[ML] Text/Log categorization multi-bucket aggregation

benchmarks/src/main/java/org/elasticsearch/benchmark/search/aggregations/AggConstructionContentionBenchmark.java

@@ -22,6 +22,7 @@
 import org.elasticsearch.core.Releasables;
 import org.elasticsearch.index.Index;
 import org.elasticsearch.index.IndexSettings;
+import org.elasticsearch.index.analysis.NameOrDefinition;
 import org.elasticsearch.index.analysis.NamedAnalyzer;
 import org.elasticsearch.index.cache.bitset.BitsetFilterCache;
 import org.elasticsearch.index.fielddata.IndexFieldData;
@@ -197,6 +198,22 @@ public long nowInMillis() {
             return 0;
         }
 
+        @Override
+        public Analyzer getNamedAnalyzer(String analyzer) {
+            return null;
+        }
+
+        @Override
+        public Analyzer buildCustomAnalyzer(
+            IndexSettings indexSettings,
+            boolean normalizer,
+            NameOrDefinition tokenizer,
+            List<NameOrDefinition> charFilters,
+            List<NameOrDefinition> tokenFilters
+        ) {
+            return null;
+        }
+
         @Override
         protected IndexFieldData<?> buildFieldData(MappedFieldType ft) {
             IndexFieldDataCache indexFieldDataCache = indicesFieldDataCache.buildIndexFieldDataCache(new IndexFieldDataCache.Listener() {

docs/build.gradle

@@ -1071,6 +1071,39 @@ buildRestTests.setups['farequote_datafeed'] = buildRestTests.setups['farequote_j
           "indexes":"farequote"
           }
 '''
+buildRestTests.setups['categorize_text'] = '''
+  - do:
+        indices.create:
+          index: log-messages
+          body:
+            settings:
+              number_of_shards: 1
+              number_of_replicas: 0
+            mappings:
+              properties:
+                time:
+                  type: date
+                message:
+                  type: text
+
+  - do:
+        bulk:
+          index: log-messages
+          refresh: true
+          body: |
+            {"index": {"_id":"1"}}
+            {"time":"2016-02-07T00:01:00+0000", "message": "2016-02-07T00:00:00+0000 Node 3 shutting down"}
+            {"index": {"_id":"2"}}
+            {"time":"2016-02-07T00:02:00+0000", "message": "2016-02-07T00:00:00+0000 Node 5 starting up"}
+            {"index": {"_id":"3"}}
+            {"time":"2016-02-07T00:03:00+0000", "message": "2016-02-07T00:00:00+0000 Node 4 shutting down"}
+            {"index": {"_id":"4"}}
+            {"time":"2016-02-08T00:01:00+0000", "message": "2016-02-08T00:00:00+0000 Node 5 shutting down"}
+            {"index": {"_id":"5"}}
+            {"time":"2016-02-08T00:02:00+0000", "message": "2016-02-08T00:00:00+0000 User foo_325 logging on"}
+            {"index": {"_id":"6"}}
+            {"time":"2016-02-08T00:04:00+0000", "message": "2016-02-08T00:00:00+0000 User foo_864 logged off"}
+'''
 buildRestTests.setups['server_metrics_index'] = '''
   - do:
         indices.create:

docs/reference/aggregations/bucket.asciidoc

@@ -20,6 +20,8 @@ include::bucket/adjacency-matrix-aggregation.asciidoc[]
 
 include::bucket/autodatehistogram-aggregation.asciidoc[]
 
+include::bucket/categorize-text-aggregation.asciidoc[]
+
 include::bucket/children-aggregation.asciidoc[]
 
 include::bucket/composite-aggregation.asciidoc[]