X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=utf8.c;h=c6276c7b739c87f869e653e53c1e4d64ed394301;hb=91f668c3f8088a8ade9864ff2621af073dcb5766;hp=6f201a23f1dfccf1c058567390765e7318bc451b;hpb=71bed85a8e466f6c3e557b1ecdc84ea0b18975ee;p=p5sagit%2Fp5-mst-13.2.git

diff --git a/utf8.c b/utf8.c
index 6f201a2..c6276c7 100644
--- a/utf8.c
+++ b/utf8.c
@@ -29,6 +29,12 @@ static char unees[] = "Malformed UTF-8 character (unexpected end of string)";
 /* 
 =head1 Unicode Support
 
+This file contains various utility functions for manipulating UTF8-encoded
+strings. For the uninitiated, this is a method of representing arbitrary
+Unicode characters as a variable number of bytes, in such a way that
+characters in the ASCII range are unmodified, and a zero byte never appears
+within non-zero characters.
+
 =for apidoc A|U8 *|uvuni_to_utf8_flags|U8 *d|UV uv|UV flags
 
 Adds the UTF-8 representation of the Unicode codepoint C<uv> to the end
@@ -232,7 +238,7 @@ Perl_is_utf8_string(pTHX_ U8 *s, STRLEN len)
     U8* send;
     STRLEN c;
 
-    if (!len)
+    if (!len && s)
 	len = strlen((char *)s);
     send = s + len;
 
@@ -272,7 +278,7 @@ Perl_is_utf8_string_loc(pTHX_ U8 *s, STRLEN len, U8 **p)
     U8* send;
     STRLEN c;
 
-    if (!len)
+    if (!len && s)
 	len = strlen((char *)s);
     send = s + len;
 
@@ -426,7 +432,7 @@ Perl_utf8n_to_uvuni(pTHX_ U8 *s, STRLEN curlen, STRLEN *retlen, U32 flags)
 	if (!(uv > ouv)) {
 	    /* These cannot be allowed. */
 	    if (uv == ouv) {
-		if (!(flags & UTF8_ALLOW_LONG)) {
+		if (expectlen != 13 && !(flags & UTF8_ALLOW_LONG)) {
 		    warning = UTF8_WARN_LONG;
 		    goto malformed;
 		}
@@ -862,8 +868,14 @@ Perl_utf16_to_utf8(pTHX_ U8* p, U8* d, I32 bytelen, I32 *newlen)
     U8* pend;
     U8* dstart = d;
 
+    if (bytelen == 1 && p[0] == 0) { /* Be understanding. */
+	 d[0] = 0;
+	 *newlen = 1;
+	 return d;
+    }
+
     if (bytelen & 1)
-	Perl_croak(aTHX_ "panic: utf16_to_utf8: odd bytelen");
+	Perl_croak(aTHX_ "panic: utf16_to_utf8: odd bytelen %d", bytelen);
 
     pend = p + bytelen;
 
@@ -1916,7 +1928,7 @@ If the pe1 and pe2 are non-NULL, the scanning pointers will be copied
 in there (they will point at the beginning of the I<next> character).
 If the pointers behind pe1 or pe2 are non-NULL, they are the end
 pointers beyond which scanning will not continue under any
-circustances.  If the byte lengths l1 and l2 are non-zero, s1+l1 and
+circumstances.  If the byte lengths l1 and l2 are non-zero, s1+l1 and
 s2+l2 will be used as goal end pointers that will also stop the scan,
 and which qualify towards defining a successful match: all the scans
 that define an explicit length must reach their goal pointers for