Package de.uni_mannheim.informatik.dws.melt.matching_ml.python

Class StringUtil

java.lang.Object

de.uni_mannheim.informatik.dws.melt.matching_ml.python.StringUtil

public class StringUtil
extends Object

A collection of useful String operations that can be used for matcher development.

Field Summary

Fields

Modifier and Type	Field	Description
private static Set<String>	ENGLISH_STOPWORDS	A set of English stopwords.
private static String	myFormat
private static HashMap<String,List<String>>	tokenMap

Constructor Summary

Constructors

Constructor	Description
StringUtil()

Method Summary

Modifier and Type	Method	Description
static boolean	containsMostlyNumbers(String term)
static int	damerauLevenshtein(String compOne, String compTwo)
static double	damerauLevenshteinNormalised(String a, String b)
static int	editDistance(String a, String b, boolean cased)
static double	editDistanceNormalised(String a, String b)
static String	exactLength(String in, int length)
private static double	getMaxLength(String a, String b)
private static double	getNormalised(double editDistance, double maxLength)
static String	getProcessedString(String text)
static List<String>	getTokensWithoutStopword(String text)
static boolean	isPrefix(String s1, String s2)
static boolean	isSuffix(String s1, String s2)
static List<String>	removeStopwords(List<String> tokens)
static List<String>	removeStopwords(List<String> tokens, Set<String> stopwords)
static List<String>	tokenize(String text)	Make tokens out of a String.
static String	tokenizeToString(String text)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Details

tokenMap

private static HashMap<String,List<String>> tokenMap

myFormat

private static String myFormat

ENGLISH_STOPWORDS

private static final Set<String> ENGLISH_STOPWORDS

A set of English stopwords.

Constructor Details

StringUtil

public StringUtil()

Method Details

tokenize

public static List<String> tokenize(String text)

Make tokens out of a String.

Parameters:

text - String to be tokenized.

Returns:

A list of tokens.

tokenizeToString

public static String tokenizeToString(String text)

containsMostlyNumbers

public static boolean containsMostlyNumbers(String term)

getProcessedString

public static String getProcessedString(String text)

getTokensWithoutStopword

public static List<String> getTokensWithoutStopword(String text)

removeStopwords

public static List<String> removeStopwords(List<String> tokens)

removeStopwords

public static List<String> removeStopwords(List<String> tokens,
Set<String> stopwords)

editDistance

public static int editDistance(String a,
String b,
boolean cased)

editDistanceNormalised

public static double editDistanceNormalised(String a,
String b)

isSuffix

public static boolean isSuffix(String s1,
String s2)

isPrefix

public static boolean isPrefix(String s1,
String s2)

damerauLevenshtein

public static int damerauLevenshtein(String compOne,
String compTwo)

damerauLevenshteinNormalised

public static double damerauLevenshteinNormalised(String a,
String b)

exactLength

public static String exactLength(String in,
int length)

getNormalised

private static double getNormalised(double editDistance,
double maxLength)

getMaxLength

private static double getMaxLength(String a,
String b)