data_collector 0.28.0 → 0.29.0
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 +4 -4
- data/lib/data_collector/input.rb +5 -5
- data/lib/data_collector/version.rb +1 -1
- data/lib/data_collector.rb +4 -2
- 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: d09248a6f7a15b7c6ad783502506e9cdc3ba5010070a810b9bc8c803b15fc862
|
|
4
|
+
data.tar.gz: d47019eddd26810162229555997d957f35823e45b105036cbd1e4f90d361be81
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 8f508edbc7ad18d413bf6deac82c0848ab04955edd347b2a749b0ecf8baf3caef4052fdcd8b424d6b17e82b8da18e4f9cc8b40160d1b22566241986a4d5c6e7c
|
|
7
|
+
data.tar.gz: 4c339eb2adc53e2afe615a9b1ebca1649c0466c51366babd574bf7bdfbb4ef0c8df121308561514c69dc6fcd31cd6c4fa6e8d689ab0cff0e9bcff9554f96f85a
|
data/lib/data_collector/input.rb
CHANGED
|
@@ -28,7 +28,7 @@ module DataCollector
|
|
|
28
28
|
def from_uri(source, options = {})
|
|
29
29
|
source = CGI.unescapeHTML(source)
|
|
30
30
|
@logger.info("Reading #{source}")
|
|
31
|
-
raise DataCollector::Error 'from_uri expects a scheme like file:// of https://' unless source =~ /:\/\//
|
|
31
|
+
raise DataCollector::Error, 'from_uri expects a scheme like file:// of https://' unless source =~ /:\/\//
|
|
32
32
|
|
|
33
33
|
scheme, path = source.split('://')
|
|
34
34
|
source="#{scheme}://#{URI.encode_www_form_component(path)}"
|
|
@@ -67,13 +67,13 @@ module DataCollector
|
|
|
67
67
|
data
|
|
68
68
|
end
|
|
69
69
|
rescue DataCollector::InputError => e
|
|
70
|
-
@logger.
|
|
70
|
+
@logger.error(e.message)
|
|
71
71
|
raise e
|
|
72
72
|
rescue DataCollector::Error => e
|
|
73
|
-
@logger.
|
|
73
|
+
@logger.error(e.message)
|
|
74
74
|
nil
|
|
75
75
|
rescue StandardError => e
|
|
76
|
-
@logger.
|
|
76
|
+
@logger.error(e.message)
|
|
77
77
|
puts e.backtrace.join("\n")
|
|
78
78
|
nil
|
|
79
79
|
end
|
|
@@ -220,11 +220,11 @@ module DataCollector
|
|
|
220
220
|
|
|
221
221
|
def xml_to_hash(data, options = {})
|
|
222
222
|
#gsub('<\/', '< /') outherwise wrong XML-parsing (see records lirias1729192 )
|
|
223
|
+
data.force_encoding('UTF-8') #encode("UTF-8", invalid: :replace, replace: "")
|
|
223
224
|
data = data.gsub /</, '< /'
|
|
224
225
|
xml_typecast = options.with_indifferent_access.key?('xml_typecast') ? options.with_indifferent_access['xml_typecast'] : true
|
|
225
226
|
nori = Nori.new(parser: :nokogiri, advanced_typecasting: xml_typecast, strip_namespaces: true, convert_tags_to: lambda { |tag| tag.gsub(/^@/, '_') })
|
|
226
227
|
nori.parse(data)
|
|
227
|
-
#JSON.parse(nori.parse(data).to_json)
|
|
228
228
|
end
|
|
229
229
|
|
|
230
230
|
def csv_to_hash(data)
|
data/lib/data_collector.rb
CHANGED
|
@@ -8,7 +8,9 @@ require 'data_collector/pipeline'
|
|
|
8
8
|
require 'data_collector/ext/xml_utility_node'
|
|
9
9
|
|
|
10
10
|
module DataCollector
|
|
11
|
-
class Error < StandardError
|
|
11
|
+
class Error < StandardError
|
|
12
|
+
end
|
|
12
13
|
|
|
13
|
-
class InputError <
|
|
14
|
+
class InputError < Error
|
|
15
|
+
end
|
|
14
16
|
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: 0.29.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Mehmet Celik
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: exe
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2023-08-
|
|
11
|
+
date: 2023-08-08 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: activesupport
|