| Total Complexity | 56 |
| Total Lines | 242 |
| Duplicated Lines | 0 % |
| Changes | 2 | ||
| Bugs | 0 | Features | 0 |
Complex classes like FeedParser 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 FeedParser, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 2 | class FeedParser { |
||
| 3 | private $doc; |
||
| 4 | private $error; |
||
| 5 | private $libxml_errors = array(); |
||
| 6 | private $items; |
||
| 7 | private $link; |
||
| 8 | private $title; |
||
| 9 | private $type; |
||
| 10 | private $xpath; |
||
| 11 | |||
| 12 | const FEED_RDF = 0; |
||
| 13 | const FEED_RSS = 1; |
||
| 14 | const FEED_ATOM = 2; |
||
| 15 | |||
| 16 | public function __construct($data) { |
||
| 17 | libxml_use_internal_errors(true); |
||
| 18 | libxml_clear_errors(); |
||
| 19 | $this->doc = new DOMDocument(); |
||
| 20 | $this->doc->loadXML($data); |
||
| 21 | |||
| 22 | mb_substitute_character("none"); |
||
| 23 | |||
| 24 | $error = libxml_get_last_error(); |
||
| 25 | |||
| 26 | if ($error) { |
||
|
|
|||
| 27 | foreach (libxml_get_errors() as $error) { |
||
| 28 | if ($error->level == LIBXML_ERR_FATAL) { |
||
| 29 | if (!isset($this->error)) { |
||
| 30 | //currently only the first error is reported |
||
| 31 | $this->error = $this->format_error($error); |
||
| 32 | } |
||
| 33 | $this->libxml_errors [] = $this->format_error($error); |
||
| 34 | } |
||
| 35 | } |
||
| 36 | } |
||
| 37 | libxml_clear_errors(); |
||
| 38 | |||
| 39 | $this->items = array(); |
||
| 40 | } |
||
| 41 | |||
| 42 | public function init() { |
||
| 43 | $xpath = new DOMXPath($this->doc); |
||
| 44 | $xpath->registerNamespace('atom', 'http://www.w3.org/2005/Atom'); |
||
| 45 | $xpath->registerNamespace('atom03', 'http://purl.org/atom/ns#'); |
||
| 46 | $xpath->registerNamespace('media', 'http://search.yahoo.com/mrss/'); |
||
| 47 | $xpath->registerNamespace('rdf', 'http://www.w3.org/1999/02/22-rdf-syntax-ns#'); |
||
| 48 | $xpath->registerNamespace('slash', 'http://purl.org/rss/1.0/modules/slash/'); |
||
| 49 | $xpath->registerNamespace('dc', 'http://purl.org/dc/elements/1.1/'); |
||
| 50 | $xpath->registerNamespace('content', 'http://purl.org/rss/1.0/modules/content/'); |
||
| 51 | $xpath->registerNamespace('thread', 'http://purl.org/syndication/thread/1.0'); |
||
| 52 | |||
| 53 | $this->xpath = $xpath; |
||
| 54 | |||
| 55 | $root = $xpath->query("(//atom03:feed|//atom:feed|//channel|//rdf:rdf|//rdf:RDF)"); |
||
| 56 | |||
| 57 | if ($root && $root->length > 0) { |
||
| 58 | $root = $root->item(0); |
||
| 59 | |||
| 60 | if ($root) { |
||
| 61 | switch (mb_strtolower($root->tagName)) { |
||
| 62 | case "rdf:rdf": |
||
| 63 | $this->type = $this::FEED_RDF; |
||
| 64 | break; |
||
| 65 | case "channel": |
||
| 66 | $this->type = $this::FEED_RSS; |
||
| 67 | break; |
||
| 68 | case "feed": |
||
| 69 | case "atom:feed": |
||
| 70 | $this->type = $this::FEED_ATOM; |
||
| 71 | break; |
||
| 72 | default: |
||
| 73 | if (!isset($this->error)) { |
||
| 74 | $this->error = "Unknown/unsupported feed type"; |
||
| 75 | } |
||
| 76 | return; |
||
| 77 | } |
||
| 78 | } |
||
| 79 | |||
| 80 | switch ($this->type) { |
||
| 81 | case $this::FEED_ATOM: |
||
| 82 | |||
| 83 | $title = $xpath->query("//atom:feed/atom:title")->item(0); |
||
| 84 | |||
| 85 | if (!$title) { |
||
| 86 | $title = $xpath->query("//atom03:feed/atom03:title")->item(0); |
||
| 87 | } |
||
| 88 | |||
| 89 | |||
| 90 | if ($title) { |
||
| 91 | $this->title = $title->nodeValue; |
||
| 92 | } |
||
| 93 | |||
| 94 | $link = $xpath->query("//atom:feed/atom:link[not(@rel)]")->item(0); |
||
| 95 | |||
| 96 | if (!$link) { |
||
| 97 | $link = $xpath->query("//atom:feed/atom:link[@rel='alternate']")->item(0); |
||
| 98 | } |
||
| 99 | |||
| 100 | if (!$link) { |
||
| 101 | $link = $xpath->query("//atom03:feed/atom03:link[not(@rel)]")->item(0); |
||
| 102 | } |
||
| 103 | |||
| 104 | if (!$link) { |
||
| 105 | $link = $xpath->query("//atom03:feed/atom03:link[@rel='alternate']")->item(0); |
||
| 106 | } |
||
| 107 | |||
| 108 | if ($link && $link->hasAttributes()) { |
||
| 109 | $this->link = $link->getAttribute("href"); |
||
| 110 | } |
||
| 111 | |||
| 112 | $articles = $xpath->query("//atom:entry"); |
||
| 113 | |||
| 114 | if (!$articles || $articles->length == 0) { |
||
| 115 | $articles = $xpath->query("//atom03:entry"); |
||
| 116 | } |
||
| 117 | |||
| 118 | foreach ($articles as $article) { |
||
| 119 | array_push($this->items, new FeedItem_Atom($article, $this->doc, $this->xpath)); |
||
| 120 | } |
||
| 121 | |||
| 122 | break; |
||
| 123 | case $this::FEED_RSS: |
||
| 124 | $title = $xpath->query("//channel/title")->item(0); |
||
| 125 | |||
| 126 | if ($title) { |
||
| 127 | $this->title = $title->nodeValue; |
||
| 128 | } |
||
| 129 | |||
| 130 | $link = $xpath->query("//channel/link")->item(0); |
||
| 131 | |||
| 132 | if ($link) { |
||
| 133 | if ($link->getAttribute("href")) { |
||
| 134 | $this->link = $link->getAttribute("href"); |
||
| 135 | } else if ($link->nodeValue) { |
||
| 136 | $this->link = $link->nodeValue; |
||
| 137 | } |
||
| 138 | } |
||
| 139 | |||
| 140 | $articles = $xpath->query("//channel/item"); |
||
| 141 | |||
| 142 | foreach ($articles as $article) { |
||
| 143 | array_push($this->items, new FeedItem_RSS($article, $this->doc, $this->xpath)); |
||
| 144 | } |
||
| 145 | |||
| 146 | break; |
||
| 147 | case $this::FEED_RDF: |
||
| 148 | $xpath->registerNamespace('rssfake', 'http://purl.org/rss/1.0/'); |
||
| 149 | |||
| 150 | $title = $xpath->query("//rssfake:channel/rssfake:title")->item(0); |
||
| 151 | |||
| 152 | if ($title) { |
||
| 153 | $this->title = $title->nodeValue; |
||
| 154 | } |
||
| 155 | |||
| 156 | $link = $xpath->query("//rssfake:channel/rssfake:link")->item(0); |
||
| 157 | |||
| 158 | if ($link) { |
||
| 159 | $this->link = $link->nodeValue; |
||
| 160 | } |
||
| 161 | |||
| 162 | $articles = $xpath->query("//rssfake:item"); |
||
| 163 | |||
| 164 | foreach ($articles as $article) { |
||
| 165 | array_push($this->items, new FeedItem_RSS($article, $this->doc, $this->xpath)); |
||
| 166 | } |
||
| 167 | |||
| 168 | break; |
||
| 169 | |||
| 170 | } |
||
| 171 | |||
| 172 | if ($this->title) { |
||
| 173 | $this->title = trim($this->title); |
||
| 174 | } |
||
| 175 | if ($this->link) { |
||
| 176 | $this->link = trim($this->link); |
||
| 177 | } |
||
| 178 | |||
| 179 | } else { |
||
| 180 | if (!isset($this->error)) { |
||
| 181 | $this->error = "Unknown/unsupported feed type"; |
||
| 182 | } |
||
| 183 | return; |
||
| 184 | } |
||
| 185 | } |
||
| 186 | |||
| 187 | public function format_error($error) { |
||
| 188 | if ($error) { |
||
| 189 | return sprintf("LibXML error %s at line %d (column %d): %s", |
||
| 190 | $error->code, $error->line, $error->column, |
||
| 191 | $error->message); |
||
| 192 | } else { |
||
| 193 | return ""; |
||
| 194 | } |
||
| 195 | } |
||
| 196 | |||
| 197 | // libxml may have invalid unicode data in error messages |
||
| 198 | public function error() { |
||
| 199 | return UConverter::transcode($this->error, 'UTF-8', 'UTF-8'); |
||
| 200 | } |
||
| 201 | |||
| 202 | // WARNING: may return invalid unicode data |
||
| 203 | public function errors() { |
||
| 204 | return $this->libxml_errors; |
||
| 205 | } |
||
| 206 | |||
| 207 | public function get_link() { |
||
| 208 | return clean($this->link); |
||
| 209 | } |
||
| 210 | |||
| 211 | public function get_title() { |
||
| 213 | } |
||
| 214 | |||
| 215 | public function get_items() { |
||
| 216 | return $this->items; |
||
| 217 | } |
||
| 218 | |||
| 219 | public function get_links($rel) { |
||
| 244 | } |
||
| 245 | } |
||
| 246 |