[SPARK-25656][SQL][DOC][EXAMPLE][BRANCH-2.4] Add a doc and examples about extra data source options

## What changes were proposed in this pull request?

Our current doc does not explain how we are passing the data source specific options to the underlying data source. According to [the review comment](#22622 (comment)), this PR aims to add more detailed information and examples. This is a backport of #22801. `orc.column.encoding.direct` is removed since it's not supported in ORC 1.5.2.

## How was this patch tested?

Manual.

Closes #22839 from dongjoon-hyun/SPARK-25656-2.4.

Authored-by: Dongjoon Hyun <[email protected]>
Signed-off-by: Dongjoon Hyun <[email protected]>

Author: dongjoon-hyun

docs/sql-data-sources-load-save-functions.md

@@ -82,6 +82,49 @@ To load a CSV file you can use:
 </div>
 </div>
 
+The extra options are also used during write operation.
+For example, you can control bloom filters and dictionary encodings for ORC data sources.
+The following ORC example will create bloom filter on `favorite_color` and use dictionary encoding for `name` and `favorite_color`.
+For Parquet, there exists `parquet.enable.dictionary`, too.
+To find more detailed information about the extra ORC/Parquet options,
+visit the official Apache ORC/Parquet websites.
+
+<div class="codetabs">
+
+<div data-lang="scala"  markdown="1">
+{% include_example manual_save_options_orc scala/org/apache/spark/examples/sql/SQLDataSourceExample.scala %}
+</div>
+
+<div data-lang="java"  markdown="1">
+{% include_example manual_save_options_orc java/org/apache/spark/examples/sql/JavaSQLDataSourceExample.java %}
+</div>
+
+<div data-lang="python"  markdown="1">
+{% include_example manual_save_options_orc python/sql/datasource.py %}
+</div>
+
+<div data-lang="r"  markdown="1">
+{% include_example manual_save_options_orc r/RSparkSQLExample.R %}
+</div>
+
+<div data-lang="sql"  markdown="1">
+
+{% highlight sql %}
+CREATE TABLE users_with_options (
+  name STRING,
+  favorite_color STRING,
+  favorite_numbers array<integer>
+) USING ORC
+OPTIONS (
+  orc.bloom.filter.columns 'favorite_color',
+  orc.dictionary.key.threshold '1.0'
+)
+{% endhighlight %}
+
+</div>
+
+</div>
+
 ### Run SQL on files directly
 
 Instead of using read API to load a file into DataFrame and query it, you can also query that

examples/src/main/java/org/apache/spark/examples/sql/JavaSQLDataSourceExample.java

@@ -123,6 +123,12 @@ private static void runBasicDataSourceExample(SparkSession spark) {
       .option("header", "true")
       .load("examples/src/main/resources/people.csv");
     // $example off:manual_load_options_csv$
+    // $example on:manual_save_options_orc$
+    usersDF.write().format("orc")
+      .option("orc.bloom.filter.columns", "favorite_color")
+      .option("orc.dictionary.key.threshold", "1.0")
+      .save("users_with_options.orc");
+    // $example off:manual_save_options_orc$
     // $example on:direct_sql$
     Dataset<Row> sqlDF =
       spark.sql("SELECT * FROM parquet.`examples/src/main/resources/users.parquet`");

examples/src/main/python/sql/datasource.py

@@ -57,6 +57,14 @@ def basic_datasource_example(spark):
                          format="csv", sep=":", inferSchema="true", header="true")
     # $example off:manual_load_options_csv$
 
+    # $example on:manual_save_options_orc$
+    df = spark.read.orc("examples/src/main/resources/users.orc")
+    (df.write.format("orc")
+        .option("orc.bloom.filter.columns", "favorite_color")
+        .option("orc.dictionary.key.threshold", "1.0")
+        .save("users_with_options.orc"))
+    # $example off:manual_save_options_orc$
+
     # $example on:write_sorting_and_bucketing$
     df.write.bucketBy(42, "name").sortBy("age").saveAsTable("people_bucketed")
     # $example off:write_sorting_and_bucketing$

examples/src/main/r/RSparkSQLExample.R

@@ -114,10 +114,14 @@ write.df(namesAndAges, "namesAndAges.parquet", "parquet")
 
 
 # $example on:manual_load_options_csv$
-df <- read.df("examples/src/main/resources/people.csv", "csv", sep=";", inferSchema=T, header=T)
+df <- read.df("examples/src/main/resources/people.csv", "csv", sep = ";", inferSchema = TRUE, header = TRUE)
 namesAndAges <- select(df, "name", "age")
 # $example off:manual_load_options_csv$
 
+# $example on:manual_save_options_orc$
+df <- read.df("examples/src/main/resources/users.orc", "orc")
+write.orc(df, "users_with_options.orc", orc.bloom.filter.columns = "favorite_color", orc.dictionary.key.threshold = 1.0)
+# $example off:manual_save_options_orc$
 
 # $example on:direct_sql$
 df <- sql("SELECT * FROM parquet.`examples/src/main/resources/users.parquet`")

examples/src/main/resources/users.orc

@@ -56,6 +56,12 @@ object SQLDataSourceExample {
       .option("header", "true")
       .load("examples/src/main/resources/people.csv")
     // $example off:manual_load_options_csv$
+    // $example on:manual_save_options_orc$
+    usersDF.write.format("orc")
+      .option("orc.bloom.filter.columns", "favorite_color")
+      .option("orc.dictionary.key.threshold", "1.0")
+      .save("users_with_options.orc")
+    // $example off:manual_save_options_orc$
 
     // $example on:direct_sql$
     val sqlDF = spark.sql("SELECT * FROM parquet.`examples/src/main/resources/users.parquet`")