Fix crash in EGG parser utf8 conversion

Fix use of iconv output variable so we don't try to free or realloc a
bad pointer. Also add a basic unit test to validate use of the utf8 conversion
function.

Fix EGG parser mem leak.

Also adjusts valgrind suppression rules to ignore valgrind false
positives in unrar code (again).

libclamav/egg.c

@@ -625,15 +625,16 @@ cl_error_t cli_codepage_to_utf8(char* in, size_t in_size, uint16_t codepage, cha
                 }
             }
 
-            if (NULL == encoding){
+            if (NULL == encoding) {
                 cli_dbgmsg("egg_filename_to_utf8: Invalid codepage parameter passed in.\n");
                 goto done;
             }
 
             for (attempt = 1; attempt <= 3; attempt++) {
-                char* out_utf8_tmp = NULL;
-                char * inbuf = in;
-                size_t iconvRet = -1;
+                char* out_utf8_index = NULL;
+                char* out_utf8_tmp   = NULL;
+                char* inbuf          = in;
+                size_t iconvRet      = -1;
 
                 /* Charset to UTF-8 should never exceed in_size * 6;
                  * We can shrink final buffer after the conversion, if needed. */
@@ -642,7 +643,7 @@ cl_error_t cli_codepage_to_utf8(char* in, size_t in_size, uint16_t codepage, cha
                 inbytesleft  = in_size;
                 outbytesleft = out_utf8_size;
 
-                out_utf8 = cli_calloc(1, out_utf8_size + 1);
+                out_utf8 = out_utf8_index = cli_calloc(1, out_utf8_size + 1);
                 if (NULL == out_utf8) {
                     cli_errmsg("egg_filename_to_utf8: Failure allocating buffer for utf8 data.\n");
                     status = CL_EMEM;
@@ -654,9 +655,9 @@ cl_error_t cli_codepage_to_utf8(char* in, size_t in_size, uint16_t codepage, cha
                     goto done;
                 }
 
-                iconvRet = iconv(conv, &inbuf, &inbytesleft, &out_utf8, &outbytesleft);
+                iconvRet = iconv(conv, &inbuf, &inbytesleft, &out_utf8_index, &outbytesleft);
                 iconv_close(conv);
-                conv = (iconv_t) -1;
+                conv = (iconv_t)-1;
                 if ((size_t)-1 == iconvRet) {
                     switch (errno) {
                         case E2BIG:
@@ -686,6 +687,7 @@ cl_error_t cli_codepage_to_utf8(char* in, size_t in_size, uint16_t codepage, cha
                 }
                 out_utf8      = out_utf8_tmp;
                 out_utf8_size = out_utf8_size - outbytesleft;
+                break;
             }
 
 #else

libclamav/libclamav.map

@@ -260,6 +260,7 @@ CLAMAV_PRIVATE {
     cli_gentemp_with_prefix;
     cli_basename;
     cli_realpath;
+    cli_codepage_to_utf8;
 
     __cli_strcasestr;
     __cli_strndup;

unit_tests/check_clamav.c

@@ -973,6 +973,26 @@ START_TEST(test_sanitize_path)
 }
 END_TEST
 
+cl_error_t cli_codepage_to_utf8(char* in, size_t in_size, uint16_t codepage, char** out, size_t* out_size);
+
+START_TEST(test_cli_codepage_to_utf8)
+{
+    cl_error_t ret;
+    char *utf8       = NULL;
+    size_t utf8_size = 0;
+
+    ret = cli_codepage_to_utf8("\x00\x48\x00\x65\x00\x6c\x00\x6c\x00\x6f\x00\x20\x00\x77\x00\x6f\x00\x72\x00\x6c\x00\x64\x00\x21\x00\x00", 26, 1201, &utf8, &utf8_size);
+    ck_assert_msg(CL_SUCCESS == ret, "test_cli_codepage_to_utf8: Failed to convert CODEPAGE_UTF16_LE to UTF8: ret != SUCCESS!");
+    ck_assert_msg(NULL != utf8, "sanitize_path: Failed to convert CODEPAGE_UTF16_LE to UTF8: utf8 pointer is NULL!");
+    ck_assert_msg(0 == strcmp(utf8, "Hello world!"), "sanitize_path: '%s' doesn't match '%s'", utf8, "Hello world!");
+
+    if (NULL != utf8) {
+        free(utf8);
+        utf8 = NULL;
+    }
+}
+END_TEST
+
 static Suite *test_cli_suite(void)
 {
     Suite *s               = suite_create("cli");
@@ -992,6 +1012,7 @@ static Suite *test_cli_suite(void)
 
     suite_add_tcase(s, tc_cli_assorted);
     tcase_add_test(tc_cli_assorted, test_sanitize_path);
+    tcase_add_test(tc_cli_assorted, test_cli_codepage_to_utf8);
 
     return s;
 }

unit_tests/valgrind.supp

@@ -265,7 +265,6 @@
    fun:internal_ascii_loop
    fun:__gconv_transform_internal_ascii
    fun:wcsrtombs
-   fun:wcsrtombs
    ...
 }
 {
@@ -273,7 +272,6 @@
    Memcheck:Cond
    fun:__wcsnlen_avx2
    fun:wcsrtombs
-   fun:wcsrtombs
    ...
 }
 {
@@ -281,7 +279,6 @@
    Memcheck:Cond
    fun:__wcsnlen_sse4_1
    fun:wcsrtombs
-   fun:wcsrtombs
    ...
 }
 {