summaryrefslogtreecommitdiff
path: root/utf8.c
diff options
context:
space:
mode:
authorJarkko Hietaniemi <jhi@iki.fi>2000-10-25 20:00:48 +0000
committerJarkko Hietaniemi <jhi@iki.fi>2000-10-25 20:00:48 +0000
commitdcad28805702d580064bc39a267d63c58bbb3b3f (patch)
treec59311ffbadd7bc18b3b7bcc1b2158652051f134 /utf8.c
parentfcc8fcf67e5ea5f08178c9ac86509bc972ef38ff (diff)
downloadperl-dcad28805702d580064bc39a267d63c58bbb3b3f.tar.gz
Continue the internal UTF-8 API tweaking.
Rename utf8_to_uv_chk() back to utf8_to_uv() because it's used much more than the simpler API, now called utf8_to_uv_simple(). Still not quite happy with API, too much partial duplication of functionality. p4raw-id: //depot/perl@7439
Diffstat (limited to 'utf8.c')
-rw-r--r--utf8.c59
1 files changed, 29 insertions, 30 deletions
diff --git a/utf8.c b/utf8.c
index 7bb34b764e..80f88466e6 100644
--- a/utf8.c
+++ b/utf8.c
@@ -171,7 +171,7 @@ Perl_is_utf8_string(pTHX_ U8 *s, STRLEN len)
}
/*
-=for apidoc Am|U8* s|utf8_to_uv_chk|STRLEN curlen|I32 *retlen|U32 flags
+=for apidoc Am|U8* s|utf8_to_uv|STRLEN curlen|I32 *retlen|U32 flags
Returns the character value of the first character in the string C<s>
which is assumed to be in UTF8 encoding and no longer than C<curlen>;
@@ -179,16 +179,15 @@ C<retlen> will be set to the length, in bytes, of that character,
and the pointer C<s> will be advanced to the end of the character.
If C<s> does not point to a well-formed UTF8 character, the behaviour
-is dependent on the value of C<checking>: if this is true, it is
-assumed that the caller will raise a warning, and this function will
-set C<retlen> to C<-1> and return. If C<checking> is not true, an optional UTF8
-warning is produced.
+is dependent on the value of C<flags>: if it contains UTF8_CHECK_ONLY,
+it is assumed that the caller will raise a warning, and this function
+will set C<retlen> to C<-1> and return. The C<flags> can also contain
+various flags to allow deviations from the strict UTF-8 encoding.
-=cut
-*/
+=cut */
UV
-Perl_utf8_to_uv_chk(pTHX_ U8* s, STRLEN curlen, STRLEN* retlen, U32 flags)
+Perl_utf8_to_uv(pTHX_ U8* s, STRLEN curlen, STRLEN* retlen, U32 flags)
{
dTHR;
UV uv = *s, ouv;
@@ -324,7 +323,7 @@ malformed:
}
/*
-=for apidoc Am|U8* s|utf8_to_uv|STRLEN *retlen
+=for apidoc Am|U8* s|utf8_to_uv_simple|STRLEN *retlen
Returns the character value of the first character in the string C<s>
which is assumed to be in UTF8 encoding; C<retlen> will be set to the
@@ -338,9 +337,9 @@ returned and retlen is set, if possible, to -1.
*/
UV
-Perl_utf8_to_uv(pTHX_ U8* s, STRLEN* retlen)
+Perl_utf8_to_uv_simple(pTHX_ U8* s, STRLEN* retlen)
{
- return Perl_utf8_to_uv_chk(aTHX_ s, (STRLEN)-1, retlen, 0);
+ return Perl_utf8_to_uv(aTHX_ s, (STRLEN)-1, retlen, 0);
}
/* utf8_distance(a,b) returns the number of UTF8 characters between
@@ -400,30 +399,30 @@ Returns zero on failure, setting C<len> to -1.
U8 *
Perl_utf8_to_bytes(pTHX_ U8* s, STRLEN *len)
{
- dTHR;
U8 *send;
U8 *d;
- U8 *save;
-
- send = s + *len;
- d = save = s;
+ U8 *save = s;
/* ensure valid UTF8 and chars < 256 before updating string */
- while (s < send) {
- U8 c = *s++;
+ for (send = s + *len; s < send; ) {
+ U8 c = *s++;
+
if (c >= 0x80 &&
- ( (s >= send) || ((*s++ & 0xc0) != 0x80) || ((c & 0xfe) != 0xc2))) {
- *len = -1;
- return 0;
- }
+ ((s >= send) ||
+ ((*s++ & 0xc0) != 0x80) || ((c & 0xfe) != 0xc2))) {
+ *len = -1;
+ return 0;
+ }
}
- s = save;
+
+ d = s = save;
while (s < send) {
- if (*s < 0x80)
- *d++ = *s++;
+ if (*s < 0x80) {
+ *d++ = *s++;
+ }
else {
STRLEN ulen;
- *d++ = (U8)utf8_to_uv(s, &ulen);
+ *d++ = (U8)utf8_to_uv_simple(s, &ulen);
s += ulen;
}
}
@@ -951,7 +950,7 @@ Perl_to_utf8_upper(pTHX_ U8 *p)
if (!PL_utf8_toupper)
PL_utf8_toupper = swash_init("utf8", "ToUpper", &PL_sv_undef, 4, 0);
uv = swash_fetch(PL_utf8_toupper, p);
- return uv ? uv : utf8_to_uv_chk(p,STRLEN_MAX,0,0);
+ return uv ? uv : utf8_to_uv(p,STRLEN_MAX,0,0);
}
UV
@@ -962,7 +961,7 @@ Perl_to_utf8_title(pTHX_ U8 *p)
if (!PL_utf8_totitle)
PL_utf8_totitle = swash_init("utf8", "ToTitle", &PL_sv_undef, 4, 0);
uv = swash_fetch(PL_utf8_totitle, p);
- return uv ? uv : utf8_to_uv_chk(p,STRLEN_MAX,0,0);
+ return uv ? uv : utf8_to_uv(p,STRLEN_MAX,0,0);
}
UV
@@ -973,7 +972,7 @@ Perl_to_utf8_lower(pTHX_ U8 *p)
if (!PL_utf8_tolower)
PL_utf8_tolower = swash_init("utf8", "ToLower", &PL_sv_undef, 4, 0);
uv = swash_fetch(PL_utf8_tolower, p);
- return uv ? uv : utf8_to_uv_chk(p,STRLEN_MAX,0,0);
+ return uv ? uv : utf8_to_uv(p,STRLEN_MAX,0,0);
}
/* a "swash" is a swatch hash */
@@ -1063,7 +1062,7 @@ Perl_swash_fetch(pTHX_ SV *sv, U8 *ptr)
PUSHMARK(SP);
EXTEND(SP,3);
PUSHs((SV*)sv);
- PUSHs(sv_2mortal(newSViv(utf8_to_uv_chk(ptr, STRLEN_MAX, 0, 0) & ~(needents - 1))));
+ PUSHs(sv_2mortal(newSViv(utf8_to_uv(ptr, STRLEN_MAX, 0, 0) & ~(needents - 1))));
PUSHs(sv_2mortal(newSViv(needents)));
PUTBACK;
if (call_method("SWASHGET", G_SCALAR))