Skip to content

Add cleanup() to URLFilter and fix timer/client leak in JSONURLFilterWrapper #1867

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jnioche merged 2 commits into from
Apr 2, 2026
Merged

Add cleanup() to URLFilter and fix timer/client leak in JSONURLFilterWrapper #1867

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
12d5aa1
Fix timer and client leak in OpenSearch JSONURLFilterWrapper
jnioche Apr 2, 2026
f5c9b43
Reformat
jnioche Apr 2, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions core/src/main/java/org/apache/stormcrawler/bolt/FeedParserBolt.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -248,6 +248,7 @@ public void declareOutputFields(OutputFieldsDeclarer declarer) {

@Override
public void cleanup() {
super.cleanup();
if (parseFilters != null) {
parseFilters.cleanup();
}
Expand Down
1 change: 1 addition & 0 deletions core/src/main/java/org/apache/stormcrawler/bolt/FetcherBolt.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1000,6 +1000,7 @@ public void declareOutputFields(OutputFieldsDeclarer declarer) {

@Override
public void cleanup() {
super.cleanup();
protocolFactory.cleanup();
}

Expand Down
1 change: 1 addition & 0 deletions core/src/main/java/org/apache/stormcrawler/bolt/JSoupParserBolt.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -570,6 +570,7 @@ protected List<Outlink> toOutlinks(

@Override
public void cleanup() {
super.cleanup();
if (parseFilters != null) {
parseFilters.cleanup();
}
Expand Down
1 change: 1 addition & 0 deletions core/src/main/java/org/apache/stormcrawler/bolt/SimpleFetcherBolt.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -260,6 +260,7 @@ public void declareOutputFields(OutputFieldsDeclarer declarer) {

@Override
public void cleanup() {
super.cleanup();
protocolFactory.cleanup();
if (fetchExecutor != null) {
fetchExecutor.shutdownNow();
Expand Down
1 change: 1 addition & 0 deletions core/src/main/java/org/apache/stormcrawler/bolt/SiteMapParserBolt.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -379,6 +379,7 @@ private boolean sniff(byte[] content) {

@Override
public void cleanup() {
super.cleanup();
if (parseFilters != null) {
parseFilters.cleanup();
}
Expand Down
7 changes: 7 additions & 0 deletions core/src/main/java/org/apache/stormcrawler/bolt/StatusEmitterBolt.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -118,4 +118,11 @@ protected Outlink filterOutlink(
protected boolean allowRedirs() {
return allowRedirs;
}

@Override
public void cleanup() {
if (urlFilters != null) {
urlFilters.cleanup();
}
}
}
7 changes: 7 additions & 0 deletions core/src/main/java/org/apache/stormcrawler/bolt/URLFilterBolt.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,4 +122,11 @@ public void prepare(
urlFilters = URLFilters.fromConf(stormConf);
}
}

@Override
public void cleanup() {
if (urlFilters != null) {
urlFilters.cleanup();
}
}
}
9 changes: 9 additions & 0 deletions core/src/main/java/org/apache/stormcrawler/filtering/URLFilter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@
package org.apache.stormcrawler.filtering;

import java.net.URL;
import org.apache.storm.task.IBolt;
import org.apache.stormcrawler.Metadata;
import org.apache.stormcrawler.util.AbstractConfigurable;
import org.jetbrains.annotations.NotNull;
Expand Down Expand Up @@ -46,4 +47,12 @@ public abstract String filter(
@Nullable URL sourceUrl,
@Nullable Metadata sourceMetadata,
@NotNull String urlToFilter);

/**
* Might be used to clean any resources associated with this {@link URLFilter}. See {@link
* IBolt#cleanup()} for more details.
*/
public void cleanup() {
// nothing to do here
}
}
7 changes: 7 additions & 0 deletions core/src/main/java/org/apache/stormcrawler/filtering/URLFilters.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -142,6 +142,13 @@ public void configure(@NotNull Map<String, Object> stormConf, @NotNull JsonNode
filters = list.toArray(new URLFilter[0]);
}

@Override
public void cleanup() {
for (URLFilter filter : filters) {
filter.cleanup();
}
}

/** Utility to check the filtering of a URL. */
public static void main(String[] args) throws ParseException {

Expand Down
80 changes: 45 additions & 35 deletions ...arch/src/main/java/org/apache/stormcrawler/opensearch/filtering/JSONURLFilterWrapper.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@

import com.fasterxml.jackson.databind.JsonNode;
import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.net.URL;
import java.util.Map;
import java.util.Timer;
Expand Down Expand Up @@ -71,6 +72,8 @@ public class JSONURLFilterWrapper extends URLFilter {
private static final Logger LOG = LoggerFactory.getLogger(JSONURLFilterWrapper.class);

private URLFilter delegatedURLFilter;
private Timer refreshTimer;
private RestHighLevelClient osClient;

public void configure(@NotNull Map<String, Object> stormConf, @NotNull JsonNode filterParams) {

Expand Down Expand Up @@ -127,42 +130,35 @@ public void configure(@NotNull Map<String, Object> stormConf, @NotNull JsonNode

final JSONResource resource = (JSONResource) delegatedURLFilter;

new Timer()
.schedule(
new TimerTask() {
private RestHighLevelClient osClient;

public void run() {
if (osClient == null) {
try {
osClient =
OpenSearchConnection.getClient(stormConf, "config");
} catch (Exception e) {
LOG.error(
"Exception while creating OpenSearch connection",
e);
}
}
if (osClient != null) {
LOG.info("Reloading json resources from OpenSearch");
try {
GetResponse response =
osClient.get(
new GetRequest(
"config",
resource.getResourceFile()),
RequestOptions.DEFAULT);
resource.loadJSONResources(
new ByteArrayInputStream(
response.getSourceAsBytes()));
} catch (Exception e) {
LOG.error("Can't load config from OpenSearch", e);
}
}
refreshTimer = new Timer();
refreshTimer.schedule(
new TimerTask() {
public void run() {
if (osClient == null) {
try {
osClient = OpenSearchConnection.getClient(stormConf, "config");
} catch (Exception e) {
LOG.error("Exception while creating OpenSearch connection", e);
}
},
0,
refreshRate * 1000);
}
if (osClient != null) {
LOG.info("Reloading json resources from OpenSearch");
try {
GetResponse response =
osClient.get(
new GetRequest(
"config", resource.getResourceFile()),
RequestOptions.DEFAULT);
resource.loadJSONResources(
new ByteArrayInputStream(response.getSourceAsBytes()));
} catch (Exception e) {
LOG.error("Can't load config from OpenSearch", e);
}
}
}
},
0,
refreshRate * 1000);
}

@Override
Expand All @@ -172,4 +168,18 @@ public void run() {
@NotNull String urlToFilter) {
return delegatedURLFilter.filter(sourceUrl, sourceMetadata, urlToFilter);
}

@Override
public void cleanup() {
if (refreshTimer != null) {
refreshTimer.cancel();
}
if (osClient != null) {
try {
osClient.close();
} catch (IOException e) {
LOG.error("Exception when closing OpenSearch client", e);
}
}
}
}