aboutsummaryrefslogtreecommitdiff
path: root/_plugins/linter.rb
blob: 8078daeb81ca582fde7c26cb52f6e8d91f580134 (about) (plain) (blame)
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
238
require 'set'

IGNORED_PAGES = Set['sitemap.xml']
LANGS = Set['en', 'pt', 'fr', 'eo'] # jp zh es de

module Jekyll
  class Linter < Generator
    safe true
    priority :high

    def insert_id(name, document)
      lang = document.data['lang']
      ref = document.data['ref']
      id = "#{name}:#{lang}:#{ref}"
      if @known_ids.include? id then
        raise "Duplicate ID found: '#{id}'"
      else
        @known_ids.add id
      end
    end

    def assert_unique_ids(site)
      @known_ids = Set[]
      all_documents(site) do |collection_name, document|
        insert_id collection_name, document
      end
    end

    def slugify(s)
      s.ljust(100)
        .gsub(/[\W]+/, ' ')
        .strip
        .gsub(/\s\s+/, '-')
        .downcase
        .gsub(' ', '-')
        .gsub('_', '-')
    end

    def assert(value, message)
      unless value
        raise message
      end
      value
    end

    def assert_field(document, field)
      f = document.data[field]
      raise "Undefined '#{field}' for #{document.path}" unless f
      f
    end

    COLLECTION_LAYOUTS = {
      'page' => 'default',
      'slides' => 'slides',
      'articles' => 'post',
      'pastebins' => 'post',
      'tils' => 'post',
      'podcasts' => 'post',
      'screencasts' => 'post'
    }

    def assert_frontmatter_fields(name, document)
      title = assert_field document, 'title'
      lang = assert_field document, 'lang'
      ref = assert_field document, 'ref'
      layout = assert_field document, 'layout'
      date = document.date.strftime('%Y-%m-%d') unless layout == 'default'
      slug = layout == 'default' ? ref : assert_field(document, 'slug')
      extension = name == 'slides' ? 'slides' : 'md'

      unless LANGS.member? lang
        raise "Invalid lang '#{lang}' in #{document.path}"
      end

      if COLLECTION_LAYOUTS[name] != layout
        raise "Layout mismatch: expected '#{COLLECTION_LAYOUTS[name]}', got '#{layout}' for #{document.path}"
      end

      if lang == 'en'
        unless ['index', 'root', 'tils'].include? ref
          if slugify(title) != ref then
            raise "#{ref} isn't a slug of the title.\nref:        '#{ref}'\ntitle slug: '#{slugify(title)}'"
          end
        end
      end

      unless layout == 'default' then
        path = "_#{name}/#{date}-#{slug}.#{extension}"
        unless path == document.relative_path then
          raise "date/filename mismatch:\ndate+slug: #{path}\nfilename:  #{document.relative_path}"
        end

        if lang == 'en' then
          unless ref == slug then
            raise "ref/slug mismatch:\nref:  #{ref}\nslug: #{slug}"
          end
        end
      end

      if name == 'podcasts' then
        flac = "resources/podcasts/#{date}-#{slug}.flac"
        unless File.exist? flac then
          raise "Missing FLAC file '#{flac}'"
        end
      end

      if name == 'screencasts' then
        webm = "resources/screencasts/#{date}-#{slug}.webm"
        unless File.exist? webm then
          raise "Missing WebM file '#{webm}'"
        end
      end
    end

    def assert_frontmatter(site)
      all_documents(site) do |collection_name, document|
        assert_frontmatter_fields collection_name, document
      end
    end

    @@first_build = true
    def assert_git_annex(site)
      url = site.config['url']
      stdout = `git annex find --not --in web`
      if stdout != '' or not $?.success? then
        puts 'Files in Git Annex not published to "web" remote:'
        puts stdout
        puts "Add them with:\n\n"
        stdout.strip.split("\n").each do |file|
          puts "git annex addurl --file #{file} #{url}/#{file}"
        end
        msg = "\nBuild again after files above are added"
        if @@first_build then
          @@first_build = false
          puts msg
        else
          raise msg
        end
      end
    end

    MEDIA_EXTENSION = {
      'podcasts' => 'flac',
      'screencasts' => 'webm'
    }

    def assert_media_metadata(site)
      site.collections.each do |name, collection|
        if ['podcasts', 'screencasts'].include? name then
          collection.docs.each do |document|
            date = document.data['date'].strftime('%Y-%m-%d')
            slug = document.data['slug']
            ext = MEDIA_EXTENSION[name]
            file =  "resources/#{name}/#{date}-#{slug}.#{ext}"
            feed_name = site.config['t'][name]['feed']['title'][document.data['lang']]
            if name == 'podcasts'
              stdout = `metaflac --export-tags-to=- #{file}`.strip.split("\n")
              expected = [
                "COMMENTS=#{site.config['url']}/#{file}",
                'ARTIST=EuAndreh',
                "DATE=#{date}",
                "TITLE=#{document.data['title']}",
                "ALBUM=#{feed_name}"
              ]
              expected.each do |metadata|
                unless stdout.include? metadata
                  tags = expected.join('\\n').gsub(/'/, "'\"'\"'")
                  add_metadata_cmd = "metaflac --remove-all #{file}\nprintf '#{tags}\\n' | metaflac --import-tags-from=- #{file}"
                  check_metadata_cmd = "metaflac --export-tags-to=- #{file}"
                  raise "Missing metadata entry '#{metadata}' in '#{file}'.\nAdd it with:\n\n#{add_metadata_cmd}\n\nCheck with:\n  #{check_metadata_cmd}"
                end
              end

              check_cover_cmd = "metaflac #{file} --export-picture-to=- | diff - static/favicon.png"
              `#{check_cover_cmd}`
              unless $?.success? then
                add_cover_cmd = "metaflac #{file} --import-picture-from=static/favicon.png"
                raise "Cover art from '#{file}' doesn't match 'static/favicon.png'.\nFix it with:\n\n#{add_cover_cmd}\n\nCheck with:\n  #{check_cover_cmd}"
              end
            elsif name == 'screencasts' then
              stdout = `mediainfo #{file} | awk -F: '/^Movie name/ { print $2 }'`.strip
              expected = document.data['title'] + ' - ' + feed_name
              unless stdout == expected then
                escaped_title = expected.gsub(/'/, "'\"'\"'")
                add_metadata_cmd = "mkvpropedit '#{file}' -e info -s title='#{escaped_title}'"
                check_metadata_cmd = "mediainfo '#{file}' | grep 'Movie name'"
                raise "Missing metadata entry 'title' in '#{file}'.\nAdd it with:\n\n#{add_metadata_cmd}\n\nCheck with:\n  #{check_metadata_cmd}"
              end
            end
          end
        end
      end
    end

    def assert_lilypond(site)
      site.config['musics'].each do |music|
        assert music['title'], "Missing 'title' in #{music}"
        assert music['composer'], "Missing 'composer' in #{music}"
        ref = assert music['ref'], "Missing 'ref' in #{music}"
        ly = "music/#{ref}.ly"
        unless File.exist? ly then
          raise "Missing '#{ly}' file present in _config.yml."
        end

        point_and_click_off = open(ly) { |f| f.include? "\\pointAndClickOff\n" }
        unless point_and_click_off then
          raise "Missing '\\pointAndClickOff' in '#{ly}'"
        end
      end
    end

    def generate(site)
      assert_unique_ids(site)
      assert_frontmatter(site)
      assert_media_metadata(site)
      assert_git_annex(site)
      assert_lilypond(site)
    end

    def all_documents(site)
      site.collections.each do |name, collection|
        collection.docs.each do |document|
          unless document.data['generated']
            yield name, document
          end
        end
      end

      site.pages.each do |page|
        unless IGNORED_PAGES.include? page.path
          unless page.data['generated']
            yield 'page', page
          end
        end
      end
    end
  end
end