mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-11-02 11:03:38 +00:00
830d67f653
* Initial commit of discord connector based off of initial work by @tnachen with modifications https://github.com/tnachen/unstructured/tree/tnachen/discord_connector * Add test file change format of imports * working version of the connector More work to be done to tidy it up and add any additional options * add to test fixtures update * fix spacing * tests working, switching to bot testing channel * add additional channel add reprocess to tests * add try clause to allow for exit on error Update changelog and bump version * add updated expected output filtes * add logic to check if —discord-period is an integer Add more to option description * fix lint error * Update discord reqs * PR feedback * add newline * another newline --------- Co-authored-by: Justin Bossert <packerbacker21@hotmail.com>
47 lines
1.5 KiB
Bash
Executable File
47 lines
1.5 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
set -e
|
|
|
|
SCRIPT_DIR=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" &>/dev/null && pwd)
|
|
cd "$SCRIPT_DIR"/.. || exit 1
|
|
|
|
if [ -z "$SLACK_TOKEN" ]; then
|
|
echo "Skipping Slack ingest test because the SLACK_TOKEN env var is not set."
|
|
exit 0
|
|
fi
|
|
|
|
PYTHONPATH=. ./unstructured/ingest/main.py \
|
|
--slack-channels C052BGT7718 \
|
|
--slack-token "${SLACK_TOKEN}" \
|
|
--download-dir slack-ingest-download \
|
|
--structured-output-dir slack-ingest-output \
|
|
--partition-strategy hi_res \
|
|
--start-date 2023-04-01 \
|
|
--end-date 2023-04-08T12:00:00-08:00 \
|
|
--reprocess
|
|
|
|
OVERWRITE_FIXTURES=${OVERWRITE_FIXTURES:-false}
|
|
|
|
set +e
|
|
|
|
# to update ingest test fixtures, run scripts/ingest-test-fixtures-update.sh on x86_64
|
|
if [[ "$OVERWRITE_FIXTURES" != "false" ]]; then
|
|
|
|
cp slack-ingest-output/* test_unstructured_ingest/expected-structured-output/slack-ingest-channel/
|
|
|
|
elif ! diff -ru slack-ingest-output test_unstructured_ingest/expected-structured-output/slack-ingest-channel; then
|
|
echo
|
|
echo "There are differences from the previously checked-in structured outputs."
|
|
echo
|
|
echo "If these differences are acceptable, overwrite by the fixtures by setting the env var:"
|
|
echo
|
|
echo " export OVERWRITE_FIXTURES=true"
|
|
echo
|
|
echo "and then rerun this script."
|
|
echo
|
|
echo "NOTE: You'll likely just want to run scripts/ingest-test-fixtures-update.sh on x86_64 hardware"
|
|
echo "to update fixtures for CI."
|
|
echo
|
|
exit 1
|
|
fi
|