Examples of XHTMLContentHandler

Examples of org.apache.tika.sax.XHTMLContentHandler

38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
            throws IOException, SAXException, TikaException {
       
        Reader reader = Utils.getUTF8Reader(stream, metadata);
        metadata.set(Metadata.CONTENT_TYPE, "text/plain");

        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();
        xhtml.startElement("p");
        char[] buffer = new char[4096];
        for (int n = reader.read(buffer); n != -1; n = reader.read(buffer)) {
            xhtml.characters(buffer, 0, n);
        }
        xhtml.endElement("p");
        xhtml.endDocument();
    }
View Full Code Here

Examples of org.apache.tika.sax.XHTMLContentHandler

62
63
64
65
66
67
68
    private final XHTMLContentHandler handler;

    private PDF2XHTML(ContentHandler handler, Metadata metadata)
            throws IOException {
        this.handler = new XHTMLContentHandler(handler, metadata);
    }
View Full Code Here

Examples of org.apache.tika.sax.XHTMLContentHandler

98
99
100
101
102
103
104
105
106
107
108
109
        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

Examples of org.apache.tika.sax.XHTMLContentHandler

52
53
54
55
56
57
58
59
60
            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
        new JpegExtractor(metadata).parse(stream);

        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();
        xhtml.endDocument();
    }
View Full Code Here

Examples of org.apache.tika.sax.XHTMLContentHandler

75
76
77
78
79
80
81
82
83
            } catch (IIOException e) {
                throw new TikaException(type + " parse error", e);
            }
        }

        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();
        xhtml.endDocument();
    }
View Full Code Here

Examples of org.apache.tika.sax.XHTMLContentHandler

131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
            int bom = reader.read();
            if (bom != '\ufeff') { // zero-width no-break space
                reader.reset();
            }

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

            xhtml.startElement("p");
            char[] buffer = new char[4096];
            int n = reader.read(buffer);
            while (n != -1) {
                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

Examples of org.apache.tika.sax.XHTMLContentHandler

76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
            throws IOException, SAXException, TikaException {
        if (metadata.get(Metadata.CONTENT_TYPE) == null) {
            metadata.set(Metadata.CONTENT_TYPE, "application/xml");
        }

        final XHTMLContentHandler xhtml =
            new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();
        xhtml.startElement("p");

        getSAXParser(context).parse(
                new CloseShieldInputStream(stream),
                new OfflineContentHandler(
                        getContentHandler(handler, metadata)));

        xhtml.endElement("p");
        xhtml.endDocument();
    }
View Full Code Here

Examples of org.apache.tika.sax.XHTMLContentHandler

62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
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
        this.parser = context.get(Parser.class, EmptyParser.INSTANCE);
    }

    public void parse(InputStream stream)
            throws IOException, SAXException, TikaException {
        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();

        // At the end we want to close the package/compression stream to
        // release any associated resources, but the underlying document
        // stream should not be closed
        stream = new CloseShieldInputStream(stream);

        // Capture two bytes to determine the packaging/compression format
        if (!stream.markSupported()) {
            stream = new BufferedInputStream(stream);
        }
        stream.mark(2);
        int a = stream.read();
        int b = stream.read();
        stream.reset();

        // Select decompression or unpacking mechanism based on the two bytes
        if (a == 'B' && b == 'Z') {
            metadata.set(Metadata.CONTENT_TYPE, "application/x-bzip");
            decompress(new BZip2CompressorInputStream(stream), xhtml);
        } else if (a == 0x1f && b == 0x8b) {
            metadata.set(Metadata.CONTENT_TYPE, "application/x-gzip");
            decompress(new GZIPInputStream(stream), xhtml);
        } else if (a == 'P' && b == 'K') {
            metadata.set(Metadata.CONTENT_TYPE, "application/zip");
            unpack(new ZipArchiveInputStream(stream), xhtml);
        } else if ((a == '0' && b == '7')
                || (a == 0x71 && b == 0xc7)
                || (a == 0xc7 && b == 0x71)) {
            metadata.set(Metadata.CONTENT_TYPE, "application/x-cpio");
            unpack(new CpioArchiveInputStream(stream), xhtml);
        } else if (a == '=' && (b == '<' || b == '!')) {
            metadata.set(Metadata.CONTENT_TYPE, "application/x-archive");
            unpack(new ArArchiveInputStream(stream), xhtml);
        } else {
            metadata.set(Metadata.CONTENT_TYPE, "application/x-tar");
            unpack(new TarArchiveInputStream(stream), xhtml);
        }

        xhtml.endDocument();
    }
View Full Code Here

Examples of org.apache.tika.sax.XHTMLContentHandler

66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
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
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
     */
    public void parse(
            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();

        POIFSFileSystem filesystem = new POIFSFileSystem(stream);

        // Parse summary entries first, to make metadata available early
        new SummaryExtractor(metadata).parseSummaries(filesystem);

        // Parse remaining document entries
        boolean outlookExtracted = false;
        Iterator<?> entries = filesystem.getRoot().getEntries();
        while (entries.hasNext()) {
            Entry entry = (Entry) entries.next();
            String name = entry.getName();
            if (entry instanceof DirectoryEntry) {
               if ("Quill".equals(name)) {
                  setType(metadata, "application/x-mspublisher");
                  PublisherTextExtractor extractor =
                      new PublisherTextExtractor(filesystem);
                  xhtml.element("p", extractor.getText());
               }
            } else if (entry instanceof DocumentEntry) {
               if ("WordDocument".equals(name)) {
                   setType(metadata, "application/msword");
                   WordExtractor extractor = new WordExtractor(filesystem);

                   addTextIfAny(xhtml, "header", extractor.getHeaderText());

                   for (String paragraph : extractor.getParagraphText()) {
                       xhtml.element("p", paragraph);
                   }

                   for (String paragraph : extractor.getFootnoteText()) {
                       xhtml.element("p", paragraph);
                   }

                   for (String paragraph : extractor.getCommentsText()) {
                       xhtml.element("p", paragraph);
                   }

                   for (String paragraph : extractor.getEndnoteText()) {
                       xhtml.element("p", paragraph);
                   }

                   addTextIfAny(xhtml, "footer", extractor.getFooterText());
               } else if ("PowerPoint Document".equals(name)) {
                   setType(metadata, "application/vnd.ms-powerpoint");
                   PowerPointExtractor extractor =
                       new PowerPointExtractor(filesystem);
                   xhtml.element("p", extractor.getText(true, true));
               } else if ("Workbook".equals(name)) {
                   setType(metadata, "application/vnd.ms-excel");
                   Locale locale = context.get(Locale.class, Locale.getDefault());
                   new ExcelExtractor().parse(filesystem, xhtml, locale);
               } else if ("VisioDocument".equals(name)) {
                   setType(metadata, "application/vnd.visio");
                   VisioTextExtractor extractor =
                       new VisioTextExtractor(filesystem);
                   for (String text : extractor.getAllText()) {
                       xhtml.element("p", text);
                   }
               } else if (!outlookExtracted && name.startsWith("__substg1.0_")) {
                   // TODO: Cleaner mechanism for detecting Outlook
                   outlookExtracted = true;
                   setType(metadata, "application/vnd.ms-outlook");
                   new OutlookExtractor(filesystem).parse(xhtml, metadata);
               }
            }
        }

        xhtml.endDocument();
    }
View Full Code Here

Examples of org.apache.tika.sax.XHTMLContentHandler

55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
        metadata.set(Metadata.CONTENT_TYPE, "audio/mpeg");

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

        // Create handlers for the various kinds of ID3 tags
        ID3TagsAndAudio audioAndTags = getAllTagHandlers(stream, handler);

        if (audioAndTags.tags.length > 0) {
           CompositeTagHandler tag = new CompositeTagHandler(audioAndTags.tags);

           metadata.set(Metadata.TITLE, tag.getTitle());
           metadata.set(Metadata.AUTHOR, tag.getArtist());
           metadata.set(XMPDM.ARTIST, tag.getArtist());
           metadata.set(XMPDM.ALBUM, tag.getAlbum());
           metadata.set(XMPDM.RELEASE_DATE, tag.getYear());
           metadata.set(XMPDM.GENRE, tag.getGenre());
           metadata.set(XMPDM.LOG_COMMENT, tag.getComment());

           xhtml.element("h1", tag.getTitle());
           xhtml.element("p", tag.getArtist());

            // ID3v1.1 Track addition
            if (tag.getTrackNumber() != null) {
                xhtml.element("p", tag.getAlbum() + ", track " + tag.getTrackNumber());
                metadata.set(XMPDM.TRACK_NUMBER, tag.getTrackNumber());
            } else {
                xhtml.element("p", tag.getAlbum());
            }
            xhtml.element("p", tag.getYear());
            xhtml.element("p", tag.getComment());
            xhtml.element("p", tag.getGenre());
        }
        if (audioAndTags.audio != null) {
            metadata.set("samplerate", String.valueOf(audioAndTags.audio.getSampleRate()));
            metadata.set("channels", String.valueOf(audioAndTags.audio.getChannels()));
            metadata.set("version", audioAndTags.audio.getVersion());
            metadata.set(
                    XMPDM.AUDIO_SAMPLE_RATE,
                    Integer.toString(audioAndTags.audio.getSampleRate()));
        }

        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.