fix(markdown): serialize hyperlink as code always with single backticks

Signed-off-by: Cesar Berrospi Ramis <[email protected]>

Author: ceberam

docling_core/transforms/serializer/markdown.py

@@ -211,7 +211,9 @@ def serialize(
                 text_part = f"{num_hashes * '#'} {text}"
         elif isinstance(item, CodeItem):
             if params.format_code_blocks:
-                text_part = f"`{text}`" if is_inline_scope else f"```\n{text}\n```"
+                # inline items and all hyperlinks: use single backticks
+                bt = is_inline_scope or (params.include_hyperlinks and item.hyperlink)
+                text_part = f"`{text}`" if bt else f"```\n{text}\n```"
             else:
                 text_part = text
             escape_html = False

test/data/doc/inline_and_formatting.gt.dt

@@ -43,5 +43,9 @@
 <formula>E=mc^2</formula>
 <text>& ampersand</text>
 </inline></section_header_level_1>
+<inline><text>A hyperlink on</text>
+<code><_unknown_>code in a line</code>
+</inline>
+<code><_unknown_>A hyperlink on code as paragraph</code>
 <text>The end.</text>
 </doctag>

test/data/doc/inline_and_formatting.gt.html

@@ -150,6 +150,8 @@ <h1>Contribution guideline example</h1>
 <em><h1>Whole heading is italic</h1></em>
 <span class='inline-group'>Some <em><code>formatted_code</code></em></span>
 <h2><span class='inline-group'><em>Partially formatted</em> heading to_escape <code>not_to_escape</code> <a href="https://en.wikipedia.org/wiki/Albert_Einstein"><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><mrow><mi>E</mi><mo>&#x0003D;</mo><mi>m</mi><msup><mi>c</mi><mn>2</mn></msup></mrow><annotation encoding="TeX">E=mc^2</annotation></math></a> &amp; ampersand</span></h2>
+<span class='inline-group'>A hyperlink on <a href="#link"><code>code in a line</code></a></span>
+<a href="#test"><pre><code>A hyperlink on code as paragraph</code></pre></a>
 <p>The end.</p>
 </div>
 </body>

test/data/doc/inline_and_formatting.gt.md

@@ -20,4 +20,8 @@ Some *`formatted_code`*
 
 ## *Partially formatted* heading to\_escape `not_to_escape` [$E=mc^2$](https://en.wikipedia.org/wiki/Albert_Einstein) & ampersand
 
+A hyperlink on [`code in a line`](#link)
+
+[`A hyperlink on code as paragraph`](#test)
+
 The end.

test/data/doc/inline_and_formatting.yaml

@@ -8,7 +8,9 @@ body:
   - $ref: '#/texts/32'
   - $ref: '#/groups/8'
   - $ref: '#/texts/35'
-  - $ref: '#/texts/41'
+  - $ref: '#/groups/10'
+  - $ref: '#/texts/43'
+  - $ref: '#/texts/44'
   content_layer: body
   label: unspecified
   name: _root_
@@ -52,7 +54,7 @@ groups:
   - $ref: '#/texts/27'
   - $ref: '#/texts/28'
   content_layer: body
-  label: ordered_list
+  label: list
   name: list
   parent:
     $ref: '#/body'
@@ -128,10 +130,19 @@ groups:
   parent:
     $ref: '#/texts/35'
   self_ref: '#/groups/9'
+- children:
+  - $ref: '#/texts/41'
+  - $ref: '#/texts/42'
+  content_layer: body
+  label: inline
+  name: group
+  parent:
+    $ref: '#/body'
+  self_ref: '#/groups/10'
 key_value_items: []
 name: inline_and_formatting
 origin:
-  binary_hash: 16409076955457599155
+  binary_hash: 9005144896041945842
   filename: inline_and_formatting.md
   mimetype: text/markdown
 pages: {}
@@ -171,6 +182,7 @@ texts:
   formatting:
     bold: false
     italic: true
+    script: baseline
     strikethrough: false
     underline: false
   label: text
@@ -185,6 +197,7 @@ texts:
   formatting:
     bold: true
     italic: false
+    script: baseline
     strikethrough: false
     underline: false
   label: text
@@ -199,6 +212,7 @@ texts:
   formatting:
     bold: true
     italic: true
+    script: baseline
     strikethrough: false
     underline: false
   label: text
@@ -274,6 +288,7 @@ texts:
   formatting:
     bold: true
     italic: false
+    script: baseline
     strikethrough: false
     underline: false
   hyperlink: https://github.com/docling-project/docling
@@ -439,6 +454,7 @@ texts:
   formatting:
     bold: true
     italic: false
+    script: baseline
     strikethrough: false
     underline: false
   label: list_item
@@ -475,6 +491,7 @@ texts:
   formatting:
     bold: false
     italic: true
+    script: baseline
     strikethrough: false
     underline: false
   label: text
@@ -498,6 +515,7 @@ texts:
   formatting:
     bold: false
     italic: true
+    script: baseline
     strikethrough: false
     underline: false
   label: title
@@ -524,6 +542,7 @@ texts:
   formatting:
     bold: false
     italic: true
+    script: baseline
     strikethrough: false
     underline: false
   label: code
@@ -550,6 +569,7 @@ texts:
   formatting:
     bold: false
     italic: true
+    script: baseline
     strikethrough: false
     underline: false
   label: text
@@ -600,13 +620,50 @@ texts:
   prov: []
   self_ref: '#/texts/40'
   text: '& ampersand'
+- children: []
+  content_layer: body
+  label: text
+  orig: A hyperlink on
+  parent:
+    $ref: '#/groups/10'
+  prov: []
+  self_ref: '#/texts/41'
+  text: A hyperlink on
+- captions: []
+  children: []
+  code_language: unknown
+  content_layer: body
+  footnotes: []
+  hyperlink: '#link'
+  label: code
+  orig: code in a line
+  parent:
+    $ref: '#/groups/10'
+  prov: []
+  references: []
+  self_ref: '#/texts/42'
+  text: code in a line
+- captions: []
+  children: []
+  code_language: unknown
+  content_layer: body
+  footnotes: []
+  hyperlink: '#test'
+  label: code
+  orig: A hyperlink on code as paragraph 
+  parent:
+    $ref: '#/body'
+  prov: []
+  references: []
+  self_ref: '#/texts/43'
+  text: A hyperlink on code as paragraph
 - children: []
   content_layer: body
   label: text
   orig: The end.
   parent:
     $ref: '#/body'
   prov: []
-  self_ref: '#/texts/41'
+  self_ref: '#/texts/44'
   text: The end.
-version: 1.3.0
+version: 1.8.0