Class LagartoParser

java.lang.Object
jodd.lagarto.LagartoParser
public class LagartoParser extends Object
HTML/XML content parser/tokenizer using TagVisitor for callbacks. Works by the HTML5 specs for tokenization, as described on WhatWG. Differences from the specs:
  • text is emitted as a block of text, and not character by character.
  • tags name case (and letter case of other entities) is not changed, but case-sensitive information exist for matching.
  • the whole tokenization process is implemented here, without going into the tree building. This applies for switching to the RAWTEXT state.
  • script tag is emitted separately
  • conditional comments added
  • xml states and callbacks added

  • Field Details

    • visitor

      protected TagVisitor visitor

    • tag

      protected ParsedTag tag

    • doctype

      protected ParsedDoctype doctype

    • in

      protected final CharsInput in

    • config

      protected final LagartoParserConfig config

    • parsing

      protected boolean parsing

    • DATA_STATE

      protected State DATA_STATE
      Data state.

    • TAG_OPEN

      protected State TAG_OPEN

    • END_TAG_OPEN

      protected State END_TAG_OPEN

    • TAG_NAME

      protected State TAG_NAME

    • BEFORE_ATTRIBUTE_NAME

      protected State BEFORE_ATTRIBUTE_NAME

    • ATTRIBUTE_NAME

      protected State ATTRIBUTE_NAME

    • AFTER_ATTRIBUTE_NAME

      protected State AFTER_ATTRIBUTE_NAME

    • BEFORE_ATTRIBUTE_VALUE

      protected State BEFORE_ATTRIBUTE_VALUE

    • ATTR_VALUE_UNQUOTED

      protected State ATTR_VALUE_UNQUOTED

    • ATTR_VALUE_SINGLE_QUOTED

      protected State ATTR_VALUE_SINGLE_QUOTED

    • ATTR_VALUE_DOUBLE_QUOTED

      protected State ATTR_VALUE_DOUBLE_QUOTED

    • AFTER_ATTRIBUTE_VALUE_QUOTED

      protected State AFTER_ATTRIBUTE_VALUE_QUOTED

    • SELF_CLOSING_START_TAG

      protected State SELF_CLOSING_START_TAG

    • BOGUS_COMMENT

      protected State BOGUS_COMMENT

    • MARKUP_DECLARATION_OPEN

      protected State MARKUP_DECLARATION_OPEN

    • rawTextStart

      protected int rawTextStart

    • rawTextEnd

      protected int rawTextEnd

    • rawTagName

      protected char[] rawTagName

    • RAWTEXT

      protected State RAWTEXT

    • RAWTEXT_LESS_THAN_SIGN

      protected State RAWTEXT_LESS_THAN_SIGN

    • RAWTEXT_END_TAG_OPEN

      protected State RAWTEXT_END_TAG_OPEN

    • RAWTEXT_END_TAG_NAME

      protected State RAWTEXT_END_TAG_NAME

    • rcdataTagStart

      protected int rcdataTagStart

    • rcdataTagName

      protected char[] rcdataTagName

    • RCDATA

      protected State RCDATA

    • RCDATA_LESS_THAN_SIGN

      protected State RCDATA_LESS_THAN_SIGN

    • RCDATA_END_TAG_OPEN

      protected State RCDATA_END_TAG_OPEN

    • RCDATA_END_TAG_NAME

      protected State RCDATA_END_TAG_NAME

    • commentStart

      protected int commentStart

    • COMMENT_START

      protected State COMMENT_START

    • COMMENT_START_DASH

      protected State COMMENT_START_DASH

    • COMMENT

      protected State COMMENT

    • COMMENT_END_DASH

      protected State COMMENT_END_DASH

    • COMMENT_END

      protected State COMMENT_END

    • COMMENT_END_BANG

      protected State COMMENT_END_BANG

    • DOCTYPE

      protected State DOCTYPE

    • BEFORE_DOCTYPE_NAME

      protected State BEFORE_DOCTYPE_NAME

    • DOCTYPE_NAME

      protected State DOCTYPE_NAME

    • AFTER_DOCUMENT_NAME

      protected State AFTER_DOCUMENT_NAME

    • doctypeIdNameStart

      protected int doctypeIdNameStart

    • AFTER_DOCTYPE_PUBLIC_KEYWORD

      protected State AFTER_DOCTYPE_PUBLIC_KEYWORD

    • BEFORE_DOCTYPE_PUBLIC_IDENTIFIER

      protected State BEFORE_DOCTYPE_PUBLIC_IDENTIFIER

    • DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED

      protected State DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED

    • DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED

      protected State DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED

    • AFTER_DOCTYPE_PUBLIC_IDENTIFIER

      protected State AFTER_DOCTYPE_PUBLIC_IDENTIFIER

    • BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS

      protected State BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS

    • BOGUS_DOCTYPE

      protected State BOGUS_DOCTYPE

    • AFTER_DOCTYPE_SYSTEM_KEYWORD

      protected State AFTER_DOCTYPE_SYSTEM_KEYWORD

    • BEFORE_DOCTYPE_SYSTEM_IDENTIFIER

      protected State BEFORE_DOCTYPE_SYSTEM_IDENTIFIER

    • DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED

      protected State DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED

    • DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED

      protected State DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED

    • AFTER_DOCTYPE_SYSTEM_IDENTIFIER

      protected State AFTER_DOCTYPE_SYSTEM_IDENTIFIER

    • scriptStartNdx

      protected int scriptStartNdx

    • scriptEndNdx

      protected int scriptEndNdx

    • scriptEndTagName

      protected int scriptEndTagName

    • SCRIPT_DATA

      protected State SCRIPT_DATA

    • SCRIPT_DATA_LESS_THAN_SIGN

      protected State SCRIPT_DATA_LESS_THAN_SIGN

    • SCRIPT_DATA_END_TAG_OPEN

      protected State SCRIPT_DATA_END_TAG_OPEN

    • SCRIPT_DATA_END_TAG_NAME

      protected State SCRIPT_DATA_END_TAG_NAME

    • scriptEscape

      protected LagartoParser.ScriptEscape scriptEscape

    • xmlDeclaration

      protected LagartoParser.XmlDeclaration xmlDeclaration

    • text

      protected char[] text

    • textLen

      protected int textLen

    • attrStartNdx

      protected int attrStartNdx

    • attrEndNdx

      protected int attrEndNdx

    • conditionalCommentStarted

      private boolean conditionalCommentStarted

    • state

      protected State state

    • TAG_WHITESPACES

      private static final char[] TAG_WHITESPACES

    • TAG_WHITESPACES_OR_END

      private static final char[] TAG_WHITESPACES_OR_END

    • CONTINUE_CHARS

      private static final char[] CONTINUE_CHARS

    • ATTR_INVALID_1

      private static final char[] ATTR_INVALID_1

    • ATTR_INVALID_2

      private static final char[] ATTR_INVALID_2

    • ATTR_INVALID_3

      private static final char[] ATTR_INVALID_3

    • ATTR_INVALID_4

      private static final char[] ATTR_INVALID_4

    • COMMENT_DASH

      private static final char[] COMMENT_DASH

    • T_DOCTYPE

      private static final char[] T_DOCTYPE

    • T_SCRIPT

      private static final char[] T_SCRIPT

    • T_XMP

      private static final char[] T_XMP

    • T_STYLE

      private static final char[] T_STYLE

    • T_IFRAME

      private static final char[] T_IFRAME

    • T_NOFRAMES

      private static final char[] T_NOFRAMES

    • T_NOEMBED

      private static final char[] T_NOEMBED

    • T_NOSCRIPT

      private static final char[] T_NOSCRIPT

    • T_TEXTAREA

      private static final char[] T_TEXTAREA

    • T_TITLE

      private static final char[] T_TITLE

    • A_PUBLIC

      private static final char[] A_PUBLIC

    • A_SYSTEM

      private static final char[] A_SYSTEM

    • CDATA

      private static final char[] CDATA

    • CDATA_END

      private static final char[] CDATA_END

    • XML

      private static final char[] XML

    • XML_VERSION

      private static final char[] XML_VERSION

    • XML_ENCODING

      private static final char[] XML_ENCODING

    • XML_STANDALONE

      private static final char[] XML_STANDALONE

    • CC_IF

      private static final char[] CC_IF

    • CC_ENDIF

      private static final char[] CC_ENDIF

    • CC_ENDIF2

      private static final char[] CC_ENDIF2

    • CC_END

      private static final char[] CC_END

    • RAWTEXT_TAGS

      private static final char[][] RAWTEXT_TAGS

    • RCDATA_TAGS

      private static final char[][] RCDATA_TAGS

    • REPLACEMENT_CHAR

      private static final char REPLACEMENT_CHAR
      See Also:

    • INVALID_CHARS

      private static final char[] INVALID_CHARS

    • _ENDIF

      private static final CharSequence _ENDIF

  • Constructor Details

    • LagartoParser

      public LagartoParser(LagartoParserConfig parserConfig, char[] input)
      Creates parser on char array.

    • LagartoParser

      public LagartoParser(char[] input)
      Creates parser on char array.

    • LagartoParser

      public LagartoParser(LagartoParserConfig parserConfig, CharSequence input)
      Creates parser on a char sequence.

    • LagartoParser

      public LagartoParser(CharSequence input)
      Creates parser on a char sequence.

  • Method Details

    • initialize

      protected void initialize()
      Initializes parser.

    • getConfig

      public LagartoParserConfig getConfig()
      Returns configuration of the parser.

    • configure

      public LagartoParser configure(Consumer<LagartoParserConfig> configConsumer)
      Configures the parser.

    • parse

      public void parse(TagVisitor visitor)
      Parses content and emits event to provided TagVisitor.

    • consumeCharacterReference

      protected void consumeCharacterReference(char allowedChar)

    • consumeCharacterReference

      protected void consumeCharacterReference()

    • _consumeCharacterReference

      private void _consumeCharacterReference()

    • _consumeAttrCharacterReference

      private void _consumeAttrCharacterReference()

    • _consumeNumber

      private void _consumeNumber(int unconsumeNdx)

    • ensureCapacity

      private void ensureCapacity()

    • ensureCapacity

      private void ensureCapacity(int growth)

    • textEmitChar

      protected void textEmitChar(char c)
      Emits characters into the local text buffer.

    • textStart

      protected void textStart()
      Resets text buffer.

    • textEmitChars

      protected void textEmitChars(int from, int to)

    • textEmitChars

      protected void textEmitChars(char[] buffer)

    • textWrap

      protected CharSequence textWrap()

    • _addAttribute

      private void _addAttribute()

    • _addAttributeWithValue

      private void _addAttributeWithValue()

    • _addAttribute

      private void _addAttribute(CharSequence attrName, CharSequence attrValue)

    • emitTag

      protected void emitTag()

    • emitComment

      protected void emitComment(int from, int to)
      Emits a comment. Also checks for conditional comments!

    • emitText

      protected void emitText()
      Emits text if there is some content.

    • emitScript

      protected void emitScript(int from, int to)

    • emitDoctype

      protected void emitDoctype()

    • emitXml

      protected void emitXml()

    • emitCData

      protected void emitCData(CharSequence charSequence)

    • errorEOF

      protected void errorEOF()

    • errorInvalidToken

      protected void errorInvalidToken()

    • errorCharReference

      protected void errorCharReference()

    • _error

      protected void _error(String message)
      Prepares error message and reports it to the visitor.

    • isAppropriateTagName

      private boolean isAppropriateTagName(char[] lowerCaseNameToMatch, int from, int to)

    • matchTagName

      private boolean matchTagName(char[] tagNameLowercase)

    • switchTypeToSelfClosing

      private void switchTypeToSelfClosing()