CODEC-308: change NYSIIS encoding to not remove the first character if its an A or S

Author: Ben-Waters

src/main/java/org/apache/commons/codec/language/Nysiis.java

@@ -275,7 +275,8 @@ public String nysiis(String str) {
 
         // First character of key = first character of name.
         final StringBuilder key = new StringBuilder(str.length());
-        key.append(str.charAt(0));
+        final char firstChar = str.charAt(0);
+        key.append(firstChar);
 
         // Transcode remaining characters, incrementing by one character each time
         final char[] chars = str.toCharArray();
@@ -314,6 +315,12 @@ public String nysiis(String str) {
             if (lastChar == 'A') {
                 key.deleteCharAt(key.length() - 1);
             }
+
+            if(key.length()==0){
+                // We've removed the first character of the string. Likely because it was na S or A
+                // We should return at least the first character
+                key.append(firstChar);
+            }
         }
 
         final String string = key.toString();

src/test/java/org/apache/commons/codec/language/NysiisTest.java

@@ -140,7 +140,8 @@ public void testDropBy() throws EncoderException {
                 new String[] { "JILES", "JAL" },
                 // violates 6: if the last two characters are AY, remove A
                 new String[] { "CARRAWAY", "CARY" },       // Original: CARAY
-                new String[] { "YAMADA", "YANAD" });
+                new String[] { "YAMADA", "YANAD" },
+                new String[] { "ASH", "A"});
     }
 
     @Test