anystyle-parser 0.5.1 → 0.5.2
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/HISTORY.md +2 -1
- data/lib/anystyle/parser/normalizer.rb +1 -2
- data/lib/anystyle/parser/version.rb +1 -1
- data/spec/anystyle/parser/normalizer_spec.rb +12 -0
- metadata +1 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: c5471f4465579c6aec53ffee37f8e337075934fd
|
|
4
|
+
data.tar.gz: e32a68bbbe093abd3c44df90df5524325afc9f7e
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: cf520db7b3e31bfe1bd02b03b3d8a951a6288e6d10055ceeccf0b515d3f45e1a83abce911cb698839169c75cf9cac8d2e4169ea54d5db900b25b134b7caffd39
|
|
7
|
+
data.tar.gz: ebc4173949674553f396dbba6631fae165493f47f748288edad5ccf4fdee33b4e0a2fe7b6a54c5fc0c95e79f8bbbf991a03f62dff202fb6ec949a1098ec1ab24
|
data/HISTORY.md
CHANGED
|
@@ -312,8 +312,7 @@ module Anystyle
|
|
|
312
312
|
url, *dangling = hash[:url]
|
|
313
313
|
unmatched(:url, hash, dangling) unless dangling.empty?
|
|
314
314
|
|
|
315
|
-
url
|
|
316
|
-
hash[:isbn] = isbn
|
|
315
|
+
hash[:url] = url[/([a-z]+:\/\/)?\w+\.\w+[\w\.\/%-]+/i] || url
|
|
317
316
|
hash
|
|
318
317
|
end
|
|
319
318
|
|
|
@@ -58,6 +58,18 @@ module Anystyle
|
|
|
58
58
|
end
|
|
59
59
|
end
|
|
60
60
|
|
|
61
|
+
describe 'URL extraction' do
|
|
62
|
+
it 'recognizes full URLs' do
|
|
63
|
+
n.normalize_url(:url => 'Available at: https://www.example.org/x.pdf').should == { :url => 'https://www.example.org/x.pdf' }
|
|
64
|
+
n.normalize_url(:url => 'Available at: https://www.example.org/x.pdf [Retrieved today]').should == { :url => 'https://www.example.org/x.pdf' }
|
|
65
|
+
end
|
|
66
|
+
|
|
67
|
+
it 'tries to detect URLs without protocol' do
|
|
68
|
+
n.normalize_url(:url => 'Available at: www.example.org/x.pdf').should == { :url => 'www.example.org/x.pdf' }
|
|
69
|
+
n.normalize_url(:url => 'Available at: example.org/x.pdf [Retrieved today]').should == { :url => 'example.org/x.pdf' }
|
|
70
|
+
end
|
|
71
|
+
end
|
|
72
|
+
|
|
61
73
|
describe 'date extraction' do
|
|
62
74
|
it 'extracts month and year from a string like "(July 2009)"' do
|
|
63
75
|
h = Normalizer.instance.normalize_date(:date => '(July 2009)')
|