#!/usr/bin/env python
"""
Parse the Unicode.org iso15924-utf8-20070715.txt file and create
an XML file for our own use.

iso15924-parse.py version 0.1

Copyright (C) 2005 Alastair McKinstry <mckinstry@computer.org>
Copyright (C) 2007 Ivan Masar <helix84@centrum.sk>
Released under the GNU License; see file COPYING for details
"""

f=open("iso15924-utf8-20070715.txt")

ot=open("iso_15924.xml","w")

ot.write("""<?xml version="1.0" encoding="UTF-8" ?>

<!-- iso-15924.xml							-->
<!--									-->
<!-- Copyright (C) 2007 Ivan Masar <helix84@centrum.sk>   		-->
<!-- Released under the GNU License; see file COPYING for details	-->
<!--									-->
<!-- Last update: 2007-09-05    					-->
<!--									-->
<!-- This file gives a list of all script names in the ISO-15924	-->
<!-- standard, and is used to provide translations (via gettext)	-->
<!--									-->
<!-- Status: ISO 15924:2004 + additions and changes until 2007-07-15	-->
<!-- About:  http://unicode.org/iso15924/				-->
<!--         http://unicode.org/iso15924/codelists.html			-->
<!-- Source: http://unicode.org/iso15924/iso15924-text.html		-->
<!-- Change: http://unicode.org/iso15924/codechanges.html 		-->

<!DOCTYPE iso_15924_entries [
	<!ELEMENT iso_15924_entries (iso_15924_entry+)>
	<!ELEMENT iso_15924_entry EMPTY>
	<!ATTLIST iso_15924_entry
		iso_15924_code		CDATA	#REQUIRED
		iso_15924_no  		CDATA	#REQUIRED
		iso_15924_alias		CDATA	#IMPLIED
		name			CDATA	#REQUIRED
	>
]>

<iso_15924_entries>
""")

for i in range(1, 7):
	f.readline()		# throw away the header

for li in f.readlines():
	(code,num,eng,fra,pva,date) = li.split(';')
	eng  = eng.strip()
	ot.write('\t<iso_15924_entry\n')
	ot.write('\t\tiso_15924_code="%s"\n' % code)
	ot.write('\t\tiso_15924_no="%s"\n' % num)
	if pva != '':
		ot.write('\t\tiso_15924_alias="%s"\n' % pva)
#	ot.write('\t\tdate="%s"\n' % date)
	ot.write('\t\tname="%s" />\n' % eng)

ot.write('</iso_15924_entries>')
ot.close()
f.close()