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
|
########################################################################
##
## Copyright (C) 2016-2025 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{native_bytes} =} unicode2native (@var{utf8_str}, @var{codepage})
## @deftypefnx {} {@var{native_bytes} =} unicode2native (@var{utf8_str})
## Convert UTF-8 string @var{utf8_str} to byte stream using @var{codepage}.
##
## The character vector @var{utf8_str} is converted to a byte stream
## @var{native_bytes} using the code page given by @var{codepage}. The
## string @var{codepage} must be an identifier of a valid code page.
## Examples for valid code pages are @qcode{"ISO-8859-1"},
## @qcode{"Shift-JIS"}, or @qcode{"UTF-16"}. For a list of supported code
## pages, see @url{https://www.gnu.org/software/libiconv}. If @var{codepage}
## is omitted or empty, the system default codepage is used.
##
## If any of the characters cannot be mapped into the codepage @var{codepage},
## they are replaced with the appropriate substitution sequence for that
## codepage.
##
## @seealso{native2unicode}
## @end deftypefn
function native_bytes = unicode2native (utf8_str, codepage = "")
if (nargin < 1)
print_usage ();
endif
## For Matlab compatibility, return empty output for empty input.
if (isempty (utf8_str))
native_bytes = uint8 ([]);
return;
endif
if (! ischar (utf8_str) || ! isvector (utf8_str))
error ("unicode2native: UTF8_STR must be a character vector");
endif
if (! (ischar (codepage) && (isrow (codepage) || isempty (codepage))))
error ("unicode2native: CODEPAGE must be a string");
endif
native_bytes = __unicode2native__ (utf8_str, codepage);
if (! isrow (utf8_str))
native_bytes = native_bytes.';
endif
endfunction
%!testif HAVE_ICONV
%! assert (unicode2native ("ЄЅІЇЈЉЊ", "ISO-8859-5"), uint8 (164:170));
%!testif HAVE_ICONV
%! assert (unicode2native (["ЄЅІ" "\0" "ЇЈЉЊ"], "ISO-8859-5"),
%! uint8 ([164:166 0 167:170]));
%!assert <*60480> (unicode2native (''), uint8 ([]))
%!testif HAVE_ICONV <*64331>
%! assert (! isempty (unicode2native ("abc")));
%!testif HAVE_ICONV <*64331>
%! assert (! isempty (unicode2native ("abc", "")));
## short character arrays with invalid UTF-8
%!testif HAVE_ICONV <*63930>
%! assert (unicode2native (char (230), 'windows-1252'), uint8 (63));
%!testif HAVE_ICONV <*63930>
%! assert (unicode2native (char (249), 'windows-1252'), uint8 (63));
%!testif HAVE_ICONV <*63930>
%! assert (unicode2native (char (230:231), 'windows-1252'), uint8 ([63, 63]));
%!testif HAVE_ICONV <*63930>
%! assert (unicode2native (char (230:234), 'windows-1252'),
%! uint8 ([63, 63, 63, 63, 63]));
%!testif HAVE_ICONV <*63930>
%! assert (unicode2native (char ([230, 10]), 'windows-1252'),
%! uint8 ([63, 10]));
## target encoding with surrogates larger than one byte
%!testif HAVE_ICONV
%! assert (size (unicode2native ('a',
%! ['utf-16', nthargout(3, 'computer'), 'e'])),
%! [1, 2]);
%!testif HAVE_ICONV
%! assert (typecast (unicode2native ('a',
%! ['utf-16', nthargout(3, 'computer'), 'e']),
%! 'uint16'),
%! uint16 (97));
%!testif HAVE_ICONV
%! assert (typecast (unicode2native ('ab',
%! ['utf-16', nthargout(3, 'computer'), 'e']),
%! 'uint16'),
%! uint16 (97:98));
%!testif HAVE_ICONV
%! assert (typecast (unicode2native ('abc',
%! ['utf-16', nthargout(3, 'computer'), 'e']),
%! 'uint16'),
%! uint16 (97:99));
%!testif HAVE_ICONV
%! assert (typecast (unicode2native ('abcd',
%! ['utf-16', nthargout(3, 'computer'), 'e']),
%! 'uint16'),
%! uint16 (97:100));
%!testif HAVE_ICONV <*64139>
%! assert (typecast (unicode2native ('abcde',
%! ['utf-16', nthargout(3, 'computer'), 'e']),
%! 'uint16'),
%! uint16 (97:101));
%!testif HAVE_ICONV
%! assert (size (unicode2native ('a',
%! ['utf-32', nthargout(3, 'computer'), 'e'])),
%! [1, 4]);
%!testif HAVE_ICONV
%! assert (typecast (unicode2native ('a',
%! ['utf-32', nthargout(3, 'computer'), 'e']),
%! 'uint32'),
%! uint32 (97));
%!testif HAVE_ICONV
%! assert (typecast (unicode2native ('ab',
%! ['utf-32', nthargout(3, 'computer'), 'e']),
%! 'uint32'),
%! uint32 (97:98));
%!testif HAVE_ICONV
%! assert (typecast (unicode2native ('abc',
%! ['utf-32', nthargout(3, 'computer'), 'e']),
%! 'uint32'),
%! uint32 (97:99));
%!testif HAVE_ICONV
%! assert (typecast (unicode2native ('abcd',
%! ['utf-32', nthargout(3, 'computer'), 'e']),
%! 'uint32'),
%! uint32 (97:100));
%!error <Invalid call> unicode2native ()
%!error <called with too many inputs> unicode2native ('a', 'ISO-8859-1', 'test')
%!error <UTF8_STR must be a character vector> unicode2native (['ab'; 'cd'])
%!error <UTF8_STR must be a character vector> unicode2native ({1 2 3 4})
%!error <CODEPAGE must be a string> unicode2native ('ЄЅІЇЈЉЊ', 123)
%!error <CODEPAGE must be a string> unicode2native ('ЄЅІЇЈЉЊ', ['ISO-8859-1'].')
%!testif HAVE_ICONV
%! fail ("unicode2native ('a', 'foo')",
%! "converting from UTF-8 to codepage 'foo'");
|
