Dockerfile

@@ -10,7 +10,7 @@ COPY scripts/ /app/scripts/
 RUN chmod +x /app/scripts/start.sh
 
 # Install packages
-RUN apt update && apt install -y graphviz libgraphviz-dev graphviz-dev tesseract-ocr tmux
+RUN apt update && apt install -y graphviz libgraphviz-dev graphviz-dev tesseract-ocr
 RUN pip3 install --upgrade pip && pip3 install --no-cache-dir -r requirements.txt
 
 # Expose port 8000 for the web server

docker-compose.dev.yml

@@ -10,8 +10,6 @@ services:
     environment:
       - PYTHONBUFFERED=1
     volumes:
-      # File Watcher is broken in Windows Docker since Docker does not notify container about any file changes you make from Windows
-      # If running on Windows, use a shared volume instead of bind mount
       - .:/app
 
   # SMTP Server

docmanager_backend/config/management/commands/start_watcher.py

@@ -1,117 +0,0 @@
-from django.core.management.base import BaseCommand, CommandError
-
-from io import BytesIO
-from documents.models import Document
-from PIL import Image
-import pytesseract
-import fitz
-import os
-from config.settings import MEDIA_ROOT
-from watchdog.observers import Observer
-from watchdog.events import FileSystemEventHandler
-from documents.models import Document
-import logging
-import time
-
-
-class PDFHandler(FileSystemEventHandler):
-    def __init__(self):
-        logging.basicConfig(level=logging.INFO,
-                            format='%(asctime)s - %(message)s',
-                            datefmt='%Y-%m-%d %H:%M:%S')
-
-        self.logger = logging.getLogger(__name__)
-        self.logger.info("Starting Document Watcher...")
-
-    def on_created(self, event):
-        if event.is_directory:
-            return None
-
-        if event.src_path.endswith('.pdf'):
-            self.logger.info(f"New PDF file detected: {event.src_path}")
-            self.process_pdf(event.src_path)
-
-    def process_pdf(self, file_path):
-        try:
-            filename = os.path.basename(file_path)
-            metadata = ""
-            document_type = ""
-
-            with fitz.open(file_path) as doc:
-                num_pages = len(doc)
-
-                for page_num in range(num_pages):
-                    page = doc[page_num]
-                    pix = page.get_pixmap(matrix=(1.2, 1.2))
-
-                    # Convert pixmap to bytes
-                    img_bytes = pix.tobytes()
-
-                    # Create a BytesIO object
-                    img_buffer = BytesIO(img_bytes)
-
-                    # Create a PIL Image object from the bytes
-                    img = Image.open(img_buffer)
-
-                    # Perform OCR
-                    text = pytesseract.image_to_string(img).strip()
-
-                    lines = text.split('\n')
-
-                    for line in lines:
-                        if line.strip():
-                            document_type = line.strip().lower()
-                            break
-                    if not document_type or document_type not in Document.DOCUMENT_TYPE_CHOICES:
-                        document_type = "other"
-
-                    metadata += text
-
-            document, created = Document.objects.get_or_create(
-                name=filename,
-                defaults={
-                    'number_pages': num_pages,
-                    'ocr_metadata': metadata,
-                    'document_type': document_type
-                }
-            )
-
-            if created:
-                self.logger.info(f"Document '{filename}' created successfully with type '{
-                    document_type}'.")
-
-            else:
-                self.logger.info(f"Document '{filename}' already exists.")
-
-            os.remove(file_path)
-        except Exception as e:
-            self.logger.error(f"Error processing PDF: {str(e)}")
-
-
-class PDFWatcher:
-    def __init__(self):
-        self.observer = Observer()
-
-    def run(self):
-        event_handler = PDFHandler()
-        watch_directory = os.path.join(MEDIA_ROOT, "uploads")
-
-        self.observer.schedule(
-            event_handler, watch_directory, recursive=True)
-        self.observer.start()
-
-        try:
-            while True:
-                time.sleep(5)
-        except:
-            self.observer.stop()
-
-        self.observer.join()
-
-
-class Command(BaseCommand):
-    help = "Runs a dedicated file watcher service"
-
-    def handle(self, *args, **options):
-        watcher = PDFWatcher()
-        watcher.run()

docmanager_backend/config/settings.py

@@ -89,7 +89,6 @@ INSTALLED_APPS = [
     "corsheaders",
     "drf_spectacular",
     "drf_spectacular_sidecar",
-    "config",
     "emails",
     "accounts",
     "documents",
@@ -267,4 +266,4 @@ GRAPH_MODELS = {"app_labels": [
     "accounts", "documents", "document_requests", "questionnaires"]}
 
 CORS_ORIGIN_ALLOW_ALL = True
-CORS_ALLOW_CREDENTIALS = True
+CORS_ALLOW_CREDENTIALS = True

docmanager_backend/documents/migrations/0004_alter_document_document_type.py

@@ -1,26 +0,0 @@
-# Generated by Django 5.1.3 on 2024-11-26 15:12
-
-from django.db import migrations, models
-
-
-class Migration(migrations.Migration):
-
-    dependencies = [
-        ("documents", "0003_remove_document_metadata_document_ocr_metadata"),
-    ]
-
-    operations = [
-        migrations.AlterField(
-            model_name="document",
-            name="document_type",
-            field=models.CharField(
-                choices=[
-                    ("memorandum", "Memorandum"),
-                    ("hoa", "HOA"),
-                    ("documented procedures manual", "Documented Procedures Manual"),
-                    ("other", "Other"),
-                ],
-                max_length=32,
-            ),
-        ),
-    ]

docmanager_backend/documents/models.py

@@ -10,9 +10,7 @@ class Document(models.Model):
     DOCUMENT_TYPE_CHOICES = (
         ("memorandum", "Memorandum"),
         ("hoa", "HOA"),
-        ("documented procedures manual", "Documented Procedures Manual"),
+        # TODO: Update this list on types of documents
-        ("other", "Other"),
-
     )
     document_type = models.CharField(
         max_length=32, choices=DOCUMENT_TYPE_CHOICES, null=False, blank=False

docmanager_backend/documents/signals.py

@@ -1,6 +1,3 @@
-
-from io import BytesIO
-from documents.models import Document
 from django.db.models.signals import post_save
 from django.dispatch import receiver
 from config.settings import MEDIA_ROOT
@@ -12,25 +9,18 @@ from .models import Document
 
 
 @receiver(post_save, sender=Document)
-def document_post_save(sender, instance, **kwargs):
+def domain_post_save(sender, instance, **kwargs):
     if not instance.ocr_metadata:
         metadata = ""
         with fitz.open(os.path.join(MEDIA_ROOT, instance.file.name)) as doc:
             mat = fitz.Matrix(1.2, 1.2)
             for page in doc:
                 pix = page.get_pixmap(matrix=mat)
-                # Convert pixmap to bytes
+                output = f'{page.number}.jpg'
-                img_bytes = pix.tobytes()
+                pix.save(output)
-
+                res = str(pytesseract.image_to_string(Image.open(output)))
-                # Create a BytesIO object
+                os.remove(output)
-                img_buffer = BytesIO(img_bytes)
+                metadata += res
-
-                # Create a PIL Image object from the bytes
-                img = Image.open(img_buffer)
-
-                # Perform OCR
-                text = pytesseract.image_to_string(img).strip()
-                metadata += text
 
         instance.ocr_metadata = metadata
         instance.save()

requirements.txt

@@ -57,6 +57,5 @@ typing_extensions==4.12.2
 tzdata==2024.2
 uritemplate==4.1.1
 urllib3==2.2.3
-watchdog==6.0.0
 whitenoise==6.8.2
 pygraphviz==1.14; platform_system == 'Linux'

scripts/start.sh

@@ -8,8 +8,7 @@ if [ ! -d "static" ]; then
     echo "Generating static files"
     python manage.py collectstatic --noinput
 fi
-    tmux new-session -d -s "API File Watcher" "cd /app/docmanager_backend && python manage.py start_watcher"
+if [ "$DEBUG" = 'True' ]; then   
-if [ "$DEBUG" = 'True' ]; then
     python manage.py runserver "0.0.0.0:8000"
 else
     gunicorn --workers 8 --bind 0.0.0.0:8000 config.wsgi:application