[SPARK-31429][SQL][DOC] Automatically generates a SQL document for built-in functions

docs/.gitignore

@@ -1 +1 @@
-sql-configs.html
+generated-*.html

docs/_data/menu-sql.yaml

@@ -242,6 +242,8 @@
     - text: Functions
       url: sql-ref-functions.html
       subitems:
+      - text: Built-in Functions
+        url: sql-ref-functions-builtin.html
       - text: Scalar UDFs (User-Defined Functions)
         url: sql-ref-functions-udf-scalar.html
       - text: UDAFs (User-Defined Aggregate Functions)

docs/configuration.md

@@ -2623,10 +2623,10 @@ Spark subsystems.
 
 
 {% for static_file in site.static_files %}
-    {% if static_file.name == 'sql-configs.html' %}
+    {% if static_file.name == 'generated-sql-configuration-table.html' %}
 ### Spark SQL
 
-        {% include_relative sql-configs.html %}
+{% include_relative generated-sql-configuration-table.html %}
         {% break %}
     {% endif %}
 {% endfor %}

docs/sql-ref-functions-builtin.md

@@ -0,0 +1,77 @@
+---
+layout: global
+title: Built-in Functions
+displayTitle: Built-in Functions
+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.
+---
+
+{% for static_file in site.static_files %}
+    {% if static_file.name == 'generated-agg-funcs-table.html' %}
+### Aggregate Functions
+{% include_relative generated-agg-funcs-table.html %}
+#### Examples
+{% include_relative generated-agg-funcs-examples.html %}
+        {% break %}
+    {% endif %}
+{% endfor %}
+
+{% for static_file in site.static_files %}
+    {% if static_file.name == 'generated-window-funcs-table.html' %}
+### Window Functions
+{% include_relative generated-window-funcs-table.html %}
+        {% break %}
+    {% endif %}
+{% endfor %}
+
+{% for static_file in site.static_files %}
+    {% if static_file.name == 'generated-array-funcs-table.html' %}
+### Array Functions
+{% include_relative generated-array-funcs-table.html %}
+#### Examples
+{% include_relative generated-array-funcs-examples.html %}
+        {% break %}
+    {% endif %}
+{% endfor %}
+
+{% for static_file in site.static_files %}
+    {% if static_file.name == 'generated-map-funcs-table.html' %}
+### Map Functions
+{% include_relative generated-map-funcs-table.html %}
+#### Examples
+{% include_relative generated-map-funcs-examples.html %}
+        {% break %}
+    {% endif %}
+{% endfor %}
+
+{% for static_file in site.static_files %}
+    {% if static_file.name == 'generated-datetime-funcs-table.html' %}
+### Date and Timestamp Functions
+{% include_relative generated-datetime-funcs-table.html %}
+#### Examples
+{% include_relative generated-datetime-funcs-examples.html %}
+        {% break %}
+    {% endif %}
+{% endfor %}
+
+{% for static_file in site.static_files %}
+    {% if static_file.name == 'generated-json-funcs-table.html' %}
+### JSON Functions
+{% include_relative generated-json-funcs-table.html %}
+#### Examples
+{% include_relative generated-agg-funcs-examples.html %}
+        {% break %}
+    {% endif %}
+{% endfor %}
+

docs/sql-ref-functions.md

@@ -22,6 +22,18 @@ license: |
 Spark SQL provides two function features to meet a wide range of user needs: built-in functions and user-defined functions (UDFs).
 Built-in functions are commonly used routines that Spark SQL predefines and a complete list of the functions can be found in the [Built-in Functions](api/sql/) API document. UDFs allow users to define their own functions when the system’s built-in functions are not enough to perform the desired task.
 
+### Built-in Functions
+
+Spark SQL has some categories of frequently-used built-in functions for aggregtion, arrays/maps, date/timestamp, and JSON data.
+This subsection presents the usages and descriptions of these functions.
+
+ * [Aggregate Functions](sql-ref-functions-builtin.html#aggregate-functions)
+ * [Window Functions](sql-ref-functions-builtin.html#window-functions)
+ * [Array Functions](sql-ref-functions-builtin.html#array-functions)
+ * [Map Functions](sql-ref-functions-builtin.html#map-functions)
+ * [Date and Timestamp Functions](sql-ref-functions-builtin.html#date-and-timestamp-functions)
+ * [JSON Functions](sql-ref-functions-builtin.html#json-functions)
+
 ### UDFs (User-Defined Functions)
 
 User-Defined Functions (UDFs) are a feature of Spark SQL that allows users to define their own functions when the system's built-in functions are not enough to perform the desired task. To use UDFs in Spark SQL, users must first define the function, then register the function with Spark, and finally call the registered function. The User-Defined Functions can act on a single row or act on multiple rows at once. Spark SQL also supports integration of existing Hive implementations of UDFs, UDAFs and UDTFs.

sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ExpressionDescription.java

@@ -31,21 +31,24 @@
  * `usage()` will be used for the function usage in brief way.
  *
  * These below are concatenated and used for the function usage in verbose way, suppose arguments,
- * examples, note, since and deprecated will be provided.
+ * examples, note, group, since and deprecated will be provided.
  *
  * `arguments()` describes arguments for the expression.
  *
  * `examples()` describes examples for the expression.
  *
  * `note()` contains some notes for the expression optionally.
  *
+ * `group()` describes the category that the expression belongs to. The valid value is
+ * "agg_funcs", "array_funcs", "datetime_funcs", "json_funcs", "map_funcs" and "window_funcs".
+ *
  * `since()` contains version information for the expression. Version is specified by,
  * for example, "2.2.0".
  *
  * `deprecated()` contains deprecation information for the expression optionally, for example,
  * "Deprecated since 2.2.0. Use something else instead".
  *
- * The format, in particular for `arguments()`, `examples()`,`note()`, `since()` and
+ * The format, in particular for `arguments()`, `examples()`,`note()`, `group()`, `since()` and
  * `deprecated()`, should strictly be as follows.
  *
  * <pre>
@@ -68,6 +71,7 @@
  *   note = """
  *     ...
  *   """,
+ *   group = "agg_funcs",
  *   since = "3.0.0",
  *   deprecated = """
  *     ...
@@ -78,8 +82,9 @@
  *  We can refer the function name by `_FUNC_`, in `usage()`, `arguments()` and `examples()` as
  *  it is registered in `FunctionRegistry`.
  *
- *  Note that, if `extended()` is defined, `arguments()`, `examples()`, `note()`, `since()` and
- *  `deprecated()` should be not defined together. `extended()` exists for backward compatibility.
+ *  Note that, if `extended()` is defined, `arguments()`, `examples()`, `note()`, `group()`,
+ *  `since()` and `deprecated()` should be not defined together. `extended()` exists
+ *  for backward compatibility.
  *
  *  Note this contents are used in the SparkSQL documentation for built-in functions. The contents
  *  here are considered as a Markdown text and then rendered.
@@ -98,6 +103,7 @@
     String arguments() default "";
     String examples() default "";
     String note() default "";
+    String group() default "";
     String since() default "";
     String deprecated() default "";
 }

sql/catalyst/src/main/java/org/apache/spark/sql/catalyst/expressions/ExpressionInfo.java

@@ -19,6 +19,10 @@
 
 import com.google.common.annotations.VisibleForTesting;
 
+import java.util.Arrays;
+import java.util.HashSet;
+import java.util.Set;
+
 /**
  * Expression information, will be used to describe a expression.
  */
@@ -31,9 +35,14 @@ public class ExpressionInfo {
     private String arguments;
     private String examples;
     private String note;
+    private String group;
     private String since;
     private String deprecated;
 
+    private static final Set<String> validGroups =
+        new HashSet<>(Arrays.asList("agg_funcs", "array_funcs", "datetime_funcs",
+            "json_funcs", "map_funcs", "window_funcs"));
+
     public String getClassName() {
         return className;
     }
@@ -75,6 +84,10 @@ public String getDeprecated() {
         return deprecated;
     }
 
+    public String getGroup() {
+        return group;
+    }
+
     public String getDb() {
         return db;
     }
@@ -87,13 +100,15 @@ public ExpressionInfo(
             String arguments,
             String examples,
             String note,
+            String group,
             String since,
             String deprecated) {
         assert name != null;
         assert arguments != null;
         assert examples != null;
         assert examples.isEmpty() || examples.contains("    Examples:");
         assert note != null;
+        assert group != null;
         assert since != null;
         assert deprecated != null;
 
@@ -104,6 +119,7 @@ public ExpressionInfo(
         this.arguments = arguments;
         this.examples = examples;
         this.note = note;
+        this.group = group;
         this.since = since;
         this.deprecated = deprecated;
 
@@ -120,6 +136,11 @@ public ExpressionInfo(
             }
             this.extended += "\n    Note:\n      " + note.trim() + "\n";
         }
+        if (!group.isEmpty() && !validGroups.contains(group)) {
+            throw new IllegalArgumentException("'group' is malformed in the expression [" +
+                this.name + "]. It should be a value in " + validGroups + "; however, " +
+                "got [" + group + "].");
+        }
         if (!since.isEmpty()) {
             if (Integer.parseInt(since.split("\\.")[0]) < 0) {
                 throw new IllegalArgumentException("'since' is malformed in the expression [" +
@@ -140,11 +161,11 @@ public ExpressionInfo(
     }
 
     public ExpressionInfo(String className, String name) {
-        this(className, null, name, null, "", "", "", "", "");
+        this(className, null, name, null, "", "", "", "", "", "");
     }
 
     public ExpressionInfo(String className, String db, String name) {
-        this(className, db, name, null, "", "", "", "", "");
+        this(className, db, name, null, "", "", "", "", "", "");
     }
 
     /**
@@ -155,7 +176,7 @@ public ExpressionInfo(String className, String db, String name) {
     public ExpressionInfo(String className, String db, String name, String usage, String extended) {
         // `arguments` and `examples` are concatenated for the extended description. So, here
         // simply pass the `extended` as `arguments` and an empty string for `examples`.
-        this(className, db, name, usage, extended, "", "", "", "");
+        this(className, db, name, usage, extended, "", "", "", "", "");
     }
 
     private String replaceFunctionName(String usage) {

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala

@@ -654,7 +654,7 @@ object FunctionRegistry {
     val clazz = scala.reflect.classTag[Cast].runtimeClass
     val usage = "_FUNC_(expr) - Casts the value `expr` to the target data type `_FUNC_`."
     val expressionInfo =
-      new ExpressionInfo(clazz.getCanonicalName, null, name, usage, "", "", "", "", "")
+      new ExpressionInfo(clazz.getCanonicalName, null, name, usage, "", "", "", "", "", "")
     (name, (expressionInfo, builder))
   }
 
@@ -674,6 +674,7 @@ object FunctionRegistry {
           df.arguments(),
           df.examples(),
           df.note(),
+          df.group(),
           df.since(),
           df.deprecated())
       } else {

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproximatePercentile.scala

@@ -65,6 +65,7 @@ import org.apache.spark.sql.types._
       > SELECT _FUNC_(10.0, 0.5, 100);
        10.0
   """,
+  group = "agg_funcs",
   since = "2.1.0")
 case class ApproximatePercentile(
     child: Expression,

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Average.scala

@@ -32,6 +32,7 @@ import org.apache.spark.sql.types._
       > SELECT _FUNC_(col) FROM VALUES (1), (2), (NULL) AS tab(col);
        1.5
   """,
+  group = "agg_funcs",
   since = "1.0.0")
 case class Average(child: Expression) extends DeclarativeAggregate with ImplicitCastInputTypes {
 

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/CentralMomentAgg.scala

@@ -142,6 +142,7 @@ abstract class CentralMomentAgg(child: Expression)
       > SELECT _FUNC_(col) FROM VALUES (1), (2), (3) AS tab(col);
        0.816496580927726
   """,
+  group = "agg_funcs",
   since = "1.6.0")
 // scalastyle:on line.size.limit
 case class StddevPop(child: Expression) extends CentralMomentAgg(child) {
@@ -164,6 +165,7 @@ case class StddevPop(child: Expression) extends CentralMomentAgg(child) {
       > SELECT _FUNC_(col) FROM VALUES (1), (2), (3) AS tab(col);
        1.0
   """,
+  group = "agg_funcs",
   since = "1.6.0")
 // scalastyle:on line.size.limit
 case class StddevSamp(child: Expression) extends CentralMomentAgg(child) {
@@ -187,6 +189,7 @@ case class StddevSamp(child: Expression) extends CentralMomentAgg(child) {
       > SELECT _FUNC_(col) FROM VALUES (1), (2), (3) AS tab(col);
        0.6666666666666666
   """,
+  group = "agg_funcs",
   since = "1.6.0")
 case class VariancePop(child: Expression) extends CentralMomentAgg(child) {
 
@@ -207,6 +210,7 @@ case class VariancePop(child: Expression) extends CentralMomentAgg(child) {
       > SELECT _FUNC_(col) FROM VALUES (1), (2), (3) AS tab(col);
        1.0
   """,
+  group = "agg_funcs",
   since = "1.6.0")
 case class VarianceSamp(child: Expression) extends CentralMomentAgg(child) {
 
@@ -229,6 +233,7 @@ case class VarianceSamp(child: Expression) extends CentralMomentAgg(child) {
       > SELECT _FUNC_(col) FROM VALUES (-1000), (-100), (10), (20) AS tab(col);
        -1.1135657469022011
   """,
+  group = "agg_funcs",
   since = "1.6.0")
 case class Skewness(child: Expression) extends CentralMomentAgg(child) {
 
@@ -251,6 +256,7 @@ case class Skewness(child: Expression) extends CentralMomentAgg(child) {
       > SELECT _FUNC_(col) FROM VALUES (1), (10), (100), (10), (1) as tab(col);
        0.19432323191699075
   """,
+  group = "agg_funcs",
   since = "1.6.0")
 case class Kurtosis(child: Expression) extends CentralMomentAgg(child) {
 

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Corr.scala

@@ -99,6 +99,7 @@ abstract class PearsonCorrelation(x: Expression, y: Expression)
       > SELECT _FUNC_(c1, c2) FROM VALUES (3, 2), (3, 3), (6, 4) as tab(c1, c2);
        0.8660254037844387
   """,
+  group = "agg_funcs",
   since = "1.6.0")
 // scalastyle:on line.size.limit
 case class Corr(x: Expression, y: Expression)

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Count.scala

@@ -39,6 +39,7 @@ import org.apache.spark.sql.types._
       > SELECT _FUNC_(DISTINCT col) FROM VALUES (NULL), (5), (5), (10) AS tab(col);
        2
   """,
+  group = "agg_funcs",
   since = "1.0.0")
 // scalastyle:on line.size.limit
 case class Count(children: Seq[Expression]) extends DeclarativeAggregate {

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/CountIf.scala

@@ -32,6 +32,7 @@ import org.apache.spark.sql.types.{AbstractDataType, BooleanType, DataType, Long
       > SELECT _FUNC_(col IS NULL) FROM VALUES (NULL), (0), (1), (2), (3) AS tab(col);
        1
   """,
+  group = "agg_funcs",
   since = "3.0.0")
 case class CountIf(predicate: Expression) extends UnevaluableAggregate with ImplicitCastInputTypes {
   override def prettyName: String = "count_if"

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/CountMinSketchAgg.scala

@@ -44,6 +44,7 @@ import org.apache.spark.util.sketch.CountMinSketch
       `CountMinSketch` before usage. Count-min sketch is a probabilistic data structure used for
       cardinality estimation using sub-linear space.
   """,
+  group = "agg_funcs",
   since = "2.2.0")
 case class CountMinSketchAgg(
     child: Expression,