Merge branch 'master' into path-search

.codespellrc

@@ -0,0 +1,8 @@
+[codespell]
+# Ref: https://github.com/codespell-project/codespell#using-a-config-file
+skip = .git*,.codespellrc,*.pdf,generated
+check-hidden = true
+# Ignore mixedCase variables, lines with latin, lines with codespell-ignore pragma, etc
+ignore-regex = \b([A-Z]*[a-z]+[A-Z][a-zA-Z]*)\b|.*(Lorem ipsum|eleifend|feugait|codespell-ignore).*
+# alph - is used frequently in tests, just ignore altogether
+ignore-words-list = ser,alph,inbetween,interm

.github/workflows/codespell.yml

@@ -0,0 +1,25 @@
+# Codespell configuration is within .codespellrc
+---
+name: Codespell
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches: [master]
+
+permissions:
+  contents: read
+
+jobs:
+  codespell:
+    name: Check for spelling errors
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Annotate locations with typos
+        uses: codespell-project/codespell-problem-matcher@v1
+      - name: Codespell
+        uses: codespell-project/actions-codespell@v2

.pre-commit-config-local.yaml

@@ -0,0 +1,22 @@
+# See .pre-commit-config.yaml for usage instructions.
+repos:
+    # Uses the local clang-format
+  - repo: local
+    hooks:
+      # Inspired by https://github.com/doublify/pre-commit-clang-format and
+      # https://github.com/pre-commit/mirrors-clang-format
+      - id: clang-format-16
+        name: clang-format
+        description: Format files with ClangFormat16.
+        entry: clang-format-16 -i
+        language: system
+        'types_or': [ c++, c ]
+        args: [ "-style=file" ]
+        require_serial: false
+
+
+  - repo: https://github.com/codespell-project/codespell
+    # Configuration for codespell is in .codespellrc
+    rev: v2.2.6
+    hooks:
+    - id: codespell

.pre-commit-config.yaml

@@ -0,0 +1,22 @@
+# Usage:
+# - Install pre-commit: `pip install pre-commit` (once).ci:
+# - In the main directory of QLever run
+#   - `pre-commit install` to use a package version of clang-format
+#   - `pre-commit install -c .pre-commit-config-local.yaml` to use the local clang-format
+# - Each git commit will now automatically be formatted. Note that
+# - commits will fail if the hook reformats your files, so you
+# - have to run git commit twice in order to first format and then
+# - actually commit.
+repos:
+  # Uses a packaged version of clang-format from https://github.com/ssciwr/clang-format-wheel
+  - repo: https://github.com/pre-commit/mirrors-clang-format
+    rev: 'v16.0.6'
+    hooks:
+      - id: clang-format
+        'types_or': [ c++, c ]
+
+  - repo: https://github.com/codespell-project/codespell
+    # Configuration for codespell is in .codespellrc
+    rev: v2.2.6
+    hooks:
+    - id: codespell

CMakeLists.txt

@@ -40,7 +40,7 @@ else ()
 endif ()
 
 ## Build targets for address sanitizer
-# AddressSanitize
+
 set(CMAKE_C_FLAGS_ASAN
         "-fsanitize=address -fsanitize=undefined -fno-optimize-sibling-calls -fsanitize-address-use-after-scope -fno-omit-frame-pointer -g -O1"
         CACHE STRING "Flags used by the C compiler during AddressSanitizer builds."
@@ -70,7 +70,7 @@ include(FetchContent)
 FetchContent_Declare(
         googletest
         GIT_REPOSITORY https://github.com/google/googletest.git
-        GIT_TAG f8d7d77c06936315286eb55f8de22cd23c188571 # release-1.14.0
+        GIT_TAG 33af80a883ddc33d9c0fac0a5b4578301efb18de # main branch on 2024/05/16
 )
 
 ################################
@@ -241,7 +241,7 @@ set(ABSL_PROPAGATE_CXX_STD ON)
 FetchContent_Declare(
         abseil
         GIT_REPOSITORY https://github.com/abseil/abseil-cpp.git
-        GIT_TAG 258e5a15759cc3d122d4a4826bc499af91d40aa9 # 2023-12-21
+        GIT_TAG 93ac3a4f9ee7792af399cebd873ee99ce15aed08  # 2024-05-16
 )
 
 if (USE_PARALLEL)
@@ -348,7 +348,7 @@ message(STATUS ---)
 include_directories(src)
 
 # Run the script `CompilationInfo.cmake` that creates the file `CompilationInfo.cpp`
-# with the current git hash and the curent time and date. When specifying
+# with the current git hash and the current time and date. When specifying
 # `-DDONT_UPDATE_COMPILATION_INFO=true` as an argument to `cmake`, the compilation info is
 # never updated. This is useful during development to avoid a relinking of the binaries for
 # every compilation.

Dockerfile

@@ -41,7 +41,7 @@ ENV MEMORY_FOR_QUERIES 70
 ENV CACHE_MAX_SIZE_GB 30
 ENV CACHE_MAX_SIZE_GB_SINGLE_ENTRY 5
 ENV CACHE_MAX_NUM_ENTRIES 1000
-# Need the shell to get the INDEX_PREFIX envirionment variable
+# Need the shell to get the INDEX_PREFIX environment variable
 ENTRYPOINT ["/bin/sh", "-c", "exec ServerMain -i \"/index/${INDEX_PREFIX}\" -j 8 -m ${MEMORY_FOR_QUERIES} -c ${CACHE_MAX_SIZE_GB} -e ${CACHE_MAX_SIZE_GB_SINGLE_ENTRY} -k ${CACHE_MAX_NUM_ENTRIES} -p 7001 \"$@\"", "--"]
 
 # Build image:  docker build -t qlever.master .

Dockerfiles/Dockerfile.Ubuntu18.04

@@ -49,7 +49,7 @@ ENV MEMORY_FOR_QUERIES 70
 ENV CACHE_MAX_SIZE_GB 30
 ENV CACHE_MAX_SIZE_GB_SINGLE_ENTRY 5
 ENV CACHE_MAX_NUM_ENTRIES 1000
-# Need the shell to get the INDEX_PREFIX envirionment variable
+# Need the shell to get the INDEX_PREFIX environment variable
 ENTRYPOINT ["/bin/sh", "-c", "exec ServerMain -i \"/index/${INDEX_PREFIX}\" -j 8 -m ${MEMORY_FOR_QUERIES} -c ${CACHE_MAX_SIZE_GB} -e ${CACHE_MAX_SIZE_GB_SINGLE_ENTRY} -k ${CACHE_MAX_NUM_ENTRIES} -p 7001 \"$@\"", "--"]
 
 # Build image:  docker build -t qlever.master .

Dockerfiles/Dockerfile.Ubuntu20.04

@@ -45,7 +45,7 @@ ENV MEMORY_FOR_QUERIES 70
 ENV CACHE_MAX_SIZE_GB 30
 ENV CACHE_MAX_SIZE_GB_SINGLE_ENTRY 5
 ENV CACHE_MAX_NUM_ENTRIES 1000
-# Need the shell to get the INDEX_PREFIX envirionment variable
+# Need the shell to get the INDEX_PREFIX environment variable
 ENTRYPOINT ["/bin/sh", "-c", "exec ServerMain -i \"/index/${INDEX_PREFIX}\" -j 8 -m ${MEMORY_FOR_QUERIES} -c ${CACHE_MAX_SIZE_GB} -e ${CACHE_MAX_SIZE_GB_SINGLE_ENTRY} -k ${CACHE_MAX_NUM_ENTRIES} -p 7001 \"$@\"", "--"]
 
 # Build image:  docker build -t qlever.master .

README.md

@@ -1,6 +1,6 @@
 # QLever
 
-[![Docker build](https://github.com/ad-freiburg/QLever/actions/workflows/docker-publish.yml/badge.svg)](https://github.com/ad-freiburg/QLever/actions/workflows/docker-build.yml)
+[![Docker build](https://github.com/ad-freiburg/QLever/actions/workflows/docker-publish.yml/badge.svg)](https://github.com/ad-freiburg/QLever/actions/workflows/docker-publish.yml)
 [![Native build](https://github.com/ad-freiburg/qlever/actions/workflows/native-build.yml/badge.svg)](https://github.com/ad-freiburg/qlever/actions/workflows/native-build.yml)
 [![Format check](https://github.com/ad-freiburg/qlever/actions/workflows/format-check.yml/badge.svg)](https://github.com/ad-freiburg/qlever/actions/workflows/format-check.yml)
 [![Test coverage](https://codecov.io/github/ad-freiburg/qlever/branch/master/graph/badge.svg?token=OHcEh02rW0)](https://codecov.io/github/ad-freiburg/qlever)

benchmark/BenchmarkExamples.cpp

@@ -62,7 +62,7 @@ class ConfigOptions : public BenchmarkInterface {
                          "allowed for the configuration option \"num-signs\".",
                          numSigns);
 
-    manager.addOption("coin-flip-try", "The number of succesful coin flips.",
+    manager.addOption("coin-flip-try", "The number of successful coin flips.",
                       &wonOnTryX_, {false, false, false, false, false});
 
     // Sub manager can be used to organize things better. They are basically
@@ -94,7 +94,7 @@ class BMSingleMeasurements : public ConfigOptions {
       exponentiate(number);
     });
     auto& multipleTimes = results.addMeasurement(
-        "Recursivly exponentiate multiple times", [&number, &exponentiate]() {
+        "Recursively exponentiate multiple times", [&number, &exponentiate]() {
           size_t toExponentiate = number;
           for (size_t i = 0; i < 10'000'000'000; i++) {
             toExponentiate = exponentiate(toExponentiate);

benchmark/CMakeLists.txt

@@ -27,6 +27,8 @@ endfunction()
 # Add benchmarks after here.
 addAndLinkBenchmark(BenchmarkExamples)
 
+addAndLinkBenchmark(JoinAlgorithmBenchmark testUtil memorySize)
+
 addAndLinkBenchmark(IdTableCompressedWriterBenchmark engine testUtil)
 
 addAndLinkBenchmark(ParallelMergeBenchmark)

benchmark/GroupByHashMapBenchmark.cpp

@@ -84,7 +84,9 @@ auto generateRandomLocalVocabAndIndicesVec = [](size_t n, size_t m) {
     for (size_t j = 0; j < m; j++) {
       str += alphanum.at(gen());
     }
-    indices.push_back(localVocab.getIndexAndAddIfNotContained(str));
+    using namespace ad_utility::triple_component;
+    indices.push_back(localVocab.getIndexAndAddIfNotContained(
+        LiteralOrIri::literalWithoutQuotes(str)));
   }
 
   return std::make_pair(std::move(localVocab), indices);