有没有任何方法可以从to向量中获得关于句子中一个词的位置和出现次数的信息?
就像这样
SELECT *
FROM get_position(to_tsvector('english', 'The Fat Rats'), to_tsquery('Rats'));将返回3
和
SELECT *
FROM get_occurrences(to_tsvector('english', 'The Fat Rats'), to_tsquery('Rats'));将返回1。
发布于 2014-08-23 16:31:04
list向量的文本表示包含特定词汇的出现列表:
test=# select to_tsvector ( 'english', 'new bar in New York' );
to_tsvector
----------------------------
'bar':2 'new':1,4 'york':5下面是基于这一点的示范功能。它接受文本参数并在内部将它们转换为ts_vector,但是可以很容易地重写为接受ts_vector。
CREATE OR REPLACE FUNCTION lexeme_occurrences (
IN _document text
, IN _word text
, IN _config regconfig
, OUT lexeme_count int
, OUT lexeme_positions int[]
) RETURNS RECORD
AS $$
DECLARE
_lexemes tsvector := to_tsvector ( _config, _document );
_searched_lexeme tsvector := strip ( to_tsvector ( _config, _word ) );
_occurences_pattern text := _searched_lexeme::text || ':([0-9,]+)';
_occurences_list text := substring ( _lexemes::text, _occurences_pattern );
BEGIN
SELECT
count ( a )
, array_agg ( a::int )
FROM regexp_split_to_table ( _occurences_list, ',' ) a
WHERE _searched_lexeme::text != '' -- preventing false positives
INTO
lexeme_count
, lexeme_positions;
RETURN;
END $$ LANGUAGE plpgsql;示例用法:
select * from lexeme_occurrences ( 'The Fat Rats', 'rat', 'english' );
lexeme_count | lexeme_positions
--------------+-----------------
1 | {3}
(1 row)https://stackoverflow.com/questions/25445670
复制相似问题