Add MD037 with tests, improve handling of line numbers for inlines.

README.md

@@ -67,6 +67,7 @@ cases come directly from that project.
 * **MD034** - Bare URL used
 * **MD035** - Horizontal rule style
 * **MD036** - Emphasis used instead of a header
+* **MD037** - Spaces inside emphasis markers
 
 See [Rules.md](doc/Rules.md) for more details.
 
@@ -78,7 +79,7 @@ See [Rules.md](doc/Rules.md) for more details.
 * **blockquote** - MD027, MD028
 * **bullet** - MD004, MD005, MD006, MD007, MD032
 * **code** - MD014, MD031
-* **emphasis** - MD036
+* **emphasis** - MD036, MD037
 * **hard_tab** - MD010
 * **headers** - MD001, MD002, MD003, MD018, MD019, MD020, MD021, MD022, MD023,
   MD024, MD025, MD026, MD036
@@ -91,7 +92,7 @@ See [Rules.md](doc/Rules.md) for more details.
 * **spaces** - MD018, MD019, MD020, MD021, MD023
 * **ul** - MD004, MD005, MD006, MD007, MD030, MD032
 * **url** - MD034
-* **whitespace** - MD009, MD010, MD012, MD027, MD028, MD030
+* **whitespace** - MD009, MD010, MD012, MD027, MD028, MD030, MD037
 
 ## API
 

doc/Rules.md

@@ -794,3 +794,33 @@ sections:
 
 Note: this rule looks for paragraphs that consist entirely of emphasized text.
 It won't fire on emphasis used within regular text.
+
+## MD037 - Spaces inside emphasis markers
+
+Tags: whitespace, emphasis
+
+This rule is triggered when emphasis markers (bold, italic) are used, but they
+have spaces between the markers and the text:
+
+    Here is some ** bold ** text.
+
+    Here is some * italic * text.
+
+    Here is some more __ bold __ text.
+
+    Here is some more _ italic _ text.
+
+To fix this, remove the spaces around the emphasis markers:
+
+    Here is some **bold** text.
+
+    Here is some *italic* text.
+
+    Here is some more __bold__ text.
+
+    Here is some more _italic_ text.
+
+Rationale: Emphasis is only parsed as such when the asterisks/underscores
+aren't completely surrounded by spaces. This rule attempts to detect where
+they were surrounded by spaces, but it appears that emphasized text was
+intended by the author.

lib/markdownlint.js

@@ -72,6 +72,14 @@ function lintFile(file, config, synchronous, callback) {
           while (!(lines[token.map[1] - 1].trim())) {
             token.map[1]--;
           }
+          // Annotate children with lineNumber
+          var lineNumber = token.lineNumber;
+          (token.children || []).forEach(function forChild(child) {
+            child.lineNumber = lineNumber;
+            if ((child.type === "softbreak") || (child.type === "hardbreak")) {
+              lineNumber++;
+            }
+          });
         }
       });
       // Create parameters for rules

lib/rules.js

@@ -60,6 +60,15 @@ function forEachLine(params, callback) {
   });
 }
 
+// Calls the provided function for each text token
+function forEachText(params, callback) {
+  filterTokens(params.tokens, "inline")
+    .forEach(function forToken(token) {
+      filterTokens(token.children, "text")
+        .forEach(callback);
+    });
+}
+
 // Calls the provided function for each heading's content
 function forEachHeading(params, callback) {
   var heading = null;
@@ -266,15 +275,11 @@ module.exports = [
     "desc": "Reversed link syntax",
     "tags": [ "links" ],
     "func": function MD011(params, errors) {
-      filterTokens(params.tokens, "inline")
-        .forEach(function forToken(token) {
-          filterTokens(token.children, "text")
-            .forEach(function forChild(child) {
-              if (/\([^)]+\)\[[^\]]+\]/.test(child.content)) {
+      forEachText(params, function forToken(token) {
+        if (/\([^)]+\)\[[^\]]+\]/.test(token.content)) {
           errors.push(token.lineNumber);
         }
       });
-        });
     }
   },
 
@@ -631,7 +636,6 @@ module.exports = [
     "func": function MD034(params, errors) {
       filterTokens(params.tokens, "inline")
         .forEach(function forToken(token) {
-          var lineNumber = token.lineNumber;
           var inLink = false;
           token.children.forEach(function forChild(child) {
             if (child.type === "link_open") {
@@ -641,10 +645,7 @@ module.exports = [
             } else if ((child.type === "text") &&
                        !inLink &&
                        /https?:\/\//.test(child.content)) {
-              errors.push(lineNumber);
-            } else if ((child.type === "softbreak") ||
-                       (child.type === "hardbreak")) {
-              lineNumber++;
+              errors.push(child.lineNumber);
             }
           });
         });
@@ -674,9 +675,7 @@ module.exports = [
     "desc": "Emphasis used instead of a header",
     "tags": [ "headers", "emphasis" ],
     "func": function MD036(params, errors) {
-      var lineNumber = 0;
       function base(token) {
-        lineNumber = token.lineNumber;
         if (token.type === "paragraph_open") {
           return function inParagraph(t) {
             if ((t.type === "inline") &&
@@ -684,7 +683,7 @@ module.exports = [
                 ((t.children[0].type === "strong_open") ||
                  (t.children[0].type === "em_open")) &&
                 (t.children[1].type === "text")) {
-              errors.push(lineNumber);
+              errors.push(t.lineNumber);
             }
           };
         } else if (token.type === "blockquote_open") {
@@ -700,5 +699,19 @@ module.exports = [
         state = state(token) || base;
       });
     }
+  },
+
+  {
+    "name": "MD037",
+    "desc": "Spaces inside emphasis markers",
+    "tags": [ "whitespace", "emphasis" ],
+    "func": function MD037(params, errors) {
+      forEachText(params, function forToken(token) {
+        if (/\s(\*\*?|__?)\s.+\1/.test(token.content) ||
+            /(\*\*?|__?).+\s\1\s/.test(token.content)) {
+          errors.push(token.lineNumber);
+        }
+      });
+    }
   }
 ];

test/markdownlint-test.js

@@ -498,7 +498,7 @@ module.exports.badFileSync = function badFileSync(test) {
 };
 
 module.exports.readme = function readme(test) {
-  test.expect(86);
+  test.expect(88);
   var tagToRules = {};
   rules.forEach(function forRule(rule) {
     rule.tags.forEach(function forTag(tag) {
@@ -555,7 +555,7 @@ module.exports.readme = function readme(test) {
 };
 
 module.exports.doc = function doc(test) {
-  test.expect(131);
+  test.expect(135);
   fs.readFile("doc/Rules.md", shared.utf8Encoding,
     function readFile(err, contents) {
       test.ifError(err);

test/spaces_inside_emphasis_markers.md

@@ -0,0 +1,35 @@
+Line with *Normal emphasis*
+
+Line with **Normal strong**
+
+Line with _Normal emphasis_
+
+Line with __Normal strong__
+
+Broken * emphasis * with spaces in {MD037}
+
+Broken ** strong ** with spaces in {MD037}
+
+Broken _ emphasis _ with spaces in {MD037}
+
+Broken __ strong __ with spaces in {MD037}
+
+Mixed *ok emphasis* and * broken emphasis * {MD037}
+
+Mixed **ok strong** and ** broken strong ** {MD037}
+
+Mixed _ok emphasis_ and _ broken emphasis _ {MD037}
+
+Mixed __ok strong__ and __ broken strong __ {MD037}
+
+Mixed *ok emphasis* **ok strong** * broken emphasis * {MD037}
+
+Multiple * broken emphasis * _ broken emphasis _ {MD037}
+
+One-sided *broken emphasis * {MD037}
+
+One-sided * broken emphasis* {MD037}
+
+Don't _flag on _words with underscores before them.
+
+The same goes for words* with asterisks* after them.