List of usage examples for org.apache.commons.codec.language Soundex encode
public String encode(String pString)
From source file:at.jps.sanction.core.util.TokenTool.java
public static float compareSoundex(final String text1, final String text2, final boolean fuzzy, final int minlen, final double fuzzyValue) { final Soundex encoder = new Soundex(); // TODO: in reallife make this go away // !!//from w w w .ja va 2 s. c om return (compareCheck(encoder.encode(text1), encoder.encode(text2), fuzzy, minlen, fuzzyValue)); }
From source file:com.vangent.hieos.empi.transform.SoundexTransformFunction.java
/** * * @param obj//from w w w . j av a2s.c o m * @return */ public Object transform(Object obj) { Soundex encoder = new Soundex(); return encoder.encode((String) obj); }
From source file:LanguageUsage.java
public void start() throws EncoderException, DecoderException { String word1 = "Wilson"; String word2 = "Wylson"; String foreignWord1 = "Otto"; String foreignWord2 = "Auto"; Soundex sndx = new Soundex(); DoubleMetaphone doubleMetaphone = new DoubleMetaphone(); System.err.println("Soundex Code for Wilson is: " + sndx.encode("Wilson")); System.err.println("Soundex Code for Wylson is: " + sndx.encode("Wylson")); // Use the StringEncoderComparator to compare these two Strings StringEncoderComparator comparator1 = new StringEncoderComparator(sndx); System.err//from w w w . jav a2 s .c om .println("Are Wilson and Wylson same based on Soundex? " + comparator1.compare("Wilson", "Wylson")); System.err.println("Are Auto and Otto same based on Soundex? " + comparator1.compare("Auto", "Otto")); StringEncoderComparator comparator2 = new StringEncoderComparator(doubleMetaphone); System.err .println("Are Auto and Otto same based on DoubleMetaphone? " + comparator2.compare("Auto", "Otto")); System.err.println( "Double Metaphone primary code for Schmidt: " + doubleMetaphone.doubleMetaphone("Schmidt")); System.err.println( "Double Metaphone secondary code for Schmidt: " + doubleMetaphone.doubleMetaphone("Schmidt", true)); }
From source file:com.medigy.persist.model.person.Person.java
@Transient public String createSoundexName(final String name) { // using default US_ENGLISH_MAPPING for now Soundex soundex = new Soundex(); return soundex.encode(name); }
From source file:org.emau.icmvc.ganimed.epix.deduplication.impl.DeduplicationEngineTest.java
@Test public void testColognePhonetic() throws EncoderException { Soundex sx = new Soundex(); ColognePhonetic cp = new ColognePhonetic(); //FellegiSunterAlgorithm fsa = new FellegiSunterAlgorithm<String>(); String toBlock = "Karl-Heinz"; String candidate = "Katl-Heinz"; System.out.println("Cologne Phonetik PCODE1: " + cp.colognePhonetic(toBlock)); System.out.println("Cologne Phonetik PCODE2: " + cp.colognePhonetic(candidate)); System.out.println("Soundex PCODE1: " + sx.encode(toBlock)); System.out.println("Soundex PCODE2: " + sx.encode(candidate)); System.out.println("Soundex PCODE1: " + sx.encode(toBlock)); System.out.println("Soundex PCODE2: " + sx.encode(candidate)); //System.out.println("FellegiSunter PCODE1: " + fsa); boolean bool = cp.isEncodeEqual(toBlock, candidate); System.out.println("Blocking: " + toBlock + " " + candidate + " " + bool); System.out.println("Decition " + bool + " " + (bool ? 1 : 0)); /*/*from w ww. j a v a 2s. c om*/ PreprocessingStrategy<Patient> ps = new CommonPreprocessor<Patient>(); ps.preprocess(cp); DeduplicationStrategy<Patient> ds = new FellegiSunterAlgorithm<Patient>(); ds.setMatchingConfiguration(matchingConfiguration); ds.match(toMatch, candidate) */ }
From source file:org.folg.names.score.CoderTest.java
public void testSoundex() throws Exception { Soundex soundex = new Soundex(); assertEquals(soundex.encode("john"), soundex.encode("jim")); assertEquals(soundex.encode("john"), soundex.encode("june")); assertEquals(soundex.encode("john"), soundex.encode("jane")); assertNotSame(soundex.encode("john"), soundex.encode("johannes")); assertEquals(soundex.encode("john"), soundex.encode("johan")); assertNotSame(soundex.encode("johan"), soundex.encode("johannes")); }
From source file:patientlinkage.Util.Util.java
public static String[][] readAndProcessCSV(String FileName, int records_num) { String[][] data1 = null;/*from w w w. j av a2 s . c om*/ int properties_num = 6; Soundex sdx = new Soundex(); try (CSVReader reader = new CSVReader(new FileReader(FileName))) { String[] nextLine; data1 = new String[records_num][properties_num]; reader.readNext(); int ind = 0; while ((nextLine = reader.readNext()) != null && ind < records_num) { data1[ind][0] = nextLine[1].toLowerCase(); data1[ind][1] = nextLine[2].toLowerCase(); data1[ind][2] = sdx.encode(nextLine[1]).toLowerCase(); data1[ind][3] = sdx.encode(nextLine[2]).toLowerCase(); data1[ind][4] = nextLine[6].replaceAll("-", ""); data1[ind][5] = nextLine[11].replaceAll("-", ""); ind++; } } catch (FileNotFoundException ex) { Logger.getLogger(PatientLinkageGadget.class.getName()).log(Level.SEVERE, null, ex); } catch (IOException ex) { Logger.getLogger(PatientLinkageGadget.class.getName()).log(Level.SEVERE, null, ex); } return data1; }