From 14a266fb6c5d6d7581b1b98d1aee7abc27555c6f Mon Sep 17 00:00:00 2001
From: larsh <larsh@unknown>
Date: Thu, 8 Dec 2011 23:01:08 +0000
Subject: [PATCH] HBASE-4981 add raw scan support to shell (Lars H)

git-svn-id: https://svn.apache.org/repos/asf/hbase/trunk@1212178 13f79535-47bb-0310-9956-ffa450edef68
---
 src/main/ruby/hbase.rb               |  1 +
 src/main/ruby/hbase/table.rb         | 10 ++++++++--
 src/main/ruby/shell/commands/scan.rb |  7 +++++++
 3 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/src/main/ruby/hbase.rb b/src/main/ruby/hbase.rb
index 460b6c4b623..2a4abcb2ed7 100644
--- a/src/main/ruby/hbase.rb
+++ b/src/main/ruby/hbase.rb
@@ -43,6 +43,7 @@ module HBaseConstants
   STOPROW = "STOPROW"
   STARTROW = "STARTROW"
   ENDROW = STOPROW
+  RAW = "RAW"
   LIMIT = "LIMIT"
   METHOD = "METHOD"
   MAXLENGTH = "MAXLENGTH"
diff --git a/src/main/ruby/hbase/table.rb b/src/main/ruby/hbase/table.rb
index 3341aa46707..6dcf47e697a 100644
--- a/src/main/ruby/hbase/table.rb
+++ b/src/main/ruby/hbase/table.rb
@@ -218,10 +218,11 @@ module Hbase
         startrow = args["STARTROW"] || ''
         stoprow = args["STOPROW"]
         timestamp = args["TIMESTAMP"]
-        columns = args["COLUMNS"] || args["COLUMN"] || get_all_columns
+        columns = args["COLUMNS"] || args["COLUMN"] || []
         cache = args["CACHE_BLOCKS"] || true
         versions = args["VERSIONS"] || 1
         timerange = args[TIMERANGE]
+        raw = args["RAW"] || false
 
         # Normalize column names
         columns = [columns] if columns.class == String
@@ -254,6 +255,7 @@ module Hbase
         scan.setCacheBlocks(cache)
         scan.setMaxVersions(versions) if versions > 1
         scan.setTimeRange(timerange[0], timerange[1]) if timerange
+        scan.setRaw(raw)
       else
         scan = org.apache.hadoop.hbase.client.Scan.new
       end
@@ -335,7 +337,11 @@ module Hbase
         end
       end
 
-      val = "timestamp=#{kv.getTimestamp}, value=#{org.apache.hadoop.hbase.util.Bytes::toStringBinary(kv.getValue)}"
+      if kv.isDelete
+        val = "timestamp=#{kv.getTimestamp}, type=#{org.apache.hadoop.hbase.KeyValue::Type::codeToType(kv.getType)}"
+      else
+        val = "timestamp=#{kv.getTimestamp}, value=#{org.apache.hadoop.hbase.util.Bytes::toStringBinary(kv.getValue)}"
+      end
       (maxlength != -1) ? val[0, maxlength] : val
     end
 
diff --git a/src/main/ruby/shell/commands/scan.rb b/src/main/ruby/shell/commands/scan.rb
index 378bd6c3153..e58aaaceb8e 100644
--- a/src/main/ruby/shell/commands/scan.rb
+++ b/src/main/ruby/shell/commands/scan.rb
@@ -51,6 +51,13 @@ switches block caching for the scanner on (true) or off (false).  By
 default it is enabled.  Examples:
 
   hbase> scan 't1', {COLUMNS => ['c1', 'c2'], CACHE_BLOCKS => false}
+
+Also for experts, there is an advanced option -- RAW -- which instructs the
+scanner to return all cells (including delete markers and uncollected deleted
+cells). This option cannot be combined with requesting specific COLUMNS.
+Disabled by default.  Example:
+
+  hbase> scan 't1', {RAW => true, VERSIONS => 10}
 EOF
       end