biodiversity 3.4.2 → 3.4.3
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/CHANGELOG +3 -0
- data/lib/biodiversity/parser/scientific_name_canonical.rb +24 -11
- data/lib/biodiversity/parser/scientific_name_clean.rb +1528 -880
- data/lib/biodiversity/parser/scientific_name_clean.treetop +35 -3
- data/lib/biodiversity/parser/scientific_name_dirty.rb +93 -64
- data/lib/biodiversity/version.rb +1 -1
- data/spec/files/test_data.txt +4 -0
- metadata +2 -2
data/lib/biodiversity/version.rb
CHANGED
data/spec/files/test_data.txt
CHANGED
|
@@ -89,8 +89,10 @@ Serjania meridionalis Cambess. var. o'donelli F.A. Barkley|{"scientificName":{"i
|
|
|
89
89
|
#binomial with several authours
|
|
90
90
|
Pseudocercospora dendrobii Goh & W.H. Hsieh 1990|{"scientificName":{"id":"988fd6ba-0221-5b62-a041-fb81addc4465", "parsed":true, "parser_version":"test_version", "verbatim":"Pseudocercospora dendrobii Goh & W.H. Hsieh 1990", "normalized":"Pseudocercospora dendrobii Goh & W.H. Hsieh 1990", "canonical":"Pseudocercospora dendrobii", "hybrid":false, "details":[{"genus":{"string":"Pseudocercospora"}, "species":{"string":"dendrobii", "authorship":"Goh & W.H. Hsieh 1990", "basionymAuthorTeam":{"authorTeam":"Goh & W.H. Hsieh", "author":["Goh", "W.H. Hsieh"], "year":"1990"}}}], "parser_run":1, "positions":{"0":["genus", 16], "17":["species", 26], "27":["author_word", 30], "33":["author_word", 37], "38":["author_word", 43], "44":["year", 48]}}}
|
|
91
91
|
Pseudocercospora dendrobii Goh and W.H. Hsieh 1990|{"scientificName":{"id":"4d701dca-8774-5a5e-9378-11f60c0e735c", "parsed":true, "parser_version":"test_version", "verbatim":"Pseudocercospora dendrobii Goh and W.H. Hsieh 1990", "normalized":"Pseudocercospora dendrobii Goh & W.H. Hsieh 1990", "canonical":"Pseudocercospora dendrobii", "hybrid":false, "details":[{"genus":{"string":"Pseudocercospora"}, "species":{"string":"dendrobii", "authorship":"Goh and W.H. Hsieh 1990", "basionymAuthorTeam":{"authorTeam":"Goh and W.H. Hsieh", "author":["Goh", "W.H. Hsieh"], "year":"1990"}}}], "parser_run":1, "positions":{"0":["genus", 16], "17":["species", 26], "27":["author_word", 30], "35":["author_word", 39], "40":["author_word", 45], "46":["year", 50]}}}
|
|
92
|
+
Pseudocercospora dendrobii Goh apud W.H. Hsieh 1990|{"scientificName":{"id":"4dee6fc8-3be1-520c-9937-5a7342a17241", "parsed":true, "parser_version":"test_version", "verbatim":"Pseudocercospora dendrobii Goh apud W.H. Hsieh 1990", "normalized":"Pseudocercospora dendrobii Goh apud W.H. Hsieh 1990", "canonical":"Pseudocercospora dendrobii", "hybrid":false, "details":[{"genus":{"string":"Pseudocercospora"}, "species":{"string":"dendrobii", "authorship":"Goh apud W.H. Hsieh 1990", "basionymAuthorTeam":{"authorTeam":"Goh apud W.H. Hsieh", "author":["Goh", "W.H. Hsieh"], "year":"1990"}}}], "parser_run":1, "positions":{"0":["genus", 16], "17":["species", 26], "27":["author_word", 30], "36":["author_word", 40], "41":["author_word", 46], "47":["year", 51]}}}
|
|
92
93
|
Pseudocercospora dendrobii Goh et W.H. Hsieh 1990|{"scientificName":{"id":"13175b62-b95b-53b7-8d88-1be6fca794ec", "parsed":true, "parser_version":"test_version", "verbatim":"Pseudocercospora dendrobii Goh et W.H. Hsieh 1990", "normalized":"Pseudocercospora dendrobii Goh & W.H. Hsieh 1990", "canonical":"Pseudocercospora dendrobii", "hybrid":false, "details":[{"genus":{"string":"Pseudocercospora"}, "species":{"string":"dendrobii", "authorship":"Goh et W.H. Hsieh 1990", "basionymAuthorTeam":{"authorTeam":"Goh et W.H. Hsieh", "author":["Goh", "W.H. Hsieh"], "year":"1990"}}}], "parser_run":1, "positions":{"0":["genus", 16], "17":["species", 26], "27":["author_word", 30], "34":["author_word", 38], "39":["author_word", 44], "45":["year", 49]}}}
|
|
93
94
|
Schottera nicaeënsis (J.V. Lamouroux ex Duby) Guiry & Hollenberg|{"scientificName":{"id":"ffeb3703-63e5-5ff3-b296-582c0c3a3373", "parsed":true, "parser_version":"test_version", "verbatim":"Schottera nicaeënsis (J.V. Lamouroux ex Duby) Guiry & Hollenberg", "normalized":"Schottera nicaeensis (J.V. Lamouroux ex Duby) Guiry & Hollenberg", "canonical":"Schottera nicaeensis", "hybrid":false, "details":[{"genus":{"string":"Schottera"}, "species":{"string":"nicaeensis", "authorship":"(J.V. Lamouroux ex Duby) Guiry & Hollenberg", "combinationAuthorTeam":{"authorTeam":"Guiry & Hollenberg", "author":["Guiry", "Hollenberg"]}, "basionymAuthorTeam":{"authorTeam":"J.V. Lamouroux", "author":["J.V. Lamouroux"], "exAuthorTeam":{"authorTeam":"Duby", "author":["Duby"]}}}}], "parser_run":1, "positions":{"0":["genus", 9], "10":["species", 20], "22":["author_word", 26], "27":["author_word", 36], "40":["author_word", 44], "46":["author_word", 51], "54":["author_word", 64]}}}
|
|
95
|
+
Schottera nicaeënsis (J.V. Lamouroux ex Duby in Duby apud Johnson) Guiry & Hollenberg|{"scientificName":{"id":"5a929f5c-c4f1-5ba4-8a5f-eb906d43c692", "parsed":true, "parser_version":"test_version", "verbatim":"Schottera nicaeënsis (J.V. Lamouroux ex Duby in Duby apud Johnson) Guiry & Hollenberg", "normalized":"Schottera nicaeensis (J.V. Lamouroux ex Duby ex Duby apud Johnson) Guiry & Hollenberg", "canonical":"Schottera nicaeensis", "hybrid":false, "details":[{"genus":{"string":"Schottera"}, "species":{"string":"nicaeensis", "authorship":"(J.V. Lamouroux ex Duby in Duby apud Johnson) Guiry & Hollenberg", "combinationAuthorTeam":{"authorTeam":"Guiry & Hollenberg", "author":["Guiry", "Hollenberg"]}, "basionymAuthorTeam":{"authorTeam":"J.V. Lamouroux", "author":["J.V. Lamouroux"], "exAuthorTeam":{"authorTeam":"Duby", "author":["Duby"]}}}}], "parser_run":1, "positions":{"0":["genus", 9], "10":["species", 20], "22":["author_word", 26], "27":["author_word", 36], "40":["author_word", 44], "67":["author_word", 72], "75":["author_word", 85]}}}
|
|
94
96
|
|
|
95
97
|
#binomial with several authors and a year
|
|
96
98
|
Pseudocercospora dendrobii U. Braun & Crous 2003|{"scientificName":{"id":"afd958fc-82a5-5551-951b-a725a49d3df0", "parsed":true, "parser_version":"test_version", "parser_run":1,"verbatim":"Pseudocercospora dendrobii U. Braun & Crous 2003","normalized":"Pseudocercospora dendrobii U. Braun & Crous 2003","canonical":"Pseudocercospora dendrobii","hybrid":false,"details":[{"genus":{"string":"Pseudocercospora"},"species":{"string":"dendrobii","authorship":"U. Braun & Crous 2003","basionymAuthorTeam":{"authorTeam":"U. Braun & Crous","author":["U. Braun","Crous"],"year":"2003"}}}],"positions":{"0":["genus",16],"17":["species",26],"27":["author_word",29],"30":["author_word",35],"38":["author_word",43],"44":["year",48]}}}
|
|
@@ -242,6 +244,7 @@ Agaricus squamula Berk. & M.A. Curtis 1860|{"scientificName":{"id":"153b8745-887
|
|
|
242
244
|
Peltula coriacea Büdel, Henssen & Wessels 1986|{"scientificName":{"id":"081f5751-4042-597e-bccc-788754ce0248", "parsed":true, "parser_version":"test_version", "parser_run":1,"verbatim":"Peltula coriacea B\u00fcdel, Henssen & Wessels 1986","normalized":"Peltula coriacea B\u00fcdel, Henssen & Wessels 1986","canonical":"Peltula coriacea","hybrid":false,"details":[{"genus":{"string":"Peltula"},"species":{"string":"coriacea","authorship":"B\u00fcdel, Henssen & Wessels 1986","basionymAuthorTeam":{"authorTeam":"B\u00fcdel, Henssen & Wessels","author":["B\u00fcdel","Henssen","Wessels"],"year":"1986"}}}],"positions":{"0":["genus",7],"8":["species",16],"17":["author_word",22],"24":["author_word",31],"34":["author_word",41],"42":["year",46]}}}
|
|
243
245
|
Saccharomyces drosophilae anon.|{"scientificName":{"id":"45e537d2-6833-5429-a58c-178fe37fc3f5", "parsed":true, "parser_version":"test_version", "parser_run":1,"verbatim":"Saccharomyces drosophilae anon.","normalized":"Saccharomyces drosophilae anon.","canonical":"Saccharomyces drosophilae","hybrid":false,"details":[{"genus":{"string":"Saccharomyces"},"species":{"string":"drosophilae","authorship":"anon.","basionymAuthorTeam":{"authorTeam":"anon.","author":["unknown"]}}}],"positions":{"0":["genus",13],"14":["species",25],"26":["unknown_author",31]}}}
|
|
244
246
|
Abacetus laevicollis de Chaudoir, 1869|{"scientificName":{"id":"8d81b939-695f-5a38-86c7-0f6efd1cacf3", "parsed":true, "parser_version":"test_version", "parser_run":1,"verbatim":"Abacetus laevicollis de Chaudoir, 1869","normalized":"Abacetus laevicollis de Chaudoir 1869","canonical":"Abacetus laevicollis","hybrid":false,"details":[{"genus":{"string":"Abacetus"},"species":{"string":"laevicollis","authorship":"de Chaudoir, 1869","basionymAuthorTeam":{"authorTeam":"de Chaudoir","author":["de Chaudoir"],"year":"1869"}}}],"positions":{"0":["genus",8],"9":["species",20],"21":["author_word",23],"24":["author_word",32],"34":["year",38]}}}
|
|
247
|
+
Abacetus laevicollis do Chaudoir, 1869|{"scientificName":{"id":"8f000a09-f5c6-55c6-891f-d60130b98ff9", "parsed":true, "parser_version":"test_version", "verbatim":"Abacetus laevicollis do Chaudoir, 1869", "normalized":"Abacetus laevicollis do Chaudoir 1869", "canonical":"Abacetus laevicollis", "hybrid":false, "details":[{"genus":{"string":"Abacetus"}, "species":{"string":"laevicollis", "authorship":"do Chaudoir, 1869", "basionymAuthorTeam":{"authorTeam":"do Chaudoir", "author":["do Chaudoir"], "year":"1869"}}}], "parser_run":1, "positions":{"0":["genus", 8], "9":["species", 20], "21":["author_word", 23], "24":["author_word", 32], "34":["year", 38]}}}
|
|
245
248
|
Gastrosericus eremorum von Beaumont 1955|{"scientificName":{"id":"98df7228-03ef-511c-9f2d-7f91e10c2af5", "parsed":true, "parser_version":"test_version", "parser_run":1,"verbatim":"Gastrosericus eremorum von Beaumont 1955","normalized":"Gastrosericus eremorum von Beaumont 1955","canonical":"Gastrosericus eremorum","hybrid":false,"details":[{"genus":{"string":"Gastrosericus"},"species":{"string":"eremorum","authorship":"von Beaumont 1955","basionymAuthorTeam":{"authorTeam":"von Beaumont","author":["von Beaumont"],"year":"1955"}}}],"positions":{"0":["genus",13],"14":["species",22],"23":["author_word",26],"27":["author_word",35],"36":["year",40]}}}
|
|
246
249
|
Cypraeovula (Luponia) amphithales perdentata|{"scientificName":{"id":"d05be4e3-a0e3-5af4-9104-7922df1bcb47", "parsed":true, "parser_version":"test_version", "parser_run":1,"verbatim":"Cypraeovula (Luponia) amphithales perdentata","normalized":"Cypraeovula (Luponia) amphithales perdentata","canonical":"Cypraeovula amphithales perdentata","hybrid":false,"details":[{"genus":{"string":"Cypraeovula"},"infragenus":{"string":"Luponia"},"species":{"string":"amphithales"},"infraspecies":[{"string":"perdentata","rank":"n\/a"}]}],"positions":{"0":["genus",11],"13":["infragenus",20],"22":["species",33],"34":["infraspecies",44]}}}
|
|
247
250
|
Polyrhachis orsyllus nat musculus Forel 1901|{"scientificName":{"id":"3392132e-3dba-5b7e-a7c9-e4a68954c8b2", "parsed":true, "parser_version":"test_version", "verbatim":"Polyrhachis orsyllus nat musculus Forel 1901", "normalized":"Polyrhachis orsyllus nat musculus Forel 1901", "canonical":"Polyrhachis orsyllus musculus", "hybrid":false, "details":[{"genus":{"string":"Polyrhachis"}, "species":{"string":"orsyllus"}, "infraspecies":[{"string":"musculus", "rank":"nat", "authorship":"Forel 1901", "basionymAuthorTeam":{"authorTeam":"Forel", "author":["Forel"], "year":"1901"}}]}], "parser_run":1, "positions":{"0":["genus", 11], "12":["species", 20], "21":["infraspecific_type", 24], "25":["infraspecies", 33], "34":["author_word", 39], "40":["year", 44]}}}
|
|
@@ -406,6 +409,7 @@ Goggia gemmula 1996|{"scientificName":{"id":"707ab43c-41bd-56bc-b2aa-96db4913ad3
|
|
|
406
409
|
Oxytropis minjanensis Rech. f.|{"scientificName":{"id":"6027cbc2-fa15-510b-ab3e-e1fa44cbd551", "parsed":true, "parser_version":"test_version", "verbatim":"Oxytropis minjanensis Rech. f.", "normalized":"Oxytropis minjanensis Rech. f.", "canonical":"Oxytropis minjanensis", "hybrid":false, "details":[{"genus":{"string":"Oxytropis"}, "species":{"string":"minjanensis", "authorship":"Rech. f.", "basionymAuthorTeam":{"authorTeam":"Rech. f.", "author":["Rech. f."]}}}], "parser_run":1, "positions":{"0":["genus", 9], "10":["species", 21], "22":["author_word", 27], "28":["author_word", 30]}}}
|
|
407
410
|
Platypus bicaudatulus Schedl f. 1935|{"scientificName":{"id":"05799df9-471e-5c68-92fe-4edcc0a69d29", "parsed":true, "parser_version":"test_version", "verbatim":"Platypus bicaudatulus Schedl f. 1935", "normalized":"Platypus bicaudatulus Schedl f. 1935", "canonical":"Platypus bicaudatulus", "hybrid":false, "details":[{"genus":{"string":"Platypus"}, "species":{"string":"bicaudatulus", "authorship":"Schedl f. 1935", "basionymAuthorTeam":{"authorTeam":"Schedl f.", "author":["Schedl f."], "year":"1935"}}}], "parser_run":1, "positions":{"0":["genus", 8], "9":["species", 21], "22":["author_word", 28], "29":["author_word", 31], "32":["year", 36]}}}
|
|
408
411
|
Platypus bicaudatulus Schedl filius 1935|{"scientificName":{"id":"2b6cd51f-aa0f-58fd-88fa-2e261cedacbb", "parsed":true, "parser_version":"test_version", "verbatim":"Platypus bicaudatulus Schedl filius 1935", "normalized":"Platypus bicaudatulus Schedl filius 1935", "canonical":"Platypus bicaudatulus", "hybrid":false, "details":[{"genus":{"string":"Platypus"}, "species":{"string":"bicaudatulus", "authorship":"Schedl filius 1935", "basionymAuthorTeam":{"authorTeam":"Schedl filius", "author":["Schedl filius"], "year":"1935"}}}], "parser_run":1, "positions":{"0":["genus", 8], "9":["species", 21], "22":["author_word", 28], "29":["author_word", 35], "36":["year", 40]}}}
|
|
412
|
+
Platypus bicaudatulus Schedl fil. 1935|{"scientificName":{"id":"9ecd2519-8481-56e4-abe0-23408cfc0922", "parsed":true, "parser_version":"test_version", "verbatim":"Platypus bicaudatulus Schedl fil. 1935", "normalized":"Platypus bicaudatulus Schedl fil. 1935", "canonical":"Platypus bicaudatulus", "hybrid":false, "details":[{"genus":{"string":"Platypus"}, "species":{"string":"bicaudatulus", "authorship":"Schedl fil. 1935", "basionymAuthorTeam":{"authorTeam":"Schedl fil.", "author":["Schedl fil."], "year":"1935"}}}], "parser_run":1, "positions":{"0":["genus", 8], "9":["species", 21], "22":["author_word", 28], "29":["author_word", 33], "34":["year", 38]}}}
|
|
409
413
|
Fimbristylis ovata (Burm. f.) J. Kern|{"scientificName":{"id":"01207e0b-8de4-5a4e-99fc-e60b581c0d1c", "parsed":true, "parser_version":"test_version", "verbatim":"Fimbristylis ovata (Burm. f.) J. Kern", "normalized":"Fimbristylis ovata (Burm. f.) J. Kern", "canonical":"Fimbristylis ovata", "hybrid":false, "details":[{"genus":{"string":"Fimbristylis"}, "species":{"string":"ovata", "authorship":"(Burm. f.) J. Kern", "combinationAuthorTeam":{"authorTeam":"J. Kern", "author":["J. Kern"]}, "basionymAuthorTeam":{"authorTeam":"Burm. f.", "author":["Burm. f."]}}}], "parser_run":1, "positions":{"0":["genus", 12], "13":["species", 18], "20":["author_word", 25], "26":["author_word", 28], "30":["author_word", 32], "33":["author_word", 37]}}}
|
|
410
414
|
Carex chordorrhiza Ehrh. ex L. f.|{"scientificName":{"id":"b972d277-3714-5549-9103-869675f490bd", "parsed":true, "parser_version":"test_version", "verbatim":"Carex chordorrhiza Ehrh. ex L. f.", "normalized":"Carex chordorrhiza Ehrh. ex L. f.", "canonical":"Carex chordorrhiza", "hybrid":false, "details":[{"genus":{"string":"Carex"}, "species":{"string":"chordorrhiza", "authorship":"Ehrh. ex L. f.", "basionymAuthorTeam":{"authorTeam":"Ehrh.", "author":["Ehrh."], "exAuthorTeam":{"authorTeam":"L. f.", "author":["L. f."]}}}}], "parser_run":1, "positions":{"0":["genus", 5], "6":["species", 18], "19":["author_word", 24], "28":["author_word", 30], "31":["author_word", 33]}}}
|
|
411
415
|
Amelanchier arborea var. arborea (Michx. f.) Fernald|{"scientificName":{"id":"1644869c-3e0c-5e7e-a709-a86dee11b917", "parsed":true, "parser_version":"test_version", "verbatim":"Amelanchier arborea var. arborea (Michx. f.) Fernald", "normalized":"Amelanchier arborea var. arborea (Michx. f.) Fernald", "canonical":"Amelanchier arborea arborea", "hybrid":false, "details":[{"genus":{"string":"Amelanchier"}, "species":{"string":"arborea"}, "infraspecies":[{"string":"arborea", "rank":"var.", "authorship":"(Michx. f.) Fernald", "combinationAuthorTeam":{"authorTeam":"Fernald", "author":["Fernald"]}, "basionymAuthorTeam":{"authorTeam":"Michx. f.", "author":["Michx. f."]}}]}], "parser_run":1, "positions":{"0":["genus", 11], "12":["species", 19], "20":["infraspecific_type", 24], "25":["infraspecies", 32], "34":["author_word", 40], "41":["author_word", 43], "45":["author_word", 52]}}}
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: biodiversity
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 3.4.
|
|
4
|
+
version: 3.4.3
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Dmitry Mozzherin
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date:
|
|
11
|
+
date: 2018-02-02 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: treetop
|