File size: 55,005 Bytes
3e65ce8 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 | """
FastAPI Backend Application for Document Processing and Management
This application provides a comprehensive backend service for processing and managing various types of documents,
including images, SMS data, contacts, and YouTube links. It integrates with multiple external services and APIs
to provide document processing, storage, and management capabilities.
Main Components:
1. API Setup and Configuration:
- FastAPI application with CORS middleware
- Firebase, Google Sheets, Drive, and YouTube API integrations
- Gemini AI model configuration for image processing
2. Core File Management Functions:
- move_file_to_folder: Handles file organization in Google Drive
- update_user_sheet: Manages data updates in Google Sheets with backup capabilities
3. Image Processing Functions:
- request_gpt4o_completion: Processes images using GPT-4 Vision or Gemini
- process_photo: Endpoint for handling image processing requests
- update_user_sheets_and_folders: Organizes processed image data
4. Sheet Management Functions:
- copy_sms_sheet: Creates new sheets for SMS data
- edit_spreadsheet: Manages template-based sheet creation
- check_user_doc: Handles user verification and transaction records
5. Data Synchronization Functions:
- sync-data endpoint: Manages contacts and SMS data synchronization
- update_fb_transaction: Updates Firebase transaction records
6. YouTube Integration:
- share-target-handle endpoint: Processes YouTube links
- Functions for video information extraction and summarization
7. Business Information Functions:
- search_business_info: Business information lookup in reference spreadsheet
8. Utility Functions:
- Helper functions for data conversion and formatting
- Error handling and logging utilities
Dependencies:
- FastAPI for API framework
- Firebase Admin for user management
- Google API clients for Drive and Sheets integration
- Various AI models for image and text processing
"""
from fastapi import FastAPI, HTTPException, UploadFile, File, Request, BackgroundTasks, Form
from fastapi.middleware.cors import CORSMiddleware
from pydantic import BaseModel
from httpx import Timeout
import httpx
import logging
import base64
import firebase_admin
from firebase_admin import credentials
from firebase_admin import firestore
import json
from datetime import datetime
import pytz
from typing import List, Optional, Dict
from google.oauth2 import service_account
from googleapiclient.discovery import build
from io import BytesIO
import google.generativeai as genai
import os
from google.cloud import vision
from typing import Tuple
from base64 import b64encode
from openai import OpenAI
from fuzzywuzzy import fuzz
from youtube_transcript_api import YouTubeTranscriptApi
from langchain_community.document_loaders import YoutubeLoader
import re
import asyncio
# start application
app = FastAPI()
# allow all origins
app.add_middleware(
CORSMiddleware,
allow_origins=["*"], # Allows all origins
allow_credentials=True, # Allows credentials (such as cookies) to be sent with requests
allow_methods=["*"], # Allows all methods
allow_headers=["*"], # Allows all headers
)
# set up logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
logging.info("Application starting up")
request_timeout = Timeout(1000.0, connect=600.0)
# set up firebase
# Load Firebase configuration from a file
with open('/app/secrets/fb_secret.json', 'r') as f:
firebase_configuration = json.load(f)
firebase_credentials = credentials.Certificate(firebase_configuration)
firebase_admin.initialize_app(firebase_credentials, {
'projectId': firebase_configuration['project_id'],
})
firestore_db = firestore.client()
users_collection_ref = firestore_db.collection('users')
transactions_collection_ref = firestore_db.collection('transactions')
SCOPES = [
'https://www.googleapis.com/auth/spreadsheets',
'https://www.googleapis.com/auth/drive',
'https://www.googleapis.com/auth/youtube.force-ssl' # Add YouTube scope
]
with open('/app/secrets/openai_key.txt', 'r') as f:
OPENAI_KEY = f.read()
APICredential = service_account.Credentials.from_service_account_file(
'/app/secrets/googleapi_secret.json', scopes=SCOPES)
sheet_service = build('sheets', 'v4', credentials=APICredential)
drive_service = build('drive', 'v3', credentials=APICredential)
# Add YouTube API key setup
YOUTUBE_API_KEY = os.getenv('YOUTUBE_API_KEY') # Add to your environment variables
youtube_service = build('youtube', 'v3', developerKey=YOUTUBE_API_KEY) # Use API key instead of OAuth
with open('/app/secrets/gemini_key.txt', 'r') as f:
api_key = f.read()
genai.configure(api_key=api_key)
# Create the model
generation_config = {
"temperature": 1,
"top_p": 0.95,
"top_k": 64,
"max_output_tokens": 8192,
"response_mime_type": "application/json",
}
model = genai.GenerativeModel(
model_name="gemini-1.5-flash",
generation_config=generation_config,
# safety_settings = Adjust safety settings
# See https://ai.google.dev/gemini-api/docs/safety-settings
)
# first three are "๋ฑ๋ก์ผ์", "์ธ๋ค์ผ", "๋ฐ๋ก๊ฐ๊ธฐ",
receipt_sheet_headers = ['๋ฐํ์ผ', '์ํธ', '์ฌ์
์๋ฒํธ', 'ํฉ๊ณ๊ธ์ก', '๋ด์ญ', '์นด๋๋ฒํธ', '์นด๋์ข
๋ฅ', '์น์ธ๋ฒํธ', '๊ธฐํ']
# at index 1 '๋ฑ๋ก ์ผ์', at last index '๋ช
ํจ๋ณด๊ธฐ'
business_card_sheet_headers = ['์ด๋ฆ', 'ํ์ฌ๋ช
', '์์ ๋ฐ ์ง์', '์ฃผ์', '์ ํ' ,'ํด๋ํฐ', 'ํฉ์ค','e-mail','ํํ์ด์ง']
sms_sheet_headers = ['๋ ์ง', '๊ณ์ข', '์
๊ธ', '์ถ๊ธ', '์์ก', '๋ฌธ์']
contact_sheet_headers = ['์ด๋ฆ', '์ ํ๋ฒํธ1', '์ ํ๋ฒํธ2', '์ ํ๋ฒํธ3', '์ด๋ฉ์ผ์ฃผ์1', '์ด๋ฉ์ผ์ฃผ์2', '์ด๋ฉ์ผ์ฃผ์3', '๊ทธ๋ฃน']
receipts_ss = 1395967745
business_cards_ss = 1733555840
contacts_ss = 1729750548
sms_ss = 1891574758
shared_links_ss = 289914391
kst = pytz.timezone('Asia/Seoul')
class SheetUpdateRequest(BaseModel):
target_sheet_id: int
data: list
def convert_dicts_to_list(dicts: List[Dict], headers: List[str], add_link: bool = False,
image_id: str = '', link_text: str = '',
link_position: int = -1) -> List[List[str]]:
rows = []
# timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
timestamp = datetime.now(kst).strftime("%Y-%m-%d %H:%M:%S")
for dict_item in dicts:
# row = list(dict_item.values())
# row = [str(value) for value in dict_item.values()]
row = [str(dict_item.get(header, '')) for header in headers]
# Always add timestamp to the first index
row.insert(0, timestamp)
if add_link:
# Ensure the list length is at least 9
while len(row) < 9:
row.append('')
if link_position == -1: # Append link at the end
row.append(f'=HYPERLINK("https://drive.google.com/file/d/{image_id}/view?usp=sharing", "{link_text}")')
else:
row.insert(link_position, f'=HYPERLINK("https://drive.google.com/file/d/{image_id}/view?usp=sharing", "{link_text}")')
rows.append(row)
# print(rows)
return rows
async def download_file_from_drive(file_id: str) -> Tuple[bytes, str]:
"""
Downloads a file from Google Drive using the file ID
and returns the file content as bytes and the MIME type.
"""
try:
url = f"https://drive.google.com/uc?export=download&id={file_id}"
async with httpx.AsyncClient(follow_redirects=True) as client: # Enable redirect following
response = await client.get(url)
if response.status_code == 200:
return response.content, response.headers.get('content-type', 'application/octet-stream')
else:
raise HTTPException(
status_code=500,
detail=f"Failed to download file, status code: {response.status_code}"
)
except Exception as e:
logging.error(f"Error downloading file from Drive: {e}")
raise HTTPException(status_code=500, detail="Failed to download file from Drive")
async def request_gpt4o_completion(image_id: str, user_credit: int, use_gpt4: bool = False):
"""
Processes images using either GPT-4 Vision or Gemini for text extraction and analysis.
Args:
image_id (str): The Google Drive ID of the image to process
user_credit (int): Available user credits for processing
use_gpt4 (bool): Whether to use GPT-4 Vision instead of Gemini
Returns:
str: JSON string containing extracted information
"""
try:
# Step 1: Download the image file from Google Drive
file_content, mime_type = await download_file_from_drive(image_id)
if use_gpt4:
# Convert image to base64 for GPT-4 Vision
base64_image = b64encode(file_content).decode('utf-8')
client = OpenAI(api_key=OPENAI_KEY)
response = client.chat.completions.create(
model="gpt-4o",
messages=[
{
"role": "system",
"content": """You are a receipt and business card data extractor. Extract information EXACTLY in the specified format.
For receipts, follow this EXACT format and order:
1. "๋ฐํ์ผ": Must be in format "M/D/YYYY HH:MM:SS"
2. "์ํธ": Store/business name only
3. "์ฌ์
์๋ฒํธ": Must be in format "###-##-#####" (if present)
4. "ํฉ๊ณ๊ธ์ก": Total amount with comma for thousands (e.g., "4,300")
5. "๋ด์ญ": List items with format "item price quantity" (e.g., "๋ณดํต 7g 10ํต 430 4,300")
6. "์นด๋๋ฒํธ": Must include asterisks for hidden numbers (e.g., "5286-6420-****-077")
7. "์นด๋์ข
๋ฅ": Card type only
8. "์น์ธ๋ฒํธ": Approval number only
9. "๊ธฐํ": All remaining information as key-value pairs separated by commas
Example receipt:
{
"receipts": [{
"๋ฐํ์ผ": "3/6/2024 15:31:00",
"์ํธ": "์ํฅ๋ฐฐ๊ณง๋์ฐ์ฒด๊ตญ",
"์ฌ์
์๋ฒํธ": "101-83-02925",
"ํฉ๊ณ๊ธ์ก": "4,300",
"๋ด์ญ": "๋ณดํต 7g 10ํต 430 4,300",
"์นด๋๋ฒํธ": "5286-6420-****-077",
"์นด๋์ข
๋ฅ": "NH๊ธฐ์
์ฒดํฌ",
"์น์ธ๋ฒํธ": "49980444",
"๊ธฐํ": "์ ํ: 031-8042-2047, ์ฃผ์: ๊ฒฝ๊ธฐ๋ ์ํฅ์ ์ ์๋ 2543, ๊ณ ๊ฐ๋ฌธ์ ์ ํ: 1588-1300"
}],
"busi_cards": []
}
For business cards, follow this EXACT format and order:
1. "์ด๋ฆ": Full name
2. "ํ์ฌ๋ช
": Company name
3. "์์ ๋ฐ ์ง์": Position and department
4. "์ฃผ์": Address with postal code in format "์ฃผ์ (์ฐํธ๋ฒํธ) ์ฝ๋"
5. "์ ํ": Office phone with hyphens
6. "ํด๋ํฐ": Mobile with hyphens (e.g., "010-0000-0000")
7. "ํฉ์ค": Fax number with hyphens
8. "e-mail": Email address
9. "ํํ์ด์ง": Website URL
Output must be valid JSON with "receipts" and "busi_cards" arrays."""
},
{
"role": "user",
"content": [
{"type": "text", "text": "Extract the information from this image following the exact format specified."},
{
"type": "image_url",
"image_url": {
"url": f"data:{mime_type};base64,{base64_image}"
}
}
]
}
],
max_tokens=4096,
temperature=1,
response_format={ "type": "json_object" }
)
return response.choices[0].message.content
else:
# Existing Gemini implementation
# Step 3: Get text data from the image using Google Cloud Vision
client = vision.ImageAnnotatorClient()
image = vision.Image(content=file_content)
response = client.text_detection(image=image)
texts = response.text_annotations
if response.error.message:
logging.error(f"Error in Google Cloud Vision API: {response.error.message}")
raise Exception(
"{}\nFor more info on error messages, check: "
"https://cloud.google.com/apis/design/errors".format(response.error.message)
)
# Extract all detected text
extracted_text = texts[0].description if texts else ""
# Step 4: Prepare the prompt for Gemini
prompt = f'''
#Direction
You are an employee of finance department of a company. For each task well done, you will be rewarded $1,000 bonus.
The boss has come to your office and gave you a task of transfering the content of receipts and business cards onto a google spreadsheet.
He hands you two things.
One, is a paper containing guideline and example.
Two, is an OCR text.
#Guideline
-strictly adhere to the given content of OCR text.
-it could be of receipt(s) or business card(s) but not both
-sort any other info that couldn't be classified as "๊ธฐํ"
-format the extracted information as a JSON object with two main keys: 'receipts' and 'busi_cards'.
-ensure the total number of receipts and business cards combined does not exceed 500.
#Example
##Receipts
Input
์์ฑ๋ง์ผ
์ฌ์
์๋ฒํธ: 727-27-01455
๋ํ์:ํ์ ์ฑ
์ฃผ
์: ๊ฒฝ๊ธฐ ์ํฅ์ ๋ฐฐ๊ณง3๋ก 96
์ ํ ๋ฒํธ: 031-431-1544
ํ๋งค์ผ: 24-02-23 20:10, ๊ธ์์ผ ๊ณ์ฐ๋:001
NO. ์ํ๋ช
๋จ๊ฐ ์๋ ๊ธ์ก
001 ๋ํ๋ฆฌ๋ฒ์ฏ
200092
1,000
1. 1,000 #
002 ์๋ฐฐ์ถ
200071
(#)๋ฉด์ธ๋ฌผํ:
ํฉ
๊ณ:
์ ์ฉ์นด๋์ง๋ถ:
โ
์นด๋์ ์ฉ์น์ธ
็ซ
1,800 1 1.800 #
2,800
2,800
2,800
๊ฐ๋งน์ ๋ช
์์ฑ๋ง์ผ
์นด๋๋ฒํธ
4673-09**-****-515*
์นด๋๋ช
: KB๊ตญ๋ฏผ์ฒดํฌ
์ ํ๋งค์
: KB๊ตญ๋ฏผ์นด๋ ๋ฌด์๋ช
: 00111521584
์น์ธ๊ธ์ก: 2,800
(์ผ์๋ถ)
์น์ธ๋ฒํธ: 30014507, ์ ํNo:201036
์ ์ถ VAN: JTNET-๋ฆฌ๋๊ธฐ
์ ์์น์ธ
๊ฐ์ฌํฉ๋๋ค.
๊ฑฐ๋NO:0223007835 ๊ณ์ฐ์: ๊ด๋ฆฌ์(001)
2502230078357
Output
๋ฐํ์ผ: 2024/02/23 20:10
์ํธ: ์์ฑ๋ง์ผ
์ฌ์
์๋ฒํธ: 727-27-01455
ํฉ๊ณ๊ธ์ก: 2,800
๋ด์ญ:
๋ํ๋ฆฌ๋ฒ์ฏ 1,000์ 1๊ฐ
์๋ฐฐ์ถ 1,800์ 1๊ฐ
์นด๋๋ฒํธ: 4673-09**-****-515*
์นด๋์ข
๋ฅ: KB๊ตญ๋ฏผ์ฒดํฌ
์น์ธ๋ฒํธ: 30014507
๊ธฐํ: ๋ํ์: ํ์ ์ฑ, ์ฃผ์: ๊ฒฝ๊ธฐ ์ํฅ์ ๋ฐฐ๊ณง3๋ก 96, ์ ํ ๋ฒํธ: 031-431-1544, ๋ฉด์ธ๋ฌผํ: 2,800, ํฉ๊ณ: 2,800, ์ ์ฉ์นด๋์ง๋ถ:2,800, ์ ํNo:201036, ์ ์ถ VAN: JTNET-๋ฆฌ๋๊ธฐ, ๊ฑฐ๋NO:0223007835 ๊ณ์ฐ์: ๊ด๋ฆฌ์(001)
##Business Cards
Input
๋ฐ์ฅ์
์์ดํ๋ฆฌ๋ง
ํ์ฅ/์ ์ฑ
์ฌ์
ํ
R&D์ฌ์
์ค
Over the MIRACLE
๊ฒฝ๊ธฐ๋ ํ์ฑ์ ์ ๋จ๋ฉด ๋ง๋
๋ก 98๋ฒ๊ธธ 55 10์ธต (์ฐ) 18523
Mobile 010-9582-0925
Tel (031) 000-0000
Fax (031) 000-0000
Email iprima@iprima.com
www.iprima.com
Output
์ด๋ฆ: ๋ฐ์ฅ์
ํ์ฌ๋ช
: ์์ดํ๋ฆฌ๋ง
์์ ๋ฐ ์ง์: ํ์ฅ/์ ์ฑ
์ฌ์
ํ R&D์ฌ์
์ค
์ฃผ์: ๊ฒฝ๊ธฐ๋ ํ์ฑ์ ์ ๋จ๋ฉด ๋ง๋
๋ก 98๋ฒ๊ธธ 55 (์ฐํธ๋ฒํธ) 18523
์ ํ: (031) 000-0000
ํด๋ํฐ: (031) 000-0000
ํฉ์ค: 010-0000-0000
e-mail: iprima@gmail.com
ํํ์ด์ง: www.iprima.com
๊ธฐํ: Over the MIRACLE
Image content: {extracted_text}
'''
logging.info("Prompt prepared for Gemini model: " + prompt)
# Generate content using the Gemini model
response = model.generate_content(
contents=[prompt]
)
if response.text:
logging.info("Parsing Gemini model response")
json_response = json.loads(response.text)
logging.info(f"JSON response parsed: {response.text}")
return json.dumps(json_response)
else:
logging.error("Gemini model did not return a text response")
raise Exception("Gemini model did not return a text response")
except Exception as e:
logging.error(f"Error in request_gpt4o_completion: {str(e)}")
raise HTTPException(status_code=500, detail=f"Failure: {str(e)}")
async def move_file_to_folder(file_id, current_parents, new_parents):
"""
Moves a file to specified folders in Google Drive while managing parent folders.
Args:
file_id (str): The ID of the file to move
current_parents (list/str): Current parent folder(s) to remove from
new_parents (list/str): New parent folder(s) to add to
Returns:
None
"""
try:
# Ensure current_parents is a list of parent IDs
if not isinstance(current_parents, list):
current_parents = [current_parents]
if not isinstance(new_parents, list):
new_parents = [new_parents]
# Retrieve the existing parents to remove
file = drive_service.files().get(fileId=file_id, fields='parents').execute()
existing_parents = file.get('parents')
logging.info(f"Existing parents of the file {file_id}: {existing_parents}")
# Remove only the current parents
parents_to_remove = [parent for parent in current_parents if parent in existing_parents]
parents_to_add = [parent for parent in new_parents if parent not in existing_parents]
previous_parents = ",".join(parents_to_remove)
logging.info(f"Parents to remove: {parents_to_remove}")
logging.info(f"Parents to add: {parents_to_add}")
# Move the file to the new folders while keeping it in yungsoogi folder
if parents_to_add:
file = drive_service.files().update(
fileId=file_id,
addParents=",".join(parents_to_add),
removeParents=previous_parents,
fields='id, parents'
).execute()
logging.info(f"File {file_id} moved to new folders {new_parents}.")
else:
logging.info(f"File {file_id} already in the target folders {new_parents}.")
except Exception as e:
logging.error(f"Failed to move file {file_id} to new folders: {e}")
async def update_user_sheet(spreadsheet_id:str, sheet_name:str, data: List[List[str]], is_reset: Optional[bool] = False):
"""
Updates a user's Google Sheet with new data, optionally creating a backup.
Args:
spreadsheet_id (str): The ID of the target spreadsheet
sheet_name (str): Name of the sheet to update
data (List[List[str]]): The data to write to the sheet
is_reset (bool, optional): Whether to create a backup before updating
Returns:
None
"""
print(f"Spreadsheet ID: {spreadsheet_id}, Sheet Name: {sheet_name}, Data: {data}")
# Get all the sheets in the spreadsheet
sheet_metadata = sheet_service.spreadsheets().get(spreadsheetId=spreadsheet_id).execute()
sheets = sheet_metadata.get('sheets', '')
# Find the sheet by name
sheet = next((sheet for sheet in sheets if sheet['properties']['title'] == sheet_name), None)
if not sheet:
raise ValueError(f"Sheet '{sheet_name}' not found in the spreadsheet.")
sheet_id = sheet['properties']['sheetId']
# Rest of the function remains the same
no_of_rows = len(data)
no_of_cols = len(data[0])
if is_reset:
new_sheet_name = f"{sheet_name} {datetime.now(kst).strftime('%Y-%m-%d %H:%M')}"
duplicate_requests = [{
"duplicateSheet": {
"sourceSheetId": sheet_id,
"newSheetName": new_sheet_name
}
}]
duplicate_response = sheet_service.spreadsheets().batchUpdate(
spreadsheetId=spreadsheet_id,
body={
'requests': duplicate_requests
}
).execute()
sheet_id = duplicate_response['replies'][0]['duplicateSheet']['properties']['sheetId']
sheet_name = new_sheet_name
# Insert new rows
requests = [
{
"updateSheetProperties": {
"properties": {
"sheetId": sheet_id,
"hidden": False
},
"fields": "hidden"
}
},
{
"insertDimension": {
"range": {
"sheetId": sheet_id,
"dimension": "ROWS",
"startIndex": 1,
"endIndex": no_of_rows + 1
},
"inheritFromBefore": False,
}
}]
response = sheet_service.spreadsheets().batchUpdate(
spreadsheetId=spreadsheet_id,
body={
'requests': requests
}
).execute()
update_body = {
'values': data
}
start_column = 'A'
end_column = chr(ord(start_column) + no_of_cols - 1)
range_to_update = f'{sheet_name}!{start_column}2:{end_column}{no_of_rows + 1}'
result = sheet_service.spreadsheets().values().update(
spreadsheetId=spreadsheet_id,
range=range_to_update,
valueInputOption='USER_ENTERED',
body=update_body
).execute()
# Format the cells
for row_index, row in enumerate(data):
for col_index, cell_value in enumerate(row):
if cell_value.startswith('=HYPERLINK'):
color = {"red": 0, "green": 0, "blue": 1} # Blue for hyperlinks
else:
color = {"red": 0, "green": 0, "blue": 0} # Black for other text
requests = [
{
"repeatCell": {
"range": {
"sheetId": sheet_id,
"startRowIndex": row_index + 1,
"endRowIndex": row_index + 2,
"startColumnIndex": col_index,
"endColumnIndex": col_index + 1
},
"cell": {
"userEnteredFormat": {
"textFormat": {
"foregroundColor": color
}
}
},
"fields": "userEnteredFormat.textFormat.foregroundColor"
}
}
]
response = sheet_service.spreadsheets().batchUpdate(
spreadsheetId=spreadsheet_id,
body={
'requests': requests
}
).execute()
async def copy_sms_sheet(phone_no: str, spreadsheet_id: str):
"""
Creates a new sheet for SMS data by copying a template.
Args:
phone_no (str): Phone number to create sheet for
spreadsheet_id (str): Target spreadsheet ID
Returns:
str: ID of the newly created sheet
"""
requests = [
{
"duplicateSheet": {
"sourceSheetId": sms_ss,
"newSheetName": 'SMS ' + phone_no
}
}
]
response = sheet_service.spreadsheets().batchUpdate(
spreadsheetId=spreadsheet_id,
body={
'requests': requests
}
).execute()
print(response)
new_sheet_id = response['replies'][0]['duplicateSheet']['properties']['sheetId']
unhide_request = [{
"updateSheetProperties": {
"properties": {
"sheetId": new_sheet_id,
"hidden": False
},
"fields": "hidden"
}
}]
sheet_service.spreadsheets().batchUpdate(
spreadsheetId=spreadsheet_id,
body={
'requests': unhide_request
}
).execute()
return new_sheet_id
async def update_fb_transaction(transaction_ref: firestore.DocumentReference, no_sms: Optional[int] = 0, no_contacts: Optional[int] = 0, no_receipts: Optional[int] = 0, no_business_cards: Optional[int] = 0):
try:
# Update the transaction
transaction_ref.update({
"no_sms": firestore.Increment(no_sms),
"no_contacts": firestore.Increment(no_contacts),
"no_receipts": firestore.Increment(no_receipts),
"no_business_cards": firestore.Increment(no_business_cards)
})
return {"status": "Success"}
except Exception as e:
logging.error(f"Error updating transaction: {e}")
return {"status": f"Error: {str(e)}"}
async def get_youtube_transcript_url(video_id: str) -> str:
try:
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
'Accept-Language': 'ko,en;q=0.9'
}
url = f"https://www.youtube.com/watch?v={video_id}"
async with httpx.AsyncClient() as client:
response = await client.get(url, headers=headers)
page_content = response.text
# Look for timedtext URLs
timedtext_pattern = r'"baseUrl":"(https://www\.youtube\.com/api/timedtext[^"]+)"'
matches = re.finditer(timedtext_pattern, page_content)
urls = {} # Dictionary to store language:url pairs
for match in matches:
url = match.group(1).replace('\\u0026', '&')
# Extract language from URL
lang_match = re.search(r'lang=(\w+)', url)
if lang_match:
lang = lang_match.group(1)
urls[lang] = url
if urls:
# Try languages in order of preference
if 'ko' in urls:
logging.info("Found Korean transcript")
return urls['ko']
elif 'en' in urls:
logging.info("Found English transcript")
return urls['en']
else:
# Get first available language
lang = next(iter(urls))
logging.info(f"Found {lang.upper()} transcript")
return urls[lang]
else:
logging.warning("No transcript URLs found in the page content")
return "No transcript URLs found"
except Exception as e:
logging.error(f"Error in get_youtube_transcript_url: {str(e)}")
return f"Error: {str(e)}"
async def process_youtube_video(video_id: str, video_title: str = "") -> dict:
try:
# Get video details from YouTube Data API
video_response = youtube_service.videos().list(
part='snippet',
id=video_id
).execute()
if not video_response.get('items'):
return {
"title": video_title,
"summary": "๋น๋์ค๋ฅผ ์ฐพ์ ์ ์์ต๋๋ค.",
"key_points": [],
"timestamps": {}
}
video_info = video_response['items'][0]['snippet']
video_title = video_info.get('title', video_title)
description = video_info.get('description', '')
# Get transcript URL
transcript_url = await get_youtube_transcript_url(video_id)
if not transcript_url:
return {
"title": video_title,
"summary": "์๋ง์ ์ฐพ์ ์ ์์ต๋๋ค.",
"key_points": [],
"timestamps": {}
}
# Get the actual captions
async with httpx.AsyncClient() as client:
response = await client.get(transcript_url)
if response.status_code != 200:
return {
"title": video_title,
"summary": "์๋ง์ ๊ฐ์ ธ์ค๋๋ฐ ์คํจํ์ต๋๋ค.",
"key_points": [],
"timestamps": {}
}
full_transcript = response.text
# Generate summary using Gemini
prompt = """
You are a professional content summarizer. Summarize the following YouTube video transcript
in Korean. Focus on the key points and main ideas. Keep the summary concise but informative.
Video Title: {title}
Description: {description}
Transcript:
{transcript}
Please format the response as a JSON object with the following structure:
{{
"title": "{title}",
"summary": "Comprehensive summary in Korean",
"key_points": ["Key point 1", "Key point 2", "..."],
"timestamps": {{"topic": "timestamp"}} (if any significant timestamps are mentioned)
}}
"""
response = model.generate_content(
prompt.format(
title=video_title,
description=description,
transcript=full_transcript
)
)
return json.loads(response.text)
except Exception as e:
logging.error(f"Error in summary generation: {str(e)}")
return {
"title": video_title,
"summary": "๋์์ ์ฒ๋ฆฌ ์ค ์ค๋ฅ๊ฐ ๋ฐ์ํ์ต๋๋ค.",
"key_points": [],
"timestamps": {}
}
def extract_youtube_id(url: str) -> str:
"""
Extract YouTube video ID from various URL formats
Returns None if URL is invalid
"""
if "youtube.com/watch?v=" in url:
return url.split("watch?v=")[1].split("&")[0]
elif "youtu.be/" in url:
return url.split("youtu.be/")[1].split("?")[0]
return None
@app.post("/share-target-handle")
async def share_target_handle(request: Request):
"""
Endpoint for processing shared YouTube links.
Extracts video information and creates summaries in user's spreadsheet.
Args:
request (Request): FastAPI request object containing share data
Returns:
dict: Processing status and summary data
"""
logging.info("Starting share-target-handle endpoint")
try:
# Parse request data
request_data = await request.json()
logging.info(f"Received request data: {request_data}")
shared_data = request_data.get("shared_data", {})
video_url = shared_data.get("text", "")
video_title = shared_data.get("title", "") # Get the video title
user_id = request_data.get("user_id")
logging.info(f"Extracted shared_data: {shared_data}, user_id: {user_id}")
# Validate user exists
user_ref = users_collection_ref.document(user_id)
user = user_ref.get()
if not user.exists:
logging.error(f"User not found: {user_id}")
return {"status": "error", "message": "User not found"}
user_data = user.to_dict()
logging.info(f"Found user data: {user_data}")
# Check if spreadsheet exists
if 'spreadsheet' not in user_data['gDrive_metadata']:
return {"status": "error", "message": "User's spreadsheet not found"}
# Check if shared links sheet exists
sheet_metadata = sheet_service.spreadsheets().get(
spreadsheetId=user_data['gDrive_metadata']['spreadsheet']
).execute()
shared_links_sheet_exists = any(
sheet['properties']['title'] == '๊ณต์ ๋งํฌ'
for sheet in sheet_metadata.get('sheets', [])
)
# Create sheet if it doesn't exist
if not shared_links_sheet_exists:
try:
logging.info(f"Copying template sheet to user's spreadsheet: {user_data['gDrive_metadata']['spreadsheet']}")
# Copy template sheet using shared_links_ss
copied_sheet = sheet_service.spreadsheets().sheets().copyTo(
spreadsheetId=template_sheet_id,
sheetId=shared_links_ss,
body={"destinationSpreadsheetId": user_data['gDrive_metadata']['spreadsheet']}
).execute()
logging.info(f"Copied sheet to user's spreadsheet: {copied_sheet}")
# Update sheet name to remove "Copy of" prefix
rename_request = {
"updateSheetProperties": {
"properties": {
"sheetId": copied_sheet['sheetId'],
"title": "๊ณต์ ๋งํฌ"
},
"fields": "title"
}
}
sheet_service.spreadsheets().batchUpdate(
spreadsheetId=user_data['gDrive_metadata']['spreadsheet'],
body={"requests": [rename_request]}
).execute()
logging.info("Renamed sheet to '๊ณต์ ๋งํฌ'")
except Exception as e:
logging.error(f"Failed to create shared links sheet: {e}")
return {"status": "error", "message": f"Failed to create shared links sheet: {str(e)}"}
# Process YouTube URL
video_id = extract_youtube_id(video_url)
if not video_id:
return {"status": "error", "message": "Not a valid YouTube URL"}
# Generate video summary
summary_data = await process_youtube_video(video_id, video_title)
# Prepare sheet data
sheet_data = [[
f'=HYPERLINK("{video_url}", "๋ฐ๋ก๊ฐ๊ธฐ")',
summary_data.get('title', video_title), # Use video_title as fallback
summary_data.get('summary', ''),
datetime.now(kst).strftime("%Y-%m-%d %H:%M:%S")
]]
# Update spreadsheet
await update_user_sheet(
spreadsheet_id=user_data['gDrive_metadata']['spreadsheet'],
sheet_name="๊ณต์ ๋งํฌ",
data=sheet_data
)
return {
"status": "success",
"message": "Video processed and saved successfully",
"data": summary_data
}
except Exception as e:
logging.error(f"Error in share-target-handle: {str(e)}", exc_info=True)
return {"status": "error", "message": str(e)}
@app.post("/check-userdoc")
async def check_user_doc(user_id: str = Form(...)):
"""
Verifies user existence and initializes transaction records if needed.
Args:
user_id (str): ID of the user to check
Returns:
dict: User existence status
"""
user_ref = users_collection_ref.document(user_id)
user = user_ref.get()
if user.exists:
return {"dbUserExists": True}
transaction_ref = transactions_collection_ref.document(user_id)
transaction = transaction_ref.get()
if not transaction.exists:
transaction_ref.set({
"no_sms": 0,
"no_contacts": 0,
"no_receipts": 0,
"no_business_cards": 0,
"purchased_credit": {
"image_detection": 100,
"sync_data": 500,
},
"uid": user_id,
})
return {"dbUserExists": False}
template_sheet_id = '1i5mrmlTs5sPWtx2mBtc_f-zm1D3x21r1T_77guki8_8'
@app.post("/edit-spreadsheet")
async def edit_spreadsheet(target_sheet_id: str = Form(...)):
"""
Endpoint for creating or updating a spreadsheet from a template.
Replaces all sheets in the target spreadsheet with template sheets.
Args:
target_sheet_id (str): ID of the spreadsheet to edit
Returns:
dict: Status of the operation
"""
try:
# Retrieve the target spreadsheet's metadata
target_spreadsheet = sheet_service.spreadsheets().get(spreadsheetId=target_sheet_id).execute()
# Collect all sheet IDs in the target spreadsheet
target_sheet_ids = [sheet['properties']['sheetId'] for sheet in target_spreadsheet.get('sheets', [])]
# Prepare batch update request to delete existing sheets
requests = []
for sheet_id in target_sheet_ids:
requests.append({
"deleteSheet": {
"sheetId": sheet_id
}
})
# Retrieve the template spreadsheet's metadata
template_spreadsheet = sheet_service.spreadsheets().get(spreadsheetId=template_sheet_id).execute()
# Iterate through each sheet in the template spreadsheet
for sheet in template_spreadsheet.get('sheets', []):
sheet_id = sheet['properties']['sheetId']
# Use the copyTo method to copy the sheet to the target spreadsheet
copy_request = sheet_service.spreadsheets().sheets().copyTo(
spreadsheetId=template_sheet_id,
sheetId=sheet_id,
body={"destinationSpreadsheetId": target_sheet_id}
)
copy_response = copy_request.execute()
# Get the copied sheet ID
copied_sheet_id = copy_response['sheetId']
# Rename the copied sheet to remove "Copy of"
copied_sheet_title = sheet['properties']['title'].replace("Copy of ", "")
rename_request = {
"updateSheetProperties": {
"properties": {
"sheetId": copied_sheet_id,
"title": copied_sheet_title
},
"fields": "title"
}
}
# Execute rename request
sheet_service.spreadsheets().batchUpdate(
spreadsheetId=target_sheet_id,
body={"requests": [rename_request]}
).execute()
logging.info(f"Sheet {sheet['properties']['title']} copied and renamed to {copied_sheet_title} in {target_sheet_id}.")
if requests:
# Execute batch update to delete sheets
batch_update_request = {"requests": requests}
sheet_service.spreadsheets().batchUpdate(
spreadsheetId=target_sheet_id,
body=batch_update_request
).execute()
logging.info(f"Deleted existing sheets in target spreadsheet {target_sheet_id}.")
logging.info(f"All sheets from template {template_sheet_id} copied to {target_sheet_id}.")
return {"message": "Spreadsheet copied successfully"}
except Exception as e:
logging.error(f"Failed to copy sheets: {e}")
return {"error": str(e)}
async def create_shortcut(file_id, parent_folder_id, name):
try:
file_metadata = {
'name': name,
'mimeType': 'application/vnd.google-apps.shortcut',
'parents': [parent_folder_id],
'shortcutDetails': {
'targetId': file_id
}
}
shortcut = drive_service.files().create(body=file_metadata, fields='id').execute()
return shortcut.get('id')
except Exception as e:
logging.error(f"Failed to create shortcut: {e}")
return None
async def search_business_info(company_name: str, address: str, spreadsheet_id: str = '1YhbIaFFcz6mrMpA9yCSri8zaPL49V6v7l1YYt0AiKss') -> dict:
"""
Enhanced search for business information using fuzzy string matching and weighted scoring
"""
try:
logging.info(f"Searching business info for company: '{company_name}', address: '{address}'")
# Clean and normalize input strings
company_name = company_name.strip().lower()
address = address.strip().lower()
# Remove common company suffixes for better matching
company_suffixes = ['(์ฃผ)', '(์ )', '์ฃผ์ํ์ฌ', '์ ํํ์ฌ']
normalized_company = company_name
for suffix in company_suffixes:
normalized_company = normalized_company.replace(suffix.lower(), '').strip()
# Get all rows from the spreadsheet
range_name = "๊ฒฝ๊ธฐ๋!A2:P" # Extending range to include all relevant columns
result = sheet_service.spreadsheets().values().get(
spreadsheetId=spreadsheet_id,
range=range_name,
valueRenderOption='UNFORMATTED_VALUE'
).execute()
if not result.get('values'):
logging.info("No data found in spreadsheet")
return None
# Process each row and calculate match scores
matches = []
for row in result.get('values', []):
if len(row) < 15: # Skip incomplete rows
continue
db_company = str(row[1]).strip().lower() # Company name is in column B
db_address = str(row[12]).strip().lower() # Address is in column M
# Normalize database company name
normalized_db_company = db_company
for suffix in company_suffixes:
normalized_db_company = normalized_db_company.replace(suffix.lower(), '').strip()
# Calculate match scores
company_score = fuzz.token_sort_ratio(normalized_company, normalized_db_company)
address_score = fuzz.token_sort_ratio(address, db_address)
# Weight the scores (giving more weight to company name match)
total_score = (company_score * 0.7) + (address_score * 0.3)
# Only consider matches above certain thresholds
if company_score > 60 or address_score > 80:
matches.append({
'score': total_score,
'data': {
"์ฌ์
์๋ฒํธ": str(row[2]) if len(row) > 2 else "",
"๋ํ์๋ช
": str(row[11]) if len(row) > 11 else "",
"์ ํ๋ฒํธ": str(row[13]) if len(row) > 13 else "",
"์ฐํธ๋ฒํธ": str(row[14]) if len(row) > 14 else "",
},
'company_score': company_score,
'address_score': address_score
})
logging.info(f"Found potential match: {db_company}")
logging.info(f"Scores - Company: {company_score}, Address: {address_score}, Total: {total_score}")
if not matches:
logging.info("No matches found meeting the threshold criteria")
return None
# Sort matches by total score and return the best match
matches.sort(key=lambda x: x['score'], reverse=True)
best_match = matches[0]
logging.info(f"Best match found with score {best_match['score']}")
logging.info(f"Company match score: {best_match['company_score']}")
logging.info(f"Address match score: {best_match['address_score']}")
return best_match['data']
except Exception as e:
logging.error(f"Error searching business info: {str(e)}", exc_info=True)
return None
async def update_user_sheets_and_folders(user_data, transaction_ref, transaction_data, image_id):
"""
Updates sheets with processed image data and organizes files in Google Drive.
Args:
user_data (dict): User's metadata and preferences
transaction_ref: Firebase transaction reference
transaction_data (dict): User's transaction data
image_id (str): The ID of the processed image
Returns:
dict: Status of the update operation
"""
try:
parent_folders = [user_data['gDrive_metadata']['yungsoogi'], user_data['gDrive_metadata']['uploaded']]
dataJson = await request_gpt4o_completion(image_id, transaction_data['purchased_credit']['image_detection'], use_gpt4=True)
if dataJson is None:
return {"error": "An error occurred while processing the image"}
data = json.loads(dataJson)
# Check if 'receipts' key exists and the length
found_receipt_no = len(data['receipts']) if 'receipts' in data else 0
found_business_cards_no = len(data['busi_cards']) if 'busi_cards' in data else 0
new_folder = None
secondary_folder = None
# timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
timestamp = datetime.now(kst).strftime("%Y-%m-%d %H:%M:%S")
# https://drive.google.com/file/d/1cFIA09PBqFjM8YvIz1D60p7HMGk1uBvo/view?usp=sharing
download_image_url = f"https://drive.google.com/uc?id={image_id}&export=download"
image_url = f"https://drive.google.com/file/d/{image_id}/view?usp=sharing"
# ์ด๋ฏธ์ง๋ฅผ ๋ณด์ฌ์ฃผ์ด์ผ ํ ๋ =image({image_url})๋ฅผ ์ฌ์ฉํ๊ณ ๊ฐ ์ ์๋ ๊ฒฝ๋ก๋ฅผ ๋ง๋ค๋๋ =HYPERLINK({image_url}, '๋ฐ๋ก๊ฐ๊ธฐ')๋ฅผ ์ฌ์ฉํ์ธ์.
# Determine the primary folder to move the image to and secondary folder for shortcut
if found_receipt_no > 0:
new_folder = user_data['gDrive_metadata']['receipts']
receipts_data = convert_dicts_to_list(
data['receipts'],
receipt_sheet_headers,
add_link=True,
image_id=image_id,
link_text="๋ฐ๋ก๊ฐ๊ธฐ",
link_position=1 # Link third
)
print(receipts_data)
await update_user_sheet(user_data['gDrive_metadata']['spreadsheet'], "์์์ฆ", receipts_data)
if found_business_cards_no > 0:
# Enrich business card data with additional info
for card in data['busi_cards']:
if card.get('ํ์ฌ๋ช
') and card.get('์ฃผ์'):
additional_info = await search_business_info(card['ํ์ฌ๋ช
'], card['์ฃผ์'])
if additional_info:
# Update business number if empty
if not card.get('์ฌ์
์๋ฒํธ') and additional_info.get('์ฌ์
์๋ฒํธ'):
card['์ฌ์
์๋ฒํธ'] = additional_info['์ฌ์
์๋ฒํธ']
# Add additional info to ๊ธฐํ
extra_info = []
if additional_info.get('๋ํ์๋ช
'):
extra_info.append(f"๋ํ์: {additional_info['๋ํ์๋ช
']}")
if additional_info.get('์ฐํธ๋ฒํธ'):
extra_info.append(f"์ฐํธ๋ฒํธ: {additional_info['์ฐํธ๋ฒํธ']}")
if extra_info:
if '๊ธฐํ' in card:
card['๊ธฐํ'] += ", " + ", ".join(extra_info)
else:
card['๊ธฐํ'] = ", ".join(extra_info)
if new_folder is None:
new_folder = user_data['gDrive_metadata']['business_cards']
else:
secondary_folder = user_data['gDrive_metadata']['business_cards']
business_cards_data = convert_dicts_to_list(
data['busi_cards'],
business_card_sheet_headers,
add_link=True,
image_id=image_id,
link_text="๋ช
ํจ๋ณด๊ธฐ",
link_position=10
)
await update_user_sheet(user_data['gDrive_metadata']['spreadsheet'], "๋ช
ํจ", business_cards_data)
print(f"{found_receipt_no}, {found_business_cards_no}")
status = await update_fb_transaction(
transaction_ref,
no_receipts=found_receipt_no,
no_business_cards=found_business_cards_no
)
if status['status'] == "Success":
if new_folder:
await move_file_to_folder(image_id, parent_folders, [new_folder])
if secondary_folder:
await create_shortcut(image_id, secondary_folder, f"Shortcut to {image_id}")
return {"success": True}
else:
logging.error(f"Transaction update failed with status: {status['status']}")
return {"error": "An error has occurred while updating the transaction"}
except Exception as e:
logging.error(f"An error occurred: {e}")
# Move the image file to the error folder
await move_file_to_folder(image_id, parent_folders, [user_data['gDrive_metadata']['error']])
return {"error": str(e)}
@app.post("/process-image")
async def process_photo(background_tasks: BackgroundTasks, image_id: str = Form(...), user_id: str = Form(...)):
"""
Endpoint for processing uploaded images. Handles receipt and business card detection.
Args:
background_tasks: FastAPI background tasks handler
image_id (str): The ID of the uploaded image in Google Drive
user_id (str): The ID of the user making the request
Returns:
dict: Processing status and any errors
"""
transaction_ref = transactions_collection_ref.document(user_id)
transaction = transaction_ref.get()
if not transaction.exists:
transaction_ref.set({
"no_sms": 0,
"no_contacts": 0,
"no_receipts": 0,
"no_business_cards": 0,
"purchased_credit": {
"image_detection": 100,
"sync_data": 500,
}
})
transaction = transaction_ref.get()
transaction_data = transaction.to_dict()
if transaction_data['no_receipts'] + transaction_data['no_business_cards'] >= transaction_data['purchased_credit']['image_detection']:
return {"error": "You have reached the limit of the number of items you can process. Please upgrade your plan."}
user_ref = users_collection_ref.document(user_id)
user = user_ref.get()
user_data = user.to_dict()
background_tasks.add_task(update_user_sheets_and_folders, user_data, transaction_ref, transaction_data, image_id)
return {"success": True}
@app.post("/sync-data")
async def process_photo(data_json: str = Form(...), user_id: str = Form(...)):
"""
Endpoint for synchronizing contacts and SMS data.
Handles creation of new SMS sheets and updates existing ones.
Args:
data_json (str): JSON string containing sync data
user_id (str): ID of the user making the request
Returns:
dict: Sync operation status
"""
# print(data_json)
data: Dict[str, Any] = json.loads(data_json)
transaction_ref = transactions_collection_ref.document(user_id)
transaction = transaction_ref.get()
if not transaction.exists:
transaction_ref.set({
"no_sms": 0,
"no_contacts": 0,
"no_receipts": 0,
"no_business_cards": 0,
"purchased_credit": {
"image_detection": 100,
"sync_data": 500,
}
})
transaction = transaction_ref.get()
transaction_data = transaction.to_dict()
if transaction_data['no_contacts'] + transaction_data['no_sms'] >= transaction_data['purchased_credit']['sync_data']:
return {"error": "You have reached the limit of the number of items you can process. Please upgrade your plan."}
user_ref = users_collection_ref.document(user_id)
user = user_ref.get()
user_data = user.to_dict()
try:
if data['isContacts']:
await update_user_sheet(user_data['gDrive_metadata']['spreadsheet'], "์ฐ๋ฝ์ฒ", data['data'], True)
transaction_data['no_contacts'] += len(data['data'])
transaction_ref.update({'no_contacts': transaction_data['no_contacts']})
else:
if 'sms_ids' not in user_data:
print('No sms_ids')
user_data['sms_ids'] = {}
existing_phones = set(user_data.get('sms_ids', {}).keys())
new_phones = [phone['address'] for phone in data['data'] if phone['address'] not in existing_phones]
print(f"Existing phones: {existing_phones}")
for phone_address in new_phones:
new_sheet_id = await copy_sms_sheet(phone_address, user_data['gDrive_metadata']['spreadsheet'])
print(f"New sheet id: {new_sheet_id}")
user_data['sms_ids'][phone_address] = {'sheet_id': new_sheet_id, 'last_updated': "1970-01-01T00:00:00.000"}
print(user_data['sms_ids'])
updated_sms_count = 0
for phone in data['data']:
last_updated = user_data['sms_ids'][phone['address']]['last_updated']
print(f"Last updated: {last_updated}")
# Convert last_updated to datetime for comparison
last_updated_dt = datetime.fromisoformat(last_updated)
update_message = [sms for sms in phone['sms'] if datetime.fromisoformat(sms[0]) > last_updated_dt]
print(f"Update message: {update_message}")
if not update_message:
continue
sheet_id = user_data['sms_ids'][phone['address']]['sheet_id']
print(f"Sheet ID: {sheet_id}")
await update_user_sheet(user_data['gDrive_metadata']['spreadsheet'], sheet_id, 'SMS ' + phone['address'], update_message, False)
user_data['sms_ids'][phone['address']]['last_updated'] = phone['sms'][0][0]
updated_sms_count += len(update_message)
user_ref.update({'sms_ids': user_data['sms_ids']})
transaction_data['no_sms'] += updated_sms_count
transaction_ref.update({'no_sms': transaction_data['no_sms']})
return {"success": True}
except Exception as e:
logging.error(f"An error occurred: {e}")
return {"error": str(e)} |