summaryrefslogtreecommitdiff
path: root/spec/lib/gitlab/conflict/parser_spec.rb
blob: 2570f95dd21be4bc396c4df1feb44e7233f697ae (plain)
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
require 'spec_helper'

describe Gitlab::Conflict::Parser, lib: true do
  let(:parser) { Gitlab::Conflict::Parser.new }

  describe '#parse' do
    def parse_text(text)
      parser.parse(text, our_path: 'README.md', their_path: 'README.md')
    end

    context 'when the file has valid conflicts' do
      let(:text) do
        <<CONFLICT
module Gitlab
  module Regexp
    extend self

    def username_regexp
      default_regexp
    end

<<<<<<< files/ruby/regex.rb
    def project_name_regexp
      /\A[a-zA-Z0-9][a-zA-Z0-9_\-\. ]*\z/
    end

    def name_regexp
      /\A[a-zA-Z0-9_\-\. ]*\z/
=======
    def project_name_regex
      %r{\A[a-zA-Z0-9][a-zA-Z0-9_\-\. ]*\z}
    end

    def name_regex
      %r{\A[a-zA-Z0-9_\-\. ]*\z}
>>>>>>> files/ruby/regex.rb
    end

    def path_regexp
      default_regexp
    end

<<<<<<< files/ruby/regex.rb
    def archive_formats_regexp
      /(zip|tar|7z|tar\.gz|tgz|gz|tar\.bz2|tbz|tbz2|tb2|bz2)/
=======
    def archive_formats_regex
      %r{(zip|tar|7z|tar\.gz|tgz|gz|tar\.bz2|tbz|tbz2|tb2|bz2)}
>>>>>>> files/ruby/regex.rb
    end

    def git_reference_regexp
      # Valid git ref regexp, see:
      # https://www.kernel.org/pub/software/scm/git/docs/git-check-ref-format.html
      %r{
        (?!
           (?# doesn't begins with)
           \/|                    (?# rule #6)
           (?# doesn't contain)
           .*(?:
              [\/.]\.|            (?# rule #1,3)
              \/\/|               (?# rule #6)
              @\{|                (?# rule #8)
              \\                  (?# rule #9)
           )
        )
        [^\000-\040\177~^:?*\[]+  (?# rule #4-5)
        (?# doesn't end with)
        (?<!\.lock)               (?# rule #1)
        (?<![\/.])                (?# rule #6-7)
      }x
    end

    protected

<<<<<<< files/ruby/regex.rb
    def default_regexp
      /\A[.?]?[a-zA-Z0-9][a-zA-Z0-9_\-\.]*(?<!\.git)\z/
=======
    def default_regex
      %r{\A[.?]?[a-zA-Z0-9][a-zA-Z0-9_\-\.]*(?<!\.git)\z}
>>>>>>> files/ruby/regex.rb
    end
  end
end
CONFLICT
      end

      let(:lines) do
        parser.parse(text, our_path: 'files/ruby/regex.rb', their_path: 'files/ruby/regex.rb')
      end

      it 'sets our lines as new lines' do
        expect(lines[8..13]).to all(have_attributes(type: 'new'))
        expect(lines[26..27]).to all(have_attributes(type: 'new'))
        expect(lines[56..57]).to all(have_attributes(type: 'new'))
      end

      it 'sets their lines as old lines' do
        expect(lines[14..19]).to all(have_attributes(type: 'old'))
        expect(lines[28..29]).to all(have_attributes(type: 'old'))
        expect(lines[58..59]).to all(have_attributes(type: 'old'))
      end

      it 'sets non-conflicted lines as both' do
        expect(lines[0..7]).to all(have_attributes(type: nil))
        expect(lines[20..25]).to all(have_attributes(type: nil))
        expect(lines[30..55]).to all(have_attributes(type: nil))
        expect(lines[60..62]).to all(have_attributes(type: nil))
      end

      it 'sets consecutive line numbers for index, old_pos, and new_pos' do
        old_line_numbers = lines.select { |line| line.type != 'new' }.map(&:old_pos)
        new_line_numbers = lines.select { |line| line.type != 'old' }.map(&:new_pos)

        expect(lines.map(&:index)).to eq(0.upto(62).to_a)
        expect(old_line_numbers).to eq(1.upto(53).to_a)
        expect(new_line_numbers).to eq(1.upto(53).to_a)
      end
    end

    context 'when the file contents include conflict delimiters' do
      context 'when there is a non-start delimiter first' do
        it 'raises UnexpectedDelimiter when there is a middle delimiter first' do
          expect { parse_text('=======') }.
            to raise_error(Gitlab::Conflict::Parser::UnexpectedDelimiter)
        end

        it 'raises UnexpectedDelimiter when there is an end delimiter first' do
          expect { parse_text('>>>>>>> README.md') }.
            to raise_error(Gitlab::Conflict::Parser::UnexpectedDelimiter)
        end

        it 'does not raise when there is an end delimiter for a different path first' do
          expect { parse_text('>>>>>>> some-other-path.md') }.
            not_to raise_error
        end
      end

      context 'when a start delimiter is followed by a non-middle delimiter' do
        let(:start_text) { "<<<<<<< README.md\n" }
        let(:end_text) { "\n=======\n>>>>>>> README.md" }

        it 'raises UnexpectedDelimiter when it is followed by an end delimiter' do
          expect { parse_text(start_text + '>>>>>>> README.md' + end_text) }.
            to raise_error(Gitlab::Conflict::Parser::UnexpectedDelimiter)
        end

        it 'raises UnexpectedDelimiter when it is followed by another start delimiter' do
          expect { parse_text(start_text + start_text + end_text) }.
            to raise_error(Gitlab::Conflict::Parser::UnexpectedDelimiter)
        end

        it 'does not raise when it is followed by a start delimiter for a different path' do
          expect { parse_text(start_text + '>>>>>>> some-other-path.md' + end_text) }.
            not_to raise_error
        end
      end

      context 'when a middle delimiter is followed by a non-end delimiter' do
        let(:start_text) { "<<<<<<< README.md\n=======\n" }
        let(:end_text) { "\n>>>>>>> README.md" }

        it 'raises UnexpectedDelimiter when it is followed by another middle delimiter' do
          expect { parse_text(start_text + '=======' + end_text) }.
            to raise_error(Gitlab::Conflict::Parser::UnexpectedDelimiter)
        end

        it 'raises UnexpectedDelimiter when it is followed by a start delimiter' do
          expect { parse_text(start_text + start_text + end_text) }.
            to raise_error(Gitlab::Conflict::Parser::UnexpectedDelimiter)
        end

        it 'does not raise when it is followed by a start delimiter for another path' do
          expect { parse_text(start_text + '<<<<<<< some-other-path.md' + end_text) }.
            not_to raise_error
        end
      end

      it 'raises MissingEndDelimiter when there is no end delimiter at the end' do
        start_text = "<<<<<<< README.md\n=======\n"

        expect { parse_text(start_text) }.
          to raise_error(Gitlab::Conflict::Parser::MissingEndDelimiter)

        expect { parse_text(start_text + '>>>>>>> some-other-path.md') }.
          to raise_error(Gitlab::Conflict::Parser::MissingEndDelimiter)
      end
    end

    context 'other file types' do
      it 'raises UnmergeableFile when lines is blank, indicating a binary file' do
        expect { parse_text('') }.
          to raise_error(Gitlab::Conflict::Parser::UnmergeableFile)

        expect { parse_text(nil) }.
          to raise_error(Gitlab::Conflict::Parser::UnmergeableFile)
      end

      it 'raises UnmergeableFile when the file is over 200 KB' do
        expect { parse_text('a' * 204801) }.
          to raise_error(Gitlab::Conflict::Parser::UnmergeableFile)
      end

      # All text from Rugged has an encoding of ASCII_8BIT, so force that in
      # these strings.
      context 'when the file contains UTF-8 characters' do
        it 'does not raise' do
          expect { parse_text("Espa\xC3\xB1a".force_encoding(Encoding::ASCII_8BIT)) }.
            not_to raise_error
        end
      end

      context 'when the file contains non-UTF-8 characters' do
        it 'raises UnsupportedEncoding' do
          expect { parse_text("a\xC4\xFC".force_encoding(Encoding::ASCII_8BIT)) }.
            to raise_error(Gitlab::Conflict::Parser::UnsupportedEncoding)
        end
      end
    end
  end
end