Author: ggregory
Date: Wed Nov 28 20:57:07 2012
New Revision: 1414916
URL: http://svn.apache.org/viewvc?rev=1414916&view=rev
Log:
<action dev="ggregory" type="add" issue="CODEC-161" due-to="crice">Add Match
Rating Approach (MRA) phonetic algorithm encoder.</action>
Added:
commons/proper/codec/trunk/src/main/java/org/apache/commons/codec/language/MatchRatingApproachEncoder.java
(with props)
commons/proper/codec/trunk/src/test/java/org/apache/commons/codec/language/MatchRatingApproachEncoderTest.java
(with props)
Modified:
commons/proper/codec/trunk/pom.xml
commons/proper/codec/trunk/src/changes/changes.xml
Modified: commons/proper/codec/trunk/pom.xml
URL:
http://svn.apache.org/viewvc/commons/proper/codec/trunk/pom.xml?rev=1414916&r1=1414915&r2=1414916&view=diff
==============================================================================
--- commons/proper/codec/trunk/pom.xml (original)
+++ commons/proper/codec/trunk/pom.xml Wed Nov 28 20:57:07 2012
@@ -190,6 +190,13 @@ limitations under the License.
<role>Beider-Morse phonetic matching</role>
</roles>
</contributor>
+ <contributor>
+ <name>Colm Rice</name>
+ <email>colm_rice at hotmail dot com</email>
+ <roles>
+ <role>Submitted Match Rating Approach (MRA) phonetic encoder and tests
[CODEC-161]</role>
+ </roles>
+ </contributor>
</contributors>
<!-- Codec should depend on very little -->
<dependencies>
Modified: commons/proper/codec/trunk/src/changes/changes.xml
URL:
http://svn.apache.org/viewvc/commons/proper/codec/trunk/src/changes/changes.xml?rev=1414916&r1=1414915&r2=1414916&view=diff
==============================================================================
--- commons/proper/codec/trunk/src/changes/changes.xml (original)
+++ commons/proper/codec/trunk/src/changes/changes.xml Wed Nov 28 20:57:07 2012
@@ -48,6 +48,7 @@ The <action> type attribute can be add,u
</release>
-->
<release version="1.8" date="TBA" description="Feature and fix release.">
+ <action dev="ggregory" type="add" issue="CODEC-161" due-to="crice">Add
Match Rating Approach (MRA) phonetic algorithm encoder.</action>
<action dev="ggregory" type="fix" issue="CODEC-163"
due-to="leo141">ColognePhonetic encoder unneccessarily creates many char arrays
on every loop run.</action>
<action dev="sebb" type="fix"
issue="CODEC-160">Base64.encodeBase64URLSafeString doesn't add padding
characters at the end.</action>
</release>
Added:
commons/proper/codec/trunk/src/main/java/org/apache/commons/codec/language/MatchRatingApproachEncoder.java
URL:
http://svn.apache.org/viewvc/commons/proper/codec/trunk/src/main/java/org/apache/commons/codec/language/MatchRatingApproachEncoder.java?rev=1414916&view=auto
==============================================================================
---
commons/proper/codec/trunk/src/main/java/org/apache/commons/codec/language/MatchRatingApproachEncoder.java
(added)
+++
commons/proper/codec/trunk/src/main/java/org/apache/commons/codec/language/MatchRatingApproachEncoder.java
Wed Nov 28 20:57:07 2012
@@ -0,0 +1,421 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.commons.codec.language;
+
+import java.util.Locale;
+
+import org.apache.commons.codec.EncoderException;
+import org.apache.commons.codec.StringEncoder;
+
+/**
+ * Match Rating Approach Phonetic Algorithm Developed by <CITE>Western
Airlines</CITE> in 1977.
+ *
+ * @see <a href="http://en.wikipedia.org/wiki/Match_rating_approach";>Wikipedia
- Match Rating Approach</a>
+ * @since 1.8
+ */
+public class MatchRatingApproachEncoder implements StringEncoder {
+
+ private static final String SPACE = " ";
+
+ private static final String EMPTY = "";
+
+ /**
+ * Constants used mainly for the min rating value.
+ */
+ private static final int ONE = 1, TWO = 2, THREE = 3, FOUR = 4, FIVE = 5,
SIX = 6, SEVEN = 7, EIGHT = 8, ELEVEN = 11, TWELVE = 12;
+
+ /**
+ * The plain letter equivalent of the accented letters.
+ */
+ private static final String PLAIN_ASCII = "AaEeIiOoUu" // grave
+ + "AaEeIiOoUuYy" // acute
+ + "AaEeIiOoUuYy" // circumflex
+ + "AaOoNn" // tilde
+ + "AaEeIiOoUuYy" // umlaut
+ + "Aa" // ring
+ + "Cc" // cedilla
+ + "OoUu"; // double acute
+
+ /**
+ * Unicode characters corresponding to various accented letters. For
example: \u00DA is U acute etc...
+ */
+ private static final String UNICODE =
"\u00C0\u00E0\u00C8\u00E8\u00CC\u00EC\u00D2\u00F2\u00D9\u00F9"
+ +
"\u00C1\u00E1\u00C9\u00E9\u00CD\u00ED\u00D3\u00F3\u00DA\u00FA\u00DD\u00FD"
+ +
"\u00C2\u00E2\u00CA\u00EA\u00CE\u00EE\u00D4\u00F4\u00DB\u00FB\u0176\u0177" +
"\u00C3\u00E3\u00D5\u00F5\u00D1\u00F1"
+ +
"\u00C4\u00E4\u00CB\u00EB\u00CF\u00EF\u00D6\u00F6\u00DC\u00FC\u0178\u00FF" +
"\u00C5\u00E5" + "\u00C7\u00E7"
+ + "\u0150\u0151\u0170\u0171";
+
+ /**
+ * Cleans up a name: 1. Upper-cases everything 2. Removes some common
punctuation 3. Removes accents 4. Removes any
+ * spaces.
+ *
+ * <h2>API Usage</h2>
+ * <p>
+ * Consider this method private, it is package protected for unit testing
only.
+ * </p>
+ *
+ * @param name
+ * The name to be cleaned
+ * @return The cleaned name
+ */
+ String cleanName(final String name) {
+ String upperName = name.toUpperCase(Locale.ENGLISH);
+
+ String[] charsToTrim = { "\\-", "[&]", "\\'", "\\.", "[\\,]" };
+ for (String str : charsToTrim) {
+ upperName = upperName.replaceAll(str, EMPTY);
+ }
+
+ upperName = removeAccents(upperName);
+ upperName = upperName.replaceAll("\\s+", EMPTY);
+
+ return upperName;
+ }
+
+ /**
+ * Encodes an Object using the Match Rating Approach algo. Method is here
to satisfy the requirements of the
+ * Encoder interface Throws an EncoderException if input object is not of
type java.lang.String.
+ *
+ * @param pObject
+ * Object to encode
+ * @return An object (or type java.lang.String) containing the Match
Rating Approach code which corresponds to the
+ * String supplied.
+ * @throws EncoderException
+ * if the parameter supplied is not of type java.lang.String
+ */
+ @Override
+ public final Object encode(final Object pObject) throws EncoderException {
+ if (!(pObject instanceof String)) {
+ throw new EncoderException("Parameter supplied to Match Rating
Approach encoder is not of type java.lang.String");
+ }
+ return encode((String) pObject);
+ }
+
+ /**
+ * Encodes a String using the Match Rating Approach (MRA) algorithm.
+ *
+ * @param name
+ * String object to encode
+ * @return The MRA code corresponding to the String supplied
+ */
+ @Override
+ public final String encode(String name) {
+ // Bulletproof for trivial input - NINO
+ if (name == null || EMPTY.equalsIgnoreCase(name) ||
SPACE.equalsIgnoreCase(name) || name.length() == 1) {
+ return EMPTY;
+ }
+
+ // Preprocessing
+ name = cleanName(name);
+
+ // BEGIN: Actual encoding part of the algorithm...
+ // 1. Delete all vowels unless the vowel begins the word
+ name = removeVowels(name);
+
+ // 2. Remove second consonant from any double consonant
+ name = removeDoubleConsonants(name);
+
+ // 3. Reduce codex to 6 letters by joining the first 3 and last 3
letters
+ name = getFirst3Last3(name);
+
+ return name;
+ }
+
+ /**
+ * Gets the first & last 3 letters of a name (if > 6 characters) Else just
returns the name.
+ *
+ * <h2>API Usage</h2>
+ * <p>
+ * Consider this method private, it is package protected for unit testing
only.
+ * </p>
+ *
+ * @param name
+ * The string to get the substrings from
+ * @return Annexed first & last 3 letters of input word.
+ */
+ String getFirst3Last3(final String name) {
+ int nameLength = name.length();
+
+ if (nameLength > SIX) {
+ String firstThree = name.substring(0, THREE);
+ String lastThree = name.substring(nameLength - THREE, nameLength);
+ return firstThree + lastThree;
+ } else {
+ return name;
+ }
+ }
+
+ /**
+ * Obtains the min rating of the length sum of the 2 names. In essence the
larger the sum length the smaller the
+ * min rating. Values strictly from documentation.
+ *
+ * <h2>API Usage</h2>
+ * <p>
+ * Consider this method private, it is package protected for unit testing
only.
+ * </p>
+ *
+ * @param sumLength
+ * The length of 2 strings sent down
+ * @return The min rating value
+ */
+ int getMinRating(final int sumLength) {
+ int minRating = 0;
+
+ if (sumLength <= FOUR) {
+ minRating = FIVE;
+ } else if ((sumLength >= FIVE) && (sumLength <= SEVEN)) {
+ minRating = FOUR;
+ } else if ((sumLength >= EIGHT) && (sumLength <= ELEVEN)) {
+ minRating = THREE;
+ } else if (sumLength == TWELVE) {
+ minRating = TWO;
+ } else {
+ minRating = ONE; // docs said little here.
+ }
+
+ return minRating;
+ }
+
+ /**
+ * Determines if two names are homophonous via Match Rating Approach (MRA)
algorithm. It should be noted that the
+ * strings are cleaned in the same way as {@link #encode(String)}.
+ *
+ * @param name1
+ * First of the 2 strings (names) to compare
+ * @param name2
+ * Second of the 2 names to compare
+ * @return <code>true</code> if the encodings are identical
<code>false</code> otherwise.
+ */
+ public boolean isEncodeEquals(String name1, String name2) {
+ // Bulletproof for trivial input - NINO
+ if (name1 == null || EMPTY.equalsIgnoreCase(name1) ||
SPACE.equalsIgnoreCase(name1)) {
+ return false;
+ } else if (name2 == null || EMPTY.equalsIgnoreCase(name2) ||
SPACE.equalsIgnoreCase(name2)) {
+ return false;
+ } else if (name1.length() == 1 || name2.length() == 1) {
+ return false;
+ } else if (name1.equalsIgnoreCase(name2)) {
+ return true;
+ }
+
+ // Preprocessing
+ name1 = cleanName(name1);
+ name2 = cleanName(name2);
+
+ // Actual MRA Algorithm
+
+ // 1. Remove vowels
+ name1 = removeVowels(name1);
+ name2 = removeVowels(name2);
+
+ // 2. Remove double consonants
+ name1 = removeDoubleConsonants(name1);
+ name2 = removeDoubleConsonants(name2);
+
+ // 3. Reduce down to 3 letters
+ name1 = getFirst3Last3(name1);
+ name2 = getFirst3Last3(name2);
+
+ // 4. Check for length difference - if 3 or greater then no similarity
+ // comparison is done
+ if (Math.abs(name1.length() - name2.length()) >= THREE) {
+ return false;
+ }
+
+ // 5. Obtain the minimum rating value by calculating the length sum of
the
+ // encoded Strings and sending it down.
+ int sumLength = Math.abs(name1.length() + name2.length());
+ int minRating = 0;
+ minRating = getMinRating(sumLength);
+
+ // 6. Process the encoded Strings from left to right and remove any
+ // identical characters found from both Strings respectively.
+ int count = leftToRightThenRightToLeftProcessing(name1, name2);
+
+ // 7. Each PNI item that has a similarity rating equal to or greater
than
+ // the min is considered to be a good candidate match
+ return count >= minRating;
+
+ }
+
+ /**
+ * Determines if a letter is a vowel.
+ *
+ * <h2>API Usage</h2>
+ * <p>
+ * Consider this method private, it is package protected for unit testing
only.
+ * </p>
+ *
+ * @param letter
+ * The letter under investiagtion
+ * @return True if a vowel, else false
+ */
+ boolean isVowel(String letter) {
+ return letter.equalsIgnoreCase("E") || letter.equalsIgnoreCase("A") ||
letter.equalsIgnoreCase("O") || letter.equalsIgnoreCase("I") ||
+ letter.equalsIgnoreCase("U");
+ }
+
+ /**
+ * Processes the names from left to right (first) then right to left
removing identical letters in same positions.
+ * Then subtracts the longer string that remains from 6 and returns this.
+ *
+ * <h2>API Usage</h2>
+ * <p>
+ * Consider this method private, it is package protected for unit testing
only.
+ * </p>
+ *
+ * @param name1
+ * name2
+ * @return
+ */
+ int leftToRightThenRightToLeftProcessing(String name1, String name2) {
+ char[] name1Char = name1.toCharArray();
+ char[] name2Char = name2.toCharArray();
+
+ int name1Size = name1.length() - 1;
+ int name2Size = name2.length() - 1;
+
+ String name1LtRStart = EMPTY;
+ String name1LtREnd = EMPTY;
+
+ String name2RtLStart = EMPTY;
+ String name2RtLEnd = EMPTY;
+
+ for (int i = 0; i < name1Char.length; i++) {
+ if (i > name2Size) {
+ break;
+ }
+
+ name1LtRStart = name1.substring(i, i + 1);
+ name1LtREnd = name1.substring(name1Size - i, (name1Size - i) + 1);
+
+ name2RtLStart = name2.substring(i, i + 1);
+ name2RtLEnd = name2.substring(name2Size - i, (name2Size - i) + 1);
+
+ // Left to right...
+ if (name1LtRStart.equals(name2RtLStart)) {
+ name1Char[i] = ' ';
+ name2Char[i] = ' ';
+ }
+
+ // Right to left...
+ if (name1LtREnd.equals(name2RtLEnd)) {
+ name1Char[name1Size - i] = ' ';
+ name2Char[name2Size - i] = ' ';
+ }
+ }
+
+ // Char arrays -> string & remove extraneous space
+ String strA = new String(name1Char).replaceAll("\\s+", EMPTY);
+ String strB = new String(name2Char).replaceAll("\\s+", EMPTY);
+
+ // Final bit - subtract longest string from 6 and return this int value
+ if (strA.length() > strB.length()) {
+ return Math.abs(SIX - strA.length());
+ } else {
+ return Math.abs(SIX - strB.length());
+ }
+ }
+
+ /**
+ * Removes accented letters and replaces with non-accented ascii
equivalent Case is preserved.
+ *
http://www.codecodex.com/wiki/Remove_accent_from_letters_%28ex_.%C3%A9_to_e%29
+ *
+ * @param accentedWord
+ * The word that may have accents in it.
+ * @return De-accented word
+ */
+ String removeAccents(final String accentedWord) {
+ if (accentedWord == null) {
+ return null;
+ }
+
+ StringBuilder sb = new StringBuilder();
+ int n = accentedWord.length();
+
+ for (int i = 0; i < n; i++) {
+ char c = accentedWord.charAt(i);
+ int pos = UNICODE.indexOf(c);
+ if (pos > -1) {
+ sb.append(PLAIN_ASCII.charAt(pos));
+ } else {
+ sb.append(c);
+ }
+ }
+
+ return sb.toString();
+ }
+
+ /**
+ * Replaces any double consonant pair with the single letter equivalent.
+ *
+ * <h2>API Usage</h2>
+ * <p>
+ * Consider this method private, it is package protected for unit testing
only.
+ * </p>
+ *
+ * @param name
+ * String to have double consonants removed
+ * @return Single consonant word
+ */
+ String removeDoubleConsonants(String name) {
+ String[] dblCnstArray = new String[] { "BB", "CC", "DD", "FF", "GG",
"HH", "JJ", "KK", "LL", "MM", "NN", "PP", "QQ", "RR", "SS", "TT", "VV",
+ "WW", "XX", "YY", "ZZ" };
+
+ String replacedName = name.toUpperCase();
+ for (String dc : dblCnstArray) {
+ if (replacedName.contains(dc)) {
+ String singleLetter = dc.substring(0, 1);
+ replacedName = replacedName.replace(dc, singleLetter);
+ }
+ }
+
+ return replacedName;
+ }
+
+ /**
+ * Deletes all vowels unless the vowel begins the word.
+ *
+ * <h2>API Usage</h2>
+ * <p>
+ * Consider this method private, it is package protected for unit testing
only.
+ * </p>
+ *
+ * @param name
+ * The name to have vowels removed
+ * @return De-voweled word
+ */
+ String removeVowels(String name) {
+ // Extract first letter
+ String firstLetter = name.substring(0, 1);
+
+ name = name.replaceAll("A", EMPTY);
+ name = name.replaceAll("E", EMPTY);
+ name = name.replaceAll("I", EMPTY);
+ name = name.replaceAll("O", EMPTY);
+ name = name.replaceAll("U", EMPTY);
+
+ name = name.replaceAll("\\s{2,}\\b", SPACE);
+
+ // return isVowel(firstLetter) ? (firstLetter + name) : name;
+ if (isVowel(firstLetter)) {
+ return (firstLetter + name);
+ } else {
+ return name;
+ }
+ }
+}
Propchange:
commons/proper/codec/trunk/src/main/java/org/apache/commons/codec/language/MatchRatingApproachEncoder.java
------------------------------------------------------------------------------
svn:eol-style = native
Propchange:
commons/proper/codec/trunk/src/main/java/org/apache/commons/codec/language/MatchRatingApproachEncoder.java
------------------------------------------------------------------------------
svn:keywords = Id
Added:
commons/proper/codec/trunk/src/test/java/org/apache/commons/codec/language/MatchRatingApproachEncoderTest.java
URL:
http://svn.apache.org/viewvc/commons/proper/codec/trunk/src/test/java/org/apache/commons/codec/language/MatchRatingApproachEncoderTest.java?rev=1414916&view=auto
==============================================================================
---
commons/proper/codec/trunk/src/test/java/org/apache/commons/codec/language/MatchRatingApproachEncoderTest.java
(added)
+++
commons/proper/codec/trunk/src/test/java/org/apache/commons/codec/language/MatchRatingApproachEncoderTest.java
Wed Nov 28 20:57:07 2012
@@ -0,0 +1,426 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.commons.codec.language;
+
+import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertFalse;
+import static org.junit.Assert.assertTrue;
+
+import org.apache.commons.codec.StringEncoder;
+import org.apache.commons.codec.StringEncoderAbstractTest;
+import org.junit.Test;
+
+/**
+ * Series of tests for the Match Rating Approach algorithm.
+ *
+ * General naming nomeneclature for the test is of the form:
+ * GeneralMetadataOnTheTestArea_ActualTestValues_ExpectedResult
+ *
+ * An unusual value is indicated by the term "corner case"
+ */
+public class MatchRatingApproachEncoderTest extends StringEncoderAbstractTest {
+
+ private MatchRatingApproachEncoder getMatchRatingApproachEncoder() {
+ return (MatchRatingApproachEncoder) this.getStringEncoder();
+ }
+
+ // ********** BEGIN REGION - TEST SUPPORT METHODS
+
+ @Test
+ public final void testAccentRemoval_AllLower_SuccessfullyRemoved() {
+ assertEquals("aeiou",
getMatchRatingApproachEncoder().removeAccents("áéÃóú"));
+ }
+
+ @Test
+ public final void
testAccentRemoval_WithSpaces_SuccessfullyRemovedAndSpacesInvariant() {
+ assertEquals("ae io u",
getMatchRatingApproachEncoder().removeAccents("áé Ãó ú"));
+ }
+
+ @Test
+ public final void
testAccentRemoval_UpperandLower_SuccessfullyRemovedAndCaseInvariant() {
+ assertEquals("AeiOuu",
getMatchRatingApproachEncoder().removeAccents("ÃeÃÃuu"));
+ }
+
+ @Test
+ public final void
testAccentRemoval_MixedWithUnusualChars_SuccessfullyRemovedAndUnusualcharactersInvariant()
{
+ assertEquals("A-e'i.,o&u",
getMatchRatingApproachEncoder().removeAccents("Ã-e'Ã.,ó&ú"));
+ }
+
+ @Test
+ public final void testAccentRemoval_GerSpanFrenMix_SuccessfullyRemoved() {
+ assertEquals("aeouÃAEOUnNa",
getMatchRatingApproachEncoder().removeAccents("äëöüÃÃÃÃÃñÃà "));
+ }
+
+ @Test
+ public final void
testAccentRemoval_ComprehensiveAccentMix_AllSuccessfullyRemoved() {
+ assertEquals("E,E,E,E,U,U,I,I,A,A,O,e,e,e,e,u,u,i,i,a,a,o,c",
+
getMatchRatingApproachEncoder().removeAccents("Ã,Ã,Ã,Ã,Ã,Ã,Ã,Ã,Ã,Ã,Ã,è,é,ê,ë,û,ù,ï,î,à ,â,ô,ç"));
+ }
+
+ @Test
+ public final void testAccentRemovalNormalString_NoChange() {
+ assertEquals("Colorless green ideas sleep furiously",
getMatchRatingApproachEncoder().removeAccents("Colorless green ideas sleep
furiously"));
+ }
+
+ @Test
+ public final void testAccentRemoval_NINO_NoChange() {
+ assertEquals("", getMatchRatingApproachEncoder().removeAccents(""));
+ }
+
+ @Test
+ public final void
testRemoveSingleDoubleConsonants_BUBLE_RemovedSuccessfully() {
+ assertEquals("BUBLE",
getMatchRatingApproachEncoder().removeDoubleConsonants("BUBBLE"));
+ }
+
+ @Test
+ public final void
testRemoveDoubleConsonants_MISSISSIPPI_RemovedSuccessfully() {
+ assertEquals("MISISIPI",
getMatchRatingApproachEncoder().removeDoubleConsonants("MISSISSIPPI"));
+ }
+
+ @Test
+ public final void testRemoveDoubleDoubleVowel_BEETLE_NotRemoved() {
+ assertEquals("BEETLE",
getMatchRatingApproachEncoder().removeDoubleConsonants("BEETLE"));
+ }
+
+ @Test
+ public final void testIsVowel_CapitalA_ReturnsTrue() {
+ assertEquals(true, getMatchRatingApproachEncoder().isVowel("A"));
+ }
+
+ @Test
+ public final void testIsVowel_SmallD_ReturnsFalse() {
+ assertFalse(getMatchRatingApproachEncoder().isVowel("d"));
+ }
+
+ @Test
+ public final void testRemoveVowel_ALESSANDRA_Returns_ALSSNDR() {
+ assertEquals("ALSSNDR",
getMatchRatingApproachEncoder().removeVowels("ALESSANDRA"));
+ }
+
+ @Test
+ public final void testRemoveVowel__AIDAN_Returns_ADN() {
+ assertEquals("ADN",
getMatchRatingApproachEncoder().removeVowels("AIDAN"));
+ }
+
+ @Test
+ public final void testRemoveVowel__DECLAN_Returns_DCLN() {
+ assertEquals("DCLN",
getMatchRatingApproachEncoder().removeVowels("DECLAN"));
+ }
+
+ @Test
+ public final void testGetFirstLast3__ALEXANDER_Returns_Aleder() {
+ assertEquals("Aleder",
getMatchRatingApproachEncoder().getFirst3Last3("Alexzander"));
+ }
+
+ @Test
+ public final void testGetFirstLast3_PETE_Returns_PETE() {
+ assertEquals("PETE",
getMatchRatingApproachEncoder().getFirst3Last3("PETE"));
+ }
+
+ @Test
+ public final void
testleftTorightThenRightToLeft_ALEXANDER_ALEXANDRA_Returns4() {
+ assertEquals(4,
getMatchRatingApproachEncoder().leftToRightThenRightToLeftProcessing("ALEXANDER",
"ALEXANDRA"));
+ }
+
+ @Test
+ public final void
testleftTorightThenRightToLeft_EINSTEIN_MICHAELA_Returns0() {
+ assertEquals(0,
getMatchRatingApproachEncoder().leftToRightThenRightToLeftProcessing("EINSTEIN",
"MICHAELA"));
+ }
+
+ @Test
+ public final void testGetMinRating_7_Return4_Successfully() {
+ assertEquals(4, getMatchRatingApproachEncoder().getMinRating(7));
+ }
+
+ @Test
+ public final void testGetMinRating_2_Returns5_Successfully() {
+ assertEquals(5, getMatchRatingApproachEncoder().getMinRating(2));
+ }
+
+ @Test
+ public final void testGetMinRating_2_Return1_Successfully() {
+ assertEquals(1, getMatchRatingApproachEncoder().getMinRating(13));
+ }
+
+ @Test
+ public final void testcleanName_SuccessfullyClean() {
+ assertEquals("THISISATEST",
getMatchRatingApproachEncoder().cleanName("This-Ãs a t.,es &t"));
+ }
+
+ // ***** END REGION - TEST SUPPORT METHODS
+
+ // ***** BEGIN REGION - TEST GET MRA ENCODING
+
+ @Test
+ public final void testGetEncoding_HARPER_HRPR() {
+ assertEquals("HRPR", getMatchRatingApproachEncoder().encode("HARPER"));
+ }
+
+ @Test
+ public final void testGetEncoding_SMITH_to_SMTH() {
+ assertEquals("SMTH", getMatchRatingApproachEncoder().encode("Smith"));
+ }
+
+ @Test
+ public final void testGetEncoding_SMYTH_to_SMYTH() {
+ assertEquals("SMYTH", getMatchRatingApproachEncoder().encode("Smyth"));
+ }
+
+ @Test
+ public final void testGetEncoding_Space_to_Nothing() {
+ assertEquals("", getMatchRatingApproachEncoder().encode(" "));
+ }
+
+ @Test
+ public final void testGetEncoding_NoSpace_to_Nothing() {
+ assertEquals("", getMatchRatingApproachEncoder().encode(""));
+ }
+
+ @Test
+ public final void testGetEncoding_Null_to_Nothing() {
+ assertEquals("", getMatchRatingApproachEncoder().encode(null));
+ }
+
+ @Test
+ public final void testGetEncoding_One_Letter_to_Nothing() {
+ assertEquals("", getMatchRatingApproachEncoder().encode("E"));
+ }
+
+ // ***** END REGION - TEST GET MRA ENCODING
+
+ // ***** BEGIN REGION - TEST GET MRA COMPARISONS
+
+ @Test
+ public final void testCompare_SMITH_SMYTH_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("smith",
"smyth"));
+ }
+
+ @Test
+ public final void testCompare_BURNS_BOURNE_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("Burns",
"Bourne"));
+ }
+
+ @Test
+ public final void testCompare_ShortNames_AL_ED_WorksButNoMatch() {
+ assertFalse(getMatchRatingApproachEncoder().isEncodeEquals("Al",
"Ed"));
+ }
+
+ @Test
+ public final void testCompare_CATHERINE_KATHRYN_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("Catherine",
"Kathryn"));
+ }
+
+ @Test
+ public final void testCompare_BRIAN_BRYAN_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("Brian",
"Bryan"));
+ }
+
+ @Test
+ public final void testCompare_SEAN_SHAUN_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("Séan",
"Shaun"));
+ }
+
+ @Test
+ public final void
testCompare_COLM_COLIN_WithAccentsAndSymbolsAndSpaces_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("Cólm. ",
"C-olÃn"));
+ }
+
+ @Test
+ public final void testCompare_STEPHEN_STEVEN_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("Stephen",
"Steven"));
+ }
+
+ @Test
+ public final void testCompare_STEVEN_STEFAN_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("Steven",
"Stefan"));
+ }
+
+ @Test
+ public final void testCompare_STEPHEN_STEFAN_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("Stephen",
"Stefan"));
+ }
+
+ @Test
+ public final void testCompare_SAM_SAMUEL_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("Sam",
"Samuel"));
+ }
+
+ @Test
+ public final void testCompare_MICKY_MICHAEL_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("Micky",
"Michael"));
+ }
+
+ @Test
+ public final void testCompare_OONA_OONAGH_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("Oona",
"Oonagh"));
+ }
+
+ @Test
+ public final void testCompare_SOPHIE_SOFIA_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("Sophie",
"Sofia"));
+ }
+
+ @Test
+ public final void testCompare_FRANCISZEK_FRANCES_SuccessfullyMatched() {
+
assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("Franciszek",
"Frances"));
+ }
+
+ @Test
+ public final void testCompare_TOMASZ_TOM_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("Tomasz",
"tom"));
+ }
+
+ @Test
+ public final void testCompare_SmallInput_CARK_Kl_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("Kl",
"Karl"));
+ }
+
+ @Test
+ public final void testCompareNameToSingleLetter_KARL_C_DoesNotMatch() {
+ assertFalse(getMatchRatingApproachEncoder().isEncodeEquals("Karl",
"C"));
+ }
+
+ @Test
+ public final void testCompare_ZACH_ZAKARIA_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("Zach",
"Zacharia"));
+ }
+
+ @Test
+ public final void testCompare_KARL_ALESSANDRO_DoesNotMatch() {
+ assertFalse(getMatchRatingApproachEncoder().isEncodeEquals("Karl",
"Alessandro"));
+ }
+
+ @Test
+ public final void
testCompare_Forenames_UNA_OONAGH_ShouldSuccessfullyMatchButDoesNot() {
+ assertFalse(getMatchRatingApproachEncoder().isEncodeEquals("Ãna",
"Oonagh")); // Disappointing
+ }
+
+ // ***** Begin Region - Test Get Encoding - Surnames
+
+ @Test
+ public final void
testCompare_Surname_OSULLIVAN_OSUILLEABHAIN_SuccessfulMatch() {
+
assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("O'Sullivan", "Ã '
Súilleabháin"));
+ }
+
+ @Test
+ public final void
testCompare_LongSurnames_MORIARTY_OMUIRCHEARTAIGH_DoesNotSuccessfulMatch() {
+ assertFalse(getMatchRatingApproachEncoder().isEncodeEquals("Moriarty",
"OMuircheartaigh"));
+ }
+
+ @Test
+ public final void
testCompare_LongSurnames_OMUIRCHEARTAIGH_OMIREADHAIGH_SuccessfulMatch() {
+
assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("o'muireadhaigh", "Ã
'Muircheartaigh "));
+ }
+
+ @Test
+ public final void
testCompare_Surname_COOPERFLYNN_SUPERLYN_SuccessfullyMatched() {
+
assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("Cooper-Flynn",
"Super-Lyn"));
+ }
+
+ @Test
+ public final void testCompare_Surname_HAILEY_HALLEY_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("Hailey",
"Halley"));
+ }
+
+ // **** BEGIN YIDDISH/SLAVIC SECTION ****
+
+ @Test
+ public final void
testCompare_Surname_AUERBACH_UHRBACH_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("Auerbach",
"Uhrbach"));
+ }
+
+ @Test
+ public final void
testCompare_Surname_MOSKOWITZ_MOSKOVITZ_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("Moskowitz",
"Moskovitz"));
+ }
+
+ @Test
+ public final void
testCompare_Surname_LIPSHITZ_LIPPSZYC_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("LIPSHITZ",
"LIPPSZYC"));
+ }
+
+ @Test
+ public final void
testCompare_Surname_LEWINSKY_LEVINSKI_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("LEWINSKY",
"LEVINSKI"));
+ }
+
+ @Test
+ public final void
testCompare_Surname_SZLAMAWICZ_SHLAMOVITZ_SuccessfullyMatched() {
+
assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("SZLAMAWICZ",
"SHLAMOVITZ"));
+ }
+
+ @Test
+ public final void
testCompare_Surname_ROSOCHOWACIEC_ROSOKHOVATSETS_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("R o s o ch
o w a c ie c", " R o s o k ho v a ts e ts"));
+ }
+
+ @Test
+ public final void
testCompare_Surname_PRZEMYSL_PSHEMESHIL_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals(" P rz e m y
s l", " P sh e m e sh i l"));
+ }
+
+ // **** END YIDDISH/SLAVIC SECTION ****
+
+ @Test
+ public final void testCompare_PETERSON_PETERS_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("Peterson",
"Peters"));
+ }
+
+ @Test
+ public final void testCompare_MCGOWAN_MCGEOGHEGAN_SuccessfullyMatched() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("McGowan",
"Mc Geoghegan"));
+ }
+
+ @Test
+ public final void testCompare_SurnamesCornerCase_MURPHY_Space_NoMatch() {
+ assertFalse(getMatchRatingApproachEncoder().isEncodeEquals("Murphy", "
"));
+ }
+
+ @Test
+ public final void testCompare_SurnamesCornerCase_MURPHY_NoSpace_NoMatch() {
+ assertFalse(getMatchRatingApproachEncoder().isEncodeEquals("Murphy",
""));
+ }
+
+ @Test
+ public final void testCompare_SurnameCornerCase_Nulls_NoMatch() {
+ assertFalse(getMatchRatingApproachEncoder().isEncodeEquals(null,
null));
+ }
+
+ @Test
+ public final void testCompare_Surnames_MURPHY_LYNCH_NoMatchExpected() {
+ assertFalse(getMatchRatingApproachEncoder().isEncodeEquals("Murphy",
"Lynch"));
+ }
+
+ @Test
+ public final void testCompare_Forenames_SEAN_JOHN_MatchExpected() {
+ assertTrue(getMatchRatingApproachEncoder().isEncodeEquals("Sean",
"John"));
+ }
+
+ @Test
+ public final void testCompare_Forenames_SEAN_PETE_NoMatchExpected() {
+ assertFalse(getMatchRatingApproachEncoder().isEncodeEquals("Sean",
"Pete"));
+ }
+
+ @Override
+ protected StringEncoder createStringEncoder() {
+ return new MatchRatingApproachEncoder();
+ }
+
+ // ***** END REGION - TEST GET MRA COMPARISONS
+
+}
Propchange:
commons/proper/codec/trunk/src/test/java/org/apache/commons/codec/language/MatchRatingApproachEncoderTest.java
------------------------------------------------------------------------------
svn:eol-style = native
Propchange:
commons/proper/codec/trunk/src/test/java/org/apache/commons/codec/language/MatchRatingApproachEncoderTest.java
------------------------------------------------------------------------------
svn:keywords = Id
