database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-28 23:42:10 +03:00
Code Activity

Handle Unicode surrogate pairs correctly when processing JSON.

Browse Source 
In 9.2, Unicode escape sequences are not analysed at all other than
to make sure that they are in the form \uXXXX. But in 9.3 many of the
new operators and functions try to turn JSON text values into text in
the server encoding, and this includes de-escaping Unicode escape
sequences. This processing had not taken into account the possibility
that this might contain a surrogate pair to designate a character
outside the BMP. That is now handled correctly.

This also enforces correct use of surrogate pairs, something that is not
done by the type's input routines. This fact is noted in the docs.
This commit is contained in:
Andrew Dunstan
2013-06-08 09:12:48 -04:00
parent c99d5d1bcc
commit 94e3311b97
4 changed files with 92 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/test/regress/sql/json.sql
View File

@ -296,3 +296,11 @@ select * from json_populate_recordset(null::jpop,'[{"a":"blurfl","x":43.2},{"b":
select * from json_populate_recordset(row('def',99,null)::jpop,'[{"a":"blurfl","x":43.2},{"b":3,"c":"2012-01-20 10:42:53"}]') q;
select * from json_populate_recordset(row('def',99,null)::jpop,'[{"a":[100,200,300],"x":43.2},{"a":{"z":true},"b":3,"c":"2012-01-20 10:42:53"}]') q;
select * from json_populate_recordset(row('def',99,null)::jpop,'[{"c":[100,200,300],"x":43.2},{"a":{"z":true},"b":3,"c":"2012-01-20 10:42:53"}]') q;
-- handling of unicode surrogate pairs
select json '{ "a": "\ud83d\ude04\ud83d\udc36" }' -> 'a' as correct;
select json '{ "a": "\ud83d\ud83d" }' -> 'a'; -- 2 high surrogates in a row
select json '{ "a": "\ude04\ud83d" }' -> 'a'; -- surrogates in wrong order
select json '{ "a": "\ud83dX" }' -> 'a'; -- orphan high surrogate
select json '{ "a": "\ude04X" }' -> 'a'; -- orphan low surrogate