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
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
|
#!/bin/sh
#
# Copyright (c) 2007, 2008 Oligem.com. All rights reserved.
#
# Permission to use, copy, modify, and distribute this software for any
# purpose with or without fee is hereby granted, provided that the above
# copyright notice and this permission notice appear in all copies.
#
# THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
# WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
# MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
# ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
# ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
# OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
#
# wd, word diff
usage()
{
echo 'NAME
wd - word differences
SYNOPSIS
wd [-123NvV] [-w|-x|-y|-z Mark] Oldfile Newfile
OPTIONS
-1 inhibit output of deleted words
-2 inhibit output of inserted words
-3 inhibit output of common words
-N treat absent files as empty
-O Optimal markup. Default marks are redundant, but
make less(1) happy for colorizing.
-V print version and exit
-v print a header line with old and new filenames.
-w Mark mark beginning of old word
-x Mark mark end of old word
-y Mark mark beginning of new word
-z Mark mark end of new word
AUTHORS
Philippe Bergheaud and Marc Vertes' >&2
exit 2
}
istextfile()
{
diff /dev/null "$1" 2>/dev/null | awk '/differ/ {exit 1} {exit 0}'
}
opt1=0 opt2=0 opt3=0
red=""; red="$red[01;31m"
blue=""; blue="$blue[01;34m"
green=""; green="$green[01;35m"
white=""; white="$white[00m"
opth=$green optw=$blue optx=$white opty=$red optz=$white
while getopts :123L:NOuVvw:x:y:z: opt
do
case $opt in
([123NOuv]) eval opt$opt=1 ;;
([Lwxyz]) eval "opt$opt=\"$OPTARG\"" ;;
(V) echo wd-0.6; exit ;;
(*) usage ;;
esac
done
shift $((OPTIND - 1))
[ $# -eq 2 ] || usage
if [ $opt1 -eq 0 -a $opt2 -ne 0 ]
then
# show old: swap files and colors
old_file=$2 new_file=$1
opt2=0 opt1=1 opty=$optw optz=$optx
else
old_file=$1 new_file=$2
fi
[ -f "$old_file" ] || { [ "$Optn" ] && old_file=/dev/null || exit; }
[ -f "$new_file" ] || { [ "$OptN" ] && new_file=/dev/null || exit; }
istextfile $new_file || exit
old_word_file=/tmp/old_word_file.$$
trap 'rm -f $old_word_file' EXIT
tr -s '[:blank:]' '\n' <$old_file >$old_word_file
tr -s '[:blank:]' '\n' <$new_file |
diff -B --new-group-format='n %dF %dL
' --old-group-format='o %df %dl
' --line-format= "$old_word_file" - |
awk -v optv="$optv" -v new_file="$new_file" -v old_file="$old_file" \
-v optO="$optO" -v opt1=$opt1 -v opt2=$opt2 -v opt3=$opt3 -v opth="$opth" \
-v optw="$optw" -v optx="$optx" -v opty="$opty" -v optz="$optz" '
function print_tblank(file, blank1, display, resume)
{
if (!display) return
if (tblank ~ /\n/) {
if (prev_file != file && resume) {
if (blank1)
printf("%s%s", tblank, blank1)
else
printf(" ")
} else
printf("%s%s", tblank, blank1)
} else {
if (prev_file && prev_file != file)
printf(" ")
else
printf("%s%s", tblank, blank1)
}
prev_file = file
tblank = ""
}
function print_word(file, begin, end, blank, word, display, bmark, emark)
{
bmark_printed = 0
emark_toprint = 0
while (W[file] != end) {
if (i[file] > nf[file]) {
if (getline line <file == 0) {
print_tblank(file, "", display, 0)
exit # end of file, exit
}
split(line, blank, "[^ ]+") # anti-split
if (tblank || nf[file] != -1)
print_tblank(file, blank[1], display, 0)
if (!blank[1] || nf[file] == -1)
i[file] = 1 # initialize the for loop
else
i[file] = 2 # line starts with blank
nf[file] = split(line, word, "[ ]+")
if (nf[file] && word[nf[file]] == "")
nf[file]-- # line ends with blank
} else
print_tblank(file, "", display, 1)
# redundant per line marks (for less(1) colorizing)
if (! optO) {
bmark_printed = 0
emark_toprint = 0
}
for (; i[file] <= nf[file]; i[file]++) {
if (++W[file] < begin)
continue
if (display) {
if (! bmark_printed) {
if (emark_toprint) {
printf("%s", emark)
emark_toprint = 0
}
printf("%s", bmark)
bmark_printed = 1
}
printf("%s", word[i[file]])
emark_toprint = 1
if (W[file] == end)
tblank = blank[i[file] + (blank[1] ? 0 : 1)]
else
printf("%s", blank[i[file] + (blank[1]? 0 : 1)])
}
if (W[file] == end) {
i[file]++
break
}
}
# redundant per line marks
if (! optO && emark_toprint) {
printf("%s", emark)
emark_toprint = 0
}
if (display && i[file] > nf[file]) {
if (W[file] == end)
tblank = tblank "\n"
else {
print ""
tblank = ""
}
}
if (W[file] == end)
break
}
if (emark_toprint)
printf("%s", emark)
w[file] = end + 1
}
function same_group(begin, end)
{
print_word(old_file, w[old_file], w[old_file] + end - begin,
oblank, oword, 0, "", "")
print_word(new_file, begin, end, nblank, nword, !opt3, "", "")
}
function old_group(begin, end)
{
if (begin > w[old_file])
same_group(w[new_file], w[new_file] + begin - w[old_file] - 1)
print_word(old_file, begin, end, oblank, oword, !opt1, optw, optx)
}
function new_group(begin, end)
{
if (begin > w[new_file]) same_group(w[new_file], begin - 1)
print_word(new_file, begin, end, nblank, nword, !opt2, opty, optz)
}
BEGIN {
# index of old word read, to be printed
W[old_file] = 0; w[old_file] = 1
# index of new word read, to be printed
W[new_file] = 0; w[new_file] = 1
# initialize the for loop on old lines
i[old_file] = 0; nf[old_file] = -1
# initialize the for loop on new lines
i[new_file] = 0; nf[new_file] = -1
oblank[1] = ""; oword[1] = "" # old blank and old word arrays
nblank[1] = ""; nword[1] = "" # new blank and new word arrays
# trailing blank, replaced by a space after the last word
# of an old group when followed by a word on the same line
tblank = ""
prev_file = "" # previous file
if (optv) print opth "### wd " optw old_file " " opty new_file optx
}
/^n/ { new_group($2, $3) } # display common and new words
/^o/ { old_group($2, $3) } # display common and old words
END { # display common words, up to the end of file
if ((!opt1 || !opt2) && opt3)
print ""
print_word(new_file, w[new_file], -1, nblank, nword, !opt3, "", "")
}' |
less -CimqGrX -j9 -h0 +/'\[01'; echo -n '[00m'
echo -n '[00m' # force color reset
|
