Package org.languagetool.rules.de

Class AgreementRule

java.lang.Object

org.languagetool.rules.Rule

org.languagetool.rules.de.AgreementRule

public class AgreementRule
extends Rule

Simple agreement checker for German noun phrases. Checks agreement in:

• DET/PRO NOUN: e.g. "mein Auto", "der Mann", "die Frau" (correct), "die Haus" (incorrect)
• DET/PRO ADJ NOUN: e.g. "der riesige Tisch" (correct), "die riesigen Tisch" (incorrect)
• DET/PRO ADJ ADJ NOUN: e.g. "der große riesige Tisch" (correct), "die große riesige Tisch" (incorrect)

Note that this rule only checks agreement inside the noun phrase, not whether e.g. the correct case is used. For example, "Es ist das Haus dem Mann" is not detected as incorrect.

TODO: the implementation could use a re-write that first detects the relevant noun phrases and then checks agreement

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
(package private) static enum	AgreementRule.GrammarCategory
(package private) static enum	AgreementRule.ReplacementType

Field Summary

Fields

Modifier and Type	Field	Description
private static final List<List<PatternToken>>	allAntiPatterns
private final Supplier<List<DisambiguationPatternRule>>	antiPatterns
private static final Pattern	HERR_FRAU
private static final AnalyzedToken[]	INS_REPLACEMENT
private final German	language
private JLanguageTool	lt
private static final Pattern	MIT_MIR_ETC
private static final Set<String>	MODIFIERS
private static final String	MSG
private static final String	MSG2
private static final Set<String>	NOUNS_TO_BE_IGNORED
private static final Pattern	OHNE_MICH_ETC
private static final Set<String>	PRONOUNS_TO_BE_IGNORED
private static final String[]	REL_PRONOUN_LEMMAS
private static final String	SHORT_MSG
private static final Pattern	VIEL_WEIT
private static final Set<String>	VIELE_WENIGE_LOWERCASE
private static final Pattern	WENIGER_EHER
private static final Pattern	ZUGESCHRIEBENEN_GENANNTEN
private static final AnalyzedToken[]	ZUR_REPLACEMENT

Fields inherited from class org.languagetool.rules.Rule

messages

Constructor Summary

Constructors

Constructor	Description
AgreementRule(ResourceBundle messages, German language)

Method Summary

Modifier and Type	Method	Description
private boolean	agreementWithCategoryRelaxation(AnalyzedTokenReadings token1, AnalyzedTokenReadings token2, AgreementRule.GrammarCategory categoryToRelax)
private RuleMatch	checkDetAdjAdjNounAgreement(AnalyzedTokenReadings maybePreposition, AnalyzedTokenReadings token1, AnalyzedTokenReadings token2, AnalyzedTokenReadings token3, AnalyzedTokenReadings token4, AnalyzedSentence sentence, int tokenPos, Map<Integer,AgreementRule.ReplacementType> replMap, String skippedStr)
private RuleMatch	checkDetAdjNounAgreement(AnalyzedTokenReadings maybePreposition, AnalyzedTokenReadings token1, AnalyzedTokenReadings token2, AnalyzedTokenReadings token3, AnalyzedSentence sentence, int tokenPos, Map<Integer,AgreementRule.ReplacementType> replMap, String skippedStr)
private RuleMatch	checkDetNounAgreement(AnalyzedTokenReadings maybePreposition, AnalyzedTokenReadings token1, AnalyzedTokenReadings token2, AnalyzedSentence sentence, int tokenPos, Map<Integer,AgreementRule.ReplacementType> replMap, String skippedStr)
private boolean	couldBeRelativeOrDependentClause(AnalyzedTokenReadings[] tokens, int pos)
int	estimateContextForSureMatch()	A number that estimates how many words there must be after a match before we can be (relatively) sure the match is valid.
private Set<String>	getAgreementCategories(AnalyzedTokenReadings aToken)
List<DisambiguationPatternRule>	getAntiPatterns()	Overwrite this to avoid false alarms by ignoring these patterns - note that your Rule.match(AnalyzedSentence) method needs to call Rule.getSentenceWithImmunization(org.languagetool.AnalyzedSentence) for this to be used and you need to check AnalyzedTokenReadings.isImmunized()
(package private) List<String>	getCategoriesCausingError(AnalyzedTokenReadings token1, AnalyzedTokenReadings token2)
private RuleMatch	getCompoundError(AnalyzedTokenReadings token1, AnalyzedTokenReadings token2, int tokenPos, AnalyzedSentence sentence)
private RuleMatch	getCompoundError(AnalyzedTokenReadings token1, AnalyzedTokenReadings token2, AnalyzedTokenReadings token3, int tokenPos, AnalyzedSentence sentence)
private RuleMatch	getCompoundError(AnalyzedTokenReadings token1, AnalyzedTokenReadings token2, AnalyzedTokenReadings token3, AnalyzedTokenReadings token4, int tokenPos, AnalyzedSentence sentence, String skippedStr)
String	getDescription()	A short description of the error this rule can detect, usually in the language of the text that is checked.
String	getId()	A string used to identify the rule in e.g.
private int	getPosAfterModifier(int startAt, AnalyzedTokenReadings[] tokens)	Search for modifiers (such as "sehr", "1,4 Meter") which can expand a determiner - adjective - noun group ("ein hohes Haus" -> "ein sehr hohes Haus", "ein 500 Meter hohes Haus") and return the index of the first non-modifier token ("Haus")
private RuleMatch	getRuleMatch(AnalyzedTokenReadings token, AnalyzedTokenReadings token2, AnalyzedSentence sentence, String testPhrase, String hyphenTestPhrase)
private void	initLt()
private boolean	isException(AnalyzedTokenReadings token1, AnalyzedTokenReadings token2)
private boolean	isNonPredicativeAdjective(AnalyzedTokenReadings tokensReadings)
private boolean	isParticiple(AnalyzedTokenReadings tokensReadings)
private boolean	isRelevantPronoun(AnalyzedTokenReadings[] tokens, int pos)
RuleMatch[]	match(AnalyzedSentence sentence)	Check whether the given sentence matches this error rule, i.e.
private Map<Integer,AgreementRule.ReplacementType>	replacePrepositionsByArticle(AnalyzedTokenReadings[] tokens)
private Set<String>	retainCommonCategories(AnalyzedTokenReadings token1, AnalyzedTokenReadings token2, AnalyzedTokenReadings token3)
private Set<String>	retainCommonCategories(AnalyzedTokenReadings token1, AnalyzedTokenReadings token2, AnalyzedTokenReadings token3, AnalyzedTokenReadings token4)

Methods inherited from class org.languagetool.rules.Rule

addExamplePair, addTags, addToneTags, cacheAntiPatterns, getCategory, getCorrectExamples, getDistanceTokens, getErrorTriggeringExamples, getFullId, getIncorrectExamples, getLocQualityIssueType, getMinPrevMatches, getPriority, getRuleOptions, getSentenceWithImmunization, getSourceFile, getSubId, getTags, getToneTags, getUrl, hasTag, hasToneTag, isDefaultOff, isDefaultTempOff, isDictionaryBasedSpellingRule, isGoalSpecific, isIncludedInHiddenMatches, isOfficeDefaultOff, isOfficeDefaultOn, isPremium, makeAntiPatterns, setCategory, setCorrectExamples, setDefaultOff, setDefaultOn, setDefaultTempOff, setDistanceTokens, setErrorTriggeringExamples, setExamplePair, setGoalSpecific, setIncludedInHiddenMatches, setIncorrectExamples, setLocQualityIssueType, setMinPrevMatches, setOfficeDefaultOff, setOfficeDefaultOn, setPremium, setPriority, setTags, setToneTags, setUrl, supportsLanguage, toRuleMatchArray, useInOffice

Methods inherited from class java.lang.Object

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

Field Details

MIT_MIR_ETC

private static final Pattern MIT_MIR_ETC

OHNE_MICH_ETC

private static final Pattern OHNE_MICH_ETC

ZUGESCHRIEBENEN_GENANNTEN

private static final Pattern ZUGESCHRIEBENEN_GENANNTEN

VIEL_WEIT

private static final Pattern VIEL_WEIT

WENIGER_EHER

private static final Pattern WENIGER_EHER

HERR_FRAU

private static final Pattern HERR_FRAU

language

private final German language

antiPatterns

private final Supplier<List<DisambiguationPatternRule>> antiPatterns

lt

private JLanguageTool lt

INS_REPLACEMENT

private static final AnalyzedToken[] INS_REPLACEMENT

ZUR_REPLACEMENT

private static final AnalyzedToken[] ZUR_REPLACEMENT

MSG

private static final String MSG

See Also:

• Constant Field Values

MSG2

private static final String MSG2

See Also:

• Constant Field Values

SHORT_MSG

private static final String SHORT_MSG

See Also:

• Constant Field Values

MODIFIERS

private static final Set<String> MODIFIERS

VIELE_WENIGE_LOWERCASE

private static final Set<String> VIELE_WENIGE_LOWERCASE

REL_PRONOUN_LEMMAS

private static final String[] REL_PRONOUN_LEMMAS

PRONOUNS_TO_BE_IGNORED

private static final Set<String> PRONOUNS_TO_BE_IGNORED

NOUNS_TO_BE_IGNORED

private static final Set<String> NOUNS_TO_BE_IGNORED

allAntiPatterns

private static final List<List<PatternToken>> allAntiPatterns

Constructor Details

AgreementRule

public AgreementRule(ResourceBundle messages,
 German language)

Method Details

getId

public String getId()

Description copied from class: Rule

A string used to identify the rule in e.g. configuration files. This string is supposed to be unique and to stay the same in all upcoming versions of LanguageTool. It's supposed to contain only the characters A-Z and the underscore.

Specified by:

getId in class Rule

estimateContextForSureMatch

public int estimateContextForSureMatch()

Description copied from class: Rule

A number that estimates how many words there must be after a match before we can be (relatively) sure the match is valid. This is useful for check-as-you-type, where a match might occur and the word that gets typed next makes the match disappear (something one would obviously like to avoid). Note: this may over-estimate the real context size. Returns -1 when the sentence needs to end to be sure there's a match.

Overrides:

estimateContextForSureMatch in class Rule

getDescription

public String getDescription()

Description copied from class: Rule

A short description of the error this rule can detect, usually in the language of the text that is checked.

Specified by:

getDescription in class Rule

replacePrepositionsByArticle

private Map<Integer,AgreementRule.ReplacementType> replacePrepositionsByArticle(AnalyzedTokenReadings[] tokens)

match

public RuleMatch[] match(AnalyzedSentence sentence)

Description copied from class: Rule

Check whether the given sentence matches this error rule, i.e. whether it contains the error detected by this rule. Note that the order in which this method is called is not always guaranteed, i.e. the sentence order in the text may be different from the order in which you get the sentences (this may be the case when LanguageTool is used as a LibreOffice/OpenOffice add-on, for example). In other words, implementations must be stateless, so that a previous call to this method has no influence on later calls.

Specified by:

match in class Rule

Parameters:

sentence - a pre-analyzed sentence

Returns:

an array of RuleMatch objects

getPosAfterModifier

private int getPosAfterModifier(int startAt,
 AnalyzedTokenReadings[] tokens)

Search for modifiers (such as "sehr", "1,4 Meter") which can expand a determiner - adjective - noun group ("ein hohes Haus" -> "ein sehr hohes Haus", "ein 500 Meter hohes Haus") and return the index of the first non-modifier token ("Haus")

Parameters:

startAt - index of array where to start searching for modifier

Returns:

index of first non-modifier token

getAntiPatterns

public List<DisambiguationPatternRule> getAntiPatterns()

Description copied from class: Rule

Overwrite this to avoid false alarms by ignoring these patterns - note that your Rule.match(AnalyzedSentence) method needs to call Rule.getSentenceWithImmunization(org.languagetool.AnalyzedSentence) for this to be used and you need to check AnalyzedTokenReadings.isImmunized()

Overrides:

getAntiPatterns in class Rule

isNonPredicativeAdjective

private boolean isNonPredicativeAdjective(AnalyzedTokenReadings tokensReadings)

isParticiple

private boolean isParticiple(AnalyzedTokenReadings tokensReadings)

isRelevantPronoun

private boolean isRelevantPronoun(AnalyzedTokenReadings[] tokens,
 int pos)

couldBeRelativeOrDependentClause

private boolean couldBeRelativeOrDependentClause(AnalyzedTokenReadings[] tokens,
 int pos)

checkDetNounAgreement

@Nullable
private RuleMatch checkDetNounAgreement(AnalyzedTokenReadings maybePreposition,
 AnalyzedTokenReadings token1,
 AnalyzedTokenReadings token2,
 AnalyzedSentence sentence,
 int tokenPos,
 Map<Integer,AgreementRule.ReplacementType> replMap,
 String skippedStr)

getCompoundError

@Nullable
private RuleMatch getCompoundError(AnalyzedTokenReadings token1,
 AnalyzedTokenReadings token2,
 int tokenPos,
 AnalyzedSentence sentence)

getCompoundError

@Nullable
private RuleMatch getCompoundError(AnalyzedTokenReadings token1,
 AnalyzedTokenReadings token2,
 AnalyzedTokenReadings token3,
 int tokenPos,
 AnalyzedSentence sentence)

getCompoundError

@Nullable
private RuleMatch getCompoundError(AnalyzedTokenReadings token1,
 AnalyzedTokenReadings token2,
 AnalyzedTokenReadings token3,
 AnalyzedTokenReadings token4,
 int tokenPos,
 AnalyzedSentence sentence,
 String skippedStr)

getRuleMatch

@Nullable
private RuleMatch getRuleMatch(AnalyzedTokenReadings token,
 AnalyzedTokenReadings token2,
 AnalyzedSentence sentence,
 String testPhrase,
 String hyphenTestPhrase)

initLt

private void initLt()

isException

private boolean isException(AnalyzedTokenReadings token1,
 AnalyzedTokenReadings token2)

getCategoriesCausingError

List<String> getCategoriesCausingError(AnalyzedTokenReadings token1,
 AnalyzedTokenReadings token2)

checkDetAdjNounAgreement

private RuleMatch checkDetAdjNounAgreement(AnalyzedTokenReadings maybePreposition,
 AnalyzedTokenReadings token1,
 AnalyzedTokenReadings token2,
 AnalyzedTokenReadings token3,
 AnalyzedSentence sentence,
 int tokenPos,
 Map<Integer,AgreementRule.ReplacementType> replMap,
 String skippedStr)

checkDetAdjAdjNounAgreement

private RuleMatch checkDetAdjAdjNounAgreement(AnalyzedTokenReadings maybePreposition,
 AnalyzedTokenReadings token1,
 AnalyzedTokenReadings token2,
 AnalyzedTokenReadings token3,
 AnalyzedTokenReadings token4,
 AnalyzedSentence sentence,
 int tokenPos,
 Map<Integer,AgreementRule.ReplacementType> replMap,
 String skippedStr)

agreementWithCategoryRelaxation

private boolean agreementWithCategoryRelaxation(AnalyzedTokenReadings token1,
 AnalyzedTokenReadings token2,
 AgreementRule.GrammarCategory categoryToRelax)

retainCommonCategories

@NotNull
private Set<String> retainCommonCategories(AnalyzedTokenReadings token1,
 AnalyzedTokenReadings token2,
 AnalyzedTokenReadings token3)

retainCommonCategories

@NotNull
private Set<String> retainCommonCategories(AnalyzedTokenReadings token1,
 AnalyzedTokenReadings token2,
 AnalyzedTokenReadings token3,
 AnalyzedTokenReadings token4)

getAgreementCategories

private Set<String> getAgreementCategories(AnalyzedTokenReadings aToken)