mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-27 04:24:45 +00:00
Add standalone equations as DocItem formula
Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
This commit is contained in:
parent
f5034944b8
commit
c7289f647a
@ -242,8 +242,8 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
|
||||
def handle_text_elements(self, element, docx_obj, doc):
|
||||
paragraph = docx.text.paragraph.Paragraph(element, docx_obj)
|
||||
|
||||
text = paragraph.text
|
||||
text = self.handle_equations_in_text(element=element, text=text)
|
||||
raw_text = paragraph.text
|
||||
text = self.handle_equations_in_text(element=element, text=raw_text)
|
||||
|
||||
if text is None:
|
||||
return
|
||||
@ -281,21 +281,20 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
|
||||
self.parents[key] = None
|
||||
self.level = self.level_at_new_list - 1
|
||||
self.level_at_new_list = None
|
||||
|
||||
if p_style_id in ["Title"]:
|
||||
for key, val in self.parents.items():
|
||||
self.parents[key] = None
|
||||
self.parents[0] = doc.add_text(
|
||||
parent=None, label=DocItemLabel.TITLE, text=text
|
||||
)
|
||||
|
||||
elif "Heading" in p_style_id:
|
||||
self.add_header(element, docx_obj, doc, p_style_id, p_level, text)
|
||||
|
||||
elif p_style_id in [
|
||||
"Paragraph",
|
||||
"Normal",
|
||||
"Subtitle",
|
||||
"Author",
|
||||
"DefaultText",
|
||||
"ListParagraph",
|
||||
"ListBullet",
|
||||
"Quote",
|
||||
@ -305,12 +304,32 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
|
||||
label=DocItemLabel.PARAGRAPH, parent=self.parents[level - 1], text=text
|
||||
)
|
||||
|
||||
elif (raw_text is None or len(raw_text) == 0) and len(text) > 0:
|
||||
# Standalone equation
|
||||
# Entities in which all text comes from equations
|
||||
level = self.get_level()
|
||||
if text.strip().startswith("$") and text.strip().endswith("$"):
|
||||
text = text.strip()[1:-1]
|
||||
doc.add_text(
|
||||
label=DocItemLabel.FORMULA, parent=self.parents[level - 1], text=text
|
||||
)
|
||||
|
||||
elif p_style_id in [
|
||||
"Paragraph",
|
||||
"Normal",
|
||||
"DefaultText",
|
||||
]:
|
||||
level = self.get_level()
|
||||
doc.add_text(
|
||||
label=DocItemLabel.PARAGRAPH, parent=self.parents[level - 1], text=text
|
||||
)
|
||||
|
||||
else:
|
||||
# Text style names can, and will have, not only default values but user values too
|
||||
# hence we treat all other labels as pure text
|
||||
level = self.get_level()
|
||||
doc.add_text(
|
||||
label=DocItemLabel.PARAGRAPH, parent=self.parents[level - 1], text=text
|
||||
label=DocItemLabel.TEXT, parent=self.parents[level - 1], text=text
|
||||
)
|
||||
self.update_history(p_style_id, p_level, numid, ilevel)
|
||||
return
|
||||
|
Loading…
Reference in New Issue
Block a user