|
| 1 | +<?php |
| 2 | + |
| 3 | +/** |
| 4 | + * The SMSCounter class |
| 5 | + * Inspired by the Javascript library https://github.com/danxexe/sms-counter |
| 6 | + * @author - acpmasquerade <acpamsquerade@gmail.com> |
| 7 | + * @date - 05th March, 2014 |
| 8 | + * |
| 9 | + * License Information |
| 10 | + * ------------------------------------------------------------------------------- |
| 11 | + * | Permission is hereby granted, free of charge, to any person obtaining a copy |
| 12 | + * | of this software and associated documentation files (the "Software"), to deal |
| 13 | + * | in the Software without restriction, including without limitation the rights |
| 14 | + * | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell |
| 15 | + * | copies of the Software, and to permit persons to whom the Software is |
| 16 | + * | furnished to do so, subject to the following conditions: |
| 17 | + * | |
| 18 | + * | The above copyright notice and this permission notice shall be included in |
| 19 | + * | all copies or substantial portions of the Software. |
| 20 | + * | |
| 21 | + * | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR |
| 22 | + * | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, |
| 23 | + * | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE |
| 24 | + * | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER |
| 25 | + * | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, |
| 26 | + * | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN |
| 27 | + * | THE SOFTWARE. |
| 28 | + * ------------------------------------------------------------------------------- |
| 29 | + */ |
| 30 | + |
| 31 | +class SMSCounter{ |
| 32 | + |
| 33 | + # character set for GSM 7 Bit charset |
| 34 | + # @deprecated |
| 35 | + const gsm_7bit_chars = "@£\$¥èéùìòÇ\nØø\rÅåΔ_ΦΓΛΩΠΨΣΘΞÆæßÉ !\"#¤%&'()*+,-./0123456789:;<=>?¡ABCDEFGHIJKLMNOPQRSTUVWXYZÄÖÑܧ¿abcdefghijklmnopqrstuvwxyzäöñüà"; |
| 36 | + |
| 37 | + # character set for GSM 7 Bit charset (each character takes two length) |
| 38 | + # @deprecated |
| 39 | + const gsm_7bitEx_chars = "\\^{}\\\\\\€[~\\]\\|"; |
| 40 | + |
| 41 | + const GSM_7BIT = 'GSM_7BIT'; |
| 42 | + const GSM_7BIT_EX = 'GSM_7BIT_EX'; |
| 43 | + const UTF16 = 'UTF16'; |
| 44 | + |
| 45 | + public static function int_gsm_7bit_map(){ |
| 46 | + return array(10,32,33,34,35,36,37,38,39,40,41,42,44,45,46,47,48,49,50, |
| 47 | + 51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70, |
| 48 | + 71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90, |
| 49 | + 92,95,97,98,99,100,101,102,103,104,105,106,107,108,109,110, |
| 50 | + 111,112,113,114,115,116,117,118,119,120,121,122, |
| 51 | + 161,163,164,165,191,196,197,198,199,201,209,214, |
| 52 | + 216,220,223,224,228,229,230,232,233,236,241,242, |
| 53 | + 246,248,249,252,915,916,920,923,926,928,931,934, |
| 54 | + 936,937); |
| 55 | + } |
| 56 | + |
| 57 | + public static function int_gsm_7bit_ex_map(){ |
| 58 | + return array(91,92,93,94,123,124,125,126,8364); |
| 59 | + } |
| 60 | + |
| 61 | + public static function int_gsm_7bit_combined_map(){ |
| 62 | + return array_merge(self::int_gsm_7bit_map(), self::int_gsm_7bit_ex_map()); |
| 63 | + } |
| 64 | + |
| 65 | + # message length for GSM 7 Bit charset |
| 66 | + const messageLength_GSM_7BIT = 160; |
| 67 | + # message length for GSM 7 Bit charset with extended characters |
| 68 | + const messageLength_GSM_7BIT_EX = 160; |
| 69 | + # message length for UTF16 charset |
| 70 | + const messageLength_UTF16 = 70; |
| 71 | + |
| 72 | + # message length for multipart message in GSM 7 Bit encoding |
| 73 | + const multiMessageLength_GSM_7BIT = 153; |
| 74 | + # message length for multipart message in GSM 7 Bit encoding with extended characters |
| 75 | + const multiMessageLength_GSM_7BIT_EX = 153; |
| 76 | + # message length for multipart message in UTF16 encoding |
| 77 | + const multiMessageLength_UTF16 = 67; |
| 78 | + |
| 79 | + /** |
| 80 | + * function count($text) |
| 81 | + * Detects the encoding, Counts the characters, message length, remaining characters |
| 82 | + * @return - stdClass Object with params encoding,length,per_message,remaining,messages |
| 83 | + */ |
| 84 | + public static function count($text){ |
| 85 | + |
| 86 | + $unicode_array = self::utf8_to_unicode($text); |
| 87 | + |
| 88 | + # variable to catch if any ex chars while encoding detection. |
| 89 | + $ex_chars = array(); |
| 90 | + $encoding = self::detect_encoding($unicode_array, $ex_chars); |
| 91 | + |
| 92 | + $length = count($unicode_array); |
| 93 | + |
| 94 | + if ( $encoding === self::GSM_7BIT_EX){ |
| 95 | + $length_exchars = count($ex_chars); |
| 96 | + # Each exchar in the GSM 7 Bit encoding takes one more space |
| 97 | + # Hence the length increases by one char for each of those Ex chars. |
| 98 | + $length += $length_exchars; |
| 99 | + } |
| 100 | + |
| 101 | + # Select the per message length according to encoding and the message length |
| 102 | + switch($encoding){ |
| 103 | + case self::GSM_7BIT: |
| 104 | + if ( $length > self::messageLength_GSM_7BIT){ |
| 105 | + $per_message = self::multiMessageLength_GSM_7BIT; |
| 106 | + }else{ |
| 107 | + $per_message = self::messageLength_GSM_7BIT; |
| 108 | + } |
| 109 | + break; |
| 110 | + |
| 111 | + case self::GSM_7BIT_EX: |
| 112 | + if ( $length > self::messageLength_GSM_7BIT_EX){ |
| 113 | + $per_message = self::multiMessageLength_GSM_7BIT_EX; |
| 114 | + }else{ |
| 115 | + $per_message = self::messageLength_GSM_7BIT_EX; |
| 116 | + } |
| 117 | + break; |
| 118 | + |
| 119 | + default: |
| 120 | + if($length > self::messageLength_UTF16){ |
| 121 | + $per_message = self::multiMessageLength_UTF16; |
| 122 | + }else{ |
| 123 | + $per_message = self::messageLength_UTF16; |
| 124 | + } |
| 125 | + break; |
| 126 | + } |
| 127 | + |
| 128 | + $messages = ceil($length / $per_message); |
| 129 | + $remaining = ( $per_message * $messages ) - $length ; |
| 130 | + |
| 131 | + $returnset = new stdClass(); |
| 132 | + |
| 133 | + $returnset->encoding = $encoding; |
| 134 | + $returnset->length = $length; |
| 135 | + $returnset->per_message = $per_message; |
| 136 | + $returnset->remaining = $remaining; |
| 137 | + $returnset->messages = $messages; |
| 138 | + |
| 139 | + return $returnset; |
| 140 | + |
| 141 | + } |
| 142 | + |
| 143 | + /** |
| 144 | + * function detect_encoding($text) |
| 145 | + * Detects the encoding of a particular text |
| 146 | + * @return - one of GSM_7BIT, GSM_7BIT_EX, UTF16 |
| 147 | + */ |
| 148 | + public static function detect_encoding ($text, & $ex_chars) { |
| 149 | + |
| 150 | + if(!is_array($text)){ |
| 151 | + $text = utf8_to_unicode($text); |
| 152 | + } |
| 153 | + |
| 154 | + $utf16_chars = array_diff($text, self::int_gsm_7bit_combined_map()); |
| 155 | + |
| 156 | + if(count($utf16_chars)){ |
| 157 | + return self::UTF16; |
| 158 | + } |
| 159 | + |
| 160 | + $ex_chars = array_intersect($text, self::int_gsm_7bit_ex_map()); |
| 161 | + |
| 162 | + if(count($ex_chars)){ |
| 163 | + return self::GSM_7BIT_EX; |
| 164 | + }else{ |
| 165 | + return self::GSM_7BIT; |
| 166 | + } |
| 167 | + |
| 168 | + } |
| 169 | + |
| 170 | + /** |
| 171 | + * function utf8_to_unicode ($str) |
| 172 | + * Generates array of unicode points for the utf8 string |
| 173 | + * @return array |
| 174 | + */ |
| 175 | + public static function utf8_to_unicode( $str ) { |
| 176 | + |
| 177 | + $unicode = array(); |
| 178 | + $values = array(); |
| 179 | + $looking_for = 1; |
| 180 | + |
| 181 | + for ($i = 0; $i < strlen( $str ); $i++ ) { |
| 182 | + |
| 183 | + $this_value = ord( $str[ $i ] ); |
| 184 | + |
| 185 | + if ( $this_value < 128 ) $unicode[] = $this_value; |
| 186 | + else { |
| 187 | + |
| 188 | + if ( count( $values ) == 0 ) $looking_for = ( $this_value < 224 ) ? 2 : 3; |
| 189 | + |
| 190 | + $values[] = $this_value; |
| 191 | + |
| 192 | + if ( count( $values ) == $looking_for ) { |
| 193 | + |
| 194 | + $number = ( $looking_for == 3 ) ? |
| 195 | + ( ( $values[0] % 16 ) * 4096 ) + ( ( $values[1] % 64 ) * 64 ) + ( $values[2] % 64 ): |
| 196 | + ( ( $values[0] % 32 ) * 64 ) + ( $values[1] % 64 ); |
| 197 | + |
| 198 | + $unicode[] = $number; |
| 199 | + $values = array(); |
| 200 | + $looking_for = 1; |
| 201 | + |
| 202 | + } # if |
| 203 | + |
| 204 | + } # if |
| 205 | + |
| 206 | + } # for |
| 207 | + |
| 208 | + return $unicode; |
| 209 | + |
| 210 | + } # utf8_to_unicode |
| 211 | + |
| 212 | + /** |
| 213 | + * unicode equivalent chr() function |
| 214 | + * @return character |
| 215 | + */ |
| 216 | + public static function utf8_chr($unicode){ |
| 217 | + $unicode=intval($unicode); |
| 218 | + |
| 219 | + if($unicode<128){ |
| 220 | + $utf8char=chr($unicode); |
| 221 | + } |
| 222 | + else if ($unicode >= 128 && $unicode < 2048){ |
| 223 | + $utf8char = chr(192 | ($unicode >> 6)) . chr(128 | ($unicode & 0x3F)); |
| 224 | + } |
| 225 | + else if ($unicode >= 2048 && $unicode < 65536){ |
| 226 | + $utf8char = chr(224 | ($unicode >> 12)) . chr(128 | (($unicode >> 6) & 0x3F)) . chr(128 | ($unicode & 0x3F)); |
| 227 | + } |
| 228 | + else{ |
| 229 | + $utf8char = chr(240 | ($unicode >> 18)) . chr(128 | (($unicode >> 12) & 0x3F)) . chr(128 | (($unicode >> 6) & 0x3F)) . chr(128 | ($unicode & 0x3F)); |
| 230 | + } |
| 231 | + |
| 232 | + return $utf8char; |
| 233 | + } |
| 234 | + |
| 235 | + public static function unicode_to_utf8($array){ |
| 236 | + $str = ''; |
| 237 | + foreach($array as $a){ |
| 238 | + $str .= self::utf8_chr($a); |
| 239 | + } |
| 240 | + |
| 241 | + return $str; |
| 242 | + } |
| 243 | + |
| 244 | + /** |
| 245 | + * Removes non GSM characters from a string |
| 246 | + * @return string |
| 247 | + */ |
| 248 | + public static function remove_non_gsm_chars( $str ){ |
| 249 | + # replace non gsm chars with a null character |
| 250 | + return self::replace_non_gsm_chars($str, null); |
| 251 | + } |
| 252 | + |
| 253 | + /** |
| 254 | + * Replaces non GSM characters from a string |
| 255 | + * @param $str - string to be replaced |
| 256 | + * @param $replacement - character to be replaced with |
| 257 | + * @return string |
| 258 | + * @return false, if replacement string is more than 1 character in length |
| 259 | + */ |
| 260 | + public static function replace_non_gsm_chars( $str , $replacement = null){ |
| 261 | + |
| 262 | + $valid_chars = self::int_gsm_7bit_combined_map(); |
| 263 | + |
| 264 | + $all_chars = self::utf8_to_unicode($str); |
| 265 | + |
| 266 | + if(strlen($replacement) > 1){ |
| 267 | + return FALSE; |
| 268 | + } |
| 269 | + |
| 270 | + $replacement_array = array(); |
| 271 | + $replacement_unicode = array_pop(self::utf8_to_unicode($replacement)); |
| 272 | + |
| 273 | + foreach($all_chars as $some_position=>$some_char){ |
| 274 | + if(!in_array($some_char, $valid_chars)){ |
| 275 | + $replacement_array[] = $some_position; |
| 276 | + } |
| 277 | + } |
| 278 | + |
| 279 | + if($replacement){ |
| 280 | + foreach($replacement_array as $some_position){ |
| 281 | + $all_chars[$some_position] = $replacement_unicode; |
| 282 | + } |
| 283 | + }else{ |
| 284 | + foreach($replacement_array as $some_position){ |
| 285 | + unset($all_chars[$some_position]); |
| 286 | + } |
| 287 | + } |
| 288 | + |
| 289 | + return self::unicode_to_utf8($all_chars); |
| 290 | + } |
| 291 | + } |
0 commit comments