[njs] Improved processing of invalid surrogate pairs in JSON strings.

[Alexander Borisov]

details:   https://hg.nginx.org/njs/rev/82ca4be8b357
branches:  
changeset: 992:82ca4be8b357
user:      Alexander Borisov <alexander.borisov at nginx.com>
date:      Tue May 28 20:51:24 2019 +0300
description:
Improved processing of invalid surrogate pairs in JSON strings.

Previously, an exception was thrown on invalid surrogate pairs.
Now, all such pairs are converted to replacement character.

diffstat:

 njs/njs_json.c           |  19 ++++++++++++-------
 njs/test/njs_unit_test.c |  13 +++++++++++--
 2 files changed, 23 insertions(+), 9 deletions(-)

diffs (62 lines):

diff -r 96dc9de9f92c -r 82ca4be8b357 njs/njs_json.c
--- a/njs/njs_json.c	Tue May 28 20:49:58 2019 +0300
+++ b/njs/njs_json.c	Tue May 28 20:51:24 2019 +0300
@@ -806,8 +806,8 @@ njs_json_parse_string(njs_json_parse_ctx
                 /* Surrogate pair. */
 
                 if (utf > 0xdbff || p[0] != '\\' || p[1] != 'u') {
-                    njs_json_parse_exception(ctx, "Invalid Unicode char", p);
-                    return NULL;
+                    s = nxt_utf8_encode(s, NXT_UTF8_REPLACEMENT);
+                    continue;
                 }
 
                 p += 2;
@@ -815,12 +815,17 @@ njs_json_parse_string(njs_json_parse_ctx
                 utf_low = njs_json_unicode(p);
                 p += 4;
 
-                if (nxt_slow_path(utf_low < 0xdc00 || utf_low > 0xdfff)) {
-                    njs_json_parse_exception(ctx, "Invalid surrogate pair", p);
-                    return NULL;
+                if (nxt_fast_path(utf_low >= 0xdc00 && utf_low <= 0xdfff)) {
+                    utf = njs_string_surrogate_pair(utf, utf_low);
+
+                } else if (utf_low >= 0xd800 && utf_low <= 0xdbff) {
+                    utf = NXT_UTF8_REPLACEMENT;
+                    s = nxt_utf8_encode(s, NXT_UTF8_REPLACEMENT);
+
+                } else {
+                    utf = utf_low;
+                    s = nxt_utf8_encode(s, NXT_UTF8_REPLACEMENT);
                 }
-
-                utf = njs_string_surrogate_pair(utf, utf_low);
             }
 
             s = nxt_utf8_encode(s, utf);
diff -r 96dc9de9f92c -r 82ca4be8b357 njs/test/njs_unit_test.c
--- a/njs/test/njs_unit_test.c	Tue May 28 20:49:58 2019 +0300
+++ b/njs/test/njs_unit_test.c	Tue May 28 20:51:24 2019 +0300
@@ -11799,10 +11799,19 @@ static njs_unit_test_t  njs_test[] =
       nxt_string("SyntaxError: Unknown escape char at position 2") },
 
     { nxt_string("JSON.parse('\"\\\\uDC01\"')"),
-      nxt_string("SyntaxError: Invalid Unicode char at position 7") },
+      nxt_string("�") },
 
     { nxt_string("JSON.parse('\"\\\\uD801\\\\uE000\"')"),
-      nxt_string("SyntaxError: Invalid surrogate pair at position 13") },
+      nxt_string("�") },
+
+    { nxt_string("JSON.parse('\"\\\\uD83D\"')"),
+      nxt_string("�") },
+
+    { nxt_string("JSON.parse('\"\\\\uD800\\\\uDB00\"')"),
+      nxt_string("��") },
+
+    { nxt_string("JSON.parse('\"\\\\ud800[\"')"),
+      nxt_string("�[") },
 
     { nxt_string("JSON.parse('{')"),
       nxt_string("SyntaxError: Unexpected end of input at position 1") },