PATCH: more sorting: multibyte case-insensitivity

[Peter Stephenson <pws@xxxxxxx>]

This extends the new sort code to handle lowering of case properly with
multibyte characters.  The locales (other than C) that I've seen mostly
seem to force case insensitivity within collate() anyway, but we might as
well do this properly.

Index: Src/sort.c
===================================================================
RCS file: /cvsroot/zsh/zsh/Src/sort.c,v
retrieving revision 1.1
diff -u -r1.1 sort.c
--- Src/sort.c	21 Jan 2007 22:47:41 -0000	1.1
+++ Src/sort.c	22 Jan 2007 14:20:58 -0000
@@ -248,7 +248,8 @@
 	    || *metaptr == Meta) {
 	    char *s, *t, *src = *arrptr, *dst;
 	    int len;
-	    sortarrptr->cmp = dst = (char *)zhalloc(strlen(src) + 1);
+	    sortarrptr->cmp = dst =
+		(char *)zhalloc(((sortwhat & SORTIT_IGNORING_CASE)?2:1)*strlen(src)+1);
 
 	    if (unmetalenp) {
 		/* Already unmetafied and we have the length. */
@@ -283,8 +284,49 @@
 		len = metaptr - src;
 	    }
 	    if (sortwhat & SORTIT_IGNORING_CASE) {
-		for (s = src, t = dst; s - src != len; )
-		    *t++ = tulower(*s++);
+		char *send = src + len;
+#ifdef MULTIBYTE_SUPPORT
+		if (isset(MULTIBYTE)) {
+		    /*
+		     * Lower the case the hard way.  Convert to a wide
+		     * character, process that, and convert back.  We
+		     * don't assume the characters have the same
+		     * multibyte length.  We can't use casemodify()
+		     * because we have unmetafied data, which may have
+		     * been passed down to use.
+		     */
+		    mbstate_t mbsin, mbsout;
+		    int clen;
+		    wchar_t wc;
+		    memset(&mbsin, 0, sizeof(mbstate_t));
+		    memset(&mbsout, 0, sizeof(mbstate_t));
+
+		    for (s = src, t = dst; s < send; ) {
+			clen = mbrtowc(&wc, s, send-s, &mbsin);
+			if (clen < 0) {
+			    /* invalid or unfinished: treat as single bytes */
+			    while (s < send)
+				*t++ = tulower(*s++);
+			    break;
+			}
+			if (clen == 0) {
+			    /* embedded null */
+			    *t++ = '\0';
+			    s++;
+			    continue;
+			}
+			s += clen;
+			wc = towlower(wc);
+			clen = wcrtomb(t, wc, &mbsout);
+			t += clen;
+			DPUTS(clen < 0, "Bad conversion when lowering case");
+		    }
+		    *t = '\0';
+		    len = t - dst;
+		} else
+#endif
+		    for (s = src, t = dst; s < send; )
+			*t++ = tulower(*s++);
 		src = dst;
 	    }
 	    if (sortwhat & SORTIT_IGNORING_BACKSLASHES) {
Index: Test/B03print.ztst
===================================================================
RCS file: /cvsroot/zsh/zsh/Test/B03print.ztst,v
retrieving revision 1.18
diff -u -r1.18 B03print.ztst
--- Test/B03print.ztst	21 Jan 2007 22:47:42 -0000	1.18
+++ Test/B03print.ztst	22 Jan 2007 14:20:58 -0000
@@ -34,7 +34,12 @@
 >baz
 >bar
 
- print -io a B c
+# some locales 
+ (LC_ALL=C; print -o a B c)
+0:case-sensitive argument sorting
+>B a c
+
+ (LC_ALL=C; print -io a B c)
 0:case-insensitive argument sorting
 >a B c
 
Index: Test/D07multibyte.ztst
===================================================================
RCS file: /cvsroot/zsh/zsh/Test/D07multibyte.ztst,v
retrieving revision 1.13
diff -u -r1.13 D07multibyte.ztst
--- Test/D07multibyte.ztst	9 Jan 2007 21:45:45 -0000	1.13
+++ Test/D07multibyte.ztst	22 Jan 2007 14:20:58 -0000
@@ -2,6 +2,8 @@
 
 # Find a UTF-8 locale.
   setopt multibyte
+# Don't let LC_* override our choice of locale.
+  unset -m LC_\*
   mb_ok=
   langs=(en_US.UTF-8 en_GB.UTF-8 en.UTF-8
 	 $(locale -a 2>/dev/null | sed -e 's/utf8/UTF-8/' | grep UTF-8))
@@ -315,3 +317,12 @@
   printf "%4.3s\n" fÅ?obar
 0:Multibyte characters in printf widths
 > fÅ?o
+
+# We ask for case-insensitive sorting here (and supply upper case
+# characters) so that we exercise the logic in the shell that lowers the
+# case of the string for case-insensitive sorting.
+  print -oi HAH HUH HEH HÃ?H HÃ?H
+  (LC_ALL=C; print -oi HAH HUH HEH HÃ?H HÃ?H)
+0:Multibyte characters in print sorting
+>HAH HEH HÃ?H HÃ?H HUH
+>HAH HEH HUH HÃ?H HÃ?H

-- 
Peter Stephenson <pws@xxxxxxx>                  Software Engineer
CSR PLC, Churchill House, Cambridge Business Park, Cowley Road
Cambridge, CB4 0WZ, UK                          Tel: +44 (0)1223 692070