dwc_agent 3.3.1.0 → 3.4.0.0
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/dwc_agent/constants.rb +2 -5
- data/lib/dwc_agent/parser.rb +5 -6
- data/lib/dwc_agent/version.rb +3 -3
- 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: a8c59f7eec17563af7a1e0ab3a931055d8181c7331f4ad4e569a61a4a05a07b8
|
4
|
+
data.tar.gz: 204d62a3fd1d5e003e455f271813d38691e00710a7e47b50e87bb60b7a4b7a90
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: b1872d38cdc1983d090850a4d0eb313c84f9b5a5c753d4a1af39fc016a3306245224f23f3fb021e1543f59646f685ba21167e80aef30bebb414349a0f675929a
|
7
|
+
data.tar.gz: 5fb3deb9a940f9407abeda5d558a2275bcc4df8180f5966e26af6692d74c044b3af88f4732a26185e2362a35d42883d45d47f1555ce9fecc10d9f0a5c37c91c9
|
data/lib/dwc_agent/constants.rb
CHANGED
@@ -202,10 +202,7 @@ module DwcAgent
|
|
202
202
|
'%' => '',
|
203
203
|
'\\' => '',
|
204
204
|
'´' => '\'',
|
205
|
-
'+' => ' | '
|
206
|
-
}
|
207
|
-
|
208
|
-
PHRASE_SUBS = {
|
205
|
+
'+' => ' | ',
|
209
206
|
', ph.d.' => ' Ph.D.',
|
210
207
|
', Ph.D.' => ' Ph.D.',
|
211
208
|
', bro.' => ' Bro.',
|
@@ -224,7 +221,7 @@ module DwcAgent
|
|
224
221
|
', &' => ' &'
|
225
222
|
}
|
226
223
|
|
227
|
-
|
224
|
+
COMPLEX_SEPARATORS = {
|
228
225
|
"^(\\S{4,}),\\s+(Mrs?\\.|MRS?\\.)\\s+([A-Za-z\\.\\s]+)$" => "\\2 \\3 \\1",
|
229
226
|
"^(Mrs?\\.?)\\s+&\\s+(Mrs?\\.?)\\s+(.*)$" => "\\1 \\3 | \\2 \\3",
|
230
227
|
"^([A-Z]{1}\\.\\s*[[:alpha:]]+),\\s*?([A-Z.]+)$" => "\\1 \\2",
|
data/lib/dwc_agent/parser.rb
CHANGED
@@ -10,10 +10,9 @@ module DwcAgent
|
|
10
10
|
suffix: SUFFIX,
|
11
11
|
strip_out_regex: Regexp.new(STRIP_OUT.to_s),
|
12
12
|
tidy_remains_regex: Regexp.new(POST_STRIP_TIDY.to_s),
|
13
|
-
|
14
|
-
|
15
|
-
residual_terminators_regex: Regexp.new(SPLIT_BY.to_s + %r{\s*\z}.to_s)
|
16
|
-
separators: SEPARATORS.map{|k,v| [ Regexp.new(k), v] }
|
13
|
+
subs_regex: Regexp.new(CHAR_SUBS.keys.map{|a| Regexp.escape a }.join('|').to_s),
|
14
|
+
complex_separators_regex: COMPLEX_SEPARATORS.map{|k,v| [Regexp.new(k), v] },
|
15
|
+
residual_terminators_regex: Regexp.new(SPLIT_BY.to_s + %r{\s*\z}.to_s)
|
17
16
|
}
|
18
17
|
|
19
18
|
class << self
|
@@ -39,8 +38,8 @@ module DwcAgent
|
|
39
38
|
return [] if name.nil? || name == ""
|
40
39
|
name.gsub!(options[:strip_out_regex], ' ')
|
41
40
|
name.gsub!(options[:tidy_remains_regex], '')
|
42
|
-
name.gsub!(
|
43
|
-
options[:
|
41
|
+
name.gsub!(options[:subs_regex], CHAR_SUBS)
|
42
|
+
options[:complex_separators_regex].each{|k| name.gsub!(k[0], k[1])}
|
44
43
|
name.gsub!(options[:residual_terminators_regex], '')
|
45
44
|
name.squeeze!(' ')
|
46
45
|
name.strip!
|
data/lib/dwc_agent/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: dwc_agent
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 3.
|
4
|
+
version: 3.4.0.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- David P. Shorthouse
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2025-
|
11
|
+
date: 2025-08-20 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: namae
|