yujunjun/unstructured
1
0
Fork 0
mirror of https://github.com/Unstructured-IO/unstructured.git synced 2025-11-30 17:20:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

roman/update language kwarg partition ingest (#1605)

Browse Source 
### Description
Change partition kwarg from ocr_languages -> languages

Closes out https://github.com/Unstructured-IO/unstructured/issues/1588
This commit is contained in:
Roman Isecke 2023-10-02 11:31:15 -04:00 committed by GitHub
parent ad59a879cc
commit 4d6492391c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
CHANGELOG.md
View File

@ -1,4 +1,4 @@
## 0.10.19-dev1 ## 0.10.19-dev2
### Enhancements ### Enhancements

2
unstructured/__version__.py
View File

@ -1 +1 @@
__version__ = "0.10.19-dev1" # pragma: no cover __version__ = "0.10.19-dev2" # pragma: no cover

3
unstructured/ingest/processor.py
View File

@ -107,10 +107,11 @@ def process_documents(
verbose: bool, verbose: bool,
dest_doc_connector: t.Optional[BaseDestinationConnector] = None, dest_doc_connector: t.Optional[BaseDestinationConnector] = None,
) -> None: ) -> None:
languages = partition_config.ocr_languages.split("+") if partition_config.ocr_languages else []
process_document_with_partition_args = partial( process_document_with_partition_args = partial(
process_document, process_document,
strategy=partition_config.strategy, strategy=partition_config.strategy,
ocr_languages=partition_config.ocr_languages, languages=languages,
encoding=partition_config.encoding, encoding=partition_config.encoding,
pdf_infer_table_structure=partition_config.pdf_infer_table_structure, pdf_infer_table_structure=partition_config.pdf_infer_table_structure,
) )