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
|
// Scilab ( http://www.scilab.org/ ) - This file is part of Scilab
// Copyright (C) DIGITEO - 2009 - Allan CORNET
//
// This file must be used under the terms of the CeCILL.
// This source file is licensed as described in the file COPYING, which
// you should have received as part of this distribution. The terms
// are also available at
// http://www.cecill.info/licences/Licence_CeCILL_V2-en.txt
function [strs, matched_separators] = %_strsplit(varargin)
//====== private macros ==================
function out_str = replace_regexp_char(in_str)
out_str = strsubst(in_str,'\','\\');
out_str = strsubst(out_str,'.','\.');
out_str = strsubst(out_str,'$','\$');
out_str = strsubst(out_str,'[','\[');
out_str = strsubst(out_str,']','\]');
out_str = strsubst(out_str,'(','\(');
out_str = strsubst(out_str,')','\)');
out_str = strsubst(out_str,'{','\{');
out_str = strsubst(out_str,'}','\}');
out_str = strsubst(out_str,'^','\^');
out_str = strsubst(out_str,'?','\?');
out_str = strsubst(out_str,'*','\*');
out_str = strsubst(out_str,'+','\+');
out_str = strsubst(out_str,'-','\-');
endfunction
//========================================
function bOK = isPattern(str)
bOK = %t;
lenstr = length(str);
if lenstr <> 0 then
if (part(str, 1) <> '/') then
bOK = %f;
end
if (part(str, length(str)) <> '/') then
bOK = %f;
end
end
endfunction
//========================================
function regexp_pattern = createPattern(StringsInput)
dims_StringsInput = size(StringsInput,'*');
if (dims_StringsInput == 1) then
if ~isPattern(StringsInput) then
regexp_pattern = '/' + replace_regexp_char(StringsInput) + '/';
else
regexp_pattern = StringsInput;
end
else
regexp_pattern = '';
for i = 1:dims_StringsInput
if (i == 1) then
regexp_pattern = replace_regexp_char(StringsInput(i));
else
regexp_pattern = regexp_pattern + '|' + replace_regexp_char(StringsInput(i));
end
end
regexp_pattern = '/' + regexp_pattern + '/';
end
endfunction
//========================================
matched_separators = [];
strs = [];
[lhs, rhs] = argn(0);
// input types are checked in strsplit primitive
if (rhs == 1) then
len = length(varargin(1));
if len == 0 then
strs = '';
else
strs = strsplit( varargin(1), 1:length(varargin(1)) - 1 );
end
if (lhs == 2) then
dims_strs = size(strs);
matched_separators = emptystr(dims_strs(1), dims_strs(2));
end
else
strsplit_limit = -1; // no limit
if (rhs == 3) then
strsplit_limit = varargin(3);
end
if varargin(2) == "" then
[strs, matched_separators] = strsplit(varargin(1));
else
strsplit_pattern = createPattern(varargin(2));
[start_regexp, end_regexp, match_regexp] = regexp(varargin(1), strsplit_pattern);
if (start_regexp <> []) then
if (end_regexp($) == length(varargin(1))) then
end_regexp($) = end_regexp($) - 1;
end
strs = strsplit(varargin(1),end_regexp);
strs = strsubst(strs, strsplit_pattern, "", 'r');
matched_separators = match_regexp;
else
strs = varargin(1);
matched_separators = [];
end
end
if (strsplit_limit > 0) then
dim_strs = size(strs,'*');
if (strsplit_limit >= dim_strs) then
strsplit_limit = dim_strs;
else
strsremain = strs(strsplit_limit + 1 : $);
dim_strsremain = size(strsremain,'*');
strslimited = strs(1:strsplit_limit);
foundedremain = matched_separators(strsplit_limit + 1 : $);
foundedremain($ + 1: dim_strsremain) = '';
matched_separators = matched_separators(1:strsplit_limit);
str = strsremain + foundedremain;
strs = [strslimited ; strcat(str)];
end
end
end
//========================================
endfunction
|
