data_taster 0.4.1 → 0.5.0

data/lib/data_taster.rb

@@ -5,13 +5,23 @@ require "logger"
 module DataTaster
   autoload :Collection, "data_taster/collection"
   autoload :Confection, "data_taster/confection"
+  autoload :DatabaseOutput, "data_taster/adapters/database_output"
   autoload :Detergent, "data_taster/detergent"
+  autoload :ExportContext, "data_taster/export_context"
+  autoload :FileOutput, "data_taster/adapters/file_output"
   autoload :Helper, "data_taster/helper"
-  autoload :Sample, "data_taster/sample"
+  autoload :MysqlSource, "data_taster/adapters/mysql_source"
+  autoload :Output, "data_taster/adapters/output"
+  autoload :SanitizerExporter, "data_taster/sanitizer_exporter"
   autoload :Sanitizer, "data_taster/sanitizer"
+  autoload :SqlLiteral, "data_taster/sql_literal"
 
   SKIP_CODE = "skip_processing"
 
+  class << self
+    attr_accessor :config
+  end
+
   def self.logger=(logger)
     @logger = logger
   end
@@ -20,13 +30,18 @@ module DataTaster
     @logger ||= Logger.new($stdout)
   end
 
-  def self.config(**args)
-    @config ||= Config.new(
-      args[:months],
-      Array.wrap(args[:list] || Rails.root.glob("**/data_taster_export_tables.yml")),
-      args[:source_client] || raise(ArgumentError, "DataTaster.config missing source_client"),
-      args[:working_client] || raise(ArgumentError, "DataTaster.config missing working_client"),
-      args[:include_insert] || false
+  def self.reset!
+    # TODO: Turn this into objects
+    self.config = nil
+    @confection = nil
+  end
+
+  def self.setup(source:, output:, months: nil, list: nil)
+    self.config = Config.new(
+      source,
+      output,
+      months,
+      Array.wrap(list || default_list)
     )
   end
 
@@ -35,25 +50,16 @@ module DataTaster
   end
 
   def self.sample!
-    DataTaster
-      .config
-      .source_client
-      .query("SHOW tables").collect { |t| t[t.keys.first] }
-      .each do |table_name|
-        DataTaster::Sample.new(table_name).serve!
-      end
-  end
-
-  def self.safe_execute(sql, client = DataTaster.config.working_client)
-    foreign_key_check = client.query("SELECT @@FOREIGN_KEY_CHECKS").first["@@FOREIGN_KEY_CHECKS"]
-
-    begin
-      client.query("SET FOREIGN_KEY_CHECKS=0")
-      client.query(sql)
-    ensure
-      client.query("SET FOREIGN_KEY_CHECKS=#{foreign_key_check};")
+    config.output.sample!
+  end
+
+  def self.default_list
+    if defined?(Rails) && Rails.respond_to?(:root)
+      Rails.root.glob("**/data_taster_export_tables.yml")
+    else
+      []
     end
   end
 
-  Config = Struct.new(:months, :list, :source_client, :working_client, :include_insert)
+  Config = Struct.new(:source, :output, :months, :list)
 end

data/sig/data_taster.rbs

@@ -1,4 +1,69 @@
 module DataTaster
   VERSION: String
-  # See the writing guide of rbs: https://github.com/ruby/rbs#guides
+  SKIP_CODE: String
+
+  type export_mode = :file | :database
+
+  def self.setup: (source: MysqlSource, output: Output, ?months: Integer?, ?list: Array[String]?) -> void
+  def self.config: () -> Config
+  def self.config=: (Config?) -> void
+  def self.sample!: () -> void
+  def self.reset!: () -> void
+  def self.confection: () -> Hash[String, untyped]
+  def self.logger: () -> ::Logger
+  def self.logger=: (::Logger) -> void
+  class MysqlSource
+    attr_reader source_client: untyped
+
+    def initialize: (source_client: untyped) -> void
+    def query: (String sql) -> untyped
+    def database: () -> String
+    def table_names: () -> Array[String]
+  end
+
+  class Output
+    def initialize: (**untyped) -> void
+    def sample!: () -> void
+    def export_mode: () -> export_mode
+    def target_database: () -> String
+    def qualified_table_name: (String table_name) -> String
+    def write_statement: (String sql) -> void
+    def write_raw: (String line) -> void
+  end
+
+  class DatabaseOutput < Output
+    attr_reader target_client: untyped
+
+    def import_table: (Collection collection, String table_name) -> void
+  end
+
+  class ExportContext
+    def self.quote_ident: (String | Symbol name) -> String
+    def initialize: (String table_name, Hash[String, untyped]? sanitize, ?insert_table_name: String?, ?column_types: Hash[String, String]) -> void
+    def insert_table_name: () -> String
+    def format_row_tuple: (Array[String | Symbol] columns, Hash[String, untyped] row, untyped client) -> String
+  end
+
+  class Sanitizer
+    BATCH_SIZE: Integer
+    def export_sanitized_rows: (Collection collection, insert_table_name: String) { (String header, String values) -> void } -> void
+  end
+
+  class FileOutput < Output
+    attr_reader path: String
+    attr_reader target_database: String
+  end
+
+  class Collection
+    def initialize: (String table_name) -> void
+    def assemble: () -> Hash[Symbol, untyped]
+    def export_select_sql: () -> String
+  end
+
+  Config = struct {
+    source: MysqlSource,
+    output: Output,
+    months: Integer?,
+    list: Array[String],
+  }
 end

metadata

@@ -1,42 +1,34 @@
 --- !ruby/object:Gem::Specification
 name: data_taster
 version: !ruby/object:Gem::Version
-  version: 0.4.1
+  version: 0.5.0
 platform: ruby
 authors:
 - Jill Klang
 bindir: exe
 cert_chain: []
-date: 2025-02-27 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
-- !ruby/object:Gem::Dependency
-  name: nokogiri
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - '='
-      - !ruby/object:Gem::Version
-        version: 1.17.2
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - '='
-      - !ruby/object:Gem::Version
-        version: 1.17.2
 - !ruby/object:Gem::Dependency
   name: rails
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '6.0'
+        version: '6.1'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '8'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '6.0'
+        version: '6.1'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '8'
 - !ruby/object:Gem::Dependency
   name: license_finder
   requirement: !ruby/object:Gem::Requirement
@@ -79,6 +71,34 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '2.1'
+- !ruby/object:Gem::Dependency
+  name: combustion
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !ruby/object:Gem::Dependency
+  name: mysql2
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 0.5.5
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 0.5.5
 - !ruby/object:Gem::Dependency
   name: parser
   requirement: !ruby/object:Gem::Requirement
@@ -105,14 +125,14 @@ dependencies:
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 2.2.2
+        version: 3.1.1
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 2.2.2
+        version: 3.1.1
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -175,14 +195,14 @@ dependencies:
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 0.9.34
+        version: 0.9.38
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 0.9.34
+        version: 0.9.38
 description: Export, sanitize, and import data to help develop better apps.
 email:
 - jillian.emilie@gmail.com
@@ -196,24 +216,29 @@ files:
 - Gemfile.lock
 - LICENSE.txt
 - Rakefile
+- config.ru
 - doc/dependency_decisions.yml
 - docs/CHANGELOG.md
 - docs/README.md
 - gemfiles/.bundle/config
-- gemfiles/rails_6_0.gemfile
-- gemfiles/rails_6_0.gemfile.lock
-- gemfiles/rails_6_1.gemfile
-- gemfiles/rails_6_1.gemfile.lock
-- gemfiles/rails_7_0.gemfile
-- gemfiles/rails_7_0.gemfile.lock
+- gemfiles/rails_7_1.gemfile
+- gemfiles/rails_7_1.gemfile.lock
+- gemfiles/rails_7_2.gemfile
+- gemfiles/rails_7_2.gemfile.lock
 - lib/data_taster.rb
+- lib/data_taster/adapters/database_output.rb
+- lib/data_taster/adapters/file_output.rb
+- lib/data_taster/adapters/mysql_source.rb
+- lib/data_taster/adapters/output.rb
 - lib/data_taster/collection.rb
 - lib/data_taster/confection.rb
 - lib/data_taster/detergent.rb
+- lib/data_taster/export_context.rb
 - lib/data_taster/flavors.rb
 - lib/data_taster/helper.rb
-- lib/data_taster/sample.rb
 - lib/data_taster/sanitizer.rb
+- lib/data_taster/sanitizer_exporter.rb
+- lib/data_taster/sql_literal.rb
 - lib/data_taster/version.rb
 - mkdocs.yml
 - sig/data_taster.rbs
@@ -239,7 +264,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.6.2
+rubygems_version: 3.6.9
 specification_version: 4
 summary: Delicious and sanitized data samples for development and testing.
 test_files: []

data/gemfiles/rails_6_0.gemfile

@@ -1,12 +0,0 @@
-# This file was generated by Appraisal
-
-source "https://rubygems.org"
-
-gem "activesupport", "< 7.2.0"
-gem "net-imap", "< 0.5.0"
-gem "rubocop-powerhome", path: "../../rubocop-powerhome", tag: "v0.5.2-rubocop-powerhome"
-gem "securerandom", "< 0.4.0"
-gem "zeitwerk", "< 2.7.0"
-gem "rails", "6.0.6.1"
-
-gemspec path: "../"

data/gemfiles/rails_6_0.gemfile.lock

@@ -1,271 +0,0 @@
-PATH
-  remote: ../../rubocop-powerhome
-  specs:
-    rubocop-powerhome (0.5.3)
-      rubocop (= 1.66.1)
-      rubocop-performance
-      rubocop-rails
-      rubocop-rake
-      rubocop-rspec
-
-PATH
-  remote: ..
-  specs:
-    data_taster (0.4.1)
-      nokogiri (= 1.17.2)
-      rails (>= 6.0)
-
-GEM
-  remote: https://rubygems.org/
-  specs:
-    actioncable (6.0.6.1)
-      actionpack (= 6.0.6.1)
-      nio4r (~> 2.0)
-      websocket-driver (>= 0.6.1)
-    actionmailbox (6.0.6.1)
-      actionpack (= 6.0.6.1)
-      activejob (= 6.0.6.1)
-      activerecord (= 6.0.6.1)
-      activestorage (= 6.0.6.1)
-      activesupport (= 6.0.6.1)
-      mail (>= 2.7.1)
-    actionmailer (6.0.6.1)
-      actionpack (= 6.0.6.1)
-      actionview (= 6.0.6.1)
-      activejob (= 6.0.6.1)
-      mail (~> 2.5, >= 2.5.4)
-      rails-dom-testing (~> 2.0)
-    actionpack (6.0.6.1)
-      actionview (= 6.0.6.1)
-      activesupport (= 6.0.6.1)
-      rack (~> 2.0, >= 2.0.8)
-      rack-test (>= 0.6.3)
-      rails-dom-testing (~> 2.0)
-      rails-html-sanitizer (~> 1.0, >= 1.2.0)
-    actiontext (6.0.6.1)
-      actionpack (= 6.0.6.1)
-      activerecord (= 6.0.6.1)
-      activestorage (= 6.0.6.1)
-      activesupport (= 6.0.6.1)
-      nokogiri (>= 1.8.5)
-    actionview (6.0.6.1)
-      activesupport (= 6.0.6.1)
-      builder (~> 3.1)
-      erubi (~> 1.4)
-      rails-dom-testing (~> 2.0)
-      rails-html-sanitizer (~> 1.1, >= 1.2.0)
-    activejob (6.0.6.1)
-      activesupport (= 6.0.6.1)
-      globalid (>= 0.3.6)
-    activemodel (6.0.6.1)
-      activesupport (= 6.0.6.1)
-    activerecord (6.0.6.1)
-      activemodel (= 6.0.6.1)
-      activesupport (= 6.0.6.1)
-    activestorage (6.0.6.1)
-      actionpack (= 6.0.6.1)
-      activejob (= 6.0.6.1)
-      activerecord (= 6.0.6.1)
-      marcel (~> 1.0)
-    activesupport (6.0.6.1)
-      concurrent-ruby (~> 1.0, >= 1.0.2)
-      i18n (>= 0.7, < 2)
-      minitest (~> 5.1)
-      tzinfo (~> 1.1)
-      zeitwerk (~> 2.2, >= 2.2.2)
-    appraisal (2.5.0)
-      bundler
-      rake
-      thor (>= 0.14.0)
-    ast (2.4.2)
-    builder (3.3.0)
-    concurrent-ruby (1.3.4)
-    crass (1.0.6)
-    csv (3.3.1)
-    date (3.4.1)
-    diff-lcs (1.5.1)
-    docile (1.1.5)
-    erubi (1.13.0)
-    globalid (1.1.0)
-      activesupport (>= 5.0)
-    i18n (1.14.6)
-      concurrent-ruby (~> 1.0)
-    json (2.9.0)
-    language_server-protocol (3.17.0.3)
-    license_finder (7.2.1)
-      bundler
-      csv (~> 3.2)
-      rubyzip (>= 1, < 3)
-      thor (~> 1.2)
-      tomlrb (>= 1.3, < 2.1)
-      with_env (= 1.1.0)
-      xml-simple (~> 1.1.9)
-    loofah (2.23.1)
-      crass (~> 1.0.2)
-      nokogiri (>= 1.12.0)
-    mail (2.8.1)
-      mini_mime (>= 0.1.1)
-      net-imap
-      net-pop
-      net-smtp
-    marcel (1.0.4)
-    method_source (1.1.0)
-    mini_mime (1.1.5)
-    mini_portile2 (2.8.8)
-    minitest (5.25.4)
-    net-imap (0.4.18)
-      date
-      net-protocol
-    net-pop (0.1.2)
-      net-protocol
-    net-protocol (0.2.2)
-      timeout
-    net-smtp (0.5.0)
-      net-protocol
-    nio4r (2.7.4)
-    nokogiri (1.17.2)
-      mini_portile2 (~> 2.8.2)
-      racc (~> 1.4)
-    nokogiri (1.17.2-arm64-darwin)
-      racc (~> 1.4)
-    nokogiri (1.17.2-x86_64-linux)
-      racc (~> 1.4)
-    parallel (1.26.3)
-    parser (3.3.6.0)
-      ast (~> 2.4.1)
-      racc
-    power_assert (2.0.4)
-    racc (1.8.1)
-    rack (2.2.10)
-    rack-test (2.1.0)
-      rack (>= 1.3)
-    rails (6.0.6.1)
-      actioncable (= 6.0.6.1)
-      actionmailbox (= 6.0.6.1)
-      actionmailer (= 6.0.6.1)
-      actionpack (= 6.0.6.1)
-      actiontext (= 6.0.6.1)
-      actionview (= 6.0.6.1)
-      activejob (= 6.0.6.1)
-      activemodel (= 6.0.6.1)
-      activerecord (= 6.0.6.1)
-      activestorage (= 6.0.6.1)
-      activesupport (= 6.0.6.1)
-      bundler (>= 1.3.0)
-      railties (= 6.0.6.1)
-      sprockets-rails (>= 2.0.0)
-    rails-dom-testing (2.2.0)
-      activesupport (>= 5.0.0)
-      minitest
-      nokogiri (>= 1.6)
-    rails-html-sanitizer (1.6.2)
-      loofah (~> 2.21)
-      nokogiri (>= 1.15.7, != 1.16.7, != 1.16.6, != 1.16.5, != 1.16.4, != 1.16.3, != 1.16.2, != 1.16.1, != 1.16.0.rc1, != 1.16.0)
-    railties (6.0.6.1)
-      actionpack (= 6.0.6.1)
-      activesupport (= 6.0.6.1)
-      method_source
-      rake (>= 0.8.7)
-      thor (>= 0.20.3, < 2.0)
-    rainbow (2.2.2)
-      rake
-    rake (13.2.1)
-    regexp_parser (2.9.3)
-    rexml (3.4.0)
-    rspec (3.13.0)
-      rspec-core (~> 3.13.0)
-      rspec-expectations (~> 3.13.0)
-      rspec-mocks (~> 3.13.0)
-    rspec-core (3.13.2)
-      rspec-support (~> 3.13.0)
-    rspec-expectations (3.13.3)
-      diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.13.0)
-    rspec-mocks (3.13.2)
-      diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.13.0)
-    rspec-support (3.13.2)
-    rubocop (1.66.1)
-      json (~> 2.3)
-      language_server-protocol (>= 3.17.0)
-      parallel (~> 1.10)
-      parser (>= 3.3.0.2)
-      rainbow (>= 2.2.2, < 4.0)
-      regexp_parser (>= 2.4, < 3.0)
-      rubocop-ast (>= 1.32.2, < 2.0)
-      ruby-progressbar (~> 1.7)
-      unicode-display_width (>= 2.4.0, < 3.0)
-    rubocop-ast (1.37.0)
-      parser (>= 3.3.1.0)
-    rubocop-performance (1.23.0)
-      rubocop (>= 1.48.1, < 2.0)
-      rubocop-ast (>= 1.31.1, < 2.0)
-    rubocop-rails (2.27.0)
-      activesupport (>= 4.2.0)
-      rack (>= 1.1)
-      rubocop (>= 1.52.0, < 2.0)
-      rubocop-ast (>= 1.31.1, < 2.0)
-    rubocop-rake (0.6.0)
-      rubocop (~> 1.0)
-    rubocop-rspec (3.3.0)
-      rubocop (~> 1.61)
-    ruby-progressbar (1.13.0)
-    rubyzip (2.3.2)
-    securerandom (0.3.2)
-    simplecov (0.15.1)
-      docile (~> 1.1.0)
-      json (>= 1.8, < 3)
-      simplecov-html (~> 0.10.0)
-    simplecov-html (0.10.2)
-    sprockets (4.2.1)
-      concurrent-ruby (~> 1.0)
-      rack (>= 2.2.4, < 4)
-    sprockets-rails (3.4.2)
-      actionpack (>= 5.2)
-      activesupport (>= 5.2)
-      sprockets (>= 3.0.0)
-    test-unit (3.1.5)
-      power_assert
-    thor (1.3.2)
-    thread_safe (0.3.6)
-    timeout (0.4.3)
-    tomlrb (2.0.3)
-    tzinfo (1.2.11)
-      thread_safe (~> 0.1)
-    unicode-display_width (2.6.0)
-    websocket-driver (0.7.6)
-      websocket-extensions (>= 0.1.0)
-    websocket-extensions (0.1.5)
-    with_env (1.1.0)
-    xml-simple (1.1.9)
-      rexml
-    yard (0.9.34)
-    zeitwerk (2.6.18)
-
-PLATFORMS
-  arm64-darwin-22
-  arm64-darwin-23
-  ruby
-  x86_64-linux
-
-DEPENDENCIES
-  activesupport (< 7.2.0)
-  appraisal (= 2.5.0)
-  bundler (~> 2.1)
-  data_taster!
-  license_finder (~> 7.0)
-  net-imap (< 0.5.0)
-  parser (>= 2.5, != 2.5.1.1)
-  rails (= 6.0.6.1)
-  rainbow (= 2.2.2)
-  rake (~> 13.0)
-  rspec (~> 3.0)
-  rubocop-powerhome!
-  securerandom (< 0.4.0)
-  simplecov (= 0.15.1)
-  test-unit (= 3.1.5)
-  yard (= 0.9.34)
-  zeitwerk (< 2.7.0)
-
-BUNDLED WITH
-   2.5.23

data/gemfiles/rails_6_1.gemfile

@@ -1,12 +0,0 @@
-# This file was generated by Appraisal
-
-source "https://rubygems.org"
-
-gem "activesupport", "< 7.2.0"
-gem "net-imap", "< 0.5.0"
-gem "rubocop-powerhome", path: "../../rubocop-powerhome", tag: "v0.5.2-rubocop-powerhome"
-gem "securerandom", "< 0.4.0"
-gem "zeitwerk", "< 2.7.0"
-gem "rails", "6.1.7.7"
-
-gemspec path: "../"