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, csv, project_members, otu_lookup) ⇒ Object

TODO: This has no autonym detection now, is it an issue?



79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
 
# File 'lib/export/coldp/files/synonym.rb', line 79

def self.add_combinations(otu, csv, project_members, otu_lookup)
  names = ::Export::Coldp::Files::Name.combination_names(otu).unscope(:select).select('taxon_names.*')
  names.length # !! Required - without this the result is truncated (see name.rb comment)


  # Iterate directly over names to avoid CTE truncation issues
  names.find_each do |t|

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

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

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



51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
 
# File 'lib/export/coldp/files/synonym.rb', line 51

def self.add_invalid_core_names(otu, csv, project_members, otu_lookup)
  names = ::Export::Coldp::Files::Name.invalid_core_names(otu)
  names.length # !! Required - without this the result is truncated (see name.rb comment)

  # Iterate directly over names (like name.rb does) to avoid CTE truncation issues
  names.find_each do |t|

    # Names like missaplications do not point to a valid name, i.e. their id == cached_valid_taxon_.
    #  - Add a synonym relationships to have them appear here.
    #  - Names skipped here are treated as bare names in CoL
    taxon_id =  otu_lookup[t.cached_valid_taxon_name_id]
    next unless taxon_id

    next if autonym_synonym?(t)

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

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



101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
 
# File 'lib/export/coldp/files/synonym.rb', line 101

def self.add_invalid_family_and_higher_names(otu, csv, project_members, otu_lookup)
  names = ::Export::Coldp::Files::Name.invalid_family_and_higher_names(otu)
  names.length # !! Required - without this the result is truncated (see name.rb comment)

  # Iterate directly over names to avoid CTE truncation issues
  names.find_each do |t|
    csv << [
      otu_lookup[t.cached_valid_taxon_name_id],                   # taxonID attached to the current valid concept
      t.id,                                                       # nameID
      nil,                                                        # status  TODO: def status(taxon_name_id)
      nil,                                                        # remarks
      nil,                                                        # referenceID  Unclear what this means in TW
      Export::Coldp.modified(t.updated_at),                       # modified
      Export::Coldp.modified_by(t.updated_by_id, project_members) # modifiedBy
    ]
  end
end

.add_invalid_original_combinations(otu, csv, project_members, otu_lookup) ⇒ Object

Add synonyms for invalid names with different original combinations (reified IDs)



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
 
# File 'lib/export/coldp/files/synonym.rb', line 146

def self.add_invalid_original_combinations(otu, csv, project_members, otu_lookup)
  names = ::Export::Coldp::Files::Name.invalid_original_combination_names(otu)
  names.length # !! Required - without this the result is truncated (see name.rb comment)

  # Iterate directly over names to avoid CTE truncation issues
  names.find_each do |t|
    next if autonym_synonym?(t)

    # By `invalid_original_combination_names(otu) these are all reified
    reified_id = ::Utilities::Nomenclature.reified_id(
      t.id,
      ::Utilities::Nomenclature.unmisspell_name(t.cached_original_combination)
    )

    csv << [
      otu_lookup[t.cached_valid_taxon_name_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(t.updated_at),                       # modified
      Export::Coldp.modified_by(t.updated_by_id, project_members) # modifiedBy
    ]
  end
end

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



119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
 
# File 'lib/export/coldp/files/synonym.rb', line 119

def self.add_original_combinations(otu, csv, project_members, otu_lookup)
  names = ::Export::Coldp::Files::Name.original_combination_names(otu)
  names.length # !! Required - without this the result is truncated (see name.rb comment)

  # Iterate directly over names to avoid CTE truncation issues
  names.find_each do |t|
    next if autonym_synonym?(t)

    # By `original_combination_names(otu) these are all reified
    reified_id = ::Utilities::Nomenclature.reified_id(
      t.id,
      ::Utilities::Nomenclature.unmisspell_name(t.cached_original_combination)
    )

    csv << [
      otu_lookup[t.cached_valid_taxon_name_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(t.updated_at),                      # modified
      Export::Coldp.modified_by(t.updated_by_id, project_members) # modifiedBy
    ]
  end
end

.autonym_synonym?(name) ⇒ Boolean

Returns:

  • (Boolean) 


172
173
174
175
 
# File 'lib/export/coldp/files/synonym.rb', line 172

def self.autonym_synonym?(name)
  return true if name.parent_name == name.name
  return name.cached.scan(name.name).count == 2
end

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



34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
 
# File 'lib/export/coldp/files/synonym.rb', line 34

def self.generate(otu, otus, project_members, reference_csv = nil)

  # Build OTU lookup hash once to avoid N+1 queries
  # Maps taxon_name_id -> otu.id for all OTUs in scope
  otu_lookup = otus.pluck(:taxon_name_id, :id).to_h

  ::CSV.generate(col_sep: "\t") do |csv|
    csv << %w{taxonID nameID status remarks referenceID modified modifiedBy}

    add_invalid_family_and_higher_names(otu, csv, project_members, otu_lookup)
    add_invalid_core_names(otu, csv, project_members, otu_lookup)
    add_original_combinations(otu, csv, project_members, otu_lookup)          # Handles reified IDs
    add_invalid_original_combinations(otu, csv, project_members, otu_lookup)  # Handles reified IDs
    add_combinations(otu, csv, project_members, otu_lookup)
  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