Source Code for Module buildxml.tools.functions

  1  # -*- coding: utf-8 -*- 
  2   
  3   
  4  """ 
  5  This module holds some utility functions. 
  6   
  7  @author: Johannes Schwenk 
  8  @copyright: 2010, Johannes Schwenk 
  9  @version: 1.0 
 10  @date: 2010-09-15 
 11   
 12  """ 
 13   
 14  import sys 
 15   
 16  # Imortant! 
 17  reload(sys) 
 18  sys.setdefaultencoding('utf-8') 
 19   
 20  import re 
 21  import htmlentitydefs 
 22  import os 
 23   
 24   
 25  from datetime import datetime, timedelta 
 26   
 27  try: 
 28      from email.utils import parsedate_tz 
 29  except ImportError: 
 30      from email.Utils import parsedate_tz 
 31   
 32   
 33   
 34 -def du(start_path=u'.'): 
 35      """ 
 36      Computes the size of the files in the file system subtree starting at 
 37      C{start_path} . 
 38   
 39      @return: The recursive size of C{start_path} in bytes. 
 40      @rtype: int 
 41   
 42      """ 
 43      total_size = 0 
 44      for dirpath, dirnames, filenames in os.walk(start_path): 
 45          for f in filenames: 
 46              fp = os.path.join(dirpath, f) 
 47              if os.path.exists(fp): 
 48                  total_size += os.path.getsize(fp) 
 49      return total_size 
 50   
 51   
 52 -def unescape(text): 
 53      """ 
 54      Unescape HTML Entities # 
 55      © October 28, 2006 | Fredrik Lundh 
 56   
 57      http://effbot.org/zone/re-sub.htm#unescape-html 
 58   
 59      Removes HTML or XML character references and entities from a text string. 
 60   
 61      @param text: The HTML (or XML) source text. 
 62      @return: The plain text, as a Unicode string, if necessary. 
 63      """ 
 64      def fixup(m): 
 65          text = m.group(0) 
 66          if text[:2] == "&#": 
 67              # character reference 
 68              try: 
 69                  if text[:3] == "&#x": 
 70                      return unichr(int(text[3:-1], 16)) 
 71                  else: 
 72                      return unichr(int(text[2:-1])) 
 73              except ValueError: 
 74                  pass 
 75          else: 
 76              # named entity 
 77              try: 
 78                  text = unichr(htmlentitydefs.name2codepoint[text[1:-1]]) 
 79              except KeyError: 
 80                  pass 
 81          return text # leave as is 
 82      return re.sub("&#?\w+;", fixup, text) 
 83   
 84   
 85  """ 
 86  ================== License for parse_date: =================================== 
 87   
 88  Copyright (c) 2010 by the Werkzeug Team, see AUTHORS for more details. 
 89   
 90  Redistribution and use in source and binary forms, with or without 
 91  modification, are permitted provided that the following conditions are 
 92  met: 
 93   
 94      * Redistributions of source code must retain the above copyright 
 95        notice, this list of conditions and the following disclaimer. 
 96   
 97      * Redistributions in binary form must reproduce the above 
 98        copyright notice, this list of conditions and the following 
 99        disclaimer in the documentation and/or other materials provided 
100        with the distribution. 
101   
102      * The names of the contributors may not be used to endorse or 
103        promote products derived from this software without specific 
104        prior written permission. 
105   
106  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 
107  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 
108  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR 
109  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT 
110  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, 
111  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT 
112  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, 
113  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY 
114  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT 
115  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE 
116  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 
117   
118  """ 
119   
120 -def parse_date(date): 
121      """ 
122      Parses date strings of formats: 
123   
124      Sun, 06 Nov 1994 08:49:37 GMT 
125      Sunday, 06-Nov-94 08:49:37 GMT 
126      Sun Nov  6 08:49:37 1994 
127   
128      @param date: Date as string. 
129      @return: A C{datetime.datetime} object or C{None} if parsing failed. 
130      """ 
131      if date: 
132          parsed_date = parsedate_tz(date.strip()) 
133          if not parsed_date == None: 
134              try: 
135                  year = parsed_date[0] 
136                  """ 
137                  Unfortunately that function does not tell us if two digit 
138                  years were part of the string, or if they were prefixed 
139                  with two zeroes.  So what we do is to assume that 69-99 
140                  refer to 1900, and everything below to 2000. 
141                  """ 
142                  if year >= 0 and year <= 68: 
143                      year += 2000 
144                  elif year >= 69 and year <= 99: 
145                      year += 1900 
146                  return datetime(*((year,) + parsed_date[1:7])) - \ 
147                         timedelta(seconds=parsed_date[-1] or 0) 
148              except (ValueError, OverflowError): 
149                  return None 
150