Struct FulltextIndexApplier

pub struct FulltextIndexApplier {
    requests: HashMap<ColumnId, FulltextRequest>,
    index_source: IndexSource,
    bloom_filter_index_cache: Option<Arc<IndexCache<(FileId, ColumnId, Tag), BloomFilterMeta>>>,
}

FulltextIndexApplier is responsible for applying fulltext index to the provided SST files

Fields

requests: HashMap<ColumnId, FulltextRequest>

Requests to be applied.

index_source: IndexSource

The source of the index.

bloom_filter_index_cache: Option<Arc<IndexCache<(FileId, ColumnId, Tag), BloomFilterMeta>>>

Cache for bloom filter index.

Implementations

impl FulltextIndexApplier

pub fn new( region_dir: String, region_id: RegionId, store: ObjectStore, requests: HashMap<ColumnId, FulltextRequest>, puffin_manager_factory: PuffinManagerFactory, ) -> Self

Creates a new FulltextIndexApplier.

pub fn with_file_cache(self, file_cache: Option<Arc<FileCache>>) -> Self

Sets the file cache.

pub fn with_puffin_metadata_cache( self, puffin_metadata_cache: Option<PuffinMetadataCacheRef>, ) -> Self

Sets the puffin metadata cache.

pub fn with_bloom_filter_cache( self, bloom_filter_index_cache: Option<Arc<IndexCache<(FileId, ColumnId, Tag), BloomFilterMeta>>>, ) -> Self

Sets the bloom filter cache.

impl FulltextIndexApplier

pub async fn apply_fine( &self, file_id: FileId, file_size_hint: Option<u64>, ) -> Result<Option<BTreeSet<RowId>>>

Applies fine-grained fulltext index to the specified SST file. Returns the row ids that match the queries.

async fn apply_fine_one_column( &self, file_size_hint: Option<u64>, file_id: FileId, column_id: ColumnId, request: &FulltextRequest, ) -> Result<Option<BTreeSet<RowId>>>

impl FulltextIndexApplier

pub async fn apply_coarse( &self, file_id: FileId, file_size_hint: Option<u64>, row_groups: impl Iterator<Item = (usize, bool)>, ) -> Result<Option<Vec<(usize, Vec<Range<usize>>)>>>

Applies coarse-grained fulltext index to the specified SST file. Returns (row group id -> ranges) that match the queries.

async fn apply_coarse_one_column( &self, file_id: FileId, file_size_hint: Option<u64>, column_id: ColumnId, terms: &[FulltextTerm], output: &mut [(usize, Vec<Range<usize>>)], ) -> Result<bool>

fn init_coarse_output( row_groups: impl Iterator<Item = (usize, bool)>, ) -> (Vec<(usize, Range<usize>)>, Vec<(usize, Vec<Range<usize>>)>)

Initializes the coarse output. Must call adjust_coarse_output after applying bloom filters.

row_groups is a list of (row group length, whether to search).

Returns (input, output):

• input is a list of (row group index to search, row group range based on start of the file).
• output is a list of (row group index to search, row group ranges based on start of the file).

fn adjust_coarse_output( input: Vec<(usize, Range<usize>)>, output: &mut Vec<(usize, Vec<Range<usize>>)>, )

Adjusts the coarse output. Makes the output ranges based on row group start.

fn terms_to_predicates( terms: &[FulltextTerm], config: &Config, ) -> Vec<InListPredicate>

Converts terms to predicates.

Split terms by non-alphanumeric characters and convert them to lowercase if case-insensitive. Multiple terms are combined with AND semantics.