mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-11-03 11:34:07 +00:00
0eb461acc2
This PR aims to improve the organization and readability of our example documents used in unit tests, specifically focusing on PDF and image files. ### Summary - Created two new subdirectories in the `example-docs` folder: - `pdf/`: for all PDF example files - `img/`: for all image example files - Moved relevant PDF files from `example-docs/` to `example-docs/pdf/` - Moved relevant image files from `example-docs/` to `example-docs/img/` - Updated file paths in affected unit & ingest tests to reflect the new directory structure ### Testing All unit & ingest tests should be updated and verified to work with the new file structure. ## Notes Other file types (e.g., office documents, HTML files) remain in the root of `example-docs/` for now. ## Next Steps Consider similar reorganization for other file types if this structure proves to be beneficial. --------- Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: christinestraub <christinestraub@users.noreply.github.com>
67 lines
1.8 KiB
Bash
Executable File
67 lines
1.8 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
set -e
|
|
|
|
DEST_PATH=$(dirname "$(realpath "$0")")
|
|
SCRIPT_DIR=$(dirname "$DEST_PATH")
|
|
cd "$SCRIPT_DIR"/.. || exit 1
|
|
OUTPUT_FOLDER_NAME=local-kafka-dest
|
|
OUTPUT_DIR=$SCRIPT_DIR/structured-output/$OUTPUT_FOLDER_NAME
|
|
WORK_DIR=$SCRIPT_DIR/workdir/$OUTPUT_FOLDER_NAME
|
|
max_processes=${MAX_PROCESSES:=$(python3 -c "import os; print(os.cpu_count())")}
|
|
|
|
RANDOM_SUFFIX=$((RANDOM % 100000 + 1))
|
|
|
|
LC_ALL=C
|
|
|
|
# Set the variables with default values if they're not set in the environment
|
|
KAFKA_TOPIC=${KAFKA_TOPIC:-"ingest-test-$RANDOM_SUFFIX"}
|
|
|
|
# shellcheck disable=SC1091
|
|
source "$SCRIPT_DIR"/cleanup.sh
|
|
function cleanup {
|
|
# Local file cleanup
|
|
cleanup_dir "$WORK_DIR"
|
|
cleanup_dir "$OUTPUT_DIR"
|
|
|
|
echo "Stopping local Kafka instance"
|
|
docker-compose -f scripts/kafka-test-helpers/docker-compose.yml down --remove-orphans -v
|
|
}
|
|
|
|
trap cleanup EXIT
|
|
|
|
echo "Creating local Kafka instance"
|
|
# shellcheck source=/dev/null
|
|
scripts/kafka-test-helpers/create-kafka-instance.sh
|
|
wait
|
|
|
|
PYTHONPATH=. ./unstructured/ingest/main.py \
|
|
local \
|
|
--num-processes "$max_processes" \
|
|
--output-dir "$OUTPUT_DIR" \
|
|
--strategy fast \
|
|
--verbose \
|
|
--reprocess \
|
|
--input-path example-docs/pdf/layout-parser-paper.pdf \
|
|
--work-dir "$WORK_DIR" \
|
|
--chunking-strategy basic \
|
|
--chunk-combine-text-under-n-chars 200 \
|
|
--chunk-new-after-n-chars 2500 \
|
|
--chunk-max-characters 38000 \
|
|
--chunk-multipage-sections \
|
|
--embedding-provider "langchain-huggingface" \
|
|
kafka \
|
|
--topic "$KAFKA_TOPIC" \
|
|
--bootstrap-server "$KAFKA_BOOTSTRAP_SERVER" \
|
|
--port 29092 \
|
|
--confluent false
|
|
|
|
echo "Checking for matching messages in Kafka"
|
|
|
|
#Check the number of messages in destination topic
|
|
python "$SCRIPT_DIR"/python/test-kafka-output.py check \
|
|
--bootstrap-server "$KAFKA_BOOTSTRAP_SERVER" \
|
|
--topic "$KAFKA_TOPIC" \
|
|
--confluent false \
|
|
--port 29092
|