Class: Taxamatch::Base
- Inherits:
-
Object
- Object
- Taxamatch::Base
- Defined in:
- lib/taxamatch_rb.rb
Instance Method Summary collapse
-
#initialize ⇒ Base
constructor
A new instance of Base.
- #match_authors(preparsed_1, preparsed_2) ⇒ Object
- #match_genera(genus1, genus2) ⇒ Object
- #match_matches(genus_match, species_match, infraspecies_matches = []) ⇒ Object
- #match_multinomial(preparsed_1, preparsed_2) ⇒ Object
- #match_species(sp1, sp2) ⇒ Object
- #match_uninomial(preparsed_1, preparsed_2) ⇒ Object
-
#taxamatch(str1, str2, return_boolean = true) ⇒ Object
takes two scientific names and returns true if names match and false if they don’t.
-
#taxamatch_preparsed(preparsed_1, preparsed_2) ⇒ Object
takes two hashes of parsed scientific names, analyses them and returns back this function is useful when species strings are preparsed.
Constructor Details
Instance Method Details
#match_authors(preparsed_1, preparsed_2) ⇒ Object
80 81 82 83 84 85 86 |
# File 'lib/taxamatch_rb.rb', line 80 def (preparsed_1, preparsed_2) au1 = preparsed_1[:all_authors] au2 = preparsed_2[:all_authors] yr1 = preparsed_1[:all_years] yr2 = preparsed_2[:all_years] Taxamatch::Authmatch.authmatch(au1, au2, yr1, yr2) end |
#match_genera(genus1, genus2) ⇒ Object
55 56 57 58 59 60 61 62 63 64 |
# File 'lib/taxamatch_rb.rb', line 55 def match_genera(genus1, genus2) genus1_length = genus1[:normalized].size genus2_length = genus2[:normalized].size match = false ed = @dlm.distance(genus1[:normalized], genus2[:normalized],1,3) #TODO put block = 2 return {'edit_distance' => ed, 'phonetic_match' => true, 'match' => true} if genus1[:phonetized] == genus2[:phonetized] match = true if ed <= 3 && ([genus1_length, genus2_length].min > ed * 2) && (ed < 2 || genus1[0] == genus2[0]) {'edit_distance' => ed, 'match' => match, 'phonetic_match' => false} end |
#match_matches(genus_match, species_match, infraspecies_matches = []) ⇒ Object
88 89 90 91 92 93 94 95 |
# File 'lib/taxamatch_rb.rb', line 88 def match_matches(genus_match, species_match, infraspecies_matches = []) match = species_match match['edit_distance'] += genus_match['edit_distance'] match['match'] = false if match['edit_distance'] > 4 match['match'] &&= genus_match['match'] match['phonetic_match'] &&= genus_match['phonetic_match'] match end |
#match_multinomial(preparsed_1, preparsed_2) ⇒ Object
47 48 49 50 51 52 53 |
# File 'lib/taxamatch_rb.rb', line 47 def match_multinomial(preparsed_1, preparsed_2) gen_match = match_genera(preparsed_1[:genus], preparsed_2[:genus]) sp_match = match_species(preparsed_1[:species], preparsed_2[:species]) total_length = preparsed_1[:genus][:epitheton].size + preparsed_2[:genus][:epitheton].size + preparsed_1[:species][:epitheton].size + preparsed_2[:species][:epitheton].size match = match_matches(gen_match, sp_match) match.merge({'score' => (1 - match['edit_distance']/(total_length/2))}) end |
#match_species(sp1, sp2) ⇒ Object
66 67 68 69 70 71 72 73 74 75 76 77 78 |
# File 'lib/taxamatch_rb.rb', line 66 def match_species(sp1, sp2) sp1_length = sp1[:normalized].size sp2_length = sp2[:normalized].size sp1[:phonetized] = Taxamatch::Phonetizer.normalize_ending sp1[:phonetized] sp2[:phonetized] = Taxamatch::Phonetizer.normalize_ending sp2[:phonetized] match = false ed = @dlm.distance(sp1[:normalized], sp2[:normalized], 1, 4) #TODO put block 4 #puts 's: %s, %s, %s' % [sp1[:normalized], sp2[:normalized], ed] return {'edit_distance' => ed, 'phonetic_match' => true, 'match' => true} if sp1[:phonetized] == sp2[:phonetized] match = true if ed <= 4 && ([sp1_length, sp2_length].min >= ed * 2) && (ed < 2 || sp1[:normalized][0] == sp2[:normalized][0]) && (ed < 4 || sp1[:normalized][0...3] == sp2[:normalized][0...3]) { 'edit_distance' => ed, 'match' => match, 'phonetic_match' => false} end |
#match_uninomial(preparsed_1, preparsed_2) ⇒ Object
43 44 45 |
# File 'lib/taxamatch_rb.rb', line 43 def match_uninomial(preparsed_1, preparsed_2) return false end |
#taxamatch(str1, str2, return_boolean = true) ⇒ Object
takes two scientific names and returns true if names match and false if they don’t
24 25 26 27 28 29 |
# File 'lib/taxamatch_rb.rb', line 24 def taxamatch(str1, str2, return_boolean = true) preparsed_1 = @parser.parse(str1) preparsed_2 = @parser.parse(str2) match = taxamatch_preparsed(preparsed_1, preparsed_2) rescue nil return_boolean && match ? match['match'] : match end |
#taxamatch_preparsed(preparsed_1, preparsed_2) ⇒ Object
takes two hashes of parsed scientific names, analyses them and returns back this function is useful when species strings are preparsed.
33 34 35 36 37 38 39 40 41 |
# File 'lib/taxamatch_rb.rb', line 33 def taxamatch_preparsed(preparsed_1, preparsed_2) result = nil result = match_uninomial(preparsed_1, preparsed_2) if preparsed_1[:uninomial] && preparsed_2[:uninomial] result = match_multinomial(preparsed_1, preparsed_2) if preparsed_1[:genus] && preparsed_2[:genus] if result && result['match'] result['match'] = (preparsed_1, preparsed_2) == 0 ? false : true end return result end |