Skip to content

Papermark is the open-source DocSend alternative and secure data rooms with built-in analytics and custom domains.

Preserve original paragraph properties in NUMPAGES field fix

Cursor Agentad105d41cd20
diff --git a/ee/features/conversions/python/docx-sanitizer.py b/ee/features/conversions/python/docx-sanitizer.py
index e038b70a..8df7c3bb 100644
--- a/ee/features/conversions/python/docx-sanitizer.py
+++ b/ee/features/conversions/python/docx-sanitizer.py
@@ -101,6 +101,8 @@ NUMPAGES_FIELD_RE = re.compile(
)
PARA_RE = re.compile(r'<w:p[\s>].*?</w:p>', re.DOTALL)
+PPR_RE = re.compile(r'<w:pPr\b[^>]*/>', re.DOTALL)
+PPR_BLOCK_RE = re.compile(r'<w:pPr\b.*?</w:pPr>', re.DOTALL)
def strip_numpages_fields_in_hf(tmp_dir: str) -> int:
@@ -132,7 +134,9 @@ def strip_numpages_fields_in_hf(tmp_dir: str) -> int:
para = m.group(0)
if NUMPAGES_FIELD_RE.search(para):
count += 1
- return '<w:p><w:pPr><w:pStyle w:val="Footer"/></w:pPr></w:p>'
+ ppr = PPR_BLOCK_RE.search(para) or PPR_RE.search(para)
+ ppr_xml = ppr.group(0) if ppr else '<w:pPr/>'
+ return f'<w:p>{ppr_xml}</w:p>'
return para
new_content = PARA_RE.sub(_replace_para, content)