jagthedrummer-roo 1.3.12

Sign up to get free protection for your applications and to get access to all the features.
Files changed (76) hide show
  1. data/History.txt +225 -0
  2. data/README.markdown +55 -0
  3. data/examples/roo_soap_client.rb +53 -0
  4. data/examples/roo_soap_server.rb +29 -0
  5. data/examples/write_me.rb +33 -0
  6. data/lib/roo.rb +29 -0
  7. data/lib/roo/excel.rb +469 -0
  8. data/lib/roo/excelx.rb +604 -0
  9. data/lib/roo/generic_spreadsheet.rb +626 -0
  10. data/lib/roo/google.rb +381 -0
  11. data/lib/roo/openoffice.rb +454 -0
  12. data/lib/roo/roo_rails_helper.rb +82 -0
  13. data/lib/roo/version.rb +9 -0
  14. data/test/1900_base.xls +0 -0
  15. data/test/1904_base.xls +0 -0
  16. data/test/Bibelbund.csv +3741 -0
  17. data/test/Bibelbund.ods +0 -0
  18. data/test/Bibelbund.xls +0 -0
  19. data/test/Bibelbund.xlsx +0 -0
  20. data/test/Bibelbund1.ods +0 -0
  21. data/test/bad_excel_date.xls +0 -0
  22. data/test/bbu.ods +0 -0
  23. data/test/bbu.xls +0 -0
  24. data/test/bbu.xlsx +0 -0
  25. data/test/bode-v1.ods.zip +0 -0
  26. data/test/bode-v1.xls.zip +0 -0
  27. data/test/boolean.ods +0 -0
  28. data/test/boolean.xls +0 -0
  29. data/test/boolean.xlsx +0 -0
  30. data/test/borders.ods +0 -0
  31. data/test/borders.xls +0 -0
  32. data/test/borders.xlsx +0 -0
  33. data/test/bug-row-column-fixnum-float.xls +0 -0
  34. data/test/datetime.ods +0 -0
  35. data/test/datetime.xls +0 -0
  36. data/test/datetime.xlsx +0 -0
  37. data/test/datetime_floatconv.xls +0 -0
  38. data/test/emptysheets.ods +0 -0
  39. data/test/emptysheets.xls +0 -0
  40. data/test/false_encoding.xls +0 -0
  41. data/test/formula.ods +0 -0
  42. data/test/formula.xls +0 -0
  43. data/test/formula.xlsx +0 -0
  44. data/test/formula_parse_error.xls +0 -0
  45. data/test/html-escape.ods +0 -0
  46. data/test/no_spreadsheet_file.txt +1 -0
  47. data/test/numbers1.csv +18 -0
  48. data/test/numbers1.ods +0 -0
  49. data/test/numbers1.xls +0 -0
  50. data/test/numbers1.xlsx +0 -0
  51. data/test/only_one_sheet.ods +0 -0
  52. data/test/only_one_sheet.xls +0 -0
  53. data/test/only_one_sheet.xlsx +0 -0
  54. data/test/paragraph.ods +0 -0
  55. data/test/paragraph.xls +0 -0
  56. data/test/paragraph.xlsx +0 -0
  57. data/test/ric.ods +0 -0
  58. data/test/simple_spreadsheet.ods +0 -0
  59. data/test/simple_spreadsheet.xls +0 -0
  60. data/test/simple_spreadsheet.xlsx +0 -0
  61. data/test/simple_spreadsheet_from_italo.ods +0 -0
  62. data/test/simple_spreadsheet_from_italo.xls +0 -0
  63. data/test/skipped_tests.rb +789 -0
  64. data/test/style.ods +0 -0
  65. data/test/style.xls +0 -0
  66. data/test/style.xlsx +0 -0
  67. data/test/test_helper.rb +19 -0
  68. data/test/test_roo.rb +1822 -0
  69. data/test/time-test.csv +2 -0
  70. data/test/time-test.ods +0 -0
  71. data/test/time-test.xls +0 -0
  72. data/test/time-test.xlsx +0 -0
  73. data/test/whitespace.ods +0 -0
  74. data/test/whitespace.xls +0 -0
  75. data/test/whitespace.xlsx +0 -0
  76. metadata +182 -0
@@ -0,0 +1,381 @@
1
+ require 'gdata/spreadsheet'
2
+ require 'xml'
3
+
4
+ class GoogleHTTPError < RuntimeError; end
5
+ class GoogleReadError < RuntimeError; end
6
+ class GoogleWriteError < RuntimeError; end
7
+
8
+ # overwrite some methods from the gdata-gem:
9
+ module GData
10
+ class Spreadsheet < GData::Base
11
+
12
+ def visibility
13
+ @headers ? "private" : "public"
14
+ end
15
+
16
+ def projection
17
+ @headers ? "full" : "values"
18
+ end
19
+
20
+ #-- modified
21
+ def evaluate_cell(cell, sheet_no=1)
22
+ raise ArgumentError, "invalid cell: #{cell}" unless cell
23
+ raise ArgumentError, "invalid sheet_no: #{sheet_no}" unless sheet_no >0 and sheet_no.class == Fixnum
24
+ path = "/feeds/cells/#{@spreadsheet_id}/#{sheet_no}/#{visibility}/#{projection}/#{cell}"
25
+ doc = Hpricot(request(path))
26
+ result = (doc/"content").inner_html
27
+ end
28
+
29
+ #-- new
30
+ def sheetlist
31
+ path = "/feeds/worksheets/#{@spreadsheet_id}/#{visibility}/#{projection}"
32
+ doc = Hpricot(request(path))
33
+ result = []
34
+ (doc/"content").each { |elem|
35
+ result << elem.inner_html
36
+ }
37
+ if result.size == 0
38
+ if (doc/"h2").inner_html =~ /Error/
39
+ raise GoogleHTTPError, "#{(doc/'h2').inner_html}: #{(doc/'title').inner_html} [key '#{@spreadsheet_id}']"
40
+ else
41
+ raise GoogleReadError, "#{doc} [key '#{@spreadsheet_id}']"
42
+ end
43
+ end
44
+ result
45
+ end
46
+
47
+ #-- new
48
+ #@@ added sheet_no to definition
49
+ def save_entry_roo(entry, sheet_no)
50
+ raise GoogleWriteError, "unable to write to public spreadsheets" if visibility == 'public'
51
+ path = "/feeds/cells/#{@spreadsheet_id}/#{sheet_no}/#{visibility}/#{projection}"
52
+ post(path, entry)
53
+ end
54
+
55
+ #-- new
56
+ def entry_roo(formula, row=1, col=1)
57
+ <<-XML
58
+ <entry xmlns='http://www.w3.org/2005/Atom' xmlns:gs='http://schemas.google.com/spreadsheets/2006'>
59
+ <gs:cell row='#{row}' col='#{col}' inputValue='#{formula}' />
60
+ </entry>
61
+ XML
62
+ end
63
+
64
+ #-- new
65
+ #@@ added sheet_no to definition
66
+ def add_to_cell_roo(row,col,value, sheet_no=1)
67
+ save_entry_roo(entry_roo(value,row,col), sheet_no)
68
+ end
69
+
70
+ #-- new
71
+ def get_one_sheet
72
+ path = "/feeds/cells/#{@spreadsheet_id}/1/#{visibility}/#{projection}"
73
+ doc = Hpricot(request(path))
74
+ end
75
+
76
+ #new
77
+ def oben_unten_links_rechts(sheet_no)
78
+ path = "/feeds/cells/#{@spreadsheet_id}/#{sheet_no}/#{visibility}/#{projection}"
79
+ doc = Hpricot(request(path))
80
+ rows = []
81
+ cols = []
82
+ (doc/"gs:cell").each {|item|
83
+ rows.push item['row'].to_i
84
+ cols.push item['col'].to_i
85
+ }
86
+ return rows.min, rows.max, cols.min, cols.max
87
+ end
88
+
89
+ def fulldoc(sheet_no)
90
+ path = "/feeds/cells/#{@spreadsheet_id}/#{sheet_no}/#{visibility}/#{projection}"
91
+ doc = Hpricot(request(path))
92
+ return doc
93
+ end
94
+
95
+ end # class
96
+ end # module
97
+
98
+ module Roo
99
+ class Google < GenericSpreadsheet
100
+ attr_accessor :date_format, :datetime_format
101
+
102
+ # Creates a new Google spreadsheet object.
103
+ def initialize(spreadsheetkey,user=nil,password=nil)
104
+ @filename = spreadsheetkey
105
+ @spreadsheetkey = spreadsheetkey
106
+ @user = user
107
+ @password = password
108
+ unless user
109
+ user = ENV['GOOGLE_MAIL']
110
+ end
111
+ unless password
112
+ password = ENV['GOOGLE_PASSWORD']
113
+ end
114
+ @cell = Hash.new {|h,k| h[k]=Hash.new}
115
+ @cell_type = Hash.new {|h,k| h[k]=Hash.new}
116
+ @formula = Hash.new
117
+ @first_row = Hash.new
118
+ @last_row = Hash.new
119
+ @first_column = Hash.new
120
+ @last_column = Hash.new
121
+ @cells_read = Hash.new
122
+ @header_line = 1
123
+ @date_format = '%d/%m/%Y'
124
+ @datetime_format = '%d/%m/%Y %H:%M:%S'
125
+ @time_format = '%H:%M:%S'
126
+ @gs = GData::Spreadsheet.new(spreadsheetkey)
127
+ @gs.authenticate(user, password) unless user.empty? || password.empty?
128
+ @sheetlist = @gs.sheetlist
129
+ @default_sheet = self.sheets.first
130
+ end
131
+
132
+ # returns an array of sheet names in the spreadsheet
133
+ def sheets
134
+ @sheetlist
135
+ end
136
+
137
+ def date?(string)
138
+ begin
139
+ Date.strptime(string, @date_format)
140
+ true
141
+ rescue
142
+ false
143
+ end
144
+ end
145
+
146
+ # is String a time with format HH:MM:SS?
147
+ def time?(string)
148
+ begin
149
+ DateTime.strptime(string, @time_format)
150
+ true
151
+ rescue
152
+ false
153
+ end
154
+ end
155
+
156
+ def datetime?(string)
157
+ begin
158
+ DateTime.strptime(string, @datetime_format)
159
+ true
160
+ rescue
161
+ false
162
+ end
163
+ end
164
+
165
+ def numeric?(string)
166
+ string =~ /^[0-9]+[\.]*[0-9]*$/
167
+ end
168
+
169
+ def timestring_to_seconds(value)
170
+ hms = value.split(':')
171
+ hms[0].to_i*3600 + hms[1].to_i*60 + hms[2].to_i
172
+ end
173
+
174
+ # Returns the content of a spreadsheet-cell.
175
+ # (1,1) is the upper left corner.
176
+ # (1,1), (1,'A'), ('A',1), ('a',1) all refers to the
177
+ # cell at the first line and first row.
178
+ def cell(row, col, sheet=nil)
179
+ sheet = @default_sheet unless sheet
180
+ check_default_sheet #TODO: 2007-12-16
181
+ read_cells(sheet) unless @cells_read[sheet]
182
+ row,col = normalize(row,col)
183
+ value = @cell[sheet]["#{row},#{col}"]
184
+ if celltype(row,col,sheet) == :date
185
+ begin
186
+ return Date.strptime(value, @date_format)
187
+ rescue ArgumentError
188
+ raise "Invalid Date #{sheet}[#{row},#{col}] #{value} using format '{@date_format}'"
189
+ end
190
+ elsif celltype(row,col,sheet) == :datetime
191
+ begin
192
+ return DateTime.strptime(value, @datetime_format)
193
+ rescue ArgumentError
194
+ raise "Invalid DateTime #{sheet}[#{row},#{col}] #{value} using format '{@datetime_format}'"
195
+ end
196
+ end
197
+ return value
198
+ end
199
+
200
+ # returns the type of a cell:
201
+ # * :float
202
+ # * :string
203
+ # * :date
204
+ # * :percentage
205
+ # * :formula
206
+ # * :time
207
+ # * :datetime
208
+ def celltype(row, col, sheet=nil)
209
+ sheet = @default_sheet unless sheet
210
+ read_cells(sheet) unless @cells_read[sheet]
211
+ row,col = normalize(row,col)
212
+ if @formula.size > 0 && @formula[sheet]["#{row},#{col}"]
213
+ return :formula
214
+ else
215
+ @cell_type[sheet]["#{row},#{col}"]
216
+ end
217
+ end
218
+
219
+ # Returns the formula at (row,col).
220
+ # Returns nil if there is no formula.
221
+ # The method #formula? checks if there is a formula.
222
+ def formula(row,col,sheet=nil)
223
+ sheet = @default_sheet unless sheet
224
+ read_cells(sheet) unless @cells_read[sheet]
225
+ row,col = normalize(row,col)
226
+ if @formula[sheet]["#{row},#{col}"] == nil
227
+ return nil
228
+ else
229
+ return @formula[sheet]["#{row},#{col}"]
230
+ end
231
+ end
232
+
233
+ # true, if there is a formula
234
+ def formula?(row,col,sheet=nil)
235
+ sheet = @default_sheet unless sheet
236
+ read_cells(sheet) unless @cells_read[sheet]
237
+ row,col = normalize(row,col)
238
+ formula(row,col) != nil
239
+ end
240
+
241
+ # returns each formula in the selected sheet as an array of elements
242
+ # [row, col, formula]
243
+ def formulas(sheet=nil)
244
+ theformulas = Array.new
245
+ sheet = @default_sheet unless sheet
246
+ read_cells(sheet) unless @cells_read[sheet]
247
+ first_row(sheet).upto(last_row(sheet)) {|row|
248
+ first_column(sheet).upto(last_column(sheet)) {|col|
249
+ if formula?(row,col,sheet)
250
+ f = [row, col, formula(row,col,sheet)]
251
+ theformulas << f
252
+ end
253
+ }
254
+ }
255
+ theformulas
256
+ end
257
+
258
+ # true, if the cell is empty
259
+ def empty?(row, col, sheet=nil)
260
+ value = cell(row, col, sheet)
261
+ return true unless value
262
+ return false if value.class == Date # a date is never empty
263
+ return false if value.class == Float
264
+ return false if celltype(row,col,sheet) == :time
265
+ value.empty?
266
+ end
267
+
268
+ # sets the cell to the content of 'value'
269
+ # a formula can be set in the form of '=SUM(...)'
270
+ def set_value(row,col,value,sheet=nil)
271
+ sheet = @default_sheet unless sheet
272
+ raise RangeError, "sheet not set" unless sheet
273
+ #@@ Set and pass sheet_no
274
+ begin
275
+ sheet_no = sheets.index(sheet)+1
276
+ rescue
277
+ raise RangeError, "invalid sheet '"+sheet.to_s+"'"
278
+ end
279
+ row,col = normalize(row,col)
280
+ @gs.add_to_cell_roo(row,col,value,sheet_no)
281
+ # re-read the portion of the document that has changed
282
+ if @cells_read[sheet]
283
+ key = "#{row},#{col}"
284
+ (value, value_type) = determine_datatype(value.to_s)
285
+ @cell[sheet][key] = value
286
+ @cell_type[sheet][key] = value_type
287
+ end
288
+ end
289
+
290
+ # returns the first non-empty row in a sheet
291
+ def first_row(sheet=nil)
292
+ sheet = @default_sheet unless sheet
293
+ unless @first_row[sheet]
294
+ sheet_no = sheets.index(sheet) + 1
295
+ @first_row[sheet], @last_row[sheet], @first_column[sheet], @last_column[sheet] = @gs.oben_unten_links_rechts(sheet_no)
296
+ end
297
+ return @first_row[sheet]
298
+ end
299
+
300
+ # returns the last non-empty row in a sheet
301
+ def last_row(sheet=nil)
302
+ sheet = @default_sheet unless sheet
303
+ unless @last_row[sheet]
304
+ sheet_no = sheets.index(sheet) + 1
305
+ @first_row[sheet], @last_row[sheet], @first_column[sheet], @last_column[sheet] = @gs.oben_unten_links_rechts(sheet_no)
306
+ end
307
+ return @last_row[sheet]
308
+ end
309
+
310
+ # returns the first non-empty column in a sheet
311
+ def first_column(sheet=nil)
312
+ sheet = @default_sheet unless sheet
313
+ unless @first_column[sheet]
314
+ sheet_no = sheets.index(sheet) + 1
315
+ @first_row[sheet], @last_row[sheet], @first_column[sheet], @last_column[sheet] = @gs.oben_unten_links_rechts(sheet_no)
316
+ end
317
+ return @first_column[sheet]
318
+ end
319
+
320
+ # returns the last non-empty column in a sheet
321
+ def last_column(sheet=nil)
322
+ sheet = @default_sheet unless sheet
323
+ unless @last_column[sheet]
324
+ sheet_no = sheets.index(sheet) + 1
325
+ @first_row[sheet], @last_row[sheet], @first_column[sheet], @last_column[sheet] = @gs.oben_unten_links_rechts(sheet_no)
326
+ end
327
+ return @last_column[sheet]
328
+ end
329
+
330
+ private
331
+
332
+ # read all cells in a sheet.
333
+ def read_cells(sheet=nil)
334
+ sheet = @default_sheet unless sheet
335
+ raise RangeError, "illegal sheet <#{sheet}>" unless sheets.index(sheet)
336
+ sheet_no = sheets.index(sheet)+1
337
+ xml = @gs.fulldoc(sheet_no).to_s
338
+ doc = XML::Parser.string(xml).parse
339
+ doc.find("//*[local-name()='cell']").each do |item|
340
+ row = item['row']
341
+ col = item['col']
342
+ key = "#{row},#{col}"
343
+ string_value = item['inputvalue'] || item['inputValue']
344
+ numeric_value = item['numericvalue'] || item['numericValue']
345
+ (value, value_type) = determine_datatype(string_value, numeric_value)
346
+ @cell[sheet][key] = value unless value == "" or value == nil
347
+ @cell_type[sheet][key] = value_type
348
+ @formula[sheet] = {} unless @formula[sheet]
349
+ @formula[sheet][key] = string_value if value_type == :formula
350
+ end
351
+ @cells_read[sheet] = true
352
+ end
353
+
354
+ def determine_datatype(val, numval=nil)
355
+ if val.nil? || val[0,1] == '='
356
+ ty = :formula
357
+ if numeric?(numval)
358
+ val = numval.to_f
359
+ else
360
+ val = numval
361
+ end
362
+ else
363
+ if datetime?(val)
364
+ ty = :datetime
365
+ elsif date?(val)
366
+ ty = :date
367
+ elsif numeric?(val)
368
+ ty = :float
369
+ val = val.to_f
370
+ elsif time?(val)
371
+ ty = :time
372
+ val = timestring_to_seconds(val)
373
+ else
374
+ ty = :string
375
+ end
376
+ end
377
+ return val, ty
378
+ end
379
+
380
+ end # class Google
381
+ end # module Roo
@@ -0,0 +1,454 @@
1
+ require 'xml'
2
+ require 'fileutils'
3
+ require 'zip/zipfilesystem'
4
+ require 'date'
5
+ require 'base64'
6
+ require 'cgi'
7
+
8
+ module Roo
9
+ class Openoffice < GenericSpreadsheet
10
+
11
+ @@nr = 0
12
+
13
+ # initialization and opening of a spreadsheet file
14
+ # values for packed: :zip
15
+ def initialize(filename, packed=nil, file_warning=:error) #, create = false)
16
+ @file_warning = file_warning
17
+ super()
18
+ @tmpdir = "oo_"+$$.to_s
19
+ @tmpdir = File.join(ENV['ROO_TMP'], @tmpdir) if ENV['ROO_TMP']
20
+ unless File.exists?(@tmpdir)
21
+ FileUtils::mkdir(@tmpdir)
22
+ end
23
+ filename = open_from_uri(filename) if filename[0,7] == "http://"
24
+ filename = unzip(filename) if packed and packed == :zip
25
+ begin
26
+ file_type_check(filename,'.ods','an openoffice')
27
+ #if create and ! File.exists?(filename)
28
+ # self.create_openoffice(filename)
29
+ #end
30
+ @cells_read = Hash.new
31
+ #TODO: @cells_read[:default] = false
32
+ @filename = filename
33
+ unless File.file?(@filename)
34
+ raise IOError, "file #{@filename} does not exist"
35
+ end
36
+ @@nr += 1
37
+ @file_nr = @@nr
38
+ extract_content
39
+ file = File.new(File.join(@tmpdir, @file_nr.to_s+"_roo_content.xml"))
40
+ @doc = XML::Parser.io(file).parse
41
+ file.close
42
+ ensure
43
+ #if ENV["roo_local"] != "thomas-p"
44
+ FileUtils::rm_r(@tmpdir)
45
+ #end
46
+ end
47
+ @default_sheet = self.sheets.first
48
+ @cell = Hash.new
49
+ @cell_type = Hash.new
50
+ @formula = Hash.new
51
+ @first_row = Hash.new
52
+ @last_row = Hash.new
53
+ @first_column = Hash.new
54
+ @last_column = Hash.new
55
+ @style = Hash.new
56
+ @style_defaults = Hash.new { |h,k| h[k] = [] }
57
+ @style_definitions = Hash.new
58
+ @header_line = 1
59
+ end
60
+
61
+ # creates a new empty openoffice-spreadsheet file
62
+ def create_openoffice(filename) #:nodoc:
63
+ #TODO: a better way for creating the file contents
64
+ # now you have to call mkbase64...rb to create an include file with all
65
+ # the empty files in an openoffice zip-file
66
+ load 'base64include.rb'
67
+ # puts @@empty_spreadsheet
68
+ f = File.open(filename,'wb')
69
+ f.print(Base64.decode64(@@empty_spreadsheet))
70
+ f.close
71
+ end
72
+
73
+ # Returns the content of a spreadsheet-cell.
74
+ # (1,1) is the upper left corner.
75
+ # (1,1), (1,'A'), ('A',1), ('a',1) all refers to the
76
+ # cell at the first line and first row.
77
+ def cell(row, col, sheet=nil)
78
+ sheet = @default_sheet unless sheet
79
+ read_cells(sheet) unless @cells_read[sheet]
80
+ row,col = normalize(row,col)
81
+ if celltype(row,col,sheet) == :date
82
+ yyyy,mm,dd = @cell[sheet][[row,col]].split('-')
83
+ return Date.new(yyyy.to_i,mm.to_i,dd.to_i)
84
+ end
85
+ @cell[sheet][[row,col]]
86
+ end
87
+
88
+ # Returns the formula at (row,col).
89
+ # Returns nil if there is no formula.
90
+ # The method #formula? checks if there is a formula.
91
+ def formula(row,col,sheet=nil)
92
+ sheet = @default_sheet unless sheet
93
+ read_cells(sheet) unless @cells_read[sheet]
94
+ row,col = normalize(row,col)
95
+ if @formula[sheet][[row,col]] == nil
96
+ return nil
97
+ else
98
+ return @formula[sheet][[row,col]]["oooc:".length..-1]
99
+ end
100
+ end
101
+
102
+ # true, if there is a formula
103
+ def formula?(row,col,sheet=nil)
104
+ sheet = @default_sheet unless sheet
105
+ read_cells(sheet) unless @cells_read[sheet]
106
+ row,col = normalize(row,col)
107
+ formula(row,col) != nil
108
+ end
109
+
110
+ class Font
111
+ attr_accessor :bold, :italic, :underline
112
+
113
+ def bold?
114
+ @bold == 'bold'
115
+ end
116
+
117
+ def italic?
118
+ @italic == 'italic'
119
+ end
120
+
121
+ def underline?
122
+ @underline != nil
123
+ end
124
+ end
125
+
126
+ # Given a cell, return the cell's style
127
+ def font(row, col, sheet=nil)
128
+ sheet = @default_sheet unless sheet
129
+ read_cells(sheet) unless @cells_read[sheet]
130
+ row,col = normalize(row,col)
131
+ style_name = @style[sheet][[row,col]] || @style_defaults[sheet][col - 1] || 'Default'
132
+ @style_definitions[style_name]
133
+ end
134
+
135
+ # set a cell to a certain value
136
+ # (this will not be saved back to the spreadsheet file!)
137
+ def set(row,col,value,sheet=nil) #:nodoc:
138
+ sheet = @default_sheet unless sheet
139
+ read_cells(sheet) unless @cells_read[sheet]
140
+ row,col = normalize(row,col)
141
+ set_value(row,col,value,sheet)
142
+ if value.class == Fixnum
143
+ set_type(row,col,:float,sheet)
144
+ elsif value.class == String
145
+ set_type(row,col,:string,sheet)
146
+ elsif value.class == Float
147
+ set_type(row,col,:string,sheet)
148
+ else
149
+ raise ArgumentError, "Type for "+value.to_s+" not set"
150
+ end
151
+ end
152
+
153
+ # returns the type of a cell:
154
+ # * :float
155
+ # * :string
156
+ # * :date
157
+ # * :percentage
158
+ # * :formula
159
+ # * :time
160
+ # * :datetime
161
+ def celltype(row,col,sheet=nil)
162
+ sheet = @default_sheet unless sheet
163
+ read_cells(sheet) unless @cells_read[sheet]
164
+ row,col = normalize(row,col)
165
+ if @formula[sheet][[row,col]]
166
+ return :formula
167
+ else
168
+ @cell_type[sheet][[row,col]]
169
+ end
170
+ end
171
+
172
+ def sheets
173
+ return_sheets = []
174
+ @doc.find("//*[local-name()='table']").each do |sheet|
175
+ return_sheets << sheet.attributes['name']
176
+ end
177
+ return_sheets
178
+ end
179
+
180
+ # version of the openoffice document
181
+ # at 2007 this is always "1.0"
182
+ def officeversion
183
+ oo_version
184
+ @officeversion
185
+ end
186
+
187
+ # shows the internal representation of all cells
188
+ # mainly for debugging purposes
189
+ def to_s(sheet=nil)
190
+ sheet = @default_sheet unless sheet
191
+ read_cells(sheet) unless @cells_read[sheet]
192
+ @cell[sheet].inspect
193
+ end
194
+
195
+ # save spreadsheet
196
+ def save #:nodoc:
197
+ 42
198
+ end
199
+
200
+ # returns each formula in the selected sheet as an array of elements
201
+ # [row, col, formula]
202
+ def formulas(sheet=nil)
203
+ theformulas = Array.new
204
+ sheet = @default_sheet unless sheet
205
+ read_cells(sheet) unless @cells_read[sheet]
206
+ first_row(sheet).upto(last_row(sheet)) {|row|
207
+ first_column(sheet).upto(last_column(sheet)) {|col|
208
+ if formula?(row,col,sheet)
209
+ f = [row, col, formula(row,col,sheet)]
210
+ theformulas << f
211
+ end
212
+ }
213
+ }
214
+ theformulas
215
+ end
216
+
217
+ private
218
+
219
+ # read the version of the OO-Version
220
+ def oo_version
221
+ @doc.find("//*[local-name()='document-content']").each do |office|
222
+ @officeversion = office.attributes['version']
223
+ end
224
+ end
225
+
226
+ # helper function to set the internal representation of cells
227
+ def set_cell_values(sheet,x,y,i,v,vt,formula,table_cell,str_v,style_name)
228
+ key = [y,x+i]
229
+ @cell_type[sheet] = {} unless @cell_type[sheet]
230
+ @cell_type[sheet][key] = Openoffice.oo_type_2_roo_type(vt)
231
+ @formula[sheet] = {} unless @formula[sheet]
232
+ @formula[sheet][key] = formula if formula
233
+ @cell[sheet] = {} unless @cell[sheet]
234
+ @style[sheet] = {} unless @style[sheet]
235
+ @style[sheet][key] = style_name
236
+ case @cell_type[sheet][key]
237
+ when :float
238
+ @cell[sheet][key] = v.to_f
239
+ when :string
240
+ @cell[sheet][key] = str_v
241
+ when :date
242
+ if table_cell.attributes['date-value'].size != "XXXX-XX-XX".size
243
+ #-- dann ist noch eine Uhrzeit vorhanden
244
+ #-- "1961-11-21T12:17:18"
245
+ @cell[sheet][key] = DateTime.parse(table_cell.attributes['date-value'])
246
+ @cell_type[sheet][key] = :datetime
247
+ else
248
+ @cell[sheet][key] = table_cell.attributes['date-value']
249
+ end
250
+ when :percentage
251
+ @cell[sheet][key] = v.to_f
252
+ when :time
253
+ hms = v.split(':')
254
+ @cell[sheet][key] = hms[0].to_i*3600 + hms[1].to_i*60 + hms[2].to_i
255
+ else
256
+ @cell[sheet][key] = v
257
+ end
258
+ end
259
+
260
+ # read all cells in the selected sheet
261
+ #--
262
+ # the following construct means '4 blanks'
263
+ # some content <text:s text:c="3"/>
264
+ #++
265
+ def read_cells(sheet=nil)
266
+ sheet = @default_sheet unless sheet
267
+ sheet_found = false
268
+ raise ArgumentError, "Error: sheet '#{sheet||'nil'}' not valid" if @default_sheet == nil and sheet==nil
269
+ raise RangeError unless self.sheets.include? sheet
270
+
271
+ @doc.find("//*[local-name()='table']").each do |ws|
272
+ if sheet == ws.attributes['name']
273
+ sheet_found = true
274
+ col = 1
275
+ row = 1
276
+ ws.each_element do |table_element|
277
+ case table_element.name
278
+ when 'table-column'
279
+ @style_defaults[sheet] << table_element.attributes['default-cell-style-name']
280
+ when 'table-row'
281
+ if table_element.attributes['number-rows-repeated']
282
+ skip_row = table_element.attributes['number-rows-repeated'].to_i
283
+ row = row + skip_row - 1
284
+ end
285
+ table_element.each_element do |cell|
286
+ skip_col = cell.attributes['number-columns-repeated']
287
+ formula = cell.attributes['formula']
288
+ vt = cell.attributes['value-type']
289
+ v = cell.attributes['value']
290
+ style_name = cell.attributes['style-name']
291
+ if vt == 'string'
292
+ str_v = ''
293
+ # insert \n if there is more than one paragraph
294
+ para_count = 0
295
+ cell.each_element do |str|
296
+ if str.name == 'p'
297
+ v = str.content
298
+ str_v += "\n" if para_count > 0
299
+ para_count += 1
300
+ if str.children.size > 1
301
+ str_v += children_to_string(str.children)
302
+ else
303
+ str.children.each do |child|
304
+ str_v += child.content #.text
305
+ end
306
+ end
307
+ str_v.gsub!(/&apos;/,"'") # special case not supported by unescapeHTML
308
+ str_v = CGI.unescapeHTML(str_v)
309
+ end # == 'p'
310
+ end
311
+ elsif vt == 'time'
312
+ cell.each_element do |str|
313
+ if str.name == 'p'
314
+ v = str.content
315
+ end
316
+ end
317
+ elsif vt == '' or vt == nil
318
+ #
319
+ elsif vt == 'date'
320
+ #
321
+ elsif vt == 'percentage'
322
+ #
323
+ elsif vt == 'float'
324
+ #
325
+ elsif vt == 'boolean'
326
+ v = cell.attributes['boolean-value']
327
+ #
328
+ else
329
+ # raise "unknown type #{vt}"
330
+ end
331
+ if skip_col
332
+ if v != nil or cell.attributes['date-value']
333
+ 0.upto(skip_col.to_i-1) do |i|
334
+ set_cell_values(sheet,col,row,i,v,vt,formula,cell,str_v,style_name)
335
+ end
336
+ end
337
+ col += (skip_col.to_i - 1)
338
+ end # if skip
339
+ set_cell_values(sheet,col,row,0,v,vt,formula,cell,str_v,style_name)
340
+ col += 1
341
+ end
342
+ row += 1
343
+ col = 1
344
+ end
345
+ end
346
+ end
347
+ end
348
+
349
+ @doc.find("//*[local-name()='automatic-styles']").each do |style|
350
+ read_styles(style)
351
+ end
352
+ if !sheet_found
353
+ raise RangeError
354
+ end
355
+ @cells_read[sheet] = true
356
+ end
357
+
358
+ def read_styles(style_elements)
359
+ @style_definitions['Default'] = Openoffice::Font.new
360
+ style_elements.each do |style|
361
+ next unless style.name == 'style'
362
+ style_name = style.attributes['name']
363
+ style.each do |properties|
364
+ font = Openoffice::Font.new
365
+ font.bold = properties.attributes['font-weight']
366
+ font.italic = properties.attributes['font-style']
367
+ font.underline = properties.attributes['text-underline-style']
368
+ @style_definitions[style_name] = font
369
+ end
370
+ end
371
+ end
372
+
373
+ # Checks if the default_sheet exists. If not an RangeError exception is
374
+ # raised
375
+ def check_default_sheet
376
+ sheet_found = false
377
+ raise ArgumentError, "Error: default_sheet not set" if @default_sheet == nil
378
+ sheet_found = true if sheets.include?(@default_sheet)
379
+ if ! sheet_found
380
+ raise RangeError, "sheet '#{@default_sheet}' not found"
381
+ end
382
+ end
383
+
384
+ def process_zipfile(zip, path='')
385
+ if zip.file.file? path
386
+ if path == "content.xml"
387
+ open(File.join(@tmpdir, @file_nr.to_s+'_roo_content.xml'),'wb') {|f|
388
+ f << zip.read(path)
389
+ }
390
+ end
391
+ else
392
+ unless path.empty?
393
+ path += '/'
394
+ end
395
+ zip.dir.foreach(path) do |filename|
396
+ process_zipfile(zip, path+filename)
397
+ end
398
+ end
399
+ end
400
+
401
+ def extract_content
402
+ Zip::ZipFile.open(@filename) do |zip|
403
+ process_zipfile(zip)
404
+ end
405
+ end
406
+
407
+ def set_value(row,col,value,sheet=nil)
408
+ sheet = @default_value unless sheet
409
+ @cell[sheet][[row,col]] = value
410
+ end
411
+
412
+ def set_type(row,col,type,sheet=nil)
413
+ sheet = @default_value unless sheet
414
+ @cell_type[sheet][[row,col]] = type
415
+ end
416
+
417
+ A_ROO_TYPE = {
418
+ "float" => :float,
419
+ "string" => :string,
420
+ "date" => :date,
421
+ "percentage" => :percentage,
422
+ "time" => :time,
423
+ }
424
+
425
+ def Openoffice.oo_type_2_roo_type(ootype)
426
+ return A_ROO_TYPE[ootype]
427
+ end
428
+
429
+ # helper method to convert compressed spaces and other elements within
430
+ # an text into a string
431
+ def children_to_string(children)
432
+ result = ''
433
+ children.each {|child|
434
+ if child.text?
435
+ result = result + child.content
436
+ else
437
+ if child.name == 's'
438
+ compressed_spaces = child.attributes['c'].to_i
439
+ # no explicit number means a count of 1:
440
+ if compressed_spaces == 0
441
+ compressed_spaces = 1
442
+ end
443
+ result = result + " "*compressed_spaces
444
+ else
445
+ result = result + child.content
446
+ end
447
+ end
448
+ }
449
+ result
450
+ end
451
+
452
+ end # class
453
+
454
+ end #module Roo