# This is an awk script, but no awk colour coding is available here.

#
# input: an LDAP query pulling back the displayName and sAMAccountName properties 
# for an entire ActiveDirectory forest
# 
# output: yaml format of same data
# ex. 
# 1:
#   name: "Doll, Brian A"
#   lan_id: "brian.a.doll"


# split on newline for fields
BEGIN { FS = "\n"; RS = "" }

# don't deal with incomplete records, gotta have 3 fields 
NF == 3 { 

  name = $2
  lanid = $3

  # get rid of the prefixes
  sub(/displayName\: /, "", name)
  sub(/sAMAccountName\: /, "", lanid) 
 
  # escape the quotes on familiar names like "Tina" for Christina
  gsub(/"/,"\\\"",name)  

  # get rid of the tabs
  gsub(/[\t]/,"",name) 
  
  # skip numeric account names
  if (!gsub(/^[0-9]/,"",name)) {

    # print in yaml format
    printf("%s:\n  name: \"%s\"\n  lan_id: \"%s\"\n", NR, name, lanid)  

  }
}