Files
unstructured-io--unstructured/test_unstructured_ingest/src/local-single-file-basic-chunking.sh
T
wehub-resource-sync 461bf6fd40
CI / lint (3.11) (push) Has been cancelled
CI / lint (3.12) (push) Has been cancelled
CI / lint (3.13) (push) Has been cancelled
CI / shellcheck (push) Has been cancelled
CI / shfmt (push) Has been cancelled
CI / setup (3.11) (push) Has been cancelled
CI / setup (3.12) (push) Has been cancelled
CI / setup (3.13) (push) Has been cancelled
CI / check-licenses (3.12) (push) Has been cancelled
CI / test_unit (3.11) (push) Has been cancelled
CI / test_unit (3.12) (push) Has been cancelled
CI / test_unit (3.13) (push) Has been cancelled
CI / test_unit_no_extras (3.11) (push) Has been cancelled
CI / test_unit_no_extras (3.12) (push) Has been cancelled
CI / test_json_to_html (3.12) (push) Has been cancelled
CI / test_unit_no_extras (3.13) (push) Has been cancelled
CI / test_unit_dependency_extras (csv, 3.12, --extra csv) (push) Has been cancelled
CI / test_unit_dependency_extras (xlsx, 3.11, --extra xlsx) (push) Has been cancelled
CI / test_unit_dependency_extras (xlsx, 3.12, --extra xlsx) (push) Has been cancelled
CI / test_unit_dependency_extras (csv, 3.11, --extra csv) (push) Has been cancelled
CI / test_unit_dependency_extras (csv, 3.13, --extra csv) (push) Has been cancelled
CI / test_unit_dependency_extras (docx, 3.11, --extra docx) (push) Has been cancelled
CI / test_unit_dependency_extras (docx, 3.12, --extra docx) (push) Has been cancelled
CI / test_unit_dependency_extras (docx, 3.13, --extra docx) (push) Has been cancelled
CI / test_unit_dependency_extras (markdown, 3.11, --extra md) (push) Has been cancelled
CI / test_unit_dependency_extras (markdown, 3.12, --extra md) (push) Has been cancelled
CI / test_unit_dependency_extras (markdown, 3.13, --extra md) (push) Has been cancelled
CI / test_unit_dependency_extras (odt, 3.11, --extra odt) (push) Has been cancelled
CI / test_unit_dependency_extras (odt, 3.12, --extra odt) (push) Has been cancelled
CI / test_unit_dependency_extras (odt, 3.13, --extra odt) (push) Has been cancelled
CI / test_unit_dependency_extras (pdf-image, 3.11, --extra pdf --extra image --extra paddleocr) (push) Has been cancelled
CI / test_unit_dependency_extras (pdf-image, 3.12, --extra pdf --extra image --extra paddleocr) (push) Has been cancelled
CI / test_unit_dependency_extras (pdf-image, 3.13, --extra pdf --extra image --extra paddleocr) (push) Has been cancelled
CI / test_unit_dependency_extras (pptx, 3.11, --extra pptx) (push) Has been cancelled
CI / test_unit_dependency_extras (pptx, 3.12, --extra pptx) (push) Has been cancelled
CI / test_unit_dependency_extras (pptx, 3.13, --extra pptx) (push) Has been cancelled
CI / test_unit_dependency_extras (pypandoc, 3.11, --extra epub --extra org --extra rtf --extra rst) (push) Has been cancelled
CI / test_unit_dependency_extras (pypandoc, 3.12, --extra epub --extra org --extra rtf --extra rst) (push) Has been cancelled
CI / test_unit_dependency_extras (pypandoc, 3.13, --extra epub --extra org --extra rtf --extra rst) (push) Has been cancelled
Build And Push Docker Image / set-short-sha (push) Has been cancelled
Partition Benchmark / setup (push) Has been cancelled
Partition Benchmark / Measure and compare partition() runtime (push) Has been cancelled
CI / test_unit_dependency_extras (xlsx, 3.13, --extra xlsx) (push) Has been cancelled
CI / test_ingest_src (3.12) (push) Has been cancelled
CI / test_json_to_markdown (3.12) (push) Has been cancelled
CI / changelog (push) Has been cancelled
CI / test_dockerfile (push) Has been cancelled
CodeQL / Analyze (python) (push) Has been cancelled
Build And Push Docker Image / build-images (linux/amd64, opensource-linux-8core) (push) Has been cancelled
Build And Push Docker Image / build-images (linux/arm64, ubuntu-24.04-arm) (push) Has been cancelled
Build And Push Docker Image / publish-images (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 13:33:56 +08:00

55 lines
1.7 KiB
Bash
Executable File

#!/usr/bin/env bash
# shellcheck disable=SC2329 # Functions are invoked indirectly
set -e
SRC_PATH=$(dirname "$(realpath "$0")")
SCRIPT_DIR=$(dirname "$SRC_PATH")
cd "$SCRIPT_DIR"/.. || exit 1
OUTPUT_FOLDER_NAME=local-single-file-basic-chunking
OUTPUT_ROOT=${OUTPUT_ROOT:-$SCRIPT_DIR}
OUTPUT_DIR=$OUTPUT_ROOT/structured-output/$OUTPUT_FOLDER_NAME
WORK_DIR=$OUTPUT_ROOT/workdir/$OUTPUT_FOLDER_NAME
# -- use absolute path of input file to verify passing an absolute path --
ABS_INPUT_PATH="$SCRIPT_DIR/../example-docs/handbook-1p.docx"
max_processes=${MAX_PROCESSES:=$(python3 -c "import os; print(os.cpu_count())")}
# shellcheck disable=SC1091
source "$SCRIPT_DIR"/cleanup.sh
# shellcheck disable=SC2317
function cleanup() {
cleanup_dir "$OUTPUT_DIR"
cleanup_dir "$WORK_DIR"
}
trap cleanup EXIT
RUN_SCRIPT=${RUN_SCRIPT:-unstructured-ingest}
PYTHONPATH=${PYTHONPATH:-.} "$RUN_SCRIPT" \
local \
--chunking-strategy basic \
--chunk-overlap 20 \
--chunk-max-characters 150 \
--input-path "$ABS_INPUT_PATH" \
--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 \
--num-processes "$max_processes" \
--reprocess \
--verbose \
--work-dir "$WORK_DIR" \
local \
--output-dir "$OUTPUT_DIR"
set +e
"$SCRIPT_DIR"/check-diff-expected-output.sh $OUTPUT_FOLDER_NAME
EXIT_CODE=$?
set -e
if [ "$EXIT_CODE" -ne 0 ]; then
echo "The last script run exited with a non-zero exit code: $EXIT_CODE."
# Handle the error or exit
fi
"$SCRIPT_DIR"/evaluation-ingest-cp.sh "$OUTPUT_DIR" "$OUTPUT_FOLDER_NAME"
exit $EXIT_CODE