X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=utf8.c;h=e21cb4f6b582499c312405fc2093517cd39036c1;hb=4e592f10f45677b2800948f688180c0f1ee587b4;hp=28ac6052955321b568a1db20cad6fc6663a5cbbb;hpb=670f1322a800dc03404a696600a617f3804f797d;p=p5sagit%2Fp5-mst-13.2.git

diff --git a/utf8.c b/utf8.c
index 28ac605..e21cb4f 100644
--- a/utf8.c
+++ b/utf8.c
@@ -1,6 +1,6 @@
 /*    utf8.c
  *
- *    Copyright (C) 2000, 2001, 2002, 2003, 2004, 2005, 2006,
+ *    Copyright (C) 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007
  *    by Larry Wall and others
  *
  *    You may distribute under the terms of either the GNU General Public
@@ -25,6 +25,13 @@
 #define PERL_IN_UTF8_C
 #include "perl.h"
 
+#ifndef EBCDIC
+/* Separate prototypes needed because in ASCII systems these
+ * usually macros but they still are compiled as code, too. */
+PERL_CALLCONV UV	Perl_utf8n_to_uvchr(pTHX_ const U8 *s, STRLEN curlen, STRLEN *retlen, U32 flags);
+PERL_CALLCONV U8*	Perl_uvchr_to_utf8(pTHX_ U8 *d, UV uv);
+#endif
+
 static const char unees[] =
     "Malformed UTF-8 character (unexpected end of string)";
 
@@ -371,7 +378,7 @@ Perl_is_utf8_string_loclen(pTHX_ const U8 *s, STRLEN len, const U8 **ep, STRLEN
 =for apidoc A|UV|utf8n_to_uvuni|const U8 *s|STRLEN curlen|STRLEN *retlen|U32 flags
 
 Bottom level UTF-8 decode routine.
-Returns the unicode code point value of the first character in the string C<s>
+Returns the Unicode code point value of the first character in the string C<s>
 which is assumed to be in UTF-8 encoding and no longer than C<curlen>;
 C<retlen> will be set to the length, in bytes, of that character.
 
@@ -524,7 +531,7 @@ malformed:
 
     if (flags & UTF8_CHECK_ONLY) {
 	if (retlen)
-	    *retlen = -1;
+	    *retlen = ((STRLEN) -1);
 	return 0;
     }
 
@@ -653,6 +660,7 @@ Perl_utf8_length(pTHX_ const U8 *s, const U8 *e)
 {
     dVAR;
     STRLEN len = 0;
+    U8 t = 0;
 
     /* Note: cannot use UTF8_IS_...() too eagerly here since e.g.
      * the bitops (especially ~) can create illegal UTF-8.
@@ -661,7 +669,7 @@ Perl_utf8_length(pTHX_ const U8 *s, const U8 *e)
     if (e < s)
 	goto warn_and_return;
     while (s < e) {
-	const U8 t = UTF8SKIP(s);
+	t = UTF8SKIP(s);
 	if (e - s < t) {
 	    warn_and_return:
 	    if (ckWARN_d(WARN_UTF8)) {
@@ -760,7 +768,7 @@ Perl_utf8_to_bytes(pTHX_ U8 *s, STRLEN *len)
         if (!UTF8_IS_INVARIANT(c) &&
             (!UTF8_IS_DOWNGRADEABLE_START(c) || (s >= send)
 	     || !(c = *s++) || !UTF8_IS_CONTINUATION(c))) {
-            *len = -1;
+            *len = ((STRLEN) -1);
             return 0;
         }
     }
@@ -888,7 +896,7 @@ Perl_utf16_to_utf8(pTHX_ U8* p, U8* d, I32 bytelen, I32 *newlen)
     }
 
     if (bytelen & 1)
-	Perl_croak(aTHX_ "panic: utf16_to_utf8: odd bytelen %"UVf, (UV)bytelen);
+	Perl_croak(aTHX_ "panic: utf16_to_utf8: odd bytelen %"UVuf, (UV)bytelen);
 
     pend = p + bytelen;
 
@@ -1548,11 +1556,10 @@ Perl_swash_init(pTHX_ const char* pkg, const char* name, SV *listsv, I32 minbits
 {
     dVAR;
     SV* retval;
-    SV* const tokenbufsv = sv_newmortal();
     dSP;
     const size_t pkg_len = strlen(pkg);
     const size_t name_len = strlen(name);
-    HV * const stash = gv_stashpvn(pkg, pkg_len, FALSE);
+    HV * const stash = gv_stashpvn(pkg, pkg_len, 0);
     SV* errsv_save;
 
     PUSHSTACKi(PERLSI_MAGIC);
@@ -1586,12 +1593,6 @@ Perl_swash_init(pTHX_ const char* pkg, const char* name, SV *listsv, I32 minbits
     PUSHs(sv_2mortal(newSViv(minbits)));
     PUSHs(sv_2mortal(newSViv(none)));
     PUTBACK;
-    if (IN_PERL_COMPILETIME) {
-	/* XXX ought to be handled by lex_start */
-	SAVEI32(PL_in_my);
-	PL_in_my = 0;
-	sv_setpv(tokenbufsv, PL_tokenbuf);
-    }
     errsv_save = newSVsv(ERRSV);
     if (call_method("SWASHNEW", G_SCALAR))
 	retval = newSVsv(*PL_stack_sp--);
@@ -1603,16 +1604,12 @@ Perl_swash_init(pTHX_ const char* pkg, const char* name, SV *listsv, I32 minbits
     LEAVE;
     POPSTACK;
     if (IN_PERL_COMPILETIME) {
-	STRLEN len;
-	const char* const pv = SvPV_const(tokenbufsv, len);
-
-	Copy(pv, PL_tokenbuf, len+1, char);
 	CopHINTS_set(PL_curcop, PL_hints);
     }
     if (!SvROK(retval) || SvTYPE(SvRV(retval)) != SVt_PVHV) {
         if (SvPOK(retval))
 	    Perl_croak(aTHX_ "Can't find Unicode property definition \"%"SVf"\"",
-		       (void*)retval);
+		       SVfARG(retval));
 	Perl_croak(aTHX_ "SWASHNEW didn't return an HV ref");
     }
     return retval;
@@ -1718,7 +1715,8 @@ Perl_swash_fetch(pTHX_ SV *swash, const U8 *ptr, bool do_utf8)
 	}
 
 	PL_last_swash_hv = hv;
-	PL_last_swash_klen = klen;
+	assert(klen <= sizeof(PL_last_swash_key));
+	PL_last_swash_klen = (U8)klen;
 	/* FIXME change interpvar.h?  */
 	PL_last_swash_tmps = (U8 *) tmps;
 	PL_last_swash_slen = slen;
@@ -1776,9 +1774,9 @@ S_swash_get(pTHX_ SV* swash, UV start, UV span)
     }
 
     /* create and initialize $swatch */
-    swatch = newSVpvs("");
     scur   = octets ? (span * octets) : (span + 7) / 8;
-    SvGROW(swatch, scur + 1);
+    swatch = newSV(scur);
+    SvPOK_on(swatch);
     s = (U8*)SvPVX(swatch);
     if (octets && none) {
 	const U8* const e = s + scur;
@@ -2138,6 +2136,7 @@ Perl_pv_uni_display(pTHX_ SV *dsv, const U8 *spv, STRLEN len, STRLEN pvlim, UV f
     const char *s, *e;
 
     sv_setpvn(dsv, "", 0);
+    SvUTF8_off(dsv);
     for (s = (const char *)spv, e = s + len; s < e; s += UTF8SKIP(s)) {
 	 UV u;
 	  /* This serves double duty as a flag and a character to print after
@@ -2169,12 +2168,14 @@ Perl_pv_uni_display(pTHX_ SV *dsv, const U8 *spv, STRLEN len, STRLEN pvlim, UV f
 		 default: break;
 		 }
 		 if (ok) {
-		     Perl_sv_catpvf(aTHX_ dsv, "\\%c", ok);
+		     const char string = ok;
+		     sv_catpvn(dsv, &string, 1);
 		 }
 	     }
 	     /* isPRINT() is the locale-blind version. */
 	     if (!ok && (flags & UNI_DISPLAY_ISPRINT) && isPRINT(c)) {
-	         Perl_sv_catpvf(aTHX_ dsv, "%c", c);
+		 const char string = c;
+		 sv_catpvn(dsv, &string, 1);
 		 ok = 1;
 	     }
 	 }