natural 7.1.0 → 8.0.0

package/lib/natural/tokenizers/index.d.ts

@@ -136,9 +136,6 @@ export class TokenizerJa extends Tokenizer {
 }
 
 export class SentenceTokenizer extends Tokenizer {
-  tokenize (text: string): string[]
-}
-
-export class SentenceTokenizerNew extends Tokenizer {
+  constructor (abbreviations: string[], sentenceDemarkers?: string[])
   tokenize (text: string): string[]
 }

package/lib/natural/tokenizers/index.js

@@ -46,4 +46,4 @@ exports.WordPunctTokenizer = require('./regexp_tokenizer').WordPunctTokenizer
 exports.TreebankWordTokenizer = require('./treebank_word_tokenizer')
 exports.TokenizerJa = require('./tokenizer_ja')
 exports.SentenceTokenizer = require('./sentence_tokenizer')
-exports.SentenceTokenizerNew = require('./sentence_tokenizer_parser')
+exports.SentenceTokenizerNew = require('./sentence_tokenizer')

package/lib/natural/tokenizers/sentence_tokenizer.js

@@ -1,5 +1,5 @@
 /*
-Copyright (c) 2011, Chris Umbel
+Copyright (c) 2024, Hugo W.L. ter Doest
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal
@@ -20,31 +20,174 @@ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 THE SOFTWARE.
 */
 
-'use strict'
-
 const Tokenizer = require('./tokenizer')
 
+// Strings that will be used to create placeholders
+const NUM = 'NUMBER'
+const DELIM = 'DELIM'
+const URI = 'URI'
+const ABBREV = 'ABBREV'
+
 const DEBUG = false
 
+function generateUniqueCode (base, index) {
+  return `${base}_${index}`
+}
+
+function escapeRegExp (string) {
+  return string.replace(/[.*+?^${}()|[\]\\]/g, '\\$&')
+}
+
 class SentenceTokenizer extends Tokenizer {
-  tokenize (text) {
-    // Break string up in to sentences based on punctation and quotation marks
-    // See https://gist.github.com/Hugo-ter-Doest/4ed21fb7eb5077814d998fa61a726566
-    // for a breakdown of the regular expression
-    let tokens = text.match(/(?<=\s+|^)["'‘“'"[({⟨]?(.*?[.?!…]|.+)(\s[.?!…])*["'’”'"\])}⟩]?(?=\s+|$)/g)
+  constructor (abbreviations, sentenceDemarkers) {
+    super()
+    this.abbreviations = abbreviations
+    if (sentenceDemarkers) {
+      this.sentenceDemarkers = sentenceDemarkers
+    } else {
+      this.sentenceDemarkers = ['.', '!', '?']
+    }
+    this.replacementMap = null
+    this.replacementCounter = 0
+  }
+
+  replaceUrisWithPlaceholders (text) {
+    const urlPattern = /(https?:\/\/\S+|www\.\S+|ftp:\/\/\S+|(mailto:)?[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}|file:\/\/\S+)/gi
+
+    const modifiedText = text.replace(urlPattern, (match) => {
+      const placeholder = generateUniqueCode(URI, this.replacementCounter++)
+      this.replacementMap.set(placeholder, match)
+      return placeholder
+    })
 
-    DEBUG && console.log('SentenceTokenizer.tokenize: ' + tokens)
+    return modifiedText
+  }
+
+  replaceAbbreviations (text) {
+    const pattern = new RegExp(`(${this.abbreviations.map(abbrev => escapeRegExp(abbrev)).join('|')})`, 'g')
+    const replacedText = text.replace(pattern, match => {
+      const code = generateUniqueCode(ABBREV, this.replacementCounter++)
+      this.replacementMap.set(code, match)
+      return code
+    })
+
+    return replacedText
+  }
+
+  replaceDelimitersWithPlaceholders (text) {
+    // Regular expression for sentence delimiters optionally followed by a bracket or quote
+    // Multiple delimiters with spaces in between are allowed
+    // The look ahead makes sure that there is punctuation symbol as next symbol
+    const delimiterPattern = /(?=[.?!…])([.?!… ]+)(["'”’)}\]]?)/g
+
+    const modifiedText = text.replace(delimiterPattern, (match, p1, p2) => {
+      const placeholder = generateUniqueCode(DELIM, this.replacementCounter++)
+      this.delimiterMap.set(placeholder, p1 + p2)
+      return placeholder
+    })
 
-    if (!tokens) {
+    return modifiedText
+  }
+
+  splitOnPlaceholders (text, placeholders) {
+    if (this.delimiterMap.size === 0) {
       return [text]
     }
 
-    // remove unecessary white space
-    tokens = tokens.map(Function.prototype.call, String.prototype.trim)
+    const keys = Array.from(this.delimiterMap.keys())
+    const pattern = new RegExp(`(${keys.map(escapeRegExp).join('|')})`)
+    const parts = text.split(pattern)
+
+    const sentences = []
+    for (let i = 0; i < parts.length; i += 2) {
+      const sentence = parts[i]
+      const placeholder = parts[i + 1] || ''
+      sentences.push(sentence + placeholder)
+    }
+
+    return sentences
+  }
+
+  replaceNumbersWithCode (text) {
+    // Regular expression to match numbers, including decimal points and commas
+    const numberPattern = /\b\d{1,3}(?:,\d{3})*(?:\.\d+)?\b/g
+
+    const replacedText = text.replace(numberPattern, match => {
+      const code = generateUniqueCode(NUM, this.replacementCounter++)
+      this.replacementMap.set(code, match)
+      return code
+    })
+
+    return replacedText
+  }
+
+  revertReplacements (text) {
+    let originalText = text
+    for (const [placeholder, replacement] of this.replacementMap.entries()) {
+      const pattern = new RegExp(escapeRegExp(placeholder), 'g')
+      originalText = originalText.replace(pattern, replacement)
+    }
+
+    return originalText
+  }
+
+  revertDelimiters (text) {
+    let originalText = text
+    for (const [placeholder, replacement] of this.delimiterMap.entries()) {
+      const pattern = new RegExp(escapeRegExp(placeholder), 'g')
+      originalText = originalText.replace(pattern, replacement)
+    }
+
+    return originalText
+  }
+
+  tokenize (text) {
+    this.replacementCounter = 0
+    this.replacementMap = new Map()
+    this.delimiterMap = new Map()
+
+    DEBUG && console.log('---Start of sentence tokenization-----------------------')
+    DEBUG && console.log('Original input: >>>' + text + '<<<')
+    // Replace abbreviations
+    const result1 = this.replaceAbbreviations(text)
+    DEBUG && console.log('Phase 1: replacing abbreviations: ' + JSON.stringify(result1))
+
+    // Replace URIs
+    const result2 = this.replaceUrisWithPlaceholders(result1)
+    DEBUG && console.log('Phase 2: replacing URIs: ' + JSON.stringify(result2))
+
+    // Replace delimiters followed by optional quotes, brackets, and braces
+    const result3 = this.replaceNumbersWithCode(result2)
+    DEBUG && console.log('Phase 3: replacing numbers with placeholders: ' + JSON.stringify(result3))
+
+    // Replace delimiters followed by optional quotes, brackets, and braces
+    const result4 = this.replaceDelimitersWithPlaceholders(result3)
+    DEBUG && console.log('Phase 4: replacing delimiters with placeholders: ' + JSON.stringify(result4))
+
+    // Split on placeholders for sentence delimiters
+    const sentences = this.splitOnPlaceholders(result4)
+    DEBUG && console.log('Phase 5: splitting into sentences on placeholders: ' + JSON.stringify(sentences))
+
+    // Replace back all abbreviations, URIs, and delimiters
+    const newSentences = sentences.map(s => {
+      const s1 = this.revertReplacements(s)
+      return this.revertDelimiters(s1)
+    })
+    DEBUG && console.log('Phase 6: replacing back abbreviations, URIs, numbers and delimiters: ' + JSON.stringify(newSentences))
+
+    const trimmedSentences = this.trim(newSentences)
+    DEBUG && console.log('Phase 7: trimming array of empty sentences: ' + JSON.stringify(trimmedSentences))
 
-    DEBUG && console.log('SentenceTokenizer.tokenize: tokens after removing whitespace ' + tokens)
+    const trimmedSentences2 = trimmedSentences.map(sent => sent.trim())
+    DEBUG && console.log('Phase 8: trimming sentences from surrounding whitespace: ' + JSON.stringify(trimmedSentences2))
+    DEBUG && console.log('---End of sentence tokenization--------------------------')
+    DEBUG && console.log('---Replacement map---------------------------------------')
+    DEBUG && console.log([...this.replacementMap.entries()])
+    DEBUG && console.log('---Delimiter map-----------------------------------------')
+    DEBUG && console.log([...this.delimiterMap.entries()])
+    DEBUG && console.log('---------------------------------------------------------')
 
-    return this.trim(tokens)
+    return trimmedSentences2
   }
 }
 

package/lib/natural/tokenizers/{sentence_tokenizer_parser.js → sentence_tokenizer_deprecated.js}

@@ -1,13 +1,16 @@
 /*
-Copyright (c) 2020, Hugo ter Doest
+Copyright (c) 2011, Chris Umbel
+
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal
 in the Software without restriction, including without limitation the rights
 to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 copies of the Software, and to permit persons to whom the Software is
 furnished to do so, subject to the following conditions:
+
 The above copyright notice and this permission notice shall be included in
 all copies or substantial portions of the Software.
+
 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
@@ -19,13 +22,29 @@ THE SOFTWARE.
 
 'use strict'
 
-const parser = require('./parser_sentence_tokenizer')
-
 const Tokenizer = require('./tokenizer')
 
+const DEBUG = false
+
 class SentenceTokenizer extends Tokenizer {
   tokenize (text) {
-    return (parser.parse(text))
+    // Break string up in to sentences based on punctation and quotation marks
+    // See https://gist.github.com/Hugo-ter-Doest/4ed21fb7eb5077814d998fa61a726566
+    // for a breakdown of the regular expression
+    let tokens = text.match(/(?<=\s+|^)["'‘“'"[({⟨]?(.*?[.?!…]|.+)(\s[.?!…])*["'’”'"\])}⟩]?(?=\s+|$)/g)
+
+    DEBUG && console.log('SentenceTokenizer.tokenize: ' + tokens)
+
+    if (!tokens) {
+      return [text]
+    }
+
+    // remove unecessary white space
+    tokens = tokens.map(Function.prototype.call, String.prototype.trim)
+
+    DEBUG && console.log('SentenceTokenizer.tokenize: tokens after removing whitespace ' + tokens)
+
+    return this.trim(tokens)
   }
 }
 

package/lib/natural/util/abbreviations_en.js

@@ -19,7 +19,8 @@ const knownAbbreviations = [
   'tel.',
   'temp.',
   'vet.',
-  'vs.'
+  'vs.',
+  'i.e.'
 ]
 
 exports.knownAbbreviations = knownAbbreviations

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "natural",
   "description": "General natural language (tokenizing, stemming (English, Russian, Spanish), part-of-speech tagging, sentiment analysis, classification, inflection, phonetics, tfidf, WordNet, jaro-winkler, Levenshtein distance, Dice's Coefficient) facilities for node.",
-  "version": "7.1.0",
+  "version": "8.0.0",
   "homepage": "https://github.com/NaturalNode/natural",
   "repository": {
     "type": "git",