dwc_agent 1.5.0.5 → 1.5.1.0

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 CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 0445f35092b28cfbcc273d01f90eee34c9642d7fc8b9c0b7e32e7720dc2f316b
4
- data.tar.gz: f10b0b6424007a829196851ece90d6138693dcd1825b6b5712a96b9b9a2ce224
3
+ metadata.gz: 3b4adb16325e2c9ac0cd8ed23eb0c9455632d447b942c765af5fb1876b821ab1
4
+ data.tar.gz: f9890ec976e2626700939134fc7f5ba3b5a5dea6eae94cea3f39579b208e2ee8
5
5
  SHA512:
6
- metadata.gz: 69d6e2be09b6edc55b5ebd0fef931dd5fcaf9df09b150bcd4580a9aace8c24576db65ea194352c134418f974b4cbfc0bf3254a1d4e22132f56203afcc06dbc08
7
- data.tar.gz: 467f50b23cb2d3cf8ad406b9cd14c3bdbd6635806c46304be7a0708a03755c23db56f0295dd2d89f8325dbc7ac1a3c34b237103974bb27a62ab38446838b21bd
6
+ metadata.gz: 1b9f1998b5edb9d6c5931e2fc1b87c46078875ac9715979f6ae0a7924f08c78731b05ead538c832d32f3e6025c102f18fa575a875186fdd9207f9bbc78f1c16c
7
+ data.tar.gz: 451672cdf4a81718096534247d46e73c3bf56770b646e0b67ea401d8e194c7acf21edfd7f2223acd0d75def6fe9848734f891be3d67a93fe277af94d69fbc192
@@ -18,10 +18,6 @@ module DwcAgent
18
18
  def clean(parsed_namae)
19
19
  blank_name = { title: nil, appellation: nil, given: nil, particle: nil, family: nil, suffix: nil }
20
20
 
21
- if parsed_namae.family && FAMILY_BLACKLIST.any?{ |s| s.casecmp(parsed_namae.family) == 0 }
22
- return blank_name
23
- end
24
-
25
21
  if parsed_namae.given && GIVEN_BLACKLIST.any?{ |s| s.casecmp(parsed_namae.given) == 0 }
26
22
  return blank_name
27
23
  end
@@ -79,6 +75,10 @@ module DwcAgent
79
75
  parsed_namae.given = NameCase(parsed_namae.given)
80
76
  end
81
77
 
78
+ if parsed_namae.family && FAMILY_BLACKLIST.any?{ |s| s.casecmp(parsed_namae.family) == 0 }
79
+ return blank_name
80
+ end
81
+
82
82
  parsed_namae.normalize_initials
83
83
 
84
84
  family = parsed_namae.family.gsub(/\.\z/, '').strip rescue nil
@@ -114,7 +114,7 @@ module DwcAgent
114
114
  return blank_name
115
115
  end
116
116
 
117
- if !family.nil? && family.match(/^[A-Z]{2}/)
117
+ if given.nil? && !family.nil? && family.match(/^[A-Z]{2}/)
118
118
  return blank_name
119
119
  end
120
120
 
@@ -3,6 +3,7 @@ module DwcAgent
3
3
  ^[\[{(]|
4
4
  [\]})]\??$|
5
5
  (?i:acc\s?\#)|
6
+ [,;]?\s*(?i:1st|2nd|3rd|[4-9]th)|
6
7
  \s*?\d+\.\d+|
7
8
  \b\d+\(?(?i:[[:alpha:]])\)?\b|
8
9
  \b[,;]?\s*(?i:et\.?\s+al|&\s+al)\.?|
@@ -49,34 +50,38 @@ module DwcAgent
49
50
  \d+\s+(?i:Oct|Octob(er|re))\.?\b|
50
51
  \d+\s+(?i:Nov|Novemb(er|re))\.?\b|
51
52
  \d+\s+(?i:Dec|D(e|é)cemb(er|re))\.?\b|
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|
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
+ \b[.-–,;:/]?\s*(?i:Alabama|Alaska|Arizona|Arkansas|California|Colorado|Connecticut|Delaware|Evergreen|Florida|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|Washington|West\s+Virginia|Wisconsin|Wyoming)\s+(?i:State)\s*\b|
54
+ \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|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|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|
54
55
  (?i:autres?\s+de|probab|likely|possibl(e|y)|doubtful)|
55
56
  \b\s*(?i:maybe)\s*\b|
56
57
  \b\s*(?i:prob)\.\s*\b|
57
- \(?[,]?\s*?(?i:(local)?\s?collector|data\s*recorder|netter|(oper|prepar)ator)\(?s?\)?\.?\:?|
58
+ \(?[,]?\s*?(?i:(local)?\s?collectors?|data\s*recorder|netter|(oper|prepar)ator)\(?s?\)?\.?\:?|
58
59
  \b[.-–,;:]?\s*(?i:department|faculty)\s*?(?i:of)?\s*?(?i:entomology|biology|zoology)|
59
60
  (?i:Engº|Agrº|Fcº|Drº|Mº|Profº|Dº|Fº)|
60
61
  (?i:fide)\:?\s*\b|
62
+ (?i:first\s+name\s+unknown)|
61
63
  (?i:game\s+dept)\.?\s*\b|
62
64
  (?i:see\s+notes?\s*(inside)?)|
63
65
  (?i:see\s+letter\s+enclosed)|
64
66
  (?i:(by)?\s+correspondance)|
65
67
  (?i:pers\.?\s*comm\.?)|
66
68
  (?i:crossed\s+out)|
69
+ (?i:(ohne|keine)\s+angaben)|
67
70
  \(?(?i:source)\(?|
68
71
  (?i:according\s+to)|
69
72
  (?i:lanuv)\d+|
73
+ \b\s*name\b|
74
+ \b\s*lost\b|
70
75
  (?i:nswobs)|
71
76
  ORCID|
72
77
  MRI(\s|-)PAS|
73
78
  urn\:qm\.qld\.gov\.au\:collector|
74
79
  (?i:University\s+of\s+(Southern\s+)?California(,\s+Berkeley)?)|
75
- (?i:Field\s+Museum\s+of\s+Natural\s+History)|
76
- (?i:American\s+Museum\s+of\s+Natural\s+History)|
80
+ (?i:field\s+museum\s+of\s+natural\s+history)|
81
+ (?i:american\s+museum\s+of\s+natural\s+history)|
77
82
  (?i:The\s+Paleontological\s+Research\s+Institution)|
78
83
  (?i:museums?\s+victoria)|
79
- \b\s*(?i:United\s+States|Russia)\s*\b|
84
+ \b\s*(?i:united\s+states|russia)\s*\b|
80
85
  (?i:revised|photograph|fruits\s+only)|
81
86
  -?\s*(?i:sight\s+(id|identifi?cation))\.?\s*\b|
82
87
  -?\s*(?i:synonym(y|ie))|
@@ -106,11 +111,14 @@ module DwcAgent
106
111
  (\(|\[|\{).{1,}\z|
107
112
  \b(?i:leg)[\.:]?\s*\b|
108
113
  (?i:ded)\:|
114
+ \d*[A-Za-z]*\d*-\d*\z|
115
+ \s+[A-Z]*\d+\z|
116
+ \s+\d+[A-Za-z]+\z|
109
117
  ^[-,.\s;*\d]+\s?|
110
- -\d?\z|
111
118
  \s*?-{2,}\s*?|
112
119
  ^(?i:exc?p?)[:.]\s*|
113
- \s+de\s*$
120
+ \s+de\s*$|
121
+ \.{2,}$
114
122
  }x
115
123
 
116
124
  SPLIT_BY = %r{
@@ -244,7 +252,7 @@ module DwcAgent
244
252
  (?i:though)|
245
253
  (?i:texas\s+instruments?)\s*?(for)?|
246
254
  (?:tropical)|
247
- (?i:toward|seen at)|
255
+ (?i:toward|seen\s+at)|
248
256
  (?i:unidentified|unspecified|unk?nown?|unnamed|unread|unmistak|no agent)|
249
257
  (?i:urn\:)|
250
258
  (?i:usda|ucla)|
@@ -253,30 +261,47 @@ module DwcAgent
253
261
  }x
254
262
 
255
263
  FAMILY_BLACKLIST = [
264
+ "ap",
256
265
  "da",
266
+ "de",
257
267
  "de'",
258
268
  "del",
259
269
  "der",
270
+ "di",
271
+ "do",
272
+ "dos",
260
273
  "du",
261
274
  "el",
275
+ "le",
276
+ "la",
262
277
  "van",
263
278
  "von",
264
279
  "the",
265
280
  "of",
266
281
  "adjustment",
282
+ "annotator",
267
283
  "available",
268
284
  "arachnology",
269
285
  "catalogue",
270
286
  "curators",
271
287
  "data",
288
+ "details",
289
+ "determiner",
272
290
  "determination",
273
291
  "dissection",
274
292
  "entered",
293
+ "erased",
275
294
  "indecipherable",
276
295
  "nomenclatural",
277
296
  "orig",
278
297
  "registration",
279
- "science"
298
+ "science",
299
+ "wg",
300
+ "wm",
301
+ "wn",
302
+ "zw",
303
+ "zz",
304
+ "z-"
280
305
  ]
281
306
 
282
307
  GIVEN_BLACKLIST = [
@@ -3,8 +3,8 @@ module DwcAgent
3
3
 
4
4
  MAJOR = 1
5
5
  MINOR = 5
6
- PATCH = 0
7
- BUILD = 5
6
+ PATCH = 1
7
+ BUILD = 0
8
8
 
9
9
  def self.version
10
10
  [MAJOR, MINOR, PATCH, BUILD].compact.join('.').freeze
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: 1.5.0.5
4
+ version: 1.5.1.0
5
5
  platform: ruby
6
6
  authors:
7
7
  - David P. Shorthouse
8
- autorequire:
8
+ autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2020-08-18 00:00:00.000000000 Z
11
+ date: 2020-10-07 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: namae
@@ -102,7 +102,7 @@ homepage: https://github.com/bionomia/dwc_agent
102
102
  licenses:
103
103
  - MIT
104
104
  metadata: {}
105
- post_install_message:
105
+ post_install_message:
106
106
  rdoc_options:
107
107
  - "--encoding"
108
108
  - UTF-8
@@ -112,15 +112,15 @@ required_ruby_version: !ruby/object:Gem::Requirement
112
112
  requirements:
113
113
  - - "~>"
114
114
  - !ruby/object:Gem::Version
115
- version: '2.6'
115
+ version: '2.7'
116
116
  required_rubygems_version: !ruby/object:Gem::Requirement
117
117
  requirements:
118
118
  - - ">="
119
119
  - !ruby/object:Gem::Version
120
120
  version: '0'
121
121
  requirements: []
122
- rubygems_version: 3.0.6
123
- signing_key:
122
+ rubygems_version: 3.1.2
123
+ signing_key:
124
124
  specification_version: 4
125
125
  summary: Parse Darwin Core agent terms such as recordedBy and identifiedBy
126
126
  test_files: []