diff options
| author | Nick Vatamaniuc <vatamane@apache.org> | 2017-09-19 10:16:41 -0400 |
|---|---|---|
| committer | Nick Vatamaniuc <nickva@users.noreply.github.com> | 2017-09-19 11:27:36 -0400 |
| commit | c531a13b22cc6fcea6afb342eb3f5cb315db0313 (patch) | |
| tree | e5a080e70619160d3b323470f0915918ffa0c2a1 | |
| parent | 190ee307b0ce70ece06face009eb4ab5abdb33b4 (diff) | |
| download | couchdb-c531a13b22cc6fcea6afb342eb3f5cb315db0313.tar.gz | |
Fix replication ID parsing in URL paths
Previously users had to URL encode replication IDs when using
`_scheduler/jobs/<job_id>` endpoint because Mochiweb incorrectly decoded the
`+` character from URL path. So users were forced to encode so that the
replicator would correctly receive a `+` after Mochiweb parsing.
`+` is decoded as ` ` (space) probably because in query strings that's a valid
application/x-www-form-urlencoded encoding, but that decoding is not meant for
decoding URL paths, only query strings.
Notice RFC 3986 https://tools.ietf.org/html/rfc3986#section-2.2
`+` is a `sub-delim` (term from RFC) and in the path component it can be used
unquoted as a delimiter.
https://tools.ietf.org/html/rfc3986#section-3.3
Indeed, the replication ID is a compound ID and `+` is a valid delimiter
which separates the base part from the extensions.
For more details see also:
https://github.com/perwendel/spark/issues/490
https://www.w3.org/TR/html401/interact/forms.html#h-17.13.4.1
Fixes #825
| -rw-r--r-- | src/couch_replicator/src/couch_replicator_ids.erl | 16 |
1 files changed, 15 insertions, 1 deletions
diff --git a/src/couch_replicator/src/couch_replicator_ids.erl b/src/couch_replicator/src/couch_replicator_ids.erl index 62cfdf267..e7067622b 100644 --- a/src/couch_replicator/src/couch_replicator_ids.erl +++ b/src/couch_replicator/src/couch_replicator_ids.erl @@ -78,7 +78,11 @@ replication_id(#rep{user_ctx = UserCtx} = Rep, 1) -> -spec convert([_] | binary() | {string(), string()}) -> {string(), string()}. convert(Id) when is_list(Id) -> convert(?l2b(Id)); -convert(Id) when is_binary(Id) -> +convert(Id0) when is_binary(Id0) -> + % Spaces can result from mochiweb incorrectly unquoting + characters from + % the URL path. So undo the incorrect parsing here to avoid forcing + % users to url encode + characters. + Id = binary:replace(Id0, <<" ">>, <<"+">>, [global]), lists:splitwith(fun(Char) -> Char =/= $+ end, ?b2l(Id)); convert({BaseId, Ext} = Id) when is_list(BaseId), is_list(Ext) -> Id. @@ -222,6 +226,16 @@ get_non_default_port(_Schema, Port) -> -include_lib("eunit/include/eunit.hrl"). + +replication_id_convert_test_() -> + [?_assertEqual(Expected, convert(Id)) || {Expected, Id} <- [ + {{"abc", ""}, "abc"}, + {{"abc", ""}, <<"abc">>}, + {{"abc", "+x+y"}, <<"abc+x+y">>}, + {{"abc", "+x+y"}, {"abc", "+x+y"}}, + {{"abc", "+x+y"}, <<"abc x y">>} + ]]. + http_v4_endpoint_test_() -> [?_assertMatch({remote, User, Host, Port, Path, HeadersNoAuth, undefined}, get_v4_endpoint(nil, #httpdb{url = Url, headers = Headers})) || |