natural-content - npm Package Compare versions

Comparing version 1.0.9 to 1.0.10

index.js

@@ -1,24 +0,23 @@
-var _          = require('underscore');
-var diacritics = require('./lib/diacritics.js');
 
-var WORD_SEPARATOR = " ";
-var STATEMENT_SEPARATOR = "##";
-var EMPTY = "";
+const _ = require('underscore');
+const diacritics = require('./lib/diacritics.js');
 
+const WORD_SEPARATOR = ' ';
+const STATEMENT_SEPARATOR = '##';
 
 /**
- *  Get all statements
- *
- * @param Text or HTML content (String)
- * @return an array of statements
- */
- function getStatements (text) {
-  return text.replace(/[\n\r]/g, WORD_SEPARATOR)   // Convert end of line
+  * getStatements - Get all statements from a text
+  *
+  * @param  {string} text the text from which we want to extract the statements
+  * @returns {Array}      an array of statements
+  */
+function getStatements(text) {
+  return text.replace(/[\n\r]/g, WORD_SEPARATOR) // Convert end of line
                       .replace(/[\t]/g, WORD_SEPARATOR) // Remove Tabs
-                      .replace(/ /gi,WORD_SEPARATOR)// remove HTML entities, only non breaking space
-                      .replace(/(<([^>]+)>)/ig, WORD_SEPARATOR)   // remove HTML tags
+                      .replace(/&nbsp;/gi, WORD_SEPARATOR)// remove HTML entities, only non breaking space
+                      .replace(/(<([^>]+)>)/ig, WORD_SEPARATOR) // remove HTML tags
                       .replace(/  +/g, WORD_SEPARATOR) // remove multiple spaces
-                      .replace(/[.]/g, "." + STATEMENT_SEPARATOR)
-                      .replace(/[!]/g, "!" + STATEMENT_SEPARATOR)
-                      .replace(/[?]/g, "?" + STATEMENT_SEPARATOR)
+                      .replace(/[.]/g, `.${ STATEMENT_SEPARATOR }`)
+                      .replace(/[!]/g, `!${ STATEMENT_SEPARATOR }`)
+                      .replace(/[?]/g, `?${ STATEMENT_SEPARATOR }`)
                       .split(STATEMENT_SEPARATOR);
@@ -28,38 +27,37 @@ }
 /**
- *  Remove all special caracters, symbols & digits
+ * removeSpecials - Remove specials caracters from a text
  *
- * @param a text as a String
- * @return The text without special caracters
+ * @param  {string} text the text
+ * @returns {string}     the same text without specials caracters
  */
 function removeSpecials(text) {
-  var cleanText = text.replace(/[\t]/g, WORD_SEPARATOR) // Remove Tabs
+  const cleanText = text.replace(/[\t]/g, WORD_SEPARATOR) // Remove Tabs
                       .replace(/[\n\r]/g, WORD_SEPARATOR)
-                      .replace(/&nbsp;/gi,WORD_SEPARATOR)// remove HTML entities, only non breaking space
-                      .replace(/(<([^>]+)>)/ig,WORD_SEPARATOR)  // remove HTML tags
+                      .replace(/&nbsp;/gi, WORD_SEPARATOR)// remove HTML entities, only non breaking space
+                      .replace(/(<([^>]+)>)/ig, WORD_SEPARATOR) // remove HTML tags
                       .replace(/[|&’«»'"\/(\/)\/!\/?\\-]/g, WORD_SEPARATOR);
 
+  const lower = cleanText.toLowerCase();
+  const upper = cleanText.toUpperCase();
 
-    var lower = cleanText.toLowerCase();
-    var upper = cleanText.toUpperCase();
+  let result = '';
 
-    var result = "";
-    for(var i=0; i<lower.length; ++i) {
-
-        if(lower[i] !== upper[i] || lower[i].trim() === ''){
-          result += cleanText[i];
-        }
+  for (let i = 0; i < lower.length; ++i) {
+    if (lower[i] !== upper[i] || lower[i].trim() === '') {
+      result += cleanText[i];
     }
+  }
 
+  // remove multiple spaces
+  result = result.replace(/\s+/g, WORD_SEPARATOR);
 
-    result = result.replace(/\s+/g, WORD_SEPARATOR);  // remove multiple spaces
-    return result;
+  return result;
 }
 
 /**
- *  Remove all diacritics from a text
- *
- *
- * @param a text as a String
- * @return the text without diacritics
- */
+  * removeDiacritics -  Remove all diacritics from a text
+  *
+  * @param  {string} text the text
+  * @returns {string}     the same text without diacritics
+  */
 function removeDiacritics(text) {
@@ -76,11 +74,19 @@ return diacritics.remove(text);
  * @param the iso code for the target language
- * @return an array of words (string)
+ * @returns an array of words (string)
  */
-function getWords (text, withStopWords, language) {
 
-  var words = text.replace(/[\n\r]/g, WORD_SEPARATOR)   // Convert end of line
+/**
+ * getWords - Get all words from a Text
+ *
+ * @param  {string} text          the text
+ * @param  {boolean} withStopWords if the stop words will be remove
+ * @param  {string} language      language code (fr, en, ...)
+ * @returns {string}              an array of words
+ */
+function getWords(text, withStopWords, language) {
+  const words = text.replace(/[\n\r]/g, WORD_SEPARATOR) // Convert end of line
                       .replace(/[\t]/g, WORD_SEPARATOR) // Remove Tabs
-                      .replace(/&nbsp;/gi,WORD_SEPARATOR) // remove HTML entities, only non breaking space
-                      .replace(/(<([^>]+)>)/ig,WORD_SEPARATOR)   // remove HTML tags
-                      .replace(/['’«»";:,.\/(\/)\/!\/?\\-]/g, WORD_SEPARATOR)  // Remove punctuations
+                      .replace(/&nbsp;/gi, WORD_SEPARATOR) // remove HTML entities, only non breaking space
+                      .replace(/(<([^>]+)>)/ig, WORD_SEPARATOR) // remove HTML tags
+                      .replace(/['’«»";:,.\/(\/)\/!\/?\\-]/g, WORD_SEPARATOR) // Remove punctuations
                       .replace(/\s+/g, WORD_SEPARATOR) // remove multiple spaces
@@ -90,13 +96,12 @@ .toLowerCase()
 
-
   // Remove empty string
   if (withStopWords) {
-      return _.filter(words, function(word){return (word !== '') ; });
+    return words.filter((word) => word !== '');
   }
+
   // Remove empty string & stopwords
-  else {
-      var stopwords = require("./lib/stopwords-" + language).stopwords;
-      return _.filter(words, function(word){return (word !== ''  && stopwords.indexOf(removeDiacritics(word)) === -1); });
-  }
 
+  const { stopwords } = require(`./lib/stopwords-${ language }`);
+
+  return words.filter((word) => word !== '' && stopwords.indexOf(removeDiacritics(word)) === -1);
 }
@@ -109,23 +114,34 @@
  * @param the cardinality of the grams
- * @return an array of ngrams value (string)
+ * @returns an array of ngrams value (string)
  */
- function getNgrams(words, n) {
-    var result = [];
 
-    var count = _.max([0, words.length - n + 1]);
-    for (var i = 0; i < count; i++) {
-        var slice =  words.slice(i, i + n);
-        // Convert the ngram array into a ngram string and add it in the result list
-        result.push(_.reduce(slice, function(memo, word){ return (memo ? memo + " " + word : word);}));
-    }
-    return result;
+/**
+ * getNgrams - get an array of ngrams
+ *
+ * @param  {Array} words an array of word
+ * @param  {number} n    number of words to build the ngram elements
+ * @returns {Array}       an array of ngrams
+ */
+function getNgrams(words, n) {
+  const result = [];
+
+  const count = _.max([ 0, words.length - n + 1 ]);
+
+  for (let i = 0; i < count; i++) {
+    const slice = words.slice(i, i + n);
+
+    // Convert the ngram array into a ngram string and add it in the result list
+    result.push(_.reduce(slice, (memo, word) => memo ? `${ memo } ${ word }` : word));
+  }
+
+  return result;
 }
 
 /**
- * Get the term frequency (tf) of each word of a document
+ * getTf - Get the term frequency (tf) of each word of a document
  *
- * @param an array of words (String) matching to the document content.
- * @param ngrams cardinality (optional). Has to be > 0
- * @param number  of documents for each word (optional). Those value can be used later for the IDF computation
- * @return a TF json structure :
+ * @param  {string} words array of words (String) matching to the document content
+ * @param  {number} n     cardinality of the ngrams (optional). Has to be > 0
+ * @param  {object} stats the current stat aout the word or ngrams (could be null). This is used to compute the tf/idf
+ * @returns {object}      F json structure :
  *    {
@@ -138,80 +154,74 @@ *        count : an array of word with the number of occurence in the document (the array index matches to the word)
 function getTf(words, n, stats) {
+  let ws = words;
 
-    var ws = words;
-    if (n && n > 1) {
-      ws = getNgrams(words, n);
-    }
-    var count = _.countBy(ws, function(word) { return word; });
-    var max = _.max(count);
-    var tfs = {};
+  if (n && n > 1) {
+    ws = getNgrams(words, n);
+  }
 
-    _.keys(count).forEach(function(word) {
+  const count = _.countBy(ws, (word) => word);
+  const max = _.max(count);
+  const tfs = {};
 
-        // Calculate the tf for this word
-        tfs[word] = count[word]/max;
+  _.keys(count).forEach((word) => {
+    // Calculate the tf for this word
+    tfs[word] = count[word] / max;
 
-        // Update stats
-        if (stats) {
+    // Update stats
+    if (stats) {
+      // Calculate sum & register the tf for min & max computation
+      if (stats.has(word) && stats.get(word).tfs) {
+        const wordStat = stats.get(word);
 
-            // Calculate sum & register the tf for min & max computation
-            if (stats.has(word) && stats.get(word).tfs) {
-                var wordStat = stats.get(word);
-                // update the number of documents for this word
-                wordStat.nbrDocs++ ;
+        // update the number of documents for this word
+        wordStat.nbrDocs++;
 
-                // Add the tf in the list of all tfs for this word
-                wordStat.tfs.push(tfs[word]);
-                wordStat.tfSum += tfs[word];
-            }
-            else {
-                var newWordStat = initWordStat(word, tfs[word]);
-                stats.set(word, newWordStat);
-            }
-        }
+        // Add the tf in the list of all tfs for this word
+        wordStat.tfs.push(tfs[word]);
+        wordStat.tfSum += tfs[word];
+      } else {
+        const newWordStat = initWordStat(word, tfs[word]);
 
-    });
+        stats.set(word, newWordStat);
+      }
+    }
+  });
 
-    return {
-      count : count,
-      tfs : tfs,
-      max : max
-    };
-
+  return {
+    count,
+    tfs,
+    max
+  };
 }
 
-
 /**
- * Get the tfIdf for each word of a document
- *
- *
- * @param the document represented by an term frequency array.
- *        the function getTf can be used for generating the term frequency array
- * @param the number of document per word (index = word)
- * @param the number of documents
- * @param the stats about the words for the full set of documents
- * @return
- */
+  * geTfIdf - Get the tfIdf for each word of a document
+  *
+  * @param  {object} document the document represented by an term frequency array.
+  * @param  {number} nbrDocs  the number of documents
+  * @param  {object} stats    stats about the words for the full set of documents
+  * @returns {object}         the tf/idf info for this document
+  */
 function geTfIdf(document, nbrDocs, stats) {
+  const tfIdf = {};
 
-    var tfIdf = {};
-    _.keys(document.tfs).forEach(function(word) {
-        var idf = Math.log(nbrDocs/stats.get(word).nbrDocs) + 1;
-        tfIdf[word] = document.tfs[word] * idf;
+  _.keys(document.tfs).forEach((word) => {
+    const idf = Math.log(nbrDocs / stats.get(word).nbrDocs) + 1;
 
-        if (stats.has(word) && stats.get(word).tfIdfs &&  stats.get(word).idfs) {
-            var wordStat = stats.get(word);
+    tfIdf[word] = document.tfs[word] * idf;
 
-            wordStat.tfIdfs.push(tfIdf[word]);
-            wordStat.tfIdfSum += tfIdf[word];
-            wordStat.idfs.push(idf);
-            wordStat.idfSum += idf;
-        }
+    if (stats.has(word) && stats.get(word).tfIdfs && stats.get(word).idfs) {
+      const wordStat = stats.get(word);
 
-    });
+      wordStat.tfIdfs.push(tfIdf[word]);
+      wordStat.tfIdfSum += tfIdf[word];
+      wordStat.idfs.push(idf);
+      wordStat.idfSum += idf;
+    }
+  });
 
-    document.tfIdf = tfIdf;
-    return document;
+  document.tfIdf = tfIdf;
+
+  return document;
 }
 
-
 /**
@@ -224,65 +234,78 @@ *  Get the TF.IDF for each words found in several documents
  */
+
+/**
+  * getTfIdfs - Get the TF.IDF for each words found in several documents
+  *
+  * @param  {Array} documents    arrays of String matching to the document content. It could be Text or HTML
+  * @param  {number} n             ngram cardinality (optional). Has to be > 0
+  * @param  {boolean} withStopWords if true, remove the stopwords
+  * @param  {string} language      the language code (fr, en, ... )
+  * @returns {object}              the tf/idf for each word/ngrams
+  */
 function getTfIdfs(documents, n, withStopWords, language) {
+  const result = {};
+  const stats = new Map();
 
-    var result = {};
-    var stats = new Map();
+  // Calculate the TF of each words for each docs
+  const tfs = _.map(documents, (document) => getTf(getWords(document, withStopWords, language), n, stats));
 
-    // Calculate the TF of each words for each docs
-    var tfs = _.map(documents, function(document){ return getTf(getWords(document, withStopWords, language), n, stats);});
+  // Calculate the tf.idf for each each docs & produce stats per word
+  const data = _.map(tfs, (docTfs) => geTfIdf(docTfs, documents.length, stats));
 
-    // Calculate the tf.idf for each each docs & produce stats per word
-    var data = _.map(tfs, function(docTfs) { return geTfIdf(docTfs, documents.length, stats );});
+  // Calculate stats : min, max, avg for tf, idf & tf.idf
+  for (const wordStat of stats.values()) {
+    wordStat.tfMin = _.min(wordStat.tfs);
+    wordStat.tfMax = _.max(wordStat.tfs);
+    wordStat.tfAvg = wordStat.tfSum / wordStat.nbrDocs;
 
-    // Calculate stats : min, max, avg for tf, idf & tf.idf
-    for (var wordStat of stats.values()) {
+    wordStat.idfMax = _.max(wordStat.idfs);
+    wordStat.idfAvg = wordStat.idfSum / wordStat.nbrDocs;
 
-        wordStat.tfMin = _.min(wordStat.tfs);
-        wordStat.tfMax = _.max(wordStat.tfs);
-        wordStat.tfAvg = wordStat.tfSum / wordStat.nbrDocs;
+    wordStat.tfIdfMin = _.min(wordStat.tfIdfs);
+    wordStat.tfIdfMax = _.max(wordStat.tfIdfs);
+    wordStat.tfIdfAvg = wordStat.tfIdfSum / wordStat.nbrDocs;
+  }
 
-        wordStat.idfMax = _.max(wordStat.idfs);
-        wordStat.idfAvg = wordStat.idfSum / wordStat.nbrDocs;
+  result.documents = data;
+  result.numberOfDocs = documents.length;
+  result.stats = stats;
 
-        wordStat.tfIdfMin = _.min(wordStat.tfIdfs);
-        wordStat.tfIdfMax = _.max(wordStat.tfIdfs);
-        wordStat.tfIdfAvg = wordStat.tfIdfSum / wordStat.nbrDocs;
-
-    }
-
-    result.documents = data;
-    result.numberOfDocs = documents.length;
-    result.stats = stats;
-
-    return result;
+  return result;
 }
 
-
 /**
- *  Create an new Stat object for one word
+ * initWordStat - Create an new Stat object for one word
  *
+ * @param  {string} word the word
+ * @param  {number} tf   the tf value
+ * @returns {object}     the stat about the word
  */
-function initWordStat(word,  tf) {
+function initWordStat(word, tf) {
+  return {
+    word,
+    nbrDocs: 1,
+    tfSum: tf,
+    tfs: [ tf ],
 
-    return {
-      word : word,
-      nbrDocs : 1,
-      tfSum : tf,
-      tfs : [tf],
+    idfSum: 0,
+    idfs: [],
 
-      idfSum : 0,
-      idfs : [],
+    tfIdfSum: 0,
+    tfIdfs: []
 
-      tfIdfSum : 0,
-      tfIdfs : []
-
-    };
-
+  };
 }
 
 exports.getStatements = getStatements;
+
 exports.removeSpecials = removeSpecials;
+
 exports.removeDiacritics = removeDiacritics;
+
 exports.getWords = getWords;
+
 exports.getNgrams = getNgrams;
+
 exports.getTf = getTf;
+
 exports.getTfIdfs = getTfIdfs;

lib/diacritics.js

@@ -1,104 +0,104 @@
-var defaultDiacriticsRemovalap = [
-    {'base':'A', 'letters':'\u0041\u24B6\uFF21\u00C0\u00C1\u00C2\u1EA6\u1EA4\u1EAA\u1EA8\u00C3\u0100\u0102\u1EB0\u1EAE\u1EB4\u1EB2\u0226\u01E0\u00C4\u01DE\u1EA2\u00C5\u01FA\u01CD\u0200\u0202\u1EA0\u1EAC\u1EB6\u1E00\u0104\u023A\u2C6F'},
-    {'base':'AA','letters':'\uA732'},
-    {'base':'AE','letters':'\u00C6\u01FC\u01E2'},
-    {'base':'AO','letters':'\uA734'},
-    {'base':'AU','letters':'\uA736'},
-    {'base':'AV','letters':'\uA738\uA73A'},
-    {'base':'AY','letters':'\uA73C'},
-    {'base':'B', 'letters':'\u0042\u24B7\uFF22\u1E02\u1E04\u1E06\u0243\u0182\u0181'},
-    {'base':'C', 'letters':'\u0043\u24B8\uFF23\u0106\u0108\u010A\u010C\u00C7\u1E08\u0187\u023B\uA73E'},
-    {'base':'D', 'letters':'\u0044\u24B9\uFF24\u1E0A\u010E\u1E0C\u1E10\u1E12\u1E0E\u0110\u018B\u018A\u0189\uA779'},
-    {'base':'DZ','letters':'\u01F1\u01C4'},
-    {'base':'Dz','letters':'\u01F2\u01C5'},
-    {'base':'E', 'letters':'\u0045\u24BA\uFF25\u00C8\u00C9\u00CA\u1EC0\u1EBE\u1EC4\u1EC2\u1EBC\u0112\u1E14\u1E16\u0114\u0116\u00CB\u1EBA\u011A\u0204\u0206\u1EB8\u1EC6\u0228\u1E1C\u0118\u1E18\u1E1A\u0190\u018E'},
-    {'base':'F', 'letters':'\u0046\u24BB\uFF26\u1E1E\u0191\uA77B'},
-    {'base':'G', 'letters':'\u0047\u24BC\uFF27\u01F4\u011C\u1E20\u011E\u0120\u01E6\u0122\u01E4\u0193\uA7A0\uA77D\uA77E'},
-    {'base':'H', 'letters':'\u0048\u24BD\uFF28\u0124\u1E22\u1E26\u021E\u1E24\u1E28\u1E2A\u0126\u2C67\u2C75\uA78D'},
-    {'base':'I', 'letters':'\u0049\u24BE\uFF29\u00CC\u00CD\u00CE\u0128\u012A\u012C\u0130\u00CF\u1E2E\u1EC8\u01CF\u0208\u020A\u1ECA\u012E\u1E2C\u0197'},
-    {'base':'J', 'letters':'\u004A\u24BF\uFF2A\u0134\u0248'},
-    {'base':'K', 'letters':'\u004B\u24C0\uFF2B\u1E30\u01E8\u1E32\u0136\u1E34\u0198\u2C69\uA740\uA742\uA744\uA7A2'},
-    {'base':'L', 'letters':'\u004C\u24C1\uFF2C\u013F\u0139\u013D\u1E36\u1E38\u013B\u1E3C\u1E3A\u0141\u023D\u2C62\u2C60\uA748\uA746\uA780'},
-    {'base':'LJ','letters':'\u01C7'},
-    {'base':'Lj','letters':'\u01C8'},
-    {'base':'M', 'letters':'\u004D\u24C2\uFF2D\u1E3E\u1E40\u1E42\u2C6E\u019C'},
-    {'base':'N', 'letters':'\u004E\u24C3\uFF2E\u01F8\u0143\u00D1\u1E44\u0147\u1E46\u0145\u1E4A\u1E48\u0220\u019D\uA790\uA7A4'},
-    {'base':'NJ','letters':'\u01CA'},
-    {'base':'Nj','letters':'\u01CB'},
-    {'base':'O', 'letters':'\u004F\u24C4\uFF2F\u00D2\u00D3\u00D4\u1ED2\u1ED0\u1ED6\u1ED4\u00D5\u1E4C\u022C\u1E4E\u014C\u1E50\u1E52\u014E\u022E\u0230\u00D6\u022A\u1ECE\u0150\u01D1\u020C\u020E\u01A0\u1EDC\u1EDA\u1EE0\u1EDE\u1EE2\u1ECC\u1ED8\u01EA\u01EC\u00D8\u01FE\u0186\u019F\uA74A\uA74C'},
-    {'base':'OI','letters':'\u01A2'},
-    {'base':'OO','letters':'\uA74E'},
-    {'base':'OU','letters':'\u0222'},
-    {'base':'OE','letters':'\u008C\u0152'},
-    {'base':'oe','letters':'\u009C\u0153'},
-    {'base':'P', 'letters':'\u0050\u24C5\uFF30\u1E54\u1E56\u01A4\u2C63\uA750\uA752\uA754'},
-    {'base':'Q', 'letters':'\u0051\u24C6\uFF31\uA756\uA758\u024A'},
-    {'base':'R', 'letters':'\u0052\u24C7\uFF32\u0154\u1E58\u0158\u0210\u0212\u1E5A\u1E5C\u0156\u1E5E\u024C\u2C64\uA75A\uA7A6\uA782'},
-    {'base':'S', 'letters':'\u0053\u24C8\uFF33\u1E9E\u015A\u1E64\u015C\u1E60\u0160\u1E66\u1E62\u1E68\u0218\u015E\u2C7E\uA7A8\uA784'},
-    {'base':'T', 'letters':'\u0054\u24C9\uFF34\u1E6A\u0164\u1E6C\u021A\u0162\u1E70\u1E6E\u0166\u01AC\u01AE\u023E\uA786'},
-    {'base':'TZ','letters':'\uA728'},
-    {'base':'U', 'letters':'\u0055\u24CA\uFF35\u00D9\u00DA\u00DB\u0168\u1E78\u016A\u1E7A\u016C\u00DC\u01DB\u01D7\u01D5\u01D9\u1EE6\u016E\u0170\u01D3\u0214\u0216\u01AF\u1EEA\u1EE8\u1EEE\u1EEC\u1EF0\u1EE4\u1E72\u0172\u1E76\u1E74\u0244'},
-    {'base':'V', 'letters':'\u0056\u24CB\uFF36\u1E7C\u1E7E\u01B2\uA75E\u0245'},
-    {'base':'VY','letters':'\uA760'},
-    {'base':'W', 'letters':'\u0057\u24CC\uFF37\u1E80\u1E82\u0174\u1E86\u1E84\u1E88\u2C72'},
-    {'base':'X', 'letters':'\u0058\u24CD\uFF38\u1E8A\u1E8C'},
-    {'base':'Y', 'letters':'\u0059\u24CE\uFF39\u1EF2\u00DD\u0176\u1EF8\u0232\u1E8E\u0178\u1EF6\u1EF4\u01B3\u024E\u1EFE'},
-    {'base':'Z', 'letters':'\u005A\u24CF\uFF3A\u0179\u1E90\u017B\u017D\u1E92\u1E94\u01B5\u0224\u2C7F\u2C6B\uA762'},
-    {'base':'a', 'letters':'\u0061\u24D0\uFF41\u1E9A\u00E0\u00E1\u00E2\u1EA7\u1EA5\u1EAB\u1EA9\u00E3\u0101\u0103\u1EB1\u1EAF\u1EB5\u1EB3\u0227\u01E1\u00E4\u01DF\u1EA3\u00E5\u01FB\u01CE\u0201\u0203\u1EA1\u1EAD\u1EB7\u1E01\u0105\u2C65\u0250'},
-    {'base':'aa','letters':'\uA733'},
-    {'base':'ae','letters':'\u00E6\u01FD\u01E3'},
-    {'base':'ao','letters':'\uA735'},
-    {'base':'au','letters':'\uA737'},
-    {'base':'av','letters':'\uA739\uA73B'},
-    {'base':'ay','letters':'\uA73D'},
-    {'base':'b', 'letters':'\u0062\u24D1\uFF42\u1E03\u1E05\u1E07\u0180\u0183\u0253'},
-    {'base':'c', 'letters':'\u0063\u24D2\uFF43\u0107\u0109\u010B\u010D\u00E7\u1E09\u0188\u023C\uA73F\u2184'},
-    {'base':'d', 'letters':'\u0064\u24D3\uFF44\u1E0B\u010F\u1E0D\u1E11\u1E13\u1E0F\u0111\u018C\u0256\u0257\uA77A'},
-    {'base':'dz','letters':'\u01F3\u01C6'},
-    {'base':'e', 'letters':'\u0065\u24D4\uFF45\u00E8\u00E9\u00EA\u1EC1\u1EBF\u1EC5\u1EC3\u1EBD\u0113\u1E15\u1E17\u0115\u0117\u00EB\u1EBB\u011B\u0205\u0207\u1EB9\u1EC7\u0229\u1E1D\u0119\u1E19\u1E1B\u0247\u025B\u01DD'},
-    {'base':'f', 'letters':'\u0066\u24D5\uFF46\u1E1F\u0192\uA77C'},
-    {'base':'g', 'letters':'\u0067\u24D6\uFF47\u01F5\u011D\u1E21\u011F\u0121\u01E7\u0123\u01E5\u0260\uA7A1\u1D79\uA77F'},
-    {'base':'h', 'letters':'\u0068\u24D7\uFF48\u0125\u1E23\u1E27\u021F\u1E25\u1E29\u1E2B\u1E96\u0127\u2C68\u2C76\u0265'},
-    {'base':'hv','letters':'\u0195'},
-    {'base':'i', 'letters':'\u0069\u24D8\uFF49\u00EC\u00ED\u00EE\u0129\u012B\u012D\u00EF\u1E2F\u1EC9\u01D0\u0209\u020B\u1ECB\u012F\u1E2D\u0268\u0131'},
-    {'base':'j', 'letters':'\u006A\u24D9\uFF4A\u0135\u01F0\u0249'},
-    {'base':'k', 'letters':'\u006B\u24DA\uFF4B\u1E31\u01E9\u1E33\u0137\u1E35\u0199\u2C6A\uA741\uA743\uA745\uA7A3'},
-    {'base':'l', 'letters':'\u006C\u24DB\uFF4C\u0140\u013A\u013E\u1E37\u1E39\u013C\u1E3D\u1E3B\u017F\u0142\u019A\u026B\u2C61\uA749\uA781\uA747'},
-    {'base':'lj','letters':'\u01C9'},
-    {'base':'m', 'letters':'\u006D\u24DC\uFF4D\u1E3F\u1E41\u1E43\u0271\u026F'},
-    {'base':'n', 'letters':'\u006E\u24DD\uFF4E\u01F9\u0144\u00F1\u1E45\u0148\u1E47\u0146\u1E4B\u1E49\u019E\u0272\u0149\uA791\uA7A5'},
-    {'base':'nj','letters':'\u01CC'},
-    {'base':'o', 'letters':'\u006F\u24DE\uFF4F\u00F2\u00F3\u00F4\u1ED3\u1ED1\u1ED7\u1ED5\u00F5\u1E4D\u022D\u1E4F\u014D\u1E51\u1E53\u014F\u022F\u0231\u00F6\u022B\u1ECF\u0151\u01D2\u020D\u020F\u01A1\u1EDD\u1EDB\u1EE1\u1EDF\u1EE3\u1ECD\u1ED9\u01EB\u01ED\u00F8\u01FF\u0254\uA74B\uA74D\u0275'},
-    {'base':'oi','letters':'\u01A3'},
-    {'base':'ou','letters':'\u0223'},
-    {'base':'oo','letters':'\uA74F'},
-    {'base':'p','letters':'\u0070\u24DF\uFF50\u1E55\u1E57\u01A5\u1D7D\uA751\uA753\uA755'},
-    {'base':'q','letters':'\u0071\u24E0\uFF51\u024B\uA757\uA759'},
-    {'base':'r','letters':'\u0072\u24E1\uFF52\u0155\u1E59\u0159\u0211\u0213\u1E5B\u1E5D\u0157\u1E5F\u024D\u027D\uA75B\uA7A7\uA783'},
-    {'base':'s','letters':'\u0073\u24E2\uFF53\u00DF\u015B\u1E65\u015D\u1E61\u0161\u1E67\u1E63\u1E69\u0219\u015F\u023F\uA7A9\uA785\u1E9B'},
-    {'base':'t','letters':'\u0074\u24E3\uFF54\u1E6B\u1E97\u0165\u1E6D\u021B\u0163\u1E71\u1E6F\u0167\u01AD\u0288\u2C66\uA787'},
-    {'base':'tz','letters':'\uA729'},
-    {'base':'u','letters': '\u0075\u24E4\uFF55\u00F9\u00FA\u00FB\u0169\u1E79\u016B\u1E7B\u016D\u00FC\u01DC\u01D8\u01D6\u01DA\u1EE7\u016F\u0171\u01D4\u0215\u0217\u01B0\u1EEB\u1EE9\u1EEF\u1EED\u1EF1\u1EE5\u1E73\u0173\u1E77\u1E75\u0289'},
-    {'base':'v','letters':'\u0076\u24E5\uFF56\u1E7D\u1E7F\u028B\uA75F\u028C'},
-    {'base':'vy','letters':'\uA761'},
-    {'base':'w','letters':'\u0077\u24E6\uFF57\u1E81\u1E83\u0175\u1E87\u1E85\u1E98\u1E89\u2C73'},
-    {'base':'x','letters':'\u0078\u24E7\uFF58\u1E8B\u1E8D'},
-    {'base':'y','letters':'\u0079\u24E8\uFF59\u1EF3\u00FD\u0177\u1EF9\u0233\u1E8F\u00FF\u1EF7\u1E99\u1EF5\u01B4\u024F\u1EFF'},
-    {'base':'z','letters':'\u007A\u24E9\uFF5A\u017A\u1E91\u017C\u017E\u1E93\u1E95\u01B6\u0225\u0240\u2C6C\uA763'}
+const defaultDiacriticsRemovalap = [
+  { base: 'A', letters: '\u0041\u24B6\uFF21\u00C0\u00C1\u00C2\u1EA6\u1EA4\u1EAA\u1EA8\u00C3\u0100\u0102\u1EB0\u1EAE\u1EB4\u1EB2\u0226\u01E0\u00C4\u01DE\u1EA2\u00C5\u01FA\u01CD\u0200\u0202\u1EA0\u1EAC\u1EB6\u1E00\u0104\u023A\u2C6F' },
+  { base: 'AA', letters: '\uA732' },
+  { base: 'AE', letters: '\u00C6\u01FC\u01E2' },
+  { base: 'AO', letters: '\uA734' },
+  { base: 'AU', letters: '\uA736' },
+  { base: 'AV', letters: '\uA738\uA73A' },
+  { base: 'AY', letters: '\uA73C' },
+  { base: 'B', letters: '\u0042\u24B7\uFF22\u1E02\u1E04\u1E06\u0243\u0182\u0181' },
+  { base: 'C', letters: '\u0043\u24B8\uFF23\u0106\u0108\u010A\u010C\u00C7\u1E08\u0187\u023B\uA73E' },
+  { base: 'D', letters: '\u0044\u24B9\uFF24\u1E0A\u010E\u1E0C\u1E10\u1E12\u1E0E\u0110\u018B\u018A\u0189\uA779' },
+  { base: 'DZ', letters: '\u01F1\u01C4' },
+  { base: 'Dz', letters: '\u01F2\u01C5' },
+  { base: 'E', letters: '\u0045\u24BA\uFF25\u00C8\u00C9\u00CA\u1EC0\u1EBE\u1EC4\u1EC2\u1EBC\u0112\u1E14\u1E16\u0114\u0116\u00CB\u1EBA\u011A\u0204\u0206\u1EB8\u1EC6\u0228\u1E1C\u0118\u1E18\u1E1A\u0190\u018E' },
+  { base: 'F', letters: '\u0046\u24BB\uFF26\u1E1E\u0191\uA77B' },
+  { base: 'G', letters: '\u0047\u24BC\uFF27\u01F4\u011C\u1E20\u011E\u0120\u01E6\u0122\u01E4\u0193\uA7A0\uA77D\uA77E' },
+  { base: 'H', letters: '\u0048\u24BD\uFF28\u0124\u1E22\u1E26\u021E\u1E24\u1E28\u1E2A\u0126\u2C67\u2C75\uA78D' },
+  { base: 'I', letters: '\u0049\u24BE\uFF29\u00CC\u00CD\u00CE\u0128\u012A\u012C\u0130\u00CF\u1E2E\u1EC8\u01CF\u0208\u020A\u1ECA\u012E\u1E2C\u0197' },
+  { base: 'J', letters: '\u004A\u24BF\uFF2A\u0134\u0248' },
+  { base: 'K', letters: '\u004B\u24C0\uFF2B\u1E30\u01E8\u1E32\u0136\u1E34\u0198\u2C69\uA740\uA742\uA744\uA7A2' },
+  { base: 'L', letters: '\u004C\u24C1\uFF2C\u013F\u0139\u013D\u1E36\u1E38\u013B\u1E3C\u1E3A\u0141\u023D\u2C62\u2C60\uA748\uA746\uA780' },
+  { base: 'LJ', letters: '\u01C7' },
+  { base: 'Lj', letters: '\u01C8' },
+  { base: 'M', letters: '\u004D\u24C2\uFF2D\u1E3E\u1E40\u1E42\u2C6E\u019C' },
+  { base: 'N', letters: '\u004E\u24C3\uFF2E\u01F8\u0143\u00D1\u1E44\u0147\u1E46\u0145\u1E4A\u1E48\u0220\u019D\uA790\uA7A4' },
+  { base: 'NJ', letters: '\u01CA' },
+  { base: 'Nj', letters: '\u01CB' },
+  { base: 'O', letters: '\u004F\u24C4\uFF2F\u00D2\u00D3\u00D4\u1ED2\u1ED0\u1ED6\u1ED4\u00D5\u1E4C\u022C\u1E4E\u014C\u1E50\u1E52\u014E\u022E\u0230\u00D6\u022A\u1ECE\u0150\u01D1\u020C\u020E\u01A0\u1EDC\u1EDA\u1EE0\u1EDE\u1EE2\u1ECC\u1ED8\u01EA\u01EC\u00D8\u01FE\u0186\u019F\uA74A\uA74C' },
+  { base: 'OI', letters: '\u01A2' },
+  { base: 'OO', letters: '\uA74E' },
+  { base: 'OU', letters: '\u0222' },
+  { base: 'OE', letters: '\u008C\u0152' },
+  { base: 'oe', letters: '\u009C\u0153' },
+  { base: 'P', letters: '\u0050\u24C5\uFF30\u1E54\u1E56\u01A4\u2C63\uA750\uA752\uA754' },
+  { base: 'Q', letters: '\u0051\u24C6\uFF31\uA756\uA758\u024A' },
+  { base: 'R', letters: '\u0052\u24C7\uFF32\u0154\u1E58\u0158\u0210\u0212\u1E5A\u1E5C\u0156\u1E5E\u024C\u2C64\uA75A\uA7A6\uA782' },
+  { base: 'S', letters: '\u0053\u24C8\uFF33\u1E9E\u015A\u1E64\u015C\u1E60\u0160\u1E66\u1E62\u1E68\u0218\u015E\u2C7E\uA7A8\uA784' },
+  { base: 'T', letters: '\u0054\u24C9\uFF34\u1E6A\u0164\u1E6C\u021A\u0162\u1E70\u1E6E\u0166\u01AC\u01AE\u023E\uA786' },
+  { base: 'TZ', letters: '\uA728' },
+  { base: 'U', letters: '\u0055\u24CA\uFF35\u00D9\u00DA\u00DB\u0168\u1E78\u016A\u1E7A\u016C\u00DC\u01DB\u01D7\u01D5\u01D9\u1EE6\u016E\u0170\u01D3\u0214\u0216\u01AF\u1EEA\u1EE8\u1EEE\u1EEC\u1EF0\u1EE4\u1E72\u0172\u1E76\u1E74\u0244' },
+  { base: 'V', letters: '\u0056\u24CB\uFF36\u1E7C\u1E7E\u01B2\uA75E\u0245' },
+  { base: 'VY', letters: '\uA760' },
+  { base: 'W', letters: '\u0057\u24CC\uFF37\u1E80\u1E82\u0174\u1E86\u1E84\u1E88\u2C72' },
+  { base: 'X', letters: '\u0058\u24CD\uFF38\u1E8A\u1E8C' },
+  { base: 'Y', letters: '\u0059\u24CE\uFF39\u1EF2\u00DD\u0176\u1EF8\u0232\u1E8E\u0178\u1EF6\u1EF4\u01B3\u024E\u1EFE' },
+  { base: 'Z', letters: '\u005A\u24CF\uFF3A\u0179\u1E90\u017B\u017D\u1E92\u1E94\u01B5\u0224\u2C7F\u2C6B\uA762' },
+  { base: 'a', letters: '\u0061\u24D0\uFF41\u1E9A\u00E0\u00E1\u00E2\u1EA7\u1EA5\u1EAB\u1EA9\u00E3\u0101\u0103\u1EB1\u1EAF\u1EB5\u1EB3\u0227\u01E1\u00E4\u01DF\u1EA3\u00E5\u01FB\u01CE\u0201\u0203\u1EA1\u1EAD\u1EB7\u1E01\u0105\u2C65\u0250' },
+  { base: 'aa', letters: '\uA733' },
+  { base: 'ae', letters: '\u00E6\u01FD\u01E3' },
+  { base: 'ao', letters: '\uA735' },
+  { base: 'au', letters: '\uA737' },
+  { base: 'av', letters: '\uA739\uA73B' },
+  { base: 'ay', letters: '\uA73D' },
+  { base: 'b', letters: '\u0062\u24D1\uFF42\u1E03\u1E05\u1E07\u0180\u0183\u0253' },
+  { base: 'c', letters: '\u0063\u24D2\uFF43\u0107\u0109\u010B\u010D\u00E7\u1E09\u0188\u023C\uA73F\u2184' },
+  { base: 'd', letters: '\u0064\u24D3\uFF44\u1E0B\u010F\u1E0D\u1E11\u1E13\u1E0F\u0111\u018C\u0256\u0257\uA77A' },
+  { base: 'dz', letters: '\u01F3\u01C6' },
+  { base: 'e', letters: '\u0065\u24D4\uFF45\u00E8\u00E9\u00EA\u1EC1\u1EBF\u1EC5\u1EC3\u1EBD\u0113\u1E15\u1E17\u0115\u0117\u00EB\u1EBB\u011B\u0205\u0207\u1EB9\u1EC7\u0229\u1E1D\u0119\u1E19\u1E1B\u0247\u025B\u01DD' },
+  { base: 'f', letters: '\u0066\u24D5\uFF46\u1E1F\u0192\uA77C' },
+  { base: 'g', letters: '\u0067\u24D6\uFF47\u01F5\u011D\u1E21\u011F\u0121\u01E7\u0123\u01E5\u0260\uA7A1\u1D79\uA77F' },
+  { base: 'h', letters: '\u0068\u24D7\uFF48\u0125\u1E23\u1E27\u021F\u1E25\u1E29\u1E2B\u1E96\u0127\u2C68\u2C76\u0265' },
+  { base: 'hv', letters: '\u0195' },
+  { base: 'i', letters: '\u0069\u24D8\uFF49\u00EC\u00ED\u00EE\u0129\u012B\u012D\u00EF\u1E2F\u1EC9\u01D0\u0209\u020B\u1ECB\u012F\u1E2D\u0268\u0131' },
+  { base: 'j', letters: '\u006A\u24D9\uFF4A\u0135\u01F0\u0249' },
+  { base: 'k', letters: '\u006B\u24DA\uFF4B\u1E31\u01E9\u1E33\u0137\u1E35\u0199\u2C6A\uA741\uA743\uA745\uA7A3' },
+  { base: 'l', letters: '\u006C\u24DB\uFF4C\u0140\u013A\u013E\u1E37\u1E39\u013C\u1E3D\u1E3B\u017F\u0142\u019A\u026B\u2C61\uA749\uA781\uA747' },
+  { base: 'lj', letters: '\u01C9' },
+  { base: 'm', letters: '\u006D\u24DC\uFF4D\u1E3F\u1E41\u1E43\u0271\u026F' },
+  { base: 'n', letters: '\u006E\u24DD\uFF4E\u01F9\u0144\u00F1\u1E45\u0148\u1E47\u0146\u1E4B\u1E49\u019E\u0272\u0149\uA791\uA7A5' },
+  { base: 'nj', letters: '\u01CC' },
+  { base: 'o', letters: '\u006F\u24DE\uFF4F\u00F2\u00F3\u00F4\u1ED3\u1ED1\u1ED7\u1ED5\u00F5\u1E4D\u022D\u1E4F\u014D\u1E51\u1E53\u014F\u022F\u0231\u00F6\u022B\u1ECF\u0151\u01D2\u020D\u020F\u01A1\u1EDD\u1EDB\u1EE1\u1EDF\u1EE3\u1ECD\u1ED9\u01EB\u01ED\u00F8\u01FF\u0254\uA74B\uA74D\u0275' },
+  { base: 'oi', letters: '\u01A3' },
+  { base: 'ou', letters: '\u0223' },
+  { base: 'oo', letters: '\uA74F' },
+  { base: 'p', letters: '\u0070\u24DF\uFF50\u1E55\u1E57\u01A5\u1D7D\uA751\uA753\uA755' },
+  { base: 'q', letters: '\u0071\u24E0\uFF51\u024B\uA757\uA759' },
+  { base: 'r', letters: '\u0072\u24E1\uFF52\u0155\u1E59\u0159\u0211\u0213\u1E5B\u1E5D\u0157\u1E5F\u024D\u027D\uA75B\uA7A7\uA783' },
+  { base: 's', letters: '\u0073\u24E2\uFF53\u00DF\u015B\u1E65\u015D\u1E61\u0161\u1E67\u1E63\u1E69\u0219\u015F\u023F\uA7A9\uA785\u1E9B' },
+  { base: 't', letters: '\u0074\u24E3\uFF54\u1E6B\u1E97\u0165\u1E6D\u021B\u0163\u1E71\u1E6F\u0167\u01AD\u0288\u2C66\uA787' },
+  { base: 'tz', letters: '\uA729' },
+  { base: 'u', letters: '\u0075\u24E4\uFF55\u00F9\u00FA\u00FB\u0169\u1E79\u016B\u1E7B\u016D\u00FC\u01DC\u01D8\u01D6\u01DA\u1EE7\u016F\u0171\u01D4\u0215\u0217\u01B0\u1EEB\u1EE9\u1EEF\u1EED\u1EF1\u1EE5\u1E73\u0173\u1E77\u1E75\u0289' },
+  { base: 'v', letters: '\u0076\u24E5\uFF56\u1E7D\u1E7F\u028B\uA75F\u028C' },
+  { base: 'vy', letters: '\uA761' },
+  { base: 'w', letters: '\u0077\u24E6\uFF57\u1E81\u1E83\u0175\u1E87\u1E85\u1E98\u1E89\u2C73' },
+  { base: 'x', letters: '\u0078\u24E7\uFF58\u1E8B\u1E8D' },
+  { base: 'y', letters: '\u0079\u24E8\uFF59\u1EF3\u00FD\u0177\u1EF9\u0233\u1E8F\u00FF\u1EF7\u1E99\u1EF5\u01B4\u024F\u1EFF' },
+  { base: 'z', letters: '\u007A\u24E9\uFF5A\u017A\u1E91\u017C\u017E\u1E93\u1E95\u01B6\u0225\u0240\u2C6C\uA763' }
 ];
 
-var diacriticsMap = {};
-for (var i=0; i < defaultDiacriticsRemovalap.length; i++){
-    var letters = defaultDiacriticsRemovalap[i].letters;
-    for (var j=0; j < letters.length ; j++){
-        diacriticsMap[letters[j]] = defaultDiacriticsRemovalap[i].base;
-    }
+const diacriticsMap = {};
+
+for (let i = 0; i < defaultDiacriticsRemovalap.length; i++) {
+  const { letters } = defaultDiacriticsRemovalap[i];
+
+  for (let j = 0; j < letters.length; j++) {
+    diacriticsMap[letters[j]] = defaultDiacriticsRemovalap[i].base;
+  }
 }
 
-function remove (str) {
-    return str.replace(/[^\u0000-\u007E]/g, function(a){
-       return diacriticsMap[a] || a;
-    });
+function remove(str) {
+  return str.replace(/[^\u0000-\u007E]/g, (a) => diacriticsMap[a] || a);
 }
 
 module.exports.remove = remove;

package.json

 {
   "name": "natural-content",
-  "version": "1.0.9",
+  "version": "1.0.10",
   "description": "A set of natural functions like tf.idf, extract words & n-grams, remove diacritics, ... (experimental project)",
@@ -12,4 +12,10 @@ "main": "index.js",
   "dependencies": {
-    "underscore": "*"
+    "underscore": "^1.9.1"
+  },
+  "devDependencies": {
+    "eslint": "^5.16.0",
+    "eslint-config-adidas-es8": "^1.1.0",
+    "eslint-plugin-import": "^2.17.3",
+    "eslint-plugin-promise": "^4.1.1"
   }
 }

test/test.js

@@ -1,123 +0,119 @@
-var assert     = require("assert");
-var _          = require("underscore");
-var natural    = require("../index.js");
+const assert = require('assert');
+const _ = require('underscore');
+const natural = require('../index.js');
 
+describe('Natural Content', () => {
+  const documents = [
+    'word1 word2 word3 word4 word5 word6. word7 word1 word8 word9 word10 word11 word6. word1 word12 word13. word1 word1 ',
+    'word2 word7 word8 word9 word10 word7 word11 word7 word11 word11 word11 word11.',
+    ' word7 word2 '
+  ];
 
-describe("Natural Content", function() {
-        var documents = [
-            "word1 word2 word3 word4 word5 word6. word7 word1 word8 word9 word10 word11 word6. word1 word12 word13. word1 word1 ",
-            "word2 word7 word8 word9 word10 word7 word11 word7 word11 word11 word11 word11.",
-            " word7 word2 "  ];
+  const documentsFr = [
+    'Les conditions d\'utilisations de l\'objet doivent se faire dans de bonnes conditions. Sinon l\'objet ne peut pas bien être utilisé.',
+    'Les conditions d\'emploi de la chose doivent se faire dans de bonne condition. Sinon l\'objet n\'est pas utilisable.',
+    'Pour éviter une mauvaise utilisation, les conditions d\'utilisations doivent être faite correctement.'
+  ];
 
-        var documentsFr = [
-          "Les conditions d'utilisations de l'objet doivent se faire dans de bonnes conditions. Sinon l'objet ne peut pas bien être utilisé.",
-          "Les conditions d'emploi de la chose doivent se faire dans de bonne condition. Sinon l'objet n'est pas utilisable.",
-          "Pour éviter une mauvaise utilisation, les conditions d'utilisations doivent être faite correctement."
-        ];
-        it('Statements', function() {
-              var stats = natural.getStatements("word1 word2 word3 word4 :word5 word6. word7 word1, word8 word9 word10 word11 word6. word1 word12 word13");
-              assert(stats.length === 3);
+  it('Statements', () => {
+    const stats = natural.getStatements('word1 word2 word3 word4 :word5 word6. word7 word1, word8 word9 word10 word11 word6. word1 word12 word13');
 
-        });
+    assert(stats.length === 3);
+  });
 
-        it('Special caracters', function(){
-            var text = "ceci est un texte en français ! sans caractères spéciaux !§($€) # 123 avant-hier";
-            var result = natural.removeSpecials(text);
-            
-            assert( result === 'ceci est un texte en français sans caractères spéciaux avant hier');
-        });
+  it('Special caracters', () => {
+    const text = 'ceci est un texte en français ! sans caractères spéciaux !§($€) # 123 avant-hier';
+    const result = natural.removeSpecials(text);
 
+    assert(result === 'ceci est un texte en français sans caractères spéciaux avant hier');
+  });
 
-        it('apostrophe', function(){
-            var text = "ceci est un texte en français. l'été sera chaud. Les conditions d'utilisation de l'objet";
+  it('apostrophe', () => {
+    const text = 'ceci est un texte en français. l\'été sera chaud. Les conditions d\'utilisation de l\'objet';
 
-            var result = natural.removeSpecials(text);
-            assert( result === 'ceci est un texte en français l été sera chaud Les conditions d utilisation de l objet');
-        });
+    const result = natural.removeSpecials(text);
 
-        it('diacritics', function(){
-            var text = "ceci est un texte en français ! sans diacritiques çàoözęùô";
-            var result = natural.removeDiacritics(text);
-            assert(result === 'ceci est un texte en francais ! sans diacritiques caoozeuo');
-        });
+    assert(result === 'ceci est un texte en français l été sera chaud Les conditions d utilisation de l objet');
+  });
 
-        it('Words', function() {
+  it('diacritics', () => {
+    const text = 'ceci est un texte en français ! sans diacritiques çàoözęùô';
+    const result = natural.removeDiacritics(text);
 
-          var words = natural.getWords("word1 word2 word3 word4. le la sur word5, ça été bientôt & @' $ 123", true);
-          assert(words.length === 15);
+    assert(result === 'ceci est un texte en francais ! sans diacritiques caoozeuo');
+  });
 
-          words = natural.getWords(natural.removeSpecials("word1 word2 word3 word4. le la sur word5, ça été bientôt & @' $ 123"), true);
-          //console.log("words", words);
-          assert(words.length === 11);
+  it('Words', () => {
+    let words = natural.getWords('word1 word2 word3 word4. le la sur word5, ça été bientôt & @\' $ 123', true);
 
-          words = natural.getWords("word1 word2 word3 word4. le la sur word5 bientôt", false, "fr");
-          //console.log("words", words);
-          assert(words.length === 5);
+    assert(words.length === 15);
 
-          words = natural.getWords("word1 word2 word3 1234 word4 156,78. le la sur word5", false, "fr");
-          //console.log(words);
-          assert(words.length === 8);
+    words = natural.getWords(natural.removeSpecials('word1 word2 word3 word4. le la sur word5, ça été bientôt & @\' $ 123'), true);
 
-          words = natural.getWords("l'été sera chaud. Les conditions d'utilisation de l'objet", false, "fr");
-          assert(words.length === 4);
+    // console.log("words", words);
+    assert(words.length === 11);
 
-          words = natural.getWords("l'été sera chaud. Les conditions d'utilisation de l'objet", true);
-          assert(words.length === 11);
-        });
+    words = natural.getWords('word1 word2 word3 word4. le la sur word5 bientôt', false, 'fr');
 
-        it('n-grams', function() {
-          var grams = natural.getNgrams(natural.getWords("word1 word2 word3 word4. le la sur word5", true), 1);
-          assert(grams.length === 8);
-          assert(grams[3] === "word4");
+    // console.log("words", words);
+    assert(words.length === 5);
 
-          grams = natural.getNgrams(natural.getWords("word1 word2 word3 word4. le la sur word5", true), 2);
-          assert(grams.length === 7);
-          assert(grams[1] === "word2 word3");
+    words = natural.getWords('word1 word2 word3 1234 word4 156,78. le la sur word5', false, 'fr');
 
-          grams = natural.getNgrams(natural.getWords("word1 word2 word3 word4. le la sur word5", true), 3);
-          assert(grams.length === 6);
-          assert(grams[2] === "word3 word4 le");
+    // console.log(words);
+    assert(words.length === 8);
 
-          grams = natural.getNgrams(natural.getWords("l'été sera chaud. Les conditions d'utilisation de l'objet", false, "fr"), 1);
-          assert(grams.length === 4);
+    words = natural.getWords('l\'été sera chaud. Les conditions d\'utilisation de l\'objet', false, 'fr');
+    assert(words.length === 4);
 
+    words = natural.getWords('l\'été sera chaud. Les conditions d\'utilisation de l\'objet', true);
+    assert(words.length === 11);
+  });
 
-        });
+  it('n-grams', () => {
+    let grams = natural.getNgrams(natural.getWords('word1 word2 word3 word4. le la sur word5', true), 1);
 
-        it("term frequency", function(){
-            var info = natural.getTf(natural.getWords(documents[0], false, "fr"));
-            //console.log(info);
-            assert(info.max === 5);
-            assert(info.count.word1 === 5);
-            assert(info.count.word6 === 2);
-            assert(info.tfs.word1 === 1);
-            assert(info.tfs.word2 === 0.2);
-            assert(info.tfs.word6 === 0.4);
+    assert(grams.length === 8);
+    assert(grams[3] === 'word4');
 
-        });
+    grams = natural.getNgrams(natural.getWords('word1 word2 word3 word4. le la sur word5', true), 2);
+    assert(grams.length === 7);
+    assert(grams[1] === 'word2 word3');
 
+    grams = natural.getNgrams(natural.getWords('word1 word2 word3 word4. le la sur word5', true), 3);
+    assert(grams.length === 6);
+    assert(grams[2] === 'word3 word4 le');
 
-        it("tf.idf for a set of document ", function() {
+    grams = natural.getNgrams(natural.getWords('l\'été sera chaud. Les conditions d\'utilisation de l\'objet', false, 'fr'), 1);
+    assert(grams.length === 4);
+  });
 
-            var info = natural.getTfIdfs(documents, 1, false, "fr");
+  it('term frequency', () => {
+    const info = natural.getTf(natural.getWords(documents[0], false, 'fr'));
 
-            var sorted = _.sortBy(Array.from(info.stats.values()), function(word) { return -word.tfIdfSum;});
-            assert(sorted[0].word === "word1");
-            //console.log(sorted);
+    // console.log(info);
+    assert(info.max === 5);
+    assert(info.count.word1 === 5);
+    assert(info.count.word6 === 2);
+    assert(info.tfs.word1 === 1);
+    assert(info.tfs.word2 === 0.2);
+    assert(info.tfs.word6 === 0.4);
+  });
 
-        });
+  it('tf.idf for a set of document ', () => {
+    const info = natural.getTfIdfs(documents, 1, false, 'fr');
 
-        /*
-        it.only("tf.idf for a set of document in french", function() {
+    const sorted = _.sortBy(Array.from(info.stats.values()), (word) => -word.tfIdfSum);
 
-            var info = natural.getTfIdfs(documentsFr, 3, true);
+    assert(sorted[0].word === 'word1');
 
-            var sorted = _.sortBy(Array.from(info.stats.values()), function(word) { return -word.tfIdfSum;});
-            //assert(sorted[0].word === "word1");
-            console.log(sorted);
+    // console.log(sorted);
+  });
 
-        });
-        */
-
-
+  // it.only("tf.idf for a set of document in french", function() {
+  // var info = natural.getTfIdfs(documentsFr, 3, true);
+  // var sorted = _.sortBy(Array.from(info.stats.values()), function(word) { return -word.tfIdfSum;});
+  // //assert(sorted[0].word === "word1");
+  // console.log(sorted);
+  // });
 });

New alerts

Dynamic require

Supply chain risk

Dynamic require can indicate the package is performing dangerous or unsafe dynamic code execution.

Found 1 instance in 1 package

Fixed alerts

Wildcard dependency

Quality

Package has a dependency with a floating version range. This can cause issues if the dependency publishes a new major version.

Found 1 instance in 1 package

Dynamic require

Supply chain risk

Dynamic require can indicate the package is performing dangerous or unsafe dynamic code execution.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

32803

increased by1.47%

Lines of code

1313

increased by1.31%

Number of medium quality alerts

1

decreased by-50%

Worsened metrics

Dev dependency count

4

increased byInfinity%

Dependency changes

• Updatedunderscore@^1.9.1