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
|
# -*- ruby encoding: utf-8 -*-
$LOAD_PATH.unshift File.expand_path('../../lib', __FILE__)
require 'open-uri'
require 'nokogiri'
require 'cgi'
require 'pathname'
require 'yaml'
ENV['RUBY_MIME_TYPES_LAZY_LOAD'] = 'yes'
require 'mime/types'
class IANARegistry
DEFAULTS = {
url: %q(https://www.iana.org/assignments/media-types/media-types.xml),
to: Pathname(__FILE__).join('../../type-lists')
}.freeze.each_value(&:freeze)
def self.download(options = {})
dest = Pathname(options[:to] || DEFAULTS[:to]).expand_path
url = options.fetch(:url, DEFAULTS[:url])
puts "Downloading IANA MIME type assignments."
puts "\t#{url}"
xml = Nokogiri::XML(open(url) { |f| f.read })
xml.css('registry registry').each do |registry|
next if registry.at_css('title').text == 'example'
new(registry: registry, to: dest) do |parser|
puts "Extracting #{parser.type}/*."
parser.parse
parser.save
end
end
end
attr_reader :type
def initialize(options = {})
@registry = options.fetch(:registry)
@to = Pathname(options.fetch(:to)).expand_path
@type = @registry.at_css('title').text
@name = "#{@type}.yaml"
@file = @to.join(@name)
@types = mime_types_for(@file)
yield self if block_given?
end
ASSIGNMENT_FILE_REF = "{%s=http://www.iana.org/assignments/media-types/%s}"
def parse
@registry.css('record').each do |record|
subtype = record.at_css('name').text
refs, xrefs = parse_refs_and_files(record.css('xref'), record.css('file'))
content_type = [ @type, subtype ].join('/')
obsolete = record.at_css('obsolete')
use_instead = record.at_css('deprecated').text rescue nil
types = @types.select { |t|
(t.content_type.downcase == content_type.downcase)
}
if types.empty?
MIME::Type.new(content_type) do |mt|
mt.references = %w(IANA) + refs
mt.xrefs = xrefs
mt.registered = true
mt.obsolete = obsolete if obsolete
mt.use_instead = use_instead if use_instead
@types << mt
end
else
types.each { |mt|
mt.references = %w(IANA) + refs
mt.registered = true
mt.xrefs = xrefs
mt.obsolete = obsolete if obsolete
mt.use_instead = use_instead if use_instead
}
end
end
end
def save
@to.mkpath
File.open(@file, 'wb') { |f| f.puts @types.map.to_a.sort.to_yaml }
end
private
def mime_types_for(file)
if file.exist?
MIME::Types::Loader.load_from_yaml(file)
else
MIME::Types.new
end
end
def parse_refs_and_files(refs, files)
xr = MIME::Types::Container.new
r = []
refs.each do |xref|
type, data = xref["type"], xref["data"]
# Fix some known-broken links that are actually people.
if type == 'uri'
case data
when /contact-people.htmll#Dolan\z/
type, data = "person", "Dolan"
when /contact-people.htmll#Rottmann?\z/
type, data = "person", "Frank_Rottman"
else
nil # There’s no error with this URI.
end
end
r << xref_to_ref(type, data)
xrefs[type] << data
end
files.each do |file|
file_name = if file.text == subtype
[ @type, subtype ].join('/')
else
file.text
end
if file["type"] == "template"
refs << (ASSIGNMENT_FILE_REF % [ file_name, file_name ])
end
xrefs[file["type"]] << file_name
end
r, xr
end
def ref_from_type(type, data)
case type
when 'person'
"[#{data}]"
when 'rfc'
data.upcase
when 'draft'
"DRAFT:#{data.sub(/^RFC-/, 'draft-')}"
when 'rfc-errata'
"{RFC Errata #{data}=http://www.rfc-editor.org/errata_search.php?eid=#{data}}"
when 'uri'
"{#{data}}"
else # 'text' or something else
data
end
end
end
|
