biodiversity19 1.0.14 → 1.0.15
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.
- data/CHANGELOG +2 -0
- data/VERSION +1 -1
- data/lib/biodiversity/parser.rb +1 -1
- data/spec/parser/test_data.txt +6 -1
- metadata +2 -2
data/CHANGELOG
CHANGED
data/VERSION
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
1.0.
|
|
1
|
+
1.0.15
|
data/lib/biodiversity/parser.rb
CHANGED
|
@@ -14,7 +14,7 @@ module PreProcessor
|
|
|
14
14
|
NOMEN_CONCEPTS = /(,\s*|\s+)(\(?nomen|\(?nom\.|\(?comb\.).*$/i
|
|
15
15
|
COMPARATORS = /\s+(aff\.|aff)\b.*$/i
|
|
16
16
|
CF_COMPARATOR = /\s+(cf\.|cf)\s+/i
|
|
17
|
-
LAST_WORD_JUNK = /(,\s*|\s+)(spp\.|spp|var\.|var|von|van|sensu|new|non|nec|cf|ssp|subsp|subgen|hybrid|hort\.|hort)\s*$/i
|
|
17
|
+
LAST_WORD_JUNK = /(,\s*|\s+)(spp\.|spp|var\.|var|von|van|sensu|new|non|nec|cf\.|cf|sp\.|sp|ssp\.|ssp|subsp|subgen|hybrid|hort\.|hort)\s*$/i
|
|
18
18
|
|
|
19
19
|
def self.clean(a_string)
|
|
20
20
|
[NOTES, TAXON_CONCEPTS1, TAXON_CONCEPTS2, TAXON_CONCEPTS3, NOMEN_CONCEPTS, COMPARATORS, LAST_WORD_JUNK].each do |i|
|
data/spec/parser/test_data.txt
CHANGED
|
@@ -134,9 +134,14 @@ Alviniconcha cf alba|{"scientificName":{"parsed":true, "parser_version":"test_ve
|
|
|
134
134
|
Alyxia reinwardti var|{"scientificName":{"parsed":true, "parser_version":"test_version", "verbatim":"Alyxia reinwardti var", "normalized":"Alyxia reinwardti", "canonical":"Alyxia reinwardti", "hybrid":false, "details":[{"genus":{"string":"Alyxia"}, "species":{"string":"reinwardti"}}], "parser_run":1, "positions":{"0":["genus", 6], "7":["species", 17]}}}
|
|
135
135
|
Alyxia reinwardti var.|{"scientificName":{"parsed":true, "parser_version":"test_version", "verbatim":"Alyxia reinwardti var.", "normalized":"Alyxia reinwardti", "canonical":"Alyxia reinwardti", "hybrid":false, "details":[{"genus":{"string":"Alyxia"}, "species":{"string":"reinwardti"}}], "parser_run":1, "positions":{"0":["genus", 6], "7":["species", 17]}}}
|
|
136
136
|
Alyxia reinwardti ssp|{"scientificName":{"parsed":true, "parser_version":"test_version", "verbatim":"Alyxia reinwardti ssp", "normalized":"Alyxia reinwardti", "canonical":"Alyxia reinwardti", "hybrid":false, "details":[{"genus":{"string":"Alyxia"}, "species":{"string":"reinwardti"}}], "parser_run":1, "positions":{"0":["genus", 6], "7":["species", 17]}}}
|
|
137
|
-
Alyxia reinwardti ssp.|{"scientificName":{"parsed":true, "parser_version":"test_version", "verbatim":"Alyxia reinwardti ssp.", "normalized":"Alyxia reinwardti
|
|
137
|
+
Alyxia reinwardti ssp.|{"scientificName":{"parsed":true, "parser_version":"test_version", "verbatim":"Alyxia reinwardti ssp.", "normalized":"Alyxia reinwardti", "canonical":"Alyxia reinwardti", "hybrid":false, "details":[{"genus":{"string":"Alyxia"}, "species":{"string":"reinwardti"}}], "parser_run":1, "positions":{"0":["genus", 6], "7":["species", 17]}}}
|
|
138
138
|
Alaria spp|{"scientificName":{"parsed":true, "parser_version":"test_version", "verbatim":"Alaria spp", "normalized":"Alaria", "canonical":"Alaria", "hybrid":false, "details":[{"uninomial":{"string":"Alaria"}}], "parser_run":1, "positions":{"0":["uninomial", 6]}}}
|
|
139
139
|
Alaria spp.|{"scientificName":{"parsed":true, "parser_version":"test_version", "verbatim":"Alaria spp.", "normalized":"Alaria", "canonical":"Alaria", "hybrid":false, "details":[{"uninomial":{"string":"Alaria"}}], "parser_run":1, "positions":{"0":["uninomial", 6]}}}
|
|
140
|
+
Xenodon sp|{"scientificName":{"parsed":true, "parser_version":"test_version", "verbatim":"Xenodon sp", "normalized":"Xenodon", "canonical":"Xenodon", "hybrid":false, "details":[{"uninomial":{"string":"Xenodon"}}], "parser_run":1, "positions":{"0":["uninomial", 7]}}}
|
|
141
|
+
Xenodon sp.|{"scientificName":{"parsed":true, "parser_version":"test_version", "verbatim":"Xenodon sp.", "normalized":"Xenodon", "canonical":"Xenodon", "hybrid":false, "details":[{"uninomial":{"string":"Xenodon"}}], "parser_run":1, "positions":{"0":["uninomial", 7]}}}
|
|
142
|
+
Formicidae cf.|{"scientificName":{"parsed":true, "parser_version":"test_version", "verbatim":"Formicidae cf.", "normalized":"Formicidae", "canonical":"Formicidae", "hybrid":false, "details":[{"uninomial":{"string":"Formicidae"}}], "parser_run":1, "positions":{"0":["uninomial", 10]}}}
|
|
143
|
+
Formicidae cf|{"scientificName":{"parsed":true, "parser_version":"test_version", "verbatim":"Formicidae cf", "normalized":"Formicidae", "canonical":"Formicidae", "hybrid":false, "details":[{"uninomial":{"string":"Formicidae"}}], "parser_run":1, "positions":{"0":["uninomial", 10]}}}
|
|
144
|
+
|
|
140
145
|
|
|
141
146
|
#unknown authorship
|
|
142
147
|
Tragacantha leporina (?) Kuntze|{"scientificName":{"parsed":true, "parser_version":"test_version", "parser_run":1,"verbatim":"Tragacantha leporina (?) Kuntze","normalized":"Tragacantha leporina (?) Kuntze","canonical":"Tragacantha leporina","hybrid":false,"details":[{"genus":{"string":"Tragacantha"},"species":{"string":"leporina","authorship":"(?) Kuntze","combinationAuthorTeam":{"authorTeam":"Kuntze","author":["Kuntze"]},"basionymAuthorTeam":{"authorTeam":"(?)","author":["?"]}}}],"positions":{"0":["genus",11],"12":["species",20],"22":["unknown_author",23],"25":["author_word",31]}}}
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: biodiversity19
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 1.0.
|
|
4
|
+
version: 1.0.15
|
|
5
5
|
prerelease:
|
|
6
6
|
platform: ruby
|
|
7
7
|
authors:
|
|
@@ -9,7 +9,7 @@ authors:
|
|
|
9
9
|
autorequire:
|
|
10
10
|
bindir: bin
|
|
11
11
|
cert_chain: []
|
|
12
|
-
date: 2012-07-
|
|
12
|
+
date: 2012-07-30 00:00:00.000000000 Z
|
|
13
13
|
dependencies:
|
|
14
14
|
- !ruby/object:Gem::Dependency
|
|
15
15
|
name: treetop
|