#!/usr/bin/env python
"""Pretty print a mbox -- since some previous date -- as a simple HTML file"""


import os, re, sys
import textwrap
import cgi

from email.Utils import parsedate # http://docs.python.org/lib/module-email.Utils.html
import email.Parser, mailbox

import time
from datetime import * 	# http://docs.python.org/lib/datetime-date.html
from dateutil.tz import *
from dateutil.parser import *	# http://labix.org/python-dateutil
from dateutil.relativedelta import *

import markup			# http://markup.sourceforge.net/#documentation

def msgfactory(fp):
	try:
		return email.message_from_file(fp)
	except email.Errors.MessageParseError:
		# Don't return None since that will
		# stop the mailbox iterator
		return ''

def main():
	if len(sys.argv)==1:
		print "Usage: %s filename" % os.path.basename(sys.argv[0])
		sys.exit(1)
	fp = open(sys.argv[1], 'r')
	mbox = mailbox.UnixMailbox(fp, msgfactory)
	
	page = markup.page( )
	page.init( title="Student Responses",
		css='http://reagle.org/joseph/2005/01/mm-print.css',
		charset = 'utf-8')	# http://reagle.org/joseph/2005/01/mm-print.css

	now = datetime.now(tzlocal())	# could use (pytz.timezone('US/Eastern'))
	for msg in mbox:
		subject = sender = msg_date = None
		subject = cgi.escape(msg.get('subject'))
		sender = cgi.escape(msg.get('from').split('@')[0]  + '>')
		msg_date = parse(msg.get('date'))
		
		if now.today().weekday() in (2,3,4,5): # WE,TH,FR,SA msgs since prev TU
			# previous class is the previous TU ending at noon tzlocal
			prev_class = now+relativedelta(hour=12,minute=0,second=0,weekday=TU(-1))
		elif now.today().weekday() in (6,0,1): # SU,MO,TU msgs since prev TH
			prev_class = now+relativedelta(hour=12,minute=0,second=0,weekday=TH(-1))

		if msg_date > prev_class:

			page.div.open()
			page.hr()
			page.h1(subject, class_='subject')
			page.h2(sender, class_='sender')
			page.h2(str(msg_date), class_='msg_date')
			for part in msg.walk():
				#print part.get_content_subtype()
				if part.get_content_subtype() == 'plain':
					charset = part.get_content_charset()
					content = part.get_payload(decode=True).decode(charset,'replace').encode('utf-8','replace')
					content = cgi.escape(content)
					lines = content.split('\n')
					if any(len(line) > 100 for line in lines):
						pass	# hasn't been wrapped
					else:		# un/re-wrap
						content = content.replace ('\n\n', '***!!!')
						content = content.replace ('\n', ' ') # rm artifical breaks
						content = content.replace ('***!!!', '\n\n')
						lines = content.split('\n\n')
					for line in lines:
						page.p(''.join(line))
				else:
					if part.get_content_subtype() == 'msword' or \
						part.get_content_subtype() == 'octet-stream':
						tmpf = '/tmp/mail-part-msw'
						tmpft = '/tmp/mail-part-msw.txt'
						os.system('rm %s %s' % (tmpf,tmpft) )
						charset = part.get_content_charset()
						content = part.get_payload(decode=True)
						tmpfp = open(tmpf, 'w')
						tmpfp.write(content)
						tmpfp.close()
						os.system('catdoc %s > %s' % (tmpf,tmpft) )
						tmpftpt = open(tmpft, 'r')
						content = ' '.join(tmpftpt.readlines())
						content = cgi.escape(content)
						page.pre(content)
			page.div.close( )

	print page


class opts:
	recent = False

if __name__=="__main__":
	import getopt, os, sys
	
	try:
		options, arguments = getopt.getopt (sys.argv[1:],"r")
	except getopt.error:
		print 'Error: Unknown option or missing argument.'

	for opt, val in options:
		if opt == '-r':
			opts.recent = True
	main()