Packages

package root

Definition Classes: root

package com

Definition Classes: root

package github

Definition Classes: com

package vickumar1981

Definition Classes: github

package stringdistance

Provides classes for calculating distances and fuzzy match similarities between two strings.

Provides classes for calculating distances and fuzzy match similarities between two strings. Also provides implicits for using distance and fuzzy match scores as an operator, like:

val result = "abc" levenshtein "abc"

Includes functionality for phonetic comparisons between strings.

Overview

The main class to use is com.github.vickumar1981.stringdistance.StringDistance

If you include com.github.vickumar1981.stringdistance.StringConverter, you can convert/use the string distance and score functions as an operator between two strings.

To compare two strings phonetically, i.e. if they sound alike, use the com.github.vickumar1981.stringdistance.util.StringSound class.

To use in Java, please use the corresponding classes in the com.github.vickumar1981.stringdistance.util package.

Java String Distance Class: com.github.vickumar1981.stringdistance.util.StringDistance
Java String Sound Class: com.github.vickumar1981.stringdistance.util.StringSound

Class	Description
com.github.vickumar1981.stringdistance.StringDistance	Singleton class with fuzzy match scores and distances
com.github.vickumar1981.stringdistance.StringConverter	Implicit converstions between strings s1 and s2
com.github.vickumar1981.stringdistance.StringSound	Phonetic comparison between strings s1 and s2
com.github.vickumar1981.stringdistance.util.StringDistance	Java class for fuzzy match scores and distances
com.github.vickumar1981.stringdistance.util.StringSound	Java class for phonetic comparison between strings s1 and s2

Definition Classes: vickumar1981

object StringConverter

Object to extend operations to the String class.

import com.github.vickumar1981.stringdistance.StringConverter._

// Scores between two strings
val cosSimilarity: Double = "hello".cosine("chello")
val damerau: Double = "martha".damerau("marhta")
val diceCoefficient: Double = "martha".diceCoefficient("marhta")
val hamming: Double = "martha".hamming("marhta")
val jaccard: Double = "karolin".jaccard("kathrin")
val jaro: Double = "martha".jaro("marhta")
val jaroWinkler: Double = "martha".jaroWinkler("marhta")
val levenshtein: Double = "martha".levenshtein("marhta")
val needlemanWunsch: Double = "martha".needlemanWusnch("marhta")
val ngramSimilarity: Double = "karolin".nGram("kathrin")
val bigramSimilarity: Double = "karolin".nGram("kathrin", 2)
val overlap: Double = "karolin".overlap("kathrin")
val smithWaterman: Double = "martha".smithWaterman("marhta")
val smithWatermanGotoh: Double = "martha".smithWatermanGotoh("marhta")
val tversky: Double = "karolin".tversky("kathrin", 0.5)

// return a List[String] of ngram tokens
val tokens = "martha".tokens(2) // List("ma", "ar", "rt", "th", "ha")

// Distances between two strings
val damerauDist: int = "martha".damerauDist("marhta")
val hammingDist: Int = "martha".hammingDist("marhta")
val levenshteinDist: Int = "martha".levenshteinDist("marhta")
val longestCommonSeq: Int = "martha".longestCommonSeq("marhta")
val ngramDist: Int = "karolin".nGramDist("kathrin")
val bigramDist: Int = "karolin".nGramDist("kathrin", 2)

// Phonetic similarity of two strings
val metaphone: Boolean = "merci".metaphone("mercy")
val soundex: Boolean = "merci".soundex("mercy")

Definition Classes: stringdistance

StringToStringDistanceConverter

com.github.vickumar1981.stringdistance.StringConverter

StringToStringDistanceConverter

implicit class StringToStringDistanceConverter extends AnyRef

Linear Supertypes

AnyRef, Any

Ordering

Alphabetic
By Inheritance

Inherited

StringToStringDistanceConverter
AnyRef
Any

Hide All
Show All

Visibility

Public
Protected

Instance Constructors

new StringToStringDistanceConverter(s1: String)

Value Members

final def !=(arg0: Any): Boolean
Definition Classes
AnyRef → Any
final def ##(): Int
Definition Classes
AnyRef → Any
final def ==(arg0: Any): Boolean
Definition Classes
AnyRef → Any
final def asInstanceOf[T0]: T0
Definition Classes
Any
def clone(): AnyRef
Attributes
protected[lang]
Definition Classes
AnyRef
Annotations
@throws(classOf[java.lang.CloneNotSupportedException]) @native() @HotSpotIntrinsicCandidate()
def cosine(s2: String): Double
def damerau(s2: String): Double
def damerauDist(s2: String): Int
def diceCoefficient(s2: String): Double
final def eq(arg0: AnyRef): Boolean
Definition Classes
AnyRef
def equals(arg0: AnyRef): Boolean
Definition Classes
AnyRef → Any
final def getClass(): Class[_ <: AnyRef]
Definition Classes
AnyRef → Any
Annotations
@native() @HotSpotIntrinsicCandidate()
def hamming(s2: String): Double
def hammingDist(s2: String): Int
def hashCode(): Int
Definition Classes
AnyRef → Any
Annotations
@native() @HotSpotIntrinsicCandidate()
final def isInstanceOf[T0]: Boolean
Definition Classes
Any
def jaccard(s2: String, nGram: Int = 1): Double
def jaro(s2: String): Double
def jaroWinkler(s2: String, weight: Double = 0.1): Double
def levenshtein(s2: String): Double
def levenshteinDist(s2: String): Int
def longestCommonSeq(s2: String): Int
def metaphone(s2: String): Boolean
def nGram(s2: String, nGram: Int = 1): Double
def nGramDist(s2: String, nGram: Int = 1): Int
final def ne(arg0: AnyRef): Boolean
Definition Classes
AnyRef
def needlemanWunsch(s2: String, gap: ConstantGap = ConstantGap()): Double
final def notify(): Unit
Definition Classes
AnyRef
Annotations
@native() @HotSpotIntrinsicCandidate()
final def notifyAll(): Unit
Definition Classes
AnyRef
Annotations
@native() @HotSpotIntrinsicCandidate()
def overlap(s2: String, nGram: Int = 1): Double
def smithWaterman(s2: String, gap: Gap = LinearGap(gapValue = -1), windowSize: Int = Integer.MAX_VALUE): Double
def smithWatermanGotoh(s2: String, gap: ConstantGap = ConstantGap()): Double
def soundex(s2: String): Boolean
final def synchronized[T0](arg0: => T0): T0
Definition Classes
AnyRef
def toString(): String
Definition Classes
AnyRef → Any
def tokens(n: Int): List[String]
def tversky(s2: String, n: Double = 1): Double
final def wait(arg0: Long, arg1: Int): Unit
Definition Classes
AnyRef
Annotations
@throws(classOf[java.lang.InterruptedException])
final def wait(arg0: Long): Unit
Definition Classes
AnyRef
Annotations
@throws(classOf[java.lang.InterruptedException]) @native()
final def wait(): Unit
Definition Classes
AnyRef
Annotations
@throws(classOf[java.lang.InterruptedException])

Deprecated Value Members

def finalize(): Unit
Attributes
protected[lang]
Definition Classes
AnyRef
Annotations
@throws(classOf[java.lang.Throwable]) @Deprecated @deprecated
Deprecated
(Since version ) see corresponding Javadoc for more information.

Packages

Overview

StringToStringDistanceConverter

implicit class StringToStringDistanceConverter extends AnyRef

Instance Constructors

Value Members

Deprecated Value Members

Inherited from AnyRef

Inherited from Any

Ungrouped

Packages

Overview

StringToStringDistanceConverter

implicit class StringToStringDistanceConverter extends AnyRef

Instance Constructors

Value Members

Deprecated Value Members

Inherited from AnyRef

Inherited from Any

Ungrouped

StringToStringDistanceConverter