LLM/docling-serve
1
0
Fork 0
mirror of https://github.com/docling-project/docling-serve.git synced 2025-12-02 10:03:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: Expose more conversion options (#142)

Browse Source 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi
2025-04-22 10:41:47 +02:00
committed by GitHub
parent b598872e5c
commit 6b3d281f02
8 changed files with 1058 additions and 930 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/test_1-url-all-outputs.py
View File

@@ -93,9 +93,9 @@ async def test_convert_url(async_client):
)
if data.get("document", {}).get("html_content") is not None:
check.is_in(
'<!DOCTYPE html>\n<html lang="en">\n<head>',
"<!DOCTYPE html>\n<html>\n<head>",
data["document"]["html_content"],
msg=f"HTML document should contain '<!DOCTYPE html>\\n<html lang=\"en'>. Received: {safe_slice(data['document']['html_content'])}",
msg=f"HTML document should contain '<!DOCTYPE html>\\n<html>'. Received: {safe_slice(data['document']['html_content'])}",
)
# Text check
check.is_in(
@@ -117,7 +117,7 @@ async def test_convert_url(async_client):
)
if data.get("document", {}).get("doctags_content") is not None:
check.is_in(
"<document>\n<section_header_level_1><location>",
"<doctag><page_header><loc",
data["document"]["doctags_content"],
msg=f"DocTags document should contain '<document>\\n<section_header_level_1><location>'. Received: {safe_slice(data['document']['doctags_content'])}",
msg=f"DocTags document should contain '<doctag><page_header><loc'. Received: {safe_slice(data['document']['doctags_content'])}",
)