# Method1: Generate a general citation for publication purposes:
usethis::edit_r_environ()
### this code opens Renviron file- to generate citation we have to add credentials to access gbif with userid specific query.
GBIF_USER <- "myuser"
GBIF_PWD <- "mypwd"
GBIF_EMAIL <- "myemail@gmail.com"
d1 <- occ_download_meta(occ_download(pred("taxonKey", taxonkey)))
gbif_citation_general <- gbif_citation(d1)[1]
DOI <- d1[["doi"]]
DOI
gbif_citation_general
### A DOI will save in gbif_citation_general variable which can be use to add in the publication.
### for example: "GBIF Occurrence Download https://www.gbif.org/occurrence/download/0035415-250802193616735 Accessed from R via rgbif (https://github.com/ropensci/rgbif) on 2025-08-10"
# Method2: Generate derived citation:
### This citation is generated specifically for the cleaned/significantly reduced datasets. This method can generate one DOI for the subset dataset as well as provide detailed DOIs for each dataset: https://docs.ropensci.org/rgbif/reference/derived_dataset.html
### Other methods include: function rgbif::dataset_get() or occCite::occCitation() to extract DOI for each data based on datasetKey values.
### In this case as our requirement is merging several databases, we have to create a seperate dataframe call "datasetkey_lookup" with datasetKey and catalogNumber. This lookup file can be used later to merge with cleaned records.
### Code for datasetKey_lookup file:
datasetkey_lookup <- gbif.occ %>%
select(datasetKey, catalogNumber)
### run all the steps to get final file called: cleaned_data
cleaned_data_w_datasetKey <- cleaned_data %>%
left_join(
datasetkey_lookup %>%
filter(catalogNumber %in% cleaned_data$cleaned_catalog) %>%
select(catalogNumber, datasetKey),
by = c("cleaned_catalog" = "catalogNumber")
)
lookup_first <- datasetkey_lookup %>%
arrange(catalogNumber, datasetKey) %>%
distinct(catalogNumber, .keep_all = TRUE) %>%
select(catalogNumber, datasetKey)
cleaned_data_w_datasetKey <- cleaned_data %>%
left_join(lookup_first, by = c("cleaned_catalog" = "catalogNumber"))
write.csv(cleaned_data_w_datasetKey %>% count(datasetKey), "xxx.csv")
## clean_data_w_datasetKey will have datasetKey for each record if there is any.
## this csv file can be used to get derived cite from gbif portal: https://www.gbif.org/derived-dataset
# or through rgbif and occCite
# use article - to get the derived citation using rgbif: https://docs.ropensci.org/rgbif/reference/derived_dataset.html
# Another method using function rgbif::dataset_get() or occCite::occCitation() to extract DOI for each data based on datasetKey values.
