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

6 files changed, 36 insertions, 15 deletions

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<FeedItem> 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;
         }
diff --git a/parser/feed/src/main/java/de/danoeh/antennapod/parser/feed/namespace/Itunes.java b/parser/feed/src/main/java/de/danoeh/antennapod/parser/feed/namespace/Itunes.java
index cb4bcb8a7..e76b678f1 100644
--- a/parser/feed/src/main/java/de/danoeh/antennapod/parser/feed/namespace/Itunes.java
+++ b/parser/feed/src/main/java/de/danoeh/antennapod/parser/feed/namespace/Itunes.java
@@ -51,12 +51,12 @@ public class Itunes extends Namespace {
         }
 
         String content = state.getContentBuf().toString();
-        String contentFromHtml = HtmlCompat.fromHtml(content, HtmlCompat.FROM_HTML_MODE_COMPACT).toString();
         if (TextUtils.isEmpty(content)) {
             return;
         }
 
         if (AUTHOR.equals(localName) && state.getFeed() != null && state.getTagstack().size() <= 3) {
+            String contentFromHtml = HtmlCompat.fromHtml(content, HtmlCompat.FROM_HTML_MODE_COMPACT).toString();
             state.getFeed().setAuthor(contentFromHtml);
         } else if (DURATION.equals(localName)) {
             try {
diff --git a/parser/feed/src/main/java/de/danoeh/antennapod/parser/feed/namespace/Media.java b/parser/feed/src/main/java/de/danoeh/antennapod/parser/feed/namespace/Media.java
index 85cafea84..9336423c6 100644
--- a/parser/feed/src/main/java/de/danoeh/antennapod/parser/feed/namespace/Media.java
+++ b/parser/feed/src/main/java/de/danoeh/antennapod/parser/feed/namespace/Media.java
@@ -73,10 +73,12 @@ public class Media extends Namespace {
                     && url != null && validTypeMedia) {
                 long size = 0;
                 String sizeStr = attributes.getValue(SIZE);
-                try {
-                    size = Long.parseLong(sizeStr);
-                } catch (NumberFormatException e) {
-                    Log.e(TAG, "Size \"" + sizeStr + "\" could not be parsed.");
+                if (!TextUtils.isEmpty(sizeStr)) {
+                    try {
+                        size = Long.parseLong(sizeStr);
+                    } catch (NumberFormatException e) {
+                        Log.e(TAG, "Size \"" + sizeStr + "\" could not be parsed.");
+                    }
                 }
 
                 int durationMs = 0;
diff --git a/parser/feed/src/main/java/de/danoeh/antennapod/parser/feed/namespace/Rss20.java b/parser/feed/src/main/java/de/danoeh/antennapod/parser/feed/namespace/Rss20.java
index b19500895..fd5e91e9d 100644
--- a/parser/feed/src/main/java/de/danoeh/antennapod/parser/feed/namespace/Rss20.java
+++ b/parser/feed/src/main/java/de/danoeh/antennapod/parser/feed/namespace/Rss20.java
@@ -92,7 +92,6 @@ public class Rss20 extends Namespace {
         } else if (state.getTagstack().size() >= 2 && state.getContentBuf() != null) {
             String contentRaw = state.getContentBuf().toString();
             String content = SyndStringUtils.trimAllWhitespace(contentRaw);
-            String contentFromHtml = HtmlCompat.fromHtml(content, HtmlCompat.FROM_HTML_MODE_COMPACT).toString();
             SyndElement topElement = state.getTagstack().peek();
             String top = topElement.getName();
             SyndElement secondElement = state.getSecondTag();
@@ -108,6 +107,8 @@ public class Rss20 extends Namespace {
                     state.getCurrentItem().setItemIdentifier(contentRaw);
                 }
             } else if (TITLE.equals(top)) {
+                // Calling fromHtml only if needed because it is slow for huge feeds
+                String contentFromHtml = HtmlCompat.fromHtml(content, HtmlCompat.FROM_HTML_MODE_COMPACT).toString();
                 if (ITEM.equals(second) && state.getCurrentItem() != null) {
                     state.getCurrentItem().setTitle(contentFromHtml);
                 } else if (CHANNEL.equals(second) && state.getFeed() != null) {
@@ -128,6 +129,8 @@ public class Rss20 extends Namespace {
                 }
             } else if (DESCR.equals(localName)) {
                 if (CHANNEL.equals(second) && state.getFeed() != null) {
+                    // Calling fromHtml only if needed because it is slow for huge feeds
+                    String contentFromHtml = HtmlCompat.fromHtml(content, HtmlCompat.FROM_HTML_MODE_COMPACT).toString();
                     state.getFeed().setDescription(contentFromHtml);
                 } else if (ITEM.equals(second) && state.getCurrentItem() != null) {
                     state.getCurrentItem().setDescriptionIfLonger(content); // fromHtml here breaks \n when not html
diff --git a/parser/feed/src/main/java/de/danoeh/antennapod/parser/feed/util/DateUtils.java b/parser/feed/src/main/java/de/danoeh/antennapod/parser/feed/util/DateUtils.java
index 9b7f48769..4d9f68905 100644
--- a/parser/feed/src/main/java/de/danoeh/antennapod/parser/feed/util/DateUtils.java
+++ b/parser/feed/src/main/java/de/danoeh/antennapod/parser/feed/util/DateUtils.java
@@ -5,6 +5,7 @@ import android.util.Log;
 import androidx.annotation.Nullable;
 import org.apache.commons.lang3.StringUtils;
 
+import java.text.ParseException;
 import java.text.ParsePosition;
 import java.text.SimpleDateFormat;
 import java.util.Date;
@@ -14,19 +15,27 @@ import java.util.TimeZone;
 /**
  * Parses several date formats.
  */
-public class DateUtils {
-
-    private DateUtils() {
-
-    }
-
+public abstract class DateUtils {
     private static final String TAG = "DateUtils";
-    private static final TimeZone defaultTimezone = TimeZone.getTimeZone("GMT");
+    private static final TimeZone TIME_ZONE_GMT = TimeZone.getTimeZone("GMT");
+    private static final ThreadLocal<SimpleDateFormat> RFC822_DATE_FORMAT = new ThreadLocal<>() {
+        @Override
+        protected SimpleDateFormat initialValue() {
+            SimpleDateFormat dateFormat = new SimpleDateFormat("EEE, dd MMM yyyy HH:mm:ss Z", Locale.US);
+            dateFormat.setTimeZone(TIME_ZONE_GMT);
+            return dateFormat;
+        }
+    };
 
     public static Date parse(final String input) {
         if (input == null) {
             throw new IllegalArgumentException("Date must not be null");
         }
+        try {
+            return RFC822_DATE_FORMAT.get().parse(input);
+        } catch (ParseException ignored) {
+            // Feed not following the specification? Now start all our expensive workarounds.
+        }
         String date = input.trim().replace('/', '-').replaceAll("( ){2,}+", " ");
 
         // remove colon from timezone to avoid differences between Android and Java SimpleDateFormat
@@ -97,7 +106,7 @@ public class DateUtils {
 
         SimpleDateFormat parser = new SimpleDateFormat("", Locale.US);
         parser.setLenient(false);
-        parser.setTimeZone(defaultTimezone);
+        parser.setTimeZone(TIME_ZONE_GMT);
 
         ParsePosition pos = new ParsePosition(0);
         for (String pattern : patterns) {