Package org.languagetool.rules.spelling.hunspell

Class HunspellRule

java.lang.Object

org.languagetool.rules.Rule

org.languagetool.rules.spelling.SpellingCheckRule

org.languagetool.rules.spelling.hunspell.HunspellRule

Direct Known Subclasses:

ArabicHunspellSpellerRule, CompoundAwareHunspellRule, HunspellNoSuggestionRule, KhmerHunspellRule

public class HunspellRule
extends SpellingCheckRule

A hunspell-based spellchecking-rule. The default dictionary is set to the first country variant on the list - so the order in the Language class declaration is important!

Field Summary

Fields

Modifier and Type	Field	Description
private static final ConcurrentLinkedQueue<String>	activeChecks
private final List<String>	commonGermanWords
private final List<String>	commonPortugueseWords
private final List<RuleWithLanguage>	enSpellRules
protected static final String	FILE_EXTENSION
protected HunspellDictionary	hunspell
private static final ConcurrentMap<URL,List<String>>	ignoreFileContents
private static final org.slf4j.Logger	logger
private final Pattern	MINUS_PLUS
private static final boolean	monitorRules
private boolean	needsInit
private static final String	NON_ALPHABETIC
private static final Pattern	NON_ALPHABETIC_PATTERN
protected Pattern	nonWordPattern
private static final ConcurrentMap<String,Pattern>	nonWordPatterns
static final String	RULE_ID
private static final Pattern	STARTS_WITH_TWO_UPPERCASE_CHARS
private final UserConfig	userConfig
private static final String[]	WHITESPACE_ARRAY

Fields inherited from class org.languagetool.rules.spelling.SpellingCheckRule

CUSTOM_SPELLING_FILE, GLOBAL_SPELLING_FILE, HIGH_CONFIDENCE, ignoreWordsWithLength, language, languageModel, LANGUAGETOOL, LANGUAGETOOLER, MAX_TOKEN_LENGTH, wordListLoader, wordsToBeIgnored

Fields inherited from class org.languagetool.rules.Rule

messages

Constructor Summary

Constructors

Constructor	Description
HunspellRule(ResourceBundle messages, Language language, UserConfig userConfig)
HunspellRule(ResourceBundle messages, Language language, UserConfig userConfig, List<Language> altLanguages)
HunspellRule(ResourceBundle messages, Language language, UserConfig userConfig, List<Language> altLanguages, LanguageModel languageModel)

Method Summary

Modifier and Type	Method	Description
protected boolean	acceptSuggestion(String suggestion)
private void	addIgnoreWords()
private List<SuggestedReplacement>	calcSuggestions(String word, String cleanWord)
private static Pattern	computeNonWordPattern(InputStream stream)
private static String	cutOffDot(String s)
protected final void	ensureInitialized()
private static void	fileCopy(InputStream in, File targetFile)
static Queue<String>	getActiveChecks()
String	getDescription()	A short description of the error this rule can detect, usually in the language of the text that is checked.
protected String	getDictFilenameInResources(String langCountry)
private static String	getDictionaryPath(String dicName, String originalPath)
private List<RuleWithLanguage>	getEnglishSpellingRules()
String	getId()	A string used to identify the rule in e.g.
protected String	getMessage(String origWord, SuggestedReplacement firstSuggestion)
protected String	getSentenceTextWithoutUrlsAndImmunizedTokens(AnalyzedSentence sentence)
protected String	getShortMessage(String origWord, SuggestedReplacement firstSuggestion)
List<String>	getSuggestions(String word)
protected void	init()
private boolean	isEnglish(String word)
(package private) boolean	isFirstItemHighConfidenceSuggestion(String word, List<SuggestedReplacement> sugg)
protected boolean	isInIgnoredSet(String word)
boolean	isMisspelled(String word)
protected boolean	isQuotedCompound(AnalyzedSentence analyzedSentence, int idx, String token)	Is the given token part of a hyphenated compound preceded by a quoted token (e.g., „Spiegel“-Magazin) and should be treated as an ordinary hyphenated compound (e.g., „Spiegel-Magazin“)
RuleMatch[]	match(AnalyzedSentence sentence)	Check whether the given sentence matches this error rule, i.e.
private static Pattern	nonWordPatternFromPath(Path affPath)
protected List<String>	sortSuggestionByQuality(String misspelling, List<String> suggestions)
protected String[]	tokenizeText(String sentence)

Methods inherited from class org.languagetool.rules.spelling.SpellingCheckRule

acceptPhrases, addIgnoreTokens, addIgnoreWords, addProhibitedWords, addSuggestionsToRuleMatch, createWrongSplitMatch, expandLine, filterDupes, filterNoSuggestWords, filterSuggestions, getAdditionalProhibitFileNames, getAdditionalSpellingFileNames, getAdditionalSuggestions, getAdditionalTopSuggestions, getAntiPatterns, getIgnoreFileName, getLanguageVariantSpellingFileName, getOnlySuggestions, getProhibitFileName, getSpellingFileName, ignorePotentiallyMisspelledWord, ignoreToken, ignoreWord, ignoreWord, isDictionaryBasedSpellingRule, isEMail, isIgnoredNoCase, isLatinScript, isProhibited, isUrl, setConsiderIgnoreWords, setConvertsCase, startsWithIgnoredWord, tokenizeNewWords

Methods inherited from class org.languagetool.rules.Rule

addExamplePair, addTags, addToneTags, cacheAntiPatterns, estimateContextForSureMatch, getCategory, getCorrectExamples, getDistanceTokens, getErrorTriggeringExamples, getFullId, getIncorrectExamples, getLocQualityIssueType, getMinPrevMatches, getPriority, getRuleOptions, getSentenceWithImmunization, getSourceFile, getSubId, getTags, getToneTags, getUrl, hasTag, hasToneTag, isDefaultOff, isDefaultTempOff, 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

RULE_ID

public static final String RULE_ID

See Also:

• Constant Field Values

FILE_EXTENSION

protected static final String FILE_EXTENSION

See Also:

• Constant Field Values

needsInit

private volatile boolean needsInit

hunspell

protected volatile HunspellDictionary hunspell

logger

private static final org.slf4j.Logger logger

activeChecks

private static final ConcurrentLinkedQueue<String> activeChecks

NON_ALPHABETIC

private static final String NON_ALPHABETIC

See Also:

• Constant Field Values

NON_ALPHABETIC_PATTERN

private static final Pattern NON_ALPHABETIC_PATTERN

STARTS_WITH_TWO_UPPERCASE_CHARS

private static final Pattern STARTS_WITH_TWO_UPPERCASE_CHARS

monitorRules

private static final boolean monitorRules

commonPortugueseWords

private final List<String> commonPortugueseWords

commonGermanWords

private final List<String> commonGermanWords

MINUS_PLUS

private final Pattern MINUS_PLUS

ignoreFileContents

private static final ConcurrentMap<URL,List<String>> ignoreFileContents

nonWordPatterns

private static final ConcurrentMap<String,Pattern> nonWordPatterns

WHITESPACE_ARRAY

private static final String[] WHITESPACE_ARRAY

nonWordPattern

protected Pattern nonWordPattern

userConfig

private final UserConfig userConfig

enSpellRules

private final List<RuleWithLanguage> enSpellRules

Constructor Details

HunspellRule

public HunspellRule(ResourceBundle messages,
 Language language,
 UserConfig userConfig)

HunspellRule

public HunspellRule(ResourceBundle messages,
 Language language,
 UserConfig userConfig,
 List<Language> altLanguages)

Since:

4.3

HunspellRule

public HunspellRule(ResourceBundle messages,
 Language language,
 UserConfig userConfig,
 List<Language> altLanguages,
 LanguageModel languageModel)

Method Details

getActiveChecks

public static Queue<String> getActiveChecks()

getEnglishSpellingRules

private List<RuleWithLanguage> getEnglishSpellingRules()

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 SpellingCheckRule

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 SpellingCheckRule

isQuotedCompound

protected boolean isQuotedCompound(AnalyzedSentence analyzedSentence,
 int idx,
 String token)

Is the given token part of a hyphenated compound preceded by a quoted token (e.g., „Spiegel“-Magazin) and should be treated as an ordinary hyphenated compound (e.g., „Spiegel-Magazin“)

match

public RuleMatch[] match(AnalyzedSentence sentence)
                  throws IOException

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 SpellingCheckRule

Parameters:

sentence - a pre-analyzed sentence

Returns:

an array of RuleMatch objects

Throws:

IOException

getMessage

@NotNull
protected String getMessage(String origWord,
 SuggestedReplacement firstSuggestion)

getShortMessage

@NotNull
protected String getShortMessage(String origWord,
 SuggestedReplacement firstSuggestion)

acceptSuggestion

protected boolean acceptSuggestion(String suggestion)

isFirstItemHighConfidenceSuggestion

boolean isFirstItemHighConfidenceSuggestion(String word,
 List<SuggestedReplacement> sugg)

isEnglish

private boolean isEnglish(String word)
                   throws IOException

Throws:

IOException

calcSuggestions

private List<SuggestedReplacement> calcSuggestions(String word,
 String cleanWord)
                                            throws IOException

Throws:

IOException

cutOffDot

private static String cutOffDot(String s)

isMisspelled

public boolean isMisspelled(String word)

Specified by:

isMisspelled in class SpellingCheckRule

Since:

public since 4.1

getSuggestions

public List<String> getSuggestions(String word)
                            throws IOException

Throws:

IOException

sortSuggestionByQuality

protected List<String> sortSuggestionByQuality(String misspelling,
 List<String> suggestions)

tokenizeText

protected String[] tokenizeText(String sentence)

getSentenceTextWithoutUrlsAndImmunizedTokens

protected String getSentenceTextWithoutUrlsAndImmunizedTokens(AnalyzedSentence sentence)

ensureInitialized

protected final void ensureInitialized()
                                throws IOException

Throws:

IOException

init

protected void init()
             throws IOException

Overrides:

init in class SpellingCheckRule

Throws:

IOException

nonWordPatternFromPath

private static Pattern nonWordPatternFromPath(Path affPath)

computeNonWordPattern

private static Pattern computeNonWordPattern(InputStream stream)

getDictFilenameInResources

@NotNull
protected String getDictFilenameInResources(String langCountry)

addIgnoreWords

private void addIgnoreWords()
                     throws IOException

Throws:

IOException

isInIgnoredSet

protected boolean isInIgnoredSet(String word)

Overrides:

isInIgnoredSet in class SpellingCheckRule

getDictionaryPath

private static String getDictionaryPath(String dicName,
 String originalPath)
                                 throws IOException

Throws:

IOException

fileCopy

private static void fileCopy(InputStream in,
 File targetFile)
                      throws IOException

Throws:

IOException