Bug 44986

Summary: JSP compilation exception with pageEncoding="utf-8" and file with byte order marks
Product: Tomcat 6 Reporter: Ralf Zimmermann <ralf.zimmermann>
Component: JasperAssignee: Tomcat Developers Mailing List <dev>
Status: RESOLVED FIXED    
Severity: normal    
Priority: P2    
Version: unspecified   
Target Milestone: default   
Hardware: PC   
OS: Windows XP   

Description Ralf Zimmermann 2008-05-13 04:42:11 UTC
JSP-File has byte order marks. If the attribute is set to "UTF-8" (upper case) or the file has no byte order marks, the compilation workes fine. 

{code} 
12:32:16,946 ERROR [[jsp]] Servlet.service() for servlet jsp threw exception 
org.apache.jasper.JasperException: /dialog.jsp(2,0) Page-encoding specified in XML prolog (UTF-8) is different from that specified in page directive (utf-8) 
at org.apache.jasper.compiler.DefaultErrorHandler.jspError(DefaultErrorHandler.java:40) 
at org.apache.jasper.compiler.ErrorDispatcher.dispatch(ErrorDispatcher.java:407) 
at org.apache.jasper.compiler.ErrorDispatcher.jspError(ErrorDispatcher.java:236) 
at org.apache.jasper.compiler.Validator$DirectiveVisitor.comparePageEncodings(Validator.java:362) 
at org.apache.jasper.compiler.Validator$DirectiveVisitor.visit(Validator.java:197) 
at org.apache.jasper.compiler.Node$PageDirective.accept(Node.java:590) 
at org.apache.jasper.compiler.Node$Nodes.visit(Node.java:2338) 
at org.apache.jasper.compiler.Node$Visitor.visitBody(Node.java:2388) 
at org.apache.jasper.compiler.Node$Visitor.visit(Node.java:2394) 
at org.apache.jasper.compiler.Node$Root.accept(Node.java:489) 
at org.apache.jasper.compiler.Node$Nodes.visit(Node.java:2338) 
at org.apache.jasper.compiler.Validator.validate(Validator.java:1700) 
at org.apache.jasper.compiler.Compiler.generateJava(Compiler.java:178) 
at org.apache.jasper.compiler.Compiler.compile(Compiler.java:306) 
at org.apache.jasper.compiler.Compiler.compile(Compiler.java:286) 
at org.apache.jasper.compiler.Compiler.compile(Compiler.java:273) 
at org.apache.jasper.JspCompilationContext.compile(JspCompilationContext.java:566) 
at org.apache.jasper.servlet.JspServletWrapper.service(JspServletWrapper.java:316) 
at org.apache.jasper.servlet.JspServlet.serviceJspFile(JspServlet.java:336) 
at org.apache.jasper.servlet.JspServlet.service(JspServlet.java:265) 
at javax.servlet.http.HttpServlet.service(HttpServlet.java:803) 
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.ApplicationDispatcher.invoke(ApplicationDispatcher.java:654) 
at org.apache.catalina.core.ApplicationDispatcher.processRequest(ApplicationDispatcher.java:445) 
at org.apache.catalina.core.ApplicationDispatcher.doForward(ApplicationDispatcher.java:379) 
at org.apache.catalina.core.ApplicationDispatcher.forward(ApplicationDispatcher.java:292) 
at de.cit.jsp.control.DispatchServlet.forward(DispatchServlet.java:286) 
at de.cit.jsp.control.DispatchServlet.doGet(DispatchServlet.java:272) 
at javax.servlet.http.HttpServlet.service(HttpServlet.java:690) 
at javax.servlet.http.HttpServlet.service(HttpServlet.java:803) 
at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:290) 
at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:206) 
at de.cit.util.javax.servlet.ValidationFilter.doFilter(ValidationFilter.java:108) 
at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:235) 
at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:206) 
at de.cit.util.javax.servlet.jsp.XHtmlContentTypeFilter.doFilter(XHtmlContentTypeFilter.java:36) 
at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:235) 
at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:206) 
at org.jboss.web.tomcat.filters.ReplyHeaderFilter.doFilter(ReplyHeaderFilter.java:96) 
at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:235) 
at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:206) 
at org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.java:230) 
at org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.java:175) 
at org.jboss.web.tomcat.security.SecurityAssociationValve.invoke(SecurityAssociationValve.java:179) 
at org.apache.catalina.authenticator.AuthenticatorBase.invoke(AuthenticatorBase.java:432) 
at org.jboss.web.tomcat.security.JaccContextValve.invoke(JaccContextValve.java:84) 
at org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:127) 
at org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:102) 
at org.jboss.web.tomcat.service.jca.CachedConnectionValve.invoke(CachedConnectionValve.java:157) 
at org.apache.catalina.authenticator.SingleSignOn.invoke(SingleSignOn.java:420) 
at org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.java:109) 
at org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:262) 
at org.apache.coyote.ajp.AjpProcessor.process(AjpProcessor.java:437) 
at org.apache.coyote.ajp.AjpProtocol$AjpConnectionHandler.process(AjpProtocol.java:366) 
at org.apache.tomcat.util.net.JIoEndpoint$Worker.run(JIoEndpoint.java:446) 
at java.lang.Thread.run(Thread.java:619) 
{code} 

Case insensitive camparison in org.apache.jasper.compiler.Validator.comparePageEncodings(...) seems to fix the problem: 
{code} 
        /* 
         * Compares page encodings specified in various places, and throws 
         * exception in case of page encoding mismatch. 
         * 
         * @param pageDirEnc The value of the pageEncoding attribute of the page 
         * directive @param pageDir The page directive node 
         * 
         * @throws JasperException in case of page encoding mismatch 
         */ 
        private String comparePageEncodings(String pageDirEnc, 
                Node.PageDirective pageDir) throws JasperException { 

            Node.Root root = pageDir.getRoot(); 
            String configEnc = root.getJspConfigPageEncoding(); 

            /* 
             * Compare the 'pageEncoding' attribute of the page directive with 
             * the encoding specified in the JSP config element whose URL 
             * pattern matches this page. Treat "UTF-16", "UTF-16BE", and 
             * "UTF-16LE" as identical. 
             */ 
            if (configEnc != null) { 
                if (!pageDirEnc.equalsIgnoreCase(configEnc) 
                        && (!pageDirEnc.toUpperCase().startsWith("UTF-16") || !configEnc 
                                .toUpperCase().startsWith("UTF-16"))) { 
                    err.jspError(pageDir, 
                            "jsp.error.config_pagedir_encoding_mismatch", 
                            configEnc, pageDirEnc); 
                } else { 
                    return configEnc; 
                } 
            } 

            /* 
             * Compare the 'pageEncoding' attribute of the page directive with 
             * the encoding specified in the XML prolog (only for XML syntax, 
             * and only if JSP document contains XML prolog with encoding 
             * declaration). Treat "UTF-16", "UTF-16BE", and "UTF-16LE" as 
             * identical. 
             */ 
            if ((root.isXmlSyntax() && root.isEncodingSpecifiedInProlog()) || root.isBomPresent()) { 
                String pageEnc = root.getPageEncoding(); 
                if (!pageDirEnc.equalsIgnoreCase(pageEnc) 
                        && (!pageDirEnc.toUpperCase().startsWith("UTF-16") || !pageEnc 
                                .toUpperCase().startsWith("UTF-16"))) { 
                    err.jspError(pageDir, 
                            "jsp.error.prolog_pagedir_encoding_mismatch", 
                            pageEnc, pageDirEnc); 
                } else { 
                    return pageEnc; 
                } 
            } 
             
            return pageDirEnc; 
        } 
{code}
Comment 1 Mark Thomas 2008-05-13 14:44:12 UTC
Thanks for the report. This has been fixed in trunk with an alternative patch that converts the encodings to upper case before comparison. The patch has been proposed for 6.0.x
Comment 2 Mark Thomas 2008-05-15 14:11:04 UTC
The patch has been applied to 6.0.x and will be included in 6.0.17 onwards.