Mirror/MarginaliaSearch
1
0
Fork 0
mirror of https://github.com/MarginaliaSearch/MarginaliaSearch.git synced 2025-02-23 04:58:59 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

(feeds) Make feed XML parsing more lenient

Browse Source 
... by consuming BOM markers and leading whitespace.
This commit is contained in:
Viktor Lofgren 2024-12-18 17:18:41 +01:00
parent b66fb9caf6
commit 2dc9f2e639
2 changed files with 9 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
code/functions/live-capture/build.gradle
View File

@ -31,6 +31,7 @@ dependencies {
implementation libs.sqlite
implementation libs.bundles.slf4j
implementation libs.commons.lang3
implementation libs.commons.io
implementation libs.prometheus
implementation libs.guava

11
code/functions/live-capture/java/nu/marginalia/rss/svc/FeedFetcherService.java
View File

@ -18,6 +18,7 @@ import nu.marginalia.storage.FileStorageService;
import nu.marginalia.storage.model.FileStorage;
import nu.marginalia.storage.model.FileStorageType;
import nu.marginalia.util.SimpleBlockingThreadPool;
import org.apache.commons.io.input.BOMInputStream;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@ -29,6 +30,7 @@ import java.net.URISyntaxException;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
import java.nio.charset.StandardCharsets;
import java.sql.SQLException;
import java.time.Duration;
import java.time.LocalDateTime;
@ -150,7 +152,7 @@ public class FeedFetcherService {
}
switch (feedData) {
case FetchResult.Success(String value) -> writer.saveFeed(fetchFeed(value, feed));
case FetchResult.Success(String value) -> writer.saveFeed(parseFeed(value, feed));
case FetchResult.TransientError() -> {
int errorCount = errorCounts.getOrDefault(feed.domain().toLowerCase(), 0);
writer.setErrorCount(feed.domain().toLowerCase(), ++errorCount);
@ -296,9 +298,12 @@ public class FeedFetcherService {
}
}
public FeedItems fetchFeed(String feedData, FeedDefinition definition) {
public FeedItems parseFeed(String feedData, FeedDefinition definition) {
try {
List<Item> rawItems = rssReader.read(new ByteArrayInputStream(feedData.getBytes())).toList();
List<Item> rawItems = rssReader.read(
// Massage the data to maximize the possibility of the flaky XML parser consuming it
new BOMInputStream(new ByteArrayInputStream(feedData.trim().getBytes(StandardCharsets.UTF_8)), false)
).toList();
boolean keepUriFragment = rawItems.size() < 2 || areFragmentsDisparate(rawItems);