def process_pdf_bundle(file_bundles: List[FileBundle],
fields_to_redact: List[str]):
renderer = PdfRenderer()
for file_bundle in file_bundles:
pdf_pre_processing_bundle = PdfPreProcessingBundle.from_file_bundle(
file_bundle)
redacted_image_name = get_redacted_file_name(
pdf_pre_processing_bundle.rendered_file_name)
redacted_fott_name = get_redacted_file_name(file_bundle.fott_file_name)
redacted_ocr_name = get_redacted_file_name(file_bundle.ocr_file_name)
# Render PDF
renderer.render_pdf_and_save(
Path(build_pre_processing_folder, file_bundle.image_file_name),
Path(build_pre_processing_folder,
pdf_pre_processing_bundle.rendered_file_name),
target_pdf_render_dpi)
# Follow the regular redaction process with taking files from slightly different source folders
redact_image(
Path(build_pre_processing_folder,
pdf_pre_processing_bundle.rendered_file_name),
Path(build_pre_processing_folder, file_bundle.fott_file_name),
Path(build_output_folder, redacted_image_name), fields_to_redact)
redact_fott_label(
Path(build_pre_processing_folder, file_bundle.fott_file_name),
Path(build_output_folder, redacted_fott_name), fields_to_redact)
redact_ocr_result(
Path(build_pre_processing_folder, file_bundle.ocr_file_name),
Path(build_pre_processing_folder, file_bundle.fott_file_name),
Path(build_output_folder, redacted_ocr_name), fields_to_redact)
def test_redact_image_file(tempdir, capsys):
test_filepath = os.path.join(RESOURCE_DIRECTORY, 'test.png')
output_filepath = os.path.join(tempdir, 'redacted.png')
redact.redact_image(test_filepath, output_filepath)
out, _ = capsys.readouterr()
assert output_filepath in out
def test_redact_image_file(tempdir, capsys):
test_filepath = os.path.join(RESOURCE_DIRECTORY, 'test.png')
output_filepath = os.path.join(tempdir, 'redacted.png')
redact.redact_image(GCLOUD_PROJECT, test_filepath, output_filepath,
['FIRST_NAME', 'EMAIL_ADDRESS'])
out, _ = capsys.readouterr()
assert output_filepath in out
def test_redact_image_file(tempdir, capsys):
test_filepath = os.path.join(RESOURCE_DIRECTORY, "test.png")
output_filepath = os.path.join(tempdir, "redacted.png")
redact.redact_image(GCLOUD_PROJECT, test_filepath, output_filepath,
["FIRST_NAME", "EMAIL_ADDRESS"])
out, _ = capsys.readouterr()
assert output_filepath in out
def test_redact_image_file_with_infotype(tempdir, capsys):
test_filepath = os.path.join(RESOURCE_DIRECTORY, 'test.png')
output_filepath = os.path.join(tempdir, 'redacted_with_infotype.png')
redact.redact_image(test_filepath,
output_filepath,
info_types=['EMAIL_ADDRESS', 'US_MALE_NAME'])
out, _ = capsys.readouterr()
assert output_filepath in out
def test_redact_image_file(tempdir, capsys):
test_filepath = os.path.join(RESOURCE_DIRECTORY, 'test.png')
output_filepath = os.path.join(tempdir, 'redacted.png')
redact.redact_image(
GCLOUD_PROJECT,
test_filepath,
output_filepath,
['FIRST_NAME', 'EMAIL_ADDRESS'])
out, _ = capsys.readouterr()
assert output_filepath in out
pdf_file_bundle_list = reader.download_bundles(
to=build_pre_processing_folder, mode=FileType.PDF_ONLY)
file_bundle_list = reader.download_bundles(to=build_input_folder)
else:
reader = LocalReader(input_path)
pdf_file_bundle_list = reader.copy_bundles(
to=build_pre_processing_folder, mode=FileType.PDF_ONLY)
file_bundle_list = reader.copy_bundles(to=build_input_folder)
for fb in file_bundle_list:
redacted_image_name = get_redacted_file_name(fb.image_file_name)
redacted_fott_name = get_redacted_file_name(fb.fott_file_name)
redacted_ocr_name = get_redacted_file_name(fb.ocr_file_name)
redact_image(Path(build_input_folder, fb.image_file_name),
Path(build_input_folder, fb.fott_file_name),
Path(build_output_folder, redacted_image_name),
fields_to_redact)
redact_fott_label(Path(build_input_folder, fb.fott_file_name),
Path(build_output_folder, redacted_fott_name),
fields_to_redact)
redact_ocr_result(Path(build_input_folder, fb.ocr_file_name),
Path(build_input_folder, fb.fott_file_name),
Path(build_output_folder, redacted_ocr_name),
fields_to_redact)
# Render and process PDF files if any
if pdf_file_bundle_list is not None:
process_pdf_bundle(pdf_file_bundle_list, fields_to_redact)
if is_blob_url(output_container):
writer = BlobWriter(output_container, output_path)
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License. See License.txt in the project
# root for license information.
import sys
from redact import redact_image, redact_fott_label, redact_ocr_result
if __name__ == '__main__':
operator = sys.argv[1]
if operator == 'image':
labels_to_redact = [] if len(sys.argv) < 6 else sys.argv[5].split(',')
redact_image(image_path=sys.argv[2],
fott_label_path=sys.argv[3],
output_path=sys.argv[4],
labels_to_redact=labels_to_redact)
elif operator == 'fott':
labels_to_redact = [] if len(sys.argv) < 5 else sys.argv[4].split(',')
redact_fott_label(fott_label_path=sys.argv[2],
output_path=sys.argv[3],
labels_to_redact=labels_to_redact)
elif operator == 'ocr':
labels_to_redact = [] if len(sys.argv) < 6 else sys.argv[5].split(',')
redact_ocr_result(ocr_result_path=sys.argv[2],
fott_label_path=sys.argv[3],
output_path=sys.argv[4],
labels_to_redact=labels_to_redact)
else: