implement String/Symbol#casecmp? including Unicode case folding

* string.c: Implement String#casecmp? and Symbol#casecmp? by using
  String#downcase :fold for Unicode case folding. This does not include
  options such as :turkic, because these currently cannot be combined
  with the :fold option. This implements feature #12786.

* test/ruby/test_string.rb/test_symbol.rb: Tests for above.

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@56912 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

string.c

@@ -3194,6 +3194,40 @@ rb_str_casecmp(VALUE str1, VALUE str2)
     return INT2FIX(-1);
 }
 
+/*
+ *  call-seq:
+ *     str.casecmp?(other_str)   -> true, false, or nil
+ *
+ *  Returns true if str and other_other_str are equal after Unicode case folding,
+ *  false if they are not equal, and nil if other_str is not a string.
+ *
+ *     "abcdef".casecmp("abcde")     #=> false
+ *     "aBcDeF".casecmp("abcdef")    #=> true
+ *     "abcdef".casecmp("abcdefg")   #=> false
+ *     "abcdef".casecmp("ABCDEF")    #=> true
+ */
+
+
+static VALUE rb_str_downcase(int argc, VALUE *argv, VALUE str);  /* forward declaration */
+static VALUE
+rb_str_casecmp_p(VALUE str1, VALUE str2)
+{
+    rb_encoding *enc;
+    VALUE folded_str1, folded_str2;
+    VALUE fold_opt = sym_fold;
+
+    StringValue(str2);
+    enc = rb_enc_compatible(str1, str2);
+    if (!enc) {
+	return Qnil;
+    }
+
+    folded_str1 = rb_str_downcase(1, &fold_opt, str1);
+    folded_str2 = rb_str_downcase(1, &fold_opt, str2);
+
+    return rb_str_eql(folded_str1, folded_str2);
+}
+
 #define rb_str_index(str, sub, offset) rb_strseq_index(str, sub, offset, 0)
 
 static long
@@ -9615,6 +9649,24 @@ sym_casecmp(VALUE sym, VALUE other)
     return rb_str_casecmp(rb_sym2str(sym), rb_sym2str(other));
 }
 
+/*
+ * call-seq:
+ *
+ *   sym.casecmp?(other)  -> true, false, or nil
+ *
+ * Returns true if sym and other are equal after Unicode case folding,
+ * false if they are not equal, and nil if other is not a symbol.
+ */
+
+static VALUE
+sym_casecmp_p(VALUE sym, VALUE other)
+{
+    if (!SYMBOL_P(other)) {
+	return Qnil;
+    }
+    return rb_str_casecmp_p(rb_sym2str(sym), rb_sym2str(other));
+}
+
 /*
  * call-seq:
  *   sym =~ obj   -> integer or nil
@@ -9814,6 +9866,7 @@ Init_String(void)
     rb_define_method(rb_cString, "eql?", rb_str_eql, 1);
     rb_define_method(rb_cString, "hash", rb_str_hash_m, 0);
     rb_define_method(rb_cString, "casecmp", rb_str_casecmp, 1);
+    rb_define_method(rb_cString, "casecmp?", rb_str_casecmp_p, 1);
     rb_define_method(rb_cString, "+", rb_str_plus, 1);
     rb_define_method(rb_cString, "*", rb_str_times, 1);
     rb_define_method(rb_cString, "%", rb_str_format_m, 1);
@@ -9963,6 +10016,7 @@ Init_String(void)
 
     rb_define_method(rb_cSymbol, "<=>", sym_cmp, 1);
     rb_define_method(rb_cSymbol, "casecmp", sym_casecmp, 1);
+    rb_define_method(rb_cSymbol, "casecmp?", sym_casecmp_p, 1);
     rb_define_method(rb_cSymbol, "=~", sym_match, 1);
 
     rb_define_method(rb_cSymbol, "[]", sym_aref, -1);

test/ruby/test_string.rb

@@ -2210,6 +2210,13 @@ CODE
     assert_equal(1, "\u3042B".casecmp("\u3042a"))
   end
 
+  def test_casecmp?
+    assert_equal(true, 'FoO'.casecmp?('fOO'))
+    assert_equal(false, 'FoO'.casecmp?('BaR'))
+    assert_equal(false, 'baR'.casecmp?('FoO'))
+    assert_equal(true, 'äöü'.casecmp?('ÄÖÜ'))
+  end
+
   def test_upcase2
     assert_equal("\u3042AB", "\u3042aB".upcase)
   end

test/ruby/test_symbol.rb

@@ -276,6 +276,14 @@ class TestSymbol < Test::Unit::TestCase
     assert_nil(:foo.casecmp("foo"))
   end
 
+  def test_casecmp?
+    assert_equal(true, :FoO.casecmp?(:fOO))
+    assert_equal(false, :FoO.casecmp?(:BaR))
+    assert_equal(false, :baR.casecmp?(:FoO))
+    assert_nil(:foo.casecmp?("foo"))
+    assert_equal(true, :äöü.casecmp?(:ÄÖÜ))
+  end
+
   def test_length
     assert_equal(3, :FoO.length)
     assert_equal(3, :FoO.size)