Modernised Brill POS Tagger to classes (#717)

NaturalNode · Dec 5, 2023 · 3a08b4a · 3a08b4a
1 parent a728884
commit 3a08b4a
Show file tree

Hide file tree

Showing 10 changed files with 777 additions and 764 deletions.
diff --git a/lib/natural/brill_pos_tagger/lib/Brill_POS_Tagger.js b/lib/natural/brill_pos_tagger/lib/Brill_POS_Tagger.js
@@ -22,42 +22,44 @@ const Sentence = require('./Sentence')
 
 const DEBUG = false
 
-function BrillPOSTagger (lexicon, ruleSet) {
-  this.lexicon = lexicon
-  this.ruleSet = ruleSet
-}
-
-// Tags a sentence, sentence is an array of words
-// Returns an array of tagged words; a tagged words is an array consisting of
-// the word itself followed by its lexical category
-BrillPOSTagger.prototype.tag = function (sentence) {
-  const taggedSentence = this.tagWithLexicon(sentence)
-  DEBUG && console.log(taggedSentence)
-  return this.applyRules(taggedSentence)
-}
+class BrillPOSTagger {
+  constructor (lexicon, ruleSet) {
+    this.lexicon = lexicon
+    this.ruleSet = ruleSet
+  }
 
-BrillPOSTagger.prototype.tagWithLexicon = function (sentence) {
-  const taggedSentence = new Sentence()
+  // Tags a sentence, sentence is an array of words
+  // Returns an array of tagged words; a tagged words is an array consisting of
+  // the word itself followed by its lexical category
+  tag (sentence) {
+    const taggedSentence = this.tagWithLexicon(sentence)
+    DEBUG && console.log(taggedSentence)
+    return this.applyRules(taggedSentence)
+  }
 
-  const that = this
-  sentence.forEach(function (word, index) {
-    const categories = that.lexicon.tagWord(word)
-    taggedSentence.addTaggedWord(word, categories[0])
-  })
-  return (taggedSentence)
-}
+  tagWithLexicon (sentence) {
+    const taggedSentence = new Sentence()
 
-// Applies the transformation rules to an initially tagged sentence.
-// taggedSentence is an array of tagged words.
-// A tagged word is an array consisting of the word itself followed by its lexical category.
-// Returns an array of tagged words as well
-BrillPOSTagger.prototype.applyRules = function (sentence) {
-  for (let i = 0, size = sentence.taggedWords.length; i < size; i++) {
-    this.ruleSet.getRules().forEach(function (rule) {
-      rule.apply(sentence, i)
+    const that = this
+    sentence.forEach(function (word, index) {
+      const categories = that.lexicon.tagWord(word)
+      taggedSentence.addTaggedWord(word, categories[0])
     })
+    return (taggedSentence)
+  }
+
+  // Applies the transformation rules to an initially tagged sentence.
+  // taggedSentence is an array of tagged words.
+  // A tagged word is an array consisting of the word itself followed by its lexical category.
+  // Returns an array of tagged words as well
+  applyRules (sentence) {
+    for (let i = 0, size = sentence.taggedWords.length; i < size; i++) {
+      this.ruleSet.getRules().forEach(function (rule) {
+        rule.apply(sentence, i)
+      })
+    }
+    return sentence
   }
-  return sentence
 }
 
 module.exports = BrillPOSTagger
diff --git a/lib/natural/brill_pos_tagger/lib/Brill_POS_Tester.js b/lib/natural/brill_pos_tagger/lib/Brill_POS_Tester.js
@@ -18,43 +18,41 @@
 
 'use strict'
 
-function BrillPOSTester () {
-
-}
-
-BrillPOSTester.prototype.test = function (corpus, tagger) {
-  let totalWords = 0
-  let correctTagsLexicon = 0
-  let correctTagsAfterRules = 0
-
-  // Tag the corpus using the tagger
-  corpus.sentences.forEach(function (sentence) {
-    const s = sentence.taggedWords.map(function (token) {
-      return token.token
-    })
-
-    // Use the lexicon to tag the sentence
-    const taggedSentence = tagger.tagWithLexicon(s)
-    // Count the right tags
-    sentence.taggedWords.forEach(function (token, i) {
-      totalWords++
-      if (token.tag === taggedSentence.taggedWords[i].tag) {
-        correctTagsLexicon++
-      }
-    })
-
-    // Use the rule set to tag the sentence
-    const taggedSentenceAfterRules = tagger.applyRules(taggedSentence)
-    // Count the right tags
-    sentence.taggedWords.forEach(function (token, i) {
-      if (token.tag === taggedSentenceAfterRules.taggedWords[i].tag) {
-        correctTagsAfterRules++
-      }
+class BrillPOSTester {
+  test (corpus, tagger) {
+    let totalWords = 0
+    let correctTagsLexicon = 0
+    let correctTagsAfterRules = 0
+
+    // Tag the corpus using the tagger
+    corpus.sentences.forEach(function (sentence) {
+      const s = sentence.taggedWords.map(function (token) {
+        return token.token
+      })
+
+      // Use the lexicon to tag the sentence
+      const taggedSentence = tagger.tagWithLexicon(s)
+      // Count the right tags
+      sentence.taggedWords.forEach(function (token, i) {
+        totalWords++
+        if (token.tag === taggedSentence.taggedWords[i].tag) {
+          correctTagsLexicon++
+        }
+      })
+
+      // Use the rule set to tag the sentence
+      const taggedSentenceAfterRules = tagger.applyRules(taggedSentence)
+      // Count the right tags
+      sentence.taggedWords.forEach(function (token, i) {
+        if (token.tag === taggedSentenceAfterRules.taggedWords[i].tag) {
+          correctTagsAfterRules++
+        }
+      })
     })
-  })
 
-  // Return percentage right
-  return [100 * correctTagsLexicon / totalWords, 100 * correctTagsAfterRules / totalWords]
+    // Return percentage right
+    return [100 * correctTagsLexicon / totalWords, 100 * correctTagsAfterRules / totalWords]
+  }
 }
 
 module.exports = BrillPOSTester