use utf8_length() instead of local function, isValidUtf8()

utf8_length() from libutils returns -1 when source not contains
valid sequence for UTF-8. Fixed to use it and removed the local
function isValidUtf8().

Change-Id: If2834ce1d1ae07fd8526ce8bc5df3fd3f44e85c8
Signed-off-by: Homin Lee <suapapa@insignal.co.kr>
This commit is contained in:
Homin Lee
2012-04-05 20:11:27 +09:00
parent 3d7f0cb3d9
commit 1a8b6c29aa

View File

@@ -19,6 +19,7 @@
#define LOG_TAG "MediaScannerJNI"
#include <utils/Log.h>
#include <utils/threads.h>
#include <utils/Unicode.h>
#include <media/mediascanner.h>
#include <media/stagefright/StagefrightMediaScanner.h>
@@ -56,53 +57,6 @@ static status_t checkAndClearExceptionFromCallback(JNIEnv* env, const char* meth
return OK;
}
// stolen from dalvik/vm/checkJni.cpp
static bool isValidUtf8(const char* bytes) {
while (*bytes != '\0') {
unsigned char utf8 = *(bytes++);
// Switch on the high four bits.
switch (utf8 >> 4) {
case 0x00:
case 0x01:
case 0x02:
case 0x03:
case 0x04:
case 0x05:
case 0x06:
case 0x07:
// Bit pattern 0xxx. No need for any extra bytes.
break;
case 0x08:
case 0x09:
case 0x0a:
case 0x0b:
case 0x0f:
/*
* Bit pattern 10xx or 1111, which are illegal start bytes.
* Note: 1111 is valid for normal UTF-8, but not the
* modified UTF-8 used here.
*/
return false;
case 0x0e:
// Bit pattern 1110, so there are two additional bytes.
utf8 = *(bytes++);
if ((utf8 & 0xc0) != 0x80) {
return false;
}
// Fall through to take care of the final byte.
case 0x0c:
case 0x0d:
// Bit pattern 110x, so there is one additional byte.
utf8 = *(bytes++);
if ((utf8 & 0xc0) != 0x80) {
return false;
}
break;
}
}
return true;
}
class MyMediaScannerClient : public MediaScannerClient
{
public:
@@ -170,8 +124,11 @@ public:
mEnv->ExceptionClear();
return NO_MEMORY;
}
// Check if the value is valid UTF-8 string and replace
// any un-printable characters with '?' when it's not.
char *cleaned = NULL;
if (!isValidUtf8(value)) {
if (utf8_length(value) == -1) {
cleaned = strdup(value);
char *chp = cleaned;
char ch;