Mercurial > hg > octave-nkf
annotate scripts/strings/findstr.m @ 18015:fe59ef0084a6
maint: Periodic merge of stable to default.
| author | Rik <rik@octave.org> |
|---|---|
| date | Mon, 25 Nov 2013 22:25:35 -0800 |
| parents | d63878346099 |
| children | f9959972949a |
| rev | line source |
|---|---|
|
17744
d63878346099
maint: Update copyright notices for release.
John W. Eaton <jwe@octave.org>
parents:
14363
diff
changeset
|
1 ## Copyright (C) 1996-2013 Kurt Hornik |
| 2325 | 2 ## |
| 2313 | 3 ## This file is part of Octave. |
| 4 ## | |
| 5 ## Octave is free software; you can redistribute it and/or modify it | |
| 6 ## under the terms of the GNU General Public License as published by | |
| 7016 | 7 ## the Free Software Foundation; either version 3 of the License, or (at |
| 8 ## your option) any later version. | |
| 2313 | 9 ## |
| 10 ## Octave is distributed in the hope that it will be useful, but | |
| 11 ## WITHOUT ANY WARRANTY; without even the implied warranty of | |
| 12 ## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU | |
| 13 ## General Public License for more details. | |
| 14 ## | |
| 15 ## You should have received a copy of the GNU General Public License | |
| 7016 | 16 ## along with Octave; see the file COPYING. If not, see |
| 17 ## <http://www.gnu.org/licenses/>. | |
| 2272 | 18 |
| 3361 | 19 ## -*- texinfo -*- |
|
13177
17b702fae303
findstr.m: Use more modern code practices in function.
Rik <octave@nomad.inbox5.com>
parents:
11587
diff
changeset
|
20 ## @deftypefn {Function File} {} findstr (@var{s}, @var{t}) |
|
17b702fae303
findstr.m: Use more modern code practices in function.
Rik <octave@nomad.inbox5.com>
parents:
11587
diff
changeset
|
21 ## @deftypefnx {Function File} {} findstr (@var{s}, @var{t}, @var{overlap}) |
| 3361 | 22 ## Return the vector of all positions in the longer of the two strings |
| 23 ## @var{s} and @var{t} where an occurrence of the shorter of the two starts. | |
|
13177
17b702fae303
findstr.m: Use more modern code practices in function.
Rik <octave@nomad.inbox5.com>
parents:
11587
diff
changeset
|
24 ## If the optional argument @var{overlap} is true, the returned vector |
|
10821
693e22af08ae
Grammarcheck documentation of m-files
Rik <octave@nomad.inbox5.com>
parents:
10549
diff
changeset
|
25 ## can include overlapping positions (this is the default). For example: |
| 3426 | 26 ## |
| 3361 | 27 ## @example |
|
8442
502e58a0d44f
Fix docstrings, add examples, references and tests to string functions
Thorsten Meyer <thorsten.meyier@gmx.de>
parents:
7411
diff
changeset
|
28 ## @group |
| 3361 | 29 ## findstr ("ababab", "a") |
|
13177
17b702fae303
findstr.m: Use more modern code practices in function.
Rik <octave@nomad.inbox5.com>
parents:
11587
diff
changeset
|
30 ## @result{} [1, 3, 5]; |
| 3361 | 31 ## findstr ("abababa", "aba", 0) |
|
8442
502e58a0d44f
Fix docstrings, add examples, references and tests to string functions
Thorsten Meyer <thorsten.meyier@gmx.de>
parents:
7411
diff
changeset
|
32 ## @result{} [1, 5] |
|
502e58a0d44f
Fix docstrings, add examples, references and tests to string functions
Thorsten Meyer <thorsten.meyier@gmx.de>
parents:
7411
diff
changeset
|
33 ## @end group |
| 3361 | 34 ## @end example |
|
13177
17b702fae303
findstr.m: Use more modern code practices in function.
Rik <octave@nomad.inbox5.com>
parents:
11587
diff
changeset
|
35 ## |
|
17b702fae303
findstr.m: Use more modern code practices in function.
Rik <octave@nomad.inbox5.com>
parents:
11587
diff
changeset
|
36 ## @strong{Caution:} @code{findstr} is scheduled for deprecation. Use |
|
17b702fae303
findstr.m: Use more modern code practices in function.
Rik <octave@nomad.inbox5.com>
parents:
11587
diff
changeset
|
37 ## @code{strfind} in all new code. |
|
8442
502e58a0d44f
Fix docstrings, add examples, references and tests to string functions
Thorsten Meyer <thorsten.meyier@gmx.de>
parents:
7411
diff
changeset
|
38 ## @seealso{strfind, strmatch, strcmp, strncmp, strcmpi, strncmpi, find} |
| 3361 | 39 ## @end deftypefn |
| 2272 | 40 |
| 3891 | 41 ## Note that this implementation swaps the strings if second one is longer |
| 42 ## than the first, so try to put the longer one first. | |
| 43 ## | |
| 5428 | 44 ## Author: Kurt Hornik <Kurt.Hornik@wu-wien.ac.at> |
| 2355 | 45 ## Adapted-By: jwe |
| 2314 | 46 |
|
13177
17b702fae303
findstr.m: Use more modern code practices in function.
Rik <octave@nomad.inbox5.com>
parents:
11587
diff
changeset
|
47 function v = findstr (s, t, overlap = true) |
| 2275 | 48 |
| 49 if (nargin < 2 || nargin > 3) | |
| 6046 | 50 print_usage (); |
| 2275 | 51 endif |
| 52 | |
| 5348 | 53 if (all (size (s) > 1) || all (size (t) > 1)) |
| 54 error ("findstr: arguments must have only one non-singleton dimension"); | |
| 3891 | 55 endif |
| 56 | |
| 57 ## Make S be the longer string. | |
| 58 if (length (s) < length (t)) | |
|
13177
17b702fae303
findstr.m: Use more modern code practices in function.
Rik <octave@nomad.inbox5.com>
parents:
11587
diff
changeset
|
59 [s, t] = deal (t, s); |
| 3891 | 60 endif |
|
11587
c792872f8942
all script files: untabify and strip trailing whitespace
John W. Eaton <jwe@octave.org>
parents:
11523
diff
changeset
|
61 |
| 3891 | 62 l_s = length (s); |
| 63 l_t = length (t); | |
|
11587
c792872f8942
all script files: untabify and strip trailing whitespace
John W. Eaton <jwe@octave.org>
parents:
11523
diff
changeset
|
64 |
| 3891 | 65 if (l_t == 0) |
| 4321 | 66 ## zero length target: return empty set |
| 67 v = []; | |
|
11587
c792872f8942
all script files: untabify and strip trailing whitespace
John W. Eaton <jwe@octave.org>
parents:
11523
diff
changeset
|
68 |
| 3891 | 69 elseif (l_t == 1) |
| 70 ## length one target: simple find | |
| 71 v = find (s == t); | |
|
11587
c792872f8942
all script files: untabify and strip trailing whitespace
John W. Eaton <jwe@octave.org>
parents:
11523
diff
changeset
|
72 |
| 3891 | 73 elseif (l_t == 2) |
| 74 ## length two target: find first at i and second at i+1 | |
| 75 v = find (s(1:l_s-1) == t(1) & s(2:l_s) == t(2)); | |
|
11587
c792872f8942
all script files: untabify and strip trailing whitespace
John W. Eaton <jwe@octave.org>
parents:
11523
diff
changeset
|
76 |
| 3891 | 77 else |
| 78 ## length three or more: match the first three by find then go through | |
| 79 ## the much smaller list to determine which of them are real matches | |
| 80 limit = l_s - l_t + 1; | |
| 81 v = find (s(1:limit) == t(1) | |
| 10549 | 82 & s(2:limit+1) == t(2) |
| 83 & s (3:limit+2) == t(3)); | |
| 3891 | 84 endif |
| 3759 | 85 |
| 3891 | 86 ## Need to search the index vector if our find was too short |
| 87 ## (target length > 3), or if we don't allow overlaps. Note though | |
| 88 ## that there cannot be any overlaps if the first character in the | |
| 89 ## target is different from the remaining characters in the target, | |
| 90 ## so a single character, two different characters, or first character | |
| 91 ## different from the second two don't need to be searched. | |
| 92 if (l_t >= 3 || (! overlap && l_t > 1 && any (t(1) == t(2:l_t)))) | |
| 93 ## force strings to be both row vectors or both column vectors | |
| 94 if (all (size (s) != size (t))) | |
| 95 t = t.'; | |
| 96 endif | |
|
11587
c792872f8942
all script files: untabify and strip trailing whitespace
John W. Eaton <jwe@octave.org>
parents:
11523
diff
changeset
|
97 |
| 3891 | 98 ## determine which ones to keep |
| 99 keep = zeros (size (v)); | |
| 100 ind = 0:l_t-1; | |
| 101 if (overlap) | |
| 102 for idx = 1:length (v) | |
| 10549 | 103 keep(idx) = all (s(v(idx) + ind) == t); |
| 3891 | 104 endfor |
| 2272 | 105 else |
| 8506 | 106 ## First possible position for next non-overlapping match. |
| 107 next = 1; | |
| 3891 | 108 for idx = 1:length (v) |
| 10549 | 109 if (v(idx) >= next && s(v(idx) + ind) == t) |
| 110 keep(idx) = 1; | |
| 111 ## Skip to the next possible match position. | |
| 112 next = v(idx) + l_t; | |
| 113 else | |
| 114 keep(idx) = 0; | |
| 115 endif | |
| 3891 | 116 endfor |
| 2272 | 117 endif |
| 3891 | 118 if (! isempty (v)) |
| 119 v = v(find (keep)); | |
| 120 endif | |
| 121 endif | |
| 5400 | 122 |
| 123 if (isempty (v)) | |
| 124 v = []; | |
| 125 endif | |
| 126 | |
|
13177
17b702fae303
findstr.m: Use more modern code practices in function.
Rik <octave@nomad.inbox5.com>
parents:
11587
diff
changeset
|
127 ## Always return a row vector, because that's what the old one did. |
|
17b702fae303
findstr.m: Use more modern code practices in function.
Rik <octave@nomad.inbox5.com>
parents:
11587
diff
changeset
|
128 if (iscolumn (v)) |
| 3891 | 129 v = v.'; |
| 2272 | 130 endif |
| 131 | |
| 132 endfunction | |
| 7411 | 133 |
|
13177
17b702fae303
findstr.m: Use more modern code practices in function.
Rik <octave@nomad.inbox5.com>
parents:
11587
diff
changeset
|
134 |
|
17b702fae303
findstr.m: Use more modern code practices in function.
Rik <octave@nomad.inbox5.com>
parents:
11587
diff
changeset
|
135 %!assert (findstr ("abababa", "a"), [1, 3, 5, 7]) |
|
14363
f3d52523cde1
Use Octave coding conventions in all m-file %!test blocks
Rik <octave@nomad.inbox5.com>
parents:
14138
diff
changeset
|
136 %!assert (findstr ("abababa", "aba"), [1, 3, 5]) |
|
f3d52523cde1
Use Octave coding conventions in all m-file %!test blocks
Rik <octave@nomad.inbox5.com>
parents:
14138
diff
changeset
|
137 %!assert (findstr ("aba", "abababa", 0), [1, 5]) |
| 7411 | 138 |
|
13177
17b702fae303
findstr.m: Use more modern code practices in function.
Rik <octave@nomad.inbox5.com>
parents:
11587
diff
changeset
|
139 %% Test input validation |
|
17b702fae303
findstr.m: Use more modern code practices in function.
Rik <octave@nomad.inbox5.com>
parents:
11587
diff
changeset
|
140 %!error findstr () |
|
14363
f3d52523cde1
Use Octave coding conventions in all m-file %!test blocks
Rik <octave@nomad.inbox5.com>
parents:
14138
diff
changeset
|
141 %!error findstr ("foo", "bar", 3, 4) |
|
f3d52523cde1
Use Octave coding conventions in all m-file %!test blocks
Rik <octave@nomad.inbox5.com>
parents:
14138
diff
changeset
|
142 %!error <must have only one non-singleton dimension> findstr (["AB" ; "CD"], "C") |
| 7411 | 143 |