4254512104

Build Type

github

Committed by GitHub

Commit Message

Merge bd6a0ab8d into c409d01fa

Pull Request Pull Request #21: Test on Ruby 3.1 and 3.2

Run Details

334 of 339 relevant lines covered (98.53%)

134.55 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

86.84

/lib/java-properties/encoding/unicode.rb

module JavaProperties
  module Encoding
    # Module to encode and decode unicode chars
    # This code is highly influced by Florian Frank's JSON gem
    # @see https://github.com/flori/json/
    module Unicode

      # @private
      MAP = {
        "\x0" => '\u0000',
        "\x1" => '\u0001',
        "\x2" => '\u0002',
        "\x3" => '\u0003',
        "\x4" => '\u0004',
        "\x5" => '\u0005',
        "\x6" => '\u0006',
        "\x7" => '\u0007',
        "\xb" => '\u000b',
        "\xe" => '\u000e',
        "\xf" => '\u000f',
        "\x10" => '\u0010',
        "\x11" => '\u0011',
        "\x12" => '\u0012',
        "\x13" => '\u0013',
        "\x14" => '\u0014',
        "\x15" => '\u0015',
        "\x16" => '\u0016',
        "\x17" => '\u0017',
        "\x18" => '\u0018',
        "\x19" => '\u0019',
        "\x1a" => '\u001a',
        "\x1b" => '\u001b',
        "\x1c" => '\u001c',
        "\x1d" => '\u001d',
        "\x1e" => '\u001e',
        "\x1f" => '\u001f',
      }

      # @private
      EMPTY_8BIT_STRING = ''
      EMPTY_8BIT_STRING.force_encoding(::Encoding::ASCII_8BIT)

      # Decodes all unicode chars from escape sequences in place
      # @param text [String]
      # @return [String] The encoded text for chaining
      def self.decode!(text)
        string = text.dup
        string = string.gsub(%r((?:\\[uU](?:[A-Fa-f\d]{4}))+)) do |c|
          c.downcase!
          bytes = EMPTY_8BIT_STRING.dup
          i = 0
          while c[6 * i] == ?\\ && c[6 * i + 1] == ?u
            bytes << c[6 * i + 2, 2].to_i(16) << c[6 * i + 4, 2].to_i(16)
            i += 1
          end
          bytes.encode("utf-8", "utf-16be")
        end
        string.force_encoding(::Encoding::UTF_8)

        text.replace string
        text
      end

      # Decodes all unicode chars into escape sequences in place
      # @param text [String]
      # @return [String] The decoded text for chaining
      def self.encode!(text)
        string = text.dup
        string.force_encoding(::Encoding::ASCII_8BIT)
        string.gsub!(/["\\\x0-\x1f]/n) { |c| MAP[c] || c }
        string.gsub!(/(
          (?:
           [\xc2-\xdf][\x80-\xbf]    |
           [\xe0-\xef][\x80-\xbf]{2} |
           [\xf0-\xf4][\x80-\xbf]{3}
          )+ |
          [\x80-\xc1\xf5-\xff]       # invalid
        )/nx) { |c|
          c.size == 1 and raise "Invalid utf8 byte: '#{c}'"
          s = c.encode("utf-16be", "utf-8").unpack('H*')[0]
          s.force_encoding(::Encoding::ASCII_8BIT)
          s.gsub!(/.{4}/n, '\\\\u\&')
          s.force_encoding(::Encoding::UTF_8)
        }
        string.force_encoding(::Encoding::UTF_8)
        text.replace string
        text
      end

      private

      def self.unicode(code)
        code.chr(::Encoding::UTF_8)
      end

      def self.hex(codepoint)
        hex  = codepoint.to_s(16)
        size = [4, hex.size].max
        target_size = size.even? ? size : size+1
        hex.rjust(target_size, '0')
      end

    end
  end
end

1	module JavaProperties	7✔
2	module Encoding	7✔
3	# Module to encode and decode unicode chars
4	# This code is highly influced by Florian Frank's JSON gem
5	# @see https://github.com/flori/json/
6	module Unicode	7✔
7
8	# @private
9	MAP = {	2✔
10	"\x0" => '\u0000',	5✔
11	"\x1" => '\u0001',
12	"\x2" => '\u0002',
13	"\x3" => '\u0003',
14	"\x4" => '\u0004',
15	"\x5" => '\u0005',
16	"\x6" => '\u0006',
17	"\x7" => '\u0007',
18	"\xb" => '\u000b',
19	"\xe" => '\u000e',
20	"\xf" => '\u000f',
21	"\x10" => '\u0010',
22	"\x11" => '\u0011',
23	"\x12" => '\u0012',
24	"\x13" => '\u0013',
25	"\x14" => '\u0014',
26	"\x15" => '\u0015',
27	"\x16" => '\u0016',
28	"\x17" => '\u0017',
29	"\x18" => '\u0018',
30	"\x19" => '\u0019',
31	"\x1a" => '\u001a',
32	"\x1b" => '\u001b',
33	"\x1c" => '\u001c',
34	"\x1d" => '\u001d',
35	"\x1e" => '\u001e',
36	"\x1f" => '\u001f',
37	}
38
39	# @private
40	EMPTY_8BIT_STRING = ''	7✔
41	EMPTY_8BIT_STRING.force_encoding(::Encoding::ASCII_8BIT)	7✔
42
43	# Decodes all unicode chars from escape sequences in place
44	# @param text [String]
45	# @return [String] The encoded text for chaining
46	def self.decode!(text)	7✔
47	string = text.dup	301✔
48	string = string.gsub(%r((?:\\[uU](?:[A-Fa-f\d]{4}))+)) do \|c\|	301✔
49	c.downcase!	119✔
50	bytes = EMPTY_8BIT_STRING.dup	119✔
51	i = 0	119✔
52	while c[6 * i] == ?\\ && c[6 * i + 1] == ?u	119✔
53	bytes << c[6 * i + 2, 2].to_i(16) << c[6 * i + 4, 2].to_i(16)	147✔
54	i += 1	147✔
55	end
56	bytes.encode("utf-8", "utf-16be")	119✔
57	end
58	string.force_encoding(::Encoding::UTF_8)	301✔
59
60	text.replace string	301✔
61	text	301✔
62	end
63
64	# Decodes all unicode chars into escape sequences in place
65	# @param text [String]
66	# @return [String] The decoded text for chaining
67	def self.encode!(text)	7✔
68	string = text.dup	588✔
69	string.force_encoding(::Encoding::ASCII_8BIT)	588✔
70	string.gsub!(/["\\\x0-\x1f]/n) { \|c\| MAP[c] \|\| c }	889✔
71	string.gsub!(/(	420✔
72	(?:
73	[\xc2-\xdf][\x80-\xbf] \|
74	[\xe0-\xef][\x80-\xbf]{2} \|
75	[\xf0-\xf4][\x80-\xbf]{3}
76	)+ \|
77	[\x80-\xc1\xf5-\xff] # invalid
78	)/nx) { \|c\|	168✔
79	c.size == 1 and raise "Invalid utf8 byte: '#{c}'"	182✔
80	s = c.encode("utf-16be", "utf-8").unpack('H*')[0]	182✔
81	s.force_encoding(::Encoding::ASCII_8BIT)	182✔
82	s.gsub!(/.{4}/n, '\\\\u\&')	182✔
83	s.force_encoding(::Encoding::UTF_8)	182✔
84	}
85	string.force_encoding(::Encoding::UTF_8)	588✔
86	text.replace string	588✔
87	text	588✔
88	end
89
90	private	7✔
91
92	def self.unicode(code)	7✔
93	code.chr(::Encoding::UTF_8)	×
94	end
95
96	def self.hex(codepoint)	7✔
97	hex = codepoint.to_s(16)	×
98	size = [4, hex.size].max	×
99	target_size = size.even? ? size : size+1	×
100	hex.rjust(target_size, '0')	×
101	end
102
103	end
104	end
105	end

jnbt / java-properties / 4254512104

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous