FILE_EXT = 'html'
"""
Files with a .html extension will be an entry.
"""
__version__ = '$Id:$0.2'	# change title search to regexp
__author__ = 'Joseph Reagle joseph.2008@reagle.org'

def cb_entryparser(args):
	args[FILE_EXT] = readfile
	return args

def readfile(filename, request):
	
	from Pyblosxom import tools
	import re
	
	entryData = {}
	html = file(filename).read()
	#title = html[html.find('<h1>') + 4:html.find('</h1>')]
	title_p = re.compile(r'<h1.*?>(.*?)</h1', re.DOTALL)
	title = title_p.search(html).group(1)
	# (Could one find a date of publication in a META tag?)
	body = html[html.find('</h1>') + 5:html.find('</body>')]
	entryData = {'title': title,
		'body': body}
	# Call the postformat callbacks
	tools.run_callback('postformat',
			{'request': request,
			'entry_data': entryData})
	
	return entryData