datastore/tests/performance/text_index_analysis.xml

<test>
  <settings>
      <use_skip_indexes_on_data_read>1</use_skip_indexes_on_data_read>
      <query_plan_direct_read_from_text_index>1</query_plan_direct_read_from_text_index>
      <force_data_skipping_indices>idx_s</force_data_skipping_indices>
  </settings>

  <create_query>
    CREATE TABLE t_text_index_analysis
    (
        s String,
        INDEX idx_s (s) TYPE text(tokenizer = 'splitByNonAlpha')
    )
    ENGINE = MergeTree
    ORDER BY tuple()
    SETTINGS index_granularity = 1
  </create_query>

  <fill_query>INSERT INTO t_text_index_analysis SELECT concat('common ', 'medium' || intDiv(number, 1000), ' rare' || number) FROM numbers(1000000)</fill_query>
  <fill_query>OPTIMIZE TABLE t_text_index_analysis FINAL</fill_query>

  <query>SELECT count() FROM t_text_index_analysis WHERE hasAllTokens(s, 'common')</query>
  <query>SELECT count() FROM t_text_index_analysis WHERE hasAllTokens(s, 'medium789')</query>
  <query>SELECT count() FROM t_text_index_analysis WHERE hasAllTokens(s, 'rare123456')</query>
  <query>SELECT count() FROM t_text_index_analysis WHERE hasAllTokens(s, 'nonexistent')</query>

  <query>SELECT count() FROM t_text_index_analysis WHERE hasAllTokens(s, 'common medium789')</query>
  <query>SELECT count() FROM t_text_index_analysis WHERE hasAllTokens(s, 'common rare123456')</query>
  <query>SELECT count() FROM t_text_index_analysis WHERE hasAllTokens(s, 'medium789 rare123456')</query>
  <query>SELECT count() FROM t_text_index_analysis WHERE hasAnyTokens(s, 'medium789 rare123456')</query>

  <drop_query>DROP TABLE IF EXISTS t_text_index_analysis</drop_query>
</test>