tb 0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/README +60 -0
- data/bin/tb +1137 -0
- data/lib/tb.rb +35 -0
- data/lib/tb/basic.rb +1071 -0
- data/lib/tb/csv.rb +125 -0
- data/lib/tb/enumerable.rb +284 -0
- data/lib/tb/fieldset.rb +96 -0
- data/lib/tb/pathfinder.rb +569 -0
- data/lib/tb/qtsv.rb +93 -0
- data/lib/tb/reader.rb +213 -0
- data/lib/tb/record.rb +129 -0
- data/lib/tb/tsv.rb +93 -0
- data/sample/excel2csv +270 -0
- data/sample/poi-xls2csv.rb +397 -0
- data/sample/poi-xls2csv.sh +39 -0
- data/test-all.rb +7 -0
- data/test/test_basic.rb +290 -0
- data/test/test_csv.rb +78 -0
- data/test/test_enumerable.rb +122 -0
- data/test/test_record.rb +12 -0
- data/test/test_tsv.rb +41 -0
- metadata +73 -0
data/lib/tb/csv.rb
ADDED
@@ -0,0 +1,125 @@
|
|
1
|
+
# lib/tb/csv.rb - CSV related fetures for table library
|
2
|
+
#
|
3
|
+
# Copyright (C) 2010-2011 Tanaka Akira <akr@fsij.org>
|
4
|
+
#
|
5
|
+
# Redistribution and use in source and binary forms, with or without
|
6
|
+
# modification, are permitted provided that the following conditions are met:
|
7
|
+
#
|
8
|
+
# 1. Redistributions of source code must retain the above copyright notice, this
|
9
|
+
# list of conditions and the following disclaimer.
|
10
|
+
# 2. Redistributions in binary form must reproduce the above copyright notice,
|
11
|
+
# this list of conditions and the following disclaimer in the documentation
|
12
|
+
# and/or other materials provided with the distribution.
|
13
|
+
# 3. The name of the author may not be used to endorse or promote products
|
14
|
+
# derived from this software without specific prior written permission.
|
15
|
+
#
|
16
|
+
# THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED
|
17
|
+
# WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
|
18
|
+
# MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO
|
19
|
+
# EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
|
20
|
+
# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT
|
21
|
+
# OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
22
|
+
# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
|
23
|
+
# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
|
24
|
+
# IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY
|
25
|
+
# OF SUCH DAMAGE.
|
26
|
+
|
27
|
+
require 'csv'
|
28
|
+
|
29
|
+
class Tb
|
30
|
+
def Tb.csv_stream_input(csv, &b)
|
31
|
+
csvreader = CSVReader.new(csv)
|
32
|
+
begin
|
33
|
+
csvreader.each(&b)
|
34
|
+
ensure
|
35
|
+
csvreader.close
|
36
|
+
end
|
37
|
+
nil
|
38
|
+
end
|
39
|
+
|
40
|
+
class CSVReader
|
41
|
+
if defined? CSV::Reader
|
42
|
+
# Ruby 1.8
|
43
|
+
def initialize(input)
|
44
|
+
if input.respond_to? :to_str
|
45
|
+
@csv = CSV::StringReader.new(input)
|
46
|
+
else
|
47
|
+
@csv = CSV::IOReader.new(input)
|
48
|
+
end
|
49
|
+
@eof = false
|
50
|
+
end
|
51
|
+
|
52
|
+
def shift
|
53
|
+
return nil if @eof
|
54
|
+
ary = @csv.shift
|
55
|
+
if ary.empty?
|
56
|
+
ary = nil
|
57
|
+
@eof = true
|
58
|
+
elsif ary == [nil]
|
59
|
+
ary = []
|
60
|
+
end
|
61
|
+
ary
|
62
|
+
end
|
63
|
+
else
|
64
|
+
# Ruby 1.9
|
65
|
+
def initialize(input)
|
66
|
+
@csv = CSV.new(input)
|
67
|
+
end
|
68
|
+
|
69
|
+
def shift
|
70
|
+
@csv.shift
|
71
|
+
end
|
72
|
+
end
|
73
|
+
|
74
|
+
def each
|
75
|
+
while ary = self.shift
|
76
|
+
yield ary
|
77
|
+
end
|
78
|
+
nil
|
79
|
+
end
|
80
|
+
|
81
|
+
def close
|
82
|
+
@csv.close
|
83
|
+
end
|
84
|
+
end
|
85
|
+
|
86
|
+
def Tb.csv_stream_output(out)
|
87
|
+
require 'csv'
|
88
|
+
if defined? CSV::Writer
|
89
|
+
# Ruby 1.8
|
90
|
+
CSV::Writer.generate(out) {|csvgen|
|
91
|
+
yield csvgen
|
92
|
+
}
|
93
|
+
else
|
94
|
+
# Ruby 1.9
|
95
|
+
gen = Object.new
|
96
|
+
gen.instance_variable_set(:@out, out)
|
97
|
+
def gen.<<(ary)
|
98
|
+
@out << ary.to_csv
|
99
|
+
end
|
100
|
+
yield gen
|
101
|
+
end
|
102
|
+
end
|
103
|
+
|
104
|
+
# :call-seq:
|
105
|
+
# generate_csv(out='', fields=nil) {|recordids| modified_recordids }
|
106
|
+
# generate_csv(out='', fields=nil)
|
107
|
+
#
|
108
|
+
def generate_csv(out='', fields=nil, &block)
|
109
|
+
if fields.nil?
|
110
|
+
fields = list_fields
|
111
|
+
end
|
112
|
+
require 'csv'
|
113
|
+
recordids = list_recordids
|
114
|
+
if block_given?
|
115
|
+
recordids = yield(recordids)
|
116
|
+
end
|
117
|
+
Tb.csv_stream_output(out) {|gen|
|
118
|
+
gen << fields
|
119
|
+
recordids.each {|recordid|
|
120
|
+
gen << get_values(recordid, *fields)
|
121
|
+
}
|
122
|
+
}
|
123
|
+
out
|
124
|
+
end
|
125
|
+
end
|
@@ -0,0 +1,284 @@
|
|
1
|
+
# lib/tb/enumerable.rb - extensions for Enumerable
|
2
|
+
#
|
3
|
+
# Copyright (C) 2010 Tanaka Akira <akr@fsij.org>
|
4
|
+
#
|
5
|
+
# Redistribution and use in source and binary forms, with or without
|
6
|
+
# modification, are permitted provided that the following conditions are met:
|
7
|
+
#
|
8
|
+
# 1. Redistributions of source code must retain the above copyright notice, this
|
9
|
+
# list of conditions and the following disclaimer.
|
10
|
+
# 2. Redistributions in binary form must reproduce the above copyright notice,
|
11
|
+
# this list of conditions and the following disclaimer in the documentation
|
12
|
+
# and/or other materials provided with the distribution.
|
13
|
+
# 3. The name of the author may not be used to endorse or promote products
|
14
|
+
# derived from this software without specific prior written permission.
|
15
|
+
#
|
16
|
+
# THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED
|
17
|
+
# WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
|
18
|
+
# MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO
|
19
|
+
# EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
|
20
|
+
# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT
|
21
|
+
# OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
22
|
+
# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
|
23
|
+
# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
|
24
|
+
# IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY
|
25
|
+
# OF SUCH DAMAGE.
|
26
|
+
|
27
|
+
module Enumerable
|
28
|
+
# :call-seq:
|
29
|
+
# enum.tb_categorize(ksel1, ksel2, ..., vsel, [opts])
|
30
|
+
# enum.tb_categorize(ksel1, ksel2, ..., vsel, [opts]) {|ks, vs| ... }
|
31
|
+
#
|
32
|
+
# categorizes the elements in _enum_ and returns a hash.
|
33
|
+
# This method assumes multiple elements for a category.
|
34
|
+
#
|
35
|
+
# +tb_categorize+ takes one or more key selectors,
|
36
|
+
# one value selector and
|
37
|
+
# an optional option hash.
|
38
|
+
# It also takes an optional block.
|
39
|
+
#
|
40
|
+
# The selectors specify how to extract a value from an element in _enum_.
|
41
|
+
#
|
42
|
+
# The key selectors, _kselN_, are used to extract hash keys from an element.
|
43
|
+
# If two or more key selectors are specified, the result hash will be nested.
|
44
|
+
#
|
45
|
+
# The value selector, _vsel_, is used for the values of innermost hashes.
|
46
|
+
# By default, all values extracted by _vsel_ from the elements which
|
47
|
+
# key selectors extracts same value are composed as an array.
|
48
|
+
# The array is set to the values of the innermost hashes.
|
49
|
+
# This behavior can be customized by the options: :seed, :op and :update.
|
50
|
+
#
|
51
|
+
# a = [{:fruit => "banana", :color => "yellow", :taste => "sweet", :price => 100},
|
52
|
+
# {:fruit => "melon", :color => "green", :taste => "sweet", :price => 300},
|
53
|
+
# {:fruit => "grapefruit", :color => "yellow", :taste => "tart", :price => 200}]
|
54
|
+
# p a.tb_categorize(:color, :fruit)
|
55
|
+
# #=> {"yellow"=>["banana", "grapefruit"], "green"=>["melon"]}
|
56
|
+
# p a.tb_categorize(:taste, :fruit)
|
57
|
+
# #=> {"sweet"=>["banana", "melon"], "tart"=>["grapefruit"]}
|
58
|
+
# p a.tb_categorize(:taste, :color, :fruit)
|
59
|
+
# #=> {"sweet"=>{"yellow"=>["banana"], "green"=>["melon"]}, "tart"=>{"yellow"=>["grapefruit"]}}
|
60
|
+
# p a.tb_categorize(:taste, :color)
|
61
|
+
# #=> {"sweet"=>["yellow", "green"], "tart"=>["yellow"]}
|
62
|
+
#
|
63
|
+
# In the above example, :fruit, :color and :taste is specified as selectors.
|
64
|
+
# There are several types of selectors as follows:
|
65
|
+
#
|
66
|
+
# - object with +call+ method (procedure, etc.): extracts a value from the element by calling the procedure with the element as an argument.
|
67
|
+
# - array of selectors: make an array which contains the values extracted by the selectors.
|
68
|
+
# - other object: extracts a value from the element using +[]+ method as +element[selector]+.
|
69
|
+
#
|
70
|
+
# So the selector :fruit extracts the value from the element
|
71
|
+
# {:fruit => "banana", :color => "yellow", :taste => "sweet", :price => 100}
|
72
|
+
# as {...}[:fruit].
|
73
|
+
#
|
74
|
+
# p a.tb_categorize(lambda {|elt| elt[:fruit][4] }, :fruit)
|
75
|
+
# #=> {"n"=>["banana", "melon"], "e"=>["grapefruit"]}
|
76
|
+
#
|
77
|
+
# When the key selectors returns same key for two or or more elements,
|
78
|
+
# corresponding values extracted by the value selector are combined.
|
79
|
+
# By default, all values are collected as an array.
|
80
|
+
# :seed, :op and :update option in the option hash customizes this behavior.
|
81
|
+
# :seed option and :op option is similar to Enumerable#inject.
|
82
|
+
# :seed option specifies an initial value.
|
83
|
+
# (If :seed option is not given, the first value for each category is treated as an initial value.)
|
84
|
+
# :op option specifies a procedure to combine a seed and an element into a next seed.
|
85
|
+
# :update option is same as :op option except it takes three arguments instead of two:
|
86
|
+
# keys, seed and element.
|
87
|
+
# +to_proc+ method is used to convert :op and :update option to a procedure.
|
88
|
+
# So a symbol can be used for them.
|
89
|
+
#
|
90
|
+
# # count categorized elements.
|
91
|
+
# p a.tb_categorize(:color, lambda {|e| 1 }, :op=>:+)
|
92
|
+
# #=> {"yellow"=>2, "green"=>1}
|
93
|
+
#
|
94
|
+
# p a.tb_categorize(:color, :fruit, :seed=>"", :op=>:+)
|
95
|
+
# #=> {"yellow"=>"bananagrapefruit", "green"=>"melon"}
|
96
|
+
#
|
97
|
+
# The default behavior, collecting all values as an array, is implemented as follows.
|
98
|
+
# :seed => nil
|
99
|
+
# :update => {|ks, s, v| !s ? [v] : (s << v) }
|
100
|
+
#
|
101
|
+
# :op and :update option are disjoint.
|
102
|
+
# ArgumentError is raised if both are specified.
|
103
|
+
#
|
104
|
+
# The block for +tb_categorize+ method converts combined values to final innermost hash values.
|
105
|
+
#
|
106
|
+
# p a.tb_categorize(:color, :fruit) {|ks, vs| vs.join(",") }
|
107
|
+
# #=> {"yellow"=>"banana,grapefruit", "green"=>"melon"}
|
108
|
+
#
|
109
|
+
# # calculates the average price for fruits of each color.
|
110
|
+
# p a.tb_categorize(:color, :price) {|ks, vs| vs.inject(0.0, &:+) / vs.length }
|
111
|
+
# #=> {"yellow"=>150.0, "green"=>300.0}
|
112
|
+
#
|
113
|
+
def tb_categorize(*args, &reduce_proc)
|
114
|
+
opts = args.last.kind_of?(Hash) ? args.pop : {}
|
115
|
+
if args.length < 2
|
116
|
+
raise ArgumentError, "needs 2 or more arguments without option hash (but #{args.length})"
|
117
|
+
end
|
118
|
+
value_selector = tb_cat_selector_proc(args.pop)
|
119
|
+
key_selectors = args.map {|a| tb_cat_selector_proc(a) }
|
120
|
+
has_seed = opts.include? :seed
|
121
|
+
seed_value = opts[:seed]
|
122
|
+
if opts.include?(:update) && opts.include?(:op)
|
123
|
+
raise ArgumentError, "both :op and :update option specified"
|
124
|
+
elsif opts.include? :update
|
125
|
+
update_proc = opts[:update].to_proc
|
126
|
+
elsif opts.include? :op
|
127
|
+
op_proc = opts[:op].to_proc
|
128
|
+
update_proc = lambda {|ks, s, v| op_proc.call(s, v) }
|
129
|
+
else
|
130
|
+
has_seed = true
|
131
|
+
seed_value = nil
|
132
|
+
update_proc = lambda {|ks, s, v| !s ? [v] : (s << v) }
|
133
|
+
end
|
134
|
+
result = {}
|
135
|
+
each {|*elts|
|
136
|
+
elt = elts.length <= 1 ? elts[0] : elts
|
137
|
+
ks = key_selectors.map {|ksel| ksel.call(elt) }
|
138
|
+
v = value_selector.call(elt)
|
139
|
+
h = result
|
140
|
+
0.upto(ks.length-2) {|i|
|
141
|
+
k = ks[i]
|
142
|
+
h[k] = {} if !h.include?(k)
|
143
|
+
h = h[k]
|
144
|
+
}
|
145
|
+
lastk = ks.last
|
146
|
+
if !h.include?(lastk)
|
147
|
+
if has_seed
|
148
|
+
h[lastk] = update_proc.call(ks, seed_value, v)
|
149
|
+
else
|
150
|
+
h[lastk] = v
|
151
|
+
end
|
152
|
+
else
|
153
|
+
h[lastk] = update_proc.call(ks, h[lastk], v)
|
154
|
+
end
|
155
|
+
}
|
156
|
+
if reduce_proc
|
157
|
+
tb_cat_reduce(result, [], key_selectors.length-1, reduce_proc)
|
158
|
+
end
|
159
|
+
result
|
160
|
+
end
|
161
|
+
|
162
|
+
def tb_cat_selector_proc(selector)
|
163
|
+
if selector.respond_to?(:call)
|
164
|
+
selector
|
165
|
+
elsif selector.respond_to? :to_ary
|
166
|
+
selector_procs = selector.to_ary.map {|sel| tb_cat_selector_proc(sel) }
|
167
|
+
lambda {|elt| selector_procs.map {|selproc| selproc.call(elt) } }
|
168
|
+
else
|
169
|
+
lambda {|elt| elt[selector] }
|
170
|
+
end
|
171
|
+
end
|
172
|
+
private :tb_cat_selector_proc
|
173
|
+
|
174
|
+
def tb_cat_reduce(hash, ks, nestlevel, reduce_proc)
|
175
|
+
if nestlevel.zero?
|
176
|
+
hash.each {|k, v|
|
177
|
+
ks << k
|
178
|
+
begin
|
179
|
+
hash[k] = reduce_proc.call(ks.dup, v)
|
180
|
+
ensure
|
181
|
+
ks.pop
|
182
|
+
end
|
183
|
+
}
|
184
|
+
else
|
185
|
+
hash.each {|k, h|
|
186
|
+
ks << k
|
187
|
+
begin
|
188
|
+
tb_cat_reduce(h, ks, nestlevel-1, reduce_proc)
|
189
|
+
ensure
|
190
|
+
ks.pop
|
191
|
+
end
|
192
|
+
}
|
193
|
+
end
|
194
|
+
end
|
195
|
+
private :tb_cat_reduce
|
196
|
+
|
197
|
+
# :call-seq:
|
198
|
+
# enum.tb_unique_categorize(ksel1, ksel2, ..., vsel, [opts]) -> hash
|
199
|
+
# enum.tb_unique_categorize(ksel1, ksel2, ..., vsel, [opts]) {|s, v| ... } -> hash
|
200
|
+
#
|
201
|
+
# categorizes the elements in _enum_ and returns a hash.
|
202
|
+
# This method assumes one element for a category by default.
|
203
|
+
#
|
204
|
+
# +tb_unique_categorize+ takes one or more key selectors,
|
205
|
+
# one value selector and
|
206
|
+
# an optional option hash.
|
207
|
+
# It also takes an optional block.
|
208
|
+
#
|
209
|
+
# The selectors specify how to extract a value from an element in _enum_.
|
210
|
+
# See Enumerable#tb_categorize for details of selectors.
|
211
|
+
#
|
212
|
+
# The key selectors, _kselN_, are used to extract hash keys from an element.
|
213
|
+
# If two or more key selectors are specified, the result hash will be nested.
|
214
|
+
#
|
215
|
+
# The value selector, _vsel_, is used for the values of innermost hashes.
|
216
|
+
# By default, this method assumes the key selectors categorizes elements in enum uniquely.
|
217
|
+
# If the key selectors generates same keys for two or more elements, ArgumentError is raised.
|
218
|
+
# This behavior can be customized by :seed option and the block.
|
219
|
+
#
|
220
|
+
# a = [{:fruit => "banana", :color => "yellow", :taste => "sweet", :price => 100},
|
221
|
+
# {:fruit => "melon", :color => "green", :taste => "sweet", :price => 300},
|
222
|
+
# {:fruit => "grapefruit", :color => "yellow", :taste => "tart", :price => 200}]
|
223
|
+
# p a.tb_unique_categorize(:fruit, :price)
|
224
|
+
# #=> {"banana"=>100, "melon"=>300, "grapefruit"=>200}
|
225
|
+
#
|
226
|
+
# p a.tb_unique_categorize(:color, :price)
|
227
|
+
# # ArgumentError
|
228
|
+
#
|
229
|
+
# If the block is given, it is used for combining values in a category.
|
230
|
+
# The arguments for the block is a seed and the value extracted by _vsel_.
|
231
|
+
# The return value of the block is used as the next seed.
|
232
|
+
# :seed option specifies the initial seed.
|
233
|
+
# If :seed is not given, the first value for each category is used for the seed.
|
234
|
+
#
|
235
|
+
# p a.tb_unique_categorize(:taste, :price) {|s, v| s + v }
|
236
|
+
# #=> {"sweet"=>400, "tart"=>200}
|
237
|
+
#
|
238
|
+
# p a.tb_unique_categorize(:color, :price) {|s, v| s + v }
|
239
|
+
# #=> {"yellow"=>300, "green"=>300}
|
240
|
+
#
|
241
|
+
def tb_unique_categorize(*args, &update_proc)
|
242
|
+
opts = args.last.kind_of?(Hash) ? args.pop.dup : {}
|
243
|
+
if update_proc
|
244
|
+
opts[:update] = lambda {|ks, s, v| update_proc.call(s, v) }
|
245
|
+
else
|
246
|
+
seed = Object.new
|
247
|
+
opts[:seed] = seed
|
248
|
+
opts[:update] = lambda {|ks, s, v|
|
249
|
+
if s.equal? seed
|
250
|
+
v
|
251
|
+
else
|
252
|
+
raise ArgumentError, "ambiguous key: #{ks.map {|k| k.inspect }.join(',')}"
|
253
|
+
end
|
254
|
+
}
|
255
|
+
end
|
256
|
+
tb_categorize(*(args + [opts]))
|
257
|
+
end
|
258
|
+
|
259
|
+
# :call-seq:
|
260
|
+
# enum.tb_category_count(ksel1, ksel2, ...)
|
261
|
+
#
|
262
|
+
# counts elements in _enum_ for each category defined by the key selectors.
|
263
|
+
#
|
264
|
+
# a = [{:fruit => "banana", :color => "yellow", :taste => "sweet", :price => 100},
|
265
|
+
# {:fruit => "melon", :color => "green", :taste => "sweet", :price => 300},
|
266
|
+
# {:fruit => "grapefruit", :color => "yellow", :taste => "tart", :price => 200}]
|
267
|
+
#
|
268
|
+
# p a.tb_category_count(:color)
|
269
|
+
# #=> {"yellow"=>2, "green"=>1}
|
270
|
+
#
|
271
|
+
# p a.tb_category_count(:taste)
|
272
|
+
# #=> {"sweet"=>2, "tart"=>1}
|
273
|
+
#
|
274
|
+
# p a.tb_category_count(:taste, :color)
|
275
|
+
# #=> {"sweet"=>{"yellow"=>1, "green"=>1}, "tart"=>{"yellow"=>1}}
|
276
|
+
#
|
277
|
+
# The selectors specify how to extract a value from an element in _enum_.
|
278
|
+
# See Enumerable#tb_categorize for details of selectors.
|
279
|
+
#
|
280
|
+
def tb_category_count(*args)
|
281
|
+
tb_categorize(*(args + [lambda {|e| 1 }, {:update => lambda {|ks, s, v| s + v }}]))
|
282
|
+
end
|
283
|
+
|
284
|
+
end
|
data/lib/tb/fieldset.rb
ADDED
@@ -0,0 +1,96 @@
|
|
1
|
+
# lib/tb/fieldset.rb - Tb::FieldSet class
|
2
|
+
#
|
3
|
+
# Copyright (C) 2011 Tanaka Akira <akr@fsij.org>
|
4
|
+
#
|
5
|
+
# Redistribution and use in source and binary forms, with or without
|
6
|
+
# modification, are permitted provided that the following conditions are met:
|
7
|
+
#
|
8
|
+
# 1. Redistributions of source code must retain the above copyright notice, this
|
9
|
+
# list of conditions and the following disclaimer.
|
10
|
+
# 2. Redistributions in binary form must reproduce the above copyright notice,
|
11
|
+
# this list of conditions and the following disclaimer in the documentation
|
12
|
+
# and/or other materials provided with the distribution.
|
13
|
+
# 3. The name of the author may not be used to endorse or promote products
|
14
|
+
# derived from this software without specific prior written permission.
|
15
|
+
#
|
16
|
+
# THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED
|
17
|
+
# WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
|
18
|
+
# MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO
|
19
|
+
# EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
|
20
|
+
# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT
|
21
|
+
# OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
22
|
+
# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
|
23
|
+
# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
|
24
|
+
# IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY
|
25
|
+
# OF SUCH DAMAGE.
|
26
|
+
|
27
|
+
class Tb::FieldSet
|
28
|
+
def initialize(*fs)
|
29
|
+
@header = []
|
30
|
+
add_fields(*fs) if !fs.empty?
|
31
|
+
end
|
32
|
+
attr_reader :header
|
33
|
+
|
34
|
+
def index_from_field(f)
|
35
|
+
i = self.header.index(f)
|
36
|
+
if i.nil?
|
37
|
+
raise ArgumentError, "unexpected field name: #{f.inspect}"
|
38
|
+
end
|
39
|
+
i
|
40
|
+
end
|
41
|
+
|
42
|
+
def field_from_index_ex(i)
|
43
|
+
if self.length <= i
|
44
|
+
fs2 = extend_length(i+1)
|
45
|
+
fs2.last
|
46
|
+
else
|
47
|
+
field_from_index(i)
|
48
|
+
end
|
49
|
+
end
|
50
|
+
|
51
|
+
def field_from_index(i)
|
52
|
+
raise ArgumentError, "negative index: #{i}" if i < 0
|
53
|
+
f = self.header[i]
|
54
|
+
if f.nil?
|
55
|
+
raise ArgumentError, "index too big: #{i}"
|
56
|
+
end
|
57
|
+
f
|
58
|
+
end
|
59
|
+
|
60
|
+
def length
|
61
|
+
@header.length
|
62
|
+
end
|
63
|
+
|
64
|
+
def extend_length(len)
|
65
|
+
fs = [""] * (len - self.length)
|
66
|
+
add_fields(*fs)
|
67
|
+
end
|
68
|
+
|
69
|
+
def add_fields(*fs)
|
70
|
+
h = {}
|
71
|
+
max = {}
|
72
|
+
@header.each {|f|
|
73
|
+
h[f] = true
|
74
|
+
if /\((\d+)\)\z/ =~ f
|
75
|
+
prefix = $`
|
76
|
+
n = $1.to_i
|
77
|
+
max[prefix] = n if !max[prefix] || max[prefix] < n
|
78
|
+
end
|
79
|
+
}
|
80
|
+
fs2 = []
|
81
|
+
fs.each {|f|
|
82
|
+
f ||= ''
|
83
|
+
if !h[f]
|
84
|
+
f2 = f
|
85
|
+
else
|
86
|
+
max[f] = 1 if !max[f]
|
87
|
+
max[f] += 1
|
88
|
+
f2 = "#{f}(#{max[f]})"
|
89
|
+
end
|
90
|
+
fs2 << f2
|
91
|
+
h[f2] = true
|
92
|
+
}
|
93
|
+
@header.concat fs2
|
94
|
+
fs2
|
95
|
+
end
|
96
|
+
end
|