Class: Gem::Indexer

Inherits:
Object
  • 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

Constructor Details

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

Create an indexer that will index the gems in directory.



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
 
# File 'lib/rubygems/indexer.rb', line 60

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

  if Gem::VERSION < "3.2.0" && !defined?(Builder::XChar)
    raise "Gem::Indexer requires that the XML Builder library be installed:" \
          "\n\tgem install builder"
  end

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

  @build_modern = options[:build_modern]
  @build_compact = options[:build_compact]

  @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_compact ⇒ Object

Build compact index files when true



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

def build_compact
  @build_compact
end

#build_modern ⇒ Object

Build indexes for RubyGems 1.2.0 and newer when true



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

def build_modern
  @build_modern
end

#dest_directory ⇒ Object (readonly)

Index install location



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

def dest_directory
  @dest_directory
end

#dest_latest_specs_index ⇒ Object (readonly)

Latest specs index install location



45
46
47
 
# File 'lib/rubygems/indexer.rb', line 45

def dest_latest_specs_index
  @dest_latest_specs_index
end

#dest_prerelease_specs_index ⇒ Object (readonly)

Prerelease specs index install location



50
51
52
 
# File 'lib/rubygems/indexer.rb', line 50

def dest_prerelease_specs_index
  @dest_prerelease_specs_index
end

#dest_specs_index ⇒ Object (readonly)

Specs index install location



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

def dest_specs_index
  @dest_specs_index
end

#directory ⇒ Object (readonly)

Index build directory



55
56
57
 
# File 'lib/rubygems/indexer.rb', line 55

def directory
  @directory
end

Instance Method Details

#build_compact_index(specs) ⇒ Object

Builds compact index files



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
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
 
# File 'lib/rubygems/indexer.rb', line 210

def build_compact_index(specs)
  gems = compact_index_gems(specs)

  progress = ui.progress_reporter gems.count + 2,
    "Generating compact index files for #{gems.count} gems",
    "Complete"

  Gem.time "Generated compact index files" do
    info_dir = File.join(@directory, "info")
    FileUtils.mkdir_p info_dir

    gems.each do |gem|
      info = CompactIndex.info(gem.versions)

      info_checksum = Digest::MD5.hexdigest(info)
      gem[:versions].last[:info_checksum] = info_checksum

      info_path = File.join(@directory, "info", gem.name)
      if File.exist?(info_path)
        raise "info file already exists: #{info_path}"
      end

      File.open(info_path, "wb") do |io|
        io.write info
      end

      progress.updated "/info/#{gem.name}"
    end

    File.open(File.join(@directory, "names"), "wb") do |io|
      io.write CompactIndex.names(gems.map(&:name))
    end
    progress.updated "/names"

    CompactIndex::VersionsFile.new(
      File.join(@directory, "versions")
    ).create(
      gems,
    )

    progress.updated "/versions"

    @files << info_dir << File.join(@directory, "names") << File.join(@directory, "versions")

    progress.done
  end
end

#build_indices ⇒ Object

Build various indices



108
109
110
111
112
113
114
115
116
 
# File 'lib/rubygems/indexer.rb', line 108

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
  build_compact_index specs if @build_compact

  compress_indices
end

#build_marshal_gemspecs(specs) ⇒ Object

Builds Marshal quick index gemspecs.



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
 
# File 'lib/rubygems/indexer.rb', line 121

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



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
 
# File 'lib/rubygems/indexer.rb', line 157

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? || 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



187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
 
# File 'lib/rubygems/indexer.rb', line 187

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_index_gems(specs) ⇒ Object 



568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
 
# File 'lib/rubygems/indexer.rb', line 568

def compact_index_gems(specs)
  versions_by_name = Hash.new {|h, k| h[k] = [] }
  specs.each do |spec|
    checksum = spec.loaded_from && Digest::SHA256.file(spec.loaded_from).base64digest!
    versions_by_name[spec.name] << CompactIndex::GemVersion.new(
      spec.version.version,
      spec.platform.to_s,
      checksum,
      nil, # info_checksum
      spec.runtime_dependencies.map {|d| CompactIndex::Dependency.new(d.name, d.requirement.to_s) },
      spec.required_ruby_version&.to_s,
      spec.required_rubygems_version&.to_s
    )
  end
  versions_by_name.map do |name, versions|
    versions.sort!
    CompactIndex::Gem.new(name, versions)
  end.tap(&:sort!)
end

#compact_specs(specs) ⇒ Object

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



306
307
308
309
310
311
312
313
314
315
316
317
318
 
# File 'lib/rubygems/indexer.rb', line 306

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.



323
324
325
326
327
328
329
330
331
 
# File 'lib/rubygems/indexer.rb', line 323

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_indices ⇒ Object

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



290
291
292
293
294
295
296
297
298
299
300
 
# File 'lib/rubygems/indexer.rb', line 290

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_list ⇒ Object

List of gem file names to index.



336
337
338
 
# File 'lib/rubygems/indexer.rb', line 336

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

#generate_index ⇒ Object

Builds and installs indices.



343
344
345
346
347
348
349
350
 
# File 'lib/rubygems/indexer.rb', line 343

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.



355
356
357
358
359
 
# File 'lib/rubygems/indexer.rb', line 355

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

#install_indices ⇒ Object

Install generated indices into the destination directory.



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
 
# File 'lib/rubygems/indexer.rb', line 364

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) && !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(%r{^#{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_directories ⇒ Object

Make directories for index generation



400
401
402
403
404
 
# File 'lib/rubygems/indexer.rb', line 400

def make_temp_directories
  FileUtils.rm_rf @directory
  FileUtils.mkdir_p @directory, :mode => 0o700
  FileUtils.mkdir_p @quick_marshal_dir
end

#map_gems_to_specs(gems) ⇒ Object 



258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
 
# File 'lib/rubygems/indexer.rb', line 258

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 StandardError => 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.



409
410
411
412
413
414
415
416
 
# File 'lib/rubygems/indexer.rb', line 409

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_compact_index(new_specs, source, dest) ⇒ Object

Combines specs in index and source then writes out a new compact index to dest.



511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
 
# File 'lib/rubygems/indexer.rb', line 511

def update_compact_index(new_specs, source, dest)
  files = []
  source_versions_path = File.join(source, "versions")
  versions_file = CompactIndex::VersionsFile.new source_versions_path

  gems = compact_index_gems new_specs

  FileUtils.mkdir_p File.join(dest, "info")

  new_names = []
  gems.each do |gem|
    existing_info_path = File.join(source, "info", gem.name)
    if File.exist? existing_info_path
      info = Gem.read_binary(existing_info_path) +
             CompactIndex.info(gem.versions).sub(/\A---\n/, "")
    else
      new_names << gem.name
      info = CompactIndex.info gem.versions
    end

    info_checksum = Digest::MD5.hexdigest(info)
    gem[:versions].last[:info_checksum] = info_checksum

    info_path = File.join(dest, "info", gem.name)
    if File.exist?(info_path)
      raise "info file already exists: #{info_path}"
    end

    File.open(info_path, "wb") do |io|
      io.write info
    end
    files << info_path
  end

  versions_path = File.join(dest, "versions")
  File.open(versions_path, "wb") do |io|
    io.write versions_file.contents(gems)
  end
  files << versions_path

  unless new_names.empty?
    old_names = Gem.read_binary(File.join(source, "names")).lines(chomp: true)[2..]
    names_path = File.join(dest, "names")

    names = old_names + new_names
    names.sort!

    File.open(names_path, "wb") do |io|
      io.write CompactIndex.names(names)
    end

    files << names_path
  end

  files
end

#update_index ⇒ Object

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



421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
 
# File 'lib/rubygems/indexer.rb', line 421

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

  if @build_compact
    Gem.time "Updated compact index files" do
      files += update_compact_index released, @dest_directory, @directory
    end
  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(%r{^#{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
ensure
  FileUtils.rm_rf @directory
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.



491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
 
# File 'lib/rubygems/indexer.rb', line 491

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? || 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