reject CATEGORIZE with INLINEJOIN

Author: bpintea

x-pack/plugin/esql/src/main/java/org/elasticsearch/xpack/esql/expression/function/grouping/Categorize.java

@@ -16,7 +16,9 @@
 import org.elasticsearch.license.XPackLicenseState;
 import org.elasticsearch.xpack.esql.LicenseAware;
 import org.elasticsearch.xpack.esql.SupportsObservabilityTier;
+import org.elasticsearch.xpack.esql.common.Failures;
 import org.elasticsearch.xpack.esql.core.InvalidArgumentException;
+import org.elasticsearch.xpack.esql.core.expression.Alias;
 import org.elasticsearch.xpack.esql.core.expression.Expression;
 import org.elasticsearch.xpack.esql.core.expression.MapExpression;
 import org.elasticsearch.xpack.esql.core.expression.Nullability;
@@ -33,6 +35,9 @@
 import org.elasticsearch.xpack.esql.expression.function.Options;
 import org.elasticsearch.xpack.esql.expression.function.Param;
 import org.elasticsearch.xpack.esql.io.stream.PlanStreamInput;
+import org.elasticsearch.xpack.esql.plan.logical.Aggregate;
+import org.elasticsearch.xpack.esql.plan.logical.InlineStats;
+import org.elasticsearch.xpack.esql.plan.logical.LogicalPlan;
 import org.elasticsearch.xpack.ml.MachineLearning;
 
 import java.io.IOException;
@@ -41,11 +46,13 @@
 import java.util.Locale;
 import java.util.Map;
 import java.util.TreeMap;
+import java.util.function.BiConsumer;
 
 import static java.util.Map.entry;
 import static org.elasticsearch.common.logging.LoggerMessageFormat.format;
 import static org.elasticsearch.compute.aggregation.blockhash.BlockHash.CategorizeDef.OutputFormat.REGEX;
 import static org.elasticsearch.xpack.esql.SupportsObservabilityTier.ObservabilityTier.COMPLETE;
+import static org.elasticsearch.xpack.esql.common.Failure.fail;
 import static org.elasticsearch.xpack.esql.core.expression.TypeResolutions.ParamOrdinal.DEFAULT;
 import static org.elasticsearch.xpack.esql.core.expression.TypeResolutions.ParamOrdinal.SECOND;
 import static org.elasticsearch.xpack.esql.core.expression.TypeResolutions.isString;
@@ -248,4 +255,26 @@ public String toString() {
     public boolean licenseCheck(XPackLicenseState state) {
         return MachineLearning.CATEGORIZE_TEXT_AGG_FEATURE.check(state);
     }
+
+    @Override
+    public BiConsumer<LogicalPlan, Failures> postAnalysisPlanVerification() {
+        return (p, failures) -> {
+            super.postAnalysisPlanVerification().accept(p, failures);
+
+            if (p instanceof InlineStats inlineStats && inlineStats.child() instanceof Aggregate aggregate) {
+                aggregate.groupings().forEach(grp -> {
+                    if (grp instanceof Alias alias && alias.child() instanceof Categorize categorize) {
+                        failures.add(
+                            fail(
+                                categorize,
+                                "CATEGORIZE [{}] is not yet supported with INLINESTATS [{}]",
+                                categorize.sourceText(),
+                                inlineStats.sourceText()
+                            )
+                        );
+                    }
+                });
+            }
+        };
+    }
 }

x-pack/plugin/esql/src/test/java/org/elasticsearch/xpack/esql/analysis/VerifierTests.java

@@ -2063,6 +2063,26 @@ public void testCategorizeOptionSimilarityThreshold() {
         );
     }
 
+    public void testCategorizeWithInlineStats() {
+        assertEquals(
+            "1:37: CATEGORIZE [CATEGORIZE(last_name, { \"similarity_threshold\": 1 })] is not yet supported with "
+                + "INLINESTATS [INLINESTATS COUNT(*) BY CATEGORIZE(last_name, { \"similarity_threshold\": 1 })]",
+            error("FROM test | INLINESTATS COUNT(*) BY CATEGORIZE(last_name, { \"similarity_threshold\": 1 })")
+        );
+
+        assertEquals("""
+            3:35: CATEGORIZE [CATEGORIZE(gender)] is not yet supported with \
+            INLINESTATS [INLINESTATS SUM(salary) BY c3 = CATEGORIZE(gender)]
+            line 2:91: CATEGORIZE grouping function [CATEGORIZE(first_name)] can only be in the first grouping expression
+            line 2:32: CATEGORIZE [CATEGORIZE(last_name, { "similarity_threshold": 1 })] is not yet supported with \
+            INLINESTATS [INLINESTATS COUNT(*) BY c1 = CATEGORIZE(last_name, { "similarity_threshold": 1 }), \
+            c2 = CATEGORIZE(first_name)]""", error("""
+            FROM test
+            | INLINESTATS COUNT(*) BY c1 = CATEGORIZE(last_name, { "similarity_threshold": 1 }), c2 = CATEGORIZE(first_name)
+            | INLINESTATS SUM(salary) BY c3 = CATEGORIZE(gender)
+            """));
+    }
+
     public void testChangePoint() {
         assumeTrue("change_point must be enabled", EsqlCapabilities.Cap.CHANGE_POINT.isEnabled());
         var airports = AnalyzerTestUtils.analyzer(loadMapping("mapping-airports.json", "airports"));