active_record_data_loader 1.2.0 → 1.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8ae60492b342e71d8a1a2e20aff31794af784f1009346f4d5dc4375dd939bb48
-  data.tar.gz: ab5be5bdf1cb5af69f5f8a1ac65ea8f64ee1338398c7f6cae6e15e6276d2e954
+  metadata.gz: 19d357e3af1a3864a020996df4da4d1d4d710dccd15e50cc10c30f0498acb64b
+  data.tar.gz: 7a706dcaa17777c1fa93090212385fcd18742d84099663d9555e54452c046595
 SHA512:
-  metadata.gz: 8b860a06433a0661a765428f37df596ac0b3fd46ff447fbf3edfa5cf50f89dcda0f146b25074959ca5aee792dff153a56eb37888075ae10649d6cde1e598c53d
-  data.tar.gz: dc9b43011f8c1b8c7b663b650b5ba11e43b9dd040a8ef6b7a58b24c7da903b1c963104a06c39f45e5ebaa4f01e815d8d6d565ded2fd9b5a186dcd50ed69b2e7c
+  metadata.gz: 6b541ceb75b06c6152184ae4f9d66e6a1268a8a758c23ce959fb608a78a7860c8f17596fd90b5a9bbadf0853c2d2009b8b68304e6f852d4eed2a3e5ddd1b59d1
+  data.tar.gz: 509fce080286cae5770bbe6b42ace34b34f1804c8834114d7c0fbbd2e0323b2c785fde4188de6d7221666fd6489eb8229a76c47fea90cddcd96bf3628260c5e8

data/.github/workflows/codeql-analysis.yml

@@ -0,0 +1,70 @@
+# For most projects, this workflow file will not need changing; you simply need
+# to commit it to your repository.
+#
+# You may wish to alter this file to override the set of languages analyzed,
+# or to provide custom queries or build logic.
+#
+# ******** NOTE ********
+# We have attempted to detect the languages in your repository. Please check
+# the `language` matrix defined below to confirm you have the correct set of
+# supported CodeQL languages.
+#
+name: "CodeQL"
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    # The branches below must be a subset of the branches above
+    branches: [ master ]
+  schedule:
+    - cron: '26 13 * * 4'
+
+jobs:
+  analyze:
+    name: Analyze
+    runs-on: ubuntu-latest
+    permissions:
+      actions: read
+      contents: read
+      security-events: write
+
+    strategy:
+      fail-fast: false
+      matrix:
+        language: [ 'ruby' ]
+        # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python', 'ruby' ]
+        # Learn more about CodeQL language support at https://git.io/codeql-language-support
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v2
+
+    # Initializes the CodeQL tools for scanning.
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@v1
+      with:
+        languages: ${{ matrix.language }}
+        # If you wish to specify custom queries, you can do so here or in a config file.
+        # By default, queries listed here will override any specified in a config file.
+        # Prefix the list here with "+" to use these queries and those in the config file.
+        # queries: ./path/to/local/query, your-org/your-repo/queries@main
+
+    # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
+    # If this step fails, then you should remove it and run the build manually (see below)
+    - name: Autobuild
+      uses: github/codeql-action/autobuild@v1
+
+    # ℹ️ Command-line programs to run using the OS shell.
+    # 📚 https://git.io/JvXDl
+
+    # ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
+    #    and modify them (or add more) to build your code if your project
+    #    uses a compiled language
+
+    #- run: |
+    #   make bootstrap
+    #   make release
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v1

data/.rubocop.yml

@@ -3,6 +3,9 @@ AllCops:
   NewCops: enable
   SuggestExtensions: false
 
+Gemspec/RequireMFA:
+  Enabled: false
+
 Layout/LineLength:
   Max: 110
   Exclude: ["*.gemspec"]
@@ -27,15 +30,18 @@ Metrics/BlockLength:
   Exclude: ["spec/**/*", "*.gemspec"]
 
 Metrics/ClassLength:
+  Max: 150
   Exclude: ["spec/**/*", "*.gemspec"]
 
 Metrics/MethodLength:
-  Max: 15
+  Max: 25
   Exclude: ["spec/**/*"]
 
 Metrics/ParameterLists:
   Max: 5
-  Exclude: ["lib/active_record_data_loader/configuration.rb"]
+  Exclude:
+    - "lib/active_record_data_loader/configuration.rb"
+    - "lib/active_record_data_loader/active_record/model_data_generator.rb"
 
 Style/CaseLikeIf:
   Enabled: false

data/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Change log
 
+## [v1.3.0] - 2021-12-10
+
+[Diff](https://github.com/abeiderman/active_record_data_loader/compare/v1.2.0...v1.3.0)
+
+### Changes:
+* Replace the `:file` output option with simply accepting an optional file path as `output`. A SQL script file will be generated in addition to loading the data into the database.
+* Identify and handle unique indexes by attempting to generate unique values. Add configuration options for behavior around duplicate rows.
+
 ## [v1.2.0] - 2021-11-14
 
 [Diff](https://github.com/abeiderman/active_record_data_loader/compare/v1.1.0...v1.2.0)
@@ -40,3 +48,4 @@ Initial stable release
 [v1.0.2]: https://github.com/abeiderman/active_record_data_loader/releases/tag/v1.0.2
 [v1.1.0]: https://github.com/abeiderman/active_record_data_loader/releases/tag/v1.1.0
 [v1.2.0]: https://github.com/abeiderman/active_record_data_loader/releases/tag/v1.2.0
+[v1.3.0]: https://github.com/abeiderman/active_record_data_loader/releases/tag/v1.3.0

data/CODE_OF_CONDUCT.md

@@ -55,8 +55,8 @@ further defined and clarified by project maintainers.
 ## Enforcement
 
 Instances of abusive, harassing, or otherwise unacceptable behavior may be
-reported by contacting the project team at abeiderman@gmail.com. All
-complaints will be reviewed and investigated and will result in a response that
+reported by contacting the project team at active_record_data_loader@ossprojects.dev.
+All complaints will be reviewed and investigated and will result in a response that
 is deemed necessary and appropriate to the circumstances. The project team is
 obligated to maintain confidentiality with regard to the reporter of an incident.
 Further details of specific enforcement policies may be posted separately.

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    active_record_data_loader (1.2.0)
+    active_record_data_loader (1.3.0)
       activerecord (>= 5.0)
 
 GEM
@@ -18,14 +18,14 @@ GEM
       minitest (>= 5.1)
       tzinfo (~> 2.0)
       zeitwerk (~> 2.3)
-    appraisal (2.2.0)
+    appraisal (2.4.1)
       bundler
       rake
       thor (>= 0.14.0)
     ast (2.4.2)
-    coderay (1.1.2)
+    coderay (1.1.3)
     concurrent-ruby (1.1.9)
-    diff-lcs (1.3)
+    diff-lcs (1.4.4)
     docile (1.4.0)
     i18n (1.8.11)
       concurrent-ruby (~> 1.0)
@@ -33,32 +33,32 @@ GEM
     minitest (5.14.4)
     mysql2 (0.5.3)
     parallel (1.21.0)
-    parser (3.0.2.0)
+    parser (3.0.3.2)
       ast (~> 2.4.1)
     pg (1.2.3)
-    pry (0.13.1)
+    pry (0.14.1)
       coderay (~> 1.1)
       method_source (~> 1.0)
     rainbow (3.0.0)
-    rake (13.0.1)
-    regexp_parser (2.1.1)
+    rake (13.0.6)
+    regexp_parser (2.2.0)
     rexml (3.2.5)
-    rspec (3.9.0)
-      rspec-core (~> 3.9.0)
-      rspec-expectations (~> 3.9.0)
-      rspec-mocks (~> 3.9.0)
+    rspec (3.10.0)
+      rspec-core (~> 3.10.0)
+      rspec-expectations (~> 3.10.0)
+      rspec-mocks (~> 3.10.0)
     rspec-collection_matchers (1.2.0)
       rspec-expectations (>= 2.99.0.beta1)
-    rspec-core (3.9.2)
-      rspec-support (~> 3.9.3)
-    rspec-expectations (3.9.1)
+    rspec-core (3.10.1)
+      rspec-support (~> 3.10.0)
+    rspec-expectations (3.10.1)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.9.0)
-    rspec-mocks (3.9.1)
+      rspec-support (~> 3.10.0)
+    rspec-mocks (3.10.2)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.9.0)
-    rspec-support (3.9.3)
-    rubocop (1.22.3)
+      rspec-support (~> 3.10.0)
+    rspec-support (3.10.3)
+    rubocop (1.23.0)
       parallel (~> 1.10)
       parser (>= 3.0.0.0)
       rainbow (>= 2.2.2, < 4.0)
@@ -67,7 +67,7 @@ GEM
       rubocop-ast (>= 1.12.0, < 2.0)
       ruby-progressbar (~> 1.7)
       unicode-display_width (>= 1.4.0, < 3.0)
-    rubocop-ast (1.13.0)
+    rubocop-ast (1.14.0)
       parser (>= 3.0.1.1)
     ruby-progressbar (1.11.0)
     simplecov (0.21.2)
@@ -77,9 +77,9 @@ GEM
     simplecov-html (0.12.3)
     simplecov-lcov (0.8.0)
     simplecov_json_formatter (0.1.3)
-    sqlite3 (1.4.1)
-    thor (0.20.3)
-    timecop (0.9.1)
+    sqlite3 (1.4.2)
+    thor (1.1.0)
+    timecop (0.9.4)
     tzinfo (2.0.4)
       concurrent-ruby (~> 1.0)
     unicode-display_width (2.1.0)

data/README.md

@@ -41,6 +41,7 @@ Polymorphic associations need to be defined explicitly as shown in [Polymorphic
 ### Basic usage
 
 Let's say you have the following models:
+
 ```ruby
 class Customer < ApplicationRecord
 end
@@ -51,6 +52,7 @@ end
 ```
 
 The following code will create 10,000 customers and 100,000 orders, and will associate the orders to those customers evenly:
+
 ```ruby
 data_loader = ActiveRecordDataLoader.define do
   model Customer do |m|
@@ -67,6 +69,7 @@ data_loader.load_data
 
 #### Overriding column values
 To provide your own values for columns your can provide a lambda or a constant value:
+
 ```ruby
 data_loader = ActiveRecordDataLoader.define do
   model Customer do |m|
@@ -91,7 +94,7 @@ In this example, we are creating 25K orders for customers in CAN with a CAD curr
 data_loader = ActiveRecordDataLoader.define do
   model Customer do |m|
     m.count 10_000
-    m.column :country, -> { %w[CAN MXN USA].sample }
+    m.column :country, -> { %w[CAN MEX USA].sample }
   end
 
   model Order do |m|
@@ -121,6 +124,7 @@ data_loader.load_data
 If you have a polymorphic `belongs_to` association, you will need to define that explicitly for it to be populated.
 
 Let's assume the following models where an order could belong to either a person or a business:
+
 ```ruby
 class Person < ApplicationRecord
   has_many :orders
@@ -136,6 +140,7 @@ end
 ```
 
 In order to populate the `customer` association in orders, you would specify them like this:
+
 ```ruby
 data_loader = ActiveRecordDataLoader.define do
   model Person do |m|
@@ -160,6 +165,7 @@ data_loader.load_data
 ```
 
 You can also provide a `weight` to each of the target models if you want to control how they are distributed. If you wanted to have twice as many orders for `Person` than for `Business`, it would look like this:
+
 ```ruby
 data_loader = ActiveRecordDataLoader.define do
   model Person do |m|
@@ -184,6 +190,7 @@ data_loader.load_data
 ```
 
 Additionaly, you can also provide an `eligible_set` to control which records to limit the association to:
+
 ```ruby
 data_loader = ActiveRecordDataLoader.define do
   model Person do |m|
@@ -208,6 +215,81 @@ end
 data_loader.load_data
 ```
 
+### Unique indexes
+
+Unique indexes will be detected automatically and the data generator will attempt to generate unique values for each row. The generator keeps track of unique values previously generated and retries rows with repeating values. Because some columns could be generating random values, retrying can eventually be successful.
+
+There are a couple of behaviors you can control regarding preventing duplicates. The first is the number of times to retry a given row with duplicate values (that would fail the unique index/constraint). The second is what to do if a unique value cannot be generated after the retries are exhausted.
+
+By default, there will be 5 retries per row and the row will be skipped after all retries are unsuccessful. This means fewer rows than requested may end up being populated on that table.
+
+Alternatively, you can choose to raise an error if a unique row cannot be generated. You can also set the number of retries to 0 to not retry at all. If the table in question is a primary target for your testing and will be loaded with a lot of data, you will likely not want to have retries since it could potentially slow down data generation significantly.
+
+Here is how to adjust these settings. Here let's assyme that `daily_notes` has a unique index on both `date` and `person_id`:
+
+```ruby
+class Person < ApplicationRecord
+end
+
+class DailyNotes < ApplicationRecord
+  belongs_to :person
+end
+
+data_loader = ActiveRecordDataLoader.define do
+  model Person do |m|
+    m.count 500
+  end
+
+  model DailyNotes do |m|
+    m.count 10_000
+    m.max_duplicate_retries 10
+    m.do_not_raise_on_duplicates
+
+    m.column :date, -> { Date.today - rand(20) }
+  end
+end
+
+data_loader.load_data
+```
+
+In the case above, retrying could be a reasonable choice since the date is generated at random and it's a small number of rows being generated.
+
+If you want to disable retrying duplicates altogether and raise an error to fail fast you can specify it like this:
+
+```ruby
+class Person < ApplicationRecord
+end
+
+class Skill < ApplicationRecord
+end
+
+class SkillRating < ApplicationRecord
+  belongs_to :person
+  belongs_to :skill
+end
+
+data_loader = ActiveRecordDataLoader.define do
+  model Person do |m|
+    m.count 100_000
+  end
+
+  model Skill do |m|
+    m.count 100
+  end
+
+  model SkillRating do |m|
+    m.count 10_000_000
+    m.max_duplicate_retries 0
+    m.raise_on_duplicates
+
+    m.column :rating, -> { rand(1..10) }
+  end
+end
+
+data_loader.load_data
+```
+
+
 ### Configuration options
 
 You can define global configuration options like this:
@@ -257,31 +339,19 @@ end
 
 #### output
 
-The `output` option accepts either `:connection` or `:file`. The default behavior is `:connection` which means the data will be loaded into the database using the database connection.
-
-If `:file` is specified, instead of the data being loaded into the database, a script file will be generated. This script file can then be executed manually to load the data. This can be helpful if you need to load the same data multiple times. For example if you are profiling different alternatives in your code and you want to see how each performs with a fully loaded database. In that case you would want to have the same data starting point for each alternative you evaluate. By generating the script file ahead of time, it would be significantly faster to load that data over and over by executing the existing script.
-
-Here are some examples on how to use the `output` option:
+The `output` option accepts an optional file name to write a SQL script with the data loading statements. This script file can then be executed manually to load the data. This can be helpful if you need to load the same data multiple times. For example if you are profiling different alternatives in your code and you want to see how each performs with a fully loaded database. In that case you would want to have the same data starting point for each alternative you evaluate. By generating the script file, it would be significantly faster to load that data over and over by executing the existing script.
 
-```ruby
-ActiveRecordDataLoader.configure do |c|
-  c.output = :connection  # This is the default behavior
-end
-```
+If `output` is nil or empty, no script file will be written.
 
-```ruby
-ActiveRecordDataLoader.configure do |c|
-  c.output = :file  # Outputs to a file with a default name
-end
-```
+Example usage:
 
 ```ruby
 ActiveRecordDataLoader.configure do |c|
-  c.output = { type: :file, filename: "./my_script.sql" }  # Outputs to the provided file
+  c.output = "./my_script.sql"  # Outputs to the provided file
 end
 ```
 
-When using the `:file` type with Postgres, the resulting script will have `\COPY` commands which reference CSV files that contain the data batches to be copied. The CSV files will be created along side the SQL script and will have a naming convention of using the table name and the rows range for the given batch. For example `./my_script_customers_1_to_1000.csv`. Each `\COPY` command in the SQL file will reference the corresponding CSV file so all you need to do is execute the SQL file using `psql`:
+When using an output script file with Postgres, the resulting script will have `\COPY` commands which reference CSV files that contain the data batches to be copied. The CSV files will be created along side the SQL script and will have a naming convention of using the table name and the rows range for the given batch. For example `./my_script_customers_1_to_1000.csv`. Each `\COPY` command in the SQL file will reference the corresponding CSV file so all you need to do is execute the SQL file using `psql`:
 
 ```bash
 psql -h my-db-host -U my_user -f my_script.sql

data/active_record_data_loader.gemspec

@@ -8,7 +8,7 @@ Gem::Specification.new do |spec|
   spec.name          = "active_record_data_loader"
   spec.version       = ActiveRecordDataLoader::VERSION
   spec.authors       = ["Alejandro Beiderman"]
-  spec.email         = ["abeiderman@gmail.com"]
+  spec.email         = ["active_record_data_loader@ossprojects.dev"]
 
   spec.summary       = "A utility to bulk load test data for performance testing."
   spec.description   = "A utility to bulk load test data for performance testing."

data/lib/active_record_data_loader/active_record/{belongs_to_configuration.rb → belongs_to_data_provider.rb}

@@ -2,26 +2,27 @@
 
 module ActiveRecordDataLoader
   module ActiveRecord
-    class BelongsToConfiguration
-      def self.config_for(ar_association:, query: nil)
+    class BelongsToDataProvider
+      def self.provider_for(ar_association:, query: nil, strategy: :random)
         raise "#{name} does not support polymorphic associations" if ar_association.polymorphic?
 
-        { ar_association.join_foreign_key.to_sym => new(ar_association, query).foreign_key_func }
+        { ar_association.join_foreign_key.to_sym => new(ar_association, query, strategy).foreign_key_func }
       end
 
-      def initialize(ar_association, query)
+      def initialize(ar_association, query, strategy)
         @ar_association = ar_association
         @query = query
+        @strategy = strategy
       end
 
       def foreign_key_func
-        -> { possible_values.sample }
+        -> { possible_values.next }
       end
 
       private
 
       def possible_values
-        @possible_values ||= base_query.pluck(@ar_association.join_primary_key).to_a
+        @possible_values ||= List.for(base_query.pluck(@ar_association.join_primary_key), strategy: @strategy)
       end
 
       def base_query

data/lib/active_record_data_loader/active_record/{column_configuration.rb → column_data_provider.rb}

@@ -2,7 +2,7 @@
 
 module ActiveRecordDataLoader
   module ActiveRecord
-    class ColumnConfiguration
+    class ColumnDataProvider
       class << self
         VALUE_GENERATORS = {
           enum: EnumValueGenerator,
@@ -12,7 +12,7 @@ module ActiveRecordDataLoader
           datetime: DatetimeValueGenerator,
         }.freeze
 
-        def config_for(model_class:, ar_column:, connection_factory:)
+        def provider_for(model_class:, ar_column:, connection_factory:)
           raise_error_if_not_supported(model_class, ar_column)
 
           {

data/lib/active_record_data_loader/active_record/list.rb

@@ -0,0 +1,35 @@
+# frozen_string_literal: true
+
+module ActiveRecordDataLoader
+  module ActiveRecord
+    class List
+      def self.for(enumerable, strategy: :random)
+        if strategy == :cycle
+          Cycle.new(enumerable)
+        else
+          Random.new(enumerable)
+        end
+      end
+
+      class Random
+        def initialize(enumerable)
+          @list = enumerable
+        end
+
+        def next
+          @list.sample
+        end
+      end
+
+      class Cycle
+        def initialize(enumerable)
+          @list = enumerable.cycle
+        end
+
+        def next
+          @list.next
+        end
+      end
+    end
+  end
+end

data/lib/active_record_data_loader/active_record/model_data_generator.rb

@@ -9,6 +9,9 @@ module ActiveRecordDataLoader
         model:,
         column_settings:,
         connection_factory:,
+        logger:,
+        raise_on_duplicates:,
+        max_duplicate_retries:,
         polymorphic_settings: [],
         belongs_to_settings: []
       )
@@ -18,6 +21,11 @@ module ActiveRecordDataLoader
         @polymorphic_settings = polymorphic_settings
         @belongs_to_settings = belongs_to_settings.map { |s| [s.name, s.query] }.to_h
         @connection_factory = connection_factory
+        @raise_on_duplicates = raise_on_duplicates
+        @max_duplicate_retries = max_duplicate_retries
+        @logger = logger
+        @index_tracker = UniqueIndexTracker.new(model: model, connection_factory: connection_factory)
+        @index_tracker.map_indexed_columns(column_list)
       end
 
       def column_list
@@ -25,11 +33,41 @@ module ActiveRecordDataLoader
       end
 
       def generate_row(row_number)
-        column_list.map { |c| column_data(row_number, c) }
+        @index_tracker.capture_unique_values(generate_row_with_retries(row_number))
       end
 
       private
 
+      def generate_row_with_retries(row_number)
+        retries = 0
+        while @index_tracker.repeating_unique_values?(row = generate_candidate_row(row_number))
+          if (retries += 1) > @max_duplicate_retries
+            raise DuplicateKeyError, <<~MSG if @raise_on_duplicates
+              Exhausted retries looking for unique values for row #{row_number} for '#{table}'.
+              Table '#{table}' has unique indexes that would have prevented inserting this row. If you would
+              like to skip non-unique rows instead of raising, configure `raise_on_duplicates` to be `false`.
+            MSG
+
+            @logger.warn(
+              "[ActiveRecordDataLoader] "\
+              "Exhausted retries looking for unique values. Skipping row #{row_number} for '#{table}'."
+            )
+            return nil
+          else
+            @logger.info(
+              "[ActiveRecordDataLoader] "\
+              "Retrying row #{row_number} for '#{table}' looking for unique values compliant with indexes. "\
+              "Retry number #{retries}."
+            )
+          end
+        end
+        row
+      end
+
+      def generate_candidate_row(row_number)
+        column_list.map { |c| column_data(row_number, c) }
+      end
+
       def column_data(row_number, column)
         column_value = columns[column]
         return column_value unless column_value.respond_to?(:call)
@@ -56,9 +94,9 @@ module ActiveRecordDataLoader
         @model_class
           .columns_hash
           .reject { |name| name == @model_class.primary_key }
-          .select { |_, c| ColumnConfiguration.supported?(model_class: @model_class, ar_column: c) }
+          .select { |_, c| ColumnDataProvider.supported?(model_class: @model_class, ar_column: c) }
           .map do |_, c|
-            ColumnConfiguration.config_for(
+            ColumnDataProvider.provider_for(
               model_class: @model_class,
               ar_column: c,
               connection_factory: @connection_factory
@@ -73,16 +111,33 @@ module ActiveRecordDataLoader
           .select(&:belongs_to?)
           .reject(&:polymorphic?)
           .map do |assoc|
-            BelongsToConfiguration.config_for(ar_association: assoc, query: @belongs_to_settings[assoc.name])
+            BelongsToDataProvider.provider_for(
+              ar_association: assoc,
+              query: @belongs_to_settings[assoc.name],
+              strategy: column_config_strategy(assoc)
+            )
           end
           .reduce({}, :merge)
       end
 
       def polymorphic_config
         @polymorphic_settings
-          .map { |s| PolymorphicBelongsToConfiguration.config_for(polymorphic_settings: s) }
+          .map do |s|
+            PolymorphicBelongsToDataProvider.provider_for(
+              polymorphic_settings: s,
+              strategy: column_config_strategy(s.model_class.reflect_on_association(s.name))
+            )
+          end
           .reduce({}, :merge)
       end
+
+      def column_config_strategy(column)
+        if @index_tracker.contained_in_index?(column)
+          :cycle
+        else
+          :random
+        end
+      end
     end
   end
 end