rightmove_blm 0.1.1 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: '08bd05a65c0404a94ac0923c3ac48b338d7714b6f0b53dd6b879607e501adced'
-  data.tar.gz: 294e256eb0bc617199816ef32c4ee5f92c785da180ef88e4fcd816e2eb59e86d
+  metadata.gz: a4ec5f3eee9950c331f0a1dd23129b47d6917c332fae762df37346f67c3ae15b
+  data.tar.gz: e803eb23307b33115103e2cd99c94398d272576db5206670eff24c64f13f72af
 SHA512:
-  metadata.gz: 351167830c63ca9037d91300d1081d6afa8d665c5fc3bcdabbbc5f7e4304784ad5738c7d9111878b33a8c67cb8a2a56c1d715bf8db9654ef7d8413c6ee805753
-  data.tar.gz: 9ecc44105fbebec4e3f07e6596f9ad0336368f1e7cac604c4d728a32232905d16f0740153b298976c2e2101ccb6cdd3455d1aa8017d586a25093823a16224b1a
+  metadata.gz: 784c8aad75336281c6e7bc59a0a16866929f62268542d0ebf93c5bccb5a21b1e651a91b1edeca885d571ab18bdd35289afd27937316ff8a5c473d44ad612c760
+  data.tar.gz: 9f8dc40c0e294360d4ca3b7b713da7922b4c9a90795517f98fcd71d13b9ba22e21435aa5f984618d3d30aabb91a6ffa0fad7640d248339a2b59c1c20453e4f96

data/.gitignore

@@ -15,6 +15,8 @@ doc
 pkg
 
 .rspec_status
+
+*.gem
 # Have editor/IDE/OS specific files you need to ignore? Consider using a global gitignore: 
 #
 # * Create a file at ~/.gitignore

data/.rubocop.yml

@@ -1,6 +1,9 @@
+require:
+  - rubocop-rspec
+
 AllCops:
   NewCops: enable
 
 Metrics/BlockLength:
   Exclude:
-  - 'spec/blm_spec.rb'
+  - 'spec/**/*_spec.rb'

data/.ruby-version

@@ -1 +1 @@
-2.5.9
+2.7.7

data/Gemfile.lock

@@ -3,16 +3,17 @@ GEM
   specs:
     ast (2.4.2)
     concurrent-ruby (1.1.8)
-    devpack (0.3.2)
+    devpack (0.3.3)
     diff-lcs (1.4.4)
     i18n (1.8.10)
       concurrent-ruby (~> 1.0)
+    json (2.6.3)
     paint (2.2.1)
-    parallel (1.20.1)
-    parser (3.0.1.0)
+    parallel (1.22.1)
+    parser (3.1.3.0)
       ast (~> 2.4.1)
-    rainbow (3.0.0)
-    regexp_parser (2.1.1)
+    rainbow (3.1.1)
+    regexp_parser (2.6.1)
     rexml (3.2.5)
     rspec (3.10.0)
       rspec-core (~> 3.10.0)
@@ -32,17 +33,18 @@ GEM
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.10.0)
     rspec-support (3.10.2)
-    rubocop (1.13.0)
+    rubocop (1.41.1)
+      json (~> 2.3)
       parallel (~> 1.10)
-      parser (>= 3.0.0.0)
+      parser (>= 3.1.2.1)
       rainbow (>= 2.2.2, < 4.0)
       regexp_parser (>= 1.8, < 3.0)
-      rexml
-      rubocop-ast (>= 1.2.0, < 2.0)
+      rexml (>= 3.2.5, < 4.0)
+      rubocop-ast (>= 1.23.0, < 2.0)
       ruby-progressbar (~> 1.7)
       unicode-display_width (>= 1.4.0, < 3.0)
-    rubocop-ast (1.4.1)
-      parser (>= 2.7.1.5)
+    rubocop-ast (1.24.0)
+      parser (>= 3.1.1.0)
     rubocop-rspec (2.2.0)
       rubocop (~> 1.0)
       rubocop-ast (>= 1.1.0)
@@ -50,7 +52,7 @@ GEM
     strong_versions (0.4.5)
       i18n (>= 0.5)
       paint (~> 2.0)
-    unicode-display_width (2.0.0)
+    unicode-display_width (2.3.0)
 
 PLATFORMS
   ruby
@@ -65,4 +67,4 @@ DEPENDENCIES
   strong_versions (~> 0.4.5)
 
 BUNDLED WITH
-   2.2.16
+   2.3.7

data/README.md

@@ -10,6 +10,8 @@ This library is not affiliated with or endorsed by _Rightmove Plc_ in any way.
 
 ### Loading a BLM file
 
+#### RightmoveBLM::Document
+
 Load a BLM file by passing the `source` parameter to `RightmoveBLM::Document.new`:
 
 ```ruby
@@ -20,17 +22,32 @@ The returned `RightmoveBLM::Document` instance implements:
 
 * `#header` - the header containing information about the document's structure.
 * `#definition` - the field list contained in the document.
-* `#data` - an array of `RightmoveBLM::Row` objects (use dot notation to access fields, e.g. `row.foo` to access the "foo" field).
+* `#rows` - an array of `RightmoveBLM::Row` objects.
+* `#valid?` - `true` if no rows have errors, `false` if any rows have errors.
+* `#errors` - all error messages for all invalid rows.
+* `#version` - the version of the document format as a string (e.g. `'3'`).
+* `#international?` - `true` if document meets the [Rightmove International](https://www.rightmove.co.uk/ps/pdf/guides/RightmoveDatafeedFormatV3iOVS_1.6.pdf) specification, `false` otherwise.
+
+#### RightmoveBLM::Row
+
+`RightmoveBLM::Row` implements:
 
-`RightmoveBLM::Row` also implements `#to_h` which provides a _Hash_ of the row data.
+* `#valid?` - `true` if no errors were encountered, false otherwise.
+* `#errors` - an array of error strings (empty if no errors present).
+* `#to_h` (or `#attributes`) - a hash of row attributes (`nil` if errors encountered).
+* `#method_missing` - allows accessing row attributes by dot notation (e.g. `row.address_1`).
 
 #### Example
 
 ```ruby
-blm.data.each do |row|
+blm.data.select(&:valid?).each do |row|
   puts row.address_1
   puts row.to_h
 end
+
+blm.data.reject(&:valid?).each do |row|
+  puts "Errors: #{row.errors.join(', ')}"
+end
 ```
 
 ### Writing BLM data

data/lib/rightmove_blm/document.rb

@@ -5,7 +5,7 @@ module RightmoveBLM
   class Document
     def self.from_array_of_hashes(array)
       date = Time.now.utc.strftime('%d-%b-%Y %H:%M').upcase
-      header = { version: '3', eof: '^', eor: '~', "property count": array.size.to_s, "generated date": date }
+      header = { version: '3', eof: '^', eor: '~', 'property count': array.size.to_s, 'generated date': date }
       new(header: header, definition: array.first.keys.map(&:to_sym), data: array)
     end
 
@@ -13,7 +13,15 @@ module RightmoveBLM
       @source = source
       @header = header
       @definition = definition
-      @data = data&.map { |row| Row.new(row) }
+      initialize_with_data(data) unless data.nil?
+    end
+
+    def inspect
+      %(<##{self.class.name} version=#{version} rows=#{rows.size} valid=#{valid?} errors=#{errors.size}>)
+    end
+
+    def to_s
+      inspect
     end
 
     def to_blm
@@ -43,27 +51,49 @@ module RightmoveBLM
       end.compact
     end
 
-    def data
-      @data ||= contents.split(header[:eor]).map do |line|
-        row(line)
-      end
+    def rows
+      data
+    end
+
+    def errors
+      @errors ||= data.reject(&:valid?).flat_map(&:errors)
+    end
+
+    def valid?
+      errors.empty?
+    end
+
+    def version
+      header[:version]
+    end
+
+    def international?
+      %w[H1 3I].include?(version)
     end
 
     private
 
+    def initialize_with_data(data)
+      @data = data.each_with_index.map { |hash, index| Row.from_attributes(hash, index: index) }
+    end
+
+    def data
+      @data ||= contents.split(header[:eor]).each_with_index.map do |line, index|
+        Row.new(index: index, data: line, separator: header[:eof], definition: definition)
+      end
+    end
+
     def contents(section = :data)
       marker = "##{section.to_s.upcase}#"
-      start = @source.index(marker) + marker.size
-      finish = @source.index('#', start) - 1
+      start = verify(:start, @source.index(marker)) + marker.size
+      finish = verify(:end, @source.index('#', start)) - 1
       @source[start..finish].strip
     end
 
-    def row(line)
-      entry = {}
-      line.split(header[:eof]).each_with_index do |field, index|
-        entry[definition[index].to_sym] = field.strip
-      end
-      Row.new(entry)
+    def verify(type, val)
+      return val unless val.nil?
+
+      raise ParserError, "Unable to parse document: could not detect #{type} marker."
     end
 
     def generated_date

data/lib/rightmove_blm/row.rb

@@ -3,22 +3,72 @@
 module RightmoveBLM
   # A row in a BLM document.
   class Row
-    attr_accessor :attributes
+    attr_reader :index
 
-    def initialize(hash)
-      @attributes = hash
+    def self.from_attributes(attributes, index:)
+      new(index: index, data: nil, separator: nil, definition: attributes.keys, attributes: attributes)
+    end
+
+    def initialize(index:, data:, separator:, definition:, attributes: nil)
+      @index = index
+      @data = data
+      @separator = separator
+      @definition = definition
+      @attributes = attributes
+      @fields = attributes.keys unless attributes.nil?
     end
 
     def to_h
-      @attributes
+      attributes
+    end
+
+    def valid?
+      return false unless field_size_valid?
+
+      true
+    end
+
+    def errors
+      return [] if valid?
+
+      errors = []
+      errors << field_size_mismatch_message unless field_size_valid?
+      errors
+    end
+
+    def attributes
+      return nil unless valid?
+
+      @attributes ||= fields.each_with_index.to_h do |field, field_index|
+        [definition[field_index].to_sym, field.strip]
+      end
+    end
+
+    private
+
+    attr_reader :data, :separator, :definition
+
+    def field_size_mismatch_message
+      "Field size mismatch in row #{index}. Expected: #{definition.size} fields, found: #{fields.size}"
+    end
+
+    def fields
+      @fields ||= data.split(separator)
+    end
+
+    def field_size_valid?
+      definition.size >= fields.size
     end
 
     def method_missing(method, *_arguments)
-      return @attributes[method] unless @attributes[method].nil?
+      return super if attributes.nil?
+      return attributes[method] unless attributes[method].nil?
+
+      super
     end
 
     def respond_to_missing?(method, _ = false)
-      !@attributes[method].nil?
+      !attributes[method].nil?
     end
   end
 end

data/lib/rightmove_blm/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module RightmoveBLM
-  VERSION = '0.1.1'
+  VERSION = '0.2.0'
 end

data/lib/rightmove_blm.rb

@@ -8,4 +8,6 @@ require 'time'
 # Rightmove BLM (Bulk Load Mass) data format parsing tools.
 # https://www.rightmove.co.uk/ps/pdf/guides/RightmoveDatafeedFormatV3iOVS_1.6.pdf
 module RightmoveBLM
+  class Error < StandardError; end
+  class ParserError < Error; end
 end

data/rightmove_blm.gemspec

@@ -5,24 +5,20 @@ require_relative 'lib/rightmove_blm/version'
 Gem::Specification.new do |spec|
   spec.name = 'rightmove_blm'
   spec.version = RightmoveBLM::VERSION
-  spec.authors = ['Robert Farrell']
+  spec.authors = ['Bob Farrell']
   spec.email = 'git@bob.frl'
 
   spec.summary
   spec.description = 'Parse and generate Rightmove BLM files'
-  spec.required_ruby_version = '~> 2.5'
+  spec.required_ruby_version = '>= 2.7'
 
   spec.files = Dir.chdir(File.expand_path(__dir__)) do
     `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
   end
 
-  spec.homepage = 'https://github.com/bobf/rightmove_blm'
+  spec.homepage = 'http://github.com/robertmay/blm'
   spec.licenses = ['MIT']
   spec.require_paths = ['lib']
-  spec.rubygems_version = '1.3.7'
   spec.summary = 'A parser for the Rightmove .blm format'
-  spec.test_files = [
-    'spec/blm_spec.rb',
-    'spec/spec_helper.rb'
-  ]
+  spec.metadata['rubygems_mfa_required'] = 'true'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rightmove_blm
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.2.0
 platform: ruby
 authors:
-- Robert Farrell
+- Bob Farrell
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-09-27 00:00:00.000000000 Z
+date: 2023-05-06 00:00:00.000000000 Z
 dependencies: []
 description: Parse and generate Rightmove BLM files
 email: git@bob.frl
@@ -27,37 +27,33 @@ files:
 - Makefile
 - README.md
 - Rakefile
-- VERSION
 - lib/rightmove_blm.rb
 - lib/rightmove_blm/document.rb
 - lib/rightmove_blm/row.rb
 - lib/rightmove_blm/version.rb
 - rightmove_blm.gemspec
-- spec/blm_spec.rb
-- spec/spec_helper.rb
-homepage: https://github.com/bobf/rightmove_blm
+homepage: http://github.com/robertmay/blm
 licenses:
 - MIT
-metadata: {}
+metadata:
+  rubygems_mfa_required: 'true'
 post_install_message:
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - "~>"
+  - - ">="
     - !ruby/object:Gem::Version
-      version: '2.5'
+      version: '2.7'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.3
+rubygems_version: 3.1.6
 signing_key:
 specification_version: 4
 summary: A parser for the Rightmove .blm format
-test_files:
-- spec/blm_spec.rb
-- spec/spec_helper.rb
+test_files: []

data/VERSION

@@ -1 +0,0 @@
-0.1.1

data/spec/blm_spec.rb

@@ -1,72 +0,0 @@
-# frozen_string_literal: true
-
-RSpec.describe RightmoveBLM do
-  context 'reading a .blm file' do
-    let(:data) { fixture('example_data.blm') }
-    let(:blm) { RightmoveBLM::Document.new(source: data.read) }
-
-    it 'should parse settings from the header' do
-      expect(blm.header).to be_a(Hash)
-      expect(blm.header[:version]).to  eq('3')
-      expect(blm.header[:eof]).to_not be_nil
-      expect(blm.header[:eor]).to_not be_nil
-    end
-
-    it 'should parse the column definition' do
-      expect(blm.definition).to be_a(Array)
-      expect(blm.definition.size).to be >= 1
-    end
-
-    it 'should parse the data into an array of hashes' do
-      expect(blm.data).to be_a(Array)
-      expect(blm.data.size).to be >= 1
-      expect(blm.data).to respond_to(:each, :each_with_index)
-      blm.data.each { |row| expect(row).to be_a(RightmoveBLM::Row) }
-    end
-
-    it 'should allow access to data values via methods' do
-      blm.data.each { |row| expect(row.address_1).to_not be_nil }
-    end
-
-    it 'should allow access to the @attributes hash directly' do
-      blm.data.each { |row| expect(row.attributes).to be_a(Hash) }
-    end
-  end
-
-  context 'creating a .blm file' do
-    subject(:document) { RightmoveBLM::Document.from_array_of_hashes(data) }
-
-    let(:data) do
-      [{ field1: 'row 1 field 1 data', field2: 'row 1 field 2 data', field3: 'row 1 field 3 data' },
-       { field1: 'row 2 field 1 data', field2: 'row 2 field 2 data', field3: 'row 2 field 3 data' }]
-    end
-
-    its(:header) { is_expected.to include({ 'property count': '2' }) }
-    its(:header) { is_expected.to include({ version: '3' }) }
-    its(:definition) { is_expected.to eql %i[field1 field2 field3] }
-
-    describe '#to_blm' do
-      let(:loaded_document) { RightmoveBLM::Document.new(source: subject.to_blm) }
-
-      it 'has a property count' do
-        expect(loaded_document.header[:'property count']).to eql '2'
-      end
-
-      it 'has a version' do
-        expect(loaded_document.header[:version]).to eql '3'
-      end
-
-      it 'has a "generated date" timestamp' do
-        expect(loaded_document.header[:'generated date']).to start_with Time.now.utc.strftime('%d-%b-%Y').upcase
-      end
-
-      it 'has property data' do
-        expect(loaded_document.data.map(&:to_h)).to eql data
-      end
-
-      it 'has a field definition' do
-        expect(loaded_document.definition).to eql %w[field1 field2 field3]
-      end
-    end
-  end
-end

data/spec/spec_helper.rb

@@ -1,16 +0,0 @@
-# frozen_string_literal: true
-
-require 'bundler/setup'
-require 'devpack'
-require 'rightmove_blm'
-
-require 'rspec/file_fixtures'
-require 'rspec/its'
-
-RSpec.configure do |config|
-  config.example_status_persistence_file_path = '.rspec_status'
-  config.disable_monkey_patching!
-  config.expect_with :rspec do |c|
-    c.syntax = :expect
-  end
-end