Branch itools/devel-utf8 created

1 files changed, 285 insertions, 0 deletions

diff --git a/devel-utf8/tests/it.t b/devel-utf8/tests/it.t
new file mode 100755
index 0000000..1a308ec
--- /dev/null
+++ b/devel-utf8/tests/it.t
@@ -0,0 +1,285 @@
+#!/www/server/bin/php -qC
+<?php
+
+# Tests for it.class
+
+function match($regex, $string, $expect, $name)
+{
+	$GLOBALS['TEST_MORE_LEVEL'] = 1;
+	$pass = is (it::match($regex, $string), $expect, $name);
+	if (!$pass) {
+		diag("        regex given: $regex");
+		diag("    regex converted: " . it::convertregex($regex));
+	} 
+	$GLOBALS['TEST_MORE_LEVEL'] = 0;
+}
+
+match(
+	'b', 'aaaabaaaa',
+	'b',
+	'simple regex'
+	);
+match(
+	'a/b', '   a/b   ',
+	'a/b',
+	'regex with /'
+);
+match(
+	'aa(bb)aa(cc)aa(dd)qq', 'aabbaaccaaddqq',
+	array( 'bb', 'cc', 'dd' ),
+	'return array of captures'
+	);
+match(
+	'\bblah\b', ' blah ',
+	'blah',
+	'match \b at spaces'
+	);
+match(
+	'\bblah\b', 'blah',
+	'blah',
+	'match \b at end of string'
+	);
+match(
+	'\bblah\b', 'ablahc',
+	false,
+	'don\'t match \b at word chars'
+	);
+match(
+	'\bblah\b', 'Üblahä',
+	false,
+	'don\'t match \b at umlaute in latin1'
+	);
+match(
+	'\Bblah\B', ' blah ',
+	false,
+	'don\'t match \B at spaces'
+	);
+match(
+	'\Bblah\B', 'blah',
+	false,
+	'don\'t match \B at end of string'
+	);
+match(
+	'\Bblah\B', 'ablahc',
+	'blah',
+	'match \B at word chars'
+	);
+match(
+	'\Bblah\B', 'Üblahä',
+	'blah',
+	'match \B at umlaute in latin1'
+	);
+match(
+	'\w+', '  |#Üblahä   ',
+	'Üblahä',
+	'include umlaute in \w'
+	);
+match(
+	'[[:alpha:]]+', '  |#blahä   ',
+	'blahä',
+	'include umlaute in [[:alpha:]]'
+	);
+match(
+	'\W+', '  |#Üblahä  ',
+	'  |#',
+	'don\'t include umlaute in \W'
+	);
+match(
+	'\ba', 'äa',
+	'',
+	'\b must know umlauts'
+	);
+
+eval( '$escapedwordregex = "' . it::convertregex( '\w' ) . '";' );
+$escapedwordregex = preg_replace( '|[\\\\/]|', '', $escapedwordregex );
+
+match(
+	'\\\\w+',  $escapedwordregex,
+	false,
+	'don\'t parse \w in \\\\w at beginning (no match)'
+	);
+match(
+	'aaa\\\\w+', '   aaa\www  ',
+	'aaa\www',
+	'don\'t parse \w in \\\\w at beginning (match)'
+	);
+match(
+	'aaa\\\\w+', 'aaa' . $escapedwordregex,
+	false,
+	'don\'t parse \w in \\\\w after chars (no match)'
+	);
+match(
+	'aaa\\\\w+', '   aaa\www  ',
+	'aaa\www',
+	'don\'t parse \w in \\\\w after chars (match)'
+	);
+match(
+	'\\\\\\\\w+', '\\' . $escapedwordregex,
+	false,
+	'don\'t parse \w in \\\\\\\w (no match)'
+	);
+match(
+	'\\\\\\\\w+', '  \\\\www  ',
+	'\\\\www',
+	'don\'t parse \\\\\\\\w as \w (match)'
+	);
+match(
+	'[\w]+', '[[[]]]---',
+	false,
+	'replace \w in [\w] correctly (no match)'
+	);
+match(
+	'[\w]+', '  \\\\aword[[[]]]   ',
+	'aword',
+	'replace \w in [\w] correctly (match)'
+	);
+match(
+	'[\\\\w]+', ' blabergna ',
+	false,
+	'don\'t parse \w in [\\\\w] (no match)'
+	);
+match(
+	'[\\\\w]+', '  \\\\worda[[[]',
+	'\\\\w',
+	'don\'t parse \w in [\\\\w] (match)'
+	);
+match(
+	'[a\W]+', 'bbbbbbb a a%$+ accccc',
+	' a a%$+ a',
+	'\W in []'
+	);
+match(
+	'\\\\\\w+', '  \Üblahä  ',
+	'\Üblahä',
+	'parse \w in \\\\\\w at beginning'
+	);
+match(
+	'aaa\\\\\\w+', '  aaa\Üblahä  ',
+	'aaa\Üblahä',
+	'parse \w in \\\\\\w after chars'
+	);
+is(
+	it::replace(
+		array(
+			'regex1' => 'repl1',
+			'regex2' => 'repl2',
+			'regex3' => 'repl3' ),
+		'regex2 regex1 regex3' ),
+	'repl2 repl1 repl3',
+	'test tr regex function'
+	);
+is(
+	it::match( '\w+', 'word1 wörd2 word_3', array('all' => true )),
+	array( 'word1', 'wörd2', 'word_3' ),
+	"test match_all function"
+	);
+match(
+	'aBcD', '  aBcD  ',
+	'aBcD',
+	"caseinsensitive is default"
+	);
+match(
+	'ö', 'Ö',
+	'Ö',
+	'match umlaute in latin1 case insensitive'
+	);
+
+is(
+	it::match(utf8_encode('aöBÜ'), utf8_encode("AÖbü"), array('utf8' => true)),
+	utf8_encode('AÖbü'),
+	"match utf-8 umlaute in case insensitive"
+);
+
+$oldcharset = ini_get('default_charset');
+ini_set('default_charset', 'utf-8');
+match(
+	utf8_encode('aöBÜ'), utf8_encode('AÖbü'),
+	utf8_encode('AÖbü'),
+	"match utf-8 umlaute in case insensitive using default_charset"
+);
+is(
+	it::match('aöBÜ', 'AÖbü', array('utf8' => false)),
+	'AÖbü',
+	"non-utf-8 override with default_charset=utf-8"
+);
+match(
+	'\w+', utf8_encode('Müller'),
+	utf8_encode('Müller'),
+	'\w matches umlaut in utf-8 mode'
+);
+match(
+	'M.ller', utf8_encode('Müller'),
+	utf8_encode('Müller'),
+	'. matches umlaut in utf-8 mode'
+);
+ini_set('default_charset', $oldcharset);
+
+is(
+	it::match( 'abc', "aBc", array('casesensitive' => 1 )),
+	false,
+	"set case sensitivity by parameter"
+	);
+
+is(
+	it::match( '\w+', 'word1 wörd2 word_3', array('all' => 1 )),
+	array( 'word1', 'wörd2', 'word_3' ),
+	"test all=>1 without captures"
+	);
+is(
+	it::match( '\w+\s+(\d+)', 'word1 12 wörd2 3 word_3 4', array('all' => 1 )),
+	array( '12', '3', '4' ),
+	"test all=>1 with one capture"
+	);
+is(
+	it::match( '(\w+)\s+(\d+)', 'word1 12 wörd2 3 word_3 4', array('all' => 1 )),
+	array( array( 'word1', '12' ), array( 'wörd2', '3' ), array( 'word_3', '4' ) ),
+	"test all=>1 with captures"
+	);
+is(
+	it::match( '(\w+)\s+(\d+)', 'word1 12 wörd2 3 word_3 4', array('all' => 1, 'pattern_order' => 1 )),
+	array( array( 'word1', 'wörd2', 'word_3' ), array( '12', '3', '4' ) ),
+	"test all=>1,pattern_order=>1"
+	);
+
+is(it::replace(array('a' => "1", 'b' => "2"), "ab"), "12");
+is(it::replace(array('!' => "x"), "!"), "x");
+is(it::replace(array('\w' => "x"), "oö"), "xx");
+is(it::replace(array('[[:alpha:]]' => "x"), "ö"), "x");
+is(it::replace(array('\w' => "x", '#' => "!"), "#ö"), "!x");
+is(it::replace(array('#' => "!", '\w' => "x"), "#ö"), "!x");
+is(it::replace(array('ö' => "x"), "Ö"), "x");
+is(it::replace(array('a' => "1"), "aaa", array('limit' => 1)), "1aa");
+
+# it::filter_keys tests
+
+$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
+
+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', time()), it::date('datetime'), 'recognize int as timestamp');
+is(it::date('datetime', time()*1.0), it::date('datetime'), 'recognize float as timestamp');
+is(it::date('datetime', time() . ''), it::date('datetime'), 'recognize digit string as timestamp');
+is(it::date('datetime', '@' . 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');
+
+?>