mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-03 07:05:20 +00:00
5291a96616
* Add `AzureBlobStorageConnector` based on its `fsspec` implementation inheriting from `FsspecConnector` * Start deprecation life cycle for `unstructured-ingest --s3-url` option, to be deprecated in favor of `--remote-url`. --------- Co-authored-by: Tom Aarsen <37621491+tomaarsen@users.noreply.github.com>
17 lines
476 B
Bash
Executable File
17 lines
476 B
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
SCRIPT_DIR=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" &>/dev/null && pwd)
|
|
cd "$SCRIPT_DIR"/.. || exit 1
|
|
|
|
PYTHONPATH=. ./unstructured/ingest/main.py \
|
|
--remote-url abfs://container1/ \
|
|
--azure-account-name azureunstructured1 \
|
|
--structured-output-dir azure-ingest-output \
|
|
--num-processes 2
|
|
|
|
if [ "$(find 'azure-ingest-output' -type f -printf '.' | wc -c)" -ne 5 ]; then
|
|
echo
|
|
echo "5 files should have been created."
|
|
exit 1
|
|
fi
|