1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
|
#!/bin/sh
# Copyright (C) 2019-2020 Free Software Foundation, Inc.
# 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/>.
# This script intends to facilitate spell checking of source/doc files.
# It:
# - transforms the files into a list of lowercase words
# - prefixes each word with the frequency
# - filters out words within a frequency range
# - sorts the words, longest first
#
# If '-c' is passed as option, it operates on the C comments only, rather than
# on the entire file.
#
# For:
# ...
# $ files=$(find gdb -type f -name "*.c" -o -name "*.h")
# $ ./gdb/contrib/words.sh -c $files
# ...
# it generates a list of ~15000 words prefixed with frequency.
#
# This could be used to generate a dictionary that is kept as part of the
# sources, against which new code can be checked, generating a warning or
# error. The hope is that misspellings would trigger this frequently, and rare
# words rarely, otherwise the burden of updating the dictionary would be too
# much.
#
# And for:
# ...
# $ files=$(find gdb -type f -name "*.c" -o -name "*.h")
# $ ./gdb/contrib/words.sh -c -f 1 $files
# ...
# it generates a list of ~5000 words with frequency 1.
#
# This can be used to scan for misspellings manually.
#
minfreq=
maxfreq=
c=false
while [ $# -gt 0 ]; do
case "$1" in
-c)
c=true
shift
;;
--freq|-f)
minfreq=$2
maxfreq=$2
shift 2
;;
--min)
minfreq=$2
if [ "$maxfreq" = "" ]; then
maxfreq=0
fi
shift 2
;;
--max)
maxfreq=$2
if [ "$minfreq" = "" ]; then
minfreq=0
fi
shift 2
;;
*)
break;
;;
esac
done
if [ "$minfreq" = "" ] && [ "$maxfreq" = "" ]; then
minfreq=0
maxfreq=0
fi
awkfile=$(mktemp)
trap 'rm -f "$awkfile"' EXIT
cat > "$awkfile" <<EOF
BEGIN {
in_comment=0
}
// {
line=\$0
}
/\/\*/ {
in_comment=1
sub(/.*\/\*/, "", line)
}
/\*\// {
sub(/\*\/.*/, "", line)
in_comment=0
print line
next
}
// {
if (in_comment) {
print line
}
}
EOF
# Stabilize sort.
export LC_ALL=C
if $c; then
awk \
-f "$awkfile" \
-- "$@"
else
cat "$@"
fi \
| sed \
-e 's/[!"?;:%^$~#{}`&=@,. \t\/_()|<>\+\*-]/\n/g' \
-e 's/\[/\n/g' \
-e 's/\]/\n/g' \
-e "s/'/\n/g" \
-e 's/[0-9][0-9]*/\n/g' \
-e 's/[ \t]*//g' \
| tr '[:upper:]' '[:lower:]' \
| sort \
| uniq -c \
| awk "{ if (($minfreq == 0 || $minfreq <= \$1) \
&& ($maxfreq == 0 || \$1 <= $maxfreq)) { print \$0; } }" \
| awk '{ print length($0) " " $0; }' \
| sort -n -r \
| cut -d ' ' -f 2-
|