Skip to content

Honour ignoreOutsideDomain when set on its own in HostURLFilter #2074

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 1 commit into from
Aug 28, 2026
+37 −2
Merged

Honour ignoreOutsideDomain when set on its own in HostURLFilter #2074

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion core/src/main/java/org/apache/stormcrawler/filtering/host/HostURLFilter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,7 +62,7 @@ public void configure(@NotNull Map<String, Object> stormConf, @NotNull JsonNode
// always the same
if (!ignoreOutsideHost) {
JsonNode filterByDomainNode = filterParams.get("ignoreOutsideDomain");
if (filterByHostNode == null) {
if (filterByDomainNode == null) {
ignoreOutsideDomain = false;
} else {
ignoreOutsideDomain = filterByDomainNode.asBoolean(false);
Expand Down
37 changes: 36 additions & 1 deletion core/src/test/java/org/apache/stormcrawler/filtering/HostURLFilterTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,10 +36,14 @@
class HostURLFilterTest {

private HostURLFilter createFilter(boolean ignoreOutsideHost, boolean ignoreOutsideDomain) {
HostURLFilter filter = new HostURLFilter();
ObjectNode filterParams = new ObjectNode(JsonNodeFactory.instance);
filterParams.put("ignoreOutsideHost", Boolean.valueOf(ignoreOutsideHost));
filterParams.put("ignoreOutsideDomain", Boolean.valueOf(ignoreOutsideDomain));
return createFilter(filterParams);
}

private HostURLFilter createFilter(ObjectNode filterParams) {
HostURLFilter filter = new HostURLFilter();
Map<String, Object> conf = new HashMap<>();
filter.configure(conf, filterParams);
return filter;
Expand Down Expand Up @@ -108,4 +112,35 @@ void testWithinDomain() throws MalformedURLException {
allAllowed.filter(sourceURL, metadata, "http://sub.sourcedomain.com/index.html");
Assertions.assertEquals("http://sub.sourcedomain.com/index.html", filterResult);
}

/** The two modes are independent, so ignoreOutsideDomain must be honoured on its own. */
@Test
void testWithinDomainWithoutHostParameter() throws MalformedURLException {
ObjectNode filterParams = new ObjectNode(JsonNodeFactory.instance);
filterParams.put("ignoreOutsideDomain", Boolean.TRUE);
HostURLFilter withinDomain = createFilter(filterParams);
URL sourceURL = URLUtil.toURL("http://www.sourcedomain.com/index.html");
Metadata metadata = new Metadata();
String filterResult =
withinDomain.filter(sourceURL, metadata, "http://sub.sourcedomain.com/index.html");
Assertions.assertEquals("http://sub.sourcedomain.com/index.html", filterResult);
filterResult =
withinDomain.filter(sourceURL, metadata, "http://www.anotherDomain.com/index.html");
Assertions.assertNull(filterResult);
}

/**
* A configuration which sets ignoreOutsideHost only must not fail on the missing domain key.
*/
@Test
void testHostParameterWithoutDomainParameter() throws MalformedURLException {
ObjectNode filterParams = new ObjectNode(JsonNodeFactory.instance);
filterParams.put("ignoreOutsideHost", Boolean.FALSE);
HostURLFilter allAllowed = createFilter(filterParams);
URL sourceURL = URLUtil.toURL("http://www.sourcedomain.com/index.html");
Metadata metadata = new Metadata();
String filterResult =
allAllowed.filter(sourceURL, metadata, "http://www.anotherDomain.com/index.html");
Assertions.assertEquals("http://www.anotherDomain.com/index.html", filterResult);
}
}
Loading