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
|
########################################################################
##
## Copyright (C) 1996-2024 The Octave Project Developers
##
## See the file COPYRIGHT.md in the top-level directory of this
## distribution or <https://octave.org/copyright/>.
##
## This file is part of Octave.
##
## Octave 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.
##
## Octave 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 Octave; see the file COPYING. If not, see
## <https://www.gnu.org/licenses/>.
##
########################################################################
## -*- texinfo -*-
## @deftypefn {} {@var{v} =} findstr (@var{s}, @var{t})
## @deftypefnx {} {@var{v} =} findstr (@var{s}, @var{t}, @var{overlap})
##
## This function is obsolete. Use @code{strfind} instead.
##
## Return the vector of all positions in the longer of the two strings @var{s}
## and @var{t} where an occurrence of the shorter of the two starts.
##
## If the optional argument @var{overlap} is true (default), the returned
## vector can include overlapping positions. For example:
##
## @example
## @group
## findstr ("ababab", "a")
## @result{} [1, 3, 5];
## findstr ("abababa", "aba", 0)
## @result{} [1, 5]
## @end group
## @end example
##
## @strong{Caution:} @code{findstr} is obsolete. Use @code{strfind} in all new
## code.
## @seealso{strfind, strmatch, strcmp, strncmp, strcmpi, strncmpi, find}
## @end deftypefn
## Note that this implementation swaps the strings if second one is longer
## than the first, so try to put the longer one first.
function v = findstr (s, t, overlap = true)
persistent warned = false;
if (! warned)
warned = true;
warning ("Octave:legacy-function",
"findstr is obsolete; use strfind instead\n");
endif
if (nargin < 2)
print_usage ();
endif
if (all (size (s) > 1) || all (size (t) > 1))
error ("findstr: arguments must have only one non-singleton dimension");
endif
## Make S be the longer string.
if (length (s) < length (t))
[s, t] = deal (t, s);
endif
l_s = length (s);
l_t = length (t);
if (l_t == 0)
## zero length target: return empty set
v = [];
elseif (l_t == 1)
## length one target: simple find
v = find (s == t);
elseif (l_t == 2)
## length two target: find first at i and second at i+1
v = find (s(1:l_s-1) == t(1) & s(2:l_s) == t(2));
else
## length three or more: match the first three by find then go through
## the much smaller list to determine which of them are real matches
limit = l_s - l_t + 1;
v = find ( s(1:limit) == t(1)
& s(2:limit+1) == t(2)
& s(3:limit+2) == t(3));
endif
## Need to search the index vector if our find was too short
## (target length > 3), or if we don't allow overlaps. Note though
## that there cannot be any overlaps if the first character in the
## target is different from the remaining characters in the target,
## so a single character, two different characters, or first character
## different from the second two don't need to be searched.
if (l_t >= 3 || (! overlap && l_t > 1 && any (t(1) == t(2:l_t))))
## force strings to be both row vectors or both column vectors
if (all (size (s) != size (t)))
t = t.';
endif
## determine which ones to keep
keep = zeros (size (v));
ind = 0:l_t-1;
if (overlap)
for idx = 1:length (v)
keep(idx) = all (s(v(idx) + ind) == t);
endfor
else
## First possible position for next non-overlapping match.
next = 1;
for idx = 1:length (v)
if (v(idx) >= next && s(v(idx) + ind) == t)
keep(idx) = 1;
## Skip to the next possible match position.
next = v(idx) + l_t;
else
keep(idx) = 0;
endif
endfor
endif
if (! isempty (v))
v = v(find (keep));
endif
endif
if (isempty (v))
v = [];
endif
## Always return a row vector, because that's what the old one did.
if (iscolumn (v))
v = v.';
endif
endfunction
## First test is necessary to provoke 1-time legacy warning
%!test
%! warning ("off", "Octave:legacy-function", "local");
%! findstr ("", "");
%!assert (findstr ("abababa", "a"), [1, 3, 5, 7])
%!assert (findstr ("abababa", "aba"), [1, 3, 5])
%!assert (findstr ("aba", "abababa", 0), [1, 5])
## Test input validation
%!error <Invalid call> findstr ()
%!error <Invalid call> findstr ("str1")
%!error <must have only one non-singleton dimension> findstr (["AB" ; "CD"], "C")
|
