Spaces:
Sleeping
Sleeping
Update main.py
Browse files
main.py
CHANGED
@@ -12,6 +12,7 @@ from nltk.tokenize import sent_tokenize
|
|
12 |
from transformers import MarianMTModel, MarianTokenizer
|
13 |
|
14 |
API_KEY = os.environ.get("API_KEY")
|
|
|
15 |
|
16 |
app = FastAPI()
|
17 |
# CORS issue write below code
|
@@ -41,6 +42,11 @@ async def ocr(
|
|
41 |
# languages: list = Body(["eng"])
|
42 |
):
|
43 |
try:
|
|
|
|
|
|
|
|
|
|
|
44 |
content = await image.read()
|
45 |
image = Image.open(BytesIO(content))
|
46 |
text = pytesseract.image_to_string(image, lang = 'eng')
|
|
|
12 |
from transformers import MarianMTModel, MarianTokenizer
|
13 |
|
14 |
API_KEY = os.environ.get("API_KEY")
|
15 |
+
VALID_IMAGE_EXTENSIONS = {".jpg", ".jpeg", ".png"}
|
16 |
|
17 |
app = FastAPI()
|
18 |
# CORS issue write below code
|
|
|
42 |
# languages: list = Body(["eng"])
|
43 |
):
|
44 |
try:
|
45 |
+
# Check if the file format is allowed
|
46 |
+
file_extension = image.filename.split(".")[-1].lower()
|
47 |
+
if file_extension not in VALID_IMAGE_EXTENSIONS:
|
48 |
+
raise HTTPException(status_code=400, detail="Invalid file format. Only .jpg, .jpeg, and .png are allowed.")
|
49 |
+
|
50 |
content = await image.read()
|
51 |
image = Image.open(BytesIO(content))
|
52 |
text = pytesseract.image_to_string(image, lang = 'eng')
|