dwc_agent 1.5.0 → 1.5.0.5
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 +4 -4
- data/lib/dwc_agent/constants.rb +29 -13
- data/lib/dwc_agent/parser.rb +1 -1
- data/lib/dwc_agent/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: 0445f35092b28cfbcc273d01f90eee34c9642d7fc8b9c0b7e32e7720dc2f316b
|
4
|
+
data.tar.gz: f10b0b6424007a829196851ece90d6138693dcd1825b6b5712a96b9b9a2ce224
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 69d6e2be09b6edc55b5ebd0fef931dd5fcaf9df09b150bcd4580a9aace8c24576db65ea194352c134418f974b4cbfc0bf3254a1d4e22132f56203afcc06dbc08
|
7
|
+
data.tar.gz: 467f50b23cb2d3cf8ad406b9cd14c3bdbd6635806c46304be7a0708a03755c23db56f0295dd2d89f8325dbc7ac1a3c34b237103974bb27a62ab38446838b21bd
|
data/lib/dwc_agent/cleaner.rb
CHANGED
@@ -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
|
|
@@ -85,8 +85,8 @@ module DwcAgent
|
|
85
85
|
given = parsed_namae.given.strip rescue nil
|
86
86
|
particle = parsed_namae.particle.strip rescue nil
|
87
87
|
appellation = parsed_namae.appellation.strip rescue nil
|
88
|
-
suffix =
|
89
|
-
title =
|
88
|
+
suffix = parsed_namae.suffix.strip rescue nil
|
89
|
+
title = parsed_namae.title.strip rescue nil
|
90
90
|
|
91
91
|
if !given.nil? && given.match(/[A-Z]\.[A-Za-z]{2,}/)
|
92
92
|
given = given.gsub(".", ". ").strip
|
@@ -126,7 +126,7 @@ module DwcAgent
|
|
126
126
|
return blank_name
|
127
127
|
end
|
128
128
|
|
129
|
-
{ title:
|
129
|
+
{ title: title, appellation: appellation, given: given, particle: particle, family: family, suffix: suffix }
|
130
130
|
end
|
131
131
|
|
132
132
|
end
|
data/lib/dwc_agent/constants.rb
CHANGED
@@ -6,15 +6,16 @@ module DwcAgent
|
|
6
6
|
\s*?\d+\.\d+|
|
7
7
|
\b\d+\(?(?i:[[:alpha:]])\)?\b|
|
8
8
|
\b[,;]?\s*(?i:et\.?\s+al|&\s+al)\.?|
|
9
|
+
\b[,;]?\s*(?i:etal)\.?|
|
9
10
|
\b\s+(bis|ter)(\b|\z)|
|
10
11
|
\bu\.\s*a\.|
|
11
|
-
\b[,;]?\s*(?i:and|&)?\s*(?i:others)\s*\b|
|
12
|
+
\b[,;]?\s*(?i:and|&)?\s*(?i:others|party)\s*\b|
|
12
13
|
\b[,;]?\s*(?i:etc)\.?|
|
13
14
|
\b[,;]?\s*(?i:on)\b|
|
14
15
|
\b[,;]?\s*(?i:unkn?own)\b|
|
15
16
|
\b[,;]?\s*(?i:n/a)\b|
|
16
17
|
\b[,;]?\s*(?i:ann?onymous)\b|
|
17
|
-
\b[,;]?\s*\(?(?i:undetermined|indeterminable|dummy|interim|accession|ill(eg|is)ible|scripsit|presumed
|
18
|
+
\b[,;]?\s*\(?(?i:undetermined|indeterminable|dummy|interim|accession|ill(eg|is)ible|scripsit|presumed?|presumably)\)?\b|
|
18
19
|
\b[,;]?\s*(?i:importer|gift)\:?\b|
|
19
20
|
\b[,;]?\s*(?i:string)\b|
|
20
21
|
\b[,;]?\s*(?i:person\s*string)\b|
|
@@ -49,7 +50,7 @@ module DwcAgent
|
|
49
50
|
\d+\s+(?i:Nov|Novemb(er|re))\.?\b|
|
50
51
|
\d+\s+(?i:Dec|D(e|é)cemb(er|re))\.?\b|
|
51
52
|
\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)|
|
53
|
+
\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
54
|
(?i:autres?\s+de|probab|likely|possibl(e|y)|doubtful)|
|
54
55
|
\b\s*(?i:maybe)\s*\b|
|
55
56
|
\b\s*(?i:prob)\.\s*\b|
|
@@ -61,7 +62,7 @@ module DwcAgent
|
|
61
62
|
(?i:see\s+notes?\s*(inside)?)|
|
62
63
|
(?i:see\s+letter\s+enclosed)|
|
63
64
|
(?i:(by)?\s+correspondance)|
|
64
|
-
(?i:pers\.?\s
|
65
|
+
(?i:pers\.?\s*comm\.?)|
|
65
66
|
(?i:crossed\s+out)|
|
66
67
|
\(?(?i:source)\(?|
|
67
68
|
(?i:according\s+to)|
|
@@ -83,11 +84,14 @@ module DwcAgent
|
|
83
84
|
\b(?i:to\s+(sub)?spp?)\.?|
|
84
85
|
(?i:nom\.?\s+rev\.?)|
|
85
86
|
FNA|DAO|HUH|FDNMB|MNHN|PNI|USNM|ZMUC|CSIRO|ACAD|USGS|NAWQA|
|
87
|
+
\b,?\s*(?i:para|topo|syn)?(?i:type)|
|
86
88
|
AFSC\/POLISH\s+SORTING\s+CTR\.?|
|
87
89
|
(?i:university|museum|exhibits?)|
|
88
90
|
(?i:uqam)|
|
89
91
|
(?i:sem\s+(colec?tor|data))|
|
90
92
|
(?i:no\s+coll\.?(ector)?)|
|
93
|
+
(?i:not?)\s+(?i:name|date|details?|specific)?\s*?(?i:given|name|date|noted)|
|
94
|
+
(?i:non?)\s+(?i:specificato)|
|
91
95
|
\b[,;]\s+\d+\z|
|
92
96
|
["!@?]|
|
93
97
|
[,]?\d+|
|
@@ -113,19 +117,22 @@ module DwcAgent
|
|
113
117
|
[–|ǀ∣|│&+\/;:]|
|
114
118
|
\s+-\s+|
|
115
119
|
\s+a\.\s+|
|
116
|
-
\b(e|y|i|en|et|or|per|for)\s*\b|
|
120
|
+
\b(con|e|y|i|en|et|or|per|for)\s*\b|
|
117
121
|
\b(?i:and|with)\s*\b|
|
118
122
|
\b(?i:annotated(\s+by)?)\s*\b|
|
119
123
|
\b(?i:coll\.)\s*\b|
|
120
124
|
\b(?i:communicate?d(\s+to)?)\s*\b|
|
121
125
|
\b(?i:conf\.?(\s+by)?|confirmed(\s+by)?)\s*\b|
|
126
|
+
\b(?i:confirmada)(\s+por)?\s*\b|
|
122
127
|
\b(?i:checked?(\s+by)?)\s*\b|
|
123
128
|
\b(?i:det\.?(\s+by)?)\s*\b|
|
124
129
|
\b(?i:dupl?\.?(\s+by)?|duplicate(\s+by)?)\s*\b|
|
125
130
|
\b(?i:ex\.?(\s+by)?|examined(\s+by)?)\s*\b|
|
126
131
|
\b(?i:in?dentified(\s+by)?)\s*\b|
|
127
132
|
\b(?i:in\s+part(\s+by)?)\s*\b|
|
133
|
+
\b(?i:och)\s*\b|
|
128
134
|
\b(?i:prep\.?\s+(?i:by)?)\s*\b|
|
135
|
+
\b(?i:purchased?)(\s+by)?\s*\b|
|
129
136
|
\b(?i:redet\.?(\s+by?)?)\s*\b|
|
130
137
|
\b(?i:reidentified(\s+by)?)\s*\b|
|
131
138
|
\b(?i:stet)\s*\b|
|
@@ -155,16 +162,24 @@ module DwcAgent
|
|
155
162
|
'}' => '',
|
156
163
|
'@' => '',
|
157
164
|
'%' => '',
|
158
|
-
'\\' => ''
|
165
|
+
'\\' => '',
|
166
|
+
'´' => '\'',
|
167
|
+
'+' => ' | '
|
159
168
|
}
|
160
169
|
|
161
170
|
PHRASE_SUBS = {
|
162
|
-
'
|
163
|
-
'
|
164
|
-
'
|
165
|
-
'
|
166
|
-
'
|
167
|
-
'
|
171
|
+
', ph.d.' => ' Ph.D.',
|
172
|
+
', Ph.D.' => ' Ph.D.',
|
173
|
+
', bro.' => ' Bro.',
|
174
|
+
', Jr.,' => ' Jr.;',
|
175
|
+
', Jr.' => ' Jr.',
|
176
|
+
',Jr.' => ' Jr.',
|
177
|
+
', Sr.' => ' Sr.',
|
178
|
+
',Sr.' => ' Sr.',
|
179
|
+
' jr.,' => ' Jr.;',
|
180
|
+
' jr,' => ' Jr.;',
|
181
|
+
'-jr' => ' Jr.',
|
182
|
+
'-Jr' => ' Jr.'
|
168
183
|
}
|
169
184
|
|
170
185
|
COMPLEX_SEPARATORS = %r{
|
@@ -257,6 +272,7 @@ module DwcAgent
|
|
257
272
|
"determination",
|
258
273
|
"dissection",
|
259
274
|
"entered",
|
275
|
+
"indecipherable",
|
260
276
|
"nomenclatural",
|
261
277
|
"orig",
|
262
278
|
"registration",
|
@@ -268,7 +284,7 @@ module DwcAgent
|
|
268
284
|
"has not"
|
269
285
|
]
|
270
286
|
|
271
|
-
TITLE = /\s*\b(sir|count(ess)?|colonel|(gen|adm|col|maj|capt|cmdr|lt|sgt|cpl|pvt|
|
287
|
+
TITLE = /\s*\b(sir|count(ess)?|colonel|(gen|adm|col|maj|major|capt|cmdr|lt|sgt|cpl|pvt|proff?|dr|md|ph\.?d|rev|mme|abbé|ptre|bro|esq)\.?|docteur|father|cantor|vicar|père|pastor|rabbi|reverend|pere|soeur|sister|professor)(\s+|$)/i
|
272
288
|
|
273
289
|
APPELLATION = /\s*\b((mrs?|ms|fr|hr)\.?|miss|herr|frau)(\s+|$)/i
|
274
290
|
|
data/lib/dwc_agent/parser.rb
CHANGED
@@ -20,7 +20,7 @@ module DwcAgent
|
|
20
20
|
@strip_out_regex = Regexp.new STRIP_OUT.to_s
|
21
21
|
@residual_terminators_regex = Regexp.new SPLIT_BY.to_s + %r{\s*\z}.to_s
|
22
22
|
@char_subs_regex = Regexp.new [CHAR_SUBS.keys.join].to_s
|
23
|
-
@phrase_subs_regex = Regexp.new PHRASE_SUBS.keys.join('|').to_s
|
23
|
+
@phrase_subs_regex = Regexp.new PHRASE_SUBS.keys.map{|a| Regexp.escape a }.join('|').to_s
|
24
24
|
@complex_separators_regex = Regexp.new COMPLEX_SEPARATORS.to_s
|
25
25
|
@add_separators_regex = Regexp.new %r{(\S{1}\.)([[:alpha:]]{2,})}.to_s
|
26
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: 1.5.0
|
4
|
+
version: 1.5.0.5
|
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: 2020-08-18 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: namae
|