HBASE-20282 Clean up tooling docs/help

bin/hbase

@@ -103,6 +103,7 @@ if [ $# = 0 ]; then
   echo "  ltt             Run LoadTestTool"
   echo "  canary          Run the Canary tool"
   echo "  version         Print the version"
+  echo "  regionsplitter  Run RegionSplitter tool"
   echo "  CLASSNAME       Run the class named CLASSNAME"
   exit 1
 fi
@@ -456,6 +457,8 @@ elif [ "$COMMAND" = "canary" ] ; then
   HBASE_OPTS="$HBASE_OPTS $HBASE_CANARY_OPTS"
 elif [ "$COMMAND" = "version" ] ; then
   CLASS='org.apache.hadoop.hbase.util.VersionInfo'
+elif [ "$COMMAND" = "regionsplitter" ] ; then
+  CLASS='org.apache.hadoop.hbase.util.RegionSplitter'
 else
   CLASS=$COMMAND
 fi

hbase-common/src/main/java/org/apache/hadoop/hbase/util/AbstractHBaseTool.java

@@ -137,7 +137,7 @@ public abstract class AbstractHBaseTool implements Tool, Configurable {
       }
       String[] remainingArgs = new String[argsList.size()];
       argsList.toArray(remainingArgs);
-      cmd = new DefaultParser().parse(options, remainingArgs);
+      cmd = newParser().parse(options, remainingArgs);
     } catch (MissingOptionException e) {
       LOG.error(e.getMessage());
       LOG.error("Use -h or --help for usage instructions.");
@@ -160,6 +160,16 @@ public abstract class AbstractHBaseTool implements Tool, Configurable {
     return ret;
   }
 
+  /**
+   * Create the parser to use for parsing and validating the command line. Since commons-cli lacks
+   * the capability to validate arbitrary combination of options, it may be helpful to bake custom
+   * logic into a specialized parser implementation. See LoadTestTool for examples.
+   * @return a new parser specific to the current tool
+   */
+  protected CommandLineParser newParser() {
+    return new DefaultParser();
+  }
+
   private boolean isHelpCommand(String[] args) throws ParseException {
     Options helpOption = new Options().addOption(HELP_OPTION);
     // this parses the command line but doesn't throw an exception on unknown options

hbase-mapreduce/src/test/java/org/apache/hadoop/hbase/util/LoadTestTool.java

@@ -58,7 +58,14 @@ import org.apache.hadoop.hbase.security.access.Permission;
 import org.apache.hadoop.hbase.util.test.LoadTestDataGenerator;
 import org.apache.hadoop.hbase.util.test.LoadTestDataGeneratorWithACL;
 import org.apache.hadoop.util.ToolRunner;
+
+import org.apache.hbase.thirdparty.org.apache.commons.cli.AlreadySelectedException;
 import org.apache.hbase.thirdparty.org.apache.commons.cli.CommandLine;
+import org.apache.hbase.thirdparty.org.apache.commons.cli.CommandLineParser;
+import org.apache.hbase.thirdparty.org.apache.commons.cli.DefaultParser;
+import org.apache.hbase.thirdparty.org.apache.commons.cli.MissingOptionException;
+import org.apache.hbase.thirdparty.org.apache.commons.cli.Options;
+import org.apache.hbase.thirdparty.org.apache.commons.cli.ParseException;
 
 /**
  * A command-line utility that reads, writes, and verifies data. Unlike
@@ -358,6 +365,40 @@ public class LoadTestTool extends AbstractHBaseTool {
     addOptWithArg(OPT_MOB_THRESHOLD, OPT_MOB_THRESHOLD_USAGE);
   }
 
+  @Override
+  protected CommandLineParser newParser() {
+    // Commons-CLI lacks the capability to handle combinations of options, so we do it ourselves
+    // Validate in parse() to get helpful error messages instead of exploding in processOptions()
+    return new DefaultParser() {
+      @Override
+      public CommandLine parse(Options opts, String[] args, Properties props, boolean stop)
+          throws ParseException {
+        CommandLine cl = super.parse(opts, args, props, stop);
+
+        boolean isReadWriteUpdate = cmd.hasOption(OPT_READ)
+            || cmd.hasOption(OPT_WRITE)
+            || cmd.hasOption(OPT_UPDATE);
+        boolean isInitOnly = cmd.hasOption(OPT_INIT_ONLY);
+
+        if (!isInitOnly && !isReadWriteUpdate) {
+          throw new MissingOptionException("Must specify either -" + OPT_INIT_ONLY
+              + " or at least one of -" + OPT_READ + ", -" + OPT_WRITE + ", -" + OPT_UPDATE);
+        }
+
+        if (isInitOnly && isReadWriteUpdate) {
+          throw new AlreadySelectedException(OPT_INIT_ONLY + " cannot be specified with any of -"
+              + OPT_READ + ", -" + OPT_WRITE + ", -" + OPT_UPDATE);
+        }
+
+        if (isReadWriteUpdate && !cmd.hasOption(OPT_NUM_KEYS)) {
+          throw new MissingOptionException(OPT_NUM_KEYS + " must be specified in read/write mode.");
+        }
+
+        return cl;
+      }
+    };
+  }
+
   @Override
   protected void processOptions(CommandLine cmd) {
     this.cmd = cmd;
@@ -381,21 +422,7 @@ public class LoadTestTool extends AbstractHBaseTool {
     isInitOnly = cmd.hasOption(OPT_INIT_ONLY);
     deferredLogFlush = cmd.hasOption(OPT_DEFERRED_LOG_FLUSH);
 
-    if (!isWrite && !isRead && !isUpdate && !isInitOnly) {
-      throw new IllegalArgumentException("Either -" + OPT_WRITE + " or " +
-        "-" + OPT_UPDATE + " or -" + OPT_READ + " has to be specified");
-    }
-
-    if (isInitOnly && (isRead || isWrite || isUpdate)) {
-      throw new IllegalArgumentException(OPT_INIT_ONLY + " cannot be specified with"
-          + " either -" + OPT_WRITE + " or -" + OPT_UPDATE + " or -" + OPT_READ);
-    }
-
     if (!isInitOnly) {
-      if (!cmd.hasOption(OPT_NUM_KEYS)) {
-        throw new IllegalArgumentException(OPT_NUM_KEYS + " must be specified in "
-            + "read or write mode");
-      }
       startKey = parseLong(cmd.getOptionValue(OPT_START_KEY,
           String.valueOf(DEFAULT_START_KEY)), 0, Long.MAX_VALUE);
       long numKeys = parseLong(cmd.getOptionValue(OPT_NUM_KEYS), 1,

hbase-server/src/main/java/org/apache/hadoop/hbase/tool/Canary.java

@@ -837,9 +837,8 @@ public final class Canary implements Tool {
   }
 
   private void printUsageAndExit() {
-    System.err.printf(
+    System.err.println(
-      "Usage: hbase %s [opts] [table1 [table2]...] | [regionserver1 [regionserver2]..]%n",
+      "Usage: hbase canary [opts] [table1 [table2]...] | [regionserver1 [regionserver2]..]");
-        getClass().getName());
     System.err.println(" where [opts] are:");
     System.err.println("   -help          Show this help and exit.");
     System.err.println("   -regionserver  replace the table argument to regionserver,");

hbase-server/src/main/java/org/apache/hadoop/hbase/util/RegionSplitter.java

@@ -331,7 +331,7 @@ public class RegionSplitter {
     opt.addOption(null, "lastrow", true,
         "Last Row in Table for Split Algorithm");
     opt.addOption(null, "risky", false,
-        "Skip verification steps to complete quickly."
+        "Skip verification steps to complete quickly. "
             + "STRONGLY DISCOURAGED for production systems.  ");
     CommandLine cmd = new GnuParser().parse(opt, args);
 
@@ -356,8 +356,8 @@ public class RegionSplitter {
     boolean oneOperOnly = createTable ^ rollingSplit;
 
     if (2 != cmd.getArgList().size() || !oneOperOnly || cmd.hasOption("h")) {
-      new HelpFormatter().printHelp("RegionSplitter <TABLE> <SPLITALGORITHM>\n"+
+      new HelpFormatter().printHelp("bin/hbase regionsplitter <TABLE> <SPLITALGORITHM>\n"+
-          "SPLITALGORITHM is a java class name of a class implementing " +
+          "SPLITALGORITHM is the java class name of a class implementing " +
           "SplitAlgorithm, or one of the special strings HexStringSplit or " +
           "DecimalStringSplit or UniformSplit, which are built-in split algorithms. " +
           "HexStringSplit treats keys as hexadecimal ASCII, and " +

src/main/asciidoc/_chapters/ops_mgt.adoc

@@ -68,6 +68,7 @@ Some commands take arguments. Pass no args or -h for usage.
   pe              Run PerformanceEvaluation
   ltt             Run LoadTestTool
   canary          Run the Canary tool
+  regionsplitter  Run the RegionSplitter tool
   version         Print the version
   CLASSNAME       Run the class named CLASSNAME
 ----
@@ -83,7 +84,7 @@ To see the usage, use the `--help` parameter.
 ----
 $ ${HBASE_HOME}/bin/hbase canary -help
 
-Usage: hbase org.apache.hadoop.hbase.tool.Canary [opts] [table1 [table2]...] | [regionserver1 [regionserver2]..]
+Usage: hbase canary [opts] [table1 [table2]...] | [regionserver1 [regionserver2]..]
  where [opts] are:
    -help          Show this help and exit.
    -regionserver  replace the table argument to regionserver,
@@ -276,6 +277,35 @@ property>
 ----
 ====
 
+=== RegionSplitter
+
+----
+usage: bin/hbase regionsplitter <TABLE> <SPLITALGORITHM>
+SPLITALGORITHM is the java class name of a class implementing
+                      SplitAlgorithm, or one of the special strings
+                      HexStringSplit or DecimalStringSplit or
+                      UniformSplit, which are built-in split algorithms.
+                      HexStringSplit treats keys as hexadecimal ASCII, and
+                      DecimalStringSplit treats keys as decimal ASCII, and
+                      UniformSplit treats keys as arbitrary bytes.
+ -c <region count>        Create a new table with a pre-split number of
+                          regions
+ -D <property=value>      Override HBase Configuration Settings
+ -f <family:family:...>   Column Families to create with new table.
+                          Required with -c
+    --firstrow <arg>      First Row in Table for Split Algorithm
+ -h                       Print this usage help
+    --lastrow <arg>       Last Row in Table for Split Algorithm
+ -o <count>               Max outstanding splits that have unfinished
+                          major compactions
+ -r                       Perform a rolling split of an existing region
+    --risky               Skip verification steps to complete
+                          quickly. STRONGLY DISCOURAGED for production
+                          systems.
+----
+
+For additional detail, see <<manual_region_splitting_decisions>>.
+
 [[health.check]]
 === Health Checker
 
@@ -758,7 +788,7 @@ The PerformanceEvaluation tool has received many updates in recent HBase release
 
 The `hbase ltt` command runs the LoadTestTool utility, which is used for testing.
 
-You must specify one of `-write`, `-update`, or `-read` as the first option.
+You must specify either `-init_only` or at least one of `-write`, `-update`, or `-read`.
 For general usage instructions, pass the `-h` option.
 
 The LoadTestTool has received many updates in recent HBase releases, including support for namespaces, support for tags, cell-level ACLS and visibility labels, testing security-related features, ability to specify the number of regions per server, tests for multi-get RPC calls, and tests relating to replication.