Package org.languagetool.tagging.de
Class GermanTagger
- java.lang.Object
-
- org.languagetool.tagging.BaseTagger
-
- org.languagetool.tagging.de.GermanTagger
-
- All Implemented Interfaces:
org.languagetool.tagging.Tagger
- Direct Known Subclasses:
SwissGermanTagger
public class GermanTagger extends org.languagetool.tagging.BaseTagger
German part-of-speech tagger, requires data file inde/german.dict
in the classpath. The POS tagset is described in tagset.txt
-
-
Field Summary
Fields Modifier and Type Field Description private GermanCompoundTokenizer
compoundTokenizer
private org.languagetool.tagging.ManualTagger
removalTagger
-
Constructor Summary
Constructors Constructor Description GermanTagger()
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description private java.util.List<org.languagetool.tagging.TaggedWord>
addStem(java.util.List<org.languagetool.tagging.TaggedWord> analyzedWordResults, java.lang.String stem)
private java.util.List<org.languagetool.AnalyzedToken>
getAnalyzedTokens(java.util.List<org.languagetool.tagging.TaggedWord> taggedWords, java.lang.String word)
private java.util.List<org.languagetool.AnalyzedToken>
getAnalyzedTokens(java.util.List<org.languagetool.tagging.TaggedWord> taggedWords, java.lang.String word, java.util.List<java.lang.String> compoundParts)
private java.util.List<org.languagetool.AnalyzedToken>
getImperativeForm(java.lang.String word, java.util.List<java.lang.String> sentenceTokens, int pos)
java.lang.String
getManualAdditionsFileName()
java.lang.String
getManualRemovalsFileName()
private org.languagetool.AnalyzedToken
getNoInfoToken(java.lang.String word)
private java.util.List<org.languagetool.AnalyzedToken>
getSubstantivatedForms(java.lang.String word, java.util.List<java.lang.String> sentenceTokens, int pos)
private void
initializeIfRequired()
@Nullable org.languagetool.AnalyzedTokenReadings
lookup(java.lang.String word)
Return only the first reading of the given word ornull
.private boolean
matchesUppercaseAdjective(java.lang.String unknownUppercaseToken)
private java.lang.String
sanitizeWord(java.lang.String word)
java.util.List<org.languagetool.tagging.TaggedWord>
tag(java.lang.String word)
java.util.List<org.languagetool.AnalyzedTokenReadings>
tag(java.util.List<java.lang.String> sentenceTokens)
java.util.List<org.languagetool.AnalyzedTokenReadings>
tag(java.util.List<java.lang.String> sentenceTokens, boolean ignoreCase)
-
-
-
Field Detail
-
removalTagger
private final org.languagetool.tagging.ManualTagger removalTagger
-
compoundTokenizer
private GermanCompoundTokenizer compoundTokenizer
-
-
Method Detail
-
addStem
private java.util.List<org.languagetool.tagging.TaggedWord> addStem(java.util.List<org.languagetool.tagging.TaggedWord> analyzedWordResults, java.lang.String stem)
-
sanitizeWord
private java.lang.String sanitizeWord(java.lang.String word)
-
getManualAdditionsFileName
public java.lang.String getManualAdditionsFileName()
- Specified by:
getManualAdditionsFileName
in classorg.languagetool.tagging.BaseTagger
-
getManualRemovalsFileName
public java.lang.String getManualRemovalsFileName()
- Overrides:
getManualRemovalsFileName
in classorg.languagetool.tagging.BaseTagger
-
lookup
@Nullable public @Nullable org.languagetool.AnalyzedTokenReadings lookup(java.lang.String word) throws java.io.IOException
Return only the first reading of the given word ornull
.- Throws:
java.io.IOException
-
tag
public java.util.List<org.languagetool.tagging.TaggedWord> tag(java.lang.String word)
-
matchesUppercaseAdjective
private boolean matchesUppercaseAdjective(java.lang.String unknownUppercaseToken)
-
tag
public java.util.List<org.languagetool.AnalyzedTokenReadings> tag(java.util.List<java.lang.String> sentenceTokens) throws java.io.IOException
- Specified by:
tag
in interfaceorg.languagetool.tagging.Tagger
- Overrides:
tag
in classorg.languagetool.tagging.BaseTagger
- Throws:
java.io.IOException
-
tag
public java.util.List<org.languagetool.AnalyzedTokenReadings> tag(java.util.List<java.lang.String> sentenceTokens, boolean ignoreCase) throws java.io.IOException
- Throws:
java.io.IOException
-
getImperativeForm
private java.util.List<org.languagetool.AnalyzedToken> getImperativeForm(java.lang.String word, java.util.List<java.lang.String> sentenceTokens, int pos)
-
getSubstantivatedForms
private java.util.List<org.languagetool.AnalyzedToken> getSubstantivatedForms(java.lang.String word, java.util.List<java.lang.String> sentenceTokens, int pos)
-
initializeIfRequired
private void initializeIfRequired() throws java.io.IOException
- Throws:
java.io.IOException
-
getNoInfoToken
private org.languagetool.AnalyzedToken getNoInfoToken(java.lang.String word)
-
getAnalyzedTokens
private java.util.List<org.languagetool.AnalyzedToken> getAnalyzedTokens(java.util.List<org.languagetool.tagging.TaggedWord> taggedWords, java.lang.String word)
-
getAnalyzedTokens
private java.util.List<org.languagetool.AnalyzedToken> getAnalyzedTokens(java.util.List<org.languagetool.tagging.TaggedWord> taggedWords, java.lang.String word, java.util.List<java.lang.String> compoundParts)
-
-