This is an automated email from the ASF dual-hosted git repository.
morningman pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/doris.git
from 0f8b15b902 [feature](nereids) support string alias in select list
(#15369)
add 75aa00d3d0 [Feature](NGram BloomFilter Index) add new ngram bloom
filter index to speed up like query (#11579)
No new revisions were added by this update.
Summary of changes:
.clang-format-ignore | 4 +
.licenserc.yaml | 1 +
be/src/common/config.h | 1 +
be/src/olap/CMakeLists.txt | 2 +
be/src/olap/column_predicate.h | 9 +
be/src/olap/itoken_extractor.cpp | 77 ++++
be/src/olap/itoken_extractor.h | 98 +++++
be/src/olap/like_column_predicate.h | 24 +-
be/src/olap/reader.cpp | 33 ++
.../rowset/segment_v2/block_split_bloom_filter.h | 1 +
be/src/olap/rowset/segment_v2/bloom_filter.cpp | 6 +-
be/src/olap/rowset/segment_v2/bloom_filter.h | 27 +-
.../segment_v2/bloom_filter_index_reader.cpp | 2 +-
.../segment_v2/bloom_filter_index_writer.cpp | 75 ++++
.../rowset/segment_v2/bloom_filter_index_writer.h | 29 +-
be/src/olap/rowset/segment_v2/column_writer.cpp | 11 +-
be/src/olap/rowset/segment_v2/column_writer.h | 3 +
.../olap/rowset/segment_v2/ngram_bloom_filter.cpp | 74 ++++
..._filter_index_writer.h => ngram_bloom_filter.h} | 52 +--
be/src/olap/rowset/segment_v2/segment_iterator.cpp | 1 +
be/src/olap/rowset/segment_v2/segment_writer.cpp | 8 +
be/src/olap/tablet_meta.cpp | 12 +
be/src/olap/tablet_schema.cpp | 34 ++
be/src/olap/tablet_schema.h | 25 +-
be/src/util/CMakeLists.txt | 1 +
be/src/util/cityhash102/city.cc | 481 +++++++++++++++++++++
be/src/util/cityhash102/city.h | 104 +++++
be/src/util/cityhash102/citycrc.h | 48 ++
be/src/util/cityhash102/config.h | 125 ++++++
be/src/util/simd/vstring_function.h | 4 +
be/test/CMakeLists.txt | 1 +
be/test/olap/itoken_extractor_test.cpp | 78 ++++
.../rowset/segment_v2/block_bloom_filter_test.cpp | 29 ++
.../data-table/index/ngram-bloomfilter-index.md | 79 ++++
.../data-table/index/ngram-bloomfilter-index.md | 81 ++++
fe/fe-core/src/main/cup/sql_parser.cup | 15 +-
.../apache/doris/alter/SchemaChangeHandler.java | 12 +-
.../java/org/apache/doris/analysis/IndexDef.java | 38 +-
.../main/java/org/apache/doris/catalog/Index.java | 32 ++
.../apache/doris/datasource/InternalCatalog.java | 2 +
fe/fe-core/src/main/jflex/sql_scanner.flex | 1 +
gensrc/proto/olap_file.proto | 1 +
gensrc/proto/segment_v2.proto | 2 +
gensrc/thrift/Descriptors.thrift | 6 +-
44 files changed, 1690 insertions(+), 59 deletions(-)
create mode 100644 be/src/olap/itoken_extractor.cpp
create mode 100644 be/src/olap/itoken_extractor.h
create mode 100644 be/src/olap/rowset/segment_v2/ngram_bloom_filter.cpp
copy be/src/olap/rowset/segment_v2/{bloom_filter_index_writer.h =>
ngram_bloom_filter.h} (50%)
create mode 100644 be/src/util/cityhash102/city.cc
create mode 100644 be/src/util/cityhash102/city.h
create mode 100644 be/src/util/cityhash102/citycrc.h
create mode 100644 be/src/util/cityhash102/config.h
create mode 100644 be/test/olap/itoken_extractor_test.cpp
create mode 100644 docs/en/docs/data-table/index/ngram-bloomfilter-index.md
create mode 100644 docs/zh-CN/docs/data-table/index/ngram-bloomfilter-index.md
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]