pylint: upgrade to 1.3.1

third_party/logilab/common/textutils.py

 # copyright 2003-2011 LOGILAB S.A. (Paris, FRANCE), all rights reserved.
 # contact http://www.logilab.fr/ -- mailto:contact@logilab.fr
 #
 # This file is part of logilab-common.
 #
 # logilab-common is free software: you can redistribute it and/or modify it under
 # the terms of the GNU Lesser General Public License as published by the Free
 # Software Foundation, either version 2.1 of the License, or (at your option) any
 # later version.
 #
@@ skipping 266 matching lines @@
     if '://' in url_or_path:
         return url_or_path.rstrip('/').rsplit('/', 1)
     return osp.split(url_or_path.rstrip(osp.sep))
 
 
 def text_to_dict(text):
     """parse multilines text containing simple 'key=value' lines and return a
     dict of {'key': 'value'}. When the same key is encountered multiple time,
     value is turned into a list containing all values.
 
-    >>> text_to_dict('''multiple=1
+    >>> d = text_to_dict('''multiple=1
     ... multiple= 2
     ... single =3
     ... ''')
-    {'single': '3', 'multiple': ['1', '2']}
+    >>> d['single']
+    '3'
+    >>> d['multiple']
+    ['1', '2']
 
     """
     res = {}
     if not text:
         return res
     for line in text.splitlines():
         line = line.strip()
         if line and not line.startswith('#'):
             key, value = [w.strip() for w in line.split('=', 1)]
             if key in res:
                 try:
                     res[key].append(value)
                 except AttributeError:
                     res[key] = [res[key], value]
             else:
                 res[key] = value
     return res
 
 
 _BLANK_URE = r'(\s|,)+'
 _BLANK_RE = re.compile(_BLANK_URE)
 __VALUE_URE = r'-?(([0-9]+\.[0-9]*)|((0x?)?[0-9]+))'
 __UNITS_URE = r'[a-zA-Z]+'
 _VALUE_RE = re.compile(r'(?P<value>%s)(?P<unit>%s)?'%(__VALUE_URE, __UNITS_URE))
+_VALIDATION_RE = re.compile(r'^((%s)(%s))*(%s)?$' % (__VALUE_URE, __UNITS_URE,
+                                                    __VALUE_URE))
 
 BYTE_UNITS = {
     "b": 1,
     "kb": 1024,
     "mb": 1024 ** 2,
     "gb": 1024 ** 3,
     "tb": 1024 ** 4,
 }
 
 TIME_UNITS = {
@@ skipping 19 matching lines @@
     :param inter: used to parse every intermediate value (need __sum__)
 
     :type blank_reg: regexp
     :param blank_reg: should match every blank char to ignore.
 
     :type value_reg: regexp with "value" and optional "unit" group
     :param value_reg: match a value and it's unit into the
     """
     if inter is None:
         inter = final
-    string = _BLANK_RE.sub('', string)
+    fstring = _BLANK_RE.sub('', string)
+    if not (fstring and _VALIDATION_RE.match(fstring)):
+        raise ValueError("Invalid unit string: %r." % string)
     values = []
-    for match in value_reg.finditer(string):
+    for match in value_reg.finditer(fstring):
         dic = match.groupdict()
-        #import sys
-        #print >> sys.stderr, dic
         lit, unit = dic["value"], dic.get("unit")
         value = inter(lit)
         if unit is not None:
             try:
                 value *= units[unit.lower()]
             except KeyError:
                 raise KeyError('invalid unit %s. valid units are %s' %
                                (unit, units.keys()))
         values.append(value)
     return final(sum(values))
@@ skipping 152 matching lines @@
             out.write(colorize_ansi(line, style['remove']))
         elif line[0] == '+':
             out.write(colorize_ansi(line, style['add']))
         elif line[:4] == '--- ':
             out.write(colorize_ansi(line, style['separator']))
         elif line[:4] == '+++ ':
             out.write(colorize_ansi(line, style['separator']))
         else:
             out.write(line)