/** * Returns the position of the first occurrence of a substring in a string * based on grapheme units or -1 in case the given substring was not found * within the given string. * * @param string $haystack The string to search in * @param string $needle The string to get the first index of * @param int $offset Offset index where to start looking for the needle * @return int */ public static function getFirstIndexOf(string $haystack, string $needle, int $offset = 0) : int { // try/catch-block is necessary because grapheme_strpos produces E_NOTICE (which becomes // converted to an exception by the system) in case $offset is not available in $haystack // (e.g. empty haystack with offset "0") try { // get first index $firstIndex = grapheme_strpos($haystack, $needle, $offset); // return int -1 if not found instead of boolean FALSE return $firstIndex === false ? -1 : $firstIndex; } catch (Exception $e) { return -1; } }
/** * @covers Patchwork\PHP\Override\Intl::grapheme_strpos * @covers Patchwork\PHP\Override\Intl::grapheme_stripos * @covers Patchwork\PHP\Override\Intl::grapheme_strrpos * @covers Patchwork\PHP\Override\Intl::grapheme_strripos * @covers Patchwork\PHP\Override\Intl::grapheme_position */ function testGrapheme_strpos() { $this->assertSame(false, grapheme_strpos('abc', '')); $this->assertSame(false, grapheme_strpos('abc', 'd')); $this->assertSame(false, grapheme_strpos('abc', 'a', 3)); $this->assertSame(0, grapheme_strpos('abc', 'a', -1)); $this->assertSame(1, grapheme_strpos('한국어', '국')); $this->assertSame(3, grapheme_stripos('DÉJÀ', 'à')); $this->assertSame(false, grapheme_strrpos('한국어', '')); $this->assertSame(1, grapheme_strrpos('한국어', '국')); $this->assertSame(3, grapheme_strripos('DÉJÀ', 'à')); $this->assertSame(false, p::grapheme_strpos('abc', '')); $this->assertSame(false, p::grapheme_strpos('abc', 'd')); $this->assertSame(false, p::grapheme_strpos('abc', 'a', 3)); $this->assertSame(0, p::grapheme_strpos('abc', 'a', -1)); $this->assertSame(1, p::grapheme_strpos('한국어', '국')); $this->assertSame(3, p::grapheme_stripos('DÉJÀ', 'à')); $this->assertSame(false, p::grapheme_strrpos('한국어', '')); $this->assertSame(1, p::grapheme_strrpos('한국어', '국')); $this->assertSame(3, p::grapheme_strripos('DÉJÀ', 'à')); $this->assertSame(16, p::grapheme_stripos('der Straße nach Paris', 'Paris')); }
/** * Returns the result of filtering $value * * @param mixed $value * @return mixed */ public function filter($value) { // Store original value $unfilteredValue = $value; if (is_string($value)) { // Initialization $formatter = $this->getFormatter(); // Disable scientific notation $formatter->setSymbol(\NumberFormatter::EXPONENTIAL_SYMBOL, null); if ($this->getBreakingSpaceAllowed()) { // Replace spaces with NBSP (non breaking spaces) $value = str_replace(" ", " ", $value); // FIXME? can be removed } // Parse as currency ErrorHandler::start(); $position = 0; $currencyCode = $this->setupCurrencyCode(); if ($this->getCurrencyCorrectness()) { // The following parsing mode allows the predefined currency code ONLY. // Also it should be more strict and faster than parseCurrency. $result = $formatter->parse($value, \NumberFormatter::TYPE_DOUBLE, $position); } else { // The following parsing mode can work with multiple currencies. $result = $formatter->parseCurrency($value, $resultCurrencyCode, $position); } $fractionDigits = $formatter->getAttribute(\NumberFormatter::FRACTION_DIGITS); // Input is a valid currency and the result is within the codomain? if ($result !== false && (is_float($result) && !is_infinite($result) && !is_nan($result))) { ErrorHandler::stop(); // Exit if the parsing has finished before the end of the input if ($position < grapheme_strlen($value)) { return $unfilteredValue; } // Retrieve currency symbol for the given locale and currency code $currencySymbol = $this->getFirstCurrencySymbol($this->getLocale(), $currencyCode); // Exit if the currency correctness is mandatory and the currency symbol is not present in the input if ($this->getCurrencyCorrectness() && grapheme_strpos($value, $currencySymbol) === false) { return $unfilteredValue; } if ($this->getScaleCorrectness()) { $countedDecimals = $this->countDecimalDigits($value, $formatter->getSymbol(\NumberFormatter::MONETARY_SEPARATOR_SYMBOL), $currencySymbol); // Exit if the number of decimal digits (i.e., the scale) does not match the requirement if ($fractionDigits !== $countedDecimals) { return $unfilteredValue; } } // Here we have a perfectly parsed (pattern correct, currency correct, scale correct) currency amount return $result; } // At this stage result is FALSE and input probably is a not canonical currency amount // Check if the currency symbol is mandatory (assiming 'parse MODE') if ($this->getCurrencyCorrectness()) { ErrorHandler::stop(); return $unfilteredValue; } // Retrieve symbols $symbolKeys = [self::CURRENCY_SYMBOL, self::GROUP_SEPARATOR_SYMBOL, self::SEPARATOR_SYMBOL, self::INFINITY_SYMBOL, self::NAN_SYMBOL, self::POSITIVE_PREFIX, self::POSITIVE_SUFFIX, self::NEGATIVE_PREFIX, self::NEGATIVE_SUFFIX, self::FRACTION_DIGITS]; $symbols = []; foreach ($symbolKeys as $symbol) { $symbols[$symbol] = $this->getSymbol($symbol); } // Regex components $regexSymbols = array_filter(array_unique(array_values($symbols))); $numbers = $this->getRegexComponent(self::REGEX_NUMBERS); $flags = $this->getRegexComponent(self::REGEX_FLAGS); // Build allowed chars regex $allowedChars = sprintf('#^[%s]+$#%s', $numbers . implode('', array_map('preg_quote', $regexSymbols)), $flags); // FIXME: pay attention to NaN and INF symbols here // Check that value contains only allowed characters (digits, group and decimal separator) $result = false; if (preg_match($allowedChars, $value)) { $decimal = \NumberFormatter::create($this->getLocale(), \NumberFormatter::DECIMAL); // Get decimal place info // FIXME: parse and parseCurrancy could use different symbols // when used with non default currency code $currencySymbol = $this->getFirstCurrencySymbol($this->getLocale(), $currencyCode); $numDecimals = $this->countDecimalDigits($value, $symbols[self::SEPARATOR_SYMBOL], $currencySymbol); // Check if the number of decimal digits match the requirement if ($this->getScaleCorrectness() && $numDecimals !== $fractionDigits) { return $unfilteredValue; } // Ignore spaces $value = str_replace(" ", '', $value); // Substitute negative currency representation with negative number representation $decimalNegPrefix = $decimal->getTextAttribute(\NumberFormatter::NEGATIVE_PREFIX); $decimalNegSuffix = $decimal->getTextAttribute(\NumberFormatter::NEGATIVE_SUFFIX); $currencyNegPrefix = $symbols[self::NEGATIVE_PREFIX]; $currencyNegSuffix = $symbols[self::NEGATIVE_SUFFIX]; if ($decimalNegPrefix !== $currencyNegPrefix && $decimalNegSuffix !== $currencyNegSuffix) { $regex = sprintf('#^%s([%s%s%s]+)%s$#%s', preg_quote($currencyNegPrefix), $numbers, preg_quote($symbols[self::SEPARATOR_SYMBOL]), preg_quote($symbols[self::GROUP_SEPARATOR_SYMBOL]), preg_quote($currencyNegSuffix), $flags); $value = preg_replace($regex, $decimalNegPrefix . '\\1' . $decimalNegSuffix, $value); } // Try to parse as a simple decimal (formatted) number $result = $decimal->parse($value, \NumberFormatter::TYPE_DOUBLE); } ErrorHandler::stop(); return $result !== false ? $result : $unfilteredValue; // FIXME? strict check that it is a double } // At this stage input is not a string return $unfilteredValue; }
/** * Here used as a multibyte enabled equivalent of `strpos()`. * * @link http://php.net/manual/en/function.grapheme-strpos.php * @param string $haystack * @param string $needle * @param integer $offset * @return integer|boolean */ public function strpos($haystack, $needle, $offset) { return grapheme_strpos($haystack, $needle, $offset); }
static function strpos($s, $needle, $offset = 0) { return grapheme_strpos($s, $needle, $offset); }
/** * Returns the position of the first occurrence of a substring in a string, searching case-sensitively. * * As a special case, the method returns the starting position of the search if the searched substring is empty. * * @param string $string The string to be looked into. * @param string $ofString The searched substring. * @param int $startPos **OPTIONAL. Default is** `0`. The starting position for the search. * * @return int The position of the first occurrence of the substring in the string or `-1` if no such substring was * found, taking into account the letter case during the search. */ public static function indexOf($string, $ofString, $startPos = 0) { assert('is_cstring($string) && is_cstring($ofString) && is_int($startPos)', vs(isset($this), get_defined_vars())); assert('0 <= $startPos && $startPos <= self::length($string)', vs(isset($this), get_defined_vars())); if (self::isEmpty($ofString)) { return $startPos; } $res = grapheme_strpos($string, $ofString, $startPos); return is_int($res) ? $res : -1; }
/** * Generate dataset. * * Formats: * - (positive and negative) currency amounts with their own currency symbol * - (positive and negative) currency amounts with ISO currency symbol * - (positive and negative) numbers (without currency symbol) * - (positive and negative) numbers expressed in scientific notation (without currency symbol) * * @return array */ public function valuesProvider() { $data = []; $values = [0, 0.1, 0.01, 1000, 1234.61, 12345678.9]; $values = array_unique(array_merge($values, array_map(function ($i) { return -$i; }, $values))); foreach ($this->locales as $locale) { $formatter = \NumberFormatter::create($locale, \NumberFormatter::CURRENCY); $currencySymbol = $formatter->getSymbol(\NumberFormatter::CURRENCY_SYMBOL); $isoSymbol = $formatter->getTextAttribute(\NumberFormatter::CURRENCY_CODE); $groupSep = $formatter->getSymbol(\NumberFormatter::MONETARY_GROUPING_SEPARATOR_SYMBOL); $numDecimals = $formatter->getAttribute(\NumberFormatter::FRACTION_DIGITS); $posPre = $formatter->getTextAttribute(\NumberFormatter::POSITIVE_PREFIX); $negPre = $formatter->getTextAttribute(\NumberFormatter::NEGATIVE_PREFIX); $posSuf = $formatter->getTextAttribute(\NumberFormatter::POSITIVE_SUFFIX); $negSuf = $formatter->getTextAttribute(\NumberFormatter::NEGATIVE_SUFFIX); $exponantiatior = \NumberFormatter::create($locale, \NumberFormatter::SCIENTIFIC); foreach ($values as $value) { // Restore currency symbol $formatter->setSymbol(\NumberFormatter::CURRENCY_SYMBOL, $currencySymbol); if (is_float($value)) { // If value is float and current currency does not have cents, jump it if ($numDecimals === 0) { continue; } // Create a currency with less decimal places then required (w/ currency symbol) $formatter->setAttribute(\NumberFormatter::FRACTION_DIGITS, $numDecimals - 1); $currency = preg_replace('/^[\\xC2\\xA0\\s]+|[\\xC2\\xA0\\s]+$/u', '', $formatter->format($value)); // echo $currency . PHP_EOL; $data[] = [$locale, true, true, $currency, $currency]; // Not filtered $data[] = [$locale, true, false, $currency, $currency]; // Not filtered $data[] = [$locale, false, false, (double) sprintf('%.' . ($numDecimals - 1) . 'f', $value), $currency]; // Filtered $data[] = [$locale, false, true, (double) sprintf('%.' . ($numDecimals - 1) . 'f', $value), $currency]; // Filtered // Create a currency with less decimal places then required (w/o currency symbol) $currency = preg_replace('#' . preg_quote($currencySymbol) . '#u', '', $currency); $currency = preg_replace('/^[\\xC2\\xA0\\s]+|[\\xC2\\xA0\\s]+$/u', '', $currency); // echo $currency . PHP_EOL; $data[] = [$locale, true, true, $currency, $currency]; // Not filtered $data[] = [$locale, true, false, $currency, $currency]; // Not filtered $data[] = [$locale, false, false, (double) sprintf('%.' . ($numDecimals - 1) . 'f', $value), $currency]; // Filtered $data[] = [$locale, false, true, $currency, $currency]; // Not filtered // Create a currency with more decimal places then required (w/ currency symbol) $formatter->setAttribute(\NumberFormatter::FRACTION_DIGITS, $numDecimals + 1); $currency = preg_replace('/^[\\xC2\\xA0\\s]+|[\\xC2\\xA0\\s]+$/u', '', $formatter->format($value)); // echo $currency . PHP_EOL; $data[] = [$locale, true, true, $currency, $currency]; // Not filtered $data[] = [$locale, true, false, $currency, $currency]; // Not filtered $data[] = [$locale, false, false, (double) sprintf('%.' . ($numDecimals + 1) . 'f', $value), $currency]; // Filtered $data[] = [$locale, false, true, (double) sprintf('%.' . ($numDecimals + 1) . 'f', $value), $currency]; // Filtered // Create a currency with more decimal places then required (w/o currency symbol) $currency = preg_replace('#' . preg_quote($currencySymbol) . '#u', '', $currency); $currency = preg_replace('/^[\\xC2\\xA0\\s]+|[\\xC2\\xA0\\s]+$/u', '', $currency); // echo $currency . PHP_EOL; $data[] = [$locale, true, true, $currency, $currency]; // Not filtered $data[] = [$locale, true, false, $currency, $currency]; // Not filtered $data[] = [$locale, false, false, (double) sprintf('%.' . ($numDecimals + 1) . 'f', $value), $currency]; // Filtered $data[] = [$locale, false, true, $currency, $currency]; // Not filtered } // Restore correct number of maximum decimal places $formatter->setAttribute(\NumberFormatter::FRACTION_DIGITS, $numDecimals); // Create completely formatted currency value (w/ currency symbol) $currency = $formatter->formatCurrency($value, $isoSymbol); // echo $currency . PHP_EOL; $data[] = [$locale, true, true, $value, $currency]; // Filtered // Create currency value with letters inside $randomPos = rand(0, grapheme_strlen($currency) - 1); $currency = grapheme_substr($currency, 0, $randomPos) . 'X' . grapheme_substr($currency, $randomPos); // echo $currency . PHP_EOL; $daa[] = [$locale, true, true, $currency, $currency]; // Not filtered // Create currency value (w/ currency symbol) (w/o group separators) if (grapheme_strpos($currency, $groupSep) !== false) { $formatter->setSymbol(\NumberFormatter::MONETARY_GROUPING_SEPARATOR_SYMBOL, null); $currency = $formatter->formatCurrency($value, $isoSymbol); // echo $currency . PHP_EOL; $data[] = [$locale, true, true, $value, $currency]; // Filtered $formatter->setSymbol(\NumberFormatter::MONETARY_GROUPING_SEPARATOR_SYMBOL, $groupSep); } // Create currency value with ISO currency symbol $formatter->setSymbol(\NumberFormatter::CURRENCY_SYMBOL, $isoSymbol); $currency = $formatter->format($value); // echo $currency . PHP_EOL; $data[] = [$locale, true, true, $value, $currency]; // Filtered // Create currency value with ISO currency symbol (w/o group separators) if (grapheme_strpos($currency, $groupSep) !== false) { $formatter->setSymbol(\NumberFormatter::MONETARY_GROUPING_SEPARATOR_SYMBOL, null); $currency = $formatter->format($value); // echo $currency . PHP_EOL; $data[] = [$locale, true, true, $value, $currency]; // Filtered $formatter->setSymbol(\NumberFormatter::MONETARY_GROUPING_SEPARATOR_SYMBOL, $groupSep); } // Create currency values with wrong ISO currency symbol or other text after it $currency = $currency . 'S'; // echo $currency . PHP_EOL; $data[] = [$locale, true, true, $currency, $currency]; // Not filtered // Create currency value w/o any currency symbol $formatter->setSymbol(\NumberFormatter::CURRENCY_SYMBOL, null); $currency = $formatter->format($value); // preg_replace('/^[\xC2\xA0\s]+|[\xC2\xA0\s]+$/u', '', ...); // echo $currency . PHP_EOL; $data[] = [$locale, true, true, $currency, $currency]; // Not filtered $data[] = [$locale, true, false, $value, $currency]; // Filtered when currency symbol is not mandatory if ($value >= 0) { // Create currency value expressed in scientific notation w/o any currency symbol $currency = $exponantiatior->format($value, \NumberFormatter::TYPE_DOUBLE); // echo $currency . PHP_EOL; $data[] = [$locale, true, true, $currency, $currency]; // Not filtered $data[] = [$locale, true, false, $currency, $currency]; // Not filtered // Create currency value expressed in scientific notation with proper currency symbol $currency = $posPre . $currency . $posSuf; // echo $currency . PHP_EOL; $data[] = [$locale, true, true, $currency, $currency]; // Not filtered $data[] = [$locale, true, false, $currency, $currency]; // Not filtered } else { // Create negative currency value expressed in scientific notation with proper currency symbol $currency = $exponantiatior->format(abs($value), \NumberFormatter::TYPE_DOUBLE); $currency = $negPre . $currency . $negSuf; // echo $currency . PHP_EOL; $data[] = [$locale, true, true, $currency, $currency]; // Not filtered $data[] = [$locale, true, false, $currency, $currency]; // Not filtered } } // echo '---' . PHP_EOL; } return $data; }
<?php var_dump(grapheme_stripos(1, 1, 2147483648)); var_dump(grapheme_strpos(1, 1, 2147483648));
<?php var_dump(grapheme_strpos('abaa', 'a', 1)); var_dump(grapheme_strpos('abaa', 'a', 0)); var_dump(grapheme_strpos('abaa', 'a', -1)); var_dump(grapheme_strpos('abaa', 'a', -2)); var_dump(grapheme_strrpos('abaa', 'a', 1)); var_dump(grapheme_strrpos('abaa', 'a', 0)); var_dump(grapheme_strrpos('abaa', 'a', -1)); var_dump(grapheme_strrpos('abaa', 'a', -2));
function ut_main() { $res_str = ''; $char_a_diaeresis = "ä"; // 'LATIN SMALL LETTER A WITH DIAERESIS' (U+00E4) $char_a_ring = "å"; // 'LATIN SMALL LETTER A WITH RING ABOVE' (U+00E5) $char_o_diaeresis = "ö"; // 'LATIN SMALL LETTER O WITH DIAERESIS' (U+00F6) $char_O_diaeresis = "Ö"; // 'LATIN CAPITAL LETTER O WITH DIAERESIS' (U+00D6) $char_angstrom_sign = "Å"; // 'ANGSTROM SIGN' (U+212B) $char_A_ring = "Å"; // 'LATIN CAPITAL LETTER A WITH RING ABOVE' (U+00C5) $char_ohm_sign = "Ω"; // 'OHM SIGN' (U+2126) $char_omega = "Ω"; // 'GREEK CAPITAL LETTER OMEGA' (U+03A9) $char_combining_ring_above = "̊"; // 'COMBINING RING ABOVE' (U+030A) $char_fi_ligature = "fi"; // 'LATIN SMALL LIGATURE FI' (U+FB01) $char_long_s_dot = "ẛ"; // 'LATIN SMALL LETTER LONG S WITH DOT ABOVE' (U+1E9B) // the word 'hindi' using Devanagari characters: $hindi = "हिन्दी"; $char_a_ring_nfd = "å"; $char_A_ring_nfd = "Å"; $char_o_diaeresis_nfd = "ö"; $char_O_diaeresis_nfd = "Ö"; $char_diaeresis = "̈"; //===================================================================================== $res_str .= "\n" . 'function grapheme_strlen($string) {}' . "\n\n"; $res_str .= "\"hindi\" in devanagari strlen " . grapheme_strlen($hindi) . "\n"; $res_str .= "\"ab\" + \"hindi\" + \"cde\" strlen " . grapheme_strlen('ab' . $hindi . 'cde') . "\n"; $res_str .= "\"\" strlen " . grapheme_strlen("") . "\n"; $res_str .= "char_a_ring_nfd strlen " . grapheme_strlen($char_a_ring_nfd) . "\n"; $res_str .= "char_a_ring_nfd + \"bc\" strlen " . grapheme_strlen($char_a_ring_nfd . 'bc') . "\n"; $res_str .= "\"abc\" strlen " . grapheme_strlen('abc') . "\n"; //===================================================================================== $res_str .= "\n" . 'function grapheme_strpos($haystack, $needle, $offset = 0) {}' . "\n\n"; $tests = array(array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "o", "o", 5), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd, "o", "false"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd, $char_o_diaeresis_nfd, 4), array($char_o_diaeresis_nfd . "a" . $char_a_ring_nfd . "bc", $char_a_ring_nfd, 2), array("a" . $char_a_ring_nfd . "bc", $char_a_ring_nfd, 1), array("abc", $char_a_ring_nfd, "false"), array($char_a_ring_nfd . "bc", "a", "false"), array("abc", "d", "false"), array("abc", "c", 2), array("abc", "b", 1), array("abc", "a", 0), array("abc", "a", 0, 0), array("abc", "a", 1, "false"), array("ababc", "a", 1, 2), array("ao" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "o", "o", 2, 6), array($char_o_diaeresis_nfd . $char_a_ring_nfd . "a" . $char_a_ring_nfd . "bc", $char_a_ring_nfd, 2, 3), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "opq", "op", 5), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "opq", "opq", 5), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd, "abc", "false"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "bc" . $char_o_diaeresis_nfd, $char_o_diaeresis_nfd . "bc" . $char_o_diaeresis_nfd, 4), array($char_o_diaeresis_nfd . "a" . $char_a_ring_nfd . "bc", $char_a_ring_nfd . "bc", 2), array("a" . $char_a_ring_nfd . "bc", $char_a_ring_nfd . "bc", 1), array("abc", $char_a_ring_nfd . "bc", "false"), array($char_a_ring_nfd . "bc", "abcdefg", "false"), array("abc", "defghijklmnopq", "false"), array("abc", "ab", 0), array("abc", "bc", 1), array("abc", "abc", 0), array("abc", "abcd", "false"), array("abc", "ab", 0, 0), array("abc", "abc", 0, 0), array("abc", "abc", 1, "false"), array("ababc", "ab", 1, 2), array("ababc", "abc", 1, 2), array("ao" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "o" . $char_a_ring_nfd . "bc", "o" . $char_a_ring_nfd . "bc", 2, 6), array($char_o_diaeresis_nfd . $char_a_ring_nfd . "a" . $char_a_ring_nfd . "bc" . $char_a_ring_nfd . "def", $char_a_ring_nfd . "bc" . $char_a_ring_nfd, 2, 3)); foreach ($tests as $test) { $arg1 = urlencode($test[1]); $arg0 = urlencode($test[0]); $res_str .= "find \"{$arg1}\" in \"{$arg0}\" - grapheme_strpos"; if (3 == count($test)) { $result = grapheme_strpos($test[0], $test[1]); } else { $res_str .= " from {$test['2']}"; $result = grapheme_strpos($test[0], $test[1], $test[2]); } $res_str .= " = "; if ($result === false) { $res_str .= 'false'; } else { $res_str .= $result; } $res_str .= " == " . $test[count($test) - 1] . check_result($result, $test[count($test) - 1]) . "\n"; } //===================================================================================== $res_str .= "\n" . 'function grapheme_stripos($haystack, $needle, $offset = 0) {}' . "\n\n"; $tests = array(array("ao" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "O", "o", 2, 6), array($char_o_diaeresis_nfd . $char_a_ring_nfd . "a" . $char_A_ring_nfd . "bc", $char_a_ring_nfd, 2, 3), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "O", "o", 5), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd, "O", "false"), array("a" . $char_a_ring_nfd . "bc" . $char_O_diaeresis_nfd, $char_o_diaeresis_nfd, 4), array($char_o_diaeresis_nfd . "a" . $char_a_ring_nfd . "bc", $char_A_ring_nfd, 2), array("a" . $char_A_ring_nfd . "bc", $char_a_ring_nfd, 1), array("Abc", $char_a_ring_nfd, "false"), array($char_a_ring_nfd . "bc", "A", "false"), array("abc", "D", "false"), array("abC", "c", 2), array("abc", "B", 1), array("Abc", "a", 0), array("abc", "A", 0, 0), array("Abc", "a", 1, "false"), array("ababc", "A", 1, 2), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", "oP", 5), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", "opQ", 5), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd, "abc", "false"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "bC" . $char_o_diaeresis_nfd, $char_O_diaeresis_nfd . "bc" . $char_o_diaeresis_nfd, 4), array($char_o_diaeresis_nfd . "a" . $char_a_ring_nfd . "Bc", $char_A_ring_nfd . "bc", 2), array("a" . $char_a_ring_nfd . "BC", $char_a_ring_nfd . "bc", 1), array("abc", $char_a_ring_nfd . "BC", "false"), array($char_a_ring_nfd . "BC", "aBCdefg", "false"), array("aBC", "Defghijklmnopq", "false"), array("abC", "Ab", 0), array("aBC", "bc", 1), array("abC", "Abc", 0), array("abC", "aBcd", "false"), array("ABc", "ab", 0, 0), array("aBc", "abC", 0, 0), array("abc", "aBc", 1, "false"), array("ABabc", "AB", 1, 2), array("abaBc", "aBc", 1, 2), array("ao" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "o" . $char_A_ring_nfd . "bC", "O" . $char_a_ring_nfd . "bC", 2, 6), array($char_o_diaeresis_nfd . $char_a_ring_nfd . "a" . $char_A_ring_nfd . "bC" . $char_a_ring_nfd . "def", $char_a_ring_nfd . "Bc" . $char_a_ring_nfd, 2, 3)); foreach ($tests as $test) { $arg1 = urlencode($test[1]); $arg0 = urlencode($test[0]); $res_str .= "find \"{$arg1}\" in \"{$arg0}\" - grapheme_stripos"; if (3 == count($test)) { $result = grapheme_stripos($test[0], $test[1]); } else { $res_str .= " from {$test['2']}"; $result = grapheme_stripos($test[0], $test[1], $test[2]); } $res_str .= " = "; if ($result === false) { $res_str .= 'false'; } else { $res_str .= $result; } $res_str .= " == " . $test[count($test) - 1] . check_result($result, $test[count($test) - 1]) . "\n"; } //===================================================================================== $res_str .= "\n" . 'function grapheme_strrpos($haystack, $needle, $offset = 0) {}' . "\n\n"; $tests = array(array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "o", "o", 5), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd, "o", "false"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd, $char_o_diaeresis_nfd, 4), array($char_o_diaeresis_nfd . "a" . $char_a_ring_nfd . "bc", $char_a_ring_nfd, 2), array("a" . $char_a_ring_nfd . "bc", $char_a_ring_nfd, 1), array("abc", $char_a_ring_nfd, "false"), array($char_a_ring_nfd . "bc", "a", "false"), array("abc", "d", "false"), array("abc", "c", 2), array("abc", "b", 1), array("abc", "a", 0), array("abc", "a", 0, 0), array("abc", "a", 1, "false"), array("ababc", "a", 1, 2), array("ao" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "o", "o", 2, 6), array($char_o_diaeresis_nfd . $char_a_ring_nfd . "a" . $char_a_ring_nfd . "bc", $char_a_ring_nfd, 2, 3), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "opq", "op", 5), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "opq", "opq", 5), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd, "abc", "false"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "bc" . $char_o_diaeresis_nfd, $char_o_diaeresis_nfd . "bc" . $char_o_diaeresis_nfd, 4), array($char_o_diaeresis_nfd . "a" . $char_a_ring_nfd . "bc", $char_a_ring_nfd . "bc", 2), array("a" . $char_a_ring_nfd . "bc", $char_a_ring_nfd . "bc", 1), array("abc", $char_a_ring_nfd . "bc", "false"), array($char_a_ring_nfd . "bc", "abcdefg", "false"), array("abc", "defghijklmnopq", "false"), array("abc", "ab", 0), array("abc", "bc", 1), array("abc", "abc", 0), array("abc", "abcd", "false"), array("abc", "ab", 0, 0), array("abc", "abc", 0, 0), array("abc", "abc", 1, "false"), array("ababc", "ab", 1, 2), array("ababc", "abc", 1, 2), array("ao" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "o" . $char_a_ring_nfd . "bc", "o" . $char_a_ring_nfd . "bc", 2, 6), array($char_o_diaeresis_nfd . $char_a_ring_nfd . "a" . $char_a_ring_nfd . "bc" . $char_a_ring_nfd . "def", $char_a_ring_nfd . "bc" . $char_a_ring_nfd, 2, 3)); foreach ($tests as $test) { $arg1 = urlencode($test[1]); $arg0 = urlencode($test[0]); $res_str .= "find \"{$arg1}\" in \"{$arg0}\" - grapheme_strrpos"; if (3 == count($test)) { $result = grapheme_strrpos($test[0], $test[1]); } else { $res_str .= " from {$test['2']}"; $result = grapheme_strrpos($test[0], $test[1], $test[2]); } $res_str .= " = "; if ($result === false) { $res_str .= 'false'; } else { $res_str .= $result; } $res_str .= " == " . $test[count($test) - 1] . check_result($result, $test[count($test) - 1]) . "\n"; } //===================================================================================== $res_str .= "\n" . 'function grapheme_strripos($haystack, $needle, $offset = 0) {}' . "\n\n"; $tests = array(array("ao" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "O", "o", 2, 6), array($char_o_diaeresis_nfd . $char_a_ring_nfd . "a" . $char_A_ring_nfd . "bc", $char_a_ring_nfd, 2, 3), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "O", "o", 5), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd, "O", "false"), array("a" . $char_a_ring_nfd . "bc" . $char_O_diaeresis_nfd, $char_o_diaeresis_nfd, 4), array($char_o_diaeresis_nfd . "a" . $char_a_ring_nfd . "bc", $char_A_ring_nfd, 2), array("a" . $char_A_ring_nfd . "bc", $char_a_ring_nfd, 1), array("Abc", $char_a_ring_nfd, "false"), array($char_a_ring_nfd . "bc", "A", "false"), array("abc", "D", "false"), array("abC", "c", 2), array("abc", "B", 1), array("Abc", "a", 0), array("abc", "A", 0, 0), array("Abc", "a", 1, "false"), array("ababc", "A", 1, 2), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", "oP", 5), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", "opQ", 5), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd, "abc", "false"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "bC" . $char_o_diaeresis_nfd, $char_O_diaeresis_nfd . "bc" . $char_o_diaeresis_nfd, 4), array($char_o_diaeresis_nfd . "a" . $char_a_ring_nfd . "Bc", $char_A_ring_nfd . "bc", 2), array("a" . $char_a_ring_nfd . "BC", $char_a_ring_nfd . "bc", 1), array("abc", $char_a_ring_nfd . "BC", "false"), array($char_a_ring_nfd . "BC", "aBCdefg", "false"), array("aBC", "Defghijklmnopq", "false"), array("abC", "Ab", 0), array("aBC", "bc", 1), array("abC", "Abc", 0), array("abC", "aBcd", "false"), array("ABc", "ab", 0, 0), array("aBc", "abC", 0, 0), array("abc", "aBc", 1, "false"), array("ABabc", "AB", 1, 2), array("abaBc", "aBc", 1, 2), array("ao" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "o" . $char_A_ring_nfd . "bC", "O" . $char_a_ring_nfd . "bC", 2, 6), array($char_o_diaeresis_nfd . $char_a_ring_nfd . "a" . $char_A_ring_nfd . "bC" . $char_a_ring_nfd . "def", $char_a_ring_nfd . "Bc" . $char_a_ring_nfd, 2, 3)); foreach ($tests as $test) { $arg1 = urlencode($test[1]); $arg0 = urlencode($test[0]); $res_str .= "find \"{$arg1}\" in \"{$arg0}\" - grapheme_strripos"; if (3 == count($test)) { $result = grapheme_strripos($test[0], $test[1]); } else { $res_str .= " from {$test['2']}"; $result = grapheme_strripos($test[0], $test[1], $test[2]); } $res_str .= " = "; if ($result === false) { $res_str .= 'false'; } else { $res_str .= $result; } $res_str .= " == " . $test[count($test) - 1] . check_result($result, $test[count($test) - 1]) . "\n"; } //===================================================================================== $res_str .= "\n" . 'function grapheme_substr($string, $start, $length = -1) {}' . "\n\n"; $tests = array(array("abc", 3, "false"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd, 5, "false"), array("ao" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "O", 2, $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "O"), array($char_o_diaeresis_nfd . $char_a_ring_nfd . "a" . $char_A_ring_nfd . "bc", 2, "a" . $char_A_ring_nfd . "bc"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "O", 5, "O"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd, 5, "false"), array("a" . $char_a_ring_nfd . "bc" . $char_O_diaeresis_nfd, 4, $char_O_diaeresis_nfd), array($char_o_diaeresis_nfd . "a" . $char_a_ring_nfd . "bc", 2, $char_a_ring_nfd . "bc"), array("a" . $char_A_ring_nfd . "bc", 1, $char_A_ring_nfd . "bc"), array("Abc", -5, "false"), array($char_a_ring_nfd . "bc", 3, "false"), array("abc", 4, "false"), array("abC", 2, "C"), array("abc", 1, "bc"), array("Abc", 1, 1, "b"), array("abc", 0, 2, "ab"), array("Abc", -4, 1, "false"), array("ababc", 1, 2, "ba"), array("ababc", 0, 10, "ababc"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", 0, 10, "a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", 5, "Opq"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", 5, -1, "Op"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", 5, -2, "O"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", 5, -3, ""), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", 5, -4, "false"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", 0, "a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", 0, -1, "a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Op"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", 0, -2, "a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "O"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", 0, -3, "a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", 0, -4, "a" . $char_a_ring_nfd . "bc"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", 0, -5, "a" . $char_a_ring_nfd . "b"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", 0, -6, "a" . $char_a_ring_nfd), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", 0, -7, "a"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", 0, -8, ""), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", 0, -9, "false"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -8, "a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -7, $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -6, "bc" . $char_o_diaeresis_nfd . "Opq"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -5, "c" . $char_o_diaeresis_nfd . "Opq"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -4, $char_o_diaeresis_nfd . "Opq"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -3, "Opq"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -2, "pq"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -1, "q"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -999, "false"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -8, 8, "a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -8, 7, "a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Op"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -8, 6, "a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "O"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -8, 5, "a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -8, 4, "a" . $char_a_ring_nfd . "bc"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -8, 3, "a" . $char_a_ring_nfd . "b"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -8, 2, "a" . $char_a_ring_nfd), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -8, 1, "a"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -8, 0, ""), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -8, -999, "false"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -8, -1, "a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Op"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -8, -2, "a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "O"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -8, -3, "a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -8, -4, "a" . $char_a_ring_nfd . "bc"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -8, -5, "a" . $char_a_ring_nfd . "b"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -8, -6, "a" . $char_a_ring_nfd), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -8, -7, "a"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -8, -8, ""), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "Opq", -8, -9, "false")); foreach ($tests as $test) { $arg0 = urlencode($test[0]); $res_str .= "substring of \"{$arg0}\" from \"{$test['1']}\" - grapheme_substr"; if (3 == count($test)) { $result = grapheme_substr($test[0], $test[1]); } else { $res_str .= " with length {$test['2']}"; $result = grapheme_substr($test[0], $test[1], $test[2]); } $res_str .= " = "; if ($result === false) { $res_str .= 'false'; } else { $res_str .= urlencode($result); } $res_str .= " == " . urlencode($test[count($test) - 1]) . check_result($result, $test[count($test) - 1]) . "\n"; } //===================================================================================== $res_str .= "\n" . 'function grapheme_strstr($haystack, $needle, $before_needle = FALSE) {}' . "\n\n"; $tests = array(array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "o", "o", "o"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd, "o", "false"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd, $char_o_diaeresis_nfd, $char_o_diaeresis_nfd), array($char_o_diaeresis_nfd . "a" . $char_a_ring_nfd . "bc", $char_a_ring_nfd, $char_a_ring_nfd . "bc"), array("a" . $char_a_ring_nfd . "bc", $char_a_ring_nfd, $char_a_ring_nfd . "bc"), array("abc", $char_a_ring_nfd, "false"), array($char_a_ring_nfd . "bc", "a", "false"), array("abc", "d", "false"), array("abc", "c", "c"), array("abc", "b", "bc"), array("abc", "a", "abc"), array("abc", "ab", "abc"), array("abc", "abc", "abc"), array("abc", "bc", "bc"), array("abc", "a", FALSE, "abc"), array("abc", "a", TRUE, ""), array("abc", "b", TRUE, "a"), array("abc", "c", TRUE, "ab"), array("ababc", "bab", TRUE, "a"), array("ababc", "abc", TRUE, "ab"), array("ababc", "abc", FALSE, "abc"), array("ab" . $char_a_ring_nfd . "c", "d", "false"), array("bc" . $char_a_ring_nfd . "a", "a", "a"), array("a" . $char_a_ring_nfd . "bc", "b", "bc"), array($char_a_ring_nfd . "bc", "a", "false"), array($char_a_ring_nfd . "abc", "ab", "abc"), array("abc" . $char_a_ring_nfd, "abc", "abc" . $char_a_ring_nfd), array("a" . $char_a_ring_nfd . "bc", $char_a_ring_nfd . "bc", $char_a_ring_nfd . "bc"), array("a" . $char_a_ring_nfd . "bc", $char_a_ring_nfd, FALSE, $char_a_ring_nfd . "bc"), array("a" . $char_a_ring_nfd . "bc", "a", TRUE, ""), array($char_a_ring_nfd . "abc", "b", TRUE, $char_a_ring_nfd . "a"), array("ab" . $char_a_ring_nfd . "c", "c", TRUE, "ab" . $char_a_ring_nfd), array("aba" . $char_a_ring_nfd . "bc", "ba" . $char_a_ring_nfd . "b", TRUE, "a"), array("ababc" . $char_a_ring_nfd, "abc" . $char_a_ring_nfd, TRUE, "ab"), array("abab" . $char_a_ring_nfd . "c", "ab" . $char_a_ring_nfd . "c", FALSE, "ab" . $char_a_ring_nfd . "c")); foreach ($tests as $test) { $arg1 = urlencode($test[1]); $arg0 = urlencode($test[0]); $res_str .= "find \"{$arg1}\" in \"{$arg0}\" - grapheme_strstr"; if (3 == count($test)) { $result = grapheme_strstr($test[0], $test[1]); } else { $res_str .= " before flag is " . ($test[2] ? "TRUE" : "FALSE"); $result = grapheme_strstr($test[0], $test[1], $test[2]); } $res_str .= " = "; if ($result === false) { $res_str .= 'false'; } else { $res_str .= urlencode($result); } $res_str .= " == " . urlencode($test[count($test) - 1]) . check_result($result, $test[count($test) - 1]) . "\n"; } //===================================================================================== $res_str .= "\n" . 'function grapheme_stristr($haystack, $needle, $before_needle = FALSE) {}' . "\n\n"; $tests = array(array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd, $char_O_diaeresis_nfd, $char_o_diaeresis_nfd), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd . "O", "o", "O"), array("a" . $char_a_ring_nfd . "bc" . $char_o_diaeresis_nfd, "o", "false"), array($char_o_diaeresis_nfd . "a" . $char_a_ring_nfd . "bc", $char_a_ring_nfd, $char_a_ring_nfd . "bc"), array("a" . $char_a_ring_nfd . "bc", $char_A_ring_nfd, $char_a_ring_nfd . "bc"), array("abc", $char_a_ring_nfd, "false"), array($char_a_ring_nfd . "bc", "A", "false"), array("abc", "d", "false"), array("abc", "C", "c"), array("aBc", "b", "Bc"), array("abc", "A", "abc"), array("abC", "ab", "abC"), array("abc", "aBc", "abc"), array("abC", "bc", "bC"), array("abc", "A", FALSE, "abc"), array("abc", "a", TRUE, ""), array("aBc", "b", TRUE, "a"), array("abc", "C", TRUE, "ab"), array("aBabc", "bab", TRUE, "a"), array("ababc", "aBc", TRUE, "ab"), array("ababc", "abC", FALSE, "abc"), array("ab" . $char_a_ring_nfd . "c", "d", "false"), array("bc" . $char_a_ring_nfd . "A", "a", "A"), array("a" . $char_a_ring_nfd . "bc", "B", "bc"), array($char_A_ring_nfd . "bc", "a", "false"), array($char_a_ring_nfd . "abc", "Ab", "abc"), array("abc" . $char_A_ring_nfd, "abc", "abc" . $char_A_ring_nfd), array("a" . $char_a_ring_nfd . "bc", $char_A_ring_nfd . "bc", $char_a_ring_nfd . "bc"), array("a" . $char_A_ring_nfd . "bc", $char_a_ring_nfd, FALSE, $char_A_ring_nfd . "bc"), array("a" . $char_a_ring_nfd . "bc", "A", TRUE, ""), array($char_a_ring_nfd . "aBc", "b", TRUE, $char_a_ring_nfd . "a"), array("ab" . $char_a_ring_nfd . "c", "C", TRUE, "ab" . $char_a_ring_nfd), array("aba" . $char_A_ring_nfd . "bc", "ba" . $char_a_ring_nfd . "b", TRUE, "a"), array("ababc" . $char_a_ring_nfd, "aBc" . $char_A_ring_nfd, TRUE, "ab"), array("abAB" . $char_A_ring_nfd . "c", "ab" . $char_a_ring_nfd . "c", FALSE, "AB" . $char_A_ring_nfd . "c")); foreach ($tests as $test) { $arg1 = urlencode($test[1]); $arg0 = urlencode($test[0]); $res_str .= "find \"{$arg1}\" in \"{$arg0}\" - grapheme_stristr"; if (3 == count($test)) { $result = grapheme_stristr($test[0], $test[1]); } else { $res_str .= " before flag is " . ($test[2] ? "TRUE" : "FALSE"); $result = grapheme_stristr($test[0], $test[1], $test[2]); } $res_str .= " = "; if ($result === false) { $res_str .= 'false'; } else { $res_str .= urlencode($result); } $res_str .= " == " . urlencode($test[count($test) - 1]) . check_result($result, $test[count($test) - 1]) . "\n"; } //===================================================================================== $res_str .= "\n" . 'function grapheme_extract($haystack, $size, $extract_type = GRAPHEME_EXTR_COUNT, $start = 0[, $next])' . "\n\n"; $tests = array(array("abc", 3, "abc"), array("abc", 2, "ab"), array("abc", 1, "a"), array("abc", 0, ""), array("abc", 1, 0, "a"), array("abc", 1, 1, "b"), array("abc", 1, 2, "c"), array("abc", 0, 2, ""), array("abc", 3, 0, 3, "abc"), array("abc", 2, 0, 2, "ab"), array("abc", 1, 0, 1, "a"), array("abc", 0, 0, 0, ""), array("abc", 1, 0, 1, "a"), array("abc", 1, 1, 2, "b"), array("abc", 1, 2, 3, "c"), array("abc", 0, 2, 2, ""), array("http://news.bbc.co.uk/2/hi/middle_east/7831588.stm", 48, 48, 50, "tm"), array($char_a_ring_nfd . "bc", 3, $char_a_ring_nfd . "bc"), array($char_a_ring_nfd . "bc", 2, $char_a_ring_nfd . "b"), array($char_a_ring_nfd . "bc", 1, $char_a_ring_nfd . ""), array($char_a_ring_nfd . "bc", 3, 0, 5, $char_a_ring_nfd . "bc"), array($char_a_ring_nfd . "bc", 2, 0, 4, $char_a_ring_nfd . "b"), array($char_a_ring_nfd . "bc", 1, 0, 3, $char_a_ring_nfd . ""), array($char_a_ring_nfd . "bcde", 2, 3, 5, "bc"), array($char_a_ring_nfd . "bcde", 2, 4, 6, "cd"), array($char_a_ring_nfd . "bcde" . $char_a_ring_nfd . "f", 4, 5, 11, "de" . $char_a_ring_nfd . "f"), array($char_a_ring_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 3, $char_a_ring_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd), array($char_a_ring_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 2, $char_a_ring_nfd . $char_o_diaeresis_nfd), array($char_a_ring_nfd . $char_o_diaeresis_nfd . "c", 1, $char_a_ring_nfd . ""), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 1, 0, $char_o_diaeresis_nfd), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 1, 2, $char_o_diaeresis_nfd), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 1, 3, $char_o_diaeresis_nfd), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 1, 4, $char_diaeresis), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 2, 0, $char_o_diaeresis_nfd . $char_o_diaeresis_nfd), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 2, 2, $char_o_diaeresis_nfd . $char_o_diaeresis_nfd), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 2, 3, $char_o_diaeresis_nfd . $char_o_diaeresis_nfd), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 2, 4, $char_diaeresis . $char_o_diaeresis_nfd), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 2, 7, $char_diaeresis . $char_o_diaeresis_nfd), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 2, 8, $char_o_diaeresis_nfd), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 2, 10, $char_diaeresis), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 2, 11, "false")); $next = -1; foreach ($tests as $test) { $arg0 = urlencode($test[0]); $res_str .= "extract from \"{$arg0}\" \"{$test['1']}\" graphemes - grapheme_extract"; if (3 == count($test)) { $result = grapheme_extract($test[0], $test[1]); } elseif (4 == count($test)) { $res_str .= " starting at byte position {$test['2']}"; $result = grapheme_extract($test[0], $test[1], GRAPHEME_EXTR_COUNT, $test[2]); } else { $res_str .= " starting at byte position {$test['2']} with \$next"; $result = grapheme_extract($test[0], $test[1], GRAPHEME_EXTR_COUNT, $test[2], $next); } $res_str .= " = "; if ($result === false) { $res_str .= 'false'; } else { $res_str .= urlencode($result); } $res_str .= " == " . urlencode($test[count($test) - 1]) . check_result($result, $test[count($test) - 1]); if (5 == count($test)) { $res_str .= " \$next={$next} == {$test['3']} "; if ($next != $test[3]) { $res_str .= "***FAILED***"; } } $res_str .= "\n"; } //===================================================================================== $res_str .= "\n" . 'function grapheme_extract($haystack, $size, $extract_type = GRAPHEME_EXTR_MAXBYTES, $start = 0)' . "\n\n"; $tests = array(array("abc", 3, "abc"), array("abc", 2, "ab"), array("abc", 1, "a"), array("abc", 0, ""), array($char_a_ring_nfd . "bc", 5, $char_a_ring_nfd . "bc"), array($char_a_ring_nfd . "bc", 4, $char_a_ring_nfd . "b"), array($char_a_ring_nfd . "bc", 1, ""), array($char_a_ring_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 9, $char_a_ring_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd), array($char_a_ring_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 10, $char_a_ring_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd), array($char_a_ring_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 11, $char_a_ring_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd), array($char_a_ring_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 6, $char_a_ring_nfd . $char_o_diaeresis_nfd), array($char_a_ring_nfd . $char_o_diaeresis_nfd . "c", 3, $char_a_ring_nfd . ""), array($char_a_ring_nfd . $char_o_diaeresis_nfd . "c", 4, $char_a_ring_nfd . ""), array($char_a_ring_nfd . $char_o_diaeresis_nfd . "c", 5, $char_a_ring_nfd . ""), array($char_a_ring_nfd . $char_o_diaeresis_nfd . "c", 6, $char_a_ring_nfd . $char_o_diaeresis_nfd), array($char_a_ring_nfd . $char_o_diaeresis_nfd . "c", 7, $char_a_ring_nfd . $char_o_diaeresis_nfd . "c"), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 3, 0, $char_o_diaeresis_nfd), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 3, 2, $char_o_diaeresis_nfd), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 3, 3, $char_o_diaeresis_nfd), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 3, 4, $char_diaeresis), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 6, 0, $char_o_diaeresis_nfd . $char_o_diaeresis_nfd), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 6, 2, $char_o_diaeresis_nfd . $char_o_diaeresis_nfd), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 6, 3, $char_o_diaeresis_nfd . $char_o_diaeresis_nfd), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 5, 4, $char_diaeresis . $char_o_diaeresis_nfd), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 5, 7, $char_diaeresis . $char_o_diaeresis_nfd), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 3, 8, $char_o_diaeresis_nfd), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 2, 10, $char_diaeresis), array($char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd . $char_o_diaeresis_nfd, 2, 11, "false")); foreach ($tests as $test) { $arg0 = urlencode($test[0]); $res_str .= "extract from \"{$arg0}\" \"{$test['1']}\" graphemes - grapheme_extract GRAPHEME_EXTR_MAXBYTES"; if (3 == count($test)) { $result = grapheme_extract($test[0], $test[1], GRAPHEME_EXTR_MAXBYTES); } else { $res_str .= " starting at byte position {$test['2']}"; $result = grapheme_extract($test[0], $test[1], GRAPHEME_EXTR_MAXBYTES, $test[2]); } $res_str .= " = "; if ($result === false) { $res_str .= 'false'; } else { $res_str .= urlencode($result); } $res_str .= " == " . urlencode($test[count($test) - 1]) . check_result($result, $test[count($test) - 1]) . "\n"; } //===================================================================================== $res_str .= "\n" . 'function grapheme_extract($haystack, $size, $extract_type = GRAPHEME_EXTR_MAXCHARS, $start = 0)' . "\n\n"; $tests = array(array("abc", 3, "abc"), array("abc", 2, "ab"), array("abc", 1, "a"), array("abc", 0, ""), array("abc" . $char_o_diaeresis_nfd, 0, ""), array("abc" . $char_o_diaeresis_nfd, 1, "a"), array("abc" . $char_o_diaeresis_nfd, 2, "ab"), array("abc" . $char_o_diaeresis_nfd, 3, "abc"), array("abc" . $char_o_diaeresis_nfd, 4, "abc"), array("abc" . $char_o_diaeresis_nfd, 5, "abc" . $char_o_diaeresis_nfd), array("abc" . $char_o_diaeresis_nfd, 6, "abc" . $char_o_diaeresis_nfd), array($char_o_diaeresis_nfd . "abc", 0, ""), array($char_o_diaeresis_nfd . "abc", 1, ""), array($char_o_diaeresis_nfd . "abc", 2, $char_o_diaeresis_nfd), array($char_o_diaeresis_nfd . "abc", 3, $char_o_diaeresis_nfd . "a"), array($char_o_diaeresis_nfd . "abc", 4, $char_o_diaeresis_nfd . "ab"), array($char_o_diaeresis_nfd . "abc" . $char_a_ring_nfd . "xyz", 5, $char_o_diaeresis_nfd . "abc"), array($char_o_diaeresis_nfd . "abc" . $char_a_ring_nfd . "xyz", 6, $char_o_diaeresis_nfd . "abc"), array($char_o_diaeresis_nfd . "abc" . $char_a_ring_nfd . "xyz", 7, $char_o_diaeresis_nfd . "abc" . $char_a_ring_nfd), array($char_o_diaeresis_nfd . "abc" . $char_a_ring_nfd . "xyz", 8, $char_o_diaeresis_nfd . "abc" . $char_a_ring_nfd . "x"), array("abc", 3, 0, "abc"), array("abc", 2, 1, "bc"), array("abc", 1, 2, "c"), array("abc", 0, 3, "false"), array("abc", 1, 3, "false"), array("abc", 1, 999, "false"), array($char_o_diaeresis_nfd . "abc", 1, 6, "false"), array($char_o_diaeresis_nfd . "abc", 1, 999, "false"), array($char_o_diaeresis_nfd . "abc" . $char_a_ring_nfd . "xyz", 8, 0, $char_o_diaeresis_nfd . "abc" . $char_a_ring_nfd . "x"), array($char_o_diaeresis_nfd . "abc" . $char_a_ring_nfd . "xyz", 8, 1, $char_diaeresis . "abc" . $char_a_ring_nfd . "xy"), array($char_o_diaeresis_nfd . "abc" . $char_a_ring_nfd . "xyz", 8, 2, "abc" . $char_a_ring_nfd . "xyz"), array($char_o_diaeresis_nfd . "abc" . $char_a_ring_nfd . "xyz", 8, 3, "abc" . $char_a_ring_nfd . "xyz"), array($char_o_diaeresis_nfd . "abc" . $char_a_ring_nfd . "xyz", 8, 4, "bc" . $char_a_ring_nfd . "xyz"), array($char_o_diaeresis_nfd . "abc" . $char_a_ring_nfd . "xyz", 8, 5, "c" . $char_a_ring_nfd . "xyz"), array($char_o_diaeresis_nfd . "abc" . $char_a_ring_nfd . "xyz", 8, 6, $char_a_ring_nfd . "xyz")); foreach ($tests as $test) { $arg0 = urlencode($test[0]); $res_str .= "extract from \"{$arg0}\" \"{$test['1']}\" graphemes - grapheme_extract GRAPHEME_EXTR_MAXCHARS"; if (3 == count($test)) { $result = grapheme_extract($test[0], $test[1], GRAPHEME_EXTR_MAXCHARS); } else { $res_str .= " starting at byte position {$test['2']}"; $result = grapheme_extract($test[0], $test[1], GRAPHEME_EXTR_MAXCHARS, $test[2]); } $res_str .= " = "; if ($result === false) { $res_str .= 'false'; } else { $res_str .= urlencode($result); } $res_str .= " == " . urlencode($test[count($test) - 1]) . check_result($result, $test[count($test) - 1]) . "\n"; } //===================================================================================== return $res_str; }
/** * Find position of first occurrence of string in a string * * @link http://php.net/manual/en/function.mb-strpos.php * * @param string $haystack <p> * The string being checked. * </p> * @param string $needle <p> * The position counted from the beginning of haystack. * </p> * @param int $offset [optional] <p> * The search offset. If it is not specified, 0 is used. * </p> * @param boolean $cleanUtf8 Clean non UTF-8 chars from the string * * @return int the numeric position of * the first occurrence of needle in the * haystack string. If * needle is not found, it returns false. */ public static function strpos($haystack, $needle, $offset = 0, $cleanUtf8 = false) { $haystack = (string) $haystack; $needle = (string) $needle; if (!isset($haystack[0]) || !isset($needle[0])) { return false; } // init self::checkForSupport(); $offset = (int) $offset; // iconv and mbstring do not support integer $needle if ((int) $needle === $needle && $needle >= 0) { $needle = self::chr($needle); } if ($cleanUtf8 === true) { // mb_strpos returns wrong position if invalid characters are found in $haystack before $needle // iconv_strpos is not tolerant to invalid characters $needle = self::clean((string) $needle); $haystack = self::clean($haystack); } if (self::$support['mbstring'] === true) { return mb_strpos($haystack, $needle, $offset, 'UTF-8'); } if (self::$support['iconv'] === true) { return grapheme_strpos($haystack, $needle, $offset); } if ($offset > 0) { $haystack = self::substr($haystack, $offset); } if (($pos = strpos($haystack, $needle)) !== false) { $left = substr($haystack, 0, $pos); // negative offset not supported in PHP strpos(), ignoring return ($offset > 0 ? $offset : 0) + self::strlen($left); } return false; }