mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-09-15 03:27:40 +00:00
62e20442df
- Adds reusable validation scripts (check-x.sh) to minimize repeated (or near-repeated) code and create one source of truth - Restructures the location of download and output folders such that they are nested in the test_unstructured_ingest directory - Adds gitignore for output folders / files to avoid them accidentally getting checked into the repository - Construct paths as reusable variables declared at top of scripts - Sort order of flag for ingest calls, across all tests (this makes it easier to parse at a glance) - OVERWRITE_FIXTURES removes all old fixtures for path to guarantee no stale results are left behind - Bonus: don't check/exit on expected number of expected outputs when OVERWRITE_FIXTURES is true - Bonus: exclude file_directory from Slack and Discord test scripts (match convention in all others)
37 lines
1.3 KiB
Bash
Executable File
37 lines
1.3 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
set -e
|
|
|
|
SCRIPT_DIR=$(dirname "$(realpath "$0")")
|
|
cd "$SCRIPT_DIR"/.. || exit 1
|
|
OUTPUT_FOLDER_NAME=github
|
|
OUTPUT_DIR=$SCRIPT_DIR/structured-output/$OUTPUT_FOLDER_NAME
|
|
DOWNLOAD_DIR=$SCRIPT_DIR/download/$OUTPUT_FOLDER_NAME
|
|
|
|
GH_READ_ONLY_ACCESS_TOKEN=${GH_READ_ONLY_ACCESS_TOKEN:-none}
|
|
|
|
ACCESS_TOKEN_FLAGS=""
|
|
# to update test fixtures, "export OVERWRITE_FIXTURES=true" and rerun this script
|
|
if [[ "$GH_READ_ONLY_ACCESS_TOKEN" != "none" ]]; then
|
|
ACCESS_TOKEN_FLAGS="--git-access-token $GH_READ_ONLY_ACCESS_TOKEN"
|
|
elif [[ "$CI" == "true" ]]; then
|
|
echo "Warning: GH_READ_ONLY_ACCESS_TOKEN is not defined in the CI environment."
|
|
echo "This can lead to intermittent failures in test-ingest-github.sh, as non-auth'ed"
|
|
echo "requests are severely rate limited by GitHub."
|
|
echo
|
|
fi
|
|
|
|
#shellcheck disable=SC2086
|
|
PYTHONPATH=. ./unstructured/ingest/main.py \
|
|
--download-dir "$DOWNLOAD_DIR" \
|
|
--git-file-glob '*.html,*.txt' \
|
|
--github-url dcneiner/Downloadify \
|
|
--metadata-exclude filename,file_directory,metadata.data_source.date_processed \
|
|
--partition-strategy hi_res \
|
|
--preserve-downloads \
|
|
--reprocess \
|
|
--structured-output-dir "$OUTPUT_DIR" \
|
|
--verbose $ACCESS_TOKEN_FLAGS
|
|
|
|
sh "$SCRIPT_DIR"/check-diff-expected-output.sh $OUTPUT_FOLDER_NAME
|