Module: GoodData::Model

Defined in:
lib/gooddata/models/model.rb,
lib/gooddata/models/from_wire.rb,
lib/gooddata/models/tab_builder.rb,
lib/gooddata/models/project_creator.rb,
lib/gooddata/models/module_constants.rb,
lib/gooddata/models/blueprint/to_wire.rb,
lib/gooddata/models/blueprint/fact_field.rb,
lib/gooddata/models/blueprint/label_field.rb,
lib/gooddata/models/blueprint/to_manifest.rb,
lib/gooddata/models/blueprint/anchor_field.rb,
lib/gooddata/models/blueprint/date_dimension.rb,
lib/gooddata/models/blueprint/schema_builder.rb,
lib/gooddata/models/blueprint/attribute_field.rb,
lib/gooddata/models/blueprint/blueprint_field.rb,
lib/gooddata/models/blueprint/project_builder.rb,
lib/gooddata/models/blueprint/reference_field.rb,
lib/gooddata/models/blueprint/schema_blueprint.rb,
lib/gooddata/models/blueprint/dashboard_builder.rb,
lib/gooddata/models/blueprint/dataset_blueprint.rb,
lib/gooddata/models/blueprint/project_blueprint.rb

Defined Under Namespace

Modules: FromWire, ToManifest, ToWire Classes: AnchorBlueprintField, AttributeBlueprintField, BlueprintField, DashboardBuilder, DatasetBlueprint, DateDimension, FactBlueprintField, LabelBlueprintField, ProjectBlueprint, ProjectBuilder, ProjectCreator, ReferenceBlueprintField, SchemaBlueprint, SchemaBuilder, TabBuilder

Constant Summary collapse

GD_TYPES =

See https://confluence.intgdc.com/display/plat/Catalog+of+Attribute+Types

[
  # Common Types
  'GDC.link',
  'GDC.text',
  'GDC.time',

  # Common Date Attribute Types
  'GDC.time.year',
  'GDC.time.quarter',
  'GDC.time.month',
  'GDC.time.week',
  'GDC.time.date',

  # Specific Date Attribute Types
  'GDC.time.day_in_euweek',
  'GDC.time.day_in_week',
  'GDC.time.day_in_month',
  'GDC.time.day_in_quarter',
  'GDC.time.day_in_year',
  'GDC.time.euweek_in_quarter',
  'GDC.time.week_in_quarter',
  'GDC.time.euweek_in_year',
  'GDC.time.week_in_year',
  'GDC.time.month_in_quarter',
  'GDC.time.month_in_year',
  'GDC.time.quarter_in_year',

  # Legacy Date Attribute Types - Possibly Obsolete
  'GDC.time.dayOfWeek',
  'GDC.time.dayOfMonth',
  'GDC.time.dayOfQuarter',
  'GDC.time.dayOfYear',
  'GDC.time.weekOfYear',
  'GDC.time.monthOfYear',
  'GDC.time.quarterOfYear',

  # Types for Geo
  'GDC.geo.pin',                 # Geo pushpin
  'GDC.geo.ausstates.name',      # Australia States (Name)
  'GDC.geo.ausstates.code',      # Australia States (ISO code)
  'GDC.geo.usstates.name',       # US States (Name)
  'GDC.geo.usstates.geo_id',     # US States (US Census ID)
  'GDC.geo.usstates.code',       # US States (2-letter code)
  'GDC.geo.uscounties.geo_id',   # US Counties (US Census ID)
  'GDC.geo.worldcountries.name', # World countries (Name)
  'GDC.geo.worldcountries.iso2', # World countries (ISO a2)
  'GDC.geo.worldcountries.iso3', # World countries (ISO a3)
  'GDC.geo.czdistricts.name',    #	Czech Districts (Name)
  'GDC.geo.czdistricts.name_no_diacritics', # Czech Districts
  'GDC.geo.czdistricts.nuts4',   # Czech Districts (NUTS 4)
  'GDC.geo.czdistricts.knok',    # Czech Districts (KNOK)

  # Day Display Forms
  'GDC.time.day',              # yyyy-MM-dd
  'GDC.time.day_us',           # MM/dd/yyyy
  'GDC.time.day_eu',           # dd/MM/yyyy
  'GDC.time.day_iso',          # dd-MM-yyyy
  'GDC.time.day_us_long',      # EEE, MMM d, yyyy
  'GDC.time.day_us_noleading', # M/d/yy
]
GD_DATA_TYPES = 
['BIGINT', 'DOUBLE', 'INTEGER', 'INT', /^VARCHAR\(\d{1,4}\)$/i, /^DECIMAL\(\d{1,3},\s*\d{1,3}\)$/i]
DEFAULT_FACT_DATATYPE = 
'DECIMAL(12,2)'
DEFAULT_ATTRIBUTE_DATATYPE = 
'VARCHAR(128)'
DEFAULT_TYPE = 
'GDC.text'
DEFAULT_DATE_FORMAT = 
'MM/dd/yyyy'
LDM_CTG =

GoodData REST API categories

'ldm'
LDM_MANAGE_CTG = 
'ldm-manage2'
FIELD_PK =

Model naming conventions

'id'
FK_SUFFIX = 
'_id'
FACT_COLUMN_PREFIX = 
'f_'
DATE_COLUMN_PREFIX = 
'dt_'
TIME_COLUMN_PREFIX = 
'tm_'
LABEL_COLUMN_PREFIX = 
'nm_'
ATTRIBUTE_FOLDER_PREFIX = 
'dim'
ATTRIBUTE_PREFIX = 
'attr'
LABEL_PREFIX = 
'label'
FACT_PREFIX = 
'fact'
DATE_FACT_PREFIX = 
'dt'
DATE_ATTRIBUTE = 
'date'
DATE_ATTRIBUTE_DEFAULT_DISPLAY_FORM = 
'mdyy'
TIME_FACT_PREFIX = 
'tm.dt'
TIME_ATTRIBUTE_PREFIX = 
'attr.time'
FACT_FOLDER_PREFIX = 
'ffld'

Class Method Summary collapse

Class Method Details

.check_gd_data_type(value) ⇒ Object 



115
116
117
118
119
120
121
122
123
124
125
126
 
# File 'lib/gooddata/models/model.rb', line 115

def check_gd_data_type(value)
  GD_DATA_TYPES.any? do |v|
    case v
    when Regexp
      v =~ value
    when String
      v == (value && value.upcase)
    else
      fail 'Unkown predicate'
    end
  end
end

.check_gd_type(value) ⇒ Object 



111
112
113
 
# File 'lib/gooddata/models/model.rb', line 111

def check_gd_type(value)
  GD_TYPES.any? { |v| v == value }
end

.column_name(item) ⇒ Object 



103
104
105
 
# File 'lib/gooddata/models/model.rb', line 103

def column_name(item)
  item[:column_name] || item[:id]
end

.description(item) ⇒ Object 



107
108
109
 
# File 'lib/gooddata/models/model.rb', line 107

def description(item)
  item[:description]
end

.merge_dataset_columns(a_schema_blueprint, b_schema_blueprint) ⇒ Object 



264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
 
# File 'lib/gooddata/models/model.rb', line 264

def merge_dataset_columns(a_schema_blueprint, b_schema_blueprint)
  a_schema_blueprint = a_schema_blueprint.to_hash
  b_schema_blueprint = b_schema_blueprint.to_hash
  d = GoodData::Helpers.deep_dup(a_schema_blueprint)
  d[:columns] = d[:columns] + b_schema_blueprint[:columns]
  d[:columns].uniq!
  columns_that_failed_to_merge = d[:columns].group_by { |x| [:reference, :date].include?(x[:type]) ? x[:dataset] : x[:id] }.map { |k, v| [k, v.count, v] }.select { |x| x[1] > 1 }
  unless columns_that_failed_to_merge.empty?
    columns_that_failed_to_merge.each do |error|
      GoodData.logger.error "Columns #{error[0]} failed to merge. There are #{error[1]} conflicting columns. When merging columns with the same name they have to be identical."
      GoodData.logger.error error[2]
    end
    fail "Columns #{columns_that_failed_to_merge.first} failed to merge. There are #{columns_that_failed_to_merge[1]} conflicting columns. #{columns_that_failed_to_merge[2]} When merging columns with the same name they have to be identical." unless columns_that_failed_to_merge.empty?
  end
  d
end

.normalize_gd_data_type(type) ⇒ Object 



128
129
130
131
132
133
134
 
# File 'lib/gooddata/models/model.rb', line 128

def normalize_gd_data_type(type)
  if type && type.upcase == 'INTEGER'
    'INT'
  else
    type
  end
end

.title(item) ⇒ Object 



99
100
101
 
# File 'lib/gooddata/models/model.rb', line 99

def title(item)
  item[:title] || GoodData::Helpers.titleize(item[:id])
end

.upload_data(path, project_blueprint, dataset, options = { :client => GoodData.connection, :project => GoodData.project }) ⇒ Object

Load given file into a data set described by the given schema



137
138
139
140
141
142
143
144
145
146
 
# File 'lib/gooddata/models/model.rb', line 137

def upload_data(path, project_blueprint, dataset, options = { :client => GoodData.connection, :project => GoodData.project })
  data = [
    {
      data: path,
      dataset: dataset,
      options: options
    }
  ]
  GoodData::Model.upload_multiple_data(data, project_blueprint, options)
end

.upload_multiple_data(data, project_blueprint, options = { :client => GoodData.connection, :project => GoodData.project }) ⇒ Hash

Uploads multiple data sets using batch upload interface

Parameters:

  • data (String|Array) —

    Input data

  • project_blueprint (ProjectBlueprint) —

    Project blueprint

  • options (Hash) (defaults to: { :client => GoodData.connection, :project => GoodData.project }) —

    Additional options

Returns:

  • (Hash) —

    Batch upload result



153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
 
# File 'lib/gooddata/models/model.rb', line 153

def upload_multiple_data(data, project_blueprint, options = { :client => GoodData.connection, :project => GoodData.project })
  client, project = GoodData.get_client_and_project(options)

  project ||= GoodData.project

  manifest = {

    'dataSetSLIManifestList' => data.map do |d|
      mode = d[:options] && d[:options][:mode] ? d[:options][:mode] : options[:mode] || 'FULL'
      GoodData::Model::ToManifest.dataset_to_manifest(project_blueprint, d[:dataset], mode)
    end
  }

  csv_headers = []

  # create a temporary zip file
  dir = Dir.mktmpdir
  begin
    Zip::File.open("#{dir}/upload.zip", Zip::File::CREATE) do |zip|
      # TODO: make sure schema columns match CSV column names
      zip.get_output_stream('upload_info.json') { |f| f.puts JSON.pretty_generate(manifest) }

      data.zip(manifest['dataSetSLIManifestList']).each do |item|
        path = item[0][:data]
        path = item[0][:data].path if item[0][:data].respond_to? :path
        inline_data = !path.is_a?(String)
        csv_header = nil

        filename = item[1]['dataSetSLIManifest']['file']

        if inline_data
          csv_header = path.first
          zip.get_output_stream(filename) do |f|
            path.each do |row|
              f.puts row.to_csv
            end
          end
        else
          csv_header = File.open(path, &:gets).split(',')
          zip.add(filename, path)
        end

        csv_headers << csv_header
      end
    end

    # upload it
    client.upload_to_user_webdav("#{dir}/upload.zip", :directory => File.basename(dir), :client => options[:client], :project => options[:project])
  ensure
    FileUtils.rm_rf dir
  end
  csv_headers.flatten!

  # kick the load
  pull = { 'pullIntegration' => File.basename(dir) }
  link = project.md.links('etl')['pull2']

  # TODO: List uploaded datasets
  task = client.post(link, pull, :info_message => 'Starting the data load from user storage to dataset.')

  res = client.poll_on_response(task['pull2Task']['links']['poll'], :info_message => 'Getting status of the dataload task.') do |body|
    body['wTaskStatus']['status'] == 'RUNNING' || body['wTaskStatus']['status'] == 'PREPARED'
  end

  if res['wTaskStatus']['status'] == 'ERROR'
    s = StringIO.new

    messages = res['wTaskStatus']['messages'] || []
    messages.each do |msg|
      GoodData.logger.error(JSON.pretty_generate(msg))
    end

    begin
      client.download_from_user_webdav(File.basename(dir) + '/upload_status.json', s, :client => client, :project => project)
    rescue => e
      raise "Unable to download upload_status.json from remote server, reason: #{e.message}"
    end

    js = MultiJson.load(s.string)
    manifests = manifest['dataSetSLIManifestList'].map do |m|
      m['dataSetSLIManifest']
    end

    parts = manifests.map do |m|
      m['parts']
    end

    manifest_cols = parts.flatten.map { |c| c['columnName'] }

    # extract some human readable error message from the webdav file
    manifest_extra = manifest_cols - csv_headers
    csv_extra = csv_headers - manifest_cols

    error_message = begin
      js['error']['message'] % js['error']['parameters']
    rescue NoMethodError, ArgumentError
      ''
    end
    m = "Load failed with error '#{error_message}'.\n"
    m += "Columns that should be there (manifest) but aren't in uploaded csv: #{manifest_extra}\n" unless manifest_extra.empty?
    m += "Columns that are in csv but shouldn't be there (manifest): #{csv_extra}\n" unless csv_extra.empty?
    m += "Columns in the uploaded csv: #{csv_headers}\n"
    m += "Columns in the manifest: #{manifest_cols}\n"
    m += "Original message:\n#{JSON.pretty_generate(js)}\n"
    m += "Manifest used for uploading:\n#{JSON.pretty_generate(manifest)}"
    fail m
  end

  res
end