Add missing end-of-string checks to RegExp parser in unicode mode (#3875)

Fixes #3870.
Fixes #3871.

JerryScript-DCO-1.0-Signed-off-by: Dániel Bátyai dbatyai@inf.u-szeged.hu
This commit is contained in:
Dániel Bátyai 2020-06-08 11:09:08 +02:00 committed by GitHub
parent b7a641c124
commit fed1b0c827
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 52 additions and 18 deletions

View File

@ -612,30 +612,28 @@ re_parse_char_escape (re_compiler_ctx_t *re_ctx_p) /**< RegExp compiler context
#if ENABLED (JERRY_ES2015)
if (re_ctx_p->flags & RE_FLAG_UNICODE)
{
if (*re_ctx_p->input_curr_p == LIT_CHAR_LEFT_BRACE)
if (re_ctx_p->input_curr_p + 1 < re_ctx_p->input_end_p
&& re_ctx_p->input_curr_p[0] == LIT_CHAR_LEFT_BRACE
&& lit_char_is_hex_digit (re_ctx_p->input_curr_p[1]))
{
re_ctx_p->input_curr_p++;
lit_code_point_t cp = lit_char_hex_to_int (re_ctx_p->input_curr_p[1]);
re_ctx_p->input_curr_p += 2;
if (re_ctx_p->input_curr_p < re_ctx_p->input_end_p && lit_char_is_hex_digit (*re_ctx_p->input_curr_p))
while (re_ctx_p->input_curr_p < re_ctx_p->input_end_p && lit_char_is_hex_digit (*re_ctx_p->input_curr_p))
{
lit_code_point_t cp = lit_char_hex_to_int (*re_ctx_p->input_curr_p++);
cp = cp * 16 + lit_char_hex_to_int (*re_ctx_p->input_curr_p++);
while (re_ctx_p->input_curr_p < re_ctx_p->input_end_p && lit_char_is_hex_digit (*re_ctx_p->input_curr_p))
if (JERRY_UNLIKELY (cp > LIT_UNICODE_CODE_POINT_MAX))
{
cp = cp * 16 + lit_char_hex_to_int (*re_ctx_p->input_curr_p++);
if (JERRY_UNLIKELY (cp > LIT_UNICODE_CODE_POINT_MAX))
{
return ecma_raise_syntax_error (ECMA_ERR_MSG ("Invalid unicode escape sequence"));
}
return ecma_raise_syntax_error (ECMA_ERR_MSG ("Invalid unicode escape sequence"));
}
}
if (re_ctx_p->input_curr_p < re_ctx_p->input_end_p && *re_ctx_p->input_curr_p == LIT_CHAR_RIGHT_BRACE)
{
re_ctx_p->input_curr_p++;
re_ctx_p->token.value = cp;
break;
}
if (re_ctx_p->input_curr_p < re_ctx_p->input_end_p && *re_ctx_p->input_curr_p == LIT_CHAR_RIGHT_BRACE)
{
re_ctx_p->input_curr_p++;
re_ctx_p->token.value = cp;
break;
}
}
@ -867,7 +865,8 @@ re_parse_next_token (re_compiler_ctx_t *re_ctx_p) /**< RegExp compiler context *
#if ENABLED (JERRY_ES2015)
if (re_ctx_p->flags & RE_FLAG_UNICODE
&& lit_is_code_point_utf16_high_surrogate (ch))
&& lit_is_code_point_utf16_high_surrogate (ch)
&& re_ctx_p->input_curr_p < re_ctx_p->input_end_p)
{
const ecma_char_t next = lit_cesu8_peek_next (re_ctx_p->input_curr_p);
if (lit_is_code_point_utf16_low_surrogate (next))

View File

@ -0,0 +1,15 @@
// Copyright JS Foundation and other contributors, http://js.foundation
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
assert (new RegExp("\ud800", "u").exec("\ud800")[0] === "\ud800");

View File

@ -0,0 +1,20 @@
// Copyright JS Foundation and other contributors, http://js.foundation
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
try {
new RegExp('"\\u', 'u');
assert (false);
} catch (e) {
assert (e instanceof SyntaxError);
}