Revision 10619
Added by Aaron Marcuse-Kubitza almost 11 years ago
| inputs/UNCC/Specimen/postprocess.sql | ||
|---|---|---|
| 1 | 1 |
SELECT util.search_path_append('util');
|
| 2 | 2 |
|
| 3 |
SELECT util.rename_cols(:table_str, $$ |
|
| 4 |
cultivated => *cultivated, |
|
| 5 |
flower => *flower, |
|
| 6 |
fruit => *fruit, |
|
| 7 |
$$::hstore); |
|
| 3 |
SELECT create_if_not_exists($$CREATE INDEX "Specimen.infrarank" ON $$||:table_str||$$ ("EQUIV#to:usdaRank#infrarank")$$); -- runtime: 0.1 s ("Time: 135.984 ms") @starscream
|
|
| 8 | 4 |
|
| 9 |
SELECT create_if_not_exists($$CREATE INDEX "Specimen.infrarank" ON $$||:table_str||$$ ("infrarank")$$); -- runtime: 0.1 s ("Time: 135.984 ms") @starscream
|
|
| 10 |
|
|
| 11 | 5 |
-- remove mismapped values |
| 12 |
UPDATE :table SET infrarank = NULL WHERE infrarank = 'L.'; -- runtime: ~0 ("Time: 2.370 ms") @starscream
|
|
| 6 |
UPDATE :table SET "EQUIV#to:usdaRank#infrarank" = NULL WHERE "EQUIV#to:usdaRank#infrarank" = 'L.'; -- runtime: ~0 ("Time: 2.370 ms") @starscream
|
|
| 13 | 7 |
|
| 14 | 8 |
|
| 15 | 9 |
SELECT mk_derived_col((:table_str, 'specimenDonorInstitution'), |
| 16 | 10 |
-- UNCCD likely = UNCC database |
| 17 |
$$_map('UNCCD=>UNCC, *=>*', "herbarium")$$)
|
|
| 11 |
$$_map('UNCCD=>UNCC, *=>*', "specimenDonorInstitution_verbatim")$$)
|
|
| 18 | 12 |
; -- runtime: 1 s ("Time: 1057.222 ms") @starscream
|
| 19 | 13 |
|
| 20 | 14 |
SELECT mk_derived_col((:table_str, 'recordedBy'), |
| 21 |
$$_join("collector", "collector1", "collector2", "collector3")$$)
|
|
| 15 |
$$_join("recordedBy__primary", "recordedBy__additional__1", "recordedBy__additional__2", "recordedBy__additional__3")$$)
|
|
| 22 | 16 |
; -- runtime: 1 s ("Time: 1001.616 ms") @starscream
|
| 23 | 17 |
|
| 24 | 18 |
SELECT mk_derived_col((:table_str, 'occurrenceRemarks'), |
| 25 |
$$_join("comment1", "comment2", "comment3", "comment4")$$)
|
|
| 19 |
$$_join("occurrenceRemarks__1", "occurrenceRemarks__2", "occurrenceRemarks__3", "occurrenceRemarks__4")$$)
|
|
| 26 | 20 |
; -- runtime: 1 s ("Time: 996.729 ms") @starscream
|
| 27 | 21 |
|
| 28 | 22 |
|
| ... | ... | |
| 31 | 25 |
of the codes. Presumably C = cultivated" |
| 32 | 26 |
(https://projects.nceas.ucsb.edu/nceas/attachments/download/723/UNCC-validate_rkp_bb_rkp.xlsx#Campus) |
| 33 | 27 |
*/ |
| 34 |
$$_map('*=>true', "campus")$$)
|
|
| 28 |
$$_map('*=>true', "cultivated__campus__verbatim")$$)
|
|
| 35 | 29 |
; -- runtime: 0.5 s ("Time: 353.373 ms") @starscream
|
| 36 | 30 |
|
| 37 | 31 |
SELECT mk_derived_col((:table_str, 'cultivated__main'), |
| 38 | 32 |
-- for our purposes, anything non-NULL should be assumed to be cultivated |
| 39 |
$$_map('*=>true', "*cultivated")$$)
|
|
| 33 |
$$_map('*=>true', "cultivated__main__verbatim")$$)
|
|
| 40 | 34 |
; -- runtime: 0.5 s ("Time: 403.916 ms") @starscream
|
| 41 | 35 |
|
| 42 | 36 |
SELECT mk_derived_col((:table_str, 'cultivated'), |
| ... | ... | |
| 63 | 57 |
LANGUAGE sql IMMUTABLE |
| 64 | 58 |
COST 100; |
| 65 | 59 |
|
| 66 |
SELECT mk_derived_col((:table_str, 'flower'), $$map_reproductive_condition("*flower")$$); -- runtime: 0.5 s ("Time: 635.054 ms") @starscream
|
|
| 67 |
SELECT mk_derived_col((:table_str, 'fruit' ), $$map_reproductive_condition("*fruit" )$$); -- runtime: 0.5 s ("Time: 591.854 ms") @starscream
|
|
| 60 |
SELECT mk_derived_col((:table_str, 'flower'), $$map_reproductive_condition("flower_verbatim")$$); -- runtime: 0.5 s ("Time: 635.054 ms") @starscream
|
|
| 61 |
SELECT mk_derived_col((:table_str, 'fruit' ), $$map_reproductive_condition("fruit_verbatim" )$$); -- runtime: 0.5 s ("Time: 591.854 ms") @starscream
|
|
| 68 | 62 |
|
| 69 | 63 |
SELECT mk_derived_col((:table_str, 'reproductiveCondition'), |
| 70 | 64 |
-- using the suggested values at DwC.vegpath.org?reproductiveCondition |
| inputs/UNCC/Specimen/run | ||
|---|---|---|
| 1 |
#!/bin/bash -e |
|
| 2 |
. "$(dirname "${BASH_SOURCE[0]}")"/../table.run
|
|
| 0 | 3 | |
| inputs/UNCC/Specimen/map.csv | ||
|---|---|---|
| 46 | 46 |
cultivated,cultivated__main__verbatim,, |
| 47 | 47 |
filler,*filler,,"Where used, same as family" |
| 48 | 48 |
:UNCC,specimenHolderInstitutions,, |
| 49 |
recordedBy,recordedBy,, |
|
| 50 |
cultivated,cultivated,, |
|
| 51 |
reproductiveCondition,reproductiveCondition,, |
|
| 52 |
occurrenceRemarks,occurrenceRemarks,, |
|
| inputs/UNCC/Specimen/test.xml.ref | ||
|---|---|---|
| 10 | 10 |
<authorlocationcode> |
| 11 | 11 |
<_join> |
| 12 | 12 |
<1>UNCC</1> |
| 13 |
<3>$accession</3> |
|
| 13 |
<3>$accessionNumber</3>
|
|
| 14 | 14 |
</_join> |
| 15 | 15 |
</authorlocationcode> |
| 16 | 16 |
<iscultivated> |
| ... | ... | |
| 32 | 32 |
<_nullIf> |
| 33 | 33 |
<null>0</null> |
| 34 | 34 |
<type>float</type> |
| 35 |
<value>$collday</value>
|
|
| 35 |
<value>$dayCollected</value>
|
|
| 36 | 36 |
</_nullIf> |
| 37 | 37 |
</day> |
| 38 | 38 |
<month> |
| 39 | 39 |
<_nullIf> |
| 40 | 40 |
<null>0</null> |
| 41 | 41 |
<type>float</type> |
| 42 |
<value>$collmonth</value>
|
|
| 42 |
<value>$monthCollected</value>
|
|
| 43 | 43 |
</_nullIf> |
| 44 | 44 |
</month> |
| 45 | 45 |
<year> |
| 46 | 46 |
<_nullIf> |
| 47 | 47 |
<null>0</null> |
| 48 | 48 |
<type>float</type> |
| 49 |
<value>$collyear</value>
|
|
| 49 |
<value>$yearCollected</value>
|
|
| 50 | 50 |
</_nullIf> |
| 51 | 51 |
</year> |
| 52 | 52 |
</_date> |
| 53 | 53 |
</collectiondate> |
| 54 | 54 |
<notes>$occurrenceRemarks</notes> |
| 55 | 55 |
<plantobservation> |
| 56 |
<authorplantcode>$collectno</authorplantcode>
|
|
| 56 |
<authorplantcode>$collectorNumber</authorplantcode>
|
|
| 57 | 57 |
<reproductivecondition>$reproductiveCondition</reproductivecondition> |
| 58 | 58 |
<specimenreplicate> |
| 59 |
<catalognumber_dwc>$accession</catalognumber_dwc> |
|
| 60 |
<collectionnumber>$collectno</collectionnumber>
|
|
| 59 |
<catalognumber_dwc>$accessionNumber</catalognumber_dwc>
|
|
| 60 |
<collectionnumber>$collectorNumber</collectionnumber>
|
|
| 61 | 61 |
<institution_id> |
| 62 | 62 |
<sourcelist> |
| 63 | 63 |
<name>UNCC</name> |
| ... | ... | |
| 83 | 83 |
<taxonlabel> |
| 84 | 84 |
<parent_id> |
| 85 | 85 |
<taxonlabel> |
| 86 |
<rank>$usdaRank</rank>
|
|
| 86 |
<rank>$taxonRank</rank>
|
|
| 87 | 87 |
<parent_id> |
| 88 | 88 |
<taxonlabel> |
| 89 | 89 |
<rank>cultivar</rank> |
| ... | ... | |
| 99 | 99 |
<parent_id> |
| 100 | 100 |
<taxonlabel> |
| 101 | 101 |
<rank>species</rank> |
| 102 |
<taxonepithet>$species</taxonepithet>
|
|
| 102 |
<taxonepithet>$specificEpithet</taxonepithet>
|
|
| 103 | 103 |
<parent_id> |
| 104 | 104 |
<taxonlabel> |
| 105 | 105 |
<rank>genus</rank> |
| ... | ... | |
| 122 | 122 |
</parent_id> |
| 123 | 123 |
</taxonlabel> |
| 124 | 124 |
</parent_id> |
| 125 |
<taxonepithet>$infraname</taxonepithet>
|
|
| 125 |
<taxonepithet>$infraspecificEpithet</taxonepithet>
|
|
| 126 | 126 |
</taxonlabel> |
| 127 | 127 |
</parent_id> |
| 128 |
<rank>$usdaRank</rank>
|
|
| 128 |
<rank>$taxonRank</rank>
|
|
| 129 | 129 |
<taxonomicname> |
| 130 | 130 |
<_merge_prefix> |
| 131 | 131 |
<prefix><_taxon_family_require_std><family>$family</family></_taxon_family_require_std></prefix> |
| ... | ... | |
| 133 | 133 |
<_join_words> |
| 134 | 134 |
<1> |
| 135 | 135 |
<_alt> |
| 136 |
<1>$SciName</1>
|
|
| 136 |
<1>$taxonName</1>
|
|
| 137 | 137 |
<2> |
| 138 | 138 |
<_join_words> |
| 139 | 139 |
<2><_filter_genus><value>$genus</value></_filter_genus></2> |
| 140 |
<3>$species</3>
|
|
| 140 |
<3>$specificEpithet</3>
|
|
| 141 | 141 |
<5> |
| 142 | 142 |
<_join_words> |
| 143 | 143 |
<1> |
| 144 | 144 |
<_if name="if has infraspecificEpithet"> |
| 145 |
<cond>$infraname</cond>
|
|
| 146 |
<then>$usdaRank</then>
|
|
| 145 |
<cond>$infraspecificEpithet</cond>
|
|
| 146 |
<then>$taxonRank</then>
|
|
| 147 | 147 |
</_if> |
| 148 | 148 |
</1> |
| 149 |
<2>$infraname</2>
|
|
| 149 |
<2>$infraspecificEpithet</2>
|
|
| 150 | 150 |
</_join_words> |
| 151 | 151 |
</5> |
| 152 | 152 |
</_join_words> |
| 153 | 153 |
</2> |
| 154 | 154 |
</_alt> |
| 155 | 155 |
</1> |
| 156 |
<2>$authors</2>
|
|
| 156 |
<2>$scientificNameAuthorship</2>
|
|
| 157 | 157 |
</_join_words> |
| 158 | 158 |
</value> |
| 159 | 159 |
</_merge_prefix> |
| 160 | 160 |
</taxonomicname> |
| 161 | 161 |
</taxonlabel> |
| 162 | 162 |
</taxonlabel_id> |
| 163 |
<author>$authors</author>
|
|
| 163 |
<author>$scientificNameAuthorship</author>
|
|
| 164 | 164 |
<family>$family</family> |
| 165 | 165 |
<genus>$genus</genus> |
| 166 |
<specific_epithet>$species</specific_epithet>
|
|
| 167 |
<taxonname>$SciName</taxonname>
|
|
| 168 |
<verbatimrank>$usdaRank</verbatimrank>
|
|
| 166 |
<specific_epithet>$specificEpithet</specific_epithet>
|
|
| 167 |
<taxonname>$taxonName</taxonname>
|
|
| 168 |
<verbatimrank>$taxonRank</verbatimrank>
|
|
| 169 | 169 |
</taxonverbatim> |
| 170 | 170 |
</taxonverbatim_id> |
| 171 | 171 |
</taxondetermination> |
| ... | ... | |
| 192 | 192 |
<source_id><source><shortname>geoscrub</shortname></source></source_id> |
| 193 | 193 |
<country>$country</country> |
| 194 | 194 |
<county>$county</county> |
| 195 |
<stateprovince>$state</stateprovince> |
|
| 195 |
<stateprovince>$stateProvince</stateprovince>
|
|
| 196 | 196 |
</place> |
| 197 | 197 |
</matched_place_id> |
| 198 |
<stateprovince>$state</stateprovince> |
|
| 198 |
<stateprovince>$stateProvince</stateprovince>
|
|
| 199 | 199 |
</place> |
| 200 | 200 |
</place_id> |
| 201 | 201 |
</locationplace> |
| inputs/UNCC/Specimen/VegBIEN.csv | ||
|---|---|---|
| 1 |
UNCC,VegBIEN:/_setDefault:[source_id/source/shortname/_env:[name=source]]/path/_simplifyPath:[next=parent_id]/path,Comments |
|
| 2 |
accession,"/_if[@name=""if specimen""]/cond/_exists","Globally unique, although occasionally duplicated. [1] |
|
| 3 |
|
|
| 4 |
[1] Using the following query: |
|
| 5 |
----- |
|
| 6 |
SELECT herbarium, accession, count(*) |
|
| 7 |
FROM ""UNCC"".""Specimen"" |
|
| 8 |
GROUP BY herbarium, accession |
|
| 9 |
HAVING count(*) > 1 |
|
| 10 |
-----" |
|
| 11 |
:UNCC,"/_if[@name=""if specimen""]/else/source/shortname/_first/1", |
|
| 12 |
accession,"/location/_if[@name=""if subplot""]/else/authorlocationcode/_first/3/_if[@name=""if plot""]/else/_alt/2/_if[@name=""if catalogNumber""]/cond/_exists","Globally unique, although occasionally duplicated. [1] |
|
| 13 |
|
|
| 14 |
[1] Using the following query: |
|
| 15 |
----- |
|
| 16 |
SELECT herbarium, accession, count(*) |
|
| 17 |
FROM ""UNCC"".""Specimen"" |
|
| 18 |
GROUP BY herbarium, accession |
|
| 19 |
HAVING count(*) > 1 |
|
| 20 |
-----" |
|
| 21 |
accession,"/location/_if[@name=""if subplot""]/else/authorlocationcode/_first/3/_if[@name=""if plot""]/else/_alt/2/_if[@name=""if catalogNumber""]/then/_join/1/_if[@name=""if specimen""]/cond/_exists","Globally unique, although occasionally duplicated. [1] |
|
| 22 |
|
|
| 23 |
[1] Using the following query: |
|
| 24 |
----- |
|
| 25 |
SELECT herbarium, accession, count(*) |
|
| 26 |
FROM ""UNCC"".""Specimen"" |
|
| 27 |
GROUP BY herbarium, accession |
|
| 28 |
HAVING count(*) > 1 |
|
| 29 |
-----" |
|
| 30 |
:UNCC,"/location/_if[@name=""if subplot""]/else/authorlocationcode/_first/3/_if[@name=""if plot""]/else/_alt/2/_if[@name=""if catalogNumber""]/then/_join/1/_if[@name=""if specimen""]/then/_first/2", |
|
| 31 |
accession,"/location/_if[@name=""if subplot""]/else/authorlocationcode/_first/3/_if[@name=""if plot""]/else/_alt/2/_if[@name=""if catalogNumber""]/then/_join/3/_if[@name=""if indirect voucher""]/else","Globally unique, although occasionally duplicated. [1] |
|
| 32 |
|
|
| 33 |
[1] Using the following query: |
|
| 34 |
----- |
|
| 35 |
SELECT herbarium, accession, count(*) |
|
| 36 |
FROM ""UNCC"".""Specimen"" |
|
| 37 |
GROUP BY herbarium, accession |
|
| 38 |
HAVING count(*) > 1 |
|
| 39 |
-----" |
|
| 40 |
collectno,"/location/iscultivated/_or/1/_if[@name=""if TaxonOccurrence""]/cond/_exists", |
|
| 41 |
cultivated,"/location/iscultivated/_or/1/_if[@name=""if TaxonOccurrence""]/else/_first/1", |
|
| 42 |
locality,/location/iscultivated/_or/2/_locationnarrative_is_cultivated/locationnarrative/_join/1, |
|
| 43 |
habitat,/location/iscultivated/_or/2/_locationnarrative_is_cultivated/locationnarrative/_join/3, |
|
| 44 |
collday,"/location/locationevent/taxonoccurrence/aggregateoccurrence/collectiondate/_alt/2/_date/day/_nullIf:[null=0,type=float]/value", |
|
| 45 |
collmonth,"/location/locationevent/taxonoccurrence/aggregateoccurrence/collectiondate/_alt/2/_date/month/_nullIf:[null=0,type=float]/value", |
|
| 46 |
collyear,"/location/locationevent/taxonoccurrence/aggregateoccurrence/collectiondate/_alt/2/_date/year/_nullIf:[null=0,type=float]/value", |
|
| 47 |
occurrenceRemarks,/location/locationevent/taxonoccurrence/aggregateoccurrence/notes/_join/1, |
|
| 48 |
collectno,/location/locationevent/taxonoccurrence/aggregateoccurrence/plantobservation/authorplantcode/_first/2, |
|
| 49 |
reproductiveCondition,/location/locationevent/taxonoccurrence/aggregateoccurrence/plantobservation/reproductivecondition, |
|
| 50 |
accession,"/location/locationevent/taxonoccurrence/aggregateoccurrence/plantobservation/specimenreplicate/catalognumber_dwc/_if[@name=""if indirect voucher""]/else","Globally unique, although occasionally duplicated. [1] |
|
| 51 |
|
|
| 52 |
[1] Using the following query: |
|
| 53 |
----- |
|
| 54 |
SELECT herbarium, accession, count(*) |
|
| 55 |
FROM ""UNCC"".""Specimen"" |
|
| 56 |
GROUP BY herbarium, accession |
|
| 57 |
HAVING count(*) > 1 |
|
| 58 |
-----" |
|
| 59 |
collectno,"/location/locationevent/taxonoccurrence/aggregateoccurrence/plantobservation/specimenreplicate/collectionnumber/_if[@name=""if indirect voucher""]/else", |
|
| 60 |
accession,"/location/locationevent/taxonoccurrence/aggregateoccurrence/plantobservation/specimenreplicate/institution_id/sourcelist/_if[@name=""if specimen""]/cond/_exists","Globally unique, although occasionally duplicated. [1] |
|
| 61 |
|
|
| 62 |
[1] Using the following query: |
|
| 63 |
----- |
|
| 64 |
SELECT herbarium, accession, count(*) |
|
| 65 |
FROM ""UNCC"".""Specimen"" |
|
| 66 |
GROUP BY herbarium, accession |
|
| 67 |
HAVING count(*) > 1 |
|
| 68 |
-----" |
|
| 69 |
:UNCC,"/location/locationevent/taxonoccurrence/aggregateoccurrence/plantobservation/specimenreplicate/institution_id/sourcelist/_if[@name=""if specimen""]/then/name/_first/2", |
|
| 70 |
:UNCC,"/location/locationevent/taxonoccurrence/aggregateoccurrence/plantobservation/specimenreplicate/institution_id/sourcelist/_if[@name=""if specimen""]/then/sourcename/name/_first/2/_split:[separator=""[,;] *""]/value", |
|
| 71 |
collectno,"/location/locationevent/taxonoccurrence/authortaxoncode/_if[@name=""if in plot""]/then/_first/2/_first/3", |
|
| 72 |
SciName,"/location/locationevent/taxonoccurrence/authortaxoncode/_if[@name=""if in plot""]/then/_first/3/_first/3", |
|
| 73 |
recordedBy,/location/locationevent/taxonoccurrence/collector_id/party/fullname, |
|
| 74 |
collectno,"/location/locationevent/taxonoccurrence/iscultivated/_alt/1/_if[@name=""if TaxonOccurrence""]/cond/_exists", |
|
| 75 |
cultivated,"/location/locationevent/taxonoccurrence/iscultivated/_alt/1/_if[@name=""if TaxonOccurrence""]/then/_first/1", |
|
| 76 |
usdaRank,"/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonverbatim/*_id/taxonlabel/parent_id/taxonlabel/_if[@name=""if has explicit parent""]/else/rank",is infraspecificRank__abbr |
|
| 77 |
species,"/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonverbatim/*_id/taxonlabel/parent_id/taxonlabel/parent_id/_forEach:[in:[cultivar,forma,variety,subspecies,],do=""taxonlabel[rank=_val]/parent_id""]/taxonlabel[rank=species]/taxonepithet", |
|
| 78 |
genus,"/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonverbatim/*_id/taxonlabel/parent_id/taxonlabel/parent_id/_forEach:[in:[cultivar,forma,variety,subspecies,species,],do=""taxonlabel[rank=_val]/parent_id""]/taxonlabel[rank=genus]/taxonepithet", |
|
| 79 |
family,"/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonverbatim/*_id/taxonlabel/parent_id/taxonlabel/parent_id/_forEach:[in:[cultivar,forma,variety,subspecies,species,genus,],do=""taxonlabel[rank=_val]/parent_id""]/taxonlabel[rank=family]/taxonepithet", |
|
| 80 |
infraname,/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonverbatim/*_id/taxonlabel/parent_id/taxonlabel/taxonepithet, |
|
| 81 |
usdaRank,/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonverbatim/*_id/taxonlabel/rank,is infraspecificRank__abbr |
|
| 82 |
usdaRank,"/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonverbatim/*_id/taxonlabel/taxonepithet/_if[@name=""if taxonomic name is epithet""]/cond/_alt:[2=true]/1/_taxonomic_name_is_epithet/rank",is infraspecificRank__abbr |
|
| 83 |
family,/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonverbatim/*_id/taxonlabel/taxonomicname/_merge_prefix/prefix/_taxon_family_require_std/family, |
|
| 84 |
SciName,/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonverbatim/*_id/taxonlabel/taxonomicname/_merge_prefix/value/_alt/2/_join_words/1/_alt/1, |
|
| 85 |
genus,/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonverbatim/*_id/taxonlabel/taxonomicname/_merge_prefix/value/_alt/2/_join_words/1/_alt/2/_join_words/2/_filter_genus/value, |
|
| 86 |
species,/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonverbatim/*_id/taxonlabel/taxonomicname/_merge_prefix/value/_alt/2/_join_words/1/_alt/2/_join_words/3/_join_words/1, |
|
| 87 |
infraname,"/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonverbatim/*_id/taxonlabel/taxonomicname/_merge_prefix/value/_alt/2/_join_words/1/_alt/2/_join_words/5/_join_words/1/_if[@name=""if has infraspecificEpithet""]/cond", |
|
| 88 |
usdaRank,"/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonverbatim/*_id/taxonlabel/taxonomicname/_merge_prefix/value/_alt/2/_join_words/1/_alt/2/_join_words/5/_join_words/1/_if[@name=""if has infraspecificEpithet""]/then",is infraspecificRank__abbr |
|
| 89 |
infraname,/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonverbatim/*_id/taxonlabel/taxonomicname/_merge_prefix/value/_alt/2/_join_words/1/_alt/2/_join_words/5/_join_words/2, |
|
| 90 |
authors,/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonverbatim/*_id/taxonlabel/taxonomicname/_merge_prefix/value/_alt/2/_join_words/2, |
|
| 91 |
authors,/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonverbatim/author, |
|
| 92 |
family,/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonverbatim/family, |
|
| 93 |
genus,/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonverbatim/genus, |
|
| 94 |
species,/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonverbatim/specific_epithet, |
|
| 95 |
SciName,/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonverbatim/taxonname, |
|
| 96 |
usdaRank,/location/locationevent/taxonoccurrence/taxondetermination[!isoriginal]/*_id/taxonverbatim/verbatimrank,is infraspecificRank__abbr |
|
| 97 |
accession,"/location/locationevent/taxonoccurrence/voucher/*_id/specimenreplicate/catalognumber_dwc/_if[@name=""if indirect voucher""]/then","Globally unique, although occasionally duplicated. [1] |
|
| 98 |
|
|
| 99 |
[1] Using the following query: |
|
| 100 |
----- |
|
| 101 |
SELECT herbarium, accession, count(*) |
|
| 102 |
FROM ""UNCC"".""Specimen"" |
|
| 103 |
GROUP BY herbarium, accession |
|
| 104 |
HAVING count(*) > 1 |
|
| 105 |
-----" |
|
| 106 |
collectno,"/location/locationevent/taxonoccurrence/voucher/*_id/specimenreplicate/collectionnumber/_if[@name=""if indirect voucher""]/then", |
|
| 107 |
locality,/location/locationnarrative/_merge/1, |
|
| 108 |
habitat,"/location/locationnarrative/_merge/3/_label[label=""habitat""]/value","Brad: Free-text description of vegetation community where collected, frequently redundane wrt 'Vegetation'. Bob, Nick: keep as user defined or create special element?" |
|
| 109 |
country,/location/locationplace/*_id/place/country, |
|
| 110 |
county,/location/locationplace/*_id/place/county, |
|
| 111 |
country,/location/locationplace/*_id/place/matched_place_id/place:[source_id/source/shortname=geoscrub]/country/_first/2, |
|
| 112 |
county,/location/locationplace/*_id/place/matched_place_id/place:[source_id/source/shortname=geoscrub]/county/_first/2, |
|
| 113 |
state,/location/locationplace/*_id/place/matched_place_id/place:[source_id/source/shortname=geoscrub]/stateprovince/_first/2, |
|
| 114 |
state,/location/locationplace/*_id/place/stateprovince, |
|
| 115 |
campus,,"** No join mapping for cultivated__campus__verbatim ** ""this refers to occurrence on the UNCC campus, but I do not know the meaning of the codes. Presumably C = cultivated"" (https://projects.nceas.ucsb.edu/nceas/attachments/download/723/UNCC-validate_rkp_bb_rkp.xlsx#Campus)" |
|
| 116 |
collector,,** No join mapping for recordedBy__primary ** |
|
| 117 |
collector1,,** No join mapping for recordedBy__additional__1 ** |
|
| 118 |
collector2,,** No join mapping for recordedBy__additional__2 ** |
|
| 119 |
collector3,,** No join mapping for recordedBy__additional__3 ** |
|
| 120 |
comment1,,** No join mapping for occurrenceRemarks__1 ** |
|
| 121 |
comment2,,** No join mapping for occurrenceRemarks__2 ** |
|
| 122 |
comment3,,** No join mapping for occurrenceRemarks__3 ** |
|
| 123 |
comment4,,** No join mapping for occurrenceRemarks__4 ** |
|
| 124 |
cultivated,,** No join mapping for cultivated__main__verbatim ** |
|
| 125 |
filler,,"** No join mapping for *filler ** Where used, same as family" |
|
| 126 |
flower,,** No join mapping for flower_verbatim ** |
|
| 127 |
fruit,,** No join mapping for fruit_verbatim ** |
|
| 128 |
herbarium,,"** No join mapping for specimenDonorInstitution_verbatim ** ""The name or acronym in use by the institution that donated the collection"" (https://projects.nceas.ucsb.edu/nceas/attachments/download/593/UNCC-validation-Peet.xlsx#institutionCode)" |
|
| 129 |
infrarank,,** No non-empty join mapping for EQUIV#to:usdaRank#infrarank ** is infraspecificRank__abbr__verbatim |
|
| 130 |
inorout,,"** No join mapping for *inorout ** values: I, A. only populated in 19 rows." |
|
| 131 |
leaves,,** No join mapping for *leaves ** |
|
| 132 |
loanto,,** No join mapping for *loanto ** only populated in one row |
|
| 133 |
root,,** No join mapping for *root ** |
|
| 134 |
row_num,,** No join mapping for *row_num ** |
|
| 135 |
sheetno,,** No join mapping for associatedMedia ** ? |
|
| 1 |
link ../../../mappings/VegCore-VegBIEN.csv |
|
| 136 | 2 | |
| inputs/UNCC/run | ||
|---|---|---|
| 1 |
#!/bin/bash -e |
|
| 2 |
. "$(dirname "${BASH_SOURCE[0]}")"/../../lib/runscripts/datasrc_dir.run
|
|
| 0 | 3 | |
Also available in: Unified diff
inputs/UNCC/: switched to new-style import, using the steps at http://wiki.vegpath.org/Adding_new-style_import_to_a_datasource