lingo 1.8.4.2 → 1.8.5

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (89) hide show
  1. checksums.yaml +4 -4
  2. data/ChangeLog +413 -325
  3. data/README +380 -131
  4. data/Rakefile +19 -21
  5. data/de/lingo-abk.txt +15 -17
  6. data/de/lingo-dic.txt +20210 -20659
  7. data/de/lingo-mul.txt +5 -13
  8. data/de/lingo-syn.txt +5 -8
  9. data/de/test_dic.txt +2 -0
  10. data/de/test_gen.txt +8 -0
  11. data/de/{test_mul2.txt → test_mu2.txt} +0 -0
  12. data/de/{test_singleword.txt → test_sgw.txt} +0 -0
  13. data/de/user-dic.txt +5 -7
  14. data/de.lang +64 -49
  15. data/en/lingo-dic.txt +6398 -6404
  16. data/en/lingo-irr.txt +2 -3
  17. data/en/lingo-mul.txt +6 -7
  18. data/en/lingo-wdn.txt +881 -1762
  19. data/en/user-dic.txt +2 -5
  20. data/en.lang +39 -39
  21. data/lib/lingo/app.rb +10 -6
  22. data/lib/lingo/attendee/abbreviator.rb +1 -0
  23. data/lib/lingo/attendee/decomposer.rb +2 -1
  24. data/lib/lingo/attendee/multi_worder.rb +5 -6
  25. data/lib/lingo/attendee/stemmer.rb +1 -1
  26. data/lib/lingo/attendee/synonymer.rb +4 -2
  27. data/lib/lingo/attendee/text_reader.rb +77 -57
  28. data/lib/lingo/attendee/text_writer.rb +1 -1
  29. data/lib/lingo/attendee/tokenizer.rb +101 -50
  30. data/lib/lingo/attendee/variator.rb +2 -1
  31. data/lib/lingo/attendee/vector_filter.rb +28 -6
  32. data/lib/lingo/attendee/word_searcher.rb +2 -1
  33. data/lib/lingo/attendee.rb +8 -4
  34. data/lib/lingo/call.rb +7 -3
  35. data/lib/lingo/cli.rb +8 -16
  36. data/lib/lingo/config.rb +11 -6
  37. data/lib/lingo/ctl.rb +54 -3
  38. data/lib/lingo/database/crypter.rb +8 -14
  39. data/lib/lingo/database/hash_store.rb +1 -1
  40. data/lib/lingo/database/{show_progress.rb → progress.rb} +7 -8
  41. data/lib/lingo/database/source/key_value.rb +6 -5
  42. data/lib/lingo/database/source/multi_key.rb +5 -2
  43. data/lib/lingo/database/source/multi_value.rb +6 -4
  44. data/lib/lingo/database/source/single_word.rb +2 -3
  45. data/lib/lingo/database/source/word_class.rb +24 -5
  46. data/lib/lingo/database/source.rb +5 -3
  47. data/lib/lingo/database.rb +102 -41
  48. data/lib/lingo/error.rb +24 -2
  49. data/lib/lingo/language/dictionary.rb +26 -54
  50. data/lib/lingo/language/grammar.rb +19 -23
  51. data/lib/lingo/language/lexical.rb +5 -1
  52. data/lib/lingo/language/lexical_hash.rb +7 -12
  53. data/lib/lingo/language/token.rb +10 -1
  54. data/lib/lingo/language/word.rb +35 -23
  55. data/lib/lingo/language/word_form.rb +5 -4
  56. data/lib/lingo/{show_progress.rb → progress.rb} +43 -30
  57. data/lib/lingo/srv/lingosrv.cfg +1 -1
  58. data/lib/lingo/srv/public/.gitkeep +0 -0
  59. data/lib/lingo/srv.rb +11 -6
  60. data/lib/lingo/version.rb +2 -2
  61. data/lib/lingo/web/lingoweb.cfg +1 -1
  62. data/lib/lingo/web/views/index.erb +4 -4
  63. data/lib/lingo/web.rb +4 -6
  64. data/lib/lingo.rb +4 -12
  65. data/lingo.cfg +1 -1
  66. data/lir.cfg +1 -1
  67. data/ru/lingo-dic.txt +33473 -2113
  68. data/ru/lingo-mul.txt +8430 -1913
  69. data/ru/lingo-syn.txt +1634 -0
  70. data/ru/user-dic.txt +6 -0
  71. data/ru.lang +49 -47
  72. data/spec/spec_helper.rb +4 -0
  73. data/test/attendee/ts_decomposer.rb +2 -2
  74. data/test/attendee/ts_synonymer.rb +3 -3
  75. data/test/attendee/ts_tokenizer.rb +215 -2
  76. data/test/attendee/ts_variator.rb +2 -2
  77. data/test/attendee/ts_word_searcher.rb +10 -6
  78. data/test/ref/artikel.seq +2 -2
  79. data/test/ref/artikel.vec +5 -5
  80. data/test/ref/artikel.ven +11 -11
  81. data/test/ref/artikel.ver +11 -11
  82. data/test/ref/lir.seq +13 -13
  83. data/test/ref/lir.vec +31 -31
  84. data/test/test_helper.rb +19 -5
  85. data/test/ts_database.rb +206 -77
  86. data/test/ts_language.rb +86 -26
  87. metadata +93 -49
  88. data/.rspec +0 -1
  89. data/de/test_syn2.txt +0 -1
data/Rakefile CHANGED
@@ -26,7 +26,7 @@ begin
26
26
  summary: 'The full-featured automatic indexing system',
27
27
  authors: ['John Vorhauer', 'Jens Wille'],
28
28
  email: ['lingo@vorhauer.de', 'jens.wille@gmail.com'],
29
- license: 'AGPL',
29
+ license: 'AGPL-3.0',
30
30
  homepage: 'http://lex-lingo.de',
31
31
  description: <<-EOT,
32
32
  Lingo is an open source indexing system for research and teachings.
@@ -42,24 +42,24 @@ The main functions of Lingo are:
42
42
  extra_files: FileList[
43
43
  'lingo.rb', 'lingo{,-call}.cfg', 'lir.cfg',
44
44
  '{de,en,ru}.lang', '{de,en,ru}/{lingo-*,user-dic,test_*}.txt',
45
- 'txt/{artikel{,-en,-ru},lir}.txt', 'lib/lingo/{srv,web}/**/*'
45
+ 'txt/{artikel{,-en,-ru},lir}.txt', 'lib/lingo/{srv,web}/**/{,.}*'
46
46
  ].to_a,
47
- required_ruby_version: '>= 1.9.2',
48
- dependencies: [
49
- 'highline',
50
- ['ruby-nuggets', '>= 0.9.2', '<= 0.9.7'],
51
- 'sinatra',
52
- 'sinatra-contrib',
53
- 'unicode'
54
- ],
55
- development_dependencies: [
56
- ['diff-lcs', '>= 1.1.3'],
57
- 'open4'
58
- ]
47
+ required_ruby_version: '>= 1.9.3',
48
+ dependencies: {
49
+ 'cyclops' => ['~> 0.0', '>= 0.0.4'],
50
+ 'nuggets' => '~> 1.0',
51
+ 'rubyzip' => '~> 1.1',
52
+ 'sinatra-bells' => '~> 0.0',
53
+ 'unicode' => '~> 0.4'
54
+ },
55
+ development_dependencies: {
56
+ 'diff-lcs' => '~> 1.2',
57
+ 'open4' => '~> 1.3'
58
+ }
59
59
  }
60
60
  }}
61
61
  rescue LoadError => err
62
- warn "Please install the `hen' gem first. (#{err})"
62
+ warn "Please install the `hen' gem. (#{err})"
63
63
  end
64
64
 
65
65
  CLEAN.include(
@@ -69,9 +69,7 @@ CLEAN.include(
69
69
  'bench/tmp.*'
70
70
  )
71
71
 
72
- CLOBBER.include(
73
- 'store', 'doc' ,'pkg/*', PACKAGE_PATH + '.*'
74
- )
72
+ CLOBBER.include('store')
75
73
 
76
74
  task :checkdoc do
77
75
  docfile = File.join(__DIR__, 'doc', 'index.html')
@@ -118,7 +116,7 @@ def test_ref(name, cfg = name)
118
116
  require 'diff/lcs/ldiff'
119
117
 
120
118
  cmd = %W[lingo.rb -c #{cfg} txt/#{name}.txt]
121
- continue, msg = 0, ["Command failed: #{cmd.join(' ')}"]
119
+ diff, msg = 0, ["Command failed: #{cmd.join(' ')}"]
122
120
 
123
121
  Process.ruby(*cmd) { |_, _, o, e|
124
122
  IO.interact({}, { o => msg, e => msg })
@@ -126,8 +124,8 @@ def test_ref(name, cfg = name)
126
124
 
127
125
  Dir["test/ref/#{name}.*"].each { |ref|
128
126
  puts "## #{org = ref.sub(/test\/ref/, 'txt')}"
129
- continue += Diff::LCS::Ldiff.run(ARGV.clear << '-a' << org << ref)
127
+ diff += Diff::LCS::Ldiff.run(ARGV.clear << '-a' << org << ref)
130
128
  }
131
129
 
132
- exit continue + 1 unless continue.zero?
130
+ exit diff + 1 unless diff.zero?
133
131
  end
data/de/lingo-abk.txt CHANGED
@@ -1,18 +1,16 @@
1
+ # Abkürzungswörterbuch lingo-abk.txt
2
+ # enthält Abkürzungen und ihre Auflösungen
1
3
  #
2
- # Abkürzungswörterbuch lingo-abk.txt
3
- # enthält Abkürzungen und ihre Auflösungen
4
- #
5
- # Stand: 16.03.06 / Jan-Helge Jacobs
6
- #
7
- #
8
- abb=abbildung #s
9
- abk=abkürzung #s
4
+ # Stand: 16.03.06 / Jan-Helge Jacobs
5
+
6
+ abb=abbildung #s.f
7
+ abk=abkürzung #s.f
10
8
  altdt=altdeutsch #a
11
9
  architekton=architektonisch #a
12
- aufl=auflage #s
10
+ aufl=auflage #s.f
13
11
  b.a.w=bis auf weiteres #w
14
12
  b.z.w=beziehungsweise #w
15
- beisp=beispiel #s
13
+ beisp=beispiel #s.n
16
14
  bzgl=bezüglich #w
17
15
  bzw=beziehungsweise #w
18
16
  ca=circa #w
@@ -21,14 +19,14 @@ christol=christologisch #a
21
19
  d.h=das heißt #w
22
20
  desgl=desgleichen #w
23
21
  dgl=dergleichen #w
24
- dr=doktor #s
22
+ dr=doktor #s.m
25
23
  dt=deutsch #w
26
- Dtld=deutschland #e
24
+ Dtld=deutschland #e.n
27
25
  entspr=entsprechend #w
28
26
  etc=et cetera #w
29
27
  evang=evangelisch #a
30
28
  evtl=eventuell #w
31
- gesch=geschichtlich #a geschichte #s
29
+ gesch=geschichte #s.f geschichtlich #a
32
30
  ggf=gegebenenfalls #w
33
31
  griech=griechisch #a
34
32
  inkl=inklusive #w
@@ -36,7 +34,7 @@ insbes=insbesondere #w
36
34
  insges=insgesamt #w
37
35
  ital=italienisch #a
38
36
  Jb=Jahrbuch #s
39
- jh=jahrhundert #s
37
+ jh=jahrhundert #s.n
40
38
  kaiserl=kaiserlich #a
41
39
  kathol=katholisch #a
42
40
  lfd=laufend #a
@@ -54,13 +52,13 @@ pfarrk=pfarrkirche #s
54
52
  philol=philologisch #a
55
53
  prakt=praktisch #a
56
54
  prot=protestantisch #a
57
- renss=renaissance #s
55
+ renss=renaissance #s.f
58
56
  Schifffahrtmus=schifffahrtmuseum #s
59
57
  sog=sogenannt #w
60
58
  stck=stück #s
61
- std=stunde #s
59
+ std=stunde #s.n
62
60
  tbc=tbc #w tuberkulose #s
63
- tex=texas #e
61
+ tex=texas #e.n
64
62
  textabb=textabbildung #s
65
63
  trojan=trojanisch #a
66
64
  trop=tropisch #a