Révision ed9a13f1
Ajouté par Assos Assos il y a presque 4 ans
| drupal7/sites/all/modules/feeds/libraries/common_syndication_parser.inc | ||
|---|---|---|
| 2 | 2 |
|
| 3 | 3 |
/** |
| 4 | 4 |
* @file |
| 5 |
* Downloading and parsing functions for Common Syndication Parser.
|
|
| 6 |
* Pillaged from FeedAPI common syndication parser.
|
|
| 5 |
* Downloading and parsing functions for Common Syndication Parser. |
|
| 6 |
* Pillaged from FeedAPI common syndication parser. |
|
| 7 | 7 |
* |
| 8 | 8 |
* @todo Restructure. OO could work wonders here. |
| 9 | 9 |
* @todo Write unit tests. |
| ... | ... | |
| 31 | 31 |
return FALSE; |
| 32 | 32 |
} |
| 33 | 33 |
$feed_type = _parser_common_syndication_feed_format_detect($xml); |
| 34 |
if ($feed_type == "atom1.0") {
|
|
| 34 |
if ($feed_type == "atom1.0") {
|
|
| 35 | 35 |
return _parser_common_syndication_atom10_parse($xml); |
| 36 | 36 |
} |
| 37 | 37 |
if ($feed_type == "RSS2.0" || $feed_type == "RSS0.91" || $feed_type == "RSS0.92") {
|
| ... | ... | |
| 88 | 88 |
|
| 89 | 89 |
$base = _parser_common_syndication_atom10_parse_base_url($feed_XML); |
| 90 | 90 |
|
| 91 |
// Detect the title |
|
| 91 |
// Detect the title.
|
|
| 92 | 92 |
$parsed_source['title'] = isset($feed_XML->title) ? _parser_common_syndication_title("{$feed_XML->title}") : "";
|
| 93 |
// Detect the description |
|
| 93 |
// Detect the description.
|
|
| 94 | 94 |
$parsed_source['description'] = isset($feed_XML->subtitle) ? "{$feed_XML->subtitle}" : "";
|
| 95 | 95 |
|
| 96 | 96 |
$parsed_source['link'] = _parser_common_syndication_link($feed_XML->link); |
| ... | ... | |
| 101 | 101 |
$parsed_source['items'] = array(); |
| 102 | 102 |
|
| 103 | 103 |
foreach ($feed_XML->entry as $news) {
|
| 104 |
$georss = (array)$news->children($ns["georss"]); |
|
| 104 |
$georss = (array) $news->children($ns["georss"]);
|
|
| 105 | 105 |
$geoname = ''; |
| 106 | 106 |
if (isset($georss['featureName'])) {
|
| 107 | 107 |
$geoname = "{$georss['featureName']}";
|
| ... | ... | |
| 127 | 127 |
if (isset($category['scheme'])) {
|
| 128 | 128 |
$domain = "{$category['scheme']}";
|
| 129 | 129 |
if (!empty($domain)) {
|
| 130 |
if (!isset($additional_taxonomies['ATOM Domains'][$domain])) {
|
|
| 131 |
$additional_taxonomies['ATOM Domains'][$domain] = array();
|
|
| 132 |
}
|
|
| 133 |
$additional_taxonomies['ATOM Domains'][$domain][] = count($additional_taxonomies['ATOM Categories']) - 1;
|
|
| 130 |
if (!isset($additional_taxonomies['ATOM Domains'][$domain])) {
|
|
| 131 |
$additional_taxonomies['ATOM Domains'][$domain] = array(); |
|
| 132 |
} |
|
| 133 |
$additional_taxonomies['ATOM Domains'][$domain][] = count($additional_taxonomies['ATOM Categories']) - 1; |
|
| 134 | 134 |
} |
| 135 | 135 |
} |
| 136 | 136 |
$additional_taxonomies['ATOM Categories'][] = "{$category['term']}";
|
| ... | ... | |
| 141 | 141 |
|
| 142 | 142 |
$body = ''; |
| 143 | 143 |
if (!empty($news->content)) {
|
| 144 |
foreach ($news->content->children() as $child) {
|
|
| 144 |
foreach ($news->content->children() as $child) {
|
|
| 145 | 145 |
$body .= $child->asXML(); |
| 146 | 146 |
} |
| 147 | 147 |
$body .= "{$news->content}";
|
| 148 | 148 |
} |
| 149 | 149 |
elseif (!empty($news->summary)) {
|
| 150 |
foreach ($news->summary->children() as $child) {
|
|
| 150 |
foreach ($news->summary->children() as $child) {
|
|
| 151 | 151 |
$body .= $child->asXML(); |
| 152 | 152 |
} |
| 153 | 153 |
$body .= "{$news->summary}";
|
| ... | ... | |
| 175 | 175 |
$item['timestamp'] = _parser_common_syndication_parse_date("{$news->published}");
|
| 176 | 176 |
} |
| 177 | 177 |
elseif (isset($news->issued)) {
|
| 178 |
$item['timestamp'] = _parser_common_syndication_parse_date("{$news->issued}");
|
|
| 178 |
$item['timestamp'] = _parser_common_syndication_parse_date("{$news->issued}");
|
|
| 179 | 179 |
} |
| 180 | 180 |
elseif (isset($news->updated)) {
|
| 181 | 181 |
$item['timestamp'] = _parser_common_syndication_parse_date("{$news->updated}");
|
| ... | ... | |
| 340 | 340 |
'author_name' => array('dc:creator', 'dc:publisher'),
|
| 341 | 341 |
'guid' => 'rdf:about', |
| 342 | 342 |
'timestamp' => 'dc:date', |
| 343 |
'tags' => 'dc:subject' |
|
| 343 |
'tags' => 'dc:subject',
|
|
| 344 | 344 |
)); |
| 345 | 345 |
|
| 346 | 346 |
// Special handling for the title: |
| ... | ... | |
| 357 | 357 |
// Add every found RDF property to the feed item. |
| 358 | 358 |
$item['rdf'] = array(); |
| 359 | 359 |
foreach ($rdf_data as $rdf_property => $rdf_value) {
|
| 360 |
// looks nicer in the mapper UI
|
|
| 360 |
// Looks nicer in the mapper UI.
|
|
| 361 | 361 |
// @todo Revisit, not used with feedapi mapper anymore. |
| 362 | 362 |
$rdf_property = str_replace(':', '_', $rdf_property);
|
| 363 | 363 |
$item['rdf'][$rdf_property] = $rdf_value; |
| ... | ... | |
| 369 | 369 |
return $parsed_source; |
| 370 | 370 |
} |
| 371 | 371 |
|
| 372 |
/** |
|
| 373 |
* |
|
| 374 |
*/ |
|
| 372 | 375 |
function _parser_common_syndication_RDF10_property($rdf_data, $rdf_properties = array()) {
|
| 373 | 376 |
$rdf_properties = is_array($rdf_properties) ? $rdf_properties : array_slice(func_get_args(), 1); |
| 374 | 377 |
foreach ($rdf_properties as $rdf_property) {
|
| 375 | 378 |
if ($rdf_property && !empty($rdf_data[$rdf_property])) {
|
| 376 |
// remove empty strings
|
|
| 379 |
// Remove empty strings.
|
|
| 377 | 380 |
return array_filter($rdf_data[$rdf_property], 'strlen'); |
| 378 | 381 |
} |
| 379 | 382 |
} |
| 380 | 383 |
} |
| 381 | 384 |
|
| 385 |
/** |
|
| 386 |
* |
|
| 387 |
*/ |
|
| 382 | 388 |
function _parser_common_syndication_RDF10_item($rdf_data, $mappings) {
|
| 383 | 389 |
foreach ($mappings as $k => $v) {
|
| 384 | 390 |
$values = _parser_common_syndication_RDF10_property($rdf_data, $v); |
| ... | ... | |
| 394 | 400 |
|
| 395 | 401 |
$ns = array( |
| 396 | 402 |
"content" => "http://purl.org/rss/1.0/modules/content/", |
| 397 |
"dc" => "http://purl.org/dc/elements/1.1/",
|
|
| 398 |
"georss" => "http://www.georss.org/georss",
|
|
| 403 |
"dc" => "http://purl.org/dc/elements/1.1/", |
|
| 404 |
"georss" => "http://www.georss.org/georss", |
|
| 399 | 405 |
); |
| 400 | 406 |
|
| 401 | 407 |
$parsed_source = array(); |
| ... | ... | |
| 415 | 421 |
|
| 416 | 422 |
$category = $news->xpath('category');
|
| 417 | 423 |
// Get children for current namespace. |
| 418 |
$content = (array)$news->children($ns["content"]); |
|
| 419 |
$dc = (array)$news->children($ns["dc"]); |
|
| 420 |
$georss = (array)$news->children($ns["georss"]); |
|
| 424 |
$content = (array) $news->children($ns["content"]);
|
|
| 425 |
$dc = (array) $news->children($ns["dc"]);
|
|
| 426 |
$georss = (array) $news->children($ns["georss"]);
|
|
| 421 | 427 |
$news = (array) $news; |
| 422 | 428 |
$news['category'] = $category; |
| 423 | 429 |
|
| ... | ... | |
| 430 | 436 |
} |
| 431 | 437 |
// Some sources use content:encoded as description i.e. |
| 432 | 438 |
// PostNuke PageSetter module. |
| 433 |
if (isset($news['encoded'])) { // content:encoded for PHP < 5.1.2.
|
|
| 439 |
// content:encoded for PHP < 5.1.2. |
|
| 440 |
if (isset($news['encoded'])) {
|
|
| 434 | 441 |
if (strlen($body) < strlen("{$news['encoded']}")) {
|
| 435 | 442 |
$body = "{$news['encoded']}";
|
| 436 | 443 |
} |
| 437 | 444 |
} |
| 438 |
if (isset($content['encoded'])) { // content:encoded for PHP >= 5.1.2.
|
|
| 445 |
// content:encoded for PHP >= 5.1.2. |
|
| 446 |
if (isset($content['encoded'])) {
|
|
| 439 | 447 |
if (strlen($body) < strlen("{$content['encoded']}")) {
|
| 440 | 448 |
$body = "{$content['encoded']}";
|
| 441 | 449 |
} |
| ... | ... | |
| 448 | 456 |
$original_author = "{$news['author']}";
|
| 449 | 457 |
} |
| 450 | 458 |
elseif (!empty($dc["creator"])) {
|
| 451 |
$original_author = (string)$dc["creator"]; |
|
| 459 |
$original_author = (string) $dc["creator"];
|
|
| 452 | 460 |
} |
| 453 | 461 |
|
| 454 | 462 |
if (!empty($news['link'])) {
|
| ... | ... | |
| 486 | 494 |
if (isset($category['domain'])) {
|
| 487 | 495 |
$domain = "{$category['domain']}";
|
| 488 | 496 |
if (!empty($domain)) {
|
| 489 |
if (!isset($additional_taxonomies['RSS Domains'][$domain])) {
|
|
| 490 |
$additional_taxonomies['RSS Domains'][$domain] = array();
|
|
| 491 |
}
|
|
| 492 |
$additional_taxonomies['RSS Domains'][$domain][] = count($additional_taxonomies['RSS Categories']) - 1;
|
|
| 497 |
if (!isset($additional_taxonomies['RSS Domains'][$domain])) {
|
|
| 498 |
$additional_taxonomies['RSS Domains'][$domain] = array(); |
|
| 499 |
} |
|
| 500 |
$additional_taxonomies['RSS Domains'][$domain][] = count($additional_taxonomies['RSS Categories']) - 1; |
|
| 493 | 501 |
} |
| 494 | 502 |
} |
| 495 | 503 |
} |
| ... | ... | |
| 587 | 595 |
list($year, $month, $day, $hours, $minutes, $seconds) = array($match[1], $match[2], $match[3], $match[4], $match[5], $match[6]); |
| 588 | 596 |
// Calculate the epoch for current date assuming GMT. |
| 589 | 597 |
$epoch = gmmktime($hours, $minutes, $seconds, $month, $day, $year); |
| 590 |
if ($match[10] != 'Z') { // Z is zulu time, aka GMT
|
|
| 598 |
// Z is zulu time, aka GMT. |
|
| 599 |
if ($match[10] != 'Z') {
|
|
| 591 | 600 |
list($tz_mod, $tz_hour, $tz_min) = array($match[8], $match[9], $match[10]); |
| 592 | 601 |
// Zero out the variables. |
| 593 | 602 |
if (!$tz_hour) {
|
| ... | ... | |
| 615 | 624 |
* original article) |
| 616 | 625 |
* |
| 617 | 626 |
* @param array $links |
| 618 |
* Array of SimpleXML objects |
|
| 627 |
* Array of SimpleXML objects.
|
|
| 619 | 628 |
* |
| 620 | 629 |
* @return string |
| 621 | 630 |
* An URL if found. An empty string otherwise. |
| ... | ... | |
| 637 | 646 |
} |
| 638 | 647 |
|
| 639 | 648 |
/** |
| 640 |
* Prepare raw data to be a title |
|
| 649 |
* Prepare raw data to be a title.
|
|
| 641 | 650 |
*/ |
| 642 | 651 |
function _parser_common_syndication_title($title, $body = FALSE) {
|
| 643 | 652 |
if (empty($title) && !empty($body)) {
|
Formats disponibles : Unified diff
Weekly update of contrib modules