Class: Wp2txt::DumpManager

Inherits:
Object
  • Object
show all
Defined in:
lib/wp2txt/multistream.rb

Overview

Manages downloading and caching of dump files Supports any Wikipedia language code (e.g., en, ja, de, fr, zh, ar, etc.) Language metadata is stored in lib/wp2txt/data/language_metadata.json

Constant Summary collapse

DUMP_BASE_URL = 
"https://dumps.wikimedia.org"
DEFAULT_CACHE_DIR = 
File.expand_path("~/.wp2txt/cache")
CACHE_DIR =

Legacy constant for backward compatibility

"tmp/dump_cache"

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(lang, cache_dir: nil, dump_expiry_days: nil) ⇒ DumpManager

Returns a new instance of DumpManager.



438
439
440
441
442
443
 
# File 'lib/wp2txt/multistream.rb', line 438

def initialize(lang, cache_dir: nil, dump_expiry_days: nil)
  @lang = lang.to_sym
  @cache_dir = cache_dir || DEFAULT_CACHE_DIR
  @dump_expiry_days = dump_expiry_days || Wp2txt::DEFAULT_DUMP_EXPIRY_DAYS
  FileUtils.mkdir_p(@cache_dir)
end

Instance Attribute Details

#cache_dir ⇒ Object (readonly)

Returns the value of attribute cache_dir.



429
430
431
 
# File 'lib/wp2txt/multistream.rb', line 429

def cache_dir
  @cache_dir
end

#dump_expiry_days ⇒ Object (readonly)

Returns the value of attribute dump_expiry_days.



429
430
431
 
# File 'lib/wp2txt/multistream.rb', line 429

def dump_expiry_days
  @dump_expiry_days
end

#lang ⇒ Object (readonly)

Returns the value of attribute lang.



429
430
431
 
# File 'lib/wp2txt/multistream.rb', line 429

def lang
  @lang
end

Class Method Details

.all_cache_status(cache_dir = DEFAULT_CACHE_DIR) ⇒ Object

Get status for all cached languages



886
887
888
889
890
891
892
893
894
895
896
897
898
 
# File 'lib/wp2txt/multistream.rb', line 886

def self.all_cache_status(cache_dir = DEFAULT_CACHE_DIR)
  return {} unless File.exist?(cache_dir)

  status = {}
  Dir.glob(File.join(cache_dir, "*wiki")).each do |lang_dir|
    lang = File.basename(lang_dir).sub(/wiki$/, "").to_sym
    manager = new(lang, cache_dir: cache_dir)
    status[lang] = manager.cache_status
  rescue IOError, Errno::ENOENT, Errno::EACCES, JSON::ParserError => e
    status[lang] = { error: e.message }
  end
  status
end

.clear_all_cache!(cache_dir = DEFAULT_CACHE_DIR) ⇒ Object

Clear all cache



881
882
883
 
# File 'lib/wp2txt/multistream.rb', line 881

def self.clear_all_cache!(cache_dir = DEFAULT_CACHE_DIR)
  FileUtils.rm_rf(cache_dir) if File.exist?(cache_dir)
end

.default_cache_dir ⇒ Object

Get default cache directory



433
434
435
 
# File 'lib/wp2txt/multistream.rb', line 433

def default_cache_dir
  DEFAULT_CACHE_DIR
end

Instance Method Details

#cache_age_days ⇒ Object

Get cache age in days Returns nil if no cache exists



842
843
844
 
# File 'lib/wp2txt/multistream.rb', line 842

def cache_age_days
  Wp2txt.file_age_days(cached_index_path)
end

#cache_fresh?(days = nil) ⇒ Boolean

Check if cache is fresh (within configured days)

Returns:

  • (Boolean) 


830
831
832
833
 
# File 'lib/wp2txt/multistream.rb', line 830

def cache_fresh?(days = nil)
  days ||= @dump_expiry_days
  Wp2txt.file_fresh?(cached_index_path, days)
end

#cache_mtime ⇒ Object

Get cache modification time Returns nil if no cache exists



848
849
850
851
852
853
 
# File 'lib/wp2txt/multistream.rb', line 848

def cache_mtime
  path = cached_index_path
  return nil unless File.exist?(path)

  File.mtime(path)
end

#cache_stale? ⇒ Boolean

Check if cache is stale (beyond configured expiry days)

Returns:

  • (Boolean) 


836
837
838
 
# File 'lib/wp2txt/multistream.rb', line 836

def cache_stale?
  !cache_fresh?
end

#cache_status ⇒ Object

Get cache status information



856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
 
# File 'lib/wp2txt/multistream.rb', line 856

def cache_status
  {
    lang: @lang,
    cache_dir: @cache_dir,
    index_exists: File.exist?(cached_index_path),
    index_path: cached_index_path,
    index_size: File.exist?(cached_index_path) ? File.size(cached_index_path) : 0,
    multistream_exists: File.exist?(cached_multistream_path),
    multistream_path: cached_multistream_path,
    multistream_size: File.exist?(cached_multistream_path) ? File.size(cached_multistream_path) : 0,
    dump_date: (latest_dump_date rescue nil),
    fresh: cache_fresh?,
    age_days: cache_age_days,
    mtime: cache_mtime,
    expiry_days: @dump_expiry_days
  }
end

#cached_index_path ⇒ Object

Get paths for cached files



821
822
823
 
# File 'lib/wp2txt/multistream.rb', line 821

def cached_index_path
  File.join(@cache_dir, "#{@lang}wiki-#{latest_dump_date}-multistream-index.txt.bz2")
end

#cached_multistream_path ⇒ Object 



825
826
827
 
# File 'lib/wp2txt/multistream.rb', line 825

def cached_multistream_path
  File.join(@cache_dir, "#{@lang}wiki-#{latest_dump_date}-multistream.xml.bz2")
end

#cached_partial_multistream_path(stream_count) ⇒ Object

Path for partial multistream cache



816
817
818
 
# File 'lib/wp2txt/multistream.rb', line 816

def cached_partial_multistream_path(stream_count)
  File.join(@cache_dir, "#{@lang}wiki-#{latest_dump_date}-multistream-#{stream_count}streams.xml.bz2")
end

#can_resume_from_partial?(partial_info) ⇒ Hash

Check if incremental download is possible from existing partial

Parameters:

  • partial_info (Hash) —

    Info from find_any_partial_cache

Returns:

  • (Hash) —

    Result with :possible, :reason, and details



568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
 
# File 'lib/wp2txt/multistream.rb', line 568

def can_resume_from_partial?(partial_info)
  return { possible: false, reason: :no_partial } unless partial_info

  current_date = latest_dump_date

  # Check if dump dates match
  if partial_info[:dump_date] != current_date
    return {
      possible: false,
      reason: :date_mismatch,
      partial_date: partial_info[:dump_date],
      latest_date: current_date
    }
  end

  # Validate the partial file with Bz2Validator
  require_relative "bz2_validator"
  validation = Bz2Validator.validate_quick(partial_info[:path])
  unless validation.valid?
    return {
      possible: false,
      reason: :invalid_partial,
      error: validation.message
    }
  end

  # Verify file size matches expected offset
  index_path = download_index
  index = MultistreamIndex.new(index_path, cache_dir: @cache_dir)

  expected_size = if partial_info[:stream_count] < index.stream_offsets.size
                    index.stream_offsets[partial_info[:stream_count]]
                  else
                    # Partial has all streams - no need to resume
                    return { possible: false, reason: :already_complete }
                  end

  actual_size = partial_info[:size]
  if actual_size != expected_size
    return {
      possible: false,
      reason: :size_mismatch,
      expected: expected_size,
      actual: actual_size
    }
  end

  {
    possible: true,
    partial_info: partial_info,
    current_streams: partial_info[:stream_count],
    total_streams: index.stream_offsets.size,
    current_size: actual_size
  }
end

#clear_cache! ⇒ Object

Clear cache for this language



875
876
877
878
 
# File 'lib/wp2txt/multistream.rb', line 875

def clear_cache!
  lang_dir = File.join(@cache_dir, "#{@lang}wiki")
  FileUtils.rm_rf(lang_dir) if File.exist?(lang_dir)
end

#download_index(force: false) ⇒ Object

Download multistream index file



456
457
458
459
460
461
462
463
464
465
466
467
468
469
 
# File 'lib/wp2txt/multistream.rb', line 456

def download_index(force: false)
  index_path = cached_index_path
  if File.exist?(index_path) && !force
    puts "Index already cached: #{File.basename(index_path)}"
    $stdout.flush
    return index_path
  end

  url = index_url
  puts "Downloading index: #{url}"
  $stdout.flush
  download_file(url, index_path)
  index_path
end

#download_multistream(force: false, max_streams: nil) ⇒ Object

Download multistream dump file

Parameters:

  • force (Boolean) (defaults to: false) —

    Force re-download even if cached

  • max_streams (Integer, nil) (defaults to: nil) —

    If set, only download first N streams (partial download)



474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
 
# File 'lib/wp2txt/multistream.rb', line 474

def download_multistream(force: false, max_streams: nil)
  # For partial downloads, first check if full dump exists (most efficient)
  if max_streams && !force
    full_path = cached_multistream_path
    if File.exist?(full_path)
      puts "Using cached full dump: #{File.basename(full_path)}"
      $stdout.flush
      return full_path
    end

    # Check if a larger partial download exists
    existing_partial = find_suitable_partial_cache(max_streams)
    if existing_partial
      puts "Using cached partial: #{File.basename(existing_partial)}"
      $stdout.flush
      return existing_partial
    end
  end

  dump_path = max_streams ? cached_partial_multistream_path(max_streams) : cached_multistream_path
  if File.exist?(dump_path) && !force
    puts "Multistream already cached: #{File.basename(dump_path)}"
    $stdout.flush
    return dump_path
  end

  url = multistream_url

  if max_streams
    # Partial download: need index first to know byte range
    index_path = download_index
    index = MultistreamIndex.new(index_path, cache_dir: @cache_dir)

    if index.stream_offsets.size >= max_streams
      # Get byte range for first N streams
      end_offset = index.stream_offsets[max_streams]
      puts "Downloading first #{max_streams} streams (#{format_size(end_offset)}): #{url}"
      $stdout.flush
      download_file_range(url, dump_path, 0, end_offset - 1)
    else
      puts "Only #{index.stream_offsets.size} streams available, downloading all"
      $stdout.flush
      download_file(url, dump_path)
    end
  else
    puts "Downloading multistream: #{url}"
    $stdout.flush
    download_file(url, dump_path)
  end

  dump_path
end

#download_multistream_full(force: false, interactive: true) ⇒ String

Download full dump with incremental support

Parameters:

  • force (Boolean) (defaults to: false) —

    Force re-download

  • interactive (Boolean) (defaults to: true) —

    Prompt user for choices (default: true)

Returns:

  • (String) —

    Path to downloaded file



628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
 
# File 'lib/wp2txt/multistream.rb', line 628

def download_multistream_full(force: false, interactive: true)
  full_path = cached_multistream_path

  # If full dump exists, use it
  if File.exist?(full_path) && !force
    puts "Using cached full dump: #{File.basename(full_path)}"
    $stdout.flush
    return full_path
  end

  # Check for existing partial dump
  partial = find_any_partial_cache
  if partial && interactive
    resume_info = can_resume_from_partial?(partial)

    if resume_info[:possible]
      # Same date - can resume
      return handle_resumable_partial(partial, resume_info, force)
    elsif resume_info[:reason] == :date_mismatch
      # Different date - ask user
      return handle_outdated_partial(partial, resume_info, force)
    elsif resume_info[:reason] == :size_mismatch || resume_info[:reason] == :invalid_partial
      # Corrupted partial - inform and re-download
      puts "Warning: Existing partial dump appears corrupted."
      puts "  Reason: #{resume_info[:reason]}"
      puts "  Will download fresh copy."
      FileUtils.rm_f(partial[:path])
    end
  end

  # Standard full download
  download_multistream(force: force, max_streams: nil)
end

#find_any_partial_cache ⇒ Hash?

Find any existing partial dump (any date)

Returns:

  • (Hash, nil) —

    Info about existing partial dump, or nil



543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
 
# File 'lib/wp2txt/multistream.rb', line 543

def find_any_partial_cache
  pattern = File.join(@cache_dir, "#{@lang}wiki-*-multistream-*streams.xml.bz2")
  partials = []

  Dir.glob(pattern).each do |path|
    if path =~ /#{@lang}wiki-(\d{8})-multistream-(\d+)streams\.xml\.bz2$/
      dump_date = $1
      stream_count = $2.to_i
      partials << {
        path: path,
        dump_date: dump_date,
        stream_count: stream_count,
        size: File.size(path),
        mtime: File.mtime(path)
      }
    end
  end

  # Return the largest partial (by stream count)
  partials.max_by { |p| p[:stream_count] }
end

#find_suitable_partial_cache(min_streams) ⇒ String?

Find a suitable cached partial download (same or larger than needed)

Parameters:

  • min_streams (Integer) —

    Minimum number of streams needed

Returns:

  • (String, nil) —

    Path to suitable cached file, or nil



530
531
532
533
534
535
536
537
538
539
 
# File 'lib/wp2txt/multistream.rb', line 530

def find_suitable_partial_cache(min_streams)
  pattern = File.join(@cache_dir, "#{@lang}wiki-#{latest_dump_date}-multistream-*streams.xml.bz2")
  Dir.glob(pattern).each do |path|
    if path =~ /multistream-(\d+)streams\.xml\.bz2$/
      stream_count = $1.to_i
      return path if stream_count >= min_streams
    end
  end
  nil
end

#format_size(bytes) ⇒ Object

Format bytes as human-readable string



446
447
448
 
# File 'lib/wp2txt/multistream.rb', line 446

def format_size(bytes)
  Wp2txt.format_file_size(bytes)
end

#latest_dump_date ⇒ Object

Get the latest dump date for a language



451
452
453
 
# File 'lib/wp2txt/multistream.rb', line 451

def latest_dump_date
  @latest_dump_date ||= fetch_latest_dump_date
end