5.6.0 Patch for EPOC

[p5sagit/p5-mst-13.2.git] / toke.c

diff --git a/toke.c b/toke.c
index 4a54f72..d6bb6d9 100644 (file)
--- a/toke.c
+++ b/toke.c
@@ -326,7 +326,7 @@ S_cr_textfilter(pTHX_ int idx, SV *sv, int maxlen)
 }
 #endif
 
-#if 0
+#ifdef PERL_UTF16_FILTER
 STATIC I32
 S_utf16_textfilter(pTHX_ int idx, SV *sv, int maxlen)
 {
@@ -2490,6 +2490,8 @@ Perl_yylex(pTHX)
            goto retry;
        }
        do {
+        bool bof;
+        bof = PL_rsfp && (PerlIO_tell(PL_rsfp)==0); /* *Before* read! */
            if ((s = filter_gets(PL_linestr, PL_rsfp, 0)) == Nullch) {
              fake_eof:
                if (PL_rsfp) {
@@ -2525,7 +2527,9 @@ Perl_yylex(pTHX)
                    PL_bufend = SvPVX(PL_linestr) + SvCUR(PL_linestr);
                    PL_doextract = FALSE;
                }
-           }
+           } 
+        if (bof)
+            s = swallow_bom(s);
            incline(s);
        } while (PL_doextract);
        PL_oldoldbufptr = PL_oldbufptr = PL_bufptr = PL_linestart = s;
@@ -7407,3 +7411,55 @@ restore_rsfp(pTHXo_ void *f)
        PerlIO_close(PL_rsfp);
     PL_rsfp = fp;
 }
+
+STATIC char*
+S_swallow_bom(pTHX_ char *s) {
+    STRLEN slen;
+    slen = SvCUR(PL_linestr);
+    switch (*s) {
+    case -1:       
+    if ((s[1] & 255) == 254) { 
+        /* UTF-16 little-endian */
+#ifdef PERL_UTF16_FILTER
+        U8 *news;
+#endif
+        s+=2;
+        if (*s == 0 && s[1] == 0)  /* UTF-32 little-endian */
+            Perl_croak(aTHX_ "Unsupported script encoding");
+#ifdef PERL_UTF16_FILTER
+        filter_add(S_utf16rev_textfilter, NULL);
+        New(898, news, (PL_bufend - s) * 3 / 2 + 1, U8);
+        PL_bufend = utf16_to_utf8((U16*)s, news, PL_bufend - s);
+        s = news;
+#else
+        Perl_croak(aTHX_ "Unsupported script encoding");
+#endif
+    }
+    break;
+
+    case -2:
+    if ((s[1] & 255) == 255) {   /* UTF-16 big-endian */
+#ifdef PERL_UTF16_FILTER
+        U8 *news;
+        filter_add(S_utf16_textfilter, NULL);
+        New(898, news, (PL_bufend - s) * 3 / 2 + 1, U8);
+        PL_bufend = utf16_to_utf8((U16*)s, news, PL_bufend - s);
+        s = news;
+#else
+        Perl_croak(aTHX_ "Unsupported script encoding");
+#endif
+   }
+   break;
+
+   case -17:
+   if ( slen>2 && (s[1] & 255) == 187 && (s[2] & 255) == 191) {
+        s+=3;                      /* UTF-8 */
+   }
+   break;
+   case 0:
+   if (slen > 3 && s[1] == 0 &&  /* UTF-32 big-endian */
+       s[2] & 255 == 254 && s[3] & 255 == 255)
+       Perl_croak(aTHX_ "Unsupported script encoding");
+} 
+return s;
+}