Update MD051/link-fragments to handle backslash-escaped content in link and definition destinations (fixes #956).

Author: DavidAnson

demo/markdownlint-browser.js

@@ -6229,11 +6229,15 @@ var anchorRe = /\{(#[0-9a-z]+(?:[\x2D_][0-9a-z]+)*)\}/g;
 var childrenExclude = new Set(["image", "reference", "resource"]);
 var tokensInclude = new Set(["codeTextData", "data"]);
 
+/**
+ * @typedef {import("../helpers/micromark.cjs").Token} Token
+ */
+
 /**
  * Converts a Markdown heading into an HTML fragment according to the rules
  * used by GitHub.
  *
- * @param {Object} headingText Heading text token.
+ * @param {Token} headingText Heading text token.
  * @returns {string} Fragment string for heading.
  */
 function convertHeadingToHTMLFragment(headingText) {
@@ -6251,6 +6255,18 @@ function convertHeadingToHTMLFragment(headingText) {
   // https://ruby-doc.org/core-3.0.2/Regexp.html
   .replace(/(?:[\0-\x1F!-,\.\/:-@\[-\^`\{-\xA9\xAB-\xB1\xB4\xB6-\xB8\xBB\xBF\xD7\xF7\u02C2-\u02C5\u02D2-\u02DF\u02E5-\u02EB\u02ED\u02EF-\u02FF\u0375\u0378\u0379\u037E\u0380-\u0385\u0387\u038B\u038D\u03A2\u03F6\u0482\u0530\u0557\u0558\u055A-\u055F\u0589-\u0590\u05BE\u05C0\u05C3\u05C6\u05C8-\u05CF\u05EB-\u05EE\u05F3-\u060F\u061B-\u061F\u066A-\u066D\u06D4\u06DD\u06DE\u06E9\u06FD\u06FE\u0700-\u070F\u074B\u074C\u07B2-\u07BF\u07F6-\u07F9\u07FB\u07FC\u07FE\u07FF\u082E-\u083F\u085C-\u085F\u086B-\u086F\u0888\u088F-\u0897\u08E2\u0964\u0965\u0970\u0984\u098D\u098E\u0991\u0992\u09A9\u09B1\u09B3-\u09B5\u09BA\u09BB\u09C5\u09C6\u09C9\u09CA\u09CF-\u09D6\u09D8-\u09DB\u09DE\u09E4\u09E5\u09F2\u09F3\u09FA\u09FB\u09FD\u09FF\u0A00\u0A04\u0A0B-\u0A0E\u0A11\u0A12\u0A29\u0A31\u0A34\u0A37\u0A3A\u0A3B\u0A3D\u0A43-\u0A46\u0A49\u0A4A\u0A4E-\u0A50\u0A52-\u0A58\u0A5D\u0A5F-\u0A65\u0A76-\u0A80\u0A84\u0A8E\u0A92\u0AA9\u0AB1\u0AB4\u0ABA\u0ABB\u0AC6\u0ACA\u0ACE\u0ACF\u0AD1-\u0ADF\u0AE4\u0AE5\u0AF0-\u0AF8\u0B00\u0B04\u0B0D\u0B0E\u0B11\u0B12\u0B29\u0B31\u0B34\u0B3A\u0B3B\u0B45\u0B46\u0B49\u0B4A\u0B4E-\u0B54\u0B58-\u0B5B\u0B5E\u0B64\u0B65\u0B70\u0B78-\u0B81\u0B84\u0B8B-\u0B8D\u0B91\u0B96-\u0B98\u0B9B\u0B9D\u0BA0-\u0BA2\u0BA5-\u0BA7\u0BAB-\u0BAD\u0BBA-\u0BBD\u0BC3-\u0BC5\u0BC9\u0BCE\u0BCF\u0BD1-\u0BD6\u0BD8-\u0BE5\u0BF3-\u0BFF\u0C0D\u0C11\u0C29\u0C3A\u0C3B\u0C45\u0C49\u0C4E-\u0C54\u0C57\u0C5B\u0C5C\u0C5E\u0C5F\u0C64\u0C65\u0C70-\u0C77\u0C7F\u0C84\u0C8D\u0C91\u0CA9\u0CB4\u0CBA\u0CBB\u0CC5\u0CC9\u0CCE-\u0CD4\u0CD7-\u0CDC\u0CDF\u0CE4\u0CE5\u0CF0\u0CF4-\u0CFF\u0D0D\u0D11\u0D45\u0D49\u0D4F-\u0D53\u0D64\u0D65\u0D79\u0D80\u0D84\u0D97-\u0D99\u0DB2\u0DBC\u0DBE\u0DBF\u0DC7-\u0DC9\u0DCB-\u0DCE\u0DD5\u0DD7\u0DE0-\u0DE5\u0DF0\u0DF1\u0DF4-\u0E00\u0E3B-\u0E3F\u0E4F\u0E5A-\u0E80\u0E83\u0E85\u0E8B\u0EA4\u0EA6\u0EBE\u0EBF\u0EC5\u0EC7\u0ECF\u0EDA\u0EDB\u0EE0-\u0EFF\u0F01-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0F3A-\u0F3D\u0F48\u0F6D-\u0F70\u0F85\u0F98\u0FBD-\u0FC5\u0FC7-\u0FFF\u104A-\u104F\u109E\u109F\u10C6\u10C8-\u10CC\u10CE\u10CF\u10FB\u1249\u124E\u124F\u1257\u1259\u125E\u125F\u1289\u128E\u128F\u12B1\u12B6\u12B7\u12BF\u12C1\u12C6\u12C7\u12D7\u1311\u1316\u1317\u135B\u135C\u1360-\u1368\u137D-\u137F\u1390-\u139F\u13F6\u13F7\u13FE-\u1400\u166D\u166E\u1680\u169B-\u169F\u16EB-\u16ED\u16F9-\u16FF\u1716-\u171E\u1735-\u173F\u1754-\u175F\u176D\u1771\u1774-\u177F\u17D4-\u17D6\u17D8-\u17DB\u17DE\u17DF\u17EA-\u17EF\u17FA-\u180A\u180E\u181A-\u181F\u1879-\u187F\u18AB-\u18AF\u18F6-\u18FF\u191F\u192C-\u192F\u193C-\u1945\u196E\u196F\u1975-\u197F\u19AC-\u19AF\u19CA-\u19CF\u19DB-\u19FF\u1A1C-\u1A1F\u1A5F\u1A7D\u1A7E\u1A8A-\u1A8F\u1A9A-\u1AA6\u1AA8-\u1AAF\u1ACF-\u1AFF\u1B4D-\u1B4F\u1B5A-\u1B6A\u1B74-\u1B7F\u1BF4-\u1BFF\u1C38-\u1C3F\u1C4A-\u1C4C\u1C7E\u1C7F\u1C89-\u1C8F\u1CBB\u1CBC\u1CC0-\u1CCF\u1CD3\u1CFB-\u1CFF\u1F16\u1F17\u1F1E\u1F1F\u1F46\u1F47\u1F4E\u1F4F\u1F58\u1F5A\u1F5C\u1F5E\u1F7E\u1F7F\u1FB5\u1FBD\u1FBF-\u1FC1\u1FC5\u1FCD-\u1FCF\u1FD4\u1FD5\u1FDC-\u1FDF\u1FED-\u1FF1\u1FF5\u1FFD-\u203E\u2041-\u2053\u2055-\u206F\u2072\u2073\u207A-\u207E\u208A-\u208F\u209D-\u20CF\u20F1-\u2101\u2103-\u2106\u2108\u2109\u2114\u2116-\u2118\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u2140-\u2144\u214A-\u214D\u214F\u218A-\u245F\u249C-\u24E9\u2500-\u2775\u2794-\u2BFF\u2CE5-\u2CEA\u2CF4-\u2CFC\u2CFE\u2CFF\u2D26\u2D28-\u2D2C\u2D2E\u2D2F\u2D68-\u2D6E\u2D70-\u2D7E\u2D97-\u2D9F\u2DA7\u2DAF\u2DB7\u2DBF\u2DC7\u2DCF\u2DD7\u2DDF\u2E00-\u2E2E\u2E30-\u3004\u3008-\u3020\u3030\u3036\u3037\u303D-\u3040\u3097\u3098\u309B\u309C\u30A0\u30FB\u3100-\u3104\u3130\u318F-\u3191\u3196-\u319F\u31C0-\u31EF\u3200-\u321F\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u33FF\u4DC0-\u4DFF\uA48D-\uA4CF\uA4FE\uA4FF\uA60D-\uA60F\uA62C-\uA63F\uA673\uA67E\uA6F2-\uA716\uA720\uA721\uA789\uA78A\uA7CB-\uA7CF\uA7D2\uA7D4\uA7DA-\uA7F1\uA828-\uA82B\uA82D-\uA82F\uA836-\uA83F\uA874-\uA87F\uA8C6-\uA8CF\uA8DA-\uA8DF\uA8F8-\uA8FA\uA8FC\uA92E\uA92F\uA954-\uA95F\uA97D-\uA97F\uA9C1-\uA9CE\uA9DA-\uA9DF\uA9FF\uAA37-\uAA3F\uAA4E\uAA4F\uAA5A-\uAA5F\uAA77-\uAA79\uAAC3-\uAADA\uAADE\uAADF\uAAF0\uAAF1\uAAF7-\uAB00\uAB07\uAB08\uAB0F\uAB10\uAB17-\uAB1F\uAB27\uAB2F\uAB5B\uAB6A-\uAB6F\uABEB\uABEE\uABEF\uABFA-\uABFF\uD7A4-\uD7AF\uD7C7-\uD7CA\uD7FC-\uD7FF\uE000-\uF8FF\uFA6E\uFA6F\uFADA-\uFAFF\uFB07-\uFB12\uFB18-\uFB1C\uFB29\uFB37\uFB3D\uFB3F\uFB42\uFB45\uFBB2-\uFBD2\uFD3E-\uFD4F\uFD90\uFD91\uFDC8-\uFDEF\uFDFC-\uFDFF\uFE10-\uFE1F\uFE30-\uFE32\uFE35-\uFE4C\uFE50-\uFE6F\uFE75\uFEFD-\uFF0F\uFF1A-\uFF20\uFF3B-\uFF3E\uFF40\uFF5B-\uFF65\uFFBF-\uFFC1\uFFC8\uFFC9\uFFD0\uFFD1\uFFD8\uFFD9\uFFDD-\uFFFF]|\uD800[\uDC0C\uDC27\uDC3B\uDC3E\uDC4E\uDC4F\uDC5E-\uDC7F\uDCFB-\uDD06\uDD34-\uDD3F\uDD79-\uDD89\uDD8C-\uDDFC\uDDFE-\uDE7F\uDE9D-\uDE9F\uDED1-\uDEDF\uDEFC-\uDEFF\uDF24-\uDF2C\uDF4B-\uDF4F\uDF7B-\uDF7F\uDF9E\uDF9F\uDFC4-\uDFC7\uDFD0\uDFD6-\uDFFF]|\uD801[\uDC9E\uDC9F\uDCAA-\uDCAF\uDCD4-\uDCD7\uDCFC-\uDCFF\uDD28-\uDD2F\uDD64-\uDD6F\uDD7B\uDD8B\uDD93\uDD96\uDDA2\uDDB2\uDDBA\uDDBD-\uDDFF\uDF37-\uDF3F\uDF56-\uDF5F\uDF68-\uDF7F\uDF86\uDFB1\uDFBB-\uDFFF]|\uD802[\uDC06\uDC07\uDC09\uDC36\uDC39-\uDC3B\uDC3D\uDC3E\uDC56\uDC57\uDC77\uDC78\uDC9F-\uDCA6\uDCB0-\uDCDF\uDCF3\uDCF6-\uDCFA\uDD1C-\uDD1F\uDD3A-\uDD7F\uDDB8-\uDDBB\uDDD0\uDDD1\uDE04\uDE07-\uDE0B\uDE14\uDE18\uDE36\uDE37\uDE3B-\uDE3E\uDE49-\uDE5F\uDE7F\uDEA0-\uDEBF\uDEC8\uDEE7-\uDEEA\uDEF0-\uDEFF\uDF36-\uDF3F\uDF56\uDF57\uDF73-\uDF77\uDF92-\uDFA8\uDFB0-\uDFFF]|\uD803[\uDC49-\uDC7F\uDCB3-\uDCBF\uDCF3-\uDCF9\uDD28-\uDD2F\uDD3A-\uDE5F\uDE7F\uDEAA\uDEAD-\uDEAF\uDEB2-\uDEFC\uDF28-\uDF2F\uDF55-\uDF6F\uDF86-\uDFAF\uDFCC-\uDFDF\uDFF7-\uDFFF]|\uD804[\uDC47-\uDC51\uDC76-\uDC7E\uDCBB-\uDCC1\uDCC3-\uDCCF\uDCE9-\uDCEF\uDCFA-\uDCFF\uDD35\uDD40-\uDD43\uDD48-\uDD4F\uDD74\uDD75\uDD77-\uDD7F\uDDC5-\uDDC8\uDDCD\uDDDB\uDDDD-\uDDE0\uDDF5-\uDDFF\uDE12\uDE38-\uDE3D\uDE42-\uDE7F\uDE87\uDE89\uDE8E\uDE9E\uDEA9-\uDEAF\uDEEB-\uDEEF\uDEFA-\uDEFF\uDF04\uDF0D\uDF0E\uDF11\uDF12\uDF29\uDF31\uDF34\uDF3A\uDF45\uDF46\uDF49\uDF4A\uDF4E\uDF4F\uDF51-\uDF56\uDF58-\uDF5C\uDF64\uDF65\uDF6D-\uDF6F\uDF75-\uDFFF]|\uD805[\uDC4B-\uDC4F\uDC5A-\uDC5D\uDC62-\uDC7F\uDCC6\uDCC8-\uDCCF\uDCDA-\uDD7F\uDDB6\uDDB7\uDDC1-\uDDD7\uDDDE-\uDDFF\uDE41-\uDE43\uDE45-\uDE4F\uDE5A-\uDE7F\uDEB9-\uDEBF\uDECA-\uDEFF\uDF1B\uDF1C\uDF2C-\uDF2F\uDF3C-\uDF3F\uDF47-\uDFFF]|\uD806[\uDC3B-\uDC9F\uDCF3-\uDCFE\uDD07\uDD08\uDD0A\uDD0B\uDD14\uDD17\uDD36\uDD39\uDD3A\uDD44-\uDD4F\uDD5A-\uDD9F\uDDA8\uDDA9\uDDD8\uDDD9\uDDE2\uDDE5-\uDDFF\uDE3F-\uDE46\uDE48-\uDE4F\uDE9A-\uDE9C\uDE9E-\uDEAF\uDEF9-\uDFFF]|\uD807[\uDC09\uDC37\uDC41-\uDC4F\uDC6D-\uDC71\uDC90\uDC91\uDCA8\uDCB7-\uDCFF\uDD07\uDD0A\uDD37-\uDD39\uDD3B\uDD3E\uDD48-\uDD4F\uDD5A-\uDD5F\uDD66\uDD69\uDD8F\uDD92\uDD99-\uDD9F\uDDAA-\uDEDF\uDEF7-\uDEFF\uDF11\uDF3B-\uDF3D\uDF43-\uDF4F\uDF5A-\uDFAF\uDFB1-\uDFBF\uDFD5-\uDFFF]|\uD808[\uDF9A-\uDFFF]|\uD809[\uDC6F-\uDC7F\uDD44-\uDFFF]|[\uD80A\uD80E-\uD810\uD812-\uD819\uD824-\uD82A\uD82D\uD82E\uD830-\uD832\uD83D\uD83F\uD87B-\uD87D\uD87F\uD889-\uDB3F\uDB41-\uDBFF][\uDC00-\uDFFF]|\uD80B[\uDC00-\uDF8F\uDFF1-\uDFFF]|\uD80D[\uDC30-\uDC3F\uDC56-\uDFFF]|\uD811[\uDE47-\uDFFF]|\uD81A[\uDE39-\uDE3F\uDE5F\uDE6A-\uDE6F\uDEBF\uDECA-\uDECF\uDEEE\uDEEF\uDEF5-\uDEFF\uDF37-\uDF3F\uDF44-\uDF4F\uDF5A\uDF62\uDF78-\uDF7C\uDF90-\uDFFF]|\uD81B[\uDC00-\uDE3F\uDE97-\uDEFF\uDF4B-\uDF4E\uDF88-\uDF8E\uDFA0-\uDFDF\uDFE2\uDFE5-\uDFEF\uDFF2-\uDFFF]|\uD821[\uDFF8-\uDFFF]|\uD823[\uDCD6-\uDCFF\uDD09-\uDFFF]|\uD82B[\uDC00-\uDFEF\uDFF4\uDFFC\uDFFF]|\uD82C[\uDD23-\uDD31\uDD33-\uDD4F\uDD53\uDD54\uDD56-\uDD63\uDD68-\uDD6F\uDEFC-\uDFFF]|\uD82F[\uDC6B-\uDC6F\uDC7D-\uDC7F\uDC89-\uDC8F\uDC9A-\uDC9C\uDC9F-\uDFFF]|\uD833[\uDC00-\uDEFF\uDF2E\uDF2F\uDF47-\uDFFF]|\uD834[\uDC00-\uDD64\uDD6A-\uDD6C\uDD73-\uDD7A\uDD83\uDD84\uDD8C-\uDDA9\uDDAE-\uDE41\uDE45-\uDEBF\uDED4-\uDEDF\uDEF4-\uDF5F\uDF79-\uDFFF]|\uD835[\uDC55\uDC9D\uDCA0\uDCA1\uDCA3\uDCA4\uDCA7\uDCA8\uDCAD\uDCBA\uDCBC\uDCC4\uDD06\uDD0B\uDD0C\uDD15\uDD1D\uDD3A\uDD3F\uDD45\uDD47-\uDD49\uDD51\uDEA6\uDEA7\uDEC1\uDEDB\uDEFB\uDF15\uDF35\uDF4F\uDF6F\uDF89\uDFA9\uDFC3\uDFCC\uDFCD]|\uD836[\uDC00-\uDDFF\uDE37-\uDE3A\uDE6D-\uDE74\uDE76-\uDE83\uDE85-\uDE9A\uDEA0\uDEB0-\uDFFF]|\uD837[\uDC00-\uDEFF\uDF1F-\uDF24\uDF2B-\uDFFF]|\uD838[\uDC07\uDC19\uDC1A\uDC22\uDC25\uDC2B-\uDC2F\uDC6E-\uDC8E\uDC90-\uDCFF\uDD2D-\uDD2F\uDD3E\uDD3F\uDD4A-\uDD4D\uDD4F-\uDE8F\uDEAF-\uDEBF\uDEFA-\uDFFF]|\uD839[\uDC00-\uDCCF\uDCFA-\uDFDF\uDFE7\uDFEC\uDFEF\uDFFF]|\uD83A[\uDCC5\uDCC6\uDCD7-\uDCFF\uDD4C-\uDD4F\uDD5A-\uDFFF]|\uD83B[\uDC00-\uDC70\uDCAC\uDCB0\uDCB5-\uDD00\uDD2E\uDD3E-\uDDFF\uDE04\uDE20\uDE23\uDE25\uDE26\uDE28\uDE33\uDE38\uDE3A\uDE3C-\uDE41\uDE43-\uDE46\uDE48\uDE4A\uDE4C\uDE50\uDE53\uDE55\uDE56\uDE58\uDE5A\uDE5C\uDE5E\uDE60\uDE63\uDE65\uDE66\uDE6B\uDE73\uDE78\uDE7D\uDE7F\uDE8A\uDE9C-\uDEA0\uDEA4\uDEAA\uDEBC-\uDFFF]|\uD83C[\uDC00-\uDCFF\uDD0D-\uDFFF]|\uD83E[\uDC00-\uDFEF\uDFFA-\uDFFF]|\uD869[\uDEE0-\uDEFF]|\uD86D[\uDF3A-\uDF3F]|\uD86E[\uDC1E\uDC1F]|\uD873[\uDEA2-\uDEAF]|\uD87A[\uDFE1-\uDFFF]|\uD87E[\uDE1E-\uDFFF]|\uD884[\uDF4B-\uDF4F]|\uD888[\uDFB0-\uDFFF]|\uDB40[\uDC00-\uDCFF\uDDF0-\uDFFF]|[\uD800-\uDBFF](?![\uDC00-\uDFFF])|(?:[^\uD800-\uDBFF]|^)[\uDC00-\uDFFF])/g, "").replace(/ /g, "-"));
 }
+
+/**
+ * Unescapes the text of a String-type micromark Token.
+ *
+ * @param {Token} token String-type micromark Token.
+ * @returns {string} Unescaped token text.
+ */
+function unescapeStringTokenText(token) {
+  return filterByTypes(token.children, ["characterEscapeValue", "data"]).map(function (child) {
+    return child.text;
+  }).join("");
+}
 module.exports = {
   "names": ["MD051", "link-fragments"],
   "description": "Link fragments should be valid",
@@ -6329,8 +6345,8 @@ module.exports = {
             var _loop = function _loop() {
               var definition = _step4.value;
               var endColumn = definition.endColumn,
-                startColumn = definition.startColumn,
-                text = definition.text;
+                startColumn = definition.startColumn;
+              var text = unescapeStringTokenText(definition);
               if (text.length > 1 && text.startsWith("#") && !fragments.has(text) && !fragments.has("#".concat(encodeURIComponent(text.slice(1))))) {
                 // eslint-disable-next-line no-undef-init
                 var context = undefined;

lib/md051.js

@@ -15,11 +15,15 @@ const anchorRe = /\{(#[a-z\d]+(?:[-_][a-z\d]+)*)\}/gu;
 const childrenExclude = new Set([ "image", "reference", "resource" ]);
 const tokensInclude = new Set([ "codeTextData", "data" ]);
 
+/**
+ * @typedef {import("../helpers/micromark.cjs").Token} Token
+ */
+
 /**
  * Converts a Markdown heading into an HTML fragment according to the rules
  * used by GitHub.
  *
- * @param {Object} headingText Heading text token.
+ * @param {Token} headingText Heading text token.
  * @returns {string} Fragment string for heading.
  */
 function convertHeadingToHTMLFragment(headingText) {
@@ -46,6 +50,18 @@ function convertHeadingToHTMLFragment(headingText) {
   );
 }
 
+/**
+ * Unescapes the text of a String-type micromark Token.
+ *
+ * @param {Token} token String-type micromark Token.
+ * @returns {string} Unescaped token text.
+ */
+function unescapeStringTokenText(token) {
+  return filterByTypes(token.children, [ "characterEscapeValue", "data" ])
+    .map((child) => child.text)
+    .join("");
+}
+
 module.exports = {
   "names": [ "MD051", "link-fragments" ],
   "description": "Link fragments should be valid",
@@ -99,7 +115,8 @@ module.exports = {
       for (const link of links) {
         const definitions = filterByTypes(link.children, [ definitionType ]);
         for (const definition of definitions) {
-          const { endColumn, startColumn, text } = definition;
+          const { endColumn, startColumn } = definition;
+          const text = unescapeStringTokenText(definition);
           if (
             (text.length > 1) &&
             text.startsWith("#") &&

test/link-fragments.md

@@ -64,6 +64,10 @@
 
 [Valid](#valid-heading-has-)
 
+[Valid](#valid_heading-escaped_underscores)
+
+[Valid](#valid\_heading\-escaped\_underscores)
+
 [Valid](#namedlink)
 
 [Valid](#idlink)
@@ -78,6 +82,8 @@
 
 [Valid][goodref]
 
+[Valid][escapedref]
+
 ### Valid H3 Heading
 
 Text
@@ -159,6 +165,8 @@ Text
 
 ### Valid Heading Has ![an Image](https://example.com)
 
+### Valid_Heading Escaped_Underscores
+
 <a name="namedlink"></a>
 
 <a id = idlink></a>
@@ -177,6 +185,8 @@ Text
 
 [goodref]: #namedlink
 
+[escapedref]: #valid\_heading\-escaped\_underscores
+
 ## Invalid Fragments
 
 [Invalid](#valid-heading-is-an-image) {MD051}