biodiversity19 1.0.13 → 1.0.14

data/CHANGELOG

@@ -1,3 +1,7 @@
+1.0.14 -- canonical forms had allowed ë as a character until now. After this 
+version the only utf-8 character allowed in canonical forms should be the 
+multiplication sign for hybrids.
+
 1.0.13 -- canonical forms for cf. aff. qualifiers are modified: canonical for 
 'Aus cf. bus' is now 'Aus bus'; canonical for 'Aus aff. bus' is now 'Aus'.
 Ranks at the end of the name like 'var', 'ssp', 'spp' are considered junk and

data/VERSION

@@ -1 +1 @@
-1.0.13
+1.0.14

data/lib/biodiversity/parser/scientific_name_clean.treetop

@@ -1167,9 +1167,9 @@ grammar ScientificNameClean
         text_value.split('').each do |l|
           l = 'ae' if l == 'æ'
           l = 'oe' if l == 'œ'
-          # not sure if we should normalize ë as well. It is legal in botanical code, but it 
-          # might be beneficial to normalize it for the reconsiliation purposes
-          # l = 'e' if l == 'ë' 
+          # We normalize ë as well. It is legal in botanical code, but it 
+          # is beneficial to normalize it for the reconsiliation purposes
+          l = 'e' if l == 'ë' 
           res << l
         end
         res

data/spec/parser/scientific_name_clean.spec.rb

@@ -131,9 +131,9 @@ describe ScientificNameClean do
   
   it 'should parse names with e-umlaut' do
    sn = 'Kalanchoë tuberosa'
-   canonical(sn).should == 'Kalanchoë tuberosa'
+   canonical(sn).should == 'Kalanchoe tuberosa'
    sn = 'Isoëtes asplundii H. P. Fuchs'
-   canonical(sn).should == 'Isoëtes asplundii'
+   canonical(sn).should == 'Isoetes asplundii'
   end
 
   it 'should parse infragenus (ICZN code)' do
@@ -555,7 +555,7 @@ describe ScientificNameClean do
     sn = 'Flexibacter elegans Soriano 1945, non Lewin 1969'
     details(sn).should == [{:genus=>{:string=>"Flexibacter"}, :species=>{:string=>"elegans", :authorship=>"Soriano 1945, non Lewin 1969", :basionymAuthorTeam=>{:authorTeam=>"Soriano", :author=>["Soriano"], :year=>"1945"}}}]
     sn = 'Schottera nicaeënsis (J.V. Lamouroux ex Duby) Guiry & Hollenberg'
-    details(sn).should == [{:genus=>{:string=>"Schottera"}, :species=>{:string=>"nicaeënsis", :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"]}}}}]
+    details(sn).should == [{: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"]}}}}]
     sn = 'Deschampsia cespitosa ssp pumila'
     details(sn).should == [{:genus=>{:string=>"Deschampsia"}, :species=>{:string=>"cespitosa"}, :infraspecies=>[{:string=>"pumila", :rank=>"ssp"}]}]
   end

data/spec/parser/test_data.txt

@@ -55,7 +55,7 @@ Platypus bicaudatulus Schedl, 1935h|{"scientificName":{"parsed":true, "parser_ve
 Pseudocercospora dendrobii U. Braun & Crous|{"scientificName":{"parsed":true, "parser_version":"test_version", "parser_run":1,"verbatim":"Pseudocercospora dendrobii U. Braun & Crous","normalized":"Pseudocercospora dendrobii U. Braun et Crous","canonical":"Pseudocercospora dendrobii","hybrid":false,"details":[{"genus":{"string":"Pseudocercospora"},"species":{"string":"dendrobii","authorship":"U. Braun & Crous","basionymAuthorTeam":{"authorTeam":"U. Braun & Crous","author":["U. Braun","Crous"]}}}],"positions":{"0":["genus",16],"17":["species",26],"27":["author_word",29],"30":["author_word",35],"38":["author_word",43]}}}
 Pseudocercospora dendrobii U. Braun et Crous|{"scientificName":{"parsed":true, "parser_version":"test_version", "parser_run":1,"verbatim":"Pseudocercospora dendrobii U. Braun et Crous","normalized":"Pseudocercospora dendrobii U. Braun et Crous","canonical":"Pseudocercospora dendrobii","hybrid":false,"details":[{"genus":{"string":"Pseudocercospora"},"species":{"string":"dendrobii","authorship":"U. Braun et Crous","basionymAuthorTeam":{"authorTeam":"U. Braun et Crous","author":["U. Braun","Crous"]}}}],"positions":{"0":["genus",16],"17":["species",26],"27":["author_word",29],"30":["author_word",35],"39":["author_word",44]}}}
 Pseudocercospora dendrobii U. Braun and Crous|{"scientificName":{"parsed":true, "parser_version":"test_version", "parser_run":1,"verbatim":"Pseudocercospora dendrobii U. Braun and Crous","normalized":"Pseudocercospora dendrobii U. Braun et Crous","canonical":"Pseudocercospora dendrobii","hybrid":false,"details":[{"genus":{"string":"Pseudocercospora"},"species":{"string":"dendrobii","authorship":"U. Braun and Crous","basionymAuthorTeam":{"authorTeam":"U. Braun and Crous","author":["U. Braun","Crous"]}}}],"positions":{"0":["genus",16],"17":["species",26],"27":["author_word",29],"30":["author_word",35],"40":["author_word",45]}}}
-Schottera nicaeënsis (J.V. Lamouroux ex Duby) Guiry & Hollenberg|{"scientificName":{"parsed":true, "verbatim":"Schottera nicaeënsis (J.V. Lamouroux ex Duby) Guiry & Hollenberg", "normalized":"Schottera nicaeënsis (J.V. Lamouroux ex Duby) Guiry et Hollenberg", "canonical":"Schottera nicaeënsis", "hybrid":false, "details":[{"genus":{"string":"Schottera"}, "species":{"string":"nicaeënsis", "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_version":"test_version", "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]}}}
+Schottera nicaeënsis (J.V. Lamouroux ex Duby) Guiry & Hollenberg|{"scientificName":{"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 et 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]}}}
 
 #binomial with several authors and a year
 Pseudocercospora dendrobii U. Braun & Crous 2003|{"scientificName":{"parsed":true, "parser_version":"test_version", "parser_run":1,"verbatim":"Pseudocercospora dendrobii U. Braun & Crous 2003","normalized":"Pseudocercospora dendrobii U. Braun et 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]}}}
@@ -72,7 +72,7 @@ Ferganoconcha? oblonga|{"scientificName":{"parsed":true, "parser_version":"test_
 Rühlella|{"scientificName":{"parsed":true, "parser_version":"test_version", "parser_run":2,"verbatim":"R\u00fchlella","normalized":"Ruhlella","canonical":"Ruhlella","hybrid":false,"details":[{"uninomial":{"string":"Ruhlella"}}],"positions":{"0":["uninomial",8]}}}
 Sténométope laevissimus Bibron 1855|{"scientificName":{"parsed":true, "parser_version":"test_version", "parser_run":2,"verbatim":"St\u00e9nom\u00e9tope laevissimus Bibron 1855","normalized":"Stenometope laevissimus Bibron 1855","canonical":"Stenometope laevissimus","hybrid":false,"details":[{"genus":{"string":"Stenometope"},"species":{"string":"laevissimus","authorship":"Bibron 1855","basionymAuthorTeam":{"authorTeam":"Bibron","author":["Bibron"],"year":"1855"}}}],"positions":{"0":["genus",11],"12":["species",23],"24":["author_word",30],"31":["year",35]}}}
 Choriozopella trägårdhi Lawrence, 1947|{"scientificName":{"parsed":true, "verbatim":"Choriozopella trägårdhi Lawrence, 1947", "normalized":"Choriozopella tragardhi Lawrence 1947", "canonical":"Choriozopella tragardhi", "hybrid":false, "details":[{"genus":{"string":"Choriozopella"}, "species":{"string":"tragardhi", "authorship":"Lawrence, 1947", "basionymAuthorTeam":{"authorTeam":"Lawrence", "author":["Lawrence"], "year":"1947"}}}],  "parser_version":"test_version", "parser_run":2, "positions":{"0":["genus", 13], "14":["species", 23], "24":["author_word", 32], "34":["year", 38]}}}
-Isoëtes asplundii H. P. Fuchs|{"scientificName":{"parsed":true, "verbatim":"Isoëtes asplundii H. P. Fuchs", "normalized":"Isoëtes asplundii H. P. Fuchs", "canonical":"Isoëtes asplundii", "hybrid":false, "details":[{"genus":{"string":"Isoëtes"}, "species":{"string":"asplundii", "authorship":"H. P. Fuchs", "basionymAuthorTeam":{"authorTeam":"H. P. Fuchs", "author":["H. P. Fuchs"]}}}],  "parser_version":"test_version", "parser_run":1, "positions":{"0":["genus", 7], "8":["species", 17], "18":["author_word", 20], "21":["author_word", 23], "24":["author_word", 29]}}}
+Isoëtes asplundii H. P. Fuchs|{"scientificName":{"parsed":true, "parser_version":"test_version", "verbatim":"Isoëtes asplundii H. P. Fuchs", "normalized":"Isoetes asplundii H. P. Fuchs", "canonical":"Isoetes asplundii", "hybrid":false, "details":[{"genus":{"string":"Isoetes"}, "species":{"string":"asplundii", "authorship":"H. P. Fuchs", "basionymAuthorTeam":{"authorTeam":"H. P. Fuchs", "author":["H. P. Fuchs"]}}}], "parser_run":1, "positions":{"0":["genus", 7], "8":["species", 17], "18":["author_word", 20], "21":["author_word", 23], "24":["author_word", 29]}}}
 Cerambyx thomæ GMELIN J. F., 1790|{"scientificName":{"parsed":true, "verbatim":"Cerambyx thomæ GMELIN J. F., 1790", "normalized":"Cerambyx thomae GMELIN J. F. 1790", "canonical":"Cerambyx thomae", "hybrid":false, "details":[{"genus":{"string":"Cerambyx"}, "species":{"string":"thomae", "authorship":"GMELIN J. F., 1790", "basionymAuthorTeam":{"authorTeam":"GMELIN J. F.", "author":["GMELIN J. F."], "year":"1790"}}}],  "parser_version":"test_version", "parser_run":1, "positions":{"0":["genus", 8], "9":["species", 14], "15":["author_word", 21], "22":["author_word", 24], "25":["author_word", 27], "29":["year", 33]}}}
 #digraph unicode characters
 Læptura laetifica Dow, 1913|{"scientificName":{"parsed":true, "parser_version":"test_version", "parser_run":1,"verbatim":"L\u00e6ptura laetifica Dow, 1913","normalized":"Laeptura laetifica Dow 1913","canonical":"Laeptura laetifica","hybrid":false,"details":[{"genus":{"string":"Laeptura"},"species":{"string":"laetifica","authorship":"Dow, 1913","basionymAuthorTeam":{"authorTeam":"Dow","author":["Dow"],"year":"1913"}}}],"positions":{"0":["genus",7],"8":["species",17],"18":["author_word",21],"23":["year",27]}}}

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: biodiversity19
 version: !ruby/object:Gem::Version
-  version: 1.0.13
+  version: 1.0.14
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-06-26 00:00:00.000000000 Z
+date: 2012-07-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: treetop