summaryrefslogtreecommitdiff
path: root/magpierss/rss_fetch.inc
diff options
context:
space:
mode:
Diffstat (limited to 'magpierss/rss_fetch.inc')
-rw-r--r--magpierss/rss_fetch.inc30
1 files changed, 29 insertions, 1 deletions
diff --git a/magpierss/rss_fetch.inc b/magpierss/rss_fetch.inc
index 695d3b69e..dd475e31d 100644
--- a/magpierss/rss_fetch.inc
+++ b/magpierss/rss_fetch.inc
@@ -279,6 +279,33 @@ function _fetch_remote_file ($url, $headers = "" ) {
}
+function _convert_entities ($string) {
+ # Source: http://www.w3.org/TR/REC-html40/sgml/entities.html
+ $html_entities = array(
+ "&nbsp", "&iexcl", "&cent", "&pound", "&curren", "&yen", "&brvbar", "&sect", "&uml", "&copy",
+ "&ordf", "&laquo", "&not", "&shy", "&reg", "&macr", "&deg", "&plusmn", "&sup2", "&sup3",
+ "&acute", "&micro", "&para", "&middot", "&cedil", "&sup1", "&ordm", "&raquo", "&frac14", "&frac12",
+ "&frac34", "&iquest", "&Agrave", "&Aacute", "&Acirc", "&Atilde", "&Auml", "&Aring", "&AElig", "&Ccedil",
+ "&Egrave", "&Eacute", "&Ecirc", "&Euml", "&Igrave", "&Iacute", "&Icirc", "&Iuml", "&ETH", "&Ntilde",
+ "&Ograve", "&Oacute", "&Ocirc", "&Otilde", "&Ouml", "&times", "&Oslash", "&Ugrave", "&Uacute", "&Ucirc",
+ "&Uuml", "&Yacute", "&THORN", "&szlig", "&agrave", "&aacute", "&acirc", "&atilde", "&auml", "&aring",
+ "&aelig", "&ccedil", "&egrave", "&eacute", "&ecirc", "&euml", "&igrave", "&iacute", "&icirc", "&iuml",
+ "&eth", "&ntilde", "&ograve", "&oacute", "&ocirc", "&otilde", "&ouml", "&divide", "&oslash", "&ugrave",
+ "&uacute", "&ucirc", "&uuml", "&yacute", "&thorn", "&yuml",);
+ $numeric_entities = array(
+ " ", "¡", "¢", "£", "¤", "¥", "¦", "§", "¨", "©",
+ "ª", "«", "¬", "­", "®", "¯", "°", "±", "²", "³",
+ "´", "µ", "¶", "·", "¸", "¹", "º", "»", "¼", "½",
+ "¾", "¿", "À", "Á", "Â", "Ã", "Ä", "Å", "Æ", "Ç",
+ "È", "É", "Ê", "Ë", "Ì", "Í", "Î", "Ï", "Ð", "Ñ",
+ "Ò", "Ó", "Ô", "Õ", "Ö", "×", "Ø", "Ù", "Ú", "Û",
+ "Ü", "Ý", "Þ", "ß", "à", "á", "â", "ã", "ä", "å",
+ "æ", "ç", "è", "é", "ê", "ë", "ì", "í", "î", "ï",
+ "ð", "ñ", "ò", "ó", "ô", "õ", "ö", "÷", "ø", "ù",
+ "ú", "û", "ü", "ý", "þ", "ÿ");
+ return str_replace($html_entities, $numeric_entities, $string);
+}
+
/*=======================================================================*\
Function: _response_to_rss
Purpose: parse an HTTP response object into an RSS object
@@ -286,7 +313,8 @@ function _fetch_remote_file ($url, $headers = "" ) {
Output: parsed RSS object (see rss_parse)
\*=======================================================================*/
function _response_to_rss ($resp) {
- $rss = new MagpieRSS( $resp->results, MAGPIE_OUTPUT_ENCODING, MAGPIE_INPUT_ENCODING, MAGPIE_DETECT_ENCODING );
+ $converted_source = _convert_entities(mb_convert_encoding($resp->results, "UTF-8", mb_detect_encoding($resp->results)));
+ $rss = new MagpieRSS( $converted_source, MAGPIE_OUTPUT_ENCODING, "UTF-8", false);
// if RSS parsed successfully
if ( $rss and !$rss->ERROR) {