Skip to content
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.

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

#1475 -- Regular crawling should work when autodiscovery of sitemaps is turned off #1477

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from 3 commits
Commits
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
Original file line number Diff line number Diff line change
Expand Up @@ -551,6 +551,9 @@ public void run() {
smautodisco = false;
} else {
smautodisco = sitemapsAutoDiscovery;
// SitemapFilter needs this
metadata.setValue(
SITEMAP_DISCOVERY_PARAM_KEY, Boolean.toString(smautodisco));
}

if (!fromCache && smautodisco) {
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -309,6 +309,8 @@ public void execute(Tuple input) {
smautodisco = false;
} else {
smautodisco = sitemapsAutoDiscovery;
// SitemapFilter needs this
metadata.setValue(SITEMAP_DISCOVERY_PARAM_KEY, Boolean.toString(smautodisco));
}

if (!fromCache && smautodisco) {
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -43,18 +43,23 @@
*/
public class SitemapFilter extends URLFilter {

private static final String SITEMAP_DISCOVERY_PARAM_KEY = "sitemap.discovery";

@Override
public @Nullable String filter(
@Nullable URL sourceUrl,
@Nullable Metadata sourceMetadata,
@NotNull String urlToFilter) {

if (sourceMetadata != null
&& !Boolean.parseBoolean(
sourceMetadata.getFirstValue(SiteMapParserBolt.isSitemapKey))
&& Boolean.parseBoolean(
sourceMetadata.getFirstValue(SiteMapParserBolt.foundSitemapKey))) {
return null;
if (sourceMetadata != null) {
if (!Boolean.parseBoolean(sourceMetadata.getFirstValue(SITEMAP_DISCOVERY_PARAM_KEY))) {
return urlToFilter;
} else if (!Boolean.parseBoolean(
sourceMetadata.getFirstValue(SiteMapParserBolt.isSitemapKey))
&& Boolean.parseBoolean(
sourceMetadata.getFirstValue(SiteMapParserBolt.foundSitemapKey))) {
return null;
}
}
return urlToFilter;
}
Expand Down