Django uploads: Discard uploaded duplicates, use existing file (md5 based check)

Question

I have a model with a FileField, which holds user uploaded files. Since I want to save space, I would like to avoid duplicates.

What I\'d like t

Answer 1

Data goes from template -> forms -> views -> db(model). It makes sense to stop the duplicates at the earliest step itself. In this case forms.py.

# scripts.py
import hashlib
from .models import *
def generate_sha(file):
    sha = hashlib.sha1()
    file.seek(0)
    while True:
        buf = file.read(104857600)
        if not buf:
            break
        sha.update(buf)
    sha1 = sha.hexdigest()
    file.seek(0)
    return sha1

# models.py
class images(models.Model):
    label = models.CharField(max_length=21, blank=False, null=False)
    image = models.ImageField(upload_to='images/')
    image_sha1 = models.CharField(max_length=40, blank=False, null=False)
    create_time = models.DateTimeField(auto_now=True)

# forms.py
class imageForm(forms.Form):
    Label = forms.CharField(max_length=21, required=True)
    Image = forms.ImageField(required=True)

    def clean(self):
        cleaned_data = super(imageForm, self).clean()
        Label = cleaned_data.get('Label')
        Image = cleaned_data.get('Image')
        sha1 = generate_sha(Image)
        if images.objects.filter(image_sha1=sha1).exists():
            raise forms.ValidationError('This already exists')
        if not Label:
            raise forms.ValidationError('No Label')
        if not Image:
            raise forms.ValidationError('No Image')

# views.py
from .scripts import *
from .models import *
from .forms import *

def image(request):
    if request.method == 'POST':
        form = imageForm(request.POST, request.FILES)
        if form.is_valid():
            photo = images (
                payee=request.user,
                image=request.FILES['Image'],
                image_sha1=generate_sha(request.FILES['Image'],),
                label=form.cleaned_data.get('Label'),
                )
            photo.save()
            return render(request, 'stars/image_form.html', {'form' : form})
    else:
        form = imageForm()
    context = {'form': form,}
    return render(request, 'stars/image_form.html', context)

# image_form.html
{% extends "base.html" %}
{% load static %}
{% load staticfiles %}

{% block content %}

 

    

        

            {% csrf_token %}
            {{ form  }}
            
        

        {% if form.errors %}
            {% for field in form %}
                {% for error in field.errors %}
                    
 {{ error }} 
                {% endfor %}
            {% endfor %}
        {% endif %}

    


{% endblock content %}  

reference: http://josephmosby.com/2015/05/13/preventing-file-dupes-in-django.html