Class: Roo::GenericSpreadsheet

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

Overview

Base class for all other types of spreadsheets

Direct Known Subclasses

Csv, Excel, Excel2003XML, Excelx, Google, Openoffice

Constant Summary collapse

TEMP_PREFIX = 
"oo_"

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(filename, packed = nil, file_warning = :error, tmpdir = nil) ⇒ GenericSpreadsheet

Returns a new instance of GenericSpreadsheet.



39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
 
# File 'lib/roo/generic_spreadsheet.rb', line 39

def initialize(filename, packed=nil, file_warning=:error, tmpdir=nil)
  @cell = Hash.new{|h,k| h[k] = {}}
  @cell_type = Hash.new{|h,k| h[k] = {}}
  @cells_read = {}

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

  @style = {}
  @style_defaults = Hash.new { |h,k| h[k] = [] }
  @style_definitions = {}

  @default_sheet = self.sheets.first
  @formula = {}
  @header_line = 1
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)



368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
 
# File 'lib/roo/generic_spreadsheet.rb', line 368

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

Instance Attribute Details

#default_sheet ⇒ Object

Returns the value of attribute default_sheet.



12
13
14
 
# File 'lib/roo/generic_spreadsheet.rb', line 12

def default_sheet
  @default_sheet
end

#header_line ⇒ Object

sets the line with attribute names (default: 1)



15
16
17
 
# File 'lib/roo/generic_spreadsheet.rb', line 15

def header_line
  @header_line
end

#headers ⇒ Object (readonly)

Returns the value of attribute headers.



12
13
14
 
# File 'lib/roo/generic_spreadsheet.rb', line 12

def headers
  @headers
end

Instance Method Details

#column(columnnumber, sheet = nil) ⇒ Object

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



265
266
267
268
269
270
271
272
273
274
 
# File 'lib/roo/generic_spreadsheet.rb', line 265

def column(columnnumber,sheet=nil)
  if columnnumber.class == String
    columnnumber = Roo::Excel.letter_to_number(columnnumber)
  end
  sheet ||= @default_sheet
  read_cells(sheet) unless @cells_read[sheet]
  first_row(sheet).upto(last_row(sheet)).map do |row|
    cell(row,columnnumber,sheet)
  end
end

#each(options = {}) ⇒ Object

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



448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
 
# File 'lib/roo/generic_spreadsheet.rb', line 448

def each(options={})
  if options.empty?
    1.upto(last_row) do |line|
      yield row(line)
    end
  else
    if options[:clean]
      options.delete(:clean)
      @cleaned ||= {}
      @cleaned[@default_sheet] || clean_sheet(@default_sheet)
    end

    if options[:header_search]
      @headers = nil
      @header_line = row_with(options[:header_search])
    elsif [:first_row,true].include?(options[:headers])
      @headers = []
      row(first_row).each_with_index {|x,i| @headers << [x,i + 1]}
    else
      set_headers(options)
    end

    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_pagename ⇒ Object

iterate through all worksheets of a document



419
420
421
422
423
 
# File 'lib/roo/generic_spreadsheet.rb', line 419

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

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

true if cell is empty

Returns:

  • (Boolean) 


307
308
309
310
311
312
313
314
 
# File 'lib/roo/generic_spreadsheet.rb', line 307

def empty?(row, col, sheet=nil)
  sheet ||= @default_sheet
  read_cells(sheet) unless @cells_read[sheet] or self.class == Roo::Excel
  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)



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
 
# File 'lib/roo/generic_spreadsheet.rb', line 211

def find(*args) # :nodoc
  options = (args.last.is_a?(Hash) ? args.pop : {})
  result_array = options[:array]
  header_for = Hash[1.upto(last_column).map do |col|
    [col, cell(@header_line,col)]
  end]
  #-- id
  if args[0].class == Fixnum
    rownum = args[0]
    if @header_line
      [Hash[1.upto(self.row().size).map {|j|
        [header_for.fetch(j), cell(rownum,j)]
      }]]
    else
      self.row(rownum).size.times.map {|j|
        cell(rownum,j + 1)
      }
    end
  #-- :all
  elsif args[0] == :all
    rows = first_row.upto(last_row)

    # are all conditions met?
    if (conditions = options[:conditions]) && !conditions.empty?
      column_with = header_for.invert
      rows = rows.select do |i|
        conditions.all? { |key,val| cell(i,column_with[key]) == val }
      end
    end

    rows.map do |i|
      if result_array
        self.row(i)
      else
        Hash[1.upto(self.row(i).size).map do |j|
          [header_for.fetch(j), cell(i,j)]
        end]
      end
    end
  end
end

#first_column(sheet = nil) ⇒ Object

returns the number of the first non-empty column



114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
 
# File 'lib/roo/generic_spreadsheet.rb', line 114

def first_column(sheet=nil)
  sheet ||= @default_sheet
  read_cells(sheet) unless @cells_read[sheet]
  if @first_column[sheet]
    return @first_column[sheet]
  end
  impossible_value = 999_999 # more than a spreadsheet can hold
  result = impossible_value
  @cell[sheet].each_pair {|key,value|
    x = key.last.to_i # _to_string(key).split(',')
    result = [result, x].min if value
  } if @cell[sheet]
  result = nil if result == impossible_value
  @first_column[sheet] = result
  result
end

#first_column_as_letter(sheet = nil) ⇒ Object

first non-empty column as a letter



68
69
70
 
# File 'lib/roo/generic_spreadsheet.rb', line 68

def first_column_as_letter(sheet=nil)
  Roo::GenericSpreadsheet.number_to_letter(first_column(sheet))
end

#first_row(sheet = nil) ⇒ Object

returns the number of the first non-empty row



78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
 
# File 'lib/roo/generic_spreadsheet.rb', line 78

def first_row(sheet=nil)
  sheet ||= @default_sheet
  read_cells(sheet) unless @cells_read[sheet]
  if @first_row[sheet]
    return @first_row[sheet]
  end
  impossible_value = 999_999 # more than a spreadsheet can hold
  result = impossible_value
  @cell[sheet].each_pair {|key,value|
    y = key.first.to_i # _to_string(key).split(',')
    result = [result, y].min if value
  } if @cell[sheet]
  result = nil if result == impossible_value
  @first_row[sheet] = result
  result
end

#info ⇒ Object

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



318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
 
# File 'lib/roo/generic_spreadsheet.rb', line 318

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

#last_column(sheet = nil) ⇒ Object

returns the number of the last non-empty column



132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
 
# File 'lib/roo/generic_spreadsheet.rb', line 132

def last_column(sheet=nil)
  sheet ||= @default_sheet
  read_cells(sheet) unless @cells_read[sheet]
  if @last_column[sheet]
    return @last_column[sheet]
  end
  impossible_value = 0
  result = impossible_value
  @cell[sheet].each_pair {|key,value|
    x = key.last.to_i # _to_string(key).split(',')
    result = [result, x].max if value
  } if @cell[sheet]
  result = nil if result == impossible_value
  @last_column[sheet] = result
  result
end

#last_column_as_letter(sheet = nil) ⇒ Object

last non-empty column as a letter



73
74
75
 
# File 'lib/roo/generic_spreadsheet.rb', line 73

def last_column_as_letter(sheet=nil)
  Roo::GenericSpreadsheet.number_to_letter(last_column(sheet))
end

#last_row(sheet = nil) ⇒ Object

returns the number of the last non-empty row



96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
 
# File 'lib/roo/generic_spreadsheet.rb', line 96

def last_row(sheet=nil)
  sheet ||= @default_sheet
  read_cells(sheet) unless @cells_read[sheet]
  if @last_row[sheet]
    return @last_row[sheet]
  end
  impossible_value = 0
  result = impossible_value
  @cell[sheet].each_pair {|key,value|
    y = key.first.to_i # _to_string(key).split(',')
    result = [result, y].max if value
  } if @cell[sheet]
  result = nil if result == impossible_value
  @last_row[sheet] = result
  result
end

#longest_sheet ⇒ Object

this method lets you find the worksheet with the most data



512
513
514
515
516
 
# File 'lib/roo/generic_spreadsheet.rb', line 512

def longest_sheet
  sheet(@workbook.worksheets.inject {|m,o|
    o.row_count > m.row_count ? o : m
  }.name)
end

#parse(options = {}) ⇒ Object 



481
482
483
484
485
486
487
488
489
 
# File 'lib/roo/generic_spreadsheet.rb', line 481

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

#reload ⇒ Object

reopens and read a spreadsheet document



294
295
296
297
298
299
300
301
302
303
304
 
# File 'lib/roo/generic_spreadsheet.rb', line 294

def reload
  # von Abfrage der Klasse direkt auf .to_s == '..' umgestellt
  ds = @default_sheet
  if self.class.to_s == 'Google'
    initialize(@spreadsheetkey,@user,@password)
  else
    initialize(@filename)
  end
  self.default_sheet = ds
  #@first_row = @last_row = @first_column = @last_column = nil
end

#row(rownumber, sheet = nil) ⇒ Object

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



255
256
257
258
259
260
261
 
# File 'lib/roo/generic_spreadsheet.rb', line 255

def row(rownumber,sheet=nil)
  sheet ||= @default_sheet
  read_cells(sheet) unless @cells_read[sheet]
  first_column(sheet).upto(last_column(sheet)).map do |col|
    cell(rownumber,col,sheet)
  end
end

#row_with(query, return_headers = false) ⇒ Object 



491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
 
# File 'lib/roo/generic_spreadsheet.rb', line 491

def row_with(query,return_headers=false)
  query.map! {|x| Array(x.split('*'))}
  line_no = 0
  each do |row|
    line_no += 1
    # makes sure headers is the first part of wildcard search for priority
    # ex. if UPC and SKU exist for UPC*SKU search, UPC takes the cake
    headers = query.map do |q|
      q.map {|i| row.grep(/#{i}/i)[0]}.compact[0]
    end.compact

    if headers.length == query.length
      @header_line = line_no
      return return_headers ? headers : line_no
    elsif line_no > 100
      raise "Couldn't find header row."
    end
  end
end

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

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



278
279
280
281
282
283
284
285
286
287
288
289
290
291
 
# File 'lib/roo/generic_spreadsheet.rb', line 278

def set(row,col,value,sheet=nil) #:nodoc:
  sheet ||= @default_sheet
  read_cells(sheet) unless @cells_read[sheet]
  row, col = normalize(row,col)
  cell_type = case value
              when Fixnum then :float
              when String, Float then :string
              else
                raise ArgumentError, "Type for #{value} not set"
              end

  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’)



413
414
415
416
 
# File 'lib/roo/generic_spreadsheet.rb', line 413

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

#to_csv(filename = nil, sheet = nil) ⇒ Object

write the current spreadsheet to stdout or into a file



179
180
181
182
183
184
185
186
187
188
189
190
191
192
 
# File 'lib/roo/generic_spreadsheet.rb', line 179

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

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

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



195
196
197
198
199
200
201
202
203
204
205
206
 
# File 'lib/roo/generic_spreadsheet.rb', line 195

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

  sheet ||= @default_sheet
  return Matrix.empty unless first_row

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

#to_xml ⇒ Object

returns an XML representation of all sheets of a spreadsheet file



341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
 
# File 'lib/roo/generic_spreadsheet.rb', line 341

def to_xml
  Nokogiri::XML::Builder.new do |xml|
    xml.spreadsheet {
      self.sheets.each do |sheet|
        self.default_sheet = sheet
        xml.sheet(:name => sheet) { |x|
          if first_row and last_row and first_column and last_column
            # sonst gibt es Fehler bei leeren Blaettern
            first_row.upto(last_row) do |row|
              first_column.upto(last_column) do |col|
                unless empty?(row,col)
                  x.cell(cell(row,col),
                    :row =>row,
                    :column => col,
                    :type => celltype(row,col))
                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 = nil) ⇒ 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”)



152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
 
# File 'lib/roo/generic_spreadsheet.rb', line 152

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

  (from_row||first_row(sheet)).upto(to_row||last_row(sheet)) do |row|
    (from_column||first_column(sheet)).upto(to_column||last_column(sheet)) do |col|
      unless empty?(row,col,sheet)
        result << "cell_#{row}_#{col}: \n"
        prefix.each {|k,v|
          result << "  #{k}: #{v} \n"
        }
        result << "  row: #{row} \n"
        result << "  col: #{col} \n"
        result << "  celltype: #{self.celltype(row,col,sheet)} \n"
        if self.celltype(row,col,sheet) == :time
          result << "  value: #{Roo::GenericSpreadsheet.integer_to_timestring( self.cell(row,col,sheet))} \n"
        else
          result << "  value: #{self.cell(row,col,sheet)} \n"
        end
      end
    end
  end
  result
end