7e38198287
The SQLite tokeniser does not deal with scripts that do not use spaces for word breaking (CJK, Thai, etc), thus searching in those languages does not work well. This adds a custom SQLite tokeniser based on ICU that breaks words for all languages supported by that library, and uses NFKC_Casefold normalisation to handle normalisation, case folding, and dropping of ignorable characters. Fixes #121
19 lines
303 B
SQL
19 lines
303 B
SQL
--
|
|
-- Convert full-text search from FTS3/4 to FTS5
|
|
--
|
|
|
|
DROP TABLE IF EXISTS MessageSearchTable;
|
|
|
|
CREATE VIRTUAL TABLE MessageSearchTable USING fts5(
|
|
body,
|
|
attachments,
|
|
subject,
|
|
"from",
|
|
receivers,
|
|
cc,
|
|
bcc,
|
|
flags,
|
|
|
|
tokenize="geary_tokeniser",
|
|
prefix="2,4,6,8,10"
|
|
)
|