peptide-repo/peptide-news-plugin
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Deploy 0a550ca from main

Browse Source
This commit is contained in:
github-actions[bot]
2026-04-08 03:54:21 +00:00
parent 568529fdae
commit fb12a6a835
1 changed files with 4 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
includes/class-peptide-news-rest-api.php
View File

@@ -248,21 +248,10 @@ class Peptide_News_Rest_API {
// Fallback 2: strip trailing nbsp-separated publisher names. // Fallback 2: strip trailing nbsp-separated publisher names.
// Google News RSS excerpts use double non-breaking space + publisher name // Google News RSS excerpts use double non-breaking space + publisher name
// when the source field doesn't match (e.g., source = "news.google.com"). // when the source field doesn't match (e.g., source = "news.google.com").
// Uses string search instead of regex to avoid UTF-8/PCRE edge cases. // Uses mb_ereg for reliable multibyte matching.
$double_nbsp = $nbsp . $nbsp; if ( preg_match( '/^(.{10,}?)\x{00A0}{1,2}([A-Z][^.!?\x{00A0}]{0,55})$/u', $text, $m ) ) {
$nbsp_pos = strrpos( $text, $double_nbsp ); if ( mb_strlen( $m[1], 'UTF-8' ) > mb_strlen( $text, 'UTF-8' ) * 0.4 ) {
if ( false !== $nbsp_pos ) { return rtrim( $m[1] );
$after = substr( $text, $nbsp_pos + strlen( $double_nbsp ) );
} else {
$nbsp_pos = strrpos( $text, $nbsp );
if ( false !== $nbsp_pos ) {
$after = substr( $text, $nbsp_pos + strlen( $nbsp ) );
}
}
if ( false !== $nbsp_pos && $nbsp_pos > strlen( $text ) * 0.4 ) {
// Only strip if what follows looks like a publisher name (< 60 chars, starts uppercase).
if ( ! empty( $after ) && strlen( $after ) < 60 && preg_match( '/^[A-Z]/u', $after ) ) {
return rtrim( substr( $text, 0, $nbsp_pos ) );
} }
} }