[ML] Add default categorization analyzer definition to ML info (#49545)

The categorization job wizard in the ML UI will use this
information when showing the effect of the chosen categorization
analyzer on a sample of input.

docs/reference/ml/anomaly-detection/apis/get-ml-info.asciidoc

@@ -50,6 +50,56 @@ This is a possible response:
 {
   "defaults" : {
     "anomaly_detectors" : {
+      "categorization_analyzer" : {
+        "tokenizer" : "ml_classic",
+        "filter" : [
+          {
+            "type" : "stop",
+            "stopwords" : [
+              "Monday",
+              "Tuesday",
+              "Wednesday",
+              "Thursday",
+              "Friday",
+              "Saturday",
+              "Sunday",
+              "Mon",
+              "Tue",
+              "Wed",
+              "Thu",
+              "Fri",
+              "Sat",
+              "Sun",
+              "January",
+              "February",
+              "March",
+              "April",
+              "May",
+              "June",
+              "July",
+              "August",
+              "September",
+              "October",
+              "November",
+              "December",
+              "Jan",
+              "Feb",
+              "Mar",
+              "Apr",
+              "May",
+              "Jun",
+              "Jul",
+              "Aug",
+              "Sep",
+              "Oct",
+              "Nov",
+              "Dec",
+              "GMT",
+              "UTC"
+            ]
+          }
+        ]
+      },
       "model_memory_limit" : "1gb",
       "categorization_examples_limit" : 4,
       "model_snapshot_retention_days" : 1

x-pack/plugin/core/src/main/java/org/elasticsearch/xpack/core/ml/job/config/CategorizationAnalyzerConfig.java

@@ -6,12 +6,16 @@
 package org.elasticsearch.xpack.core.ml.job.config;
 
 import org.elasticsearch.common.ParseField;
+import org.elasticsearch.common.Strings;
 import org.elasticsearch.common.io.stream.StreamInput;
 import org.elasticsearch.common.io.stream.StreamOutput;
 import org.elasticsearch.common.io.stream.Writeable;
+import org.elasticsearch.common.xcontent.LoggingDeprecationHandler;
+import org.elasticsearch.common.xcontent.NamedXContentRegistry;
 import org.elasticsearch.common.xcontent.ToXContentFragment;
 import org.elasticsearch.common.xcontent.XContentBuilder;
 import org.elasticsearch.common.xcontent.XContentParser;
+import org.elasticsearch.common.xcontent.json.JsonXContent;
 import org.elasticsearch.index.analysis.NameOrDefinition;
 import org.elasticsearch.rest.action.admin.indices.RestAnalyzeAction;
 
@@ -245,6 +249,18 @@ public class CategorizationAnalyzerConfig implements ToXContentFragment, Writeab
         return builder;
     }
 
+    /**
+     * Get the categorization analyzer structured as a generic map.
+     * This can be used to provide the structure that the XContent serialization but as a Java map rather than text.
+     * Since it is created by round-tripping through text it is not particularly efficient and is expected to be
+     * used only rarely.
+     */
+    public Map<String, Object> asMap(NamedXContentRegistry xContentRegistry) throws IOException {
+        String strRep = Strings.toString(this);
+        XContentParser parser = JsonXContent.jsonXContent.createParser(xContentRegistry, LoggingDeprecationHandler.INSTANCE, strRep);
+        return parser.mapOrdered();
+    }
+
     @Override
     public boolean equals(Object o) {
         if (this == o) return true;

x-pack/plugin/ml/src/main/java/org/elasticsearch/xpack/ml/action/TransportMlInfoAction.java

@@ -12,6 +12,7 @@ import org.elasticsearch.cluster.service.ClusterService;
 import org.elasticsearch.common.inject.Inject;
 import org.elasticsearch.common.unit.ByteSizeUnit;
 import org.elasticsearch.common.unit.ByteSizeValue;
+import org.elasticsearch.common.xcontent.NamedXContentRegistry;
 import org.elasticsearch.tasks.Task;
 import org.elasticsearch.transport.TransportService;
 import org.elasticsearch.xpack.core.ml.MachineLearningField;
@@ -19,9 +20,12 @@ import org.elasticsearch.xpack.core.ml.MlMetadata;
 import org.elasticsearch.xpack.core.ml.action.MlInfoAction;
 import org.elasticsearch.xpack.core.ml.datafeed.DatafeedConfig;
 import org.elasticsearch.xpack.core.ml.job.config.AnalysisLimits;
+import org.elasticsearch.xpack.core.ml.job.config.CategorizationAnalyzerConfig;
 import org.elasticsearch.xpack.core.ml.job.config.Job;
 import org.elasticsearch.xpack.ml.process.MlControllerHolder;
 
+import java.io.IOException;
+import java.util.Collections;
 import java.util.HashMap;
 import java.util.Map;
 import java.util.concurrent.TimeoutException;
@@ -29,13 +33,15 @@ import java.util.concurrent.TimeoutException;
 public class TransportMlInfoAction extends HandledTransportAction<MlInfoAction.Request, MlInfoAction.Response> {
 
     private final ClusterService clusterService;
+    private final NamedXContentRegistry xContentRegistry;
     private final Map<String, Object> nativeCodeInfo;
 
     @Inject
-    public TransportMlInfoAction(TransportService transportService, ActionFilters actionFilters,
-                                 ClusterService clusterService, MlControllerHolder mlControllerHolder) {
+    public TransportMlInfoAction(TransportService transportService, ActionFilters actionFilters, ClusterService clusterService,
+                                 NamedXContentRegistry xContentRegistry, MlControllerHolder mlControllerHolder) {
         super(MlInfoAction.NAME, transportService, actionFilters, MlInfoAction.Request::new);
         this.clusterService = clusterService;
+        this.xContentRegistry = xContentRegistry;
 
         try {
             nativeCodeInfo = mlControllerHolder.getMlController().getNativeCodeInfo();
@@ -70,6 +76,13 @@ public class TransportMlInfoAction extends HandledTransportAction<MlInfoAction.R
         defaults.put(AnalysisLimits.MODEL_MEMORY_LIMIT.getPreferredName(), defaultModelMemoryLimit());
         defaults.put(AnalysisLimits.CATEGORIZATION_EXAMPLES_LIMIT.getPreferredName(), AnalysisLimits.DEFAULT_CATEGORIZATION_EXAMPLES_LIMIT);
         defaults.put(Job.MODEL_SNAPSHOT_RETENTION_DAYS.getPreferredName(), Job.DEFAULT_MODEL_SNAPSHOT_RETENTION_DAYS);
+        try {
+            defaults.put(CategorizationAnalyzerConfig.CATEGORIZATION_ANALYZER.getPreferredName(),
+                CategorizationAnalyzerConfig.buildDefaultCategorizationAnalyzer(Collections.emptyList())
+                    .asMap(xContentRegistry).get(CategorizationAnalyzerConfig.CATEGORIZATION_ANALYZER.getPreferredName()));
+        } catch (IOException e) {
+            logger.error("failed to convert default categorization analyzer to map", e);
+        }
         return defaults;
     }
 

x-pack/plugin/ml/src/test/java/org/elasticsearch/xpack/ml/job/config/CategorizationAnalyzerConfigTests.java

@@ -6,14 +6,20 @@
 package org.elasticsearch.xpack.ml.job.config;
 
 import org.elasticsearch.common.io.stream.Writeable;
+import org.elasticsearch.common.xcontent.NamedXContentRegistry;
 import org.elasticsearch.common.xcontent.XContentParser;
 import org.elasticsearch.test.AbstractSerializingTestCase;
 import org.elasticsearch.xpack.core.ml.job.config.CategorizationAnalyzerConfig;
 
 import java.io.IOException;
+import java.util.Collections;
 import java.util.HashMap;
 import java.util.Map;
 
+import static org.hamcrest.Matchers.is;
+import static org.hamcrest.Matchers.not;
+import static org.hamcrest.Matchers.nullValue;
+
 public class CategorizationAnalyzerConfigTests extends AbstractSerializingTestCase<CategorizationAnalyzerConfig> {
 
     @Override
@@ -64,6 +70,17 @@ public class CategorizationAnalyzerConfigTests extends AbstractSerializingTestCa
         return builder;
     }
 
+    public void testAsMap() throws IOException {
+        Map<String, Object> map = CategorizationAnalyzerConfig.buildDefaultCategorizationAnalyzer(Collections.emptyList())
+            .asMap(NamedXContentRegistry.EMPTY);
+        @SuppressWarnings("unchecked")
+        Map<String, Object> firstLevel =
+            (Map<String, Object>) map.get(CategorizationAnalyzerConfig.CATEGORIZATION_ANALYZER.getPreferredName());
+        assertThat(firstLevel, not(nullValue()));
+        String tokenizer = (String) firstLevel.get(CategorizationAnalyzerConfig.TOKENIZER.getPreferredName());
+        assertThat(tokenizer, is("ml_classic"));
+    }
+
     @Override
     protected Writeable.Reader<CategorizationAnalyzerConfig> instanceReader() {
         return CategorizationAnalyzerConfig::new;

x-pack/plugin/src/test/resources/rest-api-spec/test/ml/ml_info.yml

@@ -10,6 +10,7 @@ teardown:
 "Test ml info":
   - do:
       ml.info: {}
+  - match: { defaults.anomaly_detectors.categorization_analyzer.tokenizer: "ml_classic" }
   - match: { defaults.anomaly_detectors.model_memory_limit: "1gb" }
   - match: { defaults.anomaly_detectors.categorization_examples_limit: 4 }
   - match: { defaults.anomaly_detectors.model_snapshot_retention_days: 1 }
@@ -25,6 +26,7 @@ teardown:
 
   - do:
       ml.info: {}
+  - match: { defaults.anomaly_detectors.categorization_analyzer.tokenizer: "ml_classic" }
   - match: { defaults.anomaly_detectors.model_memory_limit: "512mb" }
   - match: { defaults.anomaly_detectors.categorization_examples_limit: 4 }
   - match: { defaults.anomaly_detectors.model_snapshot_retention_days: 1 }
@@ -40,6 +42,7 @@ teardown:
 
   - do:
       ml.info: {}
+  - match: { defaults.anomaly_detectors.categorization_analyzer.tokenizer: "ml_classic" }
   - match: { defaults.anomaly_detectors.model_memory_limit: "1gb" }
   - match: { defaults.anomaly_detectors.categorization_examples_limit: 4 }
   - match: { defaults.anomaly_detectors.model_snapshot_retention_days: 1 }