How to validate an XML file using Java with an XSD having an include?

I'm using Java 5 javax.xml.validation.Validator to validate XML file. I've done it for one schema that uses only imports and everything works fine. Now I'm trying to validate with another schema that uses import and one include. The problem I have is that element in the main schema are ignored, the validation says it cannot find their declaration.

Here is how I build the Schema:

InputStream includeInputStream = getClass().getClassLoader().getResource("include.xsd").openStream();
InputStream importInputStream = getClass().getClassLoader().getResource("import.xsd").openStream();
InputStream mainInputStream = getClass().getClassLoader().getResource("main.xsd").openStream();
Source[] sourceSchema = new SAXSource[]{includeInputStream , importInputStream, 
mainInputStream };
Schema schema = factory.newSchema(sourceSchema);

Now here is the extract of the declaration in main.xsd

<xsd:schema xmlns="http://schema.omg.org/spec/BPMN/2.0" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:import="http://www.foo.com/import" targetNamespace="http://main/namespace" elementFormDefault="qualified" attributeFormDefault="unqualified">
    <xsd:import namespace="http://www.foo.com/import" schemaLocation="import.xsd"/>
    <xsd:include schemaLocation="include.xsd"/>
    <xsd:element name="element" type="tElement"/>
    <...>
</xsd:schema>

If I copy the code of my included XSD in the main.xsd, it works fine. If I don't, validation doesn't find the declaration of "Element".

you need to use an LSResourceResolver for this to work. please take a look at the sample code below.

a validate method:

// note that if your XML already declares the XSD to which it has to conform, then there's no need to declare the schemaName here
void validate(String xml, String schemaName) throws Exception {

    DocumentBuilderFactory builderFactory = DocumentBuilderFactory.newInstance();
    builderFactory.setNamespaceAware(true);

    DocumentBuilder parser = builderFactory
            .newDocumentBuilder();

    // parse the XML into a document object
    Document document = parser.parse(new StringInputStream(xml));

    SchemaFactory factory = SchemaFactory
            .newInstance(XMLConstants.W3C_XML_SCHEMA_NS_URI);

    // associate the schema factory with the resource resolver, which is responsible for resolving the imported XSD's
    factory.setResourceResolver(new ResourceResolver());

            // note that if your XML already declares the XSD to which it has to conform, then there's no need to create a validator from a Schema object
    Source schemaFile = new StreamSource(getClass().getClassLoader()
            .getResourceAsStream(schemaName));
    Schema schema = factory.newSchema(schemaFile);

    Validator validator = schema.newValidator();
    validator.validate(new DOMSource(document));
}

the resource resolver implementation:

public class ResourceResolver  implements LSResourceResolver {

public LSInput resolveResource(String type, String namespaceURI,
        String publicId, String systemId, String baseURI) {

     // note: in this sample, the XSD's are expected to be in the root of the classpath
    InputStream resourceAsStream = this.getClass().getClassLoader()
            .getResourceAsStream(systemId);
    return new Input(publicId, systemId, resourceAsStream);
}

 }

The Input implemetation returned by the resource resolver:

public class Input implements LSInput {

private String publicId;

private String systemId;

public String getPublicId() {
    return publicId;
}

public void setPublicId(String publicId) {
    this.publicId = publicId;
}

public String getBaseURI() {
    return null;
}

public InputStream getByteStream() {
    return null;
}

public boolean getCertifiedText() {
    return false;
}

public Reader getCharacterStream() {
    return null;
}

public String getEncoding() {
    return null;
}

public String getStringData() {
    synchronized (inputStream) {
        try {
            byte[] input = new byte[inputStream.available()];
            inputStream.read(input);
            String contents = new String(input);
            return contents;
        } catch (IOException e) {
            e.printStackTrace();
            System.out.println("Exception " + e);
            return null;
        }
    }
}

public void setBaseURI(String baseURI) {
}

public void setByteStream(InputStream byteStream) {
}

public void setCertifiedText(boolean certifiedText) {
}

public void setCharacterStream(Reader characterStream) {
}

public void setEncoding(String encoding) {
}

public void setStringData(String stringData) {
}

public String getSystemId() {
    return systemId;
}

public void setSystemId(String systemId) {
    this.systemId = systemId;
}

public BufferedInputStream getInputStream() {
    return inputStream;
}

public void setInputStream(BufferedInputStream inputStream) {
    this.inputStream = inputStream;
}

private BufferedInputStream inputStream;

public Input(String publicId, String sysId, InputStream input) {
    this.publicId = publicId;
    this.systemId = sysId;
    this.inputStream = new BufferedInputStream(input);
}
}

The accepted answer is perfectly ok, but does not work with Java 8 without some modifications. It would also be nice to be able to specify a base path from which the imported schemas are read.

I have used in my Java 8 the following code which allows to specify an embedded schema path other than the root path:

import com.sun.org.apache.xerces.internal.dom.DOMInputImpl;
import org.w3c.dom.ls.LSInput;
import org.w3c.dom.ls.LSResourceResolver;

import java.io.InputStream;
import java.util.Objects;

public class ResourceResolver implements LSResourceResolver {

    private String basePath;

    public ResourceResolver(String basePath) {
        this.basePath = basePath;
    }

    @Override
    public LSInput resolveResource(String type, String namespaceURI, String publicId, String systemId, String baseURI) {
        // note: in this sample, the XSD's are expected to be in the root of the classpath
        InputStream resourceAsStream = this.getClass().getClassLoader()
                .getResourceAsStream(buildPath(systemId));
        Objects.requireNonNull(resourceAsStream, String.format("Could not find the specified xsd file: %s", systemId));
        return new DOMInputImpl(publicId, systemId, baseURI, resourceAsStream, "UTF-8");
    }

    private String buildPath(String systemId) {
        return basePath == null ? systemId : String.format("%s/%s", basePath, systemId);
    }
}

This implementation also gives to the user a meaningful message in case the schema cannot be read.

As user "ulab" points out in a comment on another answer the solution described in this answer (to a separate stackoverflow question) will work for many. Here's the rough outline of that approach:

SchemaFactory schemaFactory = SchemaFactory.newInstance(XMLConstants.W3C_XML_SCHEMA_NS_URI);
URL xsdURL = this.getResource("/xsd/my-schema.xsd");
Schema schema = schemaFactory.newSchema(xsdURL);

The key to this approach is avoiding handing the schema factory a stream and instead giving it a URL. This way it gets information about the location of the XSD file.

One thing to keep in mind here is that the "schemaLocation" attribute on include and/or import elements will be treated as relative to the classpath location of the XSD file whose URL you've handed to the validator when you use simple file paths in the form "my-common.xsd" or "common/some-concept.xsd".

Notes: - In the example above I've placed the schema file into a jar file under an "xsd" folder. - The leading slash in the "getResource" argument tells Java to start at the root of the classloader instead of at the "this" object's package name.

I had to make some modifications to this post by AMegmondoEmber

My main schema file had some includes from sibling folders, and the included files also had some includes from their local folders. I also had to track down the base resource path and relative path of the current resource. This code works for me know, but please keep in mind that it assumes all xsd files have a unique name. If you have some xsd files with same name, but different content at different paths, it will probably give you problems.

import java.io.ByteArrayInputStream;
import java.io.InputStream;
import java.util.HashMap;
import java.util.Map;
import java.util.Scanner;

import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.w3c.dom.ls.LSInput;
import org.w3c.dom.ls.LSResourceResolver;

/**
 * The Class ResourceResolver.
 */
public class ResourceResolver implements LSResourceResolver {

    /** The logger. */
    private final Logger logger = LoggerFactory.getLogger(this.getClass());

    /** The schema base path. */
    private final String schemaBasePath;

    /** The path map. */
    private Map<String, String> pathMap = new HashMap<String, String>();

    /**
     * Instantiates a new resource resolver.
     *
     * @param schemaBasePath the schema base path
     */
    public ResourceResolver(String schemaBasePath) {
        this.schemaBasePath = schemaBasePath;
        logger.warn("This LSResourceResolver implementation assumes that all XSD files have a unique name. "
                + "If you have some XSD files with same name but different content (at different paths) in your schema structure, "
                + "this resolver will fail to include the other XSD files except the first one found.");
    }

    /* (non-Javadoc)
     * @see org.w3c.dom.ls.LSResourceResolver#resolveResource(java.lang.String, java.lang.String, java.lang.String, java.lang.String, java.lang.String)
     */
    @Override
    public LSInput resolveResource(String type, String namespaceURI,
            String publicId, String systemId, String baseURI) {
        // The base resource that includes this current resource
        String baseResourceName = null;
        String baseResourcePath = null;
        // Extract the current resource name
        String currentResourceName = systemId.substring(systemId
                .lastIndexOf("/") + 1);

        // If this resource hasn't been added yet
        if (!pathMap.containsKey(currentResourceName)) {
            if (baseURI != null) {
                baseResourceName = baseURI
                        .substring(baseURI.lastIndexOf("/") + 1);
            }

            // we dont need "./" since getResourceAsStream cannot understand it
            if (systemId.startsWith("./")) {
                systemId = systemId.substring(2, systemId.length());
            }

            // If the baseResourcePath has already been discovered, get that
            // from pathMap
            if (pathMap.containsKey(baseResourceName)) {
                baseResourcePath = pathMap.get(baseResourceName);
            } else {
                // The baseResourcePath should be the schemaBasePath
                baseResourcePath = schemaBasePath;
            }

            // Read the resource as input stream
            String normalizedPath = getNormalizedPath(baseResourcePath, systemId);
            InputStream resourceAsStream = this.getClass().getClassLoader()
                    .getResourceAsStream(normalizedPath);

            // if the current resource is not in the same path with base
            // resource, add current resource's path to pathMap
            if (systemId.contains("/")) {
                pathMap.put(currentResourceName, normalizedPath.substring(0,normalizedPath.lastIndexOf("/")+1));
            } else {
                // The current resource should be at the same path as the base
                // resource
                pathMap.put(systemId, baseResourcePath);
            }
            Scanner s = new Scanner(resourceAsStream).useDelimiter("\\A");
            String s1 = s.next().replaceAll("\\n", " ") // the parser cannot understand elements broken down multiple lines e.g. (<xs:element \n name="buxing">)
                    .replace("\\t", " ") // these two about whitespaces is only for decoration
                    .replaceAll("\\s+", " ").replaceAll("[^\\x20-\\x7e]", ""); // some files has a special character as a first character indicating utf-8 file
            InputStream is = new ByteArrayInputStream(s1.getBytes());

            return new LSInputImpl(publicId, systemId, is); // same as Input class
        }

        // If this resource has already been added, do not add the same resource again. It throws
        // "org.xml.sax.SAXParseException: sch-props-correct.2: A schema cannot contain two global components with the same name; this schema contains two occurrences of ..."
        // return null instead.
        return null;
    }

    /**
     * Gets the normalized path.
     *
     * @param basePath the base path
     * @param relativePath the relative path
     * @return the normalized path
     */
    private String getNormalizedPath(String basePath, String relativePath){
        if(!relativePath.startsWith("../")){
            return basePath + relativePath;
        }
        else{
            while(relativePath.startsWith("../")){
                basePath = basePath.substring(0,basePath.substring(0, basePath.length()-1).lastIndexOf("/")+1);
                relativePath = relativePath.substring(3);
            }
            return basePath+relativePath;
        }
    }
}