Package org.ccil.cowan.tagsoup

Examples of org.ccil.cowan.tagsoup.Schema

911
912
913
914
915
916
917
918
919
920
921
922
        // Expect no anchor text
        assertEquals("", linkContentHandler.getLinks().get(0).getText());

        // We'll change the schema to allow tables inside anchors!
        Schema schema = new HTMLSchema();
        schema.elementType("a", HTMLSchema.M_ANY, 65535, 0);

        ParseContext parseContext = new ParseContext();
        parseContext.set(Schema.class, schema);
        linkContentHandler = new LinkContentHandler();
        new HtmlParser().parse (
View Full Code Here
910
911
912
913
914
915
916
917
918
919
920
921
        // Expect no anchor text
        assertEquals("", linkContentHandler.getLinks().get(0).getText());

        // We'll change the schema to allow tables inside anchors!
        Schema schema = new HTMLSchema();
        schema.elementType("a", HTMLSchema.M_ANY, 65535, 0);

        ParseContext parseContext = new ParseContext();
        parseContext.set(Schema.class, schema);
        linkContentHandler = new LinkContentHandler();
        new HtmlParser().parse (
View Full Code Here
91
92
93
94
95
96
97
98
99
100
101
            // Parse the HTML document
            org.ccil.cowan.tagsoup.Parser parser =
                    new org.ccil.cowan.tagsoup.Parser();

            // Use schema from context or default
            Schema schema = context.get(Schema.class, HTML_SCHEMA);

            // TIKA-528: Reuse share schema to avoid heavy instantiation
            parser.setProperty(
                    org.ccil.cowan.tagsoup.Parser.schemaProperty, schema);
            // TIKA-599: Shared schema is thread-safe only if bogons are ignored
View Full Code Here
107
108
109
110
111
112
113
114
115
116
117
        metadata.set("LoC", String.valueOf(nbLines));
        Renderer renderer = getRenderer(type.toString());
       
        String codeAsHtml = renderer.highlight(name, out.toString(), charset.name(), false);
       
        Schema schema = context.get(Schema.class, HTML_SCHEMA);

        org.ccil.cowan.tagsoup.Parser parser = new org.ccil.cowan.tagsoup.Parser();
        parser.setProperty(org.ccil.cowan.tagsoup.Parser.schemaProperty, schema);
        parser.setContentHandler(handler);
        parser.parse(new InputSource(new StringReader(codeAsHtml)));
View Full Code Here
TOP

Related Classes of org.ccil.cowan.tagsoup.Schema

  • org.apache.tika.parser.code.SourceCodeParser
  • org.apache.tika.parser.html.HtmlParser
  • org.apache.tika.parser.html.HtmlParserTest
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.