data_resurrection 0.1.3 → 0.2.0

data/README.rdoc

@@ -28,11 +28,16 @@ In some cases, field types in original tables are not compatible with ones in th
 
     @data_resurrection.resurrect(@dbf_file_path, :target => 'nationality',
       :from => ['WINDOWS-1252', 'CP850'], :to => 'UTF-8',
-      :field_types => {:nr => :string })
+      :field_types => {:nr => :string },
+      :replacement => { '╟' => 'Ã' })
 
 The option :field_types is a hash in which each key is the field name and the value is the field type in the target table.
 
-If a field name equals to SQL reserved words or core Ruby methods like "class", the field name are appended with an underscore in the new table.
+The option :replacement allows defining arbitrary character replacement, *after*
+running all encodings. In the example, all existing weird "╟" in all strings
+will be replaced by "Ã".
+
+If a field name equals to SQL reserved words or core Ruby methods like "class", the field name is appended with an underscore in the new table.
 
 
 == But gem dbf does this work!

data/lib/data_resurrection.rb

@@ -1,4 +1,6 @@
 require 'active_record'
-data_resurrection_folder = File.join(File.dirname(__FILE__), 'data_resurrection', '*.rb')
-Dir.glob(data_resurrection_folder).each {|f| require f }
 
+module DataResurrection
+  autoload :Resuscitator, 'data_resurrection/resuscitator'
+  autoload :Adapter, 'data_resurrection/adapter'
+end

data/lib/data_resurrection/adapter.rb

@@ -0,0 +1,8 @@
+# coding: utf-8
+
+module DataResurrection
+  module Adapter
+  end
+end
+
+Dir.glob(File.dirname(__FILE__) + '/adapter/*.rb') {|f| require f }

data/lib/data_resurrection/{adapters.rb → adapter/dbf.rb}

@@ -4,7 +4,7 @@ require 'dbf'
 require 'iconv'
 
 module DataResurrection
-  module Adapters
+  module Adapter
     module DBF
       def resurrect(origin_table, options)
         target_table_name = options[:target]
@@ -12,14 +12,15 @@ module DataResurrection
         field_types = options[:field_types]
         table = ::DBF::Table.new(origin_table)
         encodings = from.present? ? {from: from, to: to} : nil
-        data = get_data(table, encodings, reserved_words)
+        data = get_data(table, encodings, reserved_words, options[:replacement])
         create_table(table, target_table_name, data, field_types)
         copy_data(target_table_name, data)
       end
 
-      def get_data(table, encodings=nil, reserved_words=[])
+      def get_data(table, encodings=nil, reserved_words=[], replacement = {})
         result = get_raw_data(table, reserved_words)
         result = handle_encodings(result, encodings) if encodings.present?
+        result = apply_replacements(result, replacement) if replacement
         result
       end
 
@@ -76,6 +77,18 @@ module DataResurrection
         end
       end
 
+      def apply_replacements(data, replacements)
+        data.each do |record|
+          record.each do |k, v|
+            replacements.each do |source, target|
+              if v.kind_of? String
+                record[k] = v.gsub(source, target) if v.include?(source)
+              end
+            end
+          end
+        end
+      end
+
       def mark_name_clashed_fields(schema, field_names)
         field_names.each do |field|
           if !schema.include?('column "%s"' % field)
@@ -116,6 +129,11 @@ module DataResurrection
         reserved_words.include?(field_name.upcase) ? "#{field_name}_" : field_name
       end
 
+      def reserved_words
+        @reserved_words ||= File.read(File.expand_path(File.join(File.dirname(__FILE__), 'dbf_reserved_words'))).
+          each_line.map(&:chomp)
+    end
+
       class ARObject < ActiveRecord::Base
       end
 
@@ -126,5 +144,4 @@ module DataResurrection
       VALID_CHARS = [REGULAR_LETTERS, DIGITS, ACCENTED_LETTERS, SYMBOLS].join
     end
   end
-end
-
+end

data/lib/data_resurrection/resuscitator.rb

@@ -0,0 +1,19 @@
+module DataResurrection
+  class Resuscitator
+    def initialize(adapter_key, active_record_settings)
+      extend find_adapter(adapter_key)
+      ActiveRecord::Base.establish_connection(active_record_settings)
+      @connection = ActiveRecord::Base.connection
+    end
+
+    private
+
+    def find_adapter(adapter_key)
+      adapter = DataResurrection::Adapter
+      adapter.const_get(adapter.constants.
+        select {|const_name| adapter.const_get(const_name).is_a? Module }.
+        find {|a| a.to_s.underscore.to_sym == adapter_key })
+    end
+  end
+end
+

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: data_resurrection
 version: !ruby/object:Gem::Version
-  version: 0.1.3
+  version: 0.2.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-09-21 00:00:00.000000000 Z
+date: 2013-04-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activerecord
@@ -81,12 +81,13 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- lib/data_resurrection/adapters.rb
-- lib/data_resurrection/resurrector.rb
+- lib/data_resurrection/adapter.rb
+- lib/data_resurrection/resuscitator.rb
+- lib/data_resurrection/adapter/dbf.rb
 - lib/data_resurrection.rb
 - README.rdoc
 - LICENSE.txt
-- lib/data_resurrection/reserved_words
+- lib/data_resurrection/adapter/dbf_reserved_words
 homepage: https://github.com/rodrigomanhaes/data_resurrection
 licenses: []
 post_install_message: 
@@ -108,7 +109,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.24
+rubygems_version: 1.8.23
 signing_key: 
 specification_version: 3
 summary: Bring your data, buried in decrepit formats, back to life! Convert data from

data/lib/data_resurrection/resurrector.rb

@@ -1,21 +0,0 @@
-module DataResurrection
-  class Resuscitator
-    def initialize(adapter, active_record_settings)
-      extend adapters[adapter]
-      ActiveRecord::Base.establish_connection(active_record_settings)
-      @connection = ActiveRecord::Base.connection
-    end
-
-    private
-
-    def adapters
-      @adapters ||= {:dbf => DataResurrection::Adapters::DBF }
-    end
-
-    def reserved_words
-      @reserved_words ||= File.read(File.expand_path(File.join(File.dirname(__FILE__), 'reserved_words'))).
-        each_line.map(&:chomp)
-    end
-  end
-end
-