[pull] master from ruby:master

NEWS.md

@@ -222,7 +222,7 @@ They are still available on rubygems.org and can be installed with
   * 3.7.5 to [3.7.6][test-unit-3.7.6], [3.7.7][test-unit-3.7.7], [3.7.8][test-unit-3.7.8]
 * rss 0.3.3
   * 0.3.2 to [0.3.3][rss-0.3.3]
-* net-imap 0.6.6
+* net-imap 0.6.7
   * 0.6.2 to [v0.6.3][net-imap-v0.6.3], [v0.6.4][net-imap-v0.6.4], [v0.6.4.1][net-imap-v0.6.4.1], [v0.6.5][net-imap-v0.6.5], [v0.6.6][net-imap-v0.6.6]
 * rbs 4.2.0
   * 3.10.0 to [v3.10.1][rbs-v3.10.1], [v3.10.2][rbs-v3.10.2], [v3.10.3][rbs-v3.10.3], [v3.10.4][rbs-v3.10.4], [v4.0.0.dev.1][rbs-v4.0.0.dev.1], [v4.0.0.dev.2][rbs-v4.0.0.dev.2], [v4.0.0.dev.3][rbs-v4.0.0.dev.3], [v4.0.0.dev.4][rbs-v4.0.0.dev.4], [v4.0.0.dev.5][rbs-v4.0.0.dev.5], [v4.0.0][rbs-v4.0.0], [v4.0.1.dev.1][rbs-v4.0.1.dev.1], [v4.0.1.dev.2][rbs-v4.0.1.dev.2], [v4.0.1][rbs-v4.0.1], [v4.0.2][rbs-v4.0.2], [v4.0.3][rbs-v4.0.3], [v4.1.0.pre.1][rbs-v4.1.0.pre.1], [v4.1.0.pre.2][rbs-v4.1.0.pre.2], [v4.1.0][rbs-v4.1.0], [v4.1.1.pre.1][rbs-v4.1.1.pre.1], [v4.1.1][rbs-v4.1.1], [v4.1.2][rbs-v4.1.2], [v4.1.3][rbs-v4.1.3], [v4.2.0.pre.1][rbs-v4.2.0.pre.1], [v4.2.0][rbs-v4.2.0]

gc/mmtk/mmtk.c

@@ -1054,6 +1054,10 @@ rb_gc_impl_new_obj(void *objspace_ptr, void *cache_ptr, VALUE klass, VALUE flags
     alloc_obj[0] = flags;
     alloc_obj[1] = klass;
 
+    if (RB_UNLIKELY(!wb_protected)) {
+        mmtk_register_wb_unprotected_object((MMTk_ObjectReference)alloc_obj);
+    }
+
     if (semantics == MMTK_ALLOCATION_SEMANTICS_LOS || ractor_cache->bump_pointer == NULL) {
         mmtk_post_alloc(ractor_cache->mutator, (void*)alloc_obj, total_size, semantics);
     }
@@ -1741,16 +1745,18 @@ rb_gc_impl_stat_heap(void *objspace_ptr, VALUE heap_name, VALUE hash_or_sym)
 
 // Miscellaneous
 
-#define RB_GC_OBJECT_METADATA_ENTRY_COUNT 1
+#define RB_GC_OBJECT_METADATA_ENTRY_COUNT 2
 static struct rb_gc_object_metadata_entry object_metadata_entries[RB_GC_OBJECT_METADATA_ENTRY_COUNT + 1];
 
 struct rb_gc_object_metadata_entry *
 rb_gc_impl_object_metadata(void *objspace_ptr, VALUE obj)
 {
+    static ID ID_wb_protected;
     static ID ID_object_id;
 
     if (!ID_object_id) {
 #define I(s) ID_##s = rb_intern(#s);
+        I(wb_protected);
         I(object_id);
 #undef I
     }
@@ -1764,6 +1770,7 @@ rb_gc_impl_object_metadata(void *objspace_ptr, VALUE obj)
     n++; \
 } while (0)
 
+    if (!mmtk_object_wb_unprotected_p((MMTk_ObjectReference)obj)) SET_ENTRY(wb_protected, Qtrue);
     if (rb_obj_id_p(obj)) SET_ENTRY(object_id, rb_obj_id(obj));
 
     object_metadata_entries[n].name = 0;

gems/bundled_gems

@@ -12,7 +12,7 @@ rake                13.4.2  https://github.com/ruby/rake
 test-unit           3.7.8   https://github.com/test-unit/test-unit
 rexml               3.4.4   https://github.com/ruby/rexml
 rss                 0.3.3   https://github.com/ruby/rss
-net-imap            0.6.6   https://github.com/ruby/net-imap
+net-imap            0.6.7   https://github.com/ruby/net-imap
 net-smtp            0.5.1   https://github.com/ruby/net-smtp
 matrix              0.4.3   https://github.com/ruby/matrix
 prime               0.1.4   https://github.com/ruby/prime

io_buffer.c

@@ -1158,6 +1158,8 @@ io_buffer_validate_for_writing(struct rb_io_buffer *buffer)
 static struct rb_io_buffer *
 get_io_buffer_for_writing(VALUE self)
 {
+    rb_check_frozen(self);
+
     struct rb_io_buffer *buffer = get_io_buffer(self);
     io_buffer_validate_for_writing(buffer);
     return buffer;
@@ -3302,7 +3304,7 @@ io_buffer_set_string(int argc, VALUE *argv, VALUE self)
 {
     rb_check_arity(argc, 1, 4);
 
-    struct rb_io_buffer *buffer = get_io_buffer(self);
+    struct rb_io_buffer *buffer = get_io_buffer_for_writing(self);
 
     VALUE string = rb_str_to_str(argv[0]);
 
@@ -3317,7 +3319,7 @@ io_buffer_set_string(int argc, VALUE *argv, VALUE self)
 void
 rb_io_buffer_clear(VALUE self, uint8_t value, size_t offset, size_t length)
 {
-    struct rb_io_buffer *buffer = get_io_buffer(self);
+    struct rb_io_buffer *buffer = get_io_buffer_for_writing(self);
 
     void *base;
     size_t size;
@@ -3472,10 +3474,10 @@ io_buffer_read_internal(void *_argument)
 VALUE
 rb_io_buffer_read(VALUE self, VALUE io, size_t offset, size_t length)
 {
+    struct rb_io_buffer *buffer = get_io_buffer_for_writing(self);
+
     io = rb_io_get_io(io);
 
-    struct rb_io_buffer *buffer = get_io_buffer(self);
-    io_buffer_validate_for_writing(buffer);
     io_buffer_validate_range(buffer, offset, length);
 
     if (length == 0) return SIZET2NUM(0);
@@ -3563,10 +3565,10 @@ io_buffer_pread_internal(void *_argument)
 VALUE
 rb_io_buffer_pread(VALUE self, VALUE io, rb_off_t from, size_t offset, size_t length)
 {
+    struct rb_io_buffer *buffer = get_io_buffer_for_writing(self);
+
     io = rb_io_get_io(io);
 
-    struct rb_io_buffer *buffer = get_io_buffer(self);
-    io_buffer_validate_for_writing(buffer);
     io_buffer_validate_range(buffer, offset, length);
 
     if (length == 0) return SIZET2NUM(0);
@@ -4032,7 +4034,7 @@ memory_and_inplace(unsigned char * restrict base, size_t size, unsigned char * r
 static VALUE
 io_buffer_and_inplace(VALUE self, VALUE mask)
 {
-    struct rb_io_buffer *buffer = get_io_buffer(self);
+    struct rb_io_buffer *buffer = get_io_buffer_for_writing(self);
 
     struct rb_io_buffer *mask_buffer = get_io_buffer(mask);
 
@@ -4080,7 +4082,7 @@ memory_or_inplace(unsigned char * restrict base, size_t size, unsigned char * re
 static VALUE
 io_buffer_or_inplace(VALUE self, VALUE mask)
 {
-    struct rb_io_buffer *buffer = get_io_buffer(self);
+    struct rb_io_buffer *buffer = get_io_buffer_for_writing(self);
 
     struct rb_io_buffer *mask_buffer = get_io_buffer(mask);
 
@@ -4128,7 +4130,7 @@ memory_xor_inplace(unsigned char * restrict base, size_t size, unsigned char * r
 static VALUE
 io_buffer_xor_inplace(VALUE self, VALUE mask)
 {
-    struct rb_io_buffer *buffer = get_io_buffer(self);
+    struct rb_io_buffer *buffer = get_io_buffer_for_writing(self);
 
     struct rb_io_buffer *mask_buffer = get_io_buffer(mask);
 
@@ -4176,7 +4178,7 @@ memory_not_inplace(unsigned char * restrict base, size_t size)
 static VALUE
 io_buffer_not_inplace(VALUE self)
 {
-    struct rb_io_buffer *buffer = get_io_buffer(self);
+    struct rb_io_buffer *buffer = get_io_buffer_for_writing(self);
 
     void *base;
     size_t size;

spec/ruby/core/kernel/require_spec.rb

@@ -33,15 +33,16 @@
     when "jruby"
       features -= %w[java.rb jruby/util.rb]
     when "ruby"
-      so = RbConfig::CONFIG['DLEXT']
-      features.reject! { |feature| feature.end_with?("windows_1252.#{so}", "windows_31j.#{so}") }
-      features.reject! { |feature| feature.end_with? "encdb.#{so}" }
-      features.reject! { |feature| feature.end_with? "transdb.#{so}" }
-      features.reject! { |feature| feature.include?('-fake') }
+      # remove all external libraries first
+      features.reject! { |feature| File.absolute_path?(feature) }
+
+      # for statically-linked ruby
+      features -= [ "encdb.so", "trans/transdb.so" ] # the suffixes are always ".so"
+      features.reject! { |feature| feature.start_with?("enc/") } # and "enc/trans/"
     end
 
-    features_no_ext = features.map { |path| File.basename(path, '.*') }
-    features_no_ext.sort.should == provided.sort
+    features_no_ext = features.map { |path| path.sub(/\.(?:rb|so)\z/, '') }
+    features_no_ext.sort.uniq.should == provided.sort
 
     requires = features
     code = requires.map { |f| "puts require #{f.inspect}\n" }.join

spec/ruby/core/string/tr_spec.rb

@@ -32,6 +32,11 @@
     "hello".tr("a-z", "A-H.").should == "HE..."
   end
 
+  it "raises an ArgumentError when the receiver has broken encoding" do
+    -> { "\xFF".tr("€", "b") }.should.raise(ArgumentError)
+    -> { "\xFF".tr("", "") }.should.raise(ArgumentError)
+  end
+
   it "raises an ArgumentError when given wrong number of arguments" do
     -> { "hello".tr }.should.raise(ArgumentError)
     ruby_version_is ""..."4.1" do
@@ -141,6 +146,10 @@
         "h€llø".tr("€" => "e", "ø" => "o").should == "hello"
       end
 
+      it "returns a copy of self if the translation hash is empty" do
+        "hello".tr({}).should == "hello"
+      end
+
       it "returns a string in the combined encoding" do
         str = "hello".encode(Encoding::US_ASCII).tr("e" => "é")
         str.should == "héllo"
@@ -160,6 +169,11 @@
         ).should == "hello".encode(Encoding::UTF_16LE)
       end
 
+      it "raises ArgumentError the string encoding is broken" do
+        -> { "\xFF".tr("€" => "b") }.should.raise(ArgumentError)
+        -> { "\xFF".tr({}) }.should.raise(ArgumentError)
+      end
+
       it "raises ArgumentError if a key is more than one codepoint" do
         -> { "hello".tr("hel" => "") }.should.raise(ArgumentError)
         -> { "🤦🏼‍♂️".tr("🤦🏼‍♂️" => "") }.should.raise(ArgumentError)
@@ -231,7 +245,18 @@
       end
 
       it "returns nil if the string wasn't modified" do
-        "hello".tr!("€" => "", "Ø" => "").should == nil
+        s = "hello"
+        s.tr!({}).should == nil
+        s.should == "hello"
+
+        s = "hello"
+        s.tr!("€" => "", "Ø" => "").should == nil
+        s.should == "hello"
+      end
+
+      it "raises ArgumentError the string encoding is broken" do
+        -> { "\xFF".tr!("€" => "b") }.should.raise(ArgumentError)
+        -> { "\xFF".tr!({}) }.should.raise(ArgumentError)
       end
 
       it "raises ArgumentError if a key is more than one codepoint" do

string.c

@@ -9362,7 +9362,7 @@ tr_trans_pairs_search_sse2(struct tr_trans_pairs_search *search)
                 matches[i] = _mm_cmpeq_epi8(bytes, masks[i]);
             }
 
-            for (i = i; i < search->needles_count; i++) {
+            for (i = 1; i < search->needles_count; i++) {
                 matches[0] = _mm_or_si128(matches[0], matches[i]);
             }
 
@@ -9427,7 +9427,7 @@ tr_trans_pairs_search_neon(struct tr_trans_pairs_search *search)
                     matches[i] = vceqq_u8(bytes, masks[i]);
                 }
 
-                for (i = i; i < search->needles_count; i++) {
+                for (i = 1; i < search->needles_count; i++) {
                     matches[0] = vorrq_u8(matches[0], matches[i]);
                 }
 
@@ -9457,6 +9457,7 @@ tr_trans_pairs(VALUE str, VALUE pairs_val)
 {
     Check_Type(pairs_val, T_HASH);
     size_t pairs_count = RHASH_SIZE(pairs_val);
+    mustnot_broken(str);
     rb_str_modify(str);
 
     if (RSTRING_LEN(str) == 0 || !RSTRING_PTR(str) || pairs_count == 0) return Qnil;
@@ -9486,6 +9487,7 @@ tr_trans_pairs(VALUE str, VALUE pairs_val)
     bool modify = false;
 
     if (RB_LIKELY(rb_str_encindex_fastpath(rb_enc_to_index(e1)))) {
+
         struct tr_trans_pairs_search search = {
             .s = sstart,
             .send = sstart + str_len,
@@ -9609,6 +9611,10 @@ tr_trans_pairs(VALUE str, VALUE pairs_val)
         }
     }
 
+    if (!modify) {
+        return Qnil;
+    }
+
     if (!STR_EMBED_P(str)) {
         SIZED_FREE_N(STR_HEAP_PTR(str), STR_HEAP_SIZE(str));
     }
@@ -9621,13 +9627,10 @@ tr_trans_pairs(VALUE str, VALUE pairs_val)
 
     RB_GC_GUARD(hash);
 
-    if (modify) {
-        if (cr != ENC_CODERANGE_BROKEN)
-            ENC_CODERANGE_SET(str, cr);
-        rb_enc_associate(str, e1);
-        return str;
-    }
-    return Qnil;
+    if (cr != ENC_CODERANGE_BROKEN)
+        ENC_CODERANGE_SET(str, cr);
+    rb_enc_associate(str, e1);
+    return str;
 }
 
 /*
@@ -9661,9 +9664,24 @@ rb_str_tr_bang(int argc, VALUE *argv, VALUE str)
 /*
  *  call-seq:
  *    tr(selector, replacements) -> new_string
+ *    tr(pairs) -> new_string
+ *
+ *  Accepts either a +selector+ and a +replacements+ string,
+ *  or a single +pairs+ Hash.
+ *
+ *  When a +pairs+ Hash is provided the keys, returns a copy of +self+ with
+ *  the keys of the hash replaced by the values.
+ *
+ *  - They keys must be strings containing a single codepoints.
+ *  - The values can be of any length.
  *
- *  Returns a copy of +self+ with each character specified by string +selector+
- *  translated to the corresponding character in string +replacements+.
+ *  Example:
+ *
+ *    'hello'.tr('e' => 'er', 'l' => '', 'o' => 'o !') #=> "hero !"
+ *
+ *  When +selector+ and +replacements+are provided, returns a copy of +self+
+ *  with each character specified by string +selector+ translated to the
+ *  corresponding character in string +replacements+.
  *  The correspondence is _positional_:
  *
  *  - Each occurrence of the first character specified by +selector+
@@ -9704,7 +9722,9 @@ rb_str_tr(int argc, VALUE *argv, VALUE str)
 
     if (argc == 1) {
         VALUE pairs = argv[0];
-        return tr_trans_pairs(str, pairs);
+        VALUE result = tr_trans_pairs(str, pairs);
+        if (NIL_P(result)) result = str;
+        return str;
     }
 
     VALUE src = argv[0], repl = argv[1];

test/.excludes-mmtk/TestObjSpace.rb

@@ -1,6 +1,5 @@
 exclude(:test_dump_all_full, "testing behaviour specific to default GC")
 exclude(:test_dump_flag_age, "testing behaviour specific to default GC")
 exclude(:test_dump_flags, "testing behaviour specific to default GC")
-exclude(:test_dump_flags_wb_protected, "testing behaviour specific to default GC")
 exclude(:test_dump_objects_dumps_page_slot_sizes, "testing behaviour specific to default GC")
 exclude(:test_trace_object_allocations_does_not_reuse_freed_allocation_info, "hang up")

test/ruby/test_io_buffer.rb

@@ -838,6 +838,30 @@ def test_transfer_frozen_external
     assert_equal string, buffer.get_string
   end
 
+  def test_write_frozen
+    buffer = IO::Buffer.new(8)
+    buffer.freeze
+
+    mask = IO::Buffer.new(8)
+
+    assert_raise(FrozenError) {buffer.set_string("x")}
+    assert_raise(FrozenError) {buffer.copy(IO::Buffer.new(8))}
+    assert_raise(FrozenError) {buffer.clear}
+    assert_raise(FrozenError) {buffer.set_value(:U8, 0, 1)}
+    assert_raise(FrozenError) {buffer.set_values([:U8], 0, [1])}
+    assert_raise(FrozenError) {buffer.and!(mask)}
+    assert_raise(FrozenError) {buffer.or!(mask)}
+    assert_raise(FrozenError) {buffer.xor!(mask)}
+    assert_raise(FrozenError) {buffer.not!}
+
+    File.open(__FILE__) do |file|
+      assert_raise(FrozenError) {buffer.read(file)}
+      assert_raise(FrozenError) {buffer.pread(file, 0)}
+    end
+
+    assert_equal "\0" * 8, buffer.get_string
+  end
+
   def test_counted_locking
     buffer = IO::Buffer.new(128)
 

test/ruby/test_string.rb

@@ -2687,6 +2687,8 @@ def test_tr_hash
     assert_equal S(("A"*16 + "x" + "B"*3)), S(("A"*16  + "<" + "B"*3)).tr({"<"=>"x"})
     assert_equal S(("x"+"A"*16 + "B"*3)), S(("<"+"A"*16 + "B"*3)).tr({"<"=>"x"})
     assert_equal S(("."*15 + "<" * 17)), S(("."*15  + "x"*17)).tr({"x"=>"<"})
+
+    assert_equal(S("01@3456789abcdefgHij"), S("0123456789abcdefghij").tr("h" => "H", "2" => "@"))
   end
 
   def test_tr!