Class: Gem::Indexer

Inherits:
Object show all
Includes:
UserInteraction
Defined in:
lib/rubygems/indexer.rb

Overview

Top level class for building the gem repository index.

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods included from UserInteraction

#alert, #alert_error, #alert_warning, #ask, #ask_for_password, #ask_yes_no, #choose_from_list, #say, #terminate_interaction, #verbose

Methods included from DefaultUserInteraction

ui, #ui, ui=, #ui=, use_ui, #use_ui

Methods included from Text

#clean_text, #format_text, #levenshtein_distance, #min3, #truncate_text

Constructor Details

#initialize(directory, options = {}) ⇒ Indexer

Create an indexer that will index the gems in directory.



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
# File 'lib/rubygems/indexer.rb', line 45

def initialize(directory, options = {})
  require 'fileutils'
  require 'tmpdir'
  require 'zlib'

  options = { :build_modern => true }.merge options

  @build_modern = options[:build_modern]

  @dest_directory = directory
  @directory = Dir.mktmpdir 'gem_generate_index'

  marshal_name = "Marshal.#{Gem.marshal_version}"

  @master_index = File.join @directory, 'yaml'
  @marshal_index = File.join @directory, marshal_name

  @quick_dir = File.join @directory, 'quick'
  @quick_marshal_dir = File.join @quick_dir, marshal_name
  @quick_marshal_dir_base = File.join "quick", marshal_name # FIX: UGH

  @quick_index = File.join @quick_dir, 'index'
  @latest_index = File.join @quick_dir, 'latest_index'

  @specs_index = File.join @directory, "specs.#{Gem.marshal_version}"
  @latest_specs_index =
    File.join(@directory, "latest_specs.#{Gem.marshal_version}")
  @prerelease_specs_index =
    File.join(@directory, "prerelease_specs.#{Gem.marshal_version}")
  @dest_specs_index =
    File.join(@dest_directory, "specs.#{Gem.marshal_version}")
  @dest_latest_specs_index =
    File.join(@dest_directory, "latest_specs.#{Gem.marshal_version}")
  @dest_prerelease_specs_index =
    File.join(@dest_directory, "prerelease_specs.#{Gem.marshal_version}")

  @files = []
end

Instance Attribute Details

#build_modernObject

Build indexes for RubyGems 1.2.0 and newer when true



15
16
17
# File 'lib/rubygems/indexer.rb', line 15

def build_modern
  @build_modern
end

#dest_directoryObject (readonly)

Index install location



20
21
22
# File 'lib/rubygems/indexer.rb', line 20

def dest_directory
  @dest_directory
end

#dest_latest_specs_indexObject (readonly)

Latest specs index install location



30
31
32
# File 'lib/rubygems/indexer.rb', line 30

def dest_latest_specs_index
  @dest_latest_specs_index
end

#dest_prerelease_specs_indexObject (readonly)

Prerelease specs index install location



35
36
37
# File 'lib/rubygems/indexer.rb', line 35

def dest_prerelease_specs_index
  @dest_prerelease_specs_index
end

#dest_specs_indexObject (readonly)

Specs index install location



25
26
27
# File 'lib/rubygems/indexer.rb', line 25

def dest_specs_index
  @dest_specs_index
end

#directoryObject (readonly)

Index build directory



40
41
42
# File 'lib/rubygems/indexer.rb', line 40

def directory
  @directory
end

Instance Method Details

#build_indicesObject

Build various indices



87
88
89
90
91
92
93
94
# File 'lib/rubygems/indexer.rb', line 87

def build_indices
  specs = map_gems_to_specs gem_file_list
  Gem::Specification._resort! specs
  build_marshal_gemspecs specs
  build_modern_indices specs if @build_modern

  compress_indices
end

#build_marshal_gemspecs(specs) ⇒ Object

Builds Marshal quick index gemspecs.



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
# File 'lib/rubygems/indexer.rb', line 99

def build_marshal_gemspecs(specs)
  count = specs.count
  progress = ui.progress_reporter count,
                                  "Generating Marshal quick index gemspecs for #{count} gems",
                                  "Complete"

  files = []

  Gem.time 'Generated Marshal quick index gemspecs' do
    specs.each do |spec|
      next if spec.default_gem?
      spec_file_name = "#{spec.original_name}.gemspec.rz"
      marshal_name = File.join @quick_marshal_dir, spec_file_name

      marshal_zipped = Gem.deflate Marshal.dump(spec)

      File.open marshal_name, 'wb' do |io|
        io.write marshal_zipped
      end

      files << marshal_name

      progress.updated spec.original_name
    end

    progress.done
  end

  @files << @quick_marshal_dir

  files
end

#build_modern_index(index, file, name) ⇒ Object

Build a single index for RubyGems 1.2 and newer



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
# File 'lib/rubygems/indexer.rb', line 135

def build_modern_index(index, file, name)
  say "Generating #{name} index"

  Gem.time "Generated #{name} index" do
    File.open(file, 'wb') do |io|
      specs = index.map do |*spec|
        # We have to splat here because latest_specs is an array, while the
        # others are hashes.
        spec = spec.flatten.last
        platform = spec.original_platform

        # win32-api-1.0.4-x86-mswin32-60
        unless String === platform
          alert_warning "Skipping invalid platform in gem: #{spec.full_name}"
          next
        end

        platform = Gem::Platform::RUBY if platform.nil? or platform.empty?
        [spec.name, spec.version, platform]
      end

      specs = compact_specs(specs)
      Marshal.dump(specs, io)
    end
  end
end

#build_modern_indices(specs) ⇒ Object

Builds indices for RubyGems 1.2 and newer. Handles full, latest, prerelease



165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
# File 'lib/rubygems/indexer.rb', line 165

def build_modern_indices(specs)
  prerelease, released = specs.partition do |s|
    s.version.prerelease?
  end
  latest_specs =
    Gem::Specification._latest_specs specs

  build_modern_index(released.sort, @specs_index, 'specs')
  build_modern_index(latest_specs.sort, @latest_specs_index, 'latest specs')
  build_modern_index(prerelease.sort, @prerelease_specs_index,
                     'prerelease specs')

  @files += [@specs_index,
             "#{@specs_index}.gz",
             @latest_specs_index,
             "#{@latest_specs_index}.gz",
             @prerelease_specs_index,
             "#{@prerelease_specs_index}.gz"]
end

#compact_specs(specs) ⇒ Object

Compacts Marshal output for the specs index data source by using identical objects as much as possible.



233
234
235
236
237
238
239
240
241
242
243
244
245
# File 'lib/rubygems/indexer.rb', line 233

def compact_specs(specs)
  names = {}
  versions = {}
  platforms = {}

  specs.map do |(name, version, platform)|
    names[name] = name unless names.include? name
    versions[version] = version unless versions.include? version
    platforms[platform] = platform unless platforms.include? platform

    [names[name], versions[version], platforms[platform]]
  end
end

#compress(filename, extension) ⇒ Object

Compress filename with extension.



250
251
252
253
254
255
256
257
258
# File 'lib/rubygems/indexer.rb', line 250

def compress(filename, extension)
  data = Gem.read_binary filename

  zipped = Gem.deflate data

  File.open "#{filename}.#{extension}", 'wb' do |io|
    io.write zipped
  end
end

#compress_indicesObject

Compresses indices on disk – All future files should be compressed using gzip, not deflate



217
218
219
220
221
222
223
224
225
226
227
# File 'lib/rubygems/indexer.rb', line 217

def compress_indices
  say "Compressing indices"

  Gem.time 'Compressed indices' do
    if @build_modern
      gzip @specs_index
      gzip @latest_specs_index
      gzip @prerelease_specs_index
    end
  end
end

#gem_file_listObject

List of gem file names to index.



263
264
265
# File 'lib/rubygems/indexer.rb', line 263

def gem_file_list
  Gem::Util.glob_files_in_dir("*.gem", File.join(@dest_directory, "gems"))
end

#generate_indexObject

Builds and installs indices.



270
271
272
273
274
275
276
277
# File 'lib/rubygems/indexer.rb', line 270

def generate_index
  make_temp_directories
  build_indices
  install_indices
rescue SignalException
ensure
  FileUtils.rm_rf @directory
end

#gzip(filename) ⇒ Object

Zlib::GzipWriter wrapper that gzips filename on disk.



282
283
284
285
286
# File 'lib/rubygems/indexer.rb', line 282

def gzip(filename)
  Zlib::GzipWriter.open "#{filename}.gz" do |io|
    io.write Gem.read_binary(filename)
  end
end

#install_indicesObject

Install generated indices into the destination directory.



291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
# File 'lib/rubygems/indexer.rb', line 291

def install_indices
  verbose = Gem.configuration.really_verbose

  say "Moving index into production dir #{@dest_directory}" if verbose

  files = @files
  files.delete @quick_marshal_dir if files.include? @quick_dir

  if files.include? @quick_marshal_dir and not files.include? @quick_dir
    files.delete @quick_marshal_dir

    dst_name = File.join(@dest_directory, @quick_marshal_dir_base)

    FileUtils.mkdir_p File.dirname(dst_name), :verbose => verbose
    FileUtils.rm_rf dst_name, :verbose => verbose
    FileUtils.mv(@quick_marshal_dir, dst_name,
                 :verbose => verbose, :force => true)
  end

  files = files.map do |path|
    path.sub(/^#{Regexp.escape @directory}\/?/, '') # HACK?
  end

  files.each do |file|
    src_name = File.join @directory, file
    dst_name = File.join @dest_directory, file

    FileUtils.rm_rf dst_name, :verbose => verbose
    FileUtils.mv(src_name, @dest_directory,
                 :verbose => verbose, :force => true)
  end
end

#make_temp_directoriesObject

Make directories for index generation



327
328
329
330
331
# File 'lib/rubygems/indexer.rb', line 327

def make_temp_directories
  FileUtils.rm_rf @directory
  FileUtils.mkdir_p @directory, :mode => 0700
  FileUtils.mkdir_p @quick_marshal_dir
end

#map_gems_to_specs(gems) ⇒ Object



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
# File 'lib/rubygems/indexer.rb', line 185

def map_gems_to_specs(gems)
  gems.map do |gemfile|
    if File.size(gemfile) == 0
      alert_warning "Skipping zero-length gem: #{gemfile}"
      next
    end

    begin
      spec = Gem::Package.new(gemfile).spec
      spec.loaded_from = gemfile

      spec.abbreviate
      spec.sanitize

      spec
    rescue SignalException
      alert_error "Received signal, exiting"
      raise
    rescue Exception => e
      msg = ["Unable to process #{gemfile}",
             "#{e.message} (#{e.class})",
             "\t#{e.backtrace.join "\n\t"}"].join("\n")
      alert_error msg
    end
  end.compact
end

#paranoid(path, extension) ⇒ Object

Ensure path and path with extension are identical.



336
337
338
339
340
341
342
343
# File 'lib/rubygems/indexer.rb', line 336

def paranoid(path, extension)
  data = Gem.read_binary path
  compressed_data = Gem.read_binary "#{path}.#{extension}"

  unless data == Gem::Util.inflate(compressed_data)
    raise "Compressed file #{compressed_path} does not match uncompressed file #{path}"
  end
end

#update_indexObject

Perform an in-place update of the repository from newly added gems.



348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
# File 'lib/rubygems/indexer.rb', line 348

def update_index
  make_temp_directories

  specs_mtime = File.stat(@dest_specs_index).mtime
  newest_mtime = Time.at 0

  updated_gems = gem_file_list.select do |gem|
    gem_mtime = File.stat(gem).mtime
    newest_mtime = gem_mtime if gem_mtime > newest_mtime
    gem_mtime >= specs_mtime
  end

  if updated_gems.empty?
    say 'No new gems'
    terminate_interaction 0
  end

  specs = map_gems_to_specs updated_gems
  prerelease, released = specs.partition {|s| s.version.prerelease? }

  files = build_marshal_gemspecs specs

  Gem.time 'Updated indexes' do
    update_specs_index released, @dest_specs_index, @specs_index
    update_specs_index released, @dest_latest_specs_index, @latest_specs_index
    update_specs_index(prerelease,
                       @dest_prerelease_specs_index,
                       @prerelease_specs_index)
  end

  compress_indices

  verbose = Gem.configuration.really_verbose

  say "Updating production dir #{@dest_directory}" if verbose

  files << @specs_index
  files << "#{@specs_index}.gz"
  files << @latest_specs_index
  files << "#{@latest_specs_index}.gz"
  files << @prerelease_specs_index
  files << "#{@prerelease_specs_index}.gz"

  files = files.map do |path|
    path.sub(/^#{Regexp.escape @directory}\/?/, '') # HACK?
  end

  files.each do |file|
    src_name = File.join @directory, file
    dst_name = File.join @dest_directory, file # REFACTOR: duped above

    FileUtils.mv src_name, dst_name, :verbose => verbose,
                 :force => true

    File.utime newest_mtime, newest_mtime, dst_name
  end
end

#update_specs_index(index, source, dest) ⇒ Object

Combines specs in index and source then writes out a new copy to dest. For a latest index, does not ensure the new file is minimal.



410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
# File 'lib/rubygems/indexer.rb', line 410

def update_specs_index(index, source, dest)
  specs_index = Marshal.load Gem.read_binary(source)

  index.each do |spec|
    platform = spec.original_platform
    platform = Gem::Platform::RUBY if platform.nil? or platform.empty?
    specs_index << [spec.name, spec.version, platform]
  end

  specs_index = compact_specs specs_index.uniq.sort

  File.open dest, 'wb' do |io|
    Marshal.dump specs_index, io
  end
end