#!/usr/bin/env python

import sys
import csv

def read_entries():
    """Read tab-separated input from stdin"""
    entries = []
    for l in sys.stdin:
        e = l[:-1].split('\t') 
        if len(e) > 0:
            entries.append(e)
    #entries = [e for e in csv.reader(sys.stdin,delimiter='\t') if len(e) > 0]
    if len(entries) < 1:
        return (0,[])
    else:
        return (len(entries[0]),entries)

def read_tags():
    """Read the tags for the input from argv"""
    args = sys.argv[1:]
    return (args[0],len(args[1:]),args[1:])

def amp(s):
    return s.replace('&','&amp;')

def splitter(e,t):
    if t[0] == '+':
        t = t[1:]
        return [(entry,t) for entry in e.split()]
    else:
        return [(e,t)]

def tag_entry(zs):
    return "\n".join(
        ["  <LexicalEntry>",
         "\n".join(['    <' + t + '>' + amp(e) + '</' + t + '>' for (_e,_t) in zs if _t[0] != '-' for (e,t) in splitter(_e,_t)]),
         "  </LexicalEntry>"])

def tag_entries(entries,elen,tags):
    return "\n".join(
        [tag_entry(zip(e,tags)) for e in entries if len(e) == elen])
    
def xmlize(name,entries,elen,tags):
    return "\n".join([
            '<?xml version="1.0" encoding="UTF-8"?>',
            '<!-- $Id$ -->',
            '<Lexicon xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="https://svn.spraakdata.gu.se/sb-arkiv/pub/lexikon/%s/%s.xsd">' % (name,name), 
            tag_entries(entries,elen,tags), 
            '</Lexicon>'])

if __name__ == '__main__':
    (elen,entries) = read_entries()
    (name,tlen,tags) = read_tags()
    if(elen == tlen):
        print xmlize(name, entries,elen,tags)
    else:
        raise Exception, "entry line - tag count mismatch"