Class: LibGems::Indexer

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

Overview

Top level class for building the gem repository index.

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods included from UserInteraction

#methname

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.



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
 
# File 'lib/libgems/indexer.rb', line 59

def initialize(directory, options = {})
  unless defined?(Builder::XChar) then
    raise "LibGems::Indexer requires that the XML Builder library be installed:" \
         "\n\tgem install builder"
  end

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

  @build_legacy = options[:build_legacy]
  @build_modern = options[:build_modern]

  @rss_title = options[:rss_title]
  @rss_host = options[:rss_host]
  @rss_gems_host = options[:rss_gems_host]

  @dest_directory = directory
  @directory = File.join Dir.tmpdir, "gem_generate_index_#{$$}"

  marshal_name = "Marshal.#{LibGems.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_index = File.join @quick_dir, 'index'
  @latest_index = File.join @quick_dir, 'latest_index'

  @specs_index = File.join @directory, "specs.#{LibGems.marshal_version}"
  @latest_specs_index = File.join @directory,
                                  "latest_specs.#{LibGems.marshal_version}"
  @prerelease_specs_index = File.join(@directory,
                                      "prerelease_specs.#{LibGems.marshal_version}")

  @dest_specs_index = File.join @dest_directory,
                                "specs.#{LibGems.marshal_version}"
  @dest_latest_specs_index = File.join @dest_directory,
                                       "latest_specs.#{LibGems.marshal_version}"
  @dest_prerelease_specs_index = File.join @dest_directory,
                                          "prerelease_specs.#{LibGems.marshal_version}"

  @rss_index = File.join @directory, 'index.rss'

  @files = []
end

Instance Attribute Details

#build_legacy ⇒ Object

Build indexes for SlimGems older than 1.2.0 when true



24
25
26
 
# File 'lib/libgems/indexer.rb', line 24

def build_legacy
  @build_legacy
end

#build_modern ⇒ Object

Build indexes for SlimGems 1.2.0 and newer when true



29
30
31
 
# File 'lib/libgems/indexer.rb', line 29

def build_modern
  @build_modern
end

#dest_directory ⇒ Object (readonly)

Index install location



34
35
36
 
# File 'lib/libgems/indexer.rb', line 34

def dest_directory
  @dest_directory
end

#dest_latest_specs_index ⇒ Object (readonly)

Latest specs index install location



44
45
46
 
# File 'lib/libgems/indexer.rb', line 44

def dest_latest_specs_index
  @dest_latest_specs_index
end

#dest_prerelease_specs_index ⇒ Object (readonly)

Prerelease specs index install location



49
50
51
 
# File 'lib/libgems/indexer.rb', line 49

def dest_prerelease_specs_index
  @dest_prerelease_specs_index
end

#dest_specs_index ⇒ Object (readonly)

Specs index install location



39
40
41
 
# File 'lib/libgems/indexer.rb', line 39

def dest_specs_index
  @dest_specs_index
end

#directory ⇒ Object (readonly)

Index build directory



54
55
56
 
# File 'lib/libgems/indexer.rb', line 54

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.



113
114
115
116
117
118
119
120
 
# File 'lib/libgems/indexer.rb', line 113

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

#build_indicies(index) ⇒ Object

Build various indicies



125
126
127
128
129
130
131
132
133
 
# File 'lib/libgems/indexer.rb', line 125

def build_indicies(index)
  # Marshal gemspecs are used by both modern and legacy SlimGems
  build_marshal_gemspecs index
  build_legacy_indicies index if @build_legacy
  build_modern_indicies index if @build_modern
  build_rss index

  compress_indicies
end

#build_legacy_indicies(index) ⇒ Object

Builds indicies for SlimGems older than 1.2.x



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
198
199
200
201
202
203
204
205
206
207
208
209
210
211
 
# File 'lib/libgems/indexer.rb', line 138

def build_legacy_indicies(index)
  progress = ui.progress_reporter index.size,
                                  "Generating YAML quick index gemspecs for #{index.size} gems",
                                  "Complete"

  LibGems.time 'Generated YAML quick index gemspecs' do
    index.released_gems.each do |original_name, spec|
      spec_file_name = "#{original_name}.gemspec.rz"
      yaml_name = File.join @quick_dir, spec_file_name

      yaml_zipped = LibGems.deflate spec.to_yaml
      open yaml_name, 'wb' do |io| io.write yaml_zipped end

      progress.updated original_name
    end

    progress.done
  end

  say "Generating quick index"

  LibGems.time 'Generated quick index' do
    open @quick_index, 'wb' do |io|
      io.puts index.sort.map { |_, spec| spec.original_name }
    end
  end

  say "Generating latest index"

  LibGems.time 'Generated latest index' do
    open @latest_index, 'wb' do |io|
      io.puts index.latest_specs.sort.map { |spec| spec.original_name }
    end
  end

  # Don't need prerelease legacy index

  say "Generating Marshal master index"

  LibGems.time 'Generated Marshal master index' do
    open @marshal_index, 'wb' do |io|
      io.write index.dump
    end
  end

  progress = ui.progress_reporter index.size,
                                  "Generating YAML master index for #{index.size} gems (this may take a while)",
                                  "Complete"

  LibGems.time 'Generated YAML master index' do
    open @master_index, 'wb' do |io|
      io.puts "--- !ruby/object:#{index.class}"
      io.puts "gems:"

      gems = index.sort_by { |name, gemspec| gemspec.sort_obj }
      gems.each do |original_name, gemspec|
        yaml = gemspec.to_yaml.gsub(/^/, '    ')
        yaml = yaml.sub(/\A    ---/, '') # there's a needed extra ' ' here
        io.print "  #{original_name}:"
        io.puts yaml

        progress.updated original_name
      end
    end

    progress.done
  end

  @files << @quick_dir
  @files << @master_index
  @files << "#{@master_index}.Z"
  @files << @marshal_index
  @files << "#{@marshal_index}.Z"
end

#build_marshal_gemspecs(index) ⇒ Object

Builds Marshal quick index gemspecs.



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
 
# File 'lib/libgems/indexer.rb', line 216

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

  files = []

  LibGems.time 'Generated Marshal quick index gemspecs' do
    index.gems.each do |original_name, spec|
      spec_file_name = "#{original_name}.gemspec.rz"
      marshal_name = File.join @quick_marshal_dir, spec_file_name

      marshal_zipped = LibGems.deflate Marshal.dump(spec)
      open marshal_name, 'wb' do |io| io.write marshal_zipped end

      files << marshal_name

      progress.updated original_name
    end

    progress.done
  end

  @files << @quick_marshal_dir

  files
end

#build_modern_index(index, file, name) ⇒ Object

Build a single index for SlimGems 1.2 and newer



247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
 
# File 'lib/libgems/indexer.rb', line 247

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

  LibGems.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. See the TODO in source_index.rb
        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 = LibGems::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(index) ⇒ Object

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



277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
 
# File 'lib/libgems/indexer.rb', line 277

def build_modern_indicies(index)
  build_modern_index(index.released_specs.sort, @specs_index, 'specs')
  build_modern_index(index.latest_specs.sort,
                     @latest_specs_index,
                     'latest specs')
  build_modern_index(index.prerelease_specs.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

#build_rss(index) ⇒ Object

Builds an RSS feed for past two days gem releases according to the gem’s date.



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
323
324
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
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
 
# File 'lib/libgems/indexer.rb', line 298

def build_rss(index)
  if @rss_host.nil? or @rss_gems_host.nil? then
    if LibGems.configuration.really_verbose then
      alert_warning "no --rss-host or --rss-gems-host, RSS generation disabled"
    end
    return
  end

  require 'cgi'
  require 'libgems/text'

  extend LibGems::Text

  LibGems.time 'Generated rss' do
    open @rss_index, 'wb' do |io|
      rss_host = CGI.escapeHTML @rss_host
      rss_title = CGI.escapeHTML(@rss_title || 'gems')

      io.puts <<-HEADER
<?xml version="1.0"?>
<rss version="2.0">
<channel>
  <title>#{rss_title}</title>
  <link>http://#{rss_host}</link>
  <description>Recently released gems from http://#{rss_host}</description>
  <generator>#{LibGems::NAME} v#{LibGems::LIBGEMS_VERSION} (RubyGems v#{LibGems::VERSION})</generator>
  <docs>http://cyber.law.harvard.edu/rss/rss.html</docs>
      HEADER

      today = LibGems::Specification::TODAY
      yesterday = today - 86400

      index = index.select do |_, spec|
        spec_date = spec.date

        case spec_date
        when Date
          Time.parse(spec_date.to_s) >= yesterday
        when Time
          spec_date >= yesterday
        end
      end

      index = index.select do |_, spec|
        spec_date = spec.date

        case spec_date
        when Date
          Time.parse(spec_date.to_s) <= today
        when Time
          spec_date <= today
        end
      end

      index.sort_by { |_, spec| [-spec.date.to_i, spec] }.each do |_, spec|
        gem_path = CGI.escapeHTML "http://#{@rss_gems_host}/gems/#{spec.file_name}"
        size = File.stat(spec.loaded_from).size rescue next

        description = spec.description || spec.summary || ''
        authors = Array spec.authors
        emails = Array spec.email
        authors = emails.zip(authors).map do |email, author|
          email += " (#{author})" if author and not author.empty?
        end.join ', '

        description = description.split(/\n\n+/).map do |chunk|
          format_text chunk, 78
        end

        description = description.join "\n\n"

        item = ''

        item << <<-ITEM
  <item>
    <title>#{CGI.escapeHTML spec.full_name}</title>
    <description>
&lt;pre&gt;#{CGI.escapeHTML description.chomp}&lt;/pre&gt;
    </description>
    <author>#{CGI.escapeHTML authors}</author>
    <guid>#{CGI.escapeHTML spec.full_name}</guid>
    <enclosure url=\"#{gem_path}\"
               length=\"#{size}\" type=\"application/octet-stream\" />
    <pubDate>#{spec.date.rfc2822}</pubDate>
        ITEM

        item << <<-ITEM if spec.homepage
    <link>#{CGI.escapeHTML spec.homepage}</link>
        ITEM

        item << <<-ITEM
  </item>
        ITEM

        io.puts item
      end

      io.puts <<-FOOTER
</channel>
</rss>
      FOOTER
    end
  end

  @files << @rss_index
end

#collect_specs(gems = gem_file_list) ⇒ Object

Collect specifications from .gem files from the gem directory.



408
409
410
411
412
413
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
 
# File 'lib/libgems/indexer.rb', line 408

def collect_specs(gems = gem_file_list)
  index = LibGems::SourceIndex.new

  progress = ui.progress_reporter gems.size,
                                  "Loading #{gems.size} gems from #{@dest_directory}",
                                  "Loaded all gems"

  LibGems.time 'loaded' do
    gems.each do |gemfile|
      if File.size(gemfile.to_s) == 0 then
        alert_warning "Skipping zero-length gem: #{gemfile}"
        next
      end

      begin
        spec = LibGems::Format.from_file_by_path(gemfile).spec
        spec.loaded_from = gemfile

        unless gemfile =~ /\/#{Regexp.escape spec.original_name}.*\.gem\z/i then
          expected_name = spec.full_name
          expected_name << " (#{spec.original_name})" if
            spec.original_name != spec.full_name
          alert_warning "Skipping misnamed gem: #{gemfile} should be named #{expected_name}"
          next
        end

        abbreviate spec
        sanitize spec

        index.add_spec spec, spec.original_name

        progress.updated spec.original_name

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

    progress.done
  end

  index
end

#compact_specs(specs) ⇒ Object

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



490
491
492
493
494
495
496
497
498
499
500
501
502
 
# File 'lib/libgems/indexer.rb', line 490

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.



507
508
509
510
511
512
513
514
515
 
# File 'lib/libgems/indexer.rb', line 507

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

  zipped = LibGems.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



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
 
# File 'lib/libgems/indexer.rb', line 460

def compress_indicies
  say "Compressing indicies"

  LibGems.time 'Compressed indicies' do
    if @build_legacy then
      compress @quick_index, 'rz'
      paranoid @quick_index, 'rz'

      compress @latest_index, 'rz'
      paranoid @latest_index, 'rz'

      compress @marshal_index, 'Z'
      paranoid @marshal_index, 'Z'

      compress @master_index, 'Z'
      paranoid @master_index, 'Z'
    end

    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.



520
521
522
 
# File 'lib/libgems/indexer.rb', line 520

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

#generate_index ⇒ Object

Builds and installs indicies.



527
528
529
530
531
532
533
534
535
 
# File 'lib/libgems/indexer.rb', line 527

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

#gzip(filename) ⇒ Object

Zlib::GzipWriter wrapper that gzips filename on disk.



540
541
542
543
544
 
# File 'lib/libgems/indexer.rb', line 540

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

#install_indicies ⇒ Object

Install generated indicies into the destination directory.



549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
 
# File 'lib/libgems/indexer.rb', line 549

def install_indicies
  verbose = LibGems.configuration.really_verbose

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

  files = @files.dup
  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
    quick_marshal_dir = @quick_marshal_dir.sub @directory, ''

    dst_name = File.join @dest_directory, quick_marshal_dir

    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 @directory, ''
  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



587
588
589
590
591
 
# File 'lib/libgems/indexer.rb', line 587

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

#paranoid(path, extension) ⇒ Object

Ensure path and path with extension are identical.



596
597
598
599
600
601
602
603
 
# File 'lib/libgems/indexer.rb', line 596

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

  unless data == LibGems.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.



610
611
612
613
614
615
616
617
 
# File 'lib/libgems/indexer.rb', line 610

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.



622
623
624
625
626
627
628
629
630
631
632
633
634
635
 
# File 'lib/libgems/indexer.rb', line 622

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 gempsec
  # 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. Only works for modern indicies, and sets #build_legacy to false when run.



641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
 
# File 'lib/libgems/indexer.rb', line 641

def update_index
  @build_legacy = false

  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

  index = collect_specs updated_gems

  files = build_marshal_gemspecs index

  LibGems.time 'Updated indexes' do
    update_specs_index index.released_gems, @dest_specs_index, @specs_index
    update_specs_index index.released_gems, @dest_latest_specs_index, @latest_specs_index
    update_specs_index(index.prerelease_gems, @dest_prerelease_specs_index,
                       @prerelease_specs_index)
  end

  compress_indicies

  verbose = LibGems.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 @directory, ''
  end

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

    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.



703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
 
# File 'lib/libgems/indexer.rb', line 703

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

  index.each do |_, spec|
    platform = spec.original_platform
    platform = LibGems::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