davidrichards-etl 0.0.5 → 0.0.6
Sign up to get free protection for your applications and to get access to all the features.
- data/VERSION.yml +1 -1
- data/lib/etl/csv_et.rb +2 -28
- data/lib/etl/rdf_2_data_frame.rb +19 -0
- data/lib/helpers/open_content.rb +1 -0
- data/lib/helpers/open_content/extractor.rb +43 -0
- metadata +6 -2
data/VERSION.yml
CHANGED
data/lib/etl/csv_et.rb
CHANGED
@@ -19,34 +19,8 @@ module CSV
|
|
19
19
|
|
20
20
|
# Attempts to get a string from a file, a uri, or a string
|
21
21
|
def extract
|
22
|
-
|
23
|
-
|
24
|
-
raise ArgumentError, "Could not determine what #{obj.inspect} was. CSV::ET cannot work with this data." unless @raw
|
25
|
-
end
|
26
|
-
|
27
|
-
# Handles local filename cases, reading the contents of the file.
|
28
|
-
def extract_locally(filename)
|
29
|
-
@raw = File.read(filename) if File.exist?(filename)
|
30
|
-
ET.logger.info "Extracted the data from from filesystem" if @raw
|
31
|
-
@raw ? true : false
|
32
|
-
end
|
33
|
-
|
34
|
-
# Handles remote uri cases, reading the remote resource with open-uri, part of the Standard Library
|
35
|
-
def extract_remotely(uri)
|
36
|
-
begin
|
37
|
-
open(uri) {|f| @raw = f.read}
|
38
|
-
ET.logger.info "Extracted the data from a remote location."
|
39
|
-
return true
|
40
|
-
rescue
|
41
|
-
ET.logger.info "Tested whether #{uri} was a remote resource. Failed to read it."
|
42
|
-
return false
|
43
|
-
end
|
44
|
-
end
|
45
|
-
|
46
|
-
# If this is a string, assumes that the contents of the string are CSV contents.
|
47
|
-
def extract_from_string(string)
|
48
|
-
@raw = string if string.is_a?(String)
|
49
|
-
@raw ? true : false
|
22
|
+
source = self.options.fetch(:source, nil)
|
23
|
+
@raw = OpenContent::Extractor.process(source, ET.logger)
|
50
24
|
end
|
51
25
|
|
52
26
|
def transform
|
@@ -0,0 +1,19 @@
|
|
1
|
+
# Requires data_frame (sudo gem install davidrichards-data_frame)
|
2
|
+
# gem 'davidrichards-data_frame'
|
3
|
+
# require 'data_frame'
|
4
|
+
#
|
5
|
+
# # This is a simple tool that converts RDF to DataFrames. It uses the
|
6
|
+
# # subjects as the rows, the objects as the columns, and the predicates
|
7
|
+
# # as the values. This can make the data much more accessible by more
|
8
|
+
# # analysis tools.
|
9
|
+
# class RDF2DataFrame < ETL
|
10
|
+
#
|
11
|
+
# def extract
|
12
|
+
# source = self.options.fetch(:source, nil)
|
13
|
+
# @raw = OpenContent::Extractor.process(source, RDF2DataFrame.logger)
|
14
|
+
# end
|
15
|
+
#
|
16
|
+
# def transform
|
17
|
+
# # TODO
|
18
|
+
# end
|
19
|
+
# end
|
@@ -0,0 +1 @@
|
|
1
|
+
Dir.glob("#{File.dirname(__FILE__)}/open_content/*.rb").each { |file| require file }
|
@@ -0,0 +1,43 @@
|
|
1
|
+
require 'open-uri'
|
2
|
+
module OpenContent
|
3
|
+
class Extractor
|
4
|
+
class << self
|
5
|
+
|
6
|
+
attr_reader :logger
|
7
|
+
|
8
|
+
def process(source, logger)
|
9
|
+
@logger = logger
|
10
|
+
extract_locally(source) or extract_remotely(source) or extract_from_string(source)
|
11
|
+
raise ArgumentError, "Could not determine what #{source.inspect} was. Cannot extract this data." unless @raw
|
12
|
+
@raw
|
13
|
+
end
|
14
|
+
|
15
|
+
protected
|
16
|
+
# Handles local filename cases, reading the contents of the file.
|
17
|
+
def extract_locally(filename)
|
18
|
+
@raw = File.read(filename) if File.exist?(filename)
|
19
|
+
self.logger.info "Extracted the data from from filesystem" if @raw
|
20
|
+
@raw ? true : false
|
21
|
+
end
|
22
|
+
|
23
|
+
# Handles remote uri cases, reading the remote resource with open-uri, part of the Standard Library
|
24
|
+
def extract_remotely(uri)
|
25
|
+
begin
|
26
|
+
open(uri) {|f| @raw = f.read}
|
27
|
+
self.logger.info "Extracted the data from a remote location."
|
28
|
+
return true
|
29
|
+
rescue
|
30
|
+
self.logger.info "Tested whether #{uri} was a remote resource. Failed to read it."
|
31
|
+
return false
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
# If this is a string, assumes that the contents of the string are CSV contents.
|
36
|
+
def extract_from_string(string)
|
37
|
+
@raw = string if string.is_a?(String)
|
38
|
+
@raw ? true : false
|
39
|
+
end
|
40
|
+
|
41
|
+
end
|
42
|
+
end
|
43
|
+
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: davidrichards-etl
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.6
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- David Richards
|
@@ -9,7 +9,7 @@ autorequire:
|
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
11
|
|
12
|
-
date: 2009-08-
|
12
|
+
date: 2009-08-09 00:00:00 -07:00
|
13
13
|
default_executable: etl
|
14
14
|
dependencies:
|
15
15
|
- !ruby/object:Gem::Dependency
|
@@ -50,12 +50,16 @@ files:
|
|
50
50
|
- lib/etl/bucket.rb
|
51
51
|
- lib/etl/csv_et.rb
|
52
52
|
- lib/etl/etl.rb
|
53
|
+
- lib/etl/rdf_2_data_frame.rb
|
53
54
|
- lib/etl/time_bucket.rb
|
54
55
|
- lib/etl/xml_et.rb
|
55
56
|
- lib/etl.rb
|
56
57
|
- lib/helpers
|
57
58
|
- lib/helpers/array.rb
|
58
59
|
- lib/helpers/observation.rb
|
60
|
+
- lib/helpers/open_content
|
61
|
+
- lib/helpers/open_content/extractor.rb
|
62
|
+
- lib/helpers/open_content.rb
|
59
63
|
- lib/helpers/open_struct.rb
|
60
64
|
- lib/helpers/string.rb
|
61
65
|
- lib/helpers/symbol.rb
|