Commit 93be35e0 authored by Philipp Stephani's avatar Philipp Stephani

Fix encoding of JSON surrogate pairs

JSON requires that such pairs be treated as UTF-16 surrogate pairs, not
individual code points; cf. Bug #24784.

* lisp/json.el (json-read-escaped-char): Fix decoding of surrogate
(json--decode-utf-16-surrogates): New defun.

* test/lisp/json-tests.el (test-json-read-string): Add test for
surrogate pairs.
parent baa370f2
......@@ -363,6 +363,10 @@ representation will be parsed correctly."
;; String parsing
(defun json--decode-utf-16-surrogates (high low)
"Return the code point represented by the UTF-16 surrogates HIGH and LOW."
(+ (lsh (- high #xD800) 10) (- low #xDC00) #x10000))
(defun json-read-escaped-char ()
"Read the JSON string escaped character at point."
;; Skip over the '\'
......@@ -372,6 +376,17 @@ representation will be parsed correctly."
(special (cdr special))
((not (eq char ?u)) char)
;; Special-case UTF-16 surrogate pairs,
;; cf. Note that
;; this clause overlaps with the next one and therefore has to
;; come first.
(rx (group (any "Dd") (any "89ABab") (= 2 (any "0-9A-Fa-f")))
"\\u" (group (any "Dd") (any "C-Fc-f") (= 2 (any "0-9A-Fa-f")))))
(json-advance 10)
(string-to-number (match-string 1) 16)
(string-to-number (match-string 2) 16)))
((looking-at "[0-9A-Fa-f][0-9A-Fa-f][0-9A-Fa-f][0-9A-Fa-f]")
(let ((hex (match-string 0)))
(json-advance 4)
......@@ -167,6 +167,9 @@ Point is moved to beginning of the buffer."
(should (equal (json-read-string) "abcαβγ")))
(json-tests--with-temp-buffer "\"\\nasd\\u0444\\u044b\\u0432fgh\\t\""
(should (equal (json-read-string) "\nasdфывfgh\t")))
;; Bug#24784
(json-tests--with-temp-buffer "\"\\uD834\\uDD1E\""
(should (equal (json-read-string) "\U0001D11E")))
(json-tests--with-temp-buffer "foo"
(should-error (json-read-string) :type 'json-string-format)))
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment