treecutter/directory.py

   1 #!/usr/bin/python
   2 import os
   3 import fnmatch
   4 import subprocess
   5 import amara
   6 import re
   7 import tempfile
   8 import errno
   9 import time
  10 import argparse
  11 import shutil
  12 import pygraphviz as pgv
  13 import glob
  14 import gettext
  15 import shutil
  16 from amara import bindery
  17 from amara.xslt import transform
  18 from Cheetah.Template import Template
  19
  20 class Directory():
  21     """Class containing the state of the directory with articles"""
  22     def __init__(self):
  23         self._cwd = '.'
  24         self._tree = []
  25
  26     def scan(self):
  27         for dirname, dirnames, filenames in os.walk(self._cwd):
  28             for filename in filenames:
  29                 if fnmatch.fnmatch(filename, '*.xml'):
  30                     file_ = os.path.join(dirname,filename)
  31                     doc = bindery.parse(file_, prefixes=PREFIXES)
  32                     title = doc.xml_select(u'/db:article/db:info/db:title')
  33                     menu  = doc.xml_select(u'/db:article/db:info/db:titleabbrev')
  34                     if title and menu:
  35                         base = file_.split('.')[1]
  36                         link = base.replace('index','')
  37                         self._tree.append(link)
  38
  39     def set(self):
  40         return set(self._tree)