Java SaxParser XSD验证报错：无法解析global:Document类型定义

问题场景 #

我有一个引用多个XSD文件的根XSD，所有相关文件都已放入src/main/java/resources目录。使用SaxParser进行Schema验证XML文件时，出现如下错误：

org.xml.sax.SAXParseException; lineNumber: 27; columnNumber: 48; src-resolve: Cannot resolve the name 'global:Document' to a(n) 'type definition' component.

根XSD第27行代码：

<xsd:extension base="global:Document">

根XSD的schema命名空间声明：

<xsd:schema xmlns:global="urn:global:xsd:1" xmlns:xsd="http://www.w3.org/2001/XMLSchema" targetNamespace="urn:global:company:xsd:2" elementFormDefault="unqualified" attributeFormDefault="unqualified" version="2.0">

根XSD中导入global.xsd的语句（第16行）：

<xsd:import namespace="urn:global:xsd:1" schemaLocation="./global.xsd"/>

global.xsd确实存在于resources目录，IntelliJ可以通过cmd+鼠标点击跳转，但SaxParser无法识别该文件中的Document类型。global.xsd内容如下：

<xsd:schema xmlns:global="urn:global:xsd:1" xmlns:xsd="http://www.w3.org/2001/XMLSchema" targetNamespace="urn:global:xsd:1" elementFormDefault="unqualified" attributeFormDefault="unqualified" version="1.0">
    <xsd:annotation>
        <xsd:documentation>
            <global:copyright>Copyright (C) 2004 global Inc., All Rights Reserved.</global:copyright>
            <global:specification>global common components Version 1.0</global:specification>
        </xsd:documentation>
    </xsd:annotation>
    <xsd:complexType name="Document" abstract="true">
        <xsd:annotation>
            <xsd:documentation xml:lang="en">
                global document properties for all messages.
            </xsd:documentation>
        </xsd:annotation>
        <xsd:attribute name="schemaVersion" type="xsd:decimal" use="required">
            <xsd:annotation>
                <xsd:documentation xml:lang="en">
                    The version of the schema corresponding to which the instance conforms. 
                </xsd:documentation>
            </xsd:annotation>
        </xsd:attribute>
        <xsd:attribute name="creationDate" type="xsd:dateTime" use="required">
            <xsd:annotation>
                <xsd:documentation xml:lang="en">
                    The date the message was created. Used for auditing and logging.
                </xsd:documentation>
            </xsd:annotation>
        </xsd:attribute>
    </xsd:complexType>
</xsd:schema>

由于依赖的XSD文件过多无法合并，求可行的解决办法。当前代码实现如下：

import java.io.InputStream;
import javax.xml.XMLConstants;
import javax.xml.transform.Source;
import javax.xml.transform.stream.StreamSource;
import javax.xml.validation.Schema;
import javax.xml.validation.SchemaFactory;
import javax.xml.validation.Validator;

public class XmlSchemaValidator {

  private final SchemaFactory schemaFactory = SchemaFactory.newInstance(XMLConstants.W3C_XML_SCHEMA_NS_URI);
  private final Schema xmlCaptureSchema;

  private static final String[] XSD_FILES = {
    "/Types.xsd", 
    "/Identification.xsd",
    "/Partner.xsd",
    "/Manifest.xsd", 
    "/BusinessScope.xsd",
    "/BusinessDocumentHeader.xsd", 
    "/global.xsd",
    "/global-1_1.xsd",
    "/global-query-1_1.xsd",
    "/global-masterdata-1_1.xsd",
  };

  public XmlSchemaValidator() {
    //this.xmlCaptureSchema = loadSchema("/global-1_1.xsd");
    this.xmlCaptureSchema = loadSchemaType2();
  }

  public void validateAgainstCaptureSchema(final InputStream input) {
    try {
      final Validator validator = xmlCaptureSchema.newValidator();
      validator.validate(new StreamSource(input));
    } catch (Exception e) {
      e.printStackTrace();
    }
  }

  public Schema loadSchema(final String name) {
    Schema schema = null;
    try {
      schema = schemaFactory.newSchema(new StreamSource(getClass().getResourceAsStream(name)));
    } catch (Exception e) {
      e.printStackTrace();
    }
    return schema;
  }

  public Schema loadSchemaType2() {
    Schema schema = null;
    try {
      Source[] xsdSources = new Source[XSD_FILES.length];
      int i = 0;

      for (String xsdFile : XSD_FILES) {
        final InputStream xsdStreamData = getClass().getResourceAsStream(xsdFile);
        final StreamSource xsdStreamSource = new StreamSource(xsdStreamData);
        xsdSources[i] = xsdStreamSource;
        i++;
      }
      schema = schemaFactory.newSchema(xsdSources);
    } catch (Exception e) {
      e.printStackTrace();
    }
    return schema;
  }
}

解决办法 #

问题核心是通过InputStream加载XSD时，StreamSource没有设置systemId，导致SaxParser无法识别XSD之间的相对路径引用。虽然你把所有XSD都加载到了Source数组中，但解析器处理根XSD的schemaLocation="./global.xsd"时，因为无法确定当前XSD的位置，无法解析相对路径指向的文件。

修改loadSchemaType2方法，为每个StreamSource设置对应的systemId即可解决：

public Schema loadSchemaType2() {
    Schema schema = null;
    try {
        Source[] xsdSources = new Source[XSD_FILES.length];
        int i = 0;

        for (String xsdFile : XSD_FILES) {
            final InputStream xsdStreamData = getClass().getResourceAsStream(xsdFile);
            final StreamSource xsdStreamSource = new StreamSource(xsdStreamData);
            // 设置systemId为XSD文件的资源路径，让解析器能正确解析相对引用
            xsdStreamSource.setSystemId(getClass().getResource(xsdFile).toExternalForm());
            xsdSources[i] = xsdStreamSource;
            i++;
        }
        schema = schemaFactory.newSchema(xsdSources);
    } catch (Exception e) {
        e.printStackTrace();
    }
    return schema;
}

额外优化建议 #

• 根XSD中的schemaLocation="./global.xsd"可以简化为global.xsd，避免相对路径的解析歧义，因为所有XSD都在同一目录下。
• 如果后续遇到更复杂的XSD引用场景，可以自定义LSResourceResolver来统一管理XSD的加载逻辑，但设置systemId是当前场景下最直接有效的方案。

内容的提问来源于stack exchange，提问作者BATMAN_2008