Rename capability to CATEGORIZE_V2

nik9000 · Nov 27, 2024 · 30412ad · 30412ad
1 parent b622e6c
commit 30412ad
Show file tree

Hide file tree

Showing 3 changed files with 42 additions and 39 deletions.
diff --git a/x-pack/plugin/esql/qa/testFixtures/src/main/resources/categorize.csv-spec b/x-pack/plugin/esql/qa/testFixtures/src/main/resources/categorize.csv-spec
@@ -1,5 +1,5 @@
 standard aggs
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | STATS count=COUNT(),
@@ -17,7 +17,7 @@ count:long | sum:long |     avg:double     | count_distinct:long | category:keyw
 ;
 
 values aggs
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | STATS values=MV_SORT(VALUES(message)),
@@ -33,7 +33,7 @@ values:keyword                                                        |      top
 ;
 
 mv
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM mv_sample_data
   | STATS COUNT() BY category=CATEGORIZE(message)
@@ -48,7 +48,7 @@ COUNT():long | category:keyword
 ;
 
 row mv
-required_capability: categorize
+required_capability: categorize_v2
 
 ROW message = ["connected to a", "connected to b", "disconnected"]
   | STATS COUNT() BY category=CATEGORIZE(message)
@@ -61,7 +61,7 @@ COUNT():long | category:keyword
 ;
 
 with multiple indices
-required_capability: categorize
+required_capability: categorize_v2
 required_capability: union_types
 
 FROM sample_data*
@@ -76,7 +76,7 @@ COUNT():long | category:keyword
 ;
 
 mv with many values
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM employees
   | STATS COUNT() BY category=CATEGORIZE(job_positions)
@@ -93,7 +93,7 @@ COUNT():long | category:keyword
 ;
 
 mv via eval
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | EVAL message = MV_APPEND(message, "Banana")
@@ -109,7 +109,7 @@ COUNT():long | category:keyword
 ;
 
 mv via eval const
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | EVAL message = ["Banana", "Bread"]
@@ -123,7 +123,7 @@ COUNT():long | category:keyword
 ;
 
 mv via eval const without aliases
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | EVAL message = ["Banana", "Bread"]
@@ -137,7 +137,7 @@ COUNT():long | CATEGORIZE(message):keyword
 ;
 
 mv const in parameter
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | STATS COUNT() BY c = CATEGORIZE(["Banana", "Bread"])
@@ -150,7 +150,7 @@ COUNT():long | c:keyword
 ;
 
 agg alias shadowing
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | STATS c = COUNT() BY c = CATEGORIZE(["Banana", "Bread"])
@@ -165,7 +165,7 @@ c:keyword
 ;
 
 chained aggregations using categorize
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | STATS COUNT() BY category=CATEGORIZE(message)
@@ -180,7 +180,7 @@ COUNT():long | category:keyword
 ;
 
 stats without aggs
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | STATS BY category=CATEGORIZE(message)
@@ -194,7 +194,7 @@ category:keyword
 ;
 
 text field
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM hosts
   | STATS COUNT() BY category=CATEGORIZE(host_group)
@@ -208,7 +208,7 @@ COUNT():long | category:keyword
 ;
 
 on TO_UPPER
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | STATS COUNT() BY category=CATEGORIZE(TO_UPPER(message))
@@ -222,7 +222,7 @@ COUNT():long | category:keyword
 ;
 
 on CONCAT
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | STATS COUNT() BY category=CATEGORIZE(CONCAT(message, " banana"))
@@ -236,7 +236,7 @@ COUNT():long | category:keyword
 ;
 
 on CONCAT with unicode
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | STATS COUNT() BY category=CATEGORIZE(CONCAT(message, " 👍🏽😊"))
@@ -250,7 +250,7 @@ COUNT():long | category:keyword
 ;
 
 on REVERSE(CONCAT())
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | STATS COUNT() BY category=CATEGORIZE(REVERSE(CONCAT(message, " 👍🏽😊")))
@@ -264,7 +264,7 @@ COUNT():long | category:keyword
 ;
 
 and then TO_LOWER
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | STATS COUNT() BY category=CATEGORIZE(message)
@@ -280,7 +280,7 @@ COUNT():long | category:keyword
 
 # Throws NPE - Requires nulls support
 on const empty string-Ignore
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | STATS COUNT() BY category=CATEGORIZE("")
@@ -293,7 +293,7 @@ COUNT():long | category:keyword
 
 # Throws NPE - Requires nulls support
 on const empty string from eval-Ignore
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | EVAL x = ""
@@ -306,7 +306,7 @@ COUNT():long | category:keyword
 ;
 
 on null
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | EVAL x = null
@@ -318,7 +318,7 @@ COUNT():long | category:keyword
 ;
 
 on null string
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | EVAL x = null::string
@@ -330,7 +330,7 @@ COUNT():long | category:keyword
 ;
 
 filtering out all data
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | WHERE @timestamp < "2023-10-23T00:00:00Z"
@@ -342,7 +342,7 @@ COUNT():long | category:keyword
 ;
 
 filtering out all data with constant
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | STATS COUNT() BY category=CATEGORIZE(message)
@@ -353,7 +353,7 @@ COUNT():long | category:keyword
 ;
 
 drop output columns
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | STATS count=COUNT() BY category=CATEGORIZE(message)
@@ -368,7 +368,7 @@ x:integer
 ;
 
 category value processing
-required_capability: categorize
+required_capability: categorize_v2
 
 ROW message = ["connected to a", "connected to b", "disconnected"]
   | STATS COUNT() BY category=CATEGORIZE(message)
@@ -382,7 +382,7 @@ COUNT():long | category:keyword
 ;
 
 row aliases
-required_capability: categorize
+required_capability: categorize_v2
 
 ROW message = "connected to a"
   | EVAL x = message
@@ -396,7 +396,7 @@ COUNT():long | category:keyword         | y:keyword
 ;
 
 from aliases
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | EVAL x = message
@@ -412,7 +412,7 @@ COUNT():long | category:keyword         | y:keyword
 ;
 
 row aliases with keep
-required_capability: categorize
+required_capability: categorize_v2
 
 ROW message = "connected to a"
   | EVAL x = message
@@ -428,7 +428,7 @@ COUNT():long | y:keyword
 ;
 
 from aliases with keep
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | EVAL x = message
@@ -446,7 +446,7 @@ COUNT():long | y:keyword
 ;
 
 row rename
-required_capability: categorize
+required_capability: categorize_v2
 
 ROW message = "connected to a"
   | RENAME message as x
@@ -460,7 +460,7 @@ COUNT():long | y:keyword
 ;
 
 from rename
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | RENAME message as x
@@ -476,7 +476,7 @@ COUNT():long | y:keyword
 ;
 
 row drop
-required_capability: categorize
+required_capability: categorize_v2
 
 ROW message = "connected to a"
   | STATS c = COUNT() BY category=CATEGORIZE(message)
@@ -489,7 +489,7 @@ c:long
 ;
 
 from drop
-required_capability: categorize
+required_capability: categorize_v2
 
 FROM sample_data
   | STATS c = COUNT() BY category=CATEGORIZE(message)

diff --git a/x-pack/plugin/esql/src/main/java/org/elasticsearch/xpack/esql/action/EsqlCapabilities.java b/x-pack/plugin/esql/src/main/java/org/elasticsearch/xpack/esql/action/EsqlCapabilities.java
@@ -402,8 +402,11 @@ public enum Cap {
 
         /**
          * Supported the text categorization function "CATEGORIZE".
+         * <p>
+         *     This capability was initially named `CATEGORIZE`, and got renamed after the function started correctly returning keywords.
+         * </p>
          */
-        CATEGORIZE(Build.current().isSnapshot()),
+        CATEGORIZE_V2(Build.current().isSnapshot()),
 
         /**
          * QSTR function

diff --git a/x-pack/plugin/esql/src/test/java/org/elasticsearch/xpack/esql/analysis/VerifierTests.java b/x-pack/plugin/esql/src/test/java/org/elasticsearch/xpack/esql/analysis/VerifierTests.java
@@ -1821,7 +1821,7 @@ public void testIntervalAsString() {
     }
 
     public void testCategorizeSingleGrouping() {
-        assumeTrue("requires Categorize capability", EsqlCapabilities.Cap.CATEGORIZE.isEnabled());
+        assumeTrue("requires Categorize capability", EsqlCapabilities.Cap.CATEGORIZE_V2.isEnabled());
 
         query("from test | STATS COUNT(*) BY CATEGORIZE(first_name)");
         query("from test | STATS COUNT(*) BY cat = CATEGORIZE(first_name)");
@@ -1850,7 +1850,7 @@ public void testCategorizeSingleGrouping() {
     }
 
     public void testCategorizeNestedGrouping() {
-        assumeTrue("requires Categorize capability", EsqlCapabilities.Cap.CATEGORIZE.isEnabled());
+        assumeTrue("requires Categorize capability", EsqlCapabilities.Cap.CATEGORIZE_V2.isEnabled());
 
         query("from test | STATS COUNT(*) BY CATEGORIZE(LENGTH(first_name)::string)");
 
@@ -1865,7 +1865,7 @@ public void testCategorizeNestedGrouping() {
     }
 
     public void testCategorizeWithinAggregations() {
-        assumeTrue("requires Categorize capability", EsqlCapabilities.Cap.CATEGORIZE.isEnabled());
+        assumeTrue("requires Categorize capability", EsqlCapabilities.Cap.CATEGORIZE_V2.isEnabled());
 
         query("from test | STATS MV_COUNT(cat), COUNT(*) BY cat = CATEGORIZE(first_name)");