Documentation of 'org.ujmp.core.text.TextUtil' Java class
TextUtil
org.ujmp.core.text

Class TextUtil



  • public abstract class TextUtil
    extends java.lang.Object
    • Constructor Detail

      • TextUtil

        public TextUtil()
    • Method Detail

      • getCharacterFrequencies

        public static final DenseDoubleMatrix2D getCharacterFrequencies(java.lang.String s,
                                                                        char... validCharacters)
      • splitLineIntoSentences

        public static final java.util.List<java.lang.String> splitLineIntoSentences(java.lang.String line)
      • splitTextIntoObjects

        public static final DefaultTextBlock splitTextIntoObjects(java.lang.String text)
      • createWordTrigrams

        public static final java.util.List<java.util.List<java.lang.String>> createWordTrigrams(java.lang.String text)
      • splitTextIntoLines

        public static final java.util.List<java.lang.String> splitTextIntoLines(java.lang.String text)
      • createWordBigrams

        public static final java.util.List<java.util.List<java.lang.String>> createWordBigrams(java.lang.String text)
      • createWordUnigrams

        public static final java.util.List<java.lang.String> createWordUnigrams(java.lang.String text,
                                                                                int ngramSize)
      • getWordBigramCounts

        public static java.util.Map<java.util.List<java.lang.String>,java.lang.Integer> getWordBigramCounts(java.lang.String text)
      • getWordUnigramCounts

        public static java.util.Map<java.lang.String,java.lang.Integer> getWordUnigramCounts(java.lang.String text,
                                                                                             int ngramSize)
      • splitSentenceIntoTokens

        public static final java.util.List<java.lang.String> splitSentenceIntoTokens(java.lang.String sentence,
                                                                                     int ngramSize)
      • createWordBigrams

        public static final java.util.List<java.util.List<java.lang.String>> createWordBigrams(java.util.List<java.lang.String> words)
      • createWordTrigrams

        public static final java.util.List<java.util.List<java.lang.String>> createWordTrigrams(java.util.List<java.lang.String> words)
      • endsWithAbbreviation

        public static boolean endsWithAbbreviation(java.lang.String string)
      • getCharacterBigramFrequencies

        public static final Matrix getCharacterBigramFrequencies(java.lang.String s,
                                                                 char... validCharacters)
      • getCharacterTrigramFrequencies

        public static final Matrix getCharacterTrigramFrequencies(java.lang.String s,
                                                                  char... validCharacters)
      • createBagOfWordsVector

        public static final Matrix createBagOfWordsVector(java.lang.String string,
                                                          java.util.List<java.lang.String> dictionary)
      • convertSentenceToTextTokens

        public static java.util.Collection<TextToken> convertSentenceToTextTokens(java.lang.String sentence)
      • convertToTextBlockToSentences

        public static java.util.Collection<TextSentence> convertToTextBlockToSentences(java.lang.String text)
      • splitTextIntoSentences

        public static java.util.List<java.lang.String> splitTextIntoSentences(java.lang.String text)
      • stringToVector

        public static Matrix stringToVector(java.lang.String string)
      • stringToVector

        public static Matrix stringToVector(java.lang.String string,
                                            int size)

DataMelt 3.0 © DataMelt by jWork.ORG

You see the box below because you did not login.