Examples of PDFParser

Examples of org.pdfbox.pdfparser.PDFParser

76
77
78
79
80
81
82
83
84
85
86
87
88
        this.contentHandler.startElement(NAMESPACE, "document", PREFIX + ":document",
                new AttributesImpl());

        try {
            PDFTextStripper stripper = new PDFTextStripper();
            PDFParser parser = new PDFParser(this.content.getInputStream());
            parser.parse();
            PDDocument doc = parser.getPDDocument();
            String text = stripper.getText(doc);
            doc.close();
            char[] chars = text.toCharArray();
            this.contentHandler.characters(chars, 0, chars.length);
        } catch (Exception e) {
View Full Code Here

Examples of org.pdfbox.pdfparser.PDFParser

54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
     */
    public Reader extractText(InputStream stream,
                              String type,
                              String encoding) throws IOException {
        try {
            PDFParser parser = new PDFParser(new BufferedInputStream(stream));
            try {
                parser.parse();
                PDDocument document = parser.getPDDocument();
                CharArrayWriter writer = new CharArrayWriter();

                PDFTextStripper stripper = new PDFTextStripper();
                stripper.setLineSeparator("\n");
                stripper.writeText(document, writer);

                return new CharArrayReader(writer.toCharArray());
            } finally {
                try {
                    PDDocument doc = parser.getPDDocument();
                    if (doc != null) {
                        doc.close();
                    }
                } catch (IOException e) {
                    // ignore
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.