[SPARK-16734][EXAMPLES][SQL] Revise examples of all language bindings

docs/sql-programming-guide.md

@@ -132,7 +132,7 @@ from a Hive table, or from [Spark data sources](#data-sources).
 
 As an example, the following creates a DataFrame based on the content of a JSON file:
 
-{% include_example create_DataFrames r/RSparkSQLExample.R %}
+{% include_example create_df r/RSparkSQLExample.R %}
 
 </div>
 </div>
@@ -180,7 +180,7 @@ In addition to simple column references and expressions, DataFrames also have a
 
 <div data-lang="r"  markdown="1">
 
-{% include_example dataframe_operations r/RSparkSQLExample.R %}
+{% include_example untyped_ops r/RSparkSQLExample.R %}
 
 For a complete list of the types of operations that can be performed on a DataFrame refer to the [API Documentation](api/R/index.html).
 
@@ -214,7 +214,7 @@ The `sql` function on a `SparkSession` enables applications to run SQL queries p
 <div data-lang="r"  markdown="1">
 The `sql` function enables applications to run SQL queries programmatically and returns the result as a `SparkDataFrame`.
 
-{% include_example sql_query r/RSparkSQLExample.R %}
+{% include_example run_sql r/RSparkSQLExample.R %}
 
 </div>
 </div>
@@ -377,7 +377,7 @@ In the simplest form, the default data source (`parquet` unless otherwise config
 
 <div data-lang="r"  markdown="1">
 
-{% include_example source_parquet r/RSparkSQLExample.R %}
+{% include_example generic_load_save_functions r/RSparkSQLExample.R %}
 
 </div>
 </div>
@@ -400,13 +400,11 @@ using this syntax.
 </div>
 
 <div data-lang="python"  markdown="1">
-
 {% include_example manual_load_options python/sql/datasource.py %}
 </div>
-<div data-lang="r"  markdown="1">
-
-{% include_example source_json r/RSparkSQLExample.R %}
 
+<div data-lang="r"  markdown="1">
+{% include_example manual_load_options r/RSparkSQLExample.R %}
 </div>
 </div>
 
@@ -425,13 +423,11 @@ file directly with SQL.
 </div>
 
 <div data-lang="python"  markdown="1">
-
 {% include_example direct_sql python/sql/datasource.py %}
 </div>
 
 <div data-lang="r"  markdown="1">
-
-{% include_example direct_query r/RSparkSQLExample.R %}
+{% include_example direct_sql r/RSparkSQLExample.R %}
 
 </div>
 </div>
@@ -523,7 +519,7 @@ Using the data from the above example:
 
 <div data-lang="r"  markdown="1">
 
-{% include_example load_programmatically r/RSparkSQLExample.R %}
+{% include_example basic_parquet_example r/RSparkSQLExample.R %}
 
 </div>
 
@@ -839,7 +835,7 @@ Note that the file that is offered as _a json file_ is not a typical JSON file.
 line must contain a separate, self-contained valid JSON object. As a consequence,
 a regular multi-line JSON file will most often fail.
 
-{% include_example load_json_file r/RSparkSQLExample.R %}
+{% include_example json_dataset r/RSparkSQLExample.R %}
 
 </div>
 
@@ -925,7 +921,7 @@ You may need to grant write privilege to the user who starts the spark applicati
 When working with Hive one must instantiate `SparkSession` with Hive support. This
 adds support for finding tables in the MetaStore and writing queries using HiveQL.
 
-{% include_example hive_table r/RSparkSQLExample.R %}
+{% include_example spark_hive r/RSparkSQLExample.R %}
 
 </div>
 </div>
@@ -1067,43 +1063,19 @@ the Data Sources API. The following options are supported:
 <div class="codetabs">
 
 <div data-lang="scala"  markdown="1">
-
-{% highlight scala %}
-val jdbcDF = spark.read.format("jdbc").options(
-  Map("url" -> "jdbc:postgresql:dbserver",
-  "dbtable" -> "schema.tablename")).load()
-{% endhighlight %}
-
+{% include_example jdbc_dataset scala/org/apache/spark/examples/sql/SQLDataSourceExample.scala %}
 </div>
 
 <div data-lang="java"  markdown="1">
-
-{% highlight java %}
-
-Map<String, String> options = new HashMap<>();
-options.put("url", "jdbc:postgresql:dbserver");
-options.put("dbtable", "schema.tablename");
-
-Dataset<Row> jdbcDF = spark.read().format("jdbc"). options(options).load();
-{% endhighlight %}
-
-
+{% include_example jdbc_dataset java/org/apache/spark/examples/sql/JavaSQLDataSourceExample.java %}
 </div>
 
 <div data-lang="python"  markdown="1">
-
-{% highlight python %}
-
-df = spark.read.format('jdbc').options(url='jdbc:postgresql:dbserver', dbtable='schema.tablename').load()
-
-{% endhighlight %}
-
+{% include_example jdbc_dataset python/sql/datasource.py %}
 </div>
 
 <div data-lang="r"  markdown="1">
-
-{% include_example jdbc r/RSparkSQLExample.R %}
-
+{% include_example jdbc_dataset r/RSparkSQLExample.R %}
 </div>
 
 <div data-lang="sql"  markdown="1">

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

@@ -25,7 +25,6 @@
 // $example on:basic_parquet_example$
 import org.apache.spark.api.java.function.MapFunction;
 import org.apache.spark.sql.Encoders;
-// import org.apache.spark.sql.Encoders;
 // $example on:schema_merging$
 // $example on:json_dataset$
 import org.apache.spark.sql.Dataset;
@@ -92,14 +91,15 @@ public void setCube(int cube) {
   public static void main(String[] args) {
     SparkSession spark = SparkSession
       .builder()
-      .appName("Java Spark SQL Data Sources Example")
+      .appName("Java Spark SQL data sources example")
       .config("spark.some.config.option", "some-value")
       .getOrCreate();
 
     runBasicDataSourceExample(spark);
     runBasicParquetExample(spark);
     runParquetSchemaMergingExample(spark);
     runJsonDatasetExample(spark);
+    runJdbcDatasetExample(spark);
 
     spark.stop();
   }
@@ -183,10 +183,10 @@ private static void runParquetSchemaMergingExample(SparkSession spark) {
     // The final schema consists of all 3 columns in the Parquet files together
     // with the partitioning column appeared in the partition directory paths
     // root
-    // |-- value: int (nullable = true)
-    // |-- square: int (nullable = true)
-    // |-- cube: int (nullable = true)
-    // |-- key : int (nullable = true)
+    //  |-- value: int (nullable = true)
+    //  |-- square: int (nullable = true)
+    //  |-- cube: int (nullable = true)
+    //  |-- key: int (nullable = true)
     // $example off:schema_merging$
   }
 
@@ -216,4 +216,15 @@ private static void runJsonDatasetExample(SparkSession spark) {
     // $example off:json_dataset$
   }
 
+  private static void runJdbcDatasetExample(SparkSession spark) {
+    // $example on:jdbc_dataset$
+    Dataset<Row> jdbcDF = spark.read()
+      .format("jdbc")
+      .option("url", "jdbc:postgresql:dbserver")
+      .option("dbtable", "schema.tablename")
+      .option("user", "username")
+      .option("password", "password")
+      .load();
+    // $example off:jdbc_dataset$
+  }
 }

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

@@ -88,7 +88,7 @@ public static void main(String[] args) {
     // $example on:init_session$
     SparkSession spark = SparkSession
       .builder()
-      .appName("Java Spark SQL Example")
+      .appName("Java Spark SQL basic example")
       .config("spark.some.config.option", "some-value")
       .getOrCreate();
     // $example off:init_session$

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

@@ -182,7 +182,7 @@ def programmatic_schema_example(spark):
     # $example on:init_session$
     spark = SparkSession \
         .builder \
-        .appName("PythonSQL") \
+        .appName("Python Spark SQL basic example") \
         .config("spark.some.config.option", "some-value") \
         .getOrCreate()
     # $example off:init_session$

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

@@ -92,14 +92,14 @@ def parquet_schema_merging_example(spark):
     # The final schema consists of all 3 columns in the Parquet files together
     # with the partitioning column appeared in the partition directory paths.
     # root
-    # |-- double: long (nullable = true)
-    # |-- single: long (nullable = true)
-    # |-- triple: long (nullable = true)
-    # |-- key: integer (nullable = true)
+    #  |-- double: long (nullable = true)
+    #  |-- single: long (nullable = true)
+    #  |-- triple: long (nullable = true)
+    #  |-- key: integer (nullable = true)
     # $example off:schema_merging$
 
 
-def json_dataset_examplg(spark):
+def json_dataset_example(spark):
     # $example on:json_dataset$
     # spark is from the previous example.
     sc = spark.sparkContext
@@ -112,8 +112,8 @@ def json_dataset_examplg(spark):
     # The inferred schema can be visualized using the printSchema() method
     peopleDF.printSchema()
     # root
-    # |-- age: long (nullable = true)
-    # |-- name: string (nullable = true)
+    #  |-- age: long (nullable = true)
+    #  |-- name: string (nullable = true)
 
     # Creates a temporary view using the DataFrame
     peopleDF.createOrReplaceTempView("people")
@@ -140,15 +140,29 @@ def json_dataset_examplg(spark):
     # +---------------+----+
     # $example off:json_dataset$
 
+
+def jdbc_dataset_example(spark):
+    # $example on:jdbc_dataset$
+    jdbcDF = spark.read \
+        .format("jdbc") \
+        .option("url", "jdbc:postgresql:dbserver") \
+        .option("dbtable", "schema.tablename") \
+        .option("user", "username") \
+        .option("password", "password") \
+        .load()
+    # $example off:jdbc_dataset$
+
+
 if __name__ == "__main__":
     spark = SparkSession \
         .builder \
-        .appName("PythonSQL") \
+        .appName("Python Spark SQL data source example") \
         .getOrCreate()
 
     basic_datasource_example(spark)
     parquet_example(spark)
     parquet_schema_merging_example(spark)
-    json_dataset_examplg(spark)
+    json_dataset_example(spark)
+    jdbc_dataset_example(spark)
 
     spark.stop()

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

@@ -38,7 +38,7 @@
 
     spark = SparkSession \
         .builder \
-        .appName("PythonSQL") \
+        .appName("Python Spark SQL Hive integration example") \
         .config("spark.sql.warehouse.dir", warehouse_location) \
         .enableHiveSupport() \
         .getOrCreate()