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

Methods included from UserInteraction

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

Methods included from DefaultUserInteraction

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

Constructor Details

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

Create an indexer that will index the gems in directory.



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

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

  unless defined?(Builder::XChar) then
    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]

  @dest_directory = directory
  @directory = File.join(Dir.tmpdir, "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_modern ⇒ Object

Build indexes for RubyGems 1.2.0 and newer when true



21
22
23
 
# File 'lib/rubygems/indexer.rb', line 21

def build_modern
  @build_modern
end

#dest_directory ⇒ Object (readonly)

Index install location



26
27
28
 
# File 'lib/rubygems/indexer.rb', line 26

def dest_directory
  @dest_directory
end

#dest_latest_specs_index ⇒ Object (readonly)

Latest specs index install location



36
37
38
 
# File 'lib/rubygems/indexer.rb', line 36

def dest_latest_specs_index
  @dest_latest_specs_index
end

#dest_prerelease_specs_index ⇒ Object (readonly)

Prerelease specs index install location



41
42
43
 
# File 'lib/rubygems/indexer.rb', line 41

def dest_prerelease_specs_index
  @dest_prerelease_specs_index
end

#dest_specs_index ⇒ Object (readonly)

Specs index install location



31
32
33
 
# File 'lib/rubygems/indexer.rb', line 31

def dest_specs_index
  @dest_specs_index
end

#directory ⇒ Object (readonly)

Index build directory



46
47
48
 
# File 'lib/rubygems/indexer.rb', line 46

def directory
  @directory
end

Instance Method Details

#abbreviate(spec) ⇒ Object

Abbreviate the spec for downloading. Abbreviated specs are only used for searching, downloading and related activities and do not need deployment specific information (e.g. list of files). So we abbreviate the spec, making it much smaller for quicker downloads. – TODO move to Gem::Specification



103
104
105
106
107
108
109
110
 
# File 'lib/rubygems/indexer.rb', line 103

def abbreviate(spec)
  spec.files = []
  spec.test_files = []
  spec.rdoc_options = []
  spec.extra_rdoc_files = []
  spec.cert_chain = []
  spec
end

#build_indicies ⇒ Object

Build various indicies



115
116
117
118
119
120
121
122
123
 
# File 'lib/rubygems/indexer.rb', line 115

def build_indicies
  Gem::Specification.dirs = []
  Gem::Specification.add_specs(*map_gems_to_specs(gem_file_list))

  build_marshal_gemspecs
  build_modern_indicies if @build_modern

  compress_indicies
end

#build_marshal_gemspecs ⇒ Object

Builds Marshal quick index gemspecs.



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
 
# File 'lib/rubygems/indexer.rb', line 128

def build_marshal_gemspecs
  count = Gem::Specification.count
  progress = ui.progress_reporter count,
                                  "Generating Marshal quick index gemspecs for #{count} gems",
                                  "Complete"

  files = []

  Gem.time 'Generated Marshal quick index gemspecs' do
    Gem::Specification.each do |spec|
      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)
      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



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
 
# File 'lib/rubygems/indexer.rb', line 160

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

  Gem.time "Generated #{name} index" do
    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 then
          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_indicies ⇒ Object

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



190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
 
# File 'lib/rubygems/indexer.rb', line 190

def build_modern_indicies
  prerelease, released = Gem::Specification.partition { |s|
    s.version.prerelease?
  }
  latest_specs = Gem::Specification.latest_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.



267
268
269
270
271
272
273
274
275
276
277
278
279
 
# File 'lib/rubygems/indexer.rb', line 267

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.



284
285
286
287
288
289
290
291
292
 
# File 'lib/rubygems/indexer.rb', line 284

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

  zipped = Gem.deflate data

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

#compress_indicies ⇒ Object

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



251
252
253
254
255
256
257
258
259
260
261
 
# File 'lib/rubygems/indexer.rb', line 251

def compress_indicies
  say "Compressing indicies"

  Gem.time 'Compressed indicies' do
    if @build_modern then
      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.



297
298
299
 
# File 'lib/rubygems/indexer.rb', line 297

def gem_file_list
  Dir[File.join(@dest_directory, "gems", '*.gem')]
end

#generate_index ⇒ Object

Builds and installs indicies.



304
305
306
307
308
309
310
311
 
# File 'lib/rubygems/indexer.rb', line 304

def generate_index
  make_temp_directories
  build_indicies
  install_indicies
rescue SignalException
ensure
  FileUtils.rm_rf @directory
end

#gzip(filename) ⇒ Object

Zlib::GzipWriter wrapper that gzips filename on disk.



316
317
318
319
320
 
# File 'lib/rubygems/indexer.rb', line 316

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

#install_indicies ⇒ Object

Install generated indicies into the destination directory.



325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
 
# File 'lib/rubygems/indexer.rb', line 325

def install_indicies
  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 then
    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_directories ⇒ Object

Make directories for index generation



361
362
363
364
365
 
# File 'lib/rubygems/indexer.rb', line 361

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 



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
239
240
241
242
243
244
 
# File 'lib/rubygems/indexer.rb', line 209

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

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

      # HACK: fuck this shit - borks all tests that use pl1
      # if File.basename(gemfile, ".gem") != spec.original_name then
      #   exp = spec.full_name
      #   exp << " (#{spec.original_name})" if
      #     spec.original_name != spec.full_name
      #   msg = "Skipping misnamed gem: #{gemfile} should be named #{exp}"
      #   alert_warning msg
      #   next
      # end

      abbreviate spec
      sanitize spec

      spec
    rescue SignalException => e
      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
  }.compact
end

#paranoid(path, extension) ⇒ Object

Ensure path and path with extension are identical.



370
371
372
373
374
375
376
377
 
# File 'lib/rubygems/indexer.rb', line 370

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

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

#sanitize(spec) ⇒ Object

Sanitize the descriptive fields in the spec. Sometimes non-ASCII characters will garble the site index. Non-ASCII characters will be replaced by their XML entity equivalent.



384
385
386
387
388
389
390
391
 
# File 'lib/rubygems/indexer.rb', line 384

def sanitize(spec)
  spec.summary              = sanitize_string(spec.summary)
  spec.description          = sanitize_string(spec.description)
  spec.post_install_message = sanitize_string(spec.post_install_message)
  spec.authors              = spec.authors.collect { |a| sanitize_string(a) }

  spec
end

#sanitize_string(string) ⇒ Object

Sanitize a single string.



396
397
398
399
400
401
402
403
404
405
406
407
408
409
 
# File 'lib/rubygems/indexer.rb', line 396

def sanitize_string(string)
  return string unless string

  # HACK the #to_s is in here because RSpec has an Array of Arrays of
  # Strings for authors.  Need a way to disallow bad values on gemspec
  # generation.  (Probably won't happen.)
  string = string.to_s

  begin
    Builder::XChar.encode string
  rescue NameError, NoMethodError
    string.to_xs
  end
end

#update_index ⇒ Object

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



414
415
416
417
418
419
420
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
 
# File 'lib/rubygems/indexer.rb', line 414

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? then
    say 'No new gems'
    terminate_interaction 0
  end

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

  Gem::Specification.dirs = []
  Gem::Specification.add_specs(*specs)

  files = build_marshal_gemspecs

  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_indicies

  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.



479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
 
# File 'lib/rubygems/indexer.rb', line 479

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

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