merge revision(s) cd5e6cc0ea48353c88d921b885b552dc76da255c,bbf54ec334fe2edd7669a944d88d17efde49a412: [Backport #19307]

	Update to ruby/mspec@fef9b81

	---
	 spec/mspec/tool/tag_from_output.rb | 2 +-
	 1 file changed, 1 insertion(+), 1 deletion(-)

	Update to ruby/spec@9d69b95

	---
	 spec/ruby/core/array/keep_if_spec.rb               |   1 +
	 spec/ruby/core/array/pack/c_spec.rb                |  14 +-
	 spec/ruby/core/array/pack/shared/basic.rb          |  40 ++++
	 spec/ruby/core/array/pack/shared/float.rb          |  66 ++++++-
	 spec/ruby/core/array/pack/shared/integer.rb        |  96 +++++++--
	 spec/ruby/core/array/pack/shared/numeric_basic.rb  |  10 +-
	 spec/ruby/core/array/pack/shared/unicode.rb        |  14 +-
	 spec/ruby/core/array/pack/w_spec.rb                |  14 +-
	 spec/ruby/core/array/shared/unshift.rb             |  18 ++
	 spec/ruby/core/array/values_at_spec.rb             |   1 +
	 spec/ruby/core/array/zip_spec.rb                   |   6 +
	 spec/ruby/core/class/subclasses_spec.rb            |  22 +++
	 spec/ruby/core/dir/home_spec.rb                    |  44 +++--
	 spec/ruby/core/dir/mkdir_spec.rb                   |  18 +-
	 spec/ruby/core/enumerable/zip_spec.rb              |   5 +
	 spec/ruby/core/float/comparison_spec.rb            |  35 ++--
	 spec/ruby/core/float/divmod_spec.rb                |   2 +-
	 spec/ruby/core/float/gt_spec.rb                    |  21 ++
	 spec/ruby/core/float/gte_spec.rb                   |  21 ++
	 spec/ruby/core/float/lt_spec.rb                    |  21 ++
	 spec/ruby/core/float/lte_spec.rb                   |  21 ++
	 spec/ruby/core/float/shared/equal.rb               |  21 ++
	 spec/ruby/core/io/gets_spec.rb                     |   4 +
	 spec/ruby/core/io/lineno_spec.rb                   |   9 +-
	 spec/ruby/core/io/new_spec.rb                      |   2 +
	 spec/ruby/core/io/readline_spec.rb                 |   4 +
	 spec/ruby/core/io/readlines_spec.rb                |   4 +
	 spec/ruby/core/io/shared/each.rb                   |   4 +
	 spec/ruby/core/io/shared/new.rb                    |   2 +
	 spec/ruby/core/io/shared/pos.rb                    |   8 +-
	 spec/ruby/core/io/shared/readlines.rb              |   4 +
	 spec/ruby/core/io/sysseek_spec.rb                  |   2 +-
	 spec/ruby/core/kernel/shared/load.rb               |  31 ++-
	 spec/ruby/core/kernel/singleton_class_spec.rb      |   2 +
	 spec/ruby/core/marshal/dump_spec.rb                |  45 ++++-
	 spec/ruby/core/marshal/fixtures/classes.rb         |   4 +
	 spec/ruby/core/matchdata/values_at_spec.rb         |  73 ++++++-
	 spec/ruby/core/module/fixtures/classes.rb          |   1 +
	 spec/ruby/core/module/include_spec.rb              |   4 +-
	 spec/ruby/core/module/prepend_spec.rb              |  12 ++
	 .../ruby/core/objectspace/define_finalizer_spec.rb |  22 +++
	 spec/ruby/core/process/constants_spec.rb           |   1 +
	 spec/ruby/core/process/detach_spec.rb              |  29 +++
	 spec/ruby/core/process/spawn_spec.rb               |  10 +
	 spec/ruby/core/process/times_spec.rb               |   2 +-
	 spec/ruby/core/queue/initialize_spec.rb            |  13 +-
	 spec/ruby/core/refinement/import_methods_spec.rb   |  34 ++++
	 spec/ruby/core/refinement/include_spec.rb          |  27 +++
	 spec/ruby/core/refinement/prepend_spec.rb          |  27 +++
	 spec/ruby/core/regexp/initialize_spec.rb           |   2 +-
	 spec/ruby/core/signal/trap_spec.rb                 |  12 ++
	 spec/ruby/core/string/byteslice_spec.rb            |   6 +
	 spec/ruby/core/string/capitalize_spec.rb           |   4 +
	 spec/ruby/core/string/chars_spec.rb                |   7 +-
	 spec/ruby/core/string/chomp_spec.rb                |   4 +
	 spec/ruby/core/string/chop_spec.rb                 |   4 +
	 spec/ruby/core/string/clone_spec.rb                |   4 +
	 spec/ruby/core/string/delete_prefix_spec.rb        |   4 +
	 spec/ruby/core/string/delete_spec.rb               |   4 +
	 spec/ruby/core/string/delete_suffix_spec.rb        |   4 +
	 spec/ruby/core/string/downcase_spec.rb             |   4 +
	 spec/ruby/core/string/dump_spec.rb                 |  10 +-
	 spec/ruby/core/string/dup_spec.rb                  |   4 +
	 spec/ruby/core/string/lines_spec.rb                |   1 -
	 spec/ruby/core/string/reverse_spec.rb              |   4 +
	 spec/ruby/core/string/scan_spec.rb                 |   6 +
	 spec/ruby/core/string/scrub_spec.rb                |  10 +
	 spec/ruby/core/string/shared/each_line.rb          |   6 +
	 spec/ruby/core/string/shared/partition.rb          |  15 ++
	 spec/ruby/core/string/shared/slice.rb              |  13 +-
	 spec/ruby/core/string/shared/strip.rb              |   4 +
	 spec/ruby/core/string/shared/succ.rb               |   4 +
	 spec/ruby/core/string/split_spec.rb                |  17 +-
	 spec/ruby/core/string/squeeze_spec.rb              |   5 +
	 spec/ruby/core/string/swapcase_spec.rb             |   4 +
	 spec/ruby/core/string/undump_spec.rb               |   2 +-
	 spec/ruby/core/string/unpack/b_spec.rb             |  28 ++-
	 spec/ruby/core/string/unpack/c_spec.rb             |  14 +-
	 spec/ruby/core/string/unpack/h_spec.rb             |  28 ++-
	 spec/ruby/core/string/unpack/shared/basic.rb       |  28 ---
	 spec/ruby/core/string/unpack/shared/float.rb       |  60 +++++-
	 spec/ruby/core/string/unpack/shared/integer.rb     |  88 +++++++--
	 spec/ruby/core/string/unpack/shared/unicode.rb     |  14 +-
	 spec/ruby/core/string/unpack/w_spec.rb             |  14 +-
	 spec/ruby/core/string/unpack1_spec.rb              |  12 +-
	 spec/ruby/core/string/unpack_spec.rb               |  34 ++++
	 spec/ruby/core/string/upcase_spec.rb               |   4 +
	 spec/ruby/core/string/valid_encoding/utf_8_spec.rb | 214 +++++++++++++++++++++
	 spec/ruby/core/struct/values_at_spec.rb            |  55 +++++-
	 spec/ruby/core/symbol/shared/id2name.rb            |   7 +
	 spec/ruby/core/time/at_spec.rb                     |  16 ++
	 spec/ruby/core/time/localtime_spec.rb              |  16 +-
	 spec/ruby/core/time/new_spec.rb                    |  94 +++++++--
	 spec/ruby/core/time/shared/gmtime.rb               |   4 +-
	 spec/ruby/core/time/shared/time_params.rb          |  11 +-
	 spec/ruby/core/time/strftime_spec.rb               |  40 +++-
	 spec/ruby/core/time/utc_spec.rb                    |  41 +++-
	 spec/ruby/core/time/zone_spec.rb                   |  20 +-
	 spec/ruby/core/tracepoint/inspect_spec.rb          |   9 +
	 spec/ruby/fixtures/code/load_wrap_fixture.rb       |  12 ++
	 spec/ruby/fixtures/code/wrap_fixture.rb            |   9 -
	 spec/ruby/language/case_spec.rb                    |   4 +-
	 .../ruby/language/regexp/character_classes_spec.rb |   5 +
	 spec/ruby/library/coverage/running_spec.rb         |  20 ++
	 spec/ruby/library/date/civil_spec.rb               |   7 +-
	 spec/ruby/library/objectspace/fixtures/trace.rb    |   5 +
	 spec/ruby/library/objectspace/trace_spec.rb        |  15 ++
	 spec/ruby/library/openssl/x509/name/verify_spec.rb |   4 +-
	 spec/ruby/library/stringio/initialize_spec.rb      |  85 ++++++++
	 spec/ruby/library/stringio/new_spec.rb             |   8 +
	 spec/ruby/library/stringio/shared/write.rb         |  22 +++
	 spec/ruby/optional/capi/ext/io_spec.c              |  43 +++++
	 spec/ruby/optional/capi/io_spec.rb                 |  15 ++
	 spec/ruby/shared/rational/Rational.rb              |  48 ++---
	 114 files changed, 1963 insertions(+), 245 deletions(-)
	 create mode 100644 spec/ruby/core/marshal/fixtures/classes.rb
	 create mode 100644 spec/ruby/core/refinement/import_methods_spec.rb
	 create mode 100644 spec/ruby/core/refinement/include_spec.rb
	 create mode 100644 spec/ruby/core/refinement/prepend_spec.rb
	 create mode 100644 spec/ruby/core/string/unpack_spec.rb
	 create mode 100644 spec/ruby/core/string/valid_encoding/utf_8_spec.rb
	 create mode 100644 spec/ruby/fixtures/code/load_wrap_fixture.rb
	 delete mode 100644 spec/ruby/fixtures/code/wrap_fixture.rb
	 create mode 100644 spec/ruby/library/coverage/running_spec.rb
	 create mode 100644 spec/ruby/library/objectspace/fixtures/trace.rb
	 create mode 100644 spec/ruby/library/objectspace/trace_spec.rb
	 create mode 100644 spec/ruby/library/stringio/new_spec.rb

1 files changed, 214 insertions, 0 deletions

diff --git a/spec/ruby/core/string/valid_encoding/utf_8_spec.rb b/spec/ruby/core/string/valid_encoding/utf_8_spec.rb
new file mode 100644
index 0000000000..a14c3af830
--- /dev/null
+++ b/spec/ruby/core/string/valid_encoding/utf_8_spec.rb
@@ -0,0 +1,214 @@
+# -*- encoding: utf-8 -*-
+require_relative '../../../spec_helper'
+
+describe "String#valid_encoding? and UTF-8" do
+  def utf8(bytes)
+    bytes.pack("C*").force_encoding("UTF-8")
+  end
+
+  describe "1-byte character" do
+    it "is valid if is in format 0xxxxxxx" do
+      utf8([0b00000000]).valid_encoding?.should == true
+      utf8([0b01111111]).valid_encoding?.should == true
+    end
+
+    it "is not valid if is not in format 0xxxxxxx" do
+      utf8([0b10000000]).valid_encoding?.should == false
+      utf8([0b11111111]).valid_encoding?.should == false
+    end
+  end
+
+  describe "2-bytes character" do
+    it "is valid if in format [110xxxxx 10xxxxx]" do
+      utf8([0b11000010, 0b10000000]).valid_encoding?.should == true
+      utf8([0b11000010, 0b10111111]).valid_encoding?.should == true
+
+      utf8([0b11011111, 0b10000000]).valid_encoding?.should == true
+      utf8([0b11011111, 0b10111111]).valid_encoding?.should == true
+    end
+
+    it "is not valid if the first byte is not in format 110xxxxx" do
+      utf8([0b00000010, 0b10000000]).valid_encoding?.should == false
+      utf8([0b00100010, 0b10000000]).valid_encoding?.should == false
+      utf8([0b01000010, 0b10000000]).valid_encoding?.should == false
+      utf8([0b01100010, 0b10000000]).valid_encoding?.should == false
+      utf8([0b10000010, 0b10000000]).valid_encoding?.should == false
+      utf8([0b10100010, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11000010, 0b10000000]).valid_encoding?.should == true # correct bytes
+      utf8([0b11100010, 0b10000000]).valid_encoding?.should == false
+    end
+
+    it "is not valid if the second byte is not in format 10xxxxxx" do
+      utf8([0b11000010, 0b00000000]).valid_encoding?.should == false
+      utf8([0b11000010, 0b01000000]).valid_encoding?.should == false
+      utf8([0b11000010, 0b11000000]).valid_encoding?.should == false
+    end
+
+    it "is not valid if is smaller than [xxxxxx10 xx000000] (codepoints < U+007F, that are encoded with the 1-byte format)" do
+      utf8([0b11000000, 0b10111111]).valid_encoding?.should == false
+      utf8([0b11000001, 0b10111111]).valid_encoding?.should == false
+    end
+
+    it "is not valid if the first byte is missing" do
+      bytes = [0b11000010, 0b10000000]
+      utf8(bytes[1..1]).valid_encoding?.should == false
+    end
+
+    it "is not valid if the second byte is missing" do
+      bytes = [0b11000010, 0b10000000]
+      utf8(bytes[0..0]).valid_encoding?.should == false
+    end
+  end
+
+  describe "3-bytes character" do
+    it "is valid if in format [1110xxxx 10xxxxxx 10xxxxxx]" do
+      utf8([0b11100000, 0b10100000, 0b10000000]).valid_encoding?.should == true
+      utf8([0b11100000, 0b10100000, 0b10111111]).valid_encoding?.should == true
+      utf8([0b11100000, 0b10111111, 0b10111111]).valid_encoding?.should == true
+      utf8([0b11101111, 0b10111111, 0b10111111]).valid_encoding?.should == true
+    end
+
+    it "is not valid if the first byte is not in format 1110xxxx" do
+      utf8([0b00000000, 0b10100000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b00010000, 0b10100000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b00100000, 0b10100000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b00110000, 0b10100000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b01000000, 0b10100000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b01010000, 0b10100000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b01100000, 0b10100000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b01110000, 0b10100000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b10000000, 0b10100000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b10010000, 0b10100000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b10100000, 0b10100000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b10110000, 0b10100000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11000000, 0b10100000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11010000, 0b10100000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11100000, 0b10100000, 0b10000000]).valid_encoding?.should == true # correct bytes
+      utf8([0b11110000, 0b10100000, 0b10000000]).valid_encoding?.should == false
+    end
+
+    it "is not valid if the second byte is not in format 10xxxxxx" do
+      utf8([0b11100000, 0b00100000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11100000, 0b01100000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11100000, 0b11100000, 0b10000000]).valid_encoding?.should == false
+    end
+
+    it "is not valid if the third byte is not in format 10xxxxxx" do
+      utf8([0b11100000, 0b10100000, 0b00000000]).valid_encoding?.should == false
+      utf8([0b11100000, 0b10100000, 0b01000000]).valid_encoding?.should == false
+      utf8([0b11100000, 0b10100000, 0b01000000]).valid_encoding?.should == false
+    end
+
+    it "is not valid if is smaller than [xxxx0000 xx100000 xx000000] (codepoints < U+07FF that are encoded with the 2-byte format)" do
+      utf8([0b11100000, 0b10010000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11100000, 0b10001000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11100000, 0b10000100, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11100000, 0b10000010, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11100000, 0b10000001, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11100000, 0b10000000, 0b10000000]).valid_encoding?.should == false
+    end
+
+    it "is not valid if in range [xxxx1101 xx100000 xx000000] - [xxxx1101 xx111111 xx111111] (codepoints U+D800 - U+DFFF)" do
+      utf8([0b11101101, 0b10100000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11101101, 0b10100000, 0b10000001]).valid_encoding?.should == false
+      utf8([0b11101101, 0b10111111, 0b10111111]).valid_encoding?.should == false
+
+      utf8([0b11101101, 0b10011111, 0b10111111]).valid_encoding?.should == true # lower boundary - 1
+      utf8([0b11101110, 0b10000000, 0b10000000]).valid_encoding?.should == true # upper boundary + 1
+    end
+
+    it "is not valid if the first byte is missing" do
+      bytes = [0b11100000, 0b10100000, 0b10000000]
+      utf8(bytes[2..3]).valid_encoding?.should == false
+    end
+
+    it "is not valid if the second byte is missing" do
+      bytes = [0b11100000, 0b10100000, 0b10000000]
+      utf8([bytes[0], bytes[2]]).valid_encoding?.should == false
+    end
+
+    it "is not valid if the second and the third bytes are missing" do
+      bytes = [0b11100000, 0b10100000, 0b10000000]
+      utf8(bytes[0..0]).valid_encoding?.should == false
+    end
+  end
+
+  describe "4-bytes character" do
+    it "is valid if in format [11110xxx 10xxxxxx 10xxxxxx 10xxxxxx]" do
+      utf8([0b11110000, 0b10010000, 0b10000000, 0b10000000]).valid_encoding?.should == true
+      utf8([0b11110000, 0b10010000, 0b10000000, 0b10111111]).valid_encoding?.should == true
+      utf8([0b11110000, 0b10010000, 0b10111111, 0b10111111]).valid_encoding?.should == true
+      utf8([0b11110000, 0b10111111, 0b10111111, 0b10111111]).valid_encoding?.should == true
+      utf8([0b11110100, 0b10001111, 0b10111111, 0b10111111]).valid_encoding?.should == true
+    end
+
+    it "is not valid if the first byte is not in format 11110xxx" do
+      utf8([0b11100000, 0b10010000, 0b10000000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11010000, 0b10010000, 0b10000000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b10110000, 0b10010000, 0b10000000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b01110000, 0b10010000, 0b10000000, 0b10000000]).valid_encoding?.should == false
+    end
+
+    it "is not valid if the second byte is not in format 10xxxxxx" do
+      utf8([0b11110000, 0b00010000, 0b10000000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11110000, 0b01010000, 0b10000000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11110000, 0b10010000, 0b10000000, 0b10000000]).valid_encoding?.should == true # correct bytes
+      utf8([0b11110000, 0b11010000, 0b10000000, 0b10000000]).valid_encoding?.should == false
+    end
+
+    it "is not valid if the third byte is not in format 10xxxxxx" do
+      utf8([0b11110000, 0b10010000, 0b00000000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11110000, 0b10010000, 0b01000000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11110000, 0b10010000, 0b10000000, 0b10000000]).valid_encoding?.should == true # correct bytes
+      utf8([0b11110000, 0b10010000, 0b11000000, 0b10000000]).valid_encoding?.should == false
+    end
+
+    it "is not valid if the forth byte is not in format 10xxxxxx" do
+      utf8([0b11110000, 0b10010000, 0b10000000, 0b00000000]).valid_encoding?.should == false
+      utf8([0b11110000, 0b10010000, 0b10000000, 0b01000000]).valid_encoding?.should == false
+      utf8([0b11110000, 0b10010000, 0b10000000, 0b10000000]).valid_encoding?.should == true # correct bytes
+      utf8([0b11110000, 0b10010000, 0b10000000, 0b11000000]).valid_encoding?.should == false
+    end
+
+    it "is not valid if is smaller than [xxxxx000 xx001000 xx000000 xx000000] (codepoint < U+10000)" do
+      utf8([0b11110000, 0b10000111, 0b10000000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11110000, 0b10000110, 0b10000000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11110000, 0b10000101, 0b10000000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11110000, 0b10000100, 0b10000000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11110000, 0b10000011, 0b10000000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11110000, 0b10000010, 0b10000000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11110000, 0b10000001, 0b10000000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11110000, 0b10000000, 0b10000000, 0b10000000]).valid_encoding?.should == false
+    end
+
+    it "is not valid if is greater than [xxxxx100 xx001111 xx111111 xx111111] (codepoint > U+10FFFF)" do
+      utf8([0b11110100, 0b10010000, 0b10000000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11110100, 0b10100000, 0b10000000, 0b10000000]).valid_encoding?.should == false
+      utf8([0b11110100, 0b10110000, 0b10000000, 0b10000000]).valid_encoding?.should == false
+
+      utf8([0b11110101, 0b10001111, 0b10111111, 0b10111111]).valid_encoding?.should == false
+      utf8([0b11110110, 0b10001111, 0b10111111, 0b10111111]).valid_encoding?.should == false
+      utf8([0b11110111, 0b10001111, 0b10111111, 0b10111111]).valid_encoding?.should == false
+    end
+
+    it "is not valid if the first byte is missing" do
+      bytes = [0b11110000, 0b10010000, 0b10000000, 0b10000000]
+      utf8(bytes[1..3]).valid_encoding?.should == false
+    end
+
+    it "is not valid if the second byte is missing" do
+      bytes = [0b11110000, 0b10010000, 0b10000000, 0b10000000]
+      utf8([bytes[0], bytes[2], bytes[3]]).valid_encoding?.should == false
+    end
+
+    it "is not valid if the second and the third bytes are missing" do
+      bytes = [0b11110000, 0b10010000, 0b10000000, 0b10000000]
+      utf8([bytes[0], bytes[3]]).valid_encoding?.should == false
+    end
+
+    it "is not valid if the second, the third and the fourth bytes are missing" do
+      bytes = [0b11110000, 0b10010000, 0b10000000, 0b10000000]
+      utf8(bytes[0..0]).valid_encoding?.should == false
+    end
+  end
+end