Fix html strip

html_tags.json

@@ -0,0 +1,119 @@
+[
+	"a",
+	"abbr",
+	"address",
+	"area",
+	"article",
+	"aside",
+	"audio",
+	"b",
+	"base",
+	"bdi",
+	"bdo",
+	"blockquote",
+	"body",
+	"br",
+	"button",
+	"canvas",
+	"caption",
+	"cite",
+	"code",
+	"col",
+	"colgroup",
+	"data",
+	"datalist",
+	"dd",
+	"del",
+	"details",
+	"dfn",
+	"dialog",
+	"div",
+	"dl",
+	"dt",
+	"em",
+	"embed",
+	"fieldset",
+	"figcaption",
+	"figure",
+	"footer",
+	"form",
+	"h1",
+	"h2",
+	"h3",
+	"h4",
+	"h5",
+	"h6",
+	"head",
+	"header",
+	"hgroup",
+	"hr",
+	"html",
+	"i",
+	"iframe",
+	"img",
+	"input",
+	"ins",
+	"kbd",
+	"label",
+	"legend",
+	"li",
+	"link",
+	"main",
+	"map",
+	"mark",
+	"math",
+	"menu",
+	"menuitem",
+	"meta",
+	"meter",
+	"nav",
+	"noscript",
+	"object",
+	"ol",
+	"optgroup",
+	"option",
+	"output",
+	"p",
+	"param",
+	"picture",
+	"pre",
+	"progress",
+	"q",
+	"rb",
+	"rp",
+	"rt",
+	"rtc",
+	"ruby",
+	"s",
+	"samp",
+	"script",
+	"section",
+	"select",
+	"slot",
+	"small",
+	"source",
+	"span",
+	"strong",
+	"style",
+	"sub",
+	"summary",
+	"sup",
+	"svg",
+	"table",
+	"tbody",
+	"td",
+	"template",
+	"textarea",
+	"tfoot",
+	"th",
+	"thead",
+	"time",
+	"title",
+	"tr",
+	"track",
+	"u",
+	"ul",
+	"var",
+	"video",
+	"wbr"
+]

index.js

@@ -35,9 +35,6 @@ module.exports = function(md, options) {
       // Remove abbreviations
       output = output.replace(/\*\[.*\]:.*\n/, '');
     }
-    output = output
-    // Remove HTML tags
-      .replace(/<[^>]*>/g, '')
 
     var htmlReplaceRegex = new RegExp('<[^>]*>', 'g');
     if (options.htmlTagsToSkip.length > 0) {
@@ -53,9 +50,16 @@ module.exports = function(md, options) {
       );
     }
 
+    const htmlPossibleTags = output.match(htmlReplaceRegex);
+    if (htmlPossibleTags) {
+      htmlPossibleTags.forEach(function(string) {
+        if (isHtmlTag(string)) {
+          output = removeHtmltagIfNotInsideCodeblock(md, output, string);
+        }
+      });
+    }
+
     output = output
-      // Remove HTML tags
-      .replace(htmlReplaceRegex, '')
       // Remove setext-style headers
       .replace(/^[=\-]{2,}\s*$/g, '')
       // Remove footnotes?
@@ -94,3 +98,24 @@ module.exports = function(md, options) {
   }
   return output;
 };
+
+function isHtmlTag(string) {
+  const splittedString = string.replace('/', '').split(' ');
+  const htmlTags = require('./html_tags.json');
+
+  string = string.replace('<', '').replace('>', '').replace('/', '');
+
+  return !(Boolean( string.match(/\d/) ) && (!isNaN(splittedString[1]) || !isNaN(splittedString.reverse()[1]))) && htmlTags.includes(string[0]);
+}
+
+function removeHtmltagIfNotInsideCodeblock(md, output, tag, codeMark = '`') {
+  const re = new RegExp(tag,'gi');
+
+  while (exec = re.exec(output)){
+    if (md[exec.index - 1] !== codeMark || md[re.lastIndex] !== codeMark) {
+      output = output.substring(0, exec.index) + output.substring(re.lastIndex);
+    }
+  }
+
+  return output;
+}

test/remove-markdown.js

@@ -33,6 +33,18 @@ describe('remove Markdown', function () {
       expect(removeMd(string)).to.equal(expected);
     });
 
+    it('should not strip arithmetic signs', function() {
+      const string = '`<p class="class1 class2" id="id1">The equations 2 < 3 and 3 > 1 are both true</p>`';
+      const expected = 'The equations 2 < 3 and 3 > 1 are both true';
+      expect(removeMd(string)).to.equal(expected);
+    });
+
+    it('should not strip html inside code element', function() {
+      const string = 'HTML tags look like this: `<div>`.';
+      const expected = 'HTML tags look like this: <div>.';
+      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.';
@@ -183,5 +195,11 @@ describe('remove Markdown', function () {
       const duration = Date.now()-start;
       expect(duration).to.be.lt(1000);
     });
+
+    it('should not strip not HTML corner braces', function () {
+      const string = 'You can write to John Doe <john.doe AT example DOT com>';
+      const expected = 'You can write to John Doe <john.doe AT example DOT com>';
+      expect(removeMd(string)).to.equal(expected);
+    });
   });
 });