perldelta for eff754733a9

[perl5.git] / inline.h

diff --git a/inline.h b/inline.h
index 615c2e3..0792694 100644 (file)
--- a/inline.h
+++ b/inline.h
@@ -188,17 +188,16 @@ S_sv_or_pv_pos_u2b(pTHX_ SV *sv, const char *pv, STRLEN pos, STRLEN *lenp)
 /* ------------------------------- handy.h ------------------------------- */
 
 /* saves machine code for a common noreturn idiom typically used in Newx*() */
-#ifdef __clang__
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Wunused-function"
+#ifdef GCC_DIAG_PRAGMA
+GCC_DIAG_IGNORE(-Wunused-function) /* Intentionally left semicolonless. */
 #endif
 static void
 S_croak_memory_wrap(void)
 {
     Perl_croak_nocontext("%s",PL_memory_wrap);
 }
-#ifdef __clang__
-#pragma clang diagnostic pop
+#ifdef GCC_DIAG_PRAGMA
+GCC_DIAG_RESTORE /* Intentionally left semicolonless. */
 #endif
 
 /* ------------------------------- utf8.h ------------------------------- */
@@ -219,28 +218,41 @@ S_append_utf8_from_native_byte(const U8 byte, U8** dest)
     }
 }
 
-/* These two exist only to replace the macros they formerly were so that their
- * use can be deprecated */
+/*
 
-PERL_STATIC_INLINE bool
-S_isIDFIRST_lazy(pTHX_ const char* p)
-{
-    PERL_ARGS_ASSERT_ISIDFIRST_LAZY;
+A helper function for the macro isUTF8_CHAR(), which should be used instead of
+this function.  The macro will handle smaller code points directly saving time,
+using this function as a fall-back for higher code points.
 
-    return isIDFIRST_lazy_if(p,1);
-}
+Tests if the first bytes of string C<s> form a valid UTF-8 character.  0 is
+returned if the bytes starting at C<s> up to but not including C<e> do not form a
+complete well-formed UTF-8 character; otherwise the number of bytes in the
+character is returned.
 
-PERL_STATIC_INLINE bool
-S_isALNUM_lazy(pTHX_ const char* p)
+Note that an INVARIANT (i.e. ASCII on non-EBCDIC) character is a valid UTF-8
+character.
+
+=cut */
+PERL_STATIC_INLINE STRLEN
+S__is_utf8_char_slow(const U8 *s, const U8 *e)
 {
-    PERL_ARGS_ASSERT_ISALNUM_LAZY;
+    dTHX;   /* The function called below requires thread context */
+
+    STRLEN actual_len;
+
+    PERL_ARGS_ASSERT__IS_UTF8_CHAR_SLOW;
 
-    return isALNUM_lazy_if(p,1);
+    assert(e >= s);
+    utf8n_to_uvchr(s, e - s, &actual_len, UTF8_CHECK_ONLY);
+
+    return (actual_len == (STRLEN) -1) ? 0 : actual_len;
 }
 
 /* ------------------------------- perl.h ----------------------------- */
 
 /*
+=head1 Miscellaneous Functions
+
 =for apidoc AiR|bool|is_safe_syscall|const char *pv|STRLEN len|const char *what|const char *op_name
 
 Test that the given C<pv> doesn't contain any internal C<NUL> characters.
@@ -307,6 +319,33 @@ S_should_warn_nl(const char *pv) {
 
 #endif
 
+/* ------------------ pp.c, regcomp.c, toke.c, universal.c ------------ */
+
+#define MAX_CHARSET_NAME_LENGTH 2
+
+PERL_STATIC_INLINE const char *
+get_regex_charset_name(const U32 flags, STRLEN* const lenp)
+{
+    /* Returns a string that corresponds to the name of the regex character set
+     * given by 'flags', and *lenp is set the length of that string, which
+     * cannot exceed MAX_CHARSET_NAME_LENGTH characters */
+
+    *lenp = 1;
+    switch (get_regex_charset(flags)) {
+        case REGEX_DEPENDS_CHARSET: return DEPENDS_PAT_MODS;
+        case REGEX_LOCALE_CHARSET:  return LOCALE_PAT_MODS;
+        case REGEX_UNICODE_CHARSET: return UNICODE_PAT_MODS;
+       case REGEX_ASCII_RESTRICTED_CHARSET: return ASCII_RESTRICT_PAT_MODS;
+       case REGEX_ASCII_MORE_RESTRICTED_CHARSET:
+           *lenp = 2;
+           return ASCII_MORE_RESTRICT_PAT_MODS;
+    }
+    /* The NOT_REACHED; hides an assert() which has a rather complex
+     * definition in perl.h. */
+    NOT_REACHED; /* NOTREACHED */
+    return "?";            /* Unknown */
+}
+
 /*
  * Local variables:
  * c-indentation-style: bsd