perldelta for fb5e77103dd4, 35608a1658fe

[perl5.git] / mathoms.c

diff --git a/mathoms.c b/mathoms.c
index d059f19..b8dcb89 100644 (file)
--- a/mathoms.c
+++ b/mathoms.c
@@ -518,7 +518,7 @@ int
 Perl_fprintf_nocontext(PerlIO *stream, const char *format, ...)
 {
     int ret = 0;
-    va_list(arglist);
+    va_list arglist;
 
     /* Easier to special case this here than in embed.pl. (Look at what it
        generates for proto.h) */
@@ -536,7 +536,7 @@ int
 Perl_printf_nocontext(const char *format, ...)
 {
     dTHX;
-    va_list(arglist);
+    va_list arglist;
     int ret = 0;
 
 #ifdef PERL_IMPLICIT_CONTEXT
@@ -1140,6 +1140,38 @@ Perl_newSUB(pTHX_ I32 floor, OP *o, OP *proto, OP *block)
     return newATTRSUB(floor, o, proto, NULL, block);
 }
 
+UV
+Perl_to_utf8_fold(pTHX_ const U8 *p, U8* ustrp, STRLEN *lenp)
+{
+    PERL_ARGS_ASSERT_TO_UTF8_FOLD;
+
+    return toFOLD_utf8(p, ustrp, lenp);
+}
+
+UV
+Perl_to_utf8_lower(pTHX_ const U8 *p, U8* ustrp, STRLEN *lenp)
+{
+    PERL_ARGS_ASSERT_TO_UTF8_LOWER;
+
+    return toLOWER_utf8(p, ustrp, lenp);
+}
+
+UV
+Perl_to_utf8_title(pTHX_ const U8 *p, U8* ustrp, STRLEN *lenp)
+{
+    PERL_ARGS_ASSERT_TO_UTF8_TITLE;
+
+    return toTITLE_utf8(p, ustrp, lenp);
+}
+
+UV
+Perl_to_utf8_upper(pTHX_ const U8 *p, U8* ustrp, STRLEN *lenp)
+{
+    PERL_ARGS_ASSERT_TO_UTF8_UPPER;
+
+    return toUPPER_utf8(p, ustrp, lenp);
+}
+
 SV *
 Perl_sv_mortalcopy(pTHX_ SV *const oldstr)
 {
@@ -1168,6 +1200,22 @@ ASCII_TO_NEED(const UV enc, const UV ch)
     return ch;
 }
 
+bool      /* Made into a function, so can be deprecated */
+Perl_isIDFIRST_lazy(pTHX_ const char* p)
+{
+    PERL_ARGS_ASSERT_ISIDFIRST_LAZY;
+
+    return isIDFIRST_lazy_if(p,1);
+}
+
+bool      /* Made into a function, so can be deprecated */
+Perl_isALNUM_lazy(pTHX_ const char* p)
+{
+    PERL_ARGS_ASSERT_ISALNUM_LAZY;
+
+    return isALNUM_lazy_if(p,1);
+}
+
 bool
 Perl_is_uni_alnum(pTHX_ UV c)
 {
@@ -1329,6 +1377,38 @@ Perl_is_uni_idfirst(pTHX_ UV c)
 }
 
 bool
+Perl_is_utf8_idfirst(pTHX_ const U8 *p) /* The naming is historical. */
+{
+    PERL_ARGS_ASSERT_IS_UTF8_IDFIRST;
+
+    return _is_utf8_idstart(p);
+}
+
+bool
+Perl_is_utf8_xidfirst(pTHX_ const U8 *p) /* The naming is historical. */
+{
+    PERL_ARGS_ASSERT_IS_UTF8_XIDFIRST;
+
+    return _is_utf8_xidstart(p);
+}
+
+bool
+Perl_is_utf8_idcont(pTHX_ const U8 *p)
+{
+    PERL_ARGS_ASSERT_IS_UTF8_IDCONT;
+
+    return _is_utf8_idcont(p);
+}
+
+bool
+Perl_is_utf8_xidcont(pTHX_ const U8 *p)
+{
+    PERL_ARGS_ASSERT_IS_UTF8_XIDCONT;
+
+    return _is_utf8_xidcont(p);
+}
+
+bool
 Perl_is_uni_upper_lc(pTHX_ UV c)
 {
     return isUPPER_LC_uvchr(c);
@@ -1400,6 +1480,167 @@ Perl_to_uni_lower_lc(pTHX_ U32 c)
     return (U32)to_uni_lower(c, tmpbuf, &len);
 }
 
+bool
+Perl_is_utf8_alnum(pTHX_ const U8 *p)
+{
+    PERL_ARGS_ASSERT_IS_UTF8_ALNUM;
+
+    /* NOTE: "IsWord", not "IsAlnum", since Alnum is a true
+     * descendant of isalnum(3), in other words, it doesn't
+     * contain the '_'. --jhi */
+    return isWORDCHAR_utf8(p);
+}
+
+bool
+Perl_is_utf8_alnumc(pTHX_ const U8 *p)
+{
+    PERL_ARGS_ASSERT_IS_UTF8_ALNUMC;
+
+    return isALPHANUMERIC_utf8(p);
+}
+
+bool
+Perl_is_utf8_alpha(pTHX_ const U8 *p)
+{
+    PERL_ARGS_ASSERT_IS_UTF8_ALPHA;
+
+    return isALPHA_utf8(p);
+}
+
+bool
+Perl_is_utf8_ascii(pTHX_ const U8 *p)
+{
+    PERL_ARGS_ASSERT_IS_UTF8_ASCII;
+    PERL_UNUSED_CONTEXT;
+
+    return isASCII_utf8(p);
+}
+
+bool
+Perl_is_utf8_blank(pTHX_ const U8 *p)
+{
+    PERL_ARGS_ASSERT_IS_UTF8_BLANK;
+    PERL_UNUSED_CONTEXT;
+
+    return isBLANK_utf8(p);
+}
+
+bool
+Perl_is_utf8_space(pTHX_ const U8 *p)
+{
+    PERL_ARGS_ASSERT_IS_UTF8_SPACE;
+    PERL_UNUSED_CONTEXT;
+
+    return isSPACE_utf8(p);
+}
+
+bool
+Perl_is_utf8_perl_space(pTHX_ const U8 *p)
+{
+    PERL_ARGS_ASSERT_IS_UTF8_PERL_SPACE;
+    PERL_UNUSED_CONTEXT;
+
+    /* Only true if is an ASCII space-like character, and ASCII is invariant
+     * under utf8, so can just use the macro */
+    return isSPACE_A(*p);
+}
+
+bool
+Perl_is_utf8_perl_word(pTHX_ const U8 *p)
+{
+    PERL_ARGS_ASSERT_IS_UTF8_PERL_WORD;
+    PERL_UNUSED_CONTEXT;
+
+    /* Only true if is an ASCII word character, and ASCII is invariant
+     * under utf8, so can just use the macro */
+    return isWORDCHAR_A(*p);
+}
+
+bool
+Perl_is_utf8_digit(pTHX_ const U8 *p)
+{
+    PERL_ARGS_ASSERT_IS_UTF8_DIGIT;
+
+    return isDIGIT_utf8(p);
+}
+
+bool
+Perl_is_utf8_posix_digit(pTHX_ const U8 *p)
+{
+    PERL_ARGS_ASSERT_IS_UTF8_POSIX_DIGIT;
+    PERL_UNUSED_CONTEXT;
+
+    /* Only true if is an ASCII digit character, and ASCII is invariant
+     * under utf8, so can just use the macro */
+    return isDIGIT_A(*p);
+}
+
+bool
+Perl_is_utf8_upper(pTHX_ const U8 *p)
+{
+    PERL_ARGS_ASSERT_IS_UTF8_UPPER;
+
+    return isUPPER_utf8(p);
+}
+
+bool
+Perl_is_utf8_lower(pTHX_ const U8 *p)
+{
+    PERL_ARGS_ASSERT_IS_UTF8_LOWER;
+
+    return isLOWER_utf8(p);
+}
+
+bool
+Perl_is_utf8_cntrl(pTHX_ const U8 *p)
+{
+    PERL_ARGS_ASSERT_IS_UTF8_CNTRL;
+    PERL_UNUSED_CONTEXT;
+
+    return isCNTRL_utf8(p);
+}
+
+bool
+Perl_is_utf8_graph(pTHX_ const U8 *p)
+{
+    PERL_ARGS_ASSERT_IS_UTF8_GRAPH;
+
+    return isGRAPH_utf8(p);
+}
+
+bool
+Perl_is_utf8_print(pTHX_ const U8 *p)
+{
+    PERL_ARGS_ASSERT_IS_UTF8_PRINT;
+
+    return isPRINT_utf8(p);
+}
+
+bool
+Perl_is_utf8_punct(pTHX_ const U8 *p)
+{
+    PERL_ARGS_ASSERT_IS_UTF8_PUNCT;
+
+    return isPUNCT_utf8(p);
+}
+
+bool
+Perl_is_utf8_xdigit(pTHX_ const U8 *p)
+{
+    PERL_ARGS_ASSERT_IS_UTF8_XDIGIT;
+    PERL_UNUSED_CONTEXT;
+
+    return isXDIGIT_utf8(p);
+}
+
+bool
+Perl_is_utf8_mark(pTHX_ const U8 *p)
+{
+    PERL_ARGS_ASSERT_IS_UTF8_MARK;
+
+    return _is_utf8_mark(p);
+}
+
 /*
 =for apidoc is_utf8_char
 
@@ -1419,8 +1660,9 @@ Perl_is_utf8_char(const U8 *s)
 {
     PERL_ARGS_ASSERT_IS_UTF8_CHAR;
 
-    /* Assumes we have enough space, which is why this is deprecated */
-    return isUTF8_CHAR(s, s + UTF8SKIP(s));
+    /* Assumes we have enough space, which is why this is deprecated.  But the
+     * strnlen() makes it safe for the common case of NUL-terminated strings */
+    return isUTF8_CHAR(s, s + my_strnlen((char *) s, UTF8SKIP(s)));
 }
 
 /*
@@ -1513,6 +1755,12 @@ Perl_instr(const char *big, const char *little)
     return instr((char *) big, (char *) little);
 }
 
+SV *
+Perl_newSVsv(pTHX_ SV *const old)
+{
+    return newSVsv(old);
+}
+
 #endif /* NO_MATHOMS */
 
 /*