo.Percentile(90.0))),
.p95 = Duration(static_cast<int64_t>(histo.Percentile(95.0))),
.p975 = Duration(static_cast<int64_t>(histo.Percentile(97.5))),
.p99 = Duration(static_cast<int64_t>(histo.Percentile(99.0))),
.p999 = Duration(static_cast<int64_t>(histo.Percentile(99.9))),
.p9999 = Duration(static_cast<int64_t>(histo.Percentile(99.99))),
.p100 = Duration(static_cast<int64_t>(histo.Percentile(100.0))),
.sum = Duration(histo.Sum()),
};
ret.emplace(demangled_name, latency_histogram_summary);
}
return LatencyHistogramSummaries{.latencies = ret};
}
};
} // namespace memgraph::io

View File

@@ -1,46 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <variant>
#include <coordinator/coordinator.hpp>
#include <io/rsm/raft.hpp>
#include "query/v2/requests.hpp"
#include "utils/concepts.hpp"
namespace memgraph::io::messages {
using memgraph::coordinator::CoordinatorReadRequests;
using memgraph::coordinator::CoordinatorWriteRequests;
using memgraph::coordinator::CoordinatorWriteResponses;
using StorageReadRequest = msgs::ReadRequests;
using StorageWriteRequest = msgs::WriteRequests;
using memgraph::io::rsm::AppendRequest;
using memgraph::io::rsm::AppendResponse;
using memgraph::io::rsm::ReadRequest;
using memgraph::io::rsm::VoteRequest;
using memgraph::io::rsm::VoteResponse;
using memgraph::io::rsm::WriteRequest;
using memgraph::io::rsm::WriteResponse;
using CoordinatorMessages =
std::variant<ReadRequest<CoordinatorReadRequests>, AppendRequest<CoordinatorWriteRequests>, AppendResponse,
WriteRequest<CoordinatorWriteRequests>, VoteRequest, VoteResponse>;
using ShardMessages = std::variant<ReadRequest<StorageReadRequest>, AppendRequest<StorageWriteRequest>, AppendResponse,
WriteRequest<StorageWriteRequest>, VoteRequest, VoteResponse>;
using ShardManagerMessages = std::variant<WriteResponse<CoordinatorWriteResponses>>;
} // namespace memgraph::io::messages

View File

@@ -1,93 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <condition_variable>
#include <functional>
#include <mutex>
#include <optional>
#include <vector>
namespace memgraph::io {
class ReadinessToken {
size_t id_;
public:
explicit ReadinessToken(size_t id) : id_(id) {}
size_t GetId() const { return id_; }
};
class Inner {
std::condition_variable cv_;
std::mutex mu_;
std::vector<ReadinessToken> ready_;
std::optional<std::function<bool()>> tick_simulator_;
public:
void Notify(ReadinessToken readiness_token) {
{
std::unique_lock<std::mutex> lock(mu_);
ready_.emplace_back(readiness_token);
} // mutex dropped
cv_.notify_all();
}
ReadinessToken Await() {
std::unique_lock<std::mutex> lock(mu_);
while (ready_.empty()) {
if (tick_simulator_) [[unlikely]] {
// This avoids a deadlock in a similar way that
// Future::Wait will release its mutex while
// interacting with the simulator, due to
// the fact that the simulator may cause
// notifications that we are interested in.
lock.unlock();
std::invoke(tick_simulator_.value());
lock.lock();
} else {
cv_.wait(lock);
}
}
ReadinessToken ret = ready_.back();
ready_.pop_back();
return ret;
}
void InstallSimulatorTicker(std::function<bool()> tick_simulator) {
std::unique_lock<std::mutex> lock(mu_);
tick_simulator_ = tick_simulator;
}
};
class Notifier {
std::shared_ptr<Inner> inner_;
public:
Notifier() : inner_(std::make_shared<Inner>()) {}
Notifier(const Notifier &) = default;
Notifier &operator=(const Notifier &) = default;
Notifier(Notifier &&old) = default;
Notifier &operator=(Notifier &&old) = default;
~Notifier() = default;
void Notify(ReadinessToken readiness_token) const { inner_->Notify(readiness_token); }
ReadinessToken Await() const { return inner_->Await(); }
void InstallSimulatorTicker(std::function<bool()> tick_simulator) { inner_->InstallSimulatorTicker(tick_simulator); }
};
} // namespace memgraph::io

View File

@@ -1,972 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
// TODO(tyler) buffer out-of-order Append buffers on the Followers to reassemble more quickly
// TODO(tyler) handle granular batch sizes based on simple flow control
#pragma once
#include <deque>
#include <iostream>
#include <map>
#include <set>
#include <thread>
#include <vector>
#include <boost/core/demangle.hpp>
#include "io/message_conversion.hpp"
#include "io/simulator/simulator.hpp"
#include "io/transport.hpp"
#include "utils/concepts.hpp"
namespace memgraph::io::rsm {
/// Timeout and replication tunables
using namespace std::chrono_literals;
static constexpr auto kMinimumElectionTimeout = 100ms;
static constexpr auto kMaximumElectionTimeout = 200ms;
static constexpr auto kMinimumBroadcastTimeout = 40ms;
static constexpr auto kMaximumBroadcastTimeout = 60ms;
static constexpr auto kMinimumCronInterval = 1ms;
static constexpr auto kMaximumCronInterval = 2ms;
static constexpr auto kMinimumReceiveTimeout = 40ms;
static constexpr auto kMaximumReceiveTimeout = 60ms;
static_assert(kMinimumElectionTimeout > kMaximumBroadcastTimeout,
"The broadcast timeout has to be smaller than the election timeout!");
static_assert(kMinimumElectionTimeout < kMaximumElectionTimeout,
"The minimum election timeout has to be smaller than the maximum election timeout!");
static_assert(kMinimumBroadcastTimeout < kMaximumBroadcastTimeout,
"The minimum broadcast timeout has to be smaller than the maximum broadcast timeout!");
static_assert(kMinimumCronInterval < kMaximumCronInterval,
"The minimum cron interval has to be smaller than the maximum cron interval!");
static_assert(kMinimumReceiveTimeout < kMaximumReceiveTimeout,
"The minimum receive timeout has to be smaller than the maximum receive timeout!");
static constexpr size_t kMaximumAppendBatchSize = 1024;
using Term = uint64_t;
using LogIndex = uint64_t;
using LogSize = uint64_t;
template <typename WriteOperation>
struct WriteRequest {
WriteOperation operation;
};
/// WriteResponse is returned to a client after
/// their WriteRequest was entered in to the raft
/// log and it reached consensus.
///
/// WriteReturn is the result of applying the WriteRequest to
/// ReplicatedState, and if the ReplicatedState::write
/// method is deterministic, all replicas will
/// have the same ReplicatedState after applying
/// the submitted WriteRequest.
template <typename WriteReturn>
struct WriteResponse {
bool success;
WriteReturn write_return;
std::optional<Address> retry_leader;
LogIndex raft_index;
};
template <typename ReadOperation>
struct ReadRequest {
ReadOperation operation;
};
template <typename ReadReturn>
struct ReadResponse {
bool success;
ReadReturn read_return;
std::optional<Address> retry_leader;
};
template <class... ReadReturn>
utils::TypeInfoRef TypeInfoFor(const ReadResponse<std::variant<ReadReturn...>> &response) {
return TypeInfoForVariant(response.read_return);
}
template <class ReadReturn>
utils::TypeInfoRef TypeInfoFor(const ReadResponse<ReadReturn> & /* response */) {
return typeid(ReadReturn);
}
template <class ReadOperation>
utils::TypeInfoRef TypeInfoFor(const ReadRequest<ReadOperation> & /* request */) {
return typeid(ReadOperation);
}
template <class... ReadOperations>
utils::TypeInfoRef TypeInfoFor(const ReadRequest<std::variant<ReadOperations...>> &request) {
return TypeInfoForVariant(request.operation);
}
template <class... WriteReturn>
utils::TypeInfoRef TypeInfoFor(const WriteResponse<std::variant<WriteReturn...>> &response) {
return TypeInfoForVariant(response.write_return);
}
template <class WriteReturn>
utils::TypeInfoRef TypeInfoFor(const WriteResponse<WriteReturn> & /* response */) {
return typeid(WriteReturn);
}
template <class WriteOperation>
utils::TypeInfoRef TypeInfoFor(const WriteRequest<WriteOperation> & /* request */) {
return typeid(WriteOperation);
}
template <class... WriteOperations>
utils::TypeInfoRef TypeInfoFor(const WriteRequest<std::variant<WriteOperations...>> &request) {
return TypeInfoForVariant(request.operation);
}
/// AppendRequest is a raft-level message that the Leader
/// periodically broadcasts to all Follower peers. This
/// serves three main roles:
/// 1. acts as a heartbeat from the Leader to the Follower
/// 2. replicates new data that the Leader has received to the Follower
/// 3. informs Follower peers when the commit index has increased,
/// signalling that it is now safe to apply log items to the
/// replicated state machine
template <typename WriteRequest>
struct AppendRequest {
Term term = 0;
LogIndex batch_start_log_index;
Term last_log_term;
std::vector<std::pair<Term, WriteRequest>> entries;
LogSize leader_commit;
};
struct AppendResponse {
bool success;
Term term;
Term last_log_term;
// a small optimization over the raft paper, tells
// the leader the offset that we are interested in
// to send log offsets from for us. This will only
// be useful at the beginning of a leader's term.
LogSize log_size;
};
struct VoteRequest {
Term term = 0;
LogSize log_size;
Term last_log_term;
};
struct VoteResponse {
Term term = 0;
LogSize committed_log_size;
bool vote_granted = false;
};
template <typename WriteRequest>
struct CommonState {
Term term = 0;
std::vector<std::pair<Term, WriteRequest>> log;
LogSize committed_log_size = 0;
LogSize applied_size = 0;
};
struct FollowerTracker {
LogIndex next_index = 0;
LogSize confirmed_log_size = 0;
};
struct PendingClientRequest {
RequestId request_id;
Address address;
Time received_at;
};
struct Leader {
std::map<Address, FollowerTracker> followers;
std::map<LogIndex, PendingClientRequest> pending_client_requests;
Time last_broadcast = Time::min();
std::string static ToString() { return "\tLeader \t"; }
};
struct Candidate {
std::map<Address, LogSize> successful_votes;
Time election_began = Time::min();
std::set<Address> outstanding_votes;
std::string static ToString() { return "\tCandidate\t"; }
};
struct Follower {
Time last_received_append_entries_timestamp;
Address leader_address;
std::string static ToString() { return "\tFollower \t"; }
};
using Role = std::variant<Candidate, Leader, Follower>;
template <typename Role>
concept AllRoles = memgraph::utils::SameAsAnyOf<Role, Leader, Follower, Candidate>;
template <typename Role>
concept LeaderOrFollower = memgraph::utils::SameAsAnyOf<Role, Leader, Follower>;
template <typename Role>
concept FollowerOrCandidate = memgraph::utils::SameAsAnyOf<Role, Follower, Candidate>;
/*
all ReplicatedState classes should have an Apply method
that returns our WriteResponseValue after consensus, and
a Read method that returns our ReadResponseValue without
requiring consensus.
ReadResponse Read(ReadOperation);
WriteResponseValue ReplicatedState::Apply(WriteRequest);
For example:
If the state is uint64_t, and WriteRequest is `struct PlusOne {};`,
and WriteResponseValue is also uint64_t (the new value), then
each call to state.Apply(PlusOne{}) will return the new value
after incrementing it. 0, 1, 2, 3... and this will be sent back
to the client that requested the mutation.
In practice, these mutations will usually be predicated on some
previous value, so that they are idempotent, functioning similarly
to a CAS operation.
*/
template <typename WriteOperation, typename ReadOperation, typename ReplicatedState, typename WriteResponseValue,
typename ReadResponseValue>
concept Rsm = requires(ReplicatedState state, WriteOperation w, ReadOperation r) {
{ state.Read(r) } -> std::same_as<ReadResponseValue>;
{ state.Apply(w) } -> std::same_as<WriteResponseValue>;
};
/// Parameter Purpose
/// --------------------------
/// IoImpl the concrete Io provider - SimulatorTransport, ThriftTransport, etc...
/// ReplicatedState the high-level data structure that is managed by the raft-backed replicated state machine
/// WriteOperation the individual operation type that is applied to the ReplicatedState in identical order
/// across each replica
/// WriteResponseValue the return value of calling ReplicatedState::Apply(WriteOperation), which is executed in
/// identical order across all replicas after an WriteOperation reaches consensus.
/// ReadOperation the type of operations that do not require consensus before executing directly
/// on a const ReplicatedState &
/// ReadResponseValue the return value of calling ReplicatedState::Read(ReadOperation), which is executed directly
/// without going through consensus first
template <typename IoImpl, typename ReplicatedState, typename WriteOperation, typename WriteResponseValue,
typename ReadOperation, typename ReadResponseValue>
requires Rsm<WriteOperation, ReadOperation, ReplicatedState, WriteResponseValue, ReadResponseValue>
class Raft {
CommonState<WriteOperation> state_;
Role role_ = Candidate{};
Io<IoImpl> io_;
std::vector<Address> peers_;
ReplicatedState replicated_state_;
Time next_cron_;
public:
Raft(Io<IoImpl> &&io, std::vector<Address> peers, ReplicatedState &&replicated_state)
: io_(std::forward<Io<IoImpl>>(io)),
peers_(peers),
replicated_state_(std::forward<ReplicatedState>(replicated_state)) {
if (peers.empty()) {
role_ = Leader{};
}
}
/// Periodic protocol maintenance. Returns the time that Cron should be called again
/// in the future.
Time Cron() {
// dispatch periodic logic based on our role to a specific Cron method.
std::optional<Role> new_role = std::visit([&](auto &role) { return Cron(role); }, role_);
if (new_role) {
role_ = std::move(new_role).value();
}
const Duration random_cron_interval = RandomTimeout(kMinimumCronInterval, kMaximumCronInterval);
return io_.Now() + random_cron_interval;
}
/// Returns the Address for our underlying Io implementation
Address GetAddress() { return io_.GetAddress(); }
using ReceiveVariant = std::variant<ReadRequest<ReadOperation>, AppendRequest<WriteOperation>, AppendResponse,
WriteRequest<WriteOperation>, VoteRequest, VoteResponse>;
void Handle(ReceiveVariant &&message_variant, RequestId request_id, Address from_address) {
// dispatch the message to a handler based on our role,
// which can be specified in the Handle first argument,
// or it can be `auto` if it's a handler for several roles
// or messages.
std::optional<Role> new_role = std::visit(
[&](auto &&msg, auto &role) mutable {
return Handle(role, std::forward<decltype(msg)>(msg), request_id, from_address);
},
std::forward<ReceiveVariant>(message_variant), role_);
// TODO(tyler) (M3) maybe replace std::visit with get_if for explicit prioritized matching, [[likely]] etc...
if (new_role) {
role_ = std::move(new_role).value();
}
}
void Run() {
while (!io_.ShouldShutDown()) {
const auto now = io_.Now();
if (now >= next_cron_) {
next_cron_ = Cron();
}
const Duration receive_timeout = RandomTimeout(kMinimumReceiveTimeout, kMaximumReceiveTimeout);
auto request_result =
io_.template ReceiveWithTimeout<ReadRequest<ReadOperation>, AppendRequest<WriteOperation>, AppendResponse,
WriteRequest<WriteOperation>, VoteRequest, VoteResponse>(receive_timeout);
if (request_result.HasError()) {
continue;
}
auto request = std::move(request_result.GetValue());
Handle(std::move(request.message), request.request_id, request.from_address);
}
}
private:
// Raft paper - 5.3
// When the entry has been safely replicated, the leader applies the
// entry to its state machine and returns the result of that
// execution to the client.
//
// "Safely replicated" is defined as being known to be present
// on at least a majority of all peers (inclusive of the Leader).
void BumpCommitIndexAndReplyToClients(Leader &leader) {
auto confirmed_log_sizes = std::vector<LogSize>{};
// We include our own log size in the calculation of the log
// confirmed log size that is present on at least a majority of all peers.
confirmed_log_sizes.push_back(state_.log.size());
for (const auto &[addr, f] : leader.followers) {
confirmed_log_sizes.push_back(f.confirmed_log_size);
Log("Follower at port ", addr.last_known_port, " has confirmed log size of: ", f.confirmed_log_size);
}
// reverse sort from highest to lowest (using std::ranges::greater)
std::ranges::sort(confirmed_log_sizes, std::ranges::greater());
// This is a particularly correctness-critical calculation because it
// determines the committed log size that will be broadcast in
// the next AppendRequest.
//
// If the following sizes are recorded for clusters of different numbers of peers,
// these are the expected sizes that are considered to have reached consensus:
//
// state | expected value | (confirmed_log_sizes.size() / 2)
// [1] 1 (1 / 2) => 0
// [2, 1] 1 (2 / 2) => 1
// [3, 2, 1] 2 (3 / 2) => 1
// [4, 3, 2, 1] 2 (4 / 2) => 2
// [5, 4, 3, 2, 1] 3 (5 / 2) => 2
const size_t majority_index = confirmed_log_sizes.size() / 2;
const LogSize new_committed_log_size = confirmed_log_sizes[majority_index];
// We never go backwards in history.
MG_ASSERT(state_.committed_log_size <= new_committed_log_size,
"as a Leader, we have previously set our committed_log_size to {}, but our Followers have a majority "
"committed_log_size of {}",
state_.committed_log_size, new_committed_log_size);
state_.committed_log_size = new_committed_log_size;
// For each size between the old size and the new one (inclusive),
// Apply that log's WriteOperation to our replicated_state_,
// and use the specific return value of the ReplicatedState::Apply
// method (WriteResponseValue) to respond to the requester.
for (; state_.applied_size < state_.committed_log_size; state_.applied_size++) {
const LogIndex apply_index = state_.applied_size;
const auto &write_request = state_.log[apply_index].second;
const WriteResponseValue write_return = replicated_state_.Apply(write_request);
if (leader.pending_client_requests.contains(apply_index)) {
const PendingClientRequest client_request = std::move(leader.pending_client_requests.at(apply_index));
leader.pending_client_requests.erase(apply_index);
const WriteResponse<WriteResponseValue> resp{
.success = true,
.write_return = std::move(write_return),
.raft_index = apply_index,
};
io_.Send(client_request.address, client_request.request_id, std::move(resp));
}
}
Log("committed_log_size is now ", state_.committed_log_size);
}
// Raft paper - 5.1
// AppendEntries RPCs are initiated by leaders to replicate log entries and to provide a form of heartbeat
void BroadcastAppendEntries(std::map<Address, FollowerTracker> &followers) {
for (auto &[address, follower] : followers) {
const LogIndex next_index = follower.next_index;
const auto missing = state_.log.size() - next_index;
const auto batch_size = std::min(missing, kMaximumAppendBatchSize);
const auto start_index = next_index;
const auto end_index = start_index + batch_size;
// advance follower's next index
follower.next_index += batch_size;
std::vector<std::pair<Term, WriteOperation>> entries;
entries.insert(entries.begin(), state_.log.begin() + start_index, state_.log.begin() + end_index);
const Term previous_term_from_index = PreviousTermFromIndex(start_index);
Log("sending ", entries.size(), " entries to Follower ", address.last_known_port,
" which are above its next_index of ", next_index);
AppendRequest<WriteOperation> ar{
.term = state_.term,
.batch_start_log_index = start_index,
.last_log_term = previous_term_from_index,
.entries = std::move(entries),
.leader_commit = state_.committed_log_size,
};
// request_id not necessary to set because it's not a Future-backed Request.
static constexpr RequestId request_id = 0;
io_.Send(address, request_id, std::move(ar));
}
}
// Raft paper - 5.2
// Raft uses randomized election timeouts to ensure that split votes are rare and that they are resolved quickly
Duration RandomTimeout(Duration min, Duration max) {
std::uniform_int_distribution time_distrib(min.count(), max.count());
const auto rand_micros = io_.Rand(time_distrib);
return Duration{rand_micros};
}
Duration RandomTimeout(int min_micros, int max_micros) {
std::uniform_int_distribution time_distrib(min_micros, max_micros);
const int rand_micros = io_.Rand(time_distrib);
return std::chrono::microseconds{rand_micros};
}
Term PreviousTermFromIndex(LogIndex index) const {
if (index == 0 || state_.log.size() + 1 <= index) {
return 0;
}
const auto &[term, data] = state_.log.at(index - 1);
return term;
}
Term CommittedLogTerm() {
MG_ASSERT(state_.log.size() >= state_.committed_log_size);
if (state_.log.empty() || state_.committed_log_size == 0) {
return 0;
}
const auto &[term, data] = state_.log.at(state_.committed_log_size - 1);
return term;
}
Term LastLogTerm() const {
if (state_.log.empty()) {
return 0;
}
const auto &[term, data] = state_.log.back();
return term;
}
template <typename... Ts>
void Log(Ts &&...args) {
const Time now = io_.Now();
const auto micros = std::chrono::duration_cast<std::chrono::milliseconds>(now.time_since_epoch()).count();
const Term term = state_.term;
const std::string role_string = std::visit([&](const auto &role) { return role.ToString(); }, role_);
std::ostringstream out;
out << '\t' << static_cast<int>(micros) << "\t" << term << "\t" << io_.GetAddress().last_known_port;
out << role_string;
(out << ... << args);
spdlog::info(out.str());
}
/////////////////////////////////////////////////////////////
/// Raft-related Cron methods
///
/// Cron + std::visit is how events are dispatched
/// to certain code based on Raft role.
///
/// Cron(role) takes as the first argument a reference to its
/// role, and as the second argument, the message that has
/// been received.
/////////////////////////////////////////////////////////////
// Raft paper - 5.2
// Candidates keep sending Vote to peers until:
// 1. receiving Append with a higher term (become Follower)
// 2. receiving Vote with a higher term (become a Follower)
// 3. receiving a quorum of responses to our last batch of Vote (become a Leader)
std::optional<Role> Cron(Candidate &candidate) {
const auto now = io_.Now();
const Duration election_timeout = RandomTimeout(kMinimumElectionTimeout, kMaximumElectionTimeout);
const auto election_timeout_us = std::chrono::duration_cast<std::chrono::milliseconds>(election_timeout).count();
if (now - candidate.election_began > election_timeout) {
state_.term++;
Log("becoming Candidate for term ", state_.term, " after leader timeout of ", election_timeout_us,
"ms elapsed since last election attempt");
const VoteRequest request{
.term = state_.term,
.log_size = state_.log.size(),
.last_log_term = LastLogTerm(),
};
auto outstanding_votes = std::set<Address>();
for (const auto &peer : peers_) {
// request_id not necessary to set because it's not a Future-backed Request.
static constexpr auto request_id = 0;
io_.template Send<VoteRequest>(peer, request_id, request);
outstanding_votes.insert(peer);
}
return Candidate{
.successful_votes = std::map<Address, LogIndex>(),
.election_began = now,
.outstanding_votes = outstanding_votes,
};
}
return std::nullopt;
}
// Raft paper - 5.2
// Followers become candidates if we haven't heard from the leader
// after a randomized timeout.
std::optional<Role> Cron(Follower &follower) {
const auto now = io_.Now();
const auto time_since_last_append_entries = now - follower.last_received_append_entries_timestamp;
// randomized follower timeout
const Duration election_timeout = RandomTimeout(kMinimumElectionTimeout, kMaximumElectionTimeout);
if (time_since_last_append_entries > election_timeout) {
// become a Candidate if we haven't heard from the Leader after this timeout
return Candidate{};
}
return std::nullopt;
}
// Leaders (re)send AppendRequest to followers.
std::optional<Role> Cron(Leader &leader) {
const Time now = io_.Now();
const Duration broadcast_timeout = RandomTimeout(kMinimumBroadcastTimeout, kMaximumBroadcastTimeout);
if (now > leader.last_broadcast + broadcast_timeout) {
BroadcastAppendEntries(leader.followers);
leader.last_broadcast = now;
}
return std::nullopt;
}
/////////////////////////////////////////////////////////////
/// Raft-related Handle methods
///
/// Handle + std::visit is how events are dispatched
/// to certain code based on Raft role.
///
/// Handle(role, message, ...)
/// takes as the first argument a reference
/// to its role, and as the second argument, the
/// message that has been received.
/////////////////////////////////////////////////////////////
// all roles can receive Vote and possibly become a follower
template <AllRoles ALL>
std::optional<Role> Handle(ALL & /* variable */, VoteRequest &&req, RequestId request_id, Address from_address) {
Log("received VoteRequest from ", from_address.last_known_port, " with term ", req.term);
const bool last_log_term_dominates = req.last_log_term >= LastLogTerm();
const bool term_dominates = req.term > state_.term;
const bool log_size_dominates = req.log_size >= state_.log.size();
const bool new_leader = last_log_term_dominates && term_dominates && log_size_dominates;
if (new_leader) {
MG_ASSERT(req.term > state_.term);
MG_ASSERT(std::max(req.term, state_.term) == req.term);
}
const VoteResponse res{
.term = std::max(req.term, state_.term),
.committed_log_size = state_.committed_log_size,
.vote_granted = new_leader,
};
io_.Send(from_address, request_id, res);
if (new_leader) {
// become a follower
state_.term = req.term;
return Follower{
.last_received_append_entries_timestamp = io_.Now(),
.leader_address = from_address,
};
}
if (term_dominates) {
Log("received a vote from an inferior candidate. Becoming Candidate");
state_.term = std::max(state_.term, req.term) + 1;
return Candidate{};
}
return std::nullopt;
}
std::optional<Role> Handle(Candidate &candidate, VoteResponse &&res, RequestId /* variable */, Address from_address) {
Log("received VoteResponse");
if (!res.vote_granted || res.term != state_.term) {
Log("received unsuccessful VoteResponse from term ", res.term, " when our candidacy term is ", state_.term);
// we received a delayed VoteResponse from the past, which has to do with an election that is
// no longer valid. We can simply drop this.
return std::nullopt;
}
MG_ASSERT(candidate.outstanding_votes.contains(from_address),
"Received unexpected VoteResponse from server not present in Candidate's outstanding_votes!");
candidate.outstanding_votes.erase(from_address);
MG_ASSERT(!candidate.successful_votes.contains(from_address),
"Received unexpected VoteResponse from server already in Candidate's successful_votes!");
candidate.successful_votes.insert({from_address, res.committed_log_size});
if (candidate.successful_votes.size() >= candidate.outstanding_votes.size()) {
std::map<Address, FollowerTracker> followers{};
for (const auto &[address, committed_log_size] : candidate.successful_votes) {
FollowerTracker follower{
.next_index = committed_log_size,
.confirmed_log_size = committed_log_size,
};
followers.insert({address, follower});
}
for (const auto &address : candidate.outstanding_votes) {
FollowerTracker follower{
.next_index = state_.log.size(),
.confirmed_log_size = 0,
};
followers.insert({address, follower});
}
Log("becoming Leader at term ", state_.term);
BroadcastAppendEntries(followers);
return Leader{
.followers = std::move(followers),
.pending_client_requests = std::map<LogIndex, PendingClientRequest>(),
};
}
return std::nullopt;
}
template <LeaderOrFollower LOF>
std::optional<Role> Handle(LOF & /* variable */, VoteResponse && /* variable */, RequestId /* variable */,
Address /* variable */) {
Log("non-Candidate received VoteResponse");
return std::nullopt;
}
template <AllRoles ALL>
std::optional<Role> Handle(ALL &role, AppendRequest<WriteOperation> &&req, RequestId request_id,
Address from_address) {
// log size starts out as state_.committed_log_size and only if everything is successful do we
// switch it to the log length.
AppendResponse res{
.success = false,
.term = state_.term,
.last_log_term = CommittedLogTerm(),
.log_size = state_.log.size(),
};
if constexpr (std::is_same<ALL, Leader>()) {
MG_ASSERT(req.term != state_.term, "Multiple leaders are acting under the term ", req.term);
}
const bool is_candidate = std::is_same<ALL, Candidate>();
const bool is_failed_competitor = is_candidate && req.term == state_.term;
const Time now = io_.Now();
// Raft paper - 5.2
// While waiting for votes, a candidate may receive an
// AppendEntries RPC from another server claiming to be leader. If
// the leaders term (included in its RPC) is at least as large as
// the candidates current term, then the candidate recognizes the
// leader as legitimate and returns to follower state.
if (req.term > state_.term || is_failed_competitor) {
// become follower of this leader, reply with our log status
state_.term = req.term;
io_.Send(from_address, request_id, res);
Log("becoming Follower of Leader ", from_address.last_known_port, " at term ", req.term);
return Follower{
.last_received_append_entries_timestamp = now,
.leader_address = from_address,
};
}
if (req.term < state_.term) {
// nack this request from an old leader
io_.Send(from_address, request_id, res);
return std::nullopt;
}
// at this point, we're dealing with our own leader
if constexpr (std::is_same<ALL, Follower>()) {
// small specialization for when we're already a Follower
MG_ASSERT(role.leader_address == from_address, "Multiple Leaders are acting under the same term number!");
role.last_received_append_entries_timestamp = now;
} else {
Log("Somehow entered Follower-specific logic as a non-Follower");
MG_ASSERT(false, "Somehow entered Follower-specific logic as a non-Follower");
}
// Handle steady-state conditions.
if (req.batch_start_log_index != state_.log.size()) {
Log("req.batch_start_log_index of ", req.batch_start_log_index, " does not match our log size of ",
state_.log.size());
} else if (req.last_log_term != LastLogTerm()) {
Log("req.last_log_term differs from our leader term at that slot, expected: ", LastLogTerm(), " but got ",
req.last_log_term);
} else {
// happy path - Apply log
Log("applying batch of ", req.entries.size(), " entries to our log starting at index ",
req.batch_start_log_index);
const auto resize_length = req.batch_start_log_index;
MG_ASSERT(resize_length >= state_.committed_log_size,
"Applied history from Leader which goes back in time from our commit_index");
// possibly chop-off stuff that was replaced by
// things with different terms (we got data that
// hasn't reached consensus yet, which is normal)
state_.log.resize(resize_length);
if (req.entries.size() > 0) {
auto &[first_term, op] = req.entries.at(0);
MG_ASSERT(LastLogTerm() <= first_term);
}
state_.log.insert(state_.log.end(), std::make_move_iterator(req.entries.begin()),
std::make_move_iterator(req.entries.end()));
MG_ASSERT(req.leader_commit >= state_.committed_log_size);
state_.committed_log_size = std::min(req.leader_commit, state_.log.size());
for (; state_.applied_size < state_.committed_log_size; state_.applied_size++) {
const auto &write_request = state_.log[state_.applied_size].second;
replicated_state_.Apply(write_request);
}
res.success = true;
}
res.last_log_term = LastLogTerm();
res.log_size = state_.log.size();
Log("returning log_size of ", res.log_size);
io_.Send(from_address, request_id, res);
return std::nullopt;
}
std::optional<Role> Handle(Leader &leader, AppendResponse &&res, RequestId /* variable */, Address from_address) {
if (res.term != state_.term) {
Log("received AppendResponse related to a previous term when we (presumably) were the leader");
return std::nullopt;
}
// TODO(tyler) when we have dynamic membership, this assert will become incorrect, but we should
// keep it in-place until then because it has bug finding value.
MG_ASSERT(leader.followers.contains(from_address), "received AppendResponse from unknown Follower");
// at this point, we know the term matches and we know this Follower
FollowerTracker &follower = leader.followers.at(from_address);
if (res.success) {
Log("got successful AppendResponse from ", from_address.last_known_port, " with log_size of ", res.log_size);
follower.next_index = std::max(follower.next_index, res.log_size);
} else {
Log("got unsuccessful AppendResponse from ", from_address.last_known_port, " with log_size of ", res.log_size);
follower.next_index = res.log_size;
}
follower.confirmed_log_size = std::max(follower.confirmed_log_size, res.log_size);
BumpCommitIndexAndReplyToClients(leader);
return std::nullopt;
}
template <FollowerOrCandidate FOC>
std::optional<Role> Handle(FOC & /* variable */, AppendResponse && /* variable */, RequestId /* variable */,
Address /* variable */) {
// we used to be the leader, and are getting old delayed responses
return std::nullopt;
}
/////////////////////////////////////////////////////////////
/// RSM-related handle methods
/////////////////////////////////////////////////////////////
// Leaders are able to immediately respond to the requester (with a ReadResponseValue) applied to the ReplicatedState
std::optional<Role> Handle(Leader & /* variable */, ReadRequest<ReadOperation> &&req, RequestId request_id,
Address from_address) {
auto type_info = TypeInfoFor(req);
std::string demangled_name = boost::core::demangle(type_info.get().name());
Log("handling ReadOperation<" + demangled_name + ">");
ReadOperation read_operation = req.operation;
ReadResponseValue read_return = replicated_state_.Read(read_operation);
const ReadResponse<ReadResponseValue> resp{
.success = true,
.read_return = std::move(read_return),
.retry_leader = std::nullopt,
};
io_.Send(from_address, request_id, resp);
return std::nullopt;
}
// Candidates should respond with a failure, similar to the Candidate + WriteRequest failure below
std::optional<Role> Handle(Candidate & /* variable */, ReadRequest<ReadOperation> && /* variable */,
RequestId request_id, Address from_address) {
Log("received ReadOperation - not redirecting because no Leader is known");
const ReadResponse<ReadResponseValue> res{
.success = false,
};
io_.Send(from_address, request_id, res);
Cron();
return std::nullopt;
}
// Followers should respond with a redirection, similar to the Follower + WriteRequest response below
std::optional<Role> Handle(Follower &follower, ReadRequest<ReadOperation> && /* variable */, RequestId request_id,
Address from_address) {
Log("redirecting client to known Leader with port ", follower.leader_address.last_known_port);
const ReadResponse<ReadResponseValue> res{
.success = false,
.retry_leader = follower.leader_address,
};
io_.Send(from_address, request_id, res);
return std::nullopt;
}
// Raft paper - 8
// When a client first starts up, it connects to a randomly chosen
// server. If the clients first choice is not the leader, that
// server will reject the clients request and supply information
// about the most recent leader it has heard from.
std::optional<Role> Handle(Follower &follower, WriteRequest<WriteOperation> && /* variable */, RequestId request_id,
Address from_address) {
Log("redirecting client to known Leader with port ", follower.leader_address.last_known_port);
const WriteResponse<WriteResponseValue> res{
.success = false,
.retry_leader = follower.leader_address,
};
io_.Send(from_address, request_id, res);
return std::nullopt;
}
std::optional<Role> Handle(Candidate & /* variable */, WriteRequest<WriteOperation> && /* variable */,
RequestId request_id, Address from_address) {
Log("received WriteRequest - not redirecting because no Leader is known");
const WriteResponse<WriteResponseValue> res{
.success = false,
};
io_.Send(from_address, request_id, res);
Cron();
return std::nullopt;
}
// only leaders actually handle replication requests from clients
std::optional<Role> Handle(Leader &leader, WriteRequest<WriteOperation> &&req, RequestId request_id,
Address from_address) {
auto type_info = TypeInfoFor(req);
std::string demangled_name = boost::core::demangle(type_info.get().name());
Log("handling WriteRequest<" + demangled_name + ">");
// we are the leader. add item to log and send Append to peers
MG_ASSERT(state_.term >= LastLogTerm());
state_.log.emplace_back(std::pair(state_.term, std::move(req.operation)));
LogIndex log_index = state_.log.size() - 1;
PendingClientRequest pcr{
.request_id = request_id,
.address = from_address,
.received_at = io_.Now(),
};
leader.pending_client_requests.emplace(log_index, pcr);
if (peers_.empty()) {
BumpCommitIndexAndReplyToClients(leader);
} else {
BroadcastAppendEntries(leader.followers);
}
return std::nullopt;
}
};
}; // namespace memgraph::io::rsm

View File

@@ -1,257 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <iostream>
#include <optional>
#include <type_traits>
#include <unordered_map>
#include <vector>
#include "io/address.hpp"
#include "io/errors.hpp"
#include "io/notifier.hpp"
#include "io/rsm/raft.hpp"
#include "utils/result.hpp"
namespace memgraph::io::rsm {
using memgraph::io::Address;
using memgraph::io::Duration;
using memgraph::io::ResponseEnvelope;
using memgraph::io::ResponseFuture;
using memgraph::io::ResponseResult;
using memgraph::io::Time;
using memgraph::io::TimedOut;
using memgraph::io::rsm::ReadRequest;
using memgraph::io::rsm::ReadResponse;
using memgraph::io::rsm::WriteRequest;
using memgraph::io::rsm::WriteResponse;
using memgraph::utils::BasicResult;
template <typename RequestT, typename ResponseT>
struct AsyncRequest {
Time start_time;
RequestT request;
Notifier notifier;
ResponseFuture<ResponseT> future;
};
template <typename IoImpl, typename WriteRequestT, typename WriteResponseT, typename ReadRequestT,
typename ReadResponseT>
class RsmClient {
using ServerPool = std::vector<Address>;
Io<IoImpl> io_;
Address leader_;
ServerPool server_addrs_;
/// State for single async read/write operations. In the future this could become a map
/// of async operations that can be accessed via an ID etc...
std::unordered_map<size_t, AsyncRequest<ReadRequestT, ReadResponse<ReadResponseT>>> async_reads_;
std::unordered_map<size_t, AsyncRequest<WriteRequestT, WriteResponse<WriteResponseT>>> async_writes_;
void SelectRandomLeader() {
std::uniform_int_distribution<size_t> addr_distrib(0, (server_addrs_.size() - 1));
size_t addr_index = io_.Rand(addr_distrib);
leader_ = server_addrs_[addr_index];
spdlog::debug("selecting a random leader at index {} with address {}", addr_index, leader_.ToString());
}
template <typename ResponseT>
void PossiblyRedirectLeader(const ResponseT &response) {
if (response.retry_leader) {
MG_ASSERT(!response.success, "retry_leader should never be set for successful responses");
leader_ = response.retry_leader.value();
spdlog::debug("client redirected to leader server {}", leader_.ToString());
}
if (!response.success) {
SelectRandomLeader();
}
}
public:
RsmClient(Io<IoImpl> io, Address leader, ServerPool server_addrs)
: io_{io}, leader_{leader}, server_addrs_{server_addrs} {}
RsmClient(const RsmClient &) = delete;
RsmClient &operator=(const RsmClient &) = delete;
RsmClient(RsmClient &&) noexcept = default;
RsmClient &operator=(RsmClient &&) noexcept = default;
RsmClient() = delete;
~RsmClient() = default;
BasicResult<TimedOut, WriteResponseT> SendWriteRequest(WriteRequestT req) {
Notifier notifier;
const ReadinessToken readiness_token{0};
SendAsyncWriteRequest(req, notifier, readiness_token);
auto poll_result = AwaitAsyncWriteRequest(readiness_token);
while (!poll_result) {
poll_result = AwaitAsyncWriteRequest(readiness_token);
}
return poll_result.value();
}
BasicResult<TimedOut, ReadResponseT> SendReadRequest(ReadRequestT req) {
Notifier notifier;
const ReadinessToken readiness_token{0};
SendAsyncReadRequest(req, notifier, readiness_token);
auto poll_result = AwaitAsyncReadRequest(readiness_token);
while (!poll_result) {
poll_result = AwaitAsyncReadRequest(readiness_token);
}
return poll_result.value();
}
/// AsyncRead methods
void SendAsyncReadRequest(const ReadRequestT &req, Notifier notifier, ReadinessToken readiness_token) {
ReadRequest<ReadRequestT> read_req = {.operation = req};
AsyncRequest<ReadRequestT, ReadResponse<ReadResponseT>> async_request{
.start_time = io_.Now(),
.request = std::move(req),
.notifier = notifier,
.future = io_.template RequestWithNotification<ReadRequest<ReadRequestT>, ReadResponse<ReadResponseT>>(
leader_, read_req, notifier, readiness_token),
};
async_reads_.emplace(readiness_token.GetId(), std::move(async_request));
}
void ResendAsyncReadRequest(const ReadinessToken &readiness_token) {
auto &async_request = async_reads_.at(readiness_token.GetId());
ReadRequest<ReadRequestT> read_req = {.operation = async_request.request};
async_request.future = io_.template RequestWithNotification<ReadRequest<ReadRequestT>, ReadResponse<ReadResponseT>>(
leader_, read_req, async_request.notifier, readiness_token);
}
std::optional<BasicResult<TimedOut, ReadResponseT>> PollAsyncReadRequest(const ReadinessToken &readiness_token) {
auto &async_request = async_reads_.at(readiness_token.GetId());
if (!async_request.future.IsReady()) {
return std::nullopt;
}
return AwaitAsyncReadRequest(readiness_token);
}
std::optional<BasicResult<TimedOut, ReadResponseT>> AwaitAsyncReadRequest(const ReadinessToken &readiness_token) {
auto &async_request = async_reads_.at(readiness_token.GetId());
ResponseResult<ReadResponse<ReadResponseT>> get_response_result = std::move(async_request.future).Wait();
const Duration overall_timeout = io_.GetDefaultTimeout();
const bool past_time_out = io_.Now() > async_request.start_time + overall_timeout;
const bool result_has_error = get_response_result.HasError();
if (result_has_error && past_time_out) {
// TODO static assert the exact type of error.
spdlog::debug("client timed out while trying to communicate with leader server {}", leader_.ToString());
async_reads_.erase(readiness_token.GetId());
return TimedOut{};
}
if (!result_has_error) {
ResponseEnvelope<ReadResponse<ReadResponseT>> &&get_response_envelope = std::move(get_response_result.GetValue());
ReadResponse<ReadResponseT> &&read_get_response = std::move(get_response_envelope.message);
PossiblyRedirectLeader(read_get_response);
if (read_get_response.success) {
async_reads_.erase(readiness_token.GetId());
spdlog::debug("returning read_return for RSM request");
return std::move(read_get_response.read_return);
}
} else {
SelectRandomLeader();
}
ResendAsyncReadRequest(readiness_token);
return std::nullopt;
}
/// AsyncWrite methods
void SendAsyncWriteRequest(const WriteRequestT &req, Notifier notifier, ReadinessToken readiness_token) {
WriteRequest<WriteRequestT> write_req = {.operation = req};
AsyncRequest<WriteRequestT, WriteResponse<WriteResponseT>> async_request{
.start_time = io_.Now(),
.request = std::move(req),
.notifier = notifier,
.future = io_.template RequestWithNotification<WriteRequest<WriteRequestT>, WriteResponse<WriteResponseT>>(
leader_, write_req, notifier, readiness_token),
};
async_writes_.emplace(readiness_token.GetId(), std::move(async_request));
}
void ResendAsyncWriteRequest(const ReadinessToken &readiness_token) {
auto &async_request = async_writes_.at(readiness_token.GetId());
WriteRequest<WriteRequestT> write_req = {.operation = async_request.request};
async_request.future =
io_.template RequestWithNotification<WriteRequest<WriteRequestT>, WriteResponse<WriteResponseT>>(
leader_, write_req, async_request.notifier, readiness_token);
}
std::optional<BasicResult<TimedOut, WriteResponseT>> PollAsyncWriteRequest(const ReadinessToken &readiness_token) {
auto &async_request = async_writes_.at(readiness_token.GetId());
if (!async_request.future.IsReady()) {
return std::nullopt;
}
return AwaitAsyncWriteRequest(readiness_token);
}
std::optional<BasicResult<TimedOut, WriteResponseT>> AwaitAsyncWriteRequest(const ReadinessToken &readiness_token) {
auto &async_request = async_writes_.at(readiness_token.GetId());
ResponseResult<WriteResponse<WriteResponseT>> get_response_result = std::move(async_request.future).Wait();
const Duration overall_timeout = io_.GetDefaultTimeout();
const bool past_time_out = io_.Now() > async_request.start_time + overall_timeout;
const bool result_has_error = get_response_result.HasError();
if (result_has_error && past_time_out) {
// TODO static assert the exact type of error.
spdlog::debug("client timed out while trying to communicate with leader server {}", leader_.ToString());
async_writes_.erase(readiness_token.GetId());
return TimedOut{};
}
if (!result_has_error) {
ResponseEnvelope<WriteResponse<WriteResponseT>> &&get_response_envelope =
std::move(get_response_result.GetValue());
WriteResponse<WriteResponseT> &&write_get_response = std::move(get_response_envelope.message);
PossiblyRedirectLeader(write_get_response);
if (write_get_response.success) {
async_writes_.erase(readiness_token.GetId());
return std::move(write_get_response.write_return);
}
} else {
SelectRandomLeader();
}
ResendAsyncWriteRequest(readiness_token);
return std::nullopt;
}
};
} // namespace memgraph::io::rsm

View File

@@ -1,155 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
/// The ShardRsm is a simple in-memory raft-backed kv store that can be used for simple testing
/// and implementation of some query engine logic before storage engines are fully implemented.
///
/// To implement multiple read and write commands, change the StorageRead* and StorageWrite* requests
/// and responses to a std::variant of the different options, and route them to specific handlers in
/// the ShardRsm's Read and Apply methods. Remember that Read is called immediately when the Raft
/// leader receives the request, and does not replicate anything over Raft. Apply is called only
/// AFTER the StorageWriteRequest is replicated to a majority of Raft peers, and the result of calling
/// ShardRsm::Apply(StorageWriteRequest) is returned to the client that submitted the request.
#include <deque>
#include <iostream>
#include <map>
#include <optional>
#include <set>
#include <thread>
#include <vector>
#include "coordinator/hybrid_logical_clock.hpp"
#include "io/address.hpp"
#include "io/rsm/raft.hpp"
#include "storage/v3/id_types.hpp"
#include "storage/v3/property_value.hpp"
#include "utils/logging.hpp"
namespace memgraph::io::rsm {
using memgraph::coordinator::Hlc;
using memgraph::storage::v3::LabelId;
using memgraph::storage::v3::PropertyValue;
using ShardRsmKey = std::vector<PropertyValue>;
struct StorageWriteRequest {
LabelId label_id;
Hlc transaction_id;
ShardRsmKey key;
std::optional<int> value;
};
struct StorageWriteResponse {
bool shard_rsm_success;
std::optional<int> last_value;
// Only has a value if the given shard does not contain the requested key
std::optional<Hlc> latest_known_shard_map_version{std::nullopt};
};
struct StorageReadRequest {
LabelId label_id;
Hlc transaction_id;
ShardRsmKey key;
};
struct StorageReadResponse {
bool shard_rsm_success;
std::optional<int> value;
// Only has a value if the given shard does not contain the requested key
std::optional<Hlc> latest_known_shard_map_version{std::nullopt};
};
class ShardRsm {
std::map<ShardRsmKey, int> state_;
ShardRsmKey minimum_key_;
std::optional<ShardRsmKey> maximum_key_{std::nullopt};
Hlc shard_map_version_;
// The key is not located in this shard
bool IsKeyInRange(const ShardRsmKey &key) const {
if (maximum_key_) [[likely]] {
return (key >= minimum_key_ && key <= maximum_key_);
}
return key >= minimum_key_;
}
public:
StorageReadResponse Read(StorageReadRequest request) const {
StorageReadResponse ret;
if (!IsKeyInRange(request.key)) {
ret.latest_known_shard_map_version = shard_map_version_;
ret.shard_rsm_success = false;
} else if (state_.contains(request.key)) {
ret.value = state_.at(request.key);
ret.shard_rsm_success = true;
} else {
ret.shard_rsm_success = false;
ret.value = std::nullopt;
}
return ret;
}
StorageWriteResponse Apply(StorageWriteRequest request) {
StorageWriteResponse ret;
// Key is outside the prohibited range
if (!IsKeyInRange(request.key)) {
ret.latest_known_shard_map_version = shard_map_version_;
ret.shard_rsm_success = false;
}
// Key exist
else if (state_.contains(request.key)) {
auto &val = state_[request.key];
/*
* Delete
*/
if (!request.value) {
ret.shard_rsm_success = true;
ret.last_value = val;
state_.erase(state_.find(request.key));
}
/*
* Update
*/
// Does old_value match?
if (request.value == val) {
ret.last_value = val;
ret.shard_rsm_success = true;
val = request.value.value();
} else {
ret.last_value = val;
ret.shard_rsm_success = false;
}
}
/*
* Create
*/
else {
ret.last_value = std::nullopt;
ret.shard_rsm_success = true;
state_.emplace(request.key, request.value.value());
}
return ret;
}
};
} // namespace memgraph::io::rsm

View File

@@ -1,8 +0,0 @@
set(io_simulator_sources
simulator_handle.cpp)
find_package(fmt REQUIRED)
find_package(Threads REQUIRED)
add_library(mg-io-simulator STATIC ${io_simulator_sources})
target_link_libraries(mg-io-simulator stdc++fs Threads::Threads fmt::fmt mg-utils)

View File

@@ -1,62 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <memory>
#include <random>
#include "io/address.hpp"
#include "io/simulator/simulator_config.hpp"
#include "io/simulator/simulator_handle.hpp"
#include "io/simulator/simulator_transport.hpp"
namespace memgraph::io::simulator {
class Simulator {
std::mt19937 rng_;
std::shared_ptr<SimulatorHandle> simulator_handle_;
uint16_t auto_port_ = 0;
public:
explicit Simulator(SimulatorConfig config)
: rng_(std::mt19937{config.rng_seed}), simulator_handle_{std::make_shared<SimulatorHandle>(config)} {}
~Simulator() { ShutDown(); }
void ShutDown() { simulator_handle_->ShutDown(); }
Io<SimulatorTransport> RegisterNew() {
Address address = Address::TestAddress(auto_port_++);
return Register(address);
}
Io<SimulatorTransport> Register(Address address) {
std::uniform_int_distribution<uint64_t> seed_distrib;
uint64_t seed = seed_distrib(rng_);
return Io{SimulatorTransport(simulator_handle_, address, seed), address};
}
void IncrementServerCountAndWaitForQuiescentState(Address address) {
simulator_handle_->IncrementServerCountAndWaitForQuiescentState(address);
}
SimulatorStats Stats() { return simulator_handle_->Stats(); }
std::shared_ptr<SimulatorHandle> GetSimulatorHandle() const { return simulator_handle_; }
std::function<bool()> GetSimulatorTickClosure() {
std::function<bool()> tick_closure = [handle_copy = simulator_handle_] {
return handle_copy->MaybeTickSimulator();
};
return tick_closure;
}
};
}; // namespace memgraph::io::simulator

View File

@@ -1,30 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <chrono>
#include "io/time.hpp"
namespace memgraph::io::simulator {
using memgraph::io::Time;
struct SimulatorConfig {
uint8_t drop_percent = 0;
bool perform_timeouts = false;
bool scramble_messages = true;
uint64_t rng_seed = 0;
Time start_time = Time::min();
Time abort_time = Time::max();
};
}; // namespace memgraph::io::simulator

View File

@@ -1,194 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#include "io/simulator/simulator_handle.hpp"
#include "io/address.hpp"
#include "io/errors.hpp"
#include "io/simulator/simulator_config.hpp"
#include "io/simulator/simulator_stats.hpp"
#include "io/time.hpp"
#include "io/transport.hpp"
#include "utils/exceptions.hpp"
namespace memgraph::io::simulator {
void SimulatorHandle::ShutDown() {
std::unique_lock<std::mutex> lock(mu_);
should_shut_down_ = true;
for (auto it = promises_.begin(); it != promises_.end();) {
auto &[promise_key, dop] = *it;
std::move(dop).promise.TimeOut();
it = promises_.erase(it);
}
can_receive_.clear();
cv_.notify_all();
}
bool SimulatorHandle::ShouldShutDown() const {
std::unique_lock<std::mutex> lock(mu_);
return should_shut_down_;
}
LatencyHistogramSummaries SimulatorHandle::ResponseLatencies() {
std::unique_lock<std::mutex> lock(mu_);
return histograms_.ResponseLatencies();
}
void SimulatorHandle::IncrementServerCountAndWaitForQuiescentState(Address address) {
std::unique_lock<std::mutex> lock(mu_);
server_addresses_.insert(address);
while (true) {
const size_t blocked_servers = blocked_on_receive_.size();
const bool all_servers_blocked = blocked_servers == server_addresses_.size();
if (all_servers_blocked) {
spdlog::trace("quiescent state detected - {} out of {} servers now blocked on receive", blocked_servers,
server_addresses_.size());
return;
}
spdlog::trace("not returning from quiescent because we see {} blocked out of {}", blocked_servers,
server_addresses_.size());
cv_.wait(lock);
}
}
bool SortInFlight(const std::pair<Address, OpaqueMessage> &lhs, const std::pair<Address, OpaqueMessage> &rhs) {
// NB: never sort based on the request ID etc...
// This should only be used from std::stable_sort
// because by comparing on the from_address alone,
// we expect the sender ordering to remain
// deterministic.
const auto &[addr_1, om_1] = lhs;
const auto &[addr_2, om_2] = rhs;
return om_1.from_address < om_2.from_address;
}
bool SimulatorHandle::MaybeTickSimulator() {
std::unique_lock<std::mutex> lock(mu_);
const size_t blocked_servers = blocked_on_receive_.size();
if (should_shut_down_ || blocked_servers < server_addresses_.size()) {
// we only need to advance the simulator when all
// servers have reached a quiescent state, blocked
// on their own futures or receive methods.
return false;
}
// We allow the simulator to progress the state of the system only
// after all servers are blocked on receive.
spdlog::trace("~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ simulator tick ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~");
stats_.simulator_ticks++;
blocked_on_receive_.clear();
cv_.notify_all();
bool timed_anything_out = TimeoutPromisesPastDeadline();
if (timed_anything_out) {
spdlog::trace("simulator progressing: timed out a request");
}
const Duration clock_advance = std::chrono::microseconds{time_distrib_(rng_)};
// We don't always want to advance the clock with every message that we deliver because
// when we advance it for every message, it causes timeouts to occur for any "request path"
// over a certain length. Alternatively, we don't want to simply deliver multiple messages
// in a single simulator tick because that would reduce the amount of concurrent message
// mixing that may naturally occur in production. This approach is to mod the random clock
// advance by a prime number (hopefully avoiding most harmonic effects that would be introduced
// by only advancing the clock by an even amount etc...) and only advancing the clock close to
// half of the time.
if (clock_advance.count() % 97 > 49) {
spdlog::trace("simulator progressing: clock advanced by {}", clock_advance.count());
cluster_wide_time_microseconds_ += clock_advance;
stats_.elapsed_time = cluster_wide_time_microseconds_ - config_.start_time;
}
if (cluster_wide_time_microseconds_ >= config_.abort_time) {
spdlog::error(
"Cluster has executed beyond its configured abort_time, and something may be failing to make progress "
"in an expected amount of time. The SimulatorConfig.rng_seed for this run is {}",
config_.rng_seed);
throw utils::BasicException{"Cluster has executed beyond its configured abort_time"};
}
if (in_flight_.empty()) {
return true;
}
std::stable_sort(in_flight_.begin(), in_flight_.end(), SortInFlight);
if (config_.scramble_messages && in_flight_.size() > 1) {
// scramble messages
std::uniform_int_distribution<size_t> swap_distrib(0, in_flight_.size() - 1);
const size_t swap_index = swap_distrib(rng_);
std::swap(in_flight_[swap_index], in_flight_.back());
}
auto [to_address, opaque_message] = std::move(in_flight_.back());
in_flight_.pop_back();
const int drop_threshold = drop_distrib_(rng_);
const bool should_drop = drop_threshold < config_.drop_percent;
if (should_drop) {
stats_.dropped_messages++;
}
PromiseKey promise_key{.requester_address = to_address, .request_id = opaque_message.request_id};
if (promises_.contains(promise_key)) {
// complete waiting promise if it's there
DeadlineAndOpaquePromise dop = std::move(promises_.at(promise_key));
promises_.erase(promise_key);
const bool normal_timeout = config_.perform_timeouts && (dop.deadline < cluster_wide_time_microseconds_);
if (should_drop || normal_timeout) {
stats_.timed_out_requests++;
dop.promise.TimeOut();
spdlog::trace("simulator timing out request ");
} else {
stats_.total_responses++;
Duration response_latency = cluster_wide_time_microseconds_ - dop.requested_at;
auto type_info = opaque_message.type_info;
dop.promise.Fill(std::move(opaque_message), response_latency);
histograms_.Measure(type_info, response_latency);
spdlog::trace("simulator replying to request");
}
} else if (should_drop) {
// don't add it anywhere, let it drop
spdlog::trace("simulator silently dropping request");
} else {
// add to can_receive_ if not
spdlog::trace("simulator adding message to can_receive_ from {} to {}", opaque_message.from_address.last_known_port,
opaque_message.to_address.last_known_port);
const auto &[om_vec, inserted] =
can_receive_.try_emplace(to_address.ToPartialAddress(), std::vector<OpaqueMessage>());
om_vec->second.emplace_back(std::move(opaque_message));
}
return true;
}
Time SimulatorHandle::Now() const {
std::unique_lock<std::mutex> lock(mu_);
return cluster_wide_time_microseconds_;
}
SimulatorStats SimulatorHandle::Stats() {
std::unique_lock<std::mutex> lock(mu_);
return stats_;
}
} // namespace memgraph::io::simulator

View File

@@ -1,226 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <any>
#include <compare>
#include <iostream>
#include <map>
#include <memory>
#include <optional>
#include <set>
#include <utility>
#include <variant>
#include <vector>
#include <boost/core/demangle.hpp>
#include "io/address.hpp"
#include "io/errors.hpp"
#include "io/message_conversion.hpp"
#include "io/message_histogram_collector.hpp"
#include "io/simulator/simulator_config.hpp"
#include "io/simulator/simulator_stats.hpp"
#include "io/time.hpp"
#include "io/transport.hpp"
namespace memgraph::io::simulator {
class SimulatorHandle {
mutable std::mutex mu_{};
mutable std::condition_variable cv_;
// messages that have not yet been scheduled or dropped
std::vector<std::pair<Address, OpaqueMessage>> in_flight_;
// the responses to requests that are being waited on
std::map<PromiseKey, DeadlineAndOpaquePromise> promises_;
// messages that are sent to servers that may later receive them
std::map<PartialAddress, std::vector<OpaqueMessage>> can_receive_;
Time cluster_wide_time_microseconds_;
bool should_shut_down_ = false;
SimulatorStats stats_;
std::set<Address> blocked_on_receive_;
std::set<Address> server_addresses_;
std::mt19937 rng_;
std::uniform_int_distribution<int> time_distrib_{0, 30000};
std::uniform_int_distribution<int> drop_distrib_{0, 99};
SimulatorConfig config_;
MessageHistogramCollector histograms_;
RequestId request_id_counter_{0};
bool TimeoutPromisesPastDeadline() {
bool timed_anything_out = false;
const Time now = cluster_wide_time_microseconds_;
for (auto it = promises_.begin(); it != promises_.end();) {
auto &[promise_key, dop] = *it;
if (dop.deadline < now && config_.perform_timeouts) {
spdlog::trace("timing out request from requester {}.", promise_key.requester_address.ToString());
std::move(dop).promise.TimeOut();
it = promises_.erase(it);
stats_.timed_out_requests++;
timed_anything_out = true;
} else {
++it;
}
}
return timed_anything_out;
}
public:
explicit SimulatorHandle(SimulatorConfig config)
: cluster_wide_time_microseconds_(config.start_time), rng_(config.rng_seed), config_(config) {}
LatencyHistogramSummaries ResponseLatencies();
~SimulatorHandle() {
for (auto it = promises_.begin(); it != promises_.end();) {
auto &[promise_key, dop] = *it;
std::move(dop).promise.TimeOut();
it = promises_.erase(it);
}
}
void IncrementServerCountAndWaitForQuiescentState(Address address);
/// This method causes most of the interesting simulation logic to happen, wrt network behavior.
/// It checks to see if all background "server" threads are blocked on new messages, and if so,
/// it will decide whether to drop, reorder, or deliver in-flight messages based on the SimulatorConfig
/// that was used to create the Simulator.
bool MaybeTickSimulator();
void ShutDown();
bool ShouldShutDown() const;
template <Message Request, Message Response>
ResponseFuture<Response> SubmitRequest(Address to_address, Address from_address, Request &&request, Duration timeout,
std::function<bool()> &&maybe_tick_simulator,
std::function<void()> &&fill_notifier) {
auto type_info = TypeInfoFor(request);
std::string demangled_name = boost::core::demangle(type_info.get().name());
spdlog::trace("simulator sending request {} to {}", demangled_name, to_address);
auto [future, promise] = memgraph::io::FuturePromisePairWithNotifications<ResponseResult<Response>>(
// set notifier for when the Future::Wait is called
std::forward<std::function<bool()>>(maybe_tick_simulator),
// set notifier for when Promise::Fill is called
std::forward<std::function<void()>>(fill_notifier));
{
std::unique_lock<std::mutex> lock(mu_);
RequestId request_id = ++request_id_counter_;
const Time deadline = cluster_wide_time_microseconds_ + timeout;
std::any message(request);
OpaqueMessage om{.to_address = to_address,
.from_address = from_address,
.request_id = request_id,
.message = std::move(message),
.type_info = type_info};
in_flight_.emplace_back(std::make_pair(to_address, std::move(om)));
PromiseKey promise_key{.requester_address = from_address, .request_id = request_id};
OpaquePromise opaque_promise(std::move(promise).ToUnique());
DeadlineAndOpaquePromise dop{
.requested_at = cluster_wide_time_microseconds_,
.deadline = deadline,
.promise = std::move(opaque_promise),
};
MG_ASSERT(!promises_.contains(promise_key));
promises_.emplace(std::move(promise_key), std::move(dop));
stats_.total_messages++;
stats_.total_requests++;
} // lock dropped here
cv_.notify_all();
return std::move(future);
}
template <Message... Ms>
requires(sizeof...(Ms) > 0) RequestResult<Ms...> Receive(const Address &receiver, Duration timeout) {
std::unique_lock<std::mutex> lock(mu_);
const Time deadline = cluster_wide_time_microseconds_ + timeout;
auto partial_address = receiver.ToPartialAddress();
while (!should_shut_down_ && (cluster_wide_time_microseconds_ < deadline)) {
if (can_receive_.contains(partial_address)) {
std::vector<OpaqueMessage> &can_rx = can_receive_.at(partial_address);
if (!can_rx.empty()) {
OpaqueMessage message = std::move(can_rx.back());
can_rx.pop_back();
// TODO(tyler) search for item in can_receive_ that matches the desired types, rather
// than asserting that the last item in can_rx matches.
auto m_opt = std::move(message).Take<Ms...>();
MG_ASSERT(m_opt.has_value(), "Wrong message type received compared to the expected type");
return std::move(m_opt).value();
}
}
if (!should_shut_down_) {
if (!blocked_on_receive_.contains(receiver)) {
blocked_on_receive_.emplace(receiver);
spdlog::trace("blocking receiver {}", receiver.ToPartialAddress().port);
cv_.notify_all();
}
cv_.wait(lock);
}
}
spdlog::trace("timing out receiver {}", receiver.ToPartialAddress().port);
return TimedOut{};
}
template <Message M>
void Send(Address to_address, Address from_address, RequestId request_id, M message) {
spdlog::trace("sending message from {} to {}", from_address.last_known_port, to_address.last_known_port);
auto type_info = TypeInfoFor(message);
{
std::unique_lock<std::mutex> lock(mu_);
std::any message_any(std::move(message));
OpaqueMessage om{.to_address = to_address,
.from_address = from_address,
.request_id = request_id,
.message = std::move(message_any),
.type_info = type_info};
in_flight_.emplace_back(std::make_pair(std::move(to_address), std::move(om)));
stats_.total_messages++;
} // lock dropped before cv notification
cv_.notify_all();
}
Time Now() const;
template <class D = std::poisson_distribution<>, class Return = uint64_t>
Return Rand(D distrib) {
std::unique_lock<std::mutex> lock(mu_);
return distrib(rng_);
}
SimulatorStats Stats();
};
}; // namespace memgraph::io::simulator

View File

@@ -1,46 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <cstdint>
#include <fmt/format.h>
#include "io/time.hpp"
namespace memgraph::io::simulator {
struct SimulatorStats {
uint64_t total_messages = 0;
uint64_t dropped_messages = 0;
uint64_t timed_out_requests = 0;
uint64_t total_requests = 0;
uint64_t total_responses = 0;
uint64_t simulator_ticks = 0;
Duration elapsed_time;
friend bool operator==(const SimulatorStats & /* lhs */, const SimulatorStats & /* rhs */) = default;
friend std::ostream &operator<<(std::ostream &in, const SimulatorStats &stats) {
auto elapsed_ms = std::chrono::duration_cast<std::chrono::milliseconds>(stats.elapsed_time).count();
std::string formated = fmt::format(
"SimulatorStats {{ total_messages: {}, dropped_messages: {}, timed_out_requests: {}, total_requests: {}, "
"total_responses: {}, simulator_ticks: {}, elapsed_time: {}ms }}",
stats.total_messages, stats.dropped_messages, stats.timed_out_requests, stats.total_requests,
stats.total_responses, stats.simulator_ticks, elapsed_ms);
in << formated;
return in;
}
};
}; // namespace memgraph::io::simulator

View File

@@ -1,68 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <memory>
#include <utility>
#include "io/address.hpp"
#include "io/notifier.hpp"
#include "io/simulator/simulator_handle.hpp"
#include "io/time.hpp"
namespace memgraph::io::simulator {
using memgraph::io::Duration;
using memgraph::io::Time;
class SimulatorTransport {
std::shared_ptr<SimulatorHandle> simulator_handle_;
Address address_;
std::mt19937 rng_;
public:
SimulatorTransport(std::shared_ptr<SimulatorHandle> simulator_handle, Address address, uint64_t seed)
: simulator_handle_(simulator_handle), address_(address), rng_(std::mt19937{seed}) {}
template <Message RequestT, Message ResponseT>
ResponseFuture<ResponseT> Request(Address to_address, Address from_address, RequestT request,
std::function<void()> notification, Duration timeout) {
std::function<bool()> tick_simulator = [handle_copy = simulator_handle_] {
return handle_copy->MaybeTickSimulator();
};
return simulator_handle_->template SubmitRequest<RequestT, ResponseT>(
to_address, from_address, std::move(request), timeout, std::move(tick_simulator), std::move(notification));
}
template <Message... Ms>
requires(sizeof...(Ms) > 0) RequestResult<Ms...> Receive(Address receiver_address, Duration timeout) {
return simulator_handle_->template Receive<Ms...>(receiver_address, timeout);
}
template <Message M>
void Send(Address to_address, Address from_address, uint64_t request_id, M message) {
return simulator_handle_->template Send<M>(to_address, from_address, request_id, message);
}
Time Now() const { return simulator_handle_->Now(); }
bool ShouldShutDown() const { return simulator_handle_->ShouldShutDown(); }
template <class D = std::poisson_distribution<>, class Return = uint64_t>
Return Rand(D distrib) {
return distrib(rng_);
}
LatencyHistogramSummaries ResponseLatencies() { return simulator_handle_->ResponseLatencies(); }
};
}; // namespace memgraph::io::simulator

View File

@@ -1,177 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <chrono>
#include <concepts>
#include <random>
#include <variant>
#include "io/address.hpp"
#include "io/errors.hpp"
#include "io/future.hpp"
#include "io/message_histogram_collector.hpp"
#include "io/notifier.hpp"
#include "io/time.hpp"
#include "utils/result.hpp"
namespace memgraph::io {
using memgraph::utils::BasicResult;
// TODO(tyler) ensure that Message continues to represent
// reasonable constraints around message types over time,
// as we adapt things to use Thrift-generated message types.
template <typename T>
concept Message = std::same_as<T, std::decay_t<T>>;
using RequestId = uint64_t;
template <Message M>
struct ResponseEnvelope {
M message;
RequestId request_id;
Address to_address;
Address from_address;
Duration response_latency;
};
template <Message M>
using ResponseResult = BasicResult<TimedOut, ResponseEnvelope<M>>;
template <Message M>
using ResponseFuture = memgraph::io::Future<ResponseResult<M>>;
template <Message M>
using ResponsePromise = memgraph::io::Promise<ResponseResult<M>>;
template <Message... Ms>
struct RequestEnvelope {
std::variant<Ms...> message;
RequestId request_id;
Address to_address;
Address from_address;
};
template <Message... Ms>
using RequestResult = BasicResult<TimedOut, RequestEnvelope<Ms...>>;
template <typename I>
class Io {
I implementation_;
Address address_;
Duration default_timeout_ = std::chrono::microseconds{100000};
public:
Io(I io, Address address) : implementation_(io), address_(address) {}
/// Set the default timeout for all requests that are issued
/// without an explicit timeout set.
void SetDefaultTimeout(Duration timeout) { default_timeout_ = timeout; }
/// Returns the current default timeout for this Io instance.
Duration GetDefaultTimeout() { return default_timeout_; }
/// Issue a request with an explicit timeout in microseconds provided. This tends to be used by clients.
template <Message RequestT, Message ResponseT>
ResponseFuture<ResponseT> RequestWithTimeout(Address address, RequestT request, Duration timeout) {
const Address from_address = address_;
std::function<void()> fill_notifier = nullptr;
return implementation_.template Request<RequestT, ResponseT>(address, from_address, request, fill_notifier,
timeout);
}
/// Issue a request that times out after the default timeout. This tends
/// to be used by clients.
template <Message RequestT, Message ResponseT>
ResponseFuture<ResponseT> Request(Address to_address, RequestT request) {
const Duration timeout = default_timeout_;
const Address from_address = address_;
std::function<void()> fill_notifier = nullptr;
return implementation_.template Request<RequestT, ResponseT>(to_address, from_address, std::move(request),
fill_notifier, timeout);
}
/// Issue a request that will notify a Notifier when it is filled or times out.
template <Message RequestT, Message ResponseT>
ResponseFuture<ResponseT> RequestWithNotification(Address to_address, RequestT request, Notifier notifier,
ReadinessToken readiness_token) {
const Duration timeout = default_timeout_;
const Address from_address = address_;
std::function<void()> fill_notifier = [notifier, readiness_token]() { notifier.Notify(readiness_token); };
return implementation_.template Request<RequestT, ResponseT>(to_address, from_address, std::move(request),
fill_notifier, timeout);
}
/// Issue a request that will notify a Notifier when it is filled or times out.
template <Message RequestT, Message ResponseT>
ResponseFuture<ResponseT> RequestWithNotificationAndTimeout(Address to_address, RequestT request, Notifier notifier,
ReadinessToken readiness_token, Duration timeout) {
const Address from_address = address_;
std::function<void()> fill_notifier = [notifier, readiness_token]() { notifier.Notify(readiness_token); };
return implementation_.template Request<RequestT, ResponseT>(to_address, from_address, std::move(request),
fill_notifier, timeout);
}
/// Wait for an explicit number of microseconds for a request of one of the
/// provided types to arrive. This tends to be used by servers.
template <Message... Ms>
RequestResult<Ms...> ReceiveWithTimeout(Duration timeout) {
return implementation_.template Receive<Ms...>(address_, timeout);
}
/// Wait the default number of microseconds for a request of one of the
/// provided types to arrive. This tends to be used by servers.
template <Message... Ms>
requires(sizeof...(Ms) > 0) RequestResult<Ms...> Receive() {
const Duration timeout = default_timeout_;
return implementation_.template Receive<Ms...>(address_, timeout);
}
/// Send a message in a best-effort fashion. This is used for messaging where
/// responses are not necessarily expected, and for servers to respond to requests.
/// If you need reliable delivery, this must be built on-top. TCP is not enough for most use cases.
template <Message M>
void Send(Address to_address, RequestId request_id, M message) {
Address from_address = address_;
return implementation_.template Send<M>(to_address, from_address, request_id, std::move(message));
}
/// The current system time. This time source should be preferred over any other,
/// because it lets us deterministically control clocks from tests for making
/// things like timeouts deterministic.
Time Now() const { return implementation_.Now(); }
/// Returns true if the system should shut-down.
bool ShouldShutDown() const { return implementation_.ShouldShutDown(); }
/// Returns a random number within the specified distribution.
template <class D = std::poisson_distribution<>, class Return = uint64_t>
Return Rand(D distrib) {
return implementation_.template Rand<D, Return>(distrib);
}
Address GetAddress() { return address_; }
void SetAddress(Address address) { address_ = address; }
Io<I> ForkLocal(boost::uuids::uuid uuid) {
Address new_address{
.unique_id = uuid,
.last_known_ip = address_.last_known_ip,
.last_known_port = address_.last_known_port,
};
return Io(implementation_, new_address);
}
LatencyHistogramSummaries ResponseLatencies() { return implementation_.ResponseLatencies(); }
};
}; // namespace memgraph::io

View File

@@ -1,48 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <algorithm>
#include <thread>
#include <boost/asio/ip/tcp.hpp>
#include "io/address.hpp"
#include "storage/v3/property_value.hpp"
#include "storage/v3/schemas.hpp"
namespace memgraph::machine_manager {
using memgraph::io::Address;
using memgraph::storage::v3::SchemaProperty;
using CompoundKey = std::vector<memgraph::storage::v3::PropertyValue>;
struct InitialLabelSpace {
std::string label_name;
std::vector<SchemaProperty> schema;
size_t replication_factor;
std::vector<CompoundKey> split_points;
};
struct MachineConfig {
std::vector<InitialLabelSpace> initial_label_spaces;
std::vector<Address> coordinator_addresses;
bool is_storage;
bool is_coordinator;
bool is_query_engine;
boost::asio::ip::address listen_ip;
uint16_t listen_port;
size_t shard_worker_threads = std::max(static_cast<unsigned int>(1), std::thread::hardware_concurrency());
bool sync_message_handling = false;
};
} // namespace memgraph::machine_manager

View File

@@ -1,233 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "coordinator/coordinator_rsm.hpp"
#include "coordinator/coordinator_worker.hpp"
#include "io/message_conversion.hpp"
#include "io/messages.hpp"
#include "io/rsm/rsm_client.hpp"
#include "io/time.hpp"
#include "machine_manager/machine_config.hpp"
#include "storage/v3/shard_manager.hpp"
namespace memgraph::machine_manager {
using coordinator::Coordinator;
using coordinator::CoordinatorReadRequests;
using coordinator::CoordinatorReadResponses;
using coordinator::CoordinatorRsm;
using coordinator::CoordinatorWriteRequests;
using coordinator::CoordinatorWriteResponses;
using coordinator::coordinator_worker::CoordinatorWorker;
using CoordinatorRouteMessage = coordinator::coordinator_worker::RouteMessage;
using CoordinatorQueue = coordinator::coordinator_worker::Queue;
using io::ConvertVariant;
using io::Duration;
using io::RequestId;
using io::Time;
using io::messages::CoordinatorMessages;
using io::messages::ShardManagerMessages;
using io::messages::ShardMessages;
using io::messages::StorageReadRequest;
using io::messages::StorageWriteRequest;
using io::rsm::AppendRequest;
using io::rsm::AppendResponse;
using io::rsm::ReadRequest;
using io::rsm::VoteRequest;
using io::rsm::VoteResponse;
using io::rsm::WriteRequest;
using io::rsm::WriteResponse;
using storage::v3::ShardManager;
/// The MachineManager is responsible for:
/// * starting the entire system and ensuring that high-level
/// operational requirements continue to be met
/// * acting as a machine's single caller of Io::Receive
/// * routing incoming messages from the Io interface to the
/// appropriate Coordinator or to the StorageManager
/// (it's not necessary to route anything in this layer
/// to the query engine because the query engine only
/// communicates using higher-level Futures that will
/// be filled immediately when the response comes in
/// at the lower-level transport layer.
///
/// Every storage engine has exactly one RsmEngine.
template <typename IoImpl>
class MachineManager {
io::Io<IoImpl> io_;
MachineConfig config_;
Address coordinator_address_;
CoordinatorQueue coordinator_queue_;
std::jthread coordinator_handle_;
ShardManager<IoImpl> shard_manager_;
Time next_cron_ = Time::min();
public:
// TODO initialize ShardManager with "real" coordinator addresses instead of io.GetAddress
// which is only true for single-machine config.
MachineManager(io::Io<IoImpl> io, MachineConfig config, Coordinator coordinator)
: io_(io),
config_(config),
coordinator_address_(io.GetAddress().ForkLocalCoordinator()),
shard_manager_{io.ForkLocal(io.GetAddress().ForkLocalShardManager().unique_id), config.shard_worker_threads,
coordinator_address_} {
auto coordinator_io = io.ForkLocal(coordinator_address_.unique_id);
CoordinatorWorker coordinator_worker{coordinator_io, coordinator_queue_, coordinator};
coordinator_handle_ = std::jthread([coordinator = std::move(coordinator_worker)]() mutable { coordinator.Run(); });
}
MachineManager(MachineManager &&) noexcept = default;
MachineManager &operator=(MachineManager &&) noexcept = default;
MachineManager(const MachineManager &) = delete;
MachineManager &operator=(const MachineManager &) = delete;
~MachineManager() {
if (coordinator_handle_.joinable()) {
coordinator_queue_.Push(coordinator::coordinator_worker::ShutDown{});
coordinator_handle_.join();
}
}
Address CoordinatorAddress() { return coordinator_address_; }
void Run() {
while (true) {
MaybeBlockOnSyncHandling();
if (io_.ShouldShutDown()) {
break;
}
const auto now = io_.Now();
uint64_t now_us = now.time_since_epoch().count();
uint64_t next_us = next_cron_.time_since_epoch().count();
if (now >= next_cron_) {
spdlog::info("now {} >= next_cron_ {}", now_us, next_us);
next_cron_ = Cron();
} else {
spdlog::info("now {} < next_cron_ {}", now_us, next_us);
}
Duration receive_timeout = std::max(next_cron_, now) - now;
// Note: this parameter pack must be kept in-sync with the ReceiveWithTimeout parameter pack below
using AllMessages =
std::variant<ReadRequest<CoordinatorReadRequests>, AppendRequest<CoordinatorWriteRequests>, AppendResponse,
WriteRequest<CoordinatorWriteRequests>, VoteRequest, VoteResponse,
WriteResponse<CoordinatorWriteResponses>, ReadRequest<StorageReadRequest>,
AppendRequest<StorageWriteRequest>, WriteRequest<StorageWriteRequest>>;
spdlog::info("MM waiting on Receive on address {}", io_.GetAddress().ToString());
// Note: this parameter pack must be kept in-sync with the AllMessages parameter pack above
auto request_result = io_.template ReceiveWithTimeout<
ReadRequest<CoordinatorReadRequests>, AppendRequest<CoordinatorWriteRequests>, AppendResponse,
WriteRequest<CoordinatorWriteRequests>, VoteRequest, VoteResponse, WriteResponse<CoordinatorWriteResponses>,
ReadRequest<StorageReadRequest>, AppendRequest<StorageWriteRequest>, WriteRequest<StorageWriteRequest>>(
receive_timeout);
if (request_result.HasError()) {
// time to do Cron
continue;
}
auto &&request_envelope = std::move(request_result.GetValue());
spdlog::info("MM got message to {}", request_envelope.to_address.ToString());
// If message is for the coordinator, cast it to subset and pass it to the coordinator
bool to_coordinator = coordinator_address_ == request_envelope.to_address;
if (to_coordinator) {
std::optional<CoordinatorMessages> conversion_attempt =
ConvertVariant<AllMessages, ReadRequest<CoordinatorReadRequests>, AppendRequest<CoordinatorWriteRequests>,
AppendResponse, WriteRequest<CoordinatorWriteRequests>, VoteRequest, VoteResponse>(
std::move(request_envelope.message));
MG_ASSERT(conversion_attempt.has_value(), "coordinator message conversion failed");
spdlog::info("got coordinator message");
CoordinatorMessages &&cm = std::move(conversion_attempt.value());
CoordinatorRouteMessage route_message{
.message = std::move(cm),
.request_id = request_envelope.request_id,
.to = request_envelope.to_address,
.from = request_envelope.from_address,
};
coordinator_queue_.Push(std::move(route_message));
continue;
}
bool to_sm = shard_manager_.GetAddress() == request_envelope.to_address;
spdlog::info("smm: {}", shard_manager_.GetAddress().ToString());
if (to_sm) {
std::optional<ShardManagerMessages> conversion_attempt =
ConvertVariant<AllMessages, WriteResponse<CoordinatorWriteResponses>>(std::move(request_envelope.message));
MG_ASSERT(conversion_attempt.has_value(), "shard manager message conversion failed");
spdlog::info("got shard manager message");
ShardManagerMessages &&smm = std::move(conversion_attempt.value());
shard_manager_.Receive(std::forward<ShardManagerMessages>(smm), request_envelope.request_id,
request_envelope.from_address);
continue;
}
// treat this as a message to a specific shard rsm and cast it accordingly
std::optional<ShardMessages> conversion_attempt =
ConvertVariant<AllMessages, ReadRequest<StorageReadRequest>, AppendRequest<StorageWriteRequest>,
AppendResponse, WriteRequest<StorageWriteRequest>, VoteRequest, VoteResponse>(
std::move(request_envelope.message));
MG_ASSERT(conversion_attempt.has_value(), "shard rsm message conversion failed for {} - incorrect message type",
request_envelope.to_address.ToString());
spdlog::info("got shard rsm message");
ShardMessages &&sm = std::move(conversion_attempt.value());
shard_manager_.Route(std::forward<ShardMessages>(sm), request_envelope.request_id, request_envelope.to_address,
request_envelope.from_address);
}
}
private:
// This method exists for controlling concurrency
// during deterministic simulation testing.
void MaybeBlockOnSyncHandling() {
if (!config_.sync_message_handling) {
return;
}
// block on coordinator
coordinator_queue_.BlockOnQuiescence();
// block on shards
shard_manager_.BlockOnQuiescence();
}
Time Cron() {
spdlog::info("running MachineManager::Cron, address {}", io_.GetAddress().ToString());
coordinator_queue_.Push(coordinator::coordinator_worker::Cron{});
MaybeBlockOnSyncHandling();
Time ret = shard_manager_.Cron();
MaybeBlockOnSyncHandling();
return ret;
}
};
} // namespace memgraph::machine_manager

View File

@@ -1,4 +1,4 @@
// Copyright 2023 Memgraph Ltd.
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
@@ -16,7 +16,6 @@
#include <cstdint>
#include <exception>
#include <filesystem>
#include <fstream>
#include <functional>
#include <limits>
#include <map>
@@ -33,31 +32,22 @@
#include <spdlog/sinks/dist_sink.h>
#include <spdlog/sinks/stdout_color_sinks.h>
#include "common/errors.hpp"
#include "communication/bolt/v1/constants.hpp"
#include "communication/websocket/auth.hpp"
#include "communication/websocket/server.hpp"
#include "coordinator/shard_map.hpp"
#include "helpers.hpp"
#include "io/address.hpp"
#include "io/local_transport/local_system.hpp"
#include "io/local_transport/local_transport.hpp"
#include "io/simulator/simulator_transport.hpp"
#include "machine_manager/machine_config.hpp"
#include "machine_manager/machine_manager.hpp"
#include "py/py.hpp"
#include "query/v2/auth_checker.hpp"
#include "query/v2/discard_value_stream.hpp"
#include "query/v2/exceptions.hpp"
#include "query/v2/frontend/ast/ast.hpp"
#include "query/v2/interpreter.hpp"
#include "query/v2/plan/operator.hpp"
#include "query/v2/procedure/module.hpp"
#include "query/v2/procedure/py_module.hpp"
#include "requests/requests.hpp"
#include "storage/v3/id_types.hpp"
#include "storage/v3/isolation_level.hpp"
#include "storage/v3/key_store.hpp"
#include "storage/v3/property_value.hpp"
#include "storage/v3/schemas.hpp"
#include "storage/v3/shard.hpp"
#include "storage/v3/storage.hpp"
#include "storage/v3/view.hpp"
#include "telemetry/telemetry.hpp"
#include "utils/event_counter.hpp"
@@ -72,6 +62,7 @@
#include "utils/settings.hpp"
#include "utils/signals.hpp"
#include "utils/string.hpp"
#include "utils/synchronized.hpp"
#include "utils/sysinfo/memory.hpp"
#include "utils/terminate_handler.hpp"
#include "version.hpp"
@@ -206,6 +197,16 @@ DEFINE_bool(storage_wal_enabled, false,
DEFINE_VALIDATED_uint64(storage_snapshot_retention_count, 3, "The number of snapshots that should always be kept.",
FLAG_IN_RANGE(1, 1000000));
// NOLINTNEXTLINE(cppcoreguidelines-avoid-non-const-global-variables)
DEFINE_VALIDATED_uint64(storage_wal_file_size_kib, memgraph::storage::v3::Config::Durability().wal_file_size_kibibytes,
"Minimum file size of each WAL file.",
FLAG_IN_RANGE(1, static_cast<unsigned long>(1000) * 1024));
// NOLINTNEXTLINE(cppcoreguidelines-avoid-non-const-global-variables)
DEFINE_VALIDATED_uint64(storage_wal_file_flush_every_n_tx,
memgraph::storage::v3::Config::Durability().wal_file_flush_every_n_tx,
"Issue a 'fsync' call after this amount of transactions are written to the "
"WAL file. Set to 1 for fully synchronous operation.",
FLAG_IN_RANGE(1, 1000000));
// NOLINTNEXTLINE(cppcoreguidelines-avoid-non-const-global-variables)
DEFINE_bool(storage_snapshot_on_exit, false, "Controls whether the storage creates another snapshot on exit.");
// NOLINTNEXTLINE(cppcoreguidelines-avoid-non-const-global-variables)
@@ -267,10 +268,6 @@ DEFINE_uint64(
"Total memory limit in MiB. Set to 0 to use the default values which are 100\% of the phyisical memory if the swap "
"is enabled and 90\% of the physical memory otherwise.");
// NOLINTNEXTLINE(cppcoreguidelines-avoid-non-const-global-variables)
DEFINE_string(split_file, "",
"Path to the split file which contains the predefined labels, properties, edge types and shard-ranges.");
namespace {
using namespace std::literals;
inline constexpr std::array isolation_level_mappings{
@@ -305,6 +302,13 @@ DEFINE_VALIDATED_string(isolation_level, "SNAPSHOT_ISOLATION", isolation_level_h
});
namespace {
memgraph::storage::v3::IsolationLevel ParseIsolationLevel() {
const auto isolation_level =
StringToEnum<memgraph::storage::v3::IsolationLevel>(FLAGS_isolation_level, isolation_level_mappings);
MG_ASSERT(isolation_level, "Invalid isolation level");
return *isolation_level;
}
int64_t GetMemoryLimit() {
if (FLAGS_memory_limit == 0) {
auto maybe_total_memory = memgraph::utils::sysinfo::TotalMemory();
@@ -325,6 +329,30 @@ int64_t GetMemoryLimit() {
}
} // namespace
namespace {
std::vector<std::filesystem::path> query_modules_directories;
} // namespace
DEFINE_VALIDATED_string(query_modules_directory, "",
"Directory where modules with custom query procedures are stored. "
"NOTE: Multiple comma-separated directories can be defined.",
{
query_modules_directories.clear();
if (value.empty()) return true;
const auto directories = memgraph::utils::Split(value, ",");
for (const auto &dir : directories) {
if (!memgraph::utils::DirExists(dir)) {
std::cout << "Expected --" << flagname << " to point to directories." << std::endl;
std::cout << dir << " is not a directory." << std::endl;
return false;
}
}
query_modules_directories.reserve(directories.size());
std::transform(directories.begin(), directories.end(),
std::back_inserter(query_modules_directories),
[](const auto &dir) { return dir; });
return true;
});
// Logging flags
DEFINE_bool(also_log_to_stderr, false, "Log messages go to stderr in addition to logfiles");
DEFINE_string(log_file, "", "Path to where the log should be stored.");
@@ -396,6 +424,13 @@ void InitializeLogger() {
CreateLoggerFromSink(sinks, ParseLogLevel());
}
void AddLoggerSink(spdlog::sink_ptr new_sink) {
auto default_logger = spdlog::default_logger();
auto sinks = default_logger->sinks();
sinks.push_back(new_sink);
CreateLoggerFromSink(sinks, default_logger->level());
}
} // namespace
// NOLINTNEXTLINE(cppcoreguidelines-avoid-non-const-global-variables)
@@ -408,24 +443,432 @@ DEFINE_string(organization_name, "", "Organization name.");
struct SessionData {
// Explicit constructor here to ensure that pointers to all objects are
// supplied.
explicit SessionData(memgraph::query::v2::InterpreterContext *interpreter_context)
: interpreter_context(interpreter_context) {}
#if MG_ENTERPRISE
SessionData(memgraph::storage::v3::Storage *db, memgraph::query::v2::InterpreterContext *interpreter_context,
memgraph::utils::Synchronized<memgraph::auth::Auth, memgraph::utils::WritePrioritizedRWLock> *auth,
memgraph::audit::Log *audit_log)
: db(db), interpreter_context(interpreter_context), auth(auth), audit_log(audit_log) {}
memgraph::storage::v3::Storage *db;
memgraph::query::v2::InterpreterContext *interpreter_context;
memgraph::utils::Synchronized<memgraph::auth::Auth, memgraph::utils::WritePrioritizedRWLock> *auth;
memgraph::audit::Log *audit_log;
#else
SessionData(memgraph::storage::v3::Storage *db, memgraph::query::v2::InterpreterContext *interpreter_context,
memgraph::utils::Synchronized<memgraph::auth::Auth, memgraph::utils::WritePrioritizedRWLock> *auth)
: db(db), interpreter_context(interpreter_context), auth(auth) {}
memgraph::storage::v3::Storage *db;
memgraph::query::v2::InterpreterContext *interpreter_context;
memgraph::utils::Synchronized<memgraph::auth::Auth, memgraph::utils::WritePrioritizedRWLock> *auth;
#endif
};
inline constexpr std::string_view default_user_role_regex = "[a-zA-Z0-9_.+-@]+";
// NOLINTNEXTLINE(cppcoreguidelines-avoid-non-const-global-variables)
DEFINE_string(auth_user_or_role_name_regex, default_user_role_regex.data(),
"Set to the regular expression that each user or role name must fulfill.");
class AuthQueryHandler final : public memgraph::query::v2::AuthQueryHandler {
memgraph::utils::Synchronized<memgraph::auth::Auth, memgraph::utils::WritePrioritizedRWLock> *auth_;
std::string name_regex_string_;
std::regex name_regex_;
public:
AuthQueryHandler(memgraph::utils::Synchronized<memgraph::auth::Auth, memgraph::utils::WritePrioritizedRWLock> *auth,
std::string name_regex_string)
: auth_(auth), name_regex_string_(std::move(name_regex_string)), name_regex_(name_regex_string_) {}
bool CreateUser(const std::string &username, const std::optional<std::string> &password) override {
if (name_regex_string_ != default_user_role_regex) {
if (const auto license_check_result =
memgraph::utils::license::global_license_checker.IsValidLicense(memgraph::utils::global_settings);
license_check_result.HasError()) {
throw memgraph::auth::AuthException(
"Custom user/role regex is a Memgraph Enterprise feature. Please set the config "
"(\"--auth-user-or-role-name-regex\") to its default value (\"{}\") or remove the flag.\n{}",
default_user_role_regex,
memgraph::utils::license::LicenseCheckErrorToString(license_check_result.GetError(), "user/role regex"));
}
}
if (!std::regex_match(username, name_regex_)) {
throw memgraph::query::v2::QueryRuntimeException("Invalid user name.");
}
try {
const auto [first_user, user_added] = std::invoke([&, this] {
auto locked_auth = auth_->Lock();
const auto first_user = !locked_auth->HasUsers();
const auto user_added = locked_auth->AddUser(username, password).has_value();
return std::make_pair(first_user, user_added);
});
if (first_user) {
spdlog::info("{} is first created user. Granting all privileges.", username);
GrantPrivilege(username, memgraph::query::v2::kPrivilegesAll);
}
return user_added;
} catch (const memgraph::auth::AuthException &e) {
throw memgraph::query::v2::QueryRuntimeException(e.what());
}
}
bool DropUser(const std::string &username) override {
if (!std::regex_match(username, name_regex_)) {
throw memgraph::query::v2::QueryRuntimeException("Invalid user name.");
}
try {
auto locked_auth = auth_->Lock();
auto user = locked_auth->GetUser(username);
if (!user) return false;
return locked_auth->RemoveUser(username);
} catch (const memgraph::auth::AuthException &e) {
throw memgraph::query::v2::QueryRuntimeException(e.what());
}
}
void SetPassword(const std::string &username, const std::optional<std::string> &password) override {
if (!std::regex_match(username, name_regex_)) {
throw memgraph::query::v2::QueryRuntimeException("Invalid user name.");
}
try {
auto locked_auth = auth_->Lock();
auto user = locked_auth->GetUser(username);
if (!user) {
throw memgraph::query::v2::QueryRuntimeException("User '{}' doesn't exist.", username);
}
user->UpdatePassword(password);
locked_auth->SaveUser(*user);
} catch (const memgraph::auth::AuthException &e) {
throw memgraph::query::v2::QueryRuntimeException(e.what());
}
}
bool CreateRole(const std::string &rolename) override {
if (!std::regex_match(rolename, name_regex_)) {
throw memgraph::query::v2::QueryRuntimeException("Invalid role name.");
}
try {
auto locked_auth = auth_->Lock();
return locked_auth->AddRole(rolename).has_value();
} catch (const memgraph::auth::AuthException &e) {
throw memgraph::query::v2::QueryRuntimeException(e.what());
}
}
bool DropRole(const std::string &rolename) override {
if (!std::regex_match(rolename, name_regex_)) {
throw memgraph::query::v2::QueryRuntimeException("Invalid role name.");
}
try {
auto locked_auth = auth_->Lock();
auto role = locked_auth->GetRole(rolename);
if (!role) return false;
return locked_auth->RemoveRole(rolename);
} catch (const memgraph::auth::AuthException &e) {
throw memgraph::query::v2::QueryRuntimeException(e.what());
}
}
std::vector<memgraph::query::v2::TypedValue> GetUsernames() override {
try {
auto locked_auth = auth_->ReadLock();
std::vector<memgraph::query::v2::TypedValue> usernames;
const auto &users = locked_auth->AllUsers();
usernames.reserve(users.size());
for (const auto &user : users) {
usernames.emplace_back(user.username());
}
return usernames;
} catch (const memgraph::auth::AuthException &e) {
throw memgraph::query::v2::QueryRuntimeException(e.what());
}
}
std::vector<memgraph::query::v2::TypedValue> GetRolenames() override {
try {
auto locked_auth = auth_->ReadLock();
std::vector<memgraph::query::v2::TypedValue> rolenames;
const auto &roles = locked_auth->AllRoles();
rolenames.reserve(roles.size());
for (const auto &role : roles) {
rolenames.emplace_back(role.rolename());
}
return rolenames;
} catch (const memgraph::auth::AuthException &e) {
throw memgraph::query::v2::QueryRuntimeException(e.what());
}
}
std::optional<std::string> GetRolenameForUser(const std::string &username) override {
if (!std::regex_match(username, name_regex_)) {
throw memgraph::query::v2::QueryRuntimeException("Invalid user name.");
}
try {
auto locked_auth = auth_->ReadLock();
auto user = locked_auth->GetUser(username);
if (!user) {
throw memgraph::query::v2::QueryRuntimeException("User '{}' doesn't exist .", username);
}
if (const auto *role = user->role(); role != nullptr) {
return role->rolename();
}
return std::nullopt;
} catch (const memgraph::auth::AuthException &e) {
throw memgraph::query::v2::QueryRuntimeException(e.what());
}
}
std::vector<memgraph::query::v2::TypedValue> GetUsernamesForRole(const std::string &rolename) override {
if (!std::regex_match(rolename, name_regex_)) {
throw memgraph::query::v2::QueryRuntimeException("Invalid role name.");
}
try {
auto locked_auth = auth_->ReadLock();
auto role = locked_auth->GetRole(rolename);
if (!role) {
throw memgraph::query::v2::QueryRuntimeException("Role '{}' doesn't exist.", rolename);
}
std::vector<memgraph::query::v2::TypedValue> usernames;
const auto &users = locked_auth->AllUsersForRole(rolename);
usernames.reserve(users.size());
for (const auto &user : users) {
usernames.emplace_back(user.username());
}
return usernames;
} catch (const memgraph::auth::AuthException &e) {
throw memgraph::query::v2::QueryRuntimeException(e.what());
}
}
void SetRole(const std::string &username, const std::string &rolename) override {
if (!std::regex_match(username, name_regex_)) {
throw memgraph::query::v2::QueryRuntimeException("Invalid user name.");
}
if (!std::regex_match(rolename, name_regex_)) {
throw memgraph::query::v2::QueryRuntimeException("Invalid role name.");
}
try {
auto locked_auth = auth_->Lock();
auto user = locked_auth->GetUser(username);
if (!user) {
throw memgraph::query::v2::QueryRuntimeException("User '{}' doesn't exist .", username);
}
auto role = locked_auth->GetRole(rolename);
if (!role) {
throw memgraph::query::v2::QueryRuntimeException("Role '{}' doesn't exist .", rolename);
}
if (const auto *current_role = user->role(); current_role != nullptr) {
throw memgraph::query::v2::QueryRuntimeException("User '{}' is already a member of role '{}'.", username,
current_role->rolename());
}
user->SetRole(*role);
locked_auth->SaveUser(*user);
} catch (const memgraph::auth::AuthException &e) {
throw memgraph::query::v2::QueryRuntimeException(e.what());
}
}
void ClearRole(const std::string &username) override {
if (!std::regex_match(username, name_regex_)) {
throw memgraph::query::v2::QueryRuntimeException("Invalid user name.");
}
try {
auto locked_auth = auth_->Lock();
auto user = locked_auth->GetUser(username);
if (!user) {
throw memgraph::query::v2::QueryRuntimeException("User '{}' doesn't exist .", username);
}
user->ClearRole();
locked_auth->SaveUser(*user);
} catch (const memgraph::auth::AuthException &e) {
throw memgraph::query::v2::QueryRuntimeException(e.what());
}
}
std::vector<std::vector<memgraph::query::v2::TypedValue>> GetPrivileges(const std::string &user_or_role) override {
if (!std::regex_match(user_or_role, name_regex_)) {
throw memgraph::query::v2::QueryRuntimeException("Invalid user or role name.");
}
try {
auto locked_auth = auth_->ReadLock();
std::vector<std::vector<memgraph::query::v2::TypedValue>> grants;
auto user = locked_auth->GetUser(user_or_role);
auto role = locked_auth->GetRole(user_or_role);
if (!user && !role) {
throw memgraph::query::v2::QueryRuntimeException("User or role '{}' doesn't exist.", user_or_role);
}
if (user) {
const auto &permissions = user->GetPermissions();
for (const auto &privilege : memgraph::query::v2::kPrivilegesAll) {
auto permission = memgraph::glue::v2::PrivilegeToPermission(privilege);
auto effective = permissions.Has(permission);
if (permissions.Has(permission) != memgraph::auth::PermissionLevel::NEUTRAL) {
std::vector<std::string> description;
auto user_level = user->permissions().Has(permission);
if (user_level == memgraph::auth::PermissionLevel::GRANT) {
description.emplace_back("GRANTED TO USER");
} else if (user_level == memgraph::auth::PermissionLevel::DENY) {
description.emplace_back("DENIED TO USER");
}
if (const auto *role = user->role(); role != nullptr) {
auto role_level = role->permissions().Has(permission);
if (role_level == memgraph::auth::PermissionLevel::GRANT) {
description.emplace_back("GRANTED TO ROLE");
} else if (role_level == memgraph::auth::PermissionLevel::DENY) {
description.emplace_back("DENIED TO ROLE");
}
}
grants.push_back({memgraph::query::v2::TypedValue(memgraph::auth::PermissionToString(permission)),
memgraph::query::v2::TypedValue(memgraph::auth::PermissionLevelToString(effective)),
memgraph::query::v2::TypedValue(memgraph::utils::Join(description, ", "))});
}
}
} else {
const auto &permissions = role->permissions();
for (const auto &privilege : memgraph::query::v2::kPrivilegesAll) {
auto permission = memgraph::glue::v2::PrivilegeToPermission(privilege);
auto effective = permissions.Has(permission);
if (effective != memgraph::auth::PermissionLevel::NEUTRAL) {
std::string description;
if (effective == memgraph::auth::PermissionLevel::GRANT) {
description = "GRANTED TO ROLE";
} else if (effective == memgraph::auth::PermissionLevel::DENY) {
description = "DENIED TO ROLE";
}
grants.push_back({memgraph::query::v2::TypedValue(memgraph::auth::PermissionToString(permission)),
memgraph::query::v2::TypedValue(memgraph::auth::PermissionLevelToString(effective)),
memgraph::query::v2::TypedValue(description)});
}
}
}
return grants;
} catch (const memgraph::auth::AuthException &e) {
throw memgraph::query::v2::QueryRuntimeException(e.what());
}
}
void GrantPrivilege(const std::string &user_or_role,
const std::vector<memgraph::query::v2::AuthQuery::Privilege> &privileges) override {
EditPermissions(user_or_role, privileges, [](auto *permissions, const auto &permission) {
// TODO (mferencevic): should we first check that the
// privilege is granted/denied/revoked before
// unconditionally granting/denying/revoking it?
permissions->Grant(permission);
});
}
void DenyPrivilege(const std::string &user_or_role,
const std::vector<memgraph::query::v2::AuthQuery::Privilege> &privileges) override {
EditPermissions(user_or_role, privileges, [](auto *permissions, const auto &permission) {
// TODO (mferencevic): should we first check that the
// privilege is granted/denied/revoked before
// unconditionally granting/denying/revoking it?
permissions->Deny(permission);
});
}
void RevokePrivilege(const std::string &user_or_role,
const std::vector<memgraph::query::v2::AuthQuery::Privilege> &privileges) override {
EditPermissions(user_or_role, privileges, [](auto *permissions, const auto &permission) {
// TODO (mferencevic): should we first check that the
// privilege is granted/denied/revoked before
// unconditionally granting/denying/revoking it?
permissions->Revoke(permission);
});
}
private:
template <class TEditFun>
void EditPermissions(const std::string &user_or_role,
const std::vector<memgraph::query::v2::AuthQuery::Privilege> &privileges,
const TEditFun &edit_fun) {
if (!std::regex_match(user_or_role, name_regex_)) {
throw memgraph::query::v2::QueryRuntimeException("Invalid user or role name.");
}
try {
std::vector<memgraph::auth::Permission> permissions;
permissions.reserve(privileges.size());
for (const auto &privilege : privileges) {
permissions.push_back(memgraph::glue::v2::PrivilegeToPermission(privilege));
}
auto locked_auth = auth_->Lock();
auto user = locked_auth->GetUser(user_or_role);
auto role = locked_auth->GetRole(user_or_role);
if (!user && !role) {
throw memgraph::query::v2::QueryRuntimeException("User or role '{}' doesn't exist.", user_or_role);
}
if (user) {
for (const auto &permission : permissions) {
edit_fun(&user->permissions(), permission);
}
locked_auth->SaveUser(*user);
} else {
for (const auto &permission : permissions) {
edit_fun(&role->permissions(), permission);
}
locked_auth->SaveRole(*role);
}
} catch (const memgraph::auth::AuthException &e) {
throw memgraph::query::v2::QueryRuntimeException(e.what());
}
}
};
class AuthChecker final : public memgraph::query::v2::AuthChecker {
public:
explicit AuthChecker(
memgraph::utils::Synchronized<memgraph::auth::Auth, memgraph::utils::WritePrioritizedRWLock> *auth)
: auth_{auth} {}
static bool IsUserAuthorized(const memgraph::auth::User &user,
const std::vector<memgraph::query::v2::AuthQuery::Privilege> &privileges) {
const auto user_permissions = user.GetPermissions();
return std::all_of(privileges.begin(), privileges.end(), [&user_permissions](const auto privilege) {
return user_permissions.Has(memgraph::glue::v2::PrivilegeToPermission(privilege)) ==
memgraph::auth::PermissionLevel::GRANT;
});
}
bool IsUserAuthorized(const std::optional<std::string> &username,
const std::vector<memgraph::query::v2::AuthQuery::Privilege> &privileges) const final {
std::optional<memgraph::auth::User> maybe_user;
{
auto locked_auth = auth_->ReadLock();
if (!locked_auth->HasUsers()) {
return true;
}
if (username.has_value()) {
maybe_user = locked_auth->GetUser(*username);
}
}
return maybe_user.has_value() && IsUserAuthorized(*maybe_user, privileges);
}
private:
memgraph::utils::Synchronized<memgraph::auth::Auth, memgraph::utils::WritePrioritizedRWLock> *auth_;
};
class BoltSession final : public memgraph::communication::bolt::Session<memgraph::communication::v2::InputStream,
memgraph::communication::v2::OutputStream> {
public:
BoltSession(SessionData &data, const memgraph::communication::v2::ServerEndpoint &endpoint,
BoltSession(SessionData *data, const memgraph::communication::v2::ServerEndpoint &endpoint,
memgraph::communication::v2::InputStream *input_stream,
memgraph::communication::v2::OutputStream *output_stream)
: memgraph::communication::bolt::Session<memgraph::communication::v2::InputStream,
memgraph::communication::v2::OutputStream>(input_stream, output_stream),
interpreter_(data.interpreter_context),
endpoint_(endpoint) {}
db_(data->db),
interpreter_(data->interpreter_context),
auth_(data->auth),
#if MG_ENTERPRISE
audit_log_(data->audit_log),
#endif
endpoint_(endpoint) {
}
using memgraph::communication::bolt::Session<memgraph::communication::v2::InputStream,
memgraph::communication::v2::OutputStream>::TEncoder;
@@ -441,8 +884,23 @@ class BoltSession final : public memgraph::communication::bolt::Session<memgraph
std::map<std::string, memgraph::storage::v3::PropertyValue> params_pv;
for (const auto &kv : params) params_pv.emplace(kv.first, memgraph::glue::v2::ToPropertyValue(kv.second));
const std::string *username{nullptr};
if (user_) {
username = &user_->username();
}
#ifdef MG_ENTERPRISE
if (memgraph::utils::license::global_license_checker.IsValidLicenseFast()) {
audit_log_->Record(endpoint_.address().to_string(), user_ ? *username : "", query,
memgraph::storage::v3::PropertyValue(params_pv));
}
#endif
try {
auto result = interpreter_.Prepare(query, params_pv, username);
if (user_ && !AuthChecker::IsUserAuthorized(*user_, result.privileges)) {
interpreter_.Abort();
throw memgraph::communication::bolt::ClientError(
"You are not authorized to execute this query! Please contact "
"your database administrator.");
}
return {result.headers, result.qid};
} catch (const memgraph::query::v2::QueryException &e) {
@@ -454,7 +912,7 @@ class BoltSession final : public memgraph::communication::bolt::Session<memgraph
std::map<std::string, memgraph::communication::bolt::Value> Pull(TEncoder *encoder, std::optional<int> n,
std::optional<int> qid) override {
TypedValueResultStream stream(encoder, interpreter_.GetRequestRouter());
TypedValueResultStream stream(encoder, db_);
return PullResults(stream, n, qid);
}
@@ -466,7 +924,14 @@ class BoltSession final : public memgraph::communication::bolt::Session<memgraph
void Abort() override { interpreter_.Abort(); }
bool Authenticate(const std::string & /*username*/, const std::string & /*password*/) override { return true; }
bool Authenticate(const std::string &username, const std::string &password) override {
auto locked_auth = auth_->Lock();
if (!locked_auth->HasUsers()) {
return true;
}
user_ = locked_auth->Authenticate(username, password);
return user_.has_value();
}
std::optional<std::string> GetServerNameForInit() override {
if (FLAGS_bolt_server_name_for_init.empty()) return std::nullopt;
@@ -481,9 +946,18 @@ class BoltSession final : public memgraph::communication::bolt::Session<memgraph
const auto &summary = interpreter_.Pull(&stream, n, qid);
std::map<std::string, memgraph::communication::bolt::Value> decoded_summary;
for (const auto &kv : summary) {
auto bolt_value = memgraph::glue::v2::ToBoltValue(kv.second, interpreter_.GetRequestRouter(),
memgraph::storage::v3::View::NEW);
decoded_summary.emplace(kv.first, std::move(bolt_value));
auto maybe_value = memgraph::glue::v2::ToBoltValue(kv.second, *db_, memgraph::storage::v3::View::NEW);
if (maybe_value.HasError()) {
switch (maybe_value.GetError()) {
case memgraph::storage::v3::Error::DELETED_OBJECT:
case memgraph::storage::v3::Error::SERIALIZATION_ERROR:
case memgraph::storage::v3::Error::VERTEX_HAS_EDGES:
case memgraph::storage::v3::Error::PROPERTIES_DISABLED:
case memgraph::storage::v3::Error::NONEXISTENT_OBJECT:
throw memgraph::communication::bolt::ClientError("Unexpected storage error when streaming summary.");
}
}
decoded_summary.emplace(kv.first, std::move(*maybe_value));
}
return decoded_summary;
} catch (const memgraph::query::v2::QueryException &e) {
@@ -497,24 +971,44 @@ class BoltSession final : public memgraph::communication::bolt::Session<memgraph
/// before forwarding the calls to original TEncoder.
class TypedValueResultStream {
public:
TypedValueResultStream(TEncoder *encoder, const memgraph::query::v2::RequestRouterInterface *request_router)
: encoder_(encoder), request_router_(request_router) {}
TypedValueResultStream(TEncoder *encoder, const memgraph::storage::v3::Storage *db) : encoder_(encoder), db_(db) {}
void Result(const std::vector<memgraph::query::v2::TypedValue> &values) {
std::vector<memgraph::communication::bolt::Value> decoded_values;
decoded_values.reserve(values.size());
for (const auto &v : values) {
auto bolt_value = memgraph::glue::v2::ToBoltValue(v, request_router_, memgraph::storage::v3::View::NEW);
decoded_values.emplace_back(std::move(bolt_value));
auto maybe_value = memgraph::glue::v2::ToBoltValue(v, *db_, memgraph::storage::v3::View::NEW);
if (maybe_value.HasError()) {
switch (maybe_value.GetError()) {
case memgraph::storage::v3::Error::DELETED_OBJECT:
throw memgraph::communication::bolt::ClientError("Returning a deleted object as a result.");
case memgraph::storage::v3::Error::NONEXISTENT_OBJECT:
throw memgraph::communication::bolt::ClientError("Returning a nonexistent object as a result.");
case memgraph::storage::v3::Error::VERTEX_HAS_EDGES:
case memgraph::storage::v3::Error::SERIALIZATION_ERROR:
case memgraph::storage::v3::Error::PROPERTIES_DISABLED:
throw memgraph::communication::bolt::ClientError("Unexpected storage error when streaming results.");
}
}
decoded_values.emplace_back(std::move(*maybe_value));
}
encoder_->MessageRecord(decoded_values);
}
private:
TEncoder *encoder_;
const memgraph::query::v2::RequestRouterInterface *request_router_{nullptr};
// NOTE: Needed only for ToBoltValue conversions
const memgraph::storage::v3::Storage *db_;
};
// NOTE: Needed only for ToBoltValue conversions
const memgraph::storage::v3::Storage *db_;
memgraph::query::v2::Interpreter interpreter_;
memgraph::utils::Synchronized<memgraph::auth::Auth, memgraph::utils::WritePrioritizedRWLock> *auth_;
std::optional<memgraph::auth::User> user_;
#ifdef MG_ENTERPRISE
memgraph::audit::Log *audit_log_;
#endif
memgraph::communication::v2::ServerEndpoint endpoint_;
};
@@ -566,12 +1060,80 @@ int main(int argc, char **argv) {
// Unhandled exception handler init.
std::set_terminate(&memgraph::utils::TerminateHandler);
// Initialize Python
auto *program_name = Py_DecodeLocale(argv[0], nullptr);
MG_ASSERT(program_name);
// Set program name, so Python can find its way to runtime libraries relative
// to executable.
Py_SetProgramName(program_name);
PyImport_AppendInittab("_mgp", &memgraph::query::v2::procedure::PyInitMgpModule);
Py_InitializeEx(0 /* = initsigs */);
PyEval_InitThreads();
Py_BEGIN_ALLOW_THREADS;
// Add our Python modules to sys.path
try {
auto exe_path = memgraph::utils::GetExecutablePath();
auto py_support_dir = exe_path.parent_path() / "python_support";
if (std::filesystem::is_directory(py_support_dir)) {
auto gil = memgraph::py::EnsureGIL();
auto maybe_exc = memgraph::py::AppendToSysPath(py_support_dir.c_str());
if (maybe_exc) {
spdlog::error(memgraph::utils::MessageWithLink("Unable to load support for embedded Python: {}.", *maybe_exc,
"https://memgr.ph/python"));
} else {
// Change how we load dynamic libraries on Python by using RTLD_NOW and
// RTLD_DEEPBIND flags. This solves an issue with using the wrong version of
// libstd.
auto gil = memgraph::py::EnsureGIL();
// NOLINTNEXTLINE(hicpp-signed-bitwise)
auto *flag = PyLong_FromLong(RTLD_NOW | RTLD_DEEPBIND);
auto *setdl = PySys_GetObject("setdlopenflags");
MG_ASSERT(setdl);
auto *arg = PyTuple_New(1);
MG_ASSERT(arg);
MG_ASSERT(PyTuple_SetItem(arg, 0, flag) == 0);
PyObject_CallObject(setdl, arg);
Py_DECREF(flag);
Py_DECREF(setdl);
Py_DECREF(arg);
}
} else {
spdlog::error(
memgraph::utils::MessageWithLink("Unable to load support for embedded Python: missing directory {}.",
py_support_dir, "https://memgr.ph/python"));
}
} catch (const std::filesystem::filesystem_error &e) {
spdlog::error(memgraph::utils::MessageWithLink("Unable to load support for embedded Python: {}.", e.what(),
"https://memgr.ph/python"));
}
// Initialize the communication library.
memgraph::communication::SSLInit sslInit;
// Initialize the requests library.
memgraph::requests::Init();
// Start memory warning logger.
memgraph::utils::Scheduler mem_log_scheduler;
if (FLAGS_memory_warning_threshold > 0) {
auto free_ram = memgraph::utils::sysinfo::AvailableMemory();
if (free_ram) {
mem_log_scheduler.Run("Memory warning", std::chrono::seconds(3), [] {
auto free_ram = memgraph::utils::sysinfo::AvailableMemory();
if (free_ram && *free_ram / 1024 < FLAGS_memory_warning_threshold)
spdlog::warn(memgraph::utils::MessageWithLink("Running out of available RAM, only {} MB left.",
*free_ram / 1024, "https://memgr.ph/ram"));
});
} else {
// Kernel version for the `MemAvailable` value is from: man procfs
spdlog::warn(
"You have an older kernel version (<3.14) or the /proc "
"filesystem isn't available so remaining memory warnings "
"won't be available.");
}
}
std::cout << "You are running Memgraph v" << gflags::VersionString() << std::endl;
std::cout << "To get started with Memgraph, visit https://memgr.ph/start" << std::endl;
@@ -604,46 +1166,65 @@ int main(int argc, char **argv) {
// Example: When the main storage is destructed it makes a snapshot. When
// audit logging is destructed it syncs all pending data to disk and that can
// fail. That is why it must be destructed *after* the main database storage
// to minimize the impact of their failure on the main storage.
// to minimise the impact of their failure on the main storage.
memgraph::io::local_transport::LocalSystem ls;
auto unique_local_addr_query = memgraph::coordinator::Address::UniqueLocalAddress();
auto io = ls.Register(unique_local_addr_query);
// Begin enterprise features initialization
memgraph::machine_manager::MachineConfig config{
.coordinator_addresses = std::vector<memgraph::io::Address>{unique_local_addr_query},
.is_storage = true,
.is_coordinator = true,
.listen_ip = unique_local_addr_query.last_known_ip,
.listen_port = unique_local_addr_query.last_known_port,
};
// Auth
memgraph::utils::Synchronized<memgraph::auth::Auth, memgraph::utils::WritePrioritizedRWLock> auth{data_directory /
"auth"};
memgraph::coordinator::ShardMap sm;
if (FLAGS_split_file.empty()) {
const std::string property{"property"};
const std::string label{"label"};
auto prop_map = sm.AllocatePropertyIds(std::vector<std::string>{property});
auto edge_type_map = sm.AllocateEdgeTypeIds(std::vector<std::string>{"TO"});
std::vector<memgraph::storage::v3::SchemaProperty> schema{
{prop_map.at(property), memgraph::common::SchemaType::INT}};
sm.InitializeNewLabel(label, schema, 1, sm.shard_map_version);
sm.SplitShard(sm.GetHlc(), *sm.GetLabelId(label),
std::vector<memgraph::storage::v3::PropertyValue>{memgraph::storage::v3::PropertyValue{2}});
} else {
std::ifstream input{FLAGS_split_file, std::ios::in};
MG_ASSERT(input.is_open(), "Cannot open split file to read: {}", FLAGS_split_file);
sm = memgraph::coordinator::ShardMap::Parse(input);
#ifdef MG_ENTERPRISE
// Audit log
memgraph::audit::Log audit_log{data_directory / "audit", FLAGS_audit_buffer_size,
FLAGS_audit_buffer_flush_interval_ms};
// Start the log if enabled.
if (FLAGS_audit_enabled) {
audit_log.Start();
}
// Setup SIGUSR2 to be used for reopening audit log files, when e.g. logrotate
// rotates our audit logs.
MG_ASSERT(memgraph::utils::SignalHandler::RegisterHandler(memgraph::utils::Signal::User2,
[&audit_log]() { audit_log.ReopenLog(); }),
"Unable to register SIGUSR2 handler!");
memgraph::coordinator::Coordinator coordinator{sm};
// End enterprise features initialization
#endif
memgraph::machine_manager::MachineManager<memgraph::io::local_transport::LocalTransport> mm{io, config, coordinator};
std::jthread mm_thread([&mm] { mm.Run(); });
auto rr_factory = std::make_unique<memgraph::query::v2::LocalRequestRouterFactory>(io);
// Main storage and execution engines initialization
memgraph::storage::v3::Config db_config{
.gc = {.type = memgraph::storage::v3::Config::Gc::Type::PERIODIC,
.interval = std::chrono::seconds(FLAGS_storage_gc_cycle_sec)},
.items = {.properties_on_edges = FLAGS_storage_properties_on_edges},
.durability = {.storage_directory = FLAGS_data_directory,
.recover_on_startup = FLAGS_storage_recover_on_startup,
.snapshot_retention_count = FLAGS_storage_snapshot_retention_count,
.wal_file_size_kibibytes = FLAGS_storage_wal_file_size_kib,
.wal_file_flush_every_n_tx = FLAGS_storage_wal_file_flush_every_n_tx,
.snapshot_on_exit = FLAGS_storage_snapshot_on_exit},
.transaction = {.isolation_level = ParseIsolationLevel()}};
if (FLAGS_storage_snapshot_interval_sec == 0) {
if (FLAGS_storage_wal_enabled) {
LOG_FATAL(
"In order to use write-ahead-logging you must enable "
"periodic snapshots by setting the snapshot interval to a "
"value larger than 0!");
db_config.durability.snapshot_wal_mode = memgraph::storage::v3::Config::Durability::SnapshotWalMode::DISABLED;
}
} else {
if (FLAGS_storage_wal_enabled) {
db_config.durability.snapshot_wal_mode =
memgraph::storage::v3::Config::Durability::SnapshotWalMode::PERIODIC_SNAPSHOT_WITH_WAL;
} else {
db_config.durability.snapshot_wal_mode =
memgraph::storage::v3::Config::Durability::SnapshotWalMode::PERIODIC_SNAPSHOT;
}
db_config.durability.snapshot_interval = std::chrono::seconds(FLAGS_storage_snapshot_interval_sec);
}
memgraph::storage::v3::Storage db(db_config);
memgraph::query::v2::InterpreterContext interpreter_context{
(memgraph::storage::v3::Shard *)(nullptr),
&db,
{.query = {.allow_load_csv = FLAGS_allow_load_csv},
.execution_timeout_sec = FLAGS_query_execution_timeout_sec,
.replication_replica_check_frequency = std::chrono::seconds(FLAGS_replication_replica_check_frequency_sec),
@@ -651,14 +1232,32 @@ int main(int argc, char **argv) {
.default_pulsar_service_url = FLAGS_pulsar_service_url,
.stream_transaction_conflict_retries = FLAGS_stream_transaction_conflict_retries,
.stream_transaction_retry_interval = std::chrono::milliseconds(FLAGS_stream_transaction_retry_interval)},
FLAGS_data_directory,
std::move(rr_factory),
mm.CoordinatorAddress()};
FLAGS_data_directory};
#ifdef MG_ENTERPRISE
SessionData session_data{&db, &interpreter_context, &auth, &audit_log};
#else
SessionData session_data{&db, &interpreter_context, &auth};
#endif
SessionData session_data{&interpreter_context};
memgraph::query::v2::procedure::gModuleRegistry.SetModulesDirectory(query_modules_directories, FLAGS_data_directory);
memgraph::query::v2::procedure::gModuleRegistry.UnloadAndLoadModulesFromDirectories();
interpreter_context.auth = nullptr;
interpreter_context.auth_checker = nullptr;
AuthQueryHandler auth_handler(&auth, FLAGS_auth_user_or_role_name_regex);
AuthChecker auth_checker{&auth};
interpreter_context.auth = &auth_handler;
interpreter_context.auth_checker = &auth_checker;
{
// Triggers can execute query procedures, so we need to reload the modules first and then
// the triggers
auto storage_accessor = interpreter_context.db->Access();
auto dba = memgraph::query::v2::DbAccessor{&storage_accessor};
interpreter_context.trigger_store.RestoreTriggers(
&interpreter_context.ast_cache, &dba, interpreter_context.config.query, interpreter_context.auth_checker);
}
// As the Stream transformations are using modules, they have to be restored after the query modules are loaded.
interpreter_context.streams.RestoreStreams();
ServerContext context;
std::string service_name = "Bolt";
@@ -673,14 +1272,37 @@ int main(int argc, char **argv) {
auto server_endpoint = memgraph::communication::v2::ServerEndpoint{
boost::asio::ip::address::from_string(FLAGS_bolt_address), static_cast<uint16_t>(FLAGS_bolt_port)};
ServerT server(server_endpoint, session_data, &context, FLAGS_bolt_session_inactivity_timeout, service_name,
ServerT server(server_endpoint, &session_data, &context, FLAGS_bolt_session_inactivity_timeout, service_name,
FLAGS_bolt_num_workers);
// Setup telemetry
std::optional<memgraph::telemetry::Telemetry> telemetry;
if (FLAGS_telemetry_enabled) {
telemetry.emplace("https://telemetry.memgraph.com/88b5e7e8-746a-11e8-9f85-538a9e9690cc/",
data_directory / "telemetry", std::chrono::minutes(10));
telemetry->AddCollector("storage", [&db]() -> nlohmann::json {
auto info = db.GetInfo();
return {{"vertices", info.vertex_count}, {"edges", info.edge_count}};
});
telemetry->AddCollector("event_counters", []() -> nlohmann::json {
nlohmann::json ret;
for (size_t i = 0; i < EventCounter::End(); ++i) {
ret[EventCounter::GetName(i)] = EventCounter::global_counters[i].load(std::memory_order_relaxed);
}
return ret;
});
telemetry->AddCollector("query_module_counters", []() -> nlohmann::json {
return memgraph::query::v2::plan::CallProcedure::GetAndResetCounters();
});
}
memgraph::communication::websocket::SafeAuth websocket_auth{&auth};
memgraph::communication::websocket::Server websocket_server{
{FLAGS_monitoring_address, static_cast<uint16_t>(FLAGS_monitoring_port)}, &context, websocket_auth};
AddLoggerSink(websocket_server.GetLoggingSink());
// Handler for regular termination signals
auto shutdown = [&server, &interpreter_context, &ls] {
auto shutdown = [&websocket_server, &server, &interpreter_context] {
// Server needs to be shutdown first and then the database. This prevents
// a race condition when a transaction is accepted during server shutdown.
server.Shutdown();
@@ -688,13 +1310,23 @@ int main(int argc, char **argv) {
// connections we tell the execution engine to stop processing all pending
// queries.
memgraph::query::v2::Shutdown(&interpreter_context);
ls.ShutDown();
websocket_server.Shutdown();
};
InitSignalHandlers(shutdown);
MG_ASSERT(server.Start(), "Couldn't start the Bolt server!");
websocket_server.Start();
server.AwaitShutdown();
websocket_server.AwaitShutdown();
memgraph::query::v2::procedure::gModuleRegistry.UnloadAllModules();
Py_END_ALLOW_THREADS;
// Shutdown Python
Py_Finalize();
PyMem_RawFree(program_name);
memgraph::utils::total_memory_tracker.LogPeakMemoryUsage();
return 0;

View File

@@ -1,41 +0,0 @@
## Generate Antlr openCypher parser
set(opencypher_frontend ${CMAKE_CURRENT_SOURCE_DIR}/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)
set(antlr_opencypher_generated_src
${opencypher_generated}/MemgraphCypherLexer.cpp
${opencypher_generated}/MemgraphCypher.cpp
${opencypher_generated}/MemgraphCypherBaseVisitor.cpp
${opencypher_generated}/MemgraphCypherVisitor.cpp
)
set(antlr_opencypher_generated_include
${opencypher_generated}/MemgraphCypherLexer.h
${opencypher_generated}/MemgraphCypher.h
${opencypher_generated}/MemgraphCypherBaseVisitor.h
${opencypher_generated}/MemgraphCypherVisitor.h
)
add_custom_command(
OUTPUT ${antlr_opencypher_generated_src} ${antlr_opencypher_generated_include}
COMMAND ${CMAKE_COMMAND} -E make_directory ${opencypher_generated}
COMMAND
java -jar ${CMAKE_SOURCE_DIR}/libs/antlr-4.10.1-complete.jar
-Dlanguage=Cpp -visitor -package antlropencypher
-o ${opencypher_generated}
${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(generated_opencypher_parser
DEPENDS ${antlr_opencypher_generated_src} ${antlr_opencypher_generated_include})
add_library(mg-parser STATIC ${antlr_opencypher_generated_src})
add_dependencies(mg-parser generated_opencypher_parser)
target_include_directories(mg-parser PUBLIC ${CMAKE_CURRENT_SOURCE_DIR})
target_link_libraries(mg-parser antlr4)

View File

@@ -1,6 +1,7 @@
define_add_lcp(add_lcp_query lcp_query_v2_cpp_files generated_lcp_query_v2_files)
add_lcp_query(frontend/ast/ast.lcp)
add_lcp_query(frontend/semantic/symbol.lcp)
add_lcp_query(plan/operator.lcp)
add_custom_target(generate_lcp_query_v2 DEPENDS ${generated_lcp_query_v2_files})
@@ -9,8 +10,15 @@ set(mg_query_v2_sources
${lcp_query_v2_cpp_files}
common.cpp
cypher_query_interpreter.cpp
dump.cpp
frontend/ast/cypher_main_visitor.cpp
frontend/ast/pretty_print.cpp
frontend/parsing.cpp
frontend/semantic/required_privileges.cpp
frontend/semantic/symbol_generator.cpp
frontend/stripped.cpp
interpret/awesome_memgraph_functions.cpp
interpret/eval.cpp
interpreter.cpp
metadata.cpp
plan/operator.cpp
@@ -21,20 +29,25 @@ set(mg_query_v2_sources
plan/rewrite/index_lookup.cpp
plan/rule_based_planner.cpp
plan/variable_start_planner.cpp
procedure/mg_procedure_impl.cpp
procedure/mg_procedure_helpers.cpp
procedure/module.cpp
procedure/py_module.cpp
serialization/property_value.cpp
bindings/typed_value.cpp
accessors.cpp
multiframe.cpp)
stream/streams.cpp
stream/sources.cpp
stream/common.cpp
trigger.cpp
trigger_context.cpp
typed_value.cpp)
find_package(Boost REQUIRED)
add_library(mg-query-v2 STATIC ${mg_query_v2_sources})
add_dependencies(mg-query-v2 generate_lcp_query_v2)
target_include_directories(mg-query-v2 PUBLIC ${CMAKE_SOURCE_DIR}/include)
target_include_directories(mg-query-v2 PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}/bindings)
target_link_libraries(mg-query-v2 dl cppitertools Boost::headers)
target_link_libraries(mg-query-v2 mg-integrations-pulsar mg-integrations-kafka mg-storage-v3 mg-license mg-utils mg-kvstore mg-memory mg-coordinator)
target_link_libraries(mg-query-v2 mg-expr mg-functions)
target_link_libraries(mg-query-v2 mg-integrations-pulsar mg-integrations-kafka mg-storage-v3 mg-license mg-utils mg-kvstore mg-memory)
if(NOT "${MG_PYTHON_PATH}" STREQUAL "")
set(Python3_ROOT_DIR "${MG_PYTHON_PATH}")
@@ -47,3 +60,45 @@ else()
endif()
target_link_libraries(mg-query-v2 Python3::Python)
# Generate Antlr openCypher parser
set(opencypher_frontend ${CMAKE_CURRENT_SOURCE_DIR}/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)
set(antlr_opencypher_generated_src
${opencypher_generated}/MemgraphCypherLexer.cpp
${opencypher_generated}/MemgraphCypher.cpp
${opencypher_generated}/MemgraphCypherBaseVisitor.cpp
${opencypher_generated}/MemgraphCypherVisitor.cpp
)
set(antlr_opencypher_generated_include
${opencypher_generated}/MemgraphCypherLexer.h
${opencypher_generated}/MemgraphCypher.h
${opencypher_generated}/MemgraphCypherBaseVisitor.h
${opencypher_generated}/MemgraphCypherVisitor.h
)
add_custom_command(
OUTPUT ${antlr_opencypher_generated_src} ${antlr_opencypher_generated_include}
COMMAND ${CMAKE_COMMAND} -E make_directory ${opencypher_generated}
COMMAND
java -jar ${CMAKE_SOURCE_DIR}/libs/antlr-4.10.1-complete.jar
-Dlanguage=Cpp -visitor -package antlropencypher
-o ${opencypher_generated}
${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(generate_opencypher_parser_v2
DEPENDS ${antlr_opencypher_generated_src} ${antlr_opencypher_generated_include})
add_library(antlr_opencypher_parser_lib_v2 STATIC ${antlr_opencypher_generated_src})
add_dependencies(antlr_opencypher_parser_lib_v2 generate_opencypher_parser_v2)
target_link_libraries(antlr_opencypher_parser_lib_v2 antlr4)
target_link_libraries(mg-query-v2 antlr_opencypher_parser_lib_v2)

View File

@@ -1,103 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#include "query/v2/accessors.hpp"
#include "query/v2/request_router.hpp"
#include "query/v2/requests.hpp"
#include "storage/v3/id_types.hpp"
namespace memgraph::query::v2::accessors {
EdgeAccessor::EdgeAccessor(Edge edge, const RequestRouterInterface *request_router)
: edge(std::move(edge)), request_router_(request_router) {}
EdgeTypeId EdgeAccessor::EdgeType() const { return edge.type.id; }
const std::vector<std::pair<PropertyId, Value>> &EdgeAccessor::Properties() const { return edge.properties; }
Value EdgeAccessor::GetProperty(const std::string &prop_name) const {
auto maybe_prop = request_router_->MaybeNameToProperty(prop_name);
if (!maybe_prop) {
return {};
}
const auto prop_id = *maybe_prop;
auto it = std::find_if(edge.properties.begin(), edge.properties.end(), [&](auto &pr) { return prop_id == pr.first; });
return it->second;
}
const Edge &EdgeAccessor::GetEdge() const { return edge; }
bool EdgeAccessor::IsCycle() const { return edge.src == edge.dst; };
size_t EdgeAccessor::CypherId() const { return edge.id.gid; }
VertexAccessor EdgeAccessor::To() const {
return VertexAccessor(Vertex{edge.dst}, std::vector<std::pair<PropertyId, msgs::Value>>{}, request_router_);
}
VertexAccessor EdgeAccessor::From() const {
return VertexAccessor(Vertex{edge.src}, std::vector<std::pair<PropertyId, msgs::Value>>{}, request_router_);
}
VertexAccessor::VertexAccessor(Vertex v, std::vector<std::pair<PropertyId, Value>> props,
const RequestRouterInterface *request_router)
: vertex(std::move(v)), properties(std::move(props)), request_router_(request_router) {}
VertexAccessor::VertexAccessor(Vertex v, std::map<PropertyId, Value> &&props,
const RequestRouterInterface *request_router)
: vertex(std::move(v)), request_router_(request_router) {
properties.reserve(props.size());
for (auto &[id, value] : props) {
properties.emplace_back(std::make_pair(id, std::move(value)));
}
}
VertexAccessor::VertexAccessor(Vertex v, const std::map<PropertyId, Value> &props,
const RequestRouterInterface *request_router)
: vertex(std::move(v)), request_router_(request_router) {
properties.reserve(props.size());
for (const auto &[id, value] : props) {
properties.emplace_back(std::make_pair(id, value));
}
}
Label VertexAccessor::PrimaryLabel() const { return vertex.id.first; }
const msgs::VertexId &VertexAccessor::Id() const { return vertex.id; }
std::vector<Label> VertexAccessor::Labels() const { return vertex.labels; }
bool VertexAccessor::HasLabel(Label &label) const {
return std::find_if(vertex.labels.begin(), vertex.labels.end(),
[label](const auto &l) { return l.id == label.id; }) != vertex.labels.end();
}
const std::vector<std::pair<PropertyId, Value>> &VertexAccessor::Properties() const { return properties; }
Value VertexAccessor::GetProperty(PropertyId prop_id) const {
auto it = std::find_if(properties.begin(), properties.end(), [&](auto &pr) { return prop_id == pr.first; });
if (it == properties.end()) {
return {};
}
return it->second;
}
// NOLINTNEXTLINE(readability-convert-member-functions-to-static)
Value VertexAccessor::GetProperty(const std::string &prop_name) const {
auto maybe_prop = request_router_->MaybeNameToProperty(prop_name);
if (!maybe_prop) {
return {};
}
return GetProperty(*maybe_prop);
}
msgs::Vertex VertexAccessor::GetVertex() const { return vertex; }
} // namespace memgraph::query::v2::accessors

View File

@@ -1,164 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <map>
#include <optional>
#include <utility>
#include <vector>
#include "query/exceptions.hpp"
#include "query/v2/requests.hpp"
#include "storage/v3/view.hpp"
#include "utils/bound.hpp"
#include "utils/exceptions.hpp"
#include "utils/memory.hpp"
#include "utils/memory_tracker.hpp"
namespace memgraph::query::v2 {
class RequestRouterInterface;
} // namespace memgraph::query::v2
namespace memgraph::query::v2::accessors {
using Value = msgs::Value;
using Edge = msgs::Edge;
using Vertex = msgs::Vertex;
using Label = msgs::Label;
using PropertyId = msgs::PropertyId;
using EdgeTypeId = msgs::EdgeTypeId;
class VertexAccessor;
class EdgeAccessor final {
public:
explicit EdgeAccessor(Edge edge, const RequestRouterInterface *request_router);
[[nodiscard]] EdgeTypeId EdgeType() const;
[[nodiscard]] const std::vector<std::pair<PropertyId, Value>> &Properties() const;
[[nodiscard]] Value GetProperty(const std::string &prop_name) const;
[[nodiscard]] const Edge &GetEdge() const;
[[nodiscard]] bool IsCycle() const;
[[nodiscard]] size_t CypherId() const;
[[nodiscard]] VertexAccessor To() const;
[[nodiscard]] VertexAccessor From() const;
friend bool operator==(const EdgeAccessor &lhs, const EdgeAccessor &rhs) { return lhs.edge == rhs.edge; }
friend bool operator!=(const EdgeAccessor &lhs, const EdgeAccessor &rhs) { return !(lhs == rhs); }
private:
Edge edge;
const RequestRouterInterface *request_router_;
};
class VertexAccessor final {
public:
using PropertyId = msgs::PropertyId;
using Label = msgs::Label;
using VertexId = msgs::VertexId;
VertexAccessor(Vertex v, std::vector<std::pair<PropertyId, Value>> props,
const RequestRouterInterface *request_router);
VertexAccessor(Vertex v, std::map<PropertyId, Value> &&props, const RequestRouterInterface *request_router);
VertexAccessor(Vertex v, const std::map<PropertyId, Value> &props, const RequestRouterInterface *request_router);
[[nodiscard]] Label PrimaryLabel() const;
[[nodiscard]] const msgs::VertexId &Id() const;
[[nodiscard]] std::vector<Label> Labels() const;
[[nodiscard]] bool HasLabel(Label &label) const;
[[nodiscard]] const std::vector<std::pair<PropertyId, Value>> &Properties() const;
[[nodiscard]] Value GetProperty(PropertyId prop_id) const;
[[nodiscard]] Value GetProperty(const std::string &prop_name) const;
[[nodiscard]] msgs::Vertex GetVertex() const;
// NOLINTNEXTLINE(readability-convert-member-functions-to-static)
[[nodiscard]] size_t InDegree() const { throw utils::NotYetImplemented("InDegree() not yet implemented"); }
// NOLINTNEXTLINE(readability-convert-member-functions-to-static)
[[nodiscard]] size_t OutDegree() const { throw utils::NotYetImplemented("OutDegree() not yet implemented"); }
friend bool operator==(const VertexAccessor &lhs, const VertexAccessor &rhs) {
return lhs.vertex == rhs.vertex && lhs.properties == rhs.properties;
}
friend bool operator!=(const VertexAccessor &lhs, const VertexAccessor &rhs) { return !(lhs == rhs); }
private:
Vertex vertex;
std::vector<std::pair<PropertyId, Value>> properties;
const RequestRouterInterface *request_router_;
};
// Highly mocked interface. Won't work if used.
class Path {
public:
// Empty for now
explicit Path(const VertexAccessor & /*vertex*/, utils::MemoryResource *memory = utils::NewDeleteResource())
: mem(memory) {}
template <typename... TOthers>
explicit Path(const VertexAccessor &vertex, const TOthers &...others) {}
template <typename... TOthers>
Path(std::allocator_arg_t /*unused*/, utils::MemoryResource *memory, const VertexAccessor &vertex,
const TOthers &...others) {}
Path(const Path & /*other*/) {}
Path(const Path & /*other*/, utils::MemoryResource *memory) : mem(memory) {}
Path(Path && /*other*/) noexcept {}
Path(Path && /*other*/, utils::MemoryResource *memory) : mem(memory) {}
Path &operator=(const Path &path) {
if (this == &path) {
return *this;
}
return *this;
}
Path &operator=(Path &&path) noexcept {
if (this == &path) {
return *this;
}
return *this;
}
~Path() {}
friend bool operator==(const Path & /*lhs*/, const Path & /*rhs*/) { return true; };
utils::MemoryResource *GetMemoryResource() { return mem; }
auto &vertices() { return vertices_; }
auto &edges() { return edges_; }
const auto &vertices() const { return vertices_; }
const auto &edges() const { return edges_; }
private:
std::vector<VertexAccessor> vertices_;
std::vector<EdgeAccessor> edges_;
utils::MemoryResource *mem = utils::NewDeleteResource();
};
} // namespace memgraph::query::v2::accessors

View File

@@ -1,19 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#ifdef MG_AST_INCLUDE_PATH
#error You are probably trying to include files from expr from both the storage and query engines! You will have a rough time kid!
#endif
#define MG_AST_INCLUDE_PATH "query/v2/frontend/ast/ast.hpp" // NOLINT(cppcoreguidelines-macro-usage)
#define MG_INJECTED_NAMESPACE_NAME memgraph::query::v2 // NOLINT(cppcoreguidelines-macro-usage)

View File

@@ -1,20 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "query/v2/bindings/bindings.hpp"
#include "expr/ast/cypher_main_visitor.hpp"
namespace memgraph::query::v2 {
using CypherMainVisitor = memgraph::expr::CypherMainVisitor;
} // namespace memgraph::query::v2

View File

@@ -1,47 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "query/v2/bindings/bindings.hpp"
#include "expr/interpret/eval.hpp"
#include "query/v2/bindings/typed_value.hpp"
#include "query/v2/context.hpp"
#include "query/v2/conversions.hpp"
#include "query/v2/db_accessor.hpp"
#include "query/v2/requests.hpp"
#include "storage/v3/conversions.hpp"
#include "storage/v3/property_value.hpp"
#include "storage/v3/result.hpp"
#include "storage/v3/view.hpp"
namespace memgraph::query::v2 {
class RequestRouterInterface;
namespace detail {
class Callable {
public:
auto operator()(const storage::v3::PropertyValue &val) const {
return storage::v3::PropertyToTypedValue<TypedValue>(val);
};
auto operator()(const msgs::Value &val, RequestRouterInterface *request_router) const {
return ValueToTypedValue(val, request_router);
};
};
} // namespace detail
using ExpressionEvaluator = expr::ExpressionEvaluator<TypedValue, query::v2::EvaluationContext, RequestRouterInterface,
storage::v3::View, storage::v3::LabelId, msgs::Value,
detail::Callable, common::ErrorCode, expr::QueryEngineTag>;
} // namespace memgraph::query::v2

View File

@@ -1,22 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "query/v2/bindings/bindings.hpp"
#include "expr/interpret/frame.hpp"
#include "query/v2/bindings/typed_value.hpp"
namespace memgraph::query::v2 {
using Frame = memgraph::expr::Frame;
using FrameWithValidity = memgraph::expr::FrameWithValidity;
} // namespace memgraph::query::v2

View File

@@ -1,20 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "query/v2/bindings/bindings.hpp"
#include "expr/semantic/symbol.hpp"
namespace memgraph::query::v2 {
using Symbol = memgraph::expr::Symbol;
} // namespace memgraph::query::v2

View File

@@ -1,16 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "query/v2/bindings/bindings.hpp"
#include "expr/semantic/symbol_generator.hpp"

View File

@@ -1,20 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "query/v2/bindings/bindings.hpp"
#include "expr/semantic/symbol_table.hpp"
namespace memgraph::query::v2 {
using SymbolTable = memgraph::expr::SymbolTable;
} // namespace memgraph::query::v2

View File

@@ -1,19 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#include "expr/typed_value.hpp"
#include "query/v2/accessors.hpp"
#include "query/v2/path.hpp"
namespace memgraph::expr {
namespace v2 = memgraph::query::v2;
template class TypedValueT<v2::accessors::VertexAccessor, v2::accessors::EdgeAccessor, v2::accessors::Path>;
} // namespace memgraph::expr

View File

@@ -1,27 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "query/v2/bindings/bindings.hpp"
#include "expr/typed_value.hpp"
#include "query/v2/accessors.hpp"
namespace memgraph::expr {
namespace v2 = memgraph::query::v2;
extern template class memgraph::expr::TypedValueT<v2::accessors::VertexAccessor, v2::accessors::EdgeAccessor,
v2::accessors::Path>;
} // namespace memgraph::expr
namespace memgraph::query::v2 {
using TypedValue =
memgraph::expr::TypedValueT<v2::accessors::VertexAccessor, v2::accessors::EdgeAccessor, v2::accessors::Path>;
} // namespace memgraph::query::v2

View File

@@ -18,15 +18,15 @@
#include <string_view>
#include <type_traits>
#include "query/v2/bindings/symbol.hpp"
#include "query/v2/bindings/typed_value.hpp"
#include "query/v2/db_accessor.hpp"
#include "query/v2/exceptions.hpp"
#include "query/v2/frontend/ast/ast.hpp"
#include "query/v2/path.hpp"
#include "storage/v3/conversions.hpp"
#include "query/v2/frontend/semantic/symbol.hpp"
#include "query/v2/typed_value.hpp"
#include "storage/v3/id_types.hpp"
#include "storage/v3/property_value.hpp"
#include "storage/v3/result.hpp"
#include "storage/v3/schema_validator.hpp"
#include "storage/v3/view.hpp"
#include "utils/exceptions.hpp"
#include "utils/logging.hpp"
@@ -80,5 +80,89 @@ inline void ExpectType(const Symbol &symbol, const TypedValue &value, TypedValue
throw QueryRuntimeException("Expected a {} for '{}', but got {}.", expected, symbol.name(), value.type());
}
template <typename T>
concept AccessorWithSetProperty = requires(T accessor, const storage::v3::PropertyId key,
const storage::v3::PropertyValue new_value) {
{ accessor.SetProperty(key, new_value) } -> std::same_as<storage::v3::Result<storage::v3::PropertyValue>>;
};
inline void HandleSchemaViolation(const storage::v3::SchemaViolation &schema_violation, const DbAccessor &dba) {
switch (schema_violation.status) {
case storage::v3::SchemaViolation::ValidationStatus::VERTEX_HAS_NO_PRIMARY_PROPERTY: {
throw SchemaViolationException(
fmt::format("Primary key {} not defined on label :{}",
storage::v3::SchemaTypeToString(schema_violation.violated_schema_property->type),
dba.LabelToName(schema_violation.label)));
}
case storage::v3::SchemaViolation::ValidationStatus::NO_SCHEMA_DEFINED_FOR_LABEL: {
throw SchemaViolationException(
fmt::format("Label :{} is not a primary label", dba.LabelToName(schema_violation.label)));
}
case storage::v3::SchemaViolation::ValidationStatus::VERTEX_PROPERTY_WRONG_TYPE: {
throw SchemaViolationException(
fmt::format("Wrong type of property {} in schema :{}, should be of type {}",
*schema_violation.violated_property_value, dba.LabelToName(schema_violation.label),
storage::v3::SchemaTypeToString(schema_violation.violated_schema_property->type)));
}
case storage::v3::SchemaViolation::ValidationStatus::VERTEX_UPDATE_PRIMARY_KEY: {
throw SchemaViolationException(fmt::format("Updating of primary key {} on schema :{} not supported",
*schema_violation.violated_property_value,
dba.LabelToName(schema_violation.label)));
}
case storage::v3::SchemaViolation::ValidationStatus::VERTEX_MODIFY_PRIMARY_LABEL: {
throw SchemaViolationException(fmt::format("Cannot add or remove label :{} since it is a primary label",
dba.LabelToName(schema_violation.label)));
}
case storage::v3::SchemaViolation::ValidationStatus::VERTEX_SECONDARY_LABEL_IS_PRIMARY: {
throw SchemaViolationException(
fmt::format("Cannot create vertex with secondary label :{}", dba.LabelToName(schema_violation.label)));
}
}
}
inline void HandleErrorOnPropertyUpdate(const storage::v3::Error error) {
switch (error) {
case storage::v3::Error::SERIALIZATION_ERROR:
throw TransactionSerializationException();
case storage::v3::Error::DELETED_OBJECT:
throw QueryRuntimeException("Trying to set properties on a deleted object.");
case storage::v3::Error::PROPERTIES_DISABLED:
throw QueryRuntimeException("Can't set property because properties on edges are disabled.");
case storage::v3::Error::VERTEX_HAS_EDGES:
case storage::v3::Error::NONEXISTENT_OBJECT:
throw QueryRuntimeException("Unexpected error when setting a property.");
}
}
/// Set a property `value` mapped with given `key` on a `record`.
///
/// @throw QueryRuntimeException if value cannot be set as a property value
template <AccessorWithSetProperty T>
storage::v3::PropertyValue PropsSetChecked(T *record, const DbAccessor &dba, const storage::v3::PropertyId &key,
const TypedValue &value) {
try {
if constexpr (std::is_same_v<T, VertexAccessor>) {
const auto maybe_old_value = record->SetPropertyAndValidate(key, storage::v3::PropertyValue(value));
if (maybe_old_value.HasError()) {
std::visit(utils::Overloaded{[](const storage::v3::Error error) { HandleErrorOnPropertyUpdate(error); },
[&dba](const storage::v3::SchemaViolation &schema_violation) {
HandleSchemaViolation(schema_violation, dba);
}},
maybe_old_value.GetError());
}
return std::move(*maybe_old_value);
} else {
// No validation on edge properties
const auto maybe_old_value = record->SetProperty(key, storage::v3::PropertyValue(value));
if (maybe_old_value.HasError()) {
HandleErrorOnPropertyUpdate(maybe_old_value.GetError());
}
return std::move(*maybe_old_value);
}
} catch (const TypedValueException &) {
throw QueryRuntimeException("'{}' cannot be used as a property value.", value.type());
}
}
int64_t QueryTimestamp();
} // namespace memgraph::query::v2

View File

@@ -1,4 +1,4 @@
// Copyright 2023 Memgraph Ltd.
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
@@ -13,35 +13,16 @@
#include <type_traits>
#include "io/local_transport/local_transport.hpp"
#include "query/v2/bindings/symbol_table.hpp"
#include "query/v2/common.hpp"
#include "query/v2/frontend/semantic/symbol_table.hpp"
#include "query/v2/metadata.hpp"
#include "query/v2/parameters.hpp"
#include "query/v2/plan/profile.hpp"
//#include "query/v2/trigger.hpp"
#include "query/v2/request_router.hpp"
#include "query/v2/trigger.hpp"
#include "utils/async_timer.hpp"
namespace memgraph::query::v2 {
// Used to store range of ids that are available
// Used for edge id assignment
class IdAllocator {
public:
IdAllocator() = default;
IdAllocator(uint64_t low, uint64_t high) : current_edge_id_{low}, max_id_{high} {};
uint64_t AllocateId() {
MG_ASSERT(current_edge_id_ < max_id_, "Current Edge Id went above max id");
return current_edge_id_++;
}
private:
uint64_t current_edge_id_;
uint64_t max_id_;
};
struct EvaluationContext {
/// Memory for allocations during evaluation of a *single* Pull call.
///
@@ -61,27 +42,20 @@ struct EvaluationContext {
};
inline std::vector<storage::v3::PropertyId> NamesToProperties(const std::vector<std::string> &property_names,
RequestRouterInterface *request_router) {
DbAccessor *dba) {
std::vector<storage::v3::PropertyId> properties;
// TODO Fix by using reference
properties.reserve(property_names.size());
if (request_router != nullptr) {
for (const auto &name : property_names) {
properties.push_back(request_router->NameToProperty(name));
}
for (const auto &name : property_names) {
properties.push_back(dba->NameToProperty(name));
}
return properties;
}
inline std::vector<storage::v3::LabelId> NamesToLabels(const std::vector<std::string> &label_names,
RequestRouterInterface *request_router) {
inline std::vector<storage::v3::LabelId> NamesToLabels(const std::vector<std::string> &label_names, DbAccessor *dba) {
std::vector<storage::v3::LabelId> labels;
labels.reserve(label_names.size());
// TODO Fix by using reference
if (request_router != nullptr) {
for (const auto &name : label_names) {
labels.push_back(request_router->NameToLabel(name));
}
for (const auto &name : label_names) {
labels.push_back(dba->NameToLabel(name));
}
return labels;
}
@@ -96,9 +70,8 @@ struct ExecutionContext {
plan::ProfilingStats stats;
plan::ProfilingStats *stats_root{nullptr};
ExecutionStats execution_stats;
TriggerContextCollector *trigger_context_collector{nullptr};
utils::AsyncTimer timer;
RequestRouterInterface *request_router{nullptr};
IdAllocator *edge_ids_alloc;
};
static_assert(std::is_move_assignable_v<ExecutionContext>, "ExecutionContext must be move assignable!");

View File

@@ -1,107 +0,0 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include "bindings/typed_value.hpp"
#include "query/v2/accessors.hpp"
#include "query/v2/request_router.hpp"
#include "query/v2/requests.hpp"
namespace memgraph::query::v2 {
inline TypedValue ValueToTypedValue(const msgs::Value &value, RequestRouterInterface *request_router) {
using Value = msgs::Value;
switch (value.type) {
case Value::Type::Null:
return {};
case Value::Type::Bool:
return TypedValue(value.bool_v);
case Value::Type::Int64:
return TypedValue(value.int_v);
case Value::Type::Double:
return TypedValue(value.double_v);
case Value::Type::String:
return TypedValue(value.string_v);
case Value::Type::List: {
const auto &lst = value.list_v;
std::vector<TypedValue> dst;
dst.reserve(lst.size());
for (const auto &elem : lst) {
dst.push_back(ValueToTypedValue(elem, request_router));
}
return TypedValue(std::move(dst));
}
case Value::Type::Map: {
const auto &value_map = value.map_v;
std::map<std::string, TypedValue> dst;
for (const auto &[key, val] : value_map) {
dst[key] = ValueToTypedValue(val, request_router);
}
return TypedValue(std::move(dst));
}
case Value::Type::Vertex:
return TypedValue(accessors::VertexAccessor(
value.vertex_v, std::vector<std::pair<storage::v3::PropertyId, msgs::Value>>{}, request_router));
case Value::Type::Edge:
return TypedValue(accessors::EdgeAccessor(value.edge_v, request_router));
}
throw std::runtime_error("Incorrect type in conversion");
}
inline const auto ValueToTypedValueFunctor = [](const msgs::Value &value, RequestRouterInterface *request_router) {
return ValueToTypedValue(value, request_router);
};
inline msgs::Value TypedValueToValue(const TypedValue &value) {
using Value = msgs::Value;
switch (value.type()) {
case TypedValue::Type::Null:
return {};
case TypedValue::Type::Bool:
return Value(value.ValueBool());
case TypedValue::Type::Int:
return Value(value.ValueInt());
case TypedValue::Type::Double:
return Value(value.ValueDouble());
case TypedValue::Type::String:
return Value(std::string(value.ValueString()));
case TypedValue::Type::List: {
const auto &lst = value.ValueList();
std::vector<Value> dst;
dst.reserve(lst.size());
for (const auto &elem : lst) {
dst.push_back(TypedValueToValue(elem));
}
return Value(std::move(dst));
}
case TypedValue::Type::Map: {
const auto &value_map = value.ValueMap();
std::map<std::string, Value> dst;
for (const auto &[key, val] : value_map) {
dst[std::string(key)] = TypedValueToValue(val);
}
return Value(std::move(dst));
}
case TypedValue::Type::Vertex:
return Value(value.ValueVertex().GetVertex());
case TypedValue::Type::Edge:
return Value(value.ValueEdge().GetEdge());
case TypedValue::Type::Path:
case TypedValue::Type::LocalTime:
case TypedValue::Type::LocalDateTime:
case TypedValue::Type::Date:
case TypedValue::Type::Duration:
break;
}
throw std::runtime_error("Incorrect type in conversion");
}
} // namespace memgraph::query::v2

View File

@@ -10,8 +10,6 @@
// licenses/APL.txt.
#include "query/v2/cypher_query_interpreter.hpp"
#include "query/v2/bindings/symbol_generator.hpp"
#include "query/v2/request_router.hpp"
// NOLINTNEXTLINE (cppcoreguidelines-avoid-non-const-global-variables)
DEFINE_HIDDEN_bool(query_cost_planner, true, "Use the cost-estimating query planner.");
@@ -48,7 +46,7 @@ ParsedQuery ParseQuery(const std::string &query_string, const std::map<std::stri
auto hash = stripped_query.hash();
auto accessor = cache->access();
auto it = accessor.find(hash);
std::unique_ptr<memgraph::frontend::opencypher::Parser<>> parser;
std::unique_ptr<frontend::opencypher::Parser> parser;
// Return a copy of both the AST storage and the query.
CachedQuery result;
@@ -65,11 +63,11 @@ ParsedQuery ParseQuery(const std::string &query_string, const std::map<std::stri
if (it == accessor.end()) {
try {
parser = std::make_unique<memgraph::frontend::opencypher::Parser<>>(stripped_query.query());
parser = std::make_unique<frontend::opencypher::Parser>(stripped_query.query());
} catch (const SyntaxException &e) {
// There is a syntax exception in the stripped query. Re-run the parser
// on the original query to get an appropriate error messsage.
parser = std::make_unique<memgraph::frontend::opencypher::Parser<>>(query_string);
parser = std::make_unique<frontend::opencypher::Parser>(query_string);
// If an exception was not thrown here, the stripper messed something
// up.
@@ -78,8 +76,8 @@ ParsedQuery ParseQuery(const std::string &query_string, const std::map<std::stri
// Convert the ANTLR4 parse tree into an AST.
AstStorage ast_storage;
expr::ParsingContext context{true};
memgraph::expr::CypherMainVisitor visitor(context, &ast_storage);
frontend::ParsingContext context{true};
frontend::CypherMainVisitor visitor(context, &ast_storage);
visitor.visit(parser->tree());
@@ -118,10 +116,10 @@ ParsedQuery ParseQuery(const std::string &query_string, const std::map<std::stri
}
std::unique_ptr<LogicalPlan> MakeLogicalPlan(AstStorage ast_storage, CypherQuery *query, const Parameters &parameters,
RequestRouterInterface *request_router,
DbAccessor *db_accessor,
const std::vector<Identifier *> &predefined_identifiers) {
auto vertex_counts = plan::MakeVertexCountCache(request_router);
auto symbol_table = expr::MakeSymbolTable(query, predefined_identifiers);
auto vertex_counts = plan::MakeVertexCountCache(db_accessor);
auto symbol_table = MakeSymbolTable(query, predefined_identifiers);
auto planning_context = plan::MakePlanningContext(&ast_storage, &symbol_table, query, &vertex_counts);
auto [root, cost] = plan::MakeLogicalPlan(&planning_context, parameters, FLAGS_query_cost_planner);
return std::make_unique<SingleNodeLogicalPlan>(std::move(root), cost, std::move(ast_storage),
@@ -130,7 +128,7 @@ std::unique_ptr<LogicalPlan> MakeLogicalPlan(AstStorage ast_storage, CypherQuery
std::shared_ptr<CachedPlan> CypherQueryToPlan(uint64_t hash, AstStorage ast_storage, CypherQuery *query,
const Parameters &parameters, utils::SkipList<PlanCacheEntry> *plan_cache,
RequestRouterInterface *request_router,
DbAccessor *db_accessor,
const std::vector<Identifier *> &predefined_identifiers) {
std::optional<utils::SkipList<PlanCacheEntry>::Accessor> plan_cache_access;
if (plan_cache) {
@@ -146,7 +144,7 @@ std::shared_ptr<CachedPlan> CypherQueryToPlan(uint64_t hash, AstStorage ast_stor
}
auto plan = std::make_shared<CachedPlan>(
MakeLogicalPlan(std::move(ast_storage), query, parameters, request_router, predefined_identifiers));
MakeLogicalPlan(std::move(ast_storage), query, parameters, db_accessor, predefined_identifiers));
if (plan_cache_access) {
plan_cache_access->insert({hash, plan});
}

View File

@@ -11,11 +11,11 @@
#pragma once
#include "parser/opencypher/parser.hpp"
#include "query/v2/bindings/cypher_main_visitor.hpp"
#include "query/v2/bindings/symbol_table.hpp"
#include "query/v2/config.hpp"
#include "query/v2/frontend/ast/cypher_main_visitor.hpp"
#include "query/v2/frontend/opencypher/parser.hpp"
#include "query/v2/frontend/semantic/required_privileges.hpp"
#include "query/v2/frontend/semantic/symbol_generator.hpp"
#include "query/v2/frontend/stripped.hpp"
#include "query/v2/plan/planner.hpp"
#include "utils/flag_validation.hpp"
@@ -132,7 +132,7 @@ class SingleNodeLogicalPlan final : public LogicalPlan {
};
std::unique_ptr<LogicalPlan> MakeLogicalPlan(AstStorage ast_storage, CypherQuery *query, const Parameters &parameters,
RequestRouterInterface *request_router,
DbAccessor *db_accessor,
const std::vector<Identifier *> &predefined_identifiers);
/**
@@ -145,7 +145,7 @@ std::unique_ptr<LogicalPlan> MakeLogicalPlan(AstStorage ast_storage, CypherQuery
*/
std::shared_ptr<CachedPlan> CypherQueryToPlan(uint64_t hash, AstStorage ast_storage, CypherQuery *query,
const Parameters &parameters, utils::SkipList<PlanCacheEntry> *plan_cache,
RequestRouterInterface *request_router,
DbAccessor *db_accessor,
const std::vector<Identifier *> &predefined_identifiers = {});
} // namespace memgraph::query::v2

View File

@@ -11,7 +11,6 @@
#pragma once
#include <cstdint>
#include <optional>
#include <vector>
@@ -20,7 +19,6 @@
#include "query/v2/exceptions.hpp"
#include "storage/v3/id_types.hpp"
#include "storage/v3/key_store.hpp"
#include "storage/v3/property_value.hpp"
#include "storage/v3/result.hpp"
@@ -36,7 +34,7 @@
// This cannot be avoided by simple include orderings so we
// simply undefine those macros as we're sure that libkrb5
// won't and can't be used anywhere in the query engine.
#include "storage/v3/shard.hpp"
#include "storage/v3/storage.hpp"
#include "utils/logging.hpp"
#include "utils/result.hpp"
@@ -64,11 +62,24 @@ class EdgeAccessor final {
auto Properties(storage::v3::View view) const { return impl_.Properties(view); }
storage::v3::ShardResult<storage::v3::PropertyValue> GetProperty(storage::v3::View view,
storage::v3::PropertyId key) const {
storage::v3::Result<storage::v3::PropertyValue> GetProperty(storage::v3::View view,
storage::v3::PropertyId key) const {
return impl_.GetProperty(key, view);
}
storage::v3::Result<storage::v3::PropertyValue> SetProperty(storage::v3::PropertyId key,
const storage::v3::PropertyValue &value) {
return impl_.SetProperty(key, value);
}
storage::v3::Result<storage::v3::PropertyValue> RemoveProperty(storage::v3::PropertyId key) {
return SetProperty(key, storage::v3::PropertyValue());
}
storage::v3::Result<std::map<storage::v3::PropertyId, storage::v3::PropertyValue>> ClearProperties() {
return impl_.ClearProperties();
}
VertexAccessor To() const;
VertexAccessor From() const;
@@ -98,21 +109,49 @@ class VertexAccessor final {
auto PrimaryLabel(storage::v3::View view) const { return impl_.PrimaryLabel(view); }
auto PrimaryKey(storage::v3::View view) const { return impl_.PrimaryKey(view); }
storage::v3::Result<bool> AddLabel(storage::v3::LabelId label) { return impl_.AddLabel(label); }
storage::v3::ShardResult<bool> HasLabel(storage::v3::View view, storage::v3::LabelId label) const {
storage::v3::ResultSchema<bool> AddLabelAndValidate(storage::v3::LabelId label) {
return impl_.AddLabelAndValidate(label);
}
storage::v3::Result<bool> RemoveLabel(storage::v3::LabelId label) { return impl_.RemoveLabel(label); }
storage::v3::ResultSchema<bool> RemoveLabelAndValidate(storage::v3::LabelId label) {
return impl_.RemoveLabelAndValidate(label);
}
storage::v3::Result<bool> HasLabel(storage::v3::View view, storage::v3::LabelId label) const {
return impl_.HasLabel(label, view);
}
auto Properties(storage::v3::View view) const { return impl_.Properties(view); }
storage::v3::ShardResult<storage::v3::PropertyValue> GetProperty(storage::v3::View view,
storage::v3::PropertyId key) const {
storage::v3::Result<storage::v3::PropertyValue> GetProperty(storage::v3::View view,
storage::v3::PropertyId key) const {
return impl_.GetProperty(key, view);
}
storage::v3::Result<storage::v3::PropertyValue> SetProperty(storage::v3::PropertyId key,
const storage::v3::PropertyValue &value) {
return impl_.SetProperty(key, value);
}
storage::v3::ResultSchema<storage::v3::PropertyValue> SetPropertyAndValidate(
storage::v3::PropertyId key, const storage::v3::PropertyValue &value) {
return impl_.SetPropertyAndValidate(key, value);
}
storage::v3::ResultSchema<storage::v3::PropertyValue> RemovePropertyAndValidate(storage::v3::PropertyId key) {
return SetPropertyAndValidate(key, storage::v3::PropertyValue{});
}
storage::v3::Result<std::map<storage::v3::PropertyId, storage::v3::PropertyValue>> ClearProperties() {
return impl_.ClearProperties();
}
auto InEdges(storage::v3::View view, const std::vector<storage::v3::EdgeTypeId> &edge_types) const
-> storage::v3::ShardResult<decltype(iter::imap(MakeEdgeAccessor, *impl_.InEdges(view)))> {
-> storage::v3::Result<decltype(iter::imap(MakeEdgeAccessor, *impl_.InEdges(view)))> {
auto maybe_edges = impl_.InEdges(view, edge_types);
if (maybe_edges.HasError()) return maybe_edges.GetError();
return iter::imap(MakeEdgeAccessor, std::move(*maybe_edges));
@@ -122,15 +161,14 @@ class VertexAccessor final {
auto InEdges(storage::v3::View view, const std::vector<storage::v3::EdgeTypeId> &edge_types,
const VertexAccessor &dest) const
-> storage::v3::ShardResult<decltype(iter::imap(MakeEdgeAccessor, *impl_.InEdges(view)))> {
const auto dest_id = dest.impl_.Id(view).GetValue();
auto maybe_edges = impl_.InEdges(view, edge_types, &dest_id);
-> storage::v3::Result<decltype(iter::imap(MakeEdgeAccessor, *impl_.InEdges(view)))> {
auto maybe_edges = impl_.InEdges(view, edge_types, &dest.impl_);
if (maybe_edges.HasError()) return maybe_edges.GetError();
return iter::imap(MakeEdgeAccessor, std::move(*maybe_edges));
}
auto OutEdges(storage::v3::View view, const std::vector<storage::v3::EdgeTypeId> &edge_types) const
-> storage::v3::ShardResult<decltype(iter::imap(MakeEdgeAccessor, *impl_.OutEdges(view)))> {
-> storage::v3::Result<decltype(iter::imap(MakeEdgeAccessor, *impl_.OutEdges(view)))> {
auto maybe_edges = impl_.OutEdges(view, edge_types);
if (maybe_edges.HasError()) return maybe_edges.GetError();
return iter::imap(MakeEdgeAccessor, std::move(*maybe_edges));
@@ -140,19 +178,19 @@ class VertexAccessor final {
auto OutEdges(storage::v3::View view, const std::vector<storage::v3::EdgeTypeId> &edge_types,
const VertexAccessor &dest) const
-> storage::v3::ShardResult<decltype(iter::imap(MakeEdgeAccessor, *impl_.OutEdges(view)))> {
const auto dest_id = dest.impl_.Id(view).GetValue();
auto maybe_edges = impl_.OutEdges(view, edge_types, &dest_id);
-> storage::v3::Result<decltype(iter::imap(MakeEdgeAccessor, *impl_.OutEdges(view)))> {
auto maybe_edges = impl_.OutEdges(view, edge_types, &dest.impl_);
if (maybe_edges.HasError()) return maybe_edges.GetError();
return iter::imap(MakeEdgeAccessor, std::move(*maybe_edges));
}
storage::v3::ShardResult<size_t> InDegree(storage::v3::View view) const { return impl_.InDegree(view); }
storage::v3::Result<size_t> InDegree(storage::v3::View view) const { return impl_.InDegree(view); }
storage::v3::ShardResult<size_t> OutDegree(storage::v3::View view) const { return impl_.OutDegree(view); }
storage::v3::Result<size_t> OutDegree(storage::v3::View view) const { return impl_.OutDegree(view); }
// TODO(jbajic) Fix Remove Gid
static int64_t CypherId() { return 1; }
int64_t CypherId() const { return impl_.Gid().AsInt(); }
storage::v3::Gid Gid() const noexcept { return impl_.Gid(); }
bool operator==(const VertexAccessor &v) const noexcept {
static_assert(noexcept(impl_ == v.impl_));
@@ -162,19 +200,198 @@ class VertexAccessor final {
bool operator!=(const VertexAccessor &v) const noexcept { return !(*this == v); }
};
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Wnull-dereference"
// NOLINTNEXTLINE(readability-convert-member-functions-to-static,clang-analyzer-core.NonNullParamChecker)
inline VertexAccessor EdgeAccessor::To() const { return *static_cast<VertexAccessor *>(nullptr); }
inline VertexAccessor EdgeAccessor::To() const { return VertexAccessor(impl_.ToVertex()); }
// NOLINTNEXTLINE(readability-convert-member-functions-to-static,clang-analyzer-core.NonNullParamChecker)
inline VertexAccessor EdgeAccessor::From() const { return *static_cast<VertexAccessor *>(nullptr); }
#pragma clang diagnostic pop
inline VertexAccessor EdgeAccessor::From() const { return VertexAccessor(impl_.FromVertex()); }
inline bool EdgeAccessor::IsCycle() const { return To() == From(); }
class DbAccessor final {
storage::v3::Storage::Accessor *accessor_;
class VerticesIterable final {
storage::v3::VerticesIterable iterable_;
public:
class Iterator final {
storage::v3::VerticesIterable::Iterator it_;
public:
explicit Iterator(storage::v3::VerticesIterable::Iterator it) : it_(it) {}
VertexAccessor operator*() const { return VertexAccessor(*it_); }
Iterator &operator++() {
++it_;
return *this;
}
bool operator==(const Iterator &other) const { return it_ == other.it_; }
bool operator!=(const Iterator &other) const { return !(other == *this); }
};
explicit VerticesIterable(storage::v3::VerticesIterable iterable) : iterable_(std::move(iterable)) {}
Iterator begin() { return Iterator(iterable_.begin()); }
Iterator end() { return Iterator(iterable_.end()); }
};
public:
explicit DbAccessor(storage::v3::Storage::Accessor *accessor) : accessor_(accessor) {}
std::optional<VertexAccessor> FindVertex(storage::v3::Gid gid, storage::v3::View view) {
auto maybe_vertex = accessor_->FindVertex(gid, view);
if (maybe_vertex) return VertexAccessor(*maybe_vertex);
return std::nullopt;
}
void FinalizeTransaction() { accessor_->FinalizeTransaction(); }
VerticesIterable Vertices(storage::v3::View view) { return VerticesIterable(accessor_->Vertices(view)); }
VerticesIterable Vertices(storage::v3::View view, storage::v3::LabelId label) {
return VerticesIterable(accessor_->Vertices(label, view));
}
VerticesIterable Vertices(storage::v3::View view, storage::v3::LabelId label, storage::v3::PropertyId property) {
return VerticesIterable(accessor_->Vertices(label, property, view));
}
VerticesIterable Vertices(storage::v3::View view, storage::v3::LabelId label, storage::v3::PropertyId property,
const storage::v3::PropertyValue &value) {
return VerticesIterable(accessor_->Vertices(label, property, value, view));
}
VerticesIterable Vertices(storage::v3::View view, storage::v3::LabelId label, storage::v3::PropertyId property,
const std::optional<utils::Bound<storage::v3::PropertyValue>> &lower,
const std::optional<utils::Bound<storage::v3::PropertyValue>> &upper) {
return VerticesIterable(accessor_->Vertices(label, property, lower, upper, view));
}
// TODO Remove when query modules have been fixed
[[deprecated]] VertexAccessor InsertVertex() { return VertexAccessor(accessor_->CreateVertex()); }
storage::v3::ResultSchema<VertexAccessor> InsertVertexAndValidate(
const storage::v3::LabelId primary_label, const std::vector<storage::v3::LabelId> &labels,
const std::vector<std::pair<storage::v3::PropertyId, storage::v3::PropertyValue>> &properties) {
auto maybe_vertex_acc = accessor_->CreateVertexAndValidate(primary_label, labels, properties);
if (maybe_vertex_acc.HasError()) {
return {std::move(maybe_vertex_acc.GetError())};
}
return VertexAccessor{maybe_vertex_acc.GetValue()};
}
storage::v3::Result<EdgeAccessor> InsertEdge(VertexAccessor *from, VertexAccessor *to,
const storage::v3::EdgeTypeId &edge_type) {
auto maybe_edge = accessor_->CreateEdge(&from->impl_, &to->impl_, edge_type);
if (maybe_edge.HasError()) return storage::v3::Result<EdgeAccessor>(maybe_edge.GetError());
return EdgeAccessor(*maybe_edge);
}
storage::v3::Result<std::optional<EdgeAccessor>> RemoveEdge(EdgeAccessor *edge) {
auto res = accessor_->DeleteEdge(&edge->impl_);
if (res.HasError()) {
return res.GetError();
}
const auto &value = res.GetValue();
if (!value) {
return std::optional<EdgeAccessor>{};
}
return std::make_optional<EdgeAccessor>(*value);
}
storage::v3::Result<std::optional<std::pair<VertexAccessor, std::vector<EdgeAccessor>>>> DetachRemoveVertex(
VertexAccessor *vertex_accessor) {
using ReturnType = std::pair<VertexAccessor, std::vector<EdgeAccessor>>;
auto res = accessor_->DetachDeleteVertex(&vertex_accessor->impl_);
if (res.HasError()) {
return res.GetError();
}
const auto &value = res.GetValue();
if (!value) {
return std::optional<ReturnType>{};
}
const auto &[vertex, edges] = *value;
std::vector<EdgeAccessor> deleted_edges;
deleted_edges.reserve(edges.size());
std::transform(edges.begin(), edges.end(), std::back_inserter(deleted_edges),
[](const auto &deleted_edge) { return EdgeAccessor{deleted_edge}; });
return std::make_optional<ReturnType>(vertex, std::move(deleted_edges));
}
storage::v3::Result<std::optional<VertexAccessor>> RemoveVertex(VertexAccessor *vertex_accessor) {
auto res = accessor_->DeleteVertex(&vertex_accessor->impl_);
if (res.HasError()) {
return res.GetError();
}
const auto &value = res.GetValue();
if (!value) {
return std::optional<VertexAccessor>{};
}
return {std::make_optional<VertexAccessor>(*value)};
}
storage::v3::PropertyId NameToProperty(const std::string_view name) { return accessor_->NameToProperty(name); }
storage::v3::LabelId NameToLabel(const std::string_view name) { return accessor_->NameToLabel(name); }
storage::v3::EdgeTypeId NameToEdgeType(const std::string_view name) { return accessor_->NameToEdgeType(name); }
const std::string &PropertyToName(storage::v3::PropertyId prop) const { return accessor_->PropertyToName(prop); }
const std::string &LabelToName(storage::v3::LabelId label) const { return accessor_->LabelToName(label); }
const std::string &EdgeTypeToName(storage::v3::EdgeTypeId type) const { return accessor_->EdgeTypeToName(type); }
void AdvanceCommand() { accessor_->AdvanceCommand(); }
utils::BasicResult<storage::v3::ConstraintViolation, void> Commit() { return accessor_->Commit(); }
void Abort() { accessor_->Abort(); }
bool LabelIndexExists(storage::v3::LabelId label) const { return accessor_->LabelIndexExists(label); }
bool LabelPropertyIndexExists(storage::v3::LabelId label, storage::v3::PropertyId prop) const {
return accessor_->LabelPropertyIndexExists(label, prop);
}
int64_t VerticesCount() const { return accessor_->ApproximateVertexCount(); }
int64_t VerticesCount(storage::v3::LabelId label) const { return accessor_->ApproximateVertexCount(label); }
int64_t VerticesCount(storage::v3::LabelId label, storage::v3::PropertyId property) const {
return accessor_->ApproximateVertexCount(label, property);
}
int64_t VerticesCount(storage::v3::LabelId label, storage::v3::PropertyId property,
const storage::v3::PropertyValue &value) const {
return accessor_->ApproximateVertexCount(label, property, value);
}
int64_t VerticesCount(storage::v3::LabelId label, storage::v3::PropertyId property,
const std::optional<utils::Bound<storage::v3::PropertyValue>> &lower,
const std::optional<utils::Bound<storage::v3::PropertyValue>> &upper) const {
return accessor_->ApproximateVertexCount(label, property, lower, upper);
}
storage::v3::IndicesInfo ListAllIndices() const { return accessor_->ListAllIndices(); }
storage::v3::ConstraintsInfo ListAllConstraints() const { return accessor_->ListAllConstraints(); }
const storage::v3::SchemaValidator &GetSchemaValidator() const { return accessor_->GetSchemaValidator(); }
storage::v3::SchemasInfo ListAllSchemas() const { return accessor_->ListAllSchemas(); }
};
} // namespace memgraph::query::v2

View File

@@ -13,7 +13,7 @@
#include <vector>
#include "query/v2/bindings/typed_value.hpp"
#include "query/v2/typed_value.hpp"
namespace memgraph::query::v2 {
struct DiscardValueResultStream final {

541
src/query/v2/dump.cpp Normal file
View File

@@ -0,0 +1,541 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#include "query/v2/dump.hpp"
#include <iomanip>
#include <limits>
#include <map>
#include <optional>
#include <ostream>
#include <utility>
#include <vector>
#include <fmt/format.h>
#include "query/v2/db_accessor.hpp"
#include "query/v2/exceptions.hpp"
#include "query/v2/stream.hpp"
#include "query/v2/typed_value.hpp"
#include "storage/v3/property_value.hpp"
#include "storage/v3/storage.hpp"
#include "utils/algorithm.hpp"
#include "utils/logging.hpp"
#include "utils/string.hpp"
#include "utils/temporal.hpp"
namespace memgraph::query::v2 {
namespace {
// Property that is used to make a difference among vertices. It is added to
// property set of vertices to match edges and removed after the entire graph
// is built.
const char *kInternalPropertyId = "__mg_id__";
// Label that is attached to each vertex and is used for easier creation of
// index on internal property id.
const char *kInternalVertexLabel = "__mg_vertex__";
/// A helper function that escapes label, edge type and property names.
std::string EscapeName(const std::string_view value) {
std::string out;
out.reserve(value.size() + 2);
out.append(1, '`');
for (auto c : value) {
if (c == '`') {
out.append("``");
} else {
out.append(1, c);
}
}
out.append(1, '`');
return out;
}
void DumpPreciseDouble(std::ostream *os, double value) {
// A temporary stream is used to keep precision of the original output
// stream unchanged.
std::ostringstream temp_oss;
temp_oss << std::setprecision(std::numeric_limits<double>::max_digits10) << value;
*os << temp_oss.str();
}
namespace {
void DumpDate(std::ostream &os, const storage::v3::TemporalData &value) {
utils::Date date(value.microseconds);
os << "DATE(\"" << date << "\")";
}
void DumpLocalTime(std::ostream &os, const storage::v3::TemporalData &value) {
utils::LocalTime lt(value.microseconds);
os << "LOCALTIME(\"" << lt << "\")";
}
void DumpLocalDateTime(std::ostream &os, const storage::v3::TemporalData &value) {
utils::LocalDateTime ldt(value.microseconds);
os << "LOCALDATETIME(\"" << ldt << "\")";
}
void DumpDuration(std::ostream &os, const storage::v3::TemporalData &value) {
utils::Duration dur(value.microseconds);
os << "DURATION(\"" << dur << "\")";
}
void DumpTemporalData(std::ostream &os, const storage::v3::TemporalData &value) {
switch (value.type) {
case storage::v3::TemporalType::Date: {
DumpDate(os, value);
return;
}
case storage::v3::TemporalType::LocalTime: {
DumpLocalTime(os, value);
return;
}
case storage::v3::TemporalType::LocalDateTime: {
DumpLocalDateTime(os, value);
return;
}
case storage::v3::TemporalType::Duration: {
DumpDuration(os, value);
return;
}
}
}
} // namespace
void DumpPropertyValue(std::ostream *os, const storage::v3::PropertyValue &value) {
switch (value.type()) {
case storage::v3::PropertyValue::Type::Null:
*os << "Null";
return;
case storage::v3::PropertyValue::Type::Bool:
*os << (value.ValueBool() ? "true" : "false");
return;
case storage::v3::PropertyValue::Type::String:
*os << utils::Escape(value.ValueString());
return;
case storage::v3::PropertyValue::Type::Int:
*os << value.ValueInt();
return;
case storage::v3::PropertyValue::Type::Double:
DumpPreciseDouble(os, value.ValueDouble());
return;
case storage::v3::PropertyValue::Type::List: {
*os << "[";
const auto &list = value.ValueList();
utils::PrintIterable(*os, list, ", ", [](auto &os, const auto &item) { DumpPropertyValue(&os, item); });
*os << "]";
return;
}
case storage::v3::PropertyValue::Type::Map: {
*os << "{";
const auto &map = value.ValueMap();
utils::PrintIterable(*os, map, ", ", [](auto &os, const auto &kv) {
os << EscapeName(kv.first) << ": ";
DumpPropertyValue(&os, kv.second);
});
*os << "}";
return;
}
case storage::v3::PropertyValue::Type::TemporalData: {
DumpTemporalData(*os, value.ValueTemporalData());
return;
}
}
}
void DumpProperties(std::ostream *os, query::v2::DbAccessor *dba,
const std::map<storage::v3::PropertyId, storage::v3::PropertyValue> &store,
std::optional<int64_t> property_id = std::nullopt) {
*os << "{";
if (property_id) {
*os << kInternalPropertyId << ": " << *property_id;
if (store.size() > 0) *os << ", ";
}
utils::PrintIterable(*os, store, ", ", [&dba](auto &os, const auto &kv) {
os << EscapeName(dba->PropertyToName(kv.first)) << ": ";
DumpPropertyValue(&os, kv.second);
});
*os << "}";
}
void DumpVertex(std::ostream *os, query::v2::DbAccessor *dba, const query::v2::VertexAccessor &vertex) {
*os << "CREATE (";
*os << ":" << kInternalVertexLabel;
auto maybe_labels = vertex.Labels(storage::v3::View::OLD);
if (maybe_labels.HasError()) {
switch (maybe_labels.GetError()) {
case storage::v3::Error::DELETED_OBJECT:
throw query::v2::QueryRuntimeException("Trying to get labels from a deleted node.");
case storage::v3::Error::NONEXISTENT_OBJECT:
throw query::v2::QueryRuntimeException("Trying to get labels from a node that doesn't exist.");
case storage::v3::Error::SERIALIZATION_ERROR:
case storage::v3::Error::VERTEX_HAS_EDGES:
case storage::v3::Error::PROPERTIES_DISABLED:
throw query::v2::QueryRuntimeException("Unexpected error when getting labels.");
}
}
for (const auto &label : *maybe_labels) {
*os << ":" << EscapeName(dba->LabelToName(label));
}
*os << " ";
auto maybe_props = vertex.Properties(storage::v3::View::OLD);
if (maybe_props.HasError()) {
switch (maybe_props.GetError()) {
case storage::v3::Error::DELETED_OBJECT:
throw query::v2::QueryRuntimeException("Trying to get properties from a deleted object.");
case storage::v3::Error::NONEXISTENT_OBJECT:
throw query::v2::QueryRuntimeException("Trying to get properties from a node that doesn't exist.");
case storage::v3::Error::SERIALIZATION_ERROR:
case storage::v3::Error::VERTEX_HAS_EDGES:
case storage::v3::Error::PROPERTIES_DISABLED:
throw query::v2::QueryRuntimeException("Unexpected error when getting properties.");
}
}
DumpProperties(os, dba, *maybe_props, vertex.CypherId());
*os << ");";
}
void DumpEdge(std::ostream *os, query::v2::DbAccessor *dba, const query::v2::EdgeAccessor &edge) {
*os << "MATCH ";
*os << "(u:" << kInternalVertexLabel << "), ";
*os << "(v:" << kInternalVertexLabel << ")";
*os << " WHERE ";
*os << "u." << kInternalPropertyId << " = " << edge.From().CypherId();
*os << " AND ";
*os << "v." << kInternalPropertyId << " = " << edge.To().CypherId() << " ";
*os << "CREATE (u)-[";
*os << ":" << EscapeName(dba->EdgeTypeToName(edge.EdgeType()));
auto maybe_props = edge.Properties(storage::v3::View::OLD);
if (maybe_props.HasError()) {
switch (maybe_props.GetError()) {
case storage::v3::Error::DELETED_OBJECT:
throw query::v2::QueryRuntimeException("Trying to get properties from a deleted object.");
case storage::v3::Error::NONEXISTENT_OBJECT:
throw query::v2::QueryRuntimeException("Trying to get properties from an edge that doesn't exist.");
case storage::v3::Error::SERIALIZATION_ERROR:
case storage::v3::Error::VERTEX_HAS_EDGES:
case storage::v3::Error::PROPERTIES_DISABLED:
throw query::v2::QueryRuntimeException("Unexpected error when getting properties.");
}
}
if (maybe_props->size() > 0) {
*os << " ";
DumpProperties(os, dba, *maybe_props);
}
*os << "]->(v);";
}
void DumpLabelIndex(std::ostream *os, query::v2::DbAccessor *dba, const storage::v3::LabelId label) {
*os << "CREATE INDEX ON :" << EscapeName(dba->LabelToName(label)) << ";";
}
void DumpLabelPropertyIndex(std::ostream *os, query::v2::DbAccessor *dba, storage::v3::LabelId label,
storage::v3::PropertyId property) {
*os << "CREATE INDEX ON :" << EscapeName(dba->LabelToName(label)) << "(" << EscapeName(dba->PropertyToName(property))
<< ");";
}
void DumpExistenceConstraint(std::ostream *os, query::v2::DbAccessor *dba, storage::v3::LabelId label,
storage::v3::PropertyId property) {
*os << "CREATE CONSTRAINT ON (u:" << EscapeName(dba->LabelToName(label)) << ") ASSERT EXISTS (u."
<< EscapeName(dba->PropertyToName(property)) << ");";
}
void DumpUniqueConstraint(std::ostream *os, query::v2::DbAccessor *dba, storage::v3::LabelId label,
const std::set<storage::v3::PropertyId> &properties) {
*os << "CREATE CONSTRAINT ON (u:" << EscapeName(dba->LabelToName(label)) << ") ASSERT ";
utils::PrintIterable(*os, properties, ", ", [&dba](auto &stream, const auto &property) {
stream << "u." << EscapeName(dba->PropertyToName(property));
});
*os << " IS UNIQUE;";
}
} // namespace
PullPlanDump::PullPlanDump(DbAccessor *dba)
: dba_(dba),
vertices_iterable_(dba->Vertices(storage::v3::View::OLD)),
pull_chunks_{// Dump all label indices
CreateLabelIndicesPullChunk(),
// Dump all label property indices
CreateLabelPropertyIndicesPullChunk(),
// Dump all existence constraints
CreateExistenceConstraintsPullChunk(),
// Dump all unique constraints
CreateUniqueConstraintsPullChunk(),
// Create internal index for faster edge creation
CreateInternalIndexPullChunk(),
// Dump all vertices
CreateVertexPullChunk(),
// Dump all edges
CreateEdgePullChunk(),
// Drop the internal index
CreateDropInternalIndexPullChunk(),
// Internal index cleanup
CreateInternalIndexCleanupPullChunk()} {}
bool PullPlanDump::Pull(AnyStream *stream, std::optional<int> n) {
// Iterate all functions that stream some results.
// Each function should return number of results it streamed after it
// finishes. If the function did not finish streaming all the results,
// std::nullopt should be returned because n results have already been sent.
while (current_chunk_index_ < pull_chunks_.size() && (!n || *n > 0)) {
const auto maybe_streamed_count = pull_chunks_[current_chunk_index_](stream, n);
if (!maybe_streamed_count) {
// n wasn't large enough to stream all the results from the current chunk
break;
}
if (n) {
// chunk finished streaming its results
// subtract number of results streamed in current pull
// so we know how many results we need to stream from future
// chunks.
*n -= *maybe_streamed_count;
}
++current_chunk_index_;
}
return current_chunk_index_ == pull_chunks_.size();
}
PullPlanDump::PullChunk PullPlanDump::CreateLabelIndicesPullChunk() {
// Dump all label indices
return [this, global_index = 0U](AnyStream *stream, std::optional<int> n) mutable -> std::optional<size_t> {
// Delay the construction of indices vectors
if (!indices_info_) {
indices_info_.emplace(dba_->ListAllIndices());
}
const auto &label = indices_info_->label;
size_t local_counter = 0;
while (global_index < label.size() && (!n || local_counter < *n)) {
std::ostringstream os;
DumpLabelIndex(&os, dba_, label[global_index]);
stream->Result({TypedValue(os.str())});
++global_index;
++local_counter;
}
if (global_index == label.size()) {
return local_counter;
}
return std::nullopt;
};
}
PullPlanDump::PullChunk PullPlanDump::CreateLabelPropertyIndicesPullChunk() {
return [this, global_index = 0U](AnyStream *stream, std::optional<int> n) mutable -> std::optional<size_t> {
// Delay the construction of indices vectors
if (!indices_info_) {
indices_info_.emplace(dba_->ListAllIndices());
}
const auto &label_property = indices_info_->label_property;
size_t local_counter = 0;
while (global_index < label_property.size() && (!n || local_counter < *n)) {
std::ostringstream os;
const auto &label_property_index = label_property[global_index];
DumpLabelPropertyIndex(&os, dba_, label_property_index.first, label_property_index.second);
stream->Result({TypedValue(os.str())});
++global_index;
++local_counter;
}
if (global_index == label_property.size()) {
return local_counter;
}
return std::nullopt;
};
}
PullPlanDump::PullChunk PullPlanDump::CreateExistenceConstraintsPullChunk() {
return [this, global_index = 0U](AnyStream *stream, std::optional<int> n) mutable -> std::optional<size_t> {
// Delay the construction of constraint vectors
if (!constraints_info_) {
constraints_info_.emplace(dba_->ListAllConstraints());
}
const auto &existence = constraints_info_->existence;
size_t local_counter = 0;
while (global_index < existence.size() && (!n || local_counter < *n)) {
const auto &constraint = existence[global_index];
std::ostringstream os;
DumpExistenceConstraint(&os, dba_, constraint.first, constraint.second);
stream->Result({TypedValue(os.str())});
++global_index;
++local_counter;
}
if (global_index == existence.size()) {
return local_counter;
}
return std::nullopt;
};
}
PullPlanDump::PullChunk PullPlanDump::CreateUniqueConstraintsPullChunk() {
return [this, global_index = 0U](AnyStream *stream, std::optional<int> n) mutable -> std::optional<size_t> {
// Delay the construction of constraint vectors
if (!constraints_info_) {
constraints_info_.emplace(dba_->ListAllConstraints());
}
const auto &unique = constraints_info_->unique;
size_t local_counter = 0;
while (global_index < unique.size() && (!n || local_counter < *n)) {
const auto &constraint = unique[global_index];
std::ostringstream os;
DumpUniqueConstraint(&os, dba_, constraint.first, constraint.second);
stream->Result({TypedValue(os.str())});
++global_index;
++local_counter;
}
if (global_index == unique.size()) {
return local_counter;
}
return std::nullopt;
};
}
PullPlanDump::PullChunk PullPlanDump::CreateInternalIndexPullChunk() {
return [this](AnyStream *stream, std::optional<int>) mutable -> std::optional<size_t> {
if (vertices_iterable_.begin() != vertices_iterable_.end()) {
std::ostringstream os;
os << "CREATE INDEX ON :" << kInternalVertexLabel << "(" << kInternalPropertyId << ");";
stream->Result({TypedValue(os.str())});
internal_index_created_ = true;
return 1;
}
return 0;
};
}
PullPlanDump::PullChunk PullPlanDump::CreateVertexPullChunk() {
return [this, maybe_current_iter = std::optional<VertexAccessorIterableIterator>{}](
AnyStream *stream, std::optional<int> n) mutable -> std::optional<size_t> {
// Delay the call of begin() function
// If multiple begins are called before an iteration,
// one iteration will make the rest of iterators be in undefined
// states.
if (!maybe_current_iter) {
maybe_current_iter.emplace(vertices_iterable_.begin());
}
auto &current_iter{*maybe_current_iter};
size_t local_counter = 0;
while (current_iter != vertices_iterable_.end() && (!n || local_counter < *n)) {
std::ostringstream os;
DumpVertex(&os, dba_, *current_iter);
stream->Result({TypedValue(os.str())});
++local_counter;
++current_iter;
}
if (current_iter == vertices_iterable_.end()) {
return local_counter;
}
return std::nullopt;
};
}
PullPlanDump::PullChunk PullPlanDump::CreateEdgePullChunk() {
return [this, maybe_current_vertex_iter = std::optional<VertexAccessorIterableIterator>{},
// we need to save the iterable which contains list of accessor so
// our saved iterator is valid in the next run
maybe_edge_iterable = std::shared_ptr<EdgeAccessorIterable>{nullptr},
maybe_current_edge_iter = std::optional<EdgeAccessorIterableIterator>{}](
AnyStream *stream, std::optional<int> n) mutable -> std::optional<size_t> {
// Delay the call of begin() function
// If multiple begins are called before an iteration,
// one iteration will make the rest of iterators be in undefined
// states.
if (!maybe_current_vertex_iter) {
maybe_current_vertex_iter.emplace(vertices_iterable_.begin());
}
auto &current_vertex_iter{*maybe_current_vertex_iter};
size_t local_counter = 0U;
for (; current_vertex_iter != vertices_iterable_.end() && (!n || local_counter < *n); ++current_vertex_iter) {
const auto &vertex = *current_vertex_iter;
// If we have a saved iterable from a previous pull
// we need to use the same iterable
if (!maybe_edge_iterable) {
maybe_edge_iterable = std::make_shared<EdgeAccessorIterable>(vertex.OutEdges(storage::v3::View::OLD));
}
auto &maybe_edges = *maybe_edge_iterable;
MG_ASSERT(maybe_edges.HasValue(), "Invalid database state!");
auto current_edge_iter = maybe_current_edge_iter ? *maybe_current_edge_iter : maybe_edges->begin();
for (; current_edge_iter != maybe_edges->end() && (!n || local_counter < *n); ++current_edge_iter) {
std::ostringstream os;
DumpEdge(&os, dba_, *current_edge_iter);
stream->Result({TypedValue(os.str())});
++local_counter;
}
if (current_edge_iter != maybe_edges->end()) {
maybe_current_edge_iter.emplace(current_edge_iter);
return std::nullopt;
}
maybe_current_edge_iter = std::nullopt;
maybe_edge_iterable = nullptr;
}
if (current_vertex_iter == vertices_iterable_.end()) {
return local_counter;
}
return std::nullopt;
};
}
PullPlanDump::PullChunk PullPlanDump::CreateDropInternalIndexPullChunk() {
return [this](AnyStream *stream, std::optional<int>) {
if (internal_index_created_) {
std::ostringstream os;
os << "DROP INDEX ON :" << kInternalVertexLabel << "(" << kInternalPropertyId << ");";
stream->Result({TypedValue(os.str())});
return 1;
}
return 0;
};
}
PullPlanDump::PullChunk PullPlanDump::CreateInternalIndexCleanupPullChunk() {
return [this](AnyStream *stream, std::optional<int>) {
if (internal_index_created_) {
std::ostringstream os;
os << "MATCH (u) REMOVE u:" << kInternalVertexLabel << ", u." << kInternalPropertyId << ";";
stream->Result({TypedValue(os.str())});
return 1;
}
return 0;
};
}
void DumpDatabaseToCypherQueries(query::v2::DbAccessor *dba, AnyStream *stream) { PullPlanDump(dba).Pull(stream, {}); }
} // namespace memgraph::query::v2

66
src/query/v2/dump.hpp Normal file
View File

@@ -0,0 +1,66 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <ostream>
#include "query/v2/db_accessor.hpp"
#include "query/v2/stream.hpp"
#include "storage/v3/storage.hpp"
namespace memgraph::query::v2 {
void DumpDatabaseToCypherQueries(query::v2::DbAccessor *dba, AnyStream *stream);
struct PullPlanDump {
explicit PullPlanDump(query::v2::DbAccessor *dba);
/// Pull the dump results lazily
/// @return true if all results were returned, false otherwise
bool Pull(AnyStream *stream, std::optional<int> n);
private:
query::v2::DbAccessor *dba_ = nullptr;
std::optional<storage::v3::IndicesInfo> indices_info_ = std::nullopt;
std::optional<storage::v3::ConstraintsInfo> constraints_info_ = std::nullopt;
using VertexAccessorIterable = decltype(std::declval<query::v2::DbAccessor>().Vertices(storage::v3::View::OLD));
using VertexAccessorIterableIterator = decltype(std::declval<VertexAccessorIterable>().begin());
using EdgeAccessorIterable = decltype(std::declval<VertexAccessor>().OutEdges(storage::v3::View::OLD));
using EdgeAccessorIterableIterator = decltype(std::declval<EdgeAccessorIterable>().GetValue().begin());
VertexAccessorIterable vertices_iterable_;
bool internal_index_created_ = false;
size_t current_chunk_index_ = 0;
using PullChunk = std::function<std::optional<size_t>(AnyStream *stream, std::optional<int> n)>;
// We define every part of the dump query in a self contained function.
// Each functions is responsible of keeping track of its execution status.
// If a function did finish its execution, it should return number of results
// it streamed so we know how many rows should be pulled from the next
// function, otherwise std::nullopt is returned.
std::vector<PullChunk> pull_chunks_;
PullChunk CreateLabelIndicesPullChunk();
PullChunk CreateLabelPropertyIndicesPullChunk();
PullChunk CreateExistenceConstraintsPullChunk();
PullChunk CreateUniqueConstraintsPullChunk();
PullChunk CreateInternalIndexPullChunk();
PullChunk CreateVertexPullChunk();
PullChunk CreateEdgePullChunk();
PullChunk CreateDropInternalIndexPullChunk();
PullChunk CreateInternalIndexCleanupPullChunk();
};
} // namespace memgraph::query::v2

View File

@@ -224,4 +224,12 @@ class VersionInfoInMulticommandTxException : public QueryException {
: QueryException("Version info query not allowed in multicommand transactions.") {}
};
/**
* An exception for an illegal operation that violates schema
*/
class SchemaViolationException : public QueryRuntimeException {
public:
using QueryRuntimeException::QueryRuntimeException;
};
} // namespace memgraph::query::v2

View File

@@ -17,16 +17,12 @@
#include <variant>
#include <vector>
#include "query/v2/bindings/ast_visitor.hpp"
#include "common/types.hpp"
#include "query/v2/bindings/symbol.hpp"
#include "functions/awesome_memgraph_functions.hpp"
#include "query/v2/bindings/typed_value.hpp"
#include "query/v2/db_accessor.hpp"
#include "query/v2/path.hpp"
#include "query/v2/request_router.hpp"
#include "query/v2/frontend/ast/ast_visitor.hpp"
#include "query/v2/frontend/semantic/symbol.hpp"
#include "query/v2/interpret/awesome_memgraph_functions.hpp"
#include "query/v2/typed_value.hpp"
#include "storage/v3/property_value.hpp"
#include "utils/typeinfo.hpp"
#include "query/v2/conversions.hpp"
cpp<#
@@ -634,7 +630,7 @@ cpp<#
(:clone))
(lcp:define-class primitive-literal (base-literal)
((value "TypedValue" :scope :public)
((value "::storage::v3::PropertyValue" :scope :public)
(token-position :int32_t :scope :public :initval -1
:documentation "This field contains token position of literal used to create PrimitiveLiteral object. If PrimitiveLiteral object is not created from query, leave its value at -1."))
(:public
@@ -838,15 +834,13 @@ cpp<#
:slk-load (slk-load-ast-vector "Expression"))
(function-name "std::string" :scope :public)
(function "std::function<TypedValue(const TypedValue *, int64_t,
const functions::FunctionContext<RequestRouterInterface> &)>"
const FunctionContext &)>"
:scope :public
:dont-save t
:clone :copy
:slk-load (lambda (member)
#>cpp
self->${member} = functions::NameToFunction<TypedValue,
functions::FunctionContext<RequestRouterInterface>,
functions::QueryEngineTag, decltype(ValueToTypedValueFunctor)>(self->function_name_);
self->${member} = query::v2::NameToFunction(self->function_name_);
cpp<#)))
(:public
#>cpp
@@ -869,8 +863,7 @@ cpp<#
const std::vector<Expression *> &arguments)
: arguments_(arguments),
function_name_(function_name),
function_(functions::NameToFunction<TypedValue, functions::FunctionContext<RequestRouterInterface>,
functions::QueryEngineTag, decltype(ValueToTypedValueFunctor)>(function_name_)) {
function_(NameToFunction(function_name_)) {
if (!function_) {
throw SemanticException("Function '{}' doesn't exist.", function_name);
}

View File

@@ -13,7 +13,7 @@
#include "utils/visitor.hpp"
namespace MG_INJECTED_NAMESPACE_NAME {
namespace memgraph::query::v2 {
// Forward declares for Tree visitors.
class CypherQuery;
@@ -96,7 +96,7 @@ class VersionQuery;
class Foreach;
class SchemaQuery;
using TreeCompositeVisitor = memgraph::utils::CompositeVisitor<
using TreeCompositeVisitor = utils::CompositeVisitor<
SingleQuery, CypherUnion, NamedExpression, OrOperator, XorOperator, AndOperator, NotOperator, AdditionOperator,
SubtractionOperator, MultiplicationOperator, DivisionOperator, ModOperator, NotEqualOperator, EqualOperator,
LessOperator, GreaterOperator, LessEqualOperator, GreaterEqualOperator, InListOperator, SubscriptOperator,
@@ -105,7 +105,7 @@ using TreeCompositeVisitor = memgraph::utils::CompositeVisitor<
Create, Match, Return, With, Pattern, NodeAtom, EdgeAtom, Delete, Where, SetProperty, SetProperties, SetLabels,
RemoveProperty, RemoveLabels, Merge, Unwind, RegexMatch, LoadCsv, Foreach>;
using TreeLeafVisitor = memgraph::utils::LeafVisitor<Identifier, PrimitiveLiteral, ParameterLookup>;
using TreeLeafVisitor = utils::LeafVisitor<Identifier, PrimitiveLiteral, ParameterLookup>;
class HierarchicalTreeVisitor : public TreeCompositeVisitor, public TreeLeafVisitor {
public:
@@ -117,7 +117,7 @@ class HierarchicalTreeVisitor : public TreeCompositeVisitor, public TreeLeafVisi
template <class TResult>
class ExpressionVisitor
: public memgraph::utils::Visitor<
: public utils::Visitor<
TResult, NamedExpression, OrOperator, XorOperator, AndOperator, NotOperator, AdditionOperator,
SubtractionOperator, MultiplicationOperator, DivisionOperator, ModOperator, NotEqualOperator, EqualOperator,
LessOperator, GreaterOperator, LessEqualOperator, GreaterEqualOperator, InListOperator, SubscriptOperator,
@@ -126,10 +126,9 @@ class ExpressionVisitor
None, ParameterLookup, Identifier, PrimitiveLiteral, RegexMatch> {};
template <class TResult>
class QueryVisitor
: public memgraph::utils::Visitor<TResult, CypherQuery, ExplainQuery, ProfileQuery, IndexQuery, AuthQuery,
InfoQuery, ConstraintQuery, DumpQuery, ReplicationQuery, LockPathQuery,
FreeMemoryQuery, TriggerQuery, IsolationLevelQuery, CreateSnapshotQuery,
StreamQuery, SettingQuery, VersionQuery, SchemaQuery> {};
class QueryVisitor : public utils::Visitor<TResult, CypherQuery, ExplainQuery, ProfileQuery, IndexQuery, AuthQuery,
InfoQuery, ConstraintQuery, DumpQuery, ReplicationQuery, LockPathQuery,
FreeMemoryQuery, TriggerQuery, IsolationLevelQuery, CreateSnapshotQuery,
StreamQuery, SettingQuery, VersionQuery, SchemaQuery> {};
} // namespace MG_INJECTED_NAMESPACE_NAME
} // namespace memgraph::query::v2

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,921 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#pragma once
#include <string>
#include <unordered_set>
#include <utility>
#include <antlr4-runtime.h>
#include "query/v2/frontend/ast/ast.hpp"
#include "query/v2/frontend/opencypher/generated/MemgraphCypherBaseVisitor.h"
#include "utils/exceptions.hpp"
#include "utils/logging.hpp"
namespace memgraph::query::v2::frontend {
using antlropencypher::MemgraphCypher;
struct ParsingContext {
bool is_query_cached = false;
};
class CypherMainVisitor : public antlropencypher::MemgraphCypherBaseVisitor {
public:
explicit CypherMainVisitor(ParsingContext context, AstStorage *storage) : context_(context), storage_(storage) {}
private:
Expression *CreateBinaryOperatorByToken(size_t token, Expression *e1, Expression *e2) {
switch (token) {
case MemgraphCypher::OR:
return storage_->Create<OrOperator>(e1, e2);
case MemgraphCypher::XOR:
return storage_->Create<XorOperator>(e1, e2);
case MemgraphCypher::AND:
return storage_->Create<AndOperator>(e1, e2);
case MemgraphCypher::PLUS:
return storage_->Create<AdditionOperator>(e1, e2);
case MemgraphCypher::MINUS:
return storage_->Create<SubtractionOperator>(e1, e2);
case MemgraphCypher::ASTERISK:
return storage_->Create<MultiplicationOperator>(e1, e2);
case MemgraphCypher::SLASH:
return storage_->Create<DivisionOperator>(e1, e2);
case MemgraphCypher::PERCENT:
return storage_->Create<ModOperator>(e1, e2);
case MemgraphCypher::EQ:
return storage_->Create<EqualOperator>(e1, e2);
case MemgraphCypher::NEQ1:
case MemgraphCypher::NEQ2:
return storage_->Create<NotEqualOperator>(e1, e2);
case MemgraphCypher::LT:
return storage_->Create<LessOperator>(e1, e2);
case MemgraphCypher::GT:
return storage_->Create<GreaterOperator>(e1, e2);
case MemgraphCypher::LTE:
return storage_->Create<LessEqualOperator>(e1, e2);
case MemgraphCypher::GTE:
return storage_->Create<GreaterEqualOperator>(e1, e2);
default:
throw utils::NotYetImplemented("binary operator");
}
}
Expression *CreateUnaryOperatorByToken(size_t token, Expression *e) {
switch (token) {
case MemgraphCypher::NOT:
return storage_->Create<NotOperator>(e);
case MemgraphCypher::PLUS:
return storage_->Create<UnaryPlusOperator>(e);
case MemgraphCypher::MINUS:
return storage_->Create<UnaryMinusOperator>(e);
default:
throw utils::NotYetImplemented("unary operator");
}
}
auto ExtractOperators(std::vector<antlr4::tree::ParseTree *> &all_children,
const std::vector<size_t> &allowed_operators) {
std::vector<size_t> operators;
for (auto *child : all_children) {
antlr4::tree::TerminalNode *operator_node = nullptr;
if ((operator_node = dynamic_cast<antlr4::tree::TerminalNode *>(child))) {
if (std::find(allowed_operators.begin(), allowed_operators.end(), operator_node->getSymbol()->getType()) !=
allowed_operators.end()) {
operators.push_back(operator_node->getSymbol()->getType());
}
}
}
return operators;
}
/**
* Convert opencypher's n-ary production to ast binary operators.
*
* @param _expressions Subexpressions of child for which we construct ast
* operators, for example expression6 if we want to create ast nodes for
* expression7.
*/
template <typename TExpression>
Expression *LeftAssociativeOperatorExpression(std::vector<TExpression *> _expressions,
std::vector<antlr4::tree::ParseTree *> all_children,
const std::vector<size_t> &allowed_operators) {
DMG_ASSERT(_expressions.size(), "can't happen");
std::vector<Expression *> expressions;
auto operators = ExtractOperators(all_children, allowed_operators);
for (auto *expression : _expressions) {
expressions.push_back(std::any_cast<Expression *>(expression->accept(this)));
}
Expression *first_operand = expressions[0];
for (int i = 1; i < (int)expressions.size(); ++i) {
first_operand = CreateBinaryOperatorByToken(operators[i - 1], first_operand, expressions[i]);
}
return first_operand;
}
template <typename TExpression>
Expression *PrefixUnaryOperator(TExpression *_expression, std::vector<antlr4::tree::ParseTree *> all_children,
const std::vector<size_t> &allowed_operators) {
DMG_ASSERT(_expression, "can't happen");
auto operators = ExtractOperators(all_children, allowed_operators);
Expression *expression = std::any_cast<Expression *>(_expression->accept(this));
for (int i = (int)operators.size() - 1; i >= 0; --i) {
expression = CreateUnaryOperatorByToken(operators[i], expression);
}
return expression;
}
/**
* @return CypherQuery*
*/
antlrcpp::Any visitCypherQuery(MemgraphCypher::CypherQueryContext *ctx) override;
/**
* @return IndexQuery*
*/
antlrcpp::Any visitIndexQuery(MemgraphCypher::IndexQueryContext *ctx) override;
/**
* @return ExplainQuery*
*/
antlrcpp::Any visitExplainQuery(MemgraphCypher::ExplainQueryContext *ctx) override;
/**
* @return ProfileQuery*
*/
antlrcpp::Any visitProfileQuery(MemgraphCypher::ProfileQueryContext *ctx) override;
/**
* @return InfoQuery*
*/
antlrcpp::Any visitInfoQuery(MemgraphCypher::InfoQueryContext *ctx) override;
/**
* @return Constraint
*/
antlrcpp::Any visitConstraint(MemgraphCypher::ConstraintContext *ctx) override;
/**
* @return ConstraintQuery*
*/
antlrcpp::Any visitConstraintQuery(MemgraphCypher::ConstraintQueryContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitAuthQuery(MemgraphCypher::AuthQueryContext *ctx) override;
/**
* @return DumpQuery*
*/
antlrcpp::Any visitDumpQuery(MemgraphCypher::DumpQueryContext *ctx) override;
/**
* @return ReplicationQuery*
*/
antlrcpp::Any visitReplicationQuery(MemgraphCypher::ReplicationQueryContext *ctx) override;
/**
* @return ReplicationQuery*
*/
antlrcpp::Any visitSetReplicationRole(MemgraphCypher::SetReplicationRoleContext *ctx) override;
/**
* @return ReplicationQuery*
*/
antlrcpp::Any visitShowReplicationRole(MemgraphCypher::ShowReplicationRoleContext *ctx) override;
/**
* @return ReplicationQuery*
*/
antlrcpp::Any visitRegisterReplica(MemgraphCypher::RegisterReplicaContext *ctx) override;
/**
* @return ReplicationQuery*
*/
antlrcpp::Any visitDropReplica(MemgraphCypher::DropReplicaContext *ctx) override;
/**
* @return ReplicationQuery*
*/
antlrcpp::Any visitShowReplicas(MemgraphCypher::ShowReplicasContext *ctx) override;
/**
* @return LockPathQuery*
*/
antlrcpp::Any visitLockPathQuery(MemgraphCypher::LockPathQueryContext *ctx) override;
/**
* @return LoadCsvQuery*
*/
antlrcpp::Any visitLoadCsv(MemgraphCypher::LoadCsvContext *ctx) override;
/**
* @return FreeMemoryQuery*
*/
antlrcpp::Any visitFreeMemoryQuery(MemgraphCypher::FreeMemoryQueryContext *ctx) override;
/**
* @return TriggerQuery*
*/
antlrcpp::Any visitTriggerQuery(MemgraphCypher::TriggerQueryContext *ctx) override;
/**
* @return CreateTrigger*
*/
antlrcpp::Any visitCreateTrigger(MemgraphCypher::CreateTriggerContext *ctx) override;
/**
* @return DropTrigger*
*/
antlrcpp::Any visitDropTrigger(MemgraphCypher::DropTriggerContext *ctx) override;
/**
* @return ShowTriggers*
*/
antlrcpp::Any visitShowTriggers(MemgraphCypher::ShowTriggersContext *ctx) override;
/**
* @return IsolationLevelQuery*
*/
antlrcpp::Any visitIsolationLevelQuery(MemgraphCypher::IsolationLevelQueryContext *ctx) override;
/**
* @return CreateSnapshotQuery*
*/
antlrcpp::Any visitCreateSnapshotQuery(MemgraphCypher::CreateSnapshotQueryContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitStreamQuery(MemgraphCypher::StreamQueryContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitCreateStream(MemgraphCypher::CreateStreamContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitConfigKeyValuePair(MemgraphCypher::ConfigKeyValuePairContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitConfigMap(MemgraphCypher::ConfigMapContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitKafkaCreateStream(MemgraphCypher::KafkaCreateStreamContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitKafkaCreateStreamConfig(MemgraphCypher::KafkaCreateStreamConfigContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitPulsarCreateStreamConfig(MemgraphCypher::PulsarCreateStreamConfigContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitPulsarCreateStream(MemgraphCypher::PulsarCreateStreamContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitCommonCreateStreamConfig(MemgraphCypher::CommonCreateStreamConfigContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitDropStream(MemgraphCypher::DropStreamContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitStartStream(MemgraphCypher::StartStreamContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitStartAllStreams(MemgraphCypher::StartAllStreamsContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitStopStream(MemgraphCypher::StopStreamContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitStopAllStreams(MemgraphCypher::StopAllStreamsContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitShowStreams(MemgraphCypher::ShowStreamsContext *ctx) override;
/**
* @return StreamQuery*
*/
antlrcpp::Any visitCheckStream(MemgraphCypher::CheckStreamContext *ctx) override;
/**
* @return SettingQuery*
*/
antlrcpp::Any visitSettingQuery(MemgraphCypher::SettingQueryContext *ctx) override;
/**
* @return SetSetting*
*/
antlrcpp::Any visitSetSetting(MemgraphCypher::SetSettingContext *ctx) override;
/**
* @return ShowSetting*
*/
antlrcpp::Any visitShowSetting(MemgraphCypher::ShowSettingContext *ctx) override;
/**
* @return ShowSettings*
*/
antlrcpp::Any visitShowSettings(MemgraphCypher::ShowSettingsContext *ctx) override;
/**
* @return VersionQuery*
*/
antlrcpp::Any visitVersionQuery(MemgraphCypher::VersionQueryContext *ctx) override;
/**
* @return CypherUnion*
*/
antlrcpp::Any visitCypherUnion(MemgraphCypher::CypherUnionContext *ctx) override;
/**
* @return SingleQuery*
*/
antlrcpp::Any visitSingleQuery(MemgraphCypher::SingleQueryContext *ctx) override;
/**
* @return Clause* or vector<Clause*>!!!
*/
antlrcpp::Any visitClause(MemgraphCypher::ClauseContext *ctx) override;
/**
* @return Match*
*/
antlrcpp::Any visitCypherMatch(MemgraphCypher::CypherMatchContext *ctx) override;
/**
* @return Create*
*/
antlrcpp::Any visitCreate(MemgraphCypher::CreateContext *ctx) override;
/**
* @return CallProcedure*
*/
antlrcpp::Any visitCallProcedure(MemgraphCypher::CallProcedureContext *ctx) override;
/**
* @return std::string
*/
antlrcpp::Any visitUserOrRoleName(MemgraphCypher::UserOrRoleNameContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitCreateRole(MemgraphCypher::CreateRoleContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitDropRole(MemgraphCypher::DropRoleContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitShowRoles(MemgraphCypher::ShowRolesContext *ctx) override;
/**
* @return IndexQuery*
*/
antlrcpp::Any visitCreateIndex(MemgraphCypher::CreateIndexContext *ctx) override;
/**
* @return DropIndex*
*/
antlrcpp::Any visitDropIndex(MemgraphCypher::DropIndexContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitCreateUser(MemgraphCypher::CreateUserContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitSetPassword(MemgraphCypher::SetPasswordContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitDropUser(MemgraphCypher::DropUserContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitShowUsers(MemgraphCypher::ShowUsersContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitSetRole(MemgraphCypher::SetRoleContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitClearRole(MemgraphCypher::ClearRoleContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitGrantPrivilege(MemgraphCypher::GrantPrivilegeContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitDenyPrivilege(MemgraphCypher::DenyPrivilegeContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitRevokePrivilege(MemgraphCypher::RevokePrivilegeContext *ctx) override;
/**
* @return AuthQuery::Privilege
*/
antlrcpp::Any visitPrivilege(MemgraphCypher::PrivilegeContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitShowPrivileges(MemgraphCypher::ShowPrivilegesContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitShowRoleForUser(MemgraphCypher::ShowRoleForUserContext *ctx) override;
/**
* @return AuthQuery*
*/
antlrcpp::Any visitShowUsersForRole(MemgraphCypher::ShowUsersForRoleContext *ctx) override;
/**
* @return Return*
*/
antlrcpp::Any visitCypherReturn(MemgraphCypher::CypherReturnContext *ctx) override;
/**
* @return Return*
*/
antlrcpp::Any visitReturnBody(MemgraphCypher::ReturnBodyContext *ctx) override;
/**
* @return pair<bool, vector<NamedExpression*>> first member is true if
* asterisk was found in return
* expressions.
*/
antlrcpp::Any visitReturnItems(MemgraphCypher::ReturnItemsContext *ctx) override;
/**
* @return vector<NamedExpression*>
*/
antlrcpp::Any visitReturnItem(MemgraphCypher::ReturnItemContext *ctx) override;
/**
* @return vector<SortItem>
*/
antlrcpp::Any visitOrder(MemgraphCypher::OrderContext *ctx) override;
/**
* @return SortItem
*/
antlrcpp::Any visitSortItem(MemgraphCypher::SortItemContext *ctx) override;
/**
* @return NodeAtom*
*/
antlrcpp::Any visitNodePattern(MemgraphCypher::NodePatternContext *ctx) override;
/**
* @return vector<LabelIx>
*/
antlrcpp::Any visitNodeLabels(MemgraphCypher::NodeLabelsContext *ctx) override;
/**
* @return unordered_map<PropertyIx, Expression*>
*/
antlrcpp::Any visitProperties(MemgraphCypher::PropertiesContext *ctx) override;
/**
* @return map<std::string, Expression*>
*/
antlrcpp::Any visitMapLiteral(MemgraphCypher::MapLiteralContext *ctx) override;
/**
* @return vector<Expression*>
*/
antlrcpp::Any visitListLiteral(MemgraphCypher::ListLiteralContext *ctx) override;
/**
* @return PropertyIx
*/
antlrcpp::Any visitPropertyKeyName(MemgraphCypher::PropertyKeyNameContext *ctx) override;
/**
* @return string
*/
antlrcpp::Any visitSymbolicName(MemgraphCypher::SymbolicNameContext *ctx) override;
/**
* @return vector<Pattern*>
*/
antlrcpp::Any visitPattern(MemgraphCypher::PatternContext *ctx) override;
/**
* @return Pattern*
*/
antlrcpp::Any visitPatternPart(MemgraphCypher::PatternPartContext *ctx) override;
/**
* @return Pattern*
*/
antlrcpp::Any visitPatternElement(MemgraphCypher::PatternElementContext *ctx) override;
/**
* @return vector<pair<EdgeAtom*, NodeAtom*>>
*/
antlrcpp::Any visitPatternElementChain(MemgraphCypher::PatternElementChainContext *ctx) override;
/**
*@return EdgeAtom*
*/
antlrcpp::Any visitRelationshipPattern(MemgraphCypher::RelationshipPatternContext *ctx) override;
/**
* This should never be called. Everything is done directly in
* visitRelationshipPattern.
*/
antlrcpp::Any visitRelationshipDetail(MemgraphCypher::RelationshipDetailContext *ctx) override;
/**
* This should never be called. Everything is done directly in
* visitRelationshipPattern.
*/
antlrcpp::Any visitRelationshipLambda(MemgraphCypher::RelationshipLambdaContext *ctx) override;
/**
* @return vector<EdgeTypeIx>
*/
antlrcpp::Any visitRelationshipTypes(MemgraphCypher::RelationshipTypesContext *ctx) override;
/**
* @return std::tuple<EdgeAtom::Type, int64_t, int64_t>.
*/
antlrcpp::Any visitVariableExpansion(MemgraphCypher::VariableExpansionContext *ctx) override;
/**
* Top level expression, does nothing.
*
* @return Expression*
*/
antlrcpp::Any visitExpression(MemgraphCypher::ExpressionContext *ctx) override;
/**
* OR.
*
* @return Expression*
*/
antlrcpp::Any visitExpression12(MemgraphCypher::Expression12Context *ctx) override;
/**
* XOR.
*
* @return Expression*
*/
antlrcpp::Any visitExpression11(MemgraphCypher::Expression11Context *ctx) override;
/**
* AND.
*
* @return Expression*
*/
antlrcpp::Any visitExpression10(MemgraphCypher::Expression10Context *ctx) override;
/**
* NOT.
*
* @return Expression*
*/
antlrcpp::Any visitExpression9(MemgraphCypher::Expression9Context *ctx) override;
/**
* Comparisons.
*
* @return Expression*
*/
antlrcpp::Any visitExpression8(MemgraphCypher::Expression8Context *ctx) override;
/**
* Never call this. Everything related to generating code for comparison
* operators should be done in visitExpression8.
*/
antlrcpp::Any visitPartialComparisonExpression(MemgraphCypher::PartialComparisonExpressionContext *ctx) override;
/**
* Addition and subtraction.
*
* @return Expression*
*/
antlrcpp::Any visitExpression7(MemgraphCypher::Expression7Context *ctx) override;
/**
* Multiplication, division, modding.
*
* @return Expression*
*/
antlrcpp::Any visitExpression6(MemgraphCypher::Expression6Context *ctx) override;
/**
* Power.
*
* @return Expression*
*/
antlrcpp::Any visitExpression5(MemgraphCypher::Expression5Context *ctx) override;
/**
* Unary minus and plus.
*
* @return Expression*
*/
antlrcpp::Any visitExpression4(MemgraphCypher::Expression4Context *ctx) override;
/**
* IS NULL, IS NOT NULL, STARTS WITH, END WITH, =~, ...
*
* @return Expression*
*/
antlrcpp::Any visitExpression3a(MemgraphCypher::Expression3aContext *ctx) override;
/**
* Does nothing, everything is done in visitExpression3a.
*
* @return Expression*
*/
antlrcpp::Any visitStringAndNullOperators(MemgraphCypher::StringAndNullOperatorsContext *ctx) override;
/**
* List indexing and slicing.
*
* @return Expression*
*/
antlrcpp::Any visitExpression3b(MemgraphCypher::Expression3bContext *ctx) override;
/**
* Does nothing, everything is done in visitExpression3b.
*/
antlrcpp::Any visitListIndexingOrSlicing(MemgraphCypher::ListIndexingOrSlicingContext *ctx) override;
/**
* Node labels test.
*
* @return Expression*
*/
antlrcpp::Any visitExpression2a(MemgraphCypher::Expression2aContext *ctx) override;
/**
* Property lookup.
*
* @return Expression*
*/
antlrcpp::Any visitExpression2b(MemgraphCypher::Expression2bContext *ctx) override;
/**
* Literals, params, list comprehension...
*
* @return Expression*
*/
antlrcpp::Any visitAtom(MemgraphCypher::AtomContext *ctx) override;
/**
* @return ParameterLookup*
*/
antlrcpp::Any visitParameter(MemgraphCypher::ParameterContext *ctx) override;
/**
* @return Expression*
*/
antlrcpp::Any visitParenthesizedExpression(MemgraphCypher::ParenthesizedExpressionContext *ctx) override;
/**
* @return Expression*
*/
antlrcpp::Any visitFunctionInvocation(MemgraphCypher::FunctionInvocationContext *ctx) override;
/**
* @return string - uppercased
*/
antlrcpp::Any visitFunctionName(MemgraphCypher::FunctionNameContext *ctx) override;
/**
* @return Expression*
*/
antlrcpp::Any visitLiteral(MemgraphCypher::LiteralContext *ctx) override;
/**
* Convert escaped string from a query to unescaped utf8 string.
*
* @return string
*/
antlrcpp::Any visitStringLiteral(const std::string &escaped);
/**
* @return bool
*/
antlrcpp::Any visitBooleanLiteral(MemgraphCypher::BooleanLiteralContext *ctx) override;
/**
* @return TypedValue with either double or int
*/
antlrcpp::Any visitNumberLiteral(MemgraphCypher::NumberLiteralContext *ctx) override;
/**
* @return int64_t
*/
antlrcpp::Any visitIntegerLiteral(MemgraphCypher::IntegerLiteralContext *ctx) override;
/**
* @return double
*/
antlrcpp::Any visitDoubleLiteral(MemgraphCypher::DoubleLiteralContext *ctx) override;
/**
* @return Delete*
*/
antlrcpp::Any visitCypherDelete(MemgraphCypher::CypherDeleteContext *ctx) override;
/**
* @return Where*
*/
antlrcpp::Any visitWhere(MemgraphCypher::WhereContext *ctx) override;
/**
* return vector<Clause*>
*/
antlrcpp::Any visitSet(MemgraphCypher::SetContext *ctx) override;
/**
* @return Clause*
*/
antlrcpp::Any visitSetItem(MemgraphCypher::SetItemContext *ctx) override;
/**
* return vector<Clause*>
*/
antlrcpp::Any visitRemove(MemgraphCypher::RemoveContext *ctx) override;
/**
* @return Clause*
*/
antlrcpp::Any visitRemoveItem(MemgraphCypher::RemoveItemContext *ctx) override;
/**
* @return PropertyLookup*
*/
antlrcpp::Any visitPropertyExpression(MemgraphCypher::PropertyExpressionContext *ctx) override;
/**
* @return IfOperator*
*/
antlrcpp::Any visitCaseExpression(MemgraphCypher::CaseExpressionContext *ctx) override;
/**
* Never call this. Ast generation for this production is done in
* @c visitCaseExpression.
*/
antlrcpp::Any visitCaseAlternatives(MemgraphCypher::CaseAlternativesContext *ctx) override;
/**
* @return With*
*/
antlrcpp::Any visitWith(MemgraphCypher::WithContext *ctx) override;
/**
* @return Merge*
*/
antlrcpp::Any visitMerge(MemgraphCypher::MergeContext *ctx) override;
/**
* @return Unwind*
*/
antlrcpp::Any visitUnwind(MemgraphCypher::UnwindContext *ctx) override;
/**
* Never call this. Ast generation for these expressions should be done by
* explicitly visiting the members of @c FilterExpressionContext.
*/
antlrcpp::Any visitFilterExpression(MemgraphCypher::FilterExpressionContext *) override;
/**
* @return Foreach*
*/
antlrcpp::Any visitForeach(MemgraphCypher::ForeachContext *ctx) override;
/**
* @return Schema*
*/
antlrcpp::Any visitPropertyType(MemgraphCypher::PropertyTypeContext *ctx) override;
/**
* @return Schema*
*/
antlrcpp::Any visitSchemaPropertyMap(MemgraphCypher::SchemaPropertyMapContext *ctx) override;
/**
* @return Schema*
*/
antlrcpp::Any visitSchemaQuery(MemgraphCypher::SchemaQueryContext *ctx) override;
/**
* @return Schema*
*/
antlrcpp::Any visitShowSchema(MemgraphCypher::ShowSchemaContext *ctx) override;
/**
* @return Schema*
*/
antlrcpp::Any visitShowSchemas(MemgraphCypher::ShowSchemasContext *ctx) override;
/**
* @return Schema*
*/
antlrcpp::Any visitCreateSchema(MemgraphCypher::CreateSchemaContext *ctx) override;
/**
* @return Schema*
*/
antlrcpp::Any visitDropSchema(MemgraphCypher::DropSchemaContext *ctx) override;
public:
Query *query() { return query_; }
const static std::string kAnonPrefix;
struct QueryInfo {
bool is_cacheable{true};
bool has_load_csv{false};
};
const auto &GetQueryInfo() const { return query_info_; }
private:
LabelIx AddLabel(const std::string &name);
PropertyIx AddProperty(const std::string &name);
EdgeTypeIx AddEdgeType(const std::string &name);
ParsingContext context_;
AstStorage *storage_;
std::unordered_map<uint8_t, std::variant<Expression *, std::string, std::vector<std::string>,
std::unordered_map<Expression *, Expression *>>>
memory_;
// Set of identifiers from queries.
std::unordered_set<std::string> users_identifiers;
// Identifiers that user didn't name.
std::vector<Identifier **> anonymous_identifiers;
Query *query_ = nullptr;
// All return items which are not variables must be aliased in with.
// We use this variable in visitReturnItem to check if we are in with or
// return.
bool in_with_ = false;
QueryInfo query_info_;
};
} // namespace memgraph::query::v2::frontend

View File

@@ -0,0 +1,311 @@
// Copyright 2022 Memgraph Ltd.
//
// Use of this software is governed by the Business Source License
// included in the file licenses/BSL.txt; by using this file, you agree to be bound by the terms of the Business Source
// License, and you may not use this file except in compliance with the Business Source License.
//
// As of the Change Date specified in that file, in accordance with
// the Business Source License, use of this software will be governed
// by the Apache License, Version 2.0, included in the file
// licenses/APL.txt.
#include "query/v2/frontend/ast/pretty_print.hpp"
#include <type_traits>
#include "query/v2/frontend/ast/ast.hpp"
#include "utils/algorithm.hpp"
#include "utils/string.hpp"
namespace memgraph::query::v2 {
namespace {
class ExpressionPrettyPrinter : public ExpressionVisitor<void> {
public:
explicit ExpressionPrettyPrinter(std::ostream *out);
// Unary operators
void Visit(NotOperator &op) override;
void Visit(UnaryPlusOperator &op) override;
void Visit(UnaryMinusOperator &op) override;
void Visit(IsNullOperator &op) override;
// Binary operators
void Visit(OrOperator &op) override;
void Visit(XorOperator &op) override;
void Visit(AndOperator &op) override;
void Visit(AdditionOperator &op) override;
void Visit(SubtractionOperator &op) override;
void Visit(MultiplicationOperator &op) override;
void Visit(DivisionOperator &op) override;
void Visit(ModOperator &op) override;
void Visit(NotEqualOperator &op) override;
void Visit(EqualOperator &op) override;
void Visit(LessOperator &op) override;
void Visit(GreaterOperator &op) override;
void Visit(LessEqualOperator &op) override;
void Visit(GreaterEqualOperator &op) override;
void Visit(InListOperator &op) override;
void Visit(SubscriptOperator &op) override;
// Other
void Visit(ListSlicingOperator &op) override;
void Visit(IfOperator &op) override;
void Visit(ListLiteral &op) override;
void Visit(MapLiteral &op) override;
void Visit(LabelsTest &op) override;
void Visit(Aggregation &op) override;
void Visit(Function &op) override;
void Visit(Reduce &op) override;
void Visit(Coalesce &op) override;
void Visit(Extract &op) override;
void Visit(All &op) override;
void Visit(Single &op) override;
void Visit(Any &op) override;
void Visit(None &op) override;
void Visit(Identifier &op) override;
void Visit(PrimitiveLiteral &op) override;
void Visit(PropertyLookup &op) override;
void Visit(ParameterLookup &op) override;
void Visit(NamedExpression &op) override;
void Visit(RegexMatch &op) override;
private:
std::ostream *out_;
};
// Declare all of the different `PrintObject` overloads upfront since they're
// mutually recursive. Without this, overload resolution depends on the ordering
// of the overloads within the source, which is quite fragile.
template <typename T>
void PrintObject(std::ostream *out, const T &arg);
void PrintObject(std::ostream *out, const std::string &str);
void PrintObject(std::ostream *out, Aggregation::Op op);
void PrintObject(std::ostream *out, Expression *expr);
void PrintObject(std::ostream *out, Identifier *expr);
void PrintObject(std::ostream *out, const storage::v3::PropertyValue &value);
template <typename T>
void PrintObject(std::ostream *out, const std::vector<T> &vec);
template <typename K, typename V>
void PrintObject(std::ostream *out, const std::map<K, V> &map);
template <typename T>
void PrintObject(std::ostream *out, const T &arg) {
static_assert(!std::is_convertible<T, Expression *>::value,
"This overload shouldn't be called with pointers convertible "
"to Expression *. This means your other PrintObject overloads aren't "
"being called for certain AST nodes when they should (or perhaps such "
"overloads don't exist yet).");
*out << arg;
}
void PrintObject(std::ostream *out, const std::string &str) { *out << utils::Escape(str); }
void PrintObject(std::ostream *out, Aggregation::Op op) { *out << Aggregation::OpToString(op); }
void PrintObject(std::ostream *out, Expression *expr) {
if (expr) {
ExpressionPrettyPrinter printer{out};
expr->Accept(printer);
} else {
*out << "<null>";
}
}
void PrintObject(std::ostream *out, Identifier *expr) { PrintObject(out, static_cast<Expression *>(expr)); }
void PrintObject(std::ostream *out, const storage::v3::PropertyValue &value) {
switch (value.type()) {
case storage::v3::PropertyValue::Type::Null:
*out << "null";
break;
case storage::v3::PropertyValue::Type::String:
PrintObject(out, value.ValueString());
break;
case storage::v3::PropertyValue::Type::Bool:
*out << (value.ValueBool() ? "true" : "false");
break;
case storage::v3::PropertyValue::Type::Int:
PrintObject(out, value.ValueInt());
break;
case storage::v3::PropertyValue::Type::Double:
PrintObject(out, value.ValueDouble());
break;
case storage::v3::PropertyValue::Type::List:
PrintObject(out, value.ValueList());
break;
case storage::v3::PropertyValue::Type::Map:
PrintObject(out, value.ValueMap());
break;
case storage::v3::PropertyValue::Type::TemporalData:
PrintObject(out, value.ValueTemporalData());
break;
}
}
template <typename T>
void PrintObject(std::ostream *out, const std::vector<T> &vec) {
*out << "[";
utils::PrintIterable(*out, vec, ", ", [](auto &stream, const auto &item) { PrintObject(&stream, item); });
*out << "]";
}
template <typename K, typename V>
void PrintObject(std::ostream *out, const std::map<K, V> &map) {
*out << "{";
utils::PrintIterable(*out, map, ", ", [](auto &stream, const auto &item) {
PrintObject(&stream, item.first);
stream << ": ";
PrintObject(&stream, item.second);
});
*out << "}";
}
template <typename T>
void PrintOperatorArgs(std::ostream *out, const T &arg) {
*out << " ";
PrintObject(out, arg);
*out << ")";
}
template <typename T, typename... Ts>
void PrintOperatorArgs(std::ostream *out, const T &arg, const Ts &...args) {
*out << " ";
PrintObject(out, arg);
PrintOperatorArgs(out, args...);
}
template <typename... Ts>
void PrintOperator(std::ostream *out, const std::string &name, const Ts &...args) {
*out << "(" << name;
PrintOperatorArgs(out, args...);
}
ExpressionPrettyPrinter::ExpressionPrettyPrinter(std::ostream *out) : out_(out) {}
#define UNARY_OPERATOR_VISIT(OP_NODE, OP_STR) \
void ExpressionPrettyPrinter::Visit(OP_NODE &op) { PrintOperator(out_, OP_STR, op.expression_); }
UNARY_OPERATOR_VISIT(NotOperator, "Not");
UNARY_OPERATOR_VISIT(UnaryPlusOperator, "+");
UNARY_OPERATOR_VISIT(UnaryMinusOperator, "-");
UNARY_OPERATOR_VISIT(IsNullOperator, "IsNull");
#undef UNARY_OPERATOR_VISIT
#define BINARY_OPERATOR_VISIT(OP_NODE, OP_STR) \
void ExpressionPrettyPrinter::Visit(OP_NODE &op) { PrintOperator(out_, OP_STR, op.expression1_, op.expression2_); }
BINARY_OPERATOR_VISIT(OrOperator, "Or");
BINARY_OPERATOR_VISIT(XorOperator, "Xor");
BINARY_OPERATOR_VISIT(AndOperator, "And");
BINARY_OPERATOR_VISIT(AdditionOperator, "+");
BINARY_OPERATOR_VISIT(SubtractionOperator, "-");
BINARY_OPERATOR_VISIT(MultiplicationOperator, "*");
BINARY_OPERATOR_VISIT(DivisionOperator, "/");
BINARY_OPERATOR_VISIT(ModOperator, "%");
BINARY_OPERATOR_VISIT(NotEqualOperator, "!=");
BINARY_OPERATOR_VISIT(EqualOperator, "==");
BINARY_OPERATOR_VISIT(LessOperator, "<");
BINARY_OPERATOR_VISIT(GreaterOperator, ">");
BINARY_OPERATOR_VISIT(LessEqualOperator, "<=");
BINARY_OPERATOR_VISIT(GreaterEqualOperator, ">=");
BINARY_OPERATOR_VISIT(InListOperator, "In");
BINARY_OPERATOR_VISIT(SubscriptOperator, "Subscript");
#undef BINARY_OPERATOR_VISIT
void ExpressionPrettyPrinter::Visit(ListSlicingOperator &op) {
PrintOperator(out_, "ListSlicing", op.list_, op.lower_bound_, op.upper_bound_);
}
void ExpressionPrettyPrinter::Visit(IfOperator &op) {
PrintOperator(out_, "If", op.condition_, op.then_expression_, op.else_expression_);
}
void ExpressionPrettyPrinter::Visit(ListLiteral &op) { PrintOperator(out_, "ListLiteral", op.elements_); }
void ExpressionPrettyPrinter::Visit(MapLiteral &op) {
std::map<std::string, Expression *> map;
for (const auto &kv : op.elements_) {
map[kv.first.name] = kv.second;
}
PrintObject(out_, map);
}
void ExpressionPrettyPrinter::Visit(LabelsTest &op) { PrintOperator(out_, "LabelsTest", op.expression_); }
void ExpressionPrettyPrinter::Visit(Aggregation &op) { PrintOperator(out_, "Aggregation", op.op_); }
void ExpressionPrettyPrinter::Visit(Function &op) { PrintOperator(out_, "Function", op.function_name_, op.arguments_); }
void ExpressionPrettyPrinter::Visit(Reduce &op) {
PrintOperator(out_, "Reduce", op.accumulator_, op.initializer_, op.identifier_, op.list_, op.expression_);
}
void ExpressionPrettyPrinter::Visit(Coalesce &op) { PrintOperator(out_, "Coalesce", op.expressions_); }
void ExpressionPrettyPrinter::Visit(Extract &op) {
PrintOperator(out_, "Extract", op.identifier_, op.list_, op.expression_);
}
void ExpressionPrettyPrinter::Visit(All &op) {
PrintOperator(out_, "All", op.identifier_, op.list_expression_, op.where_->expression_);
}
void ExpressionPrettyPrinter::Visit(Single &op) {
PrintOperator(out_, "Single", op.identifier_, op.list_expression_, op.where_->expression_);
}
void ExpressionPrettyPrinter::Visit(Any &op) {
PrintOperator(out_, "Any", op.identifier_, op.list_expression_, op.where_->expression_);
}
void ExpressionPrettyPrinter::Visit(None &op) {
PrintOperator(out_, "None", op.identifier_, op.list_expression_, op.where_->expression_);
}
void ExpressionPrettyPrinter::Visit(Identifier &op) { PrintOperator(out_, "Identifier", op.name_); }
void ExpressionPrettyPrinter::Visit(PrimitiveLiteral &op) { PrintObject(out_, op.value_); }
void ExpressionPrettyPrinter::Visit(PropertyLookup &op) {
PrintOperator(out_, "PropertyLookup", op.expression_, op.property_.name);
}
void ExpressionPrettyPrinter::Visit(ParameterLookup &op) { PrintOperator(out_, "ParameterLookup", op.token_position_); }
void ExpressionPrettyPrinter::Visit(NamedExpression &op) {
PrintOperator(out_, "NamedExpression", op.name_, op.expression_);
}
void ExpressionPrettyPrinter::Visit(RegexMatch &op) { PrintOperator(out_, "=~", op.string_expr_, op.regex_); }
} // namespace
void PrintExpression(Expression *expr, std::ostream *out) {
ExpressionPrettyPrinter printer{out};
expr->Accept(printer);
}
void PrintExpression(NamedExpression *expr, std::ostream *out) {
ExpressionPrettyPrinter printer{out};
expr->Accept(printer);
}
} // namespace memgraph::query::v2

View File

@@ -11,9 +11,13 @@
#pragma once
#include "query/v2/bindings/bindings.hpp"
#include <iostream>
#include "expr/ast/pretty_print.hpp"
#include "query/v2/frontend/ast/ast.hpp"
namespace memgraph::query::v2 {
void PrintExpression(Expression *expr, std::ostream *out);
void PrintExpression(NamedExpression *expr, std::ostream *out);
} // namespace memgraph::query::v2

View File

@@ -1,6 +1,6 @@
/*
* When changing this grammar make sure to update constants in
* src/parser/stripped_lexer_constants.hpp (kKeywords, kSpecialTokens
* src/query/frontend/stripped_lexer_constants.hpp (kKeywords, kSpecialTokens
* and bitsets) if needed.
*/

View File

@@ -15,7 +15,7 @@
/*
* When changing this grammar make sure to update constants in
* src/parser/stripped_lexer_constants.hpp (kKeywords, kSpecialTokens
* src/query/frontend/stripped_lexer_constants.hpp (kKeywords, kSpecialTokens
* and bitsets) if needed.
*/

Some files were not shown because too many files have changed in this diff Show More