mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-08-12 18:54:17 +00:00
894a190001
* function to check if pdf is extractable * add fallback logic for unextractable pdfs * tests for docs with copy protection * add test for unprocessable pdf * update docs * changelog and version * update logic for images; reset file before proceeding * 3 files for api tests * docs update
23 lines
505 B
Bash
Executable File
23 lines
505 B
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
set -e
|
|
|
|
SCRIPT_DIR=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" &>/dev/null && pwd)
|
|
cd "$SCRIPT_DIR"/.. || exit 1
|
|
|
|
PYTHONPATH=. ./unstructured/ingest/main.py \
|
|
--local-input-path example-docs \
|
|
--local-file-glob "*.pdf" \
|
|
--structured-output-dir api-ingest-output \
|
|
--partition-by-api \
|
|
--verbose \
|
|
--reprocess
|
|
|
|
set +e
|
|
|
|
if [ "$(find 'api-ingest-output' -type f -printf '.' | wc -c)" != 3 ]; then
|
|
echo
|
|
echo "3 files should have been created."
|
|
exit 1
|
|
fi
|