Remove pdf_url

- the field is no longer used
- it hasn't been used since migrating to Django

Author: tudoramariei

backend/donations/migrations/0016_remove_donor_pdf_url.py

@@ -0,0 +1,17 @@
+# Generated by Django 5.1.2 on 2024-10-31 14:40
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("donations", "0015_rename_last_name_donor_f_name"),
+    ]
+
+    operations = [
+        migrations.RemoveField(
+            model_name="donor",
+            name="pdf_url",
+        ),
+    ]

backend/donations/models/main.py

@@ -404,7 +404,6 @@ class Donor(models.Model):
 
     geoip = models.JSONField(verbose_name=_("Geo IP"), blank=True, null=False, default=dict)
 
-    pdf_url = models.URLField(verbose_name=_("PDF URL"), blank=True, null=False, default="", max_length=255)
     filename = models.CharField(verbose_name=_("filename"), blank=True, null=False, default="", max_length=100)
     has_signed = models.BooleanField(verbose_name=_("has signed"), db_index=True, default=False)
 

backend/donations/views/cron.py

@@ -104,7 +104,7 @@ def get(self, request):
                         donor.f_name,
                         donor.email,
                         donor.has_signed,
-                        donor.pdf_file.url if donor.pdf_file else donor.pdf_url,
+                        donor.pdf_file.url if donor.pdf_file else "",
                         donor.ngo.name,
                         donor.ngo.email,
                         donor.ngo.is_accepting_forms,

backend/donations/views/donations_download.py

@@ -253,11 +253,8 @@ def _get_address_details(donation_object: Donor) -> Dict[str, str]:
 
 
 def _get_pdf_url(donation: Donor) -> str:
-    # The 'pdf_file' property has priority over the old 'pdf_url' one
     if donation.pdf_file:
         source_url = donation.pdf_file.url
-    elif donation.pdf_url:
-        source_url = donation.pdf_url
     else:
         source_url = ""
 

backend/importer/tasks/donor_forms.py

@@ -1,20 +1,11 @@
 import logging
-import tempfile
 from typing import List
 
-import requests
-from django.conf import settings
-from django.core.files import File
 from django.db.models import Count, Q, QuerySet
 from django_q.tasks import async_task
-from pypdf import PdfReader
-from requests import Response
-from sentry_sdk import capture_message
 
 from donations.models.main import Donor, Ngo
 
-from ..extract import DATA_ZONES, extract_data
-
 logger = logging.getLogger(__name__)
 
 
@@ -37,11 +28,9 @@ def import_donor_forms_task(batch_size: int = 50, run_async: bool = False, dry_r
     index: int = 0
     processed_form_ids: List[int] = []
     for index, ngo in enumerate(ngos_by_number_of_donors):
-        donor_forms_for_ngo: List[int] = (
-            Donor.objects.exclude(pdf_url="")
-            .filter(ngo=ngo, pdf_file="", date_created__gte="2023-12-31")
-            .values_list("pk", flat=True)[: batch_size + 1]
-        )
+        donor_forms_for_ngo: List[int] = Donor.objects.filter(
+            ngo=ngo, pdf_file="", date_created__gte="2023-12-31"
+        ).values_list("pk", flat=True)[: batch_size + 1]
 
         processed_form_ids.extend(donor_forms_for_ngo)
 
@@ -68,71 +57,6 @@ def execute_import(index, processed_form_ids: List[int], run_async: bool, dry_ru
 def import_donor_forms(ids: List[int], dry_run: bool):
     """
     Download and re-upload the donation form files one by one
+    XXX: Will be removed
     """
-    target_donors: QuerySet[Donor] = Donor.objects.filter(pk__in=ids).order_by("pk")
-
-    logger.info("Found %s donors to import", target_donors.count())
-
-    attempted_donors: int = 0
-    transferred_donors: int = 0
-
-    donor: Donor
-    for attempted_donors, donor in enumerate(target_donors):
-
-        logger.debug("Processing donation: %s", donor.pk)
-
-        if not donor.pdf_url.startswith("http"):
-            logger.debug("Skipped form %s: PDF URL does not start with http", donor.pk)
-            continue
-
-        r: Response = requests.get(donor.pdf_url)
-        if r.status_code != 200:
-            error_message = f"Donation form request status: {r.status_code} for donor {donor.pk}"
-            logger.warning(error_message)
-
-            if settings.ENABLE_SENTRY:
-                capture_message(error_message, level="error")
-
-            continue
-
-        with tempfile.TemporaryFile() as fp:
-            fp.write(r.content)
-            fp.seek(0)
-            donor.pdf_file.save("donation_form.pdf", File(fp), save=False)
-            fp.seek(0)
-            reader = PdfReader(fp)
-            page = reader.pages[0]
-
-            try:
-                donor.set_cnp(extract_data(page, DATA_ZONES["cnp"]))
-                donor.initial = extract_data(page, DATA_ZONES["father"])
-
-                donor.set_address_helper(
-                    street_name=extract_data(page, DATA_ZONES["street_name"]),
-                    street_number=extract_data(page, DATA_ZONES["street_number"]),
-                    street_bl=extract_data(page, DATA_ZONES["street_bl"]),
-                    street_sc=extract_data(page, DATA_ZONES["street_sc"]),
-                    street_et=extract_data(page, DATA_ZONES["street_et"]),
-                    street_ap=extract_data(page, DATA_ZONES["street_ap"]),
-                )
-            except Exception as e:
-                logger.error("Error extracting data from PDF: %s for donor %s", e, donor.pk)
-                continue
-
-            logger.debug("New form file: %s", donor.pdf_file)
-
-            if not dry_run:
-                donor.save()
-            else:
-                logger.info("Dry run: not saving the donor form")
-
-            transferred_donors += 1
-
-    if transferred_donors:
-        logger.info("Transferred %d out of %d donors", transferred_donors, attempted_donors + 1)
-    else:
-        error_message = f"No donors were transferred for the following list of {attempted_donors + 1} IDs: {ids}"
-        logger.error(error_message)
-
-        if settings.ENABLE_SENTRY:
-            capture_message(error_message, level="error")
+    ...