burner 1.0.0.pre.alpha.3 → 1.0.0.pre.alpha.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ca551c813e385ad98bd5856ff74be816d43a57fe60003da061536b9a0a27b2a6
-  data.tar.gz: 484f1490830bd27d5eaeae2dd097ac8ee0a2024d0d231ae09f2607ab1275cd9e
+  metadata.gz: ebd1332e7b4a01aace974be43aaa77e02b3bcb13e36b2360b08192bde2b99705
+  data.tar.gz: '09095dcd305279cf2e246cca6e36256a0f7943d12d335366aa6ff9dcc92c6198'
 SHA512:
-  metadata.gz: ee7bdfe6e3571918730bf6ff983d88b3cbb10514c90feae0df736167dfaeee4cce41f3e307c743012a528e43b0c0251e60b07008908e5a1e400aec7b65fe4005
-  data.tar.gz: ebd8cde5363fcc8c509d4856ec9978c14a1601d85f492a92f76e5e35dd10629fbd19566d51d13093b8216366035cbda9b4fbef610995796f17881d09e3e45d81
+  metadata.gz: 31e45b0c0cc815d05f3424a04e77a8e36ed96e912ec0fed2dfcf8e171ecbe7f0ade1841991cdb97751bbd10d103b161d173120abd0a68689281a258de524697c
+  data.tar.gz: 751091b32afae9e386814cb16856c5b0d41393b51e4e98070579d6508484e61a27a21bddba4be08f7a8416a86b50de71eeac3d886c635c785572f1597cb9095c

data/.rubocop.yml

@@ -31,3 +31,5 @@ Style/TrailingCommaInHashLiteral:
 Style/TrailingCommaInArrayLiteral:
   Enabled: false
 
+Metrics/ParameterLists:
+  CountKeywordArgs: false

data/README.md

@@ -31,30 +31,30 @@ pipeline = {
   jobs: [
     {
       name: :read,
-      type: 'io/read',
+      type: 'b/io/read',
       path: '{input_file}'
     },
     {
       name: :output_id,
-      type: :echo,
+      type: 'b/echo',
       message: 'The job id is: {__id}'
     },
     {
       name: :output_value,
-      type: :echo,
+      type: 'b/echo',
       message: 'The current value is: {__value}'
     },
     {
       name: :parse,
-      type: 'deserialize/json'
+      type: 'b/deserialize/json'
     },
     {
       name: :convert,
-      type: 'serialize/yaml'
+      type: 'b/serialize/yaml'
     },
     {
       name: :write,
-      type: 'io/write',
+      type: 'b/io/write',
       path: '{output_file}'
     }
   ],
@@ -73,19 +73,21 @@ params = {
   input_file: 'input.json',
   output_file: 'output.yaml'
 }
+
+payload = Burner::Payload.new(params: params)
 ````
 
 Assuming we are running this script from a directory where an `input.json` file exists, we can then programatically process the pipeline:
 
 ````ruby
-Burner::Pipeline.make(pipeline).execute(params: params)
+Burner::Pipeline.make(pipeline).execute(payload: payload)
 ````
 
 We should now see a output.yaml file created.
 
 Some notes:
 
-* Some values are able to be string-interpolated using the provided params.  This allows for the passing runtime configuration/data into pipelines/jobs.
+* Some values are able to be string-interpolated using the provided Payload#params.  This allows for the passing runtime configuration/data into pipelines/jobs.
 * The job's ID can be accessed using the `__id` key.
 * The current job's payload value can be accessed using the `__value` key.
 * Jobs can be re-used (just like the output_id and output_value jobs).
@@ -116,8 +118,9 @@ end
 
 string_out = StringOut.new
 output     = Burner::Output.new(outs: string_out)
+payload    = Burner::Payload.new(params: params)
 
-Burner::Pipeline.make(pipeline).execute(output: output, params: params)
+Burner::Pipeline.make(pipeline).execute(output: output, payload: payload)
 
 log = string_out.read
 ````
@@ -130,23 +133,23 @@ The value of `log` should now look similar to:
 [8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC]   - input_file: input.json
 [8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC]   - output_file: output.yaml
 [8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC] --------------------------------------------------------------------------------
-[8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC] [1] Burner::Jobs::IO::Read::read
+[8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC] [1] Burner::Library::IO::Read::read
 [8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC]   - Reading: spec/fixtures/input.json
 [8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC]   - Completed in: 0.0 second(s)
-[8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC] [2] Burner::Jobs::Echo::output_id
+[8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC] [2] Burner::Library::Echo::output_id
 [8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC]   - The job id is:
 [8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC]   - Completed in: 0.0 second(s)
-[8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC] [3] Burner::Jobs::Echo::output_value
+[8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC] [3] Burner::Library::Echo::output_value
 [8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC]   - The current value is:
 [8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC]   - Completed in: 0.0 second(s)
-[8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC] [4] Burner::Jobs::Deserialize::Json::parse
+[8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC] [4] Burner::Library::Deserialize::Json::parse
 [8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC]   - Completed in: 0.0 second(s)
-[8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC] [5] Burner::Jobs::Serialize::Yaml::convert
+[8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC] [5] Burner::Library::Serialize::Yaml::convert
 [8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC]   - Completed in: 0.0 second(s)
-[8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC] [6] Burner::Jobs::Echo::output_value
+[8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC] [6] Burner::Library::Echo::output_value
 [8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC]   - The current value is:
 [8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC]   - Completed in: 0.0 second(s)
-[8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC] [7] Burner::Jobs::IO::Write::write
+[8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC] [7] Burner::Library::IO::Write::write
 [8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC]   - Writing: output.yaml
 [8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC]   - Completed in: 0.0 second(s)
 [8bdc394e-7047-4a1a-87ed-6c54ed690ed5 | 2020-10-14 13:49:59 UTC] --------------------------------------------------------------------------------
@@ -160,7 +163,7 @@ Notes:
 
 ### Command Line Pipeline Processing
 
-This library also ships with a built-in script `exe/burner` that illustrates using the `Burner::Cli` API.  This class can take in an array of arguments (similar to a command-line) and execute a pipeline.  The first argument is the path to a YAML file with the pipeline's configuration and each subsequent argument is a param in `key=value` form.  Here is how the json-to-yaml example can utilize this interface:
+This library also ships with a built-in script `burner` that illustrates using the `Burner::Cli` API.  This class can take in an array of arguments (similar to a command-line) and execute a pipeline.  The first argument is the path to a YAML file with the pipeline's configuration and each subsequent argument is a param in `key=value` form.  Here is how the json-to-yaml example can utilize this interface:
 
 #### Create YAML Pipeline Configuration File
 
@@ -169,25 +172,25 @@ Write the following json_to_yaml_pipeline.yaml file to disk:
 ````yaml
 jobs:
   - name: read
-    type: io/read
+    type: b/io/read
     path: '{input_file}'
 
   - name: output_id
-    type: echo
+    type: b/echo
     message: 'The job id is: {__id}'
 
   - name: output_value
-    type: echo
+    type: b/echo
     message: 'The current value is: {__value}'
 
   - name: parse
-    type: deserialize/json
+    type: b/deserialize/json
 
   - name: convert
-    type: serialize/yaml
+    type: b/serialize/yaml
 
   - name: write
-    type: io/write
+    type: b/io/write
     path: '{output_file}'
 
 steps:
@@ -228,29 +231,56 @@ Burner::Cli.new(args).invoke
 
 This library only ships with very basic, rudimentary jobs that are meant to just serve as a baseline:
 
-* **deserialize/json** []: Treat input as a string and de-serialize it to JSON.
-* **deserialize/yaml** [safe]: Treat input as a string and de-serialize it to YAML.  By default it will try and (safely de-serialize)[https://ruby-doc.org/stdlib-2.6.1/libdoc/psych/rdoc/Psych.html#method-c-safe_load] it (only using core classes).  If you wish to de-serialize it to any class type, pass in `safe: false`
-* **dummy** []: Do nothing
-* **echo** [message]: Write a message to the output.  The message parameter can be interpolated using params.
-* **io/exist** [path, short_circuit]: Check to see if a file exists. The path parameter can be interpolated using params.  If short_circuit was set to true (defaults to false) and the file does not exist then the pipeline will be short-circuited.
-* **io/read** [binary, path]: Read in a local file.  The path parameter can be interpolated using params.  If the contents are binary, pass in `binary: true` to open it up in binary+read mode.
-* **io/write** [binary, path]: Write to a local file.  The path parameter can be interpolated using params.  If the contents are binary, pass in `binary: true` to open it up in binary+write mode.
-* **serialize/json** []: Convert value to JSON.
-* **serialize/yaml** []: Convert value to YAML.
-* **set** [value]: Set the value to any arbitrary value.
-* **sleep** [seconds]: Sleep the thread for X number of seconds.
+#### Collection
+
+* **b/collection/arrays_to_objects** [mappings, register]: Convert an array of arrays to an array of objects.
+* **b/collection/graph** [config, key, register]: Use [Hashematics](https://github.com/bluemarblepayroll/hashematics) to turn a flat array of objects into a deeply nested object tree.
+* **b/collection/objects_to_arrays** [mappings, register]: Convert an array of objects to an array of arrays.
+* **b/collection/shift** [amount, register]: Remove the first N number of elements from an array.
+* **b/collection/transform** [attributes, exclusive, separator, register]: Iterate over all objects and transform each key per the attribute transformers specifications.  If exclusive is set to false then the current object will be overridden/merged.  Separator can also be set for key path support.  This job uses [Realize](https://github.com/bluemarblepayroll/realize), which provides its own extendable value-transformation pipeline.
+* **b/collection/unpivot** [pivot_set, register]: Take an array of objects and unpivot specific sets of keys into rows.  Under the hood it uses [HashMath's Unpivot class](https://github.com/bluemarblepayroll/hash_math#unpivot-hash-key-coalescence-and-row-extrapolation).
+* **b/collection/validate** [invalid_register, join_char, message_key, register, separator, validations]: Take an array of objects, run it through each declared validator, and split the objects into two registers.  The valid objects will be split into the current register while the invalid ones will go into the invalid_register as declared.  Optional arguments, join_char and message_key, help determine the compiled error messages.  The separator option can be utilized to use dot-notation for validating keys.  See each validation's options by viewing their classes within the `lib/modeling/validations` directory.
+* **b/collection/values** [include_keys, register]: Take an array of objects and call `#values` on each object. If include_keys is true (it is false by default), then call `#keys` on the first object and inject that as a "header" object.
+
+#### De-serialization
+
+* **b/deserialize/csv** [register]: Take a CSV string and de-serialize into object(s).  Currently it will return an array of arrays, with each nested array representing one row.
+* **b/deserialize/json** [register]: Treat input as a string and de-serialize it to JSON.
+* **b/deserialize/yaml** [register, safe]: Treat input as a string and de-serialize it to YAML.  By default it will try and [safely de-serialize](https://ruby-doc.org/stdlib-2.6.1/libdoc/psych/rdoc/Psych.html#method-c-safe_load) it (only using core classes).  If you wish to de-serialize it to any class type, pass in `safe: false`
+
+#### IO
+
+* **b/io/exist** [path, short_circuit]: Check to see if a file exists. The path parameter can be interpolated using `Payload#params`.  If short_circuit was set to true (defaults to false) and the file does not exist then the pipeline will be short-circuited.
+* **b/io/read** [binary, path, register]: Read in a local file.  The path parameter can be interpolated using `Payload#params`.  If the contents are binary, pass in `binary: true` to open it up in binary+read mode.
+* **b/io/write** [binary, path, register]: Write to a local file.  The path parameter can be interpolated using `Payload#params`.  If the contents are binary, pass in `binary: true` to open it up in binary+write mode.
+
+#### Serialization
 
+* **b/serialize/csv** [register]: Take an array of arrays and create a CSV.
+* **b/serialize/json** [register]: Convert value to JSON.
+* **b/serialize/yaml** [register]: Convert value to YAML.
+
+#### General
+
+* **b/dummy** []: Do nothing
+* **b/echo** [message]: Write a message to the output.  The message parameter can be interpolated using  `Payload#params`.
+* **b/set** [register, value]: Set the value to any arbitrary value.
+* **b/sleep** [seconds]: Sleep the thread for X number of seconds.
+
+Notes:
+
+* If you see that a job accepts a 'register' attribute/argument, that indicates a job will access and/or mutate the payload.  The register indicates which part of the payload the job will interact with.  This allows jobs to be placed into 'lanes'.  If register is not specified, then the default register is used.
 
 ### Adding & Registering Jobs
 
-Where this library shines is when additional jobs are plugged in.  Burner uses its `Burner::Jobs` class as its class-level registry built with (acts_as_hashable)[https://github.com/bluemarblepayroll/acts_as_hashable]'s acts_as_hashable_factory directive.
+Where this library shines is when additional jobs are plugged in.  Burner uses its `Burner::Jobs` class as its class-level registry built with [acts_as_hashable](https://github.com/bluemarblepayroll/acts_as_hashable)'s acts_as_hashable_factory directive.
 
 Let's say we would like to register a job to parse a CSV:
 
 ````ruby
-class ParseCsv < Burner::Job
-  def perform(output, payload, params)
-    payload.value = CSV.parse(payload.value, headers: true).map(&:to_h)
+class ParseCsv < Burner::JobWithRegister
+  def perform(output, payload)
+    payload[register] = CSV.parse(payload[register], headers: true).map(&:to_h)
 
     nil
   end
@@ -266,17 +296,17 @@ pipeline = {
   jobs: [
     {
       name: :read,
-      type: 'io/read',
+      type: 'b/io/read',
       path: '{input_file}'
     },
     {
       name: :output_id,
-      type: :echo,
+      type: 'b/echo',
       message: 'The job id is: {__id}'
     },
     {
       name: :output_value,
-      type: :echo,
+      type: 'b/echo',
       message: 'The current value is: {__value}'
     },
     {
@@ -285,11 +315,11 @@ pipeline = {
     },
     {
       name: :convert,
-      type: 'serialize/yaml'
+      type: 'b/serialize/yaml'
     },
     {
       name: :write,
-      type: 'io/write',
+      type: 'b/io/write',
       path: '{output_file}'
     }
   ],
@@ -309,7 +339,9 @@ params = {
   output_file: File.join(TEMP_DIR, "#{SecureRandom.uuid}.yaml")
 }
 
-Burner::Pipeline.make(pipeline).execute(output: output, params: params)
+payload = Burner::Payload.new(params: params)
+
+Burner::Pipeline.make(pipeline).execute(output: output, payload: payload)
 ````
 
 ## Contributing

data/burner.gemspec

@@ -8,7 +8,7 @@ Gem::Specification.new do |s|
   s.summary     = 'Declarative and extendable processing pipeline'
 
   s.description = <<-DESCRIPTION
-    This library serves as the skeleton for a processing engine.  It allows you to organize your code into Jobs, then stitch those jobs together as steps.
+    This library serves as the backbone for a configurable processing engine.  It allows you to organize your code into jobs, then stitch those jobs together as steps.
   DESCRIPTION
 
   s.authors     = ['Matthew Ruggio']
@@ -29,7 +29,10 @@ Gem::Specification.new do |s|
   s.required_ruby_version = '>= 2.5'
 
   s.add_dependency('acts_as_hashable', '~>1.2')
+  s.add_dependency('hashematics', '~>1.1')
+  s.add_dependency('hash_math', '~>1.2')
   s.add_dependency('objectable', '~>1.0')
+  s.add_dependency('realize', '~>1.2')
   s.add_dependency('stringento', '~>2.1')
 
   s.add_development_dependency('guard-rspec', '~>4.7')

data/exe/burner

@@ -10,11 +10,10 @@
 
 require 'bundler/setup'
 require 'burner'
-require 'pry'
 
 if ARGV.empty?
-  puts 'Usage: ./exe/burner package.yaml key=value key=value ...'
-  exit
+  warn('Usage: ./exe/burner package.yaml key=value key=value ...')
+  exit 2 # Do not return 1, that is reserved for hard errors.
 end
 
 # This should return exit code of 1 if it raises any hard errors.

data/lib/burner.rb

@@ -9,12 +9,23 @@
 
 require 'acts_as_hashable'
 require 'benchmark'
+require 'csv'
 require 'forwardable'
+require 'hash_math'
+require 'hashematics'
 require 'json'
 require 'objectable'
+require 'realize'
 require 'securerandom'
 require 'singleton'
 require 'stringento'
+require 'time'
 require 'yaml'
 
+# Common/Shared
+require_relative 'burner/modeling'
+require_relative 'burner/side_effects'
+require_relative 'burner/util'
+
+# Main Entrypoint(s)
 require_relative 'burner/cli'

data/lib/burner/cli.rb

@@ -12,20 +12,20 @@ require_relative 'pipeline'
 module Burner
   # Process a single string as a Pipeline.  This is mainly to back the command-line interface.
   class Cli
-    attr_reader :params, :pipeline
+    attr_reader :payload, :pipeline
 
     def initialize(args)
-      path       = args.first
-      cli_params = extract_cli_params(args)
-      config     = read_yaml(path)
-      @pipeline  = Burner::Pipeline.make(jobs: config['jobs'], steps: config['steps'])
-      @params    = (config['params'] || {}).merge(cli_params)
-    end
+      path      = args.first
+      params    = extract_cli_params(args)
+      config    = read_yaml(path)
+      @pipeline = Burner::Pipeline.make(jobs: config['jobs'], steps: config['steps'])
+      @payload  = Payload.new(params: params)
 
-    def execute(output: Output.new, params: {}, payload: Payload.new)
-      final_params = @params.merge(params || {})
+      freeze
+    end
 
-      pipeline.execute(output: output, params: final_params, payload: payload)
+    def execute
+      pipeline.execute(payload: payload)
     end
 
     private

data/lib/burner/job.rb

@@ -7,29 +7,49 @@
 # LICENSE file in the root directory of this source tree.
 #
 
-require_relative 'string_template'
-
 module Burner
   # Abstract base class for all job subclasses.  The only public method a subclass needs to
-  # implement #perform(params, payload, reporter) and then you can register it for use using
+  # implement #perform(output, payload) and then you can register it for use using
   # the Burner::Jobs factory class method #register.  An example of a registration:
   #   Burner::Jobs.register('your_class', YourClass)
   class Job
+    include Util::Arrayable
     acts_as_hashable
 
-    attr_reader :name, :string_template
+    attr_reader :name
 
     def initialize(name:)
       raise ArgumentError, 'name is required' if name.to_s.empty?
 
-      @name            = name.to_s
-      @string_template = StringTemplate.instance
+      @name = name.to_s
+    end
+
+    # There are only a few requirements to be considered a valid Burner Job:
+    #   1. The class responds to #name
+    #   2. The class responds to #perform(output, payload)
+    #
+    # The #perform method takes in two arguments: output (an instance of Burner::Output)
+    # and payload (an instance of Burner::Payload).  Jobs can leverage output to emit
+    # information to the pipeline's log(s).  The payload is utilized to pass data from job to job,
+    # with its most important attribute being #value.  The value attribute is mutable
+    # per the individual job's context (meaning of it is unknown without understanding a job's
+    # input and output value of #value.).  Therefore #value can mean anything and it is up to the
+    # engineers to clearly document the assumptions of its use.
+    #
+    # Returning false will short-circuit the pipeline right after the job method exits.
+    # Returning anything else besides false just means "continue".
+    def perform(output, _payload)
+      output.detail("#perform not implemented for: #{self.class.name}")
+
+      nil
     end
 
-    private
+    protected
+
+    def job_string_template(expression, output, payload)
+      templatable_params = payload.params.merge(__id: output.id, __value: payload[''])
 
-    def eval_string_template(expression, input)
-      string_template.evaluate(expression, input)
+      Util::StringTemplate.instance.evaluate(expression, templatable_params)
     end
   end
 end

data/lib/burner/job_with_register.rb

@@ -0,0 +1,24 @@
+# frozen_string_literal: true
+
+#
+# Copyright (c) 2020-present, Blue Marble Payroll, LLC
+#
+# This source code is licensed under the MIT license found in the
+# LICENSE file in the root directory of this source tree.
+#
+
+require_relative 'job'
+
+module Burner
+  # Add on a register attribute to the configuration for a job.  This indicates that a job
+  # either accesses and/or mutates the payload's registers.
+  class JobWithRegister < Job
+    attr_reader :register
+
+    def initialize(name:, register: '')
+      super(name: name)
+
+      @register = register.to_s
+    end
+  end
+end