Package org.languagetool.rules.ngrams

Class LanguageModelUtils

java.lang.Object

org.languagetool.rules.ngrams.LanguageModelUtils

public final class LanguageModelUtils
extends java.lang.Object

Field Summary

Fields

Modifier and Type	Field	Description
private static org.slf4j.Logger	logger

Constructor Summary

Constructors

Modifier	Constructor	Description
private	LanguageModelUtils()

Method Summary

Modifier and Type	Method	Description
static double	get3gramProbabilityFor(Language lang, LanguageModel lm, int position, AnalyzedSentence sentence, java.lang.String candidate)
(package private) static double	get3gramProbabilityFor(Language lang, LanguageModel lm, GoogleToken token, java.util.List<GoogleToken> tokens, java.lang.String term)
static double	get4gramProbabilityFor(Language lang, LanguageModel lm, int position, AnalyzedSentence sentence, java.lang.String candidate)
(package private) static double	get4gramProbabilityFor(Language lang, LanguageModel lm, GoogleToken token, java.util.List<GoogleToken> tokens, java.lang.String term)
(package private) static java.util.List<java.lang.String>	getContext(GoogleToken token, java.util.List<GoogleToken> tokens, java.lang.String newToken, int toLeft, int toRight)
(package private) static java.util.List<java.lang.String>	getContext(GoogleToken token, java.util.List<GoogleToken> tokens, java.util.List<GoogleToken> newTokens, int toLeft, int toRight)
static <T> java.util.List<T>	getContext(T token, java.util.List<T> tokens, java.util.List<T> newTokens, int toLeft, int toRight, java.util.function.Predicate<T> isWhitespace, T endToken)
(package private) static Tokenizer	getGoogleStyleWordTokenizer(Language language)	Return a tokenizer that works more like Google does for its ngram index (which doesn't seem to be properly documented).

Methods inherited from class java.lang.Object

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

Field Detail

logger

private static final org.slf4j.Logger logger

Constructor Detail

LanguageModelUtils

private LanguageModelUtils()

Method Detail

getGoogleStyleWordTokenizer

static Tokenizer getGoogleStyleWordTokenizer(Language language)

Return a tokenizer that works more like Google does for its ngram index (which doesn't seem to be properly documented).

getContext

static java.util.List<java.lang.String> getContext(GoogleToken token,
                                                   java.util.List<GoogleToken> tokens,
                                                   java.lang.String newToken,
                                                   int toLeft,
                                                   int toRight)

getContext

static java.util.List<java.lang.String> getContext(GoogleToken token,
                                                   java.util.List<GoogleToken> tokens,
                                                   java.util.List<GoogleToken> newTokens,
                                                   int toLeft,
                                                   int toRight)

getContext

public static <T> java.util.List<T> getContext(T token,
                                               java.util.List<T> tokens,
                                               java.util.List<T> newTokens,
                                               int toLeft,
                                               int toRight,
                                               java.util.function.Predicate<T> isWhitespace,
                                               T endToken)

get3gramProbabilityFor

public static double get3gramProbabilityFor(Language lang,
                                            LanguageModel lm,
                                            int position,
                                            AnalyzedSentence sentence,
                                            java.lang.String candidate)

get4gramProbabilityFor

public static double get4gramProbabilityFor(Language lang,
                                            LanguageModel lm,
                                            int position,
                                            AnalyzedSentence sentence,
                                            java.lang.String candidate)

get3gramProbabilityFor

static double get3gramProbabilityFor(Language lang,
                                     LanguageModel lm,
                                     GoogleToken token,
                                     java.util.List<GoogleToken> tokens,
                                     java.lang.String term)

get4gramProbabilityFor

static double get4gramProbabilityFor(Language lang,
                                     LanguageModel lm,
                                     GoogleToken token,
                                     java.util.List<GoogleToken> tokens,
                                     java.lang.String term)