Fixes an issue discovered in dotnet/docs#38912 (#283)

* Fixes an issue discovered in dotnet/docs#38912

* Fix MD lint issue in sample.md

actions/status-checker/__tests__/file-heading-extractor.test.ts

@@ -9,7 +9,7 @@ describe("file-heading-extractor", () => {
   it("when calling getHeadingTextFrom correctly returns H1 value.", async () => {
     const path = "__tests__/sample.md";
     const actual = await getHeadingTextFrom(path);
-    expect(actual).toBe("The heading");
+    expect(actual).toBe("The heading `System.Console` class");
   });
 
   it("when calling getHeadingTextFrom correctly returns title value.", async () => {

actions/status-checker/__tests__/sample.md

@@ -1,6 +1,6 @@
 ## Not heading
 
-# The heading
+# The heading <xref:System.Console> class
 
 An h1 header
 ============
@@ -10,9 +10,9 @@ Paragraphs are separated by a blank line.
 2nd paragraph. *Italic*, **bold**, and `monospace`. Itemized lists
 look like:
 
-* this one
-* that one
-* the other one
+- this one
+- that one
+- the other one
 
 Note that --- not considering the asterisk --- the actual text
 content starts at 4-columns in.
@@ -39,8 +39,8 @@ Here's a numbered list:
 Note again how the actual text starts at 4 columns in (4 characters
 from the left side). Here's a code sample:
 
-    # Let me re-iterate ...
-    for i in 1 .. 10 { do-something(i) }
+  # Let me re-iterate ...
+  for i in 1 .. 10 { do-something(i) }
 
 As you probably guessed, indented 4 spaces. By the way, instead of
 indenting the block, you can use delimited blocks, if you like:
@@ -68,9 +68,9 @@ Now a nested list:
 
  1. First, get these ingredients:
 
-      * carrots
-      * celery
-      * lentils
+      - carrots
+      - celery
+      - lentils
 
  2. Boil some water.
 

actions/status-checker/src/file-heading-extractor.ts

@@ -11,12 +11,17 @@ export async function getHeadingTextFrom(path: string): Promise<string | null> {
       return null;
     }
 
-    const result: string | null =
+    let result: string | null =
       tryGetRegExpMatch(h1RegExp, "h1", content) ??
       tryGetRegExpMatch(titleRegExp, "title", content);
 
     console.log(`Found ${result} from '${path}' contents.`);
 
+    if (result && result.indexOf("<xref:") > -1) {
+      result = normalizeHeadingOrTitleText(result);
+      console.log(`  normalized as ${result}`);
+    }
+
     return result;
   } catch (error) {
     if (error) {
@@ -29,6 +34,22 @@ export async function getHeadingTextFrom(path: string): Promise<string | null> {
   return null;
 }
 
+const xrefRegExp = /<xref:([^>]+)>/gim;
+
+function normalizeHeadingOrTitleText(headingText: string): string {
+  // If contains xref markdown, extract only the text from it.
+  // Example: "<xref:System.Globalization.CompareInfo> class"
+  //       or "<xref:System.Globalization.CompareInfo /> class"
+  // Result: "`System.Globalization.CompareInfo` class"
+  const xrefMatch = xrefRegExp.exec(headingText);
+
+  if (xrefMatch && xrefMatch[1]) {
+    headingText = headingText.replace(xrefRegExp, `\`${xrefMatch[1]}\``);
+  }
+
+  return headingText;
+}
+
 function tryGetRegExpMatch(
   expression: RegExp,
   groupName: string,