| DETECTED_FILE_EXTENSION_A | SORT_STACK_TRACE_A | COUNT |
pdf
| java.io.IOException
at org.apache.pdfbox.filter.FlateFilter.decode(FlateFilter.java:109)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:379)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:291)
at org.apache.pdfbox.cos.COSStream.getUnfilteredStream(COSStream.java:225)
at org.apache.pdfbox.pdfparser.PDFStreamParser.<init>(PDFStreamParser.java:117)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:251)
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:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.util.zip.DataFormatException
at java.util.zip.Inflater.inflateBytes(Native Method)
at java.util.zip.Inflater.inflate(Inflater.java:259)
at java.util.zip.Inflater.inflate(Inflater.java:280)
at org.apache.pdfbox.filter.FlateFilter.decompress(FlateFilter.java:128)
at org.apache.pdfbox.filter.FlateFilter.decode(FlateFilter.java:101)
... 26 more
| 19
|
pdf
| java.io.IOException
at org.apache.pdfbox.filter.FlateFilter.decode(FlateFilter.java:109)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:379)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:291)
at org.apache.pdfbox.cos.COSStream.getUnfilteredStream(COSStream.java:225)
at org.apache.pdfbox.pdmodel.common.COSStreamArray.getUnfilteredStream(COSStreamArray.java:197)
at org.apache.pdfbox.pdfparser.PDFStreamParser.<init>(PDFStreamParser.java:117)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:251)
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:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.util.zip.DataFormatException
at java.util.zip.Inflater.inflateBytes(Native Method)
at java.util.zip.Inflater.inflate(Inflater.java:259)
at java.util.zip.Inflater.inflate(Inflater.java:280)
at org.apache.pdfbox.filter.FlateFilter.decompress(FlateFilter.java:128)
at org.apache.pdfbox.filter.FlateFilter.decode(FlateFilter.java:101)
... 27 more
| 6
|
pdf
| java.lang.RuntimeException: java.io.IOException: Error: Expected operator 'ID' actual='In'
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:391)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 3
|
pdf
| java.lang.NullPointerException
at org.apache.pdfbox.filter.LZWFilter.doLZWDecode(LZWFilter.java:138)
at org.apache.pdfbox.filter.LZWFilter.decode(LZWFilter.java:114)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:351)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:291)
at org.apache.pdfbox.cos.COSStream.getUnfilteredStream(COSStream.java:225)
at org.apache.pdfbox.pdfparser.PDFStreamParser.<init>(PDFStreamParser.java:117)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:251)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
| 2
|
pdf
| java.lang.RuntimeException: java.io.IOException: Error: Expected operator 'ID' actual='IB'
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:391)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 2
|
pdf
| java.lang.NullPointerException
at org.apache.pdfbox.pdmodel.interactive.form.PDCheckbox.getOnValue(PDCheckbox.java:140)
at org.apache.pdfbox.pdmodel.interactive.form.PDCheckbox.isChecked(PDCheckbox.java:79)
at org.apache.pdfbox.pdmodel.interactive.form.PDRadioCollection.getValue(PDRadioCollection.java:128)
at o.a.t.parser.pdf.PDF2XHTML.addFieldString(PDF2XHTML.java:643)
at o.a.t.parser.pdf.PDF2XHTML.processAcroField(PDF2XHTML.java:602)
at o.a.t.parser.pdf.PDF2XHTML.extractAcroForm(PDF2XHTML.java:588)
at o.a.t.parser.pdf.PDF2XHTML.endDocument(PDF2XHTML.java:208)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:345)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
| 2
|
pdf
| java.io.IOException
at org.apache.pdfbox.filter.FlateFilter.decode(FlateFilter.java:109)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:379)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:299)
at org.apache.pdfbox.cos.COSStream.getUnfilteredStream(COSStream.java:225)
at org.apache.pdfbox.pdfparser.PDFStreamParser.<init>(PDFStreamParser.java:117)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:251)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.util.zip.DataFormatException
at java.util.zip.Inflater.inflateBytes(Native Method)
at java.util.zip.Inflater.inflate(Inflater.java:259)
at java.util.zip.Inflater.inflate(Inflater.java:280)
at org.apache.pdfbox.filter.FlateFilter.decompress(FlateFilter.java:128)
at org.apache.pdfbox.filter.FlateFilter.decode(FlateFilter.java:101)
... 26 more
| 2
|
pdf
| java.lang.RuntimeException: java.io.IOException: Error expected floating point number actual='1e'
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.cos.COSFloat.<init>(COSFloat.java:62)
at org.apache.pdfbox.cos.COSNumber.get(COSNumber.java:109)
at org.apache.pdfbox.pdfparser.BaseParser.parseDirObject(BaseParser.java:1348)
at org.apache.pdfbox.pdfparser.BaseParser.parseCOSArray(BaseParser.java:1066)
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:276)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.lang.RuntimeException: java.io.IOException: Value is not an integer: -2366213136885537460660416106463232
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.cos.COSNumber.get(COSNumber.java:104)
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:361)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.lang.RuntimeException: java.io.IOException: Value is not an integer: 14002181280108011340021812801050
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.cos.COSNumber.get(COSNumber.java:104)
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:361)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.lang.RuntimeException: java.io.IOException: Expected='null' actual='ne' at offset 1952
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.pdfparser.BaseParser.parseDirObject(BaseParser.java:1289)
at org.apache.pdfbox.pdfparser.BaseParser.parseCOSArray(BaseParser.java:1066)
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:276)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.lang.RuntimeException: java.io.IOException: expected true actual='to)-' org.apache.pdfbox.io.PushBackInputStream@68d063bb
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.pdfparser.BaseParser.parseDirObject(BaseParser.java:1303)
at org.apache.pdfbox.pdfparser.BaseParser.parseCOSArray(BaseParser.java:1066)
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:276)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.lang.IndexOutOfBoundsException: Index: 2976, Size: 2648
at java.util.ArrayList.rangeCheck(ArrayList.java:635)
at java.util.ArrayList.get(ArrayList.java:411)
at org.apache.pdfbox.filter.LZWFilter.doLZWDecode(LZWFilter.java:145)
at org.apache.pdfbox.filter.LZWFilter.decode(LZWFilter.java:114)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:351)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:291)
at org.apache.pdfbox.cos.COSStream.getUnfilteredStream(COSStream.java:225)
at org.apache.pdfbox.pdfparser.PDFStreamParser.<init>(PDFStreamParser.java:117)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:251)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
| 1
|
pdf
| java.lang.IndexOutOfBoundsException: Index: 3591, Size: 2097
at java.util.ArrayList.rangeCheck(ArrayList.java:635)
at java.util.ArrayList.get(ArrayList.java:411)
at org.apache.pdfbox.filter.LZWFilter.doLZWDecode(LZWFilter.java:157)
at org.apache.pdfbox.filter.LZWFilter.decode(LZWFilter.java:114)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:351)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:291)
at org.apache.pdfbox.cos.COSStream.getUnfilteredStream(COSStream.java:225)
at org.apache.pdfbox.pdmodel.common.COSStreamArray.getUnfilteredStream(COSStreamArray.java:197)
at org.apache.pdfbox.pdfparser.PDFStreamParser.<init>(PDFStreamParser.java:117)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:251)
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:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
| 1
|
pdf
| java.lang.RuntimeException: java.io.IOException: Error: Expected operator 'ID' actual='Id'
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:391)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.lang.IndexOutOfBoundsException: Index: 3628, Size: 2049
at java.util.ArrayList.rangeCheck(ArrayList.java:635)
at java.util.ArrayList.get(ArrayList.java:411)
at org.apache.pdfbox.filter.LZWFilter.doLZWDecode(LZWFilter.java:145)
at org.apache.pdfbox.filter.LZWFilter.decode(LZWFilter.java:114)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:351)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:291)
at org.apache.pdfbox.cos.COSStream.getUnfilteredStream(COSStream.java:225)
at org.apache.pdfbox.pdfparser.PDFStreamParser.<init>(PDFStreamParser.java:117)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:251)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
| 1
|
pdf
| java.lang.RuntimeException: java.io.IOException: Unknown dir object c=')' cInt=41 peek=')' peekInt=41 5942
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.pdfparser.BaseParser.parseDirObject(BaseParser.java:1362)
at org.apache.pdfbox.pdfparser.BaseParser.parseCOSArray(BaseParser.java:1066)
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:276)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.lang.RuntimeException: java.io.IOException: Unknown dir object c=')' cInt=41 peek=')' peekInt=41 1550
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.pdfparser.BaseParser.parseDirObject(BaseParser.java:1362)
at org.apache.pdfbox.pdfparser.BaseParser.parseCOSDictionaryValue(BaseParser.java:249)
at org.apache.pdfbox.pdfparser.BaseParser.parseCOSDictionary(BaseParser.java:356)
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:257)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.lang.IndexOutOfBoundsException: Index: 2328, Size: 2156
at java.util.ArrayList.rangeCheck(ArrayList.java:635)
at java.util.ArrayList.get(ArrayList.java:411)
at org.apache.pdfbox.filter.LZWFilter.doLZWDecode(LZWFilter.java:145)
at org.apache.pdfbox.filter.LZWFilter.decode(LZWFilter.java:114)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:351)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:291)
at org.apache.pdfbox.cos.COSStream.getUnfilteredStream(COSStream.java:225)
at org.apache.pdfbox.pdfparser.PDFStreamParser.<init>(PDFStreamParser.java:117)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:251)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
| 1
|
pdf
| java.lang.RuntimeException: java.io.IOException: Error: Expected operator 'ID' actual='Il'
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:391)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.lang.RuntimeException: java.io.IOException: Unknown dir object c=')' cInt=41 peek=')' peekInt=41 1687
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.pdfparser.BaseParser.parseDirObject(BaseParser.java:1362)
at org.apache.pdfbox.pdfparser.BaseParser.parseCOSArray(BaseParser.java:1066)
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:276)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.lang.ClassCastException: org.apache.pdfbox.cos.COSInteger cannot be cast to org.apache.pdfbox.util.PDFOperator
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:380)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
| 1
|
pdf
| java.lang.RuntimeException: java.io.IOException: Error: Expected operator 'ID' actual='I.'
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:391)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.lang.RuntimeException: java.io.IOException: Error expected floating point number actual='-600.8.3'
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.cos.COSFloat.<init>(COSFloat.java:62)
at org.apache.pdfbox.cos.COSNumber.get(COSNumber.java:109)
at org.apache.pdfbox.pdfparser.BaseParser.parseDirObject(BaseParser.java:1348)
at org.apache.pdfbox.pdfparser.BaseParser.parseCOSArray(BaseParser.java:1066)
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:276)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.lang.IndexOutOfBoundsException: Index: 3863, Size: 2223
at java.util.ArrayList.rangeCheck(ArrayList.java:635)
at java.util.ArrayList.get(ArrayList.java:411)
at org.apache.pdfbox.filter.LZWFilter.doLZWDecode(LZWFilter.java:145)
at org.apache.pdfbox.filter.LZWFilter.decode(LZWFilter.java:114)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:351)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:291)
at org.apache.pdfbox.cos.COSStream.getUnfilteredStream(COSStream.java:225)
at org.apache.pdfbox.pdmodel.common.COSStreamArray.getUnfilteredStream(COSStreamArray.java:197)
at org.apache.pdfbox.pdfparser.PDFStreamParser.<init>(PDFStreamParser.java:117)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:251)
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:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
| 1
|
pdf
| java.lang.IndexOutOfBoundsException: Index: 3898, Size: 3785
at java.util.ArrayList.rangeCheck(ArrayList.java:635)
at java.util.ArrayList.get(ArrayList.java:411)
at org.apache.pdfbox.filter.LZWFilter.doLZWDecode(LZWFilter.java:145)
at org.apache.pdfbox.filter.LZWFilter.decode(LZWFilter.java:114)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:351)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:291)
at org.apache.pdfbox.cos.COSStream.getUnfilteredStream(COSStream.java:225)
at org.apache.pdfbox.pdmodel.common.COSStreamArray.getUnfilteredStream(COSStreamArray.java:197)
at org.apache.pdfbox.pdfparser.PDFStreamParser.<init>(PDFStreamParser.java:117)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:251)
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:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
| 1
|
pdf
| java.lang.IndexOutOfBoundsException: Index: 989, Size: 897
at java.util.ArrayList.rangeCheck(ArrayList.java:635)
at java.util.ArrayList.get(ArrayList.java:411)
at org.apache.pdfbox.filter.LZWFilter.doLZWDecode(LZWFilter.java:145)
at org.apache.pdfbox.filter.LZWFilter.decode(LZWFilter.java:114)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:351)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:291)
at org.apache.pdfbox.cos.COSStream.getUnfilteredStream(COSStream.java:225)
at org.apache.pdfbox.pdmodel.common.COSStreamArray.getUnfilteredStream(COSStreamArray.java:197)
at org.apache.pdfbox.pdfparser.PDFStreamParser.<init>(PDFStreamParser.java:117)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:251)
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:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
| 1
|
pdf
| java.lang.RuntimeException: java.io.IOException: Unknown dir object c=')' cInt=41 peek=')' peekInt=41 10631
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.pdfparser.BaseParser.parseDirObject(BaseParser.java:1362)
at org.apache.pdfbox.pdfparser.BaseParser.parseCOSArray(BaseParser.java:1066)
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:276)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.lang.RuntimeException: java.io.IOException: expected false actual='fr)3.' org.apache.pdfbox.io.PushBackInputStream@5a5d8c9
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.pdfparser.BaseParser.parseDirObject(BaseParser.java:1316)
at org.apache.pdfbox.pdfparser.BaseParser.parseCOSArray(BaseParser.java:1066)
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:276)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
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:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.pdfparser.BaseParser.parseDirObject(BaseParser.java:1362)
at org.apache.pdfbox.pdfparser.BaseParser.parseCOSArray(BaseParser.java:1066)
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:276)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.io.IOException: expected='R' actual='0' at offset 2004
at org.apache.pdfbox.pdfparser.BaseParser.parseCOSDictionaryValue(BaseParser.java:260)
at org.apache.pdfbox.pdfparser.BaseParser.parseCOSDictionary(BaseParser.java:356)
at org.apache.pdfbox.pdfparser.BaseParser.parseDirObject(BaseParser.java:1264)
at org.apache.pdfbox.pdfparser.PDFObjectStreamParser.parse(PDFObjectStreamParser.java:106)
at org.apache.pdfbox.cos.COSDocument.dereferenceObjectStreams(COSDocument.java:683)
at org.apache.pdfbox.pdfparser.PDFParser.parse(PDFParser.java:255)
at org.apache.pdfbox.pdmodel.PDDocument.load(PDDocument.java:1238)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:126)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
| 1
|
pdf
| java.lang.RuntimeException: java.io.IOException: Unknown dir object c=')' cInt=41 peek=')' peekInt=41 3955
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.pdfparser.BaseParser.parseDirObject(BaseParser.java:1362)
at org.apache.pdfbox.pdfparser.BaseParser.parseCOSArray(BaseParser.java:1066)
at org.apache.pdfbox.pdfparser.BaseParser.parseDirObject(BaseParser.java:1275)
at org.apache.pdfbox.pdfparser.BaseParser.parseCOSArray(BaseParser.java:1066)
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:276)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.lang.RuntimeException: java.io.IOException: Value is not an integer: 8546736428538085463808
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.cos.COSNumber.get(COSNumber.java:104)
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:361)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.io.IOException: Unknown stream filter:COSName{LZWFecode}
at org.apache.pdfbox.filter.FilterManager.getFilter(FilterManager.java:106)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:319)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:291)
at org.apache.pdfbox.cos.COSStream.getUnfilteredStream(COSStream.java:225)
at org.apache.pdfbox.pdmodel.common.COSStreamArray.getUnfilteredStream(COSStreamArray.java:197)
at org.apache.pdfbox.pdfparser.PDFStreamParser.<init>(PDFStreamParser.java:117)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:251)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
| 1
|
pdf
| java.lang.IndexOutOfBoundsException: Index: 1887, Size: 1169
at java.util.ArrayList.rangeCheck(ArrayList.java:635)
at java.util.ArrayList.get(ArrayList.java:411)
at org.apache.pdfbox.filter.LZWFilter.doLZWDecode(LZWFilter.java:157)
at org.apache.pdfbox.filter.LZWFilter.decode(LZWFilter.java:114)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:351)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:291)
at org.apache.pdfbox.cos.COSStream.getUnfilteredStream(COSStream.java:225)
at org.apache.pdfbox.pdfparser.PDFStreamParser.<init>(PDFStreamParser.java:117)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:251)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
| 1
|
pdf
| java.lang.RuntimeException: java.io.IOException: Error: Expected operator 'ID' actual='I)'
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:391)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.lang.RuntimeException: java.io.IOException: Error expected floating point number actual='30808.58.58'
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.cos.COSFloat.<init>(COSFloat.java:62)
at org.apache.pdfbox.cos.COSNumber.get(COSNumber.java:109)
at org.apache.pdfbox.pdfparser.BaseParser.parseDirObject(BaseParser.java:1348)
at org.apache.pdfbox.pdfparser.BaseParser.parseCOSArray(BaseParser.java:1066)
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:276)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.lang.IndexOutOfBoundsException: Index: 2416, Size: 2397
at java.util.ArrayList.rangeCheck(ArrayList.java:635)
at java.util.ArrayList.get(ArrayList.java:411)
at org.apache.pdfbox.filter.LZWFilter.doLZWDecode(LZWFilter.java:157)
at org.apache.pdfbox.filter.LZWFilter.decode(LZWFilter.java:114)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:351)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:291)
at org.apache.pdfbox.cos.COSStream.getUnfilteredStream(COSStream.java:225)
at org.apache.pdfbox.pdfparser.PDFStreamParser.<init>(PDFStreamParser.java:117)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:251)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
| 1
|
pdf
| java.lang.IndexOutOfBoundsException: Index: 2027, Size: 2025
at java.util.ArrayList.rangeCheck(ArrayList.java:635)
at java.util.ArrayList.get(ArrayList.java:411)
at org.apache.pdfbox.filter.LZWFilter.doLZWDecode(LZWFilter.java:145)
at org.apache.pdfbox.filter.LZWFilter.decode(LZWFilter.java:114)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:351)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:291)
at org.apache.pdfbox.cos.COSStream.getUnfilteredStream(COSStream.java:225)
at org.apache.pdfbox.pdfparser.PDFStreamParser.<init>(PDFStreamParser.java:117)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:251)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
| 1
|
pdf
| java.lang.RuntimeException: java.io.IOException: Error expected floating point number actual='18..'
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.cos.COSFloat.<init>(COSFloat.java:62)
at org.apache.pdfbox.cos.COSNumber.get(COSNumber.java:109)
at org.apache.pdfbox.pdfparser.BaseParser.parseDirObject(BaseParser.java:1348)
at org.apache.pdfbox.pdfparser.BaseParser.parseCOSArray(BaseParser.java:1066)
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:276)
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:376)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.lang.RuntimeException: java.io.IOException: Error: Expected operator 'ID' actual='Is'
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:391)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.lang.IndexOutOfBoundsException: Index: 1670, Size: 1197
at java.util.ArrayList.rangeCheck(ArrayList.java:635)
at java.util.ArrayList.get(ArrayList.java:411)
at org.apache.pdfbox.filter.LZWFilter.doLZWDecode(LZWFilter.java:157)
at org.apache.pdfbox.filter.LZWFilter.decode(LZWFilter.java:114)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:351)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:291)
at org.apache.pdfbox.cos.COSStream.getUnfilteredStream(COSStream.java:225)
at org.apache.pdfbox.pdfparser.PDFStreamParser.<init>(PDFStreamParser.java:117)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:251)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
| 1
|
pdf
| java.io.IOException: Contents are unknown type:org.apache.pdfbox.cos.COSDictionary
at org.apache.pdfbox.pdmodel.common.PDStream.createFromCOS(PDStream.java:192)
at org.apache.pdfbox.pdmodel.PDPage.getContents(PDPage.java:639)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:380)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
| 1
|
pdf
| java.lang.IndexOutOfBoundsException: Index: 1824, Size: 1762
at java.util.ArrayList.rangeCheck(ArrayList.java:635)
at java.util.ArrayList.get(ArrayList.java:411)
at org.apache.pdfbox.filter.LZWFilter.doLZWDecode(LZWFilter.java:145)
at org.apache.pdfbox.filter.LZWFilter.decode(LZWFilter.java:114)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:351)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:291)
at org.apache.pdfbox.cos.COSStream.getUnfilteredStream(COSStream.java:225)
at org.apache.pdfbox.pdmodel.common.COSStreamArray.getUnfilteredStream(COSStreamArray.java:197)
at org.apache.pdfbox.pdfparser.PDFStreamParser.<init>(PDFStreamParser.java:117)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:251)
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:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
| 1
|
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:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.pdfparser.BaseParser.parseDirObject(BaseParser.java:1362)
at org.apache.pdfbox.pdfparser.BaseParser.parseCOSArray(BaseParser.java:1066)
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:276)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.lang.IndexOutOfBoundsException: Index: 1647, Size: 1528
at java.util.ArrayList.rangeCheck(ArrayList.java:635)
at java.util.ArrayList.get(ArrayList.java:411)
at org.apache.pdfbox.filter.LZWFilter.doLZWDecode(LZWFilter.java:145)
at org.apache.pdfbox.filter.LZWFilter.decode(LZWFilter.java:114)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:351)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:291)
at org.apache.pdfbox.cos.COSStream.getUnfilteredStream(COSStream.java:225)
at org.apache.pdfbox.pdfparser.PDFStreamParser.<init>(PDFStreamParser.java:117)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:251)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
| 1
|
pdf
| java.lang.RuntimeException: java.io.IOException: Unknown dir object c=')' cInt=41 peek=')' peekInt=41 6600
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.pdfparser.BaseParser.parseDirObject(BaseParser.java:1362)
at org.apache.pdfbox.pdfparser.BaseParser.parseCOSArray(BaseParser.java:1066)
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:276)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.lang.RuntimeException: java.io.IOException: Error expected floating point number actual='372000.408.58'
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:198)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.hasNext(PDFStreamParser.java:205)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:255)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.io.IOException
at org.apache.pdfbox.cos.COSFloat.<init>(COSFloat.java:62)
at org.apache.pdfbox.cos.COSNumber.get(COSNumber.java:109)
at org.apache.pdfbox.pdfparser.BaseParser.parseDirObject(BaseParser.java:1348)
at org.apache.pdfbox.pdfparser.BaseParser.parseCOSArray(BaseParser.java:1066)
at org.apache.pdfbox.pdfparser.PDFStreamParser.parseNextToken(PDFStreamParser.java:276)
at org.apache.pdfbox.pdfparser.PDFStreamParser.access$000(PDFStreamParser.java:49)
at org.apache.pdfbox.pdfparser.PDFStreamParser$1.tryNext(PDFStreamParser.java:193)
... 23 more
| 1
|
pdf
| java.lang.IndexOutOfBoundsException: Index: 891, Size: 567
at java.util.ArrayList.rangeCheck(ArrayList.java:635)
at java.util.ArrayList.get(ArrayList.java:411)
at org.apache.pdfbox.filter.LZWFilter.doLZWDecode(LZWFilter.java:145)
at org.apache.pdfbox.filter.LZWFilter.decode(LZWFilter.java:114)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:351)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:291)
at org.apache.pdfbox.cos.COSStream.getUnfilteredStream(COSStream.java:225)
at org.apache.pdfbox.pdfparser.PDFStreamParser.<init>(PDFStreamParser.java:117)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:251)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:235)
at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:215)
at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
| 1
|
pdf
| java.lang.IndexOutOfBoundsException: Index: 1408, Size: 1053
at java.util.ArrayList.rangeCheck(ArrayList.java:635)
at java.util.ArrayList.get(ArrayList.java:411)
at org.apache.pdfbox.filter.LZWFilter.doLZWDecode(LZWFilter.java:157)
at org.apache.pdfbox.filter.LZWFilter.decode(LZWFilter.java:114)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:351)
at org.apache.pdfbox.cos.COSStream.doDecode(COSStream.java:291)
at org.apache.pdfbox.cos.COSStream.getUnfilteredStream(COSStream.java:225)
at org.apache.pdfbox.pdmodel.common.COSStreamArray.getUnfilteredStream(COSStreamArray.java:197)
at org.apache.pdfbox.pdfparser.PDFStreamParser.<init>(PDFStreamParser.java:117)
at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:251)
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:460)
at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:385)
at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:344)
at o.a.t.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:130)
at o.a.t.parser.pdf.PDFParser.parse(PDFParser.java:149)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.CompositeParser.parse(CompositeParser.java:270)
at o.a.t.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at o.a.t.parser.RecursiveParserWrapper.parse(RecursiveParserWrapper.java:130)
at o.a.t.batch.fs.RecursiveParserWrapperFSConsumer.processFileResource(RecursiveParserWrapperFSConsumer.java:123)
at o.a.t.batch.FileResourceConsumer._processFileResource(FileResourceConsumer.java:171)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:104)
at o.a.t.batch.FileResourceConsumer.call(FileResourceConsumer.java:44)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
at java.util.concurrent.FutureTask.run(FutureTask.java:262)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
| 1
|