Details
-
Bug
-
Status: Closed
-
Major
-
Resolution: Fixed
-
2.0.6
-
None
Description
I got the next stacktrace in PDF->HTML conversion using Tika:
java.lang.IndexOutOfBoundsException: Index: 0, Size: 0
at java.util.ArrayList.rangeCheck(ArrayList.java:635)
at java.util.ArrayList.get(ArrayList.java:411)
at org.apache.fontbox.cmap.CMapParser.parseBeginbfrange(CMapParser.java:364)
at org.apache.fontbox.cmap.CMapParser.parse(CMapParser.java:136)
at org.apache.pdfbox.pdmodel.font.CMapManager.parseCMap(CMapManager.java:73)
at org.apache.pdfbox.pdmodel.font.PDFont.readCMap(PDFont.java:197)
at org.apache.pdfbox.pdmodel.font.PDFont.<init>(PDFont.java:137)
at org.apache.pdfbox.pdmodel.font.PDType0Font.<init>(PDType0Font.java:119)
at org.apache.pdfbox.pdmodel.font.PDFontFactory.createFont(PDFontFactory.java:83)
at org.apache.pdfbox.pdmodel.PDResources.getFont(PDResources.java:143)
at org.apache.pdfbox.contentstream.operator.text.SetFontAndSize.process(SetFontAndSize.java:60)
at org.apache.pdfbox.contentstream.PDFStreamEngine.processOperator(PDFStreamEngine.java:838)
at org.apache.pdfbox.contentstream.PDFStreamEngine.processStreamOperators(PDFStreamEngine.java:495)
at org.apache.pdfbox.contentstream.PDFStreamEngine.processStream(PDFStreamEngine.java:469)
at org.apache.pdfbox.contentstream.PDFStreamEngine.processPage(PDFStreamEngine.java:150)
at org.apache.pdfbox.text.LegacyPDFStreamEngine.processPage(LegacyPDFStreamEngine.java:139)
at org.apache.pdfbox.text.PDFTextStripper.processPage(PDFTextStripper.java:391)
at org.apache.tika.parser.pdf.PDF2XHTML.processPage(PDF2XHTML.java:147)
at org.apache.pdfbox.text.PDFTextStripper.processPages(PDFTextStripper.java:319)
at org.apache.pdfbox.text.PDFTextStripper.writeText(PDFTextStripper.java:266)
at org.apache.tika.parser.pdf.PDF2XHTML.process(PDF2XHTML.java:117)
at org.apache.tika.parser.pdf.PDFParser.parse(PDFParser.java:159)
at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:280)