Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 18 additions & 1 deletion src/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -26742,7 +26742,24 @@ def deprecated_function( *args, **kwargs):
f'Python {sys.version_info[0]}.{sys.version_info[1]} running on {sys.platform} ({64 if sys.maxsize > 2**32 else 32}-bit).\n'
)


def _to_markdown(*args, **kwargs):
return pymupdf4llm.to_markdown(*args, **kwargs)
def _to_text(*args, **kwargs):
return pymupdf4llm.to_text(*args, **kwargs)
def _to_json(*args, **kwargs):
return pymupdf4llm.to_json(*args, **kwargs)
def _to_chunks(*args, **kwargs):
return pymupdf4llm.to_chunks(*args, **kwargs)
def _convert_batch(*args, **kwargs):
return pymupdf4llm.convert_batch(*args, **kwargs)

try:
import pymupdf4llm # noqa: F401
except ImportError:
Document.to_markdown = _to_markdown # noqa: F401
Document.to_text = _to_text # noqa: F401
Document.to_json = _to_json # noqa: F401
Document.to_chunks = _to_chunks # noqa: F401
convert_batch = _convert_batch # noqa: F401
except (ImportError, ModuleNotFoundError):
pass
30 changes: 30 additions & 0 deletions tests/test_configurations.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,30 @@
import pymupdf
import pathlib
import util


def test_configuration_layout():
if not util._use_layout() :
print("not testing: layout feature not available")
return

doc = pymupdf.open()
page = doc.new_page()
page.insert_text((72, 72), "Hallo Welt!\nSeid umschlungen, Millionen!")

out1 = doc.to_markdown()
out2 = pymupdf.pymupdf4llm.to_markdown(doc)
assert out1 == out2

out1 = doc.to_text()
out2 = pymupdf.pymupdf4llm.to_text(doc)
assert out1 == out2

out1 = doc.to_chunks()
out2 = pymupdf.pymupdf4llm.to_chunks(doc)
assert repr(out1) == repr(out2), f"{out1=} != {out2=}"

out1 = doc.to_json()
out2 = pymupdf.pymupdf4llm.to_json(doc)
assert out1 == out2

Loading