From a488424404e1bfbe9d353353f5c9d7da9959e222 Mon Sep 17 00:00:00 2001
From: Shay Banon <kimchy@gmail.com>
Date: Wed, 21 Dec 2011 03:53:44 +0200
Subject: [PATCH] Analysis: Add phonetic encodder called `bm` or
 `beider_morse`, closes #1552.

---
 pom.xml                                       |  2 +-
 .../phonetic/PhoneticTokenFilterFactory.java  | 22 +++++++++++++++++++
 2 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/pom.xml b/pom.xml
index c2d40dd6936..694918e3ab3 100644
--- a/pom.xml
+++ b/pom.xml
@@ -124,7 +124,7 @@
         <dependency>
             <groupId>commons-codec</groupId>
             <artifactId>commons-codec</artifactId>
-            <version>1.5</version>
+            <version>1.6</version>
             <scope>compile</scope>
         </dependency>
 
diff --git a/src/main/java/org/elasticsearch/index/analysis/phonetic/PhoneticTokenFilterFactory.java b/src/main/java/org/elasticsearch/index/analysis/phonetic/PhoneticTokenFilterFactory.java
index e8c4657dfe0..b90671f5519 100644
--- a/src/main/java/org/elasticsearch/index/analysis/phonetic/PhoneticTokenFilterFactory.java
+++ b/src/main/java/org/elasticsearch/index/analysis/phonetic/PhoneticTokenFilterFactory.java
@@ -21,6 +21,9 @@ package org.elasticsearch.index.analysis.phonetic;
 
 import org.apache.commons.codec.Encoder;
 import org.apache.commons.codec.language.*;
+import org.apache.commons.codec.language.bm.BeiderMorseEncoder;
+import org.apache.commons.codec.language.bm.NameType;
+import org.apache.commons.codec.language.bm.RuleType;
 import org.apache.lucene.analysis.TokenStream;
 import org.elasticsearch.ElasticSearchIllegalArgumentException;
 import org.elasticsearch.common.inject.Inject;
@@ -67,6 +70,25 @@ public class PhoneticTokenFilterFactory extends AbstractTokenFilterFactory {
             DoubleMetaphone doubleMetaphone = new DoubleMetaphone();
             doubleMetaphone.setMaxCodeLen(settings.getAsInt("max_code_len", doubleMetaphone.getMaxCodeLen()));
             this.encoder = doubleMetaphone;
+        } else if ("bm".equalsIgnoreCase(encoder) || "beider_morse".equalsIgnoreCase(encoder)) {
+            BeiderMorseEncoder bm = new BeiderMorseEncoder();
+            String ruleType = settings.get("rule_type", "approx");
+            if ("approx".equalsIgnoreCase(ruleType)) {
+                bm.setRuleType(RuleType.APPROX);
+            } else if ("exact".equalsIgnoreCase(ruleType)) {
+                bm.setRuleType(RuleType.EXACT);
+            } else {
+                throw new ElasticSearchIllegalArgumentException("No matching rule type [" + ruleType + "] for beider morse encoder");
+            }
+            String nameType = settings.get("name_type", "generic");
+            if ("GENERIC".equalsIgnoreCase(nameType)) {
+                bm.setNameType(NameType.GENERIC);
+            } else if ("ASHKENAZI".equalsIgnoreCase(nameType)) {
+                bm.setNameType(NameType.ASHKENAZI);
+            } else if ("SEPHARDIC".equalsIgnoreCase(nameType)) {
+                bm.setNameType(NameType.SEPHARDIC);
+            }
+            this.encoder = bm;
         } else {
             throw new ElasticSearchIllegalArgumentException("unknown encoder [" + encoder + "] for phonetic token filter");
         }