Spaces:
Running
Running
Mallisetty Siva Mahesh
commited on
Commit
·
6413971
1
Parent(s):
47d6c5f
added code for msme cinllpin
Browse files
app.py
CHANGED
@@ -1,335 +1,3 @@
|
|
1 |
-
# from fastapi import FastAPI, File, UploadFile, HTTPException
|
2 |
-
# from fastapi.middleware.cors import CORSMiddleware
|
3 |
-
# from typing import Dict
|
4 |
-
# import os
|
5 |
-
# import shutil
|
6 |
-
# import logging
|
7 |
-
# from s3_setup import s3_client
|
8 |
-
|
9 |
-
# import torch
|
10 |
-
# from transformers import LayoutLMv3Processor, LayoutLMv3ForTokenClassification
|
11 |
-
|
12 |
-
# from dotenv import load_dotenv
|
13 |
-
# import os
|
14 |
-
|
15 |
-
# from utils import doc_processing
|
16 |
-
|
17 |
-
# # Load .env file
|
18 |
-
# load_dotenv()
|
19 |
-
|
20 |
-
# # Access variables
|
21 |
-
# dummy_key = os.getenv("dummy_key")
|
22 |
-
# HUGGINGFACE_AUTH_TOKEN = dummy_key
|
23 |
-
|
24 |
-
|
25 |
-
# # Hugging Face model and token
|
26 |
-
# aadhar_model = "AuditEdge/doc_ocr_a" # Replace with your fine-tuned model if applicable
|
27 |
-
# device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
28 |
-
# print(f"Using device: {device}")
|
29 |
-
|
30 |
-
# # Load the processor (tokenizer + image processor)
|
31 |
-
# processor_aadhar = LayoutLMv3Processor.from_pretrained(
|
32 |
-
# aadhar_model,
|
33 |
-
# use_auth_token=HUGGINGFACE_AUTH_TOKEN
|
34 |
-
# )
|
35 |
-
# aadhar_model = LayoutLMv3ForTokenClassification.from_pretrained(
|
36 |
-
# aadhar_model,
|
37 |
-
# use_auth_token=HUGGINGFACE_AUTH_TOKEN
|
38 |
-
# )
|
39 |
-
|
40 |
-
|
41 |
-
# aadhar_model = aadhar_model.to(device)
|
42 |
-
|
43 |
-
# # pan model
|
44 |
-
# pan_model = "AuditEdge/doc_ocr_p" # Replace with your fine-tuned model if applicable
|
45 |
-
# device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
46 |
-
# print(f"Using device: {device}")
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
# # Load the processor (tokenizer + image processor)
|
51 |
-
# processor_pan = LayoutLMv3Processor.from_pretrained(
|
52 |
-
# pan_model,
|
53 |
-
# use_auth_token=HUGGINGFACE_AUTH_TOKEN
|
54 |
-
# )
|
55 |
-
# pan_model = LayoutLMv3ForTokenClassification.from_pretrained(
|
56 |
-
# pan_model,
|
57 |
-
# use_auth_token=HUGGINGFACE_AUTH_TOKEN
|
58 |
-
# )
|
59 |
-
# pan_model = pan_model.to(device)
|
60 |
-
|
61 |
-
# #
|
62 |
-
# # gst model
|
63 |
-
# gst_model = "AuditEdge/doc_ocr_new_g" # Replace with your fine-tuned model if applicable
|
64 |
-
# device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
65 |
-
# print(f"Using device: {device}")
|
66 |
-
|
67 |
-
# # Load the processor (tokenizer + image processor)
|
68 |
-
# processor_gst = LayoutLMv3Processor.from_pretrained(
|
69 |
-
# gst_model,
|
70 |
-
# use_auth_token=HUGGINGFACE_AUTH_TOKEN
|
71 |
-
# )
|
72 |
-
# gst_model = LayoutLMv3ForTokenClassification.from_pretrained(
|
73 |
-
# gst_model,
|
74 |
-
# use_auth_token=HUGGINGFACE_AUTH_TOKEN
|
75 |
-
# )
|
76 |
-
# gst_model = gst_model.to(device)
|
77 |
-
|
78 |
-
# #cheque model
|
79 |
-
|
80 |
-
# cheque_model = "AuditEdge/doc_ocr_new_c" # Replace with your fine-tuned model if applicable
|
81 |
-
# device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
82 |
-
# print(f"Using device: {device}")
|
83 |
-
|
84 |
-
# # Load the processor (tokenizer + image processor)
|
85 |
-
# processor_cheque = LayoutLMv3Processor.from_pretrained(
|
86 |
-
# cheque_model,
|
87 |
-
# use_auth_token=HUGGINGFACE_AUTH_TOKEN
|
88 |
-
# )
|
89 |
-
# cheque_model = LayoutLMv3ForTokenClassification.from_pretrained(
|
90 |
-
# cheque_model,
|
91 |
-
# use_auth_token=HUGGINGFACE_AUTH_TOKEN
|
92 |
-
# )
|
93 |
-
# cheque_model = cheque_model.to(device)
|
94 |
-
|
95 |
-
|
96 |
-
|
97 |
-
|
98 |
-
|
99 |
-
|
100 |
-
# # Verify model and processor are loaded
|
101 |
-
# print("Model and processor loaded successfully!")
|
102 |
-
# print(f"Model is on device: {next(aadhar_model.parameters()).device}")
|
103 |
-
|
104 |
-
|
105 |
-
# # Import inference modules
|
106 |
-
# from layoutlmv3FineTuning.Layoutlm_inference.ocr import prepare_batch_for_inference
|
107 |
-
# from layoutlmv3FineTuning.Layoutlm_inference.inference_handler import handle
|
108 |
-
|
109 |
-
# # Create FastAPI instance
|
110 |
-
# app = FastAPI(debug=True)
|
111 |
-
|
112 |
-
# # Enable CORS
|
113 |
-
# app.add_middleware(
|
114 |
-
# CORSMiddleware,
|
115 |
-
# allow_origins=["*"],
|
116 |
-
# allow_credentials=True,
|
117 |
-
# allow_methods=["*"],
|
118 |
-
# allow_headers=["*"],
|
119 |
-
# )
|
120 |
-
|
121 |
-
# # Configure directories
|
122 |
-
# UPLOAD_FOLDER = './uploads/'
|
123 |
-
# processing_folder = "./processed_images"
|
124 |
-
# os.makedirs(UPLOAD_FOLDER, exist_ok=True) # Ensure the main upload folder exists
|
125 |
-
# os.makedirs(processing_folder,exist_ok=True)
|
126 |
-
|
127 |
-
# UPLOAD_DIRS = {
|
128 |
-
# "aadhar_file": "uploads/aadhar/",
|
129 |
-
# "pan_file": "uploads/pan/",
|
130 |
-
# "cheque_file": "uploads/cheque/",
|
131 |
-
# "gst_file": "uploads/gst/",
|
132 |
-
# }
|
133 |
-
|
134 |
-
# process_dirs = {
|
135 |
-
# "aadhar_file": "processed_images/aadhar/",
|
136 |
-
# "pan_file": "processed_images/pan/",
|
137 |
-
# "cheque_file": "processed_images/cheque/",
|
138 |
-
# "gst_file": "processed_images/gst/",
|
139 |
-
|
140 |
-
# }
|
141 |
-
|
142 |
-
# # Ensure individual directories exist
|
143 |
-
# for dir_path in UPLOAD_DIRS.values():
|
144 |
-
# os.makedirs(dir_path, exist_ok=True)
|
145 |
-
|
146 |
-
# for dir_path in process_dirs.values():
|
147 |
-
# os.makedirs(dir_path, exist_ok=True)
|
148 |
-
|
149 |
-
|
150 |
-
|
151 |
-
# # Logger configuration
|
152 |
-
# logging.basicConfig(level=logging.INFO)
|
153 |
-
|
154 |
-
# # Perform Inference
|
155 |
-
# def perform_inference(file_paths: Dict[str, str]):
|
156 |
-
# # Dictionary to map document types to their respective model directories
|
157 |
-
# model_dirs = {
|
158 |
-
# "aadhar_file": aadhar_model,
|
159 |
-
# "pan_file": pan_model,
|
160 |
-
# "cheque_file": cheque_model,
|
161 |
-
# "gst_file": gst_model,
|
162 |
-
# }
|
163 |
-
# try:
|
164 |
-
# # Dictionary to store results for each document type
|
165 |
-
# inference_results = {}
|
166 |
-
|
167 |
-
# # Loop through the file paths and perform inference
|
168 |
-
# for doc_type, file_path in file_paths.items():
|
169 |
-
# if doc_type in model_dirs:
|
170 |
-
# print(f"Processing {doc_type} using model at {model_dirs[doc_type]}")
|
171 |
-
|
172 |
-
# # Prepare batch for inference
|
173 |
-
# processed_file_p = file_path.split("&&")[0]
|
174 |
-
# unprocessed_file_path = file_path.split("&&")[1]
|
175 |
-
|
176 |
-
# images_path = [processed_file_p]
|
177 |
-
# inference_batch = prepare_batch_for_inference(images_path)
|
178 |
-
|
179 |
-
# # Prepare context for the specific document type
|
180 |
-
# # context = {"model_dir": model_dirs[doc_type]}
|
181 |
-
# #initialize s3 client
|
182 |
-
# client = s3_client()
|
183 |
-
|
184 |
-
# local_file_path= unprocessed_file_path
|
185 |
-
# bucket_name = "edgekycdocs"
|
186 |
-
|
187 |
-
# file_name = unprocessed_file_path.split("/")[-1]
|
188 |
-
|
189 |
-
|
190 |
-
|
191 |
-
|
192 |
-
# # context = aadhar_model
|
193 |
-
# if doc_type == "aadhar_file":
|
194 |
-
# context = aadhar_model
|
195 |
-
# processor = processor_aadhar
|
196 |
-
# name = "aadhar"
|
197 |
-
# attachemnt_num = 3
|
198 |
-
# folder_name = "aadhardocs"
|
199 |
-
|
200 |
-
|
201 |
-
# if doc_type == "pan_file":
|
202 |
-
# context = pan_model
|
203 |
-
# processor = processor_pan
|
204 |
-
# name = "pan"
|
205 |
-
# attachemnt_num = 2
|
206 |
-
# folder_name = "pandocs"
|
207 |
-
|
208 |
-
# if doc_type == "gst_file":
|
209 |
-
# context = gst_model
|
210 |
-
# processor = processor_gst
|
211 |
-
# name = "gst"
|
212 |
-
# attachemnt_num = 4
|
213 |
-
# folder_name = "gstdocs"
|
214 |
-
|
215 |
-
# if doc_type == "cheque_file":
|
216 |
-
# context = cheque_model
|
217 |
-
# processor = processor_cheque
|
218 |
-
# name = "cheque"
|
219 |
-
# attachemnt_num = 8
|
220 |
-
# folder_name = "bankchequedocs"
|
221 |
-
|
222 |
-
|
223 |
-
|
224 |
-
# # upload the document to s3 bucket here
|
225 |
-
|
226 |
-
|
227 |
-
# print("this is folder name",folder_name)
|
228 |
-
|
229 |
-
# response = client.upload_file(local_file_path,bucket_name,folder_name,file_name)
|
230 |
-
|
231 |
-
# print("The file has been uploaded to s3 bucket",response)
|
232 |
-
|
233 |
-
|
234 |
-
# # Perform inference (replace `handle` with your actual function)
|
235 |
-
# result = handle(inference_batch, context,processor,name)
|
236 |
-
# # result["attachment_url": response["url"]]
|
237 |
-
# result["attachment_url"] = response["url"]
|
238 |
-
# result["detect"] = True
|
239 |
-
|
240 |
-
# print("result required",result)
|
241 |
-
|
242 |
-
# # if result[""]
|
243 |
-
|
244 |
-
# # Store the result
|
245 |
-
# inference_results["attachment_{}".format(attachemnt_num)] = result
|
246 |
-
# else:
|
247 |
-
# print(f"Model directory not found for {doc_type}. Skipping.")
|
248 |
-
# # print(Javed)
|
249 |
-
|
250 |
-
# return inference_results
|
251 |
-
# except:
|
252 |
-
# return {
|
253 |
-
# "status": "error",
|
254 |
-
# "message": "Text extraction failed."
|
255 |
-
# }
|
256 |
-
|
257 |
-
|
258 |
-
# # Routes
|
259 |
-
# @app.get("/")
|
260 |
-
# def greet_json():
|
261 |
-
# return {"Hello": "World!"}
|
262 |
-
|
263 |
-
# @app.post("/api/aadhar_ocr")
|
264 |
-
# async def aadhar_ocr(
|
265 |
-
# aadhar_file: UploadFile = File(None),
|
266 |
-
# pan_file: UploadFile = File(None),
|
267 |
-
# cheque_file: UploadFile = File(None),
|
268 |
-
# gst_file: UploadFile = File(None),
|
269 |
-
# ):
|
270 |
-
# # try:
|
271 |
-
# # Handle file uploads
|
272 |
-
# file_paths = {}
|
273 |
-
# for file_type, folder in UPLOAD_DIRS.items():
|
274 |
-
# file = locals()[file_type] # Dynamically access the file arguments
|
275 |
-
# if file:
|
276 |
-
# # Save the file in the respective directory
|
277 |
-
# file_path = os.path.join(folder, file.filename)
|
278 |
-
|
279 |
-
# print("this is the filename",file.filename)
|
280 |
-
# with open(file_path, "wb") as buffer:
|
281 |
-
# shutil.copyfileobj(file.file, buffer)
|
282 |
-
# file_paths[file_type] = file_path
|
283 |
-
|
284 |
-
# # Log received files
|
285 |
-
# logging.info(f"Received files: {list(file_paths.keys())}")
|
286 |
-
# print("file_paths",file_paths)
|
287 |
-
|
288 |
-
# files = {}
|
289 |
-
# for key, value in file_paths.items():
|
290 |
-
# name = value.split("/")[-1].split(".")[0]
|
291 |
-
# id_type = key.split("_")[0]
|
292 |
-
# doc_type = value.split("/")[-1].split(".")[-1]
|
293 |
-
# f_path = value
|
294 |
-
|
295 |
-
# print("variables required",name,id_type,doc_type,f_path)
|
296 |
-
# preprocessing = doc_processing(name,id_type,doc_type,f_path)
|
297 |
-
# response = preprocessing.process()
|
298 |
-
|
299 |
-
# print("response after preprocessing",response)
|
300 |
-
|
301 |
-
# files[key] = response["output_p"] + "&&" + f_path
|
302 |
-
# # files["unprocessed_file_path"] = f_path
|
303 |
-
# print("response",response)
|
304 |
-
|
305 |
-
|
306 |
-
# # Perform inference
|
307 |
-
# result = perform_inference(files)
|
308 |
-
|
309 |
-
# print("this is the result we got",result)
|
310 |
-
# if "status" in list(result.keys()):
|
311 |
-
# raise Exception("Custom error message")
|
312 |
-
# # if result["status"] == "error":
|
313 |
-
|
314 |
-
|
315 |
-
|
316 |
-
# return {"status": "success", "result": result}
|
317 |
-
|
318 |
-
|
319 |
-
# # except Exception as e:
|
320 |
-
# # logging.error(f"Error processing files: {e}")
|
321 |
-
# # # raise HTTPException(status_code=500, detail="Internal Server Error")
|
322 |
-
# # return {
|
323 |
-
# # "status": 400,
|
324 |
-
# # "message": "Text extraction failed."
|
325 |
-
# # }
|
326 |
-
|
327 |
-
|
328 |
-
|
329 |
-
|
330 |
-
|
331 |
-
|
332 |
-
|
333 |
from fastapi import FastAPI, File, UploadFile, HTTPException
|
334 |
from fastapi.middleware.cors import CORSMiddleware
|
335 |
from typing import Dict
|
@@ -343,7 +11,7 @@ from fastapi import FastAPI, HTTPException, Request
|
|
343 |
from transformers import LayoutLMv3Processor, LayoutLMv3ForTokenClassification
|
344 |
from dotenv import load_dotenv
|
345 |
import urllib.parse
|
346 |
-
from utils import doc_processing
|
347 |
|
348 |
# Load .env file
|
349 |
load_dotenv()
|
@@ -475,59 +143,95 @@ for dir_path in process_dirs.values():
|
|
475 |
logging.basicConfig(level=logging.INFO)
|
476 |
|
477 |
|
478 |
-
# Perform Inference with optional S3 upload
|
479 |
def perform_inference(file_paths: Dict[str, str], upload_to_s3: bool):
|
480 |
model_dirs = {
|
481 |
"pan_file": pan_model,
|
482 |
"gst_file": gst_model,
|
483 |
"cheque_file": cheque_model,
|
484 |
}
|
|
|
485 |
try:
|
486 |
inference_results = {}
|
487 |
|
488 |
for doc_type, file_path in file_paths.items():
|
489 |
-
|
490 |
-
|
491 |
-
|
492 |
-
|
493 |
-
|
494 |
-
|
495 |
-
|
496 |
-
|
497 |
-
|
498 |
-
|
499 |
-
|
500 |
-
|
501 |
-
|
502 |
-
|
503 |
-
|
504 |
-
|
505 |
-
|
506 |
-
}
|
507 |
-
|
508 |
-
|
509 |
-
|
510 |
-
|
511 |
-
|
512 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
513 |
response = client.upload_file(
|
514 |
unprocessed_file_path, bucket_name, folder_name, file_name
|
515 |
)
|
516 |
print("The file has been uploaded to S3 bucket", response)
|
517 |
attachment_url = response["url"]
|
518 |
-
|
|
|
|
|
519 |
attachment_url = None
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
520 |
|
521 |
-
|
522 |
-
|
523 |
-
result["detect"] = True
|
524 |
|
525 |
-
|
526 |
-
|
527 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
528 |
|
529 |
return inference_results
|
530 |
-
|
|
|
|
|
531 |
return {"status": "error", "message": "Text extraction failed."}
|
532 |
|
533 |
|
@@ -566,21 +270,31 @@ async def aadhar_ocr(
|
|
566 |
print("file_paths", file_paths)
|
567 |
|
568 |
files = {}
|
569 |
-
for key, value in file_paths.items():
|
570 |
-
name = value.split("/")[-1].split(".")[0]
|
571 |
-
id_type = key.split("_")[0]
|
572 |
-
doc_type = value.split("/")[-1].split(".")[-1]
|
573 |
-
f_path = value
|
574 |
|
575 |
-
|
576 |
-
preprocessing = doc_processing(name, id_type, doc_type, f_path)
|
577 |
-
response = preprocessing.process()
|
578 |
|
579 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
580 |
|
581 |
-
|
582 |
-
|
583 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
584 |
|
585 |
# Perform inference
|
586 |
result = perform_inference(files, upload_to_s3)
|
@@ -639,16 +353,30 @@ async def document_ocr_s3(request: Request):
|
|
639 |
logging.info(f"Downloaded files: {list(file_paths.keys())}")
|
640 |
|
641 |
files = {}
|
642 |
-
for key, value in file_paths.items():
|
643 |
-
name = value.split("/")[-1].split(".")[0]
|
644 |
-
id_type = key.split("_")[0]
|
645 |
-
doc_type = value.split("/")[-1].split(".")[-1]
|
646 |
-
f_path = value
|
647 |
-
|
648 |
-
preprocessing = doc_processing(name, id_type, doc_type, f_path)
|
649 |
-
response = preprocessing.process()
|
650 |
|
651 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
652 |
|
653 |
result = perform_inference(files, upload_to_s3)
|
654 |
|
@@ -656,5 +384,3 @@ async def document_ocr_s3(request: Request):
|
|
656 |
raise HTTPException(status_code=500, detail="Custom error message")
|
657 |
|
658 |
return {"status": "success", "result": result}
|
659 |
-
|
660 |
-
print("hello")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
from fastapi import FastAPI, File, UploadFile, HTTPException
|
2 |
from fastapi.middleware.cors import CORSMiddleware
|
3 |
from typing import Dict
|
|
|
11 |
from transformers import LayoutLMv3Processor, LayoutLMv3ForTokenClassification
|
12 |
from dotenv import load_dotenv
|
13 |
import urllib.parse
|
14 |
+
from utils import doc_processing, extract_document_number_from_file
|
15 |
|
16 |
# Load .env file
|
17 |
load_dotenv()
|
|
|
143 |
logging.basicConfig(level=logging.INFO)
|
144 |
|
145 |
|
|
|
146 |
def perform_inference(file_paths: Dict[str, str], upload_to_s3: bool):
|
147 |
model_dirs = {
|
148 |
"pan_file": pan_model,
|
149 |
"gst_file": gst_model,
|
150 |
"cheque_file": cheque_model,
|
151 |
}
|
152 |
+
|
153 |
try:
|
154 |
inference_results = {}
|
155 |
|
156 |
for doc_type, file_path in file_paths.items():
|
157 |
+
processed_file_p = file_path.split("&&")[
|
158 |
+
0
|
159 |
+
] # Extracted document number or processed image
|
160 |
+
unprocessed_file_path = file_path.split("&&")[1] # Original file path
|
161 |
+
|
162 |
+
print(f"Processing {doc_type}: {processed_file_p}")
|
163 |
+
|
164 |
+
# Determine the attachment number based on the document type
|
165 |
+
attachment_num = {
|
166 |
+
"pan_file": 2,
|
167 |
+
"gst_file": 4,
|
168 |
+
"msme_file": 5,
|
169 |
+
"cin_llpin_file": 6,
|
170 |
+
"cheque_file": 8,
|
171 |
+
}.get(doc_type, None)
|
172 |
+
|
173 |
+
if attachment_num is None:
|
174 |
+
print(f"Skipping {doc_type}, not recognized.")
|
175 |
+
continue
|
176 |
+
|
177 |
+
# Upload file to S3 if required
|
178 |
+
if upload_to_s3:
|
179 |
+
client = s3_client()
|
180 |
+
bucket_name = "edgekycdocs"
|
181 |
+
if doc_type == "cin_llpin":
|
182 |
+
folder_name = f"{doc_type.replace('_', '')}docs"
|
183 |
+
else:
|
184 |
+
folder_name = f"{doc_type.split('_')[0]}docs"
|
185 |
+
|
186 |
+
file_name = unprocessed_file_path.split("/")[-1].replace(" ", "_")
|
187 |
+
|
188 |
+
try:
|
189 |
response = client.upload_file(
|
190 |
unprocessed_file_path, bucket_name, folder_name, file_name
|
191 |
)
|
192 |
print("The file has been uploaded to S3 bucket", response)
|
193 |
attachment_url = response["url"]
|
194 |
+
print(f"File uploaded to S3: {attachment_url}")
|
195 |
+
except Exception as e:
|
196 |
+
print(f"Failed to upload {file_name} to S3: {e}")
|
197 |
attachment_url = None
|
198 |
+
else:
|
199 |
+
attachment_url = None
|
200 |
+
# If it's an OCR-based extraction (CIN, MSME, LLPIN, PAN, Aadhaar), return the extracted number
|
201 |
+
if doc_type in ["msme_file", "cin_llpin_file", "aadhar_file"]:
|
202 |
+
result = {
|
203 |
+
"attachment_num": processed_file_p, # Extracted CIN, LLPIN, MSME, PAN, or Aadhaar number
|
204 |
+
"attachment_url": attachment_url,
|
205 |
+
"attachment_status": 200,
|
206 |
+
"detect": True,
|
207 |
+
}
|
208 |
+
else:
|
209 |
+
# If the document needs ML model inference (PAN, GST, Cheque)
|
210 |
+
if doc_type in model_dirs:
|
211 |
+
print(
|
212 |
+
f"Running ML inference for {doc_type} using {model_dirs[doc_type]}"
|
213 |
+
)
|
214 |
|
215 |
+
images_path = [processed_file_p]
|
216 |
+
inference_batch = prepare_batch_for_inference(images_path)
|
|
|
217 |
|
218 |
+
context = model_dirs[doc_type]
|
219 |
+
processor = globals()[f"processor_{doc_type.split('_')[0]}"]
|
220 |
+
name = doc_type.split("_")[0]
|
221 |
+
|
222 |
+
result = handle(inference_batch, context, processor, name)
|
223 |
+
result["attachment_url"] = attachment_url
|
224 |
+
result["detect"] = True
|
225 |
+
else:
|
226 |
+
print(f"No model found for {doc_type}, skipping inference.")
|
227 |
+
continue
|
228 |
+
|
229 |
+
inference_results[f"attachment_{attachment_num}"] = result
|
230 |
|
231 |
return inference_results
|
232 |
+
|
233 |
+
except Exception as e:
|
234 |
+
print(f"Error in perform_inference: {e}")
|
235 |
return {"status": "error", "message": "Text extraction failed."}
|
236 |
|
237 |
|
|
|
270 |
print("file_paths", file_paths)
|
271 |
|
272 |
files = {}
|
|
|
|
|
|
|
|
|
|
|
273 |
|
274 |
+
for key, f_path in file_paths.items():
|
|
|
|
|
275 |
|
276 |
+
name = os.path.splitext(os.path.basename(f_path))[0]
|
277 |
+
# Determine id_type: for cin_llpin_file, explicitly set id_type to "cin_llpin"
|
278 |
+
if key == "cin_llpin_file":
|
279 |
+
id_type = "cin_llpin"
|
280 |
+
else:
|
281 |
+
id_type = key.split("_")[0]
|
282 |
+
doc_type = os.path.splitext(f_path)[-1].lstrip(".")
|
283 |
|
284 |
+
if key in ["msme_file", "cin_llpin_file", "aadhar_file"]:
|
285 |
+
extracted_number = extract_document_number_from_file(f_path, id_type)
|
286 |
+
if not extracted_number:
|
287 |
+
logging.error(f"Failed to extract document number from {f_path}")
|
288 |
+
raise HTTPException(
|
289 |
+
status_code=400, detail=f"Invalid document format in {key}"
|
290 |
+
)
|
291 |
+
files[key] = extracted_number + "&&" + f_path
|
292 |
+
print("files", files[key])
|
293 |
+
else:
|
294 |
+
# For other files, use existing preprocessing.
|
295 |
+
preprocessing = doc_processing(name, id_type, doc_type, f_path)
|
296 |
+
response = preprocessing.process()
|
297 |
+
files[key] = response["output_p"] + "&&" + f_path
|
298 |
|
299 |
# Perform inference
|
300 |
result = perform_inference(files, upload_to_s3)
|
|
|
353 |
logging.info(f"Downloaded files: {list(file_paths.keys())}")
|
354 |
|
355 |
files = {}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
356 |
|
357 |
+
for key, f_path in file_paths.items():
|
358 |
+
name = f_path.split("/")[-1].split(".")[0]
|
359 |
+
if key == "cin_llpin_file":
|
360 |
+
id_type = "cin_llpin"
|
361 |
+
else:
|
362 |
+
id_type = key.split("_")[0]
|
363 |
+
# id_type = key.split("_")[0]
|
364 |
+
doc_type = f_path.split("/")[-1].split(".")[-1]
|
365 |
+
|
366 |
+
# For MSME and CIN/LLPIN files, extract document number via OCR and regex
|
367 |
+
if key in ["msme_file", "cin_llpin_file", "aadhar_file"]:
|
368 |
+
extracted_number = extract_document_number_from_file(f_path, id_type)
|
369 |
+
if not extracted_number:
|
370 |
+
logging.error(f"Failed to extract document number from {f_path}")
|
371 |
+
raise HTTPException(
|
372 |
+
status_code=400, detail=f"Invalid document format in {key}"
|
373 |
+
)
|
374 |
+
files[key] = extracted_number + "&&" + f_path
|
375 |
+
else:
|
376 |
+
# For other documents, use the existing ML model preprocessing
|
377 |
+
preprocessing = doc_processing(name, id_type, doc_type, f_path)
|
378 |
+
response = preprocessing.process()
|
379 |
+
files[key] = response["output_p"] + "&&" + f_path
|
380 |
|
381 |
result = perform_inference(files, upload_to_s3)
|
382 |
|
|
|
384 |
raise HTTPException(status_code=500, detail="Custom error message")
|
385 |
|
386 |
return {"status": "success", "result": result}
|
|
|
|
utils.py
CHANGED
@@ -1,71 +1,75 @@
|
|
1 |
import fitz
|
2 |
from PIL import Image
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
|
4 |
class doc_processing:
|
5 |
|
6 |
def __init__(self, name, id_type, doc_type, f_path):
|
7 |
-
|
8 |
self.name = name
|
9 |
self.id_type = id_type
|
10 |
self.doc_type = doc_type
|
11 |
self.f_path = f_path
|
12 |
# self.o_path = o_path
|
13 |
-
|
14 |
-
|
15 |
def pdf_to_image_scale(self):
|
16 |
pdf_document = fitz.open(self.f_path)
|
17 |
if self.id_type == "gst":
|
18 |
page_num = 2
|
19 |
else:
|
20 |
page_num = 0
|
21 |
-
|
22 |
page = pdf_document.load_page(page_num)
|
23 |
pix = page.get_pixmap() # Render page as a pixmap (image)
|
24 |
-
|
25 |
# Convert pixmap to PIL Image
|
26 |
image = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
|
27 |
-
|
28 |
original_width, original_height = image.size
|
29 |
-
|
30 |
-
print("original_width",original_width)
|
31 |
-
print("original_height",original_height)
|
32 |
|
|
|
|
|
33 |
|
34 |
new_width = (1000 / original_width) * original_width
|
35 |
new_height = (1000 / original_height) * original_height
|
36 |
-
|
37 |
-
print("new_width",new_width)
|
38 |
-
print("new_height",new_height)
|
39 |
-
# new_width =
|
40 |
-
# new_height =
|
41 |
image.resize((int(new_width), int(new_height)), Image.Resampling.LANCZOS)
|
42 |
-
output_path = "processed_images/{}/{}.jpeg".format(self.id_type,self.name)
|
43 |
image.save(output_path)
|
44 |
-
return
|
45 |
-
|
46 |
|
47 |
def scale_img(self):
|
48 |
-
|
49 |
|
50 |
-
print("path of file",self.f_path)
|
51 |
image = Image.open(self.f_path).convert("RGB")
|
52 |
original_width, original_height = image.size
|
53 |
-
|
54 |
-
print("original_width",original_width)
|
55 |
-
print("original_height",original_height)
|
56 |
|
|
|
|
|
57 |
|
58 |
new_width = (1000 / original_width) * original_width
|
59 |
new_height = (1000 / original_height) * original_height
|
60 |
-
|
61 |
-
print("new_width",new_width)
|
62 |
-
print("new_height",new_height)
|
63 |
-
# new_width =
|
64 |
-
# new_height =
|
65 |
image.resize((int(new_width), int(new_height)), Image.Resampling.LANCZOS)
|
66 |
-
output_path = "processed_images/{}/{}.jpeg".format(self.id_type,self.name)
|
67 |
image.save(output_path)
|
68 |
-
return {"success":200,"output_p":output_path}
|
69 |
|
70 |
def process(self):
|
71 |
if self.doc_type == "pdf":
|
@@ -76,12 +80,95 @@ class doc_processing:
|
|
76 |
return response
|
77 |
|
78 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
79 |
|
80 |
|
81 |
-
|
82 |
# files = {
|
83 |
# "aadhar_file": "/home/javmulla/model_one/test_images_aadhar/test_two.jpg",
|
84 |
-
# "pan_file": "/home/javmulla/model_one/test_images_pan/6ea33087.jpeg",
|
85 |
# "cheque_file": "/home/javmulla/model_one/test_images_cheque/0f81678a.jpeg",
|
86 |
# "gst_file": "/home/javmulla/model_one/test_images_gst/0a52fbcb_page3_image_0.jpg"
|
87 |
# }
|
@@ -89,7 +176,7 @@ class doc_processing:
|
|
89 |
|
90 |
# files = {
|
91 |
# "aadhar_file": "/home/javmulla/model_one/test_images_aadhar/test_two.jpg",
|
92 |
-
# "pan_file": "/home/javmulla/model_one/test_images_pan/6ea33087.jpeg",
|
93 |
# "cheque_file": "/home/javmulla/model_one/test_images_cheque/0f81678a.jpeg",
|
94 |
# "gst_file": "test_Images_folder/gst/e.pdf"
|
95 |
# }
|
@@ -102,11 +189,6 @@ class doc_processing:
|
|
102 |
# preprocessing = doc_processing(name,id_type,doc_type,f_path)
|
103 |
# response = preprocessing.process()
|
104 |
# print("response",response)
|
105 |
-
|
106 |
-
|
107 |
-
|
108 |
-
|
109 |
-
|
110 |
-
# id_type, doc_type, f_path
|
111 |
-
|
112 |
-
|
|
|
1 |
import fitz
|
2 |
from PIL import Image
|
3 |
+
import re
|
4 |
+
import io
|
5 |
+
import os
|
6 |
+
import logging
|
7 |
+
import shutil
|
8 |
+
from fastapi import FastAPI, UploadFile, File, HTTPException
|
9 |
+
from google.cloud import vision
|
10 |
+
from pdf2image import convert_from_path
|
11 |
+
|
12 |
|
13 |
class doc_processing:
|
14 |
|
15 |
def __init__(self, name, id_type, doc_type, f_path):
|
16 |
+
|
17 |
self.name = name
|
18 |
self.id_type = id_type
|
19 |
self.doc_type = doc_type
|
20 |
self.f_path = f_path
|
21 |
# self.o_path = o_path
|
22 |
+
|
|
|
23 |
def pdf_to_image_scale(self):
|
24 |
pdf_document = fitz.open(self.f_path)
|
25 |
if self.id_type == "gst":
|
26 |
page_num = 2
|
27 |
else:
|
28 |
page_num = 0
|
29 |
+
|
30 |
page = pdf_document.load_page(page_num)
|
31 |
pix = page.get_pixmap() # Render page as a pixmap (image)
|
32 |
+
|
33 |
# Convert pixmap to PIL Image
|
34 |
image = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
|
35 |
+
|
36 |
original_width, original_height = image.size
|
|
|
|
|
|
|
37 |
|
38 |
+
print("original_width", original_width)
|
39 |
+
print("original_height", original_height)
|
40 |
|
41 |
new_width = (1000 / original_width) * original_width
|
42 |
new_height = (1000 / original_height) * original_height
|
43 |
+
|
44 |
+
print("new_width", new_width)
|
45 |
+
print("new_height", new_height)
|
46 |
+
# new_width =
|
47 |
+
# new_height =
|
48 |
image.resize((int(new_width), int(new_height)), Image.Resampling.LANCZOS)
|
49 |
+
output_path = "processed_images/{}/{}.jpeg".format(self.id_type, self.name)
|
50 |
image.save(output_path)
|
51 |
+
return {"success": 200, "output_p": output_path}
|
|
|
52 |
|
53 |
def scale_img(self):
|
|
|
54 |
|
55 |
+
print("path of file", self.f_path)
|
56 |
image = Image.open(self.f_path).convert("RGB")
|
57 |
original_width, original_height = image.size
|
|
|
|
|
|
|
58 |
|
59 |
+
print("original_width", original_width)
|
60 |
+
print("original_height", original_height)
|
61 |
|
62 |
new_width = (1000 / original_width) * original_width
|
63 |
new_height = (1000 / original_height) * original_height
|
64 |
+
|
65 |
+
print("new_width", new_width)
|
66 |
+
print("new_height", new_height)
|
67 |
+
# new_width =
|
68 |
+
# new_height =
|
69 |
image.resize((int(new_width), int(new_height)), Image.Resampling.LANCZOS)
|
70 |
+
output_path = "processed_images/{}/{}.jpeg".format(self.id_type, self.name)
|
71 |
image.save(output_path)
|
72 |
+
return {"success": 200, "output_p": output_path}
|
73 |
|
74 |
def process(self):
|
75 |
if self.doc_type == "pdf":
|
|
|
80 |
return response
|
81 |
|
82 |
|
83 |
+
from google.cloud import vision
|
84 |
+
|
85 |
+
vision_client = vision.ImageAnnotatorClient()
|
86 |
+
|
87 |
+
|
88 |
+
def extract_document_number(ocr_text: str, id_type: str) -> str:
|
89 |
+
"""
|
90 |
+
Searches the OCR text for a valid document number based on regex patterns.
|
91 |
+
Checks for CIN, then MSME, and finally LLPIN.
|
92 |
+
"""
|
93 |
+
patterns = {
|
94 |
+
"cin": re.compile(r"([LUu]{1}[0-9]{5}[A-Za-z]{2}[0-9]{4}[A-Za-z]{3}[0-9]{6})"),
|
95 |
+
"msme": re.compile(r"(UDYAM-[A-Z]{2}-\d{2}-\d{7})"),
|
96 |
+
"llpin": re.compile(r"([A-Z]{3}-[0-9]{4})"),
|
97 |
+
"pan": re.compile(r"^[A-Z]{3}[PCHFTBALJGT][A-Z][\d]{4}[A-Z]$"),
|
98 |
+
"aadhaar": re.compile(r"^\d{12}$"),
|
99 |
+
}
|
100 |
+
|
101 |
+
if id_type == "cin_llpin":
|
102 |
+
# Try CIN first
|
103 |
+
match = patterns["cin"].search(ocr_text)
|
104 |
+
if match:
|
105 |
+
return match.group(0)
|
106 |
+
# If CIN not found, try LLPIN
|
107 |
+
match = patterns["llpin"].search(ocr_text)
|
108 |
+
if match:
|
109 |
+
return match.group(0)
|
110 |
+
elif id_type in patterns:
|
111 |
+
match = patterns[id_type].search(ocr_text)
|
112 |
+
if match:
|
113 |
+
return match.group(0)
|
114 |
+
|
115 |
+
return None
|
116 |
+
|
117 |
+
|
118 |
+
def run_google_vision(file_content: bytes) -> str:
|
119 |
+
"""
|
120 |
+
Uses Google Vision OCR to extract text from binary file content.
|
121 |
+
"""
|
122 |
+
image = vision.Image(content=file_content)
|
123 |
+
response = vision_client.text_detection(image=image)
|
124 |
+
texts = response.text_annotations
|
125 |
+
if texts:
|
126 |
+
# The first annotation contains the complete detected text
|
127 |
+
return texts[0].description
|
128 |
+
return ""
|
129 |
+
|
130 |
+
|
131 |
+
def extract_text_from_file(file_path: str) -> str:
|
132 |
+
"""
|
133 |
+
Reads the file from file_path. If it's a PDF, converts only the first page to an image,
|
134 |
+
then runs OCR using Google Vision.
|
135 |
+
"""
|
136 |
+
if file_path.lower().endswith(".pdf"):
|
137 |
+
try:
|
138 |
+
# Open the PDF file using PyMuPDF (fitz)
|
139 |
+
pdf_document = fitz.open(file_path)
|
140 |
+
page = pdf_document.load_page(0) # Load the first page
|
141 |
+
pix = page.get_pixmap() # Render page as an image
|
142 |
+
|
143 |
+
# Convert pixmap to PIL Image
|
144 |
+
image = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
|
145 |
+
|
146 |
+
# Convert image to bytes for OCR
|
147 |
+
img_byte_arr = io.BytesIO()
|
148 |
+
image.save(img_byte_arr, format="JPEG")
|
149 |
+
file_content = img_byte_arr.getvalue()
|
150 |
+
|
151 |
+
except Exception as e:
|
152 |
+
logging.error(f"Error converting PDF to image: {e}")
|
153 |
+
return ""
|
154 |
+
else:
|
155 |
+
with open(file_path, "rb") as f:
|
156 |
+
file_content = f.read()
|
157 |
+
|
158 |
+
return run_google_vision(file_content)
|
159 |
+
|
160 |
+
|
161 |
+
def extract_document_number_from_file(file_path: str, id_type: str) -> str:
|
162 |
+
"""
|
163 |
+
Extracts the document number (CIN, MSME, or LLPIN) from the file at file_path.
|
164 |
+
"""
|
165 |
+
ocr_text = extract_text_from_file(file_path)
|
166 |
+
return extract_document_number(ocr_text, id_type)
|
167 |
|
168 |
|
|
|
169 |
# files = {
|
170 |
# "aadhar_file": "/home/javmulla/model_one/test_images_aadhar/test_two.jpg",
|
171 |
+
# "pan_file": "/home/javmulla/model_one/test_images_pan/6ea33087.jpeg",
|
172 |
# "cheque_file": "/home/javmulla/model_one/test_images_cheque/0f81678a.jpeg",
|
173 |
# "gst_file": "/home/javmulla/model_one/test_images_gst/0a52fbcb_page3_image_0.jpg"
|
174 |
# }
|
|
|
176 |
|
177 |
# files = {
|
178 |
# "aadhar_file": "/home/javmulla/model_one/test_images_aadhar/test_two.jpg",
|
179 |
+
# "pan_file": "/home/javmulla/model_one/test_images_pan/6ea33087.jpeg",
|
180 |
# "cheque_file": "/home/javmulla/model_one/test_images_cheque/0f81678a.jpeg",
|
181 |
# "gst_file": "test_Images_folder/gst/e.pdf"
|
182 |
# }
|
|
|
189 |
# preprocessing = doc_processing(name,id_type,doc_type,f_path)
|
190 |
# response = preprocessing.process()
|
191 |
# print("response",response)
|
192 |
+
|
193 |
+
|
194 |
+
# id_type, doc_type, f_path
|
|
|
|
|
|
|
|
|
|