diff options
author | Jefim Matskin <jefimm@wix.com> | 2018-07-23 14:01:00 +0300 |
---|---|---|
committer | Jefim Matskin <jefimm@wix.com> | 2018-07-24 22:01:20 +0300 |
commit | 66986b9b77b2d699430f29c135b2b30fb2c553f6 (patch) | |
tree | 738b168ed36236fcc26ddd3213e4f8a1765db1e0 /linguistics/src/test | |
parent | ddd952a7bc5e4425cd2039bdad63491d3abf0dfe (diff) |
use com.optimaize.langdetect for lang detection
Diffstat (limited to 'linguistics/src/test')
-rw-r--r-- | linguistics/src/test/java/com/yahoo/language/simple/SimpleDetectorTestCase.java | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/linguistics/src/test/java/com/yahoo/language/simple/SimpleDetectorTestCase.java b/linguistics/src/test/java/com/yahoo/language/simple/SimpleDetectorTestCase.java index f9912f6b7a2..1905c6d98a9 100644 --- a/linguistics/src/test/java/com/yahoo/language/simple/SimpleDetectorTestCase.java +++ b/linguistics/src/test/java/com/yahoo/language/simple/SimpleDetectorTestCase.java @@ -50,6 +50,11 @@ public class SimpleDetectorTestCase { // a string from http://www.columbia.edu/kermit/utf8.html that says "I can eat glass (and it doesn't hurt me)". assertLanguage(Language.KOREAN, "\ub098\ub294 \uc720\ub9ac\ub97c \uba39\uc744 \uc218 \uc788\uc5b4\uc694. " + "\uadf8\ub798\ub3c4 \uc544\ud504\uc9c0 \uc54a\uc544\uc694"); + + // from https://ru.wikipedia.org/wiki/%D0%A0%D0%BE%D1%81%D1%81%D0%B8%D1%8F + assertLanguage(Language.RUSSIAN, "Материал из Википедии — свободной энциклопедии"); + // https://he.wikipedia.org/wiki/Yahoo! + assertLanguage(Language.HEBREW, "אתר יאהו! הוא אחד מאתרי האינטרנט הפופולריים ביותר בעולם, עם מעל 500 מיליון כניסות בכל יום"); } @Test |