diff --git a/.github/workflows/black.yml b/.github/workflows/black.yml deleted file mode 100644 index 4e7be4af3..000000000 --- a/.github/workflows/black.yml +++ /dev/null @@ -1,17 +0,0 @@ -name: Python Formatting (run ./bw-dev black to fix) - -on: - push: - branches: [ main ] - pull_request: - branches: [ main ] - -jobs: - lint: - runs-on: ubuntu-latest - steps: - - uses: actions/checkout@v3 - - uses: actions/setup-python@v4 - - uses: psf/black@22.12.0 - with: - version: 22.12.0 diff --git a/.github/workflows/codeql-analysis.yml b/.github/workflows/codeql-analysis.yml index 68bb05d7e..51316ef62 100644 --- a/.github/workflows/codeql-analysis.yml +++ b/.github/workflows/codeql-analysis.yml @@ -36,7 +36,7 @@ jobs: steps: - name: Checkout repository - uses: actions/checkout@v3 + uses: actions/checkout@v4 # Initializes the CodeQL tools for scanning. - name: Initialize CodeQL diff --git a/.github/workflows/curlylint.yaml b/.github/workflows/curlylint.yaml index 8d5c6b4f7..10ad04ce1 100644 --- a/.github/workflows/curlylint.yaml +++ b/.github/workflows/curlylint.yaml @@ -10,7 +10,7 @@ jobs: lint: runs-on: ubuntu-latest steps: - - uses: actions/checkout@v3 + - uses: actions/checkout@v4 - name: Install curlylint run: pip install curlylint diff --git a/.github/workflows/django-tests.yml b/.github/workflows/django-tests.yml deleted file mode 100644 index de71d9bcf..000000000 --- a/.github/workflows/django-tests.yml +++ /dev/null @@ -1,70 +0,0 @@ -name: Run Python Tests -on: - push: - branches: [ main ] - pull_request: - branches: [ main ] - -jobs: - build: - - runs-on: ubuntu-20.04 - services: - postgres: - image: postgres:13 - env: - POSTGRES_USER: postgres - POSTGRES_PASSWORD: hunter2 - options: >- - --health-cmd pg_isready - --health-interval 10s - --health-timeout 5s - --health-retries 5 - ports: - - 5432:5432 - steps: - - uses: actions/checkout@v3 - - name: Set up Python - uses: actions/setup-python@v4 - with: - python-version: 3.11 - - name: Install Dependencies - run: | - python -m pip install --upgrade pip - pip install -r requirements.txt - - name: Check migrations up-to-date - run: | - python ./manage.py makemigrations --check - env: - SECRET_KEY: beepbeep - DOMAIN: your.domain.here - EMAIL_HOST: "" - EMAIL_HOST_USER: "" - EMAIL_HOST_PASSWORD: "" - - name: Run Tests - env: - SECRET_KEY: beepbeep - DEBUG: false - USE_HTTPS: true - DOMAIN: your.domain.here - BOOKWYRM_DATABASE_BACKEND: postgres - MEDIA_ROOT: images/ - POSTGRES_PASSWORD: hunter2 - POSTGRES_USER: postgres - POSTGRES_DB: github_actions - POSTGRES_HOST: 127.0.0.1 - CELERY_BROKER: "" - REDIS_BROKER_PORT: 6379 - REDIS_BROKER_PASSWORD: beep - USE_DUMMY_CACHE: true - FLOWER_PORT: 8888 - EMAIL_HOST: "smtp.mailgun.org" - EMAIL_PORT: 587 - EMAIL_HOST_USER: "" - EMAIL_HOST_PASSWORD: "" - EMAIL_USE_TLS: true - ENABLE_PREVIEW_IMAGES: false - ENABLE_THUMBNAIL_GENERATION: true - HTTP_X_FORWARDED_PROTO: false - run: | - pytest -n 3 diff --git a/.github/workflows/lint-frontend.yaml b/.github/workflows/lint-frontend.yaml index 0d0559e40..21f11ebf3 100644 --- a/.github/workflows/lint-frontend.yaml +++ b/.github/workflows/lint-frontend.yaml @@ -19,7 +19,7 @@ jobs: steps: # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it. - - uses: actions/checkout@v3 + - uses: actions/checkout@v4 - name: Install modules run: npm install stylelint stylelint-config-recommended stylelint-config-standard stylelint-order eslint diff --git a/.github/workflows/mypy.yml b/.github/workflows/mypy.yml deleted file mode 100644 index 6df987aa4..000000000 --- a/.github/workflows/mypy.yml +++ /dev/null @@ -1,50 +0,0 @@ -name: Mypy - -on: - push: - branches: [ main ] - pull_request: - branches: [ main ] - -jobs: - build: - - runs-on: ubuntu-latest - - steps: - - uses: actions/checkout@v3 - - name: Set up Python 3.11 - uses: actions/setup-python@v4 - with: - python-version: 3.11 - - name: Install Dependencies - run: | - python -m pip install --upgrade pip - pip install -r requirements.txt - - name: Analysing the code with mypy - env: - SECRET_KEY: beepbeep - DEBUG: false - USE_HTTPS: true - DOMAIN: your.domain.here - BOOKWYRM_DATABASE_BACKEND: postgres - MEDIA_ROOT: images/ - POSTGRES_PASSWORD: hunter2 - POSTGRES_USER: postgres - POSTGRES_DB: github_actions - POSTGRES_HOST: 127.0.0.1 - CELERY_BROKER: "" - REDIS_BROKER_PORT: 6379 - REDIS_BROKER_PASSWORD: beep - USE_DUMMY_CACHE: true - FLOWER_PORT: 8888 - EMAIL_HOST: "smtp.mailgun.org" - EMAIL_PORT: 587 - EMAIL_HOST_USER: "" - EMAIL_HOST_PASSWORD: "" - EMAIL_USE_TLS: true - ENABLE_PREVIEW_IMAGES: false - ENABLE_THUMBNAIL_GENERATION: true - HTTP_X_FORWARDED_PROTO: false - run: | - mypy bookwyrm celerywyrm diff --git a/.github/workflows/prettier.yaml b/.github/workflows/prettier.yaml index 501516ae1..9c05c7476 100644 --- a/.github/workflows/prettier.yaml +++ b/.github/workflows/prettier.yaml @@ -14,7 +14,7 @@ jobs: steps: # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it. - - uses: actions/checkout@v3 + - uses: actions/checkout@v4 - name: Install modules run: npm install prettier@2.5.1 diff --git a/.github/workflows/pylint.yml b/.github/workflows/pylint.yml deleted file mode 100644 index ab8633b48..000000000 --- a/.github/workflows/pylint.yml +++ /dev/null @@ -1,27 +0,0 @@ -name: Pylint - -on: - push: - branches: [ main ] - pull_request: - branches: [ main ] - -jobs: - build: - - runs-on: ubuntu-latest - - steps: - - uses: actions/checkout@v3 - - name: Set up Python 3.11 - uses: actions/setup-python@v4 - with: - python-version: 3.11 - - name: Install Dependencies - run: | - python -m pip install --upgrade pip - pip install -r requirements.txt - - name: Analysing the code with pylint - run: | - pylint bookwyrm/ - diff --git a/.github/workflows/python.yml b/.github/workflows/python.yml new file mode 100644 index 000000000..01241b467 --- /dev/null +++ b/.github/workflows/python.yml @@ -0,0 +1,99 @@ +name: Python +on: + push: + branches: [ main ] + pull_request: + branches: [ main ] + +# overrides for .env.example +env: + POSTGRES_HOST: 127.0.0.1 + PGPORT: 5432 + POSTGRES_USER: postgres + POSTGRES_PASSWORD: hunter2 + POSTGRES_DB: github_actions + SECRET_KEY: beepbeep + EMAIL_HOST_USER: "" + EMAIL_HOST_PASSWORD: "" + +jobs: + pytest: + name: Tests (pytest) + runs-on: ubuntu-latest + services: + postgres: + image: postgres:13 + env: # does not inherit from jobs.build.env + POSTGRES_USER: postgres + POSTGRES_PASSWORD: hunter2 + options: >- + --health-cmd pg_isready + --health-interval 10s + --health-timeout 5s + --health-retries 5 + ports: + - 5432:5432 + steps: + - uses: actions/checkout@v4 + - name: Set up Python 3.11 + uses: actions/setup-python@v5 + with: + python-version: 3.11 + cache: pip + - name: Install Dependencies + run: | + python -m pip install --upgrade pip + pip install -r requirements.txt + pip install pytest-github-actions-annotate-failures + - name: Set up .env + run: cp .env.example .env + - name: Check migrations up-to-date + run: python ./manage.py makemigrations --check + - name: Run Tests + run: pytest -n 3 + + pylint: + name: Linting (pylint) + runs-on: ubuntu-latest + steps: + - uses: actions/checkout@v4 + - name: Set up Python 3.11 + uses: actions/setup-python@v5 + with: + python-version: 3.11 + cache: pip + - name: Install Dependencies + run: | + python -m pip install --upgrade pip + pip install -r requirements.txt + - name: Analyse code with pylint + run: pylint bookwyrm/ + + mypy: + name: Typing (mypy) + runs-on: ubuntu-latest + steps: + - uses: actions/checkout@v4 + - name: Set up Python 3.11 + uses: actions/setup-python@v5 + with: + python-version: 3.11 + cache: pip + - name: Install Dependencies + run: | + python -m pip install --upgrade pip + pip install -r requirements.txt + - name: Set up .env + run: cp .env.example .env + - name: Analyse code with mypy + run: mypy bookwyrm celerywyrm + + black: + name: Formatting (black; run ./bw-dev black to fix) + runs-on: ubuntu-latest + steps: + - uses: actions/checkout@v4 + - uses: actions/setup-python@v5 + - uses: psf/black@stable + with: + version: "22.*" diff --git a/.gitignore b/.gitignore index ec2a08f80..755375b34 100644 --- a/.gitignore +++ b/.gitignore @@ -16,6 +16,7 @@ # BookWyrm .env /images/ +/static/ bookwyrm/static/css/bookwyrm.css bookwyrm/static/css/themes/ !bookwyrm/static/css/themes/bookwyrm-*.scss diff --git a/bookwyrm/apps.py b/bookwyrm/apps.py index b0c3e3fa4..41b1a17a2 100644 --- a/bookwyrm/apps.py +++ b/bookwyrm/apps.py @@ -1,4 +1,5 @@ """Do further startup configuration and initialization""" + import os import urllib import logging @@ -14,16 +15,16 @@ def download_file(url, destination): """Downloads a file to the given path""" try: # Ensure our destination directory exists - os.makedirs(os.path.dirname(destination)) + os.makedirs(os.path.dirname(destination), exist_ok=True) with urllib.request.urlopen(url) as stream: with open(destination, "b+w") as outfile: outfile.write(stream.read()) - except (urllib.error.HTTPError, urllib.error.URLError): - logger.info("Failed to download file %s", url) - except OSError: - logger.info("Couldn't open font file %s for writing", destination) - except: # pylint: disable=bare-except - logger.info("Unknown error in file download") + except (urllib.error.HTTPError, urllib.error.URLError) as err: + logger.error("Failed to download file %s: %s", url, err) + except OSError as err: + logger.error("Couldn't open font file %s for writing: %s", destination, err) + except Exception as err: # pylint:disable=broad-except + logger.error("Unknown error in file download: %s", err) class BookwyrmConfig(AppConfig): diff --git a/bookwyrm/forms/author.py b/bookwyrm/forms/author.py index 5b54a07b5..a3a759af7 100644 --- a/bookwyrm/forms/author.py +++ b/bookwyrm/forms/author.py @@ -15,6 +15,7 @@ class AuthorForm(CustomForm): "aliases", "bio", "wikipedia_link", + "wikidata", "website", "born", "died", @@ -32,6 +33,7 @@ class AuthorForm(CustomForm): "wikipedia_link": forms.TextInput( attrs={"aria-describedby": "desc_wikipedia_link"} ), + "wikidata": forms.TextInput(attrs={"aria-describedby": "desc_wikidata"}), "website": forms.TextInput(attrs={"aria-describedby": "desc_website"}), "born": forms.SelectDateWidget(attrs={"aria-describedby": "desc_born"}), "died": forms.SelectDateWidget(attrs={"aria-describedby": "desc_died"}), diff --git a/bookwyrm/migrations/0190_book_search_updates.py b/bookwyrm/migrations/0190_book_search_updates.py new file mode 100644 index 000000000..52d80fcb9 --- /dev/null +++ b/bookwyrm/migrations/0190_book_search_updates.py @@ -0,0 +1,16 @@ +# Generated by Django 3.2.20 on 2023-11-24 17:11 + +from django.db import migrations + + +class Migration(migrations.Migration): + dependencies = [ + ("bookwyrm", "0188_theme_loads"), + ] + + operations = [ + migrations.RemoveIndex( + model_name="author", + name="bookwyrm_au_search__b050a8_gin", + ), + ] diff --git a/bookwyrm/migrations/0191_migrate_search_vec_triggers_to_pgtriggers.py b/bookwyrm/migrations/0191_migrate_search_vec_triggers_to_pgtriggers.py new file mode 100644 index 000000000..03442298f --- /dev/null +++ b/bookwyrm/migrations/0191_migrate_search_vec_triggers_to_pgtriggers.py @@ -0,0 +1,76 @@ +# Generated by Django 3.2.20 on 2023-11-25 00:47 + +from importlib import import_module +import re + +from django.db import migrations +import pgtrigger.compiler +import pgtrigger.migrations + +trigger_migration = import_module("bookwyrm.migrations.0077_auto_20210623_2155") + +# it's _very_ convenient for development that this migration be reversible +search_vector_trigger = trigger_migration.Migration.operations[4] +author_search_vector_trigger = trigger_migration.Migration.operations[5] + + +assert re.search(r"\bCREATE TRIGGER search_vector_trigger\b", search_vector_trigger.sql) +assert re.search( + r"\bCREATE TRIGGER author_search_vector_trigger\b", + author_search_vector_trigger.sql, +) + + +class Migration(migrations.Migration): + dependencies = [ + ("bookwyrm", "0190_book_search_updates"), + ] + + operations = [ + pgtrigger.migrations.AddTrigger( + model_name="book", + trigger=pgtrigger.compiler.Trigger( + name="update_search_vector_on_book_edit", + sql=pgtrigger.compiler.UpsertTriggerSql( + func="new.search_vector := setweight(coalesce(nullif(to_tsvector('english', new.title), ''), to_tsvector('simple', new.title)), 'A') || setweight(to_tsvector('english', coalesce(new.subtitle, '')), 'B') || (SELECT setweight(to_tsvector('simple', coalesce(array_to_string(array_agg(bookwyrm_author.name), ' '), '')), 'C') FROM bookwyrm_author LEFT JOIN bookwyrm_book_authors ON bookwyrm_author.id = bookwyrm_book_authors.author_id WHERE bookwyrm_book_authors.book_id = new.id ) || setweight(to_tsvector('english', coalesce(new.series, '')), 'D');RETURN NEW;", + hash="77d6399497c0a89b0bf09d296e33c396da63705c", + operation='INSERT OR UPDATE OF "title", "subtitle", "series", "search_vector"', + pgid="pgtrigger_update_search_vector_on_book_edit_bec58", + table="bookwyrm_book", + when="BEFORE", + ), + ), + ), + pgtrigger.migrations.AddTrigger( + model_name="author", + trigger=pgtrigger.compiler.Trigger( + name="reset_search_vector_on_author_edit", + sql=pgtrigger.compiler.UpsertTriggerSql( + func="WITH updated_books AS (SELECT book_id FROM bookwyrm_book_authors WHERE author_id = new.id ) UPDATE bookwyrm_book SET search_vector = '' FROM updated_books WHERE id = updated_books.book_id;RETURN NEW;", + hash="e7bbf08711ff3724c58f4d92fb7a082ffb3d7826", + operation='UPDATE OF "name"', + pgid="pgtrigger_reset_search_vector_on_author_edit_a447c", + table="bookwyrm_author", + when="AFTER", + ), + ), + ), + migrations.RunSQL( + sql="""DROP TRIGGER IF EXISTS search_vector_trigger ON bookwyrm_book; + DROP FUNCTION IF EXISTS book_trigger; + """, + reverse_sql=search_vector_trigger.sql, + ), + migrations.RunSQL( + sql="""DROP TRIGGER IF EXISTS author_search_vector_trigger ON bookwyrm_author; + DROP FUNCTION IF EXISTS author_trigger; + """, + reverse_sql=author_search_vector_trigger.sql, + ), + migrations.RunSQL( + # Recalculate book search vector for any missed author name changes + # due to bug in JOIN in the old trigger. + sql="UPDATE bookwyrm_book SET search_vector = NULL;", + reverse_sql=migrations.RunSQL.noop, + ), + ] diff --git a/bookwyrm/migrations/0196_merge_pr3134_into_main.py b/bookwyrm/migrations/0196_merge_pr3134_into_main.py new file mode 100644 index 000000000..0862f11b2 --- /dev/null +++ b/bookwyrm/migrations/0196_merge_pr3134_into_main.py @@ -0,0 +1,13 @@ +# Generated by Django 3.2.23 on 2024-03-18 00:48 + +from django.db import migrations + + +class Migration(migrations.Migration): + + dependencies = [ + ("bookwyrm", "0191_migrate_search_vec_triggers_to_pgtriggers"), + ("bookwyrm", "0195_alter_user_preferred_language"), + ] + + operations = [] diff --git a/bookwyrm/models/author.py b/bookwyrm/models/author.py index 981e3c0cc..154b00ccb 100644 --- a/bookwyrm/models/author.py +++ b/bookwyrm/models/author.py @@ -2,11 +2,12 @@ import re from typing import Tuple, Any -from django.contrib.postgres.indexes import GinIndex from django.db import models +import pgtrigger from bookwyrm import activitypub from bookwyrm.settings import DOMAIN +from bookwyrm.utils.db import format_trigger from .book import BookDataModel from . import fields @@ -67,9 +68,28 @@ class Author(BookDataModel): """editions and works both use "book" instead of model_name""" return f"https://{DOMAIN}/author/{self.id}" - activity_serializer = activitypub.Author - class Meta: - """sets up postgres GIN index field""" + """sets up indexes and triggers""" - indexes = (GinIndex(fields=["search_vector"]),) + triggers = [ + pgtrigger.Trigger( + name="reset_search_vector_on_author_edit", + when=pgtrigger.After, + operation=pgtrigger.UpdateOf("name"), + func=format_trigger( + """WITH updated_books AS ( + SELECT book_id + FROM bookwyrm_book_authors + WHERE author_id = new.id + ) + UPDATE bookwyrm_book + SET search_vector = '' + FROM updated_books + WHERE id = updated_books.book_id; + RETURN new; + """ + ), + ) + ] + + activity_serializer = activitypub.Author diff --git a/bookwyrm/models/book.py b/bookwyrm/models/book.py index 6893b9da1..e167e2138 100644 --- a/bookwyrm/models/book.py +++ b/bookwyrm/models/book.py @@ -13,6 +13,7 @@ from django.utils.translation import gettext_lazy as _ from model_utils import FieldTracker from model_utils.managers import InheritanceManager from imagekit.models import ImageSpecField +import pgtrigger from bookwyrm import activitypub from bookwyrm.isbn.isbn import hyphenator_singleton as hyphenator @@ -24,6 +25,7 @@ from bookwyrm.settings import ( ENABLE_PREVIEW_IMAGES, ENABLE_THUMBNAIL_GENERATION, ) +from bookwyrm.utils.db import format_trigger from .activitypub_mixin import OrderedCollectionPageMixin, ObjectMixin from .base_model import BookWyrmModel @@ -232,9 +234,39 @@ class Book(BookDataModel): ) class Meta: - """sets up postgres GIN index field""" + """set up indexes and triggers""" + + # pylint: disable=line-too-long indexes = (GinIndex(fields=["search_vector"]),) + triggers = [ + pgtrigger.Trigger( + name="update_search_vector_on_book_edit", + when=pgtrigger.Before, + operation=pgtrigger.Insert + | pgtrigger.UpdateOf("title", "subtitle", "series", "search_vector"), + func=format_trigger( + """new.search_vector := + -- title, with priority A (parse in English, default to simple if empty) + setweight(COALESCE(nullif( + to_tsvector('english', new.title), ''), + to_tsvector('simple', new.title)), 'A') || + -- subtitle, with priority B (always in English?) + setweight(to_tsvector('english', COALESCE(new.subtitle, '')), 'B') || + -- list of authors, with priority C (TODO: add aliases?, bookwyrm-social#3063) + (SELECT setweight(to_tsvector('simple', COALESCE(array_to_string(ARRAY_AGG(bookwyrm_author.name), ' '), '')), 'C') + FROM bookwyrm_author + LEFT JOIN bookwyrm_book_authors + ON bookwyrm_author.id = bookwyrm_book_authors.author_id + WHERE bookwyrm_book_authors.book_id = new.id + ) || + --- last: series name, with lowest priority + setweight(to_tsvector('english', COALESCE(new.series, '')), 'D'); + RETURN new; + """ + ), + ) + ] class Work(OrderedCollectionPageMixin, Book): diff --git a/bookwyrm/preview_images.py b/bookwyrm/preview_images.py index aba372abc..995f25bfd 100644 --- a/bookwyrm/preview_images.py +++ b/bookwyrm/preview_images.py @@ -1,4 +1,5 @@ """ Generate social media preview images for twitter/mastodon/etc """ + import math import os import textwrap @@ -42,8 +43,8 @@ def get_imagefont(name, size): return ImageFont.truetype(path, size) except KeyError: logger.error("Font %s not found in config", name) - except OSError: - logger.error("Could not load font %s from file", name) + except OSError as err: + logger.error("Could not load font %s from file: %s", name, err) return ImageFont.load_default() @@ -59,7 +60,7 @@ def get_font(weight, size=28): font.set_variation_by_name("Bold") if weight == "regular": font.set_variation_by_name("Regular") - except AttributeError: + except OSError: pass return font diff --git a/bookwyrm/settings.py b/bookwyrm/settings.py index 2bb68ff85..77bec0d8e 100644 --- a/bookwyrm/settings.py +++ b/bookwyrm/settings.py @@ -108,6 +108,7 @@ INSTALLED_APPS = [ "celery", "django_celery_beat", "imagekit", + "pgtrigger", "storages", ] diff --git a/bookwyrm/templates/author/edit_author.html b/bookwyrm/templates/author/edit_author.html index 12ddc4d28..f3e908c9b 100644 --- a/bookwyrm/templates/author/edit_author.html +++ b/bookwyrm/templates/author/edit_author.html @@ -55,6 +55,8 @@

{{ form.wikipedia_link }}

+

{{ form.wikidata }}

+ {% include 'snippets/form_errors.html' with errors_list=form.wikipedia_link.errors id="desc_wikipedia_link" %}

{{ form.website }}

diff --git a/bookwyrm/templates/search/book.html b/bookwyrm/templates/search/book.html index 262dcf2f9..b93c96754 100644 --- a/bookwyrm/templates/search/book.html +++ b/bookwyrm/templates/search/book.html @@ -109,7 +109,7 @@

{% if request.user.is_authenticated %} {% if not remote %} - + {% trans "Load results from other catalogues" %} {% else %} diff --git a/bookwyrm/templates/search/layout.html b/bookwyrm/templates/search/layout.html index 725a4f43f..59ea0304e 100644 --- a/bookwyrm/templates/search/layout.html +++ b/bookwyrm/templates/search/layout.html @@ -41,18 +41,18 @@

diff --git a/bookwyrm/tests/data/user_import.json b/bookwyrm/tests/data/user_import.json index 0318ddfeb..ffe2e7d9e 100644 --- a/bookwyrm/tests/data/user_import.json +++ b/bookwyrm/tests/data/user_import.json @@ -136,6 +136,7 @@ ], "bio": "

American political scientist and anthropologist

", "wikipediaLink": "https://en.wikipedia.org/wiki/James_C._Scott", + "wikidata": "Q3025403", "website": "", "@context": "https://www.w3.org/ns/activitystreams" } @@ -320,6 +321,7 @@ "aliases": [], "bio": "", "wikipediaLink": "", + "wikidata": "", "website": "", "@context": "https://www.w3.org/ns/activitystreams" } @@ -396,4 +398,4 @@ "https://your.domain.here/user/rat" ], "blocks": ["https://your.domain.here/user/badger"] -} \ No newline at end of file +} diff --git a/bookwyrm/tests/test_book_search.py b/bookwyrm/tests/test_book_search.py index d2056bfeb..0721cb142 100644 --- a/bookwyrm/tests/test_book_search.py +++ b/bookwyrm/tests/test_book_search.py @@ -1,5 +1,6 @@ """ test searching for books """ import datetime +from django.db import connection from django.test import TestCase from django.utils import timezone @@ -140,3 +141,244 @@ class BookSearch(TestCase): # there's really not much to test here, it's just a dataclass self.assertEqual(result.confidence, 1) self.assertEqual(result.title, "Title") + + +class SearchVectorTest(TestCase): + """check search_vector is computed correctly""" + + def test_search_vector_simple(self): + """simplest search vector""" + book = self._create_book("Book", "Mary") + self.assertEqual(book.search_vector, "'book':1A 'mary':2C") # A > C (priority) + + def test_search_vector_all_parts(self): + """search vector with subtitle and series""" + # for a book like this we call `to_tsvector("Book Long Mary Bunch")`, hence the + # indexes in the search vector. (priority "D" is the default, and never shown.) + book = self._create_book("Book", "Mary", subtitle="Long", series="Bunch") + self.assertEqual(book.search_vector, "'book':1A 'bunch':4 'long':2B 'mary':3C") + + def test_search_vector_parse_book(self): + """book parts are parsed in english""" + # FIXME: at some point this should stop being the default. + book = self._create_book( + "Edition", "Editor", series="Castle", subtitle="Writing" + ) + self.assertEqual( + book.search_vector, "'castl':4 'edit':1A 'editor':3C 'write':2B" + ) + + def test_search_vector_parse_author(self): + """author name is not stem'd or affected by stop words""" + book = self._create_book("Writing", "Writes") + self.assertEqual(book.search_vector, "'write':1A 'writes':2C") + + book = self._create_book("She Is Writing", "She Writes") + self.assertEqual(book.search_vector, "'she':4C 'write':3A 'writes':5C") + + def test_search_vector_parse_title_empty(self): + """empty parse in English retried as simple title""" + book = self._create_book("Here We", "John") + self.assertEqual(book.search_vector, "'here':1A 'john':3C 'we':2A") + + book = self._create_book("Hear We Come", "John") + self.assertEqual(book.search_vector, "'come':3A 'hear':1A 'john':4C") + + book = self._create_book("there there", "the") + self.assertEqual(book.search_vector, "'the':3C 'there':1A,2A") + + def test_search_vector_no_author(self): + """book with no authors gets processed normally""" + book = self._create_book("Book", None, series="Bunch") + self.assertEqual(book.search_vector, "'book':1A 'bunch':2") + + book = self._create_book("there there", None) + self.assertEqual(book.search_vector, "'there':1A,2A") + + # n.b.: the following originally from test_posgres.py + + def test_search_vector_on_update(self): + """make sure that search_vector is being set correctly on edit""" + book = self._create_book("The Long Goodbye", None) + self.assertEqual(book.search_vector, "'goodby':3A 'long':2A") + + book.title = "The Even Longer Goodbye" + book.save(broadcast=False) + book.refresh_from_db() + self.assertEqual(book.search_vector, "'even':2A 'goodby':4A 'longer':3A") + + def test_search_vector_on_author_update(self): + """update search when an author name changes""" + book = self._create_book("The Long Goodbye", "The Rays") + self.assertEqual(book.search_vector, "'goodby':3A 'long':2A 'rays':5C 'the':4C") + + author = models.Author.objects.get(name="The Rays") + author.name = "Jeremy" + author.save(broadcast=False) + book.refresh_from_db() + self.assertEqual(book.search_vector, "'goodby':3A 'jeremy':4C 'long':2A") + + def test_search_vector_on_author_delete(self): + """update search when an author is deleted""" + book = self._create_book("The Long Goodbye", "The Rays") + self.assertEqual(book.search_vector, "'goodby':3A 'long':2A 'rays':5C 'the':4C") + + author = models.Author.objects.get(name="The Rays") + book.authors.remove(author) + book.refresh_from_db() + self.assertEqual(book.search_vector, "'goodby':3A 'long':2A") + + def test_search_vector_fields(self): + """language field irrelevant for search_vector""" + author = models.Author.objects.create(name="The Rays") + book = models.Edition.objects.create( + title="The Long Goodbye", + subtitle="wow cool", + series="series name", + languages=["irrelevant"], + ) + book.authors.add(author) + book.refresh_from_db() + self.assertEqual( + book.search_vector, + # pylint: disable-next=line-too-long + "'cool':5B 'goodby':3A 'long':2A 'name':9 'rays':7C 'seri':8 'the':6C 'wow':4B", + ) + + @staticmethod + def _create_book( + title, author_name, /, *, subtitle="", series="", author_alias=None + ): + """quickly create a book""" + work = models.Work.objects.create(title="work") + edition = models.Edition.objects.create( + title=title, + series=series or None, + subtitle=subtitle or None, + isbn_10="0000000000", + parent_work=work, + ) + if author_name is not None: + author = models.Author.objects.create( + name=author_name, aliases=author_alias or [] + ) + edition.authors.add(author) + edition.save(broadcast=False) + edition.refresh_from_db() + return edition + + +class SearchVectorUpdates(TestCase): + """look for books as they change""" # functional tests of the above + + def setUp(self): + """we need basic test data and mocks""" + self.work = models.Work.objects.create(title="This Work") + self.author = models.Author.objects.create(name="Name") + self.edition = models.Edition.objects.create( + title="First Edition of Work", + subtitle="Some Extra Words Are Good", + series="A Fabulous Sequence of Items", + parent_work=self.work, + isbn_10="0000000000", + ) + self.edition.authors.add(self.author) + self.edition.save(broadcast=False) + + @classmethod + def setUpTestData(cls): + """create conditions that trigger known old bugs""" + with connection.cursor() as cursor: + cursor.execute( + """ + ALTER SEQUENCE bookwyrm_author_id_seq RESTART WITH 20; + ALTER SEQUENCE bookwyrm_book_authors_id_seq RESTART WITH 300; + """ + ) + + def test_search_after_changed_metadata(self): + """book found after updating metadata""" + self.assertEqual(self.edition, self._search_first("First")) # title + self.assertEqual(self.edition, self._search_first("Good")) # subtitle + self.assertEqual(self.edition, self._search_first("Sequence")) # series + + self.edition.title = "Second Title of Work" + self.edition.subtitle = "Fewer Words Is Better" + self.edition.series = "A Wondrous Bunch" + self.edition.save(broadcast=False) + + self.assertEqual(self.edition, self._search_first("Second")) # title new + self.assertEqual(self.edition, self._search_first("Fewer")) # subtitle new + self.assertEqual(self.edition, self._search_first("Wondrous")) # series new + + self.assertFalse(self._search_first("First")) # title old + self.assertFalse(self._search_first("Good")) # subtitle old + self.assertFalse(self._search_first("Sequence")) # series old + + def test_search_after_author_remove(self): + """book not found via removed author""" + self.assertEqual(self.edition, self._search_first("Name")) + + self.edition.authors.set([]) + self.edition.save(broadcast=False) + + self.assertFalse(self._search("Name")) + self.assertEqual(self.edition, self._search_first("Edition")) + + def test_search_after_author_add(self): + """book found by newly-added author""" + new_author = models.Author.objects.create(name="Mozilla") + + self.assertFalse(self._search("Mozilla")) + + self.edition.authors.add(new_author) + self.edition.save(broadcast=False) + + self.assertEqual(self.edition, self._search_first("Mozilla")) + self.assertEqual(self.edition, self._search_first("Name")) + + def test_search_after_author_add_remove_sql(self): + """add/remove author through SQL to ensure execution of book_authors trigger""" + # Tests calling edition.save(), above, pass even if the trigger in + # bookwyrm_book_authors is removed (probably because they trigger the one + # in bookwyrm_book directly). Here we make sure to exercise the former. + new_author = models.Author.objects.create(name="Mozilla") + + with connection.cursor() as cursor: + cursor.execute( + "DELETE FROM bookwyrm_book_authors WHERE book_id = %s", + [self.edition.id], + ) + self.assertFalse(self._search("Name")) + self.assertFalse(self._search("Mozilla")) + + with connection.cursor() as cursor: + cursor.execute( + "INSERT INTO bookwyrm_book_authors (book_id,author_id) VALUES (%s,%s)", + [self.edition.id, new_author.id], + ) + self.assertFalse(self._search("Name")) + self.assertEqual(self.edition, self._search_first("Mozilla")) + + def test_search_after_updated_author_name(self): + """book found under new author name""" + self.assertEqual(self.edition, self._search_first("Name")) + self.assertFalse(self._search("Identifier")) + + self.author.name = "Identifier" + self.author.save(broadcast=False) + + self.assertFalse(self._search("Name")) + self.assertEqual(self.edition, self._search_first("Identifier")) + self.assertEqual(self.edition, self._search_first("Work")) + + def _search_first(self, query): + """wrapper around search_title_author""" + return self._search(query, return_first=True) + + @staticmethod + def _search(query, *, return_first=False): + """wrapper around search_title_author""" + return book_search.search_title_author( + query, min_confidence=0, return_first=return_first + ) diff --git a/bookwyrm/tests/test_postgres.py b/bookwyrm/tests/test_postgres.py deleted file mode 100644 index 8fc3c9d59..000000000 --- a/bookwyrm/tests/test_postgres.py +++ /dev/null @@ -1,77 +0,0 @@ -""" django configuration of postgres """ -from unittest.mock import patch -from django.test import TestCase - -from bookwyrm import models - - -@patch("bookwyrm.models.activitypub_mixin.broadcast_task.apply_async") -class PostgresTriggers(TestCase): - """special migrations, fancy stuff ya know""" - - def test_search_vector_on_create(self, _): - """make sure that search_vector is being set correctly on create""" - book = models.Edition.objects.create(title="The Long Goodbye") - book.refresh_from_db() - self.assertEqual(book.search_vector, "'goodby':3A 'long':2A") - - def test_search_vector_on_update(self, _): - """make sure that search_vector is being set correctly on edit""" - book = models.Edition.objects.create(title="The Long Goodbye") - book.title = "The Even Longer Goodbye" - book.save(broadcast=False) - book.refresh_from_db() - self.assertEqual(book.search_vector, "'even':2A 'goodby':4A 'longer':3A") - - def test_search_vector_fields(self, _): - """use multiple fields to create search vector""" - author = models.Author.objects.create(name="The Rays") - book = models.Edition.objects.create( - title="The Long Goodbye", - subtitle="wow cool", - series="series name", - languages=["irrelevant"], - ) - book.authors.add(author) - book.refresh_from_db() - # pylint: disable=line-too-long - self.assertEqual( - book.search_vector, - "'cool':5B 'goodby':3A 'long':2A 'name':9 'rays':7C 'seri':8 'the':6C 'wow':4B", - ) - - def test_search_vector_on_author_update(self, _): - """update search when an author name changes""" - author = models.Author.objects.create(name="The Rays") - book = models.Edition.objects.create( - title="The Long Goodbye", - ) - book.authors.add(author) - author.name = "Jeremy" - author.save(broadcast=False) - book.refresh_from_db() - - self.assertEqual(book.search_vector, "'goodby':3A 'jeremy':4C 'long':2A") - - def test_search_vector_on_author_delete(self, _): - """update search when an author name changes""" - author = models.Author.objects.create(name="Jeremy") - book = models.Edition.objects.create( - title="The Long Goodbye", - ) - - book.authors.add(author) - book.refresh_from_db() - self.assertEqual(book.search_vector, "'goodby':3A 'jeremy':4C 'long':2A") - - book.authors.remove(author) - book.refresh_from_db() - self.assertEqual(book.search_vector, "'goodby':3A 'long':2A") - - def test_search_vector_stop_word_fallback(self, _): - """use a fallback when removing stop words leads to an empty vector""" - book = models.Edition.objects.create( - title="there there", - ) - book.refresh_from_db() - self.assertEqual(book.search_vector, "'there':1A,2A") diff --git a/bookwyrm/utils/db.py b/bookwyrm/utils/db.py new file mode 100644 index 000000000..2bb3b9ff6 --- /dev/null +++ b/bookwyrm/utils/db.py @@ -0,0 +1,23 @@ +""" Database utilities """ + +from typing import cast +import sqlparse # type: ignore + + +def format_trigger(sql: str) -> str: + """format SQL trigger before storing + + we remove whitespace and use consistent casing so as to avoid migrations + due to formatting changes. + """ + return cast( + str, + sqlparse.format( + sql, + strip_comments=True, + strip_whitespace=True, + use_space_around_operators=True, + keyword_case="upper", + identifier_case="lower", + ), + ) diff --git a/bookwyrm/views/books/editions.py b/bookwyrm/views/books/editions.py index 86f818d54..a3167fac4 100644 --- a/bookwyrm/views/books/editions.py +++ b/bookwyrm/views/books/editions.py @@ -3,6 +3,7 @@ from functools import reduce import operator from django.contrib.auth.decorators import login_required +from django.core.cache import cache as django_cache from django.core.paginator import Paginator from django.db import transaction from django.db.models import Q @@ -104,6 +105,13 @@ def switch_edition(request): readthrough.book = new_edition readthrough.save() + django_cache.delete_many( + [ + f"active_shelf-{request.user.id}-{book_id}" + for book_id in new_edition.parent_work.editions.values_list("id", flat=True) + ] + ) + reviews = models.Review.objects.filter( book__parent_work=new_edition.parent_work, user=request.user ) diff --git a/dev-tools/requirements.txt b/dev-tools/requirements.txt index a69d319ab..3bb771f5a 100644 --- a/dev-tools/requirements.txt +++ b/dev-tools/requirements.txt @@ -1 +1 @@ -black==22.12.0 +black==22.* diff --git a/docker-compose.yml b/docker-compose.yml index 4d4037681..034cc2677 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -11,7 +11,7 @@ services: networks: - main volumes: - - ./nginx:/etc/nginx/conf.d + - ./nginx:/etc/nginx/conf.d:ro - static_volume:/app/static - media_volume:/app/images db: @@ -26,7 +26,7 @@ services: env_file: .env command: python manage.py runserver 0.0.0.0:8000 volumes: - - .:/app + - .:/app:ro - static_volume:/app/static - media_volume:/app/images depends_on: @@ -41,7 +41,7 @@ services: image: redis:7.2.1 command: redis-server --requirepass ${REDIS_ACTIVITY_PASSWORD} --appendonly yes --port ${REDIS_ACTIVITY_PORT} volumes: - - ./redis.conf:/etc/redis/redis.conf + - ./redis.conf:/etc/redis/redis.conf:ro - redis_activity_data:/data env_file: .env networks: @@ -51,7 +51,7 @@ services: image: redis:7.2.1 command: redis-server --requirepass ${REDIS_BROKER_PASSWORD} --appendonly yes --port ${REDIS_BROKER_PORT} volumes: - - ./redis.conf:/etc/redis/redis.conf + - ./redis.conf:/etc/redis/redis.conf:ro - redis_broker_data:/data env_file: .env networks: @@ -63,9 +63,8 @@ services: networks: - main command: celery -A celerywyrm worker -l info -Q high_priority,medium_priority,low_priority,streams,images,suggested_users,email,connectors,lists,inbox,imports,import_triggered,broadcast,misc - volumes: - - .:/app + - .:/app:ro - static_volume:/app/static - media_volume:/app/images depends_on: @@ -79,7 +78,7 @@ services: - main command: celery -A celerywyrm beat -l INFO --scheduler django_celery_beat.schedulers:DatabaseScheduler volumes: - - .:/app + - .:/app:ro - static_volume:/app/static - media_volume:/app/images depends_on: @@ -90,7 +89,8 @@ services: command: celery -A celerywyrm flower --basic_auth=${FLOWER_USER}:${FLOWER_PASSWORD} --url_prefix=flower env_file: .env volumes: - - .:/app + - .:/app:ro + - static_volume:/app/static networks: - main depends_on: @@ -102,7 +102,9 @@ services: env_file: .env volumes: - /app/dev-tools/ - - .:/app + - .:/app:rw + profiles: + - tools volumes: pgdata: static_volume: diff --git a/images/.gitkeep b/images/.gitkeep new file mode 100644 index 000000000..e69de29bb diff --git a/pyproject.toml b/pyproject.toml new file mode 100644 index 000000000..292ca8c41 --- /dev/null +++ b/pyproject.toml @@ -0,0 +1,2 @@ +[tool.black] +required-version = "22" diff --git a/requirements.txt b/requirements.txt index c769916a2..6b3d838bf 100644 --- a/requirements.txt +++ b/requirements.txt @@ -4,12 +4,13 @@ boto3==1.26.57 bw-file-resubmit==0.6.0rc2 celery==5.3.1 colorthief==0.2.1 -Django==3.2.24 +Django==3.2.25 django-celery-beat==2.5.0 django-compressor==4.4 django-csp==3.7 django-imagekit==4.1.0 django-model-utils==4.3.1 +django-pgtrigger==4.11.0 django-redis==5.2.0 django-sass-processor==1.2.2 django-storages==1.13.2 @@ -25,7 +26,7 @@ opentelemetry-instrumentation-celery==0.37b0 opentelemetry-instrumentation-django==0.37b0 opentelemetry-instrumentation-psycopg2==0.37b0 opentelemetry-sdk==1.16.0 -Pillow==10.0.1 +Pillow==10.2.0 protobuf==3.20.* psycopg2==2.9.5 pycryptodome==3.19.1 @@ -40,6 +41,7 @@ setuptools>=65.5.1 # Not a direct dependency, pinned to get a security fix tornado==6.3.3 # Not a direct dependency, pinned to get a security fix # Dev +black==22.* celery-types==0.18.0 django-stubs[compatible-mypy]==4.2.4 mypy==1.5.1 @@ -53,7 +55,7 @@ pytidylib==0.3.2 types-bleach==6.0.0.4 types-dataclasses==0.6.6 types-Markdown==3.4.2.10 -types-Pillow==10.0.0.3 +types-Pillow==10.2.0.20240311 types-psycopg2==2.9.21.11 types-python-dateutil==2.8.19.14 types-requests==2.31.0.2 diff --git a/static/.gitkeep b/static/.gitkeep new file mode 100644 index 000000000..e69de29bb