From a1e50d27853b14c6a52028e60e32b8e14e28d1ad Mon Sep 17 00:00:00 2001 From: MariusArhaug Date: Thu, 4 Apr 2024 13:49:27 +0200 Subject: add comment for intention in determineScript function --- linguistics/src/main/java/com/yahoo/language/simple/SimpleTokenizer.java | 1 + 1 file changed, 1 insertion(+) (limited to 'linguistics') diff --git a/linguistics/src/main/java/com/yahoo/language/simple/SimpleTokenizer.java b/linguistics/src/main/java/com/yahoo/language/simple/SimpleTokenizer.java index fb876f5f066..75360e93729 100644 --- a/linguistics/src/main/java/com/yahoo/language/simple/SimpleTokenizer.java +++ b/linguistics/src/main/java/com/yahoo/language/simple/SimpleTokenizer.java @@ -104,6 +104,7 @@ public class SimpleTokenizer implements Tokenizer { } private TokenScript determineScript(TokenScript tokenScript, TokenScript characterScript) { + // if any character is LATIN, use that as token script; otherwise use script of first character seen. if (characterScript == TokenScript.LATIN) return TokenScript.LATIN; return tokenScript; } -- cgit v1.2.3