Package org.apache.tika.sax

Examples of org.apache.tika.sax.XHTMLContentHandler.endDocument()

163
164
165
166
167
168
169
170
171
172
173
            } else {
                root = new NPOIFSFileSystem(new CloseShieldInputStream(tstream)).getRoot();
            }
        }
        parse(root, context, metadata, xhtml);
        xhtml.endDocument();
    }

    protected void parse(
            DirectoryNode root, ParseContext context, Metadata metadata, XHTMLContentHandler xhtml)
            throws IOException, SAXException, TikaException {
View Full Code Here
72
73
74
75
76
77
78
79
80
81
82
            if (entry.getName().endsWith(".html") || entry.getName().endsWith(".htm")) {
                xhtml.characters(extract(chmExtractor.extractChmEntry(entry)));
            }
        }

        xhtml.endDocument();
    }

    /**
     * Extracts data from byte[]
     */
 
View Full Code Here
93
94
95
96
97
98
99
100
101
                TikaCoreProperties.MODIFIED,
                font.getHeader().getModified().getTime());

        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();
        xhtml.endDocument();
    }

}
View Full Code Here
59
60
61
62
63
64
65
66
67
68
69
                        header.getFileNameString());
                if (extractor.shouldParseEmbedded(entrydata)) {
                    extractor.parseEmbedded(stream, xhtml, entrydata, true);
                }
            }
            xhtml.endDocument();
        } catch (RarException e) {
            throw new TikaException("Unable to parse a RAR archive", e);
        }
    }
View Full Code Here
65
66
67
68
69
70
71
72
73
74
75
    public void getXHTML(ContentHandler handler, Metadata metadata)
            throws SAXException, XmlException, IOException {
        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();
        buildXHTML(xhtml);
        xhtml.endDocument();
    }

    /**
     * Populates the {@link XHTMLContentHandler} object received as parameter.
     */
 
View Full Code Here
41
42
43
44
45
46
47
48
49
50
51
            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws SAXException {
        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();
        xhtml.endDocument();
    }

    /**
     * @deprecated This method will be removed in Apache Tika 1.0.
     */
 
View Full Code Here
119
120
121
122
123
124
125
126
127
128
129
                xhtml.characters(buffer, 0, n);
                n = reader.read(buffer);
            }
            xhtml.endElement("p");

            xhtml.endDocument();
        } catch (UnsupportedEncodingException e) {
            throw new TikaException(
                    "Unsupported text encoding: " + encoding, e);
        }
    }
View Full Code Here
68
69
70
71
72
73
74
75
76
            throw new TikaException("Can't read JPEG metadata", e);
        }

        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();
        xhtml.endDocument();
    }

}
View Full Code Here
52
53
54
55
56
57
58
59
60
61
62
            }
        }

        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();
        xhtml.endDocument();
    }

    /**
     * @deprecated This method will be removed in Apache Tika 1.0.
     */
 
View Full Code Here
69
70
71
72
73
74
75
76
77
                    entrydata, context);
        } finally {
            gzip.close();
        }

        xhtml.endDocument();
    }

}
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.