diff options
| author | Paul Joseph Davis <davisp@apache.org> | 2011-01-28 01:52:47 +0000 |
|---|---|---|
| committer | Paul Joseph Davis <davisp@apache.org> | 2011-01-28 01:52:47 +0000 |
| commit | a666c0a3ea2fe0b65e8fb9b5034c8d9a64f5a905 (patch) | |
| tree | 06183ce02a95d85d6a6beb511157f4c632251ce1 /src/couchdb/couch_util.erl | |
| parent | 2e7ed944f2d23c2436f056e9649473cc891bd6e6 (diff) | |
Validate doc ids that come from a PUT to a URL.
Backprot of 1064417 from trunk.
git-svn-id: https://svn.apache.org/repos/asf/couchdb/branches/1.1.x@1064421 13f79535-47bb-0310-9956-ffa450edef68
Diffstat (limited to 'src/couchdb/couch_util.erl')
| -rw-r--r-- | src/couchdb/couch_util.erl | 33 |
1 files changed, 32 insertions, 1 deletions
diff --git a/src/couchdb/couch_util.erl b/src/couchdb/couch_util.erl index 0480f230..3de7739b 100644 --- a/src/couchdb/couch_util.erl +++ b/src/couchdb/couch_util.erl @@ -17,7 +17,7 @@ -export([rand32/0, implode/2, collate/2, collate/3]). -export([abs_pathname/1,abs_pathname/2, trim/1]). -export([encodeBase64Url/1, decodeBase64Url/1]). --export([to_hex/1, parse_term/1, dict_find/3]). +-export([validate_utf8/1, to_hex/1, parse_term/1, dict_find/3]). -export([get_nested_json_value/2, json_user_ctx/1]). -export([proplist_apply_field/2, json_apply_field/2]). -export([to_binary/1, to_integer/1, to_list/1, url_encode/1]). @@ -107,6 +107,37 @@ simple_call(Pid, Message) -> erlang:demonitor(MRef, [flush]) end. +validate_utf8(Data) when is_list(Data) -> + validate_utf8(?l2b(Data)); +validate_utf8(Bin) when is_binary(Bin) -> + validate_utf8_fast(Bin, 0). + +validate_utf8_fast(B, O) -> + case B of + <<_:O/binary>> -> + true; + <<_:O/binary, C1, _/binary>> when + C1 < 128 -> + validate_utf8_fast(B, 1 + O); + <<_:O/binary, C1, C2, _/binary>> when + C1 >= 194, C1 =< 223, + C2 >= 128, C2 =< 191 -> + validate_utf8_fast(B, 2 + O); + <<_:O/binary, C1, C2, C3, _/binary>> when + C1 >= 224, C1 =< 239, + C2 >= 128, C2 =< 191, + C3 >= 128, C3 =< 191 -> + validate_utf8_fast(B, 3 + O); + <<_:O/binary, C1, C2, C3, C4, _/binary>> when + C1 >= 240, C1 =< 244, + C2 >= 128, C2 =< 191, + C3 >= 128, C3 =< 191, + C4 >= 128, C4 =< 191 -> + validate_utf8_fast(B, 4 + O); + _ -> + false + end. + to_hex([]) -> []; to_hex(Bin) when is_binary(Bin) -> |