@@ -7,156 +7,156 @@ |
||
| 7 | 7 | */ |
| 8 | 8 | class Multibyte |
| 9 | 9 | { |
| 10 | - //https://stackoverflow.com/questions/20025030/convert-all-types-of-smart-quotes-with-php |
|
| 11 | - private static $unicodeCharacterMap = [ |
|
| 12 | - // Windows codepage 1252 |
|
| 13 | - "\xC2\x82" => "'", // U+0082⇒U+201A single low-9 quotation mark |
|
| 14 | - "\xC2\x84" => '"', // U+0084⇒U+201E double low-9 quotation mark |
|
| 15 | - "\xC2\x8B" => "'", // U+008B⇒U+2039 single left-pointing angle quotation mark |
|
| 16 | - "\xC2\x91" => "'", // U+0091⇒U+2018 left single quotation mark |
|
| 17 | - "\xC2\x92" => "'", // U+0092⇒U+2019 right single quotation mark |
|
| 18 | - "\xC2\x93" => '"', // U+0093⇒U+201C left double quotation mark |
|
| 19 | - "\xC2\x94" => '"', // U+0094⇒U+201D right double quotation mark |
|
| 20 | - "\xC2\x9B" => "'", // U+009B⇒U+203A single right-pointing angle quotation mark |
|
| 21 | - // Regular Unicode // U+0022 quotation mark (") |
|
| 22 | - // U+0027 apostrophe (') |
|
| 23 | - "\xC2\xAB" => '"', // U+00AB left-pointing double angle quotation mark |
|
| 24 | - "\xC2\xBB" => '"', // U+00BB right-pointing double angle quotation mark |
|
| 25 | - "\xE2\x80\x98" => "'", // U+2018 left single quotation mark |
|
| 26 | - "\xE2\x80\x99" => "'", // U+2019 right single quotation mark |
|
| 27 | - "\xE2\x80\x9A" => "'", // U+201A single low-9 quotation mark |
|
| 28 | - "\xE2\x80\x9B" => "'", // U+201B single high-reversed-9 quotation mark |
|
| 29 | - "\xE2\x80\x9C" => '"', // U+201C left double quotation mark |
|
| 30 | - "\xE2\x80\x9D" => '"', // U+201D right double quotation mark |
|
| 31 | - "\xE2\x80\x9E" => '"', // U+201E double low-9 quotation mark |
|
| 32 | - "\xE2\x80\x9F" => '"', // U+201F double high-reversed-9 quotation mark |
|
| 33 | - "\xE2\x80\xB9" => "'", // U+2039 single left-pointing angle quotation mark |
|
| 34 | - "\xE2\x80\xBA" => "'", // U+203A single right-pointing angle quotation mark |
|
| 35 | - ]; |
|
| 36 | - |
|
| 37 | - /** |
|
| 38 | - * Replace |
|
| 39 | - * |
|
| 40 | - * @staticvar array $chr_map |
|
| 41 | - * @param string $string |
|
| 42 | - * @return string |
|
| 43 | - */ |
|
| 44 | - public static function cleanUnicode($string) |
|
| 45 | - { |
|
| 46 | - $character = array_keys(self::$unicodeCharacterMap); // but: for efficiency you should |
|
| 47 | - $replace = array_values(self::$unicodeCharacterMap); // pre-calculate these two arrays |
|
| 48 | - return str_replace($character, $replace, html_entity_decode($string, ENT_QUOTES, "UTF-8")); |
|
| 49 | - } |
|
| 50 | - |
|
| 51 | - /** |
|
| 52 | - * Multibyte.php safe version of standard trim() function. |
|
| 53 | - * |
|
| 54 | - * @param string $string |
|
| 55 | - * @return string |
|
| 56 | - */ |
|
| 57 | - public static function trim($string) |
|
| 58 | - { |
|
| 59 | - return mb_ereg_replace('^\s*([\s\S]*?)\s*$', '\1', $string); |
|
| 60 | - } |
|
| 61 | - |
|
| 62 | - /** |
|
| 63 | - * A cross between mb_split and preg_split, adding the preg_split flags |
|
| 64 | - * to mb_split. |
|
| 65 | - * |
|
| 66 | - * @param string $pattern |
|
| 67 | - * @param string $string |
|
| 68 | - * @param int $limit |
|
| 69 | - * @param int $flags |
|
| 70 | - * @return array |
|
| 71 | - */ |
|
| 72 | - public static function split($pattern, $string, $limit = -1, $flags = 0) |
|
| 73 | - { |
|
| 74 | - $split_no_empty = (bool)($flags & PREG_SPLIT_NO_EMPTY); |
|
| 75 | - $offset_capture = (bool)($flags & PREG_SPLIT_OFFSET_CAPTURE); |
|
| 76 | - $delim_capture = (bool)($flags & PREG_SPLIT_DELIM_CAPTURE); |
|
| 77 | - |
|
| 78 | - $lengths = self::getSplitLengths($pattern, $string); |
|
| 79 | - |
|
| 80 | - // Substrings |
|
| 81 | - $parts = []; |
|
| 82 | - $position = 0; |
|
| 83 | - $count = 1; |
|
| 84 | - foreach ($lengths as $length) { |
|
| 85 | - $split_empty = !$split_no_empty || $length[0]; |
|
| 86 | - $is_delimiter = $length[1]; |
|
| 87 | - $is_captured = $delim_capture && $length[2]; |
|
| 88 | - |
|
| 89 | - if ($limit > 0 |
|
| 90 | - && !$is_delimiter |
|
| 91 | - && $split_empty |
|
| 92 | - && ++$count > $limit) { |
|
| 93 | - |
|
| 94 | - $parts[] = self::makePart($string, $position, null, $offset_capture); |
|
| 95 | - return $parts; |
|
| 96 | - } |
|
| 97 | - |
|
| 98 | - if ((!$is_delimiter |
|
| 99 | - || $is_captured) |
|
| 100 | - && $split_empty) { |
|
| 101 | - |
|
| 102 | - $parts[] = self::makePart($string, $position, $length[0], $offset_capture); |
|
| 103 | - } |
|
| 104 | - |
|
| 105 | - $position += $length[0]; |
|
| 106 | - } |
|
| 107 | - |
|
| 108 | - return $parts; |
|
| 109 | - } |
|
| 110 | - |
|
| 111 | - /** |
|
| 112 | - * Make part |
|
| 113 | - * @param string $string |
|
| 114 | - * @param integer $position |
|
| 115 | - * @param integer|null $length |
|
| 116 | - * @param bool $offset_capture |
|
| 117 | - * @return array|string |
|
| 118 | - */ |
|
| 119 | - private static function makePart($string, $position, $length = null, $offset_capture = false) |
|
| 120 | - { |
|
| 121 | - $cut = mb_strcut($string, $position, $length); |
|
| 122 | - |
|
| 123 | - return $offset_capture |
|
| 124 | - ? [$cut, $position] |
|
| 125 | - : $cut; |
|
| 126 | - } |
|
| 127 | - |
|
| 128 | - /** |
|
| 129 | - * Splits the string by pattern and for each element (part or split) returns: |
|
| 130 | - * [ 0 => length, 1 => is_delimiter?, 2 => |
|
| 131 | - * |
|
| 132 | - * @param $pattern |
|
| 133 | - * @param $string |
|
| 134 | - * @return array |
|
| 135 | - */ |
|
| 136 | - private static function getSplitLengths($pattern, $string) |
|
| 137 | - { |
|
| 138 | - $strlen = strlen($string); // bytes! |
|
| 139 | - $lengths = []; |
|
| 140 | - |
|
| 141 | - mb_ereg_search_init($string); |
|
| 142 | - |
|
| 143 | - $position = 0; |
|
| 144 | - while ($position < $strlen |
|
| 145 | - && ($array = mb_ereg_search_pos($pattern, '')) !== false) { |
|
| 146 | - // capture split |
|
| 147 | - $lengths[] = [$array[0] - $position, false, null]; |
|
| 148 | - |
|
| 149 | - // move position |
|
| 150 | - $position = $array[0] + $array[1]; |
|
| 151 | - |
|
| 152 | - // capture delimiter |
|
| 153 | - $regs = mb_ereg_search_getregs(); |
|
| 154 | - $lengths[] = [$array[1], true, isset($regs[1]) && $regs[1]]; |
|
| 155 | - } |
|
| 156 | - |
|
| 157 | - // Add last bit, if not ending with split |
|
| 158 | - $lengths[] = [$strlen - $position, false, null]; |
|
| 159 | - |
|
| 160 | - return $lengths; |
|
| 161 | - } |
|
| 10 | + //https://stackoverflow.com/questions/20025030/convert-all-types-of-smart-quotes-with-php |
|
| 11 | + private static $unicodeCharacterMap = [ |
|
| 12 | + // Windows codepage 1252 |
|
| 13 | + "\xC2\x82" => "'", // U+0082⇒U+201A single low-9 quotation mark |
|
| 14 | + "\xC2\x84" => '"', // U+0084⇒U+201E double low-9 quotation mark |
|
| 15 | + "\xC2\x8B" => "'", // U+008B⇒U+2039 single left-pointing angle quotation mark |
|
| 16 | + "\xC2\x91" => "'", // U+0091⇒U+2018 left single quotation mark |
|
| 17 | + "\xC2\x92" => "'", // U+0092⇒U+2019 right single quotation mark |
|
| 18 | + "\xC2\x93" => '"', // U+0093⇒U+201C left double quotation mark |
|
| 19 | + "\xC2\x94" => '"', // U+0094⇒U+201D right double quotation mark |
|
| 20 | + "\xC2\x9B" => "'", // U+009B⇒U+203A single right-pointing angle quotation mark |
|
| 21 | + // Regular Unicode // U+0022 quotation mark (") |
|
| 22 | + // U+0027 apostrophe (') |
|
| 23 | + "\xC2\xAB" => '"', // U+00AB left-pointing double angle quotation mark |
|
| 24 | + "\xC2\xBB" => '"', // U+00BB right-pointing double angle quotation mark |
|
| 25 | + "\xE2\x80\x98" => "'", // U+2018 left single quotation mark |
|
| 26 | + "\xE2\x80\x99" => "'", // U+2019 right single quotation mark |
|
| 27 | + "\xE2\x80\x9A" => "'", // U+201A single low-9 quotation mark |
|
| 28 | + "\xE2\x80\x9B" => "'", // U+201B single high-reversed-9 quotation mark |
|
| 29 | + "\xE2\x80\x9C" => '"', // U+201C left double quotation mark |
|
| 30 | + "\xE2\x80\x9D" => '"', // U+201D right double quotation mark |
|
| 31 | + "\xE2\x80\x9E" => '"', // U+201E double low-9 quotation mark |
|
| 32 | + "\xE2\x80\x9F" => '"', // U+201F double high-reversed-9 quotation mark |
|
| 33 | + "\xE2\x80\xB9" => "'", // U+2039 single left-pointing angle quotation mark |
|
| 34 | + "\xE2\x80\xBA" => "'", // U+203A single right-pointing angle quotation mark |
|
| 35 | + ]; |
|
| 36 | + |
|
| 37 | + /** |
|
| 38 | + * Replace |
|
| 39 | + * |
|
| 40 | + * @staticvar array $chr_map |
|
| 41 | + * @param string $string |
|
| 42 | + * @return string |
|
| 43 | + */ |
|
| 44 | + public static function cleanUnicode($string) |
|
| 45 | + { |
|
| 46 | + $character = array_keys(self::$unicodeCharacterMap); // but: for efficiency you should |
|
| 47 | + $replace = array_values(self::$unicodeCharacterMap); // pre-calculate these two arrays |
|
| 48 | + return str_replace($character, $replace, html_entity_decode($string, ENT_QUOTES, "UTF-8")); |
|
| 49 | + } |
|
| 50 | + |
|
| 51 | + /** |
|
| 52 | + * Multibyte.php safe version of standard trim() function. |
|
| 53 | + * |
|
| 54 | + * @param string $string |
|
| 55 | + * @return string |
|
| 56 | + */ |
|
| 57 | + public static function trim($string) |
|
| 58 | + { |
|
| 59 | + return mb_ereg_replace('^\s*([\s\S]*?)\s*$', '\1', $string); |
|
| 60 | + } |
|
| 61 | + |
|
| 62 | + /** |
|
| 63 | + * A cross between mb_split and preg_split, adding the preg_split flags |
|
| 64 | + * to mb_split. |
|
| 65 | + * |
|
| 66 | + * @param string $pattern |
|
| 67 | + * @param string $string |
|
| 68 | + * @param int $limit |
|
| 69 | + * @param int $flags |
|
| 70 | + * @return array |
|
| 71 | + */ |
|
| 72 | + public static function split($pattern, $string, $limit = -1, $flags = 0) |
|
| 73 | + { |
|
| 74 | + $split_no_empty = (bool)($flags & PREG_SPLIT_NO_EMPTY); |
|
| 75 | + $offset_capture = (bool)($flags & PREG_SPLIT_OFFSET_CAPTURE); |
|
| 76 | + $delim_capture = (bool)($flags & PREG_SPLIT_DELIM_CAPTURE); |
|
| 77 | + |
|
| 78 | + $lengths = self::getSplitLengths($pattern, $string); |
|
| 79 | + |
|
| 80 | + // Substrings |
|
| 81 | + $parts = []; |
|
| 82 | + $position = 0; |
|
| 83 | + $count = 1; |
|
| 84 | + foreach ($lengths as $length) { |
|
| 85 | + $split_empty = !$split_no_empty || $length[0]; |
|
| 86 | + $is_delimiter = $length[1]; |
|
| 87 | + $is_captured = $delim_capture && $length[2]; |
|
| 88 | + |
|
| 89 | + if ($limit > 0 |
|
| 90 | + && !$is_delimiter |
|
| 91 | + && $split_empty |
|
| 92 | + && ++$count > $limit) { |
|
| 93 | + |
|
| 94 | + $parts[] = self::makePart($string, $position, null, $offset_capture); |
|
| 95 | + return $parts; |
|
| 96 | + } |
|
| 97 | + |
|
| 98 | + if ((!$is_delimiter |
|
| 99 | + || $is_captured) |
|
| 100 | + && $split_empty) { |
|
| 101 | + |
|
| 102 | + $parts[] = self::makePart($string, $position, $length[0], $offset_capture); |
|
| 103 | + } |
|
| 104 | + |
|
| 105 | + $position += $length[0]; |
|
| 106 | + } |
|
| 107 | + |
|
| 108 | + return $parts; |
|
| 109 | + } |
|
| 110 | + |
|
| 111 | + /** |
|
| 112 | + * Make part |
|
| 113 | + * @param string $string |
|
| 114 | + * @param integer $position |
|
| 115 | + * @param integer|null $length |
|
| 116 | + * @param bool $offset_capture |
|
| 117 | + * @return array|string |
|
| 118 | + */ |
|
| 119 | + private static function makePart($string, $position, $length = null, $offset_capture = false) |
|
| 120 | + { |
|
| 121 | + $cut = mb_strcut($string, $position, $length); |
|
| 122 | + |
|
| 123 | + return $offset_capture |
|
| 124 | + ? [$cut, $position] |
|
| 125 | + : $cut; |
|
| 126 | + } |
|
| 127 | + |
|
| 128 | + /** |
|
| 129 | + * Splits the string by pattern and for each element (part or split) returns: |
|
| 130 | + * [ 0 => length, 1 => is_delimiter?, 2 => |
|
| 131 | + * |
|
| 132 | + * @param $pattern |
|
| 133 | + * @param $string |
|
| 134 | + * @return array |
|
| 135 | + */ |
|
| 136 | + private static function getSplitLengths($pattern, $string) |
|
| 137 | + { |
|
| 138 | + $strlen = strlen($string); // bytes! |
|
| 139 | + $lengths = []; |
|
| 140 | + |
|
| 141 | + mb_ereg_search_init($string); |
|
| 142 | + |
|
| 143 | + $position = 0; |
|
| 144 | + while ($position < $strlen |
|
| 145 | + && ($array = mb_ereg_search_pos($pattern, '')) !== false) { |
|
| 146 | + // capture split |
|
| 147 | + $lengths[] = [$array[0] - $position, false, null]; |
|
| 148 | + |
|
| 149 | + // move position |
|
| 150 | + $position = $array[0] + $array[1]; |
|
| 151 | + |
|
| 152 | + // capture delimiter |
|
| 153 | + $regs = mb_ereg_search_getregs(); |
|
| 154 | + $lengths[] = [$array[1], true, isset($regs[1]) && $regs[1]]; |
|
| 155 | + } |
|
| 156 | + |
|
| 157 | + // Add last bit, if not ending with split |
|
| 158 | + $lengths[] = [$strlen - $position, false, null]; |
|
| 159 | + |
|
| 160 | + return $lengths; |
|
| 161 | + } |
|
| 162 | 162 | } |
| 163 | 163 | \ No newline at end of file |