commit 54ed7e756c7ce3448537acb49cb10d4a71285308
author Akron <nils@diewald-online.de> Tue Jan 04 12:05:00 2022 +0100
committer Akron <nils@diewald-online.de> Tue Jan 04 12:05:00 2022 +0100
tree 01db05945d3462599a8254de8c0852b645d35807
parent d0c6e10aaaabd3466235829c490ca5dfecb2bc1b

Fix handling of "z.B."

Change-Id: Ie419cae80f16443c4f3f656fe827023d00c6bc12

src/tokenizer.xfst

diff --git a/src/tokenizer.xfst b/src/tokenizer.xfst
index ccc27c1..fb97c5c 100644
--- a/src/tokenizer.xfst
+++ b/src/tokenizer.xfst
@@ -129,7 +129,7 @@
 
 ! acronyms: U.S.A., I.B.M., etc.
 ! use a post-filter to remove dots
-define AcronymDep Letter %. [Letter %.]+;
+define AcronymDep Letter %. Letter %. [Letter %.]+;
 
 define Dot "."|[["["|"("] "d" "o" "t" [")"|"]"]] .o. Caseinsensitive;
 define At "@"|[["["|"("] "a" "t" [")"|"]"]] .o. Caseinsensitive;