Skip to content

URLParser and WaybackURLKeyMaker fail on URLs with IPv6 address hostname #100

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 1 commit into from
Nov 27, 2024
Merged

URLParser and WaybackURLKeyMaker fail on URLs with IPv6 address hostname #100

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
11 changes: 10 additions & 1 deletion src/main/java/org/archive/url/URLParser.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -226,7 +226,16 @@ public static HandyURL parse(String urlString) throws URISyntaxException {
String colonPort = null;

int atIndex = uriAuthority.indexOf(COMMERCIAL_AT);
int portColonIndex = uriAuthority.indexOf(COLON,(atIndex<0)?0:atIndex);
int portColonIndex = -1;
int startColonIndex = 0;
if (atIndex > -1) {
startColonIndex = atIndex;
}
if (uriAuthority.charAt(startColonIndex) == '[') {
// IPv6 address
startColonIndex = uriAuthority.indexOf(']', (startColonIndex + 1));
}
portColonIndex = uriAuthority.indexOf(COLON, startColonIndex);

if(atIndex<0 && portColonIndex<0) {
// most common case: neither userinfo nor port
Expand Down
4 changes: 4 additions & 0 deletions src/main/java/org/archive/url/URLRegexTransformer.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -121,6 +121,10 @@ public static String hostToSURT(String host) {
// TODO: ensure we DONT reverse IP addresses!
String parts[] = host.split("\\.",-1);
if(parts.length == 1) {
// strip enclosing "[" and "]" from IPv6 hosts
if (host.charAt(0) == '[' && host.charAt(host.length() - 1) == ']') {
return host.substring(1, host.length() - 1);
}
return host;
}
StringBuilder sb = new StringBuilder(host.length());
Expand Down
3 changes: 3 additions & 0 deletions src/test/java/org/archive/url/URLParserTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,6 +86,9 @@ public void testParse() throws UnsupportedEncodingException, URISyntaxException
checkParse(" \n http://:****@www.archive.org:8080/inde\rx.html?query#foo \r\n \t ",
null, "http", "", "****", "www.archive.org", 8080, "/index.html", "query", "foo",
"http://:****@www.archive.org:8080/index.html?query#foo", "/index.html?query");
checkParse("https://[2600:1f18:200d:fb00:2b74:867c:ab0c:150a]/robots.txt", null, "https", null, null,
"[2600:1f18:200d:fb00:2b74:867c:ab0c:150a]", -1, "/robots.txt", null, null,
"https://[2600:1f18:200d:fb00:2b74:867c:ab0c:150a]/robots.txt", "/robots.txt");
}

private void checkParse(String s, String opaque, String scheme, String authUser,
Expand Down
3 changes: 3 additions & 0 deletions src/test/java/org/archive/url/WaybackURLKeyMakerTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,9 @@ public void testMakeKey() throws URISyntaxException {
assertEquals("org,archive)/goo?a&b", km.makeKey("http://archive.org/goo/?b&a"));
assertEquals("org,archive)/goo?a=1&a=2&b", km.makeKey("http://archive.org/goo/?a=2&b&a=1"));
assertEquals("org,archive)/", km.makeKey("http://archive.org:/"));
assertEquals("192,211,203,34)/robots.txt", km.makeKey("https://34.203.211.192/robots.txt"));
assertEquals("2600:1f18:200d:fb00:2b74:867c:ab0c:150a)/robots.txt",
km.makeKey("https://[2600:1f18:200d:fb00:2b74:867c:ab0c:150a]/robots.txt"));
}

}