5 Malformed UTF-8 character
8 Malformed UTF-8 character
10 <<<<<< this warning can't be easily triggered from perl anymore
13 Malformed UTF-16 surrogate
14 <<<<<< Add a test when something actually calls utf16_to_utf8
17 # utf8.c [utf8_to_uvchr_buf] -W
19 if (ord('A') == 193) {
20 print "SKIPPED\n# ebcdic platforms do not generate Malformed UTF-8 warnings.";
33 Malformed UTF-8 character (unexpected non-continuation byte 0x73, immediately after start byte 0xf8) at - line 9.
34 Malformed UTF-8 character (unexpected non-continuation byte 0x73, immediately after start byte 0xf8) at - line 14.
37 my $d7ff = uc(chr(0xD7FF));
38 my $d800 = uc(chr(0xD800));
39 my $dfff = uc(chr(0xDFFF));
40 my $e000 = uc(chr(0xE000));
41 my $feff = uc(chr(0xFEFF));
42 my $fffd = uc(chr(0xFFFD));
43 my $fffe = uc(chr(0xFFFE));
44 my $ffff = uc(chr(0xFFFF));
45 my $hex4 = uc(chr(0x10000));
46 my $hex5 = uc(chr(0x100000));
47 my $maxm1 = uc(chr(0x10FFFE));
48 my $max = uc(chr(0x10FFFF));
49 my $nonUnicode = uc(chr(0x110000));
51 my $d7ff = uc(chr(0xD7FF));
52 my $d800 = uc(chr(0xD800));
53 my $dfff = uc(chr(0xDFFF));
54 my $e000 = uc(chr(0xE000));
55 my $feff = uc(chr(0xFEFF));
56 my $fffd = uc(chr(0xFFFD));
57 my $fffe = uc(chr(0xFFFE));
58 my $ffff = uc(chr(0xFFFF));
59 my $hex4 = uc(chr(0x10000));
60 my $hex5 = uc(chr(0x100000));
61 my $maxm1 = uc(chr(0x10FFFE));
62 my $max = uc(chr(0x10FFFF));
63 my $nonUnicode = uc(chr(0x110000));
65 Operation "uc" returns its argument for UTF-16 surrogate U+D800 at - line 3.
66 Operation "uc" returns its argument for UTF-16 surrogate U+DFFF at - line 4.
67 Operation "uc" returns its argument for non-Unicode code point 0x110000 at - line 14.
70 my $d800 = uc(chr(0xD800));
71 my $nonUnicode = uc(chr(0x110000));
72 no warnings 'surrogate';
73 my $d800 = uc(chr(0xD800));
74 my $nonUnicode = uc(chr(0x110000));
76 Operation "uc" returns its argument for UTF-16 surrogate U+D800 at - line 2.
77 Operation "uc" returns its argument for non-Unicode code point 0x110000 at - line 3.
78 Operation "uc" returns its argument for non-Unicode code point 0x110000 at - line 6.
81 my $d800 = uc(chr(0xD800));
82 my $nonUnicode = uc(chr(0x110000));
83 my $big_nonUnicode = uc(chr(0x8000_0000));
84 no warnings 'non_unicode';
85 my $d800 = uc(chr(0xD800));
86 my $nonUnicode = uc(chr(0x110000));
87 my $big_nonUnicode = uc(chr(0x8000_0000));
89 Operation "uc" returns its argument for UTF-16 surrogate U+D800 at - line 2.
90 Operation "uc" returns its argument for non-Unicode code point 0x110000 at - line 3.
91 Operation "uc" returns its argument for non-Unicode code point 0x80000000 at - line 4.
92 Operation "uc" returns its argument for UTF-16 surrogate U+D800 at - line 6.
95 my $d7ff = lc pack("U", 0xD7FF);
96 my $d800 = lc pack("U", 0xD800);
97 my $dfff = lc pack("U", 0xDFFF);
98 my $e000 = lc pack("U", 0xE000);
99 my $feff = lc pack("U", 0xFEFF);
100 my $fffd = lc pack("U", 0xFFFD);
101 my $fffe = lc pack("U", 0xFFFE);
102 my $ffff = lc pack("U", 0xFFFF);
103 my $hex4 = lc pack("U", 0x10000);
104 my $hex5 = lc pack("U", 0x100000);
105 my $maxm1 = lc pack("U", 0x10FFFE);
106 my $max = lc pack("U", 0x10FFFF);
107 my $nonUnicode = lc(pack("U", 0x110000));
109 my $d7ff = lc pack("U", 0xD7FF);
110 my $d800 = lc pack("U", 0xD800);
111 my $dfff = lc pack("U", 0xDFFF);
112 my $e000 = lc pack("U", 0xE000);
113 my $feff = lc pack("U", 0xFEFF);
114 my $fffd = lc pack("U", 0xFFFD);
115 my $fffe = lc pack("U", 0xFFFE);
116 my $ffff = lc pack("U", 0xFFFF);
117 my $hex4 = lc pack("U", 0x10000);
118 my $hex5 = lc pack("U", 0x100000);
119 my $maxm1 = lc pack("U", 0x10FFFE);
120 my $max = lc pack("U", 0x10FFFF);
121 my $nonUnicode = lc(pack("U", 0x110000));
123 Operation "lc" returns its argument for UTF-16 surrogate U+D800 at - line 3.
124 Operation "lc" returns its argument for UTF-16 surrogate U+DFFF at - line 4.
125 Operation "lc" returns its argument for non-Unicode code point 0x110000 at - line 14.
128 my $d7ff = ucfirst "\x{D7FF}";
129 my $d800 = ucfirst "\x{D800}";
130 my $dfff = ucfirst "\x{DFFF}";
131 my $e000 = ucfirst "\x{E000}";
132 my $feff = ucfirst "\x{FEFF}";
133 my $fffd = ucfirst "\x{FFFD}";
134 my $fffe = ucfirst "\x{FFFE}";
135 my $ffff = ucfirst "\x{FFFF}";
136 my $hex4 = ucfirst "\x{10000}";
137 my $hex5 = ucfirst "\x{100000}";
138 my $maxm1 = ucfirst "\x{10FFFE}";
139 my $max = ucfirst "\x{10FFFF}";
140 my $nonUnicode = ucfirst "\x{110000}";
142 my $d7ff = ucfirst "\x{D7FF}";
143 my $d800 = ucfirst "\x{D800}";
144 my $dfff = ucfirst "\x{DFFF}";
145 my $e000 = ucfirst "\x{E000}";
146 my $feff = ucfirst "\x{FEFF}";
147 my $fffd = ucfirst "\x{FFFD}";
148 my $fffe = ucfirst "\x{FFFE}";
149 my $ffff = ucfirst "\x{FFFF}";
150 my $hex4 = ucfirst "\x{10000}";
151 my $hex5 = ucfirst "\x{100000}";
152 my $maxm1 = ucfirst "\x{10FFFE}";
153 my $max = ucfirst "\x{10FFFF}";
154 my $nonUnicode = ucfirst "\x{110000}";
156 Operation "ucfirst" returns its argument for UTF-16 surrogate U+D800 at - line 3.
157 Operation "ucfirst" returns its argument for UTF-16 surrogate U+DFFF at - line 4.
158 Operation "ucfirst" returns its argument for non-Unicode code point 0x110000 at - line 14.
161 chr(0xD7FF) =~ /\p{Any}/;
162 chr(0xD800) =~ /\p{Any}/;
163 chr(0xDFFF) =~ /\p{Any}/;
164 chr(0xE000) =~ /\p{Any}/;
165 chr(0xFEFF) =~ /\p{Any}/;
166 chr(0xFFFD) =~ /\p{Any}/;
167 chr(0xFFFE) =~ /\p{Any}/;
168 chr(0xFFFF) =~ /\p{Any}/;
169 chr(0x10000) =~ /\p{Any}/;
170 chr(0x100000) =~ /\p{Any}/;
171 chr(0x10FFFE) =~ /\p{Any}/;
172 chr(0x10FFFF) =~ /\p{Any}/;
173 chr(0x110000) =~ /\p{Any}/;
175 chr(0xD7FF) =~ /\p{Any}/;
176 chr(0xD800) =~ /\p{Any}/;
177 chr(0xDFFF) =~ /\p{Any}/;
178 chr(0xE000) =~ /\p{Any}/;
179 chr(0xFEFF) =~ /\p{Any}/;
180 chr(0xFFFD) =~ /\p{Any}/;
181 chr(0xFFFE) =~ /\p{Any}/;
182 chr(0xFFFF) =~ /\p{Any}/;
183 chr(0x10000) =~ /\p{Any}/;
184 chr(0x100000) =~ /\p{Any}/;
185 chr(0x10FFFE) =~ /\p{Any}/;
186 chr(0x10FFFF) =~ /\p{Any}/;
187 chr(0x110000) =~ /\p{Any}/;
189 Code point 0x110000 is not Unicode, all \p{} matches fail; all \P{} matches succeed at - line 14.
192 chr(0x110000) =~ /\p{Any}/;
193 no warnings 'non_unicode';
194 chr(0x110000) =~ /\p{Any}/;
196 Code point 0x110000 is not Unicode, all \p{} matches fail; all \P{} matches succeed at - line 2.
198 require "../test.pl";
200 sub Is_Super { return '!utf8::Any' }
201 # The extra char is to avoid an optimization that avoids the problem when the
202 # property is the only non-latin1 char in a class
203 print "\x{1100000}" =~ /^[\p{Is_Super}\x{100}]$/, "\n";
207 require "../test.pl";
209 my $file = tempfile();
210 open(my $fh, "+>:utf8", $file);
211 print $fh "\x{D7FF}", "\n";
212 print $fh "\x{D800}", "\n";
213 print $fh "\x{DFFF}", "\n";
214 print $fh "\x{E000}", "\n";
215 print $fh "\x{FDCF}", "\n";
216 print $fh "\x{FDD0}", "\n";
217 print $fh "\x{FDEF}", "\n";
218 print $fh "\x{FDF0}", "\n";
219 print $fh "\x{FEFF}", "\n";
220 print $fh "\x{FFFD}", "\n";
221 print $fh "\x{FFFE}", "\n";
222 print $fh "\x{FFFF}", "\n";
223 print $fh "\x{10000}", "\n";
224 print $fh "\x{1FFFE}", "\n";
225 print $fh "\x{1FFFF}", "\n";
226 print $fh "\x{2FFFE}", "\n";
227 print $fh "\x{2FFFF}", "\n";
228 print $fh "\x{3FFFE}", "\n";
229 print $fh "\x{3FFFF}", "\n";
230 print $fh "\x{4FFFE}", "\n";
231 print $fh "\x{4FFFF}", "\n";
232 print $fh "\x{5FFFE}", "\n";
233 print $fh "\x{5FFFF}", "\n";
234 print $fh "\x{6FFFE}", "\n";
235 print $fh "\x{6FFFF}", "\n";
236 print $fh "\x{7FFFE}", "\n";
237 print $fh "\x{7FFFF}", "\n";
238 print $fh "\x{8FFFE}", "\n";
239 print $fh "\x{8FFFF}", "\n";
240 print $fh "\x{9FFFE}", "\n";
241 print $fh "\x{9FFFF}", "\n";
242 print $fh "\x{AFFFE}", "\n";
243 print $fh "\x{AFFFF}", "\n";
244 print $fh "\x{BFFFE}", "\n";
245 print $fh "\x{BFFFF}", "\n";
246 print $fh "\x{CFFFE}", "\n";
247 print $fh "\x{CFFFF}", "\n";
248 print $fh "\x{DFFFE}", "\n";
249 print $fh "\x{DFFFF}", "\n";
250 print $fh "\x{EFFFE}", "\n";
251 print $fh "\x{EFFFF}", "\n";
252 print $fh "\x{FFFFE}", "\n";
253 print $fh "\x{FFFFF}", "\n";
254 print $fh "\x{100000}", "\n";
255 print $fh "\x{10FFFE}", "\n";
256 print $fh "\x{10FFFF}", "\n";
257 print $fh "\x{110000}", "\n";
260 Unicode surrogate U+D800 is illegal in UTF-8 at - line 6.
261 Unicode surrogate U+DFFF is illegal in UTF-8 at - line 7.
262 Unicode non-character U+FDD0 is illegal for open interchange at - line 10.
263 Unicode non-character U+FDEF is illegal for open interchange at - line 11.
264 Unicode non-character U+FFFE is illegal for open interchange at - line 15.
265 Unicode non-character U+FFFF is illegal for open interchange at - line 16.
266 Unicode non-character U+1FFFE is illegal for open interchange at - line 18.
267 Unicode non-character U+1FFFF is illegal for open interchange at - line 19.
268 Unicode non-character U+2FFFE is illegal for open interchange at - line 20.
269 Unicode non-character U+2FFFF is illegal for open interchange at - line 21.
270 Unicode non-character U+3FFFE is illegal for open interchange at - line 22.
271 Unicode non-character U+3FFFF is illegal for open interchange at - line 23.
272 Unicode non-character U+4FFFE is illegal for open interchange at - line 24.
273 Unicode non-character U+4FFFF is illegal for open interchange at - line 25.
274 Unicode non-character U+5FFFE is illegal for open interchange at - line 26.
275 Unicode non-character U+5FFFF is illegal for open interchange at - line 27.
276 Unicode non-character U+6FFFE is illegal for open interchange at - line 28.
277 Unicode non-character U+6FFFF is illegal for open interchange at - line 29.
278 Unicode non-character U+7FFFE is illegal for open interchange at - line 30.
279 Unicode non-character U+7FFFF is illegal for open interchange at - line 31.
280 Unicode non-character U+8FFFE is illegal for open interchange at - line 32.
281 Unicode non-character U+8FFFF is illegal for open interchange at - line 33.
282 Unicode non-character U+9FFFE is illegal for open interchange at - line 34.
283 Unicode non-character U+9FFFF is illegal for open interchange at - line 35.
284 Unicode non-character U+AFFFE is illegal for open interchange at - line 36.
285 Unicode non-character U+AFFFF is illegal for open interchange at - line 37.
286 Unicode non-character U+BFFFE is illegal for open interchange at - line 38.
287 Unicode non-character U+BFFFF is illegal for open interchange at - line 39.
288 Unicode non-character U+CFFFE is illegal for open interchange at - line 40.
289 Unicode non-character U+CFFFF is illegal for open interchange at - line 41.
290 Unicode non-character U+DFFFE is illegal for open interchange at - line 42.
291 Unicode non-character U+DFFFF is illegal for open interchange at - line 43.
292 Unicode non-character U+EFFFE is illegal for open interchange at - line 44.
293 Unicode non-character U+EFFFF is illegal for open interchange at - line 45.
294 Unicode non-character U+FFFFE is illegal for open interchange at - line 46.
295 Unicode non-character U+FFFFF is illegal for open interchange at - line 47.
296 Unicode non-character U+10FFFE is illegal for open interchange at - line 49.
297 Unicode non-character U+10FFFF is illegal for open interchange at - line 50.
298 Code point 0x110000 is not Unicode, may not be portable at - line 51.
300 require "../test.pl";
302 my $file = tempfile();
303 open(my $fh, "+>:utf8", $file);
304 print $fh "\x{D800}", "\n";
305 print $fh "\x{FFFF}", "\n";
306 print $fh "\x{110000}", "\n";
309 Unicode surrogate U+D800 is illegal in UTF-8 at - line 5.
310 Unicode non-character U+FFFF is illegal for open interchange at - line 6.
311 Code point 0x110000 is not Unicode, may not be portable at - line 7.
313 require "../test.pl";
315 no warnings 'surrogate';
316 my $file = tempfile();
317 open(my $fh, "+>:utf8", $file);
318 print $fh "\x{D800}", "\n";
319 print $fh "\x{FFFF}", "\n";
320 print $fh "\x{110000}", "\n";
323 Unicode non-character U+FFFF is illegal for open interchange at - line 7.
324 Code point 0x110000 is not Unicode, may not be portable at - line 8.
326 require "../test.pl";
328 no warnings 'nonchar';
329 my $file = tempfile();
330 open(my $fh, "+>:utf8", $file);
331 print $fh "\x{D800}", "\n";
332 print $fh "\x{FFFF}", "\n";
333 print $fh "\x{110000}", "\n";
336 Unicode surrogate U+D800 is illegal in UTF-8 at - line 6.
337 Code point 0x110000 is not Unicode, may not be portable at - line 8.
339 require "../test.pl";
341 no warnings 'non_unicode';
342 my $file = tempfile();
343 open(my $fh, "+>:utf8", $file);
344 print $fh "\x{D800}", "\n";
345 print $fh "\x{FFFF}", "\n";
346 print $fh "\x{110000}", "\n";
349 Unicode surrogate U+D800 is illegal in UTF-8 at - line 6.
350 Unicode non-character U+FFFF is illegal for open interchange at - line 7.
352 # NAME C<use warnings "nonchar"> works in isolation
353 require "../test.pl";
354 use warnings 'nonchar';
355 my $file = tempfile();
356 open(my $fh, "+>:utf8", $file);
357 print $fh "\x{FFFF}", "\n";
360 Unicode non-character U+FFFF is illegal for open interchange at - line 5.
362 # NAME C<use warnings "surrogate"> works in isolation
363 require "../test.pl";
364 use warnings 'surrogate';
365 my $file = tempfile();
366 open(my $fh, "+>:utf8", $file);
367 print $fh "\x{D800}", "\n";
370 Unicode surrogate U+D800 is illegal in UTF-8 at - line 5.
372 # NAME C<use warnings "non_unicode"> works in isolation
373 require "../test.pl";
374 use warnings 'non_unicode';
375 my $file = tempfile();
376 open(my $fh, "+>:utf8", $file);
377 print $fh "\x{110000}", "\n";
380 Code point 0x110000 is not Unicode, may not be portable at - line 5.
382 require "../test.pl";
384 my $file = tempfile();
385 open(my $fh, "+>:utf8", $file);
386 print $fh "\x{D7FF}", "\n";
387 print $fh "\x{D800}", "\n";
388 print $fh "\x{DFFF}", "\n";
389 print $fh "\x{E000}", "\n";
390 print $fh "\x{FDCF}", "\n";
391 print $fh "\x{FDD0}", "\n";
392 print $fh "\x{FDEF}", "\n";
393 print $fh "\x{FDF0}", "\n";
394 print $fh "\x{FEFF}", "\n";
395 print $fh "\x{FFFD}", "\n";
396 print $fh "\x{FFFE}", "\n";
397 print $fh "\x{FFFF}", "\n";
398 print $fh "\x{10000}", "\n";
399 print $fh "\x{1FFFE}", "\n";
400 print $fh "\x{1FFFF}", "\n";
401 print $fh "\x{2FFFE}", "\n";
402 print $fh "\x{2FFFF}", "\n";
403 print $fh "\x{3FFFE}", "\n";
404 print $fh "\x{3FFFF}", "\n";
405 print $fh "\x{4FFFE}", "\n";
406 print $fh "\x{4FFFF}", "\n";
407 print $fh "\x{5FFFE}", "\n";
408 print $fh "\x{5FFFF}", "\n";
409 print $fh "\x{6FFFE}", "\n";
410 print $fh "\x{6FFFF}", "\n";
411 print $fh "\x{7FFFE}", "\n";
412 print $fh "\x{7FFFF}", "\n";
413 print $fh "\x{8FFFE}", "\n";
414 print $fh "\x{8FFFF}", "\n";
415 print $fh "\x{9FFFE}", "\n";
416 print $fh "\x{9FFFF}", "\n";
417 print $fh "\x{AFFFE}", "\n";
418 print $fh "\x{AFFFF}", "\n";
419 print $fh "\x{BFFFE}", "\n";
420 print $fh "\x{BFFFF}", "\n";
421 print $fh "\x{CFFFE}", "\n";
422 print $fh "\x{CFFFF}", "\n";
423 print $fh "\x{DFFFE}", "\n";
424 print $fh "\x{DFFFF}", "\n";
425 print $fh "\x{EFFFE}", "\n";
426 print $fh "\x{EFFFF}", "\n";
427 print $fh "\x{FFFFE}", "\n";
428 print $fh "\x{FFFFF}", "\n";
429 print $fh "\x{100000}", "\n";
430 print $fh "\x{10FFFE}", "\n";
431 print $fh "\x{10FFFF}", "\n";
432 print $fh "\x{110000}", "\n";