SparqlExpressions! And a properParser! (both at least partially, but with a general, extendable framework)

.github/workflows/cmake.yml

@@ -20,7 +20,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        compiler: [ g++-10, clang++-11 ]
+        compiler: [ g++-10, clang++-12 ]
         os: [ ubuntu-latest ]
         warnings: [ "", -Werror ]
         exclude:
@@ -32,7 +32,10 @@ jobs:
     - uses: actions/checkout@v2
 
     - name: Install dependencies
-      run:  sudo apt-get install -y libsparsehash-dev libicu-dev tzdata clang gcc-10 clang-11
+      run:  sudo apt-get install -y libsparsehash-dev libicu-dev tzdata clang gcc-10
+    - name: Install clang 12
+      run: wget https://apt.llvm.org/llvm.sh && sudo chmod +x llvm.sh && sudo ./llvm.sh 12
+
     - name: Python dependencies
       run: sudo apt-get install python3-yaml unzip pkg-config python3-icu
 

.gitignore

@@ -1,5 +1,6 @@
 # Build directory
 build/
+cmake-build*
 
 # End-to-End data
 e2e_data/*
@@ -8,6 +9,7 @@ e2e_data/*
 *.lo
 *.o
 *.obj
+*.jar
 
 # Precompiled Headers
 *.gch

.gitmodules

@@ -10,3 +10,6 @@
 [submodule "third_party/abseil-cpp"]
 	path = third_party/abseil-cpp
 	url = https://github.com/abseil/abseil-cpp.git
+[submodule "third_party/antlr4"]
+	path = third_party/antlr4
+	url = https://github.com/antlr/antlr4.git

CMakeLists.txt

@@ -30,21 +30,28 @@ set(CMAKE_CXX_FLAGS_ASAN
 
 # Add colored output for Ninja
 if ("${CMAKE_GENERATOR}" STREQUAL "Ninja")
-  if ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "GNU")
-     add_compile_options (-fdiagnostics-color=always)
-  elseif ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang")
-     add_compile_options (-fcolor-diagnostics)
-  endif ()
-endif()
+    if ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "GNU")
+        add_compile_options(-fdiagnostics-color=always)
+    elseif ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang")
+        add_compile_options(-fcolor-diagnostics)
+    endif ()
+endif ()
 
 ###############################################################################
 ##### Essential settings #####
 ###############################################################################
 
+###############################
+# ANTLR CPP RUNTIME FOR THE SPARQL PARSER
+###############################
+add_subdirectory(third_party/antlr4/runtime/Cpp EXCLUDE_FROM_ALL)
+target_compile_options(antlr4_static PUBLIC -Wno-attributes -Wno-implicit-fallthrough)
+include_directories(third_party/antlr4/runtime/Cpp/runtime/src)
+
 ################################
 # Threading
 ################################
-find_package (Threads REQUIRED)
+find_package(Threads REQUIRED)
 
 #################################
 # ICU (for proper collation
@@ -81,7 +88,7 @@ set(CMAKE_C_FLAGS_DEBUG "${CMAKE_C_FLAGS_DEBUG}")
 ################################
 # GTEST
 ################################
-add_subdirectory(third_party/googletest/googletest)
+add_subdirectory(third_party/googletest/googletest EXCLUDE_FROM_ALL)
 include_directories(third_party/googletest/googletest/include)
 
 ################################
@@ -100,7 +107,7 @@ include_directories(third_party/ctre/include)
 # ABSEIL
 ################################
 set(BUILD_TESTING OFF CACHE BOOL "Don't build tests for abseil" FORCE)
-add_subdirectory(third_party/abseil-cpp)
+add_subdirectory(third_party/abseil-cpp EXCLUDE_FROM_ALL)
 include_directories(third_party/abseil-cpp/)
 
 if (USE_PARALLEL)
@@ -124,7 +131,7 @@ endif()
 set(USE_GNU_PARALLEL OFF CACHE BOOL "Don't use gnu parallel" FORCE)
 set(USE_OPENMP OFF CACHE BOOL "Don't use OPENMP as default" FORCE)
 
-add_subdirectory(third_party/stxxl)
+add_subdirectory(third_party/stxxl EXCLUDE_FROM_ALL)
 
 # apply STXXL CXXFLAGS
 set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${STXXL_CXX_FLAGS}")
@@ -140,7 +147,7 @@ set(LOCAL_CXX_BACKUP_FLAGS "${CMAKE_CXX_FLAGS}")
 set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-unused-parameter")
 
 set(RE2_BUILD_TESTING OFF CACHE BOOL "enable testing for RE2" FORCE)
-add_subdirectory(third_party/re2)
+add_subdirectory(third_party/re2 EXCLUDE_FROM_ALL)
 include_directories(SYSTEM third_party/re2)
 
 # reinstate original flags including all warnings

Dockerfile

@@ -7,18 +7,21 @@ ENV DEBIAN_FRONTEND=noninteractive
 
 FROM base as builder
 RUN apt-get update && apt-get install -y build-essential cmake libsparsehash-dev libicu-dev tzdata
+RUN apt-get install -y pkg-config uuid-runtime uuid-dev git
 COPY . /app/
 
 # Check formatting with the .clang-format project style
 WORKDIR /app/
 ENV DEBIAN_FRONTEND=noninteractive
 
 WORKDIR /app/build/
-RUN cmake -DCMAKE_BUILD_TYPE=Release -DLOGLEVEL=DEBUG -DUSE_PARALLEL=true .. && make -j $(nproc) && make test
+RUN cmake -DCMAKE_BUILD_TYPE=Release -DLOGLEVEL=DEBUG -DUSE_PARALLEL=true .. && make -j $(nproc)
+# RUN make test
 
 FROM base as runtime
 WORKDIR /app
 RUN apt-get update && apt-get install -y wget python3-yaml unzip curl bzip2 pkg-config libicu-dev python3-icu libgomp1
+RUN apt-get install -y uuid-runtime
 
 ARG UID=1000
 RUN groupadd -r qlever && useradd --no-log-init -r -u $UID -g qlever qlever && chown qlever:qlever /app

e2e/scientists_queries.yaml

@@ -844,22 +844,22 @@ queries:
       - contains_row: [ "<Albert_Einstein>", "<Mileva_Marić>", 42 ]
       - order_string: { "dir": "ASC", "var": "?x" }
 
-  - query: bind-entity-constant
-    type: no-text
-    sparql: |
-      SELECT ?x ?y ?z WHERE {
-          ?x <is-a> <Scientist> .
-          ?x <Spouse_(or_domestic_partner)> ?y .
-          ?y <is-a> <Scientist> .
-          FILTER(?x < ?y) .
-          BIND(<Al_Gore> AS ?z)
-      } ORDER BY ASC(?x)
-    checks:
-      - num_cols: 3
-      - num_rows: 97
-      - selected: [ "?x", "?y", "?z" ]
-      - contains_row: [ "<Albert_Einstein>", "<Mileva_Marić>", "<Al_Gore>" ]
-      - order_string: { "dir": "ASC", "var": "?x" }
+#  - query: bind-entity-constant
+#    type: no-text
+#    sparql: |
+#      SELECT ?x ?y ?z WHERE {
+#          ?x <is-a> <Scientist> .
+#          ?x <Spouse_(or_domestic_partner)> ?y .
+#          ?y <is-a> <Scientist> .
+#          FILTER(?x < ?y) .
+#          BIND(<Al_Gore> AS ?z)
+#      } ORDER BY ASC(?x)
+#    checks:
+#      - num_cols: 3
+#      - num_rows: 97
+#      - selected: [ "?x", "?y", "?z" ]
+#      - contains_row: [ "<Albert_Einstein>", "<Mileva_Marić>", "<Al_Gore>" ]
+#      - order_string: { "dir": "ASC", "var": "?x" }
   - query: bind-entity-constant
     type: no-text
     sparql: |

src/SparqlEngineMain.cpp

@@ -221,7 +221,8 @@ void processQuery(QueryExecutionContext& qec, const string& query) {
   if (pq._offset.size() > 0) {
     offset = static_cast<size_t>(atol(pq._offset.c_str()));
   }
-  qet.writeResultToStream(cout, pq._selectedVariables, limit, offset);
+  qet.writeResultToStream(cout, pq._selectClause._selectedVariables, limit,
+                          offset);
   t.stop();
   std::cout << "\nDone. Time: " << t.usecs() / 1000.0 << " ms\n";
   size_t numMatches = qet.getResult()->size();