[
https://issues.apache.org/jira/browse/PDFBOX-1757?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13808030#comment-13808030
]
William Palmer commented on PDFBOX-1757:
----------------------------------------
More results (including comparison with loadNonSeq)
-http://digitalcorpora.org/corp/nps/files/govdocs1/367/367594.pdf
java.lang.RuntimeException: java.io.IOException: Unknown dir object
c=')' cInt=41 peek=')' peekInt=41 16574
at
org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:187)
-loadnonseq
java.lang.RuntimeException: java.io.IOException: Unknown dir object
c=')' cInt=41 peek=')' peekInt=41 16574
at
org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:187)
Caused by: java.io.IOException: Unknown dir object c=')' cInt=41
peek=')' peekInt=41 16574
at
org.apache.pdfbox.pdfparser.BaseParser.parseDirObject(BaseParser.java:1334)
at
org.apache.pdfbox.pdfparser.BaseParser.parseCOSArray(BaseParser.java:1036)
at
org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:266)
-http://digitalcorpora.org/corp/nps/files/govdocs1/379/379049.pdf
java.lang.RuntimeException: java.io.IOException: Error: Expected
operator 'ID' actual='Im'
at
org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:187)
-loadnonseq
java.lang.RuntimeException: java.io.IOException: Error: Expected
operator 'ID' actual='Im'
at
org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:187)
Caused by: java.io.IOException: Error: Expected operator 'ID'
actual='Im'
at
org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:386)
at
org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:46)
at
org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:182)
-http://digitalcorpora.org/corp/nps/files/govdocs1/392/392154.pdf
java.lang.RuntimeException: java.io.IOException: Error: Expected
operator 'ID' actual='Il'
at
org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:187)
-loadnonseq
java.io.IOException: Error: Expected an integer type, actual='ref'
at org.apache.pdfbox.pdfparser.BaseParser.readInt(BaseParser.java:1622)
-http://digitalcorpora.org/corp/nps/files/govdocs1/427/427669.pdf
java.lang.RuntimeException: java.io.IOException: Error expected
floating point number actual='50.7269.36'
at
org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:187)
-loadnonseq
java.io.IOException: Error: Expected an integer type, actual='f'
at org.apache.pdfbox.pdfparser.BaseParser.readInt(BaseParser.java:1622)
-http://digitalcorpora.org/corp/nps/files/govdocs1/435/435321.pdf
java.lang.RuntimeException: java.io.IOException: Unknown dir object
c=')' cInt=41 peek=')' peekInt=41 2965
at
org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:187)
-loadnonseq
java.io.IOException: Error: Expected an integer type, actual='ref'
at org.apache.pdfbox.pdfparser.BaseParser.readInt(BaseParser.java:1622)
-http://digitalcorpora.org/corp/nps/files/govdocs1/443/443752.pdf
java.lang.RuntimeException: java.io.IOException: Error: Expected
operator 'ID' actual='I)'
at
org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:187)
-loadnonseq
java.lang.RuntimeException: java.io.IOException: Error: Expected
operator 'ID' actual='I)'
at
org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:187)
Caused by: java.io.IOException: Error: Expected operator 'ID'
actual='I)'
at
org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:386)
at
org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:46)
at
org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:182)
-http://digitalcorpora.org/corp/nps/files/govdocs1/455/455746.pdf
java.lang.RuntimeException: java.io.IOException: Unknown dir object
c=')' cInt=41 peek=')' peekInt=41 10283
at
org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:187)
-loadnonseq
java.lang.RuntimeException: java.io.IOException: Unknown dir object
c=')' cInt=41 peek=')' peekInt=41 10283
at
org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:187)
Caused by: java.io.IOException: Unknown dir object c=')' cInt=41
peek=')' peekInt=41 10283
at
org.apache.pdfbox.pdfparser.BaseParser.parseDirObject(BaseParser.java:1334)
at
org.apache.pdfbox.pdfparser.BaseParser.parseCOSArray(BaseParser.java:1036)
at
org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:266)
at
org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:46)
at
org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:182)
-http://digitalcorpora.org/corp/nps/files/govdocs1/475/475121.pdf
java.lang.RuntimeException: java.io.IOException: Value is not an
integer: -2366213136885537460660416106463232
at
org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:187)
-loadnonseq
java.lang.RuntimeException: java.io.IOException: Value is not an
integer: -2366213136885537460660416106463232
at
org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:187)
Caused by: java.io.IOException: Value is not an integer:
-2366213136885537460660416106463232
at org.apache.pdfbox.cos.COSNumber.get(COSNumber.java:104)
at
org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:351)
at
org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:46)
at
org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:182)
-http://digitalcorpora.org/corp/nps/files/govdocs1/477/477139.pdf
java.lang.RuntimeException: java.io.IOException: Error: Expected
operator 'ID' actual='I)'
at
org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:187)
-loadnonseq
java.io.IOException: Error: Expected an integer type, actual='ref'
at org.apache.pdfbox.pdfparser.BaseParser.readInt(BaseParser.java:1622)
at
org.apache.pdfbox.pdfparser.NonSequentialPDFParser.parseXrefObjStream(NonSequentialPDFParser.java:458)
-http://digitalcorpora.org/corp/nps/files/govdocs1/498/498264.pdf
java.lang.RuntimeException: java.io.IOException: Error: Expected
operator 'ID' actual='Ia'
at
org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:187)
-loadnonseq
java.io.IOException: Error: Expected an integer type, actual=''
at org.apache.pdfbox.pdfparser.BaseParser.readInt(BaseParser.java:1622)
at
org.apache.pdfbox.pdfparser.NonSequentialPDFParser.parseXrefObjStream(NonSequentialPDFParser.java:458)
> Errors parsing/extracting text from a PDF
> -----------------------------------------
>
> Key: PDFBOX-1757
> URL: https://issues.apache.org/jira/browse/PDFBOX-1757
> Project: PDFBox
> Issue Type: Bug
> Components: Parsing
> Affects Versions: 1.8.2
> Environment: Ubuntu Linux & Windows 7 (both JDK6)
> Reporter: William Palmer
> Priority: Minor
>
> I am trying to extract text from PDFs. Extracting text from the test file
> http://digitalcorpora.org/corp/nps/files/govdocs1/020/020747.pdf causes
> exceptions to be thrown.
> The first:
> Exception in thread "main" java.lang.RuntimeException: java.io.IOException:
> Value is not an integer: 636121514401477526485946144
> at
> org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:187)
> at
> org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:194)
> at
> org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
> at
> org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
> at
> org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
> at
> org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:455)
> at
> org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:379)
> at
> org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:335)
> Caused by: java.io.IOException: Value is not an integer:
> 636121514401477526485946144
> at org.apache.pdfbox.cos.COSNumber.get(COSNumber.java:104)
> at
> org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:351)
> at
> org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:46)
> at
> org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:182)
> Code to cause above exception:
> PDFTextStripper ts = new PDFTextStripper();
> PrintWriter out = new PrintWriter(new FileWriter(new File ("020747.txt")));
> PDDocument doc = PDDocument.load(new File("020747.pdf").toURI().toURL(),
> true);
> ts.setForceParsing(true);
> ts.writeText(doc, out);
> Using the following code causes a different exception until
> org.apache.pdfbox.baseParser.pushBackSize is increased (only tested 1024768).
> After it is increased I get basically the same exception as above
> PrintWriter out = new PrintWriter(new FileWriter(new File("020747.txt")));
> PDFParser parser = new PDFParser(new FileInputStream(new File("020747.pdf")));
> parser.parse();
> PDFTextStripper ts = new PDFTextStripper();
> ts.setForceParsing(true);
> ts.writeText(parser.getPDDocument(), out);
--
This message was sent by Atlassian JIRA
(v6.1#6144)
