hdo-storting-importer 0.0.1 → 0.0.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/Gemfile +1 -6
- data/README.md +4 -5
- data/features/convert.feature +189 -0
- data/hdo-storting-importer.gemspec +6 -0
- data/lib/hdo/storting_importer/category.rb +57 -0
- data/lib/hdo/storting_importer/cli.rb +76 -97
- data/lib/hdo/storting_importer/committee.rb +20 -0
- data/lib/hdo/storting_importer/district.rb +20 -0
- data/lib/hdo/storting_importer/issue.rb +51 -0
- data/lib/hdo/storting_importer/party.rb +20 -0
- data/lib/hdo/storting_importer/promise.rb +56 -1
- data/lib/hdo/storting_importer/promise_converter.rb +1 -20
- data/lib/hdo/storting_importer/representative.rb +47 -0
- data/lib/hdo/storting_importer/version.rb +1 -1
- data/lib/hdo/storting_importer/vote.rb +73 -0
- data/lib/hdo/storting_importer.rb +3 -1
- data/spec/hdo/storting_importer/category_spec.rb +25 -1
- data/spec/hdo/storting_importer/committee_spec.rb +22 -1
- data/spec/hdo/storting_importer/district_spec.rb +22 -1
- data/spec/hdo/storting_importer/issue_spec.rb +24 -18
- data/spec/hdo/storting_importer/party_spec.rb +21 -1
- data/spec/hdo/storting_importer/promise_spec.rb +56 -0
- data/spec/hdo/storting_importer/representative_spec.rb +24 -7
- data/spec/hdo/storting_importer/vote_spec.rb +41 -29
- metadata +85 -8
- data/features/import.feature +0 -85
- data/features/step_definitions/import_steps.rb +0 -0
- data/lib/hdo/storting_importer/script_importer.rb +0 -20
    
        data/Gemfile
    CHANGED
    
    
    
        data/README.md
    CHANGED
    
    | @@ -1,14 +1,13 @@ | |
| 1 1 | 
             
            What
         | 
| 2 2 | 
             
            ====
         | 
| 3 3 |  | 
| 4 | 
            -
            Convert  | 
| 4 | 
            +
            Convert XML from data.stortinget.no to HDO XML
         | 
| 5 5 |  | 
| 6 6 | 
             
            Usage
         | 
| 7 7 | 
             
            =====
         | 
| 8 8 |  | 
| 9 | 
            -
                $  | 
| 9 | 
            +
                $ hdo-converter --help
         | 
| 10 | 
            +
                $ hdo-converter categories folketingparser/rawdata/data.stortinget.no/eksport/emner/index.html
         | 
| 11 | 
            +
                $ hdo-converter promises all-promises.csv | script/import promises
         | 
| 10 12 |  | 
| 11 | 
            -
            Caveats
         | 
| 12 | 
            -
            =======
         | 
| 13 13 |  | 
| 14 | 
            -
            Right now we're executing script/import from hdo-site to perform the import. That means running this with bundler may fail if the gems don't match. Don't do that.
         | 
| @@ -0,0 +1,189 @@ | |
| 1 | 
            +
            Feature: Import data
         | 
| 2 | 
            +
                Scenario: Import districts
         | 
| 3 | 
            +
                  Given a file named "fylker.xml" with:
         | 
| 4 | 
            +
                  """
         | 
| 5 | 
            +
                  <?xml version="1.0" encoding="utf-8"?>
         | 
| 6 | 
            +
                  <fylker_oversikt xmlns:i="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://data.stortinget.no">
         | 
| 7 | 
            +
                    <versjon>1.0</versjon>
         | 
| 8 | 
            +
                    <fylker_liste>
         | 
| 9 | 
            +
                      <fylke>
         | 
| 10 | 
            +
                        <versjon>1.0</versjon>
         | 
| 11 | 
            +
                        <id>AA</id>
         | 
| 12 | 
            +
                        <navn>Aust-Agder</navn>
         | 
| 13 | 
            +
                      </fylke>
         | 
| 14 | 
            +
                      <fylke>
         | 
| 15 | 
            +
                        <versjon>1.0</versjon>
         | 
| 16 | 
            +
                        <id>VA</id>
         | 
| 17 | 
            +
                        <navn>Vest-Agder</navn>
         | 
| 18 | 
            +
                      </fylke>
         | 
| 19 | 
            +
                      <fylke>
         | 
| 20 | 
            +
                        <versjon>1.0</versjon>
         | 
| 21 | 
            +
                        <id>Ak</id>
         | 
| 22 | 
            +
                        <navn>Akershus</navn>
         | 
| 23 | 
            +
                      </fylke>
         | 
| 24 | 
            +
                      <fylke>
         | 
| 25 | 
            +
                        <versjon>1.0</versjon>
         | 
| 26 | 
            +
                        <id>Bu</id>
         | 
| 27 | 
            +
                        <navn>Buskerud</navn>
         | 
| 28 | 
            +
                      </fylke>
         | 
| 29 | 
            +
                      <fylke>
         | 
| 30 | 
            +
                        <versjon>1.0</versjon>
         | 
| 31 | 
            +
                        <id>Fi</id>
         | 
| 32 | 
            +
                        <navn>Finnmark</navn>
         | 
| 33 | 
            +
                      </fylke>
         | 
| 34 | 
            +
                      <fylke>
         | 
| 35 | 
            +
                        <versjon>1.0</versjon>
         | 
| 36 | 
            +
                        <id>He</id>
         | 
| 37 | 
            +
                        <navn>Hedmark</navn>
         | 
| 38 | 
            +
                      </fylke>
         | 
| 39 | 
            +
                      <fylke>
         | 
| 40 | 
            +
                        <versjon>1.0</versjon>
         | 
| 41 | 
            +
                        <id>Ho</id>
         | 
| 42 | 
            +
                        <navn>Hordaland</navn>
         | 
| 43 | 
            +
                      </fylke>
         | 
| 44 | 
            +
                      <fylke>
         | 
| 45 | 
            +
                        <versjon>1.0</versjon>
         | 
| 46 | 
            +
                        <id>MR</id>
         | 
| 47 | 
            +
                        <navn>Møre og Romsdal</navn>
         | 
| 48 | 
            +
                      </fylke>
         | 
| 49 | 
            +
                      <fylke>
         | 
| 50 | 
            +
                        <versjon>1.0</versjon>
         | 
| 51 | 
            +
                        <id>No</id>
         | 
| 52 | 
            +
                        <navn>Nordland</navn>
         | 
| 53 | 
            +
                      </fylke>
         | 
| 54 | 
            +
                      <fylke>
         | 
| 55 | 
            +
                        <versjon>1.0</versjon>
         | 
| 56 | 
            +
                        <id>Op</id>
         | 
| 57 | 
            +
                        <navn>Oppland</navn>
         | 
| 58 | 
            +
                      </fylke>
         | 
| 59 | 
            +
                      <fylke>
         | 
| 60 | 
            +
                        <versjon>1.0</versjon>
         | 
| 61 | 
            +
                        <id>Os</id>
         | 
| 62 | 
            +
                        <navn>Oslo</navn>
         | 
| 63 | 
            +
                      </fylke>
         | 
| 64 | 
            +
                      <fylke>
         | 
| 65 | 
            +
                        <versjon>1.0</versjon>
         | 
| 66 | 
            +
                        <id>Ro</id>
         | 
| 67 | 
            +
                        <navn>Rogaland</navn>
         | 
| 68 | 
            +
                      </fylke>
         | 
| 69 | 
            +
                      <fylke>
         | 
| 70 | 
            +
                        <versjon>1.0</versjon>
         | 
| 71 | 
            +
                        <id>SF</id>
         | 
| 72 | 
            +
                        <navn>Sogn og Fjordane</navn>
         | 
| 73 | 
            +
                      </fylke>
         | 
| 74 | 
            +
                      <fylke>
         | 
| 75 | 
            +
                        <versjon>1.0</versjon>
         | 
| 76 | 
            +
                        <id>Te</id>
         | 
| 77 | 
            +
                        <navn>Telemark</navn>
         | 
| 78 | 
            +
                      </fylke>
         | 
| 79 | 
            +
                      <fylke>
         | 
| 80 | 
            +
                        <versjon>1.0</versjon>
         | 
| 81 | 
            +
                        <id>Tr</id>
         | 
| 82 | 
            +
                        <navn>Troms</navn>
         | 
| 83 | 
            +
                      </fylke>
         | 
| 84 | 
            +
                      <fylke>
         | 
| 85 | 
            +
                        <versjon>1.0</versjon>
         | 
| 86 | 
            +
                        <id>NT</id>
         | 
| 87 | 
            +
                        <navn>Nord-Trøndelag</navn>
         | 
| 88 | 
            +
                      </fylke>
         | 
| 89 | 
            +
                      <fylke>
         | 
| 90 | 
            +
                        <versjon>1.0</versjon>
         | 
| 91 | 
            +
                        <id>ST</id>
         | 
| 92 | 
            +
                        <navn>Sør-Trøndelag</navn>
         | 
| 93 | 
            +
                      </fylke>
         | 
| 94 | 
            +
                      <fylke>
         | 
| 95 | 
            +
                        <versjon>1.0</versjon>
         | 
| 96 | 
            +
                        <id>Ve</id>
         | 
| 97 | 
            +
                        <navn>Vestfold</navn>
         | 
| 98 | 
            +
                      </fylke>
         | 
| 99 | 
            +
                      <fylke>
         | 
| 100 | 
            +
                        <versjon>1.0</versjon>
         | 
| 101 | 
            +
                        <id>Øs</id>
         | 
| 102 | 
            +
                        <navn>Østfold</navn>
         | 
| 103 | 
            +
                      </fylke>
         | 
| 104 | 
            +
                    </fylker_liste>
         | 
| 105 | 
            +
                  </fylker_oversikt>
         | 
| 106 | 
            +
                  """
         | 
| 107 | 
            +
                  When I run `hdo-converter districts fylker.xml`
         | 
| 108 | 
            +
                  Then the stdout should contain:
         | 
| 109 | 
            +
                  """
         | 
| 110 | 
            +
                  <?xml version="1.0" encoding="UTF-8"?>
         | 
| 111 | 
            +
                  <districts>
         | 
| 112 | 
            +
                    <district>
         | 
| 113 | 
            +
                      <externalId>AA</externalId>
         | 
| 114 | 
            +
                      <name>Aust-Agder</name>
         | 
| 115 | 
            +
                    </district>
         | 
| 116 | 
            +
                    <district>
         | 
| 117 | 
            +
                      <externalId>VA</externalId>
         | 
| 118 | 
            +
                      <name>Vest-Agder</name>
         | 
| 119 | 
            +
                    </district>
         | 
| 120 | 
            +
                    <district>
         | 
| 121 | 
            +
                      <externalId>Ak</externalId>
         | 
| 122 | 
            +
                      <name>Akershus</name>
         | 
| 123 | 
            +
                    </district>
         | 
| 124 | 
            +
                    <district>
         | 
| 125 | 
            +
                      <externalId>Bu</externalId>
         | 
| 126 | 
            +
                      <name>Buskerud</name>
         | 
| 127 | 
            +
                    </district>
         | 
| 128 | 
            +
                    <district>
         | 
| 129 | 
            +
                      <externalId>Fi</externalId>
         | 
| 130 | 
            +
                      <name>Finnmark</name>
         | 
| 131 | 
            +
                    </district>
         | 
| 132 | 
            +
                    <district>
         | 
| 133 | 
            +
                      <externalId>He</externalId>
         | 
| 134 | 
            +
                      <name>Hedmark</name>
         | 
| 135 | 
            +
                    </district>
         | 
| 136 | 
            +
                    <district>
         | 
| 137 | 
            +
                      <externalId>Ho</externalId>
         | 
| 138 | 
            +
                      <name>Hordaland</name>
         | 
| 139 | 
            +
                    </district>
         | 
| 140 | 
            +
                    <district>
         | 
| 141 | 
            +
                      <externalId>MR</externalId>
         | 
| 142 | 
            +
                      <name>Møre og Romsdal</name>
         | 
| 143 | 
            +
                    </district>
         | 
| 144 | 
            +
                    <district>
         | 
| 145 | 
            +
                      <externalId>No</externalId>
         | 
| 146 | 
            +
                      <name>Nordland</name>
         | 
| 147 | 
            +
                    </district>
         | 
| 148 | 
            +
                    <district>
         | 
| 149 | 
            +
                      <externalId>Op</externalId>
         | 
| 150 | 
            +
                      <name>Oppland</name>
         | 
| 151 | 
            +
                    </district>
         | 
| 152 | 
            +
                    <district>
         | 
| 153 | 
            +
                      <externalId>Os</externalId>
         | 
| 154 | 
            +
                      <name>Oslo</name>
         | 
| 155 | 
            +
                    </district>
         | 
| 156 | 
            +
                    <district>
         | 
| 157 | 
            +
                      <externalId>Ro</externalId>
         | 
| 158 | 
            +
                      <name>Rogaland</name>
         | 
| 159 | 
            +
                    </district>
         | 
| 160 | 
            +
                    <district>
         | 
| 161 | 
            +
                      <externalId>SF</externalId>
         | 
| 162 | 
            +
                      <name>Sogn og Fjordane</name>
         | 
| 163 | 
            +
                    </district>
         | 
| 164 | 
            +
                    <district>
         | 
| 165 | 
            +
                      <externalId>Te</externalId>
         | 
| 166 | 
            +
                      <name>Telemark</name>
         | 
| 167 | 
            +
                    </district>
         | 
| 168 | 
            +
                    <district>
         | 
| 169 | 
            +
                      <externalId>Tr</externalId>
         | 
| 170 | 
            +
                      <name>Troms</name>
         | 
| 171 | 
            +
                    </district>
         | 
| 172 | 
            +
                    <district>
         | 
| 173 | 
            +
                      <externalId>NT</externalId>
         | 
| 174 | 
            +
                      <name>Nord-Trøndelag</name>
         | 
| 175 | 
            +
                    </district>
         | 
| 176 | 
            +
                    <district>
         | 
| 177 | 
            +
                      <externalId>ST</externalId>
         | 
| 178 | 
            +
                      <name>Sør-Trøndelag</name>
         | 
| 179 | 
            +
                    </district>
         | 
| 180 | 
            +
                    <district>
         | 
| 181 | 
            +
                      <externalId>Ve</externalId>
         | 
| 182 | 
            +
                      <name>Vestfold</name>
         | 
| 183 | 
            +
                    </district>
         | 
| 184 | 
            +
                    <district>
         | 
| 185 | 
            +
                      <externalId>Øs</externalId>
         | 
| 186 | 
            +
                      <name>Østfold</name>
         | 
| 187 | 
            +
                    </district>
         | 
| 188 | 
            +
                  </districts>
         | 
| 189 | 
            +
                  """
         | 
| @@ -14,4 +14,10 @@ Gem::Specification.new do |gem| | |
| 14 14 | 
             
              gem.name          = "hdo-storting-importer"
         | 
| 15 15 | 
             
              gem.require_paths = ["lib"]
         | 
| 16 16 | 
             
              gem.version       = Hdo::StortingImporter::VERSION
         | 
| 17 | 
            +
             | 
| 18 | 
            +
              gem.add_runtime_dependency "builder"
         | 
| 19 | 
            +
              gem.add_runtime_dependency "nokogiri"
         | 
| 20 | 
            +
              gem.add_runtime_dependency "aruba"
         | 
| 21 | 
            +
              gem.add_runtime_dependency "rake"
         | 
| 22 | 
            +
              gem.add_runtime_dependency "rest-client"
         | 
| 17 23 | 
             
            end
         | 
| @@ -6,10 +6,45 @@ module Hdo | |
| 6 6 | 
             
                  attr_reader :external_id, :name
         | 
| 7 7 | 
             
                  attr_accessor :children
         | 
| 8 8 |  | 
| 9 | 
            +
                  def self.type_name
         | 
| 10 | 
            +
                    'category'
         | 
| 11 | 
            +
                  end
         | 
| 12 | 
            +
             | 
| 13 | 
            +
                  def self.description
         | 
| 14 | 
            +
                    'a parliamentary category, used to categorize issues and promises'
         | 
| 15 | 
            +
                  end
         | 
| 16 | 
            +
             | 
| 17 | 
            +
                  def self.fields
         | 
| 18 | 
            +
                    [
         | 
| 19 | 
            +
                      EXTERNAL_ID_FIELD,
         | 
| 20 | 
            +
                      Field.new(:name, true, :string, 'The name of the category.'),
         | 
| 21 | 
            +
                      Field.new(:subcategories, false, 'list<category>', 'A list of subcategories.'),
         | 
| 22 | 
            +
                    ]
         | 
| 23 | 
            +
                  end
         | 
| 24 | 
            +
             | 
| 25 | 
            +
                  def self.xml_example(builder = Util.builder)
         | 
| 26 | 
            +
                    cat = new("5", "Employment")
         | 
| 27 | 
            +
                    cat.children << new("6", "Wages")
         | 
| 28 | 
            +
             | 
| 29 | 
            +
                    cat.to_hdo_xml(builder)
         | 
| 30 | 
            +
                  end
         | 
| 31 | 
            +
             | 
| 32 | 
            +
                  #
         | 
| 33 | 
            +
                  # Deserialize from a Storting XML document (<emne_liste><emne>...</emne></emne_liste>)
         | 
| 34 | 
            +
                  #
         | 
| 35 | 
            +
                  # @return [Array<Category>]
         | 
| 36 | 
            +
                  #
         | 
| 37 | 
            +
             | 
| 9 38 | 
             
                  def self.from_storting_doc(doc)
         | 
| 10 39 | 
             
                    doc.css("emne_liste > emne").map { |xt| from_storting_node(xt) }
         | 
| 11 40 | 
             
                  end
         | 
| 12 41 |  | 
| 42 | 
            +
                  #
         | 
| 43 | 
            +
                  # Deserialize form a Storting XML node (<emne>...</emne>)
         | 
| 44 | 
            +
                  #
         | 
| 45 | 
            +
                  # @return [Category]
         | 
| 46 | 
            +
                  #
         | 
| 47 | 
            +
             | 
| 13 48 | 
             
                  def self.from_storting_node(node)
         | 
| 14 49 | 
             
                    cat = Category.new node.css("id").first.text, node.css("navn").first.text
         | 
| 15 50 |  | 
| @@ -21,6 +56,24 @@ module Hdo | |
| 21 56 | 
             
                    cat
         | 
| 22 57 | 
             
                  end
         | 
| 23 58 |  | 
| 59 | 
            +
                  #
         | 
| 60 | 
            +
                  # Deserialize from a HDO XML document (<categories><category>...</category></categories>)
         | 
| 61 | 
            +
                  #
         | 
| 62 | 
            +
                  # @param [Nokogiri::XML::Element]
         | 
| 63 | 
            +
                  # @return [Array<Category>]
         | 
| 64 | 
            +
                  #
         | 
| 65 | 
            +
             | 
| 66 | 
            +
             | 
| 67 | 
            +
                  def self.from_hdo_doc(doc)
         | 
| 68 | 
            +
                    doc.css("categories > category").map { |node| from_hdo_node(node) }
         | 
| 69 | 
            +
                  end
         | 
| 70 | 
            +
             | 
| 71 | 
            +
                  #
         | 
| 72 | 
            +
                  # Deserialize from a HDO XML node
         | 
| 73 | 
            +
                  #
         | 
| 74 | 
            +
                  # @return [Category]
         | 
| 75 | 
            +
                  #
         | 
| 76 | 
            +
             | 
| 24 77 | 
             
                  def self.from_hdo_node(node)
         | 
| 25 78 | 
             
                    external_id = node.css("externalId").first.text
         | 
| 26 79 | 
             
                    name        = node.css("name").first.text
         | 
| @@ -37,6 +90,10 @@ module Hdo | |
| 37 90 | 
             
                    @children    = []
         | 
| 38 91 | 
             
                  end
         | 
| 39 92 |  | 
| 93 | 
            +
                  #
         | 
| 94 | 
            +
                  # Serialize as HDO XML
         | 
| 95 | 
            +
                  #
         | 
| 96 | 
            +
             | 
| 40 97 | 
             
                  def to_hdo_xml(builder = Util.builder)
         | 
| 41 98 | 
             
                    builder.category do |cat|
         | 
| 42 99 | 
             
                      cat.externalId external_id
         | 
| @@ -3,139 +3,118 @@ module Hdo | |
| 3 3 | 
             
                class CLI
         | 
| 4 4 | 
             
                  def initialize(args)
         | 
| 5 5 | 
             
                    @log = Logger.new(STDERR)
         | 
| 6 | 
            -
                    @ | 
| 6 | 
            +
                    @type, @files, @options = parse(args)
         | 
| 7 7 | 
             
                  end
         | 
| 8 8 |  | 
| 9 9 | 
             
                  def execute
         | 
| 10 | 
            -
                     | 
| 10 | 
            +
                    case @type
         | 
| 11 | 
            +
                    when :dld_issues
         | 
| 12 | 
            +
                      puts read_dld_issues
         | 
| 13 | 
            +
                    when :dld_votes
         | 
| 14 | 
            +
                      puts read_dld_votes
         | 
| 15 | 
            +
                    when :promises
         | 
| 16 | 
            +
                      puts read_promises
         | 
| 17 | 
            +
                    else
         | 
| 18 | 
            +
                      puts read_type(@type, class_for_type(@type))
         | 
| 19 | 
            +
                    end
         | 
| 20 | 
            +
                  rescue Errno::EPIPE
         | 
| 21 | 
            +
                    # ignored
         | 
| 11 22 | 
             
                  end
         | 
| 12 23 |  | 
| 13 24 | 
             
                  private
         | 
| 14 25 |  | 
| 26 | 
            +
                  TYPE_TO_CLASS = {
         | 
| 27 | 
            +
                    :categories      => Category,
         | 
| 28 | 
            +
                    :issues          => Issue,
         | 
| 29 | 
            +
                    :districts       => District,
         | 
| 30 | 
            +
                    :committees      => Committee,
         | 
| 31 | 
            +
                    :parties         => Party,
         | 
| 32 | 
            +
                    :representatives => Representative,
         | 
| 33 | 
            +
                    :votes           => Vote
         | 
| 34 | 
            +
                  }
         | 
| 35 | 
            +
             | 
| 36 | 
            +
                  def class_for_type(type)
         | 
| 37 | 
            +
                    TYPE_TO_CLASS[type] or raise ArgumentError, "unknown type: #{type.inspect}"
         | 
| 38 | 
            +
                  end
         | 
| 39 | 
            +
             | 
| 40 | 
            +
                  def read_type(plural, klass)
         | 
| 41 | 
            +
                    objs = @files.map do |e|
         | 
| 42 | 
            +
                      doc = Nokogiri::XML.parse(File.read(e))
         | 
| 43 | 
            +
                      doc.remove_namespaces!
         | 
| 44 | 
            +
             | 
| 45 | 
            +
                      klass.from_storting_doc(doc)
         | 
| 46 | 
            +
                    end.flatten
         | 
| 47 | 
            +
             | 
| 48 | 
            +
                    str = Util.builder do |xml|
         | 
| 49 | 
            +
                      xml.instruct!
         | 
| 50 | 
            +
                      xml.__send__(plural) do |builder|
         | 
| 51 | 
            +
                        objs.each { |e| e.to_hdo_xml(builder) }
         | 
| 52 | 
            +
                      end
         | 
| 53 | 
            +
                    end
         | 
| 54 | 
            +
             | 
| 55 | 
            +
                    str
         | 
| 56 | 
            +
                  end
         | 
| 57 | 
            +
             | 
| 15 58 | 
             
                  def parse(args)
         | 
| 16 | 
            -
                    options = { | 
| 59 | 
            +
                    options = {}
         | 
| 17 60 |  | 
| 18 61 | 
             
                    parser = OptionParser.new do |opt|
         | 
| 19 | 
            -
                       | 
| 20 | 
            -
             | 
| 62 | 
            +
                      types = TYPE_TO_CLASS.keys + [:dld_issues, :dld_votes, :promises]
         | 
| 63 | 
            +
                      opt.banner = "Usage: #{$0} <#{types.join '|'}> <file(s)>"
         | 
| 21 64 | 
             
                      opt.on("--help", "You're looking at it.") { puts opt; exit; }
         | 
| 22 | 
            -
                      opt.on("--only-print", "Don't run import, only print generated XML.") { options[:only_print] = true }
         | 
| 23 | 
            -
                      opt.on("--except WHAT", 'Ignore this comma separated list of entities from import.') { |s| options[:ignore] = s.split(",").map(&:strip).map(&:to_sym) }
         | 
| 24 | 
            -
                      opt.on("--app-root APP_ROOT", 'Path to clone of git://github.com/holderdeord/hdo-site.git') { |path| options[:app_root] = path }
         | 
| 25 | 
            -
                      opt.on("--app-url APP_URL", 'URL to hdo-site') { |url| options[:app_url] = url }
         | 
| 26 | 
            -
                      opt.on("--source SOURCE ", 'Where to take data from [disk|api]') { |source| options[:source] = source }
         | 
| 27 | 
            -
                      opt.on("--socks PROXY", 'host:port for SOCKS proxy') do |proxy|
         | 
| 28 | 
            -
                        require 'socksify'
         | 
| 29 | 
            -
                        host, port = proxy.split ":"
         | 
| 30 | 
            -
                        TCPSocket.socks_server = host
         | 
| 31 | 
            -
                        TCPSocket.socks_port = Integer(port)
         | 
| 32 | 
            -
                      end
         | 
| 33 65 | 
             
                    end
         | 
| 34 66 |  | 
| 35 67 | 
             
                    parser.parse!(args)
         | 
| 36 68 |  | 
| 37 | 
            -
                     | 
| 69 | 
            +
                    type, files = args
         | 
| 38 70 |  | 
| 39 | 
            -
                     | 
| 71 | 
            +
                    if type.nil?
         | 
| 40 72 | 
             
                      puts(parser)
         | 
| 41 73 | 
             
                      exit 1
         | 
| 42 74 | 
             
                    end
         | 
| 43 75 |  | 
| 44 | 
            -
                    [ | 
| 76 | 
            +
                    [type.to_sym, Array(files), options]
         | 
| 45 77 | 
             
                  end
         | 
| 46 78 |  | 
| 47 | 
            -
                  def  | 
| 48 | 
            -
                     | 
| 49 | 
            -
             | 
| 50 | 
            -
                             DiskDataSource.new(File.join(StortingImporter.root, 'folketingparser/rawdata/data.stortinget.no'))
         | 
| 51 | 
            -
                           elsif @options[:source] == "api"
         | 
| 52 | 
            -
                             ApiDataSource.new("http://data.stortinget.no/")
         | 
| 53 | 
            -
                           else
         | 
| 54 | 
            -
                             raise ArgumentError, "invalid source: #{@options[:source].inspect}"
         | 
| 55 | 
            -
                           end
         | 
| 56 | 
            -
             | 
| 57 | 
            -
                      ParsingDataSource.new(ds)
         | 
| 58 | 
            -
                    )
         | 
| 59 | 
            -
                  end
         | 
| 79 | 
            +
                  def read_dld_issues
         | 
| 80 | 
            +
                    doc = Nokogiri::XML.parse(File.read(File.join(StortingImporter.root, 'data/dld-issues.xml')))
         | 
| 81 | 
            +
                    issues = Issue.from_hdo_doc doc
         | 
| 60 82 |  | 
| 61 | 
            -
             | 
| 62 | 
            -
             | 
| 63 | 
            -
                       | 
| 64 | 
            -
                         | 
| 65 | 
            -
                      else
         | 
| 66 | 
            -
                        raise ArgumentError, "app-root not given, can't import"
         | 
| 83 | 
            +
                    Util.builder do |xml|
         | 
| 84 | 
            +
                      xml.instruct!
         | 
| 85 | 
            +
                      xml.issues do |issues_builder|
         | 
| 86 | 
            +
                        issues.each { |i| i.to_hdo_xml(issues_builder) }
         | 
| 67 87 | 
             
                      end
         | 
| 68 | 
            -
                    )
         | 
| 69 | 
            -
                  end
         | 
| 70 | 
            -
             | 
| 71 | 
            -
                  def import(what)
         | 
| 72 | 
            -
                    case what
         | 
| 73 | 
            -
                    when :dld
         | 
| 74 | 
            -
                      import_dld
         | 
| 75 | 
            -
                    when :promises
         | 
| 76 | 
            -
                      import_promises
         | 
| 77 | 
            -
                    when :all
         | 
| 78 | 
            -
                      import_all
         | 
| 79 | 
            -
                    else
         | 
| 80 | 
            -
                      import_docs converter.xml_for(what.to_sym)
         | 
| 81 88 | 
             
                    end
         | 
| 82 89 | 
             
                  end
         | 
| 83 90 |  | 
| 84 | 
            -
                  def  | 
| 85 | 
            -
                     | 
| 86 | 
            -
             | 
| 87 | 
            -
                    import_docs converter.xml_for(:parties) unless ignore.include?(:parties)
         | 
| 88 | 
            -
                    import_docs converter.xml_for(:committees) unless ignore.include?(:committees)
         | 
| 89 | 
            -
                    import_docs converter.xml_for(:districts) unless ignore.include?(:districts)
         | 
| 90 | 
            -
                    import_docs converter.xml_for(:representatives) unless ignore.include?(:representatives)
         | 
| 91 | 
            -
                    import_docs converter.xml_for(:categories) unless ignore.include?(:categories)
         | 
| 92 | 
            -
                    import_docs converter.xml_for(:issues) unless ignore.include?(:issues)
         | 
| 93 | 
            -
                    import_docs converter.xml_for(:votes) unless ignore.include?(:votes)
         | 
| 91 | 
            +
                  def read_dld_votes
         | 
| 92 | 
            +
                    doc = Nokogiri::XML.parse(File.read(File.join(StortingImporter.root, 'folketingparser/data/votering-2011-04-04-dld-hdo.xml')))
         | 
| 93 | 
            +
                    votes = Vote.from_hdo_doc doc
         | 
| 94 94 |  | 
| 95 | 
            -
                     | 
| 96 | 
            -
             | 
| 97 | 
            -
             | 
| 98 | 
            -
             | 
| 99 | 
            -
             | 
| 100 | 
            -
                    @converter ||= Converter.new(data_source)
         | 
| 101 | 
            -
                  end
         | 
| 102 | 
            -
             | 
| 103 | 
            -
                  def import_dld
         | 
| 104 | 
            -
                    if has_submodule?
         | 
| 105 | 
            -
                      print_or_import File.read(File.join(StortingImporter.root, 'data/dld-issues.xml'))
         | 
| 106 | 
            -
                      print_or_import File.read(File.join(StortingImporter.root, 'folketingparser/data/votering-2011-04-04-dld-hdo.xml'))
         | 
| 107 | 
            -
                    else
         | 
| 108 | 
            -
                      $stderr.puts "folketingparser not found, skipping DLD votes and issues (run `git submodule update --init` if you need this)"
         | 
| 109 | 
            -
                    end
         | 
| 110 | 
            -
                  end
         | 
| 111 | 
            -
             | 
| 112 | 
            -
                  def import_promises
         | 
| 113 | 
            -
                    csvs = Dir[File.join(StortingImporter.root, 'data/promises-*.csv')].sort_by { |e| File.basename(e) }
         | 
| 114 | 
            -
                    csvs.each do |path|
         | 
| 115 | 
            -
                      print_or_import PromiseConverter.new(path).xml
         | 
| 95 | 
            +
                    Util.builder do |xml|
         | 
| 96 | 
            +
                      xml.instruct!
         | 
| 97 | 
            +
                      xml.votes do |votes_builder|
         | 
| 98 | 
            +
                        votes.each { |v| v.to_hdo_xml(votes_builder) }
         | 
| 99 | 
            +
                      end
         | 
| 116 100 | 
             
                    end
         | 
| 117 101 | 
             
                  end
         | 
| 118 102 |  | 
| 119 | 
            -
                  def  | 
| 120 | 
            -
                     | 
| 121 | 
            -
             | 
| 122 | 
            -
                     | 
| 123 | 
            -
                       | 
| 103 | 
            +
                  def read_promises
         | 
| 104 | 
            +
                    csvs = @files.any? ? @files : Dir[File.join(StortingImporter.root, 'data/promises-*.csv')].sort_by { |e| File.basename(e) }
         | 
| 105 | 
            +
                    content = ''
         | 
| 106 | 
            +
                    csvs.each do |csv|
         | 
| 107 | 
            +
                      content << File.read(File.expand_path(csv), encoding: "ISO-8859-1").encode("UTF-8")
         | 
| 124 108 | 
             
                    end
         | 
| 125 | 
            -
                  end
         | 
| 126 109 |  | 
| 127 | 
            -
             | 
| 128 | 
            -
             | 
| 129 | 
            -
                       | 
| 130 | 
            -
             | 
| 131 | 
            -
                       | 
| 110 | 
            +
                    Util.builder do |xml|
         | 
| 111 | 
            +
                      xml.instruct!
         | 
| 112 | 
            +
                      xml.promises do |promises|
         | 
| 113 | 
            +
                        Promise.from_csv(content).each { |e| e.to_hdo_xml(promises) }
         | 
| 114 | 
            +
                      end
         | 
| 132 115 | 
             
                    end
         | 
| 133 116 | 
             
                  end
         | 
| 134 117 |  | 
| 135 | 
            -
                  def has_submodule?
         | 
| 136 | 
            -
                    File.exist?(File.join(StortingImporter.root, 'folketingparser/data'))
         | 
| 137 | 
            -
                  end
         | 
| 138 | 
            -
             | 
| 139 118 | 
             
                end
         | 
| 140 119 | 
             
              end
         | 
| 141 120 | 
             
            end
         | 
| @@ -5,6 +5,22 @@ module Hdo | |
| 5 5 |  | 
| 6 6 | 
             
                  attr_reader :external_id, :name
         | 
| 7 7 |  | 
| 8 | 
            +
                  def self.type_name
         | 
| 9 | 
            +
                    'committee'
         | 
| 10 | 
            +
                  end
         | 
| 11 | 
            +
             | 
| 12 | 
            +
                  def self.description
         | 
| 13 | 
            +
                    'a parliamentary committe'
         | 
| 14 | 
            +
                  end
         | 
| 15 | 
            +
             | 
| 16 | 
            +
                  def self.xml_example(builder = Util.builder)
         | 
| 17 | 
            +
                    new("ARBSOS", "Arbeids- og sosialkomiteen").to_hdo_xml(builder)
         | 
| 18 | 
            +
                  end
         | 
| 19 | 
            +
             | 
| 20 | 
            +
                  def self.fields
         | 
| 21 | 
            +
                    [EXTERNAL_ID_FIELD, Field.new(:name, true, :string, 'The name of the committee.')]
         | 
| 22 | 
            +
                  end
         | 
| 23 | 
            +
             | 
| 8 24 | 
             
                  def self.from_storting_doc(doc)
         | 
| 9 25 | 
             
                    doc.css("komiteer_liste komite").map do |node|
         | 
| 10 26 | 
             
                      from_storting_node(node)
         | 
| @@ -15,6 +31,10 @@ module Hdo | |
| 15 31 | 
             
                    new node.css("id").first.text, node.css("navn").first.text
         | 
| 16 32 | 
             
                  end
         | 
| 17 33 |  | 
| 34 | 
            +
                  def self.from_hdo_doc(doc)
         | 
| 35 | 
            +
                    doc.css("committees > committee").map { |e| from_hdo_node e }
         | 
| 36 | 
            +
                  end
         | 
| 37 | 
            +
             | 
| 18 38 | 
             
                  def self.from_hdo_node(node)
         | 
| 19 39 | 
             
                    new node.css("externalId").first.text, node.css("name").first.text
         | 
| 20 40 | 
             
                  end
         | 
| @@ -5,6 +5,22 @@ module Hdo | |
| 5 5 |  | 
| 6 6 | 
             
                  attr_reader :external_id, :name
         | 
| 7 7 |  | 
| 8 | 
            +
                  def self.type_name
         | 
| 9 | 
            +
                    'district'
         | 
| 10 | 
            +
                  end
         | 
| 11 | 
            +
             | 
| 12 | 
            +
                  def self.description
         | 
| 13 | 
            +
                    'an electoral district'
         | 
| 14 | 
            +
                  end
         | 
| 15 | 
            +
             | 
| 16 | 
            +
                  def self.xml_example(builder = Util.builder)
         | 
| 17 | 
            +
                    new("Db", "Duckburg").to_hdo_xml(builder)
         | 
| 18 | 
            +
                  end
         | 
| 19 | 
            +
             | 
| 20 | 
            +
                  def self.fields
         | 
| 21 | 
            +
                    [EXTERNAL_ID_FIELD, Field.new(:name, true, :string, 'The name of the electoral district.')]
         | 
| 22 | 
            +
                  end
         | 
| 23 | 
            +
             | 
| 8 24 | 
             
                  def self.from_storting_doc(doc)
         | 
| 9 25 | 
             
                    doc.css("fylker_liste fylke").map do |node|
         | 
| 10 26 | 
             
                      from_storting_node(node)
         | 
| @@ -15,6 +31,10 @@ module Hdo | |
| 15 31 | 
             
                    new node.css("id").first.text, node.css("navn").first.text
         | 
| 16 32 | 
             
                  end
         | 
| 17 33 |  | 
| 34 | 
            +
                  def self.from_hdo_doc(doc)
         | 
| 35 | 
            +
                    doc.css("districts > district").map { |e| from_hdo_node(e) }
         | 
| 36 | 
            +
                  end
         | 
| 37 | 
            +
             | 
| 18 38 | 
             
                  def self.from_hdo_node(node)
         | 
| 19 39 | 
             
                    new node.css("externalId").first.text, node.css("name").first.text
         | 
| 20 40 | 
             
                  end
         | 
| @@ -1,3 +1,5 @@ | |
| 1 | 
            +
            # encoding: UTF-8
         | 
| 2 | 
            +
             | 
| 1 3 | 
             
            module Hdo
         | 
| 2 4 | 
             
              module StortingImporter
         | 
| 3 5 | 
             
                class Issue
         | 
| @@ -6,6 +8,48 @@ module Hdo | |
| 6 8 | 
             
                  attr_reader :external_id, :summary, :description, :type, :status, :last_update,
         | 
| 7 9 | 
             
                              :reference, :document_group, :committee, :categories
         | 
| 8 10 |  | 
| 11 | 
            +
                  def self.type_name
         | 
| 12 | 
            +
                    'issue'
         | 
| 13 | 
            +
                  end
         | 
| 14 | 
            +
             | 
| 15 | 
            +
                  def self.description
         | 
| 16 | 
            +
                    'a parliament issue'
         | 
| 17 | 
            +
                  end
         | 
| 18 | 
            +
             | 
| 19 | 
            +
                  def self.example
         | 
| 20 | 
            +
                    new(
         | 
| 21 | 
            +
                      "53520",
         | 
| 22 | 
            +
                      "Inngåelse av avtale om opprettelse av sekretariatet for Den nordlige dimensjons partnerskap for helse og livskvalitet (NDPHS)",
         | 
| 23 | 
            +
                      "Samtykke til inngåelse av avtale av 25. november 2011 om opprettelse av sekretariatet for Den nordlige dimensjons partnerskap for helse og livskvalitet (NDPHS)",
         | 
| 24 | 
            +
                      "alminneligsak",
         | 
| 25 | 
            +
                      "mottatt",
         | 
| 26 | 
            +
                      "2012-04-20T00:00:00",
         | 
| 27 | 
            +
                      "Prop. 90 S (2011-2012)",
         | 
| 28 | 
            +
                      "proposisjon",
         | 
| 29 | 
            +
                      "Transport- og kommunikasjonskomiteen",
         | 
| 30 | 
            +
                      ['UTENRIKSSAKER', 'TRAKTATER', 'NORDISK SAMARBEID']
         | 
| 31 | 
            +
                    )
         | 
| 32 | 
            +
                  end
         | 
| 33 | 
            +
             | 
| 34 | 
            +
                  def self.xml_example(builder = Util.builder)
         | 
| 35 | 
            +
                    example.to_hdo_xml(builder)
         | 
| 36 | 
            +
                  end
         | 
| 37 | 
            +
             | 
| 38 | 
            +
                  def self.fields
         | 
| 39 | 
            +
                    [
         | 
| 40 | 
            +
                      EXTERNAL_ID_FIELD,
         | 
| 41 | 
            +
                      Field.new(:summary,       true,  :string, 'A (preferably one-line) summary of the issue.'),
         | 
| 42 | 
            +
                      Field.new(:description,   true,  :string, 'A longer description of the issue.'),
         | 
| 43 | 
            +
                      Field.new(:type,          true,  :string, 'The type of issue.'),
         | 
| 44 | 
            +
                      Field.new(:status,        true,  :string, 'The status of the issue.'),
         | 
| 45 | 
            +
                      Field.new(:lastUpdate,    true,  :string, 'The time the issue was last updated in the parliament.'),
         | 
| 46 | 
            +
                      Field.new(:reference,     true,  :string, 'A reference.'),
         | 
| 47 | 
            +
                      Field.new(:documentGroup, true,  :string, 'What document group this issue belongs to.'),
         | 
| 48 | 
            +
                      Field.new(:committee,     false, :string, "What committee this issue belongs to. Should match the 'name' field in the committee type."),
         | 
| 49 | 
            +
                      Field.new(:categories,    false, 'list',  "List of categories (matching the 'name' field of the category type).")
         | 
| 50 | 
            +
                    ]
         | 
| 51 | 
            +
                  end
         | 
| 52 | 
            +
             | 
| 9 53 | 
             
                  def self.from_storting_doc(doc)
         | 
| 10 54 | 
             
                    doc.css("saker_liste sak").map do |node|
         | 
| 11 55 | 
             
                      from_storting_node(node)
         | 
| @@ -33,6 +77,13 @@ module Hdo | |
| 33 77 | 
             
                    end
         | 
| 34 78 |  | 
| 35 79 | 
             
                    new(external_id, summary, description, type, status, last_update, reference, document_group, committee, categories)
         | 
| 80 | 
            +
                  rescue
         | 
| 81 | 
            +
                    puts lnode
         | 
| 82 | 
            +
                    raise
         | 
| 83 | 
            +
                  end
         | 
| 84 | 
            +
             | 
| 85 | 
            +
                  def self.from_hdo_doc(doc)
         | 
| 86 | 
            +
                    doc.css("issues > issue").map { |e| from_hdo_node(e) }
         | 
| 36 87 | 
             
                  end
         | 
| 37 88 |  | 
| 38 89 | 
             
                  def self.from_hdo_node(node)
         |