[
https://issues.apache.org/jira/browse/ANY23-166?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Ruben Verborgh updated ANY23-166:
---------------------------------
Description:
When trying http://ruben.verborgh.org/tmp/og-test.html in the validator, it
fails with:
Internal error.
================================================================
java.lang.IllegalArgumentException: Invalid content ''
at
org.apache.any23.extractor.microdata.ItemPropValue.<init>(ItemPropValue.java:89)
at
org.apache.any23.extractor.microdata.MicrodataParser.getPropertyValue(MicrodataParser.java:341)
at
org.apache.any23.extractor.microdata.MicrodataParser.getItemProps(MicrodataParser.java:394)
at
org.apache.any23.extractor.microdata.MicrodataParser.getItemScope(MicrodataParser.java:471)
at
org.apache.any23.extractor.microdata.MicrodataParser.getMicrodata(MicrodataParser.java:186)
at
org.apache.any23.extractor.microdata.MicrodataParser.getMicrodata(MicrodataParser.java:203)
at
org.apache.any23.extractor.microdata.MicrodataExtractor.run(MicrodataExtractor.java:100)
at
org.apache.any23.extractor.microdata.MicrodataExtractor.run(MicrodataExtractor.java:62)
at
org.apache.any23.extractor.SingleDocumentExtraction.runExtractor(SingleDocumentExtraction.java:477)
at
org.apache.any23.extractor.SingleDocumentExtraction.run(SingleDocumentExtraction.java:260)
at org.apache.any23.Any23.extract(Any23.java:294)
at org.apache.any23.Any23.extract(Any23.java:446)
at
org.apache.any23.servlet.WebResponder.runExtraction(WebResponder.java:113)
at org.apache.any23.servlet.Servlet.doGet(Servlet.java:74)
at javax.servlet.http.HttpServlet.service(HttpServlet.java:617)
at javax.servlet.http.HttpServlet.service(HttpServlet.java:717)
at
org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:290)
at
org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:206)
at
org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.java:233)
at
org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.java:191)
at
org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:127)
at
com.googlecode.psiprobe.Tomcat60AgentValve.invoke(Tomcat60AgentValve.java:30)
at
org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:102)
at
org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.java:109)
at
org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:293)
at
org.apache.coyote.http11.Http11Processor.process(Http11Processor.java:859)
at
org.apache.coyote.http11.Http11Protocol$Http11ConnectionHandler.process(Http11Protocol.java:602)
at
org.apache.tomcat.util.net.JIoEndpoint$Worker.run(JIoEndpoint.java:489)
at java.lang.Thread.run(Thread.java:662)
================================================================
Source:
http://any23.org/any23/?format=best&uri=http%3A%2F%2Fruben.verborgh.org%2Ftmp%2Fog-test.html&validation-mode=validate-fix
Note how a quote is missing in the prefix attribute of the html tag.
The strange thing is that editing the document body makes the error disappear,
depending on what you remove. For instance:
http://any23.org/any23/?format=best&uri=http%3A%2F%2Fruben.verborgh.org%2Ftmp%2Fog-test2.html&validation-mode=validate-fix
was:
When trying http://ruben.verborgh.org/tmp/og-test.html in the validator, it
fails with:
Internal error.
================================================================
java.lang.IllegalArgumentException: Invalid content ''
at
org.apache.any23.extractor.microdata.ItemPropValue.<init>(ItemPropValue.java:89)
at
org.apache.any23.extractor.microdata.MicrodataParser.getPropertyValue(MicrodataParser.java:341)
at
org.apache.any23.extractor.microdata.MicrodataParser.getItemProps(MicrodataParser.java:394)
at
org.apache.any23.extractor.microdata.MicrodataParser.getItemScope(MicrodataParser.java:471)
at
org.apache.any23.extractor.microdata.MicrodataParser.getMicrodata(MicrodataParser.java:186)
at
org.apache.any23.extractor.microdata.MicrodataParser.getMicrodata(MicrodataParser.java:203)
at
org.apache.any23.extractor.microdata.MicrodataExtractor.run(MicrodataExtractor.java:100)
at
org.apache.any23.extractor.microdata.MicrodataExtractor.run(MicrodataExtractor.java:62)
at
org.apache.any23.extractor.SingleDocumentExtraction.runExtractor(SingleDocumentExtraction.java:477)
at
org.apache.any23.extractor.SingleDocumentExtraction.run(SingleDocumentExtraction.java:260)
at org.apache.any23.Any23.extract(Any23.java:294)
at org.apache.any23.Any23.extract(Any23.java:446)
at
org.apache.any23.servlet.WebResponder.runExtraction(WebResponder.java:113)
at org.apache.any23.servlet.Servlet.doGet(Servlet.java:74)
at javax.servlet.http.HttpServlet.service(HttpServlet.java:617)
at javax.servlet.http.HttpServlet.service(HttpServlet.java:717)
at
org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:290)
at
org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:206)
at
org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.java:233)
at
org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.java:191)
at
org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:127)
at
com.googlecode.psiprobe.Tomcat60AgentValve.invoke(Tomcat60AgentValve.java:30)
at
org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:102)
at
org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.java:109)
at
org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:293)
at
org.apache.coyote.http11.Http11Processor.process(Http11Processor.java:859)
at
org.apache.coyote.http11.Http11Protocol$Http11ConnectionHandler.process(Http11Protocol.java:602)
at
org.apache.tomcat.util.net.JIoEndpoint$Worker.run(JIoEndpoint.java:489)
at java.lang.Thread.run(Thread.java:662)
================================================================
Source:
http://any23.org/any23/?format=best&uri=http%3A%2F%2Fruben.verborgh.org%2Ftmp%2Fog-test.html&validation-mode=validate-fix
Summary: Parsing fails with missing quote in HTML attribute (was:
Parsing fails on RDFa/Microdata combination)
> Parsing fails with missing quote in HTML attribute
> --------------------------------------------------
>
> Key: ANY23-166
> URL: https://issues.apache.org/jira/browse/ANY23-166
> Project: Apache Any23
> Issue Type: Bug
> Reporter: Ruben Verborgh
>
> When trying http://ruben.verborgh.org/tmp/og-test.html in the validator, it
> fails with:
> Internal error.
> ================================================================
> java.lang.IllegalArgumentException: Invalid content ''
> at
> org.apache.any23.extractor.microdata.ItemPropValue.<init>(ItemPropValue.java:89)
> at
> org.apache.any23.extractor.microdata.MicrodataParser.getPropertyValue(MicrodataParser.java:341)
> at
> org.apache.any23.extractor.microdata.MicrodataParser.getItemProps(MicrodataParser.java:394)
> at
> org.apache.any23.extractor.microdata.MicrodataParser.getItemScope(MicrodataParser.java:471)
> at
> org.apache.any23.extractor.microdata.MicrodataParser.getMicrodata(MicrodataParser.java:186)
> at
> org.apache.any23.extractor.microdata.MicrodataParser.getMicrodata(MicrodataParser.java:203)
> at
> org.apache.any23.extractor.microdata.MicrodataExtractor.run(MicrodataExtractor.java:100)
> at
> org.apache.any23.extractor.microdata.MicrodataExtractor.run(MicrodataExtractor.java:62)
> at
> org.apache.any23.extractor.SingleDocumentExtraction.runExtractor(SingleDocumentExtraction.java:477)
> at
> org.apache.any23.extractor.SingleDocumentExtraction.run(SingleDocumentExtraction.java:260)
> at org.apache.any23.Any23.extract(Any23.java:294)
> at org.apache.any23.Any23.extract(Any23.java:446)
> at
> org.apache.any23.servlet.WebResponder.runExtraction(WebResponder.java:113)
> at org.apache.any23.servlet.Servlet.doGet(Servlet.java:74)
> at javax.servlet.http.HttpServlet.service(HttpServlet.java:617)
> at javax.servlet.http.HttpServlet.service(HttpServlet.java:717)
> at
> org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:290)
> at
> org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:206)
> at
> org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.java:233)
> at
> org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.java:191)
> at
> org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:127)
> at
> com.googlecode.psiprobe.Tomcat60AgentValve.invoke(Tomcat60AgentValve.java:30)
> at
> org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:102)
> at
> org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.java:109)
> at
> org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:293)
> at
> org.apache.coyote.http11.Http11Processor.process(Http11Processor.java:859)
> at
> org.apache.coyote.http11.Http11Protocol$Http11ConnectionHandler.process(Http11Protocol.java:602)
> at
> org.apache.tomcat.util.net.JIoEndpoint$Worker.run(JIoEndpoint.java:489)
> at java.lang.Thread.run(Thread.java:662)
> ================================================================
> Source:
> http://any23.org/any23/?format=best&uri=http%3A%2F%2Fruben.verborgh.org%2Ftmp%2Fog-test.html&validation-mode=validate-fix
> Note how a quote is missing in the prefix attribute of the html tag.
> The strange thing is that editing the document body makes the error
> disappear, depending on what you remove. For instance:
> http://any23.org/any23/?format=best&uri=http%3A%2F%2Fruben.verborgh.org%2Ftmp%2Fog-test2.html&validation-mode=validate-fix
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira