smalot /
pdfparser
| Total Complexity | 73 |
| Total Lines | 475 |
| Duplicated Lines | 0 % |
| Coverage | 86.12% |
| 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 | 21 | public function init() |
|
| 51 | { |
||
| 52 | // Load translate table. |
||
| 53 | 21 | $this->loadTranslateTable(); |
|
| 54 | 21 | } |
|
| 55 | |||
| 56 | /** |
||
| 57 | * @return string |
||
| 58 | */ |
||
| 59 | 2 | public function getName() |
|
| 60 | { |
||
| 61 | 2 | return $this->has('BaseFont') ? (string) $this->get('BaseFont') : '[Unknown]'; |
|
| 62 | } |
||
| 63 | |||
| 64 | /** |
||
| 65 | * @return string |
||
| 66 | */ |
||
| 67 | 2 | public function getType() |
|
| 68 | { |
||
| 69 | 2 | return (string) $this->header->get('Subtype'); |
|
| 70 | } |
||
| 71 | |||
| 72 | /** |
||
| 73 | * @return array |
||
| 74 | */ |
||
| 75 | 1 | public function getDetails($deep = true) |
|
| 76 | { |
||
| 77 | 1 | $details = []; |
|
| 78 | |||
| 79 | 1 | $details['Name'] = $this->getName(); |
|
| 80 | 1 | $details['Type'] = $this->getType(); |
|
| 81 | 1 | $details['Encoding'] = ($this->has('Encoding') ? (string) $this->get('Encoding') : 'Ansi'); |
|
| 82 | |||
| 83 | 1 | $details += parent::getDetails($deep); |
|
| 84 | |||
| 85 | 1 | return $details; |
|
| 86 | } |
||
| 87 | |||
| 88 | /** |
||
| 89 | * @param string $char |
||
| 90 | * @param bool $use_default |
||
| 91 | * |
||
| 92 | * @return string|bool |
||
| 93 | */ |
||
| 94 | 12 | public function translateChar($char, $use_default = true) |
|
| 95 | { |
||
| 96 | 12 | $dec = hexdec(bin2hex($char)); |
|
| 97 | |||
| 98 | 12 | if (\array_key_exists($dec, $this->table)) { |
|
| 99 | 12 | return $this->table[$dec]; |
|
| 100 | } |
||
| 101 | |||
| 102 | 2 | return $use_default ? self::MISSING : $char; |
|
| 103 | } |
||
| 104 | |||
| 105 | /** |
||
| 106 | * @param int $code |
||
| 107 | * |
||
| 108 | * @return string |
||
| 109 | */ |
||
| 110 | 22 | public static function uchr($code) |
|
| 111 | { |
||
| 112 | 22 | return html_entity_decode('&#'.((int) $code).';', ENT_NOQUOTES, 'UTF-8'); |
|
| 113 | } |
||
| 114 | |||
| 115 | /** |
||
| 116 | * @return array |
||
| 117 | */ |
||
| 118 | 21 | public function loadTranslateTable() |
|
| 119 | { |
||
| 120 | 21 | if (null !== $this->table) { |
|
| 121 | 1 | return $this->table; |
|
| 122 | } |
||
| 123 | |||
| 124 | 21 | $this->table = []; |
|
| 125 | 21 | $this->tableSizes = [ |
|
| 126 | 'from' => 1, |
||
| 127 | 'to' => 1, |
||
| 128 | ]; |
||
| 129 | |||
| 130 | 21 | if ($this->has('ToUnicode')) { |
|
| 131 | 20 | $content = $this->get('ToUnicode')->getContent(); |
|
| 132 | 20 | $matches = []; |
|
| 133 | |||
| 134 | // Support for multiple spacerange sections |
||
| 135 | 20 | if (preg_match_all('/begincodespacerange(?P<sections>.*?)endcodespacerange/s', $content, $matches)) { |
|
| 136 | 20 | foreach ($matches['sections'] as $section) { |
|
| 137 | 20 | $regexp = '/<(?P<from>[0-9A-F]+)> *<(?P<to>[0-9A-F]+)>[ \r\n]+/is'; |
|
| 138 | |||
| 139 | 20 | preg_match_all($regexp, $section, $matches); |
|
| 140 | |||
| 141 | 20 | $this->tableSizes = [ |
|
| 142 | 20 | 'from' => max(1, \strlen(current($matches['from'])) / 2), |
|
| 143 | 20 | 'to' => max(1, \strlen(current($matches['to'])) / 2), |
|
| 144 | ]; |
||
| 145 | |||
| 146 | 20 | break; |
|
| 147 | } |
||
| 148 | } |
||
| 149 | |||
| 150 | // Support for multiple bfchar sections |
||
| 151 | 20 | if (preg_match_all('/beginbfchar(?P<sections>.*?)endbfchar/s', $content, $matches)) { |
|
| 152 | 6 | foreach ($matches['sections'] as $section) { |
|
| 153 | 6 | $regexp = '/<(?P<from>[0-9A-F]+)> +<(?P<to>[0-9A-F]+)>[ \r\n]+/is'; |
|
| 154 | |||
| 155 | 6 | preg_match_all($regexp, $section, $matches); |
|
| 156 | |||
| 157 | 6 | $this->tableSizes['from'] = max(1, \strlen(current($matches['from'])) / 2); |
|
| 158 | |||
| 159 | 6 | foreach ($matches['from'] as $key => $from) { |
|
| 160 | 6 | $parts = preg_split( |
|
| 161 | 6 | '/([0-9A-F]{4})/i', |
|
| 162 | 6 | $matches['to'][$key], |
|
| 163 | 6 | 0, |
|
| 164 | 6 | PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE |
|
| 165 | ); |
||
| 166 | 6 | $text = ''; |
|
| 167 | 6 | foreach ($parts as $part) { |
|
| 168 | 6 | $text .= self::uchr(hexdec($part)); |
|
|
Bug
introduced
by
|
|||
| 169 | } |
||
| 170 | 6 | $this->table[hexdec($from)] = $text; |
|
| 171 | } |
||
| 172 | } |
||
| 173 | } |
||
| 174 | |||
| 175 | // Support for multiple bfrange sections |
||
| 176 | 20 | if (preg_match_all('/beginbfrange(?P<sections>.*?)endbfrange/s', $content, $matches)) { |
|
| 177 | 18 | foreach ($matches['sections'] as $section) { |
|
| 178 | // Support for : <srcCode1> <srcCode2> <dstString> |
||
| 179 | 18 | $regexp = '/<(?P<from>[0-9A-F]+)> *<(?P<to>[0-9A-F]+)> *<(?P<offset>[0-9A-F]+)>[ \r\n]+/is'; |
|
| 180 | |||
| 181 | 18 | preg_match_all($regexp, $section, $matches); |
|
| 182 | |||
| 183 | 18 | foreach ($matches['from'] as $key => $from) { |
|
| 184 | 18 | $char_from = hexdec($from); |
|
| 185 | 18 | $char_to = hexdec($matches['to'][$key]); |
|
| 186 | 18 | $offset = hexdec($matches['offset'][$key]); |
|
| 187 | |||
| 188 | 18 | for ($char = $char_from; $char <= $char_to; ++$char) { |
|
| 189 | 18 | $this->table[$char] = self::uchr($char - $char_from + $offset); |
|
| 190 | } |
||
| 191 | } |
||
| 192 | |||
| 193 | // Support for : <srcCode1> <srcCodeN> [<dstString1> <dstString2> ... <dstStringN>] |
||
| 194 | // Some PDF file has 2-byte Unicode values on new lines > added \r\n |
||
| 195 | 18 | $regexp = '/<(?P<from>[0-9A-F]+)> *<(?P<to>[0-9A-F]+)> *\[(?P<strings>[\r\n<>0-9A-F ]+)\][ \r\n]+/is'; |
|
| 196 | |||
| 197 | 18 | preg_match_all($regexp, $section, $matches); |
|
| 198 | |||
| 199 | 18 | foreach ($matches['from'] as $key => $from) { |
|
| 200 | 1 | $char_from = hexdec($from); |
|
| 201 | 1 | $strings = []; |
|
| 202 | |||
| 203 | 1 | preg_match_all('/<(?P<string>[0-9A-F]+)> */is', $matches['strings'][$key], $strings); |
|
| 204 | |||
| 205 | 1 | foreach ($strings['string'] as $position => $string) { |
|
| 206 | 1 | $parts = preg_split( |
|
| 207 | 1 | '/([0-9A-F]{4})/i', |
|
| 208 | $string, |
||
| 209 | 1 | 0, |
|
| 210 | 1 | PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE |
|
| 211 | ); |
||
| 212 | 1 | $text = ''; |
|
| 213 | 1 | foreach ($parts as $part) { |
|
| 214 | 1 | $text .= self::uchr(hexdec($part)); |
|
| 215 | } |
||
| 216 | 1 | $this->table[$char_from + $position] = $text; |
|
| 217 | } |
||
| 218 | } |
||
| 219 | } |
||
| 220 | } |
||
| 221 | } |
||
| 222 | |||
| 223 | 21 | return $this->table; |
|
| 224 | } |
||
| 225 | |||
| 226 | /** |
||
| 227 | * @param array $table |
||
| 228 | */ |
||
| 229 | public function setTable($table) |
||
| 230 | { |
||
| 231 | $this->table = $table; |
||
| 232 | } |
||
| 233 | |||
| 234 | /** |
||
| 235 | * @param string $hexa |
||
| 236 | * @param bool $add_braces |
||
| 237 | * |
||
| 238 | * @return string |
||
| 239 | */ |
||
| 240 | 25 | public static function decodeHexadecimal($hexa, $add_braces = false) |
|
| 241 | { |
||
| 242 | // Special shortcut for XML content. |
||
| 243 | 25 | if (false !== stripos($hexa, '<?xml')) { |
|
| 244 | 3 | return $hexa; |
|
| 245 | } |
||
| 246 | |||
| 247 | 25 | $text = ''; |
|
| 248 | 25 | $parts = preg_split('/(<[a-f0-9]+>)/si', $hexa, -1, PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE); |
|
| 249 | |||
| 250 | 25 | foreach ($parts as $part) { |
|
| 251 | 25 | if (preg_match('/^<.*>$/s', $part) && false === stripos($part, '<?xml')) { |
|
| 252 | // strip line breaks |
||
| 253 | 8 | $part = preg_replace("/[\r\n]/", '', $part); |
|
| 254 | 8 | $part = trim($part, '<>'); |
|
| 255 | 8 | if ($add_braces) { |
|
| 256 | 1 | $text .= '('; |
|
| 257 | } |
||
| 258 | |||
| 259 | 8 | $part = pack('H*', $part); |
|
| 260 | 8 | $text .= ($add_braces ? preg_replace('/\\\/s', '\\\\\\', $part) : $part); |
|
| 261 | |||
| 262 | 8 | if ($add_braces) { |
|
| 263 | 8 | $text .= ')'; |
|
| 264 | } |
||
| 265 | } else { |
||
| 266 | 25 | $text .= $part; |
|
| 267 | } |
||
| 268 | } |
||
| 269 | |||
| 270 | 25 | return $text; |
|
| 271 | } |
||
| 272 | |||
| 273 | /** |
||
| 274 | * @param string $text |
||
| 275 | * |
||
| 276 | * @return string |
||
| 277 | */ |
||
| 278 | 25 | public static function decodeOctal($text) |
|
| 292 | } |
||
| 293 | |||
| 294 | /** |
||
| 295 | * @param string $text |
||
| 296 | * |
||
| 297 | * @return string |
||
| 298 | */ |
||
| 299 | 38 | public static function decodeEntities($text) |
|
| 300 | { |
||
| 301 | 38 | $parts = preg_split('/(#\d{2})/s', $text, -1, PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE); |
|
| 302 | 38 | $text = ''; |
|
| 303 | |||
| 304 | 38 | foreach ($parts as $part) { |
|
| 305 | 38 | if (preg_match('/^#\d{2}$/', $part)) { |
|
| 306 | 3 | $text .= \chr(hexdec(trim($part, '#'))); |
|
| 307 | } else { |
||
| 308 | 38 | $text .= $part; |
|
| 309 | } |
||
| 310 | } |
||
| 311 | |||
| 312 | 38 | return $text; |
|
| 313 | } |
||
| 314 | |||
| 315 | /** |
||
| 316 | * @param string $text |
||
| 317 | * |
||
| 318 | * @return string |
||
| 319 | */ |
||
| 320 | 25 | public static function decodeUnicode($text) |
|
| 321 | { |
||
| 322 | 25 | if (preg_match('/^\xFE\xFF/i', $text)) { |
|
| 323 | // Strip U+FEFF byte order marker. |
||
| 324 | 16 | $decode = substr($text, 2); |
|
| 325 | 16 | $text = ''; |
|
| 326 | 16 | $length = \strlen($decode); |
|
| 327 | |||
| 328 | 16 | for ($i = 0; $i < $length; $i += 2) { |
|
| 329 | 16 | $text .= self::uchr(hexdec(bin2hex(substr($decode, $i, 2)))); |
|
| 330 | } |
||
| 331 | } |
||
| 332 | |||
| 333 | 25 | return $text; |
|
| 334 | } |
||
| 335 | |||
| 336 | /** |
||
| 337 | * @return int |
||
| 338 | */ |
||
| 339 | 10 | protected function getFontSpaceLimit() |
|
| 342 | } |
||
| 343 | |||
| 344 | /** |
||
| 345 | * @param array $commands |
||
| 346 | * |
||
| 347 | * @return string |
||
| 348 | */ |
||
| 349 | 10 | public function decodeText($commands) |
|
| 350 | { |
||
| 351 | 10 | $text = ''; |
|
| 352 | 10 | $word_position = 0; |
|
| 353 | 10 | $words = []; |
|
| 354 | 10 | $unicode = false; |
|
| 355 | 10 | $font_space = $this->getFontSpaceLimit(); |
|
| 356 | |||
| 357 | 10 | foreach ($commands as $command) { |
|
| 358 | 10 | switch ($command[PDFObject::TYPE]) { |
|
| 359 | 10 | case 'n': |
|
| 360 | 9 | if ((float) (trim($command[PDFObject::COMMAND])) < $font_space) { |
|
| 361 | 4 | $word_position = \count($words); |
|
| 362 | } |
||
| 363 | 9 | continue 2; |
|
| 364 | |||
| 365 | 10 | case '<': |
|
| 366 | // Decode hexadecimal. |
||
| 367 | 6 | $text = self::decodeHexadecimal('<'.$command[PDFObject::COMMAND].'>'); |
|
| 368 | |||
| 369 | 6 | if (mb_check_encoding($text, 'UTF-8')) { |
|
| 370 | 6 | $unicode = true; |
|
| 371 | } |
||
| 372 | |||
| 373 | 6 | break; |
|
| 374 | |||
| 375 | default: |
||
| 376 | // Decode octal (if necessary). |
||
| 377 | 6 | $text = self::decodeOctal($command[PDFObject::COMMAND]); |
|
| 378 | } |
||
| 379 | |||
| 380 | // replace escaped chars |
||
| 381 | 10 | $text = str_replace( |
|
| 382 | 10 | ['\\\\', '\(', '\)', '\n', '\r', '\t', '\f', '\ '], |
|
| 383 | 10 | ['\\', '(', ')', "\n", "\r", "\t", "\f", ' '], |
|
| 384 | $text |
||
| 385 | ); |
||
| 386 | |||
| 387 | // add content to result string |
||
| 388 | 10 | if (isset($words[$word_position])) { |
|
| 389 | 9 | $words[$word_position] .= $text; |
|
| 390 | } else { |
||
| 391 | 10 | $words[$word_position] = $text; |
|
| 392 | } |
||
| 393 | } |
||
| 394 | |||
| 395 | 10 | foreach ($words as &$word) { |
|
| 396 | 10 | $loop_unicode = $unicode; |
|
| 397 | 10 | $word = $this->decodeContent($word, $loop_unicode); |
|
| 398 | } |
||
| 399 | |||
| 400 | 10 | return implode(' ', $words); |
|
| 401 | } |
||
| 402 | |||
| 403 | /** |
||
| 404 | * @param string $text |
||
| 405 | * @param bool $unicode |
||
| 406 | * |
||
| 407 | * @return string |
||
| 408 | */ |
||
| 409 | 12 | public function decodeContent($text, &$unicode) |
|
| 511 | } |
||
| 512 | } |
||
| 513 |
Loading history...
