Spaces:
Sleeping
Sleeping
Thantham
commited on
Commit
•
9c5e6eb
1
Parent(s):
fc1164a
add files
Browse files- Dockerfile +26 -0
- app.py +39 -0
Dockerfile
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
FROM ubuntu:jammy
|
2 |
+
#FROM alpine:latest
|
3 |
+
|
4 |
+
# Install dependencies
|
5 |
+
RUN apt-get update && apt-get install -y \
|
6 |
+
tesseract-ocr \
|
7 |
+
tesseract-ocr-eng \
|
8 |
+
tesseract-ocr-tha \
|
9 |
+
python3 \
|
10 |
+
python3-pip
|
11 |
+
|
12 |
+
# Install FastAPI and Uvicorn (an ASGI server)
|
13 |
+
RUN pip3 install fastapi uvicorn pillow pytesseract python-multipart PyMuPDF
|
14 |
+
|
15 |
+
# Set working directory
|
16 |
+
WORKDIR /app
|
17 |
+
|
18 |
+
# Copy your application code
|
19 |
+
COPY . .
|
20 |
+
|
21 |
+
|
22 |
+
# Expose port for the service
|
23 |
+
EXPOSE 5000
|
24 |
+
|
25 |
+
# Start your application with Uvicorn
|
26 |
+
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
|
app.py
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from fastapi import FastAPI, File, UploadFile
|
2 |
+
from PIL import Image
|
3 |
+
import pytesseract
|
4 |
+
import io
|
5 |
+
import fitz
|
6 |
+
|
7 |
+
app = FastAPI()
|
8 |
+
|
9 |
+
@app.get("/test")
|
10 |
+
async def test_api():
|
11 |
+
return {"message": "API is working ..."}
|
12 |
+
|
13 |
+
@app.post("/ocr_image")
|
14 |
+
async def perform_ocr_image(image: UploadFile = File(...)):
|
15 |
+
image_data = await image.read()
|
16 |
+
|
17 |
+
image = Image.open(io.BytesIO(image_data))
|
18 |
+
text = pytesseract.image_to_string(image, lang='tha+eng')
|
19 |
+
return {"text": text}
|
20 |
+
|
21 |
+
|
22 |
+
@app.post("/ocr_pdf")
|
23 |
+
async def perform_ocr_pdf(image: UploadFile = File(...)):
|
24 |
+
image_data = await image.read()
|
25 |
+
|
26 |
+
doc = fitz.open(stream=image_data, filetype="pdf")
|
27 |
+
|
28 |
+
page = doc[0] # Access the desired page (zero-indexed)
|
29 |
+
|
30 |
+
# Generate a high-quality image of the page
|
31 |
+
zoom = 2 # Adjust for better OCR resolution if needed
|
32 |
+
mat = fitz.Matrix(zoom, zoom) # Zoom matrix
|
33 |
+
pix = page.get_pixmap(matrix=mat)
|
34 |
+
img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
|
35 |
+
|
36 |
+
# Analyze text orientation with Pytesseract
|
37 |
+
#text_orientation = pytesseract.image_to_osd(img)
|
38 |
+
text = pytesseract.image_to_string(img, lang='tha+eng')
|
39 |
+
return {"text": text}
|