mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-04 23:52:23 +00:00
f333d7fe7f
## NOTE `test_unstructured_ingest/expected-structured-output-html` contains all test HTML fixtures. Original JSON files, from which these HTML fixtures are generated, were taken from `test_unstructured_ingest/expected-structured-output`
27 lines
758 B
Bash
Executable File
27 lines
758 B
Bash
Executable File
#!/bin/bash
|
|
|
|
# Define the input and output top directories
|
|
SCRIPT_DIR=$(dirname "$(realpath "$0")")
|
|
OUTPUT_DIR=${1:-"$SCRIPT_DIR/structured-output-html"}
|
|
INPUT_DIR="$SCRIPT_DIR/expected-structured-output"
|
|
PYTHON_SCRIPT="$SCRIPT_DIR/../scripts/html/elements_json_to_html.py"
|
|
EXCLUDE_IMG=0
|
|
NO_GROUP=1
|
|
|
|
# Function to process JSON files
|
|
process_json_files() {
|
|
# Add flags based on the variables
|
|
cmd="PYTHONPATH=${PYTHONPATH:-.} python \"$PYTHON_SCRIPT\" \"$INPUT_DIR\" --outdir \"$OUTPUT_DIR\""
|
|
if [ "$EXCLUDE_IMG" -eq 1 ]; then
|
|
cmd+=" --exclude-img"
|
|
fi
|
|
if [ "$NO_GROUP" -eq 1 ]; then
|
|
cmd+=" --no-group"
|
|
fi
|
|
# Run the Python script with the constructed command
|
|
eval "$cmd"
|
|
}
|
|
|
|
# Start processing from the input directory
|
|
process_json_files
|