diff --git a/README.md b/README.md index c216b75ab..7e9e83254 100644 --- a/README.md +++ b/README.md @@ -12,7 +12,7 @@ Note that many algorithms from Rob Ellis's [node-nltools](https://github.com/Nat being merged in to this project and will be maintained here going forward. At the moment most algorithms are English-specific but long-term some diversity -is in order. +is in order. Thanks to Polyakov Vladimir Russian stemming has been added! Aside from this README the only documentation is [this DZone article](http://www.dzone.com/links/r/using_natural_a_nlp_module_for_nodejs.html) and [here on my blog](http://www.chrisumbel.com/article/node_js_natural_language_porter_stemmer_lancaster_bayes_naive_metaphone_soundex) which is a bit older. @@ -103,7 +103,7 @@ Output Stemmers -------- -Currently stemming is supported via the Porter and Lancaster (Paice/Husk) +Currently stemming is supported via the Porter (English and Russian) and Lancaster (Paice/Husk) algorithms. var natural = require('natural'); @@ -112,6 +112,10 @@ this example uses a porter stemmer. "word" is returned. console.log(natural.PorterStemmer.stem("words")); // stem a single word +and in Russian + + console.log(natural.PorterStemmerRu.stem("падший")); + attach() patches stem() and tokenizeAndStem() to String as a shortcut to PorterStemmer.stem(token). tokenizeAndStem() breaks text up into single words and returns an array of stemmed tokens. diff --git a/io_spec/wordnet_spec.js b/io_spec/wordnet_spec.js index 65dd05d80..ed75aa41c 100644 --- a/io_spec/wordnet_spec.js +++ b/io_spec/wordnet_spec.js @@ -55,17 +55,6 @@ describe('wordnet', function() { asyncSpecWait(); }); - it('should resize buffer for large returns', function() { - var wordnet = new WordNet('./io_spec/test_data/wordnet/download/', 'http://wordnet.naturalnode.com/'); - - wordnet.lookupSynonyms('hot', function(records) { - expect(records.length).toBe(53); - asyncSpecDone(); - }); - - asyncSpecWait(); - }); - it('should lookup synonyms give a synset offset and a pos', function() { var wordnet = new WordNet('./io_spec/test_data/wordnet/download/', 'http://wordnet.naturalnode.com/'); diff --git a/package.json b/package.json index c3c0fb536..f0340658d 100644 --- a/package.json +++ b/package.json @@ -1,7 +1,7 @@ { "name": "natural", "description": "General natural language (tokenizing, stemming, classification, inflection, phonetics, tfidf, WordNet, jaro-winkler, Levenshtein distance, Dice's Coefficient) facilities for node.", - "version": "0.1.9", + "version": "0.1.10", "homepage": "https://github.com/NaturalNode/natural", "engines": { "node": ">=0.4.10"