csv-autoparser 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.
- checksums.yaml +7 -0
- data/.gitignore +18 -0
- data/LICENSE.txt +22 -0
- data/README.md +28 -0
- data/Rakefile +8 -0
- data/csv-autoparser.gemspec +23 -0
- data/lib/csv/autoparser.rb +49 -0
- data/lib/csv/autoparser/version.rb +5 -0
- data/test/fixtures/persons.csv +5 -0
- data/test/minitest_helper.rb +10 -0
- data/test/test_csv/autoparser.rb +31 -0
- metadata +84 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: dda3d9b42b637575933d1b307b5dd5f5687971c6
|
4
|
+
data.tar.gz: d28893032f72edf4824d4bed8d8c212cdab7a2d6
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 93cb849bab22ab289d59a7e1821cad3b8fcdea073793d8a804fa19b71d60d07884e44d1a4696f0daadca083ff9c40d3eb862da7a60b0565cf7180cf418c4f236
|
7
|
+
data.tar.gz: 659990a336d41c984cc5468b9729d6f47cb5f78e2a018be348f65092a8a387c4455b384f0ca3fcfe7666c925fe25f4ec7f089c6b254055ea9eca14b1a6bae314
|
data/.gitignore
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 Benjamin Delsol
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
# CSV::AutoParser
|
2
|
+
|
3
|
+
CSV::AutoParser automatically parses a CSV file given a user specified header row.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
$ gem install csv-autoparser
|
8
|
+
|
9
|
+
## Usage
|
10
|
+
|
11
|
+
# ID header row by CSV line number.
|
12
|
+
csv = CSV::AutoParser.new("my_file.csv") {|csv_line_number, header_row| csv_line_number == 1 }
|
13
|
+
csv.rows.each {|row| puts row.full_name }
|
14
|
+
|
15
|
+
# -OR- ID header row by column header names.
|
16
|
+
csv = CSV::AutoParser.new(input_file) do |line_num, header_row|
|
17
|
+
["name", "Job title"].all? {|cell| header_row.include?(cell) }
|
18
|
+
end
|
19
|
+
puts csv.rows.first.name # => "Jon Smith"
|
20
|
+
csv.rows.first.job_title # => "blacksmith"
|
21
|
+
|
22
|
+
## Contributing
|
23
|
+
|
24
|
+
1. Fork it ( http://github.com/bdiz/csv-autoparser/fork )
|
25
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
26
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
27
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
28
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'csv/autoparser/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "csv-autoparser"
|
8
|
+
spec.version = CSV::AutoParser::VERSION
|
9
|
+
spec.authors = ["Ben Delsol"]
|
10
|
+
spec.email = [] # contact me via github (username: bdiz)
|
11
|
+
spec.summary = %q{Can parse a CSV file automatically given a user specified header row.}
|
12
|
+
spec.description = %q{}
|
13
|
+
spec.homepage = ""
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0")
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_development_dependency "rake"
|
22
|
+
spec.add_development_dependency "minitest"
|
23
|
+
end
|
@@ -0,0 +1,49 @@
|
|
1
|
+
require "csv"
|
2
|
+
require "csv/autoparser/version"
|
3
|
+
|
4
|
+
class CSV
|
5
|
+
class AutoParser
|
6
|
+
class Row
|
7
|
+
|
8
|
+
def self.define_methods map
|
9
|
+
map.each_pair do |column_name, column_offset|
|
10
|
+
define_method(column_to_method_name(column_name)) { @row[column_offset] }
|
11
|
+
end
|
12
|
+
end
|
13
|
+
|
14
|
+
def self.column_to_method_name name
|
15
|
+
name.downcase.strip.gsub(/\s+/, '_').gsub(/-+/, '_').gsub(/[^\w]/, '')
|
16
|
+
end
|
17
|
+
|
18
|
+
def initialize row
|
19
|
+
@row = row
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
class HeaderRowNotFound < RuntimeError; end
|
24
|
+
|
25
|
+
attr_reader :pre_header_rows, :rows
|
26
|
+
|
27
|
+
def initialize file, &is_header
|
28
|
+
map = {}
|
29
|
+
csv_line_number = 0
|
30
|
+
@rows = []
|
31
|
+
@pre_header_rows = []
|
32
|
+
CSV.foreach(file) do |row|
|
33
|
+
csv_line_number += 1
|
34
|
+
if map.empty?
|
35
|
+
if is_header.call(csv_line_number, row)
|
36
|
+
row.each_index {|index| map[row[index]] = index }
|
37
|
+
Row.define_methods(map)
|
38
|
+
else
|
39
|
+
@pre_header_rows << row
|
40
|
+
end
|
41
|
+
else
|
42
|
+
@rows << Row.new(row)
|
43
|
+
end
|
44
|
+
end
|
45
|
+
raise HeaderRowNotFound, "Could not find header row in #{file}." if map.empty?
|
46
|
+
end
|
47
|
+
|
48
|
+
end
|
49
|
+
end
|
@@ -0,0 +1,31 @@
|
|
1
|
+
$LOAD_PATH.unshift File.expand_path('../..', __FILE__)
|
2
|
+
require 'minitest_helper'
|
3
|
+
|
4
|
+
describe CSV::AutoParser do
|
5
|
+
|
6
|
+
def input_file
|
7
|
+
fixture_file_path('persons.csv')
|
8
|
+
end
|
9
|
+
|
10
|
+
it "it can parse a csv automatically via csv line number id" do
|
11
|
+
csv = CSV::AutoParser.new(input_file) {|csv_line_number, header_row| csv_line_number == 1 }
|
12
|
+
csv.rows.length.must_equal 4
|
13
|
+
csv.rows.first.full_name.must_equal "name"
|
14
|
+
end
|
15
|
+
|
16
|
+
it "it can parse a csv automatically via header row id" do
|
17
|
+
csv = CSV::AutoParser.new(input_file) do |line_num, header_row|
|
18
|
+
["name", "Job title"].all? {|cell| header_row.include?(cell) }
|
19
|
+
end
|
20
|
+
csv.rows.length.must_equal 3
|
21
|
+
csv.rows.first.name.must_equal "Jon Smith"
|
22
|
+
csv.rows.first.job_title.must_equal "blacksmith"
|
23
|
+
csv.rows.last.age.to_i.must_equal 29
|
24
|
+
end
|
25
|
+
|
26
|
+
it "will raise an exception if it can't find the header row" do
|
27
|
+
lambda { CSV::AutoParser.new(input_file) {|csv_line_number, header_row| csv_line_number == 0 }}.
|
28
|
+
must_raise(CSV::AutoParser::HeaderRowNotFound)
|
29
|
+
end
|
30
|
+
|
31
|
+
end
|
metadata
ADDED
@@ -0,0 +1,84 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: csv-autoparser
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Ben Delsol
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-03-24 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: rake
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - '>='
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - '>='
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: minitest
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - '>='
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - '>='
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
description: ''
|
42
|
+
email: []
|
43
|
+
executables: []
|
44
|
+
extensions: []
|
45
|
+
extra_rdoc_files: []
|
46
|
+
files:
|
47
|
+
- .gitignore
|
48
|
+
- LICENSE.txt
|
49
|
+
- README.md
|
50
|
+
- Rakefile
|
51
|
+
- csv-autoparser.gemspec
|
52
|
+
- lib/csv/autoparser.rb
|
53
|
+
- lib/csv/autoparser/version.rb
|
54
|
+
- test/fixtures/persons.csv
|
55
|
+
- test/minitest_helper.rb
|
56
|
+
- test/test_csv/autoparser.rb
|
57
|
+
homepage: ''
|
58
|
+
licenses:
|
59
|
+
- MIT
|
60
|
+
metadata: {}
|
61
|
+
post_install_message:
|
62
|
+
rdoc_options: []
|
63
|
+
require_paths:
|
64
|
+
- lib
|
65
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
66
|
+
requirements:
|
67
|
+
- - '>='
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: '0'
|
70
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
71
|
+
requirements:
|
72
|
+
- - '>='
|
73
|
+
- !ruby/object:Gem::Version
|
74
|
+
version: '0'
|
75
|
+
requirements: []
|
76
|
+
rubyforge_project:
|
77
|
+
rubygems_version: 2.0.3
|
78
|
+
signing_key:
|
79
|
+
specification_version: 4
|
80
|
+
summary: Can parse a CSV file automatically given a user specified header row.
|
81
|
+
test_files:
|
82
|
+
- test/fixtures/persons.csv
|
83
|
+
- test/minitest_helper.rb
|
84
|
+
- test/test_csv/autoparser.rb
|