From acff85167db06e34b6d52a73e97e550b423e9561 Mon Sep 17 00:00:00 2001
From: Duncan Beevers <duncan@dweebd.com>
Date: Tue, 7 Jun 2011 16:21:32 -0700
Subject: [PATCH 1/2] Use MySQL enums for hadron_action column to reduce
 necessary storage

---
 lib/large_hadron_migration.rb       | 17 +++++++++--------
 spec/large_hadron_migration_spec.rb |  2 +-
 2 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/lib/large_hadron_migration.rb b/lib/large_hadron_migration.rb
index 9fe97d7b..ac6d68da 100644
--- a/lib/large_hadron_migration.rb
+++ b/lib/large_hadron_migration.rb
@@ -253,8 +253,8 @@ def self.with_master
     end
   end
 
-  def self.clone_table(source, dest, window = 0)
-    execute schema_sql(source, dest, window)
+  def self.clone_table(source, dest, window = 0, add_action_column = false)
+    execute schema_sql(source, dest, window, add_action_column)
   end
 
   def self.common_columns(t1, t2)
@@ -262,11 +262,7 @@ def self.common_columns(t1, t2)
   end
 
   def self.clone_table_for_changes(table, journal_table)
-    clone_table(table, journal_table)
-    execute %Q{
-      alter table %s
-      add column hadron_action varchar(15);
-    } % journal_table
+    clone_table(table, journal_table, 0, true)
   end
 
   def self.rename_tables(tables = {})
@@ -359,12 +355,17 @@ def self.replay_update_changes(table, journal_table, chunk_size = 10000, wait =
   #  behavior with the latter where the auto_increment of the source table
   #  got modified when updating the destination.
   #
-  def self.schema_sql(source, dest, window)
+  def self.schema_sql(source, dest, window, add_action_column = false)
     show_create(source).tap do |schema|
       schema.gsub!(/auto_increment=(\d+)/i) do
         "auto_increment=#{  $1.to_i + window }"
       end
 
+      if add_action_column
+        schema.sub!(/\) ENGINE=InnoDB/,
+          ", hadron_action ENUM('update', 'insert', 'delete') ) ENGINE=InnoDB")
+      end
+
       schema.gsub!('CREATE TABLE `%s`' % source, 'CREATE TABLE `%s`' % dest)
     end
   end
diff --git a/spec/large_hadron_migration_spec.rb b/spec/large_hadron_migration_spec.rb
index 632e43fc..e32e1f01 100644
--- a/spec/large_hadron_migration_spec.rb
+++ b/spec/large_hadron_migration_spec.rb
@@ -99,7 +99,7 @@
   end
 
   it "should create a table for triggered changes" do
-    truthiness_column "triggerme_changes", "hadron_action", "varchar"
+    truthiness_column "triggerme_changes", "hadron_action", "enum"
   end
 
   it "should trigger on insert" do

From 371f41b879e39639e2a18b9d3ce79b3faaaabd77 Mon Sep 17 00:00:00 2001
From: Duncan Beevers <duncan@dweebd.com>
Date: Wed, 8 Jun 2011 14:34:12 -0700
Subject: [PATCH 2/2] Index hadron_action

---
 lib/large_hadron_migration.rb       |  4 ++--
 spec/large_hadron_migration_spec.rb |  1 +
 spec/spec_helper.rb                 | 15 +++++++++++++++
 3 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/lib/large_hadron_migration.rb b/lib/large_hadron_migration.rb
index ac6d68da..519ad9f4 100644
--- a/lib/large_hadron_migration.rb
+++ b/lib/large_hadron_migration.rb
@@ -362,8 +362,8 @@ def self.schema_sql(source, dest, window, add_action_column = false)
       end
 
       if add_action_column
-        schema.sub!(/\) ENGINE=InnoDB/,
-          ", hadron_action ENUM('update', 'insert', 'delete') ) ENGINE=InnoDB")
+        schema.sub!(/\) ENGINE=/,
+          ", hadron_action ENUM('update', 'insert', 'delete'), INDEX hadron_action (hadron_action) USING BTREE) ENGINE=")
       end
 
       schema.gsub!('CREATE TABLE `%s`' % source, 'CREATE TABLE `%s`' % dest)
diff --git a/spec/large_hadron_migration_spec.rb b/spec/large_hadron_migration_spec.rb
index e32e1f01..acec8e6d 100644
--- a/spec/large_hadron_migration_spec.rb
+++ b/spec/large_hadron_migration_spec.rb
@@ -100,6 +100,7 @@
 
   it "should create a table for triggered changes" do
     truthiness_column "triggerme_changes", "hadron_action", "enum"
+    truthiness_index "triggerme_changes", "hadron_action", [ "hadron_action" ], false
   end
 
   it "should trigger on insert" do
diff --git a/spec/spec_helper.rb b/spec/spec_helper.rb
index acf058e9..f9c97b3a 100644
--- a/spec/spec_helper.rb
+++ b/spec/spec_helper.rb
@@ -90,6 +90,21 @@ def truthiness_rows(table_name1, table_name2, offset = 0, limit = 1000)
 
   end
 
+  def truthiness_index(table, expected_index_name, indexed_columns, unique)
+    index = sql("SHOW INDEXES FROM #{table}").all_hashes.inject({}) do |a, part|
+      index_name = part['Key_name']
+      a[index_name] ||= { 'unique' => '0' == part['Non_unique'], 'columns' => [] }
+      column_index = part['Seq_in_index'].to_i - 1
+      a[index_name]['columns'][column_index] = part['Column_name']
+      a
+    end[expected_index_name]
+
+    flunk("no index named #{expected_index_name} found on #{table}") unless index
+
+    index['columns'].should == indexed_columns
+    index['unique'].should == unique
+  end
+
 end
 
 # Mock Rails Environment