Refactor micromark token handling to remove optional Token.htmlFlowChildren property and make related code more efficient for a ~6% elapsed time reduction.

demo/markdownlint-browser.js

@@ -1150,9 +1150,24 @@ var flatTokensSymbol = Symbol("flat-tokens");
  * @property {number} endColumn End column (1-based).
  * @property {string} text Token text.
  * @property {Token[]} children Child tokens.
- * @property {Token[]} [htmlFlowChildren] Child tokens for htmlFlow.
  */
 
+/**
+ * Returns whether a token is an htmlFlow type containing an HTML comment.
+ *
+ * @param {Token} token Micromark token.
+ * @returns {boolean} True iff token is htmlFlow containing a comment.
+ */
+function isHtmlFlowComment(token) {
+  var text = token.text,
+    type = token.type;
+  if (type === "htmlFlow" && text.startsWith("<!--") && text.endsWith("-->")) {
+    var comment = text.slice(4, -3);
+    return !comment.startsWith(">") && !comment.startsWith("->") && !comment.endsWith("-") && !comment.includes("--");
+  }
+  return false;
+}
+
 /**
  * Parses a Markdown document and returns Micromark events.
  *
@@ -1205,6 +1220,7 @@ function micromarkParseWithOffset(markdown, micromarkOptions, referencesDefined,
   var history = [current];
   var reparseOptions = null;
   var lines = null;
+  var skipHtmlFlowChildren = false;
   var _iterator = _createForOfIteratorHelper(events),
     _step;
   try {
@@ -1222,7 +1238,7 @@ function micromarkParseWithOffset(markdown, micromarkOptions, referencesDefined,
       var endColumn = end["column"],
         endLine = end["line"];
       var text = context.sliceSerialize(token);
-      if (kind === "enter") {
+      if (kind === "enter" && !skipHtmlFlowChildren) {
         var previous = current;
         history.push(previous);
         current = {
@@ -1234,7 +1250,11 @@ function micromarkParseWithOffset(markdown, micromarkOptions, referencesDefined,
           text: text,
           "children": []
         };
-        if (current.type === "htmlFlow") {
+        previous.children.push(current);
+        flatTokens.push(current);
+        // @ts-ignore
+        if (current.type === "htmlFlow" && !isHtmlFlowComment(current)) {
+          skipHtmlFlowChildren = true;
           if (!reparseOptions || !lines) {
             reparseOptions = _objectSpread(_objectSpread({}, micromarkOptions), {}, {
               "extensions": [{
@@ -1246,17 +1266,22 @@ function micromarkParseWithOffset(markdown, micromarkOptions, referencesDefined,
             lines = markdown.split(newLineRe);
           }
           var reparseMarkdown = lines.slice(current.startLine - 1, current.endLine).join("\n");
-          current.htmlFlowChildren = micromarkParseWithOffset(reparseMarkdown, reparseOptions, referencesDefined, current.startLine - 1);
+          var tokens = micromarkParseWithOffset(reparseMarkdown, reparseOptions, referencesDefined, current.startLine - 1);
+          current.children = tokens;
+          flatTokens.push.apply(flatTokens, _toConsumableArray(tokens[flatTokensSymbol]));
         }
-        previous.children.push(current);
-        flatTokens.push(current);
       } else if (kind === "exit") {
+        if (type === "htmlFlow") {
+          skipHtmlFlowChildren = false;
+        }
+        if (!skipHtmlFlowChildren) {
           Object.freeze(current.children);
           Object.freeze(current);
           // @ts-ignore
           current = history.pop();
         }
       }
+    }
 
     // Return document
   } catch (err) {
@@ -1327,20 +1352,6 @@ function filterByTypes(tokens, allowed) {
   return filterByPredicate(tokens, predicate);
 }
 
-/**
- * Filter a list of Micromark tokens for HTML tokens.
- *
- * @param {Token[]} tokens Micromark tokens.
- * @returns {Token[]} Filtered tokens.
- */
-function filterByHtmlTokens(tokens) {
-  return filterByPredicate(tokens, function (token) {
-    return token.type === "htmlText";
-  }, function (token) {
-    return token.htmlFlowChildren || token.children;
-  });
-}
-
 /**
  * Gets the heading level of a Micromark heading tokan.
  *
@@ -1432,7 +1443,6 @@ function tokenIfType(token, type) {
 }
 module.exports = {
   "parse": micromarkParse,
-  filterByHtmlTokens: filterByHtmlTokens,
   filterByPredicate: filterByPredicate,
   filterByTypes: filterByTypes,
   getHeadingLevel: getHeadingLevel,
@@ -4836,7 +4846,7 @@ module.exports = {
 
     // For every top-level list...
     var topLevelLists = filterByPredicate(parsers.micromark.tokens, isList, function (token) {
-      return isList(token) ? [] : token.children;
+      return isList(token) || token.type === "htmlFlow" ? [] : token.children;
     });
     var _iterator = _createForOfIteratorHelper(topLevelLists),
       _step;
@@ -4903,7 +4913,7 @@ function _arrayLikeToArray(arr, len) { if (len == null || len > arr.length) len
 var _require = __webpack_require__(/*! ../helpers */ "../helpers/helpers.js"),
   addError = _require.addError;
 var _require2 = __webpack_require__(/*! ../helpers/micromark.cjs */ "../helpers/micromark.cjs"),
-  filterByHtmlTokens = _require2.filterByHtmlTokens,
+  filterByTypes = _require2.filterByTypes,
   getHtmlTagInfo = _require2.getHtmlTagInfo;
 var nextLinesRe = /[\r\n][\s\S]*$/;
 module.exports = {
@@ -4916,7 +4926,8 @@ module.exports = {
     allowedElements = allowedElements.map(function (element) {
       return element.toLowerCase();
     });
-    var _iterator = _createForOfIteratorHelper(filterByHtmlTokens(params.parsers.micromark.tokens)),
+    var tokens = params.parsers.micromark.tokens;
+    var _iterator = _createForOfIteratorHelper(filterByTypes(tokens, ["htmlText"])),
       _step;
     try {
       for (_iterator.s(); !(_step = _iterator.n()).done;) {
@@ -5159,14 +5170,12 @@ function _nonIterableRest() { throw new TypeError("Invalid attempt to destructur
 function _iterableToArrayLimit(r, l) { var t = null == r ? null : "undefined" != typeof Symbol && r[Symbol.iterator] || r["@@iterator"]; if (null != t) { var e, n, i, u, a = [], f = !0, o = !1; try { if (i = (t = t.call(r)).next, 0 === l) { if (Object(t) !== t) return; f = !1; } else for (; !(f = (e = i.call(t)).done) && (a.push(e.value), a.length !== l); f = !0); } catch (r) { o = !0, n = r; } finally { try { if (!f && null != t["return"] && (u = t["return"](), Object(u) !== u)) return; } finally { if (o) throw n; } } return a; } }
 function _arrayWithHoles(arr) { if (Array.isArray(arr)) return arr; }
 function _createForOfIteratorHelper(o, allowArrayLike) { var it = typeof Symbol !== "undefined" && o[Symbol.iterator] || o["@@iterator"]; if (!it) { if (Array.isArray(o) || (it = _unsupportedIterableToArray(o)) || allowArrayLike && o && typeof o.length === "number") { if (it) o = it; var i = 0; var F = function F() {}; return { s: F, n: function n() { if (i >= o.length) return { done: true }; return { done: false, value: o[i++] }; }, e: function e(_e) { throw _e; }, f: F }; } throw new TypeError("Invalid attempt to iterate non-iterable instance.\nIn order to be iterable, non-array objects must have a [Symbol.iterator]() method."); } var normalCompletion = true, didErr = false, err; return { s: function s() { it = it.call(o); }, n: function n() { var step = it.next(); normalCompletion = step.done; return step; }, e: function e(_e2) { didErr = true; err = _e2; }, f: function f() { try { if (!normalCompletion && it["return"] != null) it["return"](); } finally { if (didErr) throw err; } } }; }
-function _toConsumableArray(arr) { return _arrayWithoutHoles(arr) || _iterableToArray(arr) || _unsupportedIterableToArray(arr) || _nonIterableSpread(); }
-function _nonIterableSpread() { throw new TypeError("Invalid attempt to spread non-iterable instance.\nIn order to be iterable, non-array objects must have a [Symbol.iterator]() method."); }
 function _unsupportedIterableToArray(o, minLen) { if (!o) return; if (typeof o === "string") return _arrayLikeToArray(o, minLen); var n = Object.prototype.toString.call(o).slice(8, -1); if (n === "Object" && o.constructor) n = o.constructor.name; if (n === "Map" || n === "Set") return Array.from(o); if (n === "Arguments" || /^(?:Ui|I)nt(?:8|16|32)(?:Clamped)?Array$/.test(n)) return _arrayLikeToArray(o, minLen); }
-function _iterableToArray(iter) { if (typeof Symbol !== "undefined" && iter[Symbol.iterator] != null || iter["@@iterator"] != null) return Array.from(iter); }
-function _arrayWithoutHoles(arr) { if (Array.isArray(arr)) return _arrayLikeToArray(arr); }
 function _arrayLikeToArray(arr, len) { if (len == null || len > arr.length) len = arr.length; for (var i = 0, arr2 = new Array(len); i < len; i++) arr2[i] = arr[i]; return arr2; }
 var _require = __webpack_require__(/*! ../helpers */ "../helpers/helpers.js"),
   addError = _require.addError;
+var _require2 = __webpack_require__(/*! ../helpers/micromark.cjs */ "../helpers/micromark.cjs"),
+  filterByPredicate = _require2.filterByPredicate;
 module.exports = {
   "names": ["MD037", "no-space-in-emphasis"],
   "description": "Spaces inside emphasis markers",
@@ -5180,34 +5189,34 @@ module.exports = {
       var marker = _arr[_i];
       emphasisTokensByMarker.set(marker, []);
     }
-    var pending = _toConsumableArray(parsers.micromark.tokens);
+    var tokens = filterByPredicate(parsers.micromark.tokens, function (token) {
-    var token = null;
+      return token.children.some(function (child) {
-    while (token = pending.shift()) {
+        return child.type === "data";
-      // Use reparsed children of htmlFlow tokens
+      });
-      if (token.type === "htmlFlow") {
+    });
-        pending.unshift.apply(pending, _toConsumableArray(token.htmlFlowChildren));
+    var _iterator = _createForOfIteratorHelper(tokens),
-        continue;
-      }
-      pending.push.apply(pending, _toConsumableArray(token.children));
-
-      // Build lists of bare tokens for each emphasis marker type
-      var _iterator = _createForOfIteratorHelper(emphasisTokensByMarker.values()),
       _step;
     try {
       for (_iterator.s(); !(_step = _iterator.n()).done;) {
-          var emphasisTokens = _step.value;
+        var token = _step.value;
-          emphasisTokens.length = 0;
+        // Build lists of bare tokens for each emphasis marker type
-        }
+        var _iterator2 = _createForOfIteratorHelper(emphasisTokensByMarker.values()),
-      } catch (err) {
-        _iterator.e(err);
-      } finally {
-        _iterator.f();
-      }
-      var _iterator2 = _createForOfIteratorHelper(token.children),
           _step2;
         try {
           for (_iterator2.s(); !(_step2 = _iterator2.n()).done;) {
-          var child = _step2.value;
+            var emphasisTokens = _step2.value;
+            emphasisTokens.length = 0;
+          }
+        } catch (err) {
+          _iterator2.e(err);
+        } finally {
+          _iterator2.f();
+        }
+        var _iterator3 = _createForOfIteratorHelper(token.children),
+          _step3;
+        try {
+          for (_iterator3.s(); !(_step3 = _iterator3.n()).done;) {
+            var child = _step3.value;
             var text = child.text,
               type = child.type;
             if (type === "data" && text.length <= 3) {
@@ -5220,15 +5229,15 @@ module.exports = {
 
           // Process bare tokens for each emphasis marker type
         } catch (err) {
-        _iterator2.e(err);
+          _iterator3.e(err);
         } finally {
-        _iterator2.f();
+          _iterator3.f();
         }
-      var _iterator3 = _createForOfIteratorHelper(emphasisTokensByMarker.entries()),
+        var _iterator4 = _createForOfIteratorHelper(emphasisTokensByMarker.entries()),
-        _step3;
+          _step4;
         try {
-        for (_iterator3.s(); !(_step3 = _iterator3.n()).done;) {
+          for (_iterator4.s(); !(_step4 = _iterator4.n()).done;) {
-          var entry = _step3.value;
+            var entry = _step4.value;
             var _entry = _slicedToArray(entry, 2),
               _marker = _entry[0],
               _emphasisTokens2 = _entry[1];
@@ -5265,11 +5274,16 @@ module.exports = {
             }
           }
         } catch (err) {
-        _iterator3.e(err);
+          _iterator4.e(err);
         } finally {
-        _iterator3.f();
+          _iterator4.f();
         }
       }
+    } catch (err) {
+      _iterator.e(err);
+    } finally {
+      _iterator.f();
+    }
   }
 };
 
@@ -5738,26 +5752,19 @@ module.exports = {
     var includeCodeBlocks = codeBlocks === undefined ? true : !!codeBlocks;
     var htmlElements = params.config.html_elements;
     var includeHtmlElements = htmlElements === undefined ? true : !!htmlElements;
-    var scannedTypes = new Set(["data", "htmlFlowData"]);
+    var scannedTypes = new Set(["data"]);
     if (includeCodeBlocks) {
       scannedTypes.add("codeFlowValue");
       scannedTypes.add("codeTextData");
     }
+    if (includeHtmlElements) {
+      scannedTypes.add("htmlFlowData");
+      scannedTypes.add("htmlTextData");
+    }
     var contentTokens = filterByPredicate(params.parsers.micromark.tokens, function (token) {
       return scannedTypes.has(token.type);
     }, function (token) {
-      var children = token.children;
+      return token.children.filter(function (t) {
-      var htmlFlowChildren = token.htmlFlowChildren,
-        text = token.text,
-        type = token.type;
-      if (!includeHtmlElements && type === "htmlFlow") {
-        children = text.startsWith("<!--") ?
-        // Remove comment content
-        [] :
-        // Examine htmlText content
-        htmlFlowChildren;
-      }
-      return children.filter(function (t) {
         return !ignoredChildTypes.has(t.type);
       });
     });
@@ -6027,14 +6034,18 @@ var _require = __webpack_require__(/*! ../helpers */ "../helpers/helpers.js"),
   addError = _require.addError,
   emphasisOrStrongStyleFor = _require.emphasisOrStrongStyleFor;
 var _require2 = __webpack_require__(/*! ../helpers/micromark.cjs */ "../helpers/micromark.cjs"),
-  filterByTypes = _require2.filterByTypes,
+  filterByPredicate = _require2.filterByPredicate,
   tokenIfType = _require2.tokenIfType;
 var intrawordRe = /\w/;
 var impl = function impl(params, onError, type, asterisk, underline) {
   var style = arguments.length > 5 && arguments[5] !== undefined ? arguments[5] : "consistent";
   var lines = params.lines,
     parsers = params.parsers;
-  var emphasisTokens = filterByTypes(parsers.micromark.tokens, [type]);
+  var emphasisTokens = filterByPredicate(parsers.micromark.tokens, function (token) {
+    return token.type === type;
+  }, function (token) {
+    return token.type === "htmlFlow" ? [] : token.children;
+  });
   var _iterator = _createForOfIteratorHelper(emphasisTokens),
     _step;
   try {
@@ -6114,7 +6125,6 @@ var _require = __webpack_require__(/*! ../helpers */ "../helpers/helpers.js"),
   addError = _require.addError,
   addErrorDetailIf = _require.addErrorDetailIf;
 var _require2 = __webpack_require__(/*! ../helpers/micromark.cjs */ "../helpers/micromark.cjs"),
-  filterByHtmlTokens = _require2.filterByHtmlTokens,
   filterByTypes = _require2.filterByTypes,
   getHtmlTagInfo = _require2.getHtmlTagInfo;
 
@@ -6179,7 +6189,7 @@ module.exports = {
     } finally {
       _iterator.f();
     }
-    var _iterator2 = _createForOfIteratorHelper(filterByHtmlTokens(tokens)),
+    var _iterator2 = _createForOfIteratorHelper(filterByTypes(tokens, ["htmlText"])),
       _step2;
     try {
       for (_iterator2.s(); !(_step2 = _iterator2.n()).done;) {

helpers/micromark.cjs

@@ -23,9 +23,32 @@ const flatTokensSymbol = Symbol("flat-tokens");
  * @property {number} endColumn End column (1-based).
  * @property {string} text Token text.
  * @property {Token[]} children Child tokens.
- * @property {Token[]} [htmlFlowChildren] Child tokens for htmlFlow.
  */
 
+/**
+ * Returns whether a token is an htmlFlow type containing an HTML comment.
+ *
+ * @param {Token} token Micromark token.
+ * @returns {boolean} True iff token is htmlFlow containing a comment.
+ */
+function isHtmlFlowComment(token) {
+  const { text, type } = token;
+  if (
+    (type === "htmlFlow") &&
+    text.startsWith("<!--") &&
+    text.endsWith("-->")
+  ) {
+    const comment = text.slice(4, -3);
+    return (
+      !comment.startsWith(">") &&
+      !comment.startsWith("->") &&
+      !comment.endsWith("-") &&
+      !comment.includes("--")
+    );
+  }
+  return false;
+}
+
 /**
  * Parses a Markdown document and returns Micromark events.
  *
@@ -91,13 +114,14 @@ function micromarkParseWithOffset(
   const history = [ current ];
   let reparseOptions = null;
   let lines = null;
+  let skipHtmlFlowChildren = false;
   for (const event of events) {
     const [ kind, token, context ] = event;
     const { type, start, end } = token;
     const { "column": startColumn, "line": startLine } = start;
     const { "column": endColumn, "line": endLine } = end;
     const text = context.sliceSerialize(token);
-    if (kind === "enter") {
+    if ((kind === "enter") && !skipHtmlFlowChildren) {
       const previous = current;
       history.push(previous);
       current = {
@@ -109,7 +133,11 @@ function micromarkParseWithOffset(
         text,
         "children": []
       };
-      if (current.type === "htmlFlow") {
+      previous.children.push(current);
+      flatTokens.push(current);
+      // @ts-ignore
+      if ((current.type === "htmlFlow") && !isHtmlFlowComment(current)) {
+        skipHtmlFlowChildren = true;
         if (!reparseOptions || !lines) {
           reparseOptions = {
             ...micromarkOptions,
@@ -126,22 +154,27 @@ function micromarkParseWithOffset(
         const reparseMarkdown = lines
           .slice(current.startLine - 1, current.endLine)
           .join("\n");
-        current.htmlFlowChildren = micromarkParseWithOffset(
+        const tokens = micromarkParseWithOffset(
           reparseMarkdown,
           reparseOptions,
           referencesDefined,
           current.startLine - 1
         );
+        current.children = tokens;
+        flatTokens.push(...tokens[flatTokensSymbol]);
       }
-      previous.children.push(current);
-      flatTokens.push(current);
     } else if (kind === "exit") {
+      if (type === "htmlFlow") {
+        skipHtmlFlowChildren = false;
+      }
+      if (!skipHtmlFlowChildren) {
         Object.freeze(current.children);
         Object.freeze(current);
         // @ts-ignore
         current = history.pop();
       }
     }
+  }
 
   // Return document
   Object.defineProperty(document, flatTokensSymbol, { "value": flatTokens });
@@ -211,20 +244,6 @@ function filterByTypes(tokens, allowed) {
   return filterByPredicate(tokens, predicate);
 }
 
-/**
- * Filter a list of Micromark tokens for HTML tokens.
- *
- * @param {Token[]} tokens Micromark tokens.
- * @returns {Token[]} Filtered tokens.
- */
-function filterByHtmlTokens(tokens) {
-  return filterByPredicate(
-    tokens,
-    (token) => token.type === "htmlText",
-    (token) => token.htmlFlowChildren || token.children
-  );
-}
-
 /**
  * Gets the heading level of a Micromark heading tokan.
  *
@@ -318,7 +337,6 @@ function tokenIfType(token, type) {
 
 module.exports = {
   "parse": micromarkParse,
-  filterByHtmlTokens,
   filterByPredicate,
   filterByTypes,
   getHeadingLevel,

lib/md032.js

@@ -46,7 +46,9 @@ module.exports = {
     const topLevelLists = filterByPredicate(
       parsers.micromark.tokens,
       isList,
-      (token) => (isList(token) ? [] : token.children)
+      (token) => (
+        (isList(token) || (token.type === "htmlFlow")) ? [] : token.children
+      )
     );
     for (const list of topLevelLists) {
 

lib/md033.js

@@ -3,7 +3,7 @@
 "use strict";
 
 const { addError } = require("../helpers");
-const { filterByHtmlTokens, getHtmlTagInfo } =
+const { filterByTypes, getHtmlTagInfo } =
   require("../helpers/micromark.cjs");
 
 const nextLinesRe = /[\r\n][\s\S]*$/;
@@ -16,7 +16,8 @@ module.exports = {
     let allowedElements = params.config.allowed_elements;
     allowedElements = Array.isArray(allowedElements) ? allowedElements : [];
     allowedElements = allowedElements.map((element) => element.toLowerCase());
-    for (const token of filterByHtmlTokens(params.parsers.micromark.tokens)) {
+    const { tokens } = params.parsers.micromark;
+    for (const token of filterByTypes(tokens, [ "htmlText" ])) {
       const htmlTagInfo = getHtmlTagInfo(token);
       if (
         htmlTagInfo &&

lib/md037.js

@@ -3,6 +3,7 @@
 "use strict";
 
 const { addError } = require("../helpers");
+const { filterByPredicate } = require("../helpers/micromark.cjs");
 
 module.exports = {
   "names": [ "MD037", "no-space-in-emphasis" ],
@@ -16,16 +17,11 @@ module.exports = {
     for (const marker of [ "_", "__", "___", "*", "**", "***" ]) {
       emphasisTokensByMarker.set(marker, []);
     }
-    const pending = [ ...parsers.micromark.tokens ];
+    const tokens = filterByPredicate(
-    let token = null;
+      parsers.micromark.tokens,
-    while ((token = pending.shift())) {
+      (token) => token.children.some((child) => child.type === "data")
-
+    );
-      // Use reparsed children of htmlFlow tokens
+    for (const token of tokens) {
-      if (token.type === "htmlFlow") {
-        pending.unshift(...token.htmlFlowChildren);
-        continue;
-      }
-      pending.push(...token.children);
 
       // Build lists of bare tokens for each emphasis marker type
       for (const emphasisTokens of emphasisTokensByMarker.values()) {

lib/md044.js

@@ -29,27 +29,22 @@ module.exports = {
     const htmlElements = params.config.html_elements;
     const includeHtmlElements =
       (htmlElements === undefined) ? true : !!htmlElements;
-    const scannedTypes = new Set([ "data", "htmlFlowData" ]);
+    const scannedTypes = new Set([ "data" ]);
     if (includeCodeBlocks) {
       scannedTypes.add("codeFlowValue");
       scannedTypes.add("codeTextData");
     }
+    if (includeHtmlElements) {
+      scannedTypes.add("htmlFlowData");
+      scannedTypes.add("htmlTextData");
+    }
     const contentTokens =
       filterByPredicate(
         params.parsers.micromark.tokens,
         (token) => scannedTypes.has(token.type),
-        (token) => {
+        (token) => (
-          let { children } = token;
+          token.children.filter((t) => !ignoredChildTypes.has(t.type))
-          const { htmlFlowChildren, text, type } = token;
+        )
-          if (!includeHtmlElements && (type === "htmlFlow")) {
-            children = text.startsWith("<!--") ?
-              // Remove comment content
-              [] :
-              // Examine htmlText content
-              htmlFlowChildren;
-          }
-          return children.filter((t) => !ignoredChildTypes.has(t.type));
-        }
       );
     const exclusions = [];
     const autoLinked = new Set();

lib/md049-md050.js

@@ -3,15 +3,18 @@
 "use strict";
 
 const { addError, emphasisOrStrongStyleFor } = require("../helpers");
-const { filterByTypes, tokenIfType } = require("../helpers/micromark.cjs");
+const { filterByPredicate, tokenIfType } = require("../helpers/micromark.cjs");
 
 const intrawordRe = /\w/;
 
 const impl =
   (params, onError, type, asterisk, underline, style = "consistent") => {
     const { lines, parsers } = params;
-    const emphasisTokens =
+    const emphasisTokens = filterByPredicate(
-      filterByTypes(parsers.micromark.tokens, [ type ]);
+      parsers.micromark.tokens,
+      (token) => token.type === type,
+      (token) => ((token.type === "htmlFlow") ? [] : token.children)
+    );
     for (const token of emphasisTokens) {
       const { children } = token;
       const childType = `${type}Sequence`;

lib/md051.js

@@ -3,8 +3,7 @@
 "use strict";
 
 const { addError, addErrorDetailIf } = require("../helpers");
-const { filterByHtmlTokens, filterByTypes, getHtmlTagInfo } =
+const { filterByTypes, getHtmlTagInfo } = require("../helpers/micromark.cjs");
-  require("../helpers/micromark.cjs");
 
 // Regular expression for identifying HTML anchor names
 const idRe = /\sid\s*=\s*['"]?([^'"\s>]+)/iu;
@@ -68,7 +67,7 @@ module.exports = {
     }
 
     // Process HTML anchors
-    for (const token of filterByHtmlTokens(tokens)) {
+    for (const token of filterByTypes(tokens, [ "htmlText" ])) {
       const htmlTagInfo = getHtmlTagInfo(token);
       if (htmlTagInfo && !htmlTagInfo.close) {
         const anchorMatch = idRe.exec(token.text) ||

test/emphasis-markers.md

@@ -19,3 +19,11 @@ also` __bad__ {MD050}
 This `is
 also
 very` __bad__ {MD050}
+
+<p>HTML __should__ *be* ignored</p>
+
+<p>
+HTML __should__ *be* ignored
+</p>
+
+<!-- markdownlint-configure-file { "no-inline-html": false } -->

test/lists_without_blank_lines.md

@@ -74,7 +74,22 @@ code
 
 text
 
+<p>
+1. Not a
+2. list
+</p>
+
+<p>1. Not a list</p>
+
+<p>
+* Not a
+* list
+</p>
+
+<p>* Not a list</p>
+
 <!-- markdownlint-configure-file {
+  "no-inline-html": false,
   "ul-style": false,
   "ol-prefix": false,
   "fenced-code-language": false

test/markdownlint-test-micromark.mjs

@@ -26,17 +26,28 @@ test("getMicromarkEvents/filterByPredicate", async(t) => {
   t.plan(1);
   const content = await testContent;
   const events = getMicromarkEvents(content);
+  let inHtmlFlow = false;
   const eventTypes = events
-    .filter((event) => event[0] === "enter")
+    .filter((event) => {
+      const result = !inHtmlFlow && (event[0] === "enter");
+      if (event[1].type === "htmlFlow") {
+        inHtmlFlow = !inHtmlFlow;
+      }
+      return result;
+    })
     .map((event) => event[1].type);
   const tokens = parse(content);
-  const filtered = filterByPredicate(tokens, () => true);
+  const filtered = filterByPredicate(
+    tokens,
+    () => true,
+    (token) => ((token.type === "htmlFlow") ? [] : token.children)
+  );
   const tokenTypes = filtered.map((token) => token.type);
   t.deepEqual(tokenTypes, eventTypes);
 });
 
 test("filterByTypes", async(t) => {
-  t.plan(6);
+  t.plan(8);
   const filtered = filterByTypes(
     await testTokens,
     [ "atxHeadingText", "codeText", "htmlText", "setextHeadingText" ]

test/markdownlint-test.js

@@ -912,7 +912,7 @@ test("readme", async(t) => {
 });
 
 test("validateJsonUsingConfigSchemaStrict", (t) => {
-  t.plan(159);
+  t.plan(160);
   const configRe =
     /^[\s\S]*<!-- markdownlint-configure-file ([\s\S]*) -->[\s\S]*$/;
   const ignoreFiles = new Set([

test/snapshots/markdownlint-test-micromark.mjs.md

@@ -2574,57 +2574,6 @@ Generated by [AVA](https://avajs.dev).
       },
       {
         children: [
-          {
-            children: [],
-            endColumn: 4,
-            endLine: 43,
-            startColumn: 1,
-            startLine: 43,
-            text: '<p>',
-            type: 'htmlFlowData',
-          },
-          {
-            children: [],
-            endColumn: 1,
-            endLine: 44,
-            startColumn: 4,
-            startLine: 43,
-            text: `␊
-            `,
-            type: 'lineEnding',
-          },
-          {
-            children: [],
-            endColumn: 11,
-            endLine: 44,
-            startColumn: 1,
-            startLine: 44,
-            text: 'HTML block',
-            type: 'htmlFlowData',
-          },
-          {
-            children: [],
-            endColumn: 1,
-            endLine: 45,
-            startColumn: 11,
-            startLine: 44,
-            text: `␊
-            `,
-            type: 'lineEnding',
-          },
-          {
-            children: [],
-            endColumn: 5,
-            endLine: 45,
-            startColumn: 1,
-            startLine: 45,
-            text: '</p>',
-            type: 'htmlFlowData',
-          },
-        ],
-        endColumn: 5,
-        endLine: 45,
-        htmlFlowChildren: [
           {
             children: [
               {
@@ -2717,6 +2666,8 @@ Generated by [AVA](https://avajs.dev).
             type: 'content',
           },
         ],
+        endColumn: 5,
+        endLine: 45,
         startColumn: 1,
         startLine: 43,
         text: `<p>␊
@@ -3224,47 +3175,6 @@ Generated by [AVA](https://avajs.dev).
         ],
         endColumn: 35,
         endLine: 51,
-        htmlFlowChildren: [
-          {
-            children: [
-              {
-                children: [
-                  {
-                    children: [
-                      {
-                        children: [],
-                        endColumn: 35,
-                        endLine: 51,
-                        startColumn: 1,
-                        startLine: 51,
-                        text: '<!-- markdownlint-disable-file -->',
-                        type: 'htmlTextData',
-                      },
-                    ],
-                    endColumn: 35,
-                    endLine: 51,
-                    startColumn: 1,
-                    startLine: 51,
-                    text: '<!-- markdownlint-disable-file -->',
-                    type: 'htmlText',
-                  },
-                ],
-                endColumn: 35,
-                endLine: 51,
-                startColumn: 1,
-                startLine: 51,
-                text: '<!-- markdownlint-disable-file -->',
-                type: 'paragraph',
-              },
-            ],
-            endColumn: 35,
-            endLine: 51,
-            startColumn: 1,
-            startLine: 51,
-            text: '<!-- markdownlint-disable-file -->',
-            type: 'content',
-          },
-        ],
         startColumn: 1,
         startLine: 51,
         text: '<!-- markdownlint-disable-file -->',

test/snapshots/markdownlint-test-scenarios.js.md

@@ -10917,6 +10917,14 @@ Generated by [AVA](https://avajs.dev).
       This \`is␊
       also␊
       very\` **bad** {MD050}␊
+      ␊
+      <p>HTML __should__ *be* ignored</p>␊
+      ␊
+      <p>␊
+      HTML __should__ *be* ignored␊
+      </p>␊
+      ␊
+      <!-- markdownlint-configure-file { "no-inline-html": false } -->␊
       `,
     }
 
@@ -30582,7 +30590,7 @@ Generated by [AVA](https://avajs.dev).
             insertText: `␊
             `,
           },
-          lineNumber: 83,
+          lineNumber: 98,
           ruleDescription: 'Files should end with a single newline character',
           ruleInformation: 'https://github.com/DavidAnson/markdownlint/blob/v0.0.0/doc/md047.md',
           ruleNames: [
@@ -30679,7 +30687,22 @@ Generated by [AVA](https://avajs.dev).
       ␊
       text␊
       ␊
+      <p>␊
+      1. Not a␊
+      2. list␊
+      </p>␊
+      ␊
+      <p>1. Not a list</p>␊
+      ␊
+      <p>␊
+      * Not a␊
+      * list␊
+      </p>␊
+      ␊
+      <p>* Not a list</p>␊
+      ␊
       <!-- markdownlint-configure-file {␊
+        "no-inline-html": false,␊
         "ul-style": false,␊
         "ol-prefix": false,␊
         "fenced-code-language": false␊