mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-24 17:41:15 +00:00
8683e2695c
* initial pass on text in figures * refactor text extraction * update tests * fix title test * add test for docs that require recursive text grab * version and changelog * ingest-test-fixtures-update * there are 8 pdf files now
24 lines
539 B
Bash
Executable File
24 lines
539 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 \
|
|
--partition-strategy hi_res \
|
|
--verbose \
|
|
--reprocess
|
|
|
|
set +e
|
|
|
|
if [ "$(find 'api-ingest-output' -type f -printf '.' | wc -c)" != 8 ]; then
|
|
echo
|
|
echo "8 files should have been created."
|
|
exit 1
|
|
fi
|