test/cgi/test_cgi_util.rb


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
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237

# frozen_string_literal: true
require 'test/unit'
require 'cgi'
require 'stringio'
require_relative 'update_env'


class CGIUtilTest < Test::Unit::TestCase
  include CGI::Util
  include UpdateEnv

  def setup
    @environ = {}
    update_env(
      'REQUEST_METHOD' => 'GET',
      'SCRIPT_NAME' => nil,
    )
    @str1="&<>\" \xE3\x82\x86\xE3\x82\x93\xE3\x82\x86\xE3\x82\x93".dup
    @str1.force_encoding("UTF-8") if defined?(::Encoding)
  end

  def teardown
    ENV.update(@environ)
  end


  def test_cgi_escape
    assert_equal('%26%3C%3E%22+%E3%82%86%E3%82%93%E3%82%86%E3%82%93', CGI.escape(@str1))
    assert_equal('%26%3C%3E%22+%E3%82%86%E3%82%93%E3%82%86%E3%82%93'.ascii_only?, CGI.escape(@str1).ascii_only?) if defined?(::Encoding)
  end

  def test_cgi_escape_with_unreserved_characters
    assert_equal("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-._~",
                 CGI.escape("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-._~"),
                 "should not escape any unreserved characters, as per RFC3986 Section 2.3")
  end

  def test_cgi_escape_with_invalid_byte_sequence
    assert_equal('%C0%3C%3C', CGI.escape("\xC0\<\<".dup.force_encoding("UTF-8")))
  end

  def test_cgi_escape_preserve_encoding
    assert_equal(Encoding::US_ASCII, CGI.escape("\xC0\<\<".dup.force_encoding("US-ASCII")).encoding)
    assert_equal(Encoding::ASCII_8BIT, CGI.escape("\xC0\<\<".dup.force_encoding("ASCII-8BIT")).encoding)
    assert_equal(Encoding::UTF_8, CGI.escape("\xC0\<\<".dup.force_encoding("UTF-8")).encoding)
  end

  def test_cgi_unescape
    str = CGI.unescape('%26%3C%3E%22+%E3%82%86%E3%82%93%E3%82%86%E3%82%93')
    assert_equal(@str1, str)
    return unless defined?(::Encoding)

    assert_equal(@str1.encoding, str.encoding)
    assert_equal("\u{30E1 30E2 30EA 691C 7D22}", CGI.unescape("\u{30E1 30E2 30EA}%E6%A4%9C%E7%B4%A2"))
  end

  def test_cgi_unescape_preserve_encoding
    assert_equal(Encoding::US_ASCII, CGI.unescape("%C0%3C%3C".dup.force_encoding("US-ASCII")).encoding)
    assert_equal(Encoding::ASCII_8BIT, CGI.unescape("%C0%3C%3C".dup.force_encoding("ASCII-8BIT")).encoding)
    assert_equal(Encoding::UTF_8, CGI.unescape("%C0%3C%3C".dup.force_encoding("UTF-8")).encoding)
  end

  def test_cgi_unescape_accept_charset
    return unless defined?(::Encoding)

    assert_raise(TypeError) {CGI.unescape('', nil)}
    assert_separately(%w[-rcgi/util], "#{<<-"begin;"}\n#{<<-"end;"}")
    begin;
      assert_equal("", CGI.unescape(''))
    end;
  end

  def test_cgi_pretty
    assert_equal("<HTML>\n  <BODY>\n  </BODY>\n</HTML>\n",CGI.pretty("<HTML><BODY></BODY></HTML>"))
    assert_equal("<HTML>\n\t<BODY>\n\t</BODY>\n</HTML>\n",CGI.pretty("<HTML><BODY></BODY></HTML>","\t"))
  end

  def test_cgi_escapeHTML
    assert_equal("&#39;&amp;&quot;&gt;&lt;", CGI.escapeHTML("'&\"><"))
  end

  def test_cgi_escape_html_duplicated
    orig = "Ruby".dup.force_encoding("US-ASCII")
    str = CGI.escapeHTML(orig)
    assert_equal(orig, str)
    assert_not_same(orig, str)
  end

  def assert_cgi_escape_html_preserve_encoding(str, encoding)
    assert_equal(encoding, CGI.escapeHTML(str.dup.force_encoding(encoding)).encoding)
  end

  def test_cgi_escape_html_preserve_encoding
    Encoding.list do |enc|
      assert_cgi_escape_html_preserve_encoding("'&\"><", enc)
      assert_cgi_escape_html_preserve_encoding("Ruby", enc)
    end
  end

  def test_cgi_escape_html_dont_freeze
    assert_not_predicate CGI.escapeHTML("'&\"><".dup),    :frozen?
    assert_not_predicate CGI.escapeHTML("'&\"><".freeze), :frozen?
    assert_not_predicate CGI.escapeHTML("Ruby".dup),      :frozen?
    assert_not_predicate CGI.escapeHTML("Ruby".freeze),   :frozen?
  end

  def test_cgi_escape_html_large
    ulong_max, size_max = RbConfig::LIMITS.values_at("ULONG_MAX", "SIZE_MAX")
    return unless ulong_max < size_max # Platforms not concerned

    size = (ulong_max / 6 + 1)
    begin
      str = '"' * size
      escaped = CGI.escapeHTML(str)
    rescue NoMemoryError
      omit "Not enough memory"
    rescue => e
    end
    assert_raise_with_message(ArgumentError, /overflow/, ->{"length = #{escaped.length}"}) do
      raise e if e
    end
  end

  def test_cgi_unescapeHTML
    assert_equal("'&\"><", CGI.unescapeHTML("&#39;&amp;&quot;&gt;&lt;"))
  end

  def test_cgi_unescapeHTML_invalid
    assert_equal('&<&amp>&quot&abcdefghijklmn', CGI.unescapeHTML('&&lt;&amp&gt;&quot&abcdefghijklmn'))
  end

  Encoding.list.each do |enc|
    begin
      escaped = "&#39;&amp;&quot;&gt;&lt;".encode(enc)
      unescaped = "'&\"><".encode(enc)
    rescue Encoding::ConverterNotFoundError
      next
    else
      define_method("test_cgi_escapeHTML:#{enc.name}") do
        assert_equal(escaped, CGI.escapeHTML(unescaped))
      end
      define_method("test_cgi_unescapeHTML:#{enc.name}") do
        assert_equal(unescaped, CGI.unescapeHTML(escaped))
      end
    end
  end

  Encoding.list.each do |enc|
    next unless enc.ascii_compatible?
    begin
      escaped = "%25+%2B"
      unescaped = "% +".encode(enc)
    rescue Encoding::ConverterNotFoundError
      next
    else
      define_method("test_cgi_escape:#{enc.name}") do
        assert_equal(escaped, CGI.escape(unescaped))
      end
      define_method("test_cgi_unescape:#{enc.name}") do
        assert_equal(unescaped, CGI.unescape(escaped, enc))
      end
    end
  end

  def test_cgi_unescapeHTML_uppercasecharacter
    assert_equal("\xE3\x81\x82\xE3\x81\x84\xE3\x81\x86", CGI.unescapeHTML("&#x3042;&#x3044;&#X3046;"))
  end

  def test_cgi_include_escape
    assert_equal('%26%3C%3E%22+%E3%82%86%E3%82%93%E3%82%86%E3%82%93', escape(@str1))
  end

  def test_cgi_include_escapeHTML
    assert_equal("&#39;&amp;&quot;&gt;&lt;", escapeHTML("'&\"><"))
  end

  def test_cgi_include_h
    assert_equal("&#39;&amp;&quot;&gt;&lt;", h("'&\"><"))
  end

  def test_cgi_include_unescape
    str = unescape('%26%3C%3E%22+%E3%82%86%E3%82%93%E3%82%86%E3%82%93')
    assert_equal(@str1, str)
    return unless defined?(::Encoding)

    assert_equal(@str1.encoding, str.encoding)
    assert_equal("\u{30E1 30E2 30EA 691C 7D22}", unescape("\u{30E1 30E2 30EA}%E6%A4%9C%E7%B4%A2"))
  end

  def test_cgi_include_unescapeHTML
    assert_equal("'&\"><", unescapeHTML("&#39;&amp;&quot;&gt;&lt;"))
  end

  def test_cgi_escapeElement
    assert_equal("<BR>&lt;A HREF=&quot;url&quot;&gt;&lt;/A&gt;", escapeElement('<BR><A HREF="url"></A>', "A", "IMG"))
    assert_equal("<BR>&lt;A HREF=&quot;url&quot;&gt;&lt;/A&gt;", escapeElement('<BR><A HREF="url"></A>', ["A", "IMG"]))
    assert_equal("<BR>&lt;A HREF=&quot;url&quot;&gt;&lt;/A&gt;", escape_element('<BR><A HREF="url"></A>', "A", "IMG"))
    assert_equal("<BR>&lt;A HREF=&quot;url&quot;&gt;&lt;/A&gt;", escape_element('<BR><A HREF="url"></A>', ["A", "IMG"]))
  end


  def test_cgi_unescapeElement
    assert_equal('&lt;BR&gt;<A HREF="url"></A>', unescapeElement(escapeHTML('<BR><A HREF="url"></A>'), "A", "IMG"))
    assert_equal('&lt;BR&gt;<A HREF="url"></A>', unescapeElement(escapeHTML('<BR><A HREF="url"></A>'), ["A", "IMG"]))
    assert_equal('&lt;BR&gt;<A HREF="url"></A>', unescape_element(escapeHTML('<BR><A HREF="url"></A>'), "A", "IMG"))
    assert_equal('&lt;BR&gt;<A HREF="url"></A>', unescape_element(escapeHTML('<BR><A HREF="url"></A>'), ["A", "IMG"]))
  end
end

class CGIUtilPureRubyTest < Test::Unit::TestCase
  def setup
    CGI::Escape.module_eval do
      alias _escapeHTML escapeHTML
      remove_method :escapeHTML
      alias _unescapeHTML unescapeHTML
      remove_method :unescapeHTML
    end
  end

  def teardown
    CGI::Escape.module_eval do
      alias escapeHTML _escapeHTML
      remove_method :_escapeHTML
      alias unescapeHTML _unescapeHTML
      remove_method :_unescapeHTML
    end
  end

  def test_cgi_escapeHTML_with_invalid_byte_sequence
    assert_equal("&lt;\xA4??&gt;", CGI.escapeHTML(%[<\xA4??>]))
  end

  def test_cgi_unescapeHTML_with_invalid_byte_sequence
    input = "\xFF&"
    assert_equal(input, CGI.unescapeHTML(input))
  end
end