datanorm 0.0.1 → 1.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f44ab02c4041e106b7e120a1eae889c7d3e1384c4dbaedd6adea4bc86a0d1895
-  data.tar.gz: 338c389dded4de592d34d9730080bbf800052c32359a2294fea1aaa45d25b99b
+  metadata.gz: 9bc247f6b5cf0caa87be3451f4d2e90a72aba5ad997a00366d48d36f02b2b53d
+  data.tar.gz: 2f37db8b1e291a729c848a9fb6c2c5f8b1ec18985e2c6bc5f407a7ac06915c58
 SHA512:
-  metadata.gz: 342576af02ba6ae033e97090908944045896e2bd2df1e496ec83e08835945e737051a62d139300dd10f1d9711ac1e88901e94715e0d060024390975ed2e10e39
-  data.tar.gz: 535491f2403475fb0227e6e4e81db3b4c43bb512b70640d04852a110359c74816d1ec3b02ab959a7d83a9fed62269a54a21401efb7db1a24025e629d3c7f271b
+  metadata.gz: 06e36c422c1067c51217608f4c59b7112ae0342a4b3fae8d3f19e820c89be79363698c2e8ab39f4749243b9822739a4d752dbf785e080f45402ae44121682a07
+  data.tar.gz: 51b569323216339000c189c7c17744e403a8706ffb80095a3aec702413740d25f8f823477b5214b703779884893247f22c24d1a2fed9d3d45f6fb7e6df608f99

data/README.md

@@ -94,7 +94,27 @@ I went for a parsing mechanism that works every time, with every file, at the ex
 
 If you have a `DATANORM.001` and also a `DATPREIS.001`, you must concatenate those two files into one file first (their versions need to be the same). The resulting, merged file is what you provide to this Rubygem.
 
-If you want one product at a time, without having to deal with the complexities of Datanorm, you can use this:
+### Quick Usage
+
+If you want one product at a time (without having to deal with the complexities of Datanorm), you can use this:
+
+```ruby
+document = Datanorm::Document.new(path: 'datanorm.001')
+
+puts document.header
+puts document.version
+
+document.each do |product|
+  puts product.title
+  puts product.to_json
+end
+```
+
+Notice that it can take a long time until the first product is yielded due to the preprocessing that takes place at first.
+
+### Usage with Progress
+
+ If you want to see the progress, you can use the following:
 
 ```ruby
 document = Datanorm::Document.new(path: 'datanorm.001')
@@ -102,7 +122,7 @@ document = Datanorm::Document.new(path: 'datanorm.001')
 puts document.header
 puts document.version
 
-document.each do |product, progress|
+document.each(yield_progress: true) do |product, progress|
   # Once pre-processing is complete, you'll start to get products here
   puts product # <- can be nil in the beginning
 
@@ -111,6 +131,8 @@ document.each do |product, progress|
 end
 ```
 
+### Bare Datanorm parsing
+
 In case you only want the raw Datanorm file one line at a time as Ruby Objects, you can use this:
 
 ```ruby

data/lib/datanorm/document.rb

@@ -28,13 +28,13 @@ module Datanorm
       file.version
     end
 
-    def each(&)
+    def each(yield_progress: false, &)
       unless @preprocessed
-        ::Datanorm::Documents::Preprocess.call(file:, workdir:, &)
+        ::Datanorm::Documents::Preprocess.call(file:, workdir:, yield_progress:, &)
         @preprocessed = true
       end
 
-      ::Datanorm::Documents::Assemble.call(workdir:, &)
+      ::Datanorm::Documents::Assemble.call(workdir:, yield_progress:, &)
     ensure
       # At this point all yields have gone through and we can clean up.
       workdir.rmtree unless ENV['DEBUG_DATANORM']

data/lib/datanorm/documents/assemble.rb

@@ -8,13 +8,19 @@ module Datanorm
       include ::Datanorm::Logging
 
       option :workdir
+      option :yield_progress, default: -> { false }
 
       def call
         return unless products_file.file?
 
         ::File.foreach(products_file) do |json|
           progress.increment!
-          yield ::Datanorm::Documents::Assembles::Product.new(json:, workdir:), progress
+
+          if yield_progress
+            yield ::Datanorm::Documents::Assembles::Product.new(json:, workdir:), progress
+          else
+            yield ::Datanorm::Documents::Assembles::Product.new(json:, workdir:)
+          end
         end
       end
 

data/lib/datanorm/documents/assembles/product.rb

@@ -53,7 +53,7 @@ module Datanorm
           # Instead, we choose one or the other.
           return dimension_content if dimension_content && !dimension_content.strip.empty?
 
-          text_content
+          text_reference.read
         end
 
         # -----------------------
@@ -84,29 +84,43 @@ module Datanorm
         def prices
           return @prices if defined?(@prices)
 
-          @prices = prices_content&.split("\n")&.map do |json|
+          @prices = price_reference.read&.map do |json|
             ::Datanorm::Documents::Assembles::Price.new(json:)
           end || []
         end
 
+        # ----------------------
+        # Calculated Final Price
+        # ----------------------
+
+        # The cheapest of all prices is probably what we pay.
+        def cheapest_price
+          [price, *prices.map(&:price_after_discount)].min
+        end
+
+        # The most expensive of all prices is probably what we sell for.
+        def most_expensive_price
+          [price, *prices.map(&:price)].max
+        end
+
         # -----------------
         # Referenced Extras
         # -----------------
 
         def matchcode
-          extra_json[:matchcode]
+          extra_reference.read[:matchcode]
         end
 
         def alternative_id
-          extra_json[:alternative_id]
+          extra_reference.read[:alternative_id]
         end
 
         def ean
-          extra_json[:ean]
+          extra_reference.read[:ean]
         end
 
         def category_id
-          extra_json[:category_id]
+          extra_reference.read[:category_id]
         end
 
         # -------
@@ -119,7 +133,7 @@ module Datanorm
 
         def as_json
           # Adding referenced attributes that were cached to disk during preprocessing.
-          json.merge(description:, prices: prices.map(&:as_json)).merge(extra_json)
+          json.merge(description:, prices: prices.map(&:as_json)).merge(extra_reference.read)
         end
 
         def to_json(...)
@@ -143,32 +157,24 @@ module Datanorm
           end
         end
 
-        def text_content
+        def text_reference
           return unless text_id
-          return @text_content if defined?(@text_content)
 
-          @text_content = begin
-            path = workdir.join('T', ::Datanorm::Helpers::Filename.call(text_id))
-            path.read if path.file?
-          end
+          @text_reference ||= ::Datanorm::Documents::Assembles::Reference.new(
+            path: workdir.join('T', ::Datanorm::Helpers::Filename.call(text_id))
+          )
         end
 
-        def extra_json
-          return @extra_json if defined?(@extra_json)
-
-          @extra_json = begin
-            path = workdir.join('B', ::Datanorm::Helpers::Filename.call(id))
-            JSON.parse(path.read, symbolize_names: true) if path.file?
-          end
+        def extra_reference
+          @extra_reference ||= ::Datanorm::Documents::Assembles::Reference.new(
+            path: workdir.join('B', ::Datanorm::Helpers::Filename.call(id)), parse_json: true
+          )
         end
 
-        def prices_content
-          return @prices_content if defined?(@prices_content)
-
-          @prices_content = begin
-            path = workdir.join('P', ::Datanorm::Helpers::Filename.call(id))
-            path.read if path.file?
-          end
+        def price_reference
+          @price_reference ||= ::Datanorm::Documents::Assembles::Reference.new(
+            path: workdir.join('P', ::Datanorm::Helpers::Filename.call(id)), split_newlines: true
+          )
         end
       end
     end

data/lib/datanorm/documents/assembles/reference.rb

@@ -0,0 +1,37 @@
+# frozen_string_literal: true
+
+module Datanorm
+  module Documents
+    module Assembles
+      # Convenience helper to read the contents of a file.
+      class Reference
+        extend Dry::Initializer
+
+        option :path
+        option :parse_json, optional: true
+        option :split_newlines, optional: true
+
+        def read
+          return @read if defined?(@read)
+
+          @read = read!
+        end
+
+        private
+
+        def read!
+          if parse_json
+            JSON.parse(path.read, symbolize_names: true) if path.file?
+
+          elsif path.file?
+            if split_newlines
+              path.read.split("\n")
+            else
+              path.read
+            end
+          end
+        end
+      end
+    end
+  end
+end

data/lib/datanorm/documents/preprocess.rb

@@ -10,6 +10,7 @@ module Datanorm
 
       option :file
       option :workdir
+      option :yield_progress, default: -> { false }
 
       def call
         FileUtils.mkdir_p(workdir)
@@ -18,7 +19,9 @@ module Datanorm
           ::Datanorm::Documents::Preprocesses::Process.call(workdir:, record:)
 
           progress.increment!
-          yield nil, progress # No items to yield during preprocess.
+          if yield_progress
+            yield nil, progress # No items to yield during preprocess.
+          end
         end
       end
 

data/lib/datanorm.rb

@@ -41,6 +41,7 @@ require 'datanorm/documents/preprocesses/cache'
 require 'datanorm/documents/preprocesses/process'
 require 'datanorm/documents/assembles/product'
 require 'datanorm/documents/assembles/price'
+require 'datanorm/documents/assembles/reference'
 require 'datanorm/documents/assemble'
 require 'datanorm/progress'
 require 'datanorm/document'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: datanorm
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 1.0.1
 platform: ruby
 authors:
 - halo
@@ -103,6 +103,7 @@ files:
 - lib/datanorm/documents/assemble.rb
 - lib/datanorm/documents/assembles/price.rb
 - lib/datanorm/documents/assembles/product.rb
+- lib/datanorm/documents/assembles/reference.rb
 - lib/datanorm/documents/preprocess.rb
 - lib/datanorm/documents/preprocesses/cache.rb
 - lib/datanorm/documents/preprocesses/process.rb