def test_job_timeout(indico):
client = IndicoClient()
dataset_filepath = str(Path(__file__).parents[1]) + "/data/mock.pdf"
job = client.call(
DocumentExtraction(files=[dataset_filepath],
json_config='{"preset_config": "detailed"}'))[0]
with pytest.raises(IndicoTimeoutError):
job = client.call(JobStatus(id=job.id, wait=True, timeout=0.0))
def test_job_wait_on_failure(indico):
client = IndicoClient()
dataset_filepath = str(Path(__file__).parents[1]) + "/data/mock.pdf"
jobs = client.call(
DocumentExtraction(files=[dataset_filepath],
json_config='{"preset_config": "wrong"}'))
assert len(jobs) == 1
job = jobs[0]
assert job.id != None
job = client.call(JobStatus(id=job.id, wait=True))
assert job.status == "FAILURE"
assert type(job.result) == dict
def test_job_wait_on_success(indico):
client = IndicoClient()
dataset_filepath = str(Path(__file__).parents[1]) + "/data/mock.pdf"
jobs = client.call(
DocumentExtraction(files=[dataset_filepath],
json_config='{"preset_config": "simple"}'))
assert len(jobs) == 1
job = jobs[0]
assert job.id != None
job = client.call(JobStatus(id=job.id, wait=True))
assert job.status == "SUCCESS"
assert job.ready == True
assert type(job.result["url"]) == str
def test_document_extraction(indico):
client = IndicoClient()
dataset_filepath = str(Path(__file__).parents[1]) + "/data/mock.pdf"
jobs = client.call(DocumentExtraction(files=[dataset_filepath]))
assert len(jobs) == 1
job = jobs[0]
assert job.id is not None
job = client.call(JobStatus(id=job.id, wait=True))
assert job.status == "SUCCESS"
assert job.ready is True
assert type(job.result["url"]) == str
extract = client.call(RetrieveStorageObject(job.result))
assert type(extract) == dict
assert "pages" in extract
def test_document_extraction_batched(indico):
client = IndicoClient()
file_names = ["mock.pdf", "mock_2.pdf", "mock_3.pdf"]
parent_path = str(Path(__file__).parent.parent / "data")
dataset_filepaths = [
os.path.join(parent_path, file_name) for file_name in file_names
]
jobs = client.call(
DocumentExtraction(
files=dataset_filepaths,
json_config={"preset_config": "simple"},
upload_batch_size=1,
)
)
assert len(jobs) == 3
for job in jobs:
assert job.id is not None
job = client.call(JobStatus(id=job.id, wait=True))
assert job.status == "SUCCESS"
assert job.ready is True
assert isinstance(job.result["url"], str)
"""
Example demonstrating how to OCR a document and access the text at the document, page, and
block (or paragraph) level.
"""
from indico import IndicoClient, IndicoConfig
from indico.queries import DocumentExtraction, JobStatus, RetrieveStorageObject
# Get the OCR object
my_config = IndicoConfig(host="app.indico.io",
api_token_path=".path/to/indico_api_token.txt")
client = IndicoClient(config=my_config)
files_to_extract = client.call(
DocumentExtraction(files=["./test_paragraphs.pdf"],
json_config={"preset_config": "standard"}))
extracted_file = client.call(JobStatus(id=files_to_extract[0].id, wait=True))
json_result = client.call(RetrieveStorageObject(extracted_file.result))
# The code below shows how to get the OCR text from the 'json_result' object.
# Note: it may vary slightly if you use DocumentExtraction configurations other than 'standard'
# Full Text
full_document_text = json_result["text"]
# Doucment Text split by page
text_by_page = list()
for page in json_result["pages"]:
text_by_page.append(page["text"])
# Document Text split by block (or paragraph)
from indico import IndicoClient, IndicoConfig
from indico.queries import DocumentExtraction, JobStatus, RetrieveStorageObject
# Create an Indico API client
my_config = IndicoConfig(host="app.indico.io",
api_token_path="./path/to/indico_api_token.txt")
client = IndicoClient(config=my_config)
# OCR a single file and wait for it to complete
job = client.call(
DocumentExtraction(files=["./path_to_doc.pdf"],
json_config=dict(preset_config="ondocument")))
extracted_file = client.call(JobStatus(id=job[0].id, wait=True))
if extracted_file.status == "SUCCESS":
result = client.call(RetrieveStorageObject(extracted_file.result))
print(result)