rbhive 0.2.7 → 0.2.8

data/lib/rbhive/schema_definition.rb

@@ -20,7 +20,19 @@ module RBHive
   
     def column_names
       @column_names ||= begin
-        schema_names = @schema.fieldSchemas.map {|c| c.name.to_sym }
+        schema_names = @schema.fieldSchemas.map {|c| c.name }
+        
+        # In rare cases Hive can return two identical column names
+        # consider SELECT a.foo, b.foo...
+        # in this case you get two columns called foo with no disambiguation.
+        # as a (far from ideal) solution we detect this edge case and rename them
+        # a.foo => foo1, b.foo => foo2
+        # otherwise we will trample one of the columns during Hash mapping.
+        s = Hash.new(0)
+        schema_names.map! { |c| s[c] += 1; s[c] > 1 ? "#{c}---|---#{s[c]}" : c }
+        schema_names.map! { |c| s[c] > 1 ? "#{c}---|---1" : c }
+        schema_names.map! { |c| c.gsub('---|---', '_').to_sym }
+        
         # Lets fix the fact that Hive doesn't return schema data for partitions on SELECT * queries
         # For now we will call them :_p1, :_p2, etc. to avoid collisions.
         offset = 0

metadata

@@ -1,47 +1,33 @@
---- !ruby/object:Gem::Specification 
+--- !ruby/object:Gem::Specification
 name: rbhive
-version: !ruby/object:Gem::Version 
-  hash: 25
+version: !ruby/object:Gem::Version
+  version: 0.2.8
   prerelease: 
-  segments: 
-  - 0
-  - 2
-  - 7
-  version: 0.2.7
 platform: ruby
-authors: 
+authors:
 - Forward Internet Group
 autorequire: 
 bindir: bin
 cert_chain: []
-
-date: 2010-12-07 00:00:00 Z
-dependencies: 
-- !ruby/object:Gem::Dependency 
+date: 2010-12-07 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
   name: thrift
-  prerelease: false
-  requirement: &id001 !ruby/object:Gem::Requirement 
+  requirement: &70241606819180 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        hash: 15
-        segments: 
-        - 0
-        - 4
-        - 0
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
         version: 0.4.0
   type: :runtime
-  version_requirements: *id001
+  prerelease: false
+  version_requirements: *70241606819180
 description: Simple lib for executing Hive queries
 email: andy@forward.co.uk
 executables: []
-
 extensions: []
-
 extra_rdoc_files: []
-
-files: 
+files:
 - lib/rbhive.rb
 - lib/rbhive/connection.rb
 - lib/rbhive/table_schema.rb
@@ -65,36 +51,26 @@ files:
 - lib/thrift/thrift_hive_metastore.rb
 homepage: http://github.com/forward/rbhive
 licenses: []
-
 post_install_message: 
 rdoc_options: []
-
-require_paths: 
+require_paths:
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement 
+required_ruby_version: !ruby/object:Gem::Requirement
   none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      hash: 3
-      segments: 
-      - 0
-      version: "0"
-required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      hash: 3
-      segments: 
-      - 0
-      version: "0"
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
 requirements: []
-
 rubyforge_project: 
-rubygems_version: 1.7.2
+rubygems_version: 1.8.11
 signing_key: 
 specification_version: 3
 summary: Simple lib for executing Hive queries
 test_files: []
-