akr	2008-09-23 21:27:35 +0900 (Tue, 23 Sep 2008)

  New Revision: 19490

  http://svn.ruby-lang.org/cgi-bin/viewvc.cgi?view=rev&revision=19490

  Log:
    * string.c (rb_str_casecmp): make the ordering consistent with
      String#<=>.

  Modified files:
    trunk/ChangeLog
    trunk/string.c
    trunk/test/ruby/enc/test_utf16.rb

Index: ChangeLog
===================================================================
--- ChangeLog	(revision 19489)
+++ ChangeLog	(revision 19490)
@@ -1,3 +1,8 @@
+Tue Sep 23 21:26:32 2008  Tanaka Akira  <akr@f...>
+
+	* string.c (rb_str_casecmp): make the ordering consistent with
+	  String#<=>.
+
 Tue Sep 23 20:52:25 2008  Tanaka Akira  <akr@f...>
 
 	* io.c (io_binwrite): add nosync argument.
Index: string.c
===================================================================
--- string.c	(revision 19489)
+++ string.c	(revision 19490)
@@ -2105,10 +2105,10 @@
     if (single_byte_optimizable(str1) && single_byte_optimizable(str2)) {
 	while (p1 < p1end && p2 < p2end) {
 	    if (*p1 != *p2) {
-		unsigned int c1 = rb_enc_toupper(*p1 & 0xff, enc);
-		unsigned int c2 = rb_enc_toupper(*p2 & 0xff, enc);
-		if (c1 > c2) return INT2FIX(1);
-		if (c1 < c2) return INT2FIX(-1);
+		unsigned int c1 = TOUPPER(*p1 & 0xff);
+		unsigned int c2 = TOUPPER(*p2 & 0xff);
+                if (c1 != c2)
+                    return INT2FIX(c1 < c2 ? -1 : 1);
 	    }
 	    p1++;
 	    p2++;
@@ -2116,18 +2116,28 @@
     }
     else {
 	while (p1 < p1end && p2 < p2end) {
-	    unsigned int c1 = rb_enc_codepoint(p1, p1end, enc);
-	    unsigned int c2 = rb_enc_codepoint(p2, p2end, enc);
+            int l1, c1 = rb_enc_ascget(p1, p1end, &l1, enc);
+            int l2, c2 = rb_enc_ascget(p2, p2end, &l2, enc);
 
-	    if (c1 != c2) {
-		c1 = rb_enc_toupper(c1, enc);
-		c2 = rb_enc_toupper(c2, enc);
-		if (c1 > c2) return INT2FIX(1);
-		if (c1 < c2) return INT2FIX(-1);
-	    }
-	    len = rb_enc_codelen(c1, enc);
-	    p1 += len;
-	    p2 += len;
+            if (0 <= c1 && 0 <= c2) {
+                c1 = TOUPPER(c1);
+                c2 = TOUPPER(c2);
+                if (c1 != c2)
+                    return INT2FIX(c1 < c2 ? -1 : 1);
+            }
+            else {
+                int r;
+                l1 = rb_enc_mbclen(p1, p1end, enc);
+                l2 = rb_enc_mbclen(p2, p2end, enc);
+                len = l1 < l2 ? l1 : l2;
+                r = memcmp(p1, p2, len);
+                if (r != 0)
+                    return INT2FIX(r < 0 ? -1 : 1);
+                if (l1 != l2)
+                    return INT2FIX(l1 < l2 ? -1 : 1);
+            }
+	    p1 += l1;
+	    p2 += l2;
 	}
     }
     if (RSTRING_LEN(str1) == RSTRING_LEN(str2)) return INT2FIX(0);
Index: test/ruby/enc/test_utf16.rb
===================================================================
--- test/ruby/enc/test_utf16.rb	(revision 19489)
+++ test/ruby/enc/test_utf16.rb	(revision 19490)
@@ -368,4 +368,17 @@
     r = Regexp.new(Regexp.escape(s))
     assert(r =~ s, "#{encdump(r)} =~ #{encdump(s)}")
   end
+
+  def test_casecmp
+    assert_equal(0, "\0A".force_encoding("UTF-16BE").casecmp("\0a".force_encoding("UTF-16BE")))
+    assert_not_equal(0, "\0A".force_encoding("UTF-16LE").casecmp("\0a".force_encoding("UTF-16LE")))
+    assert_not_equal(0, "A\0".force_encoding("UTF-16BE").casecmp("a\0".force_encoding("UTF-16BE")))
+    assert_equal(0, "A\0".force_encoding("UTF-16LE").casecmp("a\0".force_encoding("UTF-16LE")))
+
+    ary = ["01".force_encoding("UTF-16LE"),
+           "10".force_encoding("UTF-16LE")]
+    e = ary.sort {|x,y| x <=> y }
+    a = ary.sort {|x,y| x.casecmp(y) }
+    assert_equal(e, a)
+  end
 end

--
ML: ruby-changes@q...
Info: http://www.atdot.net/~ko1/quickml/