Class: Dreader::Engine

Inherits:
Object
  • Object
show all
Defined in:
lib/dreader.rb

Overview

This is where the real stuff begins

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize ⇒ Engine

Returns a new instance of Engine.



108
109
110
111
112
 
# File 'lib/dreader.rb', line 108

def initialize
  @options = {}
  @colspec = []
  @virtualcols = []
end

Instance Attribute Details

#colspec ⇒ Object (readonly)

the specification of the columns to process



104
105
106
 
# File 'lib/dreader.rb', line 104

def colspec
  @colspec
end

#options(&block) ⇒ Object (readonly)

define a DSL for options any string is processed as an option and it ends up in the



102
103
104
 
# File 'lib/dreader.rb', line 102

def options
  @options
end

#table ⇒ Object (readonly)

the data we read



106
107
108
 
# File 'lib/dreader.rb', line 106

def table
  @table
end

Instance Method Details

#column(name, &block) ⇒ Object

define a DSL for column specification

  • ‘name` is the name of the column

  • ‘block` contains two declarations, `process` and `check`, which are used, respectively, to make a cell into the desired data and to check whether the desired data is ok



129
130
131
132
133
134
 
# File 'lib/dreader.rb', line 129

def column name, &block
  column = Column.new
  column.instance_eval(&block)

  @colspec << column.to_hash.merge({name: name})
end

#debug(args = {}) ⇒ Object

show to stdout the first ‘n` records we read from the file given the current configuration



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
 
# File 'lib/dreader.rb', line 210

def debug args = {}
  hash = @options.merge(args)

  # apply some defaults, if not defined in the options
  hash[:process] = true if not hash.has_key? :process # shall we apply the process function?
  hash[:check] = true if not hash.has_key? :check     # shall we check the data read?
  hash[:n] = 10 if not hash[:n]

  spreadsheet = Dreader::Engine.open_spreadsheet (hash[:filename])
  sheet = spreadsheet.sheet(hash[:sheet] || 0)

  puts "Current configuration:"
  @options.each do |k, v|
    puts "  #{k}: #{v}"
  end

  puts "Configuration used by debug:"
  hash.each do |k, v|
    puts "  #{k}: #{v}"
  end
 
  n = hash[:n]
  first_row = hash[:first_row] || 1
  last_row = first_row + n - 1

  puts "  Last row (according to roo): #{sheet.last_row}"
  puts "  Number of rows I will read in this session: #{n} (from #{first_row} to #{last_row})"
  
  (first_row..last_row).each do |row_number|
    puts "Row #{row_number} is:"
    r = Hash.new
    @colspec.each_with_index do |colspec, index|
      colname = colspec[:name]
      cell = sheet.cell(row_number, colspec[:colref])

      processed_str = ""
      checked_str = ""
      
      if hash[:process]
        processed = colspec[:process] ? colspec[:process].call(cell) : cell
        processed_str = "processed: '#{processed}' (#{processed.class})"
      end
      if hash[:check]
        processed = colspec[:process] ? colspec[:process].call(cell) : cell
        check = colspec[:check] ? colspec[:check].call(processed) : "no check specified"
        checked_str = "checked: '#{check}'"
      end

      puts "  #{colname} => orig: '#{cell}' (#{cell.class}) #{processed_str} #{checked_str} (column: '#{colspec[:colref]}')"
    end
  end
end

#errors ⇒ Object

return an array of strings with all the errors we have encounterd an empty array is a good news



265
266
267
 
# File 'lib/dreader.rb', line 265

def errors
  @errors
end

#mapping(&block) ⇒ Object

define what we do with each line we read

  • ‘block` is the code which takes as input a `row` and processes `row` is a hash in which each spreadsheet cell is accessible under the column names. Each cell has the following values: :value, :error, :row_number, :col_number



154
155
156
 
# File 'lib/dreader.rb', line 154

def mapping &block
  @mapping = block
end

#process ⇒ Object

apply the mapping code to the array it makes sense to invoke it only once

the mapping is applied only if it defined



286
287
288
289
290
 
# File 'lib/dreader.rb', line 286

def process
  @table.each do |r|
    @mapping.call(r) if @mapping
  end
end

#read(args = {}) ⇒ Object Also known as: load

read a file and store it internally

Parameters:

  • hash, —

    a hash, possibly overriding any of the parameters set in the initial options. This allows you, for instance, to apply the same column specification to different files and different sheets

Returns:

  • the data read from filename, in the form of an array of hashes



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
 
# File 'lib/dreader.rb', line 167

def read args = {}
  hash = @options.merge(args)

  spreadsheet = Dreader::Engine.open_spreadsheet (hash[:filename])
  sheet = spreadsheet.sheet(hash[:sheet] || 0)

  @table = Array.new
  @errors = Array.new

  first_row = hash[:first_row] || 1
  last_row = hash[:last_row] || sheet.last_row

  (first_row..last_row).each do |row_number|
    r = Hash.new
    @colspec.each_with_index do |colspec, index|
      cell = sheet.cell(row_number, colspec[:colref])
      
      colname = colspec[:name]

      r[colname] = Hash.new
      r[colname][:row_number] = row_number
      r[colname][:col_number] = colspec[:colref]

      r[colname][:value] = value = colspec[:process] ? colspec[:process].call(cell) : cell

      if colspec[:check] and not colspec[:check].call(value) then
        r[colname][:error] = true
        @errors << "Error: value \"#{cell}\" for #{colname} at row #{row_number} (col #{index + 1}) does not pass the check function"
      else
        r[colname][:error] = false
      end
    end

    @table << r
  end

  @table
end

#to_s ⇒ Object 



292
293
294
 
# File 'lib/dreader.rb', line 292

def to_s
  @table.to_s
end

#virtual_column(name, &block) ⇒ Object

virtual columns define derived attributes the code specified in the virtual column is executed after reading a row and before applying the mapping function

virtual colum declarations are executed in the order in which they are defined



142
143
144
145
146
147
 
# File 'lib/dreader.rb', line 142

def virtual_column name, &block
  column = Column.new
  column.instance_eval &block

  @virtualcols << column.to_hash.merge({name: name})
end

#virtual_columns ⇒ Object 



269
270
271
272
273
274
275
276
277
278
279
280
 
# File 'lib/dreader.rb', line 269

def virtual_columns
  # execute the virtual column specification
  @virtualcols.each do |virtualcol|
    @table.each do |r|
      # add the cell to the table
      r[virtualcol[:name]] = {
        value: virtualcol[:process].call(r),
        virtual: true,
      }
    end
  end
end