Division by Zero

[Whadup]

nlm-ingestor/nlm_ingestor/ingestor/visual_ingestor/visual_ingestor.py

Line 3232 in c725429

and (prev_box[1]/left > 1.1) # or is_aligned)

left might be 0.0 giving us a "Division by Zero" error. Not entirely sure what this comparison of the ratio > 1.1 is supposed to do?

[KrishnaPG]

Receiving the same error. The call stack is as below:

error uploading file, stacktrace: Traceback (most recent call last):
  File "/app/nlm_ingestor/ingestion_daemon/__main__.py", line 48, in parse_document
    return_dict, _ = ingestor_api.ingest_document(
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/nlm_ingestor/ingestor/ingestor_api.py", line 37, in ingest_document
    ingestor = pdf_ingestor.PDFIngestor(doc_location, parse_options)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/nlm_ingestor/ingestor/pdf_ingestor.py", line 35, in __init__
    blocks, _block_texts, _sents, _file_data, result, page_dim, num_pages = parse_blocks(
                                                                            ^^^^^^^^^^^^^
  File "/app/nlm_ingestor/ingestor/pdf_ingestor.py", line 176, in parse_blocks
    parsed_doc = visual_ingestor.Doc(pages, ignore_blocks, render_format)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/nlm_ingestor/ingestor/visual_ingestor/visual_ingestor.py", line 117, in __init__
    self.parse(pages)
  File "/app/nlm_ingestor/ingestor/visual_ingestor/visual_ingestor.py", line 551, in parse
    self.organize_and_indent_blocks()
  File "/app/nlm_ingestor/ingestor/visual_ingestor/visual_ingestor.py", line 3046, in organize_and_indent_blocks
    self.merge_header_blocks()
  File "/app/nlm_ingestor/ingestor/visual_ingestor/visual_ingestor.py", line 4230, in merge_header_blocks
    (len(noun_chunk_str.split()) /
     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ZeroDivisionError: division by zero
Traceback (most recent call last):
  File "/app/nlm_ingestor/ingestion_daemon/__main__.py", line 48, in parse_document
    return_dict, _ = ingestor_api.ingest_document(
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/nlm_ingestor/ingestor/ingestor_api.py", line 37, in ingest_document
    ingestor = pdf_ingestor.PDFIngestor(doc_location, parse_options)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/nlm_ingestor/ingestor/pdf_ingestor.py", line 35, in __init__
    blocks, _block_texts, _sents, _file_data, result, page_dim, num_pages = parse_blocks(
                                                                            ^^^^^^^^^^^^^
  File "/app/nlm_ingestor/ingestor/pdf_ingestor.py", line 176, in parse_blocks
    parsed_doc = visual_ingestor.Doc(pages, ignore_blocks, render_format)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/nlm_ingestor/ingestor/visual_ingestor/visual_ingestor.py", line 117, in __init__
    self.parse(pages)
  File "/app/nlm_ingestor/ingestor/visual_ingestor/visual_ingestor.py", line 551, in parse
    self.organize_and_indent_blocks()
  File "/app/nlm_ingestor/ingestor/visual_ingestor/visual_ingestor.py", line 3046, in organize_and_indent_blocks
    self.merge_header_blocks()
  File "/app/nlm_ingestor/ingestor/visual_ingestor/visual_ingestor.py", line 4230, in merge_header_blocks
    (len(noun_chunk_str.split()) /
     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ZeroDivisionError: division by zero