mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-08-01 15:02:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Improvements in md parsing

Browse Source 
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maksym Lysak 2024-10-18 16:58:22 +02:00
parent 534b2203f6
commit bef429fee3
1 changed files with 25 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
docling/backend/md_backend.py
View File

@ -129,7 +129,31 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
parent=parent_element,
caption=element.title
)
elif isinstance(element, marko.inline.RawText):
print(f" - Paragraph (raw text): {element.children}")
snippet_text = str(element.children)
doc.add_text(
label=DocItemLabel.PARAGRAPH,
parent=parent_element,
text=snippet_text
)
elif isinstance(element, marko.inline.CodeSpan):
print(f" - Paragraph (code): {element.children}")
snippet_text = str(element.children)
doc.add_text(
label=DocItemLabel.PARAGRAPH,
parent=parent_element,
text=snippet_text
)
else:
if not isinstance(element, str):
print("Something else: {}".format(element))
# print(element)
# elif isinstance(element, marko.block.Table):
# print(" - Table")
# elif isinstance(element, marko.block.Table):
# print(" - Table")