json-streamer 1.3.0 → 2.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: aac1b068e94999ad0ef0f317d819273b14069fdf
-  data.tar.gz: e9245d59c50a842953d63bfedb3aed2859b15c75
+  metadata.gz: 16e5cef72d5fa26617ed43d67982c956bf00942f
+  data.tar.gz: 067e090f2a1ec4f2a259e51b5c5a078652fd08cf
 SHA512:
-  metadata.gz: 93f9766a9086fb81f43e96f3d2c267b434148b9bcdb3bfdef2595a187507f056494b9a00955cc29a49cfc6f56883a7b04cb5d601f66661e9366203b576c71b9f
-  data.tar.gz: b5c174919a39b4b8d03ee05a6888e0b6cf134335bf3bf2ccdeaebda88fa0a1eeb8eae99875ba8e72d7e68f7b80f2e8505030570a92aa668a1912c74ee9370210
+  metadata.gz: 15cb106e6a78fc4271e4ec250279f5b1c10534e89e24ef9e5517617e1356e1b8903ecff3047d2d93466e87a085d0392e15cb46101cee87b3e1e2b879d8f36517
+  data.tar.gz: 15d3415923f32b5d2cb7edcb093e9b6ec1a7bda307ea4ace1a4fadb9710a49b89a22e421b6c8b513134d4a8de36c528f648253ec91fbceb3232e9a964442fc60

data/Guardfile

@@ -0,0 +1,20 @@
+guard 'bundler' do
+  watch('Gemfile')
+end
+
+guard 'rspec', cmd: "bundle exec spring rspec #{ENV['FOCUS']}", all_after_pass: ENV['FOCUS'].nil? do
+  watch(%r{^spec/.+_spec\.rb$})
+  watch(%r{^lib/(.+)\.rb$})                           { |m| "spec/lib/#{m[1]}_spec.rb" }
+  watch('spec/spec_helper.rb')                        { 'spec' }
+
+  watch(%r{^app/(.+)\.rb$})                           { |m| "spec/#{m[1]}_spec.rb" }
+  watch(%r{^app/(.*)(\.erb|\.haml)$})                 { |m| "spec/#{m[1]}#{m[2]}_spec.rb" }
+  watch(%r{^app/models/(.+)\.rb$})                    { |m| "spec/builders/#{m[1]}_builder_spec.rb" }
+  watch(%r{^app/controllers/(.+)_(controller)\.rb$})  { |m| ["spec/routing/#{m[1]}_routing_spec.rb", "spec/#{m[2]}s/#{m[1]}_#{m[2]}_spec.rb", "spec/acceptance/#{m[1]}_spec.rb"] }
+  watch(%r{^spec/support/(.+)\.rb$})                  { 'spec' }
+  watch(%r{^spec/factories/(.+)\.rb$})                { 'spec' }
+  watch('config/routes.rb')                           { 'spec/routing' }
+  watch('app/controllers/application_controller.rb')  { 'spec/controllers' }
+
+  watch(%r{^app/views/(.+)/.*\.(erb|haml)$})          { |m| "spec/requests/#{m[1]}_spec.rb" }
+end

data/README.md

@@ -80,7 +80,7 @@ Input:
 ```
 
 Output:
-```json
+```ruby
 "first_level_value"
 {}
 ```
@@ -109,11 +109,11 @@ Input:
 ```
 
 Output:
-```json
+```ruby
 "value1"
 "value2"
 "value3"
-{"desired_key" : "value3"}
+{"desired_key" => "value3"}
 ```
 
 #### Skip values
@@ -155,7 +155,7 @@ Input:
 ```
 
 Output:
-```json
+```ruby
 {:obj1=>{:key=>"value"}}
 ```
 
@@ -179,6 +179,71 @@ def receive_data(data)
 end
 ```
 
+#### Custom yield conditions
+
+[v2.0.0](https://github.com/thisismydesign/json-streamer/releases/tag/v2.0.0) introduces custom conditions which provide ultimate control over what to yield.
+
+The Conditions API exposes 3 callbacks:
+- `yield_value`
+- `yield_array`
+- `yield_object`
+
+Each of them may be redefined. They are called once the corresponding data (value, array or object) is available. They should return whether the data should be yielded for the outside. They receive the data and the `aggregator` as parameters.
+
+The `aggregator` exposes data about the current state of the partly parsed JSON such as:
+- `level` - current level
+- `key` - current key
+- `value` - current value
+- `key_for_level(level)` - key for custom level
+- `value_for_level(level)` - value for custom level
+- `get` - the raw data (in a custom format)
+
+Example usage (inspired by [this issue](https://github.com/thisismydesign/json-streamer/issues/7#issuecomment-330232484)):
+
+```ruby
+conditions = Json::Streamer::Conditions.new
+conditions.yield_value = ->(aggregator:, value:) { false }
+conditions.yield_array = ->(aggregator:, array:) { false }
+conditions.yield_object = lambda do |aggregator:, object:|
+    aggregator.level.eql?(2) && aggregator.key_for_level(1).eql?('items1')
+end
+
+streamer.get_with_conditions(conditions) do |object|
+    p object
+end
+```
+
+Input:
+
+```ruby
+{
+  "other": "stuff",
+  "items1": [
+    {
+      "key1": "value"
+    },
+    {
+      "key2": "value"
+    }
+  ],
+  "items2": [
+    {
+      "key3": "value"
+    },
+    {
+      "key4": "value"
+    }
+  ]
+}
+```
+
+Output:
+
+```ruby
+{"key1"=>"value"}
+{"key2"=>"value"}
+```
+
 ### Legacy API (pre-v1.2)
 
 This functionality is deprecated but kept for compatibility reasons.

data/json-streamer.gemspec

@@ -27,6 +27,9 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "coveralls"
   spec.add_development_dependency "ndhash"
   spec.add_development_dependency "get_process_mem"
+  spec.add_development_dependency "guard"
+  spec.add_development_dependency "guard-bundler"
+  spec.add_development_dependency "guard-rspec"
 
   spec.add_dependency "json-stream"
 end

data/lib/json/streamer/aggregator.rb

@@ -0,0 +1,56 @@
+require 'forwardable'
+
+module Json
+  module Streamer
+    class Aggregator
+      extend Forwardable
+      def_delegators :@aggregator, :pop, :push, :empty?
+
+      def initialize
+        @aggregator = []
+      end
+
+      def get
+        @aggregator
+      end
+
+      def level
+        @aggregator.size
+      end
+
+      def key
+        @aggregator.last[:key] unless @aggregator.last.nil?
+      end
+
+      def key=(k)
+        @aggregator.last[:key] = k
+      end
+
+      def value
+        @aggregator.last[:value]
+      end
+
+      def value=(d)
+        if array_level?
+          value << d
+        else
+          value[key] = d
+        end
+      end
+
+      def key_for_level(level)
+        @aggregator[level - 1][:key] unless @aggregator[level - 1].nil?
+      end
+
+      def value_for_level(level)
+        @aggregator[level - 1][:key] unless @aggregator[level - 1].nil?
+      end
+
+      private
+
+      def array_level?
+        value.is_a?(Array)
+      end
+    end
+  end
+end

data/lib/json/streamer/callbacks.rb

@@ -0,0 +1,55 @@
+module Json
+  module Streamer
+    class Callbacks
+      attr_reader :aggregator
+
+      def initialize(aggregator)
+        @aggregator = aggregator
+      end
+
+      def start_object
+        new_level(Hash.new)
+      end
+
+      def start_array
+        new_level(Array.new)
+      end
+
+      def key(k, symbolize_keys)
+        @aggregator.key = symbolize_keys ? k.to_sym : k
+      end
+
+      def value(value)
+        used = yield value
+        add_value(value) unless used
+      end
+
+      def end_object
+        end_level { |obj| yield obj }
+      end
+
+      def end_array
+        end_level { |obj| yield obj }
+      end
+
+      private
+
+      def end_level
+        data = @aggregator.value.clone
+
+        @aggregator.pop
+
+        used = yield data
+        add_value(data) unless used or @aggregator.empty?
+      end
+
+      def add_value(value)
+        @aggregator.value = value
+      end
+
+      def new_level(type)
+        @aggregator.push(value: type)
+      end
+    end
+  end
+end

data/lib/json/streamer/conditions.rb

@@ -0,0 +1,22 @@
+module Json
+  module Streamer
+    class Conditions
+      attr_accessor :yield_value, :yield_object, :yield_array
+
+      def initialize(yield_level: -1, yield_key: nil)
+        @yield_level = yield_level
+        @yield_key = yield_key
+
+        @yield_value = ->(aggregator:, value:nil) { yield?(aggregator) }
+        @yield_object = ->(aggregator:, object:nil) { yield?(aggregator) }
+        @yield_array = ->(aggregator:, array:nil) { yield?(aggregator) }
+      end
+
+      private
+
+      def yield?(aggregator)
+        aggregator.level.eql?(@yield_level) or (not @yield_key.nil? and @yield_key == aggregator.key)
+      end
+    end
+  end
+end

data/lib/json/streamer/json_streamer.rb

@@ -1,143 +1,57 @@
 require "json/stream"
 
+require_relative 'conditions'
+require_relative 'parser'
+
 module Json
   module Streamer
     class JsonStreamer
 
-      attr_reader :aggregator
       attr_reader :parser
 
       def initialize(file_io = nil, chunk_size = 1000)
-        @parser = JSON::Stream::Parser.new
+        @event_generator = JSON::Stream::Parser.new
 
         @file_io = file_io
         @chunk_size = chunk_size
-
-        @current_level = -1
-        @aggregator = {}
-        @aggregator_keys = {}
-
-        @parser.start_object {start_object}
-        @parser.start_array {start_array}
-        @parser.key {|k| key(k)}
       end
 
       def <<(data)
-        @parser << data
+        parser << data
       end
 
-      # Callbacks containing `yield` have to be defined in the method called via block otherwise yield won't work
       def get(nesting_level: -1, key: nil, yield_values: true, symbolize_keys: false)
-        @yield_level = nesting_level
-        @yield_key = key
-        @yield_values = yield_values
-        @symbolize_keys = symbolize_keys
-
-        @parser.value do |v|
-          value(v) { |desired_object| yield desired_object }
-        end
-
-        @parser.end_object do
-          end_level(Hash.new) { |desired_object| yield desired_object }
-        end
-
-        @parser.end_array do
-          end_level(Array.new) { |desired_object| yield desired_object }
-        end
-
-        @file_io.each(@chunk_size) { |chunk| @parser << chunk } if @file_io
-      end
-
-      def start_object
-        new_level(Hash.new)
-      end
-
-      def start_array
-        new_level(Array.new)
-      end
-
-      def key(k)
-        @current_key = @symbolize_keys ? k.to_sym : k
-      end
-
-      def value(value)
-        reset_current_key if array_level?(@current_level)
-        yield value if yield_value?
-        add_value(value)
-      end
+        conditions = Conditions.new(yield_level: nesting_level, yield_key: key)
+        conditions.yield_value = ->(aggregator:, value:) { false } unless yield_values
 
-      def add_value(value)
-        if array_level?(@current_level)
-          @aggregator[@current_level] << value
-        else
-          @aggregator[@current_level][@current_key] = value
-        end
-      end
+        # TODO: deprecate symbolize_keys and move to initialize
+        @parser = Parser.new(@event_generator, symbolize_keys: symbolize_keys)
 
-      def end_level(type)
-        if yield_object?
-          yield @aggregator[@current_level].clone
-          reset_current_level(type)
-        else
-          merge_up
+        parser.get(conditions) do |obj|
+          yield obj
         end
 
-        @current_level -= 1
-      end
-
-      def yield_object?
-        @current_level.eql?(@yield_level) or (not @yield_key.nil? and @yield_key == previous_key)
-      end
-
-      def yield_value?
-        @yield_values and ((next_level).eql?(@yield_level) or (not @yield_key.nil? and @yield_key == @current_key))
-      end
-
-      def new_level(type)
-        reset_current_key if array_level?(@current_level)
-        set_aggregator_key
-        @current_level += 1
-        reset_current_level(type)
+        process_io
       end
 
-      def reset_current_level(type)
-        @aggregator[@current_level] = type
-      end
-
-      def set_aggregator_key
-        @aggregator_keys[@current_level] = @current_key
-      end
-
-      def reset_current_key
-        @current_key = nil
-      end
+      def get_with_conditions(conditions, options = {})
+        @parser = Parser.new(@event_generator, symbolize_keys: options[:symbolize_keys])
 
-      def array_level?(nesting_level)
-        @aggregator[nesting_level].is_a?(Array)
-      end
-
-      def merge_up
-        return if @current_level.zero?
-
-        if array_level?(previous_level)
-          @aggregator[previous_level] << @aggregator[@current_level]
-        else
-          @aggregator[previous_level][previous_key] = @aggregator[@current_level]
+        parser.get(conditions) do |obj|
+          yield obj
         end
 
-        @aggregator.delete(@current_level)
+        process_io
       end
 
-      def previous_level
-        @current_level - 1
+      def aggregator
+        parser.aggregator
       end
 
-      def next_level
-        @current_level + 1
-      end
+      private
 
-      def previous_key
-        @aggregator_keys[previous_level]
+      def process_io
+        @file_io.each(@chunk_size) { |chunk| parser << chunk } if @file_io
       end
     end
   end

data/lib/json/streamer/parser.rb

@@ -0,0 +1,51 @@
+require_relative 'aggregator'
+require_relative 'callbacks'
+
+module Json
+  module Streamer
+    class Parser
+      def initialize(event_generator, options = {})
+        @event_generator = event_generator
+        @symbolize_keys = options[:symbolize_keys]
+
+        @aggregator = Aggregator.new
+        @event_consumer = Callbacks.new(@aggregator)
+      end
+
+      def get(conditions)
+        @event_generator.start_object { @event_consumer.start_object }
+        @event_generator.start_array { @event_consumer.start_array }
+
+        @event_generator.key do |k|
+          @event_consumer.key(k, @symbolize_keys)
+        end
+
+        @event_generator.value do |v|
+          @event_consumer.value(v) do |value|
+            yield value if conditions.yield_value.call(aggregator: @aggregator, value: value)
+          end
+        end
+
+        @event_generator.end_object do
+          @event_consumer.end_object do |object|
+            yield object if conditions.yield_object.call(aggregator: @aggregator, object: object)
+          end
+        end
+
+        @event_generator.end_array do
+          @event_consumer.end_array do |array|
+            yield array if conditions.yield_array.call(aggregator: @aggregator, array: array)
+          end
+        end
+      end
+
+      def <<(data)
+        @event_generator << data
+      end
+
+      def aggregator
+        @aggregator.get
+      end
+    end
+  end
+end

data/lib/json/streamer/version.rb

@@ -1,5 +1,5 @@
 module Json
   module Streamer
-    VERSION = "1.3.0"
+    VERSION = "2.0.0"
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: json-streamer
 version: !ruby/object:Gem::Version
-  version: 1.3.0
+  version: 2.0.0
 platform: ruby
 authors:
 - thisismydesign
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2017-09-16 00:00:00.000000000 Z
+date: 2017-09-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -94,6 +94,48 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: guard
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: guard-bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: guard-rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: json-stream
   requirement: !ruby/object:Gem::Requirement
@@ -121,6 +163,7 @@ files:
 - ".travis.yml"
 - CODE_OF_CONDUCT.md
 - Gemfile
+- Guardfile
 - LICENSE.txt
 - README.md
 - Rakefile
@@ -128,7 +171,11 @@ files:
 - bin/setup
 - json-streamer.gemspec
 - lib/json/streamer.rb
+- lib/json/streamer/aggregator.rb
+- lib/json/streamer/callbacks.rb
+- lib/json/streamer/conditions.rb
 - lib/json/streamer/json_streamer.rb
+- lib/json/streamer/parser.rb
 - lib/json/streamer/version.rb
 homepage: https://github.com/thisismydesign/json-streamer
 licenses: