filter-debian-changelog

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
#
# Debian/Ubuntu Packaging Scripts
# Copyright (C) 2002-2024 by Thomas Dreibholz
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.
#
# Contact: thomas.dreibholz@gmail.com


# This script filters debian/changelog entries:
# Usage: filter-debian-changelog [regexp_for_last_entry|FIRST]
# * Empty entries get dropped.
# * Stop, if entry matches regexp_for_last_entry argument.
# * Stop after first entry, if regexp_for_last_entry = FIRST.
# Example: filter-debian-changelog "Mon, 31 Oct 2016 08:08:08 \+0200"
#          Note the \+, otherwise '+' is interpreted as regexp!


import glob
import os
import re
import sys
import time


#  ====== Handle arguments ==================================================
if len(sys.argv) < 2:
  sys.stderr.write('Usage: ' + sys.argv[0] + ' regexp_for_last_entry|FIRST\n')
  sys.exit(1)

if sys.argv[1] == '':
   re_last_entry = None
elif sys.argv[1] == 'FIRST':
   re_last_entry = re.compile(r'^.*$')
else:
   re_last_entry = re.compile(r'^.*' + sys.argv[1])

re_begin_of_entry = re.compile(r'^[a-zA-Z].*$')
re_end_of_entry   = re.compile(r'^ --.*$')
re_empty          = re.compile(r'^$')
re_item           = re.compile(r'^ *')
re_item_is_itp    = re.compile(r'^(.*Closes:.*ITP.*|.*ITP.*Closes:.*)$')

entries           = 0
entryContentLines = 0
entryContent      = ''
entryIsITP        = False

contents = sys.stdin.readlines()
for line in contents:

   # ====== Begin of entry ==================================================
   if entryContentLines == 0:
      if re_begin_of_entry.match(line):
         entryContent      = line
         entryContentLines = 1

   # ====== Within entry ====================================================
   else:
      # ------ End of entry -------------------------------------------------
      if re_end_of_entry.match(line):
         entryContent   = entryContent + line + '\n'
         if entryContentLines > 1:
            entries = entries + 1

            # ------ Print entry --------------------------------------------
            if not entryIsITP:
               sys.stdout.write(entryContent)
            # ------ Print entry with ITP -----------------------------------
            # Special case: The ITP package for Debian must only contain the
            #               ITP entry with ITP item and nothing else!
            else:
               splittedITPEntry = entryContent.splitlines()
               i = 0
               for itpLine in splittedITPEntry:
                  i = i + 1
                  if (i <= 2) or (i >= len(splittedITPEntry) - 2):
                     sys.stdout.write(itpLine + '\n')
                  elif re_item_is_itp.match(itpLine) != None:
                     sys.stdout.write(itpLine + '\n')
               break   # ITP -> done!

            entryContent   = ''
            entryIsITP = False

         # ------ Check for match with last entry regexp in argument --------
         if re_last_entry != None:
            if re_last_entry.match(line) != None:
               break

         entryContentLines = 0

      # ------ Part of entry ------------------------------------------------
      else:
         if re_item.match(line):
            entryContent      = entryContent + line
            entryContentLines = entryContentLines + 1
            if re_item_is_itp.match(line):
               entryIsITP = True