contrib/regenerate-sarif-spec-index.py

   1 #!/usr/bin/env python3
   2
   3 # Copyright (C) 2024 Free Software Foundation, Inc.
   4 #
   5 # This file is part of GCC.
   6 #
   7 # GCC is free software; you can redistribute it and/or modify it under
   8 # the terms of the GNU General Public License as published by the Free
   9 # Software Foundation; either version 3, or (at your option) any later
  10 # version.
  11 #
  12 # GCC is distributed in the hope that it will be useful, but WITHOUT ANY
  13 # WARRANTY; without even the implied warranty of MERCHANTABILITY or
  14 # FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
  15 # for more details.
  16 #
  17 # You should have received a copy of the GNU General Public License
  18 # along with GCC; see the file COPYING3.  If not see
  19 # <http://www.gnu.org/licenses/>.
  20
  21 # Unfortunately the SARIF 2.1.0 spec doesn't have memorable anchors
  22 # for its subsections
  23 # (filed as https://github.com/oasis-tcs/sarif-spec/issues/533)
  24 #
  25 # In the meantime, use this script to generate a table mapping subsections
  26 # to anchors.
  27
  28 from pprint import pprint
  29 import re
  30
  31 spec_url = 'https://docs.oasis-open.org/sarif/sarif/v2.1.0/errata01/os/sarif-v2.1.0-errata01-os-complete.html'
  32 filename_in = 'sarif-v2.1.0-errata01-os-complete.html'
  33
  34 d = {}
  35 with open(filename_in, encoding='windows-1252') as infile:
  36     for line in infile:
  37         m = re.match(r'<p class=MsoToc[0-9]+><a href="#(.*)">(.*)<span.*\n', line)
  38         if m:
  39             #print('MATCH')
  40             #print(repr(line))
  41             #print(m.groups())
  42             m2 = re.match(r'([0-9.]+) .*', m.group(2))
  43             if m2:
  44                 #print(m2.groups())
  45                 d[m2.group(1)] = m.group(1)
  46
  47 filename_out = '../gcc/sarif-spec-urls.def'
  48 with open(filename_out, 'w') as outfile:
  49     outfile.write('/* Generated by regenerate-sarif-spec-index.py.  */\n\n')
  50
  51     outfile.write(f'static const char * const sarif_spec_base_url\n  = "{spec_url}";\n\n')
  52
  53     outfile.write('static const struct ref_anchor\n'
  54                   '{\n'
  55                   '  const char *m_ref;\n'
  56                   '  const char *m_anchor;\n'
  57                   '} sarif_spec_anchor_arr[] = {\n');
  58     for ref, anchor in d.items():
  59         outfile.write(f'  {{ "{ref}", "{anchor}" }},\n')
  60     outfile.write('};')