File: source_encoding_spec.rb

package info (click to toggle)
ruby3.3 3.3.8-2
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 153,620 kB
  • sloc: ruby: 1,244,308; ansic: 836,474; yacc: 28,074; pascal: 6,748; sh: 3,913; python: 1,719; cpp: 1,158; makefile: 742; asm: 712; javascript: 394; lisp: 97; perl: 62; awk: 36; sed: 23; xml: 4
file content (61 lines) | stat: -rw-r--r-- 1,978 bytes parent folder | download | duplicates (4)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
require_relative '../spec_helper'

describe "Source files" do

  describe "encoded in UTF-8 without a BOM" do
    it "can be parsed" do
      ruby_exe(fixture(__FILE__, "utf8-nobom.rb"), args: "2>&1").should == "hello\n"
    end
  end

  describe "encoded in UTF-8 with a BOM" do
    it "can be parsed" do
      ruby_exe(fixture(__FILE__, "utf8-bom.rb"), args: "2>&1").should == "hello\n"
    end
  end

  describe "encoded in UTF-16 LE without a BOM" do
    it "are parsed as empty because they contain a NUL byte before the encoding comment" do
      ruby_exe(fixture(__FILE__, "utf16-le-nobom.rb"), args: "2>&1").should == ""
    end
  end

  describe "encoded in UTF-16 LE with a BOM" do
    it "are invalid because they contain an invalid UTF-8 sequence before the encoding comment" do
      bom = "\xFF\xFE".b
      source = "# encoding: utf-16le\nputs 'hello'\n"
      source = bom + source.bytes.zip([0]*source.bytesize).flatten.pack('C*')
      path = tmp("utf16-le-bom.rb")

      touch(path, "wb") { |f| f.write source }
      begin
        ruby_exe(path, args: "2>&1", exit_status: 1).should =~ /invalid multibyte char/
      ensure
        rm_r path
      end
    end
  end

  describe "encoded in UTF-16 BE without a BOM" do
    it "are parsed as empty because they contain a NUL byte before the encoding comment" do
      ruby_exe(fixture(__FILE__, "utf16-be-nobom.rb"), args: "2>&1").should == ""
    end
  end

  describe "encoded in UTF-16 BE with a BOM" do
    it "are invalid because they contain an invalid UTF-8 sequence before the encoding comment" do
      bom = "\xFE\xFF".b
      source = "# encoding: utf-16be\nputs 'hello'\n"
      source = bom + ([0]*source.bytesize).zip(source.bytes).flatten.pack('C*')
      path = tmp("utf16-be-bom.rb")

      touch(path, "wb") { |f| f.write source }
      begin
        ruby_exe(path, args: "2>&1", exit_status: 1).should =~ /invalid multibyte char/
      ensure
        rm_r path
      end
    end
  end

end