smalot /
pdfparser
| Total Complexity | 76 |
| Total Lines | 473 |
| Duplicated Lines | 0 % |
| Coverage | 87.86% |
| 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 int |
||
| 42 | */ |
||
| 43 | public static $font_space = -50; |
||
| 44 | |||
| 45 | /** |
||
| 46 | * @var array |
||
| 47 | */ |
||
| 48 | protected $table = null; |
||
| 49 | |||
| 50 | /** |
||
| 51 | * @var array |
||
| 52 | */ |
||
| 53 | protected $tableSizes = null; |
||
| 54 | |||
| 55 | 24 | public function init() |
|
| 56 | { |
||
| 57 | // Load translate table. |
||
| 58 | 24 | $this->loadTranslateTable(); |
|
| 59 | 24 | } |
|
| 60 | |||
| 61 | /** |
||
| 62 | * @return string |
||
| 63 | */ |
||
| 64 | 2 | public function getName() |
|
| 65 | { |
||
| 66 | 2 | return $this->has('BaseFont') ? (string) $this->get('BaseFont') : '[Unknown]'; |
|
| 67 | } |
||
| 68 | |||
| 69 | /** |
||
| 70 | * @return string |
||
| 71 | */ |
||
| 72 | 2 | public function getType() |
|
| 73 | { |
||
| 74 | 2 | return (string) $this->header->get('Subtype'); |
|
| 75 | } |
||
| 76 | |||
| 77 | /** |
||
| 78 | * @return array |
||
| 79 | */ |
||
| 80 | 1 | public function getDetails($deep = true) |
|
| 81 | { |
||
| 82 | 1 | $details = []; |
|
| 83 | |||
| 84 | 1 | $details['Name'] = $this->getName(); |
|
| 85 | 1 | $details['Type'] = $this->getType(); |
|
| 86 | 1 | $details['Encoding'] = ($this->has('Encoding') ? (string) $this->get('Encoding') : 'Ansi'); |
|
| 87 | |||
| 88 | 1 | $details += parent::getDetails($deep); |
|
| 89 | |||
| 90 | 1 | return $details; |
|
| 91 | } |
||
| 92 | |||
| 93 | /** |
||
| 94 | * @param string $char |
||
| 95 | * @param bool $use_default |
||
| 96 | * |
||
| 97 | * @return string|bool |
||
| 98 | */ |
||
| 99 | 13 | public function translateChar($char, $use_default = true) |
|
| 100 | { |
||
| 101 | 13 | $dec = hexdec(bin2hex($char)); |
|
| 102 | |||
| 103 | 13 | if (\array_key_exists($dec, $this->table)) { |
|
| 104 | 13 | return $this->table[$dec]; |
|
| 105 | } |
||
| 106 | |||
| 107 | // fallback for decoding single-byte ANSI characters that are not in the lookup table |
||
| 108 | 3 | $fallbackDecoded = $char; |
|
| 109 | 3 | if (\strlen($char) < 2 && $this->has('Encoding') && 'WinAnsiEncoding' === $this->get('Encoding')->__toString()) { |
|
| 110 | $fallbackDecoded = self::uchr($dec); |
||
|
Bug
introduced
by
|
|||
| 111 | } |
||
| 112 | |||
| 113 | 3 | return $use_default ? self::MISSING : $fallbackDecoded; |
|
| 114 | } |
||
| 115 | |||
| 116 | /** |
||
| 117 | * @param int $code |
||
| 118 | * |
||
| 119 | * @return string |
||
| 120 | */ |
||
| 121 | 25 | public static function uchr($code) |
|
| 122 | { |
||
| 123 | // html_entity_decode() will not work with UTF-16 or UTF-32 char entities, |
||
| 124 | // therefore, we use mb_convert_encoding() instead |
||
| 125 | 25 | return mb_convert_encoding('&#'.((int) $code).';', 'UTF-8', 'HTML-ENTITIES'); |
|
| 126 | } |
||
| 127 | |||
| 128 | /** |
||
| 129 | * @return array |
||
| 130 | */ |
||
| 131 | 24 | public function loadTranslateTable() |
|
| 132 | { |
||
| 133 | 24 | if (null !== $this->table) { |
|
| 134 | 1 | return $this->table; |
|
| 135 | } |
||
| 136 | |||
| 137 | 24 | $this->table = []; |
|
| 138 | 24 | $this->tableSizes = [ |
|
| 139 | 'from' => 1, |
||
| 140 | 'to' => 1, |
||
| 141 | ]; |
||
| 142 | |||
| 143 | 24 | if ($this->has('ToUnicode')) { |
|
| 144 | 22 | $content = $this->get('ToUnicode')->getContent(); |
|
| 145 | 22 | $matches = []; |
|
| 146 | |||
| 147 | // Support for multiple spacerange sections |
||
| 148 | 22 | if (preg_match_all('/begincodespacerange(?P<sections>.*?)endcodespacerange/s', $content, $matches)) { |
|
| 149 | 22 | foreach ($matches['sections'] as $section) { |
|
| 150 | 22 | $regexp = '/<(?P<from>[0-9A-F]+)> *<(?P<to>[0-9A-F]+)>[ \r\n]+/is'; |
|
| 151 | |||
| 152 | 22 | preg_match_all($regexp, $section, $matches); |
|
| 153 | |||
| 154 | 22 | $this->tableSizes = [ |
|
| 155 | 22 | 'from' => max(1, \strlen(current($matches['from'])) / 2), |
|
| 156 | 22 | 'to' => max(1, \strlen(current($matches['to'])) / 2), |
|
| 157 | ]; |
||
| 158 | |||
| 159 | 22 | break; |
|
| 160 | } |
||
| 161 | } |
||
| 162 | |||
| 163 | // Support for multiple bfchar sections |
||
| 164 | 22 | if (preg_match_all('/beginbfchar(?P<sections>.*?)endbfchar/s', $content, $matches)) { |
|
| 165 | 8 | foreach ($matches['sections'] as $section) { |
|
| 166 | 8 | $regexp = '/<(?P<from>[0-9A-F]+)> +<(?P<to>[0-9A-F]+)>[ \r\n]+/is'; |
|
| 167 | |||
| 168 | 8 | preg_match_all($regexp, $section, $matches); |
|
| 169 | |||
| 170 | 8 | $this->tableSizes['from'] = max(1, \strlen(current($matches['from'])) / 2); |
|
| 171 | |||
| 172 | 8 | foreach ($matches['from'] as $key => $from) { |
|
| 173 | 8 | $parts = preg_split( |
|
| 174 | 8 | '/([0-9A-F]{4})/i', |
|
| 175 | 8 | $matches['to'][$key], |
|
| 176 | 8 | 0, |
|
| 177 | 8 | PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE |
|
| 178 | ); |
||
| 179 | 8 | $text = ''; |
|
| 180 | 8 | foreach ($parts as $part) { |
|
| 181 | 8 | $text .= self::uchr(hexdec($part)); |
|
| 182 | } |
||
| 183 | 8 | $this->table[hexdec($from)] = $text; |
|
| 184 | } |
||
| 185 | } |
||
| 186 | } |
||
| 187 | |||
| 188 | // Support for multiple bfrange sections |
||
| 189 | 22 | if (preg_match_all('/beginbfrange(?P<sections>.*?)endbfrange/s', $content, $matches)) { |
|
| 190 | 18 | foreach ($matches['sections'] as $section) { |
|
| 191 | // Support for : <srcCode1> <srcCode2> <dstString> |
||
| 192 | 18 | $regexp = '/<(?P<from>[0-9A-F]+)> *<(?P<to>[0-9A-F]+)> *<(?P<offset>[0-9A-F]+)>[ \r\n]+/is'; |
|
| 193 | |||
| 194 | 18 | preg_match_all($regexp, $section, $matches); |
|
| 195 | |||
| 196 | 18 | foreach ($matches['from'] as $key => $from) { |
|
| 197 | 18 | $char_from = hexdec($from); |
|
| 198 | 18 | $char_to = hexdec($matches['to'][$key]); |
|
| 199 | 18 | $offset = hexdec($matches['offset'][$key]); |
|
| 200 | |||
| 201 | 18 | for ($char = $char_from; $char <= $char_to; ++$char) { |
|
| 202 | 18 | $this->table[$char] = self::uchr($char - $char_from + $offset); |
|
| 203 | } |
||
| 204 | } |
||
| 205 | |||
| 206 | // Support for : <srcCode1> <srcCodeN> [<dstString1> <dstString2> ... <dstStringN>] |
||
| 207 | // Some PDF file has 2-byte Unicode values on new lines > added \r\n |
||
| 208 | 18 | $regexp = '/<(?P<from>[0-9A-F]+)> *<(?P<to>[0-9A-F]+)> *\[(?P<strings>[\r\n<>0-9A-F ]+)\][ \r\n]+/is'; |
|
| 209 | |||
| 210 | 18 | preg_match_all($regexp, $section, $matches); |
|
| 211 | |||
| 212 | 18 | foreach ($matches['from'] as $key => $from) { |
|
| 213 | 1 | $char_from = hexdec($from); |
|
| 214 | 1 | $strings = []; |
|
| 215 | |||
| 216 | 1 | preg_match_all('/<(?P<string>[0-9A-F]+)> */is', $matches['strings'][$key], $strings); |
|
| 217 | |||
| 218 | 1 | foreach ($strings['string'] as $position => $string) { |
|
| 219 | 1 | $parts = preg_split( |
|
| 220 | 1 | '/([0-9A-F]{4})/i', |
|
| 221 | $string, |
||
| 222 | 1 | 0, |
|
| 223 | 1 | PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE |
|
| 224 | ); |
||
| 225 | 1 | $text = ''; |
|
| 226 | 1 | foreach ($parts as $part) { |
|
| 227 | 1 | $text .= self::uchr(hexdec($part)); |
|
| 228 | } |
||
| 229 | 1 | $this->table[$char_from + $position] = $text; |
|
| 230 | } |
||
| 231 | } |
||
| 232 | } |
||
| 233 | } |
||
| 234 | } |
||
| 235 | |||
| 236 | 24 | return $this->table; |
|
| 237 | } |
||
| 238 | |||
| 239 | /** |
||
| 240 | * @param array $table |
||
| 241 | */ |
||
| 242 | public function setTable($table) |
||
| 243 | { |
||
| 244 | $this->table = $table; |
||
| 245 | } |
||
| 246 | |||
| 247 | /** |
||
| 248 | * @param string $hexa |
||
| 249 | * @param bool $add_braces |
||
| 250 | * |
||
| 251 | * @return string |
||
| 252 | */ |
||
| 253 | 28 | public static function decodeHexadecimal($hexa, $add_braces = false) |
|
| 254 | { |
||
| 255 | // Special shortcut for XML content. |
||
| 256 | 28 | if (false !== stripos($hexa, '<?xml')) { |
|
| 257 | 3 | return $hexa; |
|
| 258 | } |
||
| 259 | |||
| 260 | 28 | $text = ''; |
|
| 261 | 28 | $parts = preg_split('/(<[a-f0-9]+>)/si', $hexa, -1, PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE); |
|
| 262 | |||
| 263 | 28 | foreach ($parts as $part) { |
|
| 264 | 28 | if (preg_match('/^<.*>$/s', $part) && false === stripos($part, '<?xml')) { |
|
| 265 | // strip line breaks |
||
| 266 | 9 | $part = preg_replace("/[\r\n]/", '', $part); |
|
| 267 | 9 | $part = trim($part, '<>'); |
|
| 268 | 9 | if ($add_braces) { |
|
| 269 | 1 | $text .= '('; |
|
| 270 | } |
||
| 271 | |||
| 272 | 9 | $part = pack('H*', $part); |
|
| 273 | 9 | $text .= ($add_braces ? preg_replace('/\\\/s', '\\\\\\', $part) : $part); |
|
| 274 | |||
| 275 | 9 | if ($add_braces) { |
|
| 276 | 9 | $text .= ')'; |
|
| 277 | } |
||
| 278 | } else { |
||
| 279 | 28 | $text .= $part; |
|
| 280 | } |
||
| 281 | } |
||
| 282 | |||
| 283 | 28 | return $text; |
|
| 284 | } |
||
| 285 | |||
| 286 | /** |
||
| 287 | * @param string $text |
||
| 288 | * |
||
| 289 | * @return string |
||
| 290 | */ |
||
| 291 | 28 | public static function decodeOctal($text) |
|
| 305 | } |
||
| 306 | |||
| 307 | /** |
||
| 308 | * @param string $text |
||
| 309 | * |
||
| 310 | * @return string |
||
| 311 | */ |
||
| 312 | 42 | public static function decodeEntities($text) |
|
| 313 | { |
||
| 314 | 42 | $parts = preg_split('/(#\d{2})/s', $text, -1, PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE); |
|
| 315 | 42 | $text = ''; |
|
| 316 | |||
| 317 | 42 | foreach ($parts as $part) { |
|
| 318 | 42 | if (preg_match('/^#\d{2}$/', $part)) { |
|
| 319 | 3 | $text .= \chr(hexdec(trim($part, '#'))); |
|
| 320 | } else { |
||
| 321 | 42 | $text .= $part; |
|
| 322 | } |
||
| 323 | } |
||
| 324 | |||
| 325 | 42 | return $text; |
|
| 326 | } |
||
| 327 | |||
| 328 | /** |
||
| 329 | * @param string $text |
||
| 330 | * |
||
| 331 | * @return string |
||
| 332 | */ |
||
| 333 | 28 | public static function decodeUnicode($text) |
|
| 334 | { |
||
| 335 | 28 | if (preg_match('/^\xFE\xFF/i', $text)) { |
|
| 336 | // Strip U+FEFF byte order marker. |
||
| 337 | 19 | $decode = substr($text, 2); |
|
| 338 | 19 | $text = ''; |
|
| 339 | 19 | $length = \strlen($decode); |
|
| 340 | |||
| 341 | 19 | for ($i = 0; $i < $length; $i += 2) { |
|
| 342 | 19 | $text .= self::uchr(hexdec(bin2hex(substr($decode, $i, 2)))); |
|
| 343 | } |
||
| 344 | } |
||
| 345 | |||
| 346 | 28 | return $text; |
|
| 347 | } |
||
| 348 | |||
| 349 | /** |
||
| 350 | * @return int |
||
| 351 | */ |
||
| 352 | 13 | public static function getFontSpaceLimit() |
|
| 355 | } |
||
| 356 | |||
| 357 | /** |
||
| 358 | * @param int $font_space |
||
| 359 | * @return void |
||
| 360 | */ |
||
| 361 | 1 | public static function setFontSpaceLimit($font_space) |
|
| 362 | { |
||
| 363 | 1 | Font::$font_space = $font_space; |
|
| 364 | 1 | } |
|
| 365 | |||
| 366 | /** |
||
| 367 | * @param array $commands |
||
| 368 | * |
||
| 369 | * @return string |
||
| 370 | */ |
||
| 371 | 12 | public function decodeText($commands) |
|
| 417 | } |
||
| 418 | |||
| 419 | /** |
||
| 420 | * @param string $text |
||
| 421 | * @param bool $unicode This parameter is deprecated and might be removed in a future release |
||
| 422 | * |
||
| 423 | * @return string |
||
| 424 | */ |
||
| 425 | 14 | public function decodeContent($text, &$unicode = null) |
|
| 509 | } |
||
| 510 | } |
||
| 511 |
Loading history...
