SV* cv_const_sv(CV* cv)
=for hackers
-Found in file opmini.c
+Found in file op.c
=item dMARK
character. Note that an ASCII character is a valid UTF-8 character.
The actual number of bytes in the UTF-8 character will be returned if
it is valid, otherwise 0.
-
+
STRLEN is_utf8_char(U8 *p)
=for hackers
CV* newCONSTSUB(HV* stash, char* name, SV* sv)
=for hackers
-Found in file opmini.c
+Found in file op.c
=item newHV
Used by C<xsubpp> to hook up XSUBs as Perl subs.
=for hackers
-Found in file opmini.c
+Found in file op.c
=item newXSproto
=item POPp
-Pops a string off the stack.
+Pops a string off the stack. Deprecated. New code should provide
+a STRLEN n_a and use POPpx.
char* POPp
=for hackers
Found in file pp.h
+=item POPpbytex
+
+Pops a string off the stack which must consist of bytes i.e. characters < 256.
+Requires a variable STRLEN n_a in scope.
+
+ char* POPpbytex
+
+=for hackers
+Found in file pp.h
+
+=item POPpx
+
+Pops a string off the stack.
+Requires a variable STRLEN n_a in scope.
+
+ char* POPpx
+
+=for hackers
+Found in file pp.h
+
=item POPs
Pops an SV off the stack.
=for hackers
Found in file handy.h
+=item utf8n_to_uvchr
+
+Returns the native 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
+length, in bytes, of that character.
+
+Allows length and flags to be passed to low level routine.
+
+ UV utf8n_to_uvchr(U8 *s, STRLEN curlen, STRLEN* retlen, U32 flags)
+
+=for hackers
+Found in file utf8.c
+
+=item utf8n_to_uvuni
+
+Bottom level UTF-8 decode routine.
+Returns the unicode code point value of the first character in the string C<s>
+which is assumed to be in UTF8 encoding and no longer than C<curlen>;
+C<retlen> will be set to the length, in bytes, of that character.
+
+If C<s> does not point to a well-formed UTF8 character, the behaviour
+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 silently just set C<retlen> to C<-1> and return zero. If the
+C<flags> does not contain UTF8_CHECK_ONLY, warnings about
+malformations will be given, C<retlen> will be set to the expected
+length of the UTF-8 character in bytes, and zero will be returned.
+
+The C<flags> can also contain various flags to allow deviations from
+the strict UTF-8 encoding (see F<utf8.h>).
+
+Most code should use utf8_to_uvchr() rather than call this directly.
+
+ UV utf8n_to_uvuni(U8 *s, STRLEN curlen, STRLEN* retlen, U32 flags)
+
+=for hackers
+Found in file utf8.c
+
=item utf8_distance
Returns the number of UTF8 characters between the UTF-8 pointers C<a>
=for hackers
Found in file utf8.c
-=item utf8_to_uv
-
-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>;
-C<retlen> will be set to the length, in bytes, of that character.
+=item utf8_to_uvchr
-If C<s> does not point to a well-formed UTF8 character, the behaviour
-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 silently just set C<retlen> to C<-1> and return zero. If the
-C<flags> does not contain UTF8_CHECK_ONLY, warnings about
-malformations will be given, C<retlen> will be set to the expected
-length of the UTF-8 character in bytes, and zero will be returned.
+Returns the native 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
+length, in bytes, of that character.
-The C<flags> can also contain various flags to allow deviations from
-the strict UTF-8 encoding (see F<utf8.h>).
+If C<s> does not point to a well-formed UTF8 character, zero is
+returned and retlen is set, if possible, to -1.
- UV utf8_to_uv(U8 *s, STRLEN curlen, STRLEN* retlen, U32 flags)
+ UV utf8_to_uvchr(U8 *s, STRLEN* retlen)
=for hackers
Found in file utf8.c
-=item utf8_to_uv_simple
+=item utf8_to_uvuni
-Returns the character value of the first character in the string C<s>
+Returns the Unicode code point of the first character in the string C<s>
which is assumed to be in UTF8 encoding; C<retlen> will be set to the
length, in bytes, of that character.
+This function should only be used when returned UV is considered
+an index into the Unicode semantic tables (e.g. swashes).
+
If C<s> does not point to a well-formed UTF8 character, zero is
returned and retlen is set, if possible, to -1.
- UV utf8_to_uv_simple(U8 *s, STRLEN* retlen)
+ UV utf8_to_uvuni(U8 *s, STRLEN* retlen)
+
+=for hackers
+Found in file utf8.c
+
+=item uvchr_to_utf8
+
+Adds the UTF8 representation of the Native codepoint C<uv> to the end
+of the string C<d>; C<d> should be have at least C<UTF8_MAXLEN+1> free
+bytes available. The return value is the pointer to the byte after the
+end of the new character. In other words,
+
+ d = uvchr_to_utf8(d, uv);
+
+is the recommended wide native character-aware way of saying
+
+ *(d++) = uv;
+
+ U8* uvchr_to_utf8(U8 *d, UV uv)
=for hackers
Found in file utf8.c
-=item uv_to_utf8
+=item uvuni_to_utf8
Adds the UTF8 representation of the Unicode codepoint C<uv> to the end
of the string C<d>; C<d> should be have at least C<UTF8_MAXLEN+1> free
bytes available. The return value is the pointer to the byte after the
-end of the new character. In other words,
+end of the new character. In other words,
- d = uv_to_utf8(d, uv);
+ d = uvuni_to_utf8(d, uv);
is the recommended Unicode-aware way of saying
*(d++) = uv;
- U8* uv_to_utf8(U8 *d, UV uv)
+ U8* uvuni_to_utf8(U8 *d, UV uv)
=for hackers
Found in file utf8.c
https://perl5.git.perl.org / perl5.git / blobdiff