diff options
| -rwxr-xr-x | embed.pl | 2 | ||||
| -rw-r--r-- | pod/perlapi.pod | 45 | ||||
| -rw-r--r-- | utf8.c | 35 |
3 files changed, 70 insertions, 12 deletions
@@ -2079,7 +2079,7 @@ ApM |U8* |utf8_to_bytes |U8 *s|STRLEN *len ApM |U8* |bytes_to_utf8 |U8 *s|STRLEN *len Ap |UV |utf8_to_uv_simple|U8 *s|STRLEN* retlen Ap |UV |utf8_to_uv |U8 *s|STRLEN curlen|STRLEN* retlen|U32 flags -Ap |U8* |uv_to_utf8|U8 *d|UV uv +Ap |U8* |uv_to_utf8 |U8 *d|UV uv p |void |vivify_defelem |SV* sv p |void |vivify_ref |SV* sv|U32 to_what p |I32 |wait4pid |Pid_t pid|int* statusp|int flags diff --git a/pod/perlapi.pod b/pod/perlapi.pod index 1f270ce30e..50ac40c650 100644 --- a/pod/perlapi.pod +++ b/pod/perlapi.pod @@ -3219,6 +3219,43 @@ string, false otherwise. =for hackers Found in file utf8.c +=item utf8_distance + +Returns the number of UTF8 characters between the UTF-8 pointers C<a> +and C<b>. + +WARNING: use only if you *know* that the pointers point inside the +same UTF-8 buffer. + + IV utf8_distance(U8 *a, U8 *b) + +=for hackers +Found in file utf8.c + +=item utf8_hop + +Move the C<s> pointing to UTF-8 data by C<off> characters, either forward +or backward. + +WARNING: do not use the following unless you *know* C<off> is within +the UTF-8 buffer pointed to by C<s>. + + U8* utf8_hop(U8 *s, I32 off) + +=for hackers +Found in file utf8.c + +=item utf8_length + +Return the length of the UTF-8 char encoded string C<s> in characters. +Stops at C<e> (inclusive). If C<e E<lt> s> or if the scan would end +up past C<e>, croaks. + + STRLEN utf8_length(U8* s, U8 *e) + +=for hackers +Found in file utf8.c + =item utf8_to_bytes Converts a string C<s> of length C<len> from UTF8 into byte encoding. @@ -3241,9 +3278,11 @@ 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<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 -(see F<utf8.h>). +will set C<retlen> to C<-1> and return zero. If the C<flags> does not +contain UTF8_CHECK_ONLY, the UNICODE_REPLACEMENT_CHARACTER (0xFFFD) +will be returned, and C<retlen> will be set to the expected length of +the UTF-8 character in bytes. 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) @@ -189,9 +189,11 @@ 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<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 -(see F<utf8.h>). +will set C<retlen> to C<-1> and return zero. If the C<flags> does not +contain UTF8_CHECK_ONLY, the UNICODE_REPLACEMENT_CHARACTER (0xFFFD) +will be returned, and C<retlen> will be set to the expected length of +the UTF-8 character in bytes. The C<flags> can also contain various +flags to allow deviations from the strict UTF-8 encoding (see F<utf8.h>). =cut */ @@ -336,7 +338,7 @@ malformed: } if (retlen) - *retlen = expectlen ? expectlen : len; + *retlen = expectlen; return UNICODE_REPLACEMENT_CHARACTER; } @@ -362,7 +364,7 @@ Perl_utf8_to_uv_simple(pTHX_ U8* s, STRLEN* retlen) } /* -=for apidoc|utf8_length|U8 *s|U8 *e +=for apidoc Am|STRLEN|utf8_length|U8* s|U8 *e Return the length of the UTF-8 char encoded string C<s> in characters. Stops at C<e> (inclusive). If C<e E<lt> s> or if the scan would end @@ -390,8 +392,16 @@ Perl_utf8_length(pTHX_ U8* s, U8* e) return len; } -/* utf8_distance(a,b) returns the number of UTF8 characters between - the pointers a and b */ +/* +=for apidoc Am|IV|utf8_distance|U8 *a|U8 *b + +Returns the number of UTF8 characters between the UTF-8 pointers C<a> +and C<b>. + +WARNING: use only if you *know* that the pointers point inside the +same UTF-8 buffer. + +=cut */ IV Perl_utf8_distance(pTHX_ U8 *a, U8 *b) @@ -422,7 +432,16 @@ Perl_utf8_distance(pTHX_ U8 *a, U8 *b) return off; } -/* WARNING: do not use the following unless you *know* off is within bounds */ +/* +=for apidoc Am|U8*|utf8_hop|U8 *s|I32 off + +Move the C<s> pointing to UTF-8 data by C<off> characters, either forward +or backward. + +WARNING: do not use the following unless you *know* C<off> is within +the UTF-8 buffer pointed to by C<s>. + +=cut */ U8 * Perl_utf8_hop(pTHX_ U8 *s, I32 off) |