mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-12-04 03:00:24 +00:00
1c519efef5
Main Changes: 1. Removed Clarifai Dependency - Completely removed the clarifai dependency which is no longer used in the codebase - Removed clarifai from the unstructured-ingest extras list in requirements/ingest/ingest.txt:1 - Removed clarifai test script reference from test_unstructured_ingest/test-ingest-dest.sh:23 2. Updated Dependencies to Resolve CVEs - pypdf: Updated from 6.1.1 → 6.1.3 (fixes GHSA-vr63-x8vc-m265) - pip: Added explicit upgrade to >=25.3 in Dockerfile (fixes GHSA-4xh5-x5gv-qwph) - uv: Addressed GHSA-8qf3-x8v5-2pj8 and GHSA-pqhf-p39g-3x64 3. Dockerfile Security Enhancements (Dockerfile:17,28-29) - Added Alpine package upgrade for py3.12-pip - Added explicit pip upgrade step before installing Python dependencies 4. General Dependency Updates Ran pip-compile across all requirement files, resulting in updates to: - cryptography: 46.0.2 → 46.0.3 - psutil: 7.1.0 → 7.1.3 - rapidfuzz: 3.14.1 → 3.14.3 - regex: 2025.9.18 → 2025.11.3 - wrapt: 1.17.3 → 2.0.0 - Plus many other transitive dependencies across all extra requirement files 5. Version Bump - Updated version from 0.18.16 → 0.18.17 in unstructured/__version__.py:1 - Updated CHANGELOG.md with security fixes documentation Impact: This PR resolves 4 CVEs total without introducing breaking changes, making it a pure security maintenance release. --------- Co-authored-by: Claude <noreply@anthropic.com>
92 lines
2.2 KiB
Bash
Executable File
92 lines
2.2 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
set -u -o pipefail
|
|
|
|
SCRIPT_DIR=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" &>/dev/null && pwd)
|
|
SKIPPED_FILES_LOG=$SCRIPT_DIR/skipped-files.txt
|
|
# If the file already exists, reset it
|
|
if [ -f "$SKIPPED_FILES_LOG" ]; then
|
|
rm "$SKIPPED_FILES_LOG"
|
|
fi
|
|
touch "$SKIPPED_FILES_LOG"
|
|
cd "$SCRIPT_DIR"/.. || exit 1
|
|
|
|
# NOTE(crag): sets number of tesseract threads to 1 which may help with more reproducible outputs
|
|
export OMP_THREAD_LIMIT=1
|
|
|
|
all_tests=(
|
|
'astradb.sh'
|
|
'azure.sh'
|
|
'azure-cognitive-search.sh'
|
|
'box.sh'
|
|
'chroma.sh'
|
|
'delta-table.sh'
|
|
'dropbox.sh'
|
|
'elasticsearch.sh'
|
|
'gcs.sh'
|
|
'kafka-local.sh'
|
|
'mongodb.sh'
|
|
'opensearch.sh'
|
|
'pgvector.sh'
|
|
'pinecone.sh'
|
|
'qdrant.sh'
|
|
's3.sh'
|
|
'sharepoint-embed-cog-index.sh'
|
|
'sqlite.sh'
|
|
'vectara.sh'
|
|
'singlestore.sh'
|
|
'weaviate.sh'
|
|
'databricks-volumes.sh'
|
|
)
|
|
|
|
full_python_matrix_tests=(
|
|
'azure.sh'
|
|
'gcs.sh'
|
|
's3.sh'
|
|
)
|
|
|
|
CURRENT_TEST="none"
|
|
|
|
function print_last_run() {
|
|
if [ "$CURRENT_TEST" != "none" ]; then
|
|
echo "Last ran script: $CURRENT_TEST"
|
|
fi
|
|
echo "######## SKIPPED TESTS: ########"
|
|
cat "$SKIPPED_FILES_LOG"
|
|
}
|
|
|
|
trap print_last_run EXIT
|
|
|
|
python_version=$(python --version 2>&1)
|
|
|
|
tests_to_ignore=(
|
|
'notion.sh'
|
|
'dropbox.sh'
|
|
'sharepoint.sh'
|
|
'databricks-volumes.sh'
|
|
'vectara.sh'
|
|
)
|
|
|
|
for test in "${all_tests[@]}"; do
|
|
CURRENT_TEST="$test"
|
|
# IF: python_version is not 3.10 (wildcarded to match any subminor version) AND the current test is not in full_python_matrix_tests
|
|
# Note: to test we expand the full_python_matrix_tests array to a string and then regex match the current test
|
|
if [[ "$python_version" != "Python 3.10"* ]] && [[ ! "${full_python_matrix_tests[*]}" =~ $test ]]; then
|
|
echo "--------- SKIPPING SCRIPT $test ---------"
|
|
continue
|
|
fi
|
|
echo "--------- RUNNING SCRIPT $test ---------"
|
|
echo "Running ./test_unstructured_ingest/$test"
|
|
./test_unstructured_ingest/dest/"$test"
|
|
rc=$?
|
|
if [[ $rc -eq 8 ]]; then
|
|
echo "$test (skipped due to missing env var)" | tee -a "$SKIPPED_FILES_LOG"
|
|
elif [[ "${tests_to_ignore[*]}" =~ $test ]]; then
|
|
echo "$test (skipped checking error code: $rc)" | tee -a "$SKIPPED_FILES_LOG"
|
|
continue
|
|
elif [[ $rc -ne 0 ]]; then
|
|
exit $rc
|
|
fi
|
|
echo "--------- FINISHED SCRIPT $test ---------"
|
|
done
|