From 5a1c2b2677129ffadde65633577f7e0a739a1745 Mon Sep 17 00:00:00 2001
From: akr <akr@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>
Date: Sun, 9 Dec 2007 03:50:11 +0000
Subject: * re.c (append_utf8): check unicode range.

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@14154 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
---
 re.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

(limited to 're.c')

diff --git a/re.c b/re.c
index 6187273661..1c7486068f 100644
--- a/re.c
+++ b/re.c
@@ -1424,10 +1424,23 @@ unescape_escaped_nonascii(const char **pp, const char *end, rb_encoding *enc,
     return 0;
 }
 
+static int
+check_unicode_range(unsigned long code, onig_errmsg_buffer err)
+{
+    if ((0xd800 <= code && code <= 0xdfff) || /* Surrogates */
+        0x10ffff < code) {
+        strcpy(err, "invalid Unicode range");
+        return -1;
+    }
+    return 0;
+}
+
 static int
 append_utf8(unsigned long uv,
         VALUE buf, rb_encoding **encp, onig_errmsg_buffer err)
 {
+    if (check_unicode_range(uv, err) != 0)
+        return -1;
     if (uv < 0x80) {
         char escbuf[5];
         snprintf(escbuf, sizeof(escbuf), "\\x%02x", (int)uv);
@@ -1468,10 +1481,6 @@ unescape_unicode_list(const char **pp, const char *end,
             strcpy(err, "invalid Unicode range");
             return -1;
         }
-        if (0x10ffff < code) {
-            strcpy(err, "invalid Unicode range");
-            return -1;
-        }
         p += len;
         if (append_utf8(code, buf, encp, err) != 0)
             return -1;
-- 
cgit v1.2.3