A B C D F G I J L M P R S T V

A

accept(String) - Method in class com.github.chen0040.data.text.StopWordRemoval

add(String) - Method in class com.github.chen0040.data.text.BasicVocabulary

add(String) - Method in interface com.github.chen0040.data.text.Vocabulary

addStopWord(String) - Method in class com.github.chen0040.data.text.StopWordRemoval

addStopWords(String[]) - Method in class com.github.chen0040.data.text.StopWordRemoval

addStopWords(Iterator<String>) - Method in class com.github.chen0040.data.text.StopWordRemoval

B

BasicTokenizer - Class in com.github.chen0040.data.text

Created by xschen on 9/10/15.

BasicTokenizer() - Constructor for class com.github.chen0040.data.text.BasicTokenizer

BasicVocabulary - Class in com.github.chen0040.data.text

Created by xschen on 14/8/15.

BasicVocabulary(List<String>) - Constructor for class com.github.chen0040.data.text.BasicVocabulary

BasicVocabulary() - Constructor for class com.github.chen0040.data.text.BasicVocabulary

C

clone() - Method in class com.github.chen0040.data.text.PorterStemmer

clone() - Method in class com.github.chen0040.data.text.PunctuationFilter

com.github.chen0040.data.text - package com.github.chen0040.data.text

contains(String) - Method in class com.github.chen0040.data.text.BasicVocabulary

contains(String) - Method in interface com.github.chen0040.data.text.Vocabulary

copy(PunctuationFilter) - Method in class com.github.chen0040.data.text.PunctuationFilter

D

doTokenize(String) - Static method in class com.github.chen0040.data.text.BasicTokenizer

doTokenize(List<String>) - Static method in class com.github.chen0040.data.text.BasicTokenizer

F

filter(List<String>) - Method in class com.github.chen0040.data.text.LowerCase

filter(List<String>) - Method in class com.github.chen0040.data.text.PorterStemmer

filter(List<String>) - Method in class com.github.chen0040.data.text.PunctuationFilter

filter(String) - Method in class com.github.chen0040.data.text.StopWordRemoval

filter(List<String>) - Method in class com.github.chen0040.data.text.StopWordRemoval

filter(List<String>) - Method in interface com.github.chen0040.data.text.TextFilter

G

get(int) - Method in class com.github.chen0040.data.text.BasicVocabulary

get(int) - Method in interface com.github.chen0040.data.text.Vocabulary

getFilter() - Method in class com.github.chen0040.data.text.PunctuationFilter

getLength() - Method in class com.github.chen0040.data.text.BasicVocabulary

getLength() - Method in interface com.github.chen0040.data.text.Vocabulary

getRemoveIPAddress() - Method in class com.github.chen0040.data.text.StopWordRemoval

getRemoveNumbers() - Method in class com.github.chen0040.data.text.StopWordRemoval

getStripFilter() - Method in class com.github.chen0040.data.text.PunctuationFilter

I

indexOf(String) - Method in class com.github.chen0040.data.text.BasicVocabulary

indexOf(String) - Method in interface com.github.chen0040.data.text.Vocabulary

J

join(List<String>) - Method in class com.github.chen0040.data.text.StopWordRemoval

L

load(List<String>) - Method in class com.github.chen0040.data.text.StopWordRemoval

LowerCase - Class in com.github.chen0040.data.text

Created by xschen on 9/10/15.

LowerCase() - Constructor for class com.github.chen0040.data.text.LowerCase

M

makeCopy() - Method in class com.github.chen0040.data.text.BasicVocabulary

makeCopy() - Method in class com.github.chen0040.data.text.LowerCase

makeCopy() - Method in class com.github.chen0040.data.text.StopWordRemoval

makeCopy() - Method in interface com.github.chen0040.data.text.Vocabulary

P

PorterStemmer - Class in com.github.chen0040.data.text

PorterStemmer() - Constructor for class com.github.chen0040.data.text.PorterStemmer

PunctuationFilter - Class in com.github.chen0040.data.text

Created by root on 11/5/15.

PunctuationFilter() - Constructor for class com.github.chen0040.data.text.PunctuationFilter

R

resetStopWords() - Method in class com.github.chen0040.data.text.StopWordRemoval

S

setFilter(String) - Method in class com.github.chen0040.data.text.PunctuationFilter

setRemoveIPAddress(boolean) - Method in class com.github.chen0040.data.text.StopWordRemoval

setRemoveNumbers(boolean) - Method in class com.github.chen0040.data.text.StopWordRemoval

setStripFilter(List<String>) - Method in class com.github.chen0040.data.text.PunctuationFilter

setWords(List<String>) - Method in class com.github.chen0040.data.text.BasicVocabulary

setWords(List<String>) - Method in interface com.github.chen0040.data.text.Vocabulary

Stem(String) - Static method in class com.github.chen0040.data.text.PorterStemmer

StopWordRemoval - Class in com.github.chen0040.data.text

StopWordRemoval() - Constructor for class com.github.chen0040.data.text.StopWordRemoval

T

TextFilter - Interface in com.github.chen0040.data.text

Created by xschen on 15/5/2017.

tokenize(String) - Method in class com.github.chen0040.data.text.BasicTokenizer

Tokenizes a string using the algorithms by Grefenstette (1999) and Palmer (2000).

tokenize(String) - Method in interface com.github.chen0040.data.text.Tokenizer

Tokenizer - Interface in com.github.chen0040.data.text

Created by xschen on 9/10/15.

V

Vocabulary - Interface in com.github.chen0040.data.text

Created by xschen on 14/8/15.

VocabularyTableCell - Class in com.github.chen0040.data.text

Created by xschen on 11/4/15.

VocabularyTableCell() - Constructor for class com.github.chen0040.data.text.VocabularyTableCell

A B C D F G I J L M P R S T V