pos_annotated_file = "tale1.tts"

# Do not add extra newlines - apparently, this messes MMAX2 up (?)
header = """<?xml version="1.0" encoding="US-ASCII"?>
<!DOCTYPE markables SYSTEM "markables.dtd">
<markables xmlns="www.eml.org/NameSpaces/POS">"""

def make_line(id,pos_tag):
    sid = str(id)
    line = '<markable '
    line += 'mmax_level="POS" '
    line += 'id="markable_'+sid+'" '
    line += 'span="word_'+sid+'" '
    line += 'tag="'+pos_tag.lower()+'" '
    line += '/>'
    return line

file = open(pos_annotated_file,'r')

print header

index = 1
line = file.readline()
while line:
    line = line.rstrip()
    my_list = line.split('\t')
    pos_tag = my_list[-1]
    print make_line(index,pos_tag)

    index += 1
    line = file.readline()

file.close()

print "</markables>"