From e147ae63a5477768ea4cea533f997faed0fca2ce Mon Sep 17 00:00:00 2001
From: Vik Paruchuri <vik.paruchuri@gmail.com>
Date: Fri, 24 Jan 2025 17:03:15 -0500
Subject: [PATCH] Fix span id issue

---
 marker/renderers/markdown.py     | 8 +++++---
 pyproject.toml                   | 2 +-
 tests/builders/test_pdf_links.py | 4 ++--
 3 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/marker/renderers/markdown.py b/marker/renderers/markdown.py
index fef44e30..0762ab3c 100644
--- a/marker/renderers/markdown.py
+++ b/marker/renderers/markdown.py
@@ -168,11 +168,13 @@ def convert_table(self, el, text, convert_as_inline):
     def convert_a(self, el, text, convert_as_inline):
         text = self.escape(text)
         text = re.sub(r"([\[\]])", r"\\\1", text)
-        return super().convert_a(el, self.escape(text), convert_as_inline)
+        return super().convert_a(el, text, convert_as_inline)
 
     def convert_span(self, el, text, convert_as_inline):
-        return f'<span id="{el["id"]}"/>'
-
+        if el.get("id"):
+            return f'<span id="{el["id"]}">{text}</span>'
+        else:
+            return text
 
 class MarkdownOutput(BaseModel):
     markdown: str
diff --git a/pyproject.toml b/pyproject.toml
index 1c647961..0377a77a 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "marker-pdf"
-version = "1.3.1"
+version = "1.3.2"
 description = "Convert PDF to markdown with high speed and accuracy."
 authors = ["Vik Paruchuri <github@vikas.sh>"]
 readme = "README.md"
diff --git a/tests/builders/test_pdf_links.py b/tests/builders/test_pdf_links.py
index c639c59e..300a7579 100644
--- a/tests/builders/test_pdf_links.py
+++ b/tests/builders/test_pdf_links.py
@@ -29,7 +29,7 @@ def test_pdf_links(pdf_document: Document, pdf_converter: PdfConverter, temp_pdf
     markdown = markdown_output.markdown
 
     assert '[II.](#page-1-0)' in markdown
-    assert '<span id="page-1-0"/>II. THEORETICAL FRAMEWORK' in markdown
+    assert '<span id="page-1-0"></span>II. THEORETICAL FRAMEWORK' in markdown
 
-    for ref in set([f'<span id="page-{m[0]}-{m[1]}"/>' for m in re.findall(r'\]\(#page-(\d+)-(\d+)\)', markdown)]):
+    for ref in set([f'<span id="page-{m[0]}-{m[1]}">' for m in re.findall(r'\]\(#page-(\d+)-(\d+)\)', markdown)]):
         assert ref in markdown, f"Reference {ref} not found in markdown"