roo-immersion 1.0.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/History.txt +225 -0
- data/README.markdown +60 -0
- data/examples/roo_soap_client.rb +53 -0
- data/examples/roo_soap_server.rb +29 -0
- data/examples/write_me.rb +33 -0
- data/lib/roo.rb +32 -0
- data/lib/roo/excel.rb +468 -0
- data/lib/roo/excel2003xml.rb +394 -0
- data/lib/roo/excelx.rb +601 -0
- data/lib/roo/generic_spreadsheet.rb +628 -0
- data/lib/roo/google.rb +379 -0
- data/lib/roo/openoffice.rb +451 -0
- data/lib/roo/roo_rails_helper.rb +82 -0
- data/lib/roo/version.rb +9 -0
- data/test/1900_base.xls +0 -0
- data/test/1904_base.xls +0 -0
- data/test/Bibelbund.csv +3741 -0
- data/test/Bibelbund.ods +0 -0
- data/test/Bibelbund.xls +0 -0
- data/test/Bibelbund.xlsx +0 -0
- data/test/Bibelbund.xml +62518 -0
- data/test/Bibelbund1.ods +0 -0
- data/test/bad_excel_date.xls +0 -0
- data/test/bbu.ods +0 -0
- data/test/bbu.xls +0 -0
- data/test/bbu.xlsx +0 -0
- data/test/bbu.xml +152 -0
- data/test/bode-v1.ods.zip +0 -0
- data/test/bode-v1.xls.zip +0 -0
- data/test/boolean.ods +0 -0
- data/test/boolean.xls +0 -0
- data/test/boolean.xlsx +0 -0
- data/test/boolean.xml +112 -0
- data/test/borders.ods +0 -0
- data/test/borders.xls +0 -0
- data/test/borders.xlsx +0 -0
- data/test/borders.xml +144 -0
- data/test/bug-row-column-fixnum-float.xls +0 -0
- data/test/bug-row-column-fixnum-float.xml +127 -0
- data/test/datetime.ods +0 -0
- data/test/datetime.xls +0 -0
- data/test/datetime.xlsx +0 -0
- data/test/datetime.xml +142 -0
- data/test/datetime_floatconv.xls +0 -0
- data/test/datetime_floatconv.xml +148 -0
- data/test/emptysheets.ods +0 -0
- data/test/emptysheets.xls +0 -0
- data/test/emptysheets.xml +105 -0
- data/test/excel2003.xml +21140 -0
- data/test/false_encoding.xls +0 -0
- data/test/false_encoding.xml +132 -0
- data/test/formula.ods +0 -0
- data/test/formula.xls +0 -0
- data/test/formula.xlsx +0 -0
- data/test/formula.xml +134 -0
- data/test/formula_parse_error.xls +0 -0
- data/test/formula_parse_error.xml +1833 -0
- data/test/html-escape.ods +0 -0
- data/test/no_spreadsheet_file.txt +1 -0
- data/test/numbers1.csv +18 -0
- data/test/numbers1.ods +0 -0
- data/test/numbers1.xls +0 -0
- data/test/numbers1.xlsx +0 -0
- data/test/numbers1.xml +312 -0
- data/test/only_one_sheet.ods +0 -0
- data/test/only_one_sheet.xls +0 -0
- data/test/only_one_sheet.xlsx +0 -0
- data/test/only_one_sheet.xml +67 -0
- data/test/paragraph.ods +0 -0
- data/test/paragraph.xls +0 -0
- data/test/paragraph.xlsx +0 -0
- data/test/paragraph.xml +127 -0
- data/test/ric.ods +0 -0
- data/test/simple_spreadsheet.ods +0 -0
- data/test/simple_spreadsheet.xls +0 -0
- data/test/simple_spreadsheet.xlsx +0 -0
- data/test/simple_spreadsheet.xml +225 -0
- data/test/simple_spreadsheet_from_italo.ods +0 -0
- data/test/simple_spreadsheet_from_italo.xls +0 -0
- data/test/simple_spreadsheet_from_italo.xml +242 -0
- data/test/skipped_tests.rb +789 -0
- data/test/style.ods +0 -0
- data/test/style.xls +0 -0
- data/test/style.xlsx +0 -0
- data/test/style.xml +154 -0
- data/test/test_helper.rb +19 -0
- data/test/test_roo.rb +1834 -0
- data/test/time-test.csv +2 -0
- data/test/time-test.ods +0 -0
- data/test/time-test.xls +0 -0
- data/test/time-test.xlsx +0 -0
- data/test/time-test.xml +131 -0
- data/test/whitespace.ods +0 -0
- data/test/whitespace.xls +0 -0
- data/test/whitespace.xlsx +0 -0
- data/test/whitespace.xml +184 -0
- metadata +231 -0
data/lib/roo/google.rb
ADDED
@@ -0,0 +1,379 @@
|
|
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
|
+
class Google < GenericSpreadsheet
|
99
|
+
attr_accessor :date_format, :datetime_format
|
100
|
+
|
101
|
+
# Creates a new Google spreadsheet object.
|
102
|
+
def initialize(spreadsheetkey,user=nil,password=nil)
|
103
|
+
@filename = spreadsheetkey
|
104
|
+
@spreadsheetkey = spreadsheetkey
|
105
|
+
@user = user
|
106
|
+
@password = password
|
107
|
+
unless user
|
108
|
+
user = ENV['GOOGLE_MAIL']
|
109
|
+
end
|
110
|
+
unless password
|
111
|
+
password = ENV['GOOGLE_PASSWORD']
|
112
|
+
end
|
113
|
+
@cell = Hash.new {|h,k| h[k]=Hash.new}
|
114
|
+
@cell_type = Hash.new {|h,k| h[k]=Hash.new}
|
115
|
+
@formula = Hash.new
|
116
|
+
@first_row = Hash.new
|
117
|
+
@last_row = Hash.new
|
118
|
+
@first_column = Hash.new
|
119
|
+
@last_column = Hash.new
|
120
|
+
@cells_read = Hash.new
|
121
|
+
@header_line = 1
|
122
|
+
@date_format = '%d/%m/%Y'
|
123
|
+
@datetime_format = '%d/%m/%Y %H:%M:%S'
|
124
|
+
@time_format = '%H:%M:%S'
|
125
|
+
@gs = GData::Spreadsheet.new(spreadsheetkey)
|
126
|
+
@gs.authenticate(user, password) unless user.empty? || password.empty?
|
127
|
+
@sheetlist = @gs.sheetlist
|
128
|
+
@default_sheet = self.sheets.first
|
129
|
+
end
|
130
|
+
|
131
|
+
# returns an array of sheet names in the spreadsheet
|
132
|
+
def sheets
|
133
|
+
@sheetlist
|
134
|
+
end
|
135
|
+
|
136
|
+
def date?(string)
|
137
|
+
begin
|
138
|
+
Date.strptime(string, @date_format)
|
139
|
+
true
|
140
|
+
rescue
|
141
|
+
false
|
142
|
+
end
|
143
|
+
end
|
144
|
+
|
145
|
+
# is String a time with format HH:MM:SS?
|
146
|
+
def time?(string)
|
147
|
+
begin
|
148
|
+
DateTime.strptime(string, @time_format)
|
149
|
+
true
|
150
|
+
rescue
|
151
|
+
false
|
152
|
+
end
|
153
|
+
end
|
154
|
+
|
155
|
+
def datetime?(string)
|
156
|
+
begin
|
157
|
+
DateTime.strptime(string, @datetime_format)
|
158
|
+
true
|
159
|
+
rescue
|
160
|
+
false
|
161
|
+
end
|
162
|
+
end
|
163
|
+
|
164
|
+
def numeric?(string)
|
165
|
+
string =~ /^[0-9]+[\.]*[0-9]*$/
|
166
|
+
end
|
167
|
+
|
168
|
+
def timestring_to_seconds(value)
|
169
|
+
hms = value.split(':')
|
170
|
+
hms[0].to_i*3600 + hms[1].to_i*60 + hms[2].to_i
|
171
|
+
end
|
172
|
+
|
173
|
+
# Returns the content of a spreadsheet-cell.
|
174
|
+
# (1,1) is the upper left corner.
|
175
|
+
# (1,1), (1,'A'), ('A',1), ('a',1) all refers to the
|
176
|
+
# cell at the first line and first row.
|
177
|
+
def cell(row, col, sheet=nil)
|
178
|
+
sheet = @default_sheet unless sheet
|
179
|
+
check_default_sheet #TODO: 2007-12-16
|
180
|
+
read_cells(sheet) unless @cells_read[sheet]
|
181
|
+
row,col = normalize(row,col)
|
182
|
+
value = @cell[sheet]["#{row},#{col}"]
|
183
|
+
if celltype(row,col,sheet) == :date
|
184
|
+
begin
|
185
|
+
return Date.strptime(value, @date_format)
|
186
|
+
rescue ArgumentError
|
187
|
+
raise "Invalid Date #{sheet}[#{row},#{col}] #{value} using format '{@date_format}'"
|
188
|
+
end
|
189
|
+
elsif celltype(row,col,sheet) == :datetime
|
190
|
+
begin
|
191
|
+
return DateTime.strptime(value, @datetime_format)
|
192
|
+
rescue ArgumentError
|
193
|
+
raise "Invalid DateTime #{sheet}[#{row},#{col}] #{value} using format '{@datetime_format}'"
|
194
|
+
end
|
195
|
+
end
|
196
|
+
return value
|
197
|
+
end
|
198
|
+
|
199
|
+
# returns the type of a cell:
|
200
|
+
# * :float
|
201
|
+
# * :string
|
202
|
+
# * :date
|
203
|
+
# * :percentage
|
204
|
+
# * :formula
|
205
|
+
# * :time
|
206
|
+
# * :datetime
|
207
|
+
def celltype(row, col, sheet=nil)
|
208
|
+
sheet = @default_sheet unless sheet
|
209
|
+
read_cells(sheet) unless @cells_read[sheet]
|
210
|
+
row,col = normalize(row,col)
|
211
|
+
if @formula.size > 0 && @formula[sheet]["#{row},#{col}"]
|
212
|
+
return :formula
|
213
|
+
else
|
214
|
+
@cell_type[sheet]["#{row},#{col}"]
|
215
|
+
end
|
216
|
+
end
|
217
|
+
|
218
|
+
# Returns the formula at (row,col).
|
219
|
+
# Returns nil if there is no formula.
|
220
|
+
# The method #formula? checks if there is a formula.
|
221
|
+
def formula(row,col,sheet=nil)
|
222
|
+
sheet = @default_sheet unless sheet
|
223
|
+
read_cells(sheet) unless @cells_read[sheet]
|
224
|
+
row,col = normalize(row,col)
|
225
|
+
if @formula[sheet]["#{row},#{col}"] == nil
|
226
|
+
return nil
|
227
|
+
else
|
228
|
+
return @formula[sheet]["#{row},#{col}"]
|
229
|
+
end
|
230
|
+
end
|
231
|
+
|
232
|
+
# true, if there is a formula
|
233
|
+
def formula?(row,col,sheet=nil)
|
234
|
+
sheet = @default_sheet unless sheet
|
235
|
+
read_cells(sheet) unless @cells_read[sheet]
|
236
|
+
row,col = normalize(row,col)
|
237
|
+
formula(row,col) != nil
|
238
|
+
end
|
239
|
+
|
240
|
+
# returns each formula in the selected sheet as an array of elements
|
241
|
+
# [row, col, formula]
|
242
|
+
def formulas(sheet=nil)
|
243
|
+
theformulas = Array.new
|
244
|
+
sheet = @default_sheet unless sheet
|
245
|
+
read_cells(sheet) unless @cells_read[sheet]
|
246
|
+
first_row(sheet).upto(last_row(sheet)) {|row|
|
247
|
+
first_column(sheet).upto(last_column(sheet)) {|col|
|
248
|
+
if formula?(row,col,sheet)
|
249
|
+
f = [row, col, formula(row,col,sheet)]
|
250
|
+
theformulas << f
|
251
|
+
end
|
252
|
+
}
|
253
|
+
}
|
254
|
+
theformulas
|
255
|
+
end
|
256
|
+
|
257
|
+
# true, if the cell is empty
|
258
|
+
def empty?(row, col, sheet=nil)
|
259
|
+
value = cell(row, col, sheet)
|
260
|
+
return true unless value
|
261
|
+
return false if value.class == Date # a date is never empty
|
262
|
+
return false if value.class == Float
|
263
|
+
return false if celltype(row,col,sheet) == :time
|
264
|
+
value.empty?
|
265
|
+
end
|
266
|
+
|
267
|
+
# sets the cell to the content of 'value'
|
268
|
+
# a formula can be set in the form of '=SUM(...)'
|
269
|
+
def set_value(row,col,value,sheet=nil)
|
270
|
+
sheet = @default_sheet unless sheet
|
271
|
+
raise RangeError, "sheet not set" unless sheet
|
272
|
+
#@@ Set and pass sheet_no
|
273
|
+
begin
|
274
|
+
sheet_no = sheets.index(sheet)+1
|
275
|
+
rescue
|
276
|
+
raise RangeError, "invalid sheet '"+sheet.to_s+"'"
|
277
|
+
end
|
278
|
+
row,col = normalize(row,col)
|
279
|
+
@gs.add_to_cell_roo(row,col,value,sheet_no)
|
280
|
+
# re-read the portion of the document that has changed
|
281
|
+
if @cells_read[sheet]
|
282
|
+
key = "#{row},#{col}"
|
283
|
+
(value, value_type) = determine_datatype(value.to_s)
|
284
|
+
@cell[sheet][key] = value
|
285
|
+
@cell_type[sheet][key] = value_type
|
286
|
+
end
|
287
|
+
end
|
288
|
+
|
289
|
+
# returns the first non-empty row in a sheet
|
290
|
+
def first_row(sheet=nil)
|
291
|
+
sheet = @default_sheet unless sheet
|
292
|
+
unless @first_row[sheet]
|
293
|
+
sheet_no = sheets.index(sheet) + 1
|
294
|
+
@first_row[sheet], @last_row[sheet], @first_column[sheet], @last_column[sheet] = @gs.oben_unten_links_rechts(sheet_no)
|
295
|
+
end
|
296
|
+
return @first_row[sheet]
|
297
|
+
end
|
298
|
+
|
299
|
+
# returns the last non-empty row in a sheet
|
300
|
+
def last_row(sheet=nil)
|
301
|
+
sheet = @default_sheet unless sheet
|
302
|
+
unless @last_row[sheet]
|
303
|
+
sheet_no = sheets.index(sheet) + 1
|
304
|
+
@first_row[sheet], @last_row[sheet], @first_column[sheet], @last_column[sheet] = @gs.oben_unten_links_rechts(sheet_no)
|
305
|
+
end
|
306
|
+
return @last_row[sheet]
|
307
|
+
end
|
308
|
+
|
309
|
+
# returns the first non-empty column in a sheet
|
310
|
+
def first_column(sheet=nil)
|
311
|
+
sheet = @default_sheet unless sheet
|
312
|
+
unless @first_column[sheet]
|
313
|
+
sheet_no = sheets.index(sheet) + 1
|
314
|
+
@first_row[sheet], @last_row[sheet], @first_column[sheet], @last_column[sheet] = @gs.oben_unten_links_rechts(sheet_no)
|
315
|
+
end
|
316
|
+
return @first_column[sheet]
|
317
|
+
end
|
318
|
+
|
319
|
+
# returns the last non-empty column in a sheet
|
320
|
+
def last_column(sheet=nil)
|
321
|
+
sheet = @default_sheet unless sheet
|
322
|
+
unless @last_column[sheet]
|
323
|
+
sheet_no = sheets.index(sheet) + 1
|
324
|
+
@first_row[sheet], @last_row[sheet], @first_column[sheet], @last_column[sheet] = @gs.oben_unten_links_rechts(sheet_no)
|
325
|
+
end
|
326
|
+
return @last_column[sheet]
|
327
|
+
end
|
328
|
+
|
329
|
+
private
|
330
|
+
|
331
|
+
# read all cells in a sheet.
|
332
|
+
def read_cells(sheet=nil)
|
333
|
+
sheet = @default_sheet unless sheet
|
334
|
+
raise RangeError, "illegal sheet <#{sheet}>" unless sheets.index(sheet)
|
335
|
+
sheet_no = sheets.index(sheet)+1
|
336
|
+
xml = @gs.fulldoc(sheet_no).to_s
|
337
|
+
doc = XML::Parser.string(xml).parse
|
338
|
+
doc.find("//*[local-name()='cell']").each do |item|
|
339
|
+
row = item['row']
|
340
|
+
col = item['col']
|
341
|
+
key = "#{row},#{col}"
|
342
|
+
string_value = item['inputvalue'] || item['inputValue']
|
343
|
+
numeric_value = item['numericvalue'] || item['numericValue']
|
344
|
+
(value, value_type) = determine_datatype(string_value, numeric_value)
|
345
|
+
@cell[sheet][key] = value unless value == "" or value == nil
|
346
|
+
@cell_type[sheet][key] = value_type
|
347
|
+
@formula[sheet] = {} unless @formula[sheet]
|
348
|
+
@formula[sheet][key] = string_value if value_type == :formula
|
349
|
+
end
|
350
|
+
@cells_read[sheet] = true
|
351
|
+
end
|
352
|
+
|
353
|
+
def determine_datatype(val, numval=nil)
|
354
|
+
if val.nil? || val[0,1] == '='
|
355
|
+
ty = :formula
|
356
|
+
if numeric?(numval)
|
357
|
+
val = numval.to_f
|
358
|
+
else
|
359
|
+
val = numval
|
360
|
+
end
|
361
|
+
else
|
362
|
+
if datetime?(val)
|
363
|
+
ty = :datetime
|
364
|
+
elsif date?(val)
|
365
|
+
ty = :date
|
366
|
+
elsif numeric?(val)
|
367
|
+
ty = :float
|
368
|
+
val = val.to_f
|
369
|
+
elsif time?(val)
|
370
|
+
ty = :time
|
371
|
+
val = timestring_to_seconds(val)
|
372
|
+
else
|
373
|
+
ty = :string
|
374
|
+
end
|
375
|
+
end
|
376
|
+
return val, ty
|
377
|
+
end
|
378
|
+
|
379
|
+
end # class
|
@@ -0,0 +1,451 @@
|
|
1
|
+
require 'xml'
|
2
|
+
require 'fileutils'
|
3
|
+
require 'zip/zipfilesystem'
|
4
|
+
require 'date'
|
5
|
+
require 'base64'
|
6
|
+
require 'cgi'
|
7
|
+
|
8
|
+
class Openoffice < GenericSpreadsheet
|
9
|
+
|
10
|
+
@@nr = 0
|
11
|
+
|
12
|
+
# initialization and opening of a spreadsheet file
|
13
|
+
# values for packed: :zip
|
14
|
+
def initialize(filename, packed=nil, file_warning=:error) #, create = false)
|
15
|
+
@file_warning = file_warning
|
16
|
+
super()
|
17
|
+
@tmpdir = "oo_"+$$.to_s
|
18
|
+
@tmpdir = File.join(ENV['ROO_TMP'], @tmpdir) if ENV['ROO_TMP']
|
19
|
+
unless File.exists?(@tmpdir)
|
20
|
+
FileUtils::mkdir(@tmpdir)
|
21
|
+
end
|
22
|
+
filename = open_from_uri(filename) if filename[0,7] == "http://"
|
23
|
+
filename = unzip(filename) if packed and packed == :zip
|
24
|
+
begin
|
25
|
+
file_type_check(filename,'.ods','an openoffice')
|
26
|
+
#if create and ! File.exists?(filename)
|
27
|
+
# self.create_openoffice(filename)
|
28
|
+
#end
|
29
|
+
@cells_read = Hash.new
|
30
|
+
#TODO: @cells_read[:default] = false
|
31
|
+
@filename = filename
|
32
|
+
unless File.file?(@filename)
|
33
|
+
raise IOError, "file #{@filename} does not exist"
|
34
|
+
end
|
35
|
+
@@nr += 1
|
36
|
+
@file_nr = @@nr
|
37
|
+
extract_content
|
38
|
+
file = File.new(File.join(@tmpdir, @file_nr.to_s+"_roo_content.xml"))
|
39
|
+
@doc = XML::Parser.io(file).parse
|
40
|
+
file.close
|
41
|
+
ensure
|
42
|
+
#if ENV["roo_local"] != "thomas-p"
|
43
|
+
FileUtils::rm_r(@tmpdir)
|
44
|
+
#end
|
45
|
+
end
|
46
|
+
@default_sheet = self.sheets.first
|
47
|
+
@cell = Hash.new
|
48
|
+
@cell_type = Hash.new
|
49
|
+
@formula = Hash.new
|
50
|
+
@first_row = Hash.new
|
51
|
+
@last_row = Hash.new
|
52
|
+
@first_column = Hash.new
|
53
|
+
@last_column = Hash.new
|
54
|
+
@style = Hash.new
|
55
|
+
@style_defaults = Hash.new { |h,k| h[k] = [] }
|
56
|
+
@style_definitions = Hash.new
|
57
|
+
@header_line = 1
|
58
|
+
end
|
59
|
+
|
60
|
+
# creates a new empty openoffice-spreadsheet file
|
61
|
+
def create_openoffice(filename) #:nodoc:
|
62
|
+
#TODO: a better way for creating the file contents
|
63
|
+
# now you have to call mkbase64...rb to create an include file with all
|
64
|
+
# the empty files in an openoffice zip-file
|
65
|
+
load 'base64include.rb'
|
66
|
+
# puts @@empty_spreadsheet
|
67
|
+
f = File.open(filename,'wb')
|
68
|
+
f.print(Base64.decode64(@@empty_spreadsheet))
|
69
|
+
f.close
|
70
|
+
end
|
71
|
+
|
72
|
+
# Returns the content of a spreadsheet-cell.
|
73
|
+
# (1,1) is the upper left corner.
|
74
|
+
# (1,1), (1,'A'), ('A',1), ('a',1) all refers to the
|
75
|
+
# cell at the first line and first row.
|
76
|
+
def cell(row, col, sheet=nil)
|
77
|
+
sheet = @default_sheet unless sheet
|
78
|
+
read_cells(sheet) unless @cells_read[sheet]
|
79
|
+
row,col = normalize(row,col)
|
80
|
+
if celltype(row,col,sheet) == :date
|
81
|
+
yyyy,mm,dd = @cell[sheet][[row,col]].split('-')
|
82
|
+
return Date.new(yyyy.to_i,mm.to_i,dd.to_i)
|
83
|
+
end
|
84
|
+
@cell[sheet][[row,col]]
|
85
|
+
end
|
86
|
+
|
87
|
+
# Returns the formula at (row,col).
|
88
|
+
# Returns nil if there is no formula.
|
89
|
+
# The method #formula? checks if there is a formula.
|
90
|
+
def formula(row,col,sheet=nil)
|
91
|
+
sheet = @default_sheet unless sheet
|
92
|
+
read_cells(sheet) unless @cells_read[sheet]
|
93
|
+
row,col = normalize(row,col)
|
94
|
+
if @formula[sheet][[row,col]] == nil
|
95
|
+
return nil
|
96
|
+
else
|
97
|
+
return @formula[sheet][[row,col]]["oooc:".length..-1]
|
98
|
+
end
|
99
|
+
end
|
100
|
+
|
101
|
+
# true, if there is a formula
|
102
|
+
def formula?(row,col,sheet=nil)
|
103
|
+
sheet = @default_sheet unless sheet
|
104
|
+
read_cells(sheet) unless @cells_read[sheet]
|
105
|
+
row,col = normalize(row,col)
|
106
|
+
formula(row,col) != nil
|
107
|
+
end
|
108
|
+
|
109
|
+
class Font
|
110
|
+
attr_accessor :bold, :italic, :underline
|
111
|
+
|
112
|
+
def bold?
|
113
|
+
@bold == 'bold'
|
114
|
+
end
|
115
|
+
|
116
|
+
def italic?
|
117
|
+
@italic == 'italic'
|
118
|
+
end
|
119
|
+
|
120
|
+
def underline?
|
121
|
+
@underline != nil
|
122
|
+
end
|
123
|
+
end
|
124
|
+
|
125
|
+
# Given a cell, return the cell's style
|
126
|
+
def font(row, col, sheet=nil)
|
127
|
+
sheet = @default_sheet unless sheet
|
128
|
+
read_cells(sheet) unless @cells_read[sheet]
|
129
|
+
row,col = normalize(row,col)
|
130
|
+
style_name = @style[sheet][[row,col]] || @style_defaults[sheet][col - 1] || 'Default'
|
131
|
+
@style_definitions[style_name]
|
132
|
+
end
|
133
|
+
|
134
|
+
# set a cell to a certain value
|
135
|
+
# (this will not be saved back to the spreadsheet file!)
|
136
|
+
def set(row,col,value,sheet=nil) #:nodoc:
|
137
|
+
sheet = @default_sheet unless sheet
|
138
|
+
read_cells(sheet) unless @cells_read[sheet]
|
139
|
+
row,col = normalize(row,col)
|
140
|
+
set_value(row,col,value,sheet)
|
141
|
+
if value.class == Fixnum
|
142
|
+
set_type(row,col,:float,sheet)
|
143
|
+
elsif value.class == String
|
144
|
+
set_type(row,col,:string,sheet)
|
145
|
+
elsif value.class == Float
|
146
|
+
set_type(row,col,:string,sheet)
|
147
|
+
else
|
148
|
+
raise ArgumentError, "Type for "+value.to_s+" not set"
|
149
|
+
end
|
150
|
+
end
|
151
|
+
|
152
|
+
# returns the type of a cell:
|
153
|
+
# * :float
|
154
|
+
# * :string
|
155
|
+
# * :date
|
156
|
+
# * :percentage
|
157
|
+
# * :formula
|
158
|
+
# * :time
|
159
|
+
# * :datetime
|
160
|
+
def celltype(row,col,sheet=nil)
|
161
|
+
sheet = @default_sheet unless sheet
|
162
|
+
read_cells(sheet) unless @cells_read[sheet]
|
163
|
+
row,col = normalize(row,col)
|
164
|
+
if @formula[sheet][[row,col]]
|
165
|
+
return :formula
|
166
|
+
else
|
167
|
+
@cell_type[sheet][[row,col]]
|
168
|
+
end
|
169
|
+
end
|
170
|
+
|
171
|
+
def sheets
|
172
|
+
return_sheets = []
|
173
|
+
@doc.find("//*[local-name()='table']").each do |sheet|
|
174
|
+
return_sheets << sheet.attributes['name']
|
175
|
+
end
|
176
|
+
return_sheets
|
177
|
+
end
|
178
|
+
|
179
|
+
# version of the openoffice document
|
180
|
+
# at 2007 this is always "1.0"
|
181
|
+
def officeversion
|
182
|
+
oo_version
|
183
|
+
@officeversion
|
184
|
+
end
|
185
|
+
|
186
|
+
# shows the internal representation of all cells
|
187
|
+
# mainly for debugging purposes
|
188
|
+
def to_s(sheet=nil)
|
189
|
+
sheet = @default_sheet unless sheet
|
190
|
+
read_cells(sheet) unless @cells_read[sheet]
|
191
|
+
@cell[sheet].inspect
|
192
|
+
end
|
193
|
+
|
194
|
+
# save spreadsheet
|
195
|
+
def save #:nodoc:
|
196
|
+
42
|
197
|
+
end
|
198
|
+
|
199
|
+
# returns each formula in the selected sheet as an array of elements
|
200
|
+
# [row, col, formula]
|
201
|
+
def formulas(sheet=nil)
|
202
|
+
theformulas = Array.new
|
203
|
+
sheet = @default_sheet unless sheet
|
204
|
+
read_cells(sheet) unless @cells_read[sheet]
|
205
|
+
first_row(sheet).upto(last_row(sheet)) {|row|
|
206
|
+
first_column(sheet).upto(last_column(sheet)) {|col|
|
207
|
+
if formula?(row,col,sheet)
|
208
|
+
f = [row, col, formula(row,col,sheet)]
|
209
|
+
theformulas << f
|
210
|
+
end
|
211
|
+
}
|
212
|
+
}
|
213
|
+
theformulas
|
214
|
+
end
|
215
|
+
|
216
|
+
private
|
217
|
+
|
218
|
+
# read the version of the OO-Version
|
219
|
+
def oo_version
|
220
|
+
@doc.find("//*[local-name()='document-content']").each do |office|
|
221
|
+
@officeversion = office.attributes['version']
|
222
|
+
end
|
223
|
+
end
|
224
|
+
|
225
|
+
# helper function to set the internal representation of cells
|
226
|
+
def set_cell_values(sheet,x,y,i,v,vt,formula,table_cell,str_v,style_name)
|
227
|
+
key = [y,x+i]
|
228
|
+
@cell_type[sheet] = {} unless @cell_type[sheet]
|
229
|
+
@cell_type[sheet][key] = Openoffice.oo_type_2_roo_type(vt)
|
230
|
+
@formula[sheet] = {} unless @formula[sheet]
|
231
|
+
@formula[sheet][key] = formula if formula
|
232
|
+
@cell[sheet] = {} unless @cell[sheet]
|
233
|
+
@style[sheet] = {} unless @style[sheet]
|
234
|
+
@style[sheet][key] = style_name
|
235
|
+
case @cell_type[sheet][key]
|
236
|
+
when :float
|
237
|
+
@cell[sheet][key] = (v.to_s.include?('.') ? v.to_f : v.to_i)
|
238
|
+
when :string
|
239
|
+
@cell[sheet][key] = str_v
|
240
|
+
when :date
|
241
|
+
if table_cell.attributes['date-value'].size != "XXXX-XX-XX".size
|
242
|
+
#-- dann ist noch eine Uhrzeit vorhanden
|
243
|
+
#-- "1961-11-21T12:17:18"
|
244
|
+
@cell[sheet][key] = DateTime.parse(table_cell.attributes['date-value'])
|
245
|
+
@cell_type[sheet][key] = :datetime
|
246
|
+
else
|
247
|
+
@cell[sheet][key] = table_cell.attributes['date-value']
|
248
|
+
end
|
249
|
+
when :percentage
|
250
|
+
@cell[sheet][key] = v.to_f
|
251
|
+
when :time
|
252
|
+
hms = v.split(':')
|
253
|
+
@cell[sheet][key] = hms[0].to_i*3600 + hms[1].to_i*60 + hms[2].to_i
|
254
|
+
else
|
255
|
+
@cell[sheet][key] = v
|
256
|
+
end
|
257
|
+
end
|
258
|
+
|
259
|
+
# read all cells in the selected sheet
|
260
|
+
#--
|
261
|
+
# the following construct means '4 blanks'
|
262
|
+
# some content <text:s text:c="3"/>
|
263
|
+
#++
|
264
|
+
def read_cells(sheet=nil)
|
265
|
+
sheet = @default_sheet unless sheet
|
266
|
+
sheet_found = false
|
267
|
+
raise ArgumentError, "Error: sheet '#{sheet||'nil'}' not valid" if @default_sheet == nil and sheet==nil
|
268
|
+
raise RangeError unless self.sheets.include? sheet
|
269
|
+
|
270
|
+
@doc.find("//*[local-name()='table']").each do |ws|
|
271
|
+
if sheet == ws.attributes['name']
|
272
|
+
sheet_found = true
|
273
|
+
col = 1
|
274
|
+
row = 1
|
275
|
+
ws.each_element do |table_element|
|
276
|
+
case table_element.name
|
277
|
+
when 'table-column'
|
278
|
+
@style_defaults[sheet] << table_element.attributes['default-cell-style-name']
|
279
|
+
when 'table-row'
|
280
|
+
if table_element.attributes['number-rows-repeated']
|
281
|
+
skip_row = table_element.attributes['number-rows-repeated'].to_i
|
282
|
+
row = row + skip_row - 1
|
283
|
+
end
|
284
|
+
table_element.each_element do |cell|
|
285
|
+
skip_col = cell.attributes['number-columns-repeated']
|
286
|
+
formula = cell.attributes['formula']
|
287
|
+
vt = cell.attributes['value-type']
|
288
|
+
v = cell.attributes['value']
|
289
|
+
style_name = cell.attributes['style-name']
|
290
|
+
if vt == 'string'
|
291
|
+
str_v = ''
|
292
|
+
# insert \n if there is more than one paragraph
|
293
|
+
para_count = 0
|
294
|
+
cell.each_element do |str|
|
295
|
+
if str.name == 'p'
|
296
|
+
v = str.content
|
297
|
+
str_v += "\n" if para_count > 0
|
298
|
+
para_count += 1
|
299
|
+
if str.children.size > 1
|
300
|
+
str_v += children_to_string(str.children)
|
301
|
+
else
|
302
|
+
str.children.each do |child|
|
303
|
+
str_v += child.content #.text
|
304
|
+
end
|
305
|
+
end
|
306
|
+
str_v.gsub!(/'/,"'") # special case not supported by unescapeHTML
|
307
|
+
str_v = CGI.unescapeHTML(str_v)
|
308
|
+
end # == 'p'
|
309
|
+
end
|
310
|
+
elsif vt == 'time'
|
311
|
+
cell.each_element do |str|
|
312
|
+
if str.name == 'p'
|
313
|
+
v = str.content
|
314
|
+
end
|
315
|
+
end
|
316
|
+
elsif vt == '' or vt == nil
|
317
|
+
#
|
318
|
+
elsif vt == 'date'
|
319
|
+
#
|
320
|
+
elsif vt == 'percentage'
|
321
|
+
#
|
322
|
+
elsif vt == 'float'
|
323
|
+
#
|
324
|
+
elsif vt == 'boolean'
|
325
|
+
v = cell.attributes['boolean-value']
|
326
|
+
#
|
327
|
+
else
|
328
|
+
# raise "unknown type #{vt}"
|
329
|
+
end
|
330
|
+
if skip_col
|
331
|
+
if v != nil or cell.attributes['date-value']
|
332
|
+
0.upto(skip_col.to_i-1) do |i|
|
333
|
+
set_cell_values(sheet,col,row,i,v,vt,formula,cell,str_v,style_name)
|
334
|
+
end
|
335
|
+
end
|
336
|
+
col += (skip_col.to_i - 1)
|
337
|
+
end # if skip
|
338
|
+
set_cell_values(sheet,col,row,0,v,vt,formula,cell,str_v,style_name)
|
339
|
+
col += 1
|
340
|
+
end
|
341
|
+
row += 1
|
342
|
+
col = 1
|
343
|
+
end
|
344
|
+
end
|
345
|
+
end
|
346
|
+
end
|
347
|
+
|
348
|
+
@doc.find("//*[local-name()='automatic-styles']").each do |style|
|
349
|
+
read_styles(style)
|
350
|
+
end
|
351
|
+
if !sheet_found
|
352
|
+
raise RangeError
|
353
|
+
end
|
354
|
+
@cells_read[sheet] = true
|
355
|
+
end
|
356
|
+
|
357
|
+
def read_styles(style_elements)
|
358
|
+
@style_definitions['Default'] = Openoffice::Font.new
|
359
|
+
style_elements.each do |style|
|
360
|
+
next unless style.name == 'style'
|
361
|
+
style_name = style.attributes['name']
|
362
|
+
style.each do |properties|
|
363
|
+
font = Openoffice::Font.new
|
364
|
+
font.bold = properties.attributes['font-weight']
|
365
|
+
font.italic = properties.attributes['font-style']
|
366
|
+
font.underline = properties.attributes['text-underline-style']
|
367
|
+
@style_definitions[style_name] = font
|
368
|
+
end
|
369
|
+
end
|
370
|
+
end
|
371
|
+
|
372
|
+
# Checks if the default_sheet exists. If not an RangeError exception is
|
373
|
+
# raised
|
374
|
+
def check_default_sheet
|
375
|
+
sheet_found = false
|
376
|
+
raise ArgumentError, "Error: default_sheet not set" if @default_sheet == nil
|
377
|
+
sheet_found = true if sheets.include?(@default_sheet)
|
378
|
+
if ! sheet_found
|
379
|
+
raise RangeError, "sheet '#{@default_sheet}' not found"
|
380
|
+
end
|
381
|
+
end
|
382
|
+
|
383
|
+
def process_zipfile(zip, path='')
|
384
|
+
if zip.file.file? path
|
385
|
+
if path == "content.xml"
|
386
|
+
open(File.join(@tmpdir, @file_nr.to_s+'_roo_content.xml'),'wb') {|f|
|
387
|
+
f << zip.read(path)
|
388
|
+
}
|
389
|
+
end
|
390
|
+
else
|
391
|
+
unless path.empty?
|
392
|
+
path += '/'
|
393
|
+
end
|
394
|
+
zip.dir.foreach(path) do |filename|
|
395
|
+
process_zipfile(zip, path+filename)
|
396
|
+
end
|
397
|
+
end
|
398
|
+
end
|
399
|
+
|
400
|
+
def extract_content
|
401
|
+
Zip::ZipFile.open(@filename) do |zip|
|
402
|
+
process_zipfile(zip)
|
403
|
+
end
|
404
|
+
end
|
405
|
+
|
406
|
+
def set_value(row,col,value,sheet=nil)
|
407
|
+
sheet = @default_value unless sheet
|
408
|
+
@cell[sheet][[row,col]] = value
|
409
|
+
end
|
410
|
+
|
411
|
+
def set_type(row,col,type,sheet=nil)
|
412
|
+
sheet = @default_value unless sheet
|
413
|
+
@cell_type[sheet][[row,col]] = type
|
414
|
+
end
|
415
|
+
|
416
|
+
A_ROO_TYPE = {
|
417
|
+
"float" => :float,
|
418
|
+
"string" => :string,
|
419
|
+
"date" => :date,
|
420
|
+
"percentage" => :percentage,
|
421
|
+
"time" => :time,
|
422
|
+
}
|
423
|
+
|
424
|
+
def Openoffice.oo_type_2_roo_type(ootype)
|
425
|
+
return A_ROO_TYPE[ootype]
|
426
|
+
end
|
427
|
+
|
428
|
+
# helper method to convert compressed spaces and other elements within
|
429
|
+
# an text into a string
|
430
|
+
def children_to_string(children)
|
431
|
+
result = ''
|
432
|
+
children.each {|child|
|
433
|
+
if child.text?
|
434
|
+
result = result + child.content
|
435
|
+
else
|
436
|
+
if child.name == 's'
|
437
|
+
compressed_spaces = child.attributes['c'].to_i
|
438
|
+
# no explicit number means a count of 1:
|
439
|
+
if compressed_spaces == 0
|
440
|
+
compressed_spaces = 1
|
441
|
+
end
|
442
|
+
result = result + " "*compressed_spaces
|
443
|
+
else
|
444
|
+
result = result + child.content
|
445
|
+
end
|
446
|
+
end
|
447
|
+
}
|
448
|
+
result
|
449
|
+
end
|
450
|
+
|
451
|
+
end # class
|