winzer/elwig-misc
3
1
Fork 0
Code Pull Requests Activity

winziprint: add progress updates

Browse Source
This commit is contained in:
Lorenz Stechauner
2023-10-19 21:48:00 +02:00
parent 5c924c944c
commit 499cd2032e
1 changed files with 29 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
winziprint/winziprint.py
View File

@ -14,33 +14,37 @@ import pypdf
BATCH_SIZE = 10
def convert(input_file_names: list[str], output_file_name: str, encoding: str = None) -> list[int]:
def convert(input_files: list[str], output_files: str, encoding: str = None, progress: bool = False) -> list[int]:
# it takes roughly 100ms to generate one document
page_nums = []
tmp_file_names = []
steps = len(input_files) // BATCH_SIZE + 1
try:
for i in range(0, len(input_file_names), BATCH_SIZE):
batch = input_file_names[i:i + BATCH_SIZE]
for i in range(0, len(input_files), BATCH_SIZE):
batch = input_files[i:i + BATCH_SIZE]
documents = []
for file_name in batch:
for n, file_name in enumerate(batch):
html = weasyprint.HTML(file_name, encoding=encoding)
doc = html.render()
documents.append(doc)
del html
all_pages = [p for doc in documents for p in doc.pages]
tmp_file_name = f'{output_file_name}.part.{i:0000}'
tmp_file_name = f'{output_files}.part.{i:0000}'
documents[0].copy(all_pages).write_pdf(tmp_file_name)
tmp_file_names.append(tmp_file_name)
page_nums += [len(doc.pages) for doc in documents]
del documents
del all_pages
gc.collect()
if progress:
print(f'progress: {i // BATCH_SIZE + 1}/{steps}', flush=True)
merger = pypdf.PdfWriter()
for pdf in tmp_file_names:
merger.append(pdf)
merger.write(output_file_name)
merger.write(output_files)
merger.close()
del merger
finally:
@ -48,15 +52,19 @@ def convert(input_file_names: list[str], output_file_name: str, encoding: str =
if os.path.isfile(pdf):
os.remove(pdf)
if progress:
print(f'progress: {steps}/{steps}', flush=True)
return page_nums
def _wrapper_convert(args: list[str], encoding: str = None) -> None:
def _wrapper_convert(args: list[str], encoding: str = None, progress: bool = False) -> None:
try:
t0 = time.process_time()
pages = convert(args[:-1], args[-1], encoding=encoding)
pages = convert(args[:-1], args[-1], encoding=encoding, progress=progress)
t1 = time.process_time()
print(f'{len(args) - 1} documents, '
print(f'success: '
f'{len(args) - 1} documents, '
f'{sum(pages)} pages ({", ".join(str(p) for p in pages)}), '
f'{t1 - t0:.1f} sec',
flush=True)
@ -69,11 +77,12 @@ def _wrapper_convert(args: list[str], encoding: str = None) -> None:
def usage() -> None:
print(f'usage: {sys.argv[0]} [-h] [-d DIR] [-e ENCODING] [ - | INPUT [INPUT...] OUTPUT ]\n\n'
print(f'usage: {sys.argv[0]} [-h] [-p] [-d DIR] [-e ENCODING] [ - | INPUT [INPUT...] OUTPUT ]\n\n'
'options:\n'
' -h, --help show this help message and exit\n'
' -d, --directory set the working directory\n'
' -e, --encoding encoding of the input files\n'
' -p, --progress show progress updates\n'
'\n'
' - use stdin for retrieving input and output file names (semi-colon-seperated)\n'
' INPUT name of an html input file\n'
@ -104,13 +113,21 @@ def main() -> None:
os.chdir(working_dir)
encoding = _get_arg(args, '-e', '--encoding')
progress = False
if '-p' in args:
args.remove('-p')
progress = True
if '--progress' in args:
args.remove('--progress')
progress = True
if args == ['-']:
for line in sys.stdin:
_wrapper_convert(line.strip().split(';'), encoding=encoding)
_wrapper_convert(line.strip().split(';'), encoding=encoding, progress=progress)
elif len(args) < 2:
usage()
else:
_wrapper_convert(args, encoding=encoding)
_wrapper_convert(args, encoding=encoding, progress=progress)
if __name__ == '__main__':