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
#!/bin/bash
# 2009-2010, 2012, 2017 Etersoft www.etersoft.ru
# Author: Vitaly Lipatov <lav@etersoft.ru>
# Public domain
# TODO: rewrite with shell commands, perl or C
# Python - http://www.linuxtopia.org/online_books/programming_books/python_programming/python_ch16s03.html
# Shell - http://linux.byexamples.com/archives/127/uniq-and-basic-set-theory/
# - http://maiaco.com/articles/shellSetOperations.php
# Perl - http://docstore.mik.ua/orelly/perl/cookbook/ch04_09.htm
# - http://blogs.perl.org/users/polettix/2012/03/sets-operations.html
# http://rosettacode.org/wiki/Symmetric_difference
# TODO: add unit tests
# http://ru.wikipedia.org/wiki/Операции_над_множествами
# Base set operations:
# * union
# "1 2 3" "3 4 5" -> "1 2 3 4 5"
# * intersection
# "1 2 3" "3 4 5" -> "3"
# * relative complement (substracted, difference) ( A ? B – members in A but not in B )
# http://en.wikipedia.org/wiki/Complement_%28set_theory%29
# "1 3" "1 2 3 4" -> "2 4"
# * symmetric difference (симметричная разность) ( A ^ B – members in A or B but not both )
# http://en.wikipedia.org/wiki/Symmetric_difference
# "1 2 3" "3 4 5" -> "1 2 4 5"
filter_strip_spaces()
{
# possible use just
#xargs echo
sed -e "s| \+| |g" -e "s|^ ||" -e "s| \$||"
}
strip_spaces()
{
echo "$*" | filter_strip_spaces
}
isempty()
{
[ "$(strip_spaces "$*")" = "" ]
}
list()
{
local i
for i in $@ ; do
echo "$i"
done
}
count()
{
list $@ | wc -l
}
union()
{
strip_spaces $(list $@ | sort -u)
}
uniq()
{
union $@
}
has()
{
local wd="$1"
shift
echo "$*" | grep -q -- "$wd"
}
# Note: used egrep! write '[0-9]+(first|two)', not '[0-9]\+...'
match()
{
local wd="$1"
shift
echo "$*" | egrep -q -- "$wd"
}
# remove_from_list "1." "11 12 21 22" -> "21 22"
reg_remove()
{
local i
local RES=
for i in $2 ; do
echo "$i" | grep -q "$1" || RES="$RES $i"
done
strip_spaces "$RES"
}
# remove_from_list "1." "11 12 21 22" -> "21 22"
reg_wordremove()
{
local i
local RES=
for i in $2 ; do
echo "$i" | grep -q -w "$1" || RES="$RES $i"
done
strip_spaces "$RES"
}
# Args: LIST1 LIST2
# do_exclude_list print LIST2 list exclude fields contains also in LIST1
# Example: exclude "1 3" "1 2 3 4" -> "2 4"
exclude()
{
local i
local RES=
for i in $2 ; do
echo "$1" | grep -q -w "$i" || RES="$RES $i"
done
strip_spaces "$RES"
}
# regexclude_list "22 1." "11 12 21 22" -> "21"
reg_exclude()
{
local i
local RES="$2"
for i in $1 ; do
RES=$(reg_remove "$i" "$RES")
done
strip_spaces "$RES"
}
# regexclude_list "22 1." "11 12 21 22" -> "21"
reg_wordexclude()
{
local i
local RES="$2"
for i in $1 ; do
RES=$(reg_wordremove "$i" "$RES")
done
strip_spaces "$RES"
}
# FIXME:
# reg_include "1." "11 12 21 22" -> "11 12"
reg_include()
{
local i
local RES=
for i in $2 ; do
echo "$i" | grep -q -w "$1" && RES="$RES $i"
done
strip_spaces "$RES"
}
example()
{
local CMD="$1"
local ARG1="$2"
shift 2
echo "\$ $0 $CMD \"$ARG1\" \"$@\""
$0 $CMD "$ARG1" "$@"
}
example_res()
{
example "$@" && echo TRUE || echo FALSE
}
help()
{
echo "estrlist developed for string list operations. See also cut, join, paste..."
echo "Usage: $0 <command> [args]"
echo "Commands:"
echo " strip_spaces [args] - remove spaces between words"
echo " filter_strip_spaces - remove spaces from words from standart input"
echo " reg_remove <PATTERN> [word list] - remove words containing a match to the given PATTERN (grep notation)"
echo " reg_wordremove <PATTERN> [word list] - remove words containing a match to the given PATTERN (grep -w notation)"
echo " exclude <list1> <list2> - print list2 words exclude list1 items"
echo " reg_exclude <PATTERN> [word list] - print only words do not matched with PATTERN"
echo " reg_wordexclude <PATTERN> [word list] - print only words do not matched with PATTERN"
echo " has <PATTERN> string - check the string for a match to the regular expression given in PATTERN (grep notation)"
echo " match <PATTERN> string - check the string for a match to the regular expression given in PATTERN (egrep notation)"
echo " isempty [string] - true if string has no any symbols (only zero or more spaces)"
echo " union [word list] - sort and remove duplicates"
echo " uniq [word list] - alias for union"
echo " list [word list] - just list words line by line"
echo " count [word list] - print word count"
echo
echo "Examples:"
example reg_remove "1." "11 12 21 22"
example reg_wordremove "1." "11 12 21 22"
example exclude "1 3" "1 2 3 4"
example reg_exclude "22 1." "11 12 21 22"
example reg_wordexclude "wo.* er" "work were more else"
example union "1 2 2 3 3"
example count "1 2 3 4 10"
example_res isempty " "
#example_res isempty " 1 "
example_res has ex "exactly"
example_res has exo "exactly"
example_res match "M[0-9]+" "M250"
example_res match "M[0-9]+" "MI"
}
COMMAND="$1"
if [ -z "$COMMAND" ] ; then
echo "Run with --help for get command description."
exit 1
fi
if [ "$COMMAND" = "-h" ] || [ "$COMMAND" = "--help" ] ; then
COMMAND="help"
fi
shift
# FIXME: do to call function directly, use case instead?
if [ "$1" = "-" ] ; then
shift
"$COMMAND" "$(cat) $@"
elif [ "$2" = "-" ] ; then
"$COMMAND" "$1" "$(cat)"
else
"$COMMAND" "$@"
fi