From 7b390f1c9299d644ad0339e83724e1457c150410 Mon Sep 17 00:00:00 2001 From: ByteHamster Date: Sun, 24 Mar 2024 18:04:39 +0100 Subject: Speed up feed parsing (#7023) AntennaPod is quite slow with huge feeds. The reason is that we have a bunch of workarounds for misbehaving feeds that also make it slower to work with feeds that do not misbehave. Changes: - Only start guessing duplicate episodes when no "proper" match is found - Only parse non-html as HTML for attributes that really need it - Do not log failed Long parsing when size is not specified - Try to parse dates with RFC822 first before falling back to workarounds for other formats I ran a benchmark with "Stuff you should know" (for which the workarounds are not needed) containing 2k episodes. Includes download of 8MB of feed XML (~5 seconds), debug build. Before: 44 seconds, after: 13 seconds ==> 3.4 times faster feed refresh --- core/src/main/java/de/danoeh/antennapod/core/storage/DBTasks.java | 7 +++++++ .../danoeh/antennapod/core/storage/FeedItemDuplicateGuesser.java | 2 +- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'core/src') diff --git a/core/src/main/java/de/danoeh/antennapod/core/storage/DBTasks.java b/core/src/main/java/de/danoeh/antennapod/core/storage/DBTasks.java index 1fb0991dd..883aefee8 100644 --- a/core/src/main/java/de/danoeh/antennapod/core/storage/DBTasks.java +++ b/core/src/main/java/de/danoeh/antennapod/core/storage/DBTasks.java @@ -171,6 +171,13 @@ public final class DBTasks { * This is to work around podcasters breaking their GUIDs. */ private static FeedItem searchFeedItemGuessDuplicate(List items, FeedItem searchItem) { + // First, see if it is a well-behaving feed that contains an item with the same identifier + for (FeedItem item : items) { + if (FeedItemDuplicateGuesser.sameAndNotEmpty(item.getItemIdentifier(), searchItem.getItemIdentifier())) { + return item; + } + } + // Not found yet, start more expensive guessing for (FeedItem item : items) { if (FeedItemDuplicateGuesser.seemDuplicates(item, searchItem)) { return item; diff --git a/core/src/main/java/de/danoeh/antennapod/core/storage/FeedItemDuplicateGuesser.java b/core/src/main/java/de/danoeh/antennapod/core/storage/FeedItemDuplicateGuesser.java index 88f896187..1eb8b0577 100644 --- a/core/src/main/java/de/danoeh/antennapod/core/storage/FeedItemDuplicateGuesser.java +++ b/core/src/main/java/de/danoeh/antennapod/core/storage/FeedItemDuplicateGuesser.java @@ -31,7 +31,7 @@ public class FeedItemDuplicateGuesser { && mimeTypeLooksSimilar(media1, media2); } - private static boolean sameAndNotEmpty(String string1, String string2) { + public static boolean sameAndNotEmpty(String string1, String string2) { if (TextUtils.isEmpty(string1) || TextUtils.isEmpty(string2)) { return false; } -- cgit v1.2.3