HADOOP-8944. Shell command fs -count should include human readable option (Jonathan Allen via aw)

git-svn-id: https://svn.apache.org/repos/asf/hadoop/common/trunk@1617775 13f79535-47bb-0310-9956-ffa450edef68

hadoop-common-project/hadoop-common/CHANGES.txt

@@ -202,6 +202,9 @@ Trunk (Unreleased)
     HADOOP-10224. JavaKeyStoreProvider has to protect against corrupting 
     underlying store. (asuresh via tucu)
 
+    HADOOP-8944. Shell command fs -count should include human readable option
+      (Jonathan Allen via aw)
+
   BUG FIXES
 
     HADOOP-9451. Fault single-layer config if node group topology is enabled.

hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/ContentSummary.java

@@ -24,6 +24,7 @@
 import org.apache.hadoop.classification.InterfaceAudience;
 import org.apache.hadoop.classification.InterfaceStability;
 import org.apache.hadoop.io.Writable;
+import org.apache.hadoop.util.StringUtils;
 
 /** Store the summary of a content (a directory or a file). */
 @InterfaceAudience.Public
@@ -102,7 +103,7 @@ public void readFields(DataInput in) throws IOException {
    * <----12----> <----12----> <-------18------->
    *    DIR_COUNT   FILE_COUNT       CONTENT_SIZE FILE_NAME    
    */
-  private static final String STRING_FORMAT = "%12d %12d %18d ";
+  private static final String STRING_FORMAT = "%12s %12s %18s ";
   /** 
    * Output format:
    * <----12----> <----15----> <----15----> <----15----> <----12----> <----12----> <-------18------->
@@ -117,7 +118,7 @@ public void readFields(DataInput in) throws IOException {
 
   private static final String QUOTA_HEADER = String.format(
       QUOTA_STRING_FORMAT + SPACE_QUOTA_STRING_FORMAT, 
-      "quota", "remaining quota", "space quota", "reamaining quota") +
+      "name quota", "rem name quota", "space quota", "rem space quota") +
       HEADER;
   
   /** Return the header of the output.
@@ -139,11 +140,25 @@ public String toString() {
   /** Return the string representation of the object in the output format.
    * if qOption is false, output directory count, file count, and content size;
    * if qOption is true, output quota and remaining quota as well.
-   * 
+   *
    * @param qOption a flag indicating if quota needs to be printed or not
    * @return the string representation of the object
-   */
+  */
   public String toString(boolean qOption) {
+    return toString(qOption, false);
+  }
+
+  /** Return the string representation of the object in the output format.
+   * if qOption is false, output directory count, file count, and content size;
+   * if qOption is true, output quota and remaining quota as well.
+   * if hOption is false file sizes are returned in bytes
+   * if hOption is true file sizes are returned in human readable 
+   * 
+   * @param qOption a flag indicating if quota needs to be printed or not
+   * @param hOption a flag indicating if human readable output if to be used
+   * @return the string representation of the object
+   */
+  public String toString(boolean qOption, boolean hOption) {
     String prefix = "";
     if (qOption) {
       String quotaStr = "none";
@@ -152,19 +167,32 @@ public String toString(boolean qOption) {
       String spaceQuotaRem = "inf";
       
       if (quota>0) {
-        quotaStr = Long.toString(quota);
+        quotaStr = formatSize(quota, hOption);
-        quotaRem = Long.toString(quota-(directoryCount+fileCount));
+        quotaRem = formatSize(quota-(directoryCount+fileCount), hOption);
       }
       if (spaceQuota>0) {
-        spaceQuotaStr = Long.toString(spaceQuota);
+        spaceQuotaStr = formatSize(spaceQuota, hOption);
-        spaceQuotaRem = Long.toString(spaceQuota - spaceConsumed);        
+        spaceQuotaRem = formatSize(spaceQuota - spaceConsumed, hOption);
       }
       
       prefix = String.format(QUOTA_STRING_FORMAT + SPACE_QUOTA_STRING_FORMAT, 
                              quotaStr, quotaRem, spaceQuotaStr, spaceQuotaRem);
     }
     
-    return prefix + String.format(STRING_FORMAT, directoryCount, 
+    return prefix + String.format(STRING_FORMAT,
-                                  fileCount, length);
+     formatSize(directoryCount, hOption),
+     formatSize(fileCount, hOption),
+     formatSize(length, hOption));
+  }
+  /**
+   * Formats a size to be human readable or in bytes
+   * @param size value to be formatted
+   * @param humanReadable flag indicating human readable or not
+   * @return String representation of the size
+  */
+  private String formatSize(long size, boolean humanReadable) {
+    return humanReadable
+      ? StringUtils.TraditionalBinaryPrefix.long2String(size, "", 1)
+      : String.valueOf(size);
   }
 }

hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/shell/Count.java

@@ -42,16 +42,22 @@ public static void registerCommands(CommandFactory factory) {
     factory.addClass(Count.class, "-count");
   }
 
+  private static final String OPTION_QUOTA = "q";
+  private static final String OPTION_HUMAN = "h";
+
   public static final String NAME = "count";
-  public static final String USAGE = "[-q] <path> ...";
+  public static final String USAGE =
+      "[-" + OPTION_QUOTA + "] [-" + OPTION_HUMAN + "] <path> ...";
   public static final String DESCRIPTION = 
       "Count the number of directories, files and bytes under the paths\n" +
       "that match the specified file pattern.  The output columns are:\n" +
       "DIR_COUNT FILE_COUNT CONTENT_SIZE FILE_NAME or\n" +
       "QUOTA REMAINING_QUOTA SPACE_QUOTA REMAINING_SPACE_QUOTA \n" +
-      "      DIR_COUNT FILE_COUNT CONTENT_SIZE FILE_NAME";
+      "      DIR_COUNT FILE_COUNT CONTENT_SIZE FILE_NAME\n" +
+      "The -h option shows file sizes in human readable format.";
   
   private boolean showQuotas;
+  private boolean humanReadable;
 
   /** Constructor */
   public Count() {}
@@ -70,17 +76,37 @@ public Count(String[] cmd, int pos, Configuration conf) {
 
   @Override
   protected void processOptions(LinkedList<String> args) {
-    CommandFormat cf = new CommandFormat(1, Integer.MAX_VALUE, "q");
+    CommandFormat cf = new CommandFormat(1, Integer.MAX_VALUE,
+      OPTION_QUOTA, OPTION_HUMAN);
     cf.parse(args);
     if (args.isEmpty()) { // default path is the current working directory
       args.add(".");
     }
-    showQuotas = cf.getOpt("q");
+    showQuotas = cf.getOpt(OPTION_QUOTA);
+    humanReadable = cf.getOpt(OPTION_HUMAN);
   }
 
   @Override
   protected void processPath(PathData src) throws IOException {
     ContentSummary summary = src.fs.getContentSummary(src.path);
-    out.println(summary.toString(showQuotas) + src);
+    out.println(summary.toString(showQuotas, isHumanReadable()) + src);
+  }
+  
+  /**
+   * Should quotas get shown as part of the report?
+   * @return if quotas should be shown then true otherwise false
+   */
+  @InterfaceAudience.Private
+  boolean isShowQuotas() {
+    return showQuotas;
+  }
+  
+  /**
+   * Should sizes be shown in human readable format rather than bytes?
+   * @return true if human readable format
+   */
+  @InterfaceAudience.Private
+  boolean isHumanReadable() {
+    return humanReadable;
   }
 }

hadoop-common-project/hadoop-common/src/site/apt/FileSystemShell.apt.vm

@@ -138,7 +138,7 @@ copyToLocal
 
 count
 
-   Usage: <<<hdfs dfs -count [-q] <paths> >>>
+   Usage: <<<hdfs dfs -count [-q] [-h] <paths> >>>
 
    Count the number of directories, files and bytes under the paths that match
    the specified file pattern.  The output columns with -count are: DIR_COUNT,
@@ -147,12 +147,16 @@ count
    The output columns with -count -q are: QUOTA, REMAINING_QUATA, SPACE_QUOTA,
    REMAINING_SPACE_QUOTA, DIR_COUNT, FILE_COUNT, CONTENT_SIZE, FILE_NAME
 
+   The -h option shows sizes in human readable format.
+
    Example:
 
      * <<<hdfs dfs -count hdfs://nn1.example.com/file1 hdfs://nn2.example.com/file2>>>
 
      * <<<hdfs dfs -count -q hdfs://nn1.example.com/file1>>>
 
+     * <<<hdfs dfs -count -q -h hdfs://nn1.example.com/file1>>>
+
    Exit Code:
 
    Returns 0 on success and -1 on error.

hadoop-common-project/hadoop-common/src/test/resources/testConf.xml

@@ -238,7 +238,7 @@
       <comparators>
         <comparator>
           <type>RegexpComparator</type>
-          <expected-output>^-count \[-q\] &lt;path&gt; \.\.\. :\s*</expected-output>
+          <expected-output>^-count \[-q\] \[-h\] &lt;path&gt; \.\.\. :( )*</expected-output>
         </comparator>
         <comparator>
           <type>RegexpComparator</type>
@@ -260,6 +260,10 @@
           <type>RegexpComparator</type>
           <expected-output>^( |\t)*DIR_COUNT FILE_COUNT CONTENT_SIZE FILE_NAME( )*</expected-output>
         </comparator>
+        <comparator>
+          <type>RegexpComparator</type>
+          <expected-output>^( |\t)*The -h option shows file sizes in human readable format.( )*</expected-output>
+        </comparator>
       </comparators>
     </test>
 

hadoop-hdfs-project/hadoop-hdfs/src/test/resources/testHDFSConf.xml

@@ -8655,6 +8655,50 @@
       </comparators>
     </test>
 
+    <test> <!-- TESTED -->
+      <description>count: file using -h option</description>
+      <test-commands>
+        <command>-fs NAMENODE -mkdir -p dir</command> <!-- make sure user home dir exists -->
+        <command>-fs NAMENODE -put CLITEST_DATA/data15bytes file1</command>
+        <command>-fs NAMENODE -put CLITEST_DATA/data1k file2</command>
+        <command>-fs NAMENODE -count -h file1 file2</command>
+      </test-commands>
+      <cleanup-commands>
+        <command>-fs NAMENODE -rm file1 file2</command>
+      </cleanup-commands>
+      <comparators>
+        <comparator>
+          <type>RegexpComparator</type>
+          <expected-output>( |\t)*0( |\t)*1( |\t)*15 file1</expected-output>
+        </comparator>
+      </comparators>
+      <comparators>
+        <comparator>
+          <type>RegexpComparator</type>
+          <expected-output>( |\t)*0( |\t)*1( |\t)*1\.0 K file2</expected-output>
+        </comparator>
+      </comparators>
+    </test>
+
+    <test> <!-- TESTED -->
+      <description>count: directory using -q and -h options</description>
+      <test-commands>
+        <command>-fs NAMENODE -mkdir /dir1</command>
+        <dfs-admin-command>-fs NAMENODE -setQuota 10 /dir1 </dfs-admin-command>
+        <dfs-admin-command>-fs NAMENODE -setSpaceQuota 1m /dir1 </dfs-admin-command>
+        <command>-fs NAMENODE -count -q -h /dir1</command>
+      </test-commands>
+      <cleanup-commands>
+        <command>-fs NAMENODE -rm -r /dir1</command>
+      </cleanup-commands>
+      <comparators>
+        <comparator>
+          <type>RegexpComparator</type>
+          <expected-output>( |\t)*10( |\t)*9( |\t)*1 M( |\t)*1 M( |\t)*1( |\t)*0( |\t)*0 /dir1</expected-output>
+        </comparator>
+      </comparators>
+    </test>
+
     <!-- Tests for chmod -->
     <test> <!-- TESTED -->
       <description>chmod: change permission(octal mode) of file in absolute path</description>