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
|
#!/usr/bin/env ruby
require 'open-uri'
require 'open3'
require 'yaml'
require 'fileutils'
Dir.chdir(__dir__)
PACKAGES = YAML.load_stream(File.read('packages.yaml'))
BASE_URL = 'https://raw.githubusercontent.com/github/linguist/master'
DIRS = {
default: %w(syntax indent compiler autoload ftplugin ctags after/syntax after/indent after/ftplugin),
all: %w(syntax indent compiler autoload ftplugin after extras ctags),
basic: %w(syntax compiler indent after/syntax after/indent),
syntax: %w(syntax indent after/syntax after/indent),
noafter: %w(syntax compiler indent autoload ftplugin),
javascript: %w(syntax indent compiler autoload ftplugin ctags after/syntax after/indent after/ftplugin extras),
go: %w(autoload/go/config.vim syntax compiler indent after/syntax after/indent)
}
def parallel(*procs)
threads = procs.map { |p| Thread.new { method(p).call } }
threads.map(&:join).map(&:value)
end
def read_strings(data, keys, print=false)
if data.is_a?(Hash)
data.flat_map do |key, val|
read_strings(val, keys, keys.include?(key))
end
elsif data.is_a?(Array)
data.flat_map { |d| read_strings(d, keys, print) }
elsif data.is_a?(String)
print ? [data] : []
else
[]
end
end
def transform_with(data, keys, transfrom=false, &block)
if data.is_a?(Hash)
Hash[data.map do |key, val|
[key, transform_with(val, keys, keys.include?(key), &block)]
end]
elsif data.is_a?(Array)
data.map { |d| transform_with(d, keys, transfrom, &block) }
elsif data.is_a?(String)
transfrom ? yield(data) : data
else
data
end
end
def each_hash(data, &block)
if data.is_a?(Hash)
yield data
data.each do |key, val|
each_hash(val, &block)
end
elsif data.is_a?(Array)
data.map { |d| each_hash(d, &block) }
end
end
def patterns_to_vim_patterns(patterns)
stdin, stdout, stderr = Open3.popen3('vim', '-V', '--clean', '/dev/stdin', '-es', '-c', "echo expand('%:p:h') | source #{__dir__}/eregex.vim", '-c', "for line in range(0, line('$')) | call setline(line, ExtendedRegex2VimRegex(getline(line))) | endfor", '-c', ':wq! /dev/stdout', chdir: __dir__)
stdin.write(patterns.join("\n"))
stdin.close
stdout.readlines
end
def transform_patterns(data)
patterns = read_strings(data, ["pattern", "patterns"])
patterns_mapping = Hash[patterns.zip(patterns_to_vim_patterns(patterns))]
transform_with(data, ["pattern", "patterns"]) { |a| patterns_mapping[a] }
end
def load_heuristics
url = "#{BASE_URL}/lib/linguist/heuristics.yml"
data = URI.open(url) { |io| YAML.load(io.read) }
each_hash(data["disambiguations"]) do |h|
if h.has_key?("named_pattern")
h["pattern"] = data["named_patterns"].fetch(h["named_pattern"])
h.delete("named_pattern")
end
end
transform_patterns(data["disambiguations"])
end
def load_languages
url = "#{BASE_URL}/lib/linguist/languages.yml"
data = URI.open(url) { |io| YAML.load(io.read) }
end
# heuristics, languages = parallel(:load_heuristics, :load_languages)
def parse_remote(remote)
match = remote.match(/(?<repo>[^@:]+)(?:@(?<branch>[^:]+))?(?::(?<path>.*))?/)
[match[:repo], match[:branch] || "master", match[:path]]
end
def copy_file(package, src, dest)
return unless [".vim", ".ctags", ".vital"].include?(File.extname(src))
FileUtils.mkdir_p(File.dirname(dest))
name = package.fetch("name")
open(src, "r") do |input|
open(dest, "a+") do |output|
if name == "jsx"
output << "if !exists('g:polyglot_disabled') || !(index(g:polyglot_disabled, 'typescript') != -1 || index(g:polyglot_disabled, 'typescript') != -1 || index(g:polyglot_disabled, 'jsx') != -1)\n\n"
else
output << "if !exists('g:polyglot_disabled') || index(g:polyglot_disabled, '#{name}') == -1\n\n"
end
IO.copy_stream(input, output)
output << "\nendif\n"
end
end
end
def download
FileUtils.rm_rf('tmp')
PACKAGES.map do |package|
Thread.new do
repo, branch, path = parse_remote(package.fetch("remote"))
dir = "tmp/" + repo.split('/')[1]
FileUtils.mkdir_p(dir)
url = "https://codeload.github.com/#{repo}/tar.gz/#{branch}"
`curl --silent -fL #{url} | tar -zx -C "#{dir}" --strip 1`
progress
end
end.map(&:join)
end
$i = 0
LYRICS = "Never gonna give you up. Never gonna let you down. " +
"Never gonna run around and desert you. " +
"Never gonna make you cry. Never gonna say goodbye. " +
"Never gonna tell a lie and hurt you."
$mutex = Mutex.new
def progress
$mutex.synchronize do
$stdout.write(LYRICS[$i] || ".")
$i += 1
end
end
def extract
FileUtils.rm_rf(DIRS[:all])
output = []
PACKAGES.map do |package|
repo, branch, path = parse_remote(package["remote"])
dir = "tmp/" + repo.split('/')[1]
subdirs = []
for subdir in DIRS.fetch(package.fetch("dirs", "default").to_sym)
subtree = "#{dir}/#{path ? path + "/" : ""}"
subpath = "#{subtree}#{subdir}"
if FileTest.directory?(subpath)
Dir.glob("#{subdir}/**/*", base: subtree).each do |p|
next unless File.file?("#{subtree}/#{p}")
copy_file(package, "#{subtree}/#{p}", p)
end
subdirs << subdir.split("/").last
elsif File.exist?(subpath)
copy_file(package, subpath, subdir)
end
end
output << "- [#{package["name"]}](https://github.com/#{repo}) (#{subdirs.uniq.join(", ")})"
progress
end
readme = File.read('README.md')
readme.gsub!(
%r{(?<=<!--Package Count-->).*?(?=<!--/Package Count-->)},
output.size.to_s
)
readme.gsub!(
%r{(?<=<!--Language Packs-->).*?(?=<!--/Language Packs-->)}m,
"\n" + output.sort.join("\n") + "\n"
)
File.write('README.md', readme)
end
download
extract
puts(" Bye! Have a wonderful time!")
FileUtils.rm_rf("tmp")
|