toku 0.1.0.4.1 → 0.1.0.4.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 1333d67e1c83413fa3f553e9497e19ab9ccdacd4
-  data.tar.gz: 7f1b6a614639e5885ce2e682045824d101be60d3
+  metadata.gz: 25837d845a4963a5f5cafaa77a28acfdfd0b1080
+  data.tar.gz: 0a5eed937d7ebf8289cf71a86edc92e349a5059a
 SHA512:
-  metadata.gz: dafea67269e244cd83d02f403578b6d52ab6c46cb915adcc542bb31757dde94be1ae8b9a1341aa54469674fd3f06d8620b82171bbad1deeade4fd97bf81cfb45
-  data.tar.gz: 02e452d1cc15793ed3b000fa7b550860e781d8501e6b6e36d8c5f8c97c031fe37a8fc47540d348635b9e21e3e0b4d8c2a409015e39057e32ecd584df9e281166
+  metadata.gz: b66bc251a30364fe0d876130271503f4daa7819d8eb7d693cf89926474aae6ab990fad0ac445a970cbdb1ccff69238133a0f7c957585c7bc4e696d180cb5fbf6
+  data.tar.gz: b2b95c8a083fe1cfb44d963a49b4d0763397f37b286098f8294502a3198996b028be87148d17823857f44df374ad68567990666798ca4e4d308564775b60a7d7

data/README.md

@@ -34,10 +34,31 @@ Users can define custom filters by implementing a `Toku::ColumnFilter` subclass
 
 ```ruby
 module Toku
-  class NewFilter < Toku::ColumnFilter
+  class ColumnFilter
+    # @param value [Object] initial value for the column
+    # @param options [Hash{String => Object}] arguments passed to the filter
     def initialize(value, options)
+      @value = value
     end
 
+    def call
+      @value
+    end
+  end
+end
+```
+
+or a `Toku::RowFilter` like so:
+
+```ruby
+module Toku
+  class RowFilter
+    # @param options [Hash{String => Object}] arguments passed to the filter
+    def initialize(options)
+    end
+
+    # @param [LazyEnumerator] stream
+    # @return [LazyEnumerator] stream
     def call(_)
       _
     end

data/lib/toku.rb

@@ -1,9 +1,10 @@
 require "toku/version"
+require "uri"
+
 Dir[File.dirname(__FILE__) + "/toku/**/*.rb"].each { |file| require file }
 
 module Toku
   class Anonymizer
-
     attr_accessor :column_filters
     attr_accessor :row_filters
 
@@ -20,31 +21,37 @@ module Toku
       drop: Toku::RowFilter::Drop
     }
 
+    SCHEMA_DUMP_PATH = "/tmp/toku_source_schema_dump.sql"
+
     # @param [String] config_file_path path of config file
     def initialize(config_file_path, column_filters = {}, row_filters = {})
       @config = YAML.load(File.read(config_file_path))
       self.column_filters = column_filters.merge(COLUMN_FILTER_MAP)
       self.row_filters = row_filters.merge(ROW_FILTER_MAP)
+      Sequel::Database.extension(:pg_streaming)
     end
 
-    # @param [String] uri_db_source URI of the DB to be anonimized
-    # @param [String] uri_db_destination URI of the destination DB
+    # @param uri_db_source [String] uri_db_source URI of the DB to be anonimized
+    # @param uri_db_destination [String] URI of the destination DB
     # @return [void]
     def run(uri_db_source, uri_db_destination)
-
       source_db = Sequel.connect(uri_db_source)
+      dump_schema(URI(uri_db_source).path.tr("/", ""))
+      parsed_destination_uri = URI(uri_db_destination)
+      destination_db_name = parsed_destination_uri.path.tr("/", "")
+      destination_host = Sequel.connect("postgres://#{parsed_destination_uri.user}@#{parsed_destination_uri.host}:#{parsed_destination_uri.port}/template1")
+      destination_host.run("DROP DATABASE IF EXISTS #{destination_db_name}")
+      destination_host.run("CREATE DATABASE #{destination_db_name}")
       destination_db = Sequel.connect(uri_db_destination)
+      destination_db.run(File.read(SCHEMA_DUMP_PATH))
 
       raise Toku::SchemaMismatchError unless source_schema_included?(source_db, destination_db)
 
-      source_db.extension(:pg_streaming)
-
       source_db.tables.each do |table|
         if !row_filters?(table) && @config[table.to_s]['columns'].count < source_db.from(table).columns.count
           raise Toku::ColumnFilterMissingError
         end
         row_enumerator = source_db[table].stream.lazy
-        destination_db[table].truncate
 
         @config[table.to_s]['rows'].each do |f|
           if f.is_a? String
@@ -61,11 +68,15 @@ module Toku
         count = destination_db[table].count
         puts "Toku: copied #{count} objects into #{table} #{count != 0 ? ':)' : ':|'}"
       end
+
+      source_db.disconnect
+      destination_db.disconnect
+      FileUtils.rm(SCHEMA_DUMP_PATH)
       nil
     end
 
-    # @param [Symbol] name
-    # @param [Hash] row
+    # @param name [Symbol]
+    # @param row [Hash]
     # @return [String]
     def transform(row, name)
       row.map do |k, v|
@@ -92,6 +103,10 @@ module Toku
       end
     end
 
+    def dump_schema(db_name)
+      raise "Dump failed" unless system("pg_dump", "-s", "-x", "-O", "-f", SCHEMA_DUMP_PATH, "#{db_name}")
+    end
+
     # Are there row filters specified for this table?
     # @param table [Symbol]
     # @return [Boolean]

data/lib/toku/version.rb

@@ -1,3 +1,3 @@
 module Toku
-  VERSION = "0.1.0.4.1"
+  VERSION = "0.1.0.4.2"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: toku
 version: !ruby/object:Gem::Version
-  version: 0.1.0.4.1
+  version: 0.1.0.4.2
 platform: ruby
 authors:
 - PSKL
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2018-01-08 00:00:00.000000000 Z
+date: 2018-02-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler