Module: Export::Coldp::Files::Synonym

Defined in:
lib/export/coldp/files/synonym.rb

Overview

The synonym table is a list of all the Names (valid and invalid) that have been used for valid OTUs (Taxa) in the current classification.

Only TaxonIds for valid OTUs valid taxon names should be here, though the CoL parser format will apparently handle taxon ids that are not in the taxon table.

Bigger picture: understand how this maps to core name usage table in CoL

We assume that the names exporting in Names are those that must be tied to Taxa, so we re-use that scoping.

!! TODO: While the scoping of names to be considered is likely correct, invalid names are not likely pointing to valid OTUs, but rather invalid OTUs.

!? To resolve this create a single lookup of all possibile name_ids to their valid otu_id !! TODO: If a lookup is in place, then we can do this all in parallel with Name.tsv, i.e. completely removing a redundant pass

Class Method Summary collapse

Class Method Details

.add_combinations(otu, otus, csv, project_members) ⇒ Object 



74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
 
# File 'lib/export/coldp/files/synonym.rb', line 74

def self.add_combinations(otu, otus, csv, project_members)
  names = ::Export::Coldp::Files::Name.combination_names(otu).unscope(:select).select(:id, :cached_valid_taxon_name_id)

  x = Otu.with(name_scope: names)
    .joins('JOIN name_scope on name_scope.cached_valid_taxon_name_id = otus.taxon_name_id')
    .select(:id, :taxon_name_id)

  # TODO: ok to this point (check that we are not duplicating rows in y?

  y = TaxonName.with(invalid_names: names, otu_scope: x)
    .joins('JOIN invalid_names on invalid_names.id = taxon_names.id')
    .joins('LEFT JOIN otu_scope os on os.taxon_name_id = taxon_names.cached_valid_taxon_name_id')
    .select('invalid_names.id, MAX(os.id) AS otu_id, taxon_names.updated_at, taxon_names.updated_by_id') # housekeeping is meaningless here
    .group('taxon_names.id, invalid_names.id')

  y.find_each do |n|

    next if ::Export::Coldp.skipped_combinations.include?(n.id)

    csv << [
      n.otu_id,                                                  # taxonID attached to the current valid concept
      n.id,                                                      # nameID
      nil,                                                       # status  TODO: def status(taxon_name_id)
      nil,                                                       # remarks
      nil,                                                       # referenceID  Unclear what this means in TW
      Export::Coldp.modified(n.updated_at),                      # modified
      Export::Coldp.modified_by(n.updated_by_id, project_members) # modifiedBy
    ]
  end
end

.add_invalid_core_names(otu, otus, csv, project_members) ⇒ Object 



45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
 
# File 'lib/export/coldp/files/synonym.rb', line 45

def self.add_invalid_core_names(otu, otus, csv, project_members)


  names = ::Export::Coldp::Files::Name.invalid_core_names(otu)
  names.length # TODO: needed?

  x = Otu.with(name_scope: names)
    .joins('JOIN name_scope on name_scope.cached_valid_taxon_name_id = otus.taxon_name_id')
    .select(:id)

  y = TaxonName.with(invalid_names: names)
    .joins('JOIN invalid_names on invalid_names.cached_valid_taxon_name_id = taxon_names.id')
    .joins('LEFT JOIN otus on otus.taxon_name_id = taxon_names.id')
    .select('invalid_names.id, MAX(otus.id) AS otu_id, taxon_names.updated_at, taxon_names.updated_by_id') # housekeeping is meaningless here
    .group('taxon_names.id, invalid_names.id')

  y.find_each do |n|
    csv << [
      n.otu_id,                                                   # taxonID attached to the current valid concept
      n.id,                                                       # nameID
      nil,                                                        # status  TODO: def status(taxon_name_id)
      nil,                                                        # remarks
      nil,                                                        # referenceID  Unclear what this means in TW
      Export::Coldp.modified(n.updated_at),                       # modified
      Export::Coldp.modified_by(n.updated_by_id, project_members) # modifiedBy
    ]
  end
end

.add_invalid_family_and_higher_names(otu, otus, csv, project_members) ⇒ Object 



105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
 
# File 'lib/export/coldp/files/synonym.rb', line 105

def self.add_invalid_family_and_higher_names(otu, otus, csv, project_members)
  names = ::Export::Coldp::Files::Name.invalid_family_and_higher_names(otu)
  names.length # TODO: needed?

  x = Otu.with(name_scope: names)
    .joins('JOIN name_scope on name_scope.cached_valid_taxon_name_id = otus.taxon_name_id')
    .select(:id)

  y = TaxonName.with(invalid_names: names)
    .joins('JOIN invalid_names on invalid_names.cached_valid_taxon_name_id = taxon_names.id')
    .joins('LEFT JOIN otus on otus.taxon_name_id = taxon_names.id')
    .select('invalid_names.id, MAX(otus.id) AS otu_id, taxon_names.updated_at, taxon_names.updated_by_id') # housekeeping is meaningless here
    .group('taxon_names.id, invalid_names.id')

  #   x = Otu.with(name_scope: names)
  #     .joins('JOIN name_scope on name_scope.id = otus.taxon_name_id')
  #     .select(:id)

  #   y = Otu.with(otu_scope: x)
  #     .joins('JOIN otu_scope on otu_scope.id = otus.id')
  #     .select(:id, :taxon_name_id, :updated_at, :updated_by_id)

  y.find_each do |n|
    csv << [
      n.otu_id,                                                  # taxonID attached to the current valid concept
      n.id,                                                      # nameID
      nil,                                                       # status  TODO: def status(taxon_name_id)
      nil,                                                       # remarks
      nil,                                                       # referenceID  Unclear what this means in TW
      Export::Coldp.modified(n.updated_at),                      # modified
      Export::Coldp.modified_by(n.updated_by_id, project_members) # modifiedBy
    ]
  end
end

.add_original_combinations(otu, otus, csv, project_members) ⇒ Object 



140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
 
# File 'lib/export/coldp/files/synonym.rb', line 140

def self.add_original_combinations(otu, otus, csv, project_members)
  names = ::Export::Coldp::Files::Name.original_combination_names(otu)

  x = Otu.with(name_scope: names)
    .joins('JOIN name_scope on name_scope.cached_valid_taxon_name_id = otus.taxon_name_id')
    .select(:id)

  y = TaxonName.with(invalid_names: names)
    .joins('JOIN invalid_names on invalid_names.cached_valid_taxon_name_id = taxon_names.id')
    .joins('LEFT JOIN otus on otus.taxon_name_id = taxon_names.id')
    .select('invalid_names.id, MAX(otus.id) AS otu_id, taxon_names.updated_at, taxon_names.updated_by_id, invalid_names.cached_original_combination') # housekeeping is meaningless here
    .group('taxon_names.id, invalid_names.id, invalid_names.cached_original_combination')

  #   a = Otu.with(name_scope: names, otu_scope: otus)
  #     .joins('JOIN name_scope on name_scope.id = otus.taxon_name_id')
  #     .joins('JOIN otu_scope on otu_scope.id = otus.id')
  #     .select('otus.id, otus.taxon_name_id, otus.updated_at, otus.updated_by_id, name_scope.cached_original_combination').distinct

  y.find_each do |n|
    # By `original_combination_names(otu) these are all reified
    reified_id = ::Utilities::Nomenclature.reified_id(n.id, n.cached_original_combination)

    csv << [
      n.otu_id,                                                  # taxonID attached to the current valid concept
      reified_id,                                                # nameID
      nil,                                                       # status  TODO: def status(taxon_name_id)
      nil,                                                       # remarks
      nil,                                                       # referenceID  Unclear what this means in TW
      Export::Coldp.modified(n.updated_at),                      # modified
      Export::Coldp.modified_by(n.updated_by_id, project_members) # modifiedBy
    ]
  end
end

.generate(otu, otus, project_members, reference_csv = nil) ⇒ Object 



34
35
36
37
38
39
40
41
42
43
 
# File 'lib/export/coldp/files/synonym.rb', line 34

def self.generate(otu, otus, project_members, reference_csv = nil)
  ::CSV.generate(col_sep: "\t") do |csv|
    csv << %w{taxonID nameID status remarks referenceID modified modifiedBy}

    add_invalid_family_and_higher_names(otu, otus, csv, project_members)
    add_invalid_core_names(otu, otus, csv, project_members)
    add_original_combinations(otu, otus, csv, project_members)
    add_combinations(otu, otus, csv, project_members)
  end
end

.status(o, t) ⇒ Object

Last 3 of api.checklistbank.org/vocab/taxonomicstatus

Returns:

  • String



23
24
25
26
27
28
29
30
 
# File 'lib/export/coldp/files/synonym.rb', line 23

def self.status(o, t)
  #'accepted'
  #'provisionally accepted'
  #'synonym'
  #'ambiguous synonym'
  #'missaplied'
  'synonym'
end