001 /*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements. See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License. You may obtain a copy of the License at
008 *
009 * http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017
018 package org.apache.commons.codec.language;
019
020 import org.apache.commons.codec.EncoderException;
021 import org.apache.commons.codec.StringEncoderAbstractTest;
022 import org.junit.Assert;
023 import org.junit.Test;
024
025 /**
026 * Tests {@link Nysiis}
027 *
028 * @since 1.7
029 * @version $Id: NysiisTest.html 889935 2013-12-11 05:05:13Z ggregory $
030 */
031 public class NysiisTest extends StringEncoderAbstractTest<Nysiis> {
032
033 private final Nysiis fullNysiis = new Nysiis(false);
034
035 /**
036 * Takes an array of String pairs where each pair's first element is the input and the second element the expected
037 * encoding.
038 *
039 * @param testValues
040 * an array of String pairs where each pair's first element is the input and the second element the
041 * expected encoding.
042 * @throws EncoderException
043 */
044 private void assertEncodings(final String[]... testValues) throws EncoderException {
045 for (final String[] arr : testValues) {
046 Assert.assertEquals("Problem with " + arr[0], arr[1], this.fullNysiis.encode(arr[0]));
047 }
048 }
049
050 @Override
051 protected Nysiis createStringEncoder() {
052 return new Nysiis();
053 }
054
055 private void encodeAll(final String[] strings, final String expectedEncoding) {
056 for (final String string : strings) {
057 Assert.assertEquals("Problem with " + string, expectedEncoding, getStringEncoder().encode(string));
058 }
059 }
060
061 @Test
062 public void testBran() {
063 encodeAll(new String[] { "Brian", "Brown", "Brun" }, "BRAN");
064 }
065
066 @Test
067 public void testCap() {
068 this.encodeAll(new String[] { "Capp", "Cope", "Copp", "Kipp" }, "CAP");
069 }
070
071 @Test
072 public void testDad() {
073 // Data Quality and Record Linkage Techniques P.121 claims this is DAN,
074 // but it should be DAD, verified also with dropby.com
075 this.encodeAll(new String[] { "Dent" }, "DAD");
076 }
077
078 @Test
079 public void testDan() {
080 this.encodeAll(new String[] { "Dane", "Dean", "Dionne" }, "DAN");
081 }
082
083 /**
084 * Tests data gathered from around the internet.
085 *
086 * @see <a href="http://www.dropby.com/NYSIISTextStrings.html">http://www.dropby.com/NYSIISTextStrings.html</a>
087 * @throws EncoderException
088 */
089 @Test
090 public void testDropBy() throws EncoderException {
091 // Explanation of differences between this implementation and the one at dropby.com is
092 // prepended to the test string. The referenced rules refer to the outlined steps the
093 // class description for Nysiis.
094
095 this.assertEncodings(
096 // 1. Transcode first characters of name
097 new String[] { "MACINTOSH", "MCANT" },
098 // violates 4j: the second N should not be added, as the first
099 // key char is already a N
100 new String[] { "KNUTH", "NAT" }, // Original: NNAT; modified: NATH
101 // O and E are transcoded to A because of rule 4a
102 // H also to A because of rule 4h
103 // the N gets mysteriously lost, maybe because of a wrongly implemented rule 4h
104 // that skips the next char in such a case?
105 // the remaining A is removed because of rule 7
106 new String[] { "KOEHN", "CAN" }, // Original: C
107 // violates 4j: see also KNUTH
108 new String[] { "PHILLIPSON", "FALAPSAN" }, // Original: FFALAP[SAN]
109 // violates 4j: see also KNUTH
110 new String[] { "PFEISTER", "FASTAR" }, // Original: FFASTA[R]
111 // violates 4j: see also KNUTH
112 new String[] { "SCHOENHOEFT", "SANAFT" }, // Original: SSANAF[T]
113 // 2. Transcode last characters of name:
114 new String[] { "MCKEE", "MCY" },
115 new String[] { "MACKIE", "MCY" },
116 new String[] { "HEITSCHMIDT", "HATSNAD" },
117 new String[] { "BART", "BAD" },
118 new String[] { "HURD", "HAD" },
119 new String[] { "HUNT", "HAD" },
120 new String[] { "WESTERLUND", "WASTARLAD" },
121 // 4. Transcode remaining characters by following these rules,
122 // incrementing by one character each time:
123 new String[] { "CASSTEVENS", "CASTAFAN" },
124 new String[] { "VASQUEZ", "VASG" },
125 new String[] { "FRAZIER", "FRASAR" },
126 new String[] { "BOWMAN", "BANAN" },
127 new String[] { "MCKNIGHT", "MCNAGT" },
128 new String[] { "RICKERT", "RACAD" },
129 // violates 5: the last S is not removed
130 // when comparing to DEUTS, which is phonetically similar
131 // the result it also DAT, which is correct for DEUTSCH too imo
132 new String[] { "DEUTSCH", "DAT" }, // Original: DATS
133 new String[] { "WESTPHAL", "WASTFAL" },
134 // violates 4h: the H should be transcoded to S and thus ignored as
135 // the first key character is also S
136 new String[] { "SHRIVER", "SRAVAR" }, // Original: SHRAVA[R]
137 // same as KOEHN, the L gets mysteriously lost
138 new String[] { "KUHL", "CAL" }, // Original: C
139 new String[] { "RAWSON", "RASAN" },
140 // If last character is S, remove it
141 new String[] { "JILES", "JAL" },
142 // violates 6: if the last two characters are AY, remove A
143 new String[] { "CARRAWAY", "CARY" }, // Original: CARAY
144 new String[] { "YAMADA", "YANAD" });
145 }
146
147 @Test
148 public void testFal() {
149 this.encodeAll(new String[] { "Phil" }, "FAL");
150 }
151
152 /**
153 * Tests data gathered from around the internets.
154 *
155 * @throws EncoderException
156 */
157 @Test
158 public void testOthers() throws EncoderException {
159 this.assertEncodings(
160 new String[] { "O'Daniel", "ODANAL" },
161 new String[] { "O'Donnel", "ODANAL" },
162 new String[] { "Cory", "CARY" },
163 new String[] { "Corey", "CARY" },
164 new String[] { "Kory", "CARY" },
165 //
166 new String[] { "FUZZY", "FASY" });
167 }
168
169 /**
170 * Tests rule 1: Translate first characters of name: MAC → MCC, KN → N, K → C, PH, PF → FF, SCH → SSS
171 *
172 * @throws EncoderException
173 */
174 @Test
175 public void testRule1() throws EncoderException {
176 this.assertEncodings(
177 new String[] { "MACX", "MCX" },
178 new String[] { "KNX", "NX" },
179 new String[] { "KX", "CX" },
180 new String[] { "PHX", "FX" },
181 new String[] { "PFX", "FX" },
182 new String[] { "SCHX", "SX" });
183 }
184
185 /**
186 * Tests rule 2: Translate last characters of name: EE → Y, IE → Y, DT, RT, RD, NT, ND → D
187 *
188 * @throws EncoderException
189 */
190 @Test
191 public void testRule2() throws EncoderException {
192 this.assertEncodings(
193 new String[] { "XEE", "XY" },
194 new String[] { "XIE", "XY" },
195 new String[] { "XDT", "XD" },
196 new String[] { "XRT", "XD" },
197 new String[] { "XRD", "XD" },
198 new String[] { "XNT", "XD" },
199 new String[] { "XND", "XD" });
200 }
201
202 /**
203 * Tests rule 4.1: EV → AF else A, E, I, O, U → A
204 *
205 * @throws EncoderException
206 */
207 @Test
208 public void testRule4Dot1() throws EncoderException {
209 this.assertEncodings(
210 new String[] { "XEV", "XAF" },
211 new String[] { "XAX", "XAX" },
212 new String[] { "XEX", "XAX" },
213 new String[] { "XIX", "XAX" },
214 new String[] { "XOX", "XAX" },
215 new String[] { "XUX", "XAX" });
216 }
217
218 /**
219 * Tests rule 4.2: Q → G, Z → S, M → N
220 *
221 * @throws EncoderException
222 */
223 @Test
224 public void testRule4Dot2() throws EncoderException {
225 this.assertEncodings(
226 new String[] { "XQ", "XG" },
227 new String[] { "XZ", "X" },
228 new String[] { "XM", "XN" });
229 }
230
231 /**
232 * Tests rule 5: If last character is S, remove it.
233 *
234 * @throws EncoderException
235 */
236 @Test
237 public void testRule5() throws EncoderException {
238 this.assertEncodings(
239 new String[] { "XS", "X" },
240 new String[] { "XSS", "X" });
241 }
242
243 /**
244 * Tests rule 6: If last characters are AY, replace with Y.
245 *
246 * @throws EncoderException
247 */
248 @Test
249 public void testRule6() throws EncoderException {
250 this.assertEncodings(
251 new String[] { "XAY", "XY" },
252 new String[] { "XAYS", "XY" }); // Rules 5, 6
253 }
254
255 /**
256 * Tests rule 7: If last character is A, remove it.
257 *
258 * @throws EncoderException
259 */
260 @Test
261 public void testRule7() throws EncoderException {
262 this.assertEncodings(
263 new String[] { "XA", "X" },
264 new String[] { "XAS", "X" }); // Rules 5, 7
265 }
266 @Test
267 public void testSnad() {
268 // Data Quality and Record Linkage Techniques P.121 claims this is SNAT,
269 // but it should be SNAD
270 this.encodeAll(new String[] { "Schmidt" }, "SNAD");
271 }
272
273 @Test
274 public void testSnat() {
275 this.encodeAll(new String[] { "Smith", "Schmit" }, "SNAT");
276 }
277
278 @Test
279 public void testSpecialBranches() {
280 this.encodeAll(new String[] { "Kobwick" }, "CABWAC");
281 this.encodeAll(new String[] { "Kocher" }, "CACAR");
282 this.encodeAll(new String[] { "Fesca" }, "FASC");
283 this.encodeAll(new String[] { "Shom" }, "SAN");
284 this.encodeAll(new String[] { "Ohlo" }, "OL");
285 this.encodeAll(new String[] { "Uhu" }, "UH");
286 this.encodeAll(new String[] { "Um" }, "UN");
287 }
288
289 @Test
290 public void testTranan() {
291 this.encodeAll(new String[] { "Trueman", "Truman" }, "TRANAN");
292 }
293
294 @Test
295 public void testTrueVariant() {
296 final Nysiis encoder = new Nysiis(true);
297
298 final String encoded = encoder.encode("WESTERLUND");
299 Assert.assertTrue(encoded.length() <= 6);
300 Assert.assertEquals("WASTAR", encoded);
301 }
302
303 }