country-regex

C1 <- rec$C1
RP <- rec$RP
PY <- rec$PY
WC <- rec$WC
UT <- rec$UT

nr.recs <- length(PY)

C1s <- C1

for (rn in 1:nr.recs)
  {
  C1s = gsub("\\[.*?\\] ", "", C1s) #remove author assignment
  C1s = toupper(C1s) #capitals
  C1s = strsplit(C1s, ";") #separate addresses
  numbers = sapply(C1s, length) #number of adresses?
  C1s = unlist(C1s)
  C1s = gsub(",", ", ", C1s) #add spaces
  #replace 'HUMBOLDT...GERMANY' with 'HUMBOLDT'
  C1s = gsub("(.*)(HUMBOLDT)(.*)(GERMANY$)", "\\2", C1s)
  #'UNITED KINGDOM'
  C1s = gsub("ENGLAND|SCOTLAND|WALES|NORTH IRELAND", "UNITED KINGDOM", C1s)
  #'USA'
  #state and zip
  C1s = gsub(" [A-Z]{2} [0-9]{5}", " USA", C1s)
  #state only
  C1s = gsub(", [A-Z]{2}$", ", USA", C1s)
  #no comma before USA
  C1s <- gsub("(.*) USA", "USA", C1s)
  #country name is word before last comma
  C1s <- sapply(C1s, function(x)sub("^.*, ([A-Za-z ]*)$", "\\1", x))
  names(C1s) <- NULL
  C1s = gsub("^ | $", "", C1s)  #remove spaces
  }