scripts/find_repeated_words.sh

   1 #!/bin/sh
   2 #
   3 # find_repeated_words.sh
   4 #
   5 # A simple script for finding instances of repeated consecutive words
   6 # in manual pages -- human inspection can then determine if these
   7 # are real errors in the text.
   8 #
   9 # Usage: sh find_repeated_words.sh [file...]
  10 #
  11 ######################################################################
  12 #
  13 # (C) Copyright 2007 & 2013, Michael Kerrisk
  14 # This program is free software; you can redistribute it and/or
  15 # modify it under the terms of the GNU General Public License
  16 # as published by the Free Software Foundation; either version 2
  17 # of the License, or (at your option) any later version.
  18 #
  19 # This program is distributed in the hope that it will be useful,
  20 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  21 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  22 # GNU General Public License for more details
  23 # (http://www.gnu.org/licenses/gpl-2.0.html).
  24 #
  25 #
  26
  27 for file in "$@" ; do
  28    # Do not process files that are redirects.
  29    grep -qE "^\.so man.*" "$file"
  30    if test $? -ne 0; then
  31     words=$(MANWIDTH=2000 man -l "$file" 2> /dev/null | col -b | \
  32         tr ' \008' '\012' | sed -e '/^$/d' | \
  33         sed 's/ *$//' |
  34         awk 'BEGIN {p=""} {if (p==$0) print p; p=$0}' | \
  35         grep '[a-zA-Z]' | tr '\012' ' ')
  36     if test -n "$words"; then
  37         echo "$file: $words"
  38     fi
  39    fi
  40 done