Question

我正在尝试使用SAX Parser来解析XML文件。虽然我在代码中一直收到以下错误：

    Exception in thread "main" java.net.MalformedURLException: unknown protocol: c
    at java.net.URL.<init>(URL.java:592)
    at java.net.URL.<init>(URL.java:482)
   at java.net.URL.<init>(URL.java:431)
   at com.sun.org.apache.xerces.internal.impl.XMLEntityManager.setupCurrentEntity(XMLEntityManager.java:605)
   at com.sun.org.apache.xerces.internal.impl.XMLVersionDetector.determineDocVersion(XMLVersionDetector.java:189)
   at com.sun.org.apache.xerces.internal.parsers.XML11Configuration.parse(XML11Configuration.java:799)
   at com.sun.org.apache.xerces.internal.parsers.XML11Configuration.parse(XML11Configuration.java:764)
   at com.sun.org.apache.xerces.internal.parsers.XMLParser.parse(XMLParser.java:123)
   at com.sun.org.apache.xerces.internal.parsers.AbstractSAXParser.parse(AbstractSAXParser.java:1137)
   at com.sun.org.apache.xerces.internal.jaxp.SAXParserImpl$JAXPSAXParser.parse(SAXParserImpl.java:580)
   at main.main(main.java:28)
   Java Result: 1

这是我的处理程序类：

    public class MySaxParser extends DefaultHandler {

    Index i = new Index(12);
    String bookxmlfilename;
    String tmpValue;
    BookCitation c;
    JournalArticle j;
    Unpublished u;
    ConfProceedings p;

  public MySaxParser() {
      }

    @Override
    public void startElement(String s, String s1, String elementName, Attributes attr) throws SAXException {
        if (elementName.equalsIgnoreCase("JournalArticle")) {
            if (elementName.equalsIgnoreCase("Pages")) {
                j.setstartPage(Integer.parseInt(attr.getValue("StartPage")));
                j.setendPage(Integer.parseInt(attr.getValue("EndPage")));
            }
        }
        if (elementName.equalsIgnoreCase("ConferenceProceedings")) {
            if (elementName.equalsIgnoreCase("Pages")) {
                p.setstartPage(Integer.parseInt(attr.getValue("StartPage")));
                p.setendPage(Integer.parseInt(attr.getValue("EndPage")));
            }
        }
    }

    @Override
    public void endElement(String s, String s1, String element) throws SAXException {
        if (element.equalsIgnoreCase("book")) {
            i.addCitation(c);
            if (element.equalsIgnoreCase("name")) {
                c.setName(tmpValue);
            }
            if (element.equalsIgnoreCase("publisher")) {
                c.setpublisher(tmpValue);
            }
            if (element.equalsIgnoreCase("publicationDate")) {
                c.setdateOfPublication(tmpValue);
            }
            if (element.equalsIgnoreCase("authors")) {
                if (element.equalsIgnoreCase("author")) {
                    c.addAuthor(tmpValue);
                }
            }
            if (element.equalsIgnoreCase("keywords")) {
                if (element.equalsIgnoreCase("keyword")) {
                    c.addKeyword(tmpValue);
                }
            }
        }
        if (element.equalsIgnoreCase("JournalArticle")) {
            i.addCitation(j);
            if (element.equalsIgnoreCase("name")) {
                j.setName(tmpValue);
            }
           if (element.equalsIgnoreCase("TitleOfJournal")) {
                j.settitleOfJournal(tmpValue);
            }
            if (element.equalsIgnoreCase("TitleOfJournal")) {
                j.settitleOfJournal(tmpValue);
            }
            if (element.equalsIgnoreCase("PublicationDate")) {
                j.setpublicationDate(tmpValue);
            }
            if (element.equalsIgnoreCase("volNumber")) {
                j.setvolNumber(Integer.parseInt(tmpValue));
            }
            if (element.equalsIgnoreCase("IssueNumber")) {
                j.setissueNumber(Integer.parseInt(tmpValue));
            }
            if (element.equalsIgnoreCase("authors")) {
                if (element.equalsIgnoreCase("author")) {
                    j.addAuthor(tmpValue);
                }
                if (element.equalsIgnoreCase("keywords")) {
                    if (element.equalsIgnoreCase("keyword")) {
                        j.addKeyword(tmpValue);
                    }
                }
           }
        }
        if (element.equalsIgnoreCase("Unpublished")) {
            i.addCitation(u);
            if (element.equalsIgnoreCase("name")) {
                u.setName(tmpValue);
            }
            if (element.equalsIgnoreCase("authors")) {
            if (element.equalsIgnoreCase("author")) {
                    u.addAuthor(tmpValue);
                }
                if (element.equalsIgnoreCase("keywords")) {
                    if (element.equalsIgnoreCase("keyword")) {
                        u.addKeyword(tmpValue);
                    }
                }
            }
         }

        if (element.equalsIgnoreCase("ConferenceProceedings")) {
            i.addCitation(p);
            if (element.equalsIgnoreCase("name")) {
                p.setName(tmpValue);
            }
            if (element.equalsIgnoreCase("publisher")) {
                p.setpublisher(tmpValue);
            }
            if (element.equalsIgnoreCase("ConferenceLocation")) {
                p.setlocationOfConference(tmpValue);
            }
            if (element.equalsIgnoreCase("TitleOfConferenceproceeding")) {
                p.settitleOfConferenceProc(tmpValue);
            }
            if (element.equalsIgnoreCase("ConferenceYea")) {
                p.setconfYear(Integer.parseInt(tmpValue));
            }
            if (element.equalsIgnoreCase("Editor")) {
                p.seteditor(tmpValue);
            }
            if (element.equalsIgnoreCase("authors")) {
                if (element.equalsIgnoreCase("author")) {
                    p.addAuthor(tmpValue);
                }
                if (element.equalsIgnoreCase("keywords")) {
                    if (element.equalsIgnoreCase("keyword")) {
                        p.addKeyword(tmpValue);
                    }
                }
            }
        }

        if (element.equalsIgnoreCase("FormattingStyle")) {
            i.setFormatType("IEEE");

            }
            if (element.equalsIgnoreCase("FormattingStyle")) {

            try {
                i.formatIEEE(tmpValue);
            } catch (IOException ex) {
                Logger.getLogger(MySaxParser.class.getName()).log(Level.SEVERE, null, ex);
            }
        }
   }

    @Override
    public void characters(char[] ac, int i, int j) throws SAXException {
        tmpValue = new String(ac, i, j);
    }

}

这是我的主要课程：

    public class main {

     public static void main(String[] args) throws IOException,     ParserConfigurationException, SAXException {
        // Create scanner
        Scanner OswegoNote = new Scanner(System.in);
        //Create a parser factory
        SAXParserFactory factory = SAXParserFactory.newInstance();
        //Make the parser
        SAXParser saxParser = factory.newSAXParser();
        XMLReader parser = saxParser.getXMLReader();
        //Create a handler
        MySaxParser handler = new MySaxParser();
        //Tell the parser to use this handler
        parser.setContentHandler(handler);
        //read and parse the document
        parser.parse("C:\\Users\\mhromalik\\Documents\\Suny Oswego\\fall2013\\csc241fall2012\\Assignment\\MyCitation.html");
        }
}

这是我的XML文件的一部分：

        <Citation>
        <ConferenceProceedings>
            <Name>An efficient implementation of Smith Waterman algorithm on GPU using CUDA, for massively parallel scanning of sequence databases</Name>
            <Publisher>Parallel and Distributed Processing</Publisher>
            <ConferenceLocation>Austin,TX</ConferenceLocation>
            <TitleOfConferenceproceeding> IEEE International Conference on Parallel and Distributed Processing</TitleOfConferenceproceeding>
            <ConferenceYear>2009</ConferenceYear>
            <Editor>S. M. Mann</Editor>
            <Pages StartPage="85" EndPage="102"/>
            <Authors>
                <author>L. L. Ligowski</author>
                <author>W. A. Rudnicki</author>
            </Authors>
            <Keywords>
                <Keyword>Sparse Data</Keyword>
                <Keyword>DNA</Keyword>
                <Keyword>GPU</Keyword>
                <Keyword>Data Mining</Keyword>
            </Keywords>
        </ConferenceProceedings>
    </Citation>
       <FormattingStyle>IEEE</FormattingStyle>
    <FilePath>C:\\Users\\mhromalik\\Documents\\Suny Oswego\\fall2013\\csc241fall2012\\Assignment\\MyCitation.html</FilePath>
</Index>

我无法弄清楚为什么会发生这种错误。任何帮助将不胜感激！

Answer 1

设置html文件的路径时，您缺少协议。当您尝试读取本地html文件时，可以使用file协议：

file:///{yourfilepath}

Answer 2

parser.parse（）需要一个URI，而不是文件名。您可以使用

从Java中获取文件名到URI

new File(filename).toURI()

线程“main”中的异常java.net.MalformedURLException：未知协议：c

2 个答案: