+/* Optimized for char set UTF-8 */
"charset" is a (poor misnomer!) jargon term, not two words.
---
+ for (b = str[len]; b != '\0'; len++, b = str[len]) {
+ if (isAscii && b & 0x80) {
+ isAscii = JNI_FALSE;
+ }
+ }
I would write this more like
const signed char *p;
int isAscii;
for (isAscii = 0, p = (const signed char *) str; *p != '\0'; p++) isAscii
&= (*p >= 0);
Then length is (p - str)
---
+ jbyteArray hab = NULL;
I'm having a hard time decoding the name "hab"
---
The code below is not UTF-8 specific. Can it be refactored?
+ hab = (*env)->NewByteArray(env, len);
+ if (hab != 0) {
+ jclass strClazz = JNU_ClassString(env);
+ CHECK_NULL_RETURN(strClazz, 0);
+ (*env)->SetByteArrayRegion(env, hab, 0, len, (jbyte *)str);
+ result = (*env)->NewObject(env, strClazz,
+ String_init_ID, hab, jnuEncoding);
+ (*env)->DeleteLocalRef(env, hab);
+ return result;
+ }
---
We probably want to use unicode escapes in out java sources to keep all
source files strictly ASCII.
