Fix typos in comments.

[perl5.git] / utf8.c

diff --git a/utf8.c b/utf8.c
index be32870..d6e54ba 100644 (file)
--- a/utf8.c
+++ b/utf8.c
@@ -209,6 +209,9 @@ S_is_utf8_char_slow(pTHX_ const U8 *s, const STRLEN len)
 
     slen = len - 1;
     s++;
+#ifdef EBCDIC
+    u = NATIVE_TO_UTF(u);
+#endif
     u &= UTF_START_MASK(len);
     uv  = u;
     ouv = uv;
@@ -240,7 +243,7 @@ will be returned if it is valid, otherwise 0.
 STRLEN
 Perl_is_utf8_char(pTHX_ const U8 *s)
 {
-    STRLEN len = UTF8SKIP(s);
+    const STRLEN len = UTF8SKIP(s);
 #ifdef IS_UTF8_CHAR
     if (IS_UTF8_CHAR_FAST(len))
         return IS_UTF8_CHAR(s, len) ? len : 0;
@@ -267,7 +270,7 @@ Perl_is_utf8_string(pTHX_ const U8 *s, STRLEN len)
     const U8* x = s;
     const U8* send;
 
-    if (!len && s)
+    if (!len)
        len = strlen((const char *)s);
     send = s + len;
 
@@ -306,7 +309,7 @@ Perl_is_utf8_string(pTHX_ const U8 *s, STRLEN len)
 /*
 =for apidoc A|bool|is_utf8_string_loclen|const U8 *s|STRLEN len|const U8 **ep|const STRLEN *el
 
-Like is_ut8_string() but stores the location of the failure (in the
+Like is_utf8_string() but stores the location of the failure (in the
 case of "utf8ness failure") or the location s+len (in the case of
 "utf8ness success") in the C<ep>, and the number of UTF-8
 encoded characters in the C<el>.
@@ -323,7 +326,7 @@ Perl_is_utf8_string_loclen(pTHX_ const U8 *s, STRLEN len, const U8 **ep, STRLEN
     const U8* send;
     STRLEN c;
 
-    if (!len && s)
+    if (!len)
         len = strlen((const char *)s);
     send = s + len;
     if (el)
@@ -367,7 +370,7 @@ Perl_is_utf8_string_loclen(pTHX_ const U8 *s, STRLEN len, const U8 **ep, STRLEN
 /*
 =for apidoc A|bool|is_utf8_string_loc|const U8 *s|STRLEN len|const U8 **ep|const STRLEN *el
 
-Like is_ut8_string() but stores the location of the failure (in the
+Like is_utf8_string() but stores the location of the failure (in the
 case of "utf8ness failure") or the location s+len (in the case of
 "utf8ness success") in the C<ep>.
 
@@ -543,7 +546,7 @@ malformed:
     }
 
     if (dowarn) {
-       SV* sv = sv_2mortal(newSVpv("Malformed UTF-8 character ", 0));
+       SV* const sv = sv_2mortal(newSVpv("Malformed UTF-8 character ", 0));
 
        switch (warning) {
        case 0: /* Intentionally empty. */ break;
@@ -557,10 +560,12 @@ malformed:
            if (s == s0)
                Perl_sv_catpvf(aTHX_ sv, "(unexpected non-continuation byte 0x%02"UVxf", immediately after start byte 0x%02"UVxf")",
                            (UV)s[1], startbyte);
-           else
+           else {
+               const int len = (int)(s-s0);
                Perl_sv_catpvf(aTHX_ sv, "(unexpected non-continuation byte 0x%02"UVxf", %d byte%s after start byte 0x%02"UVxf", expected %d bytes)",
-                           (UV)s[1], s - s0, s - s0 > 1 ? "s" : "", startbyte, (int)expectlen);
-             
+                           (UV)s[1], len, len > 1 ? "s" : "", startbyte, (int)expectlen);
+           }
+
            break;
        case UTF8_WARN_FE_FF:
            Perl_sv_catpvf(aTHX_ sv, "(byte 0x%02"UVxf")", uv);
@@ -590,7 +595,7 @@ malformed:
        }
        
        if (warning) {
-           const char *s = SvPVX_const(sv);
+           const char * const s = SvPVX_const(sv);
 
            if (PL_op)
                Perl_warner(aTHX_ packWARN(WARN_UTF8),
@@ -1451,7 +1456,8 @@ The "normal" is a string like "ToLower" which means the swash
 =cut */
 
 UV
-Perl_to_utf8_case(pTHX_ const U8 *p, U8* ustrp, STRLEN *lenp, SV **swashp, const char *normal, const char *special)
+Perl_to_utf8_case(pTHX_ const U8 *p, U8* ustrp, STRLEN *lenp,
+                       SV **swashp, const char *normal, const char *special)
 {
     U8 tmpbuf[UTF8_MAXBYTES_CASE+1];
     STRLEN len = 0;
@@ -1625,7 +1631,7 @@ Perl_swash_init(pTHX_ const char* pkg, const char* name, SV *listsv, I32 minbits
 {
     dVAR;
     SV* retval;
-    SV* tokenbufsv = sv_newmortal();
+    SV* const tokenbufsv = sv_newmortal();
     dSP;
     const size_t pkg_len = strlen(pkg);
     const size_t name_len = strlen(name);
@@ -1826,34 +1832,6 @@ Perl_swash_fetch(pTHX_ SV *sv, const U8 *ptr, bool do_utf8)
     return 0;
 }
 
-
-/*
-=for apidoc A|U8 *|uvchr_to_utf8|U8 *d|UV uv
-
-Adds the UTF-8 representation of the Native codepoint C<uv> to the end
-of the string C<d>; C<d> should be have at least C<UTF8_MAXBYTES+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;
-
-=cut
-*/
-
-/* On ASCII machines this is normally a macro but we want a
-   real function in case XS code wants it
-*/
-#undef Perl_uvchr_to_utf8
-U8 *
-Perl_uvchr_to_utf8(pTHX_ U8 *d, UV uv)
-{
-    return Perl_uvuni_to_utf8_flags(aTHX_ d, NATIVE_TO_UNI(uv), 0);
-}
-
 U8 *
 Perl_uvchr_to_utf8_flags(pTHX_ U8 *d, UV uv, UV flags)
 {
@@ -1861,28 +1839,6 @@ Perl_uvchr_to_utf8_flags(pTHX_ U8 *d, UV uv, UV flags)
 }
 
 /*
-=for apidoc A|UV|utf8n_to_uvchr|U8 *s|STRLEN curlen|STRLEN *retlen|U32 flags
-
-Returns the native character value of the first character in the string C<s>
-which is assumed to be in UTF-8 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.
-
-=cut
-*/
-/* On ASCII machines this is normally a macro but we want
-   a real function in case XS code wants it
-*/
-#undef Perl_utf8n_to_uvchr
-UV
-Perl_utf8n_to_uvchr(pTHX_ const U8 *s, STRLEN curlen, STRLEN *retlen, U32 flags)
-{
-    const UV uv = Perl_utf8n_to_uvuni(aTHX_ s, curlen, retlen, flags);
-    return UNI_TO_NATIVE(uv);
-}
-
-/*
 =for apidoc A|char *|pv_uni_display|SV *dsv|U8 *spv|STRLEN len|STRLEN pvlim|UV flags
 
 Build to the scalar dsv a displayable version of the string spv,