Procssing this doc:
http://www.oracle.com/technetwork/java/jaf-1-150219.pdf
I am getting this:
x=33
y=159
w=216
h=43
page=1
getting text from page #1 of 21 in doc.
Exception in thread "main" java.lang.ArrayIndexOutOfBoundsException: Array
index out of range: 3
at java.util.Vector.get(Vector.java:748)
at
org.apache.pdfbox.text.PDFTextStripper.processTextPosition(PDFTextStripper.java:903)
at
org.apache.pdfbox.text.PDFTextStripperByArea.processTextPosition(PDFTextStripperByArea.java:132)
at
org.apache.pdfbox.text.PDFTextStreamEngine.showGlyph(PDFTextStreamEngine.java:229)
at
org.apache.pdfbox.contentstream.PDFStreamEngine.showText(PDFStreamEngine.java:690)
at
org.apache.pdfbox.contentstream.PDFStreamEngine.showTextStrings(PDFStreamEngine.java:600)
at
org.apache.pdfbox.contentstream.operator.text.ShowTextAdjusted.process(ShowTextAdjusted.java:38)
at
org.apache.pdfbox.contentstream.PDFStreamEngine.processOperator(PDFStreamEngine.java:802)
at
org.apache.pdfbox.contentstream.PDFStreamEngine.processStreamOperators(PDFStreamEngine.java:464)
at
org.apache.pdfbox.contentstream.PDFStreamEngine.processStream(PDFStreamEngine.java:438)
at
org.apache.pdfbox.contentstream.PDFStreamEngine.processPage(PDFStreamEngine.java:149)
at
org.apache.pdfbox.text.PDFTextStreamEngine.processPage(PDFTextStreamEngine.java:117)
at
org.apache.pdfbox.text.PDFTextStripper.processPage(PDFTextStripper.java:347)
at
org.apache.pdfbox.text.PDFTextStripperByArea.extractRegions(PDFTextStripperByArea.java:113)
Code is:
String textFromBox(PDDocument doc, int x, int y, int w, int h, int page)
throws IOException {
System.out.println("x="+x);
System.out.println("y="+y);
System.out.println("w="+w);
System.out.println("h="+h);
System.out.println("page="+page);
PDFTextStripperByArea stripper = new PDFTextStripperByArea();
Rectangle rect = new Rectangle(x, y - h, w, h);
stripper.addRegion("region", rect);
int pageCount = doc.getDocumentCatalog().getPages().getCount();
System.out.println("getting text from page #" + page + " of " +
pageCount + " in doc.");
if (page <= pageCount) {
PDPage pp = (PDPage)
doc.getDocumentCatalog().getPages().get(page - 1);
stripper.extractRegions(pp);
String text = stripper.getTextForRegion("region");
System.out.println("text=" + text);
return text;
} else {
return "No page #" + page;
}
}
Thanks!
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
