public class ImprovedWordTokenizer extends AbstractWordTokenizerImpl
EXPLIZIT_CUT, objAbbrevList, strAbbrevListFile| Constructor and Description |
|---|
ImprovedWordTokenizer()
Creates a new instance of DefaultWordTokenizer
|
| Modifier and Type | Method and Description |
|---|---|
protected int |
detectSequenceOfDot(String strWord) |
String |
execute(String strLine) |
protected boolean |
isNumber(String strWord) |
protected boolean |
isSequenceOfDot(String strWord) |
protected boolean |
needsNumberSplit(String strWord) |
protected boolean |
needsSplit(String strWord) |
protected String |
processDotAsPrefix(String strWord) |
protected String |
processDotAsSuffix(String strWord) |
protected String |
processInfixApostrophe(String strWord) |
String |
processNumber(String strWord) |
protected String |
processPrefix(String strWord) |
protected String |
processSingleNumber(String strWord) |
protected String |
processSuffix(String strWord) |
protected String |
processSuffix2(String strWord) |
void |
setBoolReplaceNumbers(boolean boolReplaceNumbers) |
getWhiteSpaceBeforeDot, getWhitespacePositionspublic ImprovedWordTokenizer()
public String execute(String strLine)
execute in class AbstractWordTokenizerImplprotected boolean isSequenceOfDot(String strWord)
protected int detectSequenceOfDot(String strWord)
protected boolean needsSplit(String strWord)
protected boolean needsNumberSplit(String strWord)
protected boolean isNumber(String strWord)
public void setBoolReplaceNumbers(boolean boolReplaceNumbers)
Copyright © 2013. All rights reserved.