dataset_explorer 0.1.1 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 788e4dd9aa7ed70db9482c9eb8c5cc35fabae5039232dc2c10e0276fa97caf14
-  data.tar.gz: 0d14ebb6e7ae2363dfe47236b1a89565fbda381fecb4dc8732448dd27fbe82bf
+  metadata.gz: e0325eced24214509e9177b70341bc1120ea26c5b523918501f2884fdd57c92a
+  data.tar.gz: face9b64530c6b771258d23f512c24955e6bd073d881802d6b538dd0f5b046b7
 SHA512:
-  metadata.gz: eae4397828a7fb6c88da601ed429292893a9925089e37c4b7be57d3879c664605bcdeb40736e27da2522c7a8e1fdd587d91419d59b22fb5912d4b96523a0b1f2
-  data.tar.gz: c41ee84d680ce45f9d22e46b732bf31fc6490b0ded9f18f7ad721df4d91b9670747a83d375fcf78128e7e06e78993f93d5874870882d668940d37e02316d782d
+  metadata.gz: a1c7aa73cd0f51295b1cf01b1ece8e7756c9a5e498a22f475efccecb2036f065844f0564e9fd6c05379cefe35729ec7cdc84aea57577f81c46a17e3ab628586b
+  data.tar.gz: 0d75d122ea2a1696a06215c631e14760b1d6cba3271c73462af85ade96f85b886f72f6fb5a0500fd2794720a5c46509c2d2e4c14ca3e7ab632a00ec4863e6532

data/.rubocop.yml

@@ -7,6 +7,7 @@ Metrics/BlockLength:
     - 'spec/**/*'
 
 Metrics/MethodLength:
+  Max: 15
   Exclude:
    - 'db/migrate/**.rb'
 

data/README.md

@@ -56,82 +56,82 @@ urls = {
 COLLECTOR = DatasetExplorer::Collector.instance
 
 urls.each do |provider, url|
-  data = [JSON.parse(open(url).read)].flatten
-
-  data.each do |item|
-    COLLECTOR.collect(provider, item)
-  end
+  data = JSON.parse(open(url).read)
+  COLLECTOR.collect(provider, data)
 end
 
-explanation = COLLECTOR.explain_all
+COLLECTOR.explain_all(format: :table).each do |type, explanation|
+  puts type
+  puts explanation
+end
 ```
 
 Explanation will be:
 
-```ruby
-{
-  github: [
-    "jekyll",
-    "jekyll-sass-converter",
-    "kramdown",
-    "jekyll-commonmark-ghpages",
-    "liquid",
-    "rouge",
-    "github-pages-health-check",
-    "jekyll-redirect-from",
-    "jekyll-sitemap",
-    "jekyll-feed",
-    "jekyll-gist",
-    "jekyll-paginate",
-    "jekyll-coffeescript",
-    "jekyll-seo-tag",
-    "jekyll-github-metadata",
-    "jekyll-avatar",
-    "jekyll-remote-theme",
-    "jemoji",
-    "jekyll-mentions",
-    "jekyll-relative-links",
-    "jekyll-optional-front-matter",
-    "jekyll-readme-index",
-    "jekyll-default-layout",
-    "jekyll-titles-from-headings",
-    "jekyll-swiss",
-    "minima",
-    "jekyll-theme-primer",
-    "jekyll-theme-architect",
-    "jekyll-theme-cayman",
-    "jekyll-theme-dinky",
-    "jekyll-theme-hacker",
-    "jekyll-theme-leap-day",
-    "jekyll-theme-merlot",
-    "jekyll-theme-midnight",
-    "jekyll-theme-minimal",
-    "jekyll-theme-modernist",
-    "jekyll-theme-slate",
-    "jekyll-theme-tactile",
-    "jekyll-theme-time-machine",
-    "ruby",
-    "github-pages",
-    "html-pipeline",
-    "sass",
-    "safe_yaml",
-    "nokogiri",
-  ],
-  github_repo: [
-    "name",
-    "path",
-    "sha",
-    "size",
-    "url",
-    "html_url",
-    "git_url",
-    "download_url",
-    "type",
-    "_links.self",
-    "_links.git",
-    "_links.html"
-  ]
-}
+```
+github
++------------------------------+--------------------------------------------------------------------------+
+| jekyll                       | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| jekyll-sass-converter        | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| kramdown                     | Possible types: [string], NULL, Min/max Length: 6/6                      |
+| jekyll-commonmark-ghpages    | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| liquid                       | Possible types: [string], NULL, Min/max Length: 5/5                      |
+| rouge                        | Possible types: [string], NULL, Min/max Length: 6/6                      |
+| github-pages-health-check    | Possible types: [string], NULL, Min/max Length: 6/6                      |
+| jekyll-redirect-from         | Possible types: [string], NULL, Min/max Length: 6/6                      |
+| jekyll-sitemap               | Possible types: [string], NULL, Min/max Length: 5/5                      |
+| jekyll-feed                  | Possible types: [string], NULL, Min/max Length: 6/6                      |
+| jekyll-gist                  | Possible types: [string], NULL, Min/max Length: 5/5                      |
+| jekyll-paginate              | Possible types: [string], NULL, Min/max Length: 5/5                      |
+| jekyll-coffeescript          | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| jekyll-seo-tag               | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| jekyll-github-metadata       | Possible types: [string], NULL, Min/max Length: 6/6                      |
+| jekyll-avatar                | Possible types: [string], NULL, Min/max Length: 5/5                      |
+| jekyll-remote-theme          | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| jemoji                       | Possible types: [date, time, string], NULL, Min/max Length: 6/6          |
+| jekyll-mentions              | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| jekyll-relative-links        | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| jekyll-optional-front-matter | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| jekyll-readme-index          | Possible types: [string], NULL, Min/max Length: 5/5                      |
+| jekyll-default-layout        | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| jekyll-titles-from-headings  | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| jekyll-swiss                 | Possible types: [string], NULL, Min/max Length: 5/5                      |
+| minima                       | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| jekyll-theme-primer          | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| jekyll-theme-architect       | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| jekyll-theme-cayman          | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| jekyll-theme-dinky           | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| jekyll-theme-hacker          | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| jekyll-theme-leap-day        | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| jekyll-theme-merlot          | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| jekyll-theme-midnight        | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| jekyll-theme-minimal         | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| jekyll-theme-modernist       | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| jekyll-theme-slate           | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| jekyll-theme-tactile         | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| jekyll-theme-time-machine    | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| ruby                         | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| github-pages                 | Possible types: [date, time, string, integer], NULL, Min/max Length: 3/3 |
+| html-pipeline                | Possible types: [date, time, string], NULL, Min/max Length: 6/6          |
+| sass                         | Possible types: [date, time, string], NULL, Min/max Length: 5/5          |
+| safe_yaml                    | Possible types: [string], NULL, Min/max Length: 5/5                      |
+| nokogiri                     | Possible types: [date, time, string], NULL, Min/max Length: 6/6          |
++------------------------------+--------------------------------------------------------------------------+
+github_repo_contents
++-----------------+---------------------------------------------------------+
+| [].name         | Possible types: [string], NULL, Min/max Length: 2/14    |
+| [].path         | Possible types: [string], NULL, Min/max Length: 2/14    |
+| [].sha          | Possible types: [string], NULL, Min/max Length: 40/40   |
+| [].size         | Possible types: [integer], NULL                         |
+| [].url          | Possible types: [string], NULL, Min/max Length: 75/87   |
+| [].html_url     | Possible types: [string], NULL, Min/max Length: 57/69   |
+| [].git_url      | Possible types: [string], NULL, Min/max Length: 103/103 |
+| [].download_url | Possible types: [string], NULL, Min/max Length: 72/79   |
+| [].type         | Possible types: [string], NULL, Min/max Length: 3/4     |
+| []._links.self  | Possible types: [string], NULL, Min/max Length: 75/87   |
+| []._links.git   | Possible types: [string], NULL, Min/max Length: 103/103 |
+| []._links.html  | Possible types: [string], NULL, Min/max Length: 57/69   |
++-----------------+---------------------------------------------------------+
 ```
 
 Or if you try like this
@@ -155,7 +155,7 @@ data = {
 }
 
 DatasetExplorer::Collector.instance.collect(:achievements, data)
-result = DatasetExplorer::Collector.explain_all(:achievements)
+result = DatasetExplorer::Collector.instance.explain(:achievements).keys
 
 # result is:
 

data/dataset_explorer.gemspec

@@ -28,4 +28,6 @@ Gem::Specification.new do |spec|
   spec.bindir        = 'exe'
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ['lib']
+
+  spec.add_dependency 'terminal-table'
 end

data/lib/dataset_explorer.rb

@@ -1,6 +1,7 @@
 # frozen_string_literal: true
 
 require 'dataset_explorer/version'
+require 'dataset_explorer/value_evaluator'
 require 'dataset_explorer/item_collector'
 require 'dataset_explorer/collector'
 

data/lib/dataset_explorer/collector.rb

@@ -14,14 +14,20 @@ module DatasetExplorer
       collector_for(type).add(item)
     end
 
-    def explain_all
+    def explain_all(format: :hash)
       @collectors.keys.map do |key|
-        [key, explain(key)]
+        [key, explain(key, format: format)]
       end.to_h
     end
 
-    def explain(type)
-      @collectors.fetch(type).values
+    def explain(type, format: :hash)
+      explanation = @collectors.fetch(type).explain
+
+      if format == :table
+        explanation = to_table(explanation)
+      end
+
+      explanation
     end
 
     private
@@ -30,6 +36,14 @@ module DatasetExplorer
       @collectors[type] ||= ItemCollector.new
     end
 
+    def to_table(fields)
+      rows = []
+      fields.each do |key, description|
+        rows << [key, description]
+      end
+      Terminal::Table.new(rows: rows)
+    end
+
     private_class_method :new
   end
 end

data/lib/dataset_explorer/item_collector.rb

@@ -3,10 +3,19 @@
 module DatasetExplorer
   class ItemCollector
     def initialize
-      @values = []
+      @keys = []
+      @evaluators = {}
     end
 
-    attr_reader :values
+    def explain
+      {}.tap do |explanation|
+        @evaluators.each do |field, evaluator|
+          explanation[field] = evaluator.describe
+        end
+      end
+    end
+
+    attr_reader :keys
 
     def add(item)
       unless item.is_a?(Array)
@@ -25,15 +34,17 @@ module DatasetExplorer
         map_keys(item[key], key, prefix)
       end.flatten.map(&:to_s).uniq
 
-      @values << new_values
-      @values = @values.flatten.uniq
+      @keys << new_values
+      @keys = @keys.flatten.uniq
     end
 
     # rubocop:disable Metrics/MethodLength
+    # rubocop:disable Metrics/AbcSize
     def map_keys(value, key = nil, prefix = nil)
       prefix = [prefix, key].compact.join('.')
 
       unless mappable?(value)
+        evaluator_for(prefix).evaluate(value)
         return prefix
       end
 
@@ -45,9 +56,9 @@ module DatasetExplorer
 
       if value.respond_to?(:each)
         prefix = "#{prefix}.[]"
-        return [].tap do |values|
+        return [].tap do |keys|
           value.each do |item_value|
-            values << map_keys(item_value, nil, prefix)
+            keys << map_keys(item_value, nil, prefix)
           end
         end
       end
@@ -55,6 +66,7 @@ module DatasetExplorer
       raise Error, 'Unforseen scenario'
     end
     # rubocop:enable Metrics/MethodLength
+    # rubocop:enable Metrics/AbcSize
 
     def mappable?(value)
       if behaves_like_hash?(value)
@@ -75,5 +87,9 @@ module DatasetExplorer
     def behaves_like_array?(value)
       value.respond_to?(:each)
     end
+
+    def evaluator_for(field)
+      @evaluators[field.to_s] ||= ValueEvaluator.new(field)
+    end
   end
 end

data/lib/dataset_explorer/value_evaluator.rb

@@ -0,0 +1,134 @@
+# frozen_string_literal: true
+
+require 'date'
+require 'time'
+require 'terminal-table'
+
+module DatasetExplorer
+  class ValueEvaluator
+    attr_reader :min_length
+    attr_reader :max_length
+
+    def initialize(field_name)
+      @field_name = field_name
+      @null = true
+      @evaluators = {
+        'date' => DateEvaluator.new,
+        'time' => TimeEvaluator.new,
+        'string' => StringEvaluator.new,
+        'float' => FloatEvaluator.new,
+        'integer' => IntegerEvaluator.new,
+        'boolean' => BooleanEvaluator.new
+      }
+      @min_length = nil
+      @max_length = nil
+    end
+
+    def evaluate(value)
+      if value.nil?
+        @null = true
+        return
+      end
+
+      evaluate_length(value)
+
+      @evaluators.each do |key, evaluator|
+        unless evaluator.accept?(value)
+          @evaluators.delete(key)
+        end
+      end
+    end
+
+    def types
+      @evaluators.keys
+    end
+
+    def describe
+      parts = ["Possible types: [#{types.join(', ')}]"]
+      if @null
+        parts << 'NULL'
+      end
+
+      if min_length
+        parts << "Min/max Length: #{min_length}/#{max_length}"
+      end
+
+      parts.join(', ')
+    end
+
+    def evaluate_length(value)
+      unless value.respond_to?(:length)
+        return
+      end
+
+      length = value.length
+      @min_length ||= length
+      @max_length ||= length
+
+      if @min_length > length
+        @min_length = length
+      end
+
+      if @max_length < length
+        @max_length = length
+      end
+    end
+
+    class TimeEvaluator
+      def accept?(value)
+        if value.is_a?(String)
+          return Time.parse(value.to_s)
+        end
+
+        value.is_a?(Time)
+      rescue ArgumentError
+        false
+      end
+    end
+
+    class DateEvaluator
+      def accept?(value)
+        if value.is_a?(String)
+          return Date.parse(value.to_s)
+        end
+
+        value.is_a?(Date)
+      rescue ArgumentError
+        false
+      end
+    end
+
+    class StringEvaluator
+      def accept?(value)
+        value.is_a?(String)
+      end
+    end
+
+    class FloatEvaluator
+      def accept?(value)
+        Float(value).to_s == value.to_s
+      rescue ArgumentError, TypeError
+        false
+      end
+    end
+
+    class IntegerEvaluator
+      def accept?(value)
+        Integer(value)
+      rescue ArgumentError, TypeError
+        false
+      end
+    end
+
+    class BooleanEvaluator
+      ACCEPT = %w[
+        true
+        false
+      ].freeze
+
+      def accept?(value)
+        ACCEPT.include?(value.to_s.downcase)
+      end
+    end
+  end
+end

data/lib/dataset_explorer/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module DatasetExplorer
-  VERSION = '0.1.1'
+  VERSION = '1.0.0'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: dataset_explorer
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 1.0.0
 platform: ruby
 authors:
 - Marcelo Jacobus
@@ -9,7 +9,21 @@ autorequire:
 bindir: exe
 cert_chain: []
 date: 2020-05-25 00:00:00.000000000 Z
-dependencies: []
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: terminal-table
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: Explore and maps fields from a dataset - I.E. Api response
 email:
 - marcelo.jacobus@gmail.com
@@ -32,6 +46,7 @@ files:
 - lib/dataset_explorer.rb
 - lib/dataset_explorer/collector.rb
 - lib/dataset_explorer/item_collector.rb
+- lib/dataset_explorer/value_evaluator.rb
 - lib/dataset_explorer/version.rb
 homepage: https://github.com/mjacobus/dataset_explorer
 licenses: