natural-content - npm Package Compare versions

Comparing version 1.2.2 to 1.2.3

index.js

@@ -18,2 +18,11 @@ const { PorterStemmerFr, TfIdf, AggressiveTokenizerFr } = require('natural');
 /**
+ * Check if a statement contains an acronym which is a substring in uppercase
+ * @param  {string} statement the statement
+ * @returns {boolean} true if the statement contains an acronym
+ */
+function containsAcronym(statement) {
+  return /^(.*)([A-Z]{2,})/.test(statement);
+}
+
+/**
   * getStatements - Get all statements from a text
@@ -26,21 +35,21 @@ *
   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(/  +/g, WORD_SEPARATOR) // remove multiple spaces
-                      .replace('...', STATEMENT_SEPARATOR)
-                      .replace(/[.]{3}/g, `.${ STATEMENT_SEPARATOR }`)
-                      .replace(/[.]/g, `.${ STATEMENT_SEPARATOR }`)
-                      .replace(/[!]/g, `!${ STATEMENT_SEPARATOR }`)
-                      .replace(/[?]/g, `?${ STATEMENT_SEPARATOR }`)
-                      .split(STATEMENT_SEPARATOR)
-                      .reduce((result, t) => {
-                        if (t.trim() === '') {
-                          return result;
-                        }
+    .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 multiple spaces
+    .replace('...', STATEMENT_SEPARATOR)
+    .replace(/[.]{3}/g, `.${STATEMENT_SEPARATOR}`)
+    .replace(/[.]/g, `.${STATEMENT_SEPARATOR}`)
+    .replace(/[!]/g, `!${STATEMENT_SEPARATOR}`)
+    .replace(/[?]/g, `?${STATEMENT_SEPARATOR}`)
+    .split(STATEMENT_SEPARATOR)
+    .reduce((result, t) => {
+      if (t.trim() === '') {
+        return result;
+      }
 
-                        result.push(t.trim());
+      result.push(t.trim());
 
-                        return result;
-                      }, []);
+      return result;
+    }, []);
 }
@@ -60,6 +69,6 @@
   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(/[|&’«»'"\/(\/)\/!\/?\\-]/g, WORD_SEPARATOR);
+    .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(/[|&’«»'"\/(\/)\/!\/?\\-]/g, WORD_SEPARATOR);
 
@@ -95,6 +104,6 @@ const lower = cleanText.toLowerCase();
   return text.replace(/[\t]/g, WORD_SEPARATOR) // Remove Tabs
-             .replace(/[\n\r]/g, WORD_SEPARATOR)
-             .replace(/[\n]/g, WORD_SEPARATOR)
-             .replace(/\s+/g, WORD_SEPARATOR)
-             .trim();
+    .replace(/[\n\r]/g, WORD_SEPARATOR)
+    .replace(/[\n]/g, WORD_SEPARATOR)
+    .replace(/\s+/g, WORD_SEPARATOR)
+    .trim();
 }
@@ -132,9 +141,9 @@
   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(/\s+/g, WORD_SEPARATOR) // remove multiple spaces
-                      .toLowerCase()
-                      .split(WORD_SEPARATOR);
+    .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(/\s+/g, WORD_SEPARATOR) // remove multiple spaces
+    .toLowerCase()
+    .split(WORD_SEPARATOR);
 
@@ -148,3 +157,3 @@ // Remove empty string
 
-  const { stopwords } = require(`./lib/stopwords-${ language.toLowerCase() }`);
+  const { stopwords } = require(`./lib/stopwords-${language.toLowerCase()}`);
 
@@ -178,3 +187,3 @@ return words.filter((word) => word !== '' && stopwords.indexOf(removeDiacritics(word)) === -1);
     // Convert the ngram array into a ngram string and add it in the result list
-    result.push(slice.reduce((memo, word) => memo ? `${ memo } ${ word }` : word));
+    result.push(slice.reduce((memo, word) => memo ? `${memo} ${word}` : word));
   }
@@ -222,2 +231,4 @@
 
+exports.containsAcronym = containsAcronym;
+
 exports.getStatements = getStatements;
@@ -224,0 +235,0 @@

package.json

 {
   "name": "natural-content",
-  "version": "1.2.2",
+  "version": "1.2.3",
   "description": "A set of natural functions like extracting words & n-grams, remove diacritics, get top keywords, ... (experimental project)",
@@ -5,0 +5,0 @@ "main": "index.js",

test/test.js

@@ -23,3 +23,4 @@ const assert = require('assert');
 
-    // console.log(natural.getStatements(txt));
+    assert(natural.containsAcronym('this is mister LOL'));
+    assert(!natural.containsAcronym('this is mister John Smith'));
   });
@@ -26,0 +27,0 @@

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

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

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

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

Lines of code

4868

increased by0.21%

Worsened metrics

Total package byte prevSize

73080

decreased by-0.21%

No dependency changes