Skip to content

BasicURLCanonicalizer: more efficient normalization of dots in host name #129

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
ato merged 2 commits into from
Nov 14, 2025
Merged

BasicURLCanonicalizer: more efficient normalization of dots in host name #129

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
3ef28b5
BasicURLCanonicalizer: more efficient normalization of dots in host name
sebastian-nagel Nov 11, 2025
44ec227
BasicURLCanonicalizer: more efficient normalization of dots in host name
sebastian-nagel Nov 13, 2025
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
35 changes: 33 additions & 2 deletions src/main/java/org/archive/url/BasicURLCanonicalizer.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,9 @@ public class BasicURLCanonicalizer implements URLCanonicalizer {
.compile("^(0[0-7]*)(\\.[0-7]+)?(\\.[0-7]+)?(\\.[0-7]+)?$");
Pattern DECIMAL_IP = Pattern
.compile("^([1-9][0-9]*)(\\.[0-9]+)?(\\.[0-9]+)?(\\.[0-9]+)?$");
Pattern MULTIDOT = Pattern.compile("\\.{2,}");

@Override
public void canonicalize(HandyURL url) {
url.setHash(null);
url.setAuthUser(minimalEscape(url.getAuthUser()));
Expand All @@ -55,8 +57,7 @@ public void canonicalize(HandyURL url) {
host = hostE;

}
host = host.replaceAll("^\\.+", "").replaceAll("\\.\\.+", ".")
.replaceAll("\\.$", "");
host = normalizeDots(host);
}

String ip = null;
Expand All @@ -74,6 +75,36 @@ public void canonicalize(HandyURL url) {
url.setPath(escapeOnce(normalizePath(path)));
}

/**
* Normalize dots in the host name.
*
* @param host
* @return host name with all sequences of dots replaced with a single dot,
* and all leading and trailing dots removed
*/
private String normalizeDots(String host) {
if (host.indexOf('.') == -1) {
return host;
}
int start = 0, end = host.length();
boolean changed = false;
while (start < end && host.charAt(start) == '.') {
start++;
changed = true;
}
while (end > start && host.charAt(end - 1) == '.') {
end--;
changed = true;
}
if (changed) {
host = host.substring(start, end);
}
if (host.contains("..")) {
host = MULTIDOT.matcher(host).replaceAll(".");
}
return host;
}

private static final Pattern SINGLE_FORWARDSLASH_PATTERN = Pattern
.compile("/");

Expand Down
10 changes: 10 additions & 0 deletions src/test/java/org/archive/url/BasicURLCanonicalizerTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -286,6 +286,16 @@ public void testUnicodeEscaping() throws URISyntaxException {
checkCanonicalization("http://example.org/%F0%9F%82%A1", "http://example.org/%F0%9F%82%A1");
}

@Test
public void testHostDots() throws URISyntaxException {
checkCanonicalization("https://foobar.org./", "https://foobar.org/");
checkCanonicalization("https://.foobar.org/", "https://foobar.org/");
checkCanonicalization("https://foo...bar.org/", "https://foo.bar.org/");
checkCanonicalization("https://...foo...bar.org.../", "https://foo.bar.org/");
checkCanonicalization("https://localhost/path/file.txt", "https://localhost/path/file.txt");
checkCanonicalization("https://....../path/file.txt", "https:///path/file.txt");
}

private void checkCanonicalization(String in, String want) throws URISyntaxException {
HandyURL h = URLParser.parse(in);
guc.canonicalize(h);
Expand Down