class DataExtraction(unittest.TestCase):
def setUp(self):
warnings.simplefilter("ignore", category=ResourceWarning)
self.sypht_client = SyphtClient(os.environ["CLIENT_ID"],
os.environ["CLIENT_SECRET"])
def test_with_wrong_fieldset(self):
with self.assertRaises(Exception) as context:
with open("tests/sample_invoice.pdf", "rb") as f:
response = self.sypht_client.upload(
f,
[
"sypht.incorrect",
],
)
self.assertIn(
"does not have permission to use fieldSet sypht.incorrect",
response["error"],
)
self.assertTrue(
"Request failed with status code" in str(context.exception))
def test_data_extraction_1(self):
with open("tests/sample_invoice.pdf", "rb") as f:
fid = self.sypht_client.upload(f, ["invoices"])
self.assertTrue(validate_uuid4(fid))
results = self.sypht_client.fetch_results(fid)
self.assertTrue(isinstance(results, dict))
self.assertIn("invoice.dueDate", results)
self.assertIn("invoice.total", results)
self.assertIn("invoice.amountPaid", results)
self.assertIn("invoice.amountDue", results)
def test_data_extraction_2(self):
with open("tests/sample_invoice.pdf", "rb") as f:
fid = self.sypht_client.upload(
f, products=["sypht.invoice", "sypht.bank"])
self.assertTrue(validate_uuid4(fid))
results = self.sypht_client.fetch_results(fid)
self.assertTrue(isinstance(results, dict))
self.assertIn("invoice.dueDate", results)
self.assertIn("invoice.total", results)
self.assertIn("invoice.amountPaid", results)
self.assertIn("invoice.amountDue", results)
self.assertIn("bank.accountNo", results)
self.assertIn("bank.bsb", results)
def test_parent_doc_id(self):
parent_doc_id = uuid4()
with open("tests/sample_invoice.pdf", "rb") as f:
fid = self.sypht_client.upload(f, ["invoices"],
parent_doc_id=parent_doc_id)
self.assertTrue(validate_uuid4(fid))
class DataExtraction(unittest.TestCase):
def setUp(self):
if not six.PY2:
warnings.simplefilter('ignore', category=ResourceWarning)
self.sypht_client = SyphtClient(os.environ['CLIENT_ID'],
os.environ['CLIENT_SECRET'])
def test_with_wrong_fieldset(self):
with self.assertRaises(Exception) as context:
with open('tests/sample_invoice.pdf', 'rb') as f:
response = self.sypht_client.upload(f,
fieldsets=[
'sypht.incorrect',
])
self.assertIn(
'does not have permission to use fieldSet sypht.incorrect',
reponse['error'])
self.assertTrue(
'Request failed with status code' in str(context.exception))
def test_data_extraction_1(self):
with open('tests/sample_invoice.pdf', 'rb') as f:
fid = self.sypht_client.upload(f, fieldsets=Fieldset.INVOICE)
self.assertTrue(validate_uuid4(fid))
results = self.sypht_client.fetch_results(fid)
self.assertTrue(isinstance(results, dict))
self.assertIn('invoice.dueDate', results)
self.assertIn('invoice.total', results)
self.assertIn('invoice.amountPaid', results)
self.assertIn('invoice.amountDue', results)
def test_data_extraction_2(self):
with open('tests/sample_invoice.pdf', 'rb') as f:
fid = self.sypht_client.upload(f,
fieldsets=[
Fieldset.INVOICE,
Fieldset.BANK,
])
self.assertTrue(validate_uuid4(fid))
results = self.sypht_client.fetch_results(fid)
self.assertTrue(isinstance(results, dict))
self.assertIn('invoice.dueDate', results)
self.assertIn('invoice.total', results)
self.assertIn('invoice.amountPaid', results)
self.assertIn('invoice.amountDue', results)
self.assertIn('bank.accountNo', results)
self.assertIn('bank.bsb', results)
def __call__(self):
sypht = SyphtClient()
print("Uploading: ", self.path, "...")
with open(self.path, "rb") as f:
doc_id = sypht.upload(f, self.products)
print("Processing: ", doc_id, "...")
print(json.dumps(sypht.fetch_results(doc_id), indent=2))
def __call__(self):
sypht = SyphtClient()
print('Uploading: ', self.path, '...')
with open(self.path, 'rb') as f:
doc_id = sypht.upload(f, self.fieldsets)
print('Processing: ', doc_id, '...')
print(json.dumps(sypht.fetch_results(doc_id), indent=2))
import pandas as pd
#give path of receipts folder to extract there dates
folder = r"C:\Users\..\Downloads\Desktop\syphtclient\Receipts"
dates = []
filenames = []
for filename in os.listdir(folder):
print(filename)
#jpgfile = Image.open(os.path.join(folder, filename))
with open(os.path.join(folder, filename), 'rb') as f:
fid = scc.upload(
f, fieldsets=["document"]
) ###obtaining results by uploading image on sypht through sypht api key
f.close()
ab = scc.fetch_results(fid) ###fetching results
print(scc.fetch_results(fid))
filenames.append(filename)
if not ab: ###check the dictionary is empty or not
#print('none')
dates.append('none')
else:
dates.append(ab['document.date'])
###store the dates and filenames respectively into a csv file
result = pd.DataFrame({'filenames': filenames, 'dates': dates})
#result2.to_csv('result2.csv')
#result1=pd.read_csv('result1.csv')
#result=pd.concat([result1,result2],ignore_index=True)
result.to_csv('result.csv')
# get the ratio between average shadow pixels and average lit pixels
ratio_as_al = average_ld / average_le
# added these difference
for i in range(y_cb_cr_img.shape[0]):
for j in range(y_cb_cr_img.shape[1]):
if erosion[i, j, 0] == 255 and erosion[i, j,
1] == 255 and erosion[i, j,
2] == 255:
y_cb_cr_img[i, j] = [
y_cb_cr_img[i, j, 0] + i_diff,
y_cb_cr_img[i, j, 1] + ratio_as_al,
y_cb_cr_img[i, j, 2] + ratio_as_al
]
# covert the YCbCr image to the BGR image
final_image = cv2.cvtColor(y_cb_cr_img, cv2.COLOR_YCR_CB2BGR)
cv2.imwrite('images/new-{}'.format(image_filename), final_image)
from sypht.client import SyphtClient, Fieldset
scc = SyphtClient('JNSJgJF3SEltPf11DZLtdPE9SFPdrmlh',
'......................................................')
with open('images/new-{}'.format(image_filename), 'rb') as f:
fid = scc.upload(f, fieldsets=["document"])
print(scc.fetch_results(fid))
cv2.imshow("im1", or_img)
cv2.imshow("im2", final_image)
cv2.waitKey(0)
cv2.destroyAllWindows()
