dwc_agent 1.4.12 → 1.5.0.4
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/cleaner.rb +6 -3
- data/lib/dwc_agent/constants.rb +21 -12
- data/lib/dwc_agent/parser.rb +4 -2
- 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: cef90f0884c7b59a1c3aae50198ef043a282127ef4b883b326a0a4b1bfdcd337
|
4
|
+
data.tar.gz: a19a07304fdd82ddd1259080a503fea4d13d5d44b60b6edb651e799a5c473525
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: bcbebc3c10b85a5a86d9d67b8dbcee31164b64c46e8626f26378b36df7a2493d0f96a527423910a8748bc45fee7a9fd6ac8633392d78882bf43ff55902e2781d
|
7
|
+
data.tar.gz: 2f7e75e44b207fc72f6c90e413ac047337362494122cfe9ce976f993fe48bd9a0407c47ff56c5991c591c1e3562e999a88cfedcb869bb2712bed787b4cd17799
|
data/lib/dwc_agent/cleaner.rb
CHANGED
@@ -16,7 +16,7 @@ module DwcAgent
|
|
16
16
|
# @param parsed_namae [Object] the namae object
|
17
17
|
# @return [Hash] the given, family hash
|
18
18
|
def clean(parsed_namae)
|
19
|
-
blank_name = { given: nil, family: nil,
|
19
|
+
blank_name = { title: nil, appellation: nil, given: nil, particle: nil, family: nil, suffix: nil }
|
20
20
|
|
21
21
|
if parsed_namae.family && FAMILY_BLACKLIST.any?{ |s| s.casecmp(parsed_namae.family) == 0 }
|
22
22
|
return blank_name
|
@@ -30,7 +30,7 @@ module DwcAgent
|
|
30
30
|
return blank_name
|
31
31
|
end
|
32
32
|
|
33
|
-
if parsed_namae.given && parsed_namae.given.length >
|
33
|
+
if parsed_namae.given && parsed_namae.given.length > 35
|
34
34
|
return blank_name
|
35
35
|
end
|
36
36
|
|
@@ -84,6 +84,9 @@ module DwcAgent
|
|
84
84
|
family = parsed_namae.family.gsub(/\.\z/, '').strip rescue nil
|
85
85
|
given = parsed_namae.given.strip rescue nil
|
86
86
|
particle = parsed_namae.particle.strip rescue nil
|
87
|
+
appellation = parsed_namae.appellation.strip rescue nil
|
88
|
+
suffix = parsed_namae.suffix.strip rescue nil
|
89
|
+
title = parsed_namae.title.strip rescue nil
|
87
90
|
|
88
91
|
if !given.nil? && given.match(/[A-Z]\.[A-Za-z]{2,}/)
|
89
92
|
given = given.gsub(".", ". ").strip
|
@@ -123,7 +126,7 @@ module DwcAgent
|
|
123
126
|
return blank_name
|
124
127
|
end
|
125
128
|
|
126
|
-
{ given: given, family: family,
|
129
|
+
{ title: title, appellation: appellation, given: given, particle: particle, family: family, suffix: suffix }
|
127
130
|
end
|
128
131
|
|
129
132
|
end
|
data/lib/dwc_agent/constants.rb
CHANGED
@@ -49,7 +49,7 @@ module DwcAgent
|
|
49
49
|
\d+\s+(?i:Nov|Novemb(er|re))\.?\b|
|
50
50
|
\d+\s+(?i:Dec|D(e|é)cemb(er|re))\.?\b|
|
51
51
|
\b[.-–,;:/]?\s*(?i:Alabama|Alaska|Arizona|Arkansas|California|Colorado|Connecticut|Delaware|Evergreen|Florida|Georgia|Hawaii|Idaho|Illinois|Indiana|Iowa|Kansas|Kentucky|Louisiana|Maine|Maryland|Massachusetts|Michigan|Minnesota|Mississippi|Missouri|Montana|Nebraska|Nevada|New\s+Hampshire|New\s+Jersey|New\s+Mexico|New\s+York|North\s+Carolina|North\s+Dakota|Ohio|Oklahoma|Oregon|Pennsylvania|Portland|Rhode\s+Island|South\s+Carolina|South\s+Dakota|St\s+Petersburg|Tennessee|Texas|Utah|Vermont|Virginia|Washington|West\s+Virginia|Wisconsin|Wyoming)\s+(?i:State)\s*\b|
|
52
|
-
\b[.,;:/]?\s*?(?i:Afghanistan|Åland Islands|Albania|Algeria|American Samoa|Andorra|Angola|Anguilla|Antarctica|Antigua and Barbuda|Argentina|Armenia|Aruba|Australia|Austria|Azerbaijan|Bahamas|Bahrain|Bangladesh|Barbados|Belarus|Belgium|Belize|Benin|Bermuda|Bhutan|Bolivia \(Plurinational State of\)|Bonaire, Sint Eustatius and Saba|Bosnia and Herzegovina|Botswana|Bouvet Island|Brazil|British Indian Ocean Territory|Brunei Darussalam|Bulgaria|Burkina Faso|Burundi|Cabo Verde|Cambodia|Cameroon|Canada|Cayman Islands|Central African Republic|Chad|Chile|China|Christmas Island|Cocos \(Keeling\) Islands|Colombia|Comoros|Congo|Congo \(Democratic Republic of the\)|Cook Islands|Costa Rica|Côte d'Ivoire|Croatia|Cuba|Curaçao|Cyprus|Czechia|Denmark|Djibouti|Dominica|Dominican Republic|Ecuador|Egypt|El Salvador|Equatorial Guinea|Eritrea|Estonia|Ethiopia|Falkland Islands \(Malvinas\)|Faroe Islands|Fiji|Finland|France|French Guiana|French Polynesia|French Southern Territories|Gabon|Gambia|Georgia|Germany|Ghana|Gibraltar|Greece|Greenland|Grenada|Guadeloupe|Guam|Guatemala|Guernsey|Guinea|Guinea-Bissau|Guyana|Haiti|Heard Island and McDonald Islands|Holy See|Honduras|Hong Kong|Hungary|Iceland|India|Indonesia|Iran \(Islamic Republic of\)|Iraq|Ireland|Isle of Man|Israel|Italy|Jamaica|Japan|Jersey|Jordan|Kazakhstan|Kenya|Kiribati|Korea \(Democratic People\'s Republic of\)|Korea \(Republic of\)|Kuwait|Kyrgyzstan|Lao People\'s Democratic Republic|Latvia|Lebanon|Lesotho|Liberia|Libya|Liechtenstein|Lithuania|Luxembourg|Macao|Macedonia (the former Yugoslav Republic of)|Madagascar|Malawi|Malaysia|Maldives|Mali|Malta|Marshall Islands|Martinique|Mauritania|Mauritius|Mayotte|Mexico|Micronesia \(Federated States of\)|Moldova \(Republic of\)|Monaco|Mongolia|Montenegro|Montserrat|Morocco|Mozambique|Myanmar|Namibia|Nauru|Nepal|Netherlands|New Caledonia|New Zealand|Nicaragua|Niger|Nigeria|Niue|Norfolk Island|Northern Mariana Islands|Norway|Oman|Pakistan|Palau|Palestine, State of|Panama|Papua New Guinea|Paraguay|Peru|Philippines|Pitcairn|Poland|Portugal|Puerto Rico|Qatar|Réunion|Romania|Russian Federation|Rwanda|Saint Barthélemy|Saint Helena, Ascension and Tristan da Cunha|Saint Kitts and Nevis|Saint Lucia|Saint Martin \(French part\)|Saint Pierre and Miquelon|Saint Vincent and the Grenadines|Samoa|San Marino|Sao Tome and Principe|Saudi Arabia|Senegal|Serbia|Seychelles|Sierra Leone|Singapore|Sint Maarten \(Dutch part\)|Slovakia|Slovenia|Solomon Islands|Somalia|South Africa|South Georgia and the South Sandwich Islands|South Sudan|Spain|Sri Lanka|Sudan|Suriname|Svalbard and Jan Mayen|Swaziland|Sweden|Switzerland|Syrian Arab Republic|Taiwan|Tajikistan|Tanzania, United Republic of|Thailand|Timor-Leste|Togo|Tokelau|Tonga|Trinidad and Tobago|Tunisia|Turkey|Turkmenistan|Turks and Caicos Islands|Tuvalu|Uganda|Ukraine|United Arab Emirates|United Kingdom of Great Britain and Northern Ireland|United States of America|United States Minor Outlying Islands|Uruguay|Uzbekistan|Vanuatu|Venezuela \(Bolivarian Republic of\)|Viet Nam|Virgin Islands \(British\)|Virgin Islands \(U\.S\.\)|Wallis and Futuna|Western Sahara|Yemen|Zambia|Zimbabwe)|
|
52
|
+
\b[.,;:/]?\s*?(?i:Afghanistan|Åland Islands|Albania|Algeria|American Samoa|Andorra|Angola|Anguilla|Antarctica|Antigua and Barbuda|Argentina|Armenia|Aruba|Australia|Austria|Azerbaijan|Bahamas|Bahrain|Bangladesh|Barbados|Belarus|Belgium|Belize|Benin|Bermuda|Bhutan|Bolivia \(Plurinational State of\)|Bonaire, Sint Eustatius and Saba|Bosnia and Herzegovina|Botswana|Bouvet Island|Brazil|British Indian Ocean Territory|Brunei Darussalam|Bulgaria|Burkina Faso|Burundi|Cabo Verde|Cambodia|Cameroon|Canada|Cayman Islands|Central African Republic|Chad|Chile|China|Christmas Island|Cocos \(Keeling\) Islands|Colombia|Comoros|Congo|Congo \(Democratic Republic of the\)|Cook Islands|Costa Rica|Côte d'Ivoire|Croatia|Cuba|Curaçao|Cyprus|Czechia|Denmark|Djibouti|Dominica|Dominican Republic|Ecuador|Egypt|El Salvador|Equatorial Guinea|Eritrea|Estonia|Ethiopia|Falkland Islands \(Malvinas\)|Faroe Islands|Fiji|Finland|France|French Guiana|French Polynesia|French Southern Territories|Gabon|Gambia|Georgia|Germany|Ghana|Gibraltar|Greece|Greenland|Grenada|Guadeloupe|Guam|Guatemala|Guernsey|Guinea|Guinea-Bissau|Guyana|Haiti|Heard Island and McDonald Islands|Holy See|Honduras|Hong Kong|Hungary|Iceland|India|Indonesia|Iran \(Islamic Republic of\)|Iraq|Ireland|Isle of Man|Israel|Italy|Jamaica|Japan|Jersey|Jordan|Kazakhstan|Kenya|Kiribati|Korea \(Democratic People\'s Republic of\)|Korea \(Republic of\)|Kuwait|Kyrgyzstan|Lao People\'s Democratic Republic|Latvia|Lebanon|Lesotho|Liberia|Libya|Liechtenstein|Lithuania|Luxembourg|Macao|Macedonia (the former Yugoslav Republic of)|Madagascar|Malawi|Malaysia|Maldives|Mali|Malta|Marshall Islands|Martinique|Mauritania|Mauritius|Mayotte|Mexico|Micronesia \(Federated States of\)|Moldova \(Republic of\)|Monaco|Mongolia|Montenegro|Montserrat|Morocco|Mozambique|Myanmar|Namibia|Nauru|Nepal|Netherlands|New Caledonia|New Zealand|Nicaragua|Niger|Nigeria|Niue|Norfolk Island|Northern Mariana Islands|Norway|Oman|Pakistan|Palau|Palestine, State of|Panama|Papua New Guinea|Paraguay|Peru|Philippines|Pitcairn|Poland|Portugal|Puerto Rico|Qatar|Réunion|Romania|Russian Federation|Rwanda|Saint Barthélemy|Saint Helena, Ascension and Tristan da Cunha|Saint Kitts and Nevis|Saint Lucia|Saint Martin \(French part\)|Saint Pierre and Miquelon|Saint Vincent and the Grenadines|Samoa|San Marino|Sao Tome and Principe|Saudi Arabia|Senegal|Serbia|Seychelles|Sierra Leone|Singapore|Sint Maarten \(Dutch part\)|Slovakia|Slovenia|Solomon Islands|Somalia|South Africa|South Georgia and the South Sandwich Islands|South Sudan|Spain|Sri Lanka|Sudan|Suriname|Svalbard and Jan Mayen|Swaziland|Sweden|Switzerland|Syrian Arab Republic|Taiwan|Tajikistan|Tanzania, United Republic of|Thailand|Timor-Leste|Togo|Tokelau|Tonga|Trinidad and Tobago|Tunisia|Turkey|Turkmenistan|Turks and Caicos Islands|Tuvalu|Uganda|Ukraine|United Arab Emirates|United Kingdom of Great Britain and Northern Ireland|United States of America|United States Minor Outlying Islands|Uruguay|Uzbekistan|Vanuatu|Venezuela \(Bolivarian Republic of\)|Viet Nam|Virgin Islands \(British\)|Virgin Islands \(U\.S\.\)|Wallis and Futuna|Western Sahara|Yemen|Zambia|Zimbabwe)\b|
|
53
53
|
(?i:autres?\s+de|probab|likely|possibl(e|y)|doubtful)|
|
54
54
|
\b\s*(?i:maybe)\s*\b|
|
55
55
|
\b\s*(?i:prob)\.\s*\b|
|
@@ -61,7 +61,7 @@ module DwcAgent
|
|
61
61
|
(?i:see\s+notes?\s*(inside)?)|
|
62
62
|
(?i:see\s+letter\s+enclosed)|
|
63
63
|
(?i:(by)?\s+correspondance)|
|
64
|
-
(?i:pers\.?\s
|
64
|
+
(?i:pers\.?\s*comm\.?)|
|
65
65
|
(?i:crossed\s+out)|
|
66
66
|
\(?(?i:source)\(?|
|
67
67
|
(?i:according\s+to)|
|
@@ -113,19 +113,22 @@ module DwcAgent
|
|
113
113
|
[–|ǀ∣|│&+\/;:]|
|
114
114
|
\s+-\s+|
|
115
115
|
\s+a\.\s+|
|
116
|
-
\b(e|y|i|en|et|or|per|for)\s*\b|
|
116
|
+
\b(con|e|y|i|en|et|or|per|for)\s*\b|
|
117
117
|
\b(?i:and|with)\s*\b|
|
118
118
|
\b(?i:annotated(\s+by)?)\s*\b|
|
119
119
|
\b(?i:coll\.)\s*\b|
|
120
120
|
\b(?i:communicate?d(\s+to)?)\s*\b|
|
121
121
|
\b(?i:conf\.?(\s+by)?|confirmed(\s+by)?)\s*\b|
|
122
|
+
\b(?i:confirmada)(\s+por)?\s*\b|
|
122
123
|
\b(?i:checked?(\s+by)?)\s*\b|
|
123
124
|
\b(?i:det\.?(\s+by)?)\s*\b|
|
124
125
|
\b(?i:dupl?\.?(\s+by)?|duplicate(\s+by)?)\s*\b|
|
125
126
|
\b(?i:ex\.?(\s+by)?|examined(\s+by)?)\s*\b|
|
126
127
|
\b(?i:in?dentified(\s+by)?)\s*\b|
|
127
128
|
\b(?i:in\s+part(\s+by)?)\s*\b|
|
129
|
+
\b(?i:och)\s*\b|
|
128
130
|
\b(?i:prep\.?\s+(?i:by)?)\s*\b|
|
131
|
+
\b(?i:purchased?)(\s+by)?\s*\b|
|
129
132
|
\b(?i:redet\.?(\s+by?)?)\s*\b|
|
130
133
|
\b(?i:reidentified(\s+by)?)\s*\b|
|
131
134
|
\b(?i:stet)\s*\b|
|
@@ -159,16 +162,18 @@ module DwcAgent
|
|
159
162
|
}
|
160
163
|
|
161
164
|
PHRASE_SUBS = {
|
162
|
-
'
|
163
|
-
'
|
164
|
-
'
|
165
|
-
'
|
166
|
-
'prof\.' => 'Prof. ',
|
167
|
-
'\, ph\.d\.' => ' Ph.D.',
|
168
|
-
'\, bro\.' => ' Bro.',
|
169
|
-
' jr\.,' => ' Jr.;',
|
165
|
+
', ph.d.' => ' Ph.D.',
|
166
|
+
', Ph.D.' => ' Ph.D.',
|
167
|
+
', bro.' => ' Bro.',
|
168
|
+
' jr.,' => ' Jr.;',
|
170
169
|
' jr,' => ' Jr.;',
|
171
|
-
'-
|
170
|
+
'-jr' => ' Jr.',
|
171
|
+
'-Jr' => ' Jr.',
|
172
|
+
', Jr.' => ' Jr.',
|
173
|
+
',Jr.' => ' Jr.',
|
174
|
+
', Sr.' => ' Sr.',
|
175
|
+
',Sr.' => ' Sr.'
|
176
|
+
|
172
177
|
}
|
173
178
|
|
174
179
|
COMPLEX_SEPARATORS = %r{
|
@@ -274,4 +279,8 @@ module DwcAgent
|
|
274
279
|
|
275
280
|
TITLE = /\s*\b(sir|count(ess)?|colonel|(gen|adm|col|maj|capt|cmdr|lt|sgt|cpl|pvt|prof|dr|md|ph\.?d|rev|mme|abbé|ptre|bro|esq)\.?|docteur|father|cantor|vicar|père|pastor|rabbi|reverend|pere|soeur|sister|professor)(\s+|$)/i
|
276
281
|
|
282
|
+
APPELLATION = /\s*\b((mrs?|ms|fr|hr)\.?|miss|herr|frau)(\s+|$)/i
|
283
|
+
|
284
|
+
SUFFIX = /\s*\b(JR|Jr|jr|SR|Sr|sr|[IVX]{2,})(\.|\b)/
|
285
|
+
|
277
286
|
end
|
data/lib/dwc_agent/parser.rb
CHANGED
@@ -11,14 +11,16 @@ module DwcAgent
|
|
11
11
|
options = {
|
12
12
|
prefer_comma_as_separator: true,
|
13
13
|
separator: SPLIT_BY,
|
14
|
-
title: TITLE
|
14
|
+
title: TITLE,
|
15
|
+
appellation: APPELLATION,
|
16
|
+
suffix: SUFFIX
|
15
17
|
}
|
16
18
|
@namae = Namae::Parser.new(options)
|
17
19
|
|
18
20
|
@strip_out_regex = Regexp.new STRIP_OUT.to_s
|
19
21
|
@residual_terminators_regex = Regexp.new SPLIT_BY.to_s + %r{\s*\z}.to_s
|
20
22
|
@char_subs_regex = Regexp.new [CHAR_SUBS.keys.join].to_s
|
21
|
-
@phrase_subs_regex = Regexp.new
|
23
|
+
@phrase_subs_regex = Regexp.new PHRASE_SUBS.keys.map{|a| Regexp.escape a }.join('|').to_s
|
22
24
|
@complex_separators_regex = Regexp.new COMPLEX_SEPARATORS.to_s
|
23
25
|
@add_separators_regex = Regexp.new %r{(\S{1}\.)([[:alpha:]]{2,})}.to_s
|
24
26
|
end
|
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: 1.4
|
4
|
+
version: 1.5.0.4
|
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: 2020-08-
|
11
|
+
date: 2020-08-16 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: namae
|