Class: Roo::Base

Inherits:
Object
  • Object
show all
Includes:
Enumerable
Defined in:
lib/roo/base.rb

Overview

Base class for all other types of spreadsheets

Direct Known Subclasses

CSV, Excelx, OpenOffice

Constant Summary collapse

TEMP_PREFIX =
'roo_'.freeze
MAX_ROW_COL =
999_999.freeze
MIN_ROW_COL =
0.freeze

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(filename, options = {}, _file_warning = :error, _tmpdir = nil) ⇒ Base

Returns a new instance of Base.


21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
# File 'lib/roo/base.rb', line 21

def initialize(filename, options = {}, _file_warning = :error, _tmpdir = nil)
  @filename = filename
  @options = options

  @cell = {}
  @cell_type = {}
  @cells_read = {}

  @first_row = {}
  @last_row = {}
  @first_column = {}
  @last_column = {}

  @header_line = 1
rescue => e # clean up any temp files, but only if an error was raised
  close
  raise e
end

Dynamic Method Handling

This class handles dynamic methods through the method_missing method

#method_missing(m, *args) ⇒ Object

when a method like spreadsheet.a42 is called convert it to a call of spreadsheet.cell('a',42)


303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
# File 'lib/roo/base.rb', line 303

def method_missing(m, *args)
  # #aa42 => #cell('aa',42)
  # #aa42('Sheet1')  => #cell('aa',42,'Sheet1')
  if m =~ /^([a-z]+)(\d+)$/
    col = ::Roo::Utils.letter_to_number(Regexp.last_match[1])
    row = Regexp.last_match[2].to_i
    if args.empty?
      cell(row, col)
    else
      cell(row, col, args.first)
    end
  else
    super
  end
end

Instance Attribute Details

#header_lineObject

sets the line with attribute names (default: 1)


19
20
21
# File 'lib/roo/base.rb', line 19

def header_line
  @header_line
end

#headersObject (readonly)

Returns the value of attribute headers


16
17
18
# File 'lib/roo/base.rb', line 16

def headers
  @headers
end

Instance Method Details

#cell_type_by_value(value) ⇒ Object


224
225
226
227
228
229
230
231
# File 'lib/roo/base.rb', line 224

def cell_type_by_value(value)
  case value
  when Fixnum then :float
  when String, Float then :string
  else
    fail ArgumentError, "Type for #{value} not set"
  end
end

#closeObject


40
41
42
43
44
# File 'lib/roo/base.rb', line 40

def close
  return nil unless @tmpdirs
  @tmpdirs.each { |dir| ::FileUtils.remove_entry(dir) }
  nil
end

#collect_last_row_col_for_sheet(sheet) ⇒ Object

Collect first/last row/column from sheet


84
85
86
87
88
89
90
91
92
93
94
95
# File 'lib/roo/base.rb', line 84

def collect_last_row_col_for_sheet(sheet)
  first_row = first_column = MAX_ROW_COL
  last_row = last_column = MIN_ROW_COL
  @cell[sheet].each_pair do|key, value|
    next unless value
    first_row = [first_row, key.first.to_i].min
    last_row = [last_row, key.first.to_i].max
    first_column = [first_column, key.last.to_i].min
    last_column = [last_column, key.last.to_i].max
  end if @cell[sheet]
  { first_row: first_row, first_column: first_column, last_row: last_row, last_column: last_column }
end

#column(column_number, sheet = default_sheet) ⇒ Object

returns all values in this column as an array column numbers are 1,2,3,… like in the spreadsheet


204
205
206
207
208
209
210
211
212
# File 'lib/roo/base.rb', line 204

def column(column_number, sheet = default_sheet)
  if column_number.is_a?(::String)
    column_number = ::Roo::Utils.letter_to_number(column_number)
  end
  read_cells(sheet)
  first_row(sheet).upto(last_row(sheet)).map do |row|
    cell(row, column_number, sheet)
  end
end

#default_sheetObject


46
47
48
# File 'lib/roo/base.rb', line 46

def default_sheet
  @default_sheet ||= sheets.first
end

#default_sheet=(sheet) ⇒ Object

sets the working sheet in the document 'sheet' can be a number (1 = first sheet) or the name of a sheet.


52
53
54
55
56
57
# File 'lib/roo/base.rb', line 52

def default_sheet=(sheet)
  validate_sheet!(sheet)
  @default_sheet = sheet
  @first_row[sheet] = @last_row[sheet] = @first_column[sheet] = @last_column[sheet] = nil
  @cells_read[sheet] = false
end

#each(options = {}) ⇒ Object

you can also pass in a :clean => true option to strip the sheet of control characters and white spaces around columns


355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
# File 'lib/roo/base.rb', line 355

def each(options = {})
  return to_enum(:each, options) unless block_given?

  if options.empty?
    1.upto(last_row) do |line|
      yield row(line)
    end
  else
    clean_sheet_if_need(options)
    search_or_set_header(options)
    headers = @headers ||
              Hash[(first_column..last_column).map do |col|
                [cell(@header_line, col), col]
              end]

    @header_line.upto(last_row) do |line|
      yield(Hash[headers.map { |k, v| [k, cell(line, v)] }])
    end
  end
end

#each_with_pagenameObject

iterate through all worksheets of a document


327
328
329
330
331
# File 'lib/roo/base.rb', line 327

def each_with_pagename
  sheets.each do |s|
    yield sheet(s, true)
  end
end

#empty?(row, col, sheet = default_sheet) ⇒ Boolean

true if cell is empty

Returns:

  • (Boolean)

241
242
243
244
245
246
247
# File 'lib/roo/base.rb', line 241

def empty?(row, col, sheet = default_sheet)
  read_cells(sheet)
  row, col = normalize(row, col)
  contents = cell(row, col, sheet)
  !contents || (celltype(row, col, sheet) == :string && contents.empty?) \
    || (row < first_row(sheet) || row > last_row(sheet) || col < first_column(sheet) || col > last_column(sheet))
end

#find(*args) ⇒ Object

find a row either by row number or a condition Caution: this works only within the default sheet -> set default_sheet before you call this method (experimental. see examples in the test_roo.rb file)


180
181
182
183
184
185
186
187
188
189
190
191
# File 'lib/roo/base.rb', line 180

def find(*args) # :nodoc
  options = (args.last.is_a?(Hash) ? args.pop : {})

  case args[0]
  when Fixnum
    find_by_row(args[0])
  when :all
    find_by_conditions(options)
  else
    fail ArgumentError, "unexpected arg #{args[0].inspect}, pass a row index or :all"
  end
end

#first_column_as_letter(sheet = default_sheet) ⇒ Object

first non-empty column as a letter


60
61
62
# File 'lib/roo/base.rb', line 60

def first_column_as_letter(sheet = default_sheet)
  ::Roo::Utils.number_to_letter(first_column(sheet))
end

#first_last_row_col_for_sheet(sheet) ⇒ Object

Set first/last row/column for sheet


70
71
72
73
74
75
76
77
78
79
80
81
# File 'lib/roo/base.rb', line 70

def first_last_row_col_for_sheet(sheet)
  @first_last_row_cols ||= {}
  @first_last_row_cols[sheet] ||= begin
    result = collect_last_row_col_for_sheet(sheet)
    {
      first_row: result[:first_row] == MAX_ROW_COL ? nil : result[:first_row],
      first_column: result[:first_column] == MAX_ROW_COL ? nil : result[:first_column],
      last_row: result[:last_row] == MIN_ROW_COL ? nil : result[:last_row],
      last_column: result[:last_column] == MIN_ROW_COL ? nil : result[:last_column]
    }
  end
end

#infoObject

returns information of the spreadsheet document and all sheets within this document.


251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
# File 'lib/roo/base.rb', line 251

def info
  without_changing_default_sheet do
    result = "File: #{File.basename(@filename)}\n"\
      "Number of sheets: #{sheets.size}\n"\
      "Sheets: #{sheets.join(', ')}\n"
    n = 1
    sheets.each do|sheet|
      self.default_sheet = sheet
      result << 'Sheet ' + n.to_s + ":\n"
      if first_row
        result << "  First row: #{first_row}\n"
        result << "  Last row: #{last_row}\n"
        result << "  First column: #{::Roo::Utils.number_to_letter(first_column)}\n"
        result << "  Last column: #{::Roo::Utils.number_to_letter(last_column)}"
      else
        result << '  - empty -'
      end
      result << "\n" if sheet != sheets.last
      n += 1
    end
    result
  end
end

#inspectObject


173
174
175
# File 'lib/roo/base.rb', line 173

def inspect
  "<##{self.class}:#{object_id.to_s(8)} #{instance_variables.join(' ')}>"
end

#last_column_as_letter(sheet = default_sheet) ⇒ Object

last non-empty column as a letter


65
66
67
# File 'lib/roo/base.rb', line 65

def last_column_as_letter(sheet = default_sheet)
  ::Roo::Utils.number_to_letter(last_column(sheet))
end

#parse(options = {}) ⇒ Object


376
377
378
379
380
381
382
383
# File 'lib/roo/base.rb', line 376

def parse(options = {})
  ary = []
  each(options) do |row|
    yield(row) if block_given?
    ary << row
  end
  ary
end

#reloadObject

reopens and read a spreadsheet document


234
235
236
237
238
# File 'lib/roo/base.rb', line 234

def reload
  ds = default_sheet
  reinitialize
  self.default_sheet = ds
end

#row(row_number, sheet = default_sheet) ⇒ Object

returns all values in this row as an array row numbers are 1,2,3,… like in the spreadsheet


195
196
197
198
199
200
# File 'lib/roo/base.rb', line 195

def row(row_number, sheet = default_sheet)
  read_cells(sheet)
  first_column(sheet).upto(last_column(sheet)).map do |col|
    cell(row_number, col, sheet)
  end
end

#row_with(query, return_headers = false) ⇒ Object


385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
# File 'lib/roo/base.rb', line 385

def row_with(query, return_headers = false)
  line_no = 0
  each do |row|
    line_no += 1
    headers = query.map { |q| row.grep(q)[0] }.compact

    if headers.length == query.length
      @header_line = line_no
      return return_headers ? headers : line_no
    elsif line_no > 100
      raise Roo::HeaderRowNotFoundError
    end
  end
  raise Roo::HeaderRowNotFoundError
end

#set(row, col, value, sheet = default_sheet) ⇒ Object

set a cell to a certain value (this will not be saved back to the spreadsheet file!)


216
217
218
219
220
221
222
# File 'lib/roo/base.rb', line 216

def set(row, col, value, sheet = default_sheet) #:nodoc:
  read_cells(sheet)
  row, col = normalize(row, col)
  cell_type = cell_type_by_value(value)
  set_value(row, col, value, sheet)
  set_type(row, col, cell_type, sheet)
end

#sheet(index, name = false) ⇒ Object

access different worksheets by calling spreadsheet.sheet(1) or spreadsheet.sheet('SHEETNAME')


321
322
323
324
# File 'lib/roo/base.rb', line 321

def sheet(index, name = false)
  self.default_sheet = index.is_a?(::String) ? index : sheets[index]
  name ? [default_sheet, self] : self
end

#to_csv(filename = nil, separator = ',', sheet = default_sheet) ⇒ Object

write the current spreadsheet to stdout or into a file


141
142
143
144
145
146
147
148
149
150
151
152
153
# File 'lib/roo/base.rb', line 141

def to_csv(filename = nil, separator = ',', sheet = default_sheet)
  if filename
    File.open(filename, 'w') do |file|
      write_csv_content(file, sheet, separator)
    end
    true
  else
    sio = ::StringIO.new
    write_csv_content(sio, sheet, separator)
    sio.rewind
    sio.read
  end
end

#to_matrix(from_row = nil, from_column = nil, to_row = nil, to_column = nil, sheet = default_sheet) ⇒ Object

returns a matrix object from the whole sheet or a rectangular area of a sheet


156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
# File 'lib/roo/base.rb', line 156

def to_matrix(from_row = nil, from_column = nil, to_row = nil, to_column = nil, sheet = default_sheet)
  require 'matrix'

  return Matrix.empty unless first_row

  from_row ||= first_row(sheet)
  to_row ||= last_row(sheet)
  from_column ||= first_column(sheet)
  to_column ||= last_column(sheet)

  Matrix.rows(from_row.upto(to_row).map do |row|
    from_column.upto(to_column).map do |col|
      cell(row, col, sheet)
    end
  end)
end

#to_xmlObject

returns an XML representation of all sheets of a spreadsheet file


276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
# File 'lib/roo/base.rb', line 276

def to_xml
  Nokogiri::XML::Builder.new do |xml|
    xml.spreadsheet do
      sheets.each do |sheet|
        self.default_sheet = sheet
        xml.sheet(name: sheet) do |x|
          if first_row && last_row && first_column && last_column
            # sonst gibt es Fehler bei leeren Blaettern
            first_row.upto(last_row) do |row|
              first_column.upto(last_column) do |col|
                next if empty?(row, col)

                x.cell(cell(row, col),
                         row: row,
                         column: col,
                         type: celltype(row, col))
              end
            end
          end
        end
      end
    end
  end.to_xml
end

#to_yaml(prefix = {}, from_row = nil, from_column = nil, to_row = nil, to_column = nil, sheet = default_sheet) ⇒ Object

returns a rectangular area (default: all cells) as yaml-output you can add additional attributes with the prefix parameter like: oo.to_yaml(“sheet” => “1”)


109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
# File 'lib/roo/base.rb', line 109

def to_yaml(prefix = {}, from_row = nil, from_column = nil, to_row = nil, to_column = nil, sheet = default_sheet)
  return '' unless first_row # empty result if there is no first_row in a sheet

  from_row ||= first_row(sheet)
  to_row ||= last_row(sheet)
  from_column ||= first_column(sheet)
  to_column ||= last_column(sheet)

  result = "--- \n"
  from_row.upto(to_row) do |row|
    from_column.upto(to_column) do |col|
      next if empty?(row, col, sheet)

      result << "cell_#{row}_#{col}: \n"
      prefix.each do|k, v|
        result << "  #{k}: #{v} \n"
      end
      result << "  row: #{row} \n"
      result << "  col: #{col} \n"
      result << "  celltype: #{celltype(row, col, sheet)} \n"
      value = cell(row, col, sheet)
      if celltype(row, col, sheet) == :time
        value = integer_to_timestring(value)
      end
      result << "  value: #{value} \n"
    end
  end

  result
end