def test_pdf_to_jpeg():
file = get_file("tests/test_sample/2003.00744v1_image_pdf.pdf")
count = 0
for image_file in PDFToJPEG().iterate_transform(file):
count += 1
assert type(image_file) == io.BytesIO
assert count == 3
def main(input_path: str, output_path: str, verbose: bool) -> None:
logger = setup_logger(verbose)
logger.info("start ocr process")
input_extension = input_path.split(".")[-1]
validation_input_path(input_path, SUPPORT_INPUT_EXTENSIONS)
validation_output_path(output_path, SUPPORT_OUTPUT_EXTENSIONS)
lines = []
input_file = get_file(input_path)
if input_extension == "pdf":
logger.info("start converting pdf to string")
for i, file in enumerate(PDFToJPEG().iterate_transform(input_file), 1):
lines.append(ocr_precess(file, PreProcessor(RGB_BORDER), OCRTesseractProcessor(), PostProcessor()))
file.close()
logger.info(f"finish converting pdf to string, at {i} page")
else:
logger.info(f"start converting {input_extension} to string")
lines.append(ocr_precess(input_file, PreProcessor(RGB_BORDER), OCRTesseractProcessor(), PostProcessor()))
logger.info(f"finish converting {input_extension} to string")
input_file.close()
logger.info(f"start converting string to text file")
write_file(lines, output_path)
logger.info(f"start converting string to text file")
logger.info(f"finish ocr processing")
def test_ocr_processor():
file = get_file("tests/test_sample/82251504.png")
fixed_text = ocr_precess(file, PreProcessor(100), OCRTesseractProcessor(), PostProcessor())
assert type(fixed_text) == str
def test_pre_processor():
file = get_file("tests/test_sample/82251504.png")
new_file = PreProcessor(100).run(file)
assert type(new_file) == io.BytesIO
def test_ocr_tesseract_processor():
file = get_file("tests/test_sample/82251504.png")
text = OCRTesseractProcessor().run(file)
assert type(text) == str