"""
filter.py is a pyblosxom plugin
filter.py filters visible entries based on a simple regex search on the path.

This allows for custom entry views at each level of your blog. For
example: news only, alerts only, user entries only


filter.py looks for a file in the current working data root.
The file name should be specified in py['filter_file']. The file
will contain a simple directive and regular expression to match.

Config file format -- 
<directive>:<regex>

directive := allow|deny
regex := std. python regex

allow means that only matches are allowed.
deny means that only non-matches are allowed.
Only the first line is read from the configuration file.


This is based heavily on the default filelist handler 
in pyblosxom.

version = "0.03/10JUN2008"

TODO:
* Add multiple lines/rules if it seems useful
* Add a reasonable boiler plate to cb_filelist

Example Usage:
1. Place filter.py in your plugins directory
2. Add it to your config.py
3. Let's say you have three directories under your
   data directory: 
   news, users, development, users/foo, users/bar, 
   users/stupid
  

   Ex 1: You only want news entries to show up
   when you browse to your blog root:
   echo 'allow:[datadir-root]/news/' > [datadir-root]/regex.filter

   Now only entries from your news will show up.

   Ex 2: You want everything to show up in user/ except
   entries from user stupid:
  
    echo 'deny:[datadir-root]/users/stupid' > [datadir-root]/users/regex.filter


  So now when you browse to '/' you see only news entries.  When you browse to
  '/users' you see entries from everyone but 'stupid'.  Remember, you can use
  full regular expressions and not just paths.  Also take note that I use
  'search' instead of 'match'.  This means .*s aren't required on the edges, but
  may mean that you end up matching more than you meant to.


If this needs any clarification, feel free to email me.

Contributors:
* willg - http://www.bluesock.org/~willg/
  - Bringing this up-to-date since I haven't used pybloxsom in a while
    Thanks!!
* Bill Powell - http://billpowellisalive.com/
  - For adding support for coexistence with tags.py

"""

__author__ = "will drewry <will+pyblosxom@cs.bu.edu>"

import time, os, re
from Pyblosxom import tools
from Pyblosxom.pyblosxom import FileEntry


def cb_filelist(args):
  dont_filter = False

  request = args["request"]

  data = request.getData()
  config = request.getConfiguration()

  # Co-exist with tags.py plugin
  if config.has_key('tag_url'):
    filter_tags = re.compile(config['tag_url'])
    if filter_tags.match(data['url']):
      return

  # Load regex filter from data['root_datadir']
  filter_expr = ''
  filter_cmd  = ''
  regex_filename = config.get('filter_file', 'regex.filter')

  try: 
    filter_file = open(data['root_datadir'] + '/' + regex_filename, 'r')
    filter_cmd = filter_file.readline()
    filter_cmd = filter_cmd.strip()
    filter_file.close()
    try: 
      (filter_action, filter_expr) = filter_cmd.split(':')
    except ValueError:
      dont_filter = True
  except IOError:
    dont_filter = True
  
  # Compile regex from file
  filter = re.compile(filter_expr)

  if data['bl_type'] == 'dir':
      filelist = tools.Walk(request, data['root_datadir'], int(config['depth']))
  elif data['bl_type'] == 'file':
      filelist = [data['root_datadir']]
  else:
      filelist = []

  entrylist = []
  for ourfile in filelist:
      entry = FileEntry(request, ourfile, data['root_datadir'])

      # Test file again configured regex and add if it is allowed
      if dont_filter == True:
      	entrylist.append((entry._mtime, entry))
      elif filter_action == 'deny' and filter.search(ourfile) == None:
      	entrylist.append((entry._mtime, entry))
      elif filter_action == 'allow' and filter.search(ourfile) != None:
      	entrylist.append((entry._mtime, entry))

  # this sorts entries by mtime in reverse order.  entries that have
  # no mtime get sorted to the top.
  entrylist.sort()
  entrylist.reverse()
  entrylist = [x[1] for x in entrylist]
  
  # Match dates with files if applicable
  if data['pi_yr']:
      month = (data['pi_mo'] in tools.month2num.keys() and tools.month2num[data['pi_mo']] or data['pi_mo'])
      matchstr = "^" + data["pi_yr"] + month + data["pi_da"]
      valid_list = [x for x in entrylist if re.match(matchstr, x['fulltime'])]
  else:
      valid_list = entrylist

  return valid_list