Manali Shah created TIKA-1897: --------------------------------- Summary: Too many daemon threads when NamedEntityParser is enabled Key: TIKA-1897 URL: https://issues.apache.org/jira/browse/TIKA-1897 Project: Tika Issue Type: Bug Components: parser Affects Versions: 1.12 Environment: MAC_OS_X 10.10.5 JDK 1.8.0_45 Tika Version 1.13-SNAPSHOT Reporter: Manali Shah
Thread Dump: {code} "Apache Tika" #2410 daemon prio=5 os_prio=31 tid=0x00007fa12cb22800 nid=0x101103 in Object.wait() [0x00000001a78c8000] java.lang.Thread.State: TIMED_WAITING (on object monitor) at java.lang.Object.wait(Native Method) at java.io.PipedReader.receive(PipedReader.java:185) - eliminated <0x0000000797c69830> (a java.io.PipedReader) at java.io.PipedReader.receive(PipedReader.java:206) - locked <0x0000000797c69830> (a java.io.PipedReader) at java.io.PipedWriter.write(PipedWriter.java:150) at org.apache.tika.sax.ToTextContentHandler.characters(ToTextContentHandler.java:93) at org.apache.tika.sax.ContentHandlerDecorator.characters(ContentHandlerDecorator.java:146) at org.apache.tika.sax.WriteOutContentHandler.characters(WriteOutContentHandler.java:136) at org.apache.tika.sax.ContentHandlerDecorator.characters(ContentHandlerDecorator.java:146) at org.apache.tika.sax.xpath.MatchingContentHandler.characters(MatchingContentHandler.java:85) at org.apache.tika.sax.ContentHandlerDecorator.characters(ContentHandlerDecorator.java:146) at org.apache.tika.sax.ContentHandlerDecorator.characters(ContentHandlerDecorator.java:146) at org.apache.tika.sax.SecureContentHandler.characters(SecureContentHandler.java:270) at org.apache.tika.sax.ContentHandlerDecorator.characters(ContentHandlerDecorator.java:146) at org.apache.tika.sax.ContentHandlerDecorator.characters(ContentHandlerDecorator.java:146) at org.apache.tika.sax.ContentHandlerDecorator.characters(ContentHandlerDecorator.java:146) at org.apache.tika.sax.SafeContentHandler.access$001(SafeContentHandler.java:46) at org.apache.tika.sax.SafeContentHandler$1.write(SafeContentHandler.java:82) at org.apache.tika.sax.SafeContentHandler.filter(SafeContentHandler.java:140) at org.apache.tika.sax.SafeContentHandler.characters(SafeContentHandler.java:287) at org.apache.tika.sax.XHTMLContentHandler.characters(XHTMLContentHandler.java:278) at org.apache.tika.sax.XHTMLContentHandler.characters(XHTMLContentHandler.java:305) at org.apache.tika.parser.ner.NamedEntityParser.extractOutput(NamedEntityParser.java:172) at org.apache.tika.parser.ner.NamedEntityParser.parse(NamedEntityParser.java:154) at org.apache.tika.parser.ParserDecorator.parse(ParserDecorator.java:177) at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:280) at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:280) at org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:120) at org.apache.tika.parser.ParsingReader$ParsingTask.run(ParsingReader.java:235) at java.lang.Thread.run(Thread.java:745) "Apache Tika" #2409 daemon prio=5 os_prio=31 tid=0x00007fa12cb21800 nid=0x100f03 in Object.wait() [0x00000001a77c5000] java.lang.Thread.State: TIMED_WAITING (on object monitor) at java.lang.Object.wait(Native Method) at java.io.PipedReader.receive(PipedReader.java:185) - eliminated <0x0000000797a477c8> (a java.io.PipedReader) at java.io.PipedReader.receive(PipedReader.java:206) - locked <0x0000000797a477c8> (a java.io.PipedReader) at java.io.PipedWriter.write(PipedWriter.java:150) at org.apache.tika.sax.ToTextContentHandler.characters(ToTextContentHandler.java:93) at org.apache.tika.sax.ContentHandlerDecorator.characters(ContentHandlerDecorator.java:146) at org.apache.tika.sax.WriteOutContentHandler.characters(WriteOutContentHandler.java:136) at org.apache.tika.sax.ContentHandlerDecorator.characters(ContentHandlerDecorator.java:146) at org.apache.tika.sax.xpath.MatchingContentHandler.characters(MatchingContentHandler.java:85) at org.apache.tika.sax.ContentHandlerDecorator.characters(ContentHandlerDecorator.java:146) at org.apache.tika.sax.ContentHandlerDecorator.characters(ContentHandlerDecorator.java:146) at org.apache.tika.sax.SecureContentHandler.characters(SecureContentHandler.java:270) at org.apache.tika.sax.ContentHandlerDecorator.characters(ContentHandlerDecorator.java:146) at org.apache.tika.sax.ContentHandlerDecorator.characters(ContentHandlerDecorator.java:146) at org.apache.tika.sax.ContentHandlerDecorator.characters(ContentHandlerDecorator.java:146) at org.apache.tika.sax.SafeContentHandler.access$001(SafeContentHandler.java:46) at org.apache.tika.sax.SafeContentHandler$1.write(SafeContentHandler.java:82) at org.apache.tika.sax.SafeContentHandler.filter(SafeContentHandler.java:140) at org.apache.tika.sax.SafeContentHandler.characters(SafeContentHandler.java:287) at org.apache.tika.sax.XHTMLContentHandler.characters(XHTMLContentHandler.java:278) at org.apache.tika.sax.XHTMLContentHandler.characters(XHTMLContentHandler.java:305) at org.apache.tika.parser.ner.NamedEntityParser.extractOutput(NamedEntityParser.java:172) at org.apache.tika.parser.ner.NamedEntityParser.parse(NamedEntityParser.java:154) at org.apache.tika.parser.ParserDecorator.parse(ParserDecorator.java:177) at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:280) at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:280) at org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:120) at org.apache.tika.parser.ParsingReader$ParsingTask.run(ParsingReader.java:235) at java.lang.Thread.run(Thread.java:745) x 2400 more threads like the above {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)