contrib/check-internal-format-escaping.py

   1 #!/usr/bin/env python3
   2 #
   3 # Check gcc.pot file for gcc-internal-format and print all strings
   4 # that contain an option that is not wrapped by %<-option_name%>.
   5 #
   6 # This file is part of GCC.
   7 #
   8 # GCC is free software; you can redistribute it and/or modify it under
   9 # the terms of the GNU General Public License as published by the Free
  10 # Software Foundation; either version 3, or (at your option) any later
  11 # version.
  12 #
  13 # GCC is distributed in the hope that it will be useful, but WITHOUT ANY
  14 # WARRANTY; without even the implied warranty of MERCHANTABILITY or
  15 # FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
  16 # for more details.
  17 #
  18 # You should have received a copy of the GNU General Public License
  19 # along with GCC; see the file COPYING3.  If not see
  20 # <http://www.gnu.org/licenses/>.  */
  21 #
  22 #
  23 #
  24
  25 import argparse
  26 import re
  27
  28 parser = argparse.ArgumentParser(description='')
  29 parser.add_argument('file', help = 'pot file')
  30
  31 args = parser.parse_args()
  32
  33 origin = None
  34 internal = False
  35
  36 lines = open(args.file).readlines()
  37 for i, l in enumerate(lines):
  38     l = l.strip()
  39     s = 'msgid '
  40     if l.startswith('#: '):
  41         origin = l
  42     elif '#, gcc-internal-format' in l:
  43         internal = True
  44     if l.startswith(s) and origin and internal:
  45         j = 0
  46         while not lines[i + j].startswith('msgstr'):
  47             l = lines[i + j]
  48             if l.startswith(s):
  49                 l = l[len(s):]
  50             text = l.strip('"').strip()
  51             if text:
  52                 parts = text.split(' ')
  53                 for p in parts:
  54                     if p.startswith('-'):
  55                         if len(p) >= 2 and (p[1].isalpha() and p != '-INF'):
  56                             print('%s: %s' % (origin, text))
  57                     elif p.startswith('__builtin_'):
  58                         print('%s: %s' % (origin, text))
  59                     if re.search("[^%]'", p):
  60                         print('%s: %s' % (origin, text))
  61                     # %< should not be preceded by a non-punctuation
  62                     # %character.
  63                     if re.search("[a-zA-Z0-9]%<", p):
  64                         print('%s: %s' % (origin, text))
  65             j += 1
  66
  67         origin = None
  68         internal = False