data_collector 0.25.0 → 0.27.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +5 -1
- data/lib/data_collector/input/rpc.rb +1 -1
- data/lib/data_collector/input.rb +25 -13
- data/lib/data_collector/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: b001584d7cb8f525f22370a79a4921104358f9de512d81da6236f65a590220bc
|
4
|
+
data.tar.gz: 773bf24b624e28e056a82f0c665e603a119830c9cc872d1938be02ab7251ad03
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 8d0a62ddf8408c72e6277080f7105bd8d12f39c2f30e4a44910d890932a50ef9399d096d98b990b87db422a6af7557821e45045a049c64ebbdd90d8cd811062c
|
7
|
+
data.tar.gz: 53e2290744797a8763ccd0491a02c9dd1ee4e73919f95c20d66bb03889cca18f31cb4090728f1ef3acee6b76ef9e062f4196d17b90b5bf0ec3d2132e74543c2a
|
data/README.md
CHANGED
@@ -8,6 +8,7 @@ include DataCollector::Core
|
|
8
8
|
```
|
9
9
|
Every object can be used on its own.
|
10
10
|
|
11
|
+
### DataCollector Objects
|
11
12
|
#### Pipeline
|
12
13
|
Allows you to create a simple pipeline of operations to process data. With a data pipeline, you can collect, process, and transform data, and then transfer it to various systems and applications.
|
13
14
|
|
@@ -20,6 +21,7 @@ executed in the [ISO8601 duration format](https://www.digi.com/resources/documen
|
|
20
21
|
- schedule: [ISO8601 duration format](https://www.digi.com/resources/documentation/digidocs//90001488-13/reference/r_iso_8601_duration_format.htm)
|
21
22
|
- cron: in cron format ex. '1 12 * * *' intervals are not supported
|
22
23
|
- uri: a directory/file to watch
|
24
|
+
- xml_typecast: true/false -> convert convert string values to TrueClass, FalseClass, Time, Date, and DateTime
|
23
25
|
- .run: start the pipeline. blocking if a schedule is supplied
|
24
26
|
- .stop: stop the pipeline
|
25
27
|
- .pause: pause the pipeline. Restart using .run
|
@@ -74,12 +76,14 @@ For a push input component, a listener is created with a processing logic block
|
|
74
76
|
A push happens when new data is created in a directory, message queue, ...
|
75
77
|
|
76
78
|
```ruby
|
77
|
-
from_uri(source, options = {:raw, :content_type})
|
79
|
+
from_uri(source, options = {:raw, :content_type, :headers, :cookies})
|
78
80
|
```
|
79
81
|
- source: an uri with a scheme of http, https, file, amqp
|
80
82
|
- options:
|
81
83
|
- raw: _boolean_ do not parse
|
82
84
|
- content_type: _string_ force a content_type if the 'Content-Type' returned by the http server is incorrect
|
85
|
+
- headers: request headers
|
86
|
+
- cookies: session cookies etc.
|
83
87
|
|
84
88
|
###### example:
|
85
89
|
```ruby
|
data/lib/data_collector/input.rb
CHANGED
@@ -31,7 +31,7 @@ module DataCollector
|
|
31
31
|
raise DataCollector::Error 'from_uri expects a scheme like file:// of https://' unless source =~ /:\/\//
|
32
32
|
|
33
33
|
scheme, path = source.split('://')
|
34
|
-
source="#{scheme}://#{URI.
|
34
|
+
source="#{scheme}://#{URI.encode_www_form_component(path)}"
|
35
35
|
uri = URI(source)
|
36
36
|
begin
|
37
37
|
data = nil
|
@@ -41,7 +41,7 @@ module DataCollector
|
|
41
41
|
when 'https'
|
42
42
|
data = from_https(uri, options)
|
43
43
|
when 'file'
|
44
|
-
absolute_path = File.absolute_path("#{URI.
|
44
|
+
absolute_path = File.absolute_path("#{URI.decode_www_form_component("#{uri.host}#{uri.path}")}")
|
45
45
|
if File.directory?(absolute_path)
|
46
46
|
#raise DataCollector::Error, "#{uri.host}/#{uri.path} not found" unless File.exist?("#{uri.host}/#{uri.path}")
|
47
47
|
return from_dir(uri, options)
|
@@ -80,7 +80,7 @@ module DataCollector
|
|
80
80
|
end
|
81
81
|
|
82
82
|
def from_https(uri, options = {})
|
83
|
-
uri = URI.
|
83
|
+
uri = URI.decode_www_form_component("#{uri.to_s}")
|
84
84
|
data = nil
|
85
85
|
if options.with_indifferent_access.include?(:logging) && options.with_indifferent_access[:logging]
|
86
86
|
HTTP.default_options = HTTP::Options.new(features: { logging: { logger: @logger } })
|
@@ -102,6 +102,16 @@ module DataCollector
|
|
102
102
|
http = HTTP.auth(bearer)
|
103
103
|
end
|
104
104
|
|
105
|
+
if options.key?(:cookies)
|
106
|
+
@logger.debug "Set cookies"
|
107
|
+
http = http.cookies( options[:cookies] )
|
108
|
+
end
|
109
|
+
|
110
|
+
if options.key?(:headers)
|
111
|
+
@logger.debug "Set http headers"
|
112
|
+
http = http.headers( options[:headers] )
|
113
|
+
end
|
114
|
+
|
105
115
|
if options.key?(:verify_ssl) && uri.scheme.eql?('https')
|
106
116
|
@logger.warn "Disabling SSL verification. "
|
107
117
|
#shouldn't use this but we all do ...
|
@@ -109,10 +119,11 @@ module DataCollector
|
|
109
119
|
ctx.verify_mode = OpenSSL::SSL::VERIFY_NONE
|
110
120
|
|
111
121
|
http_response = http.follow.get(escape_uri(uri), ssl_context: ctx)
|
122
|
+
|
112
123
|
else
|
113
124
|
http_response = http.follow.get(escape_uri(uri))
|
114
125
|
end
|
115
|
-
|
126
|
+
|
116
127
|
case http_response.code
|
117
128
|
when 200..299
|
118
129
|
@raw = data = http_response.body.to_s
|
@@ -130,15 +141,15 @@ module DataCollector
|
|
130
141
|
when 'application/json'
|
131
142
|
data = JSON.parse(data)
|
132
143
|
when 'application/atom+xml'
|
133
|
-
data = xml_to_hash(data)
|
144
|
+
data = xml_to_hash(data, options)
|
134
145
|
when 'text/csv'
|
135
146
|
data = csv_to_hash(data)
|
136
147
|
when 'application/xml'
|
137
|
-
data = xml_to_hash(data)
|
148
|
+
data = xml_to_hash(data, options)
|
138
149
|
when 'text/xml'
|
139
|
-
data = xml_to_hash(data)
|
150
|
+
data = xml_to_hash(data, options)
|
140
151
|
else
|
141
|
-
data = xml_to_hash(data)
|
152
|
+
data = xml_to_hash(data, options)
|
142
153
|
end
|
143
154
|
end
|
144
155
|
|
@@ -171,14 +182,14 @@ module DataCollector
|
|
171
182
|
when '.json'
|
172
183
|
data = JSON.parse(data)
|
173
184
|
when '.xml'
|
174
|
-
data = xml_to_hash(data)
|
185
|
+
data = xml_to_hash(data, options)
|
175
186
|
when '.gz'
|
176
187
|
Minitar.open(Zlib::GzipReader.new(File.open("#{absolute_path}", 'rb'))) do |i|
|
177
188
|
i.each do |entry|
|
178
189
|
data = entry.read
|
179
190
|
end
|
180
191
|
end
|
181
|
-
data = xml_to_hash(data)
|
192
|
+
data = xml_to_hash(data, options)
|
182
193
|
when '.csv'
|
183
194
|
data = csv_to_hash(data)
|
184
195
|
else
|
@@ -201,10 +212,11 @@ module DataCollector
|
|
201
212
|
DataCollector::Input::Rpc.new(uri, options)
|
202
213
|
end
|
203
214
|
|
204
|
-
def xml_to_hash(data)
|
215
|
+
def xml_to_hash(data, options = {})
|
205
216
|
#gsub('<\/', '< /') outherwise wrong XML-parsing (see records lirias1729192 )
|
206
217
|
data = data.gsub /</, '< /'
|
207
|
-
|
218
|
+
xml_typecast = options.with_indifferent_access.key?('xml_typecast') ? options.with_indifferent_access['xml_typecast'] : true
|
219
|
+
nori = Nori.new(parser: :nokogiri, advanced_typecasting: xml_typecast, strip_namespaces: true, convert_tags_to: lambda { |tag| tag.gsub(/^@/, '_') })
|
208
220
|
nori.parse(data)
|
209
221
|
#JSON.parse(nori.parse(data).to_json)
|
210
222
|
end
|
@@ -235,7 +247,7 @@ module DataCollector
|
|
235
247
|
end
|
236
248
|
|
237
249
|
def normalize_uri(uri)
|
238
|
-
"#{URI.
|
250
|
+
"#{URI.decode_www_form_component(uri.host)}#{URI.decode_www_form_component(uri.path)}"
|
239
251
|
end
|
240
252
|
end
|
241
253
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: data_collector
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.27.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Mehmet Celik
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2023-
|
11
|
+
date: 2023-08-04 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: activesupport
|