burner 1.0.0.pre.alpha.6 → 1.0.0.pre.alpha.11

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 73263c161bce669b99286160acb7129d33c529162da964b72fd34321cc7e3724
-  data.tar.gz: 18fd59799a73d9a8a3bf691a9dd3f8a004d442b37862bf83cbe347fbddd7e49a
+  metadata.gz: adf7e5e1ea0c19d59b6edcbb1c5073e25f533bf32076df4ec7d9122edc852958
+  data.tar.gz: 40009afdb93c5ee3971513971dd47a8f416acd04b33eb0c8e9720806cce4a515
 SHA512:
-  metadata.gz: 7db0c2be13a882885b97681ec7c9fd60b6702368d673d97ba0aa484b446db0c77c9f823adf03c8d9e970b2078b43a99d2d159ba97df345124a461497718b7046
-  data.tar.gz: 509382aa7fb48e116b8b3eb145a8b8226c1e4d4282eec1aabb10dcc9f7b333b906a7887d97cee4a96ae730dd7c02a0b0d4cd4a7b06dbfcc90349cfd82767e048
+  metadata.gz: cf255e3021e975451354a3d9537b464ffc61843c59b780ceace9dc6be04e4e2499f5d874aa905608ed3c4b60c4989e6bb3c8cccd2116e8286ca045ea4202bea7
+  data.tar.gz: 569a44eb9a5915d946b4de3038ead60094b170481583ea6974391eedaba209162df03883757b917b2e9c3ed3be6d8c2f80f64f43e6420d5fbc2d711eedc81a8c

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}'
     }
   ],
@@ -172,25 +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:
@@ -233,39 +233,43 @@ This library only ships with very basic, rudimentary jobs that are meant to just
 
 #### Collection
 
-* **collection/arrays_to_objects** [mappings]: Convert an array of arrays to an array of objects.
-* **collection/graph** [config, key]: Use [Hashematics](https://github.com/bluemarblepayroll/hashematics) to turn a flat array of objects into a deeply nested object tree.
-* **collection/objects_to_arrays** [mappings]: Convert an array of objects to an array of arrays.
-* **collection/shift** [amount]: Remove the first N number of elements from an array.
-* **collection/transform** [attributes, exclusive, separator]: 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.
-* **collection/unpivot** [pivot_set]: 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).
-* **collection/values** [include_keys]: 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.
+* **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
 
-* **deserialize/csv** []: 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.
-* **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`
+* **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
 
-* **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.
-* **io/read** [binary, path]: 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.
-* **io/write** [binary, path]: 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.
+* **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
 
-* **serialize/csv** []: Take an array of arrays and create a CSV.
-* **serialize/json** []: Convert value to JSON.
-* **serialize/yaml** []: Convert value to YAML.
+* **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
 
-* **dummy** []: Do nothing
-* **echo** [message]: Write a message to the output.  The message parameter can be interpolated using  `Payload#params`.
-* **set** [value]: Set the value to any arbitrary value.
-* **sleep** [seconds]: Sleep the thread for X number of seconds.
+* **b/echo** [message]: Write a message to the output.  The message parameter can be interpolated using  `Payload#params`.
+* **b/nothing** []: Do nothing.
+* **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
 
@@ -274,9 +278,9 @@ Where this library shines is when additional jobs are plugged in.  Burner uses i
 Let's say we would like to register a job to parse a CSV:
 
 ````ruby
-class ParseCsv < Burner::Job
+class ParseCsv < Burner::JobWithRegister
   def perform(output, payload)
-    payload.value = CSV.parse(payload.value, headers: true).map(&:to_h)
+    payload[register] = CSV.parse(payload[register], headers: true).map(&:to_h)
 
     nil
   end
@@ -292,17 +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}'
     },
     {
@@ -311,11 +315,11 @@ pipeline = {
     },
     {
       name: :convert,
-      type: 'serialize/yaml'
+      type: 'b/serialize/yaml'
     },
     {
       name: :write,
-      type: 'io/write',
+      type: 'b/io/write',
       path: '{output_file}'
     }
   ],

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']

data/lib/burner/job.rb

@@ -7,11 +7,9 @@
 # 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
@@ -26,17 +24,18 @@ module Burner
       @name = name.to_s
     end
 
-    # There are only two requirements to be considered a valid Burner Job:
+    # 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.
+    # with its most important attribute being #registers.  The registers attribute is a mutable
+    # and accessible hash per the individual job's context
+    # (meaning of it is unknown without understanding a job's input and output value
+    # of #registers.).  Therefore #register key values can mean anything
+    # and it is up to consumers 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".
@@ -49,9 +48,15 @@ module Burner
     protected
 
     def job_string_template(expression, output, payload)
-      templatable_params = payload.params.merge(__id: output.id, __value: payload.value)
+      templatable_params = payload.params
+                                  .merge(__id: output.id)
+                                  .merge(templatable_register_values(payload))
+
+      Util::StringTemplate.instance.evaluate(expression, templatable_params)
+    end
 
-      StringTemplate.instance.evaluate(expression, templatable_params)
+    def templatable_register_values(payload)
+      payload.registers.transform_keys { |key| "__#{key}_register" }
     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

data/lib/burner/jobs.rb

@@ -16,25 +16,32 @@ module Burner
   class Jobs
     acts_as_hashable_factory
 
-    register 'collection/arrays_to_objects', Library::Collection::ArraysToObjects
-    register 'collection/graph',             Library::Collection::Graph
-    register 'collection/objects_to_arrays', Library::Collection::ObjectsToArrays
-    register 'collection/shift',             Library::Collection::Shift
-    register 'collection/transform',         Library::Collection::Transform
-    register 'collection/unpivot',           Library::Collection::Unpivot
-    register 'collection/values',            Library::Collection::Values
-    register 'deserialize/csv',              Library::Deserialize::Csv
-    register 'deserialize/json',             Library::Deserialize::Json
-    register 'deserialize/yaml',             Library::Deserialize::Yaml
-    register 'dummy', '',                    Library::Dummy
-    register 'echo',                         Library::Echo
-    register 'io/exist',                     Library::IO::Exist
-    register 'io/read',                      Library::IO::Read
-    register 'io/write',                     Library::IO::Write
-    register 'serialize/csv',                Library::Serialize::Csv
-    register 'serialize/json',               Library::Serialize::Json
-    register 'serialize/yaml',               Library::Serialize::Yaml
-    register 'set_value',                    Library::SetValue
-    register 'sleep',                        Library::Sleep
+    # Nothing is the default as noted by the ''.  This means if a type is omitted, nil, or blank
+    # string then the nothing job will be used.
+    register 'b/echo',                         Library::Echo
+    register 'b/nothing', '',                  Library::Nothing
+    register 'b/set_value',                    Library::SetValue
+    register 'b/sleep',                        Library::Sleep
+
+    register 'b/collection/arrays_to_objects', Library::Collection::ArraysToObjects
+    register 'b/collection/graph',             Library::Collection::Graph
+    register 'b/collection/objects_to_arrays', Library::Collection::ObjectsToArrays
+    register 'b/collection/shift',             Library::Collection::Shift
+    register 'b/collection/transform',         Library::Collection::Transform
+    register 'b/collection/unpivot',           Library::Collection::Unpivot
+    register 'b/collection/values',            Library::Collection::Values
+    register 'b/collection/validate',          Library::Collection::Validate
+
+    register 'b/deserialize/csv',              Library::Deserialize::Csv
+    register 'b/deserialize/json',             Library::Deserialize::Json
+    register 'b/deserialize/yaml',             Library::Deserialize::Yaml
+
+    register 'b/io/exist',                     Library::IO::Exist
+    register 'b/io/read',                      Library::IO::Read
+    register 'b/io/write',                     Library::IO::Write
+
+    register 'b/serialize/csv',                Library::Serialize::Csv
+    register 'b/serialize/json',               Library::Serialize::Json
+    register 'b/serialize/yaml',               Library::Serialize::Yaml
   end
 end

data/lib/burner/library.rb

@@ -7,24 +7,30 @@
 # LICENSE file in the root directory of this source tree.
 #
 
-require_relative 'job'
+require_relative 'job_with_register'
+
+require_relative 'library/echo'
+require_relative 'library/nothing'
+require_relative 'library/set_value'
+require_relative 'library/sleep'
+
 require_relative 'library/collection/arrays_to_objects'
 require_relative 'library/collection/graph'
 require_relative 'library/collection/objects_to_arrays'
 require_relative 'library/collection/shift'
 require_relative 'library/collection/transform'
 require_relative 'library/collection/unpivot'
+require_relative 'library/collection/validate'
 require_relative 'library/collection/values'
+
 require_relative 'library/deserialize/csv'
 require_relative 'library/deserialize/json'
 require_relative 'library/deserialize/yaml'
-require_relative 'library/dummy'
-require_relative 'library/echo'
+
 require_relative 'library/io/exist'
 require_relative 'library/io/read'
 require_relative 'library/io/write'
+
 require_relative 'library/serialize/csv'
 require_relative 'library/serialize/json'
 require_relative 'library/serialize/yaml'
-require_relative 'library/set_value'
-require_relative 'library/sleep'

data/lib/burner/library/collection/arrays_to_objects.rb

@@ -14,8 +14,8 @@ module Burner
       # Burner::Modeling::KeyIndexMapping instances or hashable configurations which specifies
       # the index-to-key mappings to use.
       #
-      # Expected Payload#value input: array of arrays.
-      # Payload#value output: An array of hashes.
+      # Expected Payload[register] input: array of arrays.
+      # Payload[register] output: An array of hashes.
       #
       # An example using a configuration-first pipeline:
       #
@@ -23,14 +23,14 @@ module Burner
       #     jobs: [
       #       {
       #         name: 'set',
-      #         type: 'set_value',
+      #         type: 'b/set_value',
       #         value: [
       #           [1, 'funky']
       #         ]
       #       },
       #       {
       #         name: 'map',
-      #         type: 'collection/arrays_to_objects',
+      #         type: 'b/collection/arrays_to_objects',
       #         mappings: [
       #           { index: 0, key: 'id' },
       #           { index: 1, key: 'name' }
@@ -38,7 +38,7 @@ module Burner
       #       },
       #       {
       #         name: 'output',
-      #         type: 'echo',
+      #         type: 'b/echo',
       #         message: 'value is currently: {__value}'
       #       },
       #
@@ -47,11 +47,16 @@ module Burner
       #   }
       #
       #   Burner::Pipeline.make(config).execute
-      class ArraysToObjects < Job
+      #
+      # Given the above example, the expected output would be:
+      #  [
+      #    { 'id' => 1, 'name' => 'funky' }
+      #  ]
+      class ArraysToObjects < JobWithRegister
         attr_reader :mappings
 
-        def initialize(name:, mappings: [])
-          super(name: name)
+        def initialize(name:, mappings: [], register: '')
+          super(name: name, register: register)
 
           @mappings = Modeling::KeyIndexMapping.array(mappings)
 
@@ -59,9 +64,7 @@ module Burner
         end
 
         def perform(_output, payload)
-          payload.value = array(payload.value).map { |array| index_to_key_map(array) }
-
-          nil
+          payload[register] = array(payload[register]).map { |array| index_to_key_map(array) }
         end
 
         private

data/lib/burner/library/collection/graph.rb

@@ -13,13 +13,13 @@ module Burner
       # Take an array of (denormalized) objects and create an object hierarchy from them.
       # Under the hood it uses Hashematics: https://github.com/bluemarblepayroll/hashematics.
       #
-      # Expected Payload#value input: array of objects.
-      # Payload#value output: An array of objects.
-      class Graph < Job
+      # Expected Payload[register] input: array of objects.
+      # Payload[register] output: An array of objects.
+      class Graph < JobWithRegister
         attr_reader :key, :groups
 
-        def initialize(name:, key:, config: Hashematics::Configuration.new)
-          super(name: name)
+        def initialize(name:, key:, config: Hashematics::Configuration.new, register: '')
+          super(name: name, register: register)
 
           raise ArgumentError, 'key is required' if key.to_s.empty?
 
@@ -30,13 +30,11 @@ module Burner
         end
 
         def perform(output, payload)
-          graph = Hashematics::Graph.new(groups).add(array(payload.value))
+          graph = Hashematics::Graph.new(groups).add(array(payload[register]))
 
           output.detail("Graphing: #{key}")
 
-          payload.value = graph.data(key)
-
-          nil
+          payload[register] = graph.data(key)
         end
       end
     end