Parquet data format: update CMake configurations

CMakeLists.txt

@@ -263,8 +263,7 @@ include (cmake/find_re2.cmake)
 include (cmake/find_rdkafka.cmake)
 include (cmake/find_capnp.cmake)
 include (cmake/find_llvm.cmake)
-include (cmake/Modules/FindArrow.cmake)
-include (cmake/Modules/FindParquet.cmake)
+include (cmake/find_parquet.cmake)
 
 include (cmake/find_contrib_lib.cmake)
 find_contrib_lib(cityhash)

cmake/find_parquet.cmake

+option (USE_INTERNAL_PARQUET_LIBRARY "Set to FALSE to use system parquet library instead of bundled" ${NOT_UNBUNDLED})
+
+if (NOT EXISTS "${ClickHouse_SOURCE_DIR}/contrib/arrow/cpp/CMakeLists.txt")
+    if (USE_INTERNAL_PARQUET_LIBRARY)
+        message (WARNING "submodule contrib/arrow (required for Parquet) is missing. to fix try run: \n git submodule update --init --recursive")
+    endif ()
+    set (USE_INTERNAL_PARQUET_LIBRARY 0)
+    set (MISSING_INTERNAL_PARQUET_LIBRARY 1)
+endif ()
+
+if (NOT USE_INTERNAL_PARQUET_LIBRARY)
+    find_package (Arrow)
+    find_package (Parquet)
+endif ()
+
+if (ARROW_INCLUDE_DIR AND PARQUET_INCLUDE_DIR)
+elseif (NOT MISSING_INTERNAL_PARQUET_LIBRARY)
+    set (USE_INTERNAL_PARQUET_LIBRARY 1)
+    # TODO: is it required?
+    # set (ARROW_INCLUDE_DIR "${ClickHouse_SOURCE_DIR}/contrib/arrow/cpp/src/arrow")
+    # set (PARQUET_INCLUDE_DIR "${ClickHouse_SOURCE_DIR}/contrib/arrow/cpp/src/parquet")
+    set (ARROW_LIBRARY arrow_static)
+    set (PARQUET_LIBRARY parquet_static)
+    set (USE_PARQUET 1)
+endif ()
+
+if (USE_PARQUET)
+    message (STATUS "Using Parquet: ${ARROW_INCLUDE_DIR} ${PARQUET_INCLUDE_DIR}")
+else ()
+    message (STATUS "Building without Parquet support")
+endif ()

contrib/CMakeLists.txt

@@ -121,6 +121,19 @@ if (USE_INTERNAL_CAPNP_LIBRARY)
     target_include_directories(${CAPNP_LIBRARY} PUBLIC $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/capnproto/c++/src>)
 endif ()
 
+if (USE_INTERNAL_PARQUET_LIBRARY)
+    set (ARROW_COMPUTE ON)
+    set (ARROW_PARQUET ON)
+    set (ARROW_VERBOSE_THIRDPARTY_BUILD ON)
+    set (PARQUET_ARROW_LINKAGE "static")
+    set (ARROW_BUILD_STATIC ON)
+
+    # Because Arrow uses CMAKE_SOURCE_DIR as a project path
+    # Hopefully will be fixed in https://github.com/apache/arrow/pull/2676
+    set (CMAKE_MODULE_PATH ${CMAKE_MODULE_PATH} "${ClickHouse_SOURCE_DIR}/contrib/arrow/cpp/cmake_modules")
+    add_subdirectory (arrow/cpp)
+endif ()
+
 
 if (USE_INTERNAL_POCO_LIBRARY)
     set (save_CMAKE_CXX_FLAGS ${CMAKE_CXX_FLAGS})

dbms/CMakeLists.txt

@@ -220,10 +220,12 @@ if (USE_RDKAFKA)
     endif ()
 endif ()
 
-# TODO: make it optional
-# if (USE_PARQUET)
-    target_link_libraries(dbms ${ARROW_SHARED_LIB} ${PARQUET_SHARED_LIB})
-# endif ()
+if (USE_PARQUET)
+    target_link_libraries(dbms ${PARQUET_LIBRARY} ${ARROW_LIBRARY})
+    if (NOT USE_INTERNAL_PARQUET_LIBRARY)
+        target_include_directories (dbms BEFORE PRIVATE ${PARQUET_INCLUDE_DIR} ${ARROW_INCLUDE_DIR})
+    endif ()
+endif ()
 
 target_link_libraries (dbms
     Threads::Threads