2010-05-29 11:05:33,643 DEBUG Config: Configuration: 2010-05-29 11:05:33,645 DEBUG Config: pdfimage.recognizer.img2txt=/home/cysun/current/pdfimage/cpp/img2txt 2010-05-29 11:05:33,645 DEBUG Config: pdfimage.inserter.delete.ocr.text=false 2010-05-29 11:05:33,645 DEBUG Config: pdfimage.inserter.delete.tif=false 2010-05-29 11:05:33,645 DEBUG Config: pdfimage.extractor.extract.text=true 2010-05-29 11:05:33,646 DEBUG Config: pdfimage.recognizer.pdf2iot1.enabled=true 2010-05-29 11:05:33,646 DEBUG Config: pdfimage.inserter.enabled=false 2010-05-29 11:05:33,646 DEBUG Config: pdfimage.inserter.junk.phrases=D:/Workspaces/1/pdfimage/src/junk_phrases.txt 2010-05-29 11:05:33,646 DEBUG Config: pdfimage.recognizer.enabled=false 2010-05-29 11:05:33,647 DEBUG Config: pdfimage.recognizer.pdf2iot=/home/cysun/current/pdfimage/cpp/pdf2iot 2010-05-29 11:05:33,647 DEBUG Config: pdfimage.recognizer.pdf2iot2.enabled=true 2010-05-29 11:05:33,647 DEBUG Config: pdfimage.recognizer.img2txt.enabled=true 2010-05-29 11:05:33,647 DEBUG Config: pdfimage.inserter.image.markers=D:/Workspaces/1/pdfimage/src/image_markers.txt 2010-05-29 11:05:33,647 DEBUG Config: pdfimage.inserter.text.match.threshold=0.95 2010-05-29 11:05:33,647 DEBUG Config: pdfimage.inserter.delete.page.text=false 2010-05-29 11:05:33,647 DEBUG Config: pdfimage.extractor.enabled=true 2010-05-29 11:05:33,648 DEBUG Config: Image markers loaded: 2010-05-29 11:05:33,648 DEBUG Config: CHRG: 9 2010-05-29 11:05:33,648 DEBUG Config: FR: 1 2010-05-29 11:05:33,648 DEBUG Config: HMAN: 14 2010-05-29 11:05:33,649 DEBUG Config: STATUTE: 9 2010-05-29 11:05:33,649 DEBUG Config: PPP: 15 2010-05-29 11:05:33,655 INFO Extractor: BUDGET-2010-BUD.pdf ... 2010-05-29 11:05:46,747 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getFontWidth(PDType1CFont.java:138) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:323) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,749 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getAverageFontWidth(PDType1CFont.java:242) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:331) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,752 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getFontWidth(PDType1CFont.java:138) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:323) at org.apache.pdfbox.util.operator.ShowText.process(ShowText.java:45) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,754 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getAverageFontWidth(PDType1CFont.java:242) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:331) at org.apache.pdfbox.util.operator.ShowText.process(ShowText.java:45) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,756 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getFontWidth(PDType1CFont.java:138) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:323) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,759 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getAverageFontWidth(PDType1CFont.java:242) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:331) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,764 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getFontWidth(PDType1CFont.java:138) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:323) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,768 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getAverageFontWidth(PDType1CFont.java:242) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:331) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,770 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getFontWidth(PDType1CFont.java:138) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:323) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,772 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getAverageFontWidth(PDType1CFont.java:242) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:331) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,778 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getFontWidth(PDType1CFont.java:138) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:323) at org.apache.pdfbox.util.operator.ShowText.process(ShowText.java:45) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,781 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getAverageFontWidth(PDType1CFont.java:242) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:331) at org.apache.pdfbox.util.operator.ShowText.process(ShowText.java:45) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,783 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getFontWidth(PDType1CFont.java:138) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:323) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,785 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getAverageFontWidth(PDType1CFont.java:242) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:331) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,787 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getFontWidth(PDType1CFont.java:138) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:323) at org.apache.pdfbox.util.operator.ShowText.process(ShowText.java:45) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,789 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getAverageFontWidth(PDType1CFont.java:242) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:331) at org.apache.pdfbox.util.operator.ShowText.process(ShowText.java:45) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,791 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getFontWidth(PDType1CFont.java:138) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:323) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,793 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getAverageFontWidth(PDType1CFont.java:242) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:331) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,796 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getFontWidth(PDType1CFont.java:138) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:323) at org.apache.pdfbox.util.operator.ShowText.process(ShowText.java:45) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,798 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getAverageFontWidth(PDType1CFont.java:242) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:331) at org.apache.pdfbox.util.operator.ShowText.process(ShowText.java:45) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,800 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getFontWidth(PDType1CFont.java:138) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:323) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,810 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getAverageFontWidth(PDType1CFont.java:242) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:331) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,813 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getFontWidth(PDType1CFont.java:138) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:323) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,815 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getAverageFontWidth(PDType1CFont.java:242) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:331) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,817 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getFontWidth(PDType1CFont.java:138) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:323) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,819 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getAverageFontWidth(PDType1CFont.java:242) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:331) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,821 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getFontWidth(PDType1CFont.java:138) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:323) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,823 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getAverageFontWidth(PDType1CFont.java:242) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:331) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,826 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getFontWidth(PDType1CFont.java:138) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:323) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,827 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getAverageFontWidth(PDType1CFont.java:242) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:331) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,833 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getFontWidth(PDType1CFont.java:138) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:323) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,835 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getAverageFontWidth(PDType1CFont.java:242) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:331) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,842 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getFontWidth(PDType1CFont.java:138) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:323) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,843 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getAverageFontWidth(PDType1CFont.java:242) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:331) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,848 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getFontWidth(PDType1CFont.java:138) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:323) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,850 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getAverageFontWidth(PDType1CFont.java:242) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:331) at org.apache.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:61) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,854 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getFontWidth(PDType1CFont.java:138) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:323) at org.apache.pdfbox.util.operator.ShowText.process(ShowText.java:45) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,856 WARN PDFStreamEngine: java.lang.IllegalArgumentException java.lang.IllegalArgumentException at org.apache.fontbox.cff.CFFParser.readCharset(CFFParser.java:511) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:319) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getAverageFontWidth(PDType1CFont.java:242) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:331) at org.apache.pdfbox.util.operator.ShowText.process(ShowText.java:45) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:141) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 11:05:46,923 INFO Extractor: pages processed: 146 2010-05-29 11:05:46,923 INFO Extractor: images extracted: 9 2010-05-29 11:05:46,923 INFO Extractor: text extracted: 16 2010-05-29 11:05:46,924 INFO Extractor: processing time: 13 seconds 2010-05-29 11:05:46,924 INFO Extractor: BUDGET-2010-TRANSMITTAL.pdf ... 2010-05-29 11:05:46,973 INFO Extractor: pages processed: 3 2010-05-29 11:05:46,973 INFO Extractor: images extracted: 3 2010-05-29 11:05:46,973 INFO Extractor: text extracted: 3 2010-05-29 11:05:46,973 INFO Extractor: processing time: 0 seconds 2010-05-29 11:05:46,974 INFO Extractor: CDIR-2000-10-01-CAPITOL.pdf ... 2010-05-29 11:05:56,252 INFO Extractor: pages processed: 21 2010-05-29 11:05:56,253 INFO Extractor: images extracted: 5 2010-05-29 11:05:56,253 INFO Extractor: text extracted: 11 2010-05-29 11:05:56,253 INFO Extractor: processing time: 9 seconds 2010-05-29 11:05:56,254 INFO Extractor: CDIR-2000-10-01-STATEMAP-CA.pdf ... 2010-05-29 11:05:57,784 INFO Extractor: pages processed: 1 2010-05-29 11:05:57,784 INFO Extractor: images extracted: 1 2010-05-29 11:05:57,784 INFO Extractor: text extracted: 1 2010-05-29 11:05:57,784 INFO Extractor: processing time: 1 seconds 2010-05-29 11:05:57,785 INFO Extractor: CDIR-2000-10-01-STATEMAP-VI.pdf ... 2010-05-29 11:05:58,905 INFO Extractor: pages processed: 1 2010-05-29 11:05:58,905 INFO Extractor: images extracted: 1 2010-05-29 11:05:58,905 INFO Extractor: text extracted: 1 2010-05-29 11:05:58,905 INFO Extractor: processing time: 1 seconds 2010-05-29 11:05:58,906 INFO Extractor: CDIR-2000-10-01.pdf ... 2010-05-29 11:07:38,579 INFO Extractor: pages processed: 1213 2010-05-29 11:07:38,579 INFO Extractor: images extracted: 62 2010-05-29 11:07:38,579 INFO Extractor: text extracted: 73 2010-05-29 11:07:38,579 INFO Extractor: processing time: 99 seconds 2010-05-29 11:07:38,580 INFO Extractor: CDOC-111hdoc11.pdf ... 2010-05-29 11:07:49,434 INFO Extractor: pages processed: 1081 2010-05-29 11:07:49,434 INFO Extractor: images extracted: 1079 2010-05-29 11:07:49,434 INFO Extractor: text extracted: 1080 2010-05-29 11:07:49,434 INFO Extractor: processing time: 10 seconds 2010-05-29 11:07:49,435 INFO Extractor: CDOC-111hdoc17-pt1.pdf ... 2010-05-29 12:23:58,373 INFO Extractor: pages processed: 1548 2010-05-29 12:23:58,373 INFO Extractor: images extracted: 1546 2010-05-29 12:23:58,373 INFO Extractor: text extracted: 1547 2010-05-29 12:23:58,373 INFO Extractor: processing time: 4568 seconds 2010-05-29 12:23:58,374 INFO Extractor: CDOC-111hdoc17-pt2.pdf ... 2010-05-29 13:28:24,417 INFO Extractor: pages processed: 1345 2010-05-29 13:28:24,418 INFO Extractor: images extracted: 1343 2010-05-29 13:28:24,418 INFO Extractor: text extracted: 1344 2010-05-29 13:28:24,418 INFO Extractor: processing time: 3866 seconds 2010-05-29 13:28:24,419 INFO Extractor: CDOC-111hdoc7.pdf ... 2010-05-29 13:28:26,729 INFO Extractor: pages processed: 38 2010-05-29 13:28:26,730 INFO Extractor: images extracted: 35 2010-05-29 13:28:26,730 INFO Extractor: text extracted: 36 2010-05-29 13:28:26,730 INFO Extractor: processing time: 2 seconds 2010-05-29 13:28:26,731 INFO Extractor: CFR-2009-title49-vol7.pdf ... 2010-05-29 13:28:47,746 INFO Extractor: pages processed: 666 2010-05-29 13:28:47,746 INFO Extractor: images extracted: 129 2010-05-29 13:28:47,747 INFO Extractor: text extracted: 176 2010-05-29 13:28:47,747 INFO Extractor: processing time: 21 seconds 2010-05-29 13:28:47,748 INFO Extractor: CHRG-106shrg10636166.pdf ... 2010-05-29 13:28:48,335 INFO Extractor: pages processed: 78 2010-05-29 13:28:48,335 INFO Extractor: images extracted: 78 2010-05-29 13:28:48,335 INFO Extractor: text extracted: 78 2010-05-29 13:28:48,335 INFO Extractor: processing time: 0 seconds 2010-05-29 13:28:48,336 INFO Extractor: CHRG-110hhrg11046861.pdf ... 2010-05-29 13:28:56,347 INFO Extractor: pages processed: 169 2010-05-29 13:28:56,347 INFO Extractor: images extracted: 83 2010-05-29 13:28:56,348 INFO Extractor: text extracted: 97 2010-05-29 13:28:56,348 INFO Extractor: processing time: 8 seconds 2010-05-29 13:28:56,348 INFO Extractor: CHRG-111hhrg11147258.pdf ... 2010-05-29 13:29:01,301 INFO Extractor: pages processed: 125 2010-05-29 13:29:01,301 INFO Extractor: images extracted: 75 2010-05-29 13:29:01,301 INFO Extractor: text extracted: 78 2010-05-29 13:29:01,301 INFO Extractor: processing time: 4 seconds 2010-05-29 13:29:01,302 INFO Extractor: CHRG-111hhrg11148055.pdf ... 2010-05-29 13:29:02,795 INFO Extractor: pages processed: 74 2010-05-29 13:29:02,795 INFO Extractor: images extracted: 12 2010-05-29 13:29:02,796 INFO Extractor: text extracted: 17 2010-05-29 13:29:02,796 INFO Extractor: processing time: 1 seconds 2010-05-29 13:29:02,796 INFO Extractor: CHRG-111hhrg11151898.pdf ... 2010-05-29 13:29:05,777 INFO Extractor: pages processed: 69 2010-05-29 13:29:05,777 INFO Extractor: images extracted: 33 2010-05-29 13:29:05,777 INFO Extractor: text extracted: 46 2010-05-29 13:29:05,778 INFO Extractor: processing time: 2 seconds 2010-05-29 13:29:05,778 INFO Extractor: CHRG-111shrg37-pt1.pdf ... 2010-05-29 13:29:06,416 INFO Extractor: pages processed: 58 2010-05-29 13:29:06,416 INFO Extractor: images extracted: 2 2010-05-29 13:29:06,416 INFO Extractor: text extracted: 4 2010-05-29 13:29:06,416 INFO Extractor: processing time: 0 seconds 2010-05-29 13:29:06,417 INFO Extractor: CHRG-111shrg370.pdf ... 2010-05-29 13:29:16,545 INFO Extractor: pages processed: 193 2010-05-29 13:29:16,545 INFO Extractor: images extracted: 161 2010-05-29 13:29:16,545 INFO Extractor: text extracted: 162 2010-05-29 13:29:16,545 INFO Extractor: processing time: 10 seconds 2010-05-29 13:29:16,546 INFO Extractor: CPRT-108SPRT90655.pdf ... 2010-05-29 13:29:17,909 INFO Extractor: pages processed: 134 2010-05-29 13:29:17,910 INFO Extractor: images extracted: 10 2010-05-29 13:29:17,910 INFO Extractor: text extracted: 14 2010-05-29 13:29:17,910 INFO Extractor: processing time: 1 seconds 2010-05-29 13:29:17,911 INFO Extractor: CPRT-110HPRT44807-Part 3.pdf ... 2010-05-29 13:29:23,409 INFO Extractor: pages processed: 29 2010-05-29 13:29:23,409 INFO Extractor: images extracted: 4 2010-05-29 13:29:23,409 INFO Extractor: text extracted: 6 2010-05-29 13:29:23,409 INFO Extractor: processing time: 5 seconds 2010-05-29 13:29:23,410 INFO Extractor: CPRT-110HPRT44807-Part 4.pdf ... 2010-05-29 13:29:39,528 INFO Extractor: pages processed: 518 2010-05-29 13:29:39,528 INFO Extractor: images extracted: 243 2010-05-29 13:29:39,528 INFO Extractor: text extracted: 313 2010-05-29 13:29:39,528 INFO Extractor: processing time: 16 seconds 2010-05-29 13:29:39,529 INFO Extractor: CPRT-110HPRT44807-Part 5.pdf ... 2010-05-29 13:29:58,672 INFO Extractor: pages processed: 132 2010-05-29 13:29:58,673 INFO Extractor: images extracted: 13 2010-05-29 13:29:58,673 INFO Extractor: text extracted: 14 2010-05-29 13:29:58,673 INFO Extractor: processing time: 19 seconds 2010-05-29 13:29:58,673 INFO Extractor: CPRT-110HPRT44807-Part 6.pdf ... 2010-05-29 13:30:32,668 INFO Extractor: pages processed: 113 2010-05-29 13:30:32,668 INFO Extractor: images extracted: 24 2010-05-29 13:30:32,668 INFO Extractor: text extracted: 25 2010-05-29 13:30:32,668 INFO Extractor: processing time: 33 seconds 2010-05-29 13:30:32,669 INFO Extractor: CPRT-111HPRT54329.pdf ... 2010-05-29 13:31:18,965 INFO Extractor: pages processed: 366 2010-05-29 13:31:18,965 INFO Extractor: images extracted: 285 2010-05-29 13:31:18,965 INFO Extractor: text extracted: 301 2010-05-29 13:31:18,965 INFO Extractor: processing time: 46 seconds 2010-05-29 13:31:18,966 INFO Extractor: CPRT-111SPRT47215.pdf ... 2010-05-29 13:31:22,838 INFO Extractor: pages processed: 66 2010-05-29 13:31:22,838 INFO Extractor: images extracted: 2 2010-05-29 13:31:22,838 INFO Extractor: text extracted: 6 2010-05-29 13:31:22,838 INFO Extractor: processing time: 3 seconds 2010-05-29 13:31:22,838 INFO Extractor: CPRT-111SPRT48170.pdf ... 2010-05-29 13:39:54,593 INFO Extractor: pages processed: 269 2010-05-29 13:39:54,594 INFO Extractor: images extracted: 263 2010-05-29 13:39:54,594 INFO Extractor: text extracted: 264 2010-05-29 13:39:54,594 INFO Extractor: processing time: 511 seconds 2010-05-29 13:39:54,594 INFO Extractor: CPRT-111SPRT51207.pdf ... 2010-05-29 13:39:54,828 INFO Extractor: pages processed: 20 2010-05-29 13:39:54,829 INFO Extractor: images extracted: 2 2010-05-29 13:39:54,829 INFO Extractor: text extracted: 3 2010-05-29 13:39:54,829 INFO Extractor: processing time: 0 seconds 2010-05-29 13:39:54,830 INFO Extractor: CPRT-111SPRT51233 (no image).pdf ... 2010-05-29 13:39:54,867 INFO Extractor: pages processed: 22 2010-05-29 13:39:54,868 INFO Extractor: images extracted: 0 2010-05-29 13:39:54,868 INFO Extractor: text extracted: 0 2010-05-29 13:39:54,868 INFO Extractor: processing time: 0 seconds 2010-05-29 13:39:54,868 INFO Extractor: CREC-1996-01-22.pdf ... 2010-05-29 13:48:32,896 INFO Extractor: pages processed: 538 2010-05-29 13:48:32,896 INFO Extractor: images extracted: 132 2010-05-29 13:48:32,896 INFO Extractor: text extracted: 168 2010-05-29 13:48:32,896 INFO Extractor: processing time: 518 seconds 2010-05-29 13:48:32,897 INFO Extractor: CRECB-2001-pt20-issue-2001-12-19.pdf ... 2010-05-29 14:08:44,471 INFO Extractor: pages processed: 706 2010-05-29 14:08:44,472 INFO Extractor: images extracted: 252 2010-05-29 14:08:44,472 INFO Extractor: text extracted: 275 2010-05-29 14:08:44,472 INFO Extractor: processing time: 1211 seconds 2010-05-29 14:08:44,473 INFO Extractor: CRECB-2001-pt20.pdf ... 2010-05-29 14:30:06,671 INFO Extractor: pages processed: 1284 2010-05-29 14:30:06,671 INFO Extractor: images extracted: 262 2010-05-29 14:30:06,672 INFO Extractor: text extracted: 287 2010-05-29 14:30:06,672 INFO Extractor: processing time: 1282 seconds 2010-05-29 14:30:06,672 INFO Extractor: CRPT-108hrpt490-pt1.pdf ... 2010-05-29 14:30:07,574 INFO Extractor: pages processed: 45 2010-05-29 14:30:07,574 INFO Extractor: images extracted: 8 2010-05-29 14:30:07,574 INFO Extractor: text extracted: 12 2010-05-29 14:30:07,574 INFO Extractor: processing time: 0 seconds 2010-05-29 14:30:07,575 INFO Extractor: CRPT-108hrpt490-pt2.pdf ... 2010-05-29 14:30:07,647 WARN PDFStreamEngine: java.lang.ArrayIndexOutOfBoundsException: 5 java.lang.ArrayIndexOutOfBoundsException: 5 at org.apache.fontbox.cff.CFFParser$IndexData.getBytes(CFFParser.java:585) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:329) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getFontWidth(PDType1CFont.java:138) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:323) at org.apache.pdfbox.util.operator.ShowText.process(ShowText.java:45) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:140) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 14:30:07,648 WARN PDFStreamEngine: java.lang.ArrayIndexOutOfBoundsException: 5 java.lang.ArrayIndexOutOfBoundsException: 5 at org.apache.fontbox.cff.CFFParser$IndexData.getBytes(CFFParser.java:585) at org.apache.fontbox.cff.CFFParser.parseFont(CFFParser.java:329) at org.apache.fontbox.cff.CFFParser.parse(CFFParser.java:65) at org.apache.pdfbox.pdmodel.font.PDType1CFont.ensureLoaded(PDType1CFont.java:290) at org.apache.pdfbox.pdmodel.font.PDType1CFont.getAverageFontWidth(PDType1CFont.java:242) at org.apache.pdfbox.util.PDFStreamEngine.processEncodedText(PDFStreamEngine.java:331) at org.apache.pdfbox.util.operator.ShowText.process(ShowText.java:45) at org.apache.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:552) at org.apache.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:248) at org.apache.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:207) at org.apache.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:367) at org.apache.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:291) at org.apache.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:247) at pdfimage.Extractor.extractText(Extractor.java:247) at pdfimage.Extractor.extract(Extractor.java:140) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 14:30:07,787 INFO Extractor: pages processed: 3 2010-05-29 14:30:07,787 INFO Extractor: images extracted: 1 2010-05-29 14:30:07,787 INFO Extractor: text extracted: 3 2010-05-29 14:30:07,787 INFO Extractor: processing time: 0 seconds 2010-05-29 14:30:07,788 INFO Extractor: CRPT-110srpt251.pdf ... 2010-05-29 14:30:14,323 INFO Extractor: pages processed: 234 2010-05-29 14:30:14,323 INFO Extractor: images extracted: 54 2010-05-29 14:30:14,323 INFO Extractor: text extracted: 80 2010-05-29 14:30:14,323 INFO Extractor: processing time: 6 seconds 2010-05-29 14:30:14,324 INFO Extractor: ECONI-1910-02-Pg1.pdf ... 2010-05-29 14:30:14,458 INFO Extractor: pages processed: 1 2010-05-29 14:30:14,458 INFO Extractor: images extracted: 1 2010-05-29 14:30:14,458 INFO Extractor: text extracted: 1 2010-05-29 14:30:14,458 INFO Extractor: processing time: 0 seconds 2010-05-29 14:30:14,459 INFO Extractor: ECONI-1910-02-Pg37.pdf ... 2010-05-29 14:30:14,599 INFO Extractor: pages processed: 1 2010-05-29 14:30:14,599 INFO Extractor: images extracted: 1 2010-05-29 14:30:14,599 INFO Extractor: text extracted: 1 2010-05-29 14:30:14,599 INFO Extractor: processing time: 0 seconds 2010-05-29 14:30:14,600 INFO Extractor: ECONI-1995-04-Pg1.pdf ... 2010-05-29 14:30:15,643 INFO Extractor: pages processed: 1 2010-05-29 14:30:15,643 INFO Extractor: images extracted: 1 2010-05-29 14:30:15,643 INFO Extractor: text extracted: 1 2010-05-29 14:30:15,643 INFO Extractor: processing time: 1 seconds 2010-05-29 14:30:15,644 INFO Extractor: ECONI-1995-04-Pg13.pdf ... 2010-05-29 14:30:16,792 INFO Extractor: pages processed: 1 2010-05-29 14:30:16,792 INFO Extractor: images extracted: 1 2010-05-29 14:30:16,792 INFO Extractor: text extracted: 1 2010-05-29 14:30:16,792 INFO Extractor: processing time: 1 seconds 2010-05-29 14:30:16,793 INFO Extractor: ERP-1996-other-2.pdf ... 2010-05-29 14:30:17,479 INFO Extractor: pages processed: 3 2010-05-29 14:30:17,480 INFO Extractor: images extracted: 3 2010-05-29 14:30:17,480 INFO Extractor: text extracted: 2 2010-05-29 14:30:17,480 INFO Extractor: processing time: 0 seconds 2010-05-29 14:30:17,480 INFO Extractor: ERP-2009-chapter1.pdf ... 2010-05-29 14:31:16,955 INFO Extractor: pages processed: 29 2010-05-29 14:31:16,956 INFO Extractor: images extracted: 10 2010-05-29 14:31:16,956 INFO Extractor: text extracted: 20 2010-05-29 14:31:16,956 INFO Extractor: processing time: 59 seconds 2010-05-29 14:31:16,956 INFO Extractor: ERP-2009-chapter2.pdf ... 2010-05-29 14:32:09,543 INFO Extractor: pages processed: 36 2010-05-29 14:32:09,543 INFO Extractor: images extracted: 9 2010-05-29 14:32:09,543 INFO Extractor: text extracted: 20 2010-05-29 14:32:09,543 INFO Extractor: processing time: 52 seconds 2010-05-29 14:32:09,544 INFO Extractor: ERP-2009-chapter3.pdf ... 2010-05-29 14:32:40,649 INFO Extractor: pages processed: 30 2010-05-29 14:32:40,650 INFO Extractor: images extracted: 6 2010-05-29 14:32:40,650 INFO Extractor: text extracted: 15 2010-05-29 14:32:40,650 INFO Extractor: processing time: 31 seconds 2010-05-29 14:32:40,650 INFO Extractor: ERP-2009-chapter4.pdf ... 2010-05-29 14:33:16,871 INFO Extractor: pages processed: 24 2010-05-29 14:33:16,871 INFO Extractor: images extracted: 5 2010-05-29 14:33:16,871 INFO Extractor: text extracted: 12 2010-05-29 14:33:16,871 INFO Extractor: processing time: 36 seconds 2010-05-29 14:33:16,872 INFO Extractor: ERP-2009-chapter5.pdf ... 2010-05-29 14:33:40,205 INFO Extractor: pages processed: 23 2010-05-29 14:33:40,205 INFO Extractor: images extracted: 4 2010-05-29 14:33:40,205 INFO Extractor: text extracted: 11 2010-05-29 14:33:40,205 INFO Extractor: processing time: 23 seconds 2010-05-29 14:33:40,206 INFO Extractor: ERP-2009-chapter6.pdf ... 2010-05-29 14:34:03,526 INFO Extractor: pages processed: 21 2010-05-29 14:34:03,527 INFO Extractor: images extracted: 4 2010-05-29 14:34:03,527 INFO Extractor: text extracted: 10 2010-05-29 14:34:03,527 INFO Extractor: processing time: 23 seconds 2010-05-29 14:34:03,528 INFO Extractor: ERP-2009-chapter7.pdf ... 2010-05-29 14:34:27,286 INFO Extractor: pages processed: 20 2010-05-29 14:34:27,286 INFO Extractor: images extracted: 4 2010-05-29 14:34:27,286 INFO Extractor: text extracted: 9 2010-05-29 14:34:27,286 INFO Extractor: processing time: 23 seconds 2010-05-29 14:34:27,287 INFO Extractor: ERP-2009-chapter8.pdf ... 2010-05-29 14:34:50,101 INFO Extractor: pages processed: 22 2010-05-29 14:34:50,101 INFO Extractor: images extracted: 4 2010-05-29 14:34:50,101 INFO Extractor: text extracted: 10 2010-05-29 14:34:50,101 INFO Extractor: processing time: 22 seconds 2010-05-29 14:34:50,102 INFO Extractor: ERP-2009-chapter9.pdf ... 2010-05-29 14:35:12,601 INFO Extractor: pages processed: 22 2010-05-29 14:35:12,602 INFO Extractor: images extracted: 4 2010-05-29 14:35:12,602 INFO Extractor: text extracted: 11 2010-05-29 14:35:12,602 INFO Extractor: processing time: 22 seconds 2010-05-29 14:35:12,602 INFO Extractor: ERP-2009-frontmatter.pdf ... 2010-05-29 14:35:13,001 INFO Extractor: pages processed: 15 2010-05-29 14:35:13,001 INFO Extractor: images extracted: 4 2010-05-29 14:35:13,001 INFO Extractor: text extracted: 7 2010-05-29 14:35:13,001 INFO Extractor: processing time: 0 seconds 2010-05-29 14:35:13,002 INFO Extractor: ERP-2009.pdf ... 2010-05-29 14:35:24,809 INFO Extractor: pages processed: 419 2010-05-29 14:35:24,809 INFO Extractor: images extracted: 55 2010-05-29 14:35:24,809 INFO Extractor: text extracted: 127 2010-05-29 14:35:24,809 INFO Extractor: processing time: 11 seconds 2010-05-29 14:35:24,810 INFO Extractor: ERP-2010-chapter10.pdf ... 2010-05-29 14:35:24,963 INFO Extractor: pages processed: 26 2010-05-29 14:35:24,963 INFO Extractor: images extracted: 10 2010-05-29 14:35:24,963 INFO Extractor: text extracted: 3 2010-05-29 14:35:24,963 INFO Extractor: processing time: 0 seconds 2010-05-29 14:35:24,964 INFO Extractor: ERP-2010-chapter3.pdf ... 2010-05-29 14:35:25,109 INFO Extractor: pages processed: 31 2010-05-29 14:35:25,109 INFO Extractor: images extracted: 1 2010-05-29 14:35:25,109 INFO Extractor: text extracted: 3 2010-05-29 14:35:25,109 INFO Extractor: processing time: 0 seconds 2010-05-29 14:35:25,110 INFO Extractor: ERP-2010-chapter9.pdf ... 2010-05-29 14:35:25,238 INFO Extractor: pages processed: 24 2010-05-29 14:35:25,238 INFO Extractor: images extracted: 1 2010-05-29 14:35:25,238 INFO Extractor: text extracted: 3 2010-05-29 14:35:25,238 INFO Extractor: processing time: 0 seconds 2010-05-29 14:35:25,239 INFO Extractor: ERP-2010-frontmatter.pdf ... 2010-05-29 14:35:25,342 INFO Extractor: pages processed: 13 2010-05-29 14:35:25,342 INFO Extractor: images extracted: 6 2010-05-29 14:35:25,342 INFO Extractor: text extracted: 6 2010-05-29 14:35:25,342 INFO Extractor: processing time: 0 seconds 2010-05-29 14:35:25,343 INFO Extractor: FR-1996-02-12.pdf ... 2010-05-29 14:35:36,471 INFO Extractor: pages processed: 243 2010-05-29 14:35:36,471 INFO Extractor: images extracted: 1 2010-05-29 14:35:36,471 INFO Extractor: text extracted: 3 2010-05-29 14:35:36,471 INFO Extractor: processing time: 11 seconds 2010-05-29 14:35:36,472 INFO Extractor: FR-2008-01-29.pdf ... 2010-05-29 14:35:37,675 INFO Extractor: pages processed: 347 2010-05-29 14:35:37,676 INFO Extractor: images extracted: 2 2010-05-29 14:35:37,676 INFO Extractor: text extracted: 6 2010-05-29 14:35:37,676 INFO Extractor: processing time: 1 seconds 2010-05-29 14:35:37,676 INFO Extractor: GAOREPORTS-GAO-08-384.pdf ... 2010-05-29 14:35:38,265 INFO Extractor: pages processed: 32 2010-05-29 14:35:38,265 INFO Extractor: images extracted: 2 2010-05-29 14:35:38,265 INFO Extractor: text extracted: 6 2010-05-29 14:35:38,265 INFO Extractor: processing time: 0 seconds 2010-05-29 14:35:38,265 INFO Extractor: GAOREPORTS-GAO-08-685T.pdf ... 2010-05-29 14:35:40,273 INFO Extractor: pages processed: 17 2010-05-29 14:35:40,273 INFO Extractor: images extracted: 2 2010-05-29 14:35:40,273 INFO Extractor: text extracted: 4 2010-05-29 14:35:40,273 INFO Extractor: processing time: 2 seconds 2010-05-29 14:35:40,274 INFO Extractor: GAOREPORTS-GAO-08-876R.pdf ... 2010-05-29 14:35:41,667 INFO Extractor: pages processed: 24 2010-05-29 14:35:41,667 INFO Extractor: images extracted: 6 2010-05-29 14:35:41,667 INFO Extractor: text extracted: 11 2010-05-29 14:35:41,667 INFO Extractor: processing time: 1 seconds 2010-05-29 14:35:41,668 INFO Extractor: PPP-2004-book1-frontmatter-pgiii.pdf ... 2010-05-29 14:35:41,742 WARN Extractor: Fail to extract image 1 on page 3 java.lang.RuntimeException: 3. Unexpected value in file e - please send to IDRsolutions for analysis at org.jpedal.io.PdfReader.handleColorSpaces(Unknown Source) at org.jpedal.io.PdfReader.handleColorSpaces(Unknown Source) at org.jpedal.io.PdfReader.readKeyPairs(Unknown Source) at org.jpedal.io.PdfReader.readDictionaryAsObject(Unknown Source) at org.jpedal.io.PdfReader.convertDirectDictionaryToObject(Unknown Source) at org.jpedal.io.PdfReader.readDictionaryFromRefOrDirect(Unknown Source) at org.jpedal.io.PdfReader.checkResolved(Unknown Source) at org.jpedal.PdfDecoder.decodePage(Unknown Source) at pdfimage.Extractor.writePNGImage(Extractor.java:201) at pdfimage.Extractor.extractImage(Extractor.java:232) at pdfimage.Extractor.extract(Extractor.java:124) at pdfimage.PdfImage.run(PdfImage.java:76) at pdfimage.PdfImage.main(PdfImage.java:98) 2010-05-29 14:35:41,977 INFO Extractor: pages processed: 12 2010-05-29 14:35:41,977 INFO Extractor: images extracted: 0 2010-05-29 14:35:41,977 INFO Extractor: text extracted: 3 2010-05-29 14:35:41,977 INFO Extractor: processing time: 0 seconds 2010-05-29 14:35:41,978 INFO Extractor: STATUTE-117.pdf ... 2010-05-29 14:35:46,565 INFO Extractor: pages processed: 3158 2010-05-29 14:35:46,565 INFO Extractor: images extracted: 14 2010-05-29 14:35:46,565 INFO Extractor: text extracted: 24 2010-05-29 14:35:46,566 INFO Extractor: processing time: 4 seconds 2010-05-29 14:35:46,566 INFO Extractor: STATUTE-118-FrontMatter-Pgi.pdf ... 2010-05-29 14:35:46,693 INFO Extractor: pages processed: 31 2010-05-29 14:35:46,693 INFO Extractor: images extracted: 1 2010-05-29 14:35:46,693 INFO Extractor: text extracted: 2 2010-05-29 14:35:46,694 INFO Extractor: processing time: 0 seconds 2010-05-29 14:35:46,694 INFO Extractor: WCPD-1998-02-09-FrontMatter.pdf ... 2010-05-29 14:35:47,912 INFO Extractor: pages processed: 3 2010-05-29 14:35:47,912 INFO Extractor: images extracted: 1 2010-05-29 14:35:47,912 INFO Extractor: text extracted: 2 2010-05-29 14:35:47,912 INFO Extractor: processing time: 1 seconds