diff options
Diffstat (limited to 'app/src/main/java/org/terst/feedreader/data')
| -rw-r--r-- | app/src/main/java/org/terst/feedreader/data/FeedParser.kt | 14 |
1 files changed, 12 insertions, 2 deletions
diff --git a/app/src/main/java/org/terst/feedreader/data/FeedParser.kt b/app/src/main/java/org/terst/feedreader/data/FeedParser.kt index 735a707..629afe6 100644 --- a/app/src/main/java/org/terst/feedreader/data/FeedParser.kt +++ b/app/src/main/java/org/terst/feedreader/data/FeedParser.kt @@ -1,5 +1,6 @@ package org.terst.feedreader.data +import android.text.Html import android.util.Xml import org.xmlpull.v1.XmlPullParser import java.io.InputStream @@ -33,6 +34,15 @@ data class ParsedFeed( */ object FeedParser { + // Some feeds (kottke.org among them) double-encode titles: the XML pull parser already + // resolves the outer XML escaping (& -> &), but what's left can itself still be + // HTML-entity-encoded text (e.g. a literal "“" or "’") that the feed author + // encoded as if for direct HTML embedding. Titles are shown as plain text (Compose Text, + // not a WebView), so that residual entity needs a second, explicit decode pass or it + // shows up on-screen literally as "“" instead of the curly quote it's meant to be. + private fun decodeTitleEntities(text: String): String = + Html.fromHtml(text, Html.FROM_HTML_MODE_LEGACY).toString() + fun parse(input: InputStream): ParsedFeed { val parser = Xml.newPullParser() parser.setFeature(XmlPullParser.FEATURE_PROCESS_NAMESPACES, false) @@ -79,7 +89,7 @@ object FeedParser { itemDate = null; itemContent = null; itemDescription = null; itemImageUrl = null } "title" -> { - val text = parser.nextText() + val text = decodeTitleEntities(parser.nextText()) if (inItem) itemTitle = text else feedTitle = text } "link" -> { @@ -154,7 +164,7 @@ object FeedParser { entryDate = null; entryContent = null; entrySummary = null; entryImageUrl = null } "title" -> { - val text = parser.nextText() + val text = decodeTitleEntities(parser.nextText()) if (inEntry) entryTitle = text else feedTitle = text } "link" -> { |
