universal_data_parser 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/lib/universal_data_parser.rb +97 -0
- metadata +58 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: cfcb9e3692b604fd4f7177623a2567b9f0fc42b7
|
4
|
+
data.tar.gz: 385e774d517fca2c033ffa52dc6c72c0b157c749
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 20222da8bb9e7b99c6982aa57ee07ef71b99b0fb9e9ba97949c72d34d137b0726dfbc3eafb4c8689af4e24f93448ffa55eec83adc9e0958b201a6e175a4f9385
|
7
|
+
data.tar.gz: 6448d185b267186d81a7af96fd407981c4e51f079a51e728d27899acb034c5a61e2e4f0fbc2721233c12998aef00a8fe594b4735a1fb6971757690594ad0013e
|
@@ -0,0 +1,97 @@
|
|
1
|
+
# encoding: utf-8 #
|
2
|
+
require 'csv'
|
3
|
+
require 'charlock_holmes'
|
4
|
+
require "i18n"
|
5
|
+
|
6
|
+
I18n.enforce_available_locales = false
|
7
|
+
I18n.locale = :es
|
8
|
+
|
9
|
+
module UniversalDataParser
|
10
|
+
|
11
|
+
class DataSet
|
12
|
+
attr_accessor :columns
|
13
|
+
attr_accessor :items
|
14
|
+
attr_accessor :headers
|
15
|
+
attr_accessor :raw_data
|
16
|
+
|
17
|
+
def initialize(raw_data)
|
18
|
+
@raw_data = raw_data
|
19
|
+
guess_columns
|
20
|
+
generate_data
|
21
|
+
end
|
22
|
+
|
23
|
+
private
|
24
|
+
|
25
|
+
def generate_data
|
26
|
+
items = @raw_data.map do |row|
|
27
|
+
new_row = Hash.new
|
28
|
+
puts headers
|
29
|
+
headers.each_with_index do |c, i|
|
30
|
+
new_row[c.to_sym] = row[i]
|
31
|
+
end
|
32
|
+
new_row
|
33
|
+
end
|
34
|
+
end
|
35
|
+
|
36
|
+
def guess_columns
|
37
|
+
@raw_data.each do |row|
|
38
|
+
n = false
|
39
|
+
row.each do |c|
|
40
|
+
if c.nil? or c.empty?
|
41
|
+
n = true
|
42
|
+
break
|
43
|
+
end
|
44
|
+
end
|
45
|
+
next if n
|
46
|
+
@headers = row.map! {|c| c.underscore unless c.nil? }
|
47
|
+
break
|
48
|
+
end
|
49
|
+
end
|
50
|
+
end
|
51
|
+
|
52
|
+
def self.parse_file(path)
|
53
|
+
DataSet.new(CSV.parse(convert_file(path)))
|
54
|
+
end
|
55
|
+
|
56
|
+
private
|
57
|
+
|
58
|
+
def self.convert_file(file)
|
59
|
+
contents = ""
|
60
|
+
if file.class == String
|
61
|
+
contents = File.read(file)
|
62
|
+
elsif file.class == File ||
|
63
|
+
file.class == ActionDispatch::Http::UploadedFile
|
64
|
+
contents = file.read
|
65
|
+
end
|
66
|
+
detection = CharlockHolmes::EncodingDetector.detect(contents)
|
67
|
+
CharlockHolmes::Converter.convert contents, detection[:encoding], 'UTF-8'
|
68
|
+
end
|
69
|
+
|
70
|
+
class ::String
|
71
|
+
def underscore
|
72
|
+
I18n.transliterate(self.gsub(/::/, '/').
|
73
|
+
gsub(/([A-Z]+)([A-Z][a-z])/,'\1_\2').
|
74
|
+
gsub(/([a-z\d])([A-Z])/,'\1_\2').
|
75
|
+
tr("-", "_").
|
76
|
+
tr(" ", "_")).downcase.
|
77
|
+
gsub("?","")
|
78
|
+
end
|
79
|
+
end
|
80
|
+
|
81
|
+
# def self.guess_column_types
|
82
|
+
# @columns.each_with_index do |column, i|
|
83
|
+
# column_type = 'text'
|
84
|
+
# @data.each do |row|
|
85
|
+
# case true
|
86
|
+
# when /^\d*$/.match(row[i])
|
87
|
+
# column_type = 'number'
|
88
|
+
# when /^[^@]*@.*$/.match(row[i])
|
89
|
+
# column_type = 'email'
|
90
|
+
# else
|
91
|
+
# column_type = 'text'
|
92
|
+
# end
|
93
|
+
# end
|
94
|
+
# puts column_type
|
95
|
+
# end
|
96
|
+
# end
|
97
|
+
end
|
metadata
ADDED
@@ -0,0 +1,58 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: universal_data_parser
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Ricardo Garcia
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2010-12-06 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: charlock_holmes
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ~>
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: 0.7.3
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: 0.7.3
|
27
|
+
description: Gem intended to analize and deduct data from CSV, XLS, XLSX, files
|
28
|
+
email: ricardo@ukko.mx
|
29
|
+
executables: []
|
30
|
+
extensions: []
|
31
|
+
extra_rdoc_files: []
|
32
|
+
files:
|
33
|
+
- lib/universal_data_parser.rb
|
34
|
+
homepage: http://rubygems.org/gems/universal_data_parser
|
35
|
+
licenses:
|
36
|
+
- MIT
|
37
|
+
metadata: {}
|
38
|
+
post_install_message:
|
39
|
+
rdoc_options: []
|
40
|
+
require_paths:
|
41
|
+
- lib
|
42
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
43
|
+
requirements:
|
44
|
+
- - '>='
|
45
|
+
- !ruby/object:Gem::Version
|
46
|
+
version: '0'
|
47
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
48
|
+
requirements:
|
49
|
+
- - '>='
|
50
|
+
- !ruby/object:Gem::Version
|
51
|
+
version: '0'
|
52
|
+
requirements: []
|
53
|
+
rubyforge_project:
|
54
|
+
rubygems_version: 2.4.4
|
55
|
+
signing_key:
|
56
|
+
specification_version: 4
|
57
|
+
summary: CSV data deducting gem
|
58
|
+
test_files: []
|