treecutter/directory.py

   1 #!/usr/bin/python
   2 import os
   3 import fnmatch
   4 from lxml import etree
   5 import treecutter.constants as const
   6 from treecutter.docbook import Docbook
   7 import re
   8 from itertools import chain
   9
  10 class Directory():
  11     """Class containing the state of the directory with articles"""
  12     def __init__(self):
  13         self._cwd = u'.'
  14         self._translations = []
  15         self._tree = []
  16         self._basepath = re.compile('[/\w\._-]*/[\w-]+',re.UNICODE)
  17
  18     def translations(self, directory):
  19         paths = (self._cwd, directory)
  20         for dirname, dirnames, filenames in chain.from_iterable(os.walk(path) for path in paths):
  21             for filename in filenames:
  22                 if fnmatch.fnmatch(filename, '*.xlf'):
  23                     file_ = os.path.join(dirname,filename)
  24                     self._translations.append(file_)
  25         return self._translations
  26
  27
  28     def scan(self, draftflag, levelflag):
  29         for dirname, dirnames, filenames in os.walk(self._cwd):
  30             for filename in filenames:
  31                 if fnmatch.fnmatch(filename, '*.xml'):
  32                     file_ = os.path.join(dirname,filename)
  33                     doc = Docbook(file_)
  34                     (title, menu) = doc.title()
  35                     draft = doc.status() == "draft"
  36                     level = doc.userlevel()
  37
  38 #                    doc = etree.parse(file_)
  39 #                    title = doc.xpath(u'/db:article/db:info/db:title',namespaces=const.XPATH)
  40 #                    menu  = doc.xpath(u'/db:article/db:info/db:titleabbrev',namespaces=const.XPATH)
  41 #                    draft = doc.xpath(u'/db:article[@status="draft"]',namespaces=const.XPATH)
  42                     if draft and draftflag:
  43                         draft = False
  44                     if title and menu and not draft and level <= levelflag:
  45                         base = self._basepath.match(file_).group()
  46                         link = base.replace('index','')[1:]
  47                         self._tree.append(link)
  48
  49     def set(self):
  50         return set(self._tree)