Converting plain textual files to JSONL format

running_python2_script.py

# python2 <script> gs://<path_to_src_pdf> gs://<dest_bucket>/

# Converting one text file to JSONL format
# File name: src.pdf | GCS path for file: gs://test-bucket-for-automl-nlp/src.pdf
python2 input_helper_v2.py gs://test-bucket-for-automl-nlp/src.pdf gs://test-bucket-for-automl-nlp/

# Converting multiple text files with same extension to JSONL format
# File extension: *.pdf | GCS path for files: gs://test-bucket-for-automl-nlp/*.pdf
python2 input_helper_v2.py gs://test-bucket-for-automl-nlp/*.pdf gs://test-bucket-for-automl-nlp/
    
# File extension: *.txt | GCS path for files: gs://test-bucket-for-automl-nlp/*.txt
python2 input_helper_v2.py gs://test-bucket-for-automl-nlp/*.txt gs://test-bucket-for-automl-nlp/