/* Only to be used inside a loop (see the break) */
#define SHIFT_BYTES(utf8, s, strend, buf, len, datumtype, needs_swap) \
STMT_START { \
- if (utf8) { \
+ if (UNLIKELY(utf8)) { \
if (!uni_to_bytes(aTHX_ &s, strend, \
(char *) (buf), len, datumtype)) break; \
} else { \
- if (needs_swap) \
+ if (UNLIKELY(needs_swap)) \
S_reverse_copy(s, (char *) (buf), len); \
else \
Copy(s, (char *) (buf), len, char); \
UTF8_CHECK_ONLY : (UTF8_CHECK_ONLY | UTF8_ALLOW_ANY);
const bool needs_swap = NEEDS_SWAP(datumtype);
- if (needs_swap)
+ if (UNLIKELY(needs_swap))
buf += buf_len;
for (;buf_len > 0; buf_len--) {
bad |= 2;
val &= 0xff;
}
- if (needs_swap)
+ if (UNLIKELY(needs_swap))
*(U8 *)--buf = (U8)val;
else
*(U8 *)buf++ = (U8)val;
const int flags = ckWARN(WARN_UTF8) ? 0 : UTF8_ALLOW_ANY;
for (ptr = *s; ptr < from; ptr += UTF8SKIP(ptr)) {
if (ptr >= end) break;
- utf8n_to_uvuni((U8 *) ptr, end-ptr, &retlen, flags);
+ utf8n_to_uvchr((U8 *) ptr, end-ptr, &retlen, flags);
}
if (from > end) from = end;
}
S_bytes_to_uni(const U8 *start, STRLEN len, char *dest, const bool needs_swap) {
PERL_ARGS_ASSERT_BYTES_TO_UNI;
- if (needs_swap) {
+ if (UNLIKELY(needs_swap)) {
const U8 *p = start + len;
while (p-- > start) {
- const UV uv = NATIVE_TO_ASCII(*p);
- if (UNI_IS_INVARIANT(uv))
- *dest++ = (char)(U8)UTF_TO_NATIVE(uv);
- else {
- *dest++ = (char)(U8)UTF8_EIGHT_BIT_HI(uv);
- *dest++ = (char)(U8)UTF8_EIGHT_BIT_LO(uv);
- }
+ append_utf8_from_native_byte(*p, (U8 **) & dest);
}
} else {
const U8 * const end = start + len;
while (start < end) {
- const UV uv = NATIVE_TO_ASCII(*start);
- if (UNI_IS_INVARIANT(uv))
- *dest++ = (char)(U8)UTF_TO_NATIVE(uv);
- else {
- *dest++ = (char)(U8)UTF8_EIGHT_BIT_HI(uv);
- *dest++ = (char)(U8)UTF8_EIGHT_BIT_LO(uv);
- }
+ append_utf8_from_native_byte(*start, (U8 **) & dest);
start++;
}
}
#define PUSH_BYTES(utf8, cur, buf, len, needs_swap) \
STMT_START { \
- if (utf8) \
+ if (UNLIKELY(utf8)) \
(cur) = S_bytes_to_uni((U8 *) buf, len, (cur), needs_swap); \
else { \
- if (needs_swap) \
+ if (UNLIKELY(needs_swap)) \
S_reverse_copy((char *)(buf), cur, len); \
else \
Copy(buf, cur, len, char); \
if (!len) /* Avoid division by 0 */
len = 1;
len = total % len; /* Assumed: the start is aligned. */
- /* FALL THROUGH */
+ /* FALLTHROUGH */
case 'X':
size = -1;
if (total < len)
len = len - star;
else
len = 0;
- /* FALL THROUGH */
+ /* FALLTHROUGH */
case 'x':
case 'A':
case 'Z':
Using the template pat..patend, this function unpacks the string
s..strend into a number of mortal SVs, which it pushes onto the perl
argument (@_) stack (so you will need to issue a C<PUTBACK> before and
-C<SPAGAIN> after the call to this function). It returns the number of
+C<SPAGAIN> after the call to this function). It returns the number of
pushed elements.
The strend and patend pointers should point to the byte following the last
break;
}
len = (s - strbeg) % len;
- /* FALL THROUGH */
+ /* FALLTHROUGH */
case 'X':
if (utf8) {
while (len > 0) {
if (ai32 == 0) break;
len -= ai32;
}
- /* FALL THROUGH */
+ /* FALLTHROUGH */
case 'x':
if (utf8) {
while (len>0) {
utf8 = (symptr->flags & FLAG_DO_UTF8) ? 1 : 0;
break;
}
- /* FALL THROUGH */
+ /* FALLTHROUGH */
case 'c':
while (len-- > 0 && s < strend) {
int aint;
len = UTF8SKIP(result);
if (!uni_to_bytes(aTHX_ &ptr, strend,
(char *) &result[1], len-1, 'U')) break;
- auv = utf8n_to_uvuni(result, len, &retlen, UTF8_ALLOW_DEFAULT);
+ auv = utf8n_to_uvchr(result, len, &retlen, UTF8_ALLOW_DEFAULT);
s = ptr;
} else {
- auv = utf8n_to_uvuni((U8*)s, strend - s, &retlen, UTF8_ALLOW_DEFAULT);
+ auv = utf8n_to_uvchr((U8*)s, strend - s, &retlen, UTF8_ALLOW_DEFAULT);
if (retlen == (STRLEN) -1 || retlen == 0)
Perl_croak(aTHX_ "Malformed UTF-8 string in unpack");
s += retlen;
}
break;
#else
- /* Fallthrough! */
+ /* FALLTHROUGH */
#endif
case 's':
while (len-- > 0) {
}
break;
#else
- /* Fallthrough! */
+ /* FALLTHROUGH */
#endif
case 'v':
case 'n':
}
break;
#else
- /* Fallthrough! */
+ /* FALLTHROUGH */
#endif
case 'l':
while (len-- > 0) {
}
break;
#else
- /* Fall through! */
+ /* FALLTHROUGH */
#endif
case 'V':
case 'N':
PUSHs(newSVpvn_flags(aptr, len, SVs_TEMP));
}
break;
-#ifdef HAS_QUAD
+#if defined(HAS_QUAD) && IVSIZE >= 8
case 'q':
while (len-- > 0) {
Quad_t aquad;
SHIFT_VAR(utf8, s, strend, aquad, datumtype, needs_swap);
if (!checksum)
- mPUSHs(aquad >= IV_MIN && aquad <= IV_MAX ?
- newSViv((IV)aquad) : newSVnv((NV)aquad));
+ mPUSHs(newSViv((IV)aquad));
else if (checksum > bits_in_uv)
cdouble += (NV)aquad;
else
Uquad_t auquad;
SHIFT_VAR(utf8, s, strend, auquad, datumtype, needs_swap);
if (!checksum)
- mPUSHs(auquad <= UV_MAX ?
- newSVuv((UV)auquad) : newSVnv((NV)auquad));
+ mPUSHs(newSVuv((UV)auquad));
else if (checksum > bits_in_uv)
cdouble += (NV)auquad;
else
cuv += auquad;
}
break;
-#endif /* HAS_QUAD */
+#endif
/* float and double added gnb@melba.bby.oz.au 22/11/89 */
case 'f':
while (len-- > 0) {
from_start = SvPVX_const(sv);
from_end = from_start + SvCUR(sv);
for (from_ptr = from_start; from_ptr < from_end; from_ptr++)
- if (!NATIVE_IS_INVARIANT(*from_ptr)) break;
+ if (!NATIVE_BYTE_IS_INVARIANT(*from_ptr)) break;
if (from_ptr == from_end) {
/* Simple case: no character needs to be changed */
SvUTF8_on(sv);
break;
}
len = (cur-start) % len;
- /* FALL THROUGH */
+ /* FALLTHROUGH */
case 'X':
if (utf8) {
if (len < 1) goto no_change;
if (ai32 == 0) goto no_change;
len -= ai32;
}
- /* FALL THROUGH */
+ /* FALLTHROUGH */
case 'x':
goto grow;
case 'A':
GROWING(0, cat, start, cur, len+UTF8_MAXLEN);
end = start+SvLEN(cat)-UTF8_MAXLEN;
}
- cur = (char *) uvuni_to_utf8_flags((U8 *) cur,
- NATIVE_TO_UNI(auv),
+ cur = (char *) uvchr_to_utf8_flags((U8 *) cur,
+ auv,
warn_utf8 ?
0 : UNICODE_ALLOW_ANY);
} else {
auv = SvUV(fromstr);
if (utf8) {
U8 buffer[UTF8_MAXLEN], *endb;
- endb = uvuni_to_utf8_flags(buffer, auv,
+ endb = uvchr_to_utf8_flags(buffer, auv,
warn_utf8 ?
0 : UNICODE_ALLOW_ANY);
if (cur+(endb-buffer)*UTF8_EXPAND >= end) {
GROWING(0, cat, start, cur, len+UTF8_MAXLEN);
end = start+SvLEN(cat)-UTF8_MAXLEN;
}
- cur = (char *) uvuni_to_utf8_flags((U8 *) cur, auv,
+ cur = (char *) uvchr_to_utf8_flags((U8 *) cur, auv,
warn_utf8 ?
0 : UNICODE_ALLOW_ANY);
}
}
break;
#else
- /* Fall through! */
+ /* FALLTHROUGH */
#endif
case 'S':
while (len-- > 0) {
}
break;
#else
- /* Fall through! */
+ /* FALLTHROUGH */
#endif
case 's':
while (len-- > 0) {
PUSH32(utf8, cur, &ai32, needs_swap);
}
break;
-#ifdef HAS_QUAD
+#if defined(HAS_QUAD) && IVSIZE >= 8
case 'Q':
while (len-- > 0) {
Uquad_t auquad;
PUSH_VAR(utf8, cur, aquad, needs_swap);
}
break;
-#endif /* HAS_QUAD */
+#endif
case 'P':
len = 1; /* assume SV is correct length */
GROWING(utf8, cat, start, cur, sizeof(char *));
- /* Fall through! */
+ /* FALLTHROUGH */
case 'p':
while (len-- > 0) {
const char *aptr;