Fix Atom feeds crashing the whole parse on xhtml content/summary

<content type="xhtml">/<summary type="xhtml"> wrap real nested markup,
which XmlPullParser's nextText() can't handle (it requires a text-only
element) -- it threw and aborted parsing of the entire feed over one
xhtml-typed field. Walks and reconstructs the inner markup manually
instead, tracking depth against the parser's own getDepth().

1 files changed, 45 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 8b37e55..7a3ce93 100644
--- a/app/src/main/java/org/terst/feedreader/data/FeedParser.kt
+++ b/app/src/main/java/org/terst/feedreader/data/FeedParser.kt
@@ -43,6 +43,37 @@ object FeedParser {
     private fun decodeTitleEntities(text: String): String =
         Html.fromHtml(text, Html.FROM_HTML_MODE_LEGACY).toString()
 
+    // Atom's <content type="xhtml">/<summary type="xhtml"> wrap real nested markup
+    // (spec-legal: <content type="xhtml"><div xmlns="http://www.w3.org/1999/xhtml">
+    // ...actual HTML...</div></content>) instead of a plain text leaf. XmlPullParser's
+    // nextText() requires the element to be text-only and throws XmlPullParserException
+    // the instant it hits that nested <div> -- uncaught, that aborted parsing of the
+    // ENTIRE feed over one xhtml-typed field, not just that one entry. Manually walks and
+    // reconstructs the inner markup as an HTML string instead, tracking depth against the
+    // parser's own getDepth() (not a separately-maintained counter) so it can't drift out
+    // of sync with what nextText() would have consumed.
+    private fun readElementAsHtml(parser: XmlPullParser): String {
+        val startDepth = parser.depth
+        val sb = StringBuilder()
+        var event = parser.next()
+        while (!(event == XmlPullParser.END_TAG && parser.depth == startDepth)) {
+            when (event) {
+                XmlPullParser.START_TAG -> {
+                    sb.append('<').append(parser.name)
+                    for (i in 0 until parser.attributeCount) {
+                        sb.append(' ').append(parser.getAttributeName(i)).append("=\"")
+                            .append(parser.getAttributeValue(i).replace("\"", "&quot;")).append('"')
+                    }
+                    sb.append('>')
+                }
+                XmlPullParser.END_TAG -> sb.append("</").append(parser.name).append('>')
+                XmlPullParser.TEXT, XmlPullParser.CDSECT -> sb.append(parser.text)
+            }
+            event = parser.next()
+        }
+        return sb.toString().trim()
+    }
+
     fun parse(input: InputStream): ParsedFeed {
         val parser = Xml.newPullParser()
         parser.setFeature(XmlPullParser.FEATURE_PROCESS_NAMESPACES, false)
@@ -187,8 +218,20 @@ object FeedParser {
                         "name" -> if (inEntry && entryAuthor == null) entryAuthor = parser.nextText()
                         "updated" -> if (inEntry) entryDate = parseIso8601Date(parser.nextText())
                         "published" -> if (inEntry) entryDate = parseIso8601Date(parser.nextText()) ?: entryDate
-                        "content" -> if (inEntry) entryContent = parser.nextText()
-                        "summary" -> if (inEntry) entrySummary = parser.nextText()
+                        "content" -> if (inEntry) {
+                            entryContent = if (parser.getAttributeValue(null, "type") == "xhtml") {
+                                readElementAsHtml(parser)
+                            } else {
+                                parser.nextText()
+                            }
+                        }
+                        "summary" -> if (inEntry) {
+                            entrySummary = if (parser.getAttributeValue(null, "type") == "xhtml") {
+                                readElementAsHtml(parser)
+                            } else {
+                                parser.nextText()
+                            }
+                        }
                         "media:thumbnail" -> if (inEntry && entryImageUrl == null) {
                             entryImageUrl = parser.getAttributeValue(null, "url")
                         }