[SPARK-31753][SQL][DOCS] Add missing keywords in the SQL docs

docs/_data/menu-sql.yaml

@@ -187,6 +187,12 @@
                   url: sql-ref-syntax-qry-select-tvf.html
                 - text: Window Function
                   url: sql-ref-syntax-qry-select-window.html
+                - text: CASE Clause
+                  url: sql-ref-syntax-qry-select-case.html
+                - text: LATERAL VIEW Clause
+                  url: sql-ref-syntax-qry-select-lateral-view.html
+                - text: PIVOT Clause
+                  url: sql-ref-syntax-qry-select-pivot.html
             - text: EXPLAIN
               url: sql-ref-syntax-qry-explain.html
         - text: Auxiliary Statements

docs/sql-ref-syntax-ddl-create-table-hiveformat.md

@@ -36,6 +36,14 @@ CREATE [ EXTERNAL ] TABLE [ IF NOT EXISTS ] table_identifier
     [ LOCATION path ]
     [ TBLPROPERTIES ( key1=val1, key2=val2, ... ) ]
     [ AS select_statement ]
+
+row_format:    
+    : SERDE serde_class [ WITH SERDEPROPERTIES (k1=v1, k2=v2, ...) ]
+    | DELIMITED [ FIELDS TERMINATED BY fields_termiated_char [ ESCAPED BY escaped_char ] ] 
+        [ COLLECTION ITEMS TERMINATED BY collection_items_termiated_char ] 
+        [ MAP KEYS TERMINATED BY map_key_termiated_char ]
+        [ LINES TERMINATED BY row_termiated_char ]
+        [ NULL DEFINED AS null_char ]
 ```
 
 Note that, the clauses between the columns definition clause and the AS SELECT clause can come in
@@ -51,15 +59,55 @@ as any order. For example, you can write COMMENT table_comment after TBLPROPERTI
 
 * **EXTERNAL**
 
-    Table is defined using the path provided as LOCATION, does not use default location for this table.
+    Table is defined using the path provided as `LOCATION`, does not use default location for this table.
 
 * **PARTITIONED BY**
 
     Partitions are created on the table, based on the columns specified.
+
+* **row_format**    
+
+    Use the `SERDE` clause to specify a custom SerDe for one table. Otherwise, use the `DELIMITED` clause to use the native SerDe and specify the delimiter, escape character, null character, and so on.
+
+* **SERDE**
+
+    `SERDE` clause can be used to specify a custom `SerDe` for one table.
+
+* **serde_class**
+
+    Specify a fully-qualified class name of a custom SerDe.
+
+* **SERDEPROPERTIES**
+
+    A list of key-value pairs that is used to tag the serde definition.
+
+* **DELIMITED**
+
+    `DELIMITED` clause can be used to specify the native `SerDe` and state the delimiter, escape character, null character, and so on.
+
+* **FIELDS TERMINATED BY**
 
-* **ROW FORMAT**
+    It is used to define a column separator.
+
+* **COLLECTION ITEMS TERMINATED BY**
 
-    SERDE is used to specify a custom SerDe or the DELIMITED clause in order to use the native SerDe.
+    It is used to define a collection item separator.
+
+* **MAP KEYS TERMINATED BY**
+
+    It is used to define a map key separator.
+
+* **LINES TERMINATED BY**
+
+    It is used to define a row separator.
+
+* **NULL DEFINED AS**
+
+    It is used to define the specific value for NULL.
+
+* **ESCAPED BY**
+
+    It is used for escape mechanism.
 
 * **STORED AS**
 
@@ -114,9 +162,45 @@ CREATE TABLE student (id INT, name STRING)
     PARTITIONED BY (age INT);
 
 --Use Row Format and file format
-CREATE TABLE student (id INT,name STRING)
+CREATE TABLE student (id INT, name STRING)
     ROW FORMAT DELIMITED FIELDS TERMINATED BY ','
     STORED AS TEXTFILE;
+
+--Use complex datatype
+CREATE EXTERNAL TABLE family(
+        name STRING,
+        friends ARRAY<STRING>,
+        children MAP<STRING, INT>,
+        address STRUCT<street: STRING, city: STRING>
+    )
+    ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' ESCAPED BY '\\'
+    COLLECTION ITEMS TERMINATED BY '_'
+    MAP KEYS TERMINATED BY ':'
+    LINES TERMINATED BY '\n'
+    NULL DEFINED AS 'foonull'
+    STORED AS TEXTFILE
+    LOCATION '/tmp/family/';
+
+--Use predefined custom SerDe
+CREATE TABLE avroExample
+    ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.avro.AvroSerDe'
+    STORED AS INPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerInputFormat'
+        OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerOutputFormat'
+    TBLPROPERTIES ('avro.schema.literal'='{ "namespace": "org.apache.hive",
+        "name": "first_schema",
+        "type": "record",
+        "fields": [
+                { "name":"string1", "type":"string" },
+                { "name":"string2", "type":"string" }
+            ] }');
+
+--Use personalized custom serde(we may need to `ADD JAR xxx.jar` first to ensure we can find the serde_class, or you may run into `CLASSNOTFOUND` exception)
+ADD JAR /tmp/hive_serde_example.jar;
+CREATE EXTERNAL TABLE family (id INT, name STRING)
+    ROW FORMAT SERDE 'com.ly.spark.serde.SerDeExample'
+    STORED AS INPUTFORMAT 'com.ly.spark.example.serde.io.SerDeExampleInputFormat'
+        OUTPUTFORMAT 'com.ly.spark.example.serde.io.SerDeExampleOutputFormat'
+    LOCATION '/tmp/family/';
 ```
 
 ### Related Statements

docs/sql-ref-syntax-qry-select-case.md

@@ -0,0 +1,107 @@
+---
+layout: global
+title: CASE Clause
+displayTitle: CASE Clause
+license: |
+  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.
+---
+
+### Description
+
+`CASE` clause uses a rule to return specific result based on the specified condition, similar to if/else statements in other programming languages.
+
+### Syntax
+
+```sql
+CASE [ expression ] { WHEN boolean_expression THEN then_expression } [ ... ]
+    [ ELSE else_expression ]
+END
+```
+
+### Parameters
+
+* **boolean_expression**
+
+    Specifies an expression with a return type of boolean.
+
+* **then_expression**
+
+    Specifies the then expression based on the `boolean_expression` condition, `then_expression` and `else_expression` should all be same type or coercible to a common type.
+
+* **else_expression**
+
+    Specifies the default expression, `then_expression` and `else_expression` should all be same type or coercible to a common type.
+
+### Examples
+
+```sql
+CREATE TABLE person (id INT, name STRING, age INT);
+INSERT INTO person VALUES
+    (100, 'John', 30),
+    (200, 'Mary', NULL),
+    (300, 'Mike', 80),
+    (400, 'Dan', 50);
+
+SELECT id, CASE WHEN id > 200 THEN 'bigger' ELSE 'small' END FROM person;
++------+--------------------------------------------------+
+|  id  | CASE WHEN (id > 200) THEN bigger ELSE small END  |
++------+--------------------------------------------------+
+| 100  | small                                            |
+| 200  | small                                            |
+| 300  | bigger                                           |
+| 400  | bigger                                           |
++------+--------------------------------------------------+
+
+SELECT id, CASE id WHEN 100 then 'bigger' WHEN  id > 300 THEN '300' ELSE 'small' END FROM person;
++------+-----------------------------------------------------------------------------------------------+
+|  id  | CASE WHEN (id = 100) THEN bigger WHEN (id = CAST((id > 300) AS INT)) THEN 300 ELSE small END  |
++------+-----------------------------------------------------------------------------------------------+
+| 100  | bigger                                                                                        |
+| 200  | small                                                                                         |
+| 300  | small                                                                                         |
+| 400  | small                                                                                         |
++------+-----------------------------------------------------------------------------------------------+
+
+SELECT * FROM person
+    WHERE 
+        CASE 1 = 1 
+            WHEN 100 THEN 'big' 
+            WHEN 200 THEN 'bigger'
+            WHEN 300 THEN 'biggest' 
+            ELSE 'small'
+        END = 'small';
++------+-------+-------+
+|  id  | name  |  age  |
++------+-------+-------+
+| 100  | John  | 30    |
+| 200  | Mary  | NULL  |
+| 300  | Mike  | 80    |
+| 400  | Dan   | 50    |
++------+-------+-------+
+```
+
+### Related Statements
+
+* [SELECT Main](sql-ref-syntax-qry-select.html)
+* [WHERE Clause](sql-ref-syntax-qry-select-where.html)
+* [GROUP BY Clause](sql-ref-syntax-qry-select-groupby.html)
+* [HAVING Clause](sql-ref-syntax-qry-select-having.html)
+* [ORDER BY Clause](sql-ref-syntax-qry-select-orderby.html)
+* [SORT BY Clause](sql-ref-syntax-qry-select-sortby.html)
+* [DISTRIBUTE BY Clause](sql-ref-syntax-qry-select-distribute-by.html)
+* [LIMIT Clause](sql-ref-syntax-qry-select-limit.html)
+* [PIVOT Clause](sql-ref-syntax-qry-select-pivot.html)
+* [LATERAL VIEW Clause](sql-ref-syntax-qry-select-lateral-view.html)

docs/sql-ref-syntax-qry-select-clusterby.md

@@ -99,3 +99,6 @@ SELECT age, name FROM person CLUSTER BY age;
 * [SORT BY Clause](sql-ref-syntax-qry-select-sortby.html)
 * [DISTRIBUTE BY Clause](sql-ref-syntax-qry-select-distribute-by.html)
 * [LIMIT Clause](sql-ref-syntax-qry-select-limit.html)
+* [CASE Clause](sql-ref-syntax-qry-select-case.html)
+* [PIVOT Clause](sql-ref-syntax-qry-select-pivot.html)
+* [LATERAL VIEW Clause](sql-ref-syntax-qry-select-lateral-view.html)

docs/sql-ref-syntax-qry-select-distribute-by.md

@@ -94,3 +94,6 @@ SELECT age, name FROM person DISTRIBUTE BY age;
 * [SORT BY Clause](sql-ref-syntax-qry-select-sortby.html)
 * [CLUSTER BY Clause](sql-ref-syntax-qry-select-clusterby.html)
 * [LIMIT Clause](sql-ref-syntax-qry-select-limit.html)
+* [CASE Clause](sql-ref-syntax-qry-select-case.html)
+* [PIVOT Clause](sql-ref-syntax-qry-select-pivot.html)
+* [LATERAL VIEW Clause](sql-ref-syntax-qry-select-lateral-view.html)

docs/sql-ref-syntax-qry-select-groupby.md

@@ -81,6 +81,8 @@ aggregate_name ( [ DISTINCT ] expression [ , ... ] ) [ FILTER ( WHERE boolean_ex
 * **aggregate_name**
 
     Specifies an aggregate function name (MIN, MAX, COUNT, SUM, AVG, etc.).
+    Some aggregate function like `FIRST` and `LAST` have special usage as the following:
+    **Syntax:** `[ FIRST | LAST ] ( [ distinct ] expression [ IGNORE NULLS ] ) [ FILTER ( WHERE boolean_expression ) ]`
 
 * **DISTINCT**
 
@@ -91,6 +93,18 @@ aggregate_name ( [ DISTINCT ] expression [ , ... ] ) [ FILTER ( WHERE boolean_ex
     Filters the input rows for which the `boolean_expression` in the `WHERE` clause evaluates
     to true are passed to the aggregate function; other rows are discarded.
 
+* **FIRST**
+
+    `FIRST` selects a first expression value from the data set. We can specify an optional `IGNORE NULL` clause to ignore NULL values.
+
+* **LAST**
+
+    `LAST` select a last expression value from the data set, we can specify `IGNORE NULLS` to ignore NULLS, it is optional. 
+
+* **IGNORE NULLS**
+
+   `IGNORE NULLS` is to ignore null values, which is used in `FIRST` and `LAST` 
+
 ### Examples
 
 ```sql
@@ -260,6 +274,30 @@ SELECT city, car_model, sum(quantity) AS sum FROM dealer
 | San Jose| HondaAccord|  8|
 | San Jose|  HondaCivic|  5|
 +---------+------------+---+
+
+--Prepare data for ignore nulls example
+CREATE TABLE person (id INT, name STRING, age INT);
+INSERT INTO person VALUES
+    (100, 'Mary', NULL),
+    (200, 'John', 30),
+    (300, 'Mike', 80),
+    (400, 'Dan', 50);
+
+--Select the first row in cloumn age
+SELECT FIRST(age) FROM person;
++--------------------+
+| first(age, false)  |
++--------------------+
+| NULL               |
++--------------------+
+
+--Get the first row in cloumn `age` ignore nulls,last row in column `id` and sum of cloumn `id`.
+SELECT FIRST(age IGNORE NULLS), LAST(id), SUM(id) FROM person;
++-------------------+------------------+----------+
+| first(age, true)  | last(id, false)  | sum(id)  |
++-------------------+------------------+----------+
+| 30                | 400              | 1000     |
++-------------------+------------------+----------+
 ```
 
 ### Related Statements
@@ -272,3 +310,6 @@ SELECT city, car_model, sum(quantity) AS sum FROM dealer
 * [CLUSTER BY Clause](sql-ref-syntax-qry-select-clusterby.html)
 * [DISTRIBUTE BY Clause](sql-ref-syntax-qry-select-distribute-by.html)
 * [LIMIT Clause](sql-ref-syntax-qry-select-limit.html)
+* [CASE Clause](sql-ref-syntax-qry-select-case.html)
+* [PIVOT Clause](sql-ref-syntax-qry-select-pivot.html)
+* [LATERAL VIEW Clause](sql-ref-syntax-qry-select-lateral-view.html)

docs/sql-ref-syntax-qry-select-having.md

@@ -125,3 +125,6 @@ SELECT sum(quantity) AS sum FROM dealer HAVING sum(quantity) > 10;
 * [CLUSTER BY Clause](sql-ref-syntax-qry-select-clusterby.html)
 * [DISTRIBUTE BY Clause](sql-ref-syntax-qry-select-distribute-by.html)
 * [LIMIT Clause](sql-ref-syntax-qry-select-limit.html)
+* [CASE Clause](sql-ref-syntax-qry-select-case.html)
+* [PIVOT Clause](sql-ref-syntax-qry-select-pivot.html)
+* [LATERAL VIEW Clause](sql-ref-syntax-qry-select-lateral-view.html)