natural 0.1.27 → 0.2.1

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 (134) hide show
  1. package/.editorconfig +7 -0
  2. package/LICENSE.txt +0 -0
  3. package/Makefile +0 -0
  4. package/README.md +237 -24
  5. package/benchmarks/index.js +1 -1
  6. package/benchmarks/metaphone.js +0 -0
  7. package/benchmarks/soundex.js +0 -0
  8. package/examples/classification/basic.js +0 -0
  9. package/examples/classification/recall.js +0 -0
  10. package/examples/classification/store.js +0 -0
  11. package/examples/inflection/count.js +0 -0
  12. package/examples/inflection/noun.js +0 -0
  13. package/examples/inflection/noun_attach.js +0 -0
  14. package/examples/phonetics/compare.js +0 -0
  15. package/examples/phonetics/sounds_like.js +0 -0
  16. package/examples/phonetics/tokenize_and_phoneticize.js +0 -0
  17. package/examples/stemming/stem_corpus.js +0 -0
  18. package/examples/stemming/stem_word.js +0 -0
  19. package/examples/tfidf/array_example.js +0 -0
  20. package/examples/tfidf/multiple_terms.js +0 -0
  21. package/examples/tfidf/tfidf_example.js +0 -0
  22. package/index.js +0 -0
  23. package/io_spec/test_data/tfidf/one +0 -0
  24. package/io_spec/test_data/tfidf/two +0 -0
  25. package/io_spec/tfidf_spec.js +0 -0
  26. package/io_spec/wordnet_spec.js +0 -0
  27. package/lib/natural/analyzers/sentence_analyzer.js +16 -13
  28. package/lib/natural/classifiers/bayes_classifier.js +6 -2
  29. package/lib/natural/classifiers/classifier.js +0 -0
  30. package/lib/natural/classifiers/logistic_regression_classifier.js +0 -0
  31. package/lib/natural/distance/dice_coefficient.js +0 -0
  32. package/lib/natural/distance/jaro-winkler_distance.js +13 -8
  33. package/lib/natural/distance/levenshtein_distance.js +0 -0
  34. package/lib/natural/index.js +8 -0
  35. package/lib/natural/inflectors/count_inflector.js +0 -0
  36. package/lib/natural/inflectors/form_set.js +0 -0
  37. package/lib/natural/inflectors/fr/count_inflector.js +0 -0
  38. package/lib/natural/inflectors/fr/noun_inflector.js +0 -0
  39. package/lib/natural/inflectors/ja/noun_inflector.js +0 -0
  40. package/lib/natural/inflectors/noun_inflector.js +0 -0
  41. package/lib/natural/inflectors/present_verb_inflector.js +1 -0
  42. package/lib/natural/inflectors/singular_plural_inflector.js +1 -2
  43. package/lib/natural/ngrams/ngrams.js +45 -8
  44. package/lib/natural/ngrams/ngrams_zh.js +83 -0
  45. package/lib/natural/normalizers/normalizer.js +30 -38
  46. package/lib/natural/normalizers/normalizer_ja.js +26 -8
  47. package/lib/natural/normalizers/normalizer_no.js +59 -0
  48. package/lib/natural/phonetics/double_metaphone.js +9 -4
  49. package/lib/natural/phonetics/metaphone.js +6 -1
  50. package/lib/natural/phonetics/phonetic.js +0 -0
  51. package/lib/natural/phonetics/soundex.js +11 -7
  52. package/lib/natural/spellcheck/spellcheck.js +80 -0
  53. package/lib/natural/stemmers/lancaster_rules.js +4 -4
  54. package/lib/natural/stemmers/lancaster_stemmer.js +0 -0
  55. package/lib/natural/stemmers/porter_stemmer.js +90 -63
  56. package/lib/natural/stemmers/porter_stemmer_es.js +22 -23
  57. package/lib/natural/stemmers/porter_stemmer_fr.js +377 -0
  58. package/lib/natural/stemmers/porter_stemmer_no.js +155 -0
  59. package/lib/natural/stemmers/porter_stemmer_pt.js +302 -0
  60. package/lib/natural/stemmers/stemmer.js +0 -0
  61. package/lib/natural/stemmers/stemmer_fr.js +58 -0
  62. package/lib/natural/stemmers/stemmer_no.js +61 -0
  63. package/lib/natural/stemmers/stemmer_pt.js +65 -0
  64. package/lib/natural/stemmers/token.js +163 -0
  65. package/lib/natural/tfidf/tfidf.js +50 -19
  66. package/lib/natural/tokenizers/aggressive_tokenizer.js +0 -0
  67. package/lib/natural/tokenizers/aggressive_tokenizer_es.js +0 -0
  68. package/lib/natural/tokenizers/aggressive_tokenizer_fr.js +36 -0
  69. package/lib/natural/tokenizers/aggressive_tokenizer_nl.js +0 -0
  70. package/lib/natural/tokenizers/aggressive_tokenizer_no.js +39 -0
  71. package/lib/natural/tokenizers/aggressive_tokenizer_pt.js +0 -0
  72. package/lib/natural/tokenizers/regexp_tokenizer.js +0 -0
  73. package/lib/natural/tokenizers/tokenizer.js +2 -2
  74. package/lib/natural/tokenizers/treebank_word_tokenizer.js +0 -0
  75. package/lib/natural/trie/trie.js +47 -0
  76. package/lib/natural/util/bag.js +50 -0
  77. package/lib/natural/util/edge_weighted_digraph.js +112 -0
  78. package/lib/natural/util/longest_path_tree.js +99 -0
  79. package/lib/natural/util/shortest_path_tree.js +100 -0
  80. package/lib/natural/util/stopwords.js +0 -0
  81. package/lib/natural/util/stopwords_fr.js +194 -0
  82. package/lib/natural/util/stopwords_nl.js +43 -0
  83. package/lib/natural/util/stopwords_no.js +42 -0
  84. package/lib/natural/util/stopwords_pt.js +136 -0
  85. package/lib/natural/util/topological.js +98 -0
  86. package/lib/natural/wordnet/data_file.js +0 -0
  87. package/lib/natural/wordnet/index_file.js +0 -0
  88. package/lib/natural/wordnet/wordnet.js +0 -0
  89. package/lib/natural/wordnet/wordnet_file.js +0 -0
  90. package/package.json +2 -2
  91. package/spec/aggressive_tokenizer_fr_spec.js +101 -0
  92. package/spec/aggressive_tokenizer_pt_spec.js +0 -0
  93. package/spec/aggressive_tokenizer_spec.js +0 -0
  94. package/spec/bayes_classifier_spec.js +12 -0
  95. package/spec/classifier_spec.js +84 -0
  96. package/spec/count_inflector_fr_spec.js +0 -0
  97. package/spec/count_inflector_spec.js +0 -0
  98. package/spec/dice_coefficient_spec.js +0 -0
  99. package/spec/double_metaphone_spec.js +10 -1
  100. package/spec/jaro-winkler_spec.js +0 -0
  101. package/spec/lancaster_stemmer_spec.js +10 -1
  102. package/spec/levenshtein_spec.js +0 -0
  103. package/spec/logistic_regression_classifier_spec.js +0 -0
  104. package/spec/longest_path_tree_spec.js +102 -0
  105. package/spec/metaphone_spec.js +10 -0
  106. package/spec/ngram_spec.js +61 -0
  107. package/spec/ngram_zh_spec.js +122 -0
  108. package/spec/normalizer_ja_spec.js +9 -3
  109. package/spec/normalizer_no_spec.js +111 -0
  110. package/spec/normalizer_spec.js +26 -5
  111. package/spec/noun_inflector_fr_spec.js +0 -0
  112. package/spec/noun_inflector_ja_spec.js +0 -0
  113. package/spec/noun_inflector_spec.js +0 -0
  114. package/spec/porter_stemmer_fr_spec.js +101 -0
  115. package/spec/porter_stemmer_no_spec.js +143 -0
  116. package/spec/porter_stemmer_pt_spec.js +50 -0
  117. package/spec/porter_stemmer_spec.js +49 -0
  118. package/spec/present_verb_inflector_spec.js +3 -0
  119. package/spec/remove_diacritics_spec.js +31 -0
  120. package/spec/sentence_analyzer_spec.js +248 -0
  121. package/spec/shortest_path_tree_spec.js +132 -0
  122. package/spec/soundex_spec.js +13 -9
  123. package/spec/spellcheck_spec.js +92 -0
  124. package/spec/stemmer_token_spec.js +161 -0
  125. package/spec/test_data/snowball_fr.txt +20402 -0
  126. package/spec/test_data/snowball_no.txt +20628 -0
  127. package/spec/test_data/snowball_pt.txt +32016 -0
  128. package/spec/test_data/tfdif_testcorpus.txt +0 -0
  129. package/spec/test_data/tfidf_teststopwords.txt +0 -0
  130. package/spec/test_data/wordnet_mini.sql +0 -0
  131. package/spec/tfidf_spec.js +153 -28
  132. package/spec/tokenizer_ja_spec.js +0 -0
  133. package/spec/treebank_word_tokenizer_spec.js +0 -0
  134. package/spec/trie_spec.js +27 -3

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 package file manually.