beliefer commented on a change in pull request #28194:
URL: https://github.com/apache/spark/pull/28194#discussion_r415831986
##########
File path: sql/core/src/test/resources/sql-functions/sql-expression-schema.md
##########
@@ -0,0 +1,331 @@
+## Summary
+ - Number of queries: 324
+ - Number of expressions that missing example: 37
+ - Expressions missing examples:
and,string,tinyint,double,smallint,date,decimal,boolean,float,binary,bigint,int,timestamp,cume_dist,current_date,current_timestamp,now,dense_rank,input_file_block_length,input_file_block_start,input_file_name,lag,lead,monotonically_increasing_id,ntile,struct,!,not,or,percent_rank,rank,row_number,spark_partition_id,version,window,positive,count_min_sketch
+## Schema of Built-in Functions
+| No | Class name | Function name or alias | Query example | Output schema |
+| -- | ---------- | ---------------------- | ------------- | ------------- |
+| 1 | org.apache.spark.sql.catalyst.expressions.Abs | abs | SELECT abs(-1) |
struct<abs(-1):int> |
+| 2 | org.apache.spark.sql.catalyst.expressions.Acos | acos | SELECT acos(1) |
struct<ACOS(CAST(1 AS DOUBLE)):double> |
+| 3 | org.apache.spark.sql.catalyst.expressions.Acosh | acosh | SELECT
acosh(1) | struct<ACOSH(CAST(1 AS DOUBLE)):double> |
+| 4 | org.apache.spark.sql.catalyst.expressions.Add | + | SELECT 1 + 2 |
struct<(1 + 2):int> |
+| 5 | org.apache.spark.sql.catalyst.expressions.AddMonths | add_months |
SELECT add_months('2016-08-31', 1) | struct<add_months(CAST(2016-08-31 AS
DATE), 1):date> |
+| 6 | org.apache.spark.sql.catalyst.expressions.And | and | Example is missing
| Example is missing |
+| 7 | org.apache.spark.sql.catalyst.expressions.ArrayAggregate | aggregate |
SELECT aggregate(array(1, 2, 3), 0, (acc, x) -> acc + x) |
struct<aggregate(array(1, 2, 3), 0, lambdafunction((namedlambdavariable() +
namedlambdavariable()), namedlambdavariable(), namedlambdavariable()),
lambdafunction(namedlambdavariable(), namedlambdavariable())):int> |
+| 8 | org.apache.spark.sql.catalyst.expressions.ArrayContains | array_contains
| SELECT array_contains(array(1, 2, 3), 2) | struct<array_contains(array(1, 2,
3), 2):boolean> |
+| 9 | org.apache.spark.sql.catalyst.expressions.ArrayDistinct | array_distinct
| SELECT array_distinct(array(1, 2, 3, null, 3)) |
struct<array_distinct(array(1, 2, 3, CAST(NULL AS INT), 3)):array<int>> |
+| 10 | org.apache.spark.sql.catalyst.expressions.ArrayExcept | array_except |
SELECT array_except(array(1, 2, 3), array(1, 3, 5)) |
struct<array_except(array(1, 2, 3), array(1, 3, 5)):array<int>> |
+| 11 | org.apache.spark.sql.catalyst.expressions.ArrayExists | exists | SELECT
exists(array(1, 2, 3), x -> x % 2 == 0) | struct<exists(array(1, 2, 3),
lambdafunction(((namedlambdavariable() % 2) = 0),
namedlambdavariable())):boolean> |
+| 12 | org.apache.spark.sql.catalyst.expressions.ArrayFilter | filter | SELECT
filter(array(1, 2, 3), x -> x % 2 == 1) | struct<filter(array(1, 2, 3),
lambdafunction(((namedlambdavariable() % 2) = 1),
namedlambdavariable())):array<int>> |
+| 13 | org.apache.spark.sql.catalyst.expressions.ArrayForAll | forall | SELECT
forall(array(1, 2, 3), x -> x % 2 == 0) | struct<forall(array(1, 2, 3),
lambdafunction(((namedlambdavariable() % 2) = 0),
namedlambdavariable())):boolean> |
+| 14 | org.apache.spark.sql.catalyst.expressions.ArrayIntersect |
array_intersect | SELECT array_intersect(array(1, 2, 3), array(1, 3, 5)) |
struct<array_intersect(array(1, 2, 3), array(1, 3, 5)):array<int>> |
+| 15 | org.apache.spark.sql.catalyst.expressions.ArrayJoin | array_join |
SELECT array_join(array('hello', 'world'), ' ') |
struct<array_join(array(hello, world), ):string> |
+| 16 | org.apache.spark.sql.catalyst.expressions.ArrayMax | array_max | SELECT
array_max(array(1, 20, null, 3)) | struct<array_max(array(1, 20, CAST(NULL AS
INT), 3)):int> |
+| 17 | org.apache.spark.sql.catalyst.expressions.ArrayMin | array_min | SELECT
array_min(array(1, 20, null, 3)) | struct<array_min(array(1, 20, CAST(NULL AS
INT), 3)):int> |
+| 18 | org.apache.spark.sql.catalyst.expressions.ArrayPosition |
array_position | SELECT array_position(array(3, 2, 1), 1) |
struct<array_position(array(3, 2, 1), 1):bigint> |
+| 19 | org.apache.spark.sql.catalyst.expressions.ArrayRemove | array_remove |
SELECT array_remove(array(1, 2, 3, null, 3), 3) | struct<array_remove(array(1,
2, 3, CAST(NULL AS INT), 3), 3):array<int>> |
+| 20 | org.apache.spark.sql.catalyst.expressions.ArrayRepeat | array_repeat |
SELECT array_repeat('123', 2) | struct<array_repeat(123, 2):array<string>> |
+| 21 | org.apache.spark.sql.catalyst.expressions.ArraySort | array_sort |
SELECT array_sort(array(5, 6, 1), (left, right) -> case when left < right then
-1 when left > right then 1 else 0 end) | struct<array_sort(array(5, 6, 1),
lambdafunction(CASE WHEN (namedlambdavariable() < namedlambdavariable()) THEN
-1 WHEN (namedlambdavariable() > namedlambdavariable()) THEN 1 ELSE 0 END,
namedlambdavariable(), namedlambdavariable())):array<int>> |
+| 22 | org.apache.spark.sql.catalyst.expressions.ArrayTransform | transform |
SELECT transform(array(1, 2, 3), x -> x + 1) | struct<transform(array(1, 2, 3),
lambdafunction((namedlambdavariable() + 1), namedlambdavariable())):array<int>>
|
+| 23 | org.apache.spark.sql.catalyst.expressions.ArrayUnion | array_union |
SELECT array_union(array(1, 2, 3), array(1, 3, 5)) |
struct<array_union(array(1, 2, 3), array(1, 3, 5)):array<int>> |
+| 24 | org.apache.spark.sql.catalyst.expressions.ArraysOverlap |
arrays_overlap | SELECT arrays_overlap(array(1, 2, 3), array(3, 4, 5)) |
struct<arrays_overlap(array(1, 2, 3), array(3, 4, 5)):boolean> |
+| 25 | org.apache.spark.sql.catalyst.expressions.ArraysZip | arrays_zip |
SELECT arrays_zip(array(1, 2, 3), array(2, 3, 4)) | struct<arrays_zip(array(1,
2, 3), array(2, 3, 4)):array<struct<0:int,1:int>>> |
+| 26 | org.apache.spark.sql.catalyst.expressions.Ascii | ascii | SELECT
ascii('222') | struct<ascii(222):int> |
+| 27 | org.apache.spark.sql.catalyst.expressions.Asin | asin | SELECT asin(0)
| struct<ASIN(CAST(0 AS DOUBLE)):double> |
+| 28 | org.apache.spark.sql.catalyst.expressions.Asinh | asinh | SELECT
asinh(0) | struct<ASINH(CAST(0 AS DOUBLE)):double> |
+| 29 | org.apache.spark.sql.catalyst.expressions.AssertTrue | assert_true |
SELECT assert_true(0 < 1) | struct<assert_true((0 < 1)):null> |
+| 30 | org.apache.spark.sql.catalyst.expressions.Atan | atan | SELECT atan(0)
| struct<ATAN(CAST(0 AS DOUBLE)):double> |
+| 31 | org.apache.spark.sql.catalyst.expressions.Atan2 | atan2 | SELECT
atan2(0, 0) | struct<ATAN2(CAST(0 AS DOUBLE), CAST(0 AS DOUBLE)):double> |
+| 32 | org.apache.spark.sql.catalyst.expressions.Atanh | atanh | SELECT
atanh(0) | struct<ATANH(CAST(0 AS DOUBLE)):double> |
+| 33 | org.apache.spark.sql.catalyst.expressions.BRound | bround | SELECT
bround(2.5, 0) | struct<bround(2.5, 0):decimal(2,0)> |
+| 34 | org.apache.spark.sql.catalyst.expressions.Base64 | base64 | SELECT
base64('Spark SQL') | struct<base64(CAST(Spark SQL AS BINARY)):string> |
+| 35 | org.apache.spark.sql.catalyst.expressions.Bin | bin | SELECT bin(13) |
struct<bin(CAST(13 AS BIGINT)):string> |
+| 36 | org.apache.spark.sql.catalyst.expressions.BitLength | bit_length |
SELECT bit_length('Spark SQL') | struct<bit_length(Spark SQL):int> |
+| 37 | org.apache.spark.sql.catalyst.expressions.BitwiseAnd | & | SELECT 3 & 5
| struct<(3 & 5):int> |
+| 38 | org.apache.spark.sql.catalyst.expressions.BitwiseCount | bit_count |
SELECT bit_count(0) | struct<bit_count(0):int> |
+| 39 | org.apache.spark.sql.catalyst.expressions.BitwiseNot | ~ | SELECT ~ 0 |
struct<~0:int> |
+| 40 | org.apache.spark.sql.catalyst.expressions.BitwiseOr | | | SELECT 3 | 5
| struct<(3 | 5):int> |
Review comment:
OK. I will fix this bug.
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/ExpressionsSchemaSuite.scala
##########
@@ -0,0 +1,230 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql
+
+import java.io.File
+
+import scala.collection.mutable.ArrayBuffer
+
+import org.apache.spark.sql.catalyst.expressions.ExpressionInfo
Review comment:
OK.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
