def ocr_pdf_merge():
jpg_files = [
f for f in os.listdir('.')
if os.path.isfile(f) and f.startswith('page') and f.endswith('.jpg')
]
for jpg_file in jpg_files:
tesseract_ocr(jpg_file)
os.remove(jpg_file)
pdf_files = [
f for f in os.listdir('.')
if os.path.isfile(f) and f.startswith('page') and f.endswith('.pdf')
]
pdf_merge(pdf_files, 'ocred_document.pdf', delete=True)
)
# input
parser.add_argument(
"inputs", type=str, default=None, nargs="+", help="list of input files"
)
# output
parser.add_argument(
"-o",
"--output",
type=str,
default=None,
help="filename of the output file",
required=True,
)
# delete
parser.add_argument(
"-d",
"--delete",
action="store_true",
help="delete input files after merge",
)
return parser.parse_args(args)
if __name__ == "__main__":
args = process_arguments(sys.argv[1:])
pdf_merge(args.inputs, args.output, args.delete)
def main():
incremental_results_dir = path.join(DATA_DIR, "results", "incremental")
if path.isdir(incremental_results_dir):
print("Creating plots for incremental...")
for language in scandir(incremental_results_dir):
print(f" {language.name}")
for result_file in scandir(language.path):
csv_basename = ".".join(result_file.name.split(".")[:-1])
print(f" {csv_basename}")
result_data = read_csv(result_file.path)
result_data[0]["Added"] = None
result_data_except_first = result_data[1:]
if len([x for x in result_data if any(x[parser_type] for parser_type in parser_types())]) <= 0:
print(" No data found, skipping")
continue
figure_path = path.join(FIGURES_DIR, "incremental", language.name, csv_basename)
makedirs(figure_path, exist_ok=True)
figures = [
(plot_times(result_data, parser_types(True, "implode" in csv_basename)), "report"),
(plot_times(result_data_except_first, parser_types(False, "implode" in csv_basename)), "report-except-first"),
(plot_times_vs_changes(result_data_except_first, "bytes", "Added", "Removed"),
"report-time-vs-bytes"),
(plot_times_vs_changes(result_data_except_first, "chunks", "Changes"), "report-time-vs-changes"),
(plot_times_vs_changes_3d(result_data_except_first), "report-time-vs-changes-3D"),
]
for fig, name in figures:
fig.savefig(path.join(figure_path, name + ".pdf"))
fig.savefig(path.join(figure_path, name + ".svg"))
plt.close("all")
merged_path = path.join(figure_path, "merged.pdf")
if path.exists(merged_path):
remove(merged_path)
pdftools.pdf_merge([path.join(figure_path, name + ".pdf") for _, name in figures], merged_path)
memory_benchmarks_dir = path.join(DATA_DIR, "memoryBenchmarks")
if path.isdir(memory_benchmarks_dir):
print("Creating plots for memory benchmarks...")
for language in scandir(memory_benchmarks_dir):
print(f" {language.name}")
result_data_batch = read_csv(path.join(language.path, "batch.csv"))
result_data_incremental = read_csv(path.join(language.path, "incremental.csv"))
figure_path = path.join(FIGURES_DIR, "memoryBenchmarks", language.name)
makedirs(figure_path, exist_ok=True)
figures = [
(plot_memory_batch(result_data_batch, "incl"), "report-allocations-batch"),
(plot_memory_batch(result_data_batch, "excl"), "report-cache-size-batch"),
(plot_memory_incremental(result_data_incremental, "incl"), "report-allocations-incremental"),
(plot_memory_incremental(result_data_incremental, "excl"), "report-cache-size-incremental"),
]
for fig, name in figures:
fig.savefig(path.join(figure_path, name + ".pdf"))
fig.savefig(path.join(figure_path, name + ".svg"))
plt.close("all")
merged_path = path.join(figure_path, "merged.pdf")
if path.exists(merged_path):
remove(merged_path)
pdftools.pdf_merge([path.join(figure_path, name + ".pdf") for _, name in figures], merged_path)
parser = argparse.ArgumentParser(
parents=[parentparser],
description="Merge the pages of multiple input files in one output file.")
# input
parser.add_argument('inputs',
type=str,
default=None,
nargs='+',
help='list of input files')
# output
parser.add_argument('-o',
'--output',
type=str,
default=None,
help='filename of the output file',
required=True)
# delete
parser.add_argument('-d',
'--delete',
action='store_true',
help='delete input files after merge')
return parser.parse_args(args)
if __name__ == "__main__":
args = process_arguments(sys.argv[1:])
pdf_merge(args.inputs, args.output, args.delete)