Skip to content

Improve logging done by SiteMapParser #457

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
merged 1 commit into from
May 28, 2024
Merged

Improve logging done by SiteMapParser #457

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
12 changes: 6 additions & 6 deletions src/main/java/crawlercommons/sitemaps/SiteMapParser.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -412,7 +412,7 @@ public AbstractSiteMap parseSiteMap(String contentType, byte[] content, URL url)
*/
public void walkSiteMap(URL onlineSitemapUrl, Consumer<SiteMapURL> action) throws UnknownFormatException, IOException {
if (onlineSitemapUrl == null || action == null) {
LOG.debug("Got null sitemap URL and/or action, stopping traversal");
LOG.info("Got null sitemap URL and/or action, stopping traversal");
return;
}
walkSiteMap(parseSiteMap(onlineSitemapUrl), action);
Expand Down Expand Up @@ -441,7 +441,7 @@ public void walkSiteMap(URL onlineSitemapUrl, Consumer<SiteMapURL> action) throw
*/
public void walkSiteMap(AbstractSiteMap sitemap, Consumer<SiteMapURL> action) throws UnknownFormatException, IOException {
if (sitemap == null || action == null) {
LOG.debug("Got null sitemap and/or action, stopping traversal");
LOG.info("Got null sitemap and/or action, stopping traversal");
return;
}
if (sitemap.isIndex()) {
Expand Down Expand Up @@ -530,7 +530,7 @@ protected SiteMap processText(URL sitemapUrl, InputStream stream) throws IOExcep
}
String urlFiltered = urlFilter.apply(line);
if (urlFiltered == null) {
LOG.debug("Filtered url: [{}]", line.substring(0, Math.min(1024, line.length())));
LOG.info("Filtered url: [{}]", line.substring(0, Math.min(1024, line.length())));
continue;
}
try {
Expand All @@ -541,10 +541,10 @@ protected SiteMap processText(URL sitemapUrl, InputStream stream) throws IOExcep
textSiteMap.addSiteMapUrl(sUrl);
LOG.debug(" {}. {}", i, sUrl);
} else {
LOG.debug("URL: {} is excluded from the sitemap as it is not a valid url = not under the base url: {}", url.toExternalForm(), textSiteMap.getBaseUrl());
LOG.info("URL: {} is excluded from the sitemap as it is not a valid url = not under the base url: {}", url.toExternalForm(), textSiteMap.getBaseUrl());
}
} catch (MalformedURLException e) {
LOG.debug("Bad url: [{}]", line.substring(0, Math.min(1024, line.length())));
LOG.warn("Bad url: [{}]", line.substring(0, Math.min(1024, line.length())));
}
}
textSiteMap.setProcessed(true);
Expand Down Expand Up @@ -654,7 +654,7 @@ public InputSource resolveEntity(String publicId, String systemId) {
LOG.warn("Error parsing sitemap {}: {}", sitemapUrl, e.getMessage());
AbstractSiteMap sitemap = handler.getSiteMap();
if (allowPartial && sitemap != null) {
LOG.warn("Processed broken/partial sitemap for '" + sitemapUrl + "'");
LOG.warn("Processed broken/partial sitemap for '{}'", sitemapUrl);
sitemap.setProcessed(true);
return sitemap;
} else {
Expand Down