mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-10-28 00:23:09 +00:00
db766402a4
This PR resolves [CORE-2453](https://unstructured-ai.atlassian.net/browse/CORE-2453): - parametrizes the output folder so that ingest output files can be saved other than the same place where the scripts are; this is set by env `OUTPUT_ROOT` - parametrize the python path `PYTHONPATH` to first check existing definition before default to `.`, the current folder - parametrize the run script that carries out ingest using `RUN_SCRIPT`, default is still `./unstructured/ingest/main.py` These changes allows us to run ingest test with more control. To test: - run `OUTPUT_ROOT=/tmp ./test_unstructured_ingest/src/local-single-file.sh`: the output now should be in `/tmp` instead of in the ingest test folder - run `RUN_SCRIPT=/hope/you/do/not/have/this/folder ./test_unstructured_ingest/src/local-single-file.sh` would raise an error because system can't find `/hope/you/do/not/have/this/folder` - run `RUN_SCRIPT=./unstructured/ingest/main.py ./test_unstructured_ingest/src/local-single-file.sh` should run as normal - do the following ```bash cp ./unstructured/ingest/main.py /tmp/main.py OUTPUT_ROOT=/tmp PYTHONPATH=$(pwd) RUN_SCRIPT=./unstructured/ingest/main.py ./test_unstructured_ingest/src/local-single-file.sh ``` This will run and generate output at `/tmp` [CORE-2453]: https://unstructured-ai.atlassian.net/browse/CORE-2453?atlOrigin=eyJpIjoiNWRkNTljNzYxNjVmNDY3MDlhMDU5Y2ZhYzA5YTRkZjUiLCJwIjoiZ2l0aHViLWNvbS1KU1cifQ
41 lines
1.4 KiB
Bash
Executable File
41 lines
1.4 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
set -e
|
|
|
|
SRC_PATH=$(dirname "$(realpath "$0")")
|
|
SCRIPT_DIR=$(dirname "$SRC_PATH")
|
|
cd "$SCRIPT_DIR"/.. || exit 1
|
|
OUTPUT_FOLDER_NAME=local-single-file-with-pdf-infer-table-structure
|
|
OUTPUT_ROOT=${OUTPUT_ROOT:-$SCRIPT_DIR}
|
|
OUTPUT_DIR=$OUTPUT_ROOT/structured-output/$OUTPUT_FOLDER_NAME
|
|
WORK_DIR=$OUTPUT_ROOT/workdir/$OUTPUT_FOLDER_NAME
|
|
max_processes=${MAX_PROCESSES:=$(python3 -c "import os; print(os.cpu_count())")}
|
|
|
|
# shellcheck disable=SC1091
|
|
source "$SCRIPT_DIR"/cleanup.sh
|
|
function cleanup() {
|
|
cleanup_dir "$OUTPUT_DIR"
|
|
cleanup_dir "$WORK_DIR"
|
|
}
|
|
trap cleanup EXIT
|
|
|
|
RUN_SCRIPT=${RUN_SCRIPT:-./unstructured/ingest/main.py}
|
|
PYTHONPATH=${PYTHONPATH:-.} "$RUN_SCRIPT" \
|
|
local \
|
|
--num-processes "$max_processes" \
|
|
--metadata-exclude coordinates,filename,file_directory,metadata.data_source.date_created,metadata.data_source.date_modified,metadata.data_source.date_processed,metadata.last_modified,metadata.detection_class_prob,metadata.parent_id,metadata.category_depth \
|
|
--output-dir "$OUTPUT_DIR" \
|
|
--skip-infer-table-types "xls,xlsx" \
|
|
--pdf-infer-table-structure true \
|
|
--strategy hi_res \
|
|
--verbose \
|
|
--reprocess \
|
|
--input-path "$SCRIPT_DIR"/example-docs/ \
|
|
--work-dir "$WORK_DIR"
|
|
|
|
set +e
|
|
|
|
"$SCRIPT_DIR"/check-diff-expected-output.sh $OUTPUT_FOLDER_NAME
|
|
|
|
"$SCRIPT_DIR"/evaluation-ingest-cp.sh "$OUTPUT_DIR" "$OUTPUT_FOLDER_NAME"
|