Revert "Bug 27299: Remove tokenization for phrase register/index with ICU"

This reverts commit d446cb427c. Signed-off-by: Victor Grousset/tuxayo <victor@tuxayo.net>
2021-02-03 20:11:42 +01:00 · 2021-02-03 20:11:42 +01:00 · 56b0f9eaa4
parent c3f3015840
commit 56b0f9eaa4
1 changed files with 1 additions and 0 deletions
--- a/etc/zebradb/etc/phrases-icu.xml
+++ b/etc/zebradb/etc/phrases-icu.xml
@ -5,6 +5,7 @@
  <transliterate rule="{ Æ > ae "/>
  <!-- Remove control characters except \t\n\r -->
  <transform rule="[\x00-\x08\x0B\x0C\x0E-\x1F\x7F] Any-Remove"/>
+  <tokenize rule="l"/>
  <transform rule="[:Punctuation:] Remove"/>
  <transform rule="NFD"/>
  <transform rule="[:Nonspacing Mark:] Remove"/>