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

fix: add second-pass nbsp cleanup directly in get_articles()

Browse Source 
The strip_source_suffix() fallbacks aren't catching all nbsp-separated
publisher names. Adding a direct strrpos-based cleanup pass in the
get_articles() method itself as a safety net. This operates on the
already-decoded text returned by strip_source_suffix().

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Terence Ong
2026-04-08 11:02:28 +07:00
parent 0a550cabfe
commit 44cc4f56a3
2 changed files with 46 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
includes/class-peptide-news-rest-api.php
View File

@@ -146,14 +146,30 @@ class Peptide_News_Rest_API {
$offset $offset
) ); ) );
// Strip source name from titles and summaries (e.g. "Article Title - Toronto Star"). // Strip source name from titles, excerpts, and summaries.
$nbsp = "\xC2\xA0"; // UTF-8 non-breaking space.
foreach ( $articles as $article ) { foreach ( $articles as $article ) {
$article->title = $this->strip_source_suffix( $article->title, $article->source, $article->source_url ); $fields = array( 'title', 'excerpt', 'ai_summary' );
if ( ! empty( $article->ai_summary ) ) { foreach ( $fields as $field ) {
$article->ai_summary = $this->strip_source_suffix( $article->ai_summary, $article->source, $article->source_url ); if ( empty( $article->$field ) ) {
} continue;
if ( ! empty( $article->excerpt ) ) { }
$article->excerpt = $this->strip_source_suffix( $article->excerpt, $article->source, $article->source_url ); // First pass: use strip_source_suffix for known patterns.
$article->$field = $this->strip_source_suffix( $article->$field, $article->source, $article->source_url );
// Second pass: catch any remaining nbsp-separated publisher names
// (e.g., "...text\xC2\xA0\xC2\xA0Publisher Name" from Google News RSS).
$text = $article->$field;
$pos = strrpos( $text, $nbsp . $nbsp );
if ( false === $pos ) {
$pos = strrpos( $text, $nbsp );
}
if ( false !== $pos && $pos > 10 ) {
$candidate = rtrim( substr( $text, 0, $pos ) );
if ( strlen( $candidate ) > strlen( $text ) * 0.3 ) {
$article->$field = $candidate;
}
}
} }
} }

30
peptide-news-plugin/includes/class-peptide-news-rest-api.php
View File

@@ -143,14 +143,30 @@ class Peptide_News_Rest_API {
$offset $offset
) ); ) );
// Strip source name from titles and summaries (e.g. "Article Title - Toronto Star"). // Strip source name from titles, excerpts, and summaries.
$nbsp = "\xC2\xA0"; // UTF-8 non-breaking space.
foreach ( $articles as $article ) { foreach ( $articles as $article ) {
$article->title = $this->strip_source_suffix( $article->title, $article->source, $article->source_url ); $fields = array( 'title', 'excerpt', 'ai_summary' );
if ( ! empty( $article->ai_summary ) ) { foreach ( $fields as $field ) {
$article->ai_summary = $this->strip_source_suffix( $article->ai_summary, $article->source, $article->source_url ); if ( empty( $article->$field ) ) {
} continue;
if ( ! empty( $article->excerpt ) ) { }
$article->excerpt = $this->strip_source_suffix( $article->excerpt, $article->source, $article->source_url ); // First pass: use strip_source_suffix for known patterns.
$article->$field = $this->strip_source_suffix( $article->$field, $article->source, $article->source_url );
// Second pass: catch any remaining nbsp-separated publisher names
// (e.g., "...text\xC2\xA0\xC2\xA0Publisher Name" from Google News RSS).
$text = $article->$field;
$pos = strrpos( $text, $nbsp . $nbsp );
if ( false === $pos ) {
$pos = strrpos( $text, $nbsp );
}
if ( false !== $pos && $pos > 10 ) {
$candidate = rtrim( substr( $text, 0, $pos ) );
if ( strlen( $candidate ) > strlen( $text ) * 0.3 ) {
$article->$field = $candidate;
}
}
} }
} }