Change strict parsing option to be boolean

Author: marc-gr

docs/reference/enrich-processor/xml-processor.md

@@ -22,7 +22,7 @@ $$$xml-options$$$
 | `remove_namespaces` | no | `false` | If `true`, removes namespace prefixes from element and attribute names. |
 | `force_content` | no | `false` | If `true`, forces text content and attributes to always parse to a hash value with `#text` key for content. |
 | `force_array` | no | `false` | If `true`, forces all parsed values to be arrays. Single elements are wrapped in arrays. |
-| `parse_options` | no | - | Controls XML parsing behavior. Set to `"strict"` for strict XML validation that fails fast on invalid content. |
+| `strict_parsing` | no | `false` | If `true`, enables strict XML validation that fails fast on invalid content. |
 | `xpath` | no | - | Map of XPath expressions to target field names. Extracts values from the XML using XPath and stores them in the specified fields. |
 | `namespaces` | no | - | Map of namespace prefixes to URIs for use with XPath expressions. Required when XPath expressions contain namespace prefixes. |
 | `description` | no | - | Description of the processor. Useful for describing the purpose of the processor or its configuration. |
@@ -422,7 +422,7 @@ Result:
 
 ### Strict parsing mode
 
-Use `parse_options: "strict"` for strict XML validation:
+Use `strict_parsing: true` for strict XML validation:
 
 ```console
 POST _ingest/pipeline/_simulate
@@ -432,7 +432,7 @@ POST _ingest/pipeline/_simulate
       {
         "xml": {
           "field": "xml_content",
-          "parse_options": "strict",
+          "strict_parsing": true,
           "ignore_failure": true
         }
       }
@@ -441,7 +441,7 @@ POST _ingest/pipeline/_simulate
   "docs": [
     {
       "_source": {
-        "xml_content": "<catalog><book><title>Invalid XML with control character</title></book></catalog>"
+        "xml_content": "<catalog><book><title>Invalid XML with control character \u0000</title></book></catalog>"
       }
     }
   ]
@@ -457,7 +457,7 @@ Result (with parsing failure):
       "doc": {
         ...
         "_source": {
-          "xml_content": "<catalog><book><title>Invalid XML with control character</title></book></catalog>",
+          "xml_content": "<catalog><book><title>Invalid XML with control character \u0000</title></book></catalog>",
           "tags": ["_xmlparsefailure"]
         }
       }

modules/ingest-common/src/main/java/org/elasticsearch/ingest/common/XmlProcessor.java

@@ -79,7 +79,7 @@ public final class XmlProcessor extends AbstractProcessor {
     private final Map<String, String> xpathExpressions;
     private final Map<String, String> namespaces;
     private final Map<String, XPathExpression> compiledXPathExpressions;
-    private final String parseOptions;
+    private final boolean strictParsing;
 
     XmlProcessor(
         String tag,
@@ -96,7 +96,7 @@ public final class XmlProcessor extends AbstractProcessor {
         boolean forceArray,
         Map<String, String> xpathExpressions,
         Map<String, String> namespaces,
-        String parseOptions
+        boolean strictParsing
     ) {
         super(tag, description);
         this.field = field;
@@ -112,7 +112,7 @@ public final class XmlProcessor extends AbstractProcessor {
         this.xpathExpressions = xpathExpressions != null ? Map.copyOf(xpathExpressions) : Map.of();
         this.namespaces = namespaces != null ? Map.copyOf(namespaces) : Map.of();
         this.compiledXPathExpressions = compileXPathExpressions(this.xpathExpressions, this.namespaces);
-        this.parseOptions = parseOptions != null ? parseOptions : "";
+        this.strictParsing = strictParsing;
     }
 
     public String getField() {
@@ -144,7 +144,7 @@ public boolean isForceContent() {
     }
 
     public boolean isStrict() {
-        return "strict".equals(parseOptions);
+        return strictParsing;
     }
 
     public boolean isForceArray() {
@@ -159,8 +159,8 @@ public Map<String, String> getNamespaces() {
         return namespaces;
     }
 
-    public String getParseOptions() {
-        return parseOptions;
+    public boolean getStrictParsing() {
+        return strictParsing;
     }
 
     @Override
@@ -488,11 +488,8 @@ public XmlProcessor create(
                 }
             }
 
-            // Parse parse_options parameter
-            String parseOptions = ConfigurationUtils.readStringProperty(TYPE, processorTag, config, "parse_options", "");
-            if (parseOptions != null && !parseOptions.isEmpty() && !"strict".equals(parseOptions)) {
-                throw new IllegalArgumentException("Invalid parse_options [" + parseOptions + "]. Only 'strict' is supported.");
-            }
+            // Parse strict_parsing parameter
+            boolean strictParsing = ConfigurationUtils.readBooleanProperty(TYPE, processorTag, config, "strict_parsing", false);
 
             return new XmlProcessor(
                 processorTag,
@@ -509,7 +506,7 @@ public XmlProcessor create(
                 forceArray,
                 xpathExpressions,
                 namespaces,
-                parseOptions
+                strictParsing
             );
         }
     }

modules/ingest-common/src/test/java/org/elasticsearch/ingest/common/XmlProcessorFactoryTests.java

@@ -155,8 +155,8 @@ private Map<String, Object> createConfigWithOptions(String fieldName, String...
                 case "force_array":
                     config.put("force_array", true);
                     break;
-                case "strict":
-                    config.put("parse_options", "strict");
+                case "strict_parsing":
+                    config.put("strict_parsing", true);
                     break;
                 default:
                     throw new IllegalArgumentException("Unknown option: " + option);
@@ -329,12 +329,12 @@ public void testCreateWithForceArray() throws Exception {
         assertThat(processor.isForceArray(), equalTo(true));
     }
 
-    public void testCreateWithStrictParseOptions() throws Exception {
-        Map<String, Object> config = createConfigWithOptions(DEFAULT_FIELD, "strict");
+    public void testCreateWithStrictParsing() throws Exception {
+        Map<String, Object> config = createConfigWithOptions(DEFAULT_FIELD, "strict_parsing");
         XmlProcessor processor = createProcessor(config);
 
         assertThat(processor.getField(), equalTo(DEFAULT_FIELD));
-        assertThat(processor.getParseOptions(), equalTo("strict"));
+        assertThat(processor.getStrictParsing(), equalTo(true));
         assertThat(processor.isStrict(), equalTo(true));
     }
 
@@ -355,19 +355,6 @@ public void testCreateWithMultipleOptions() throws Exception {
         assertThat(processor.isRemoveNamespaces(), equalTo(true));
     }
 
-    // Tests for invalid parse options
-
-    public void testCreateWithInvalidParseOptions() throws Exception {
-        Map<String, Object> config = createBaseConfig();
-        config.put("parse_options", "invalid_option");
-
-        expectCreationFailure(
-            config,
-            IllegalArgumentException.class,
-            "Invalid parse_options [invalid_option]. Only 'strict' is supported."
-        );
-    }
-
     // Tests for XPath compilation errors (testing precompilation feature)
 
     public void testCreateWithInvalidXPathExpression() throws Exception {

modules/ingest-common/src/test/java/org/elasticsearch/ingest/common/XmlProcessorTests.java

@@ -544,7 +544,7 @@ public void testStrictParsing() {
         String xml = "<foo><bar>valid</bar></foo>";
 
         Map<String, Object> config = new HashMap<>();
-        config.put("parse_options", "strict");
+        config.put("strict_parsing", true);
         XmlProcessor processor = createTestProcessor(config);
         IngestDocument ingestDocument = createTestIngestDocument(xml);