Now stub_to_print checks the validity of the generated pdf. This allo…

…ws early detection of problems where the scan contains image formats that pypdf2 doesn't handle.

work related to #8

src/pymusco/__init__.py

@@ -10,17 +10,19 @@
 from .core import TableOfContents
 from .core import InstrumentNotFound
 from .core import ITrackSelector
+from .main import images_to_pdf
 from .main import scan_to_stub
 from .main import stub_to_print
 from .main import split_double_pages
 from .main import crop_pdf
 from .main import merge_pdf
 from .main import remove_unneeded_pdf_password
 from .main import StampDesc
+from .main import StubContents
 # from .tesseract import extract_pdf_text
 from .tsauto import load_musician_count
 from .tsauto import AutoTrackSelector
 from .tssingle import SingleTrackSelector
 from .tsmanual import ManualTrackSelector
-from .pdf import check_pdf, add_stamp, add_bookmarks
+from .pdf import check_pdf, check_pdf_reader, check_pdf_page, dump_pdf_page, add_stamp, add_bookmarks
 from .piece import Piece, Catalog, load_piece_description

src/pymusco/core.py

@@ -576,7 +576,7 @@ def get_pdf_toc_item_page(pdf_toc_item: Dict[str, Any], pdf_reader: PyPDF2.PdfRe
 
  # at this point, linked_page_indirect_object is of type PyPDF2.generic.IndirectObject, with a value such as:
  # IndirectObject(228, 0)
- print(dir(pdf_reader))
+ # print(dir(pdf_reader))
  linked_page_object = pdf_reader.resolved_objects[(0, linked_page_indirect_object.idnum)]
  # at this point, linked_page_object is of type PyPDF2.generic.DictionaryObject with a value such as :
  # {

src/pymusco/main.py

@@ -18,7 +18,7 @@
 from .pdf import extract_pdf_page_main_image
 from .pdf import extract_pdf_page
 from .core import get_stub_tracks
-from .pdf import check_pdf
+from .pdf import check_pdf, check_pdf_reader
 
 
 def md5(fname):
@@ -359,6 +359,7 @@ def scan_to_stub(src_scanned_pdf_file_path: Path, dst_stub_pdf_file_path: Path,
  # break
  stamp_descs = stamp_descs if stamp_descs is not None else []
  images_to_pdf(StubContents(image_file_paths=scanned_image_file_paths, toc=toc, title=title, stamp_descs=stamp_descs, page_info_line_y_pos=page_info_line_y_pos), dst_stub_pdf_file_path)
+ check_pdf(dst_stub_pdf_file_path) # ensure that the generated pdf is supported by pypdf2
 
 
 def stub_to_print(src_stub_file_path: Path, dst_print_file_path: Path, track_selector: ITrackSelector, orchestra: Orchestra):
@@ -370,6 +371,9 @@ def stub_to_print(src_stub_file_path: Path, dst_print_file_path: Path, track_sel
  :param dict(str, int) musician_count: gets the number of musicians for each musical intrument family
  :param TableOfContents or None stub_toc: if defined, gets the start page number for each track in the stub
  """
+
+ check_pdf(src_stub_file_path)
+
  stub_toc = get_stub_tracks(src_stub_file_path, orchestra)
  print(stub_toc)
 
@@ -420,11 +424,11 @@ def stub_to_print(src_stub_file_path: Path, dst_print_file_path: Path, track_sel
  (first_page_index, last_page_index) = page_range
  num_copies = range_to_num_copies[page_range]
  log_file.write(f"{num_copies} copies of {'/'.join(range_to_tracks[page_range])}\n")
- # print(page_range, num_copies)
+ # print(page_range, num_copies, range_to_tracks[page_range])
  for copy_index in range(num_copies): # @UnusedVariable pylint: disable=unused-variable
  for page_index in range(first_page_index, last_page_index + 1):
  track_page = stub_pdf.pages[page_index - 1] # -1 to convert 1-based index into 0-based index
- # print('adding page %d' % page_index)
+ # print(f'adding page {page_index}')
  print_pdf.add_page(track_page)
 
  log_file.write("\nunprinted tracks :\n\n")