csv-mapper 0.0.1
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 +4 -0
- data/Manifest.txt +15 -0
- data/README.rdoc +82 -0
- data/Rakefile +28 -0
- data/lib/csv-mapper.rb +294 -0
- data/script/console +10 -0
- data/script/destroy +14 -0
- data/script/generate +14 -0
- data/spec/csv-mapper_attribute_map_spec.rb +50 -0
- data/spec/csv-mapper_row_map_spec.rb +121 -0
- data/spec/csv-mapper_spec.rb +54 -0
- data/spec/spec.opts +1 -0
- data/spec/spec_helper.rb +10 -0
- data/spec/test.csv +4 -0
- data/tasks/rspec.rake +21 -0
- metadata +100 -0
data/History.txt
ADDED
data/Manifest.txt
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
History.txt
|
2
|
+
Manifest.txt
|
3
|
+
README.rdoc
|
4
|
+
Rakefile
|
5
|
+
lib/csv-mapper.rb
|
6
|
+
script/console
|
7
|
+
script/destroy
|
8
|
+
script/generate
|
9
|
+
spec/csv-mapper_spec.rb
|
10
|
+
spec/csv-mapper_row_map_spec.rb
|
11
|
+
spec/csv-mapper_attribute_map_spec.rb
|
12
|
+
spec/test.csv
|
13
|
+
spec/spec.opts
|
14
|
+
spec/spec_helper.rb
|
15
|
+
tasks/rspec.rake
|
data/README.rdoc
ADDED
@@ -0,0 +1,82 @@
|
|
1
|
+
= README
|
2
|
+
|
3
|
+
by Luke Pillow
|
4
|
+
|
5
|
+
== DESCRIPTION:
|
6
|
+
|
7
|
+
CsvMapper is a small library intended to simplify the common steps involved with importing CSV files to a usable form in Ruby.
|
8
|
+
|
9
|
+
== EXAMPLES:
|
10
|
+
|
11
|
+
The following example will import a CSV file to an Array of OpenStruct[http://ruby-doc.org/core/classes/OpenStruct.html] instances.
|
12
|
+
|
13
|
+
==== Example CSV File Structure
|
14
|
+
|
15
|
+
First Name,Last Name,Age
|
16
|
+
John,Doe,27
|
17
|
+
Jane,Doe,26
|
18
|
+
Bat,Man,52
|
19
|
+
...etc...
|
20
|
+
|
21
|
+
==== Simple Usage Example
|
22
|
+
include CsvMapper
|
23
|
+
|
24
|
+
results = import('/path/to/file.csv') do
|
25
|
+
start_at_row 1
|
26
|
+
[first_name, last_name, age]
|
27
|
+
end
|
28
|
+
|
29
|
+
results.first.first_name # John
|
30
|
+
results.first.last_name # Doe
|
31
|
+
results.first.age # 27
|
32
|
+
|
33
|
+
==== Import to ActiveRecord Example
|
34
|
+
Although CsvMapper has no dependency on ActiveRecord; it's easy to import a CSV file to ActiveRecord models and save them.
|
35
|
+
|
36
|
+
# Define an ActiveRecord model
|
37
|
+
class Person < ActiveRecord::Base; end
|
38
|
+
|
39
|
+
include CsvMapper
|
40
|
+
|
41
|
+
results = import('/path/to/file.csv') do
|
42
|
+
map_to Person # Map to the Person ActiveRecord class (defined above) instead of the default OpenStruct.
|
43
|
+
after_row lambda{|row, person| person.save } # Call this lambda and save each record after it's parsed.
|
44
|
+
|
45
|
+
start_at_row 1
|
46
|
+
[first_name, last_name, age]
|
47
|
+
end
|
48
|
+
|
49
|
+
See CsvMapper for a more detailed description
|
50
|
+
|
51
|
+
== REQUIREMENTS:
|
52
|
+
|
53
|
+
FasterCSV[http://fastercsv.rubyforge.org/]
|
54
|
+
|
55
|
+
== INSTALL:
|
56
|
+
|
57
|
+
* sudo gem install csv-mapper
|
58
|
+
|
59
|
+
== LICENSE:
|
60
|
+
|
61
|
+
(The MIT License)
|
62
|
+
|
63
|
+
Copyright (c) 2008 Luke Pillow
|
64
|
+
|
65
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
66
|
+
a copy of this software and associated documentation files (the
|
67
|
+
'Software'), to deal in the Software without restriction, including
|
68
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
69
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
70
|
+
permit persons to whom the Software is furnished to do so, subject to
|
71
|
+
the following conditions:
|
72
|
+
|
73
|
+
The above copyright notice and this permission notice shall be
|
74
|
+
included in all copies or substantial portions of the Software.
|
75
|
+
|
76
|
+
THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND,
|
77
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
78
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
|
79
|
+
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
|
80
|
+
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
|
81
|
+
TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
|
82
|
+
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/Rakefile
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
%w[rubygems rake rake/clean fileutils newgem rubigen].each { |f| require f }
|
2
|
+
require File.dirname(__FILE__) + '/lib/csv-mapper'
|
3
|
+
|
4
|
+
# Generate all the Rake tasks
|
5
|
+
# Run 'rake -T' to see list of generated tasks (from gem root directory)
|
6
|
+
$hoe = Hoe.new('csv-mapper', CsvMapper::VERSION) do |p|
|
7
|
+
p.developer('Luke Pillow', 'lpillow@gmail.com')
|
8
|
+
p.changes = p.paragraphs_of("History.txt", 0..1).join("\n\n")
|
9
|
+
# p.post_install_message = 'PostInstall.txt' # TODO remove if post-install message not required
|
10
|
+
p.rubyforge_name = p.name # TODO this is default value
|
11
|
+
p.extra_deps = [
|
12
|
+
['fastercsv','>= 1.4.0'],
|
13
|
+
]
|
14
|
+
p.extra_dev_deps = [
|
15
|
+
['newgem', ">= #{::Newgem::VERSION}"]
|
16
|
+
]
|
17
|
+
|
18
|
+
p.clean_globs |= %w[**/.DS_Store tmp *.log]
|
19
|
+
path = (p.rubyforge_name == p.name) ? p.rubyforge_name : "\#{p.rubyforge_name}/\#{p.name}"
|
20
|
+
p.remote_rdoc_dir = File.join(path.gsub(/^#{p.rubyforge_name}\/?/,''), 'rdoc')
|
21
|
+
p.rsync_args = '-av --delete --ignore-errors'
|
22
|
+
end
|
23
|
+
|
24
|
+
require 'newgem/tasks' # load /tasks/*.rake
|
25
|
+
Dir['tasks/**/*.rake'].each { |t| load t }
|
26
|
+
|
27
|
+
# TODO - want other tests/tasks run by default? Add them to the list
|
28
|
+
# task :default => [:spec, :features]
|
data/lib/csv-mapper.rb
ADDED
@@ -0,0 +1,294 @@
|
|
1
|
+
$:.unshift(File.dirname(__FILE__)) unless
|
2
|
+
$:.include?(File.dirname(__FILE__)) || $:.include?(File.expand_path(File.dirname(__FILE__)))
|
3
|
+
|
4
|
+
require 'ostruct'
|
5
|
+
require 'fastercsv'
|
6
|
+
|
7
|
+
# This module provides the main interface for importing CSV files & data to mapped Ruby objects.
|
8
|
+
# = Usage
|
9
|
+
# Including CsvMapper will provide two methods:
|
10
|
+
# - +import+
|
11
|
+
# - +map_csv+
|
12
|
+
#
|
13
|
+
# See csv-mapper.rb[link:files/lib/csv-mapper_rb.html] for method docs.
|
14
|
+
#
|
15
|
+
# === Import From File
|
16
|
+
# results = import('/path/to/file.csv') do
|
17
|
+
# # declare mapping here
|
18
|
+
# end
|
19
|
+
#
|
20
|
+
# === Import From String or IO
|
21
|
+
# results = import(csv_data, :type => :io) do
|
22
|
+
# # declare mapping here
|
23
|
+
# end
|
24
|
+
#
|
25
|
+
# === Mapping
|
26
|
+
# Mappings are built inside blocks. All three of CsvMapper's main API methods accept a block containing a mapping.
|
27
|
+
# Maps are defined by using +map_to+, +start_at_row+, +before_row+, and +after_row+ (methods on CsvMapper::RowMap) and
|
28
|
+
# by defining your own mapping attributes.
|
29
|
+
# A mapping block uses an internal cursor to keep track of the order the mapping attributes are declared and use that order to
|
30
|
+
# know the corresponding CSV column index to associate with the attribute.
|
31
|
+
#
|
32
|
+
# ===== The Basics
|
33
|
+
# * +map_to+ - Override the default OpenStruct target. Accepts a class and an optional hash of default attribute names and values.
|
34
|
+
# * +start_at_row+ - Specify what row to begin parsing at. Use this to skip headers.
|
35
|
+
# * +before_row+ - Accepts an Array of method name symbols or lambdas to be invoked before parsing each row.
|
36
|
+
# * +after_row+ - Accepts an Array of method name symbols or lambdas to be invoked after parsing each row.
|
37
|
+
# * +delimited_by+ - Accepts a character to be used to delimit columns. Use this to specify pipe-delimited files.
|
38
|
+
# * <tt>\_SKIP_</tt> - Use as a placehold to skip a CSV column index.
|
39
|
+
# * +parser_options+ - Accepts a hash of FasterCSV options. Can be anything FasterCSV::new()[http://fastercsv.rubyforge.org/classes/FasterCSV.html#M000018] understands
|
40
|
+
#
|
41
|
+
# ===== Attribute Mappings
|
42
|
+
# Attribute mappings are created by using the name of the attribute to be mapped to.
|
43
|
+
# The order in which attribute mappings are declared determines the index of the corresponding CSV row.
|
44
|
+
# All mappings begin at the 0th index of the CSV row.
|
45
|
+
# foo # maps the 0th CSV row position value to the value of the 'foo' attribute on the target object.
|
46
|
+
# bar # maps the 1st row position to 'bar'
|
47
|
+
# This could also be a nice one liner for easy CSV format conversion
|
48
|
+
# [foo, bar] # creates the same attribute maps as above.
|
49
|
+
# The mapping index may be specifically declared in two additional ways:
|
50
|
+
# foo(2) # maps the 2nd CSV row position value to 'foo' and moves the cursor to 3
|
51
|
+
# bar # maps the 3rd CSV row position to 'bar' due to the current cursor position
|
52
|
+
# baz.at(0) # maps the 0th CSV row position to 'baz' but only increments the cursor 1 position to 4
|
53
|
+
# Each attribute mapping may be configured to parse the record using a lambda or a method name
|
54
|
+
# foo.map lambda{|row| row[2].strip } # maps the 2nd row position value with leading and trailing whitespace removed to 'foo'.
|
55
|
+
# bar.map :clean_bar # maps the result of the clean_bar method to 'bar'. clean_bar must accept the row as a parameter.
|
56
|
+
# Attribute mapping declarations and "modifiers" may be chained
|
57
|
+
# foo.at(4).map :some_transform
|
58
|
+
#
|
59
|
+
# === Create Reusable Mappings
|
60
|
+
# Both +import_csv+ and +import_string+ accept an instance of RowMap as an optional mapping parameter.
|
61
|
+
# The easiest way to create an instance of a RowMap is by using +map_csv+.
|
62
|
+
# a_row_map = map_csv do
|
63
|
+
# # declare mapping here
|
64
|
+
# end
|
65
|
+
# Then you can reuse the mapping
|
66
|
+
# results = import(some_string, :type => :io, :map => a_row_map)
|
67
|
+
# other_results = import('/path/to/file.csv', :map => a_row_map)
|
68
|
+
#
|
69
|
+
module CsvMapper
|
70
|
+
VERSION = '0.0.1'
|
71
|
+
|
72
|
+
# Create a new RowMap instance from the definition in the given block.
|
73
|
+
def map_csv(&map_block)
|
74
|
+
CsvMapper::RowMap.new(self, &map_block)
|
75
|
+
end
|
76
|
+
|
77
|
+
# Load CSV data and map the values according to the definition in the given block.
|
78
|
+
# Accepts either a file path, String, or IO as +data+. Defaults to file path.
|
79
|
+
#
|
80
|
+
# The following +options+ may be used:
|
81
|
+
# <tt>:type</tt>:: defaults to <tt>:file_path</tt>. Use <tt>:io</tt> to specify data as String or IO.
|
82
|
+
# <tt>:map</tt>:: Specify an instance of a RowMap to take presidence over a given block defintion.
|
83
|
+
#
|
84
|
+
def import(data, options={}, &map_block)
|
85
|
+
config = { :type => :file_path,
|
86
|
+
:map => map_csv(&map_block) }.merge!(options)
|
87
|
+
|
88
|
+
csv_data = config[:type] == :io ? data : File.new(data, 'r')
|
89
|
+
map = config[:map]
|
90
|
+
|
91
|
+
results = []
|
92
|
+
FasterCSV.new(csv_data, map.parser_options ).each_with_index do |row, i|
|
93
|
+
results << map.parse(row) if i >= map.start_at_row
|
94
|
+
end
|
95
|
+
|
96
|
+
results
|
97
|
+
end
|
98
|
+
|
99
|
+
# CsvMapper::RowMap provides a simple, DSL-like interface for constructing mappings.
|
100
|
+
# A CsvMapper::RowMap provides the main functionality of the library. It will mostly be used indirectly through the CsvMapper API,
|
101
|
+
# but may be useful to use directly for the dynamic CSV mappings.
|
102
|
+
class RowMap
|
103
|
+
#Start with a 'blank slate'
|
104
|
+
instance_methods.each { |m| undef_method m unless m =~ /^__||instance_eval/ }
|
105
|
+
|
106
|
+
attr_reader :mapped_attributes
|
107
|
+
|
108
|
+
# Create a new instance with access to an evaluation context
|
109
|
+
def initialize(context, &map_block)
|
110
|
+
@context = context
|
111
|
+
@before_filters = []
|
112
|
+
@after_filters = []
|
113
|
+
@parser_options = {}
|
114
|
+
@start_at_row = 0
|
115
|
+
@delimited_by = FasterCSV::DEFAULT_OPTIONS[:col_sep]
|
116
|
+
@mapped_attributes = []
|
117
|
+
|
118
|
+
self.instance_eval(&map_block) if block_given?
|
119
|
+
end
|
120
|
+
|
121
|
+
# Each row of a CSV is parsed and mapped to a new instance of a Ruby class; OpenStruct by default.
|
122
|
+
# Use this method to change the what class each row is mapped to.
|
123
|
+
# The given class must respond to a parameter-less #new and all attribute mappings defined.
|
124
|
+
# Providing a hash of defaults will ensure that each resulting object will have the providing name and attribute values
|
125
|
+
# unless overridden by a mapping
|
126
|
+
def map_to(klass, defaults={})
|
127
|
+
@map_to_klass = klass
|
128
|
+
|
129
|
+
defaults.each do |name, value|
|
130
|
+
self.add_attribute(name, -99).map lambda{|row| value}
|
131
|
+
end
|
132
|
+
end
|
133
|
+
|
134
|
+
# Specify a hash of FasterCSV options to be used for CSV parsing
|
135
|
+
#
|
136
|
+
# Can be anything FasterCSV::new()[http://fastercsv.rubyforge.org/classes/FasterCSV.html#M000018] accepts
|
137
|
+
def parser_options(opts=nil)
|
138
|
+
@parser_options = opts if opts
|
139
|
+
@parser_options.merge :col_sep => @delimited_by
|
140
|
+
end
|
141
|
+
|
142
|
+
# Convenience method to 'move' the cursor skipping the current index.
|
143
|
+
def _SKIP_
|
144
|
+
self.move_cursor
|
145
|
+
end
|
146
|
+
|
147
|
+
# Specify the CSV column delimiter. Defaults to comma.
|
148
|
+
def delimited_by(delimiter=nil)
|
149
|
+
@delimited_by = delimiter if delimiter
|
150
|
+
@delimited_by
|
151
|
+
end
|
152
|
+
|
153
|
+
# Declare what row to begin parsing the CSV.
|
154
|
+
# This is useful for skipping headers and such.
|
155
|
+
def start_at_row(row_number=nil)
|
156
|
+
@start_at_row = row_number if row_number
|
157
|
+
@start_at_row
|
158
|
+
end
|
159
|
+
|
160
|
+
# Declare method name symbols and/or lambdas to be executed before each row.
|
161
|
+
# Each method or lambda must accept to parameters: +csv_row+, +target_object+
|
162
|
+
# Methods names should refer to methods available within the RowMap's provided context
|
163
|
+
def before_row(*befores)
|
164
|
+
self.add_filters(@before_filters, *befores)
|
165
|
+
end
|
166
|
+
|
167
|
+
# Declare method name symbols and/or lambdas to be executed before each row.
|
168
|
+
# Each method or lambda must accept to parameters: +csv_row+, +target_object+
|
169
|
+
# Methods names should refer to methods available within the RowMap's provided context
|
170
|
+
def after_row(*afters)
|
171
|
+
self.add_filters(@after_filters, *afters)
|
172
|
+
end
|
173
|
+
|
174
|
+
# Add a new attribute to this map. Mostly used internally, but is useful for dynamic map creation.
|
175
|
+
# returns the newly created CsvMapper::AttributeMap
|
176
|
+
def add_attribute(name, index=nil)
|
177
|
+
attr_mapping = CsvMapper::AttributeMap.new(name.to_sym, index, @context)
|
178
|
+
self.mapped_attributes << attr_mapping
|
179
|
+
attr_mapping
|
180
|
+
end
|
181
|
+
|
182
|
+
# The current cursor location
|
183
|
+
def cursor # :nodoc:
|
184
|
+
@cursor ||= 0
|
185
|
+
end
|
186
|
+
|
187
|
+
# Move the cursor relative to it's current position
|
188
|
+
def move_cursor(positions=1) # :nodoc:
|
189
|
+
self.cursor += positions
|
190
|
+
end
|
191
|
+
|
192
|
+
# Given a CSV row return an instance of an object defined by this mapping
|
193
|
+
def parse(csv_row)
|
194
|
+
target = self.map_to_class.new
|
195
|
+
@before_filters.each {|filter| filter.call(csv_row, target) }
|
196
|
+
|
197
|
+
self.mapped_attributes.inject(target) do |result, attr_map|
|
198
|
+
result.send("#{attr_map.name}=".to_sym, attr_map.parse(csv_row))
|
199
|
+
result
|
200
|
+
end
|
201
|
+
|
202
|
+
@after_filters.each {|filter| filter.call(csv_row, target) }
|
203
|
+
|
204
|
+
return target
|
205
|
+
end
|
206
|
+
|
207
|
+
protected # :nodoc:
|
208
|
+
|
209
|
+
# The Hacktastic "magic"
|
210
|
+
# Used to dynamically create CsvMapper::AttributeMaps based on unknown method calls that
|
211
|
+
# should represent the names of mapped attributes.
|
212
|
+
#
|
213
|
+
# An optional first argument is used to move this maps cursor position and as the index of the
|
214
|
+
# new AttributeMap
|
215
|
+
def method_missing(name, *args) # :nodoc:
|
216
|
+
|
217
|
+
if index = args[0]
|
218
|
+
self.move_cursor(index - self.cursor)
|
219
|
+
else
|
220
|
+
index = self.cursor
|
221
|
+
self.move_cursor
|
222
|
+
end
|
223
|
+
|
224
|
+
add_attribute(name, index)
|
225
|
+
end
|
226
|
+
|
227
|
+
def add_filters(to_hook, *filters) # :nodoc:
|
228
|
+
(to_hook << filters.collect do |filter|
|
229
|
+
filter.is_a?(Symbol) ? lambda{|row, target| @context.send(filter, row, target)} : filter
|
230
|
+
end).flatten!
|
231
|
+
end
|
232
|
+
|
233
|
+
def map_to_class # :nodoc:
|
234
|
+
@map_to_klass || OpenStruct
|
235
|
+
end
|
236
|
+
|
237
|
+
def cursor=(value) # :nodoc:
|
238
|
+
@cursor=value
|
239
|
+
end
|
240
|
+
|
241
|
+
|
242
|
+
end
|
243
|
+
|
244
|
+
# A CsvMapper::AttributeMap contains the instructions to parse a value from a CSV row and to know the
|
245
|
+
# name of the attribute it is targeting.
|
246
|
+
class AttributeMap
|
247
|
+
attr_reader :name, :index
|
248
|
+
|
249
|
+
# Creates a new instance using the provided attribute +name+, CSV row +index+, and evaluation +map_context+
|
250
|
+
def initialize(name, index, map_context)
|
251
|
+
@name, @index, @map_context = name, index, map_context
|
252
|
+
end
|
253
|
+
|
254
|
+
# Set the index that this map is targeting.
|
255
|
+
#
|
256
|
+
# Returns this AttributeMap for chainability
|
257
|
+
def at(index)
|
258
|
+
@index = index
|
259
|
+
self
|
260
|
+
end
|
261
|
+
|
262
|
+
# Provide a lambda or the symbol name of a method on this map's evaluation context to be used when parsing
|
263
|
+
# the value from a CSV row.
|
264
|
+
# Both the lambda or the method provided should accept a single +row+ parameter
|
265
|
+
#
|
266
|
+
# Returns this AttributeMap for chainability
|
267
|
+
def map(transform)
|
268
|
+
@transformer = transform
|
269
|
+
self
|
270
|
+
end
|
271
|
+
|
272
|
+
# Given a CSV row, return the value at this AttributeMap's index using any provided map transforms (see map)
|
273
|
+
def parse(csv_row)
|
274
|
+
@transformer ? parse_transform(csv_row) : csv_row[self.index]
|
275
|
+
end
|
276
|
+
|
277
|
+
# Access the raw value of the CSV row without any map transforms applied.
|
278
|
+
def raw_value(csv_row)
|
279
|
+
csv_row[self.index]
|
280
|
+
end
|
281
|
+
|
282
|
+
private
|
283
|
+
|
284
|
+
def parse_transform(csv_row)
|
285
|
+
if @transformer.is_a? Symbol
|
286
|
+
transform_name = @transformer
|
287
|
+
@transformer = lambda{|row| @map_context.send(transform_name, row) }
|
288
|
+
end
|
289
|
+
|
290
|
+
@transformer.call(csv_row)
|
291
|
+
end
|
292
|
+
|
293
|
+
end
|
294
|
+
end
|
data/script/console
ADDED
@@ -0,0 +1,10 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
# File: script/console
|
3
|
+
irb = RUBY_PLATFORM =~ /(:?mswin|mingw)/ ? 'irb.bat' : 'irb'
|
4
|
+
|
5
|
+
libs = " -r irb/completion"
|
6
|
+
# Perhaps use a console_lib to store any extra methods I may want available in the cosole
|
7
|
+
# libs << " -r #{File.dirname(__FILE__) + '/../lib/console_lib/console_logger.rb'}"
|
8
|
+
libs << " -r #{File.dirname(__FILE__) + '/../lib/csv-mapper.rb'}"
|
9
|
+
puts "Loading csv-mapper gem"
|
10
|
+
exec "#{irb} #{libs} --simple-prompt"
|
data/script/destroy
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
APP_ROOT = File.expand_path(File.join(File.dirname(__FILE__), '..'))
|
3
|
+
|
4
|
+
begin
|
5
|
+
require 'rubigen'
|
6
|
+
rescue LoadError
|
7
|
+
require 'rubygems'
|
8
|
+
require 'rubigen'
|
9
|
+
end
|
10
|
+
require 'rubigen/scripts/destroy'
|
11
|
+
|
12
|
+
ARGV.shift if ['--help', '-h'].include?(ARGV[0])
|
13
|
+
RubiGen::Base.use_component_sources! [:rubygems, :newgem, :newgem_theme, :test_unit]
|
14
|
+
RubiGen::Scripts::Destroy.new.run(ARGV)
|
data/script/generate
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
APP_ROOT = File.expand_path(File.join(File.dirname(__FILE__), '..'))
|
3
|
+
|
4
|
+
begin
|
5
|
+
require 'rubigen'
|
6
|
+
rescue LoadError
|
7
|
+
require 'rubygems'
|
8
|
+
require 'rubigen'
|
9
|
+
end
|
10
|
+
require 'rubigen/scripts/generate'
|
11
|
+
|
12
|
+
ARGV.shift if ['--help', '-h'].include?(ARGV[0])
|
13
|
+
RubiGen::Base.use_component_sources! [:rubygems, :newgem, :newgem_theme, :test_unit]
|
14
|
+
RubiGen::Scripts::Generate.new.run(ARGV)
|
@@ -0,0 +1,50 @@
|
|
1
|
+
require File.dirname(__FILE__) + '/spec_helper.rb'
|
2
|
+
|
3
|
+
describe CsvMapper::AttributeMap do
|
4
|
+
|
5
|
+
class TestContext
|
6
|
+
def transform_it(row)
|
7
|
+
:transform_it_success
|
8
|
+
end
|
9
|
+
end
|
10
|
+
|
11
|
+
before(:each) do
|
12
|
+
@row_attr = CsvMapper::AttributeMap.new('foo', 1, TestContext.new)
|
13
|
+
@csv_row = ['first_name', 'last_name']
|
14
|
+
end
|
15
|
+
|
16
|
+
it "should map a destination attribute name" do
|
17
|
+
@row_attr.name.should == 'foo'
|
18
|
+
end
|
19
|
+
|
20
|
+
it "should map a CSV column index" do
|
21
|
+
@row_attr.index.should be(1)
|
22
|
+
end
|
23
|
+
|
24
|
+
it "should map a transformation between the CSV value and destination value and chain method calls" do
|
25
|
+
@row_attr.map(:named_transform).should be(@row_attr)
|
26
|
+
end
|
27
|
+
|
28
|
+
it "should provide ability to set the index and chain method calls" do
|
29
|
+
@row_attr.at(9).should be(@row_attr)
|
30
|
+
@row_attr.index.should be(9)
|
31
|
+
end
|
32
|
+
|
33
|
+
it "should parse values" do
|
34
|
+
@row_attr.parse(@csv_row).should == @csv_row[1]
|
35
|
+
end
|
36
|
+
|
37
|
+
it "should parse values using mapped transformer" do
|
38
|
+
@row_attr.map( lambda{|row| :success } )
|
39
|
+
@row_attr.parse(@csv_row).should == :success
|
40
|
+
end
|
41
|
+
|
42
|
+
it "should parse values using a named method on the context" do
|
43
|
+
@row_attr.map(:transform_it).parse(@csv_row).should == :transform_it_success
|
44
|
+
end
|
45
|
+
|
46
|
+
it "should provide access to the raw value" do
|
47
|
+
@row_attr.raw_value(@csv_row).should be(@csv_row[@row_attr.index])
|
48
|
+
end
|
49
|
+
|
50
|
+
end
|
@@ -0,0 +1,121 @@
|
|
1
|
+
require File.dirname(__FILE__) + '/spec_helper.rb'
|
2
|
+
|
3
|
+
describe CsvMapper::RowMap do
|
4
|
+
|
5
|
+
class TestMapToClass
|
6
|
+
attr_accessor :foo, :bar, :baz
|
7
|
+
end
|
8
|
+
|
9
|
+
class TestMapContext
|
10
|
+
def transform(row)
|
11
|
+
:transform_success
|
12
|
+
end
|
13
|
+
|
14
|
+
def change_name(row, target)
|
15
|
+
row[0] = :changed_name
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
before(:each) do
|
20
|
+
@row_map = CsvMapper::RowMap.new(TestMapContext.new)
|
21
|
+
@csv_row = ['first_name', 'last_name']
|
22
|
+
end
|
23
|
+
|
24
|
+
it "should parse a CSV row" do
|
25
|
+
@row_map.parse(@csv_row).should_not be_nil
|
26
|
+
end
|
27
|
+
|
28
|
+
it "should map to a OpenStruct by default" do
|
29
|
+
@row_map.parse(@csv_row).should be_instance_of(OpenStruct)
|
30
|
+
end
|
31
|
+
|
32
|
+
it "should parse a CSV row returning the mapped result" do
|
33
|
+
@row_map.fname
|
34
|
+
@row_map.lname
|
35
|
+
|
36
|
+
result = @row_map.parse(@csv_row)
|
37
|
+
result.fname.should == @csv_row[0]
|
38
|
+
result.lname.should == @csv_row[1]
|
39
|
+
end
|
40
|
+
|
41
|
+
it "should map to a ruby class with optional default attribute values" do
|
42
|
+
@row_map.map_to TestMapToClass, :baz => :default_baz
|
43
|
+
|
44
|
+
@row_map.foo
|
45
|
+
@row_map.bar
|
46
|
+
|
47
|
+
(result = @row_map.parse(@csv_row)).should be_instance_of(TestMapToClass)
|
48
|
+
result.foo.should == @csv_row[0]
|
49
|
+
result.bar.should == @csv_row[1]
|
50
|
+
result.baz.should == :default_baz
|
51
|
+
end
|
52
|
+
|
53
|
+
it "should start at the specified CSV row" do
|
54
|
+
@row_map.start_at_row.should be(0)
|
55
|
+
@row_map.start_at_row(1)
|
56
|
+
@row_map.start_at_row.should be(1)
|
57
|
+
end
|
58
|
+
|
59
|
+
it "should allow before row processing" do
|
60
|
+
@row_map.before_row :change_name, lambda{|row, target| row[1] = 'bar'}
|
61
|
+
|
62
|
+
@row_map.first_name
|
63
|
+
@row_map.foo
|
64
|
+
|
65
|
+
result = @row_map.parse(@csv_row)
|
66
|
+
result.first_name.should == :changed_name
|
67
|
+
result.foo.should == 'bar'
|
68
|
+
end
|
69
|
+
|
70
|
+
it "should allow after row processing" do
|
71
|
+
@row_map.after_row lambda{|row, target| target.bam = :woot}
|
72
|
+
|
73
|
+
@row_map.parse(@csv_row).bam.should == :woot
|
74
|
+
end
|
75
|
+
|
76
|
+
it "should have a moveable cursor" do
|
77
|
+
@row_map.cursor.should be(0)
|
78
|
+
@row_map.move_cursor
|
79
|
+
@row_map.cursor.should be(1)
|
80
|
+
@row_map.move_cursor 3
|
81
|
+
@row_map.cursor.should be(4)
|
82
|
+
end
|
83
|
+
|
84
|
+
it "should skip indexes" do
|
85
|
+
pre_cursor = @row_map.cursor
|
86
|
+
@row_map._SKIP_
|
87
|
+
@row_map.cursor.should be(pre_cursor + 1)
|
88
|
+
end
|
89
|
+
|
90
|
+
it "should accept FasterCSV parser options" do
|
91
|
+
@row_map.parser_options :row_sep => :auto
|
92
|
+
@row_map.parser_options[:row_sep].should == :auto
|
93
|
+
end
|
94
|
+
|
95
|
+
it "should have a configurable the column delimiter" do
|
96
|
+
@row_map.delimited_by '|'
|
97
|
+
@row_map.delimited_by.should == '|'
|
98
|
+
end
|
99
|
+
|
100
|
+
it "should maintain a collection of attribute mappings" do
|
101
|
+
@row_map.mapped_attributes.should be_kind_of(Enumerable)
|
102
|
+
end
|
103
|
+
|
104
|
+
it "should lazy initialize attribute maps and move the cursor" do
|
105
|
+
pre_cursor = @row_map.cursor
|
106
|
+
(attr_map = @row_map.first_name).should be_instance_of(CsvMapper::AttributeMap)
|
107
|
+
attr_map.index.should be(pre_cursor)
|
108
|
+
@row_map.cursor.should be(pre_cursor + 1)
|
109
|
+
end
|
110
|
+
|
111
|
+
it "should lazy initialize attribute maps with optional cursor position" do
|
112
|
+
pre_cursor = @row_map.cursor
|
113
|
+
@row_map.last_name(1).index.should be(1)
|
114
|
+
@row_map.cursor.should be(1)
|
115
|
+
end
|
116
|
+
|
117
|
+
it "should share it context with its mappings" do
|
118
|
+
@row_map.first_name.map(:transform)
|
119
|
+
@row_map.parse(@csv_row).first_name.should == :transform_success
|
120
|
+
end
|
121
|
+
end
|
@@ -0,0 +1,54 @@
|
|
1
|
+
require File.dirname(__FILE__) + '/spec_helper.rb'
|
2
|
+
|
3
|
+
describe CsvMapper do
|
4
|
+
|
5
|
+
before(:each) do
|
6
|
+
@mapped_klass = Class.new { include CsvMapper }
|
7
|
+
@mapped = @mapped_klass.new
|
8
|
+
end
|
9
|
+
|
10
|
+
it "should allow the creation of CSV mappings" do
|
11
|
+
mapping = @mapped.map_csv do
|
12
|
+
start_at_row 2
|
13
|
+
end
|
14
|
+
|
15
|
+
mapping.should be_instance_of(CsvMapper::RowMap)
|
16
|
+
mapping.start_at_row.should == 2
|
17
|
+
end
|
18
|
+
|
19
|
+
it "should import a CSV IO" do
|
20
|
+
io = 'foo,bar,00,01'
|
21
|
+
results = @mapped.import(io, :type => :io) do
|
22
|
+
first
|
23
|
+
second
|
24
|
+
end
|
25
|
+
|
26
|
+
results.should be_kind_of(Enumerable)
|
27
|
+
results.should have(1).things
|
28
|
+
results[0].first.should == 'foo'
|
29
|
+
results[0].second.should == 'bar'
|
30
|
+
end
|
31
|
+
|
32
|
+
it "should import a CSV File IO" do
|
33
|
+
results = import(File.dirname(__FILE__) + '/test.csv') do
|
34
|
+
start_at_row 1
|
35
|
+
[first_name, last_name, age]
|
36
|
+
end
|
37
|
+
|
38
|
+
results.size.should be(3)
|
39
|
+
end
|
40
|
+
|
41
|
+
it "should import non-comma delimited files" do
|
42
|
+
piped_io = 'foo|bar|00|01'
|
43
|
+
|
44
|
+
results = import(piped_io, :type => :io) do
|
45
|
+
delimited_by '|'
|
46
|
+
[first, second]
|
47
|
+
end
|
48
|
+
|
49
|
+
results.should have(1).things
|
50
|
+
results[0].first.should == 'foo'
|
51
|
+
results[0].second.should == 'bar'
|
52
|
+
end
|
53
|
+
|
54
|
+
end
|
data/spec/spec.opts
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
--colour
|
data/spec/spec_helper.rb
ADDED
data/spec/test.csv
ADDED
data/tasks/rspec.rake
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
begin
|
2
|
+
require 'spec'
|
3
|
+
rescue LoadError
|
4
|
+
require 'rubygems'
|
5
|
+
require 'spec'
|
6
|
+
end
|
7
|
+
begin
|
8
|
+
require 'spec/rake/spectask'
|
9
|
+
rescue LoadError
|
10
|
+
puts <<-EOS
|
11
|
+
To use rspec for testing you must install rspec gem:
|
12
|
+
gem install rspec
|
13
|
+
EOS
|
14
|
+
exit(0)
|
15
|
+
end
|
16
|
+
|
17
|
+
desc "Run the specs under spec/models"
|
18
|
+
Spec::Rake::SpecTask.new do |t|
|
19
|
+
t.spec_opts = ['--options', "spec/spec.opts"]
|
20
|
+
t.spec_files = FileList['spec/**/*_spec.rb']
|
21
|
+
end
|
metadata
ADDED
@@ -0,0 +1,100 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: csv-mapper
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Luke Pillow
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
|
12
|
+
date: 2008-12-05 00:00:00 -06:00
|
13
|
+
default_executable:
|
14
|
+
dependencies:
|
15
|
+
- !ruby/object:Gem::Dependency
|
16
|
+
name: fastercsv
|
17
|
+
type: :runtime
|
18
|
+
version_requirement:
|
19
|
+
version_requirements: !ruby/object:Gem::Requirement
|
20
|
+
requirements:
|
21
|
+
- - ">="
|
22
|
+
- !ruby/object:Gem::Version
|
23
|
+
version: 1.4.0
|
24
|
+
version:
|
25
|
+
- !ruby/object:Gem::Dependency
|
26
|
+
name: newgem
|
27
|
+
type: :development
|
28
|
+
version_requirement:
|
29
|
+
version_requirements: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: 1.1.0
|
34
|
+
version:
|
35
|
+
- !ruby/object:Gem::Dependency
|
36
|
+
name: hoe
|
37
|
+
type: :development
|
38
|
+
version_requirement:
|
39
|
+
version_requirements: !ruby/object:Gem::Requirement
|
40
|
+
requirements:
|
41
|
+
- - ">="
|
42
|
+
- !ruby/object:Gem::Version
|
43
|
+
version: 1.8.0
|
44
|
+
version:
|
45
|
+
description: CsvMapper is a small library intended to simplify the common steps involved with importing CSV files to a usable form in Ruby.
|
46
|
+
email:
|
47
|
+
- lpillow@gmail.com
|
48
|
+
executables: []
|
49
|
+
|
50
|
+
extensions: []
|
51
|
+
|
52
|
+
extra_rdoc_files:
|
53
|
+
- History.txt
|
54
|
+
- Manifest.txt
|
55
|
+
- README.rdoc
|
56
|
+
files:
|
57
|
+
- History.txt
|
58
|
+
- Manifest.txt
|
59
|
+
- README.rdoc
|
60
|
+
- Rakefile
|
61
|
+
- lib/csv-mapper.rb
|
62
|
+
- script/console
|
63
|
+
- script/destroy
|
64
|
+
- script/generate
|
65
|
+
- spec/csv-mapper_spec.rb
|
66
|
+
- spec/csv-mapper_row_map_spec.rb
|
67
|
+
- spec/csv-mapper_attribute_map_spec.rb
|
68
|
+
- spec/test.csv
|
69
|
+
- spec/spec.opts
|
70
|
+
- spec/spec_helper.rb
|
71
|
+
- tasks/rspec.rake
|
72
|
+
has_rdoc: true
|
73
|
+
homepage: by Luke Pillow
|
74
|
+
post_install_message:
|
75
|
+
rdoc_options:
|
76
|
+
- --main
|
77
|
+
- README.rdoc
|
78
|
+
require_paths:
|
79
|
+
- lib
|
80
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
81
|
+
requirements:
|
82
|
+
- - ">="
|
83
|
+
- !ruby/object:Gem::Version
|
84
|
+
version: "0"
|
85
|
+
version:
|
86
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
87
|
+
requirements:
|
88
|
+
- - ">="
|
89
|
+
- !ruby/object:Gem::Version
|
90
|
+
version: "0"
|
91
|
+
version:
|
92
|
+
requirements: []
|
93
|
+
|
94
|
+
rubyforge_project: csv-mapper
|
95
|
+
rubygems_version: 1.3.1
|
96
|
+
signing_key:
|
97
|
+
specification_version: 2
|
98
|
+
summary: CsvMapper is a small library intended to simplify the common steps involved with importing CSV files to a usable form in Ruby.
|
99
|
+
test_files: []
|
100
|
+
|