Added CLI enhancement for better maintainability

integration/spark-common-test/src/test/scala/org/apache/carbondata/spark/testsuite/createTable/TestNonTransactionalCarbonTable.scala

@@ -389,6 +389,10 @@ class TestNonTransactionalCarbonTable extends QueryTest with BeforeAndAfterAll {
          |'carbondata' LOCATION
          |'$writerPath' """.stripMargin)
 
+    val output = sql("show summary for table sdkOutputTable options('command'='-cmd,summary,-p,-a,-v,-c,age')").collect()
+
+    assert(output.toList.contains(Row("written_by                       Version         ")))
+
     checkExistence(sql("describe formatted sdkOutputTable"), true, "age,name")
 
     checkExistence(sql("describe formatted sdkOutputTable"), true, writerPath)

integration/spark-common/src/main/scala/org/apache/spark/sql/catalyst/CarbonDDLSqlParser.scala

@@ -188,6 +188,7 @@ abstract class CarbonDDLSqlParser extends AbstractCarbonSparkSQLParser {
   protected val STREAM = carbonKeyWord("STREAM")
   protected val STREAMS = carbonKeyWord("STREAMS")
   protected val STMPROPERTIES = carbonKeyWord("STMPROPERTIES")
+  protected val SUMMARY = carbonKeyWord("SUMMARY")
 
   protected val doubleQuotedString = "\"([^\"]+)\"".r
   protected val singleQuotedString = "'([^']+)'".r
@@ -1141,6 +1142,13 @@ abstract class CarbonDDLSqlParser extends AbstractCarbonSparkSQLParser {
       case _ => ("", "")
     }
 
+  protected lazy val summaryOptions: Parser[(String, String)] =
+    (stringLit <~ "=") ~ stringLit ^^ {
+      case opt ~ optvalue => (opt.trim.toLowerCase(), optvalue)
+      case _ => ("", "")
+    }
+
+
   protected lazy val partitions: Parser[(String, Option[String])] =
     (ident <~ "=".?) ~ stringLit.? ^^ {
       case opt ~ optvalue => (opt.trim, optvalue)

integration/spark2/pom.xml

@@ -40,6 +40,11 @@
       <artifactId>carbondata-spark-common</artifactId>
       <version>${project.version}</version>
     </dependency>
+    <dependency>
+      <groupId>org.apache.carbondata</groupId>
+      <artifactId>carbondata-cli</artifactId>
+      <version>${project.version}</version>
+    </dependency>
     <dependency>
       <groupId>org.apache.carbondata</groupId>
       <artifactId>carbondata-store-sdk</artifactId>

integration/spark2/src/main/scala/org/apache/spark/sql/execution/command/management/CarbonShowSummaryCommand.scala

@@ -0,0 +1,62 @@
+/*
+ * 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.execution.command.management
+
+import java.util
+
+import scala.collection.JavaConverters._
+
+import org.apache.spark.sql.{CarbonEnv, Row, SparkSession}
+import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeReference}
+import org.apache.spark.sql.execution.command.{Checker, DataCommand}
+import org.apache.spark.sql.types.StringType
+
+import org.apache.carbondata.tool.CarbonCli
+
+/**
+ * Show summary command class which is integrated to cli and sql support is provided via this class
+ * @param databaseNameOp
+ * @param tableName
+ * @param commandOptions
+ */
+case class CarbonShowSummaryCommand(
+    databaseNameOp: Option[String],
+    tableName: String,
+    commandOptions: Map[String, String])
+  extends DataCommand {
+
+  override def output: Seq[Attribute] = {
+      Seq(AttributeReference("Table Summary", StringType, nullable = false)())
+  }
+
+  override def processData(sparkSession: SparkSession): Seq[Row] = {
+    Checker.validateTableExists(databaseNameOp, tableName, sparkSession)
+    val carbonTable = CarbonEnv.getCarbonTable(databaseNameOp, tableName)(sparkSession)
+    val commandArgs: Seq[String] = commandOptions("command").split(",")
+    val finalCommands = commandArgs.collect {
+      case a if a.trim.equalsIgnoreCase("-p") =>
+        Seq(a, carbonTable.getTablePath)
+      case x => Seq(x.trim)
+    }.flatten
+    val summaryOutput = new util.ArrayList[String]()
+    CarbonCli.run(finalCommands.toArray, summaryOutput)
+    summaryOutput.asScala.map(x =>
+      Row(x)
+    )
+  }
+}

integration/spark2/src/main/scala/org/apache/spark/sql/parser/CarbonSpark2SqlParser.scala

@@ -78,7 +78,7 @@ class CarbonSpark2SqlParser extends CarbonDDLSqlParser {
 
   protected lazy val startCommand: Parser[LogicalPlan] =
     loadManagement | showLoads | alterTable | restructure | updateTable | deleteRecords |
-    alterPartition | datamapManagement | alterTableFinishStreaming | stream
+    alterPartition | datamapManagement | alterTableFinishStreaming | stream | cli
 
   protected lazy val loadManagement: Parser[LogicalPlan] =
     deleteLoadsByID | deleteLoadsByLoadDate | cleanFiles | loadDataNew
@@ -495,6 +495,23 @@ class CarbonSpark2SqlParser extends CarbonDDLSqlParser {
           showHistory.isDefined)
     }
 
+
+  protected lazy val cli: Parser[LogicalPlan] =
+    (SHOW ~> SUMMARY ~> FOR ~> TABLE) ~> (ident <~ ".").? ~ ident ~
+    (OPTIONS ~> "(" ~> repsep(summaryOptions, ",") <~ ")").? <~
+    opt(";") ^^ {
+      case databaseName ~ tableName ~ commandList =>
+        var commandOptions: Map[String, String] = null
+        if (commandList.isDefined) {
+          commandOptions = commandList.getOrElse(List.empty[(String, String)]).toMap
+        }
+        CarbonShowSummaryCommand(
+          convertDbNameToLowerCase(databaseName),
+          tableName.toLowerCase(),
+          commandOptions.map { case (key, value) => key.toLowerCase -> value })
+    }
+
+
   protected lazy val alterTableModifyDataType: Parser[LogicalPlan] =
     ALTER ~> TABLE ~> (ident <~ ".").? ~ ident ~ CHANGE ~ ident ~ ident ~
     ident ~ opt("(" ~> rep1sep(valueOptions, ",") <~ ")") <~ opt(";") ^^ {

tools/cli/src/main/java/org/apache/carbondata/tool/CarbonCli.java

@@ -19,6 +19,8 @@
 
 import java.io.IOException;
 import java.io.PrintStream;
+import java.util.ArrayList;
+import java.util.List;
 
 import org.apache.carbondata.common.annotations.InterfaceAudience;
 import org.apache.carbondata.common.annotations.InterfaceStability;
@@ -40,6 +42,13 @@
 @InterfaceStability.Unstable
 public class CarbonCli {
 
+  // List to collect all the outputs of option details
+  private static List<String> outPuts;
+
+  // a boolean variable to decide whether to print the output in console or return the list,
+  // by default true, and it will be set to false if the cli is trigerred via sql command
+  private static boolean isPrintInConsole = true;
+
   private static Options buildOptions() {
     Option help = new Option("h", "help", false,"print this message");
     Option path = OptionBuilder.withArgName("path")
@@ -64,7 +73,6 @@ private static Options buildOptions() {
     Option schema = new Option("s", "schema",false, "print the schema");
     Option segment = new Option("m", "showSegment", false, "print segment information");
     Option tblProperties = new Option("t", "tblProperties", false, "print table properties");
-    Option detail = new Option("b", "blocklet", false, "print blocklet size detail");
     Option columnMeta = new Option("k", "columnChunkMeta", false, "print column chunk meta");
     Option columnName = OptionBuilder
         .withArgName("column name")
@@ -73,6 +81,15 @@ private static Options buildOptions() {
         .withLongOpt("column")
         .create("c");
 
+    Option blockletDetail = OptionBuilder.withArgName("limitSize").hasOptionalArg()
+        .withDescription("print blocklet size detail").withLongOpt("limitSize")
+        .create("b");
+
+    Option blockLevelDetail = OptionBuilder.withArgName("blockDetail").hasArg()
+        .withDescription("print block details").withLongOpt("blockDetail")
+        .create("B");
+
+    Option version = new Option("v", "version", false, "print version details of carbondata file");
     Options options = new Options();
     options.addOption(help);
     options.addOption(path);
@@ -82,17 +99,36 @@ private static Options buildOptions() {
     options.addOption(schema);
     options.addOption(segment);
     options.addOption(tblProperties);
-    options.addOption(detail);
+    options.addOption(blockletDetail);
     options.addOption(columnMeta);
     options.addOption(columnName);
+    options.addOption(version);
+    options.addOption(blockLevelDetail);
     return options;
   }
 
   public static void main(String[] args) {
     run(args, System.out);
   }
 
-  static void run(String[] args, PrintStream out) {
+  public static void run(String[] args, ArrayList<String> e) {
+    // this boolean to check whether to print in console or not
+    isPrintInConsole = false;
+    outPuts = e;
+    Options options = buildOptions();
+    CommandLineParser parser = new PosixParser();
+
+    CommandLine line;
+    try {
+      line = parser.parse(options, args);
+    } catch (ParseException exp) {
+      throw new RuntimeException("Parsing failed. Reason: " + exp.getMessage());
+    }
+
+    runCli(System.out, options, line);
+  }
+
+  public static void run(String[] args, PrintStream out) {
     Options options = buildOptions();
     CommandLineParser parser = new PosixParser();
 
@@ -104,6 +140,13 @@ static void run(String[] args, PrintStream out) {
       return;
     }
 
+    runCli(out, options, line);
+  }
+
+  private static void  runCli(PrintStream out, Options options, CommandLine line) {
+    if (outPuts == null) {
+      outPuts = new ArrayList<>();
+    }
     if (line.hasOption("h")) {
       printHelp(options);
       return;
@@ -113,22 +156,28 @@ static void run(String[] args, PrintStream out) {
     if (line.hasOption("p")) {
       path = line.getOptionValue("path");
     }
-    out.println("Input Folder: " + path);
+    outPuts.add("Input Folder: " + path);
 
     String cmd = line.getOptionValue("cmd");
     Command command;
     if (cmd.equalsIgnoreCase("summary")) {
-      command = new DataSummary(path, out);
+      command = new DataSummary(path, outPuts);
     } else if (cmd.equalsIgnoreCase("benchmark")) {
-      command = new ScanBenchmark(path, out);
+      command = new ScanBenchmark(path, outPuts);
     } else {
       out.println("command " + cmd + " is not supported");
+      outPuts.add("command " + cmd + " is not supported");
       printHelp(options);
       return;
     }
 
     try {
       command.run(line);
+      if (isPrintInConsole) {
+        for (String output : outPuts) {
+          out.println(output);
+        }
+      }
       out.flush();
     } catch (IOException | MemoryException e) {
       e.printStackTrace();

tools/cli/src/main/java/org/apache/carbondata/tool/DataFile.java

@@ -317,6 +317,10 @@ class ColumnChunk {
     // min/max stats of this column chunk
     byte[] min, max;
 
+    // to set whether min max is present for the column chunck, as we may not right min max after
+    // specific size
+    boolean isMinMaxPresent;
+
     // percentage of min/max comparing to min/max scope collected in all blocklets
     // they are set after calculation in DataSummary
     double minPercentage, maxPercentage;
@@ -335,6 +339,7 @@ class ColumnChunk {
       this.column = column;
       min = index.min_max_index.min_values.get(columnIndex).array();
       max = index.min_max_index.max_values.get(columnIndex).array();
+      isMinMaxPresent = index.min_max_index.min_max_presence.get(columnIndex);
 
       // read the column chunk metadata: DataChunk3
       ByteBuffer buffer = fileReader.readByteBuffer(