scottmotte-csvmapper 0.4.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +5 -0
- data/.gitignore +5 -0
- data/LICENSE +20 -0
- data/README.rdoc +36 -0
- data/Rakefile +51 -0
- data/VERSION +1 -0
- data/lib/csvmapper.rb +237 -0
- data/spec/csvmapper_spec.rb +7 -0
- data/spec/spec_helper.rb +9 -0
- metadata +82 -0
data/.document
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2009 scottmotte
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.rdoc
ADDED
@@ -0,0 +1,36 @@
|
|
1
|
+
= CsvMapper
|
2
|
+
|
3
|
+
Taken from Luke Pillow (pillowfactory's) gem and adjusted for my own needs very very slightly.
|
4
|
+
|
5
|
+
== INSTALL:
|
6
|
+
|
7
|
+
sudo gem install scottmotte-csvmapper
|
8
|
+
|
9
|
+
== DESCRIPTION:
|
10
|
+
|
11
|
+
CsvMapper is a small library intended to simplify the common steps involved with importing CSV files to a usable form in Ruby.
|
12
|
+
|
13
|
+
== EXAMPLES:
|
14
|
+
|
15
|
+
The following example will import a CSV file to an Array of OpenStruct[http://ruby-doc.org/core/classes/OpenStruct.html] instances.
|
16
|
+
|
17
|
+
==== Example CSV File Structure
|
18
|
+
|
19
|
+
First Name,Last Name,Age
|
20
|
+
John,Doe,27
|
21
|
+
Jane,Doe,26
|
22
|
+
Bat,Man,52
|
23
|
+
|
24
|
+
==== Simple Usage Example
|
25
|
+
include CsvMapper
|
26
|
+
|
27
|
+
results = CsvMapper.import('/path/to/file.csv') do
|
28
|
+
start_at_row 1
|
29
|
+
[first_name, last_name, age]
|
30
|
+
end
|
31
|
+
|
32
|
+
results.first.first_name # John
|
33
|
+
results.first.last_name # Doe
|
34
|
+
results.first.age # 27
|
35
|
+
|
36
|
+
|
data/Rakefile
ADDED
@@ -0,0 +1,51 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
|
4
|
+
begin
|
5
|
+
require 'jeweler'
|
6
|
+
Jeweler::Tasks.new do |gem|
|
7
|
+
gem.name = "csvmapper"
|
8
|
+
gem.summary = %Q{Stolen from pillowfactory's csv-mapper and adjusted slightly}
|
9
|
+
gem.email = "scott@scottmotte.com"
|
10
|
+
gem.homepage = "http://github.com/scottmotte/csvmapper"
|
11
|
+
gem.authors = ["scottmotte"]
|
12
|
+
# gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
|
13
|
+
|
14
|
+
gem.add_dependency('right_aws')
|
15
|
+
gem.add_dependency('mini_magick')
|
16
|
+
end
|
17
|
+
|
18
|
+
rescue LoadError
|
19
|
+
puts "Jeweler (or a dependency) not available. Install it with: sudo gem install jeweler"
|
20
|
+
end
|
21
|
+
|
22
|
+
require 'spec/rake/spectask'
|
23
|
+
Spec::Rake::SpecTask.new(:spec) do |spec|
|
24
|
+
spec.libs << 'lib' << 'spec'
|
25
|
+
spec.spec_files = FileList['spec/**/*_spec.rb']
|
26
|
+
end
|
27
|
+
|
28
|
+
Spec::Rake::SpecTask.new(:rcov) do |spec|
|
29
|
+
spec.libs << 'lib' << 'spec'
|
30
|
+
spec.pattern = 'spec/**/*_spec.rb'
|
31
|
+
spec.rcov = true
|
32
|
+
end
|
33
|
+
|
34
|
+
|
35
|
+
task :default => :spec
|
36
|
+
|
37
|
+
require 'rake/rdoctask'
|
38
|
+
Rake::RDocTask.new do |rdoc|
|
39
|
+
if File.exist?('VERSION.yml')
|
40
|
+
config = YAML.load(File.read('VERSION.yml'))
|
41
|
+
version = "#{config[:major]}.#{config[:minor]}.#{config[:patch]}"
|
42
|
+
else
|
43
|
+
version = ""
|
44
|
+
end
|
45
|
+
|
46
|
+
rdoc.rdoc_dir = 'rdoc'
|
47
|
+
rdoc.title = "csvmapper #{version}"
|
48
|
+
rdoc.rdoc_files.include('README*')
|
49
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
50
|
+
end
|
51
|
+
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.4.0
|
data/lib/csvmapper.rb
ADDED
@@ -0,0 +1,237 @@
|
|
1
|
+
require 'ostruct'
|
2
|
+
require 'fastercsv'
|
3
|
+
|
4
|
+
# this is stolen from csv-mapper gem with slight modifcations by me and a cleaner module name
|
5
|
+
module CsvMapper
|
6
|
+
# Create a new RowMap instance from the definition in the given block.
|
7
|
+
def self.map_csv(&map_block)
|
8
|
+
CsvMapper::RowMap.new(self, &map_block)
|
9
|
+
end
|
10
|
+
|
11
|
+
# Load CSV data and map the values according to the definition in the given block.
|
12
|
+
# Accepts either a file path, String, or IO as +data+. Defaults to file path.
|
13
|
+
#
|
14
|
+
# The following +options+ may be used:
|
15
|
+
# <tt>:type</tt>:: defaults to <tt>:file_path</tt>. Use <tt>:io</tt> to specify data as String or IO.
|
16
|
+
# <tt>:map</tt>:: Specify an instance of a RowMap to take presidence over a given block defintion.
|
17
|
+
#
|
18
|
+
def self.import(data, options={}, &map_block)
|
19
|
+
config = { :type => :file_path,
|
20
|
+
:map => map_csv(&map_block) }.merge!(options)
|
21
|
+
|
22
|
+
csv_data = config[:type] == :io ? data : File.new(data, 'r')
|
23
|
+
map = config[:map]
|
24
|
+
|
25
|
+
results = []
|
26
|
+
FasterCSV.new(csv_data, map.parser_options ).each_with_index do |row, i|
|
27
|
+
results << map.parse(row) if i >= map.start_at_row && i <= map.stop_at_row
|
28
|
+
end
|
29
|
+
|
30
|
+
results
|
31
|
+
end
|
32
|
+
|
33
|
+
# CsvMapper::RowMap provides a simple, DSL-like interface for constructing mappings.
|
34
|
+
# A CsvMapper::RowMap provides the main functionality of the library. It will mostly be used indirectly through the CsvMapper API,
|
35
|
+
# but may be useful to use directly for the dynamic CSV mappings.
|
36
|
+
class RowMap
|
37
|
+
#Start with a 'blank slate'
|
38
|
+
instance_methods.each { |m| undef_method m unless m =~ /^__||instance_eval/ }
|
39
|
+
|
40
|
+
Infinity = 1.0/0
|
41
|
+
attr_reader :mapped_attributes
|
42
|
+
|
43
|
+
# Create a new instance with access to an evaluation context
|
44
|
+
def initialize(context, &map_block)
|
45
|
+
@context = context
|
46
|
+
@before_filters = []
|
47
|
+
@after_filters = []
|
48
|
+
@parser_options = {}
|
49
|
+
@start_at_row = 0
|
50
|
+
@stop_at_row = Infinity
|
51
|
+
@delimited_by = FasterCSV::DEFAULT_OPTIONS[:col_sep]
|
52
|
+
@mapped_attributes = []
|
53
|
+
|
54
|
+
self.instance_eval(&map_block) if block_given?
|
55
|
+
end
|
56
|
+
|
57
|
+
# Each row of a CSV is parsed and mapped to a new instance of a Ruby class; OpenStruct by default.
|
58
|
+
# Use this method to change the what class each row is mapped to.
|
59
|
+
# The given class must respond to a parameter-less #new and all attribute mappings defined.
|
60
|
+
# Providing a hash of defaults will ensure that each resulting object will have the providing name and attribute values
|
61
|
+
# unless overridden by a mapping
|
62
|
+
def map_to(klass, defaults={})
|
63
|
+
@map_to_klass = klass
|
64
|
+
|
65
|
+
defaults.each do |name, value|
|
66
|
+
self.add_attribute(name, -99).map lambda{|row| value}
|
67
|
+
end
|
68
|
+
end
|
69
|
+
|
70
|
+
# Specify a hash of FasterCSV options to be used for CSV parsing
|
71
|
+
#
|
72
|
+
# Can be anything FasterCSV::new()[http://fastercsv.rubyforge.org/classes/FasterCSV.html#M000018] accepts
|
73
|
+
def parser_options(opts=nil)
|
74
|
+
@parser_options = opts if opts
|
75
|
+
@parser_options.merge :col_sep => @delimited_by
|
76
|
+
end
|
77
|
+
|
78
|
+
# Convenience method to 'move' the cursor skipping the current index.
|
79
|
+
def _SKIP_
|
80
|
+
self.move_cursor
|
81
|
+
end
|
82
|
+
|
83
|
+
# Specify the CSV column delimiter. Defaults to comma.
|
84
|
+
def delimited_by(delimiter=nil)
|
85
|
+
@delimited_by = delimiter if delimiter
|
86
|
+
@delimited_by
|
87
|
+
end
|
88
|
+
|
89
|
+
# Declare what row to begin parsing the CSV.
|
90
|
+
# This is useful for skipping headers and such.
|
91
|
+
def start_at_row(row_number=nil)
|
92
|
+
@start_at_row = row_number if row_number
|
93
|
+
@start_at_row
|
94
|
+
end
|
95
|
+
|
96
|
+
# Declare the last row to be parsed in a CSV.
|
97
|
+
def stop_at_row(row_number=nil)
|
98
|
+
@stop_at_row = row_number if row_number
|
99
|
+
@stop_at_row
|
100
|
+
end
|
101
|
+
|
102
|
+
# Declare method name symbols and/or lambdas to be executed before each row.
|
103
|
+
# Each method or lambda must accept to parameters: +csv_row+, +target_object+
|
104
|
+
# Methods names should refer to methods available within the RowMap's provided context
|
105
|
+
def before_row(*befores)
|
106
|
+
self.add_filters(@before_filters, *befores)
|
107
|
+
end
|
108
|
+
|
109
|
+
# Declare method name symbols and/or lambdas to be executed before each row.
|
110
|
+
# Each method or lambda must accept to parameters: +csv_row+, +target_object+
|
111
|
+
# Methods names should refer to methods available within the RowMap's provided context
|
112
|
+
def after_row(*afters)
|
113
|
+
self.add_filters(@after_filters, *afters)
|
114
|
+
end
|
115
|
+
|
116
|
+
# Add a new attribute to this map. Mostly used internally, but is useful for dynamic map creation.
|
117
|
+
# returns the newly created CsvMapper::AttributeMap
|
118
|
+
def add_attribute(name, index=nil)
|
119
|
+
attr_mapping = CsvMapper::AttributeMap.new(name.to_sym, index, @context)
|
120
|
+
self.mapped_attributes << attr_mapping
|
121
|
+
attr_mapping
|
122
|
+
end
|
123
|
+
|
124
|
+
# The current cursor location
|
125
|
+
def cursor # :nodoc:
|
126
|
+
@cursor ||= 0
|
127
|
+
end
|
128
|
+
|
129
|
+
# Move the cursor relative to it's current position
|
130
|
+
def move_cursor(positions=1) # :nodoc:
|
131
|
+
self.cursor += positions
|
132
|
+
end
|
133
|
+
|
134
|
+
# Given a CSV row return an instance of an object defined by this mapping
|
135
|
+
def parse(csv_row)
|
136
|
+
target = self.map_to_class.new
|
137
|
+
@before_filters.each {|filter| filter.call(csv_row, target) }
|
138
|
+
|
139
|
+
self.mapped_attributes.inject(target) do |result, attr_map|
|
140
|
+
result.send("#{attr_map.name}=".to_sym, attr_map.parse(csv_row))
|
141
|
+
result
|
142
|
+
end
|
143
|
+
|
144
|
+
@after_filters.each {|filter| filter.call(csv_row, target) }
|
145
|
+
|
146
|
+
return target
|
147
|
+
end
|
148
|
+
|
149
|
+
protected # :nodoc:
|
150
|
+
|
151
|
+
# The Hacktastic "magic"
|
152
|
+
# Used to dynamically create CsvMapper::AttributeMaps based on unknown method calls that
|
153
|
+
# should represent the names of mapped attributes.
|
154
|
+
#
|
155
|
+
# An optional first argument is used to move this maps cursor position and as the index of the
|
156
|
+
# new AttributeMap
|
157
|
+
def method_missing(name, *args) # :nodoc:
|
158
|
+
|
159
|
+
if index = args[0]
|
160
|
+
self.move_cursor(index - self.cursor)
|
161
|
+
else
|
162
|
+
index = self.cursor
|
163
|
+
self.move_cursor
|
164
|
+
end
|
165
|
+
|
166
|
+
add_attribute(name, index)
|
167
|
+
end
|
168
|
+
|
169
|
+
def add_filters(to_hook, *filters) # :nodoc:
|
170
|
+
(to_hook << filters.collect do |filter|
|
171
|
+
filter.is_a?(Symbol) ? lambda{|row, target| @context.send(filter, row, target)} : filter
|
172
|
+
end).flatten!
|
173
|
+
end
|
174
|
+
|
175
|
+
def map_to_class # :nodoc:
|
176
|
+
@map_to_klass || OpenStruct
|
177
|
+
end
|
178
|
+
|
179
|
+
def cursor=(value) # :nodoc:
|
180
|
+
@cursor=value
|
181
|
+
end
|
182
|
+
|
183
|
+
|
184
|
+
end
|
185
|
+
|
186
|
+
# A CsvMapper::AttributeMap contains the instructions to parse a value from a CSV row and to know the
|
187
|
+
# name of the attribute it is targeting.
|
188
|
+
class AttributeMap
|
189
|
+
attr_reader :name, :index
|
190
|
+
|
191
|
+
# Creates a new instance using the provided attribute +name+, CSV row +index+, and evaluation +map_context+
|
192
|
+
def initialize(name, index, map_context)
|
193
|
+
@name, @index, @map_context = name, index, map_context
|
194
|
+
end
|
195
|
+
|
196
|
+
# Set the index that this map is targeting.
|
197
|
+
#
|
198
|
+
# Returns this AttributeMap for chainability
|
199
|
+
def at(index)
|
200
|
+
@index = index
|
201
|
+
self
|
202
|
+
end
|
203
|
+
|
204
|
+
# Provide a lambda or the symbol name of a method on this map's evaluation context to be used when parsing
|
205
|
+
# the value from a CSV row.
|
206
|
+
# Both the lambda or the method provided should accept a single +row+ parameter
|
207
|
+
#
|
208
|
+
# Returns this AttributeMap for chainability
|
209
|
+
def map(transform)
|
210
|
+
@transformer = transform
|
211
|
+
self
|
212
|
+
end
|
213
|
+
|
214
|
+
# Given a CSV row, return the value at this AttributeMap's index using any provided map transforms (see map)
|
215
|
+
def parse(csv_row)
|
216
|
+
@transformer ? parse_transform(csv_row) : csv_row[self.index]
|
217
|
+
end
|
218
|
+
|
219
|
+
# Access the raw value of the CSV row without any map transforms applied.
|
220
|
+
def raw_value(csv_row)
|
221
|
+
csv_row[self.index]
|
222
|
+
end
|
223
|
+
|
224
|
+
private
|
225
|
+
|
226
|
+
def parse_transform(csv_row)
|
227
|
+
if @transformer.is_a? Symbol
|
228
|
+
transform_name = @transformer
|
229
|
+
@transformer = lambda{|row| @map_context.send(transform_name, row) }
|
230
|
+
end
|
231
|
+
|
232
|
+
@transformer.call(csv_row)
|
233
|
+
end
|
234
|
+
|
235
|
+
end
|
236
|
+
end
|
237
|
+
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,82 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: scottmotte-csvmapper
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.4.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- scottmotte
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
|
12
|
+
date: 2009-07-20 00:00:00 -07:00
|
13
|
+
default_executable:
|
14
|
+
dependencies:
|
15
|
+
- !ruby/object:Gem::Dependency
|
16
|
+
name: right_aws
|
17
|
+
type: :runtime
|
18
|
+
version_requirement:
|
19
|
+
version_requirements: !ruby/object:Gem::Requirement
|
20
|
+
requirements:
|
21
|
+
- - ">="
|
22
|
+
- !ruby/object:Gem::Version
|
23
|
+
version: "0"
|
24
|
+
version:
|
25
|
+
- !ruby/object:Gem::Dependency
|
26
|
+
name: mini_magick
|
27
|
+
type: :runtime
|
28
|
+
version_requirement:
|
29
|
+
version_requirements: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: "0"
|
34
|
+
version:
|
35
|
+
description:
|
36
|
+
email: scott@scottmotte.com
|
37
|
+
executables: []
|
38
|
+
|
39
|
+
extensions: []
|
40
|
+
|
41
|
+
extra_rdoc_files:
|
42
|
+
- LICENSE
|
43
|
+
- README.rdoc
|
44
|
+
files:
|
45
|
+
- .document
|
46
|
+
- .gitignore
|
47
|
+
- LICENSE
|
48
|
+
- README.rdoc
|
49
|
+
- Rakefile
|
50
|
+
- VERSION
|
51
|
+
- lib/csvmapper.rb
|
52
|
+
- spec/csvmapper_spec.rb
|
53
|
+
- spec/spec_helper.rb
|
54
|
+
has_rdoc: false
|
55
|
+
homepage: http://github.com/scottmotte/csvmapper
|
56
|
+
post_install_message:
|
57
|
+
rdoc_options:
|
58
|
+
- --charset=UTF-8
|
59
|
+
require_paths:
|
60
|
+
- lib
|
61
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
62
|
+
requirements:
|
63
|
+
- - ">="
|
64
|
+
- !ruby/object:Gem::Version
|
65
|
+
version: "0"
|
66
|
+
version:
|
67
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
68
|
+
requirements:
|
69
|
+
- - ">="
|
70
|
+
- !ruby/object:Gem::Version
|
71
|
+
version: "0"
|
72
|
+
version:
|
73
|
+
requirements: []
|
74
|
+
|
75
|
+
rubyforge_project:
|
76
|
+
rubygems_version: 1.2.0
|
77
|
+
signing_key:
|
78
|
+
specification_version: 3
|
79
|
+
summary: Stolen from pillowfactory's csv-mapper and adjusted slightly
|
80
|
+
test_files:
|
81
|
+
- spec/csvmapper_spec.rb
|
82
|
+
- spec/spec_helper.rb
|