summaryrefslogtreecommitdiff
path: root/test/it.t
blob: 0e2b06d7693eef433b2d54189f124a03dda42e6c (plain)
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
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
#!/www/server/bin/php -qC
<?php

# Tests for it.class

#
# tests for it::match()
#
$oldcharset = ini_get('default_charset');
$oldlocale = setlocale(LC_CTYPE, 0);

ini_set('default_charset', 'utf-8');
setlocale(LC_CTYPE, 'de_CH');		# required becuase we're checking German umlauts in latin1 mode

function match($regex, $string, $expect, $name, $p = array())
{
	$GLOBALS['TEST_MORE_LEVEL'] = 1;
	$pass = is (it::match($regex, $string, $p), $expect, $name);
	if (!$pass) {
		diag("        regex given: $regex" . ($p ? " " .D($p) : ""));
		diag("    regex converted: " . it::convertregex($regex));
	}
	$GLOBALS['TEST_MORE_LEVEL'] = 0;
}


match(
	'b', 'aaaabaaaa',
	'b',
	'simple regex'
);

match(
	'a/b', '   a/b   ',
	'a/b',
	'regex with /'
);

match(
	'aa(bb)aa(cc)aa(dd)qq', 'aabbaaccaaddqq',
	array('bb', 'cc', 'dd'),
	'return array of captures'
);

match(
	'\bblah\b', ' blah ',
	'blah',
	'match \b at spaces'
);

match(
	'\bblah\b', 'blah',
	'blah',
	'match \b at end of string'
);

match(
	'\bblah\b', 'ablahc',
	null,
	'don\'t match \b at word chars'
);

match(
	'\bblah\b', 'Üblahä',
	null,
	'don\'t match \b at umlaute'
);

match(
	'\Bblah\B', ' blah ',
	null,
	'don\'t match \B at spaces'
);

match(
	'\Bblah\B', 'blah',
	null,
	'don\'t match \B at end of string'
);

match(
	'\Bblah\B', 'ablahc',
	'blah',
	'match \B at word chars'
);

match(
	'\Bblah\B', 'Üblahä',
	'blah',
	'match \B at umlaute'
);

match(
	'\w+', '  |#Üblahä   ',
	'Üblahä',
	'include umlaute in \w'
);

match(
	'[[:alpha:]]+', '  |#blahä   ',
	'blahä',
	'include umlaute in [[:alpha:]]'
);

match(
	'\W+', '  |#Üblahä  ',
	'  |#',
	'don\'t include umlaute in \W'
);

match(
	'\ba', 'äa',
	null,
	'\b must know umlauts'
);

match(
	'aaa\\\\w+', '   aaa\www  ',
	'aaa\www',
	'don\'t parse \w in \\\\w at beginning (match)'
);

match(
	'aaa\\\\w+', '   aaa\www  ',
	'aaa\www',
	'don\'t parse \w in \\\\w after chars (match)'
);

eval('$escapedwordregex = "' . it::convertregex('\w') . '";');
$escapedwordregex = preg_replace('|[\\\\/]|', '', $escapedwordregex);

match(
	'\\\\w+',  $escapedwordregex,
	null,
	'don\'t parse \w in \\\\w at beginning (no match)'
);

match(
	'aaa\\\\w+', 'aaa' . $escapedwordregex,
	null,
	'don\'t parse \w in \\\\w after chars (no match)'
);

match(
	'\\\\\\\\w+', '\\' . $escapedwordregex,
	null,
	'don\'t parse \w in \\\\\\\w (no match)'
);

match(
	'\\\\\\\\w+', '  \\\\www  ',
	'\\\\www',
	'don\'t parse \\\\\\\\w as \w (match)'
);

match(
	'[\w]+', '[[[]]]---',
	null,
	'replace \w in [\w] correctly (no match)'
);

match(
	'[\w]+', '  \\\\aword[[[]]]   ',
	'aword',
	'replace \w in [\w] correctly (match)'
);

match(
	'[\\\\w]+', ' blabergna ',
	null,
	'don\'t parse \w in [\\\\w] (no match)'
);

match(
	'[\\\\w]+', '  \\\\worda[[[]',
	'\\\\w',
	'don\'t parse \w in [\\\\w] (match)'
);

match(
	'[a\W]+', 'bbbbbbb a a%$+ accccc',
	' a a%$+ a',
	'\W in []'
);

match(
	'\\\\\\w+', '  \Üblahä  ',
	'\Üblahä',
	'parse \w in \\\\\\w at beginning'
);

match(
	'aaa\\\\\\w+', '  aaa\Üblahä  ',
	'aaa\Üblahä',
	'parse \w in \\\\\\w after chars'
);

match(
	'\w+', 'word1 wörd2 word_3',
	array('word1', 'wörd2', 'word_3'),
	"test match_all function",
	array('all' => true)
);

match(
	'aBcD', '  aBcD  ',
	'aBcD',
	"caseinsensitive is default"
);

match(
	'\w+', 'Müller',
	'Müller',
	'\w matches umlaut in utf-8 mode'
);

match(
	'M.ller', 'Müller',
	'Müller',
	'. matches umlaut in utf-8 mode'
);

match(
	utf8_decode('ö'), utf8_decode('Ö'),
	utf8_decode('Ö'),
	'match umlaute in de_CH.latin1 case insensitive',
	array('utf8' => false)
);

match(
	utf8_decode('aöBÜ'), utf8_decode('AÖbü'),
	utf8_decode('AÖbü'),
	"match umlaute with non-utf-8 override in p",
	array('utf8' => false)
);


match(
	'abc', "aBc",
	null,
	"set case sensitivity by parameter",
	array('casesensitive' => 1)
);

match(
	'\w+', 'word1 wörd2 word_3',
	array('word1', 'wörd2', 'word_3'),
	"test all => 1 without captures",
	array('all' => 1)
);

match(
	'\w+\s+(\d+)', 'word1 12 wörd2 3 word_3 4',
	array('12', '3', '4'),
	"test all => 1 with one capture",
	array('all' => 1)
);

match(
	'(\w+)\s+(\d+)', 'word1 12 wörd2 3 word_3 4',
	array(array('word1', '12'), array('wörd2', '3'), array('word_3', '4')),
	"test all => 1 with captures",
	array('all' => 1)
);

match(
	'(\w+)\s+(\d+)', 'word1 12 wörd2 3 word_3 4',
	array(array('word1', 'wörd2', 'word_3'), array('12', '3', '4')),
	"test all => 1,pattern_order => 1",
	array('all' => 1, 'pattern_order' => 1)
);

ini_set('default_charset', 'iso-8859-1');
match(
	'aöBÜ', "AÖbü",
	'AÖbü',
	"match utf-8 umlaute in case insensitive mode with utf8 override",
	array('utf8' => true)
);
ini_set('default_charset', 'utf-8');


#
# tests for it::replace()
#
is(
	it::replace(
		array(
			'regex1' => 'repl1',
			'regex2' => 'repl2',
			'regex3' => 'repl3'),
		'regex2 regex1 regex3'),
	'repl2 repl1 repl3',
	'test tr regex function'
);

is(it::replace(array('a' => "1", 'b' => "2"), "ab"), "12");
is(it::replace(array('!' => "x"), "!"), "x");
is(it::replace(array('\w' => "x"), "oö"), "xx");
is(it::replace(array('[[:alpha:]]' => "x"), "ö"), "x");
is(it::replace(array('\w' => "x", '#' => "!"), "#ö"), "!x");
is(it::replace(array('#' => "!", '\w' => "x"), "#ö"), "!x");
is(it::replace(array('ö' => "x"), "Ö"), "x");
is(it::replace(array('a' => "1"), "aaa", array('limit' => 1)), "1aa");
is(it::replace(array('\s' => "x"), it_html::entity_decode("&nbsp;")), "x", "match non-breaking space as white-space character");
is(it::replace(array('a' => "b", 'b' => "c"), "a"), "c");

is(it::grep('ismatch', array('ismatch', 'isnomatch')), array('ismatch'),  'grep with simple regex');
is(it::grep('!', array('ismatch!', 'isnomatch')),      array('ismatch!'), '! in regex');
is(it::grep('lower|UPPER', array('lower', 'LOWER', 'upper', 'UPPER'), array('casesensitive' => 1)), array(0 => 'lower', 3 => 'UPPER'), 'set casesensitive');
is(it::grep('match', array('foo' => 'match', 'bar' => 'gna')), array('foo' => 'match'), 'with keys');
is(it::grep('2', [0 => 1, 1 => 2, 2 => 3], ['invert' => true]), [0 => 1, 2 => 3]);

setlocale(LC_CTYPE, $oldlocale);
ini_set('default_charset', $oldcharset);	# end of tests that must run with specific charset

# it::cidr_match tests
is(it::cidr_match('192.168.2.3', '192.168.2.5'),					false,	"cidr_match full IP no match no mask");
is(it::cidr_match('192.168.2.3', '192.168.2.3'),					true,	"cidr_match full IP match no mask");
is(it::cidr_match('192.168.2.3', '192.168.2.5/32'),					false,	"cidr_match full IP no match");
is(it::cidr_match('192.168.2.5', '192.168.2.5/32'),					true,	"cidr_match full IP match");
is(it::cidr_match('192.168.1.1', '192.168.42.0/24'),					false,	"cidr_match no match");
is(it::cidr_match('192.168.42.1', '192.168.42.0/24'),					true,	"cidr_match basic match");
is(it::cidr_match('192.168.42.42', '192.168.0.0/16'),					true,	"cidr_match class b");
is(it::cidr_match('192.168.42.42', '192.168.42.64/26'),					false,	"cidr_match offset no match");
is(it::cidr_match('192.168.42.42', '192.168.42.32/27'),					true,	"cidr_match offset");
is(it::cidr_match('2001:918:ff83:101:798e:77c0:b722:fe56', '2001:918:ff83:101::/64'),	true,	"cidr_match ipv6");
is(it::cidr_match('2001:918:ff83:102:798e:77c0:b722:fe56', '2001:918:ff83:101::/64'),	false,	"cidr_match ipv6 no match" );
is(it::cidr_match('10.11.12.13', array('10.0.0.0/8', '192.168.0.0./16')),		true,	"cidr_match array");

# it::filter_keys tests

$data = array('a' => 1, 'b' => 2, 'c' => 3);
is(it::filter_keys($data, 'a'),             array('a' => 1),           "select one key");
is(it::filter_keys($data, array('a', 'b')), array('a' => 1, 'b' => 2), "select two keys with array");
is(it::filter_keys($data, 'a,b'),           array('a' => 1, 'b' => 2), "select two keys with string");
is(
	array_keys(it::filter_keys($data, 'b,a')),
	array('a', 'b'),
	"keep order of data array per default");
is(
	array_keys(it::filter_keys($data, 'b,a', array('reorder' => true))),
	array('b', 'a'),
	"reorder with given key order");

# it::date tests

function _time($debug_time, $expected)
{
	$GLOBALS['debug_time'] = $debug_time;
	is(it::date(), $expected, ".time-$debug_time");
	$GLOBALS['debug_time'] = '';
}
_time("2014-01-01", "2014-01-01 00:00:00");
_time("2014-01-01-15-27-15", "2014-01-01 15:27:15");
_time("15-27", it::date('', '15:27'));
_time("1527", it::date('', '15:27'));
_time("15-27-15", it::date('', '15:27:15'));
_time("152715", it::date('', '15:27:15'));
_time("yesterday", it::date('', 'yesterday'));

is(it::date('date', '2011-10-25'), '25.10.2011', 'parse date string with strtotime');
is(it::date('date', '2011-10-25 + 3 days'), '28.10.2011', 'some date arithmetic');
is(it::date('datetime', it::time()), it::date('datetime'), 'recognize int as timestamp');
is(it::date('datetime', it::time()*1.0), it::date('datetime'), 'recognize float as timestamp');
is(it::date('datetime', it::time() . ''), it::date('datetime'), 'recognize digit string as timestamp');
is(it::date('datetime', '@' . it::time()), it::date('datetime'), 'recognize strtotime timestamp format');
is(it::date('datetime', 10), it::date('datetime', "10"), 'numeric and string give same result');
is(it::date('datetime', 10.0), it::date('datetime', "10"), '... as long as num is properly truncated');
is(it::date('datetime', 10.5), it::date('datetime', "10"), '... with one digit after point');
is(it::date('datetime', 10.56), it::date('datetime', "10"), '... with two digits after point');
is(it::date('datetime', 1000000), it::date('datetime', "1000000"), '... large nummer');
is(it::date('datetime', 1000000.543), it::date('datetime', "1000000"), '... large nummer and point');
is(it::date('time', "10.5"), "10:05", 'interpret string with points with strtotime');
is(it::date('time', "10.05"), "10:05", 'interpret string with points with strtotime');

# it::uc*
is(it::ucfirst('foo bär über'), 'Foo bär über');
is(it::ucwords('foo bär über'), 'Foo Bär Über');

# it::substr_replace
is(it::substr_replace('abcdefgh', 'xyz', 2, 4), substr_replace('abcdefgh', 'xyz', 2, 4), 'it::substr_replace the same as substr_replace for ascii');
is(it::substr_replace('✔☯♥', '☃☃', 1, 1), '✔☃☃♥', 'it::substr_replace for utf-8');

is(grapheme_strlen("\xc1"), null, "need grapheme_strlen side effect for any2utf8");

is(it::any2utf8('Meier'), 'Meier', "it::any2utf8 ascii input");
is(it::any2utf8('Müller'), 'Müller', "it::any2utf8 utf8 input");
is(it::any2utf8('Aslı'), 'Aslı', "it::any2utf8 utf8 non-latin1 input");
is(it::any2utf8(utf8_decode('Müller')), 'Müller', "it::any2utf8 latin1 input");

is(it::any2utf8(
	' !"#$%&\'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~ ¡¢£¤¥¦§¨©ª«¬®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ'), # omit soft hyphen cause we filter it
	' !"#$%&\'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~ ¡¢£¤¥¦§¨©ª«¬®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ',
	"it::any2utf8 utf8 input (exhaustive alphabet)");
is(it::any2utf8(
	utf8_decode(' !"#$%&\'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~ ¡¢£¤¥¦§¨©ª«¬®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ')),
	' !"#$%&\'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~ ¡¢£¤¥¦§¨©ª«¬®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ',
	"it::any2utf8 latin1 input (exhaustive alphabet)");

is(it::any2utf8(utf8_encode("ü")), "ü", "it::any2utf8 double encoding");

is(it::any2utf8("Meier"), "Meier", "it::any2utf8 ascii");
is(it::any2utf8("Müller"), "Müller", "it::any2utf8 utf-8 latin1");
is(it::any2utf8("Aslı"), "Aslı", "it::any2utf8 utf-8 non-latin1");
is(it::any2utf8("é»"), "é»", "it::any2utf8 utf-8 latin1 special combination");
is(it::any2utf8(utf8_encode("Müller")), "Müller", "it::any2utf8 doubly encoded utf8");
is(it::any2utf8(utf8_encode(utf8_encode("Müller"))), "Müller", "it::any2utf8 triply encoded utf8");
is(it::any2utf8(utf8_decode("Müller")), "Müller", "it::any2utf8 incorrectly encoded latin1");
is(it::any2utf8("a💚b"), "a💚b", "it::any2utf8 correctly handles 4-byte utf-8 character GREEN HEART");

is(it::any2utf8(array("foo", utf8_decode("bär"))), array("foo", "bär"), "any2utf8 on arrays");
is(it::any2utf8(array("foo", array(utf8_decode("bär")))), array("foo", array("bär")), "any2utf8 on recursive arrays");
is(it::any2utf8(array(1, true, false, null)), array(1, true, false, null), "any2utf8 should leave types alone");
is(it::any2utf8(array(utf8_decode('Müller') => utf8_decode('Müller'))), array('Müller' => 'Müller'), "it::any2utf8 latin1 keys");

is(it::any2utf8("\xc2\xad"), "", "it::any2utf8 remove soft hyphens");

foreach ([ 'a' => 'ä', 'e' => 'ë', 'i' => 'ï', 'o' => 'ö', 'u' => 'ü' ] as $src => $dst)
{
	is(it::any2utf8("$src\xcc\x88"), $dst, "it::any2utf8 normalize combining diaeresis $dst to umlaut code $dst");
	$src = mb_strtoupper($src);
	$dst = mb_strtoupper($dst);
	is(it::any2utf8("$src\xcc\x88"), $dst, "it::any2utf8 normalize combining diaeresis $dst to umlaut code $dst");
}

is(it::any2utf8("\x65\xcc\x81"), "é", "it::any2utf8 convert to normal form C");

foreach (array($dummy, false, true, null, 1, "a", "Ä", "/", array()) as $var)
	is(it::json_decode(it::json_encode($var)), $var);
is(it::json_decode('{"foo":"bar"}')->foo, "bar");
is(it::json_decode('{"foo":"bar"}', ['assoc' => true])['foo'], "bar");


is(it::sort(array("2!","19!","1!")), array("1!", "19!", "2!"));
is(it::sort(array("2!","19!","1!"), "r"), array("2!", "19!", "1!"));
is(it::sort(array("2!","19!","1!"), "rn"), array("19!", "2!", "1!"));

is(it::mod(-9, 4), 3);
is(it::mod(-8, 4), 0);
is(it::mod(0, 4), 0);
is(it::mod(7, 4), 3);

is(it::map('5*$k+$v', array(0 => 1, 1 => 2)), array(1, 7));
is(it::map(function($k, $v) {return 5*$k+$v;}, array(0 => 1, 1 => 2)), array(1, 7));
is(it::map('strlen', array("aaa", "aa")), array(3, 2));
is(it::map('it::ucfirst', array("aaa")), array("Aaa"));
($dom = new DOMDocument)->loadXML('<foo>42</foo>');
is(it::map('$v->C14N()', $dom->childNodes), [ '<foo>42</foo>' ], "Traversable: Needs copy, not modifiable in-place");
# Special values which are not callable
is(it::map('null', array("aaa", "aa")), array(null, null));
is(it::map('1', array("aaa", "aa")), array(1, 1));
is(it::map(42, array("aaa", "aa")), array(42, 42));
# Only map selected keys
is(it::map('2*$v', [3, 4, 5], ['keys' => '0,1']), [6, 8, 5]);
is(it::map('2*$v', [3, 4, 5], ['keys' => [0,1]]), [6, 8, 5]);
is(it::map('2*$v', ['foo' => 1, 'bar' => 2], ['keys' => 'foo']), ['foo' => 2, 'bar' => 2]);

# it::filter
is(it::filter('$v > 2', [1, 5 => 2, 2 => 3]), [2 => 3]);
is(it::filter('$k > 2', [1, 5 => 2, 2 => 3]), [5 => 2]);

is(it::split("b", "aba"),                               ["a", "a"]);
is(it::split("b", "aBa"),                               ["a", "a"]);
is(it::split("b", "abba"),                              ["a", "", "a"]);
is(it::split("b", "ababa", ['limit' => 2]),             ["a", "aba"]);
is(it::split("b", "abbba", ['no_empty' => true]),       ["a", "a"]);
is(it::split("(b)", "aba", ['delim_capture' => true]),  ["a", "b", "a"]);
is(it::split("b", "aabaa", ['offset_capture' => true]), [["aa", 0], ["aa", 3]]);

$tmpfile = tempnam("/tmp", "it_test");
it::file_put_contents($tmpfile, "aa");
is(($fh = it::fopen($tmpfile, "r")) ? fgets($fh) : null, "aa");
is(it::file_get_contents($tmpfile), "aa");
is(it::file($tmpfile), ["aa"]);
ob_start();
it::readfile($tmpfile);
is(ob_get_clean(), "aa");

it::file_put($tmpfile, "bb");
is(it::file_get($tmpfile), "bb");
unlink($tmpfile);