=for hackers
Found in file av.c
+=item bytes_from_utf8
+
+Converts a string C<s> of length C<len> from UTF8 into byte encoding.
+Unlike <utf8_to_bytes> but like C<bytes_to_utf8>, returns a pointer to
+the newly-created string, and updates C<len> to contain the new
+length. Returns the original string if no conversion occurs, C<len>
+is unchanged. Do nothing if C<is_utf8> points to 0. Sets C<is_utf8> to
+0 if C<s> is converted or contains all 7bit characters.
+
+NOTE: this function is experimental and may change or be
+removed without notice.
+
+ U8* bytes_from_utf8(U8 *s, STRLEN *len, bool *is_utf8)
+
+=for hackers
+Found in file utf8.c
+
=item bytes_to_utf8
Converts a string C<s> of length C<len> from ASCII into UTF8 encoding.
Returns a pointer to the newly-created string, and sets C<len> to
reflect the new length.
- U8 * bytes_to_utf8(U8 *s, STRLEN *len)
+NOTE: this function is experimental and may change or be
+removed without notice.
+
+ U8* bytes_to_utf8(U8 *s, STRLEN *len)
=for hackers
Found in file utf8.c
=for hackers
Found in file handy.h
+=item is_utf8_char
+
+Tests if some arbitrary number of bytes begins in a valid UTF-8
+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
+Found in file utf8.c
+
+=item is_utf8_string
+
+Returns true if first C<len> bytes of the given string form a valid UTF8
+string, false otherwise. Note that 'a valid UTF8 string' does not mean
+'a string that contains UTF8' because a valid ASCII string is a valid
+UTF8 string.
+
+ bool is_utf8_string(U8 *s, STRLEN len)
+
+=for hackers
+Found in file utf8.c
+
=item items
Variable which is setup by C<xsubpp> to indicate the number of
=for hackers
Found in file perl.c
-=item PL_DBsingle
-
-When Perl is run in debugging mode, with the B<-d> switch, this SV is a
-boolean which indicates whether subs are being single-stepped.
-Single-stepping is automatically turned on after every step. This is the C
-variable which corresponds to Perl's $DB::single variable. See
-C<PL_DBsub>.
-
- SV * PL_DBsingle
-
-=for hackers
-Found in file intrpvar.h
-
-=item PL_DBsub
-
-When Perl is run in debugging mode, with the B<-d> switch, this GV contains
-the SV which holds the name of the sub being debugged. This is the C
-variable which corresponds to Perl's $DB::sub variable. See
-C<PL_DBsingle>.
-
- GV * PL_DBsub
-
-=for hackers
-Found in file intrpvar.h
-
-=item PL_DBtrace
-
-Trace variable used when Perl is run in debugging mode, with the B<-d>
-switch. This is the C variable which corresponds to Perl's $DB::trace
-variable. See C<PL_DBsingle>.
-
- SV * PL_DBtrace
-
-=for hackers
-Found in file intrpvar.h
-
-=item PL_dowarn
-
-The C variable which corresponds to Perl's $^W warning variable.
-
- bool PL_dowarn
-
-=for hackers
-Found in file intrpvar.h
-
=item PL_modglobal
C<PL_modglobal> is a general purpose, interpreter global HV for use by
=for hackers
Found in file sv.h
-=item SvTYPE
-
-Returns the type of the SV. See C<svtype>.
+=item svtype
- svtype SvTYPE(SV* sv)
+An enum of flags for Perl types. These are found in the file B<sv.h>
+in the C<svtype> enum. Test these flags with the C<SvTYPE> macro.
=for hackers
Found in file sv.h
-=item svtype
+=item SvTYPE
-An enum of flags for Perl types. These are found in the file B<sv.h>
-in the C<svtype> enum. Test these flags with the C<SvTYPE> macro.
+Returns the type of the SV. See C<svtype>.
+
+ svtype SvTYPE(SV* sv)
=for hackers
Found in file sv.h
=item sv_catsv
-Concatenates the string from SV C<ssv> onto the end of the string in SV
-C<dsv>. Handles 'get' magic, but not 'set' magic. See C<sv_catsv_mg>.
+Concatenates the string from SV C<ssv> onto the end of the string in
+SV C<dsv>. Modifies C<dsv> but not C<ssv>. Handles 'get' magic, but
+not 'set' magic. See C<sv_catsv_mg>.
void sv_catsv(SV* dsv, SV* ssv)
=for hackers
Found in file handy.h
-=item U8 *s
-
-Returns true if first C<len> bytes of the given string form valid a UTF8
-string, false otherwise.
-
- is_utf8_string U8 *s(STRLEN len)
-
-=for hackers
-Found in file utf8.c
-
=item utf8_distance
Returns the number of UTF8 characters between the UTF-8 pointers C<a>
updates len to contain the new length.
Returns zero on failure, setting C<len> to -1.
- U8 * utf8_to_bytes(U8 *s, STRLEN *len)
+NOTE: this function is experimental and may change or be
+removed without notice.
+
+ U8* utf8_to_bytes(U8 *s, STRLEN *len)
=for hackers
Found in file utf8.c
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,
-and the pointer C<s> will be advanced to the end of the character.
+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,
The C<flags> can also contain various flags to allow deviations from
the strict UTF-8 encoding (see F<utf8.h>).
- U8* s utf8_to_uv(STRLEN curlen, STRLEN *retlen, U32 flags)
+ UV utf8_to_uv(U8 *s, STRLEN curlen, STRLEN* retlen, U32 flags)
=for hackers
Found in file utf8.c
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
-length, in bytes, of that character, and the pointer C<s> will be
-advanced to the end of the character.
+length, in bytes, of that character.
If C<s> does not point to a well-formed UTF8 character, zero is
returned and retlen is set, if possible, to -1.
- U8* s utf8_to_uv_simple(STRLEN *retlen)
+ UV utf8_to_uv_simple(U8 *s, STRLEN* retlen)
+
+=for hackers
+Found in file utf8.c
+
+=item uv_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,
+
+ d = uv_to_utf8(d, uv);
+
+is the recommended Unicode-aware way of saying
+
+ *(d++) = uv;
+
+ U8* uv_to_utf8(U8 *d, UV uv)
=for hackers
Found in file utf8.c
projects / p5sagit/p5-mst-13.2.git / blobdiff