From 4d6492391c1ad6f3eefd274303b0587f6c2dd24e Mon Sep 17 00:00:00 2001 From: Roman Isecke <136338424+rbiseck3@users.noreply.github.com> Date: Mon, 2 Oct 2023 11:31:15 -0400 Subject: [PATCH] roman/update language kwarg partition ingest (#1605) ### Description Change partition kwarg from ocr_languages -> languages Closes out https://github.com/Unstructured-IO/unstructured/issues/1588 --- CHANGELOG.md | 2 +- unstructured/__version__.py | 2 +- unstructured/ingest/processor.py | 3 ++- 3 files changed, 4 insertions(+), 3 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 264cf9f44..a4e877127 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,4 +1,4 @@ -## 0.10.19-dev1 +## 0.10.19-dev2 ### Enhancements diff --git a/unstructured/__version__.py b/unstructured/__version__.py index 2b9078795..bfddceeb0 100644 --- a/unstructured/__version__.py +++ b/unstructured/__version__.py @@ -1 +1 @@ -__version__ = "0.10.19-dev1" # pragma: no cover +__version__ = "0.10.19-dev2" # pragma: no cover diff --git a/unstructured/ingest/processor.py b/unstructured/ingest/processor.py index a133b7273..a91fc671b 100644 --- a/unstructured/ingest/processor.py +++ b/unstructured/ingest/processor.py @@ -107,10 +107,11 @@ def process_documents( verbose: bool, dest_doc_connector: t.Optional[BaseDestinationConnector] = None, ) -> None: + languages = partition_config.ocr_languages.split("+") if partition_config.ocr_languages else [] process_document_with_partition_args = partial( process_document, strategy=partition_config.strategy, - ocr_languages=partition_config.ocr_languages, + languages=languages, encoding=partition_config.encoding, pdf_infer_table_structure=partition_config.pdf_infer_table_structure, )