sastrawi-ruby 0.2.0

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 (93) hide show
  1. checksums.yaml +7 -0
  2. data/.github/workflows/ci.yml +23 -0
  3. data/.gitignore +51 -0
  4. data/.travis.yml +10 -0
  5. data/CONTRIBUTING.md +22 -0
  6. data/Gemfile +4 -0
  7. data/LICENSE.txt +21 -0
  8. data/README.md +104 -0
  9. data/Rakefile +6 -0
  10. data/_config.yml +1 -0
  11. data/bin/sastrawi +24 -0
  12. data/data/base-word.txt +29933 -0
  13. data/lib/sastrawi/dictionary/array_dictionary.rb +67 -0
  14. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule10.rb +17 -0
  15. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule11.rb +17 -0
  16. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule12.rb +17 -0
  17. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule13a.rb +17 -0
  18. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule13b.rb +17 -0
  19. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule14.rb +17 -0
  20. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule15a.rb +17 -0
  21. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule15b.rb +17 -0
  22. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule16.rb +17 -0
  23. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule17a.rb +17 -0
  24. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule17b.rb +17 -0
  25. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule17c.rb +17 -0
  26. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule17d.rb +17 -0
  27. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule18a.rb +17 -0
  28. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule18b.rb +17 -0
  29. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule19.rb +17 -0
  30. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule1a.rb +17 -0
  31. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule1b.rb +17 -0
  32. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule2.rb +19 -0
  33. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule20.rb +17 -0
  34. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule21a.rb +17 -0
  35. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule21b.rb +17 -0
  36. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule23.rb +19 -0
  37. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule24.rb +19 -0
  38. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule25.rb +17 -0
  39. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule26a.rb +17 -0
  40. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule26b.rb +17 -0
  41. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule27.rb +17 -0
  42. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule28a.rb +17 -0
  43. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule28b.rb +17 -0
  44. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule29.rb +17 -0
  45. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule3.rb +19 -0
  46. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule30a.rb +17 -0
  47. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule30b.rb +17 -0
  48. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule30c.rb +17 -0
  49. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule31a.rb +17 -0
  50. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule31b.rb +17 -0
  51. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule32.rb +19 -0
  52. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule34.rb +19 -0
  53. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule35.rb +17 -0
  54. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule36.rb +17 -0
  55. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule37a.rb +17 -0
  56. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule37b.rb +17 -0
  57. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule38a.rb +17 -0
  58. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule38b.rb +17 -0
  59. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule39a.rb +17 -0
  60. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule39b.rb +17 -0
  61. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule4.rb +11 -0
  62. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule40a.rb +17 -0
  63. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule40b.rb +17 -0
  64. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule41.rb +17 -0
  65. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule42.rb +17 -0
  66. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule5.rb +17 -0
  67. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule6a.rb +17 -0
  68. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule6b.rb +17 -0
  69. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule7.rb +19 -0
  70. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule8.rb +19 -0
  71. data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule9.rb +19 -0
  72. data/lib/sastrawi/morphology/invalid_affix_pair_specification.rb +28 -0
  73. data/lib/sastrawi/stemmer/cache/array_cache.rb +25 -0
  74. data/lib/sastrawi/stemmer/cached_stemmer.rb +33 -0
  75. data/lib/sastrawi/stemmer/confix_stripping/precedence_adjustment_specification.rb +25 -0
  76. data/lib/sastrawi/stemmer/context/context.rb +217 -0
  77. data/lib/sastrawi/stemmer/context/removal.rb +17 -0
  78. data/lib/sastrawi/stemmer/context/visitor/dont_stem_short_word.rb +17 -0
  79. data/lib/sastrawi/stemmer/context/visitor/prefix_disambiguator.rb +54 -0
  80. data/lib/sastrawi/stemmer/context/visitor/remove_derivational_suffix.rb +37 -0
  81. data/lib/sastrawi/stemmer/context/visitor/remove_inflectional_particle.rb +34 -0
  82. data/lib/sastrawi/stemmer/context/visitor/remove_inflectional_possessive_pronoun.rb +34 -0
  83. data/lib/sastrawi/stemmer/context/visitor/remove_plain_prefix.rb +34 -0
  84. data/lib/sastrawi/stemmer/context/visitor/visitor_provider.rb +157 -0
  85. data/lib/sastrawi/stemmer/filter/text_normalizer.rb +15 -0
  86. data/lib/sastrawi/stemmer/stemmer.rb +101 -0
  87. data/lib/sastrawi/stemmer/stemmer_factory.rb +49 -0
  88. data/lib/sastrawi/stop_word_remover/stop_word_remover.rb +27 -0
  89. data/lib/sastrawi/stop_word_remover/stop_word_remover_factory.rb +124 -0
  90. data/lib/sastrawi/version.rb +5 -0
  91. data/lib/sastrawi.rb +4 -0
  92. data/sastrawi.gemspec +34 -0
  93. metadata +179 -0

There are too many changes on this page to be displayed.

The amount of changes on this page would crash your brower.

You can still verify the content by downloading the gem file manually.