fix: definition list support

Author: harlan-zw

src/const.ts

@@ -96,6 +96,13 @@ export const TAG_BDO = 94
 export const TAG_RUBY = 95
 export const TAG_RT = 96
 export const TAG_RP = 97
+export const TAG_DD = 98
+export const TAG_DT = 99
+export const TAG_ADDRESS = 100
+export const TAG_DL = 101
+
+// Maximum tag ID for creating the typed array (97 for TAG_RP + 1 for buffer)
+export const MAX_TAG_ID = 102
 
 // HTML character entity mapping
 export const HTML_ENTITIES: Record<string, string> = {
@@ -214,11 +221,12 @@ export const TagIdMap: Record<string, number> = {
   ruby: TAG_RUBY,
   rt: TAG_RT,
   rp: TAG_RP,
+  dd: TAG_DD,
+  dt: TAG_DT,
+  dl: TAG_DL,
+  address: TAG_ADDRESS,
 }
 
-// Maximum tag ID for creating the typed array (97 for TAG_RP + 1 for buffer)
-export const MAX_TAG_ID = 98
-
 // Pre-defined strings to avoid repeated allocations
 export const MARKDOWN_STRONG = '**'
 export const MARKDOWN_EMPHASIS = '_'

src/tags.ts

@@ -12,6 +12,7 @@ import {
   TABLE_ROW_SPACING,
   TAG_A,
   TAG_ABBR,
+  TAG_ADDRESS,
   TAG_AREA,
   TAG_ASIDE,
   TAG_AUDIO,
@@ -27,11 +28,14 @@ import {
   TAG_CITE,
   TAG_CODE,
   TAG_COL,
+  TAG_DD,
   TAG_DEL,
   TAG_DETAILS,
   TAG_DFN,
   TAG_DIALOG,
   TAG_DIV,
+  TAG_DL,
+  TAG_DT,
   TAG_EM,
   TAG_EMBED,
   TAG_FIELDSET,
@@ -787,4 +791,31 @@ export const tagHandlers: Record<number, TagHandler> = {
     spacing: NO_SPACING,
     isInline: true,
   },
+
+  [TAG_ADDRESS]: {
+    enter: () => '<address>',
+    exit: () => '</address>',
+    spacing: NO_SPACING,
+  },
+
+  [TAG_DL]: {
+    spacing: NO_SPACING,
+    enter: () => '<dl>',
+    exit: () => '</dl>',
+  },
+
+  [TAG_DT]: {
+    // Definition term
+    enter: () => '<dt>',
+    exit: () => '</dt>',
+    collapsesInnerWhiteSpace: true,
+    spacing: [0, 1],
+  },
+
+  [TAG_DD]: {
+    // Definition term
+    enter: () => '<dd>',
+    exit: () => '</dd>',
+    spacing: [0, 1],
+  },
 }

test/unit/nodes/definition-lists.test.ts

@@ -0,0 +1,90 @@
+import { describe, expect, it } from 'vitest'
+import { syncHtmlToMarkdown } from '../../../src'
+
+describe('definition lists', () => {
+  it('converts address tags', () => {
+    const result = syncHtmlToMarkdown(`
+      <address>
+        John Doe<br>
+        123 Main St<br>
+        Anytown, CA 12345
+      </address>
+    `)
+    expect(result).toMatchInlineSnapshot(`"<address>John Doe 123 Main St Anytown, CA 12345 </address>"`)
+  })
+
+  it('handles definition lists', () => {
+    const result = syncHtmlToMarkdown(`
+      <dl>
+        <dt>HTML</dt>
+        <dd>HyperText Markup Language</dd>
+        <dt>CSS</dt>
+        <dd>Cascading Style Sheets</dd>
+      </dl>
+    `)
+    expect(result).toMatchInlineSnapshot(`
+      "<dl><dt>HTML</dt>
+      <dd>HyperText Markup Language</dd>
+      <dt>CSS</dt>
+      <dd>Cascading Style Sheets</dd>
+      </dl>"
+    `)
+  })
+
+  it('handles nested definition lists', () => {
+    const result = syncHtmlToMarkdown(`
+      <dl>
+        <dt>Web Languages</dt>
+        <dd>
+          <dl>
+            <dt>HTML</dt>
+            <dd>HyperText Markup Language</dd>
+            <dt>CSS</dt>
+            <dd>Cascading Style Sheets</dd>
+          </dl>
+        </dd>
+        <dt>Runtime</dt>
+        <dd>JavaScript</dd>
+      </dl>
+    `)
+    expect(result).toMatchInlineSnapshot(`
+      "<dl><dt>Web Languages</dt>
+      <dd><dl><dt>HTML</dt>
+      <dd>HyperText Markup Language</dd>
+      <dt>CSS</dt>
+      <dd>Cascading Style Sheets</dd>
+      </dl></dd>
+      <dt>Runtime</dt>
+      <dd>JavaScript</dd>
+      </dl>"
+    `)
+  })
+
+  it('handles complex definition list content', () => {
+    const result = syncHtmlToMarkdown(`
+      <dl>
+        <dt>Term with <strong>formatting</strong></dt>
+        <dd>Definition with <a href="https://example.com">link</a></dd>
+        <dt>Another Term</dt>
+        <dd>
+          <p>Paragraph in definition</p>
+          <ul>
+            <li>List item in definition</li>
+          </ul>
+        </dd>
+      </dl>
+    `)
+    expect(result).toMatchInlineSnapshot(`
+      "<dl><dt>Term with **formatting**</dt>
+      <dd>Definition with [link](https://example.com)</dd>
+      <dt>Another Term</dt>
+      <dd>
+
+      Paragraph in definition
+
+      - List item in definition
+
+      </dd></dl>"
+    `)
+  })
+})