Package org.languagetool.rules.patterns

Class XMLRuleHandler

java.lang.Object

org.xml.sax.helpers.DefaultHandler

org.languagetool.rules.patterns.XMLRuleHandler

All Implemented Interfaces:

ContentHandler, DTDHandler, EntityResolver, ErrorHandler

Direct Known Subclasses:

DisambiguationRuleHandler, FalseFriendRuleHandler, PatternRuleHandler

public class XMLRuleHandler
extends DefaultHandler

XML rule handler that loads rules from XML and throws exceptions on errors and warnings.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
(package private) static enum	XMLRuleHandler.RegexpMode

Field Summary

Fields

Modifier and Type	Field	Description
protected static final String	AND
protected int	andGroupCounter
protected static final String	ANTIPATTERN
protected StringBuilder	antiPatternExample
protected List<CorrectExample>	antipatternExamples
protected StringBuilder	antiPatternForRuleGroupExample
protected List<CorrectExample>	antipatternForRuleGroupsExamples
protected static final String	CASE_SENSITIVE
protected boolean	caseSensitive
protected List<String>	categoryTags
protected List<String>	categoryToneTags
protected ChunkTag	chunkTag
protected static final String	CHUNKTAG
protected static final String	CHUNKTAG_REGEXP
protected StringBuilder	correctExample
protected List<CorrectExample>	correctExamples
protected static final String	DEFAULT
protected static final String	DISTANCETOKENS
protected StringBuilder	elements
protected int	endPositionCorrection
protected Map<String,List<String>>	equivalenceFeatures
protected StringBuilder	errorTriggerExample
protected List<ErrorTriggeringExample>	errorTriggeringExamples
protected static final String	EXAMPLE
protected StringBuilder	exampleCorrection
protected static final String	EXCEPTION
protected Boolean	exceptionLevelCaseSensitive
protected boolean	exceptionLevelCaseSet
protected boolean	exceptionPosNegation
protected boolean	exceptionPosRegExp
protected String	exceptionPosToken
protected StringBuilder	exceptions
protected boolean	exceptionSet
protected boolean	exceptionSpaceBefore
protected boolean	exceptionSpaceBeforeSet
protected boolean	exceptionStringInflected
protected boolean	exceptionStringNegation
protected boolean	exceptionStringRegExp
protected boolean	exceptionValidNext
protected boolean	exceptionValidPrev
protected static final String	FALSE
protected static final String	FEATURE
protected static final String	GOAL_SPECIFIC
protected String	id
static final String	ID
protected static final String	IGNORE
protected boolean	inAndGroup
protected boolean	inAntiPatternExample
protected boolean	inAntiPatternForRuleGroupExample
protected StringBuilder	incorrectExample
protected boolean	inCorrectExample
protected List<IncorrectExample>	incorrectExamples
protected boolean	inErrorTriggerExample
protected boolean	inException
protected static final String	INFLECTED
protected boolean	inIncorrectExample
protected boolean	inMarker
protected boolean	inMatch
protected boolean	inMessage
protected boolean	inOrGroup
protected boolean	inPattern
protected boolean	inPhrases
protected boolean	inRegex
protected boolean	inRuleGroup
protected boolean	inShortMessage
protected boolean	inShortMessageForRuleGroup
protected boolean	inSuggestion
private final Map<org.apache.commons.lang3.tuple.Triple<String,Boolean,Boolean>,StringMatcher>	internedMatchers
private final Map<org.apache.commons.lang3.tuple.Triple<String,Boolean,Boolean>,PatternToken.PosToken>	internedPos
protected boolean	inToken
protected boolean	inUnification
protected boolean	inUnificationDef
protected boolean	inUnificationNeutral
protected boolean	inUrl
protected boolean	inUrlForRuleGroup
protected boolean	isGoalSpecific
protected String	isGoalSpecificCategoryAttribute
protected String	isGoalSpecificRuleGroupAttribute
protected boolean	isPremiumRule
protected Language	language
protected boolean	lastPhrase	true when phraseref is the last element in the rule.
protected static final String	MARK
protected static final String	MARKER
protected StringBuilder	match
protected static final String	MATCH
protected static final String	MAX
protected int	maxOccurrence
protected StringBuilder	message
protected static final String	MESSAGE
protected ResourceBundle	messages
protected static final String	MIN
protected int	minOccurrence
protected static final String	MINPREVMATCHES
static final String	NAME
protected static final String	NEGATE
protected static final String	NEGATE_POS
protected static final String	NO
protected static final String	OFF
protected static final String	ON
protected static final String	OR
protected int	orGroupCounter
protected static final String	PATTERN
protected PatternToken	patternToken
protected List<PatternToken>	patternTokens	List of elements as specified by tokens.
protected String	phraseId	Current phrase ID.
protected String	phraseIdRef	ID reference to the phrase.
protected Map<String,List<List<PatternToken>>>	phraseMap	Phrase store - elementLists keyed by phraseIds.
protected List<ArrayList<PatternToken>>	phrasePatternTokens	Logically forking element list, used for including multiple phrases in the current one.
protected static final String	PHRASES
protected Locator	pLocator
protected boolean	posNegation
protected boolean	posRegExp
protected static final String	POSTAG
protected static final String	POSTAG_REGEXP
protected String	posToken
protected static final String	PREMIUM	Definitions of values in XML files.
protected String	premiumCategoryAttribute
protected String	premiumFileAttribute
protected String	premiumRuleGroupAttribute
protected static final String	PRIO
protected int	prioCategoryAttribute
protected int	prioRuleAttribute
protected int	prioRuleGroupAttribute
protected StringBuilder	regex
protected boolean	regexCaseSensitive
protected XMLRuleHandler.RegexpMode	regexMode
protected static final String	REGEXP
protected int	regexpMark
protected boolean	regExpression
protected static final String	RULE
protected static final String	RULEGROUP
protected String	ruleGroupId
protected List<String>	ruleGroupTags
protected List<String>	ruleGroupToneTags
protected List<AbstractPatternRule>	rules
protected static final String	RULES
protected List<String>	ruleTags
protected List<String>	ruleToneTags
protected static final String	SCOPE
protected StringBuilder	shortMessage
protected StringBuilder	shortMessageForRuleGroup
protected static final String	SKIP
protected int	skipPos
protected static final String	SPACEBEFORE
protected int	startPositionCorrection
protected static final String	SUGGESTION
protected List<Match>	suggestionMatches
protected List<Match>	suggestionMatchesOutMsg
protected StringBuilder	suggestionsOutMsg
protected static final String	TABNAME
protected static final String	TEMP_OFF
protected static final String	TOKEN
protected int	tokenCounter
protected boolean	tokenInflected
protected boolean	tokenLevelCaseSensitive
protected boolean	tokenLevelCaseSet
protected boolean	tokenNegated
protected Match	tokenReference
protected boolean	tokenSpaceBefore
protected boolean	tokenSpaceBeforeSet
protected static final String	TRUE
protected static final String	TYPE
protected String	uFeature
protected static final String	UNIFICATION
protected static final String	UNIFY
protected static final String	UNIFY_IGNORE
protected boolean	uniNegation
protected StringBuilder	url
protected StringBuilder	urlForRuleGroup
protected String	uType
protected List<String>	uTypeList
protected int	xmlLineNumber
protected int	xmlLineNumberAntiPattern
protected static final String	YES

Constructor Summary

Constructors

Constructor	Description
XMLRuleHandler()

Method Summary

Modifier and Type	Method	Description
protected List<Match>	addLegacyMatches(List<Match> existingSugMatches, String messageStr, boolean inMessage)	Adds Match objects for all references to tokens (including '\1' and the like).
private void	checkNumber(Attributes attrs)
private void	checkRefNumber(int refNumber)
void	error(SAXParseException e)
protected void	finalizeExceptions()
protected void	finalizePhrase()
protected void	finalizeTokens(UnifierConfiguration unifierConfiguration)
List<AbstractPatternRule>	getRules()
private boolean	hasPosixCharacterClass(String s)
private StringMatcher	internMatcher(String text, boolean regexp, boolean caseSensitive)
private PatternToken.PosToken	obtainPosToken(String posToken, boolean regExp, boolean negated)
protected void	preparePhrase(Attributes attrs)
protected void	processElement(List<PatternToken> patternTokens)	Calculates the offset of the match reference (if any) in case the match element has been used in the group.
protected void	resetException()
protected void	resetToken()
void	setDocumentLocator(Locator locator)
protected void	setExceptions(Attributes attrs)
protected void	setMatchElement(Attributes attrs, boolean isSuppressMisspelled)
protected static void	setRuleFilter(String filterClassName, String filterArgs, AbstractPatternRule rule)
protected void	setToken(Attributes attrs)
protected void	startPattern(Attributes attrs)
void	warning(SAXParseException e)

Methods inherited from class org.xml.sax.helpers.DefaultHandler

characters, endDocument, endElement, endPrefixMapping, fatalError, ignorableWhitespace, notationDecl, processingInstruction, resolveEntity, skippedEntity, startDocument, startElement, startPrefixMapping, unparsedEntityDecl

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.xml.sax.ContentHandler

declaration

Field Details

ID

public static final String ID

See Also:

• Constant Field Values

NAME

public static final String NAME

See Also:

• Constant Field Values

PREMIUM

protected static final String PREMIUM

Definitions of values in XML files.

See Also:

• Constant Field Values

YES

protected static final String YES

See Also:

• Constant Field Values

OFF

protected static final String OFF

See Also:

• Constant Field Values

GOAL_SPECIFIC

protected static final String GOAL_SPECIFIC

See Also:

• Constant Field Values

TRUE

protected static final String TRUE

See Also:

• Constant Field Values

FALSE

protected static final String FALSE

See Also:

• Constant Field Values

TEMP_OFF

protected static final String TEMP_OFF

See Also:

• Constant Field Values

ON

protected static final String ON

See Also:

• Constant Field Values

POSTAG

protected static final String POSTAG

See Also:

• Constant Field Values

CHUNKTAG

protected static final String CHUNKTAG

See Also:

• Constant Field Values

CHUNKTAG_REGEXP

protected static final String CHUNKTAG_REGEXP

See Also:

• Constant Field Values

POSTAG_REGEXP

protected static final String POSTAG_REGEXP

See Also:

• Constant Field Values

REGEXP

protected static final String REGEXP

See Also:

• Constant Field Values

NEGATE

protected static final String NEGATE

See Also:

• Constant Field Values

INFLECTED

protected static final String INFLECTED

See Also:

• Constant Field Values

NEGATE_POS

protected static final String NEGATE_POS

See Also:

• Constant Field Values

MARKER

protected static final String MARKER

See Also:

• Constant Field Values

DEFAULT

protected static final String DEFAULT

See Also:

• Constant Field Values

TYPE

protected static final String TYPE

See Also:

• Constant Field Values

SPACEBEFORE

protected static final String SPACEBEFORE

See Also:

• Constant Field Values

EXAMPLE

protected static final String EXAMPLE

See Also:

• Constant Field Values

SCOPE

protected static final String SCOPE

See Also:

• Constant Field Values

IGNORE

protected static final String IGNORE

See Also:

• Constant Field Values

SKIP

protected static final String SKIP

See Also:

• Constant Field Values

MIN

protected static final String MIN

See Also:

• Constant Field Values

MAX

protected static final String MAX

See Also:

• Constant Field Values

TOKEN

protected static final String TOKEN

See Also:

• Constant Field Values

FEATURE

protected static final String FEATURE

See Also:

• Constant Field Values

UNIFY

protected static final String UNIFY

See Also:

• Constant Field Values

UNIFY_IGNORE

protected static final String UNIFY_IGNORE

See Also:

• Constant Field Values

AND

protected static final String AND

See Also:

• Constant Field Values

OR

protected static final String OR

See Also:

• Constant Field Values

EXCEPTION

protected static final String EXCEPTION

See Also:

• Constant Field Values

CASE_SENSITIVE

protected static final String CASE_SENSITIVE

See Also:

• Constant Field Values

MARK

protected static final String MARK

See Also:

• Constant Field Values

PATTERN

protected static final String PATTERN

See Also:

• Constant Field Values

ANTIPATTERN

protected static final String ANTIPATTERN

See Also:

• Constant Field Values

MATCH

protected static final String MATCH

See Also:

• Constant Field Values

UNIFICATION

protected static final String UNIFICATION

See Also:

• Constant Field Values

RULE

protected static final String RULE

See Also:

• Constant Field Values

RULES

protected static final String RULES

See Also:

• Constant Field Values

RULEGROUP

protected static final String RULEGROUP

See Also:

• Constant Field Values

NO

protected static final String NO

See Also:

• Constant Field Values

PHRASES

protected static final String PHRASES

See Also:

• Constant Field Values

MESSAGE

protected static final String MESSAGE

See Also:

• Constant Field Values

SUGGESTION

protected static final String SUGGESTION

See Also:

• Constant Field Values

TABNAME

protected static final String TABNAME

See Also:

• Constant Field Values

MINPREVMATCHES

protected static final String MINPREVMATCHES

See Also:

• Constant Field Values

DISTANCETOKENS

protected static final String DISTANCETOKENS

See Also:

• Constant Field Values

PRIO

protected static final String PRIO

See Also:

• Constant Field Values

rules

protected List<AbstractPatternRule> rules

language

protected Language language

messages

protected ResourceBundle messages

correctExample

protected StringBuilder correctExample

antiPatternExample

protected StringBuilder antiPatternExample

antiPatternForRuleGroupExample

protected StringBuilder antiPatternForRuleGroupExample

incorrectExample

protected StringBuilder incorrectExample

errorTriggerExample

protected StringBuilder errorTriggerExample

exampleCorrection

protected StringBuilder exampleCorrection

message

protected StringBuilder message

suggestionsOutMsg

protected StringBuilder suggestionsOutMsg

match

protected StringBuilder match

elements

protected StringBuilder elements

exceptions

protected StringBuilder exceptions

correctExamples

protected List<CorrectExample> correctExamples

antipatternExamples

protected List<CorrectExample> antipatternExamples

antipatternForRuleGroupsExamples

protected List<CorrectExample> antipatternForRuleGroupsExamples

incorrectExamples

protected List<IncorrectExample> incorrectExamples

errorTriggeringExamples

protected List<ErrorTriggeringExample> errorTriggeringExamples

inPattern

protected boolean inPattern

inCorrectExample

protected boolean inCorrectExample

inIncorrectExample

protected boolean inIncorrectExample

inErrorTriggerExample

protected boolean inErrorTriggerExample

inAntiPatternExample

protected boolean inAntiPatternExample

inAntiPatternForRuleGroupExample

protected boolean inAntiPatternForRuleGroupExample

inMessage

protected boolean inMessage

inSuggestion

protected boolean inSuggestion

inMatch

protected boolean inMatch

inRuleGroup

protected boolean inRuleGroup

inToken

protected boolean inToken

inException

protected boolean inException

inPhrases

protected boolean inPhrases

inAndGroup

protected boolean inAndGroup

inOrGroup

protected boolean inOrGroup

tokenSpaceBefore

protected boolean tokenSpaceBefore

tokenSpaceBeforeSet

protected boolean tokenSpaceBeforeSet

posToken

protected String posToken

chunkTag

protected ChunkTag chunkTag

posNegation

protected boolean posNegation

posRegExp

protected boolean posRegExp

caseSensitive

protected boolean caseSensitive

regExpression

protected boolean regExpression

tokenNegated

protected boolean tokenNegated

tokenInflected

protected boolean tokenInflected

premiumRuleGroupAttribute

protected String premiumRuleGroupAttribute

premiumCategoryAttribute

protected String premiumCategoryAttribute

premiumFileAttribute

protected String premiumFileAttribute

isPremiumRule

protected boolean isPremiumRule

categoryTags

protected List<String> categoryTags

ruleGroupTags

protected List<String> ruleGroupTags

ruleGroupToneTags

protected List<String> ruleGroupToneTags

categoryToneTags

protected List<String> categoryToneTags

ruleTags

protected List<String> ruleTags

ruleToneTags

protected List<String> ruleToneTags

isGoalSpecificCategoryAttribute

protected String isGoalSpecificCategoryAttribute

isGoalSpecificRuleGroupAttribute

protected String isGoalSpecificRuleGroupAttribute

isGoalSpecific

protected boolean isGoalSpecific

prioCategoryAttribute

protected int prioCategoryAttribute

prioRuleGroupAttribute

protected int prioRuleGroupAttribute

prioRuleAttribute

protected int prioRuleAttribute

tokenLevelCaseSensitive

protected boolean tokenLevelCaseSensitive

tokenLevelCaseSet

protected boolean tokenLevelCaseSet

exceptionPosToken

protected String exceptionPosToken

exceptionStringRegExp

protected boolean exceptionStringRegExp

exceptionStringNegation

protected boolean exceptionStringNegation

exceptionStringInflected

protected boolean exceptionStringInflected

exceptionPosNegation

protected boolean exceptionPosNegation

exceptionPosRegExp

protected boolean exceptionPosRegExp

exceptionValidNext

protected boolean exceptionValidNext

exceptionValidPrev

protected boolean exceptionValidPrev

exceptionSet

protected boolean exceptionSet

exceptionSpaceBefore

protected boolean exceptionSpaceBefore

exceptionSpaceBeforeSet

protected boolean exceptionSpaceBeforeSet

exceptionLevelCaseSensitive

protected Boolean exceptionLevelCaseSensitive

exceptionLevelCaseSet

protected boolean exceptionLevelCaseSet

patternTokens

protected List<PatternToken> patternTokens

List of elements as specified by tokens.

lastPhrase

protected boolean lastPhrase

true when phraseref is the last element in the rule.

phraseIdRef

protected String phraseIdRef

ID reference to the phrase.

phraseId

protected String phraseId

Current phrase ID.

skipPos

protected int skipPos

minOccurrence

protected int minOccurrence

maxOccurrence

protected int maxOccurrence

ruleGroupId

protected String ruleGroupId

id

protected String id

patternToken

protected PatternToken patternToken

tokenReference

protected Match tokenReference

suggestionMatches

protected List<Match> suggestionMatches

suggestionMatchesOutMsg

protected List<Match> suggestionMatchesOutMsg

pLocator

protected Locator pLocator

xmlLineNumber

protected int xmlLineNumber

xmlLineNumberAntiPattern

protected int xmlLineNumberAntiPattern

startPositionCorrection

protected int startPositionCorrection

endPositionCorrection

protected int endPositionCorrection

tokenCounter

protected int tokenCounter

phraseMap

protected Map<String,List<List<PatternToken>>> phraseMap

Phrase store - elementLists keyed by phraseIds.

phrasePatternTokens

protected List<ArrayList<PatternToken>> phrasePatternTokens

Logically forking element list, used for including multiple phrases in the current one.

andGroupCounter

protected int andGroupCounter

orGroupCounter

protected int orGroupCounter

inUrl

protected boolean inUrl

inUrlForRuleGroup

protected boolean inUrlForRuleGroup

url

protected StringBuilder url

urlForRuleGroup

protected StringBuilder urlForRuleGroup

inRegex

protected boolean inRegex

regex

protected StringBuilder regex

regexMode

protected XMLRuleHandler.RegexpMode regexMode

regexCaseSensitive

protected boolean regexCaseSensitive

regexpMark

protected int regexpMark

inShortMessage

protected boolean inShortMessage

inShortMessageForRuleGroup

protected boolean inShortMessageForRuleGroup

shortMessage

protected StringBuilder shortMessage

shortMessageForRuleGroup

protected StringBuilder shortMessageForRuleGroup

inUnification

protected boolean inUnification

inMarker

protected boolean inMarker

inUnificationDef

protected boolean inUnificationDef

uniNegation

protected boolean uniNegation

inUnificationNeutral

protected boolean inUnificationNeutral

uFeature

protected String uFeature

uType

protected String uType

uTypeList

protected List<String> uTypeList

equivalenceFeatures

protected Map<String,List<String>> equivalenceFeatures

internedMatchers

private final Map<org.apache.commons.lang3.tuple.Triple<String,Boolean,Boolean>,StringMatcher> internedMatchers

internedPos

private final Map<org.apache.commons.lang3.tuple.Triple<String,Boolean,Boolean>,PatternToken.PosToken> internedPos

Constructor Details

XMLRuleHandler

public XMLRuleHandler()

Method Details

getRules

public List<AbstractPatternRule> getRules()

warning

public void warning(SAXParseException e)
             throws SAXException

Specified by:

warning in interface ErrorHandler

Overrides:

warning in class DefaultHandler

Throws:

SAXException

error

public void error(SAXParseException e)
           throws SAXException

Specified by:

error in interface ErrorHandler

Overrides:

error in class DefaultHandler

Throws:

SAXException

setDocumentLocator

public void setDocumentLocator(Locator locator)

Specified by:

setDocumentLocator in interface ContentHandler

Overrides:

setDocumentLocator in class DefaultHandler

resetToken

protected void resetToken()

resetException

protected void resetException()

preparePhrase

protected void preparePhrase(Attributes attrs)

finalizePhrase

protected void finalizePhrase()

startPattern

protected void startPattern(Attributes attrs)
                     throws SAXException

Throws:

SAXException

processElement

protected void processElement(List<PatternToken> patternTokens)

Calculates the offset of the match reference (if any) in case the match element has been used in the group.

Parameters:

patternTokens - token list where the match element was used. It is directly changed.

setMatchElement

protected void setMatchElement(Attributes attrs,
 boolean isSuppressMisspelled)
                        throws SAXException

Throws:

SAXException

checkNumber

private void checkNumber(Attributes attrs)
                  throws SAXException

Throws:

SAXException

checkRefNumber

private void checkRefNumber(int refNumber)
                     throws SAXException

Throws:

SAXException

setExceptions

protected void setExceptions(Attributes attrs)

finalizeExceptions

protected void finalizeExceptions()

hasPosixCharacterClass

private boolean hasPosixCharacterClass(String s)

setToken

protected void setToken(Attributes attrs)
                 throws SAXException

Throws:

SAXException

addLegacyMatches

@Nullable
protected List<Match> addLegacyMatches(List<Match> existingSugMatches,
 String messageStr,
 boolean inMessage)

Adds Match objects for all references to tokens (including '\1' and the like).

finalizeTokens

protected void finalizeTokens(UnifierConfiguration unifierConfiguration)
                       throws SAXException

Throws:

SAXException

obtainPosToken

private PatternToken.PosToken obtainPosToken(String posToken,
 boolean regExp,
 boolean negated)

setRuleFilter

protected static void setRuleFilter(String filterClassName,
 String filterArgs,
 AbstractPatternRule rule)

internMatcher

private StringMatcher internMatcher(String text,
 boolean regexp,
 boolean caseSensitive)