# $Id$
# get element list from HTML specification

from urllib import urlopen
from ElementSoup import ET, parse

import keyword

ELEMENTS = "http://www.w3.org/TR/html4/index/elements.html"
ATTRIBUTES = "http://www.w3.org/TR/html4/index/attributes.html"

def gettext(elem):
    text = elem.text or ""
    for e in elem:
        text += gettext(e)
        if e.tail:
            text += e.tail
    return text

empty = []

print "from builder import E, ET"

print
print "# elements"
for row in parse(urlopen(ELEMENTS)).findall(".//tr"):
    d = {}
    for cell in row:
	d[cell.get("title", "").strip()] = gettext(cell).strip()
    name = d.get("Name")
    if not name:
	continue
    name = name.lower().encode("ascii")
    description = " ".join(d.get("Description").split())
    if keyword.iskeyword(name):
	print name.upper(), "=", "getattr(E, %r)" % name,
    else:
	print name.upper(), "=", "E." + name,
    print "#", description,
    if d.get("Depr."):
	print "(DEPRECATED)",
    print
    if d.get("Empty"):
	empty.append(name)

print
print "# attributes (only reserved words are included here)"
print "ATTR = dict"
last = None
for row in parse(urlopen(ATTRIBUTES)).findall(".//tr"):
    d = {}
    for cell in row:
	d[cell.get("title", "").strip()] = gettext(cell).strip()
    name = d.get("Name")
    if not name:
	continue
    name = name.lower().encode("ascii")
    if name == last:
	continue
    if not keyword.iskeyword(name):
	continue
    print "def %s(v): return {%r: v}" % (name.upper(), name)
    last = name

print
print "# elements that don't have an end tag"
print "empty", "=", empty