Enhance HTMLExtractionOptions with new annotateNumberClasses feature

- Added `annotateNumberClasses` option to the HTMLExtractionOptions interface for appending CSS class names to numeric elements in markdown output.
- Updated README to include documentation for the new feature.
- Improved HTML to Markdown conversion logic to support number class annotation, preserving semantic meaning.
- Added unit tests to ensure correct functionality across various scenarios.

Author: azhong-git

src/dev/testHtmlToMarkdown.ts

@@ -7,7 +7,7 @@ import { HTMLExtractionOptions } from "../types";
 async function testConvertHtmlToMarkdown(
   htmlFilePath: string,
   outputDir: string,
-  options?: HTMLExtractionOptions
+  options?: HTMLExtractionOptions,
 ) {
   try {
     // Read the HTML file
@@ -23,11 +23,13 @@ async function testConvertHtmlToMarkdown(
 
     // Generate output filename
     const baseName = path.basename(htmlFilePath, ".html");
-    const optionsSuffix = options?.includeImages
-      ? ".with-images"
-      : options?.extractMainHtml
-      ? ".main-content"
-      : "";
+    const optionsSuffix = options?.annotateNumberClasses
+      ? ".number-classes"
+      : options?.includeImages
+        ? ".with-images"
+        : options?.extractMainHtml
+          ? ".main-content"
+          : "";
     const outputPath = path.join(outputDir, `${baseName}${optionsSuffix}.md`);
 
     // Save the markdown
@@ -56,7 +58,7 @@ async function main() {
 
   // Test different conversion options
   console.log(
-    "\n🔍 Testing HTML to Markdown conversion with different options...\n"
+    "\n🔍 Testing HTML to Markdown conversion with different options...\n",
   );
 
   // 1. Basic conversion
@@ -78,9 +80,15 @@ async function main() {
     extractMainHtml: true,
   });
 
+  // 5. Main content extraction with number annotation
+  await testConvertHtmlToMarkdown(htmlFilePath, outputDir, {
+    extractMainHtml: true,
+    annotateNumberClasses: true,
+  });
+
   console.log(
     "\n✨ All conversions completed! Check the output in:",
-    outputDir
+    outputDir,
   );
 }