| Total Complexity | 44 |
| Total Lines | 273 |
| Duplicated Lines | 0 % |
| Changes | 19 | ||
| Bugs | 4 | Features | 2 |
Complex classes like Parser 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 Parser, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 47 | class Parser |
||
| 48 | { |
||
| 49 | /** |
||
| 50 | * @var PDFObject[] |
||
| 51 | */ |
||
| 52 | protected $objects = []; |
||
| 53 | |||
| 54 | protected $rawDataParser; |
||
| 55 | |||
| 56 | public function __construct($cfg = []) |
||
| 57 | { |
||
| 58 | $this->rawDataParser = new RawDataParser($cfg); |
||
| 59 | } |
||
| 60 | |||
| 61 | /** |
||
| 62 | * @param string $filename |
||
| 63 | * |
||
| 64 | * @return Document |
||
| 65 | * |
||
| 66 | * @throws \Exception |
||
| 67 | */ |
||
| 68 | public function parseFile($filename) |
||
| 82 | } |
||
| 83 | |||
| 84 | /** |
||
| 85 | * @param string $content PDF content to parse |
||
| 86 | * |
||
| 87 | * @return Document |
||
| 88 | * |
||
| 89 | * @throws \Exception if secured PDF file was detected |
||
| 90 | * @throws \Exception if no object list was found |
||
| 91 | */ |
||
| 92 | public function parseContent($content) |
||
| 118 | } |
||
| 119 | |||
| 120 | protected function parseTrailer($structure, $document) |
||
| 140 | } |
||
| 141 | |||
| 142 | /** |
||
| 143 | * @param string $id |
||
| 144 | * @param array $structure |
||
| 145 | * @param Document $document |
||
| 146 | */ |
||
| 147 | protected function parseObject($id, $structure, $document) |
||
| 148 | { |
||
| 149 | $header = new Header([], $document); |
||
| 150 | $content = ''; |
||
| 151 | |||
| 152 | foreach ($structure as $position => $part) { |
||
| 153 | switch ($part[0]) { |
||
| 154 | case '[': |
||
| 155 | $elements = []; |
||
| 156 | |||
| 157 | foreach ($part[1] as $sub_element) { |
||
| 158 | $sub_type = $sub_element[0]; |
||
| 159 | $sub_value = $sub_element[1]; |
||
| 160 | $elements[] = $this->parseHeaderElement($sub_type, $sub_value, $document); |
||
| 161 | } |
||
| 162 | |||
| 163 | $header = new Header($elements, $document); |
||
| 164 | break; |
||
| 165 | |||
| 166 | case '<<': |
||
| 167 | $header = $this->parseHeader($part[1], $document); |
||
| 168 | break; |
||
| 169 | |||
| 170 | case 'stream': |
||
| 171 | $content = isset($part[3][0]) ? $part[3][0] : $part[1]; |
||
| 172 | |||
| 173 | if ($header->get('Type')->equals('ObjStm')) { |
||
| 174 | $match = []; |
||
| 175 | |||
| 176 | // Split xrefs and contents. |
||
| 177 | preg_match('/^((\d+\s+\d+\s*)*)(.*)$/s', $content, $match); |
||
| 178 | $content = $match[3]; |
||
| 179 | |||
| 180 | // Extract xrefs. |
||
| 181 | $xrefs = preg_split( |
||
| 182 | '/(\d+\s+\d+\s*)/s', |
||
| 183 | $match[1], |
||
| 184 | -1, |
||
| 185 | PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE |
||
| 186 | ); |
||
| 187 | $table = []; |
||
| 188 | |||
| 189 | foreach ($xrefs as $xref) { |
||
| 190 | list($id, $position) = explode(' ', trim($xref)); |
||
| 191 | $table[$position] = $id; |
||
| 192 | } |
||
| 193 | |||
| 194 | ksort($table); |
||
| 195 | |||
| 196 | $ids = array_values($table); |
||
| 197 | $positions = array_keys($table); |
||
| 198 | |||
| 199 | foreach ($positions as $index => $position) { |
||
| 200 | $id = $ids[$index].'_0'; |
||
| 201 | $next_position = isset($positions[$index + 1]) ? $positions[$index + 1] : \strlen($content); |
||
| 202 | $sub_content = substr($content, $position, (int) $next_position - (int) $position); |
||
| 203 | |||
| 204 | $sub_header = Header::parse($sub_content, $document); |
||
| 205 | $object = PDFObject::factory($document, $sub_header, ''); |
||
| 206 | $this->objects[$id] = $object; |
||
| 207 | } |
||
| 208 | |||
| 209 | // It is not necessary to store this content. |
||
| 210 | $content = ''; |
||
| 211 | |||
| 212 | return; |
||
| 213 | } |
||
| 214 | break; |
||
| 215 | |||
| 216 | default: |
||
| 217 | if ('null' != $part) { |
||
| 218 | $element = $this->parseHeaderElement($part[0], $part[1], $document); |
||
| 219 | |||
| 220 | if ($element) { |
||
| 221 | $header = new Header([$element], $document); |
||
| 222 | } |
||
| 223 | } |
||
| 224 | break; |
||
| 225 | } |
||
| 226 | } |
||
| 227 | |||
| 228 | if (!isset($this->objects[$id])) { |
||
| 229 | $this->objects[$id] = PDFObject::factory($document, $header, $content); |
||
| 230 | } |
||
| 231 | } |
||
| 232 | |||
| 233 | /** |
||
| 234 | * @param array $structure |
||
| 235 | * @param Document $document |
||
| 236 | * |
||
| 237 | * @return Header |
||
| 238 | * |
||
| 239 | * @throws \Exception |
||
| 240 | */ |
||
| 241 | protected function parseHeader($structure, $document) |
||
| 255 | } |
||
| 256 | |||
| 257 | /** |
||
| 258 | * @param string $type |
||
| 259 | * @param string|array $value |
||
| 260 | * @param Document $document |
||
| 261 | * |
||
| 262 | * @return Element|Header|null |
||
| 263 | * |
||
| 264 | * @throws \Exception |
||
| 265 | */ |
||
| 266 | protected function parseHeaderElement($type, $value, $document) |
||
| 323 |