diff options
author | akr <akr@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2008-09-23 12:27:35 +0000 |
---|---|---|
committer | akr <akr@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2008-09-23 12:27:35 +0000 |
commit | e7e5b731c2033b337f4e2c9ac373f67e132694a0 (patch) | |
tree | e096f4cd38c5e0a09a0bbfe85d0f38a5a7e37fa4 | |
parent | 55783c696d97082f9163e1c6cc8241998f27b48d (diff) | |
download | ruby-e7e5b731c2033b337f4e2c9ac373f67e132694a0.tar.gz |
* string.c (rb_str_casecmp): make the ordering consistent with
String#<=>.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@19490 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
-rw-r--r-- | ChangeLog | 5 | ||||
-rw-r--r-- | string.c | 42 | ||||
-rw-r--r-- | test/ruby/enc/test_utf16.rb | 13 |
3 files changed, 44 insertions, 16 deletions
@@ -1,3 +1,8 @@ +Tue Sep 23 21:26:32 2008 Tanaka Akira <akr@fsij.org> + + * string.c (rb_str_casecmp): make the ordering consistent with + String#<=>. + Tue Sep 23 20:52:25 2008 Tanaka Akira <akr@fsij.org> * io.c (io_binwrite): add nosync argument. @@ -2105,10 +2105,10 @@ rb_str_casecmp(VALUE str1, VALUE str2) 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 @@ rb_str_casecmp(VALUE str1, VALUE str2) } else { while (p1 < p1end && p2 < p2end) { - unsigned int c1 = rb_enc_codepoint(p1, p1end, enc); - unsigned int c2 = rb_enc_codepoint(p2, p2end, 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; + int l1, c1 = rb_enc_ascget(p1, p1end, &l1, enc); + int l2, c2 = rb_enc_ascget(p2, p2end, &l2, enc); + + 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); diff --git a/test/ruby/enc/test_utf16.rb b/test/ruby/enc/test_utf16.rb index 30dbb2e886..c949c1e293 100644 --- a/test/ruby/enc/test_utf16.rb +++ b/test/ruby/enc/test_utf16.rb @@ -368,4 +368,17 @@ EOT 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 |