Add Porter stemmer for Dutch (NaturalNode#423)

RiturajY · Apr 7, 2018 · 261fcd5 · 261fcd5
1 parent 39cf012
commit 261fcd5
Show file tree

Hide file tree

Showing 8 changed files with 46,190 additions and 25 deletions.
diff --git a/README.md b/README.md
@@ -297,7 +297,7 @@ The following
 
 ## Stemmers
 
-Currently stemming is supported via the [Porter](http://tartarus.org/martin/PorterStemmer/index.html) and [Lancaster](http://www.comp.lancs.ac.uk/computing/research/stemming/) (Paice/Husk) algorithms.
+Currently stemming is supported via the [Porter](http://tartarus.org/martin/PorterStemmer/index.html) and [Lancaster](http://www.comp.lancs.ac.uk/computing/research/stemming/) (Paice/Husk) algorithms. The Indonesian and Japanese stemmers do not follow a known algorithm.
 
 ```javascript
 var natural = require('natural');
@@ -323,20 +323,21 @@ console.log(natural.PorterStemmerEs.stem("jugaría"));
 
 The following stemmers are available:
 
-* `PorterStemmer`
-* `LancasterStemmer`
-* `PorterStemmerFa`
-* `PorterStemmerFr`
-* `PorterStemmerRu`
-* `PorterStemmerEs`
-* `PorterStemmerIt`
-* `PorterStemmerNo`
-* `PorterStemmerSv`
-* `PorterStemmerPt`
-* `StemmerFr`
-* `StemmerPl`
-* `StemmerJa`
-* `StemmerId`
+| Language      | Porter      | Lancaster | Other     | Module name(s) | Unit test |
+| ------------- |:-----------:|:---------:|:---------:|----------------|:---------:|
+| Dutch         | X           |           |           | `PorterStemmer`   | X        |
+| English       | X           |  X        |           | `PorterStemmer`, `LancasterStemmer` | XX |
+| Farsi (in progress) |  X    |           |           | `PorterStemmerFa` |          |
+| Dutch         |             |           |           | `PorterStemmerNl` | X        |
+| French        | X           |           |           | `PorterStemmerFr` | X        |
+| Indonesian    |             |           | X         | `StemmerId`       |          |
+| Italian       | X           |           |           | `PorterStemmerIt` | X        |
+| Japanese      | X           |           | X         | `StemmerJa`       | X        |
+| Norwegian     | X           |           |           | `PorterStemmerNo` | X        |
+| Portugese     | X           |           |           | `PorterStemmerPt` | X        |
+| Russian       | X           |           |           | `PorterStemmerRu` | X        |
+| Swedish       | X           |           |           | `PorterStemmerSv` | X        |
+
 
 `attach()` patches `stem()` and `tokenizeAndStem()` to String as a shortcut to
 `PorterStemmer.stem(token)`. `tokenizeAndStem()` breaks text up into single words
@@ -348,7 +349,7 @@ console.log("i am waking up to the sounds of chainsaws".tokenizeAndStem());
 console.log("chainsaws".stem());
 ```
 
-the same thing can be done with a Lancaster stemmer:
+The same thing can be done with a Lancaster stemmer:
 
 ```javascript
 natural.LancasterStemmer.attach();

diff --git a/lib/natural/index.js b/lib/natural/index.js
@@ -33,9 +33,12 @@ exports.PorterStemmerIt = require('./stemmers/porter_stemmer_it');
 exports.PorterStemmerNo = require('./stemmers/porter_stemmer_no');
 exports.PorterStemmerSv = require('./stemmers/porter_stemmer_sv');
 exports.PorterStemmerPt = require('./stemmers/porter_stemmer_pt');
+exports.PorterStemmerNl = require('./stemmers/porter_stemmer_nl');
 exports.LancasterStemmer = require('./stemmers/lancaster_stemmer');
-exports.StemmerFr = require('./stemmers/stemmer_fr');
-exports.StemmerPl = require('./stemmers/stemmer_pl');
+// StemmerFr and StemmerPl are not stemmers. A Polish stemmer is
+// not available, and for French PorterStemmerFr should be used.
+//exports.StemmerFr = require('./stemmers/stemmer_fr');
+//exports.StemmerPl = require('./stemmers/stemmer_pl');
 exports.StemmerJa = require('./stemmers/stemmer_ja');
 exports.StemmerId = require('./stemmers/indonesian/stemmer_id');
 exports.AggressiveTokenizerNl = require('./tokenizers/aggressive_tokenizer_nl');

diff --git a/lib/natural/stemmers/porter_stemmer_fr.js b/lib/natural/stemmers/porter_stemmer_fr.js
@@ -374,4 +374,4 @@ function isVowel(letter) {
 function endsin(token, suffix) {
   if (token.length < suffix.length) return false;
   return (token.slice(-suffix.length) == suffix);
-};
+};