#213 ArrayIndexOutOfBoundsException processing a VSD file

[Anonymous]

program.name=DocFetcher
program.version=1.1-beta1
program.build=20111111-2015
java.runtime.name=Java(TM) SE Runtime Environment
java.runtime.version=1.6.0_26-b03
java.version=1.6.0_26
sun.arch.data.model=32
os.arch=x86
os.name=Windows XP
os.version=5.1
user.language=en
java.lang.ArrayIndexOutOfBoundsException: Illegal offset 8 (String data is of length 8)
at org.apache.poi.util.StringUtil.getFromUnicodeLE(StringUtil.java:70)
at org.apache.poi.hdgf.chunks.Chunk.processCommands(Chunk.java:203)
at org.apache.poi.hdgf.chunks.ChunkFactory.createChunk(ChunkFactory.java:180)
at org.apache.poi.hdgf.streams.ChunkStream.findChunks(ChunkStream.java:59)
at org.apache.poi.hdgf.streams.PointerContainingStream.findChildren(PointerContainingStream.java:93)
at org.apache.poi.hdgf.streams.PointerContainingStream.findChildren(PointerContainingStream.java:100)
at org.apache.poi.hdgf.streams.PointerContainingStream.findChildren(PointerContainingStream.java:100)
at org.apache.poi.hdgf.HDGFDiagram.<init>(HDGFDiagram.java:106)
at org.apache.poi.hdgf.extractor.VisioTextExtractor.<init>(VisioTextExtractor.java:55)
at org.apache.poi.hdgf.extractor.VisioTextExtractor.<init>(VisioTextExtractor.java:49)
at org.apache.poi.hdgf.extractor.VisioTextExtractor.<init>(VisioTextExtractor.java:65)
at net.sourceforge.docfetcher.model.parse.MSOfficeParser$MSVisioParser.extractText(MSOfficeParser.java:91)
at net.sourceforge.docfetcher.model.parse.MSOfficeParser.renderText(MSOfficeParser.java:147)
at net.sourceforge.docfetcher.model.parse.MSOfficeParser.parse(MSOfficeParser.java:112)
at net.sourceforge.docfetcher.model.parse.ParseService.doParse(ParseService.java:293)
at net.sourceforge.docfetcher.model.parse.ParseService.parse(ParseService.java:229)
at net.sourceforge.docfetcher.model.index.file.FileContext.index(FileContext.java:137)
at net.sourceforge.docfetcher.model.index.file.FileIndex$1.handleFile(FileIndex.java:276)
at net.sourceforge.docfetcher.model.index.file.HtmlFileLister.runWithHtmlPairing(HtmlFileLister.java:117)
at net.sourceforge.docfetcher.model.index.file.HtmlFileLister.doRun(HtmlFileLister.java:57)
at net.sourceforge.docfetcher.util.Stoppable.run(Stoppable.java:57)
at net.sourceforge.docfetcher.model.index.file.FileIndex.visitDirOrZip(FileIndex.java:263)
at net.sourceforge.docfetcher.model.index.file.FileIndex.doUpdate(FileIndex.java:156)
at net.sourceforge.docfetcher.model.TreeIndex.update(TreeIndex.java:126)
at net.sourceforge.docfetcher.model.index.Task.update(Task.java:98)
at net.sourceforge.docfetcher.model.index.IndexingQueue.threadLoop(IndexingQueue.java:162)
at net.sourceforge.docfetcher.model.index.IndexingQueue.access$100(IndexingQueue.java:45)
at net.sourceforge.docfetcher.model.index.IndexingQueue$2.run(IndexingQueue.java:117)

[Nam-Quang Tran]

Should be fixed in DocFetcher 1.1 beta 2.