Project

General

Profile

« Previous | Next » 

Revision 1139

input.Makefile: Generate full via maps from input via maps by appending mappings from the via format to itself when available

View differences:

inputs/NYBG/maps/DwC.specimens.full.csv
1
"NYBG-DwC:nybg_raw","DwC::[@xmlns:dcterms=""http://purl.org/dc/terms/""]/list:[institutionCode=$/_ignore/inLabel]/","Comments"
2
"key",,
3
"DateLastModified","dcterms:modified",
4
"InstitutionCode",,
5
"CollectionCode","collectionCode",
6
"CatalogNumber","catalogNumber",
7
"ScientificName","scientificName",
8
"BasisOfRecord","basisOfRecord",
9
"Kingdom","kingdom",
10
"Phylum","phylum",
11
"Class","class",
12
"Order","order",
13
"Family","family",
14
"Genus","genus",
15
"Species","specificEpithet",
16
"Subspecies","infraspecificEpithet",
17
"ScientificNameAuthor","scientificNameAuthorship",
18
"IdentifiedBy","identifiedBy",
19
"YearIdentified","dateIdentified/_alt/2/_date/year",
20
"MonthIdentified","dateIdentified/_alt/2/_date/month",
21
"DayIdentified","dateIdentified/_alt/2/_date/day",
22
"IdentifiedDate",,
23
"TypeStatus","typeStatus",
24
"CollectorNumber","recordNumber",
25
"FieldNumber","fieldNumber",
26
"Collector","recordedBy",
27
"YearCollected","eventDate/_alt/2/_date/year",
28
"MonthCollected","eventDate/_alt/2/_date/month",
29
"DayCollected","eventDate/_alt/2/_date/day",
30
"CollectedDate",,
31
"JulianDay","day",
32
"TimeOfDay","eventTime",
33
"ContinentOcean","continent",
34
"Country","country",
35
"StateProvince","stateProvince",
36
"County","county",
37
"Locality","verbatimLocality",
38
"Longitude","verbatimLongitude",
39
"Latitude","verbatimLatitude",
40
"CoordinatePrecision","coordinatePrecision/_noCV/value",
41
"BoundingBox","footprintWKT",
42
"MinimumElevation","minimumElevationInMeters",
43
"MaximumElevation","maximumElevationInMeters",
44
"MinimumDepth","minimumDepthInMeters",
45
"MaximumDepth","maximumDepthInMeters",
46
"Sex","sex",
47
"PreparationType","preparations",
48
"IndividualCount","individualCount",
49
"PreviousCatalogNumber","previousIdentifications","?"
50
"RelationshipType","relationshipOfResource",
51
"RelatedCatalogItem","relatedResourceID",
52
"Notes","fieldNotes/_merge/1",
53
"Habitat","habitat/_merge/1",
54
"PlantFungusDescription","fieldNotes/_merge/2/_label[label=""plant fungus""]/value",
55
"Substrate","bien.substrate",
56
"Vegetation","habitat/_merge/2",
57
"UniqueNYInternalRecordNumber","occurrenceID",
inputs/NYBG/DwC.specimens2.csv
1
"NYBG-DwC:nybg_raw","DwC::[@xmlns:dcterms=""http://purl.org/dc/terms/""]/list:[institutionCode=$/_ignore/inLabel]/","Comments"
2
"key",,
3
"InstitutionCode",,"Map to nothing so it doesn't overwrite the auto-generated institutionCode"
4
"IdentifiedDate",,
5
"CollectedDate",,
6
"Habitat","habitat/_merge/1",
7
"PlantFungusDescription","fieldNotes/_merge/2/_label[label=""plant fungus""]/value",
8
"Substrate","bien.substrate",
9
"Vegetation","habitat/_merge/2",
10
"UniqueNYInternalRecordNumber","occurrenceID",
inputs/SALVIAS/maps/VegX.plots.full.csv
1
"SALVIAS:plotMetadata","VegX:/*s/plotObservation","Comments"
2
"PlotID",":[partyWithRole/*ID->/parties/party/organizationName=$/_ignore/inLabel]/simpleUserdefined[name=sourceaccessioncode]/value","Brad: This is artificial internal database ID; a unique identifier within SALVIAS DB to each plot, within the table plotMetadata."
3
"orig_filename",,
4
"AccessCode",,
5
"project_id","/*ID->/*s/project:[personnel[role=metadataProvider]/organizationName=$/_ignore/inLabel]/title",
6
"PrimOwnerID",,
7
"SiteCode",":[partyWithRole/*ID->/parties/party/organizationName=$/_ignore/inLabel]/*UniqueIdentifierID->/*s/plot/plotUniqueIdentifier","Brad: plotCode is as-assigned by data provider; guranteed to be unique only within dataset (=project)"
8
"SiteName",,
9
"new_world",,
10
"MajorGeo","/*UniqueIdentifierID->/*s/plot/simpleUserdefined[name=majorGeo]/value",
11
"Country","/*UniqueIdentifierID->/*s/plot/country",
12
"PolDiv1","/*UniqueIdentifierID->/*s/plot/state","Brad: No; pol1=stateProvince"
13
"pol1_type",,
14
"pol2","/*UniqueIdentifierID->/*s/plot/county","Brad: No pol2=countyParish"
15
"pol2_type",,
16
"lat_string",,
17
"long_string",,
18
"LatDec","/*UniqueIdentifierID->/*s/plot/geospatial/DecimalLatitude",
19
"LongDec","/*UniqueIdentifierID->/*s/plot/geospatial/DecimalLongitude",
20
"lat_long_accuracy",,
21
"Elev","/*UniqueIdentifierID->/*s/plot/geospatial/verbatimElevation","Brad: Mean elevation in meters. This is a constrained decimal value; is there no place for this in VegX other than verbatimElevation? Check with Nick."
22
"elev_max_m","/*UniqueIdentifierID->/*s/plot/geospatial/maximumElevationInMeters",
23
"elev_min_m","/*UniqueIdentifierID->/*s/plot/geospatial/minimumElevationInMeters",
24
"Precip","/simpleUserdefined[name=precipMm]/value",
25
"ElevSource",,
26
"Temp","/temperature",
27
"PrecipSource",,
28
"TempSource",,
29
"bearing",,
30
"slope_aspect","/*UniqueIdentifierID->/*s/plot/slopeAspect",
31
"slope_gradient","/*UniqueIdentifierID->/*s/plot/slopeGradient",
32
"clay_percent","->/*s/abioticObservation[*ID]/simpleUserdefined[name=clayPercent]/value",
33
"silt_percent","->/*s/abioticObservation[*ID]/simpleUserdefined[name=siltPercent]/value",
34
"sand_percent","->/*s/abioticObservation[*ID]/simpleUserdefined[name=sandPercent]/value",
35
"pH","->/*s/abioticObservation[*ID]/ph","Brad: For all these soil variables, how do we store information on method, units. Seems like an ontological structure would be more appropriate (measurementName, measurementValue, measurementUnits, measurementMethod). Same as BIEN traits table. Something to discuss."
36
"soil_N","->/*s/abioticObservation[*ID]/nitrogen",
37
"soil_P","->/*s/abioticObservation[*ID]/phosphorus",
38
"soil_C","->/*s/abioticObservation[*ID]/simpleUserdefined[name=carbon]/value",
39
"soil_K","->/*s/abioticObservation[*ID]/pottasium",
40
"soil_Mg","->/*s/abioticObservation[*ID]/magnesium",
41
"soil_Ca","->/*s/abioticObservation[*ID]/simpleUserdefined[name=calcium]/value",
42
"soil_Na","->/*s/abioticObservation[*ID]/simpleUserdefined[name=sodium]/value",
43
"soil_acidity","->/*s/abioticObservation[*ID]/simpleUserdefined[name=acidity]/value",
44
"soil_base","->/*s/abioticObservation[*ID]/simpleUserdefined[name=base]/value",
45
"soil_cation_cap","->/*s/abioticObservation[*ID]/simpleUserdefined[name=cationCap]/value",
46
"soil_conductivity","->/*s/abioticObservation[*ID]/simpleUserdefined[name=conductivity]/value",
47
"organic_percent","->/*s/abioticObservation[*ID]/simpleUserdefined[name=organicPercent]/value",
48
"soil_texture","->/*s/abioticObservation[*ID]/simpleUserdefined[name=texture]/value",
49
"RevisionComments",,
50
"Locality_Description","/*UniqueIdentifierID->/*s/plot/simpleUserdefined[name=localityDescription]/value","Brad: No; this is free text description of locality where plot was situated, same as for DwC. Not a description of vegetation. Most likely='namedPlace.placeDescription' in VB; not sure about VX, again need to ask Nick where locality descriptions live in VX"
51
"topography_desc",,
52
"vegetation_1",,
53
"vegetation_2",,
54
"Habitat",,
55
"life_zone_code","->/*s/communityDetermination[*ID]/*s/communityConcept/commonName",
56
"life_zone","->/*s/communityDetermination[*ID]/*s/communityConcept/name",
57
"PlotMethod","/simpleUserdefined[name=plotMethodology]/value",
58
"MethodCode",,
59
"plot_area_ha","/*UniqueIdentifierID->/*s/plot/area","Brad: Area in hectares. Is there any way to store units?; Aaron: VegX plot area annotation says ""Total area of the plot in square meters."" so units are fixed"
60
"recensused",,"Brad: This is a 0/1 value, internal to SALVIAS. 1 indicates that a  plot has >1 set of values, from different census events.; Aaron: Different censuses are distinguished in organisms data by different census_no values"
61
"date_start","/obsStartDate/_*/date",
62
"date_finish","/obsEndDate/_*/date",
63
"plot_administrator",,
64
"plot_notes",,
65
"tmp_del",,
inputs/SALVIAS/maps/VegX.organisms.full.csv
1
"SALVIAS:plotObservations","VegX:/*s/individualOrganismObservation","Comments"
2
"PlotObsID",":[*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept/partyWithRole/*ID->/parties/party/organizationName=$/_ignore/inLabel]/simpleUserdefined[name=sourceaccessioncode]/value","Brad: Neither is correct; this is just an internal ID for table plotObservations. However, it has the important property of uniquely identifying an ""observation"", which is an individual tree, in the case of an individual observation, or a records of a species with an associated count of individuals or measurement of percent cover, in the case of aggregate observations. Not sure where to store this. Main point is that it is not part of the original data, but an auto_increment added later."
3
"PlotID","/*ID->/*s/plotObservation/simpleUserdefined[name=parent]/value->/*s/plotObservation:[partyWithRole/*ID->/parties/party/organizationName=$/_ignore/inLabel]/simpleUserdefined[name=sourceaccessioncode]/value","Brad: Not sure why this is repeated? This field and plotCode, as the same as above."
4
"PlotCode","/*ID->/*s/plotObservation/simpleUserdefined[name=parent]/value->/*s/plotObservation/*UniqueIdentifierID->/*s/plot/plotUniqueIdentifier","Brad: Same as plotCode, above"
5
"census_no","/simpleUserdefined[name=censusNo]/value","Brad: Assigned by SALVIAS. 1 for first plot, then 2, 3, etc. I can't recall if we even have repeat censuses in SALVIAS. Probably not."
6
"census_date","/simpleUserdefined[name=collectionDate]/value/_*/date",
7
"OrigRecordID",,
8
"Line","/*ID->/*s/plotObservation:[partyWithRole/*ID->/parties/party/organizationName=$/_ignore/inLabel]/*UniqueIdentifierID->/*s/plot/plotUniqueIdentifier",
9
"Ind","/simpleUserdefined[name=individualCode]/value","Brad: Code, if any, used by the data provider to indicate an individual tree. Scope is unknown, although typically this value is unique only within plot, or sometimes only within subplot."
10
"ind_id",,"Brad: OMIT"
11
"tag1","/*ID->/*s/individualOrganism/identificationLabel","Brad: Another type of code, typically a number, used by the original data provider to indicate an individual tree. These are numbers on physical tags attached to the tree. Tag2 Is the same thing, only used if the first tag was lost. Obviously not a good system as it's possible a tree tag could be lost and changed more than once."
12
"tag2","/simpleUserdefined[name=tag2]/value","Brad: See commend for tag1. Your mapping for tag2 looks correct. Probably both values would go here, only nested, with one superceding the other."
13
"x_position","/simpleUserdefined[name=xPosition]/value","Brad: Correct for VegBank. I'm not so sure for VegX. Let's ask Nick about this. These are important, fundamental values of many tree plots, and should be accommodated within VegX."
14
"y_position","/simpleUserdefined[name=yPosition]/value","Brad: See comment above for x_position"
15
"dist",,
16
"perp_dist",,
17
"SourceVoucher","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept:[partyWithRole/*ID->/parties/party/organizationName=$/_ignore/inLabel]/voucher/_alt/2","Brad: OMIT. This is the verbatim text, which includes both collectors name and collection number. I would use coll_number, below."
18
"coll_number","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept:[partyWithRole/*ID->/parties/party/organizationName=$/_ignore/inLabel]/voucher/_alt/1","Brad: Incorrect. Map instead as for voucher_string"
19
"collector_code",,"Brad: OMIT"
20
"coll_inits",,
21
"coll_lastname","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=collector]/partyWithRole/*ID->/parties/party/individualName/surName","Brad: Correct for VegBank. This is the collector of a separate specimen which vouchers this tree or species. I worry that vouchers are not properly accommodated in VegX. Again, we need to check with Nick."
22
"coll_firstname","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=collector]/partyWithRole/*ID->/parties/party/individualName/givenName","Brad: See comment above"
23
"DetType","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=collector]/groupType","Brad: A SALVIAS value referring to the relationship between the voucher specimen and the observation. Affect how the identification of the specimen(latin name) is transferred to the observation. 'direct'=voucher specimen was collected from this same tree; they are one and the same individual. 'indirect'=voucher specimen was collected for a different individual, but the original data provider confirmed that this is the same species. 'default'=basically same as 'indirect'. 'uncollected'=no voucher specimen, data provider  asserted that this was the name but was unable to collect. The main different is that with 'direct', 'indirect', and 'default', the scientific name can be updated automatically based on the name attached to the specimen voucher (assuming you have a link to that data, presumably from a herbarium database. Whereas, if det_type='uncollected', the name can never change because there is no specimen."
24
"det_by",,
25
"fam_status",,"Brad: OMIT. This will be determined later by using TNRS."
26
"gen_status",,"Brad: OMIT. This will be determined later by using TNRS."
27
"name_status",,"Brad: OMIT. Except, note that if species_status=3, this indicate that name is a morphospecies and not a standard latin name. Not exactly sure how to use this in BIEN, but could be useful during the name-scrubbing process with TNRS."
28
"SpAuthStatus",,
29
"Family","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=computer]/*s/taxonRelationshipAssertion(/assertion/*ID->/*s/taxonConcept[Rank/@code=fam])/Name",
30
"Genus","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=computer]/*s/taxonRelationshipAssertion(/assertion/*ID->/*s/taxonConcept[Rank/@code=gen])/Name",
31
"GenAuth",,
32
"Species","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=computer]/*s/taxonRelationshipAssertion(/assertion/*ID->/*s/taxonConcept[Rank/@code=sp])/Name",
33
"auth","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=computer]/*s/taxonRelationshipAssertion(/assertion/*ID->/*s/taxonConcept[Rank/@code=auth])/Name","Brad: Incorrect. This is the author of the scientificName. The should be a place for this in the taxonomic name elements of VegB and VegX. Let's discuss."
34
"infra_rank_1","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=computer]/*s/taxonRelationshipAssertion(/assertion/*ID->/*s/taxonConcept[Rank/@code=TaxonomicRankBelowSubspeciesEnum])/Rank",
35
"infra_ep_1","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=computer]/*s/taxonRelationshipAssertion(/assertion/*ID->/*s/taxonConcept[Rank/@code=TaxonomicRankBelowSubspeciesEnum])/Name",
36
"infra_auth_1",,
37
"common_name",,
38
"morphoname",,
39
"species_code",,
40
"Habit","/simpleUserdefined[name=growthForm]/value","Brad: Incorrect for VegBank, correct for VegX. This is growth form (tree, shrub, herb, etc.). It is an observation of a trait."
41
"height_class",,
42
"height_m","/height","Brad: Incorrect for VegBank. This is a measurement applied to a single tree. Check with Bob"
43
"height_m_commercial",,
44
"ht_first_branch_m","/simpleUserdefined[name=htFirstBranchM]/value","Brad: Incorrect for VegBank. This is a measurement applied to a single tree. Check with Bob"
45
"NoInd","/simpleUserdefined[name=count]/value","Brad: Incorrect for VegX. This is a count of number of indiiduals for an *aggregate* observation. For VegBank, I'm not sure. Not exactly the same as stemCount. An individual tree could have 3 stems but would still only count as 1. We need to check with Bob on this."
46
"cover_percent","/simpleUserdefined[name=coverPercent]/value",
47
"intercept_cm","/simpleUserdefined[name=interceptCm]/value","Brad: Incorrect for VegBank This is an aggregate observation. Used in line-intercept methodology only, describes the point along centerline at which an individual intercepts the center line of the plot. Used to determin relative abundance."
48
"cfaff","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=identifier]/*s/taxonRelationshipAssertion(/assertion/*ID->/*s/taxonConcept[Rank/@code=binom])/{fit,Name/_name/middle}","Brad: Not sure where this goes. Indicator of identification uncertainty. 'cf.'=similar to the species listed, 'aff.'=related to the species list, but not the same. You'll need to check with Bob and with Nick where these go in VegX and VegBank."
49
"other_annotations",,
50
"morphocf",,
51
"IsMorpho",,
52
"OrigFamily","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=identifier]/*s/taxonRelationshipAssertion(/assertion/*ID->/*s/taxonConcept[Rank/@code=fam])/Name","Brad: OMIT"
53
"OrigGenus","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=identifier]/*s/taxonRelationshipAssertion(/assertion/*ID->/*s/taxonConcept[Rank/@code=binom])/Name/_name/first",
54
"OrigSpecies","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=identifier]/*s/taxonRelationshipAssertion(/assertion/*ID->/*s/taxonConcept[Rank/@code=binom])/Name/_name/last","Brad: OMIT"
55
"OrigAuth",,
56
"phenology",,
57
"canopy_position","/simpleUserdefined[name=canopyPosition]/value","Brad: Should also be userDefined for VegBank. "
58
"canopy_form","/simpleUserdefined[name=canopyForm]/value","Brad: Should also be userDefined for VegBank. "
59
"liana_infestation","/simpleUserdefined[name=lianaInfestation]/value","Brad: Should also be userDefined for VegBank. "
60
"Notes","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept/note/text",
61
"temp_dbh","/diameterBaseDistance[baseDistance/value=1.37]/diameter",
62
"temp_liandbh",,
63
"tmp_del",,
inputs/SALVIAS/maps/VegX.stems.full.csv
1
"SALVIAS:stems","VegX:/*s/individualOrganismObservation[relatedItem[relationshipType=stemParent]/relatedItemID]","Comments"
2
"stem_id",,
3
"origrecord_id_stems",,
4
"PlotObsID","/relatedItem[relationshipType=stemParent]/relatedItemID->/*s/individualOrganismObservation/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept/voucher",
5
"NoInd","/simpleUserdefined[name=count]/value",
6
"basal_diam","/diameterBaseDistance[baseDistance/value=0]/diameter",
7
"stem_dbh","/diameterBaseDistance[baseDistance[!attributeID]/value=1.37]/diameter",
8
"gentry_dbh","/diameterBaseDistance[baseDistance[*ID/*s/attribute/quantitative/*ID/*s/method(/name=Gentry)]/value=1.37]/diameter",
9
"stem_notes","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept/note/text",
10
"stem_tag1","/*ID->/*s/individualOrganism/identificationLabel",
11
"stem_tag2","/simpleUserdefined[name=tag2]/value",
12
"stem_height_m","/simpleUserdefined[name=stemHeightM]/value",
13
"stem_height_first_branch_m","/simpleUserdefined[name=stemHeightFirstBranchM]/value",
14
"stem_canopy_form","/simpleUserdefined[name=stemCanopyForm]/value",
15
"stem_canopy_position","/simpleUserdefined[name=stemCanopyPosition]/value",
16
"stem_liana_infestation","/simpleUserdefined[name=stemLianaInfestation]/value",
17
"tmp_del",,
inputs/NYBG-CSV/maps/DwC.specimens.full.csv
1
"NYBG","DwC::[@xmlns:dcterms=""http://purl.org/dc/terms/""]/list:[institutionCode=$/_ignore/inLabel]/","Comments"
2
"key",,
3
"DateLastModified","dcterms:modified",
4
"InstitutionCode",,
5
"CollectionCode","collectionCode",
6
"CatalogNumber","catalogNumber",
7
"ScientificName","scientificName",
8
"BasisOfRecord","basisOfRecord",
9
"Kingdom","kingdom",
10
"Phylum","phylum",
11
"Class","class",
12
"Order","order",
13
"Family","family",
14
"Genus","genus",
15
"Species","specificEpithet",
16
"Subspecies","infraspecificEpithet",
17
"ScientificNameAuthor","scientificNameAuthorship",
18
"IdentifiedBy","identifiedBy",
19
"YearIdentified","dateIdentified/_alt/2/_date/year",
20
"MonthIdentified","dateIdentified/_alt/2/_date/month",
21
"DayIdentified","dateIdentified/_alt/2/_date/day",
22
"TypeStatus","typeStatus",
23
"CollectorNumber","recordNumber",
24
"FieldNumber","fieldNumber",
25
"Collector","recordedBy",
26
"YearCollected","eventDate/_alt/2/_date/year",
27
"MonthCollected","eventDate/_alt/2/_date/month",
28
"DayCollected","eventDate/_alt/2/_date/day",
29
"JulianDay","day",
30
"TimeOfDay","eventTime",
31
"ContinentOcean","continent",
32
"Country","country",
33
"StateProvince","stateProvince",
34
"County","county",
35
"Locality","verbatimLocality",
36
"Longitude","verbatimLongitude",
37
"Latitude","verbatimLatitude",
38
"CoordinatePrecision","coordinatePrecision",
39
"BoundingBox","footprintWKT",
40
"MinimumElevation","minimumElevationInMeters",
41
"MaximumElevation","maximumElevationInMeters",
42
"MinimumDepth","minimumDepthInMeters",
43
"MaximumDepth","maximumDepthInMeters",
44
"Sex","sex",
45
"PreparationType","preparations",
46
"IndividualCount","individualCount",
47
"PreviousCatalogNumber","previousIdentifications","?"
48
"RelationshipType","relationshipOfResource",
49
"RelatedCatalogItem","relatedResourceID",
50
"Notes","fieldNotes/_merge/1",
51
"Habitat","habitat/_merge/1",
52
"PlantFungusDescription","fieldNotes/_merge/2/_label[label=""plant fungus""]/value",
53
"Substrate","bien.substrate",
54
"Vegetation","habitat/_merge/2",
55
"UniqueNYInternalRecordNumber","occurrenceID",
inputs/SALVIAS-CSV/maps/VegX.plots.full.csv
1
"SALVIAS","VegX:/*s/plotObservation","Comments"
2
"project","/*ID->/*s/project:[personnel[role=metadataProvider]/organizationName=$/_ignore/inLabel]/title",
3
"PLOT_ID",":[partyWithRole/*ID->/parties/party/organizationName=$/_ignore/inLabel]/simpleUserdefined[name=sourceaccessioncode]/value","Brad: This is artificial internal database ID; a unique identifier within SALVIAS DB to each plot, within the table plotMetadata."
4
"plot_code",":[partyWithRole/*ID->/parties/party/organizationName=$/_ignore/inLabel]/*UniqueIdentifierID->/*s/plot/plotUniqueIdentifier","Brad: plotCode is as-assigned by data provider; guranteed to be unique only within dataset (=project)"
5
"major_geo","/*UniqueIdentifierID->/*s/plot/simpleUserdefined[name=majorGeo]/value",
6
"country","/*UniqueIdentifierID->/*s/plot/country",
7
"pol1","/*UniqueIdentifierID->/*s/plot/state","Brad: No; pol1=stateProvince"
8
"pol2","/*UniqueIdentifierID->/*s/plot/county","Brad: No pol2=countyParish"
9
"locality_description","/*UniqueIdentifierID->/*s/plot/simpleUserdefined[name=localityDescription]/value","Brad: No; this is free text description of locality where plot was situated, same as for DwC. Not a description of vegetation. Most likely='namedPlace.placeDescription' in VB; not sure about VX, again need to ask Nick where locality descriptions live in VX"
10
"lat_decimal","/*UniqueIdentifierID->/*s/plot/geospatial/DecimalLatitude",
11
"long_decimal","/*UniqueIdentifierID->/*s/plot/geospatial/DecimalLongitude",
12
"elev_m","/*UniqueIdentifierID->/*s/plot/geospatial/verbatimElevation","Brad: Mean elevation in meters. This is a constrained decimal value; is there no place for this in VegX other than verbatimElevation? Check with Nick."
13
"elev_max_m","/*UniqueIdentifierID->/*s/plot/geospatial/maximumElevationInMeters",
14
"elev_min_m","/*UniqueIdentifierID->/*s/plot/geospatial/minimumElevationInMeters",
15
"temp_c","/temperature",
16
"precip_mm","/simpleUserdefined[name=precipMm]/value",
17
"slope_aspect","/*UniqueIdentifierID->/*s/plot/slopeAspect",
18
"slope_gradient","/*UniqueIdentifierID->/*s/plot/slopeGradient",
19
"clay_percent","->/*s/abioticObservation[*ID]/simpleUserdefined[name=clayPercent]/value",
20
"silt_percent","->/*s/abioticObservation[*ID]/simpleUserdefined[name=siltPercent]/value",
21
"sand_percent","->/*s/abioticObservation[*ID]/simpleUserdefined[name=sandPercent]/value",
22
"organic_percent","->/*s/abioticObservation[*ID]/simpleUserdefined[name=organicPercent]/value",
23
"pH","->/*s/abioticObservation[*ID]/ph","Brad: For all these soil variables, how do we store information on method, units. Seems like an ontological structure would be more appropriate (measurementName, measurementValue, measurementUnits, measurementMethod). Same as BIEN traits table. Something to discuss."
24
"soil_N","->/*s/abioticObservation[*ID]/nitrogen",
25
"soil_P","->/*s/abioticObservation[*ID]/phosphorus",
26
"soil_C","->/*s/abioticObservation[*ID]/simpleUserdefined[name=carbon]/value",
27
"soil_K","->/*s/abioticObservation[*ID]/pottasium",
28
"soil_Mg","->/*s/abioticObservation[*ID]/magnesium",
29
"soil_Ca","->/*s/abioticObservation[*ID]/simpleUserdefined[name=calcium]/value",
30
"soil_Na","->/*s/abioticObservation[*ID]/simpleUserdefined[name=sodium]/value",
31
"soil_acidity","->/*s/abioticObservation[*ID]/simpleUserdefined[name=acidity]/value",
32
"soil_base","->/*s/abioticObservation[*ID]/simpleUserdefined[name=base]/value",
33
"soil_cation_cap","->/*s/abioticObservation[*ID]/simpleUserdefined[name=cationCap]/value",
34
"soil_conductivity","->/*s/abioticObservation[*ID]/simpleUserdefined[name=conductivity]/value",
35
"soil_texture","->/*s/abioticObservation[*ID]/simpleUserdefined[name=texture]/value",
36
"holdridge_life_zone","->/*s/communityDetermination[*ID]/*s/communityConcept/commonName",
37
"life_zone_code","->/*s/communityDetermination[*ID]/*s/communityConcept/name",
38
"observation_type",,"Brad: SALVIAS internal metadata indicating whether the record represents an individual or aggregate observation. Rather than storing, use to decide where to store in VegX.; Aaron: VegX aggregateOrganismObservation table is missing many fields available in individualOrganismObservation, so we're mapping to individualOrganismObservation regardless of observation type"
39
"plot_methodology","/simpleUserdefined[name=plotMethodology]/value",
40
"plot_area_ha","/*UniqueIdentifierID->/*s/plot/area","Brad: Area in hectares. Is there any way to store units?; Aaron: VegX plot area annotation says ""Total area of the plot in square meters."" so units are fixed"
41
"recensused",,"Brad: This is a 0/1 value, internal to SALVIAS. 1 indicates that a  plot has >1 set of values, from different census events.; Aaron: Different censuses are distinguished in organisms data by different census_no values"
42
"date_start","/obsStartDate/_*/date",
43
"date_finish","/obsEndDate/_*/date",
inputs/SALVIAS-CSV/maps/VegX.organisms.full.csv
1
"SALVIAS","VegX:/*s/individualOrganismObservation","Comments"
2
"OBSERVATION_ID",":[*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept/partyWithRole/*ID->/parties/party/organizationName=$/_ignore/inLabel]/simpleUserdefined[name=sourceaccessioncode]/value","Brad: Neither is correct; this is just an internal ID for table plotObservations. However, it has the important property of uniquely identifying an ""observation"", which is an individual tree, in the case of an individual observation, or a records of a species with an associated count of individuals or measurement of percent cover, in the case of aggregate observations. Not sure where to store this. Main point is that it is not part of the original data, but an auto_increment added later."
3
"PLOT_ID","/*ID->/*s/plotObservation/simpleUserdefined[name=parent]/value->/*s/plotObservation:[partyWithRole/*ID->/parties/party/organizationName=$/_ignore/inLabel]/simpleUserdefined[name=sourceaccessioncode]/value","Brad: Not sure why this is repeated? This field and plotCode, as the same as above."
4
"plot_code","/*ID->/*s/plotObservation/simpleUserdefined[name=parent]/value->/*s/plotObservation/*UniqueIdentifierID->/*s/plot/plotUniqueIdentifier","Brad: Same as plotCode, above"
5
"census_no","/simpleUserdefined[name=censusNo]/value","Brad: Assigned by SALVIAS. 1 for first plot, then 2, 3, etc. I can't recall if we even have repeat censuses in SALVIAS. Probably not."
6
"census_date","/*ID->/*s/plotObservation/obsStartDate/_date/year",
7
"subplot","/*ID->/*s/plotObservation:[partyWithRole/*ID->/parties/party/organizationName=$/_ignore/inLabel]/*UniqueIdentifierID->/*s/plot/plotUniqueIdentifier",
8
"individual_code","/simpleUserdefined[name=individualCode]/value","Brad: Code, if any, used by the data provider to indicate an individual tree. Scope is unknown, although typically this value is unique only within plot, or sometimes only within subplot."
9
"ind_id",,"Brad: OMIT"
10
"tag1","/*ID->/*s/individualOrganism/identificationLabel","Brad: Another type of code, typically a number, used by the original data provider to indicate an individual tree. These are numbers on physical tags attached to the tree. Tag2 Is the same thing, only used if the first tag was lost. Obviously not a good system as it's possible a tree tag could be lost and changed more than once."
11
"tag2","/simpleUserdefined[name=tag2]/value","Brad: See commend for tag1. Your mapping for tag2 looks correct. Probably both values would go here, only nested, with one superceding the other."
12
"x_position","/simpleUserdefined[name=xPosition]/value","Brad: Correct for VegBank. I'm not so sure for VegX. Let's ask Nick about this. These are important, fundamental values of many tree plots, and should be accommodated within VegX."
13
"y_position","/simpleUserdefined[name=yPosition]/value","Brad: See comment above for x_position"
14
"voucher_string","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept:[partyWithRole/*ID->/parties/party/organizationName=$/_ignore/inLabel]/voucher/_alt/2","Brad: OMIT. This is the verbatim text, which includes both collectors name and collection number. I would use coll_number, below."
15
"coll_number","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept:[partyWithRole/*ID->/parties/party/organizationName=$/_ignore/inLabel]/voucher/_alt/1","Brad: Incorrect. Map instead as for voucher_string"
16
"collector_code",,"Brad: OMIT"
17
"coll_lastname","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=collector]/partyWithRole/*ID->/parties/party/individualName/surName","Brad: Correct for VegBank. This is the collector of a separate specimen which vouchers this tree or species. I worry that vouchers are not properly accommodated in VegX. Again, we need to check with Nick."
18
"coll_firstname","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=collector]/partyWithRole/*ID->/parties/party/individualName/givenName","Brad: See comment above"
19
"det_type","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=collector]/groupType","Brad: A SALVIAS value referring to the relationship between the voucher specimen and the observation. Affect how the identification of the specimen(latin name) is transferred to the observation. 'direct'=voucher specimen was collected from this same tree; they are one and the same individual. 'indirect'=voucher specimen was collected for a different individual, but the original data provider confirmed that this is the same species. 'default'=basically same as 'indirect'. 'uncollected'=no voucher specimen, data provider  asserted that this was the name but was unable to collect. The main different is that with 'direct', 'indirect', and 'default', the scientific name can be updated automatically based on the name attached to the specimen voucher (assuming you have a link to that data, presumably from a herbarium database. Whereas, if det_type='uncollected', the name can never change because there is no specimen."
20
"fam_status",,"Brad: OMIT. This will be determined later by using TNRS."
21
"gen_status",,"Brad: OMIT. This will be determined later by using TNRS."
22
"species_status",,"Brad: OMIT. Except, note that if species_status=3, this indicate that name is a morphospecies and not a standard latin name. Not exactly sure how to use this in BIEN, but could be useful during the name-scrubbing process with TNRS."
23
"family","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=computer]/*s/taxonRelationshipAssertion(/assertion/*ID->/*s/taxonConcept[Rank/@code=fam])/Name",
24
"genus","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=computer]/*s/taxonRelationshipAssertion(/assertion/*ID->/*s/taxonConcept[Rank/@code=gen])/Name",
25
"specific_epithet","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=computer]/*s/taxonRelationshipAssertion(/assertion/*ID->/*s/taxonConcept[Rank/@code=sp])/Name",
26
"specific_authority","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=computer]/*s/taxonRelationshipAssertion(/assertion/*ID->/*s/taxonConcept[Rank/@code=auth])/Name","Brad: Incorrect. This is the author of the scientificName. The should be a place for this in the taxonomic name elements of VegB and VegX. Let's discuss."
27
"infra_rank_1","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=computer]/*s/taxonRelationshipAssertion(/assertion/*ID->/*s/taxonConcept[Rank/@code=TaxonomicRankBelowSubspeciesEnum])/Rank",
28
"infra_ep_1","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=computer]/*s/taxonRelationshipAssertion(/assertion/*ID->/*s/taxonConcept[Rank/@code=TaxonomicRankBelowSubspeciesEnum])/Name",
29
"cf_aff","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=identifier]/*s/taxonRelationshipAssertion(/assertion/*ID->/*s/taxonConcept[Rank/@code=binom])/{fit,Name/_name/middle}","Brad: Not sure where this goes. Indicator of identification uncertainty. 'cf.'=similar to the species listed, 'aff.'=related to the species list, but not the same. You'll need to check with Bob and with Nick where these go in VegX and VegBank."
30
"comments",,"Brad: OMIT"
31
"habit","/simpleUserdefined[name=growthForm]/value","Brad: Incorrect for VegBank, correct for VegX. This is growth form (tree, shrub, herb, etc.). It is an observation of a trait."
32
"no_of_individuals","/simpleUserdefined[name=count]/value","Brad: Incorrect for VegX. This is a count of number of indiiduals for an *aggregate* observation. For VegBank, I'm not sure. Not exactly the same as stemCount. An individual tree could have 3 stems but would still only count as 1. We need to check with Bob on this."
33
"cover_percent","/simpleUserdefined[name=coverPercent]/value",
34
"intercept_cm","/simpleUserdefined[name=interceptCm]/value","Brad: Incorrect for VegBank This is an aggregate observation. Used in line-intercept methodology only, describes the point along centerline at which an individual intercepts the center line of the plot. Used to determin relative abundance."
35
"height_m","/height","Brad: Incorrect for VegBank. This is a measurement applied to a single tree. Check with Bob"
36
"ht_first_branch_m","/simpleUserdefined[name=htFirstBranchM]/value","Brad: Incorrect for VegBank. This is a measurement applied to a single tree. Check with Bob"
37
"stem_tag1","/*ID->/*s/individualOrganism/identificationLabel","Brad: Same as tag1 & tag2, but applied to individual stems. I'm still not clear how to distinguish between methods which tag only individuals trees, and those which tag individual stems."
38
"stem_tag2","/*ID->/*s/individualOrganism/identificationLabel","Brad: see above"
39
"stem_dbh","/diameterBaseDistance[baseDistance/value=1.37]/diameter",
40
"basal_diam","/diameterBaseDistance[baseDistance/value=0]/diameter",
41
"stem_height_m","/simpleUserdefined[name=stemHeightM]/value","Brad: Same as for height, but applies to individuals stems, not trees. Rare."
42
"stem_height_first_branch_m","/simpleUserdefined[name=stemHeightFirstBranchM]/value","Brad: Should also be userDefined for VegBank. Same as for ht_first_branch_m, but applies to individuals stems, not trees. Rare."
43
"stem_canopy_form","/simpleUserdefined[name=stemCanopyForm]/value","Brad: Should also be userDefined for VegBank. "
44
"stem_canopy_position","/simpleUserdefined[name=stemCanopyPosition]/value","Brad: Should also be userDefined for VegBank. "
45
"stem_liana_infestation","/simpleUserdefined[name=stemLianaInfestation]/value","Brad: Should also be userDefined for VegBank. "
46
"notes","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept/note/text",
47
"orig_family","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=identifier]/*s/taxonRelationshipAssertion(/assertion/*ID->/*s/taxonConcept[Rank/@code=fam])/Name","Brad: OMIT"
48
"orig_species","/*ID->/*s/individualOrganism/*sID->/*s/taxonNameUsageConcept->/*s/taxonDetermination[*ID,partyWithRole/role=identifier]/*s/taxonRelationshipAssertion(/assertion/*ID->/*s/taxonConcept[Rank/@code=binom])/Name/_name/last","Brad: OMIT"
inputs/input.Makefile
68 68

  
69 69
##### Maps
70 70

  
71
allViaMaps := $(filter-out maps/VegBIEN.%.csv,$(wildcard maps/*.csv))
71
fullViaMap := maps/%.full.csv
72
allViaMaps := $(filter-out maps/VegBIEN.%.csv $(fullViaMap),\
73
$(wildcard maps/*.csv))
72 74
via := $(firstword $(sort $(basename $(basename $(notdir $(allViaMaps))))))
73 75

  
74 76
coreMap := $(mappings)/$(via)-VegBIEN.%.csv
77
selfMap := $(mappings)/$(via).self.%.csv
75 78

  
76 79
viaMaps := $(wildcard $(tablesSort:%=maps/$(via).%.csv))
77
viaMaps += $(filter-out $(viaMaps),$(wildcard maps/$(via).*.csv))
80
viaMaps += $(filter-out $(viaMaps) $(fullViaMap),$(wildcard maps/$(via).*.csv))
78 81

  
79 82
autogenMaps := $(subst $(via).,VegBIEN.,$(viaMaps))
80 83
directMaps := $(autogenMaps) $(filter-out $(autogenMaps),\
81 84
$(wildcard maps/VegBIEN.*.csv))
82 85
tables := $(directMaps:maps/VegBIEN.%.csv=%)
83 86

  
84
maps: $(directMaps) _always ;
85

  
86 87
.PRECIOUS: $(allViaMaps) $(directMaps)
87 88

  
88
all += $(autogenMaps)
89
maps :=
89 90

  
90 91
maps/VegBIEN.%.csv: maps/$(via).%.csv $(coreMap)
91 92
	$(root)/bin/join_union_sort <$+ >$@
92 93
.PRECIOUS: maps/VegBIEN.%.csv $(coreMap)
93 94

  
95
maps += $(autogenMaps)
96

  
97
maps/$(via).%.full.csv: maps/$(via).%.csv $(selfMap)
98
	env ignore=1 $(root)/bin/union <$+|$(root)/bin/sort_map >$@
99
maps/$(via).%.full.csv: maps/$(via).%.csv # fallback if no self map
100
	cp -p $< $@
101
.PRECIOUS: maps/$(via).%.full.csv maps/$(via).%.csv $(selfMap)
102

  
103
maps += $(patsubst maps/%.csv,maps/%.full.csv,$(viaMaps))
104

  
105
maps: $(maps) _always ;
106

  
107
all += $(maps)
108

  
94 109
##### Mapping
95 110

  
96 111
dbFile := $(firstword $(wildcard src/db.*.sql))
......
99 114
+maps = $(filter maps/% $(mappings)/%,$(+_))
100 115
<in = $(firstword $(filter-out $(+maps),$(+_)) $(wildcard $(exts:%=src/*.$*.%)))
101 116
map = $(if $(<in),<$(<in) ,$(if $(mapEnv),env $(mapEnv) ,$(error\
102
No input file src/*.{$(tables)}.{$(exts)} )))$(root)/map $(+maps)
117
No input file src/*.$*.{$(exts)} )))$(root)/map $(+maps)
103 118
map2db = env out_database=vegbien $(map)
104 119

  
105 120
##### Import to VegBIEN
......
184 199

  
185 200
tests :=
186 201

  
187
test/$(via).%.xml: maps/$(via).%.csv _always
202
test/$(via).%.xml: maps/$(via).%.full.csv _always
188 203
	$(test2File)
189 204
tests += test/$(via).%.xml
190 205

  

Also available in: Unified diff