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

occurrence$eventDate <- sprintf('%04d-%02d-%02d', occurrence$CleanedData.year, occurrence$CleanedData.month, occurrence$CleanedData.day)
occurrence <- occurrence %>%
  select(, -c(CleanedData.year, CleanedData.day, CleanedData.month))

# 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 (paste(scientificName, eventDate, CleanedData.lat_inner, CleanedData.lon_inner, CleanedData.count), algo="md5"), sep=":"))

coordinates <- data.frame(lon_inner = occurrence$CleanedData.lon_inner, lat_inner = occurrence$CleanedData.lat_inner, 
                          lon_outer = occurrence$CleanedData.lon_outer, lat_outer = occurrence$CleanedData.lat_outer)

coordinates$wkt_string <- paste("MULTIPOINT ((", coordinates$lon_inner, " ", coordinates$lat_inner, "), (", coordinates$lon_outer, " ", coordinates$lat_outer, "))", sep="")
    
#set uncertainty to ~200 meters for those with just one point
coordinates <- coordinates %>%
  rowwise() %>%
  mutate(centroids = list(calculate_centroid(wkt_string))) %>%
  unnest(centroids)

occurrence %<>% mutate(decimalLongitude = coordinates$decimalLongitude)
occurrence %<>% mutate(decimalLatitude = coordinates$decimalLatitude)
occurrence %<>% mutate(coordinateUncertaintyInMeters = coordinates$coordinateUncertaintyInMeters)

occurrence <- occurrence %>%
  select(, -c(CleanedData.lat_inner, CleanedData.lon_inner, CleanedData.lat_outer, CleanedData.lon_outer))

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

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

occurrence <- occurrence %>%
  rename(individualCount = CleanedData.count)

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

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

locality <- "Coiba National Park"
occurrence %<>% mutate(locality)

creator <- list(eml$creator(
    individualName = eml$individualName(
      givenName = "Peter", 
      surName = "Glynn")
  ), eml$creator(
    individualName = eml$individualName(
      givenName = "Peggy", 
      surName = "Fong")
  )
)


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"
)

#{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 = "IPT will autogenerate this",
      bibliography = list(
        citation = "Glynn, P., & Fong, P. (2014). Fish species counts in 3, 20x40 m transects, Panama, 1980-2010 (EPac Corals projects I-VII). Biological and Chemical Oceanography Data Management Office.")
    )
  )
)

citationdoi <- "https://doi.org/10.1575/1912/bco-dmo.516234.1"

#Coverage
coverage <- eml$coverage(
  geographicCoverage = eml$geographicCoverage(
    geographicDescription = "Coiba National Park",
    boundingCoordinates = eml$boundingCoordinates(
      westBoundingCoordinate = min(occurrence$decimalLongitude),
      eastBoundingCoordinate = max(occurrence$decimalLongitude),
      northBoundingCoordinate = max(occurrence$decimalLatitude),
      southBoundingCoordinate = min(occurrence$decimalLatitude))
    ),
  taxonomicCoverage = eml$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$beginDate(
#        calendarDate = "2019-05-01"
#      ),
#      endDate = eml$endDate(
#        calendarDate = "2016-05-06"
#      )
#    )
   )
)

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"
)

#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)

#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 = ""))

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)
}