/** * Gets the character entity parser for HTML content. The CharacterEntity parser translates known characters into * predefined entities. * * @return the character entity parser instance. */ public static synchronized CharacterEntityParser getEntityParser() { if ( entityParser == null ) { entityParser = new CharacterEntityParser( new HtmlCharacterEntities() ); } return entityParser; }
setProperty( "ang", "\u2220" ); setProperty( "spades", "\u2660" ); setProperty( "frasl", "\u2044" ); setProperty( "copy", "\u00a9" ); setProperty( "Upsilon", "\u03a5" ); setProperty( "rsquo", "\u2019" ); setProperty( "sdot", "\u22c5" ); setProperty( "beta", "\u03b2" ); setProperty( "egrave", "\u00e8" ); setProperty( "Pi", "\u03a0" ); setProperty( "micro", "\u00b5" ); setProperty( "lArr", "\u21d0" ); setProperty( "Beta", "\u0392" ); setProperty( "eacute", "\u00e9" ); setProperty( "agrave", "\u00e0" ); setProperty( "sbquo", "\u201a" ); setProperty( "ucirc", "\u00fb" ); setProperty( "mdash", "\u2014" ); setProperty( "rho", "\u03c1" ); setProperty( "Nu", "\u039d" ); setProperty( "ne", "\u2260" ); setProperty( "nsub", "\u2284" ); setProperty( "AElig", "\u00c6" ); setProperty( "raquo", "\u00bb" ); setProperty( "aacute", "\u00e1" ); setProperty( "le", "\u2264" ); setProperty( "harr", "\u2194" ); setProperty( "frac34", "\u00be" ); setProperty( "bdquo", "\u201e" );
public HtmlTextExtractor( final OutputProcessorMetaData metaData, final XmlWriter xmlWriter, final HtmlContentGenerator contentGenerator, final HtmlTagHelper tagHelper ) { super( metaData ); if ( xmlWriter == null ) { throw new NullPointerException(); } if ( contentGenerator == null ) { throw new NullPointerException(); } this.xmlWriter = xmlWriter; this.styleBuilder = tagHelper.getStyleBuilder(); this.characterEntityParser = HtmlCharacterEntities.getEntityParser(); this.textExtractorHelper = new HtmlTextExtractorHelper( tagHelper, xmlWriter, metaData, contentGenerator ); }
setProperty( "piv", "\u03d6" ); setProperty( "minus", "\u2212" ); setProperty( "zwj", "\u200d" ); setProperty( "tau", "\u03c4" ); setProperty( "Mu", "\u039c" ); setProperty( "gamma", "\u03b3" ); setProperty( "sup", "\u2283" ); setProperty( "Psi", "\u03a8" ); setProperty( "omega", "\u03c9" ); setProperty( "Oslash", "\u00d8" ); setProperty( "weierp", "\u2118" ); setProperty( "Igrave", "\u00cc" ); setProperty( "OElig", "\u0152" ); setProperty( "sup1", "\u00b9" ); setProperty( "cedil", "\u00b8" ); setProperty( "upsilon", "\u03c5" ); setProperty( "equiv", "\u2261" ); setProperty( "isin", "\u2208" ); setProperty( "Delta", "\u0394" ); setProperty( "yacute", "\u00fd" ); setProperty( "ugrave", "\u00f9" ); setProperty( "ge", "\u2265" ); setProperty( "Iacute", "\u00cd" ); setProperty( "brvbar", "\u00a6" ); setProperty( "Tau", "\u03a4" ); setProperty( "Prime", "\u2033" ); setProperty( "rfloor", "\u22a7" ); setProperty( "Ecirc", "\u00ca" ); setProperty( "ETH", "\u00d0" );
public FastHtmlTextExtractor( final OutputProcessorMetaData metaData, final XmlWriter xmlWriter, final HtmlContentGenerator contentGenerator, final HtmlTagHelper tagHelper ) { this.characterEntityParser = HtmlCharacterEntities.getEntityParser(); this.xmlWriter = xmlWriter; this.styleBuilder = tagHelper.getStyleBuilder(); this.textExtractorHelper = new HtmlTextExtractorHelper( tagHelper, xmlWriter, metaData, contentGenerator ); this.boxDefinitionFactory = new BoxDefinitionFactory(); }
.encodeEntities( textResult ) ); } else if ( encodingResult.equals( "html" ) ) { return new TypeValuePair( TextType.TYPE, HtmlCharacterEntities.getEntityParser().encodeEntities( textResult ) ); } else if ( encodingResult.equals( "formula-string" ) ) { return new TypeValuePair( TextType.TYPE, FormulaUtil.quoteString( textResult ) );