Updated import_ml_counts to pull data from hyperkitty db (#2054)

.github/workflows/actions-gcp.yaml

@@ -68,6 +68,7 @@ jobs:
       - name: Test with pytest
         env:
           DATABASE_URL: "postgres://postgres:postgres@localhost:${{ job.services.postgres.ports[5432] }}/postgres"
+          HYPERKITTY_DATABASE_URL: "postgres://postgres:postgres@localhost:${{ job.services.postgres.ports[5432] }}/lists_production_web"
           SECRET_KEY: "for-testing-only"
           REDIS_HOST: "localhost"
           CI: "true"

.github/workflows/actions.yml

@@ -58,6 +58,7 @@ jobs:
       - name: Test with pytest
         env:
           DATABASE_URL: "postgres://postgres:postgres@localhost:${{ job.services.postgres.ports[5432] }}/postgres"
+          HYPERKITTY_DATABASE_URL: "postgres://postgres:postgres@localhost:${{ job.services.postgres.ports[5432] }}/lists_production_web"
           SECRET_KEY: "for-testing-only"
           REDIS_HOST: "localhost"
           CI: "true"

config/settings.py

@@ -189,7 +189,10 @@ WSGI_APPLICATION = "config.wsgi.application"
 # https://docs.djangoproject.com/en/1.10/ref/settings/#databases
 
 try:
-    DATABASES = {"default": env.dj_db_url("DATABASE_URL")}
+    DATABASES = {
+        "default": env.dj_db_url("DATABASE_URL"),
+        "hyperkitty": env.dj_db_url("HYPERKITTY_DATABASE_URL"),
+    }
 except (ImproperlyConfigured, environs.EnvError):
     DATABASES = {
         "default": {
@@ -201,7 +204,17 @@ except (ImproperlyConfigured, environs.EnvError):
             "USER": env("PGUSER"),
             "CONN_MAX_AGE": 0,
             "OPTIONS": {"MAX_CONNS": env("MAX_CONNECTIONS", default=20)},
-        }
+        },
+        "hyperkitty": {
+            "ENGINE": "django_db_geventpool.backends.postgresql_psycopg2",
+            "HOST": env("PGHOST"),
+            "NAME": env("HYPERKITTY_DATABASE_NAME", default=""),
+            "PASSWORD": env("PGPASSWORD"),
+            "PORT": env.int("PGPORT", default=5432),
+            "USER": env("PGUSER"),
+            "CONN_MAX_AGE": 0,
+            "OPTIONS": {"MAX_CONNS": env("MAX_CONNECTIONS", default=20)},
+        },
     }
 
 # Password validation

env.template

@@ -35,6 +35,7 @@ PROD_MEDIA_CONTENT_AWS_S3_ENDPOINT_URL=$STATIC_CONTENT_AWS_S3_ENDPOINT_URL
 # Mailman database settings
 HYPERKITTY_DATABASE_NAME="lists_production_web"
 DATABASE_URL="postgresql://postgres@db:5432/postgres"
+HYPERKITTY_DATABASE_URL="postgresql://postgres@db:5432/lists_production_web"
 DATABASE_TYPE="postgres"
 DATABASE_CLASS="mailman.database.postgresql.PostgreSQLDatabase"
 HYPERKITTY_API_KEY="changeme!"

mailing_list/admin.py

@@ -11,7 +11,7 @@ from django.http import HttpResponseRedirect
 from django.contrib import admin, messages
 from django.conf import settings
 
-from mailing_list.models import EmailData, SubscriptionData
+from mailing_list.models import EmailData, SubscriptionData, ListPosting
 from mailing_list.tasks import sync_mailinglist_stats
 
 logger = logging.getLogger(__name__)
@@ -112,3 +112,18 @@ class SubscriptionDataAdmin(admin.ModelAdmin):
 
         payload = {"form": SubscribesCSVForm()}
         return render(request, "admin/mailinglist_subscribe_csv_form.html", payload)
+
+
+@admin.register(ListPosting)
+class ListPostingAdmin(admin.ModelAdmin):
+    list_display = ["id", "date", "sender_id"]
+    search_fields = ["sender_id"]
+
+    def has_add_permission(self, request):
+        return False
+
+    def has_change_permission(self, request, obj=None):
+        return False
+
+    def has_delete_permission(self, request, obj=None):
+        return False

mailing_list/management/commands/import_ml_counts.py

@@ -6,23 +6,15 @@
 import djclick as click
 import logging
 import re
-import warnings
 from datetime import timedelta, datetime
-import html
 
-from dateutil.relativedelta import relativedelta
-from unidecode import unidecode
-
-import requests
 
 from mailing_list.constants import (
-    ML_STATS_URLS,
-    LATIN_1_EQUIVS,
     ARG_DATE_REGEX,
     AUTHOR_PATTERN_REGEX,
     DATE_PATTERN_REGEX,
 )
-from mailing_list.models import PostingData
+from mailing_list.models import PostingData, ListPosting
 
 logger = logging.getLogger(__name__)
 
@@ -31,18 +23,6 @@ author_pattern = re.compile(AUTHOR_PATTERN_REGEX)
 date_pattern = re.compile(DATE_PATTERN_REGEX)
 
 
-def decode_broken_html(str):
-    def latin_1_ord(char):
-        n = ord(char)
-        return LATIN_1_EQUIVS.get(n, n)
-
-    with warnings.catch_warnings():
-        warnings.simplefilter("ignore")
-        return unidecode(
-            bytearray(map(latin_1_ord, html.unescape(str))).decode("utf-8", "ignore")
-        )
-
-
 def parse_datetime(date_str: str, is_start: bool) -> datetime:
     """
     Parse a date string (YYYY, YYYY-MM, YYYY-MM-DD) into a datetime object.
@@ -75,41 +55,12 @@ def parse_datetime(date_str: str, is_start: bool) -> datetime:
     return datetime(year, month, day, 23, 59, 59)
 
 
-def retrieve_authors_from_ml(url, start_date, end_date):
-    posts = []
-    logger.info(f"Retrieving data from {url=}.")
-    r = requests.get(url)
-    if r.status_code == 404:
-        return posts
-
-    author = None
-    for line in r.text.splitlines():
-        author_match = author_pattern.match(line)
-        if author_match:
-            # needs multiple passes to work
-            author = decode_broken_html(author_match.group(1))
-        else:
-            date_pattern_match = date_pattern.match(line)
-            if author and date_pattern_match:
-                post_date = datetime.strptime(
-                    date_pattern_match.group(1), "%Y-%m-%d %H:%M:%S"
-                )
-                if start_date <= post_date and post_date <= end_date:
-                    posts.append(PostingData(name=author, post_time=post_date))
-    return posts
-
-
 def retrieve_authors(start_date, end_date):
     logger.info(f"Retrieve_authors from {start_date:%Y-%m-%d} to {end_date:%Y-%m-%d}")
-    start_month = datetime(start_date.year, start_date.month, 1)
-    end_month = datetime(end_date.year, end_date.month, 1)
     authors = []
-    while start_month <= end_month:
-        for ml in ML_STATS_URLS:
-            authors += retrieve_authors_from_ml(
-                ml.format(start_month.year, start_month.month), start_date, end_date
-            )
-        start_month = start_month + relativedelta(months=+1)
+    for p in ListPosting.objects.filter(date__gte=start_date, date__lte=end_date):
+        authors.append(PostingData(name=p.sender_id, post_time=p.date))
+
     PostingData.objects.filter(
         post_time__gte=start_date, post_time__lte=end_date
     ).delete()

mailing_list/models.py

@@ -57,3 +57,20 @@ class SubscriptionData(models.Model):
 
     class Meta:
         unique_together = ["subscription_dt", "email", "list"]
+
+
+class ListPostingManager(models.Manager):
+    def get_queryset(self):
+        return super().get_queryset().using("hyperkitty")
+
+
+class ListPosting(models.Model):
+    id = models.IntegerField(primary_key=True, blank=False, null=False)
+    date = models.DateTimeField(blank=False, null=False)
+    sender_id = models.CharField(blank=False, null=False)
+
+    objects = ListPostingManager()
+
+    class Meta:
+        managed = False
+        db_table = "hyperkitty_email"