我使用 apache pdfbox 1.5 从 pdf 中提取文本。这是正在使用的代码。这似乎适用于某些 pdf。但它失败了一个 pdf 并出现以下错误。让我知道是否有人遇到过此类问题并已解决
java.lang.IndexOutOfBoundsException: Index: 2,Size: 2
at java.util.SubList.rangeCheck(AbstractList.java:864)
at java.util.SubList.get(AbstractList.java:737)
at org.apache.fontbox.cff.CharStringConverter.drawCurve(CharStringConverter.java:415)
at org.apache.fontbox.cff.CharStringConverter.handleType2Command(CharStringConverter.java:277)
at org.apache.fontbox.cff.CharStringConverter.handleCommand(CharStringConverter.java:81)
at org.apache.fontbox.cff.CharStringHandler.handleSequence(CharStringHandler.java:53)
at org.apache.fontbox.cff.CharStringConverter.handleType2Command(CharStringConverter.java:307)
at org.apache.fontbox.cff.CharStringConverter.handleCommand(CharStringConverter.java:81)
at org.apache.fontbox.cff.CharStringHandler.handleSequence(CharStringHandler.java:53)
at org.apache.fontbox.cff.CharStringConverter.convert(CharStringConverter.java:64)
at org.apache.fontbox.cff.CFFFont$Mapping.toType1Sequence(CFFFont.java:374)
at org.apache.fontbox.cff.AFMFormatter.renderFont(AFMFormatter.java:126)
at org.apache.fontbox.cff.AFMFormatter.printFontMetrics(AFMFormatter.java:64)
at org.apache.fontbox.cff.AFMFormatter.printFont(AFMFormatter.java:57)
at org.apache.fontbox.cff.AFMFormatter.format(AFMFormatter.java:50)