## fdex database pull ##
# Request only what you need, transport only what is necessary, and cache what you can.
# fdex_db_pull.R v1.0
# 02 April 2026

rm(list=ls())

library(data.table)
library(jsonlite)
library(RCurl)

#update_date <- Sys.Date()
t <- Sys.time()
theDate <- strftime(t,"%d_%b_%Y")

alphabet_vector <- c("a", "b", "c", "d", "e", "f", "g", "h", "i", "j", "k", "l", "m", "n", "o", 
                     "p", "q", "r", "s", "t", "u", "v", "w", "x", "y", "z")

###################################
############ FUNCTIONS ############
###################################

fd_api_base_url <- "https://fdex.org/services/api/query.php?qText="

get_fd_record <- function(theEndpoint, queryText){
  url <- paste0(fd_api_base_url, queryText, "&qField=", theEndpoint)
  tryCatch({
    response <- getURL(url)
    response <- fromJSON(response)
  }, error = function(e) NULL)
}

###################################
########### CODE BLOCK ############
###################################

the_colnames <- c("taxon", "authors", "mbNumber", "otherID", "rank", "rankCode", "taxonomicStatus", "currentTaxon",
                        "currentMbNumber", "currentOtherID", "currentStatus", "parentTaxon", "parentMbNumber", "parentOtherID", 
                        "recordSource", "taxonomicAgreement")

fdex_data_frame <- data.frame("taxon", "authors", "mbNumber", "otherID", "rank", "rankCode", "taxonomicStatus", "currentTaxon",
  "currentMbNumber", "currentOtherID", "currentStatus", "parentTaxon", "parentMbNumber", "parentOtherID", 
  "recordSource", "taxonomicAgreement")

colnames(fdex_data_frame) <- the_colnames

fdex_data_frame <- fdex_data_frame[-1,]

for(i in 1:length(alphabet_vector)){
  for(j in 1:length(alphabet_vector)){
    first_letter <- toupper(alphabet_vector[i])
    second_letter <- alphabet_vector[j]
    combined_letters <- paste0(first_letter, second_letter)
    print(paste0("Processing genera starting : '", combined_letters, "' for i = ", i, " and j = ", j))
    fdex_data <- get_fd_record("taxon", paste0(first_letter, second_letter, "%25"))
    fdex_data_frame <- rbind(fdex_data_frame, as.data.frame(fdex_data))
  }
}

fdex_data_frame <- subset(fdex_data_frame, fdex_data_frame$recordSource == "Index Fungorum")
#fdex_data_frame <- subset(fdex_data_frame, fdex_data_frame$recordSource == "MycoBank")

dt <- setDT(fdex_data_frame)

fwrite(dt, paste0(theDate, "_fdex_db.csv"))