remove-markdown - npm Package Compare versions

Comparing version 0.1.0 to 0.2.0

index.js

@@ -7,5 +7,9 @@ module.exports = function(md, options) {
   var output = md;
+
+  // Remove horizontal rules (stripListHeaders conflict with this rule, which is why it has been moved to the top)
+  output = output.replace(/^(-\s*?|\*\s*?|_\s*?){3,}\s*$/gm, '');
+
   try {
     if (options.stripListLeaders) {
-      output = output.replace(/^([\s\t]*)([\*\-\+]|\d\.)\s+/gm, '$1');
+      output = output.replace(/^([\s\t]*)([\*\-\+]|\d+\.)\s+/gm, '$1');
     }
@@ -23,3 +27,3 @@ if (options.gfm){
       // Remove HTML tags
-      .replace(/<(.*?)>/g, '$1')
+      .replace(/<[^>]*>/g, '')
       // Remove setext-style headers
@@ -39,7 +43,11 @@ .replace(/^[=\-]{2,}\s*$/g, '')
       // Remove atx-style headers
-      .replace(/^\#{1,6}\s*([^#]*)\s*(\#{1,6})?/gm, '$1')
-      .replace(/([\*_]{1,3})(\S.*?\S)\1/g, '$2')
+      .replace(/^(\n)?\s{0,}#{1,6}\s+| {0,}(\n)?\s{0,}#{0,} {0,}(\n)?\s{0,}$/gm, '$1$2$3')
+      // Remove emphasis (repeat the line to remove double emphasis)
+      .replace(/([\*_]{1,3})(\S.*?\S{0,1})\1/g, '$2')
+      .replace(/([\*_]{1,3})(\S.*?\S{0,1})\1/g, '$2')
+      // Remove code blocks
       .replace(/(`{3,})(.*?)\1/gm, '$2')
-      .replace(/^-{3,}\s*$/g, '')
+      // Remove inline code
       .replace(/`(.+?)`/g, '$1')
+      // Replace two or more newlines with exactly two? Not entirely sure this belongs here...
       .replace(/\n{2,}/g, '\n\n');
@@ -46,0 +54,0 @@ } catch(e) {

package.json

 {
   "name": "remove-markdown",
-  "version": "0.1.0",
+  "version": "0.2.0",
   "description": "Remove Markdown formatting from text",
@@ -23,2 +23,3 @@ "main": "index.js",
   "devDependencies": {
+    "chai": "^4.0.2",
     "mocha": "^2.1.0",
@@ -25,0 +26,0 @@ "should": "^5.0.0"

README.md

@@ -15,8 +15,8 @@ ## What is it?
 ```js
-var removeMd = require('remove-markdown');
-var markdown = '# This is a heading\n\nThis is a paragraph with [a link](http://www.disney.com/) in it.';
-var plainText = removeMd(markdown); // plainText is now 'This is a heading\n\nThis is a paragraph with a link in it.'
+const removeMd = require('remove-markdown');
+const markdown = '# This is a heading\n\nThis is a paragraph with [a link](http://www.disney.com/) in it.';
+const plainText = removeMd(markdown); // plainText is now 'This is a heading\n\nThis is a paragraph with a link in it.'
 ```
 
-You can also supply an options object to the function. Currently, the only two options are for stripping list headers and supporting Github Flavored Markdown:
+You can also supply an options object to the function. Currently, the only two options are for stripping list leaders and supporting Github Flavored Markdown:
 
@@ -30,4 +30,10 @@ ```js
 
-Stripping list headers will retain any list characters (`*, -, +, (digit).`).
+Setting `stripListLeaders` to false will retain any list characters (`*, -, +, (digit).`).
 
+## TODO
+PRs are very much welcome.
+* Allow the RegEx expressions to be customized per rule
+* Make the rules more robust, support more edge cases
+* Add more (comprehensive) tests
+
 ## Credits
@@ -34,0 +40,0 @@ The code is based on [Markdown Service Tools - Strip Markdown](http://brettterpstra.com/2013/10/18/a-markdown-service-to-strip-markdown/) by Brett Terpstra.

test/remove-markdown.js

 'use strict';
+const expect = require('chai').expect;
+const removeMd = require('../');
 
-var fs = require('fs'),
-    path = require('path'),
-    should = require('should'),
-    removeMd = require('../'),
-    markdown = fs.readFileSync(path.resolve(__dirname, 'markdown.md')).toString(),
-    result = fs.readFileSync(path.resolve(__dirname, 'result.txt')).toString();
+describe('remove Markdown', function () {
+  describe('removeMd', function () {
+    it('should leave a string alone without markdown', function () {
+      const string = 'Javascript Developers are the best.';
+      expect(removeMd(string)).to.equal(string);
+    });
 
-describe('remove-markdown', function () {
-  it('should remove markdown', function () {
-    removeMd(markdown).should.eql(result);
+    it('should strip out remaining markdown', function () {
+      const string = '*Javascript* developers are the _best_.';
+      const expected = 'Javascript developers are the best.';
+      expect(removeMd(string)).to.equal(expected);
+    });
+
+    it('should leave non-matching markdown markdown', function () {
+      const string = '*Javascript* developers* are the _best_.';
+      const expected = 'Javascript developers* are the best.';
+      expect(removeMd(string)).to.equal(expected);
+    });
+
+    it('should leave non-matching markdown, but strip empty anchors', function () {
+      const string = '*Javascript* [developers]()* are the _best_.';
+      const expected = 'Javascript developers* are the best.';
+      expect(removeMd(string)).to.equal(expected);
+    });
+
+    it('should strip HTML', function () {
+      const string = '<p>Hello World</p>';
+      const expected = 'Hello World';
+      expect(removeMd(string)).to.equal(expected);
+    });
+
+    it('should strip anchors', function () {
+      const string = '*Javascript* [developers](https://engineering.condenast.io/)* are the _best_.';
+      const expected = 'Javascript developers* are the best.';
+      expect(removeMd(string)).to.equal(expected);
+    });
+
+    it('should strip img tags', function () {
+      const string = '![bear](https://placebear.com/640/480)*Javascript* developers are the _best_.';
+      const expected = 'Javascript developers are the best.';
+      expect(removeMd(string)).to.equal(expected);
+    });
+
+    it('should strip code tags', function () {
+      const string = 'In `Getting Started` we set up `something` foo.';
+      const expected = 'In Getting Started we set up something foo.';
+      expect(removeMd(string)).to.equal(expected);
+    });
+
+    it('should leave hashtags in headings', function () {
+      const string = '## This #heading contains #hashtags';
+      const expected = 'This #heading contains #hashtags';
+      expect(removeMd(string)).to.equal(expected);
+    });
+
+    it('should remove emphasis', function () {
+      const string = 'I italicized an *I* and it _made_ me *sad*.';
+      const expected = 'I italicized an I and it made me sad.';
+      expect(removeMd(string)).to.equal(expected);
+    });
+
+    it('should remove double emphasis', function () {
+      const string = '**this sentence has __double styling__**';
+      const expected = 'this sentence has double styling';
+      expect(removeMd(string)).to.equal(expected);
+    });    
+
+    it('should remove horizontal rules', function () {
+      const string = 'Some text on a line\n\n---\n\nA line below';
+      const expected = 'Some text on a line\n\nA line below';
+      expect(removeMd(string)).to.equal(expected);
+    });
+
+    it('should remove horizontal rules with space-separated asterisks', function () {
+      const string = 'Some text on a line\n\n* * *\n\nA line below';
+      const expected = 'Some text on a line\n\nA line below';
+      expect(removeMd(string)).to.equal(expected);
+    });
+
+    it('should strip unordered list leaders', function () {
+      const string = 'Some text on a line\n\n* A list Item\n* Another list item';
+      const expected = 'Some text on a line\n\nA list Item\nAnother list item';
+      expect(removeMd(string)).to.equal(expected);
+    });
+
+    it('should strip ordered list leaders', function () {
+      const string = 'Some text on a line\n\n9. A list Item\n10. Another list item';
+      const expected = 'Some text on a line\n\nA list Item\nAnother list item';
+      expect(removeMd(string)).to.equal(expected);
+    });
+
+    it('should handle paragraphs with markdown', function () {
+      const paragraph = '\n## This is a heading ##\n\nThis is a paragraph with [a link](http://www.disney.com/).\n\n### This is another heading\n\nIn `Getting Started` we set up `something` foo.\n\n  * Some list\n  * With items\n    * Even indented';
+      const expected = '\nThis is a heading\n\nThis is a paragraph with a link.\n\nThis is another heading\n\nIn Getting Started we set up something foo.\n\n  Some list\n  With items\n    Even indented';
+      expect(removeMd(paragraph)).to.equal(expected);
+    });
   });
-});
+});

test/markdown.md

-## This is a heading ##
-
-This is a paragraph with [a link](http://www.disney.com/).
-
-### This is another heading
-
-In `Getting Started` we set up `something` foo.
-
-* Some list
-* With items
-  * Even indented

test/result.txt

-This is a heading 
-
-This is a paragraph with a link.
-
-This is another heading
-
-In Getting Started we set up something foo.
-
-Some list
-With items
-  Even indented

New alerts

URL strings

Supply chain risk

Package contains fragments of external URLs or IP addresses, which the package may be accessing at runtime.

Found 1 instance in 1 package

Fixed alerts

Filesystem access

Supply chain risk

Accesses the file system, and could potentially read sensitive data.

Found 1 instance in 1 package

URL strings

Supply chain risk

Package contains fragments of external URLs or IP addresses, which the package may be accessing at runtime.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

9753

81.42%

Lines of code

139

139.66%

Number of lines in readme file

42

16.67%

Number of low supply chain risk alerts

1

-50%

Worsened metrics

Dev dependency count

3

50%

Number of package files

6

-25%

No dependency changes