MLE-26427 Namespace support for exclusions

marklogic-client-api/src/main/java/com/marklogic/client/datamovement/filter/ContentExclusionUtil.java

@@ -15,6 +15,7 @@
 import org.w3c.dom.Node;
 import org.w3c.dom.NodeList;
 
+import javax.xml.namespace.NamespaceContext;
 import javax.xml.namespace.QName;
 import javax.xml.parsers.DocumentBuilder;
 import javax.xml.transform.OutputKeys;
@@ -29,6 +30,8 @@
 import java.io.ByteArrayInputStream;
 import java.io.StringWriter;
 import java.nio.charset.StandardCharsets;
+import java.util.Iterator;
+import java.util.Map;
 
 /**
  * Utility class for applying content exclusions to documents before hash calculation.
@@ -99,23 +102,28 @@ private static void removeNodeAtPointer(String uri, JsonNode rootNode, String js
 	 *
 	 * @param uri              the document URI (used for logging purposes)
 	 * @param xmlContent       the XML content as a string
+	 * @param namespaces       a map of namespace prefixes to URIs for use in XPath expressions, or null
 	 * @param xpathExpressions array of XPath expressions identifying elements to exclude
 	 * @return the modified XML content with specified elements removed
 	 * @throws Exception if the XML content cannot be parsed or serialized
 	 */
-	static String applyXmlExclusions(String uri, String xmlContent, String... xpathExpressions) throws Exception {
+	static String applyXmlExclusions(String uri, String xmlContent, Map<String, String> namespaces, String... xpathExpressions) throws Exception {
 		if (xpathExpressions == null || xpathExpressions.length == 0) {
 			return xmlContent;
 		}
 
 		DocumentBuilder builder = XmlFactories.getDocumentBuilderFactory().newDocumentBuilder();
 		Document document = builder.parse(new ByteArrayInputStream(xmlContent.getBytes(StandardCharsets.UTF_8)));
-		applyXmlExclusions(uri, document, xpathExpressions);
+		applyXmlExclusions(uri, document, namespaces, xpathExpressions);
 		return serializeDocument(document);
 	}
 
-	private static void applyXmlExclusions(String uri, Document document, String[] xpathExpressions) {
+	private static void applyXmlExclusions(String uri, Document document, Map<String, String> namespaces, String[] xpathExpressions) {
 		final XPath xpath = XmlFactories.getXPathFactory().newXPath();
+		if (namespaces != null && !namespaces.isEmpty()) {
+			xpath.setNamespaceContext(new SimpleNamespaceContext(namespaces));
+		}
+
 		for (String xpathExpression : xpathExpressions) {
 			try {
 				XPathExpression expr = xpath.compile(xpathExpression);

marklogic-client-api/src/main/java/com/marklogic/client/datamovement/filter/IncrementalWriteEvalFilter.java

@@ -12,6 +12,7 @@
 import com.marklogic.client.document.DocumentWriteSet;
 import com.marklogic.client.io.JacksonHandle;
 
+import java.util.Map;
 import java.util.function.Consumer;
 
 /**
@@ -31,8 +32,8 @@ class IncrementalWriteEvalFilter extends IncrementalWriteFilter {
 		""";
 
 	IncrementalWriteEvalFilter(String hashKeyName, String timestampKeyName, boolean canonicalizeJson,
-							   Consumer<DocumentWriteOperation[]> skippedDocumentsConsumer, String[] jsonExclusions, String[] xmlExclusions) {
-		super(hashKeyName, timestampKeyName, canonicalizeJson, skippedDocumentsConsumer, jsonExclusions, xmlExclusions);
+							   Consumer<DocumentWriteOperation[]> skippedDocumentsConsumer, String[] jsonExclusions, String[] xmlExclusions, Map<String, String> xmlNamespaces) {
+		super(hashKeyName, timestampKeyName, canonicalizeJson, skippedDocumentsConsumer, jsonExclusions, xmlExclusions, xmlNamespaces);
 	}
 
 	@Override

marklogic-client-api/src/main/java/com/marklogic/client/datamovement/filter/IncrementalWriteFilter.java

@@ -25,6 +25,7 @@
 import java.time.Instant;
 import java.util.ArrayList;
 import java.util.List;
+import java.util.Map;
 import java.util.function.Consumer;
 import java.util.function.Function;
 
@@ -51,6 +52,7 @@ public static class Builder {
 		private Consumer<DocumentWriteOperation[]> skippedDocumentsConsumer;
 		private String[] jsonExclusions;
 		private String[] xmlExclusions;
+		private Map<String, String> xmlNamespaces;
 
 		/**
 		 * @param keyName the name of the MarkLogic metadata key that will hold the hash value; defaults to "incrementalWriteHash".
@@ -117,13 +119,22 @@ public Builder xmlExclusions(String... xpathExpressions) {
 			return this;
 		}
 
+		/**
+		 * @param namespaces a map of namespace prefixes to URIs for use in XPath exclusion expressions.
+		 *                   For example, Map.of("ns", "http://example.com/ns") allows XPath like "//ns:timestamp".
+		 */
+		public Builder xmlNamespaces(Map<String, String> namespaces) {
+			this.xmlNamespaces = namespaces;
+			return this;
+		}
+
 		public IncrementalWriteFilter build() {
 			validateJsonExclusions();
 			validateXmlExclusions();
 			if (useEvalQuery) {
-				return new IncrementalWriteEvalFilter(hashKeyName, timestampKeyName, canonicalizeJson, skippedDocumentsConsumer, jsonExclusions, xmlExclusions);
+				return new IncrementalWriteEvalFilter(hashKeyName, timestampKeyName, canonicalizeJson, skippedDocumentsConsumer, jsonExclusions, xmlExclusions, xmlNamespaces);
 			}
-			return new IncrementalWriteOpticFilter(hashKeyName, timestampKeyName, canonicalizeJson, skippedDocumentsConsumer, jsonExclusions, xmlExclusions);
+			return new IncrementalWriteOpticFilter(hashKeyName, timestampKeyName, canonicalizeJson, skippedDocumentsConsumer, jsonExclusions, xmlExclusions, xmlNamespaces);
 		}
 
 		private void validateJsonExclusions() {
@@ -151,6 +162,9 @@ private void validateXmlExclusions() {
 				return;
 			}
 			XPath xpath = XmlFactories.getXPathFactory().newXPath();
+			if (xmlNamespaces != null && !xmlNamespaces.isEmpty()) {
+				xpath.setNamespaceContext(new SimpleNamespaceContext(xmlNamespaces));
+			}
 			for (String xpathExpression : xmlExclusions) {
 				if (xpathExpression == null || xpathExpression.trim().isEmpty()) {
 					throw new IllegalArgumentException(
@@ -173,18 +187,20 @@ private void validateXmlExclusions() {
 	private final Consumer<DocumentWriteOperation[]> skippedDocumentsConsumer;
 	private final String[] jsonExclusions;
 	private final String[] xmlExclusions;
+	private final Map<String, String> xmlNamespaces;
 
 	// Hardcoding this for now, with a good general purpose hashing function.
 	// See https://xxhash.com for benchmarks.
 	private final LongHashFunction hashFunction = LongHashFunction.xx3();
 
-	public IncrementalWriteFilter(String hashKeyName, String timestampKeyName, boolean canonicalizeJson, Consumer<DocumentWriteOperation[]> skippedDocumentsConsumer, String[] jsonExclusions, String[] xmlExclusions) {
+	public IncrementalWriteFilter(String hashKeyName, String timestampKeyName, boolean canonicalizeJson, Consumer<DocumentWriteOperation[]> skippedDocumentsConsumer, String[] jsonExclusions, String[] xmlExclusions, Map<String, String> xmlNamespaces) {
 		this.hashKeyName = hashKeyName;
 		this.timestampKeyName = timestampKeyName;
 		this.canonicalizeJson = canonicalizeJson;
 		this.skippedDocumentsConsumer = skippedDocumentsConsumer;
 		this.jsonExclusions = jsonExclusions;
 		this.xmlExclusions = xmlExclusions;
+		this.xmlNamespaces = xmlNamespaces;
 	}
 
 	protected final DocumentWriteSet filterDocuments(Context context, Function<String, String> hashRetriever) {
@@ -260,7 +276,7 @@ private String serializeContent(DocumentWriteOperation doc) {
 			}
 		} else if (xmlExclusions != null && xmlExclusions.length > 0) {
 			try {
-				content = ContentExclusionUtil.applyXmlExclusions(doc.getUri(), content, xmlExclusions);
+				content = ContentExclusionUtil.applyXmlExclusions(doc.getUri(), content, xmlNamespaces, xmlExclusions);
 			} catch (Exception e) {
 				logger.warn("Unable to apply XML exclusions for URI {}, using original content for hashing; cause: {}",
 					doc.getUri(), e.getMessage());

marklogic-client-api/src/main/java/com/marklogic/client/datamovement/filter/IncrementalWriteOpticFilter.java

@@ -20,8 +20,8 @@
 class IncrementalWriteOpticFilter extends IncrementalWriteFilter {
 
 	IncrementalWriteOpticFilter(String hashKeyName, String timestampKeyName, boolean canonicalizeJson,
-								Consumer<DocumentWriteOperation[]> skippedDocumentsConsumer, String[] jsonExclusions, String[] xmlExclusions) {
-		super(hashKeyName, timestampKeyName, canonicalizeJson, skippedDocumentsConsumer, jsonExclusions, xmlExclusions);
+								Consumer<DocumentWriteOperation[]> skippedDocumentsConsumer, String[] jsonExclusions, String[] xmlExclusions, Map<String, String> xmlNamespaces) {
+		super(hashKeyName, timestampKeyName, canonicalizeJson, skippedDocumentsConsumer, jsonExclusions, xmlExclusions, xmlNamespaces);
 	}
 
 	@Override

marklogic-client-api/src/main/java/com/marklogic/client/datamovement/filter/SimpleNamespaceContext.java

@@ -0,0 +1,46 @@
+/*
+ * Copyright (c) 2010-2026 Progress Software Corporation and/or its subsidiaries or affiliates. All Rights Reserved.
+ */
+package com.marklogic.client.datamovement.filter;
+
+import javax.xml.namespace.NamespaceContext;
+import java.util.Iterator;
+import java.util.Map;
+
+/**
+ * A simple implementation of {@link NamespaceContext} backed by a Map of prefix to namespace URI mappings.
+ * Used for XPath evaluation with namespace-qualified expressions.
+ *
+ * @since 8.1.0
+ */
+class SimpleNamespaceContext implements NamespaceContext {
+
+	private final Map<String, String> prefixToNamespaceUri;
+
+	SimpleNamespaceContext(Map<String, String> prefixToNamespaceUri) {
+		this.prefixToNamespaceUri = prefixToNamespaceUri;
+	}
+
+	@Override
+	public String getNamespaceURI(String prefix) {
+		return prefixToNamespaceUri.get(prefix);
+	}
+
+	@Override
+	public String getPrefix(String namespaceURI) {
+		for (Map.Entry<String, String> entry : prefixToNamespaceUri.entrySet()) {
+			if (entry.getValue().equals(namespaceURI)) {
+				return entry.getKey();
+			}
+		}
+		return null;
+	}
+
+	@Override
+	public Iterator<String> getPrefixes(String namespaceURI) {
+		return prefixToNamespaceUri.entrySet().stream()
+			.filter(entry -> entry.getValue().equals(namespaceURI))
+			.map(Map.Entry::getKey)
+			.iterator();
+	}
+}