Package org.apache.tika.parser.xml

Examples of org.apache.tika.parser.xml.XMLParser

81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
    public void parse(
            InputStream stream, ContentHandler handler, Metadata metadata)
            throws IOException, SAXException, TikaException {
        Document xmlDoc = parse(stream);
        XMLParser xp = new XMLParser();
        xp.getAllDocumentNs(xmlDoc);
        xp.extractContent(xmlDoc, Metadata.TITLE, "//dc:title", metadata);
        xp.extractContent(xmlDoc, Metadata.SUBJECT, "//dc:subject", metadata);
        xp.extractContent(xmlDoc, Metadata.CREATOR, "//dc:creator", metadata);
        xp.extractContent(xmlDoc, Metadata.DESCRIPTION, "//dc:description", metadata);
        xp.extractContent(xmlDoc, Metadata.LANGUAGE, "//dc:language", metadata);
        xp.extractContent(xmlDoc, Metadata.KEYWORDS, "//meta:keyword", metadata);
        xp.extractContent(xmlDoc, Metadata.DATE, "//dc:date", metadata);
        xp.extractContent(xmlDoc, "nbTab", "//meta:document-statistic/@meta:table-count", metadata);
        xp.extractContent(xmlDoc, "nbObject", "//meta:document-statistic/@meta:object-count", metadata);
        xp.extractContent(xmlDoc, "nbImg", "//meta:document-statistic/@meta:image-count", metadata);
        xp.extractContent(xmlDoc, "nbPage", "//meta:document-statistic/@meta:page-count", metadata);
        xp.extractContent(xmlDoc, "nbPara", "//meta:document-statistic/@meta:paragraph-count", metadata);
        xp.extractContent(xmlDoc, "nbWord", "//meta:document-statistic/@meta:word-count", metadata);
        xp.extractContent(xmlDoc, "nbcharacter", "//meta:document-statistic/@meta:character-count", metadata);

        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();
        xhtml.startElement("p");
        xp.concatOccurrence(xmlDoc, "//*", " ", new AppendableAdaptor(xhtml));
        xhtml.endElement("p");
        xhtml.endDocument();
    }
View Full Code Here
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
            } else if (name.equals("org.apache.jackrabbit.extractor.RTFTextExtractor")) {
                Parser parser = new RTFParser();
                parsers.put(MediaType.application("rtf"), parser);
                parsers.put(MediaType.text("rtf"), parser);
            } else if (name.equals("org.apache.jackrabbit.extractor.XMLTextExtractor")) {
                Parser parser = new XMLParser();
                parsers.put(MediaType.APPLICATION_XML, parser);
                parsers.put(MediaType.text("xml"), parser);
            } else {
                logger.warn("Ignoring unknown text extractor class: {}", name);
            }
        }

        parser.setParsers(parsers);
    }
View Full Code Here
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
                Parser parser = new RTFParser();
                parsers.put("application/rtf", parser);
                parsers.put("text/rtf", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.XMLTextExtractor")) {
                Parser parser = new XMLParser();
                parsers.put("application/xml", parser);
                parsers.put("text/xml", parser);
            } else {
                logger.warn("Ignoring unknown text extractor class: {}", name);
            }
        }

        parser.setParsers(parsers);
    }
View Full Code Here
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
                Parser parser = new RTFParser();
                parsers.put("application/rtf", parser);
                parsers.put("text/rtf", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.XMLTextExtractor")) {
                Parser parser = new XMLParser();
                parsers.put("application/xml", parser);
                parsers.put("text/xml", parser);
            } else {
                logger.warn("Ignoring unknown text extractor class: {}", name);
            }
        }

        parser.setParsers(parsers);
    }
View Full Code Here
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
                Parser parser = new RTFParser();
                parsers.put("application/rtf", parser);
                parsers.put("text/rtf", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.XMLTextExtractor")) {
                Parser parser = new XMLParser();
                parsers.put("application/xml", parser);
                parsers.put("text/xml", parser);
            } else {
                logger.warn("Ignoring unknown text extractor class: {}", name);
            }
        }

        parser.setParsers(parsers);
    }
View Full Code Here
TOP

Related Classes of org.apache.tika.parser.xml.XMLParser

  • org.apache.commons.io.input.CloseShieldInputStream
  • org.apache.jackrabbit.core.query.lucene.JackrabbitParser
  • org.apache.tika.io.CloseShieldInputStream
  • org.apache.tika.parser.opendocument.OpenOfficeParser
  • org.apache.tika.parser.ParseContext
  • org.apache.tika.sax.AppendableAdaptor
  • org.apache.tika.sax.EmbeddedContentHandler
  • org.apache.tika.sax.OfflineContentHandler
  • org.apache.tika.sax.TaggedContentHandler
  • org.apache.tika.sax.TextContentHandler
    • 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.