ddi-parser 0.0.1 → 0.0.2
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/ddi-parser.rb +20 -10
- data/lib/models/{variable.rb → ddi_variable.rb} +2 -2
- data/lib/models/study.rb +3 -3
- data/lib/models/version.rb +1 -1
- metadata +10 -10
data/lib/ddi-parser.rb
CHANGED
@@ -5,7 +5,7 @@ require 'models/category'
|
|
5
5
|
require 'models/category_statistic'
|
6
6
|
require 'models/study'
|
7
7
|
require 'models/study_date'
|
8
|
-
require 'models/
|
8
|
+
require 'models/ddi_variable'
|
9
9
|
require 'models/summary_stat'
|
10
10
|
|
11
11
|
module DDI
|
@@ -18,7 +18,15 @@ module DDI
|
|
18
18
|
catalog = DDI::Catalog.new
|
19
19
|
study = DDI::Study.new
|
20
20
|
study_info_hash = Hash.new
|
21
|
-
|
21
|
+
encode_type = `file --mime -br #{ddi_file}`.gsub(/\n/,"").split(';')[1].split('=')[1]
|
22
|
+
#have to convert to UTF-8 for libxml
|
23
|
+
contents = File.open(ddi_file).read
|
24
|
+
output = Iconv.conv("UTF-8", encode_type, contents)
|
25
|
+
converted_file = File.join(File.dirname(ddi_file), "converted_file.xml")
|
26
|
+
file = File.open(converted_file, 'w')
|
27
|
+
file.write(output)
|
28
|
+
file.close
|
29
|
+
parser = LibXML::XML::Parser.file(converted_file)
|
22
30
|
doc = parser.parse
|
23
31
|
studynodes = doc.find('//stdyDscr')
|
24
32
|
abstracts = studynodes[0].find('//abstract')
|
@@ -36,15 +44,17 @@ module DDI
|
|
36
44
|
date = studynodes[0].find('//sumDscr/collDate')
|
37
45
|
date.each do |d|
|
38
46
|
a = d.attributes
|
39
|
-
|
40
|
-
|
41
|
-
|
42
|
-
|
47
|
+
unless a.length == 0
|
48
|
+
study_date = DDI::StudyDate.new
|
49
|
+
study_date.type = a.get_attribute('event').value.strip
|
50
|
+
study_date.date = a.get_attribute('date').value.strip
|
51
|
+
dates.push(study_date)
|
52
|
+
end
|
43
53
|
end
|
44
54
|
study.dates = dates
|
45
|
-
study.sampling_procedure = studynodes[0].find('//sampProc')[0].first.content.strip unless studynodes[0].find('//sampProc')[0] ==
|
55
|
+
study.sampling_procedure = studynodes[0].find('//sampProc')[0].first.content.strip unless studynodes[0].find('//sampProc')[0].children.size == 0
|
46
56
|
# study.weight = studynodes[0].find('//sampProc')[0].first.content
|
47
|
-
study.
|
57
|
+
study.ddi_variables = get_variable_information doc
|
48
58
|
return study
|
49
59
|
end
|
50
60
|
|
@@ -69,7 +79,7 @@ module DDI
|
|
69
79
|
end
|
70
80
|
vars = docnodes[0].find('//dataDscr/var')
|
71
81
|
vars.each do |var|
|
72
|
-
variable = DDI::
|
82
|
+
variable = DDI::DDIVariable.new
|
73
83
|
var_attr = var.attributes
|
74
84
|
variable.id = var_attr.get_attribute('ID').value.strip unless var_attr.get_attribute('ID') == nil
|
75
85
|
variable.name = var_attr.get_attribute('name').value.strip unless var_attr.get_attribute('name') == nil
|
@@ -158,4 +168,4 @@ module DDI
|
|
158
168
|
end
|
159
169
|
|
160
170
|
end
|
161
|
-
end
|
171
|
+
end
|
@@ -1,11 +1,11 @@
|
|
1
1
|
module DDI
|
2
2
|
|
3
3
|
#Information about a variable/column in a dataset
|
4
|
-
class
|
4
|
+
class DDIVariable
|
5
5
|
|
6
6
|
attr_reader :name, :label, :group, :id, :file, :interval, :max, :min, :question, :interview_instruction, :summary_stats, :categories
|
7
7
|
attr_writer :name, :label, :group, :id, :file, :interval, :max, :min, :question, :interview_instruction, :summary_stats, :categories
|
8
8
|
|
9
9
|
end
|
10
10
|
|
11
|
-
end
|
11
|
+
end
|
data/lib/models/study.rb
CHANGED
@@ -3,9 +3,9 @@ module DDI
|
|
3
3
|
#Contains a set of variables and belongs to a catalog
|
4
4
|
class Study
|
5
5
|
|
6
|
-
attr_reader :
|
7
|
-
attr_writer :
|
6
|
+
attr_reader :ddi_variables, :abstract, :title, :id, :dates, :sampling_procedure, :weight, :nesstar_id, :nesstar_uri
|
7
|
+
attr_writer :ddi_variables, :abstract, :title, :id, :dates, :sampling_procedure, :weight, :nesstar_id, :nesstar_uri
|
8
8
|
|
9
9
|
end
|
10
10
|
|
11
|
-
end
|
11
|
+
end
|
data/lib/models/version.rb
CHANGED
metadata
CHANGED
@@ -1,13 +1,13 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: ddi-parser
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
hash:
|
5
|
-
prerelease:
|
4
|
+
hash: 27
|
5
|
+
prerelease:
|
6
6
|
segments:
|
7
7
|
- 0
|
8
8
|
- 0
|
9
|
-
-
|
10
|
-
version: 0.0.
|
9
|
+
- 2
|
10
|
+
version: 0.0.2
|
11
11
|
platform: ruby
|
12
12
|
authors:
|
13
13
|
- Ian Dunlop
|
@@ -15,7 +15,7 @@ autorequire:
|
|
15
15
|
bindir: bin
|
16
16
|
cert_chain: []
|
17
17
|
|
18
|
-
date: 2011-
|
18
|
+
date: 2011-09-26 00:00:00 +01:00
|
19
19
|
default_executable:
|
20
20
|
dependencies:
|
21
21
|
- !ruby/object:Gem::Dependency
|
@@ -45,14 +45,14 @@ extra_rdoc_files: []
|
|
45
45
|
|
46
46
|
files:
|
47
47
|
- lib/ddi-parser.rb
|
48
|
+
- lib/models/version.rb
|
49
|
+
- lib/models/summary_stat.rb
|
50
|
+
- lib/models/study.rb
|
48
51
|
- lib/models/catalog.rb
|
49
52
|
- lib/models/category.rb
|
50
53
|
- lib/models/category_statistic.rb
|
51
|
-
- lib/models/
|
54
|
+
- lib/models/ddi_variable.rb
|
52
55
|
- lib/models/study_date.rb
|
53
|
-
- lib/models/summary_stat.rb
|
54
|
-
- lib/models/variable.rb
|
55
|
-
- lib/models/version.rb
|
56
56
|
has_rdoc: true
|
57
57
|
homepage: http://github.com/mygrid/ddi-parser
|
58
58
|
licenses: []
|
@@ -83,7 +83,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
83
83
|
requirements: []
|
84
84
|
|
85
85
|
rubyforge_project: ddi-parser
|
86
|
-
rubygems_version: 1.
|
86
|
+
rubygems_version: 1.6.2
|
87
87
|
signing_key:
|
88
88
|
specification_version: 3
|
89
89
|
summary: API for parsing ddi metadata files and returning results
|