Added pdf generation for release reports/do it all (#1750)

Author: daveoconnor

docker/Dockerfile

@@ -44,7 +44,18 @@ RUN yarn build
 # Final image.
 FROM python:3.13-slim AS release
 
-RUN apt update && apt install -y git libpq-dev ruby ruby-dev && rm -rf /var/lib/apt/lists/*
+# Install system dependencies including Chromium
+RUN apt update && apt install -y \
+    git \
+    libpq-dev \
+    ruby \
+    ruby-dev \
+    fonts-liberation \
+    fonts-noto \
+    fonts-noto-mono \
+    fonts-noto-color-emoji \
+    chromium \
+    && rm -rf /var/lib/apt/lists/*
 
 # Install Asciidoctor
 RUN gem install asciidoctor asciidoctor-boost
@@ -67,6 +78,9 @@ COPY --from=builder-js /code/static/css/styles.css /code/static/css/styles.css
 
 WORKDIR /code
 
+# Set environment variable for Playwright to use system Chromium
+ENV PLAYWRIGHT_BROWSERS_PATH=/usr/bin
+
 CMD ["gunicorn", "-c", "/code/gunicorn.conf.py", "config.wsgi"]
 
 ARG TAG

libraries/admin.py

@@ -1,4 +1,5 @@
 from django.contrib import admin
+from django.core.files.storage import default_storage
 from django.db import transaction
 from django.db.models import F, Count, OuterRef, Window
 from django.db.models.functions import RowNumber
@@ -8,10 +9,13 @@
 from django.utils.safestring import mark_safe
 from django.shortcuts import redirect
 from django.views.generic import TemplateView
+from django import forms
 
+from core.admin_filters import StaffUserCreatedByFilter
 from libraries.forms import CreateReportForm, CreateReportFullForm
 from versions.models import Version
 from versions.tasks import import_all_library_versions
+from .filters import ReportConfigurationFilter
 from .models import (
     Category,
     Commit,
@@ -21,6 +25,7 @@
     Library,
     LibraryVersion,
     PullRequest,
+    ReleaseReport,
     WordcloudMergeWord,
 )
 from .tasks import (
@@ -34,6 +39,7 @@
     generate_release_report,
     synchronize_commit_author_user_data,
 )
+from .utils import generate_release_report_filename
 
 
 @admin.register(Commit)
@@ -177,7 +183,9 @@ def get_context_data(self, **kwargs):
         return context
 
     def generate_report(self):
-        generate_release_report.delay(self.request.GET)
+        generate_release_report.delay(
+            user_id=self.request.user.id, params=self.request.GET
+        )
 
     def get(self, request, *args, **kwargs):
         form = self.get_form()
@@ -440,3 +448,43 @@ class WordcloudMergeWordAdmin(admin.ModelAdmin):
             },
         ),
     ]
+
+
+class ReleaseReportAdminForm(forms.ModelForm):
+    class Meta:
+        model = ReleaseReport
+        fields = "__all__"
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+
+        if self.instance.pk and not self.instance.published:
+            file_name = generate_release_report_filename(
+                self.instance.report_configuration.get_slug()
+            )
+            published_filename = f"{ReleaseReport.upload_dir}{file_name}"
+            if default_storage.exists(published_filename):
+                # we require users to intentionally manually delete existing reports
+                self.fields["published"].disabled = True
+                self.fields["published"].help_text = (
+                    f"⚠️ A published '{file_name}' already exists. To prevent accidents "
+                    "you must manually delete that file before publishing this report."
+                )
+
+
+@admin.register(ReleaseReport)
+class ReleaseReportAdmin(admin.ModelAdmin):
+    form = ReleaseReportAdminForm
+    list_display = ["__str__", "created_at", "published", "published_at"]
+    list_filter = ["published", ReportConfigurationFilter, StaffUserCreatedByFilter]
+    search_fields = ["file"]
+    readonly_fields = ["created_at", "created_by"]
+    ordering = ["-created_at"]
+
+    def has_add_permission(self, request):
+        return False
+
+    def save_model(self, request, obj, form, change):
+        if not change:
+            obj.created_by = request.user
+        super().save_model(request, obj, form, change)

libraries/constants.py

@@ -366,3 +366,4 @@
 MASTER_RELEASE_URL_PATH_STR = "master"
 VERSION_SLUG_PREFIX = "boost-"
 RELEASE_REPORT_SEARCH_TOP_COUNTRIES_LIMIT = 5
+DOCKER_CONTAINER_URL_WEB = "http://web:8000"

libraries/filters.py

@@ -0,0 +1,22 @@
+from django.contrib import admin
+
+from versions.models import ReportConfiguration
+
+
+class ReportConfigurationFilter(admin.SimpleListFilter):
+    title = "report configuration"
+    parameter_name = "report_configuration"
+
+    def lookups(self, request, model_admin):
+        # get only ReportConfigurations that have associated ReleaseReports
+        configs = (
+            ReportConfiguration.objects.filter(releasereport__isnull=False)
+            .distinct()
+            .order_by("version")
+        )
+        return [(config.id, str(config)) for config in configs]
+
+    def queryset(self, request, queryset):
+        if self.value():
+            return queryset.filter(report_configuration_id=self.value())
+        return queryset

libraries/forms.py

@@ -90,6 +90,11 @@ class CreateReportFullForm(Form):
         initial=False,
         help_text="Force the page to be regenerated, do not use cache.",
     )
+    publish = BooleanField(
+        required=False,
+        initial=False,
+        help_text="Warning: overwrites existing published report, not reversible.",
+    )
 
     @property
     def cache_key(self):
@@ -205,13 +210,16 @@ def get_stats(self):
             "library_count": self.library_queryset.count(),
         }
 
-    def cache_html(self):
+    def cache_html(self, base_uri=None):
         """Render and cache the html for this report."""
         # ensure we have "cleaned_data"
         if not self.is_valid():
             return ""
         try:
-            html = render_to_string(self.html_template_name, self.get_stats())
+            context = self.get_stats()
+            if base_uri:
+                context["base_uri"] = base_uri
+            html = render_to_string(self.html_template_name, context)
         except FileNotFoundError as e:
             html = (
                 f"An error occurred generating the report: {e}. To see the image "

libraries/management/commands/release_tasks.py

@@ -17,11 +17,10 @@
     ActionsManager,
     send_notification,
 )
-from libraries.forms import CreateReportForm
-from libraries.tasks import update_commits
+from libraries.tasks import update_commits, generate_release_report
 from reports.models import WebsiteStatReport
 from slack.management.commands.fetch_slack_activity import get_my_channels, locked
-from versions.models import Version
+from versions.models import Version, ReportConfiguration
 
 User = get_user_model()
 
@@ -30,8 +29,12 @@ class ReleaseTasksManager(ActionsManager):
     latest_version: Version | None = None
     handled_commits: dict[str, int] = {}
 
-    def __init__(self, should_generate_report: bool = False):
+    def __init__(
+        self, base_uri: str, user_id: int, should_generate_report: bool = False
+    ):
+        self.base_uri = base_uri
         self.should_generate_report = should_generate_report
+        self.user_id = user_id
         super().__init__()
 
     def set_tasks(self):
@@ -80,20 +83,32 @@ def import_ml_counts(self):
         """
         start_date = timezone.now() - timedelta(days=120)
         date_string = start_date.strftime("%Y-%m-%d")
-        print(f"{date_string = }")
         call_command("import_ml_counts", start_date=date_string)
 
     def generate_report(self):
         if not self.should_generate_report:
             self.add_progress_message("Skipped - report generation not requested")
             return
-        form = CreateReportForm({"version": self.latest_version.id})
-        form.cache_html()
+
+        report_configuration = ReportConfiguration.objects.get(
+            version=self.latest_version.name
+        )
+        generate_release_report.delay(
+            user_id=self.user_id,
+            params={"report_configuration": report_configuration.id, "publish": True},
+            base_uri=self.base_uri,
+        )
 
 
 @locked(1138692)
-def run_commands(progress: list[str], generate_report: bool = False):
-    manager = ReleaseTasksManager(should_generate_report=generate_report)
+def run_commands(
+    progress: list[str], base_uri: str, user_id: int, generate_report: bool = False
+):
+    manager = ReleaseTasksManager(
+        base_uri=base_uri,
+        should_generate_report=generate_report,
+        user_id=user_id,
+    )
     manager.run_tasks()
     progress.extend(manager.progress_messages)
     return manager.handled_commits
@@ -125,23 +140,28 @@ def bad_credentials() -> list[str]:
 
 
 @click.command()
+@click.option(
+    "--base_uri",
+    is_flag=False,
+    help="The URI to which paths should be relative",
+    default=None,
+)
 @click.option(
     "--user_id",
     is_flag=False,
     help="The ID of the user that started this task (For notification purposes)",
-    default=None,
 )
 @click.option(
     "--generate_report",
     is_flag=True,
     help="Generate a report at the end of the command",
     default=False,
 )
-def command(user_id=None, generate_report=False):
+def command(user_id, base_uri=None, generate_report=False):
     """A long running chain of tasks to import and update library data."""
     start = timezone.now()
 
-    user = User.objects.filter(id=user_id).first() if user_id else None
+    user = User.objects.filter(id=user_id).first()
 
     progress = ["___Progress Messages___"]
     if missing_creds := bad_credentials():
@@ -162,7 +182,7 @@ def command(user_id=None, generate_report=False):
     )
 
     try:
-        handled_commits = run_commands(progress, generate_report)
+        handled_commits = run_commands(progress, base_uri, generate_report, user_id)
         end = timezone.now()
     except Exception:
         error = traceback.format_exc()

libraries/migrations/0035_releasereport.py

@@ -0,0 +1,55 @@
+# Generated by Django 5.2.7 on 2025-10-27 22:52
+
+import django.db.models.deletion
+from django.conf import settings
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("libraries", "0034_strip_boost_from_documentation_urls"),
+        ("versions", "0024_alter_versionfile_checksum_and_more"),
+        migrations.swappable_dependency(settings.AUTH_USER_MODEL),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="ReleaseReport",
+            fields=[
+                (
+                    "id",
+                    models.BigAutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                (
+                    "file",
+                    models.FileField(
+                        blank=True, null=True, upload_to="release-reports/"
+                    ),
+                ),
+                ("created_at", models.DateTimeField(auto_now_add=True)),
+                ("published", models.BooleanField(default=False)),
+                ("published_at", models.DateTimeField(blank=True, null=True)),
+                (
+                    "created_by",
+                    models.ForeignKey(
+                        null=True,
+                        on_delete=django.db.models.deletion.SET_NULL,
+                        to=settings.AUTH_USER_MODEL,
+                    ),
+                ),
+                (
+                    "report_configuration",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE,
+                        to="versions.reportconfiguration",
+                    ),
+                ),
+            ],
+        ),
+    ]