Spaces:
Sleeping
Sleeping
File size: 12,356 Bytes
0b2c576 0902287 7535d0e 71f37da 7535d0e 36a270b 590c4a4 7535d0e d244902 12f8711 d244902 4cb3f48 d244902 36a270b d244902 36a270b d244902 36a270b d244902 6b73b6f d244902 0249415 d244902 0249415 d244902 0249415 d244902 0249415 d244902 0249415 d244902 0249415 d244902 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 |
import os
import base64
from base64 import urlsafe_b64encode
import requests
from supabase_models import Supabase_Client
from authenticate import get_access_token_v1
async def extract_structure_store_message(user_id: str, message_id: str, attachment_id: str, attachment_extension: str, email: str):
if attachment_id and message_id:
project_id = os.getenv('PROJECT_ID')
processor_id = os.getenv('PROCESSOR_ID')
document_entities = {}
file_name = f"{message_id}_{attachment_id}.{attachment_extension}"
print(f"file_name: {file_name}")
supabase = Supabase_Client().instance
response = supabase.storage.from_("receipt_radar").download(file_name)
base64_data = urlsafe_b64encode(response).decode('utf-8')
payload = {
"skipHumanReview": True,
"rawDocument": {
"mimeType": f"application/{attachment_extension}",
"content": base64_data
}
}
access_token = get_access_token_v1()
print(access_token)
headers = {
'Authorization': f'Bearer {access_token}',
'Content-Type': 'application/json; charset=utf-8'
}
response = requests.post(
f'https://us-documentai.googleapis.com/v1/projects/{project_id}/locations/us/processors/{processor_id}:process',
headers=headers,
json=payload
)
response_json = response.json()
allowed_entities = [
"due_date",
"invoice_date",
"total_amount",
"total_tax_amount",
"receiver_name",
"invoice_id",
"currency",
"receiver_address",
"invoice_type",
"supplier_name",
"payment_terms",
"line_item",
"line_item/description",
"line_item/quantity",
"line_item/amount",
"line_item/unit_price"
]
print("Response")
print(response_json)
raw_text = response_json.get('document').get('text', None)
entities = response_json.get('document').get('entities', None)
document_entities['user_id'] = user_id
print('Printing entities')
print(entities)
if entities is not None:
for ent in entities:
if ent.get('type') is not None:
entity_type = ent.get('type') or ""
# Check if the entity type is in the allowed list
if entity_type in allowed_entities:
mention_text = ent.get('mentionText') or ""
normalized_values = ent.get('normalizedValue') or ""
# Initialize a list for the entity type if not already present
if entity_type not in document_entities:
document_entities[entity_type] = []
# Append the entity data to the list
document_entities[entity_type].append({
"mention_text": mention_text,
"normalizedValue": normalized_values
})
# Handling 'line_item' and its properties (line_item/description, line_item/quantity, etc.)
if entity_type == 'line_item' and 'properties' in ent:
for prop in ent['properties']:
prop_type = prop.get('type') or ""
if prop_type in allowed_entities:
mention_text = prop.get('mentionText') or ""
normalized_values = prop.get('normalizedValue') or ""
# Initialize a list for the property type if not already present
if prop_type not in document_entities:
document_entities[prop_type] = []
# Append the property data to the list
document_entities[prop_type].append({
"mention_text": mention_text,
"normalizedValue": normalized_values
})
if 'line_item/description' in document_entities:
document_entities['line_item_description'] = document_entities['line_item/description']
document_entities.pop('line_item/description', None)
if 'line_item/quantity' in document_entities:
document_entities['line_item_quantity'] = document_entities['line_item/quantity']
document_entities.pop('line_item/quantity', None)
if 'line_item/amount' in document_entities:
document_entities['line_item_amount'] = document_entities['line_item/amount']
document_entities.pop('line_item/amount', None)
if 'line_item/unit_price' in document_entities:
document_entities['line_item_unit_price'] = document_entities['line_item/unit_price']
document_entities.pop('line_item/unit_price', None)
document_entities['email'] = email
document_entities['message_id'] = message_id
print("Printing parsed json")
print(document_entities)
return document_entities
# def extract_structure_store_message(user_id:str,message_id:str , attachment_id:str,attachment_extension:str,email:str):
# if attachment_id and message_id:
# project_id = os.getenv('PROJECT_ID')
# processor_id = os.getenv('PROCESSOR_ID')
# document_entities = {}
# file_name = f"{message_id}_{attachment_id}.{attachment_extension}"
# print(f"file_name: {file_name}")
# supabase = Supabase_Client().instance
# try:
# response = supabase.storage.from_("receipt_radar").download(
# file_name
# )
# base64_data = urlsafe_b64encode(response).decode('utf-8')
# payload = {
# "skipHumanReview": True,
# "rawDocument": {
# "mimeType": f"application/{attachment_extension}",
# "content": base64_data
# }
# }
# access_token = get_access_token_v1()
# print(access_token)
# headers = {
# 'Authorization': f'Bearer {access_token}',
# 'Content-Type': 'application/json; charset=utf-8'
# }
# response = requests.post(
# f'https://us-documentai.googleapis.com/v1/projects/{project_id}/locations/us/processors/{processor_id}:process',
# headers=headers,
# json=payload
# )
# response_json = response.json()
# allowed_entities = [
# "due_date",
# "invoice_date",
# "total_amount",
# "total_tax_amount",
# "receiver_name",
# "invoice_id",
# "currency",
# "receiver_address",
# "invoice_type",
# "supplier_name",
# "payment_terms",
# "line_item",
# "line_item/description",
# "line_item/quantity",
# "line_item/amount",
# "line_item/unit_price"
# ]
# raw_text = response_json.get('document').get('text' , None)
# entities = response_json.get('document').get('entities' , None)
# document_entities['user_id'] = user_id
# # insert_ocr_data_response = (
# # supabase.table("receipt_ocr_data")
# # .insert({'user_id':user_id , 'message_id':message_id,'receipt_text':raw_text ,'email':email,'file_type':attachment_extension})
# # .execute()
# # )
# print('Printing entities')
# print(entities)
# # if entities is not None:
# # for ent in entities:
# # if ent.get('type') is not None:
# # if ent.get('type') in allowed_entities:
# # mention_text = ent.get('mentionText')
# # normalised_values = ent.get('normalizedValue') if 'normalizedValue' in ent else None
# # document_entities[ent.get('type')] = {"mention_text":mention_text,"normalizedValue":normalised_values}
# if entities is not None:
# for ent in entities:
# if ent.get('type') is not None:
# entity_type = ent.get('type') or ""
# # Check if the entity type is in the allowed list
# if entity_type in allowed_entities:
# mention_text = ent.get('mentionText') or ""
# normalized_values = ent.get('normalizedValue') or ""
# # Initialize a list for the entity type if not already present
# if entity_type not in document_entities:
# document_entities[entity_type] = []
# # Append the entity data to the list
# document_entities[entity_type].append({
# "mention_text": mention_text,
# "normalizedValue": normalized_values
# })
# # Handling 'line_item' and its properties (line_item/description, line_item/quantity, etc.)
# if entity_type == 'line_item' and 'properties' in ent:
# for prop in ent['properties']:
# prop_type = prop.get('type') or ""
# if prop_type in allowed_entities:
# mention_text = prop.get('mentionText') or ""
# normalized_values = prop.get('normalizedValue') or ""
# # Initialize a list for the property type if not already present
# if prop_type not in document_entities:
# document_entities[prop_type] = []
# # Append the property data to the list
# document_entities[prop_type].append({
# "mention_text": mention_text,
# "normalizedValue": normalized_values
# })
# document_entities['line_item_description'] = document_entities['line_item/description']
# document_entities['line_item_quantity'] = document_entities['line_item/quantity']
# document_entities['line_item_amount'] = document_entities['line_item/amount']
# document_entities['line_item_unit_price'] = document_entities['line_item/unit_price']
# document_entities.pop('line_item/description', None)
# document_entities.pop('line_item/quantity', None)
# document_entities.pop('line_item/amount', None)
# document_entities.pop('line_item/unit_price', None)
# document_entities['email'] = email
# document_entities['message_id'] = message_id
# print("Printing parsed json")
# print(document_entities)
# # insert_data_response = (
# # supabase.table("document_ai_entities")
# # .insert(document_entities)
# # .execute()
# # )
# # print(insert_data_response)
# return document_entities
# except Exception as e:
# print(f"Error downloading or encoding file: {e}") |