mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-03 07:05:20 +00:00
36c4441e2b
- parametrize the output folder paths and expected output folder paths in comparison scripts - now allow user to use env `OUTPUT_ROOT` to control where the output and expected output is - currently assumes output from test and expected output are in the same directory; this may need separation later ## test run ```bash OUTPUT_ROOT=/tmp ./test_unstructured_ingest/test-ingest-src.sh ``` and it should show files changed but not able to show diff since there is no expected output content at `OUTPUT_ROOT`. Then run ```bash cp -R test_unstructured_ingest/expected-* /tmp/ OUTPUT_ROOT=/tmp ./test_unstructured_ingest/test-ingest-src.sh ``` we can see (due to CI and local instance producing different results) actual line by line diff
27 lines
1.1 KiB
Bash
Executable File
27 lines
1.1 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
# Description: Validate that the number of files in the output directory is as expected.
|
|
#
|
|
# Arguments:
|
|
# - $1: The expected number of files in the output directory.
|
|
# - $2: Name of the output folder. This is used to determine the output directory and the expected output directory paths.
|
|
# - $3: The expected size of the output directory in bytes (e.g. "10k").
|
|
|
|
set +e
|
|
|
|
EXPECTED_NUM_FILES=$1
|
|
OUTPUT_FOLDER_NAME=$2
|
|
EXPECTED_SIZE=$3
|
|
SCRIPT_DIR=$(dirname "$(realpath "$0")")
|
|
OUTPUT_ROOT=${OUTPUT_ROOT:-$SCRIPT_DIR}
|
|
EXPECTED_OUTPUT_DIR=$OUTPUT_ROOT/expected-structured-output/$OUTPUT_FOLDER_NAME
|
|
NUM_FILES=$(find "$EXPECTED_OUTPUT_DIR" -type f -size +"$EXPECTED_SIZE" | wc -l)
|
|
|
|
# Note: single brackets and "-ne" operator were necessary for evaluation in CI
|
|
if [ "$NUM_FILES" -ne "$EXPECTED_NUM_FILES" ] && [ "$OVERWRITE_FIXTURES" != "true" ]; then
|
|
echo "The test fixtures in $EXPECTED_OUTPUT_DIR look suspicious."
|
|
echo "Expected $EXPECTED_NUM_FILES files, but found $NUM_FILES files found."
|
|
echo "Did you overwrite test fixtures with bad outputs?"
|
|
exit 1
|
|
fi
|