public final class Condenser extends Tokenizer
Modifier and Type | Field and Description |
---|---|
java.util.LinkedHashSet<java.util.Date> |
dates_in_content |
private long |
exact_signature |
private long |
fuzzy_signature |
private java.lang.String |
fuzzy_signature_text |
private Identificator |
languageIdentificator |
flag_cat_hasapp, flag_cat_hasaudio, flag_cat_hasimage, flag_cat_haslocation, flag_cat_hasvideo, flag_cat_indexof, pseudostemming, RESULT_FLAGS, RESULT_NUMB_SENTENCES, RESULT_NUMB_WORDS, tags, wordcut, wordminsize, words
Constructor and Description |
---|
Condenser(Document document,
VocabularyScraper scraper,
boolean indexText,
boolean indexMedia,
WordCache meaningLib,
boolean doAutotagging,
boolean findDatesInContent,
int timezoneOffset) |
Modifier and Type | Method and Description |
---|---|
long |
exactSignature() |
int |
excludeWords(java.util.SortedSet<java.lang.String> stopwords) |
long |
fuzzySignature() |
java.lang.String |
fuzzySignatureText() |
private void |
insertTextToWords(SentenceReader text,
int phrase,
int flagpos,
Bitfield flagstemplate,
boolean useForLanguageIdentification,
WordCache meaningLib) |
java.lang.String |
language() |
double |
languageProbability()
get the probability of the detected language received by
language() |
static void |
main(java.lang.String[] args) |
private long fuzzy_signature
private long exact_signature
private java.lang.String fuzzy_signature_text
private final Identificator languageIdentificator
public java.util.LinkedHashSet<java.util.Date> dates_in_content
public Condenser(Document document, VocabularyScraper scraper, boolean indexText, boolean indexMedia, WordCache meaningLib, boolean doAutotagging, boolean findDatesInContent, int timezoneOffset)
private void insertTextToWords(SentenceReader text, int phrase, int flagpos, Bitfield flagstemplate, boolean useForLanguageIdentification, WordCache meaningLib)
public int excludeWords(java.util.SortedSet<java.lang.String> stopwords)
public long fuzzySignature()
public java.lang.String fuzzySignatureText()
public long exactSignature()
public java.lang.String language()
public double languageProbability()
language()
public static void main(java.lang.String[] args)