[thirdparty](clucene) add clucene deps for doris inverted index (#15807)

As part of Inverted Index DSIP steps, we'd like to contribute our inverted index implementations step by step.
First of all we need to introduce clucene to doris thirdparty libs, because inverted index implementations are based on 
lucence API and index file format, also we add our features and performance improvements base on clucene, so we 
need to maintain the repo ourselves

build.sh

@@ -575,6 +575,7 @@ EOF
     copy_common_files "${DORIS_OUTPUT}/be/"
     mkdir -p "${DORIS_OUTPUT}/be/log"
     mkdir -p "${DORIS_OUTPUT}/be/storage"
+    cp -r -p "${DORIS_THIRDPARTY}/installed/share/dict" "${DORIS_OUTPUT}/be/"
 fi
 
 if [[ "${BUILD_BROKER}" -eq 1 ]]; then

thirdparty/build-thirdparty.sh

@@ -146,6 +146,7 @@ if [[ "${CC}" == *gcc ]]; then
     warning_stringop_truncation='-Wno-stringop-truncation'
     warning_class_memaccess='-Wno-class-memaccess'
     warning_array_parameter='-Wno-array-parameter'
+    warning_narrowing='-Wno-narrowing'
     boost_toolset='gcc'
 elif [[ "${CC}" == *clang ]]; then
     warning_uninitialized='-Wno-uninitialized'
@@ -156,6 +157,7 @@ elif [[ "${CC}" == *clang ]]; then
     warning_reserved_identifier='-Wno-reserved-identifier'
     warning_suggest_override='-Wno-suggest-override -Wno-suggest-destructor-override'
     warning_option_ignored='-Wno-option-ignored'
+    warning_narrowing='-Wno-c++11-narrowing'
     boost_toolset='clang'
     libhdfs_cxx17='-std=c++1z'
 
@@ -1545,12 +1547,39 @@ build_concurrentqueue() {
     cp ./*.h "${TP_INSTALL_DIR}/include/"
 }
 
+#clucene
+build_clucene() {
+    if [[ -z ${USE_AVX2} ]]; then
+        USE_AVX2=1
+    fi
+    if [[ -z ${BUILD_TYPE} ]]; then
+        BUILD_TYPE=Release
+    fi
+    check_if_source_exist "${CLUCENE_SOURCE}"
+    cd "${TP_SOURCE_DIR}/${CLUCENE_SOURCE}"
+    mkdir -p "${BUILD_DIR}" && cd "${BUILD_DIR}"
+    rm -rf CMakeCache.txt CMakeFiles/
+
+    ${CMAKE_CMD} -G "${GENERATOR}" -DCMAKE_INSTALL_PREFIX="${TP_INSTALL_DIR}" -DBUILD_STATIC_LIBRARIES=ON \
+        -DBUILD_SHARED_LIBRARIES=OFF -DCMAKE_CXX_FLAGS="-fno-omit-frame-pointer ${warning_narrowing}" \
+        -DUSE_STAT64=0 -DUSE_AVX2="${USE_AVX2}" -DCMAKE_BUILD_TYPE="${BUILD_TYPE}" -DBUILD_CONTRIBS_LIB=ON ..
+    ${BUILD_SYSTEM} -j "${PARALLEL}"
+    ${BUILD_SYSTEM} install
+
+    cd "${TP_SOURCE_DIR}/${CLUCENE_SOURCE}"
+    if [[ ! -d "${TP_INSTALL_DIR}"/share ]]; then
+        mkdir -p "${TP_INSTALL_DIR}"/share
+    fi
+    cp -rf src/contribs-lib/CLucene/analysis/jieba/dict "${TP_INSTALL_DIR}"/share/
+}
+
 if [[ "$(uname -s)" == 'Darwin' ]]; then
     echo 'build for Darwin'
     build_binutils
     build_gettext
 fi
 
+build_clucene
 build_libunixodbc
 build_openssl
 build_libevent

thirdparty/vars.sh

@@ -54,6 +54,12 @@ export TP_JAR_DIR="${TP_INSTALL_DIR}/lib/jar"
 # of all thirdparties
 #####################################################
 
+#clucene
+CLUCENE_DOWNLOAD="https://github.com/apache/doris-thirdparty/archive/refs/tags/libclucene-v2.4.4.zip"
+CLUCENE_NAME="doris-thirdparty-libclucene-v2.4.4.zip"
+CLUCENE_SOURCE="doris-thirdparty-libclucene-v2.4.4"
+CLUCENE_MD5SUM="431b4c2dc5c75df5e114da72a2e9b74a"
+
 # libevent
 LIBEVENT_DOWNLOAD="https://github.com/libevent/libevent/archive/release-2.1.12-stable.tar.gz"
 LIBEVENT_NAME=libevent-release-2.1.12-stable.tar.gz
@@ -443,6 +449,7 @@ CONCURRENTQUEUE_MD5SUM="118e5bb661b567634647312991e10222"
 
 # all thirdparties which need to be downloaded is set in array TP_ARCHIVES
 export TP_ARCHIVES=(
+    'CLUCENE'
     'LIBEVENT'
     'OPENSSL'
     'THRIFT'