a script to parse bacterial phylogeny from http://www.bacterio.net/-classifphyla.html and print it into a table format.

LPSN_parcer.rb

# original text is from http://www.bacterio.net/-classifphyla.html
# load hard-coded filename LPSN.txt into a string
# create a File object from LPSN.txt
file = open("LPSN.txt") or die "LPSN.txt not found."
lineArray = Array.new
file.each_line {|line|
  lineArray.push line
}
file.close()
# todo: parse lines your own way if it helps separate genuses.
# todo: grab this data directly from the website
# use the included date to report how old the current genus table is

# phylum = "no phylum"
# clas = "no class"
# order = "no order"
# family = "no family"
# genus = "no genus"

genusNext = false
unclassedNext = false
outFile = open("LPSN-out.txt",'w')
anomoliesFile = open("LPSN-anomolies.txt","w")
lineArray.each do |line|
  # make an exhaustive if/else chain to categorize each line
  # some update the phylogenic labels
  # some text lines are ignored
  # only the genus line adds 1 or more lines to the genus table

  # find all lines containing "Phylum"
  if (/^Phylum "?(?<phylum>\w+)/ =~ line) != nil
#    outFile.write("#{phylum}\n") # write the capture

  elsif (/^Class "?(?<clas>\w+)/ =~ line) != nil
#    outFile.write("#{clas}\n") # write the capture

  elsif (/^Order "?(?<order>\w+)/ =~ line) != nil
#    outFile.write("#{order}\n") # write the capture

  elsif (/^Family "?(?<family>\w+)/ =~ line) != nil
    genusNext = true
#    outFile.write("#{family}\n") # write the capture

  elsif (/^Unclassified "?(?<unclassed>\w+)/ =~ line) != nil
    genusNext = true
    unclassedNext = true
  
  elsif genusNext
    if (/\w+/ =~ line) != nil
      genusNext = false
      # line is list of genuses
      outFile.write(line) # write the capture
    end
  else
    # write anomaly lines to their own file.
    anomoliesFile.write(line)
  end
    
end
outFile.close()
anomoliesFile.close()

# save the table into a file
# include the date.