Bundling Gushin and Fall 2012 to a DwC Archive

This is an R Markdown Notebook for converting the species checklist found in the following reference to DarwinCore format for upload into OBIS as part of UNESCO’s eDNA Expeditions project:

Gushchin, A.V., Fall, K.O.M. Ichthyofauna of littoral of the gulf Arguin, Mauritania. J. Ichthyol. 52, 160–171 (2012).

Setup

Call the necessary libraries and variables. Suppresses loading messages.

library(magrittr)                       # To use %<>% pipes
suppressMessages(library(janitor))      # To clean input data
suppressMessages(library(dplyr))        # To clean input data
library(stringr)                        # To clean input data
suppressMessages(library(rgnparser))    # To clean species names
suppressMessages(library(taxize))       # To get WoRMS IDs
library(worrms)                         # To get WoRMS IDs
library(digest)                         # To generate hashes
suppressMessages(library(obistools))    # To generate centroid lat/long and uncertainty
suppressMessages(library(sf))           # To generate wkt polygon
suppressMessages(library(EML))          # To create eml.xml file
library(xml2)                           # To create the meta.xml file
suppressMessages(library(zip))          # To zip DwC file

Input Parameters and Paths

Note* - the table in this PDF was originally rotated 90 degrees, I pulled these out and rotated them into its own PDF.

path_to_project_root <- "../../.."
site_dir_name <- "banc_darguin_national_park"
dataset_dir_name <- "Gushin_and_Fall_2012"
original_pdf <- "S0032945212010055-4-6_rotated.pdf"
short_name <- "banc-darguin-gushin-and-fall-2012"

Parsing PDF table to CSV

The data for this reference is formatted as a text-based table inside a PDF across multiple sheets. First, we use pdf_to_table to parse out the table to a CSV.

#conda environment
condaenv <- "mwhs-data-mobilization"

# Path to the Python script
script <- paste(path_to_project_root, "scripts_data/pdf_to_tables/pdf_to_table.py", sep="/")

# Input PDF file path
input_pdf <- paste(path_to_project_root, "datasets", site_dir_name, dataset_dir_name, "raw", original_pdf, sep="/")

# Output directory for OCR/table files
output_dir <- paste(path_to_project_root, "datasets", site_dir_name, dataset_dir_name, "processed", sep="/")

# Define page numbers and table areas (see documentation)
page_args <- c(
  "-a 71.775,113.355,540.045,243.045 -p 1",
  "-a 71.775,113.355,540.045,243.045 -p 2",
  "-a 63.855,113.355,490.545,243.045 -p 3"
)

# Define run parameters (see documentation)
run_parameters <- "-s -c"

# Combine page arguments and execute
page_args_combined <- paste(page_args, collapse = " ")
command <- paste("conda run -n", condaenv, "python", script, "-i", input_pdf, run_parameters, page_args_combined, "-o", output_dir)
system(command, intern=TRUE)

##  [1] ""                                                                                                                                                  
##  [2] "Script Execution Summary"                                                                                                                          
##  [3] "Date and Time: 2023-09-12 00:02:30"                                                                                                                
##  [4] "------------------------------"                                                                                                                    
##  [5] ""                                                                                                                                                  
##  [6] "PDF input: ../../../datasets/banc_darguin_national_park/Gushin_and_Fall_2012/raw/S0032945212010055-4-6_rotated.pdf"                                
##  [7] "Perform Table Parsing: TRUE"                                                                                                                       
##  [8] "Selected Areas:"                                                                                                                                   
##  [9] "  Area 1: [71.775, 113.355, 540.045, 243.045]"                                                                                                     
## [10] "  Area 2: [71.775, 113.355, 540.045, 243.045]"                                                                                                     
## [11] "  Area 3: [63.855, 113.355, 490.545, 243.045]"                                                                                                     
## [12] "Pages: 1, 2, 3"                                                                                                                                    
## [13] "Concatenate: True"                                                                                                                                 
## [14] "Concatenate across headers: False"                                                                                                                 
## [15] "Stream Extraction: True"                                                                                                                           
## [16] "Lattice Extraction: False"                                                                                                                         
## [17] ""                                                                                                                                                  
## [18] "Parsing Tables"                                                                                                                                    
## [19] "------------------------------"                                                                                                                    
## [20] ""                                                                                                                                                  
## [21] ""                                                                                                                                                  
## [22] "Saving to CSV"                                                                                                                                     
## [23] "CSV file: ../../../datasets/banc_darguin_national_park/Gushin_and_Fall_2012/processed/S0032945212010055-4-6_rotated_tables_parsed_concatenated.csv"
## [24] "------------------------------"                                                                                                                    
## [25] ""                                                                                                                                                  
## [26] ""                                                                                                                                                  
## [27] "Run Details: ../../../datasets/banc_darguin_national_park/Gushin_and_Fall_2012/processed/S0032945212010055-4-6_rotated_parameters.txt"             
## [28] "Finished"                                                                                                                                          
## [29] ""

Read source data

Now we’ll read in the csv table outputted from the previous step

processed_csv <- "S0032945212010055-4-6_rotated_tables_parsed_concatenated.csv"

input_data <- read.csv(paste(path_to_project_root, "datasets", site_dir_name, dataset_dir_name, "processed", processed_csv, sep="/"))

#to preview pretty table
knitr::kable(head(input_data))

Species
Albula vulpes
Alectis alexandrinus
Argyrosomus regius
Arius heudeloti
A. parkii
Atherina lopeziana

Preprocessing

Here we tidy the data up, since OCR and table parsing errors are common and only take the list of species, since this is a checklist.

Tidy Data

input_data %<>%
  remove_empty(c("rows", "cols")) %>%       # Remove empty rows and columns
  clean_names()                             # Have sensible (lowercase) column names

cleaned_data <- input_data

#For elements with an abbreviated genus name, look at the precious element and grab the genus
for (i in 2:nrow(cleaned_data)) {
  if (grepl("[A-Za-z][.,]", cleaned_data$species[i])) {
    previous_species <- strsplit(cleaned_data$species[i - 1], " ")[[1]][1]
    cleaned_data$species[i] <- sub("^[A-Za-z][.,]", paste0(previous_species, " "), cleaned_data$species[i])
  }
}

#to preview pretty table
knitr::kable(head(cleaned_data))

species
Albula vulpes
Alectis alexandrinus
Argyrosomus regius
Arius heudeloti
Arius parkii
Atherina lopeziana

Get WoRMS IDs

Auto matching

First we will try to do this automatically by first cleaning the species names using gnparser and then using the taxise library to call the WoRMS database.

#Parse author names out
parsed_names <- rgnparser::gn_parse(cleaned_data[,])

#Function to get WoRMS IDs. Search for accepted names first and if not found, search for unaccepted. If still not found, use the worrms package to search.
get_worms_id_from_element <- function(element) {
  worms_id <- get_wormsid(element$canonical$full, searchtype="scientific", fuzzy=TRUE, messages = FALSE, accepted = TRUE)
  if (attr(worms_id, "match") == "not found") {
    worms_id <- get_wormsid(element$canonical$full, searchtype="scientific", messages = FALSE, fuzzy=TRUE)
    if (attr(worms_id, "match") == "not found") {
      worms_id <- NA
    }
  }
  return(worms_id)
}

#Call the function
worms_ids <- lapply(parsed_names, function(element) {
  if (element$parsed) {
    return(get_worms_id_from_element(element))
  } else {
    return(NA)
  }
})

##

##       id             target       authority     status
## 1 282977 Tilapia guineensis (Bleeker, 1863) unaccepted
## 2 367733 Tilapia guineensis (Günther, 1862) unaccepted

## 
## More than one WORMS ID found for taxon 'Tilapia guineensis'!
## 
##                   Enter rownumber of taxon (other inputs will return 'NA'):

#combine original names, parsed data and WoRMS ID into one data frame
combined_dataframe <- data.frame()

for (i in 1:nrow(cleaned_data)) {
  cleaned_value <- cleaned_data[i,]
  canonical_value <- parsed_names[[i]]$canonical$full
  worms_id_value <- worms_ids[[i]][1]
  if (is.null(canonical_value)){
    canonical_value <- NA
  }
  temp_row <- data.frame(CleanedData = cleaned_value, CanonicalFull = canonical_value, WormsIDs = worms_id_value)
  combined_dataframe <- rbind(combined_dataframe, temp_row)
}

knitr::kable(head(combined_dataframe))

CleanedData	CanonicalFull	WormsIDs
Albula vulpes	Albula vulpes	212256
Alectis alexandrinus	Alectis alexandrinus	126799
Argyrosomus regius	Argyrosomus regius	127007
Arius heudeloti	Arius heudeloti	400141
Arius parkii	Arius parkii	275583
Atherina lopeziana	Atherina lopeziana	272029

Human Verification

Sometimes there are misspellings in the original text or incorrect OCR that can be searched for and fixed by hand. To do this, view the combined dataframe, search for unmatched species in WoRMS and add the ID, and remove rows that were not autoremoved in the earlier cleaning steps

combined_dataframe[18,2:3] = c("Citharichthys stampflii", 275695)
combined_dataframe[69,2:3] = c("Smaris macrophthalmus", 321559)
combined_dataframe[72,2:3] = c("Sparisoma rubripinne", 159301)

#I think this species doesn't exist - typo
combined_dataframe[77,2:3] = c("Spicara spicara", NA)

combined_dataframe[84,2:3] = c("Tilapia guineensis", 367733)

Darwin Core mapping

Required Terms

OBIS currently has eight required DwC terms: scientificName, scientificNameID, occurrenceID, eventDate, decimalLongitude, decimalLatitude, occurrenceStatus, basisOfRecord.

scientificName/scientificNameID

Create a dataframe with unique taxa only (though this should already be unique). This will be our primary DarwinCore data frame.

#rename and restructure WoRMSIDs to OBIS requirements
occurrence <- combined_dataframe %>%
  distinct(CanonicalFull, WormsIDs) %>%
  rename(scientificName = CanonicalFull) %>%
  rename(scientificNameID = WormsIDs) %>%
  mutate(scientificNameID = ifelse(!is.na(scientificNameID), paste("urn:lsid:marinespecies.org:taxname:", scientificNameID, sep = ""), NA))

occurrenceID

OccurrenceID is an identifier for the occurrence record and should be persistent and globally unique. It is a combination of dataset-shortname:occurrence: and a hash based on the scientific name.

# Vectorize the digest function (The digest() function isn't vectorized. So if you pass in a vector, you get one value for the whole vector rather than a digest for each element of the vector):
vdigest <- Vectorize(digest)

# Generate taxonID:
occurrence %<>% mutate(occurrenceID = paste(short_name, "occurrence", vdigest (scientificName, algo="md5"), sep=":"))

eventDate

This is NULL since this is technically a checklist and we do not know the collection date.

eventDate <- ""
occurrence %<>% mutate(eventDate)

decimalLongitude/decimalLatitude

Use obistools::calculate_centroid to calculate a centroid and radius for WKT strings. This is useful for populating decimalLongitude, decimalLatitude and coordinateUncertaintyInMeters. The WKT strings are from https://github.com/iobis/mwhs-shapes.

if (!file.exists(paste(path_to_project_root, "scripts_data/marine_world_heritage.gpkg", sep="/"))) {
  download.file("https://github.com/iobis/mwhs-shapes/blob/master/output/marine_world_heritage.gpkg?raw=true", paste(path_to_project_root, "scripts_data/marine_world_heritage.gpkg", sep="/"))
}

shapes <- st_read(paste(path_to_project_root, "scripts_data/marine_world_heritage.gpkg", sep="/"))

## Reading layer `marine_world_heritage' from data source 
##   `/mnt/c/Users/Chandra Earl/Desktop/Labs/UNESCO/mwhs-data-mobilization/scripts_data/marine_world_heritage.gpkg' 
##   using driver `GPKG'
## Simple feature collection with 60 features and 4 fields
## Geometry type: MULTIPOLYGON
## Dimension:     XY
## Bounding box:  xmin: -180 ymin: -55.32282 xmax: 180 ymax: 71.81381
## Geodetic CRS:  4326

#For some sites, the GeoPackage has core as well as buffer areas. Merge the geometries by site.
shapes_processed <- shapes %>%
  group_by(name) %>%
  summarize()

#Banc d'Arguin National Park
ind_shape <- shapes_processed$geom[which(shapes_processed$name == "Banc d'Arguin National Park")]


#convert shape to WKT
wkt <- st_as_text(ind_shape, digits = 6)

localities <- calculate_centroid(wkt)

occurrence %<>% mutate(decimalLatitude = localities$decimalLatitude)
occurrence %<>% mutate(decimalLongitude = localities$decimalLongitude)

occurrenceStatus

occurrenceStatus <- "present"
occurrence %<>% mutate(occurrenceStatus)

basisOfRecord

basisOfRecord <- "HumanObservation"
occurrence %<>% mutate(basisOfRecord)

Extra Terms

footprintWKT

occurrence %<>% mutate(footprintWKT = wkt)

coordinateUncertaintyInMeters

occurrence %<>% mutate(coordinateUncertaintyInMeters = localities$coordinateUncertaintyInMeters)

geodeticDatum

geodeticDatum <- "WGS84"
occurrence %<>% mutate(geodeticDatum)

country

country <- "Mauritania"
occurrence %<>% mutate(country)

locality

locality <- "Banc d'Arguin"
occurrence %<>% mutate(locality)

Post-processing

Check data

Use the check_fields command from obistools to check if all OBIS required fields are present in an occurrence table and if any values are missing.

#Reorganize columns
occurrence = occurrence %>% select(occurrenceID, scientificName, scientificNameID, eventDate, country, locality, decimalLatitude, decimalLongitude, coordinateUncertaintyInMeters, footprintWKT, geodeticDatum, occurrenceStatus, basisOfRecord)

#Check fields
check_fields(occurrence)

## Warning: `data_frame()` was deprecated in tibble 1.1.0.
## ℹ Please use `tibble()` instead.
## ℹ The deprecated feature was likely used in the obistools package.
##   Please report the issue to the authors.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

## # A tibble: 92 × 4
##    level field       row message                                 
##    <chr> <chr>     <int> <chr>                                   
##  1 error eventDate     1 Empty value for required field eventDate
##  2 error eventDate     2 Empty value for required field eventDate
##  3 error eventDate     3 Empty value for required field eventDate
##  4 error eventDate     4 Empty value for required field eventDate
##  5 error eventDate     5 Empty value for required field eventDate
##  6 error eventDate     6 Empty value for required field eventDate
##  7 error eventDate     7 Empty value for required field eventDate
##  8 error eventDate     8 Empty value for required field eventDate
##  9 error eventDate     9 Empty value for required field eventDate
## 10 error eventDate    10 Empty value for required field eventDate
## # ℹ 82 more rows

Create the EML file

This is a file which contains the dataset’s metadata and is required in a DarwinCore-Archive.

emld::eml_version("eml-2.1.1")

## [1] "eml-2.1.1"

#Title
title <- "Ichthyofauna of Littoral of the Gulf Arguin, Mauritania: Fishes Checklist"

#AlternateIdentifier
alternateIdentifier <- paste("https://ipt.obis.org/secretariat/resource?r=", short_name, sep="")

#Abstract
abstract <- eml$abstract(
  para = "According to the materials of 2000–2004, in littoral of the gulf Arguin (at the coast of Northern Africa) dwell 91 fish species. Fish young, accumulating 97.9–99.7% of ichthyofauna, endure main cycle of development in the zone of littoral, use it for pasture and as a shelter. Five types of littoral are distinguished in the gulf. Ichthyofauna composition of different littoral types has significant similarity, but differs essentially from ichthyofauna of open ocean littoral. The role of the gulf Arguin, taking into consideration its dimensions, is unique in reproduction, biodiversity maintenance and existence of numerous fish species (including fishery species) of Northern Africa."
)

People

Here we add the people involved in the project:

The creator is the person or organization responsible for creating the resource itself.

The contact is the person or institution to contact with questions about the use, interpretation of a data set.

The metadataProvider is the person responsible for providing the metadata documentation for the resource.

The associatedParty (in this case the Data Curator) is the person who mobilized the data from the original resource.

creator <- list(eml$creator(
    individualName = eml$individualName(
      givenName = "A. V.", 
      surName = "Gushchina"),
    organizationName = "P.P. Shirshov Institute of Oceanology of Russian Academy of Sciences"
), eml$creator(
    individualName = eml$individualName(
      givenName = "Khallagi Ould Mokhamad", 
      surName = "Fall"),
    organizationName = "Mauritanian Institute for Oceanographic Research and Fisheries"
  )
)

contact <- eml$creator(
  individualName = eml$individualName(
    givenName = "OBIS", 
    surName = "Secretariat"),
  electronicMailAddress = "helpdesk@obis.org",
  organizationName = "OBIS",
  positionName = "Secretariat"
)

metadataProvider <- eml$metadataProvider(
  individualName = eml$individualName(
    givenName = "Chandra", 
    surName = "Earl"),
  electronicMailAddress = "c.earl@unesco.org",
  organizationName = "UNESCO",
  positionName = "eDNA Scientific Officer"
)

associatedParty <- eml$associatedParty(
  role = "processor",
  individualName = eml$individualName(
    givenName = "Chandra", 
    surName = "Earl"),
  electronicMailAddress = "c.earl@unesco.org",
  organizationName = "UNESCO",
  positionName = "eDNA Scientific Officer"
)

Additional Metadata

Here we add the additionalMetadata element, which is required for a GBIF-type EML file and contains information such as the citation of the dataset, the citation of the original resource and the creation timestamp of the EML.

#{dataset.authors} ({dataset.pubDate}) {dataset.title}. [Version {dataset.version}]. {organization.title}. {dataset.type} Dataset {dataset.doi}, {dataset.url}

additionalMetadata <- eml$additionalMetadata(
  metadata = list(
    gbif = list(
      dateStamp = paste0(format(Sys.time(), "%Y-%m-%dT%H:%M:%OS3"), paste0(substr(format(Sys.time(), "%z"), 1, 3), ":", paste0(substr(format(Sys.time(), "%z"), 4, 5)))),
      hierarchyLevel = "dataset",
      citation = "Gushchina A V, Fall K O M, Earl C (2023). Ichthyofauna of Littoral of the Gulf Arguin, Mauritania: Fishes Checklist. Version 1.0. OBIS Secretariat. Occurrence dataset. https://ipt.obis.org/secretariat/resource?r=banc-darguin-gushin-and-fall-2012&v=1.0",
      bibliography = list(
        citation = "Gushchin, A.V., Fall, K.O.M. Ichthyofauna of littoral of the gulf Arguin, Mauritania. J. Ichthyol. 52, 160–171 (2012).")
    )
  )
)

citationdoi <- "https://doi.org/10.1134/S0032945212010055"

Coverage

Here we describe the dataset’s geographic, taxonomic and temporal coverage.

#Coverage
coverage <- eml$coverage(
  geographicCoverage = eml$geographicCoverage(
    geographicDescription = "Banc d'Arguin",
    boundingCoordinates = eml$boundingCoordinates(
      westBoundingCoordinate = st_bbox(ind_shape)$xmax,
      eastBoundingCoordinate = st_bbox(ind_shape)$xmin,
      northBoundingCoordinate = st_bbox(ind_shape)$ymax,
      southBoundingCoordinate = st_bbox(ind_shape)$ymin)
    ),
  taxonomicCoverage = eml$taxonomicCoverage(
    generalTaxonomicCoverage = "Fishes",
    taxonomicClassification = list(
      eml$taxonomicClassification(
        taxonRankName = "Superclass",
        taxonRankValue = "Agnatha"),
      eml$taxonomicClassification(
        taxonRankName = "unranked",
        taxonRankValue = "Chondrichthyes"),
      eml$taxonomicClassification(
        taxonRankName = "unranked",
        taxonRankValue = "Osteichthyes")
      )
    
  ),
  temporalCoverage = eml$temporalCoverage(
    rangeOfDates = eml$rangeOfDates(
      beginDate = eml$beginDate(
        calendarDate = "2000-01-01"
      ),
      endDate = eml$endDate(
        calendarDate = "2004-12-31"
      )
    )
   )
)

Extra MetaData

These fields are not required, though they make the metadata more complete.

methods <- eml$methods(
  methodStep = eml$methodStep(
    description = eml$description(
      para = paste("See Github <a href=\"https://github.com/iobis/mwhs-data-mobilization\">Project</a> and <a href=\"https://iobis.github.io/mwhs-data-mobilization/notebooks/", site_dir_name, "/", dataset_dir_name, "\"> R Notebook</a> for dataset construction methods", sep="")
    )
  )
)

#Other Data
pubDate <- "2023-10-15"

#language of original document
language <- "eng"

keywordSet <- eml$keywordSet(
  keyword = "Occurrence",
  keywordThesaurus = "GBIF Dataset Type Vocabulary: http://rs.gbif.org/vocabulary/gbif/dataset_type_2015-07-10.xml"
)

maintenance <- eml$maintenance(
  description = eml$description(
    para = ""),
  maintenanceUpdateFrequency = "notPlanned"
)

#Universal CC
intellectualRights <- eml$intellectualRights(
  para = "To the extent possible under law, the publisher has waived all rights to these data and has dedicated them to the <ulink url=\"http://creativecommons.org/publicdomain/zero/1.0/legalcode\"><citetitle>Public Domain (CC0 1.0)</citetitle></ulink>. Users may copy, modify, distribute and use the work, including for commercial purposes, without restriction."
)

purpose <- eml$purpose(
  para = "These data were made accessible through UNESCO's eDNA Expeditions project to mobilize available marine species and occurrence datasets from World Heritage Sites."
)

additionalInfo <- eml$additionalInfo(
  para = "marine, harvested by iOBIS"
)

Create and Validate EML

#Put it all together
my_eml <- eml$eml(
           packageId = paste("https://ipt.obis.org/secretariat/resource?id=", short_name, "/v1.0", sep = ""),  
           system = "http://gbif.org",
           scope = "system",
           dataset = eml$dataset(
               alternateIdentifier = alternateIdentifier,
               title = title,
               creator = creator,
               metadataProvider = metadataProvider,
               associatedParty = associatedParty,
               pubDate = pubDate,
               coverage = coverage,
               language = language,
               abstract = abstract,
               keywordSet = keywordSet,
               contact = contact,
               methods = methods,
               intellectualRights = intellectualRights,
               purpose = purpose,
               maintenance = maintenance,
               additionalInfo = additionalInfo),
           additionalMetadata = additionalMetadata
)

eml_validate(my_eml)

## [1] TRUE
## attr(,"errors")
## character(0)

Create meta.xml file

This is a file which describes the archive and data file structure and is required in a DarwinCore-Archive. It is based on the template file “meta_occurrence_checklist_template.xml”

meta_template <- paste(path_to_project_root, "scripts_data/meta_occurrence_checklist_template.xml", sep="/")
meta <- read_xml(meta_template)

fields <- xml_find_all(meta, "//d1:field")

for (field in fields) {
  term <- xml_attr(field, "term")
  if (term == "http://rs.tdwg.org/dwc/terms/eventDate") {
    xml_set_attr(field, "default", eventDate)
  } else if (term == "http://rs.tdwg.org/dwc/terms/country") {
    xml_set_attr(field, "default", country)
  } else if (term == "http://rs.tdwg.org/dwc/terms/locality") {
    xml_set_attr(field, "default", locality)
  } else if (term == "http://rs.tdwg.org/dwc/terms/decimalLatitude") {
    xml_set_attr(field, "default", localities$decimalLatitude)
  } else if (term == "http://rs.tdwg.org/dwc/terms/decimalLongitude") {
    xml_set_attr(field, "default", localities$decimalLongitude)
  } else if (term == "http://rs.tdwg.org/dwc/terms/coordinateUncertaintyInMeters") {
    xml_set_attr(field, "default", localities$coordinateUncertaintyInMeters)
  } else if (term == "http://rs.tdwg.org/dwc/terms/footprintWKT") {
    xml_set_attr(field, "default", wkt)
  } else if (term == "http://rs.tdwg.org/dwc/terms/geodeticDatum") {
    xml_set_attr(field, "default", geodeticDatum)
  } else if (term == "http://rs.tdwg.org/dwc/terms/occurrenceStatus") {
    xml_set_attr(field, "default", occurrenceStatus)
  } else if (term == "http://rs.tdwg.org/dwc/terms/basisOfRecord") {
    xml_set_attr(field, "default", basisOfRecord)
  }
}

Save outputs

dwc_output_dir <- paste(path_to_project_root, "output", site_dir_name, dataset_dir_name, sep="/")

write.csv(occurrence, paste(dwc_output_dir, "/occurrence.csv", sep = ""), na = "", row.names=FALSE)
write_xml(meta, file = paste(dwc_output_dir, "/meta.xml", sep = ""))
write_eml(my_eml, paste(dwc_output_dir, "/eml.xml", sep = ""))

Edit EML

We have to further edit the eml file to conform to GBIF-specific requirements that cannot be included in the original EML construction. This includes changing the schemaLocation and rearranging the GBIF element, since the construction automatically arranges the children nodes to alphabetical order.

#edit the schemaLocation and rearrange gbif node for gbif specific eml file
eml_content <- read_xml(paste(dwc_output_dir, "/eml.xml", sep = ""))

#change schemaLocation attributes for GBIF
root_node <- xml_root(eml_content)
xml_set_attr(root_node, "xsi:schemaLocation", "https://eml.ecoinformatics.org/eml-2.1.1 http://rs.gbif.org/schema/eml-gbif-profile/1.2/eml.xsd")
xml_set_attr(root_node, "xmlns:dc", "http://purl.org/dc/terms/")
xml_set_attr(root_node, "xmlns:stmml", NULL)
xml_set_attr(root_node, "xml:lang", "eng")


#rearrange children nodes under the GBIF element
hierarchyLevel <- eml_content %>% xml_find_all(".//hierarchyLevel")
dateStamp <- eml_content %>% xml_find_all(".//dateStamp")
citation <- eml_content %>% xml_find_all("./additionalMetadata/metadata/gbif/citation")
bibcitation <- eml_content %>% xml_find_all("./additionalMetadata/metadata/gbif/bibliography/citation")
xml_set_attr(bibcitation, "identifier", citationdoi)

eml_content %>% xml_find_all(".//hierarchyLevel") %>% xml_remove()
eml_content %>% xml_find_all(".//dateStamp") %>% xml_remove()
eml_content %>% xml_find_all("./additionalMetadata/metadata/gbif/citation") %>% xml_remove()
eml_content %>% xml_find_all(".//gbif") %>% xml_add_child(citation, .where=0)
eml_content %>% xml_find_all(".//gbif") %>% xml_add_child(hierarchyLevel, .where=0)
eml_content %>% xml_find_all(".//gbif") %>% xml_add_child(dateStamp, .where=0)

write_xml(eml_content, paste(dwc_output_dir, "/eml.xml", sep = ""))

Zip files to DwC-A

output_zip <- paste(dwc_output_dir, "DwC-A.zip", sep="/")

if (file.exists(output_zip)) {
  unlink(output_zip)
}

file_paths <- list.files(dwc_output_dir, full.names = TRUE)
zip(zipfile = output_zip, files = file_paths, mode = "cherry-pick")

if (file.exists(output_zip)) {
  unlink(file_paths)
}