Package net.yacy.document

Examples of net.yacy.document.Document

58
59
60
61
62
63
64
65
66
67
68
        final StringBuilder sb = new StringBuilder();
        for (final String[] row: table) {
            sb.append(concatRow(row)).append(' ');
        }
        try {
            return new Document[]{new Document(
                    location,
                    mimeType,
                    charset,
                    this,
                    null,
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
           
            /*
             * create the plasmaParserDocument for the database
             * and set shortText and bodyText properly
             */
            final Document[] docs = new Document[]{new Document(
                    location,
                    mimeType,
                    "UTF-8",
                    this,
                    null,
View Full Code Here
141
142
143
144
145
146
147
148
149
150
151
            if (docKeywordStr != null) docKeywords = docKeywordStr.split(" |,");
           
            // create the parser document
            Document[] docs = null;
            final byte[] contentBytes = UTF8.getBytes(writer.toString());
            docs = new Document[]{new Document(
                    location,
                    mimeType,
                    "UTF-8",
                    this,
                    languages,
View Full Code Here
61
62
63
64
65
66
67
68
69
70
71
            final RTFEditorKit theRtfEditorKit = new RTFEditorKit();              
            theRtfEditorKit.read(source, doc, 0);           
           
            final String bodyText = doc.getText(0, doc.getLength());
           
            return new Document[]{new Document(
                    location,
                    mimeType,
                    "UTF-8",
                    this,
                    null,
View Full Code Here
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
109
110
     * all extracted information about the parsed document
     */
    public Document[] parse(final MultiProtocolURI location, final String mimeType, final String charset, final InputStream source)
            throws Parser.Failure, InterruptedException {

      Document theDoc = null;
     
        try {
            String contents = "";
            SummaryInformation summary = null;
            try {
                final VisioTextExtractor extractor = new VisioTextExtractor(source);
              contents = extractor.getText();
                summary = extractor.getSummaryInformation();
            } catch (Exception e) {
              Log.logWarning("vsdParser", e.getMessage());
            }

            String author = null;
            String[] keywords = null;
            String title = null;
            if (summary != null) {
                author = summary.getAuthor();
                if (summary.getKeywords() != null) {
                    keywords = summary.getKeywords().split("[ ,;]");
                }
                title = summary.getTitle();
            }

            String abstrct = null;
            abstrct = ((contents.length() > 80)? contents.substring(0, 80) : contents.trim()).
                          replaceAll("\r\n"," ").
                          replaceAll("\n"," ").
                          replaceAll("\r"," ").
                          replaceAll("\t"," ");
           
            if (title == null) {
                title = abstrct;
            }

           // As the result of parsing this function must return a plasmaParserDocument object
            return new Document[]{new Document(
                    location,     // url of the source document
                    mimeType,     // the documents mime type
                    "UTF-8",      // charset of the document text
                    this,
                    null,         // language
View Full Code Here
202
203
204
205
206
207
208
209
210
211
212
   
    return phrases;
  }

  public static String autoTag(final String url, final LoaderDispatcher loader, final int max, final TreeMap<String, YMarkTag> tags) {
    final Document document = loadDocument(url, loader);
    if (document != null)
      return autoTag(document, max, tags);
    else
      return "/IOExceptions";
  }
View Full Code Here
102
103
104
105
106
107
108
109
110
111
112
                anchors.put(new MultiProtocolURI(url), p);
                contents = contents.substring(0,urlStart)+contents.substring(urlEnd);
            }

           // As the result of parsing this function must return a plasmaParserDocument object
            return new Document[]{new Document(
                    location,     // url of the source document
                    mimeType,     // the documents mime type
                    "UTF-8",      // charset of the document text
                    this,
                    null,
View Full Code Here
156
157
158
159
160
161
162
163
164
165
166
            if (docKeywordStr != null) docKeywords = docKeywordStr.split(" |,");
           
            // create the parser document
            Document[] docs = null;
            final byte[] contentBytes = UTF8.getBytes(writer.toString());
            docs = new Document[]{new Document(
                    location,
                    mimeType,
                    "UTF-8",
                    this,
                    languages,
View Full Code Here
179
180
181
182
183
184
185
186
187
188
189
        // COSStream, COSString, COSName, COSDocument, COSInteger[], COSNull
        // the great number of these objects can easily be seen in Java Visual VM
        // we try to get this shit out of the memory here by forced clear calls, hope the best the rubbish gets out.
        COSName.clearResources();
        PDFont.clearResources();
        return new Document[]{new Document(
                location,
                mimeType,
                "UTF-8",
                this,
                null,
View Full Code Here
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
                System.out.println(pdfFile.getAbsolutePath());
                final long startTime = System.currentTimeMillis();

                // parse
                final AbstractParser parser = new pdfParser();
                Document document = null;
                try {
                    document = Document.mergeDocuments(null, "application/pdf", parser.parse(null, "application/pdf", null, new FileInputStream(pdfFile)));
                } catch (final Parser.Failure e) {
                    System.err.println("Cannot parse file " + pdfFile.getAbsolutePath());
                    Log.logException(e);
                } catch (final InterruptedException e) {
                    System.err.println("Interrupted while parsing!");
                    Log.logException(e);
                } catch (final NoClassDefFoundError e) {
                    System.err.println("class not found: " + e.getMessage());
                } catch (final FileNotFoundException e) {
                    Log.logException(e);
                }

                // statistics
                System.out.println("\ttime elapsed: " + (System.currentTimeMillis() - startTime) + " ms");

                // output
                if (document == null) {
                    System.out.println("\t!!!Parsing without result!!!");
                } else {
                    System.out.println("\tParsed text with " + document.getTextLength() + " chars of text and " + document.getAnchors().size() + " anchors");
                    try {
                        // write file
                        FileUtils.copy(document.getText(), new File("parsedPdf.txt"));
                    } catch (final IOException e) {
                        System.err.println("error saving parsed document");
                        Log.logException(e);
                    }
                }
View Full Code Here
TOP

Related Classes of net.yacy.document.Document

  • Bookmarks
  • de.anomic.data.ymark.YMarkAutoTagger
  • de.anomic.data.ymark.YMarkTables
  • de.anomic.search.DocumentIndex
  • de.anomic.search.MediaSnippet
  • de.anomic.search.Segment
  • de.anomic.search.Switchboard
  • de.anomic.search.TextSnippet
  • get_metadata
  • get_treeview
    • 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.