aboutsummaryrefslogtreecommitdiffstats
path: root/linguistics/src/main/java/com/yahoo/language/simple/SimpleTransformer.java
diff options
context:
space:
mode:
Diffstat (limited to 'linguistics/src/main/java/com/yahoo/language/simple/SimpleTransformer.java')
-rw-r--r--linguistics/src/main/java/com/yahoo/language/simple/SimpleTransformer.java25
1 files changed, 25 insertions, 0 deletions
diff --git a/linguistics/src/main/java/com/yahoo/language/simple/SimpleTransformer.java b/linguistics/src/main/java/com/yahoo/language/simple/SimpleTransformer.java
new file mode 100644
index 00000000000..409ef44986e
--- /dev/null
+++ b/linguistics/src/main/java/com/yahoo/language/simple/SimpleTransformer.java
@@ -0,0 +1,25 @@
+// Copyright 2016 Yahoo Inc. Licensed under the terms of the Apache 2.0 license. See LICENSE in the project root.
+package com.yahoo.language.simple;
+
+import com.yahoo.language.Language;
+import com.yahoo.language.process.Transformer;
+
+import java.text.Normalizer;
+import java.util.regex.Pattern;
+
+/**
+ * Converts all accented characters into their de-accented counterparts followed by their combining diacritics, then
+ * strips off the diacritics using a regex.
+ *
+ * @author <a href="mailto:simon@yahoo-inc.com">Simon Thoresen</a>
+ */
+public class SimpleTransformer implements Transformer {
+
+ private final static Pattern pattern = Pattern.compile("\\p{InCombiningDiacriticalMarks}+");
+
+ @Override
+ public String accentDrop(String input, Language language) {
+ return pattern.matcher(Normalizer.normalize(input, Normalizer.Form.NFD)).replaceAll("");
+ }
+
+}