You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@commons.apache.org by tn...@apache.org on 2014/11/04 20:49:40 UTC
svn commit: r1636703 - in /commons/proper/codec/trunk/src:
main/java/org/apache/commons/codec/language/bm/
main/resources/org/apache/commons/codec/language/bm/
test/java/org/apache/commons/codec/language/bm/
Author: tn
Date: Tue Nov 4 19:49:40 2014
New Revision: 1636703
URL: http://svn.apache.org/r1636703
Log:
[CODEC-187] Update Beider-Morse rules to v3.4.
Modified:
commons/proper/codec/trunk/src/main/java/org/apache/commons/codec/language/bm/BeiderMorseEncoder.java
commons/proper/codec/trunk/src/main/resources/org/apache/commons/codec/language/bm/ash_approx_common.txt
commons/proper/codec/trunk/src/main/resources/org/apache/commons/codec/language/bm/gen_approx_common.txt
commons/proper/codec/trunk/src/test/java/org/apache/commons/codec/language/bm/PhoneticEngineTest.java
Modified: commons/proper/codec/trunk/src/main/java/org/apache/commons/codec/language/bm/BeiderMorseEncoder.java
URL: http://svn.apache.org/viewvc/commons/proper/codec/trunk/src/main/java/org/apache/commons/codec/language/bm/BeiderMorseEncoder.java?rev=1636703&r1=1636702&r2=1636703&view=diff
==============================================================================
--- commons/proper/codec/trunk/src/main/java/org/apache/commons/codec/language/bm/BeiderMorseEncoder.java (original)
+++ commons/proper/codec/trunk/src/main/java/org/apache/commons/codec/language/bm/BeiderMorseEncoder.java Tue Nov 4 19:49:40 2014
@@ -65,7 +65,7 @@ import org.apache.commons.codec.StringEn
* Down-stream applications may wish to further process the encoding for indexing or lookup purposes, for example, by
* splitting on pipe (<code>|</code>) and indexing under each of these alternatives.
* <p>
- * <b>Note</b>: this version of the Beider-Morse encoding is equivalent with v3.3 of the reference implementation.
+ * <b>Note</b>: this version of the Beider-Morse encoding is equivalent with v3.4 of the reference implementation.
*
* @see <a href="http://stevemorse.org/phonetics/bmpm.htm">Beider-Morse Phonetic Matching</a>
* @see <a href="http://stevemorse.org/phoneticinfo.htm">Reference implementation</a>
Modified: commons/proper/codec/trunk/src/main/resources/org/apache/commons/codec/language/bm/ash_approx_common.txt
URL: http://svn.apache.org/viewvc/commons/proper/codec/trunk/src/main/resources/org/apache/commons/codec/language/bm/ash_approx_common.txt?rev=1636703&r1=1636702&r2=1636703&view=diff
==============================================================================
--- commons/proper/codec/trunk/src/main/resources/org/apache/commons/codec/language/bm/ash_approx_common.txt (original)
+++ commons/proper/codec/trunk/src/main/resources/org/apache/commons/codec/language/bm/ash_approx_common.txt Tue Nov 4 19:49:40 2014
@@ -201,7 +201,13 @@
"lEndEr" "" "$" "lYnder"
"lendEr" "" "$" "lYnder"
"lEnder" "" "$" "lYnder"
-
+
+// burg = berg
+"bUrk" "" "$" "(burk|berk)"
+"burk" "" "$" "(burk|berk)"
+"bUrg" "" "$" "(burk|berk)"
+"burg" "" "$" "(burk|berk)"
+
// CONSONANTS {z & Z; s & S} are approximately interchangeable
"s" "" "[rmnl]" "z"
"S" "" "[rmnl]" "z"
Modified: commons/proper/codec/trunk/src/main/resources/org/apache/commons/codec/language/bm/gen_approx_common.txt
URL: http://svn.apache.org/viewvc/commons/proper/codec/trunk/src/main/resources/org/apache/commons/codec/language/bm/gen_approx_common.txt?rev=1636703&r1=1636702&r2=1636703&view=diff
==============================================================================
--- commons/proper/codec/trunk/src/main/resources/org/apache/commons/codec/language/bm/gen_approx_common.txt (original)
+++ commons/proper/codec/trunk/src/main/resources/org/apache/commons/codec/language/bm/gen_approx_common.txt Tue Nov 4 19:49:40 2014
@@ -205,7 +205,17 @@
"lEndEr" "" "$" "lYnder"
"lendEr" "" "$" "lYnder"
"lEnder" "" "$" "lYnder"
-
+
+// burg = berg
+"burk" "" "$" "(burk|berk)"
+"bUrk" "" "$" "(burk|berk)"
+"burg" "" "$" "(burk|berk)"
+"bUrg" "" "$" "(burk|berk)"
+"Burk" "" "$" "(burk|berk)"
+"BUrk" "" "$" "(burk|berk)"
+"Burg" "" "$" "(burk|berk)"
+"BUrg" "" "$" "(burk|berk)"
+
// CONSONANTS {z & Z; s & S} are approximately interchangeable
"s" "" "[rmnl]" "z"
"S" "" "[rmnl]" "z"
Modified: commons/proper/codec/trunk/src/test/java/org/apache/commons/codec/language/bm/PhoneticEngineTest.java
URL: http://svn.apache.org/viewvc/commons/proper/codec/trunk/src/test/java/org/apache/commons/codec/language/bm/PhoneticEngineTest.java?rev=1636703&r1=1636702&r2=1636703&view=diff
==============================================================================
--- commons/proper/codec/trunk/src/test/java/org/apache/commons/codec/language/bm/PhoneticEngineTest.java (original)
+++ commons/proper/codec/trunk/src/test/java/org/apache/commons/codec/language/bm/PhoneticEngineTest.java Tue Nov 4 19:49:40 2014
@@ -17,7 +17,8 @@
package org.apache.commons.codec.language.bm;
-import static org.junit.Assert.*;
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertTrue;
import java.util.Arrays;
import java.util.List;
@@ -50,7 +51,13 @@ public class PhoneticEngineTest {
"(elSink|elsink|helSink|helsink|helzink|xelsink)-(banhelsink|fanhelsink|fanhelzink|vanhelsink|vanhelzink|vanjelsink)",
NameType.GENERIC,
RuleType.EXACT,
- Boolean.FALSE, TEN });
+ Boolean.FALSE, TEN },
+ new Object[] {
+ "Judenburg",
+ "iudnbYrk|iudnbirk|iudnburk|xudnbirk|xudnburk|zudnbirk|zudnburk",
+ NameType.GENERIC,
+ RuleType.APPROX,
+ Boolean.TRUE, TEN });
}
private final boolean concat;