Package org.apache.pdfbox.pdfparser

Examples of org.apache.pdfbox.pdfparser.PDFParser

56
57
58
59
60
61
62
63
64
65
66
67
68
            PDDocument document = null;
            FileInputStream file = null;
            try
            {
                file = new FileInputStream( args[0] );
                PDFParser parser = new PDFParser( file );
                parser.parse();
                document = parser.getPDDocument();
                if( document.isEncrypted() )
                {
                    try
                    {
                        document.decrypt( "" );
View Full Code Here
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
    }

    private static PDDocument getDocument( String filename ) throws IOException
    {
        FileInputStream input = null;
        PDFParser parser = null;
        PDDocument result = null;
        try
        {
            input = new FileInputStream( filename );
            parser = new PDFParser( input );
            parser.parse();
            result = parser.getPDDocument();
        }
        finally
        {
            if( input != null )
            {
View Full Code Here
835
836
837
838
839
840
841
842
843
     *
     * @throws IOException If there is an error reading from the stream.
     */
    public static PDDocument load( InputStream input, RandomAccess scratchFile ) throws IOException
    {
        PDFParser parser = new PDFParser( new BufferedInputStream( input ), scratchFile );
        parser.parse();
        return parser.getPDDocument();
    }
View Full Code Here
854
855
856
857
858
859
860
861
862
     *
     * @throws IOException If there is an error reading from the stream.
     */
    public static PDDocument load(InputStream input, RandomAccess scratchFile, boolean force) throws IOException
    {
        PDFParser parser = new PDFParser( new BufferedInputStream( input ), scratchFile, force);
        parser.parse();
        return parser.getPDDocument();
    }
View Full Code Here
59
60
61
62
63
64
65
66
67
68
69
70
71
72
        java.io.OutputStream os = null;
        COSWriter writer = null;
        try
        {
            is = new java.io.FileInputStream(in);
            PDFParser parser = new PDFParser(is);
            parser.parse();

            COSDocument doc = parser.getDocument();

            os = new java.io.FileOutputStream(out);
            writer = new COSWriter(os);

            writer.write(doc);
View Full Code Here
200
201
202
203
204
205
206
207
208
     *
     * @throws IOException If there is an error reading from the stream.
     */
    public static FDFDocument load( InputStream input ) throws IOException
    {
        PDFParser parser = new PDFParser( input );
        parser.parse();
        return parser.getFDFDocument();
    }
View Full Code Here
292
293
294
295
296
297
298
299
300
301
302
303
304
    {
        COSDocument cos = null;

        try
        {
            PDFParser parser = new PDFParser(metadata);
            parser.parse();
            cos = parser.getDocument();

            // sanity check: PDFBox breaks on encrypted documents, so give up.
            if(cos.getEncryptionDictionary() != null)
            {
                throw new MetadataValidationException("This packager cannot accept an encrypted PDF document.");
View Full Code Here
45
46
47
48
49
50
51
52
53
54
55
56
57
      pdfStripper.setStartPage(1);
      pdfStripper.setEndPage(1);

      FileInputStream input = new FileInputStream(file);

      PDFParser parser = new PDFParser(input);
      parser.parse();
      cosDoc = parser.getDocument();
      pdDoc = new PDDocument(cosDoc);

      String text = pdfStripper.getText(pdDoc);
      text = text.replaceAll("\t", " ");
      Iterable<String> lines = Splitter.on("\n").split(text);
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
65
66
67
  public InputStream cut(final InputStream source, final int start, final int end) {
    try {
      Assert.notNull(source, "source");
      Assert.greaterOrEqual(start, 1, "start");

      PDFParser parser = new PDFParser(source);
      parser.parse();

      PDDocument document = parser.getPDDocument();

      Splitter splitter = new Splitter();
      splitter.setSplitAtPage(1);

      List<PDDocument> list = splitter.split(document);
View Full Code Here
137
138
139
140
141
142
143
144
145
146
147
148
149
150
  public InputStream[] split(final InputStream source, final int size) {
    try {
      Assert.notNull(source, "source");
      Assert.greaterThan(size, 0, "size");

      PDFParser parser = new PDFParser(source);
      parser.parse();

      PDDocument document = parser.getPDDocument();
      Splitter splitter = new Splitter();
      splitter.setSplitAtPage(size);

      List<PDDocument> list = splitter.split(document);
      InputStream[] array = new InputStream[list.size()];
View Full Code Here
TOP

Related Classes of org.apache.pdfbox.pdfparser.PDFParser

  • br.com.objectos.way.reports.htmltopdf.Pdfs
  • br.net.woodstock.rockframework.document.pdf.pdfbox.CutProcessor
  • br.net.woodstock.rockframework.document.pdf.pdfbox.GetTextProcessor
  • br.net.woodstock.rockframework.document.pdf.pdfbox.PDFBox
  • br.net.woodstock.rockframework.document.pdf.pdfbox.SplitProcessor
  • br.net.woodstock.rockframework.office.pdf.impl.PDFBoxManager
  • com.stimulus.archiva.extraction.PDFExtractor
  • net.sf.regain.crawler.preparator.PdfBoxPreparator
  • org.apache.pdfbox.cos.COSBase
  • org.apache.pdfbox.cos.COSDictionary
    • 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.