github_mirrors/vectorscan
3
0
Fork 1
mirror of https://github.com/VectorCamp/vectorscan.git synced 2025-06-28 16:41:01 +03:00
Code Issues Packages Projects Releases Wiki Activity

UTF-8 validation: fix one cotec check corner issue

Browse Source 
fix github issue #362
This commit is contained in:
Hong, Yang A 2022-07-28 21:24:31 +00:00 committed by Konstantinos Margaritis
parent 7c1835c0e7
commit 684f0ce2cb
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/parser/utf8_validate.cpp
View File

@ -72,7 +72,7 @@ bool isValidUtf8(const char *expression, const size_t len) {
while (i < len) { while (i < len) {
DEBUG_PRINTF("byte %zu: 0x%02x\n", i, s[i]); DEBUG_PRINTF("byte %zu: 0x%02x\n", i, s[i]);
// One octet. // One octet.
if (s[i] < 0x7f) { if (s[i] <= 0x7f) {
DEBUG_PRINTF("one octet\n"); DEBUG_PRINTF("one octet\n");
i++; i++;
continue; continue;

4
unit/internal/utf8_validate.cpp
View File

@ -64,8 +64,8 @@ static ValidUtf8TestInfo valid_utf8_tests[] = {
{"공동경비구역", true}, {"공동경비구역", true},
{"জলসাঘর", true}, {"জলসাঘর", true},
// Invalid one-byte caseS. // Valid one-byte caseS.
{"\x7f", false}, {"\x7f", true}, // \x7f is valid
// These bytes should never appear in a UTF-8 stream. // These bytes should never appear in a UTF-8 stream.
{"\xc0", false}, {"\xc0", false},