herb/test/parser/text_content_test.rb at 00b32e2432b0469d27578f2cb0668ba3672e00ec · koddsson/herb · GitHub

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
# frozen_string_literal: true

require_relative "../test_helper"

module Parser
  class TextContentTest < Minitest::Spec
    include SnapshotUtils

    test "text content" do
      assert_parsed_snapshot("Hello World")
    end

    test "text content inside tag" do
      assert_parsed_snapshot("<h1>Hello World</h1>")
    end

    test "text content with tag after" do
      assert_parsed_snapshot("Hello<span>World</span>")
    end

    test "text content with tag before" do
      assert_parsed_snapshot("<span>Hello</span>World")
    end

    test "text content with tag around" do
      assert_parsed_snapshot("Hello<span></span>World")
    end

    test "text content that exceeds initial buffer_T size (ca. 4K)" do
      initial_buffer_capacity = 1024 # bytes
      content = cyclic_string((((initial_buffer_capacity * 2) + 1) * 2) + 1)
      result = assert_parsed_snapshot(%(<div>#{content}</div>))

      assert_equal content, result.value.children.first.body.first.content
    end

    test "text content that exceeds initial buffer_T size (ca. 8K)" do
      initial_buffer_capacity = 1024 # bytes
      content = cyclic_string((((((initial_buffer_capacity * 2) + 1) * 2) + 1) * 2) + 1)
      result = assert_parsed_snapshot(%(<div>#{content}</div>))

      assert_equal content, result.value.children.first.body.first.content
    end

    test "exclamation as only content" do
      assert_parsed_snapshot("<b>!</b>")
    end

    test "comma as only content" do
      assert_parsed_snapshot("<b>,</b>")
    end

    test "dollar sign as only content" do
      assert_parsed_snapshot("<b>$</b>")
    end

    test "dash as only content" do
      assert_parsed_snapshot("<b>-</b>")
    end

    test "period as only content" do
      assert_parsed_snapshot("<b>.</b>")
    end

    test "percent as only content" do
      assert_parsed_snapshot("<b>%</b>")
    end

    test "slash as only content" do
      assert_parsed_snapshot("<b>/</b>")
    end

    test "underscore as only content" do
      assert_parsed_snapshot("<b>_</b>")
    end

    test "colon as only content" do
      assert_parsed_snapshot("<b>:</b>")
    end

    test "semicolon as only content" do
      assert_parsed_snapshot("<b>;</b>")
    end

    test "ampersand as only content" do
      assert_parsed_snapshot("<b>&</b>")
    end

    test "equals as only content" do
      assert_parsed_snapshot("<b>=</b>")
    end

    test "a-umlaut as only content" do
      assert_parsed_snapshot("<b>ä</b>")
    end

    test "o-umlaut as only content" do
      assert_parsed_snapshot("<b>ö</b>")
    end

    test "u-umlaut as only content" do
      assert_parsed_snapshot("<b>ü</b>")
    end

    test "emoji as only content" do
      assert_parsed_snapshot("<b>🌿</b>")
    end

    test "non-breaking space (U+00A0) as only content" do
      assert_parsed_snapshot("<b> </b>")
    end

    test "non-breaking space mixed with ERB - issue 310" do
      assert_parsed_snapshot("<p><%= hello %> !</p>")
    end

    test "multiple non-breaking spaces in text" do
      assert_parsed_snapshot("<p>Hello   World</p>")
    end

    test "non-breaking space in attribute value" do
      assert_parsed_snapshot('<div title="Hello World">Content</div>')
    end

    test "at symbol (@) in text content - issue 285" do
      assert_parsed_snapshot("<p>Did we get it wrong? Respond with <em>@reverse</em> to remove the receipt.</p>")
    end

    test "at symbol at beginning of text" do
      assert_parsed_snapshot("<span>@username</span>")
    end

    test "multiple at symbols in text" do
      assert_parsed_snapshot("<p>Email me @john@example.com</p>")
    end

    test "at symbol mixed with ERB" do
      assert_parsed_snapshot("<p>Contact <%= user.name %> @support</p>")
    end

    test "at symbol in attribute value" do
      assert_parsed_snapshot('<a href="mailto:support@example.com">Contact @support</a>')
    end

    test "backtick with HTML tags - issue 467" do
      assert_parsed_snapshot("a `<b></b>` c")
    end
  end
end