├── example
    ├── set-4.txt
    ├── set-1.txt
    ├── set-2.txt
    └── set-3.txt
├── package.json
├── LICENSE
├── bin
    └── setop
└── README.md


/example/set-4.txt:
--------------------------------------------------------------------------------
1 | mno
2 | pqr
3 | stu
4 | 


--------------------------------------------------------------------------------
/example/set-1.txt:
--------------------------------------------------------------------------------
1 | abc
2 | def
3 | ghi
4 | def
5 | 


--------------------------------------------------------------------------------
/example/set-2.txt:
--------------------------------------------------------------------------------
1 | def
2 | ghi
3 | ghi
4 | abc
5 | 


--------------------------------------------------------------------------------
/example/set-3.txt:
--------------------------------------------------------------------------------
1 | abc
2 | xyz
3 | def
4 | ghi
5 | 


--------------------------------------------------------------------------------
/package.json:
--------------------------------------------------------------------------------
 1 | {
 2 |   "name": "setop",
 3 |   "version": "0.1.0",
 4 |   "preferGlobal": true,
 5 |   "description": "A Bash script to perform set operations in the UNIX shell!",
 6 |   "bin": "bin/setop",
 7 |   "homepage": "https://github.com/cdax/setop",
 8 |   "keywords": ["set", "bash", "script"],
 9 |   "license": "MIT",
10 |   "author": "Chitharanjan Das <das.chitharanjan@gmail.com>",
11 |   "files": ["bin"]
12 | }
13 | 


--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
 1 | The MIT License (MIT)
 2 | 
 3 | Copyright (c) 2016 Chitharanjan Das
 4 | 
 5 | Permission is hereby granted, free of charge, to any person obtaining a copy
 6 | of this software and associated documentation files (the "Software"), to deal
 7 | in the Software without restriction, including without limitation the rights
 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 9 | copies of the Software, and to permit persons to whom the Software is
10 | furnished to do so, subject to the following conditions:
11 | 
12 | The above copyright notice and this permission notice shall be included in all
13 | copies or substantial portions of the Software.
14 | 
15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21 | SOFTWARE.
22 | 


--------------------------------------------------------------------------------
/bin/setop:
--------------------------------------------------------------------------------
  1 | #!/bin/bash
  2 | #
  3 | # Perform set operations in the UNIX shell!
  4 | 
  5 | PROGNAME=${0##*/}
  6 | VERSION="0.1.0"
  7 | 
  8 | usage()
  9 | {
 10 |   cat <<EO
 11 | Usage: $PROGNAME <cmd> <args>
 12 | Perform set operations in the UNIX shell!
 13 | Commands:
 14 | EO
 15 | cat <<EO | column -s\& -t
 16 |   help                          & Shows this help
 17 |   is-member <kwd> <set1> ... <setn>  & Tests whether the line set1 is present in the file set2
 18 |   equals <set1> <set2>          & Tests whether the unique lines in file set1 are the same as the unique lines in set2
 19 |   count <set1> <set2> ... <setn> & Counts the number of unique lines in files set1, set2, ..., setn combined
 20 |   is-subset <base> <set1> ... <setn> & Tests whether all lines in file base are present in files set1, ..., setn combined
 21 |   union <set1> <set2> ... <setn> & Displays all unique lines that are present in files set1, set2, ..., setn combined
 22 |   inter <set1> <set2>          & Displays all unique lines that are common to files set1 and set2
 23 |   minus <set1> <set2>          & Displays all unique lines in file set1 that are not present in file set2
 24 |   sym-diff <set1> <set2> ... <setn> & Displays all unique lines that are present in either files set1 or set2 ... or setn, but not in all of them
 25 |   product <set1> <set2>          & Displays the cartesian product of the unique lines from files set1 and set2
 26 |   is-disjoint <set1> <set2>          & Tests whether there are any lines common to both files set1 and set2
 27 |   is-empty <set1> <set2> ... <setn> & Tests whether there are any lines in files set1, set2, ..., setn combined
 28 |   min <set1> <set2> ... <setn> & Displays the lexicographic minimum from among the lines in files set1, set2, ..., setn combined
 29 |   max <set1> <set2> ... <setn> & Displays the lexicographic maximum from among the lines in files set1, set2, ..., setn combined
 30 | EO
 31 | }
 32 | 
 33 | version() {
 34 |   cat <<EO
 35 | v$VERSION
 36 | EO
 37 | }
 38 | 
 39 | log_error_and_exit() {
 40 |   echo "setop: $1: $2" 1>&2; exit 1
 41 | }
 42 | 
 43 | is_not_empty() {
 44 |   head -1 "$@" | wc -l | awk {'print $1'}
 45 | }
 46 | 
 47 | is_empty() {
 48 |   head -1 "$@" | wc -l | awk {'print ($1 == 0 ? 1 : 0)'}
 49 | }
 50 | 
 51 | is_member() {
 52 |   kwd="$1"
 53 |   shift
 54 |   grep "$kwd" "$@" | is_not_empty
 55 | }
 56 | 
 57 | equals() {
 58 |   diff <(sort -u "$1") <(sort -u "$2") | is_empty
 59 | }
 60 | 
 61 | count() {
 62 |   sort -u "$@" | wc -l | awk {'print $1'}
 63 | }
 64 | 
 65 | is_subset() {
 66 |   base="$1"
 67 |   shift
 68 |   comm -23 <(sort -u "$base") <(sort -u "$@") | is_empty
 69 | }
 70 | 
 71 | union() {
 72 |   sort -u "$@"
 73 | }
 74 | 
 75 | inter() {
 76 |   comm -12 <(sort -u "$1") <(sort -u "$2")
 77 | }
 78 | 
 79 | minus() {
 80 |   comm -23 <(sort -u "$1") <(sort -u "$2")
 81 | }
 82 | 
 83 | sym_diff() {
 84 |   sort "$@" | uniq -u
 85 | }
 86 | 
 87 | product() {
 88 |   awk 'NR==FNR { a[$0]; next } { for (i in a) print i, $0 }' <(sort -u "$1") <(sort -u "$2")
 89 | }
 90 | 
 91 | is_disjoint() {
 92 |   inter "$1" "$2" | is_empty
 93 | }
 94 | 
 95 | min() {
 96 |   sort "$@" | head -1
 97 | }
 98 | 
 99 | max() {
100 |   sort "$@" | tail -1
101 | }
102 | 
103 | CMD="$1"
104 | case $CMD in
105 |   -h|--help|help)
106 |     usage; exit 0
107 |     ;;
108 |   -v|--version|version)
109 |     version; exit 0
110 |     ;;
111 |   is-member)
112 |     kwd="$2"
113 |     shift 2
114 |     is_member "$kwd" "$@"
115 |     ;;
116 |   equals)
117 |     equals "$2" "$3"
118 |     ;;
119 |   count)
120 |     shift; count "$@"
121 |     ;;
122 |   is-subset)
123 |     base="$2"
124 |     shift 2
125 |     is_subset "$base" "$@"
126 |     ;;
127 |   union)
128 |     shift; union "$@"
129 |     ;;
130 |   inter)
131 |     inter "$2" "$3"
132 |     ;;
133 |   minus)
134 |     minus "$2" "$3"
135 |     ;;
136 |   sym-diff)
137 |     shift; sym_diff "$@"
138 |     ;;
139 |   product)
140 |     product "$2" "$3"
141 |     ;;
142 |   is-disjoint)
143 |     is_disjoint "$2" "$3"
144 |     ;;
145 |   is-empty)
146 |     shift; is_empty "$@"
147 |     ;;
148 |   min)
149 |     shift; min "$@"
150 |     ;;
151 |   max)
152 |     shift; max "$@"
153 |     ;;
154 |   *)
155 |     log_error_and_exit "$CMD" "Unknown command"
156 |     ;;
157 | esac
158 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
  1 | setop
  2 | -----
  3 | 
  4 | **Set** **op**erations in the UNIX shell!
  5 | 
  6 | Resting on the shoulders of giants like `grep`, `cat`, `sort`, `uniq`, `comm`, `diff`, `cut`, `awk`, and more.
  7 | 
  8 | ## Installation
  9 | 
 10 | Using `npm`:
 11 | 
 12 |     $ npm install -g setop
 13 | 
 14 | ..or, copy the [script](https://raw.githubusercontent.com/cdax/setop/master/bin/setop) to a file called `setop`, give it the proper permissions, and move it to somewhere in your PATH, like so:
 15 | 
 16 |     $ chmod u+x setop
 17 |     $ mv setop /usr/local/bin
 18 | 
 19 | ## Usage
 20 | 
 21 | * [Membership Test](#is-member)
 22 | * [Equality Test](#equals)
 23 | * [Cardinality](#count)
 24 | * [Subset Test](#is-subset)
 25 | * [Union](#union)
 26 | * [Intersection](#inter)
 27 | * [Complement](#minus)
 28 | * [Symmetric Difference](#sym-diff)
 29 | * [Cartesian Product](#product)
 30 | * [Disjoint Sets Test](#are-disjoint)
 31 | * [Empty Set Test](#is-empty)
 32 | * [Minimum Element](#min)
 33 | * [Maximum Element](#max)
 34 | 
 35 | #### <a name="is-member"></a>Membership Test
 36 | 
 37 |     $ setop is-member <kwd> <set1> <set2> ... <setn>
 38 | 
 39 | >Tests whether the line `kwd` is present in the files `set1`, `set2`, ..., `setn`.
 40 | 
 41 | For example:
 42 | 
 43 |     $ setop is-member abc set-1.txt
 44 |     1
 45 |     $ setop is-member mno set-1.txt set-2.txt set-3.txt
 46 |     0
 47 |     $ setop is-member xyz set-*.txt
 48 |     1
 49 | 
 50 | `set-1.txt`
 51 | 
 52 |     abc
 53 |     def
 54 |     abc
 55 |     ghi
 56 | 
 57 | `set-2.txt`
 58 | 
 59 |     def
 60 |     ghi
 61 |     ghi
 62 |     abc
 63 | 
 64 | `set-3.txt`
 65 | 
 66 |     abc
 67 |     xyz
 68 |     def
 69 |     ghi
 70 | 
 71 | #### <a name="equals"></a>Equality Test
 72 | 
 73 |     $ setop equals <set1> <set2>
 74 | 
 75 | >Tests whether the unique lines in file `set1` are the same as the unique lines in `set2`.
 76 | 
 77 | For example:
 78 | 
 79 |     $ setop equals set-1.txt set-2.txt
 80 |     1
 81 |     $ setop equals set-1.txt set-3.txt
 82 |     0
 83 | 
 84 | `set-1.txt`
 85 | 
 86 |     abc
 87 |     def
 88 |     ghi
 89 |     def
 90 | 
 91 | `set-2.txt`
 92 | 
 93 |     def
 94 |     ghi
 95 |     ghi
 96 |     abc
 97 | 
 98 | `set-3.txt`
 99 | 
100 |     abc
101 |     xyz
102 |     def
103 |     ghi
104 | 
105 | 
106 | #### <a name="count"></a>Cardinality
107 | 
108 |     $ setop count <set1> <set2> ... <setn>
109 | 
110 | >Counts the number of unique lines in files `set1`, `set2`, ..., `setn` combined.
111 | 
112 | For example:
113 | 
114 |     $ setop count set-1.txt
115 |     3
116 |     $ setop count set-1.txt set-2.txt set-3.txt
117 |     4
118 |     $ setop count set-*.txt
119 |     4
120 | 
121 | `set-1.txt`
122 | 
123 |     abc
124 |     def
125 |     ghi
126 |     def
127 | 
128 | `set-2.txt`
129 | 
130 |     def
131 |     ghi
132 |     ghi
133 |     abc
134 | 
135 | `set-3.txt`
136 | 
137 |     abc
138 |     xyz
139 |     def
140 |     ghi
141 | 
142 | #### <a name="is-subset"></a>Subset Test
143 | 
144 |     $ setop is-subset <base> <set1> <set2> ... <setn>
145 | 
146 | >Tests whether all lines in file `base` are present in files `set1`, `set2`, ..., `setn` combined
147 | 
148 | For example:
149 | 
150 |     $ setop is-subset set-3.txt set-1.txt
151 |     0
152 |     $ setop is-subset set-3.txt set-2.txt set-3.txt
153 |     1
154 |     $ setop is-subset set-3.txt set-*.txt
155 |     1
156 | 
157 | `set-1.txt`
158 | 
159 |     abc
160 | 
161 |     def
162 |     ghi
163 |     def
164 | 
165 | `set-2.txt`
166 | 
167 |     def
168 |     ghi
169 |     ghi
170 |     abc
171 | 
172 | `set-3.txt`
173 | 
174 |     abc
175 |     xyz
176 |     def
177 |     ghi
178 | 
179 | #### <a name="union"></a>Union
180 | 
181 |     $ setop union <set1> <set2> ... <setn>
182 | 
183 | >Displays all unique lines that are present in files `set1`, `set2`, ..., `setn` combined
184 | 
185 | For example:
186 | 
187 |     $ setop union set-1.txt set-2.txt
188 |     abc
189 |     def
190 |     ghi
191 |     $ setop union set-1.txt set-2.txt set-3.txt
192 |     abc
193 |     def
194 |     ghi
195 |     xyz
196 |     $ setop union set-*.txt
197 |     abc
198 |     def
199 |     ghi
200 |     xyz
201 | 
202 | `set-1.txt`
203 | 
204 |     abc
205 |     def
206 |     ghi
207 |     def
208 | 
209 | `set-2.txt`
210 | 
211 |     def
212 |     ghi
213 |     ghi
214 |     abc
215 | 
216 | `set-3.txt`
217 | 
218 |     abc
219 |     xyz
220 |     def
221 |     ghi
222 | 
223 | #### <a name="inter"></a>Intersection
224 | 
225 |     $ setop inter <set1> <set2>
226 | 
227 | >Displays all unique lines that are common to files `set1` and `set2`
228 | 
229 | For example:
230 | 
231 |     $ setop inter set-1.txt set-2.txt
232 |     abc
233 |     def
234 |     ghi
235 |     $ setop inter set-1.txt set-3.txt
236 |     abc
237 |     def
238 |     ghi
239 | 
240 | `set-1.txt`
241 | 
242 |     abc
243 |     def
244 |     ghi
245 |     def
246 | 
247 | `set-2.txt`
248 | 
249 |     def
250 |     ghi
251 |     ghi
252 |     abc
253 | 
254 | `set-3.txt`
255 | 
256 |     abc
257 |     xyz
258 |     def
259 |     ghi
260 | 
261 | #### <a name="minus"></a>Complement
262 | 
263 |     $ setop minus <set1> <set2>
264 | 
265 | >Displays all unique lines in file `set1` that are not present in file `set2`
266 | 
267 | For example:
268 | 
269 |     $ setop minus set-1.txt set-2.txt
270 |     $ setop minus set-3.txt set-2.txt
271 |     xyz
272 | 
273 | `set-1.txt`
274 | 
275 |     abc
276 |     def
277 |     ghi
278 |     def
279 | 
280 | `set-2.txt`
281 | 
282 |     def
283 |     ghi
284 |     ghi
285 |     abc
286 | 
287 | `set-3.txt`
288 | 
289 |     abc
290 |     xyz
291 |     def
292 |     ghi
293 | 
294 | #### <a name="sym-diff"></a>Symmetric Difference
295 | 
296 |     $ setop sym-diff <set1> <set2> ... <setn>
297 | 
298 | >Displays all unique lines that are present in either files `set1` or `set2` ... or `setn`, but not in all of them
299 | 
300 | For example:
301 | 
302 |     $ setop sym-diff set-1.txt set-2.txt
303 |     $ setop sym-diff set-1.txt set-2.txt set-3.txt
304 |     xyz
305 |     $ setop sym-diff set-*.txt
306 |     xyz
307 | 
308 | `set-1.txt`
309 | 
310 |     abc
311 |     def
312 |     ghi
313 |     def
314 | 
315 | `set-2.txt`
316 | 
317 |     def
318 |     ghi
319 |     ghi
320 |     abc
321 | 
322 | `set-3.txt`
323 | 
324 |     abc
325 |     xyz
326 |     def
327 |     ghi
328 | 
329 | #### <a name="product"></a>Cartesian Product
330 | 
331 |     $ setop product <set1> <set2>
332 | 
333 | >Displays the cartesian product of the unique lines from files `set1` and `set2`
334 | 
335 | For example:
336 | 
337 |     $ setop product set-1.txt set-2.txt
338 |     abc abc
339 |     ghi abc
340 |     def abc
341 |     abc def
342 |     ghi def
343 |     def def
344 |     abc ghi
345 |     ghi ghi
346 |     def ghi
347 |     $ setop product set-2.txt set-3.txt
348 |     abc abc
349 |     ghi abc
350 |     def abc
351 |     abc def
352 |     ghi def
353 |     def def
354 |     abc ghi
355 |     ghi ghi
356 |     def ghi
357 |     abc xyz
358 |     ghi xyz
359 |     def xyz
360 | 
361 | `set-1.txt`
362 | 
363 |     abc
364 |     def
365 |     ghi
366 |     def
367 | 
368 | `set-2.txt`
369 | 
370 |     def
371 |     ghi
372 |     ghi
373 |     abc
374 | 
375 | `set-3.txt`
376 | 
377 |     abc
378 |     xyz
379 |     def
380 |     ghi
381 | 
382 | #### <a name="is-disjoint"></a>Disjoint Sets Test
383 | 
384 |     $ setop is-disjoint <set1> <set2>
385 | 
386 | >Tests whether there are any lines common to both files `set1` and `set2`
387 | 
388 | For example:
389 | 
390 |     $ setop is-disjoint set-1.txt set-2.txt
391 |     0
392 |     $ setop is-disjoint set-2.txt set-3.txt
393 |     0
394 |     $ setop is-disjoint set-3.txt set-4.txt
395 |     1
396 | 
397 | `set-1.txt`
398 | 
399 |     abc
400 |     def
401 |     ghi
402 |     def
403 | 
404 | `set-2.txt`
405 | 
406 |     def
407 |     ghi
408 |     ghi
409 |     abc
410 | 
411 | `set-3.txt`
412 | 
413 |     abc
414 |     xyz
415 |     def
416 |     ghi
417 | 
418 | `set-4.txt`
419 | 
420 |     mno
421 |     pqr
422 |     stu
423 | 
424 | #### <a name="is-empty"></a>Empty Set Test
425 | 
426 |     $ setop is-empty <set1> <set2> ... <setn>
427 | 
428 | >Tests whether there are any lines in files `set1`, `set2`, ..., `setn` combined
429 | 
430 | For example:
431 | 
432 |     $ setop is-empty set-1.txt
433 |     0
434 |     $ setop is-empty <(setop sym-diff set-1.txt set-2.txt)
435 |     1
436 | 
437 | `set-1.txt`
438 | 
439 |     abc
440 |     def
441 |     ghi
442 |     def
443 | 
444 | `set-2.txt`
445 | 
446 |     def
447 |     ghi
448 |     ghi
449 |     abc
450 | 
451 | #### <a name="min"></a>Minimum Element
452 | 
453 |     $ setop min <set1> <set2> ... <setn>
454 | 
455 | >Displays the lexicographic minimum from among the lines in files `set1`, `set2`, ..., `setn` combined
456 | 
457 | For example:
458 | 
459 |     $ setop min set-4.txt
460 |     mno
461 |     $ setop min set-1.txt set-4.txt
462 |     abc
463 | 
464 | `set-1.txt`
465 | 
466 |     abc
467 |     def
468 |     ghi
469 |     def
470 | 
471 | `set-4.txt`
472 | 
473 |     mno
474 |     pqr
475 |     stu
476 | 
477 | #### <a name="max"></a>Maximum Element
478 | 
479 |     $ setop max <set1> <set2> ... <setn>
480 | 
481 | >Displays the lexicographic maximum from among the lines in files `set1`, `set2`, ..., `setn` combined
482 | 
483 | For example:
484 | 
485 |     $ setop min set-1.txt
486 |     ghi
487 |     $ setop min set-1.txt set-3.txt
488 |     xyz
489 | 
490 | `set-1.txt`
491 | 
492 |     abc
493 |     def
494 |     ghi
495 |     def
496 | 
497 | `set-3.txt`
498 | 
499 |     abc
500 |     xyz
501 |     def
502 |     ghi
503 | 
504 | 
505 | ## Credits
506 | 
507 | Many of the bash one-liners that are part of this project were found at a [post on Peter Krumin's blog](//www.catonmat.net/blog/set-operations-in-unix-shell/). I've been using them for years and I finally decided to put it all together in one script, with easy-to-remember command names.
508 | 
509 | ## Support
510 | 
511 | Please [open an issue](https://github.com/cdax/setop/issues/new) for support.
512 | 


--------------------------------------------------------------------------------