ClickHouse/tests/queries/0_stateless/01889_tokenize.sql
2022-03-24 03:55:43 +01:00

12 lines
588 B
SQL
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

SET allow_experimental_nlp_functions = 1;
SELECT splitByNonAlpha('It is quite a wonderful day, isn\'t it?');
SELECT splitByNonAlpha('There is.... so much to learn!');
SELECT splitByNonAlpha('22:00 email@tut.by');
SELECT splitByNonAlpha('Токенизация каких-либо других языков?');
SELECT splitByWhitespace('It is quite a wonderful day, isn\'t it?');
SELECT splitByWhitespace('There is.... so much to learn!');
SELECT splitByWhitespace('22:00 email@tut.by');
SELECT splitByWhitespace('Токенизация каких-либо других языков?');