mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-26 20:14:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

Remove ignores for typing/linting

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer 2025-07-25 12:37:55 +02:00
parent 02a7deb882
commit e6d5e4e48f
1 changed files with 6 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
docling/pipeline/threaded_standard_pdf_pipeline.py
View File

@ -1,5 +1,4 @@
# threaded_standard_pdf_pipeline.py # threaded_standard_pdf_pipeline.py
# pylint: disable=too-many-lines,invalid-name
"""Thread-safe, production-ready PDF pipeline """Thread-safe, production-ready PDF pipeline
================================================ ================================================
A self-contained, thread-safe PDF conversion pipeline exploiting parallelism between pipeline stages and models. A self-contained, thread-safe PDF conversion pipeline exploiting parallelism between pipeline stages and models.
@ -467,7 +466,7 @@ class ThreadedStandardPdfPipeline(BasePipeline):
return RunContext(stages=stages, first_stage=preprocess, output_queue=output_q) return RunContext(stages=stages, first_stage=preprocess, output_queue=output_q)
# --------------------------------------------------------------------- build # --------------------------------------------------------------------- build
def _build_document(self, conv_res: ConversionResult) -> ConversionResult: # type: ignore[override] def _build_document(self, conv_res: ConversionResult) -> ConversionResult:
"""Stream-build the document while interleaving producer and consumer work.""" """Stream-build the document while interleaving producer and consumer work."""
run_id = next(self._run_seq) run_id = next(self._run_seq)
assert isinstance(conv_res.input._backend, PdfDocumentBackend) assert isinstance(conv_res.input._backend, PdfDocumentBackend)
@ -572,7 +571,7 @@ class ThreadedStandardPdfPipeline(BasePipeline):
p._backend.unload() p._backend.unload()
# ---------------------------------------------------------------- assemble # ---------------------------------------------------------------- assemble
def _assemble_document(self, conv_res: ConversionResult) -> ConversionResult: # type: ignore[override] def _assemble_document(self, conv_res: ConversionResult) -> ConversionResult:
elements, headers, body = [], [], [] elements, headers, body = [], [], []
with TimeRecorder(conv_res, "doc_assemble", scope=ProfilingScope.DOCUMENT): with TimeRecorder(conv_res, "doc_assemble", scope=ProfilingScope.DOCUMENT):
for p in conv_res.pages: for p in conv_res.pages:
@ -588,17 +587,17 @@ class ThreadedStandardPdfPipeline(BasePipeline):
# ---------------------------------------------------------------- misc # ---------------------------------------------------------------- misc
@classmethod @classmethod
def get_default_options(cls) -> ThreadedPdfPipelineOptions: # type: ignore[override] def get_default_options(cls) -> ThreadedPdfPipelineOptions:
return ThreadedPdfPipelineOptions() return ThreadedPdfPipelineOptions()
@classmethod @classmethod
def is_backend_supported(cls, backend: AbstractDocumentBackend) -> bool: # type: ignore[override] def is_backend_supported(cls, backend: AbstractDocumentBackend) -> bool:
return isinstance(backend, PdfDocumentBackend) return isinstance(backend, PdfDocumentBackend)
def _determine_status(self, conv_res: ConversionResult) -> ConversionStatus: # type: ignore[override] def _determine_status(self, conv_res: ConversionResult) -> ConversionStatus:
return conv_res.status return conv_res.status
def _unload(self, conv_res: ConversionResult) -> None: # type: ignore[override] def _unload(self, conv_res: ConversionResult) -> None:
for p in conv_res.pages: for p in conv_res.pages:
if p._backend is not None: if p._backend is not None:
p._backend.unload() p._backend.unload()