smalot /
pdfparser
| Total Complexity | 75 |
| Total Lines | 459 |
| Duplicated Lines | 0 % |
| Coverage | 91.13% |
| Changes | 13 | ||
| Bugs | 2 | Features | 1 |
Complex classes like Font often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
While breaking up the class, it is a good idea to analyze how other classes use Font, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 36 | class Font extends PDFObject |
||
| 37 | { |
||
| 38 | const MISSING = '?'; |
||
| 39 | |||
| 40 | /** |
||
| 41 | * @var array |
||
| 42 | */ |
||
| 43 | protected $table = null; |
||
| 44 | |||
| 45 | /** |
||
| 46 | * @var array |
||
| 47 | */ |
||
| 48 | protected $tableSizes = null; |
||
| 49 | |||
| 50 | 25 | public function init() |
|
| 51 | { |
||
| 52 | // Load translate table. |
||
| 53 | 25 | $this->loadTranslateTable(); |
|
| 54 | 25 | } |
|
| 55 | |||
| 56 | /** |
||
| 57 | * @return string |
||
| 58 | */ |
||
| 59 | 2 | public function getName() |
|
| 62 | } |
||
| 63 | |||
| 64 | /** |
||
| 65 | * @return string |
||
| 66 | */ |
||
| 67 | 2 | public function getType() |
|
| 70 | } |
||
| 71 | |||
| 72 | /** |
||
| 73 | * @return array |
||
| 74 | */ |
||
| 75 | 1 | public function getDetails($deep = true) |
|
| 86 | } |
||
| 87 | |||
| 88 | /** |
||
| 89 | * @param string $char |
||
| 90 | * @param bool $use_default |
||
| 91 | * |
||
| 92 | * @return string|bool |
||
| 93 | */ |
||
| 94 | 14 | public function translateChar($char, $use_default = true) |
|
| 95 | { |
||
| 96 | 14 | $dec = hexdec(bin2hex($char)); |
|
| 97 | |||
| 98 | 14 | if (\array_key_exists($dec, $this->table)) { |
|
| 99 | 14 | return $this->table[$dec]; |
|
| 100 | } |
||
| 101 | |||
| 102 | // fallback for decoding single-byte ANSI characters that are not in the lookup table |
||
| 103 | 3 | $fallbackDecoded = $char; |
|
| 104 | 3 | if (\strlen($char) < 2 && $this->has('Encoding') && 'WinAnsiEncoding' === $this->get('Encoding')->__toString()) { |
|
| 105 | $fallbackDecoded = self::uchr($dec); |
||
|
Bug
introduced
by
|
|||
| 106 | } |
||
| 107 | |||
| 108 | 3 | return $use_default ? self::MISSING : $fallbackDecoded; |
|
| 109 | } |
||
| 110 | |||
| 111 | /** |
||
| 112 | * @param int $code |
||
| 113 | * |
||
| 114 | * @return string |
||
| 115 | */ |
||
| 116 | 26 | public static function uchr($code) |
|
| 117 | { |
||
| 118 | // html_entity_decode() will not work with UTF-16 or UTF-32 char entities, |
||
| 119 | // therefore, we use mb_convert_encoding() instead |
||
| 120 | 26 | return mb_convert_encoding('&#'.((int) $code).';', 'UTF-8', 'HTML-ENTITIES'); |
|
| 121 | } |
||
| 122 | |||
| 123 | /** |
||
| 124 | * @return array |
||
| 125 | */ |
||
| 126 | 25 | public function loadTranslateTable() |
|
| 127 | { |
||
| 128 | 25 | if (null !== $this->table) { |
|
| 129 | 1 | return $this->table; |
|
| 130 | } |
||
| 131 | |||
| 132 | 25 | $this->table = []; |
|
| 133 | 25 | $this->tableSizes = [ |
|
| 134 | 'from' => 1, |
||
| 135 | 'to' => 1, |
||
| 136 | ]; |
||
| 137 | |||
| 138 | 25 | if ($this->has('ToUnicode')) { |
|
| 139 | 23 | $content = $this->get('ToUnicode')->getContent(); |
|
| 140 | 23 | $matches = []; |
|
| 141 | |||
| 142 | // Support for multiple spacerange sections |
||
| 143 | 23 | if (preg_match_all('/begincodespacerange(?P<sections>.*?)endcodespacerange/s', $content, $matches)) { |
|
| 144 | 23 | foreach ($matches['sections'] as $section) { |
|
| 145 | 23 | $regexp = '/<(?P<from>[0-9A-F]+)> *<(?P<to>[0-9A-F]+)>[ \r\n]+/is'; |
|
| 146 | |||
| 147 | 23 | preg_match_all($regexp, $section, $matches); |
|
| 148 | |||
| 149 | 23 | $this->tableSizes = [ |
|
| 150 | 23 | 'from' => max(1, \strlen(current($matches['from'])) / 2), |
|
| 151 | 23 | 'to' => max(1, \strlen(current($matches['to'])) / 2), |
|
| 152 | ]; |
||
| 153 | |||
| 154 | 23 | break; |
|
| 155 | } |
||
| 156 | } |
||
| 157 | |||
| 158 | // Support for multiple bfchar sections |
||
| 159 | 23 | if (preg_match_all('/beginbfchar(?P<sections>.*?)endbfchar/s', $content, $matches)) { |
|
| 160 | 8 | foreach ($matches['sections'] as $section) { |
|
| 161 | 8 | $regexp = '/<(?P<from>[0-9A-F]+)> +<(?P<to>[0-9A-F]+)>[ \r\n]+/is'; |
|
| 162 | |||
| 163 | 8 | preg_match_all($regexp, $section, $matches); |
|
| 164 | |||
| 165 | 8 | $this->tableSizes['from'] = max(1, \strlen(current($matches['from'])) / 2); |
|
| 166 | |||
| 167 | 8 | foreach ($matches['from'] as $key => $from) { |
|
| 168 | 8 | $parts = preg_split( |
|
| 169 | 8 | '/([0-9A-F]{4})/i', |
|
| 170 | 8 | $matches['to'][$key], |
|
| 171 | 8 | 0, |
|
| 172 | 8 | PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE |
|
| 173 | ); |
||
| 174 | 8 | $text = ''; |
|
| 175 | 8 | foreach ($parts as $part) { |
|
| 176 | 8 | $text .= self::uchr(hexdec($part)); |
|
| 177 | } |
||
| 178 | 8 | $this->table[hexdec($from)] = $text; |
|
| 179 | } |
||
| 180 | } |
||
| 181 | } |
||
| 182 | |||
| 183 | // Support for multiple bfrange sections |
||
| 184 | 23 | if (preg_match_all('/beginbfrange(?P<sections>.*?)endbfrange/s', $content, $matches)) { |
|
| 185 | 19 | foreach ($matches['sections'] as $section) { |
|
| 186 | // Support for : <srcCode1> <srcCode2> <dstString> |
||
| 187 | 19 | $regexp = '/<(?P<from>[0-9A-F]+)> *<(?P<to>[0-9A-F]+)> *<(?P<offset>[0-9A-F]+)>[ \r\n]+/is'; |
|
| 188 | |||
| 189 | 19 | preg_match_all($regexp, $section, $matches); |
|
| 190 | |||
| 191 | 19 | foreach ($matches['from'] as $key => $from) { |
|
| 192 | 19 | $char_from = hexdec($from); |
|
| 193 | 19 | $char_to = hexdec($matches['to'][$key]); |
|
| 194 | 19 | $offset = hexdec($matches['offset'][$key]); |
|
| 195 | |||
| 196 | 19 | for ($char = $char_from; $char <= $char_to; ++$char) { |
|
| 197 | 19 | $this->table[$char] = self::uchr($char - $char_from + $offset); |
|
| 198 | } |
||
| 199 | } |
||
| 200 | |||
| 201 | // Support for : <srcCode1> <srcCodeN> [<dstString1> <dstString2> ... <dstStringN>] |
||
| 202 | // Some PDF file has 2-byte Unicode values on new lines > added \r\n |
||
| 203 | 19 | $regexp = '/<(?P<from>[0-9A-F]+)> *<(?P<to>[0-9A-F]+)> *\[(?P<strings>[\r\n<>0-9A-F ]+)\][ \r\n]+/is'; |
|
| 204 | |||
| 205 | 19 | preg_match_all($regexp, $section, $matches); |
|
| 206 | |||
| 207 | 19 | foreach ($matches['from'] as $key => $from) { |
|
| 208 | 1 | $char_from = hexdec($from); |
|
| 209 | 1 | $strings = []; |
|
| 210 | |||
| 211 | 1 | preg_match_all('/<(?P<string>[0-9A-F]+)> */is', $matches['strings'][$key], $strings); |
|
| 212 | |||
| 213 | 1 | foreach ($strings['string'] as $position => $string) { |
|
| 214 | 1 | $parts = preg_split( |
|
| 215 | 1 | '/([0-9A-F]{4})/i', |
|
| 216 | $string, |
||
| 217 | 1 | 0, |
|
| 218 | 1 | PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE |
|
| 219 | ); |
||
| 220 | 1 | $text = ''; |
|
| 221 | 1 | foreach ($parts as $part) { |
|
| 222 | 1 | $text .= self::uchr(hexdec($part)); |
|
| 223 | } |
||
| 224 | 1 | $this->table[$char_from + $position] = $text; |
|
| 225 | } |
||
| 226 | } |
||
| 227 | } |
||
| 228 | } |
||
| 229 | } |
||
| 230 | |||
| 231 | 25 | return $this->table; |
|
| 232 | } |
||
| 233 | |||
| 234 | /** |
||
| 235 | * @param array $table |
||
| 236 | */ |
||
| 237 | public function setTable($table) |
||
| 240 | } |
||
| 241 | |||
| 242 | /** |
||
| 243 | * @param string $hexa |
||
| 244 | * @param bool $add_braces |
||
| 245 | * |
||
| 246 | * @return string |
||
| 247 | */ |
||
| 248 | 29 | public static function decodeHexadecimal($hexa, $add_braces = false) |
|
| 249 | { |
||
| 250 | // Special shortcut for XML content. |
||
| 251 | 29 | if (false !== stripos($hexa, '<?xml')) { |
|
| 252 | 3 | return $hexa; |
|
| 253 | } |
||
| 254 | |||
| 255 | 29 | $text = ''; |
|
| 256 | 29 | $parts = preg_split('/(<[a-f0-9]+>)/si', $hexa, -1, PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE); |
|
| 257 | |||
| 258 | 29 | foreach ($parts as $part) { |
|
| 259 | 29 | if (preg_match('/^<.*>$/s', $part) && false === stripos($part, '<?xml')) { |
|
| 260 | // strip line breaks |
||
| 261 | 9 | $part = preg_replace("/[\r\n]/", '', $part); |
|
| 262 | 9 | $part = trim($part, '<>'); |
|
| 263 | 9 | if ($add_braces) { |
|
| 264 | 1 | $text .= '('; |
|
| 265 | } |
||
| 266 | |||
| 267 | 9 | $part = pack('H*', $part); |
|
| 268 | 9 | $text .= ($add_braces ? preg_replace('/\\\/s', '\\\\\\', $part) : $part); |
|
| 269 | |||
| 270 | 9 | if ($add_braces) { |
|
| 271 | 9 | $text .= ')'; |
|
| 272 | } |
||
| 273 | } else { |
||
| 274 | 29 | $text .= $part; |
|
| 275 | } |
||
| 276 | } |
||
| 277 | |||
| 278 | 29 | return $text; |
|
| 279 | } |
||
| 280 | |||
| 281 | /** |
||
| 282 | * @param string $text |
||
| 283 | * |
||
| 284 | * @return string |
||
| 285 | */ |
||
| 286 | 29 | public static function decodeOctal($text) |
|
| 300 | } |
||
| 301 | |||
| 302 | /** |
||
| 303 | * @param string $text |
||
| 304 | * |
||
| 305 | * @return string |
||
| 306 | */ |
||
| 307 | 43 | public static function decodeEntities($text) |
|
| 308 | { |
||
| 309 | 43 | $parts = preg_split('/(#\d{2})/s', $text, -1, PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE); |
|
| 310 | 43 | $text = ''; |
|
| 311 | |||
| 312 | 43 | foreach ($parts as $part) { |
|
| 313 | 43 | if (preg_match('/^#\d{2}$/', $part)) { |
|
| 314 | 3 | $text .= \chr(hexdec(trim($part, '#'))); |
|
| 315 | } else { |
||
| 316 | 43 | $text .= $part; |
|
| 317 | } |
||
| 318 | } |
||
| 319 | |||
| 320 | 43 | return $text; |
|
| 321 | } |
||
| 322 | |||
| 323 | /** |
||
| 324 | * @param string $text |
||
| 325 | * |
||
| 326 | * @return string |
||
| 327 | */ |
||
| 328 | 29 | public static function decodeUnicode($text) |
|
| 329 | { |
||
| 330 | 29 | if (preg_match('/^\xFE\xFF/i', $text)) { |
|
| 331 | // Strip U+FEFF byte order marker. |
||
| 332 | 19 | $decode = substr($text, 2); |
|
| 333 | 19 | $text = ''; |
|
| 334 | 19 | $length = \strlen($decode); |
|
| 335 | |||
| 336 | 19 | for ($i = 0; $i < $length; $i += 2) { |
|
| 337 | 19 | $text .= self::uchr(hexdec(bin2hex(substr($decode, $i, 2)))); |
|
| 338 | } |
||
| 339 | } |
||
| 340 | |||
| 341 | 29 | return $text; |
|
| 342 | } |
||
| 343 | |||
| 344 | /** |
||
| 345 | * @return int |
||
| 346 | */ |
||
| 347 | 13 | protected function getFontSpaceLimit() |
|
| 350 | } |
||
| 351 | |||
| 352 | /** |
||
| 353 | * @param array $commands |
||
| 354 | * |
||
| 355 | * @return string |
||
| 356 | */ |
||
| 357 | 13 | public function decodeText($commands) |
|
| 403 | } |
||
| 404 | |||
| 405 | /** |
||
| 406 | * @param string $text |
||
| 407 | * @param bool $unicode This parameter is deprecated and might be removed in a future release |
||
| 408 | * |
||
| 409 | * @return string |
||
| 410 | */ |
||
| 411 | 15 | public function decodeContent($text, &$unicode = null) |
|
| 497 |
Loading history...
