nishant94 commented on code in PR #64667:
URL: https://github.com/apache/doris/pull/64667#discussion_r3595291295
##########
be/src/tools/CMakeLists.txt:
##########
@@ -116,3 +116,51 @@ if (BUILD_INDEX_TOOL)
)
endif()
endif()
+
+# Offline generator for the Japanese kuromoji dictionary. Compiles the UTF-8
+# mecab-ipadic source into the four dict/kuromoji/*.bin files that the BE
install
+# rule ships. EXCLUDE_FROM_ALL and not installed: it is a maintenance tool, not
+# part of doris_be. Regenerate with `ninja kuromoji_dict`.
+add_executable(kuromoji_build_dict EXCLUDE_FROM_ALL
+ kuromoji_build_dict.cpp
+)
+
+target_include_directories(kuromoji_build_dict PRIVATE
${PROJECT_SOURCE_DIR}/..)
+
+pch_reuse(kuromoji_build_dict)
+
+set_target_properties(kuromoji_build_dict PROPERTIES ENABLE_EXPORTS 1)
+
+if (COMPILER_CLANG)
+ target_compile_options(kuromoji_build_dict PRIVATE
+ -Wno-implicit-int-conversion
+ -Wno-shorten-64-to-32
+ )
+endif()
+
+target_link_libraries(kuromoji_build_dict
+ ${DORIS_LINK_LIBS}
+)
+
+# `ninja kuromoji_dict` runs the tool over the staged mecab-ipadic source and
+# (re)writes dict/kuromoji/*.bin. Point KUROMOJI_IPADIC_SRC elsewhere if the
+# source is not under the thirdparty share directory.
+set(KUROMOJI_IPADIC_SRC "${THIRDPARTY_DIR}/share/mecab-ipadic-2.7.0-20250920"
Review Comment:
fixed
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
