Merge remote-tracking branch 'apache/master' into validate-target-col…

…umn-types

.github/workflows/revised-its.yml

@@ -50,7 +50,7 @@ jobs:
       matrix:
         #jdk: [8, 11, 17]
         jdk: [8]
-        it: [HighAvailability, MultiStageQuery, Catalog, BatchIndex, MultiStageQueryWithMM, InputSource, InputFormat]
+        it: [HighAvailability, MultiStageQuery, Catalog, BatchIndex, MultiStageQueryWithMM, InputSource, InputFormat, Security]
         #indexer: [indexer, middleManager]
         indexer: [middleManager]
     uses: ./.github/workflows/reusable-revised-its.yml

.github/workflows/static-checks.yml

@@ -34,7 +34,7 @@ env:
   MVN: mvn -B
   MAVEN_SKIP: -P skip-static-checks -Dweb.console.skip=true -Dmaven.javadoc.skip=true
   MAVEN_SKIP_TESTS: -P skip-tests
-  MAVEN_OPTS: -Xmx3000m
+  MAVEN_OPTS: -Xmx8g
 
 jobs:
   static-checks:
@@ -144,6 +144,28 @@ jobs:
           --levels ERROR \
           --scope JavaInspectionsScope
 
+  openrewrite:
+    runs-on: ubuntu-latest
+    steps:
+      - name: checkout branch
+        uses: actions/checkout@v4
+
+      - uses: actions/setup-java@v4
+        with:
+          distribution: 'zulu'
+          java-version: '8'
+          cache: 'maven'
+
+      - name: maven install
+        run: |
+          echo 'Running Maven install...' &&
+          ${MVN} clean install -q -ff -pl '!distribution' ${MAVEN_SKIP} ${MAVEN_SKIP_TESTS} -T1C &&
+          ${MVN} install -q -ff -pl 'distribution' ${MAVEN_SKIP} ${MAVEN_SKIP_TESTS}
+
+      - name: rewrite:dryRun
+        run: |
+          ${MVN} rewrite:dryRun ${MAVEN_SKIP}
+
   web-checks:
     strategy:
       fail-fast: false

benchmarks/src/test/java/org/apache/druid/benchmark/query/SqlExpressionBenchmark.java

@@ -213,7 +213,12 @@ public String getFormatString()
       // 40: regex filtering
       "SELECT string4, COUNT(*) FROM foo WHERE REGEXP_EXTRACT(string1, '^1') IS NOT NULL OR REGEXP_EXTRACT('Z' || string2, '^Z2') IS NOT NULL GROUP BY 1",
       // 41: complicated filtering
-      "SELECT string2, SUM(long1) FROM foo WHERE string1 = '1000' AND string5 LIKE '%1%' AND (string3 in ('1', '10', '20', '22', '32') AND long2 IN (1, 19, 21, 23, 25, 26, 46) AND double3 < 1010.0 AND double3 > 1000.0 AND (string4 = '1' OR REGEXP_EXTRACT(string1, '^1') IS NOT NULL OR REGEXP_EXTRACT('Z' || string2, '^Z2') IS NOT NULL)) GROUP BY 1 ORDER BY 2"
+      "SELECT string2, SUM(long1) FROM foo WHERE string1 = '1000' AND string5 LIKE '%1%' AND (string3 in ('1', '10', '20', '22', '32') AND long2 IN (1, 19, 21, 23, 25, 26, 46) AND double3 < 1010.0 AND double3 > 1000.0 AND (string4 = '1' OR REGEXP_EXTRACT(string1, '^1') IS NOT NULL OR REGEXP_EXTRACT('Z' || string2, '^Z2') IS NOT NULL)) GROUP BY 1 ORDER BY 2",
+      // 42: array_contains expr
+      "SELECT ARRAY_CONTAINS(\"multi-string3\", 100) FROM foo",
+      "SELECT ARRAY_CONTAINS(\"multi-string3\", ARRAY[1, 2, 10, 11, 20, 22, 30, 33, 40, 44, 50, 55, 100]) FROM foo",
+      "SELECT ARRAY_OVERLAP(\"multi-string3\", ARRAY[1, 100]) FROM foo",
+      "SELECT ARRAY_OVERLAP(\"multi-string3\", ARRAY[1, 2, 10, 11, 20, 22, 30, 33, 40, 44, 50, 55, 100]) FROM foo"
   );
 
   @Param({"5000000"})
@@ -275,7 +280,11 @@ public String getFormatString()
       "38",
       "39",
       "40",
-      "41"
+      "41",
+      "42",
+      "43",
+      "44",
+      "45"
   })
   private String query;
 
@@ -369,8 +378,8 @@ public void setup()
                          .writeValueAsString(jsonMapper.readValue((String) planResult[0], List.class))
       );
     }
-    catch (JsonProcessingException e) {
-      throw new RuntimeException(e);
+    catch (JsonProcessingException ignored) {
+
     }
 
     try (final DruidPlanner planner = plannerFactory.createPlannerForTesting(engine, sql, ImmutableMap.of())) {
@@ -384,6 +393,9 @@ public void setup()
       }
       log.info("Total result row count:" + rowCounter);
     }
+    catch (Throwable ignored) {
+
+    }
   }
 
   @TearDown(Level.Trial)

docs/api-reference/data-management-api.md

@@ -206,20 +206,22 @@ Marks the state of a group of segments as unused, using an array of segment IDs
 Pass the array of segment IDs or interval as a JSON object in the request body.
 
 For the interval, specify the start and end times as ISO 8601 strings to identify segments inclusive of the start time and exclusive of the end time.
-Druid only updates the segments completely contained within the specified interval; partially overlapping segments are not affected.
+Optionally, specify an array of segment versions with interval. Druid updates only the segments completely contained
+within the specified interval that match the optional list of versions; partially overlapping segments are not affected.
 
 #### URL
 
 <code class="postAPI">POST</code> <code>/druid/coordinator/v1/datasources/:datasource/markUnused</code>
 
 #### Request body
 
-The group of segments is sent as a JSON request payload that accepts one of the following properties:
+The group of segments is sent as a JSON request payload that accepts the following properties:
 
-|Property|Description|Example|
-|----------|-------------|---------|
-|`interval`|ISO 8601 segments interval.|`"2015-09-12T03:00:00.000Z/2015-09-12T05:00:00.000Z"`|
-|`segmentIds`|Array of segment IDs.|`["segmentId1", "segmentId2"]`|
+|Property|Description|Required|Example|
+|----------|-------------|---------|---------|
+|`interval`|ISO 8601 segments interval.|Yes, if `segmentIds` is not specified.|`"2015-09-12T03:00:00.000Z/2015-09-12T05:00:00.000Z"`|
+|`segmentIds`|List of segment IDs.|Yes, if `interval` is not specified.|`["segmentId1", "segmentId2"]`|
+|`versions`|List of segment versions. Must be provided with `interval`.|No.|`["2024-03-14T16:00:04.086Z", ""2024-03-12T16:00:04.086Z"]`|
 
 #### Responses
 
@@ -306,20 +308,22 @@ Marks the state of a group of segments as used, using an array of segment IDs or
 Pass the array of segment IDs or interval as a JSON object in the request body.
 
 For the interval, specify the start and end times as ISO 8601 strings to identify segments inclusive of the start time and exclusive of the end time.
-Druid only updates the segments completely contained within the specified interval; partially overlapping segments are not affected.
+Optionally, specify an array of segment versions with interval. Druid updates only the segments completely contained
+within the specified interval that match the optional list of versions; partially overlapping segments are not affected.
 
 #### URL
 
 <code class="postAPI">POST</code> <code>/druid/coordinator/v1/datasources/:datasource/markUsed</code>
 
 #### Request body
 
-The group of segments is sent as a JSON request payload that accepts one of the following properties:
+The group of segments is sent as a JSON request payload that accepts the following properties:
 
-|Property|Description|Example|
-|----------|-------------|---------|
-|`interval`| ISO 8601 segments interval.|`"2015-09-12T03:00:00.000Z/2015-09-12T05:00:00.000Z"`|
-|`segmentIds`|Array of segment IDs.|`["segmentId1", "segmentId2"]`|
+|Property|Description|Required|Example|
+|----------|-------------|---------|---------|
+|`interval`|ISO 8601 segments interval.|Yes, if `segmentIds` is not specified.|`"2015-09-12T03:00:00.000Z/2015-09-12T05:00:00.000Z"`|
+|`segmentIds`|List of segment IDs.|Yes, if `interval` is not specified.|`["segmentId1", "segmentId2"]`|
+|`versions`|List of segment versions. Must be provided with `interval`.|No.|`["2024-03-14T16:00:04.086Z", ""2024-03-12T16:00:04.086Z"]`|
 
 #### Responses
 

docs/development/extensions-core/lookups-cached-global.md

@@ -211,8 +211,8 @@ The remapping values for each globally cached lookup can be specified by a JSON
 |Property|Description|Required|Default|
 |--------|-----------|--------|-------|
 |`pollPeriod`|Period between polling for updates|No|0 (only once)|
-|`uri`|URI for the file of interest, specified as a file, hdfs, s3 or gs path|No|Use `uriPrefix`|
-|`uriPrefix`|A URI that specifies a directory (or other searchable resource) in which to search for files|No|Use `uri`|
+|`uri`|URI for the lookup file. Can be a file, HDFS, S3 or GCS path|Either `uri` or `uriPrefix` must be set|None|
+|`uriPrefix`|A URI prefix that specifies a directory or other searchable resource where lookup files are located |Either `uri` or `uriPrefix` must be set|None|
 |`fileRegex`|Optional regex for matching the file name under `uriPrefix`. Only used if `uriPrefix` is used|No|`".*"`|
 |`namespaceParseSpec`|How to interpret the data at the URI|Yes||
 |`maxHeapPercentage`|The maximum percentage of heap size that the lookup should consume. If the lookup grows beyond this size, warning messages will be logged in the respective service logs.|No|10% of JVM heap size|

docs/multi-stage-query/concepts.md

@@ -200,8 +200,8 @@ To perform ingestion with rollup:
 2. Set [`finalizeAggregations: false`](reference.md#context-parameters) in your context. This causes aggregation
    functions to write their internal state to the generated segments, instead of the finalized end result, and enables
    further aggregation at query time.
-3. See [ARRAY types](../querying/arrays.md#sql-based-ingestion-with-rollup) for information about ingesting `ARRAY` columns
-4. See [multi-value dimensions](../querying/multi-value-dimensions.md#sql-based-ingestion-with-rollup) for information to ingest multi-value VARCHAR columns
+3. See [ARRAY types](../querying/arrays.md#sql-based-ingestion) for information about ingesting `ARRAY` columns
+4. See [multi-value dimensions](../querying/multi-value-dimensions.md#sql-based-ingestion) for information to ingest multi-value VARCHAR columns
 
 When you do all of these things, Druid understands that you intend to do an ingestion with rollup, and it writes
 rollup-related metadata into the generated segments. Other applications can then use [`segmentMetadata`

docs/multi-stage-query/reference.md

@@ -351,7 +351,7 @@ The following table lists the context parameters for the MSQ task engine:
 | `maxNumTasks` | SELECT, INSERT, REPLACE<br /><br />The maximum total number of tasks to launch, including the controller task. The lowest possible value for this setting is 2: one controller and one worker. All tasks must be able to launch simultaneously. If they cannot, the query returns a `TaskStartTimeout` error code after approximately 10 minutes.<br /><br />May also be provided as `numTasks`. If both are present, `maxNumTasks` takes priority. | 2 |
 | `taskAssignment` | SELECT, INSERT, REPLACE<br /><br />Determines how many tasks to use. Possible values include: <ul><li>`max`: Uses as many tasks as possible, up to `maxNumTasks`.</li><li>`auto`: When file sizes can be determined through directory listing (for example: local files, S3, GCS, HDFS) uses as few tasks as possible without exceeding 512 MiB or 10,000 files per task, unless exceeding these limits is necessary to stay within `maxNumTasks`. When calculating the size of files, the weighted size is used, which considers the file format and compression format used if any. When file sizes cannot be determined through directory listing (for example: http), behaves the same as `max`.</li></ul> | `max` |
 | `finalizeAggregations` | SELECT, INSERT, REPLACE<br /><br />Determines the type of aggregation to return. If true, Druid finalizes the results of complex aggregations that directly appear in query results. If false, Druid returns the aggregation's intermediate type rather than finalized type. This parameter is useful during ingestion, where it enables storing sketches directly in Druid tables. For more information about aggregations, see [SQL aggregation functions](../querying/sql-aggregations.md). | `true` |
-| `arrayIngestMode` | INSERT, REPLACE<br /><br /> Controls how ARRAY type values are stored in Druid segments. When set to `array` (recommended for SQL compliance), Druid will store all ARRAY typed values in [ARRAY typed columns](../querying/arrays.md), and supports storing both VARCHAR and numeric typed arrays. When set to `mvd` (the default, for backwards compatibility), Druid only supports VARCHAR typed arrays, and will store them as [multi-value string columns](../querying/multi-value-dimensions.md). When set to `none`, Druid will throw an exception when trying to store any type of arrays. `none` is most useful when set in the system default query context with (`druid.query.default.context.arrayIngestMode=none`) to be used to help migrate operators from `mvd` mode to `array` mode and force query writers to make an explicit choice between ARRAY and multi-value VARCHAR typed columns. | `mvd` (for backwards compatibility, recommended to use `array` for SQL compliance)|
+| `arrayIngestMode` | INSERT, REPLACE<br /><br /> Controls how ARRAY type values are stored in Druid segments. When set to `array` (recommended for SQL compliance), Druid will store all ARRAY typed values in [ARRAY typed columns](../querying/arrays.md), and supports storing both VARCHAR and numeric typed arrays. When set to `mvd` (the default, for backwards compatibility), Druid only supports VARCHAR typed arrays, and will store them as [multi-value string columns](../querying/multi-value-dimensions.md). See [`arrayIngestMode`] in the [Arrays](../querying/arrays.md) page for more details. | `mvd` (for backwards compatibility, recommended to use `array` for SQL compliance)|
 | `sqlJoinAlgorithm` | SELECT, INSERT, REPLACE<br /><br />Algorithm to use for JOIN. Use `broadcast` (the default) for broadcast hash join or `sortMerge` for sort-merge join. Affects all JOIN operations in the query. This is a hint to the MSQ engine and the actual joins in the query may proceed in a different way than specified. See [Joins](#joins) for more details. | `broadcast` |
 | `rowsInMemory` | INSERT or REPLACE<br /><br />Maximum number of rows to store in memory at once before flushing to disk during the segment generation process. Ignored for non-INSERT queries. In most cases, use the default value. You may need to override the default if you run into one of the [known issues](./known-issues.md) around memory usage. | 100,000 |
 | `segmentSortOrder` | INSERT or REPLACE<br /><br />Normally, Druid sorts rows in individual segments using `__time` first, followed by the [CLUSTERED BY](#clustered-by) clause. When you set `segmentSortOrder`, Druid sorts rows in segments using this column list first, followed by the CLUSTERED BY order.<br /><br />You provide the column list as comma-separated values or as a JSON array in string form. If your query includes `__time`, then this list must begin with `__time`. For example, consider an INSERT query that uses `CLUSTERED BY country` and has `segmentSortOrder` set to `__time,city`. Within each time chunk, Druid assigns rows to segments based on `country`, and then within each of those segments, Druid sorts those rows by `__time` first, then `city`, then `country`. | empty list |
@@ -364,6 +364,7 @@ The following table lists the context parameters for the MSQ task engine:
 | `waitUntilSegmentsLoad` | INSERT, REPLACE<br /><br /> If set, the ingest query waits for the generated segment to be loaded before exiting, else the ingest query exits without waiting. The task and live reports contain the information about the status of loading segments if this flag is set. This will ensure that any future queries made after the ingestion exits will include results from the ingestion. The drawback is that the controller task will stall till the segments are loaded. | `false` |
 | `includeSegmentSource` | SELECT, INSERT, REPLACE<br /><br /> Controls the sources, which will be queried for results in addition to the segments present on deep storage. Can be `NONE` or `REALTIME`. If this value is `NONE`, only non-realtime (published and used) segments will be downloaded from deep storage. If this value is `REALTIME`, results will also be included from realtime tasks. | `NONE` |
 | `rowsPerPage` | SELECT<br /><br />The number of rows per page to target. The actual number of rows per page may be somewhat higher or lower than this number. In most cases, use the default.<br /> This property comes into effect only when `selectDestination` is set to `durableStorage` | 100000 |
+| `skipTypeVerification` | INSERT or REPLACE<br /><br />During query validation, Druid validates that [string arrays](../querying/arrays.md) and [multi-value dimensions](../querying/multi-value-dimensions.md) are not mixed in the same column. If you are intentionally migrating from one to the other, use this context parameter to disable type validation.<br /><br />Provide the column list as comma-separated values or as a JSON array in string form.| empty list |
 | `failOnEmptyInsert` | INSERT or REPLACE<br /><br /> When set to false (the default), an INSERT query generating no output rows will be no-op, and a REPLACE query generating no output rows will delete all data that matches the OVERWRITE clause.  When set to true, an ingest query generating no output rows will throw an `InsertCannotBeEmpty` fault. | `false` |
 
 ## Joins