Merge branch 'main' into csv

.env.example

@@ -16,6 +16,11 @@ DEFAULT_LANGUAGE="English"
 ## Leave unset to allow all hosts
 # ALLOWED_HOSTS="localhost,127.0.0.1,[::1]"
 
+# Specify when the site is served from a port that is not the default
+# for the protocol (80 for HTTP or 443 for HTTPS).
+# Probably only necessary in development.
+# PORT=1333
+
 MEDIA_ROOT=images/
 
 # Database configuration
@@ -71,14 +76,20 @@ ENABLE_THUMBNAIL_GENERATION=true
 USE_S3=false
 AWS_ACCESS_KEY_ID=
 AWS_SECRET_ACCESS_KEY=
+# seconds for signed S3 urls to expire
+# this is currently only used for user export files
+S3_SIGNED_URL_EXPIRY=900
 
 # Commented are example values if you use a non-AWS, S3-compatible service
 # AWS S3 should work with only AWS_STORAGE_BUCKET_NAME and AWS_S3_REGION_NAME
 # non-AWS S3-compatible services will need AWS_STORAGE_BUCKET_NAME,
-# along with both AWS_S3_CUSTOM_DOMAIN and AWS_S3_ENDPOINT_URL
+# along with both AWS_S3_CUSTOM_DOMAIN and AWS_S3_ENDPOINT_URL.
+# AWS_S3_URL_PROTOCOL must end in ":" and defaults to the same protocol as
+# the BookWyrm instance ("http:" or "https:", based on USE_SSL).
 
 # AWS_STORAGE_BUCKET_NAME=        # "example-bucket-name"
 # AWS_S3_CUSTOM_DOMAIN=None       # "example-bucket-name.s3.fr-par.scw.cloud"
+# AWS_S3_URL_PROTOCOL=None        # "http:"
 # AWS_S3_REGION_NAME=None         # "fr-par"
 # AWS_S3_ENDPOINT_URL=None        # "https://s3.fr-par.scw.cloud"
 
@@ -133,7 +144,14 @@ HTTP_X_FORWARDED_PROTO=false
 TWO_FACTOR_LOGIN_VALIDITY_WINDOW=2
 TWO_FACTOR_LOGIN_MAX_SECONDS=60
 
-# Additional hosts to allow in the Content-Security-Policy, "self" (should be DOMAIN)
-# and AWS_S3_CUSTOM_DOMAIN (if used) are added by default.
-# Value should be a comma-separated list of host names.
+# Additional hosts to allow in the Content-Security-Policy, "self" (should be
+# DOMAIN with optionally ":" + PORT) and AWS_S3_CUSTOM_DOMAIN (if used) are
+# added by default.  Value should be a comma-separated list of host names.
 CSP_ADDITIONAL_HOSTS=
+
+# Time before being logged out (in seconds)
+# SESSION_COOKIE_AGE=2592000   # current default: 30 days
+
+# Maximum allowed memory for file uploads (increase if users are having trouble
+# uploading BookWyrm export files).
+# DATA_UPLOAD_MAX_MEMORY_MiB=100

.github/pull_request_template.md

@@ -0,0 +1,78 @@
+<!--
+Thanks for contributing!
+
+Please ensure the name of your PR is written in imperative present tense. For example:
+
+- "fix color contrast on submit buttons"
+- "add 'favourite food' value to Author model"
+
+To check (tick) a list item, replace the space between square brackets with an x, like this:
+
+- [x] I have checked the box
+
+You can find more information and tips for BookWyrm contributors at https://docs.joinbookwyrm.com/contributing.html
+-->
+
+## Are you finished?
+
+### Linters
+<!--
+Please run linters on your code before submitting your PR.
+If you miss this step it is likely that the GitHub task runners will fail.
+-->
+
+- [ ] I have checked my code with `black`, `pylint`, and `mypy`, or `./bw-dev formatters`
+
+### Tests
+<!-- Check one -->
+
+- [ ] My changes do not need new tests
+- [ ] All tests I have added are passing
+- [ ] I have written tests but need help to make them pass
+- [ ] I have not written tests and need help to write them
+
+## What type of Pull Request is this?
+<!-- Check all that apply -->
+
+- [ ] Bug Fix
+- [ ] Enhancement
+- [ ] Plumbing / Internals / Dependencies
+- [ ] Refactor
+
+## Does this PR change settings or dependencies, or break something?
+<!-- Check all that apply -->
+
+- [ ] This PR changes or adds default settings, configuration, or .env values
+- [ ] This PR changes or adds dependencies
+- [ ] This PR introduces other breaking changes
+
+### Details of breaking or configuration changes (if any of above checked)
+
+## Description
+
+<!--
+Describe what your pull request does here.
+
+For pull requests that relate or close an issue, please include them
+below.  We like to follow [Github's guidance on linking issues to pull requests](https://docs.github.com/en/issues/tracking-your-work-with-issues/linking-a-pull-request-to-an-issue).
+
+For example having the text: "closes #1234" would connect the current pull
+request to issue 1234.  And when we merge the pull request, Github will
+automatically close the issue.
+-->
+
+- Related Issue #
+- Closes #
+
+## Documentation
+<!--
+Documentation for users, admins, and developers is an important way to keep the BookWyrm community welcoming and make Bookwyrm easy to use.
+Our documentation is maintained in a separate repository at https://github.com/bookwyrm-social/documentation
+-->
+
+<!-- Check all that apply -->
+
+- [ ] New or amended documentation will be required if this PR is merged
+- [ ] I have created a matching pull request in the Documentation repository
+- [ ] I intend to create a matching pull request in the Documentation repository after this PR is merged
+

.github/release.yml

@@ -0,0 +1,26 @@
+changelog:
+  exclude:
+    labels:
+      - ignore-for-release
+  categories:
+    - title: ‼️ Breaking Changes & New Settings ⚙️
+      labels:
+        - breaking-change
+        - config-change
+    - title: Updated Dependencies 🧸
+      labels:
+        - dependencies
+    - title: New Features 🎉
+      labels:
+        - enhancement
+    - title: Bug Fixes 🐛
+      labels:
+        - fix
+        - bug
+    - title: Internals/Plumbing 👩‍🔧
+        - plumbing
+        - tests
+        - deployment
+    - title: Other Changes
+      labels:
+        - "*"

.github/workflows/black.yml

@@ -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

.github/workflows/codeql-analysis.yml

@@ -36,11 +36,11 @@ jobs:
 
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v3
+      uses: actions/checkout@v4
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v2
+      uses: github/codeql-action/init@v3
       with:
         languages: ${{ matrix.language }}
         # If you wish to specify custom queries, you can do so here or in a config file.
@@ -51,7 +51,7 @@ jobs:
     # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
     # If this step fails, then you should remove it and run the build manually (see below)
     - name: Autobuild
-      uses: github/codeql-action/autobuild@v2
+      uses: github/codeql-action/autobuild@v3
 
     # ℹ️ Command-line programs to run using the OS shell.
     # 📚 https://git.io/JvXDl
@@ -65,4 +65,4 @@ jobs:
     #   make release
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v2
+      uses: github/codeql-action/analyze@v3

.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

.github/workflows/django-tests.yml

@@ -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: 3.9
-    - 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

.github/workflows/lint-frontend.yaml

@@ -19,10 +19,11 @@ 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
+      #  run: npm install stylelint stylelint-config-recommended stylelint-config-standard stylelint-order eslint
+        run: npm install eslint@^8.9.0
 
       # See .stylelintignore for files that are not linted.
       # - name: Run stylelint

.github/workflows/mypy.yml

@@ -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 3.9
-      uses: actions/setup-python@v4
-      with:
-        python-version: 3.9
-    - 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

.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

.github/workflows/pylint.yml

@@ -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 3.9
-      uses: actions/setup-python@v4
-      with:
-        python-version: 3.9
-    - name: Install Dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install -r requirements.txt
-    - name: Analysing the code with pylint
-      run: |
-        pylint bookwyrm/
-

.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.*"

.gitignore

@@ -16,6 +16,8 @@
 # BookWyrm
 .env
 /images/
+/exports/
+/static/
 bookwyrm/static/css/bookwyrm.css
 bookwyrm/static/css/themes/
 !bookwyrm/static/css/themes/bookwyrm-*.scss
@@ -36,3 +38,6 @@ nginx/default.conf
 
 #macOS
 **/.DS_Store
+
+# Docker
+docker-compose.override.yml

Dockerfile

@@ -1,4 +1,4 @@
-FROM python:3.9
+FROM python:3.11
 
 ENV PYTHONUNBUFFERED 1
 

README.md

@@ -10,7 +10,6 @@ BookWyrm is a social network for tracking your reading, talking about books, wri
 ## Links
 
 [![Mastodon Follow](https://img.shields.io/mastodon/follow/000146121?domain=https%3A%2F%2Ftech.lgbt&style=social)](https://tech.lgbt/@bookwyrm)
-[![Twitter Follow](https://img.shields.io/twitter/follow/BookWyrmSocial?style=social)](https://twitter.com/BookWyrmSocial)
 
  - [Project homepage](https://joinbookwyrm.com/)
  - [Support](https://patreon.com/bookwyrm)

VERSION

@@ -1 +1 @@
-0.7.0
+0.7.3

bookwyrm/activitypub/base_activity.py

@@ -20,6 +20,7 @@ from bookwyrm.tasks import app, MISC
 
 logger = logging.getLogger(__name__)
 
+# pylint: disable=invalid-name
 TBookWyrmModel = TypeVar("TBookWyrmModel", bound=base_model.BookWyrmModel)
 
 
@@ -236,7 +237,7 @@ class ActivityObject:
         omit = kwargs.get("omit", ())
         data = self.__dict__.copy()
         # recursively serialize
-        for (k, v) in data.items():
+        for k, v in data.items():
             try:
                 if issubclass(type(v), ActivityObject):
                     data[k] = v.serialize()
@@ -249,7 +250,10 @@ class ActivityObject:
                 pass
         data = {k: v for (k, v) in data.items() if v is not None and k not in omit}
         if "@context" not in omit:
-            data["@context"] = "https://www.w3.org/ns/activitystreams"
+            data["@context"] = [
+                "https://www.w3.org/ns/activitystreams",
+                {"Hashtag": "as:Hashtag"},
+            ]
         return data
 
 
@@ -397,18 +401,14 @@ def resolve_remote_id(
 def get_representative():
     """Get or create an actor representing the instance
     to sign outgoing HTTP GET requests"""
-    username = f"{INSTANCE_ACTOR_USERNAME}@{DOMAIN}"
-    email = "bookwyrm@localhost"
-    try:
-        user = models.User.objects.get(username=username)
-    except models.User.DoesNotExist:
-        user = models.User.objects.create_user(
-            username=username,
-            email=email,
-            local=True,
-            localname=INSTANCE_ACTOR_USERNAME,
-        )
-    return user
+    return models.User.objects.get_or_create(
+        username=f"{INSTANCE_ACTOR_USERNAME}@{DOMAIN}",
+        defaults={
+            "email": "bookwyrm@localhost",
+            "local": True,
+            "localname": INSTANCE_ACTOR_USERNAME,
+        },
+    )[0]
 
 
 def get_activitypub_data(url):
@@ -427,6 +427,7 @@ def get_activitypub_data(url):
                 "Date": now,
                 "Signature": make_signature("get", sender, url, now),
             },
+            timeout=15,
         )
     except requests.RequestException:
         raise ConnectorException()

bookwyrm/activitypub/person.py

@@ -1,5 +1,5 @@
 """ actor serializer """
-from dataclasses import dataclass, field
+from dataclasses import dataclass
 from typing import Dict
 
 from .base_activity import ActivityObject
@@ -35,7 +35,7 @@ class Person(ActivityObject):
     endpoints: Dict = None
     name: str = None
     summary: str = None
-    icon: Image = field(default_factory=lambda: {})
+    icon: Image = None
     bookwyrmUser: bool = False
     manuallyApprovesFollowers: str = False
     discoverable: str = False

bookwyrm/activitypub/verbs.py

@@ -171,9 +171,19 @@ class Reject(Verb):
     type: str = "Reject"
 
     def action(self, allow_external_connections=True):
-        """reject a follow request"""
-        obj = self.object.to_model(save=False, allow_create=False)
-        obj.reject()
+        """reject a follow or follow request"""
+
+        for model_name in ["UserFollowRequest", "UserFollows", None]:
+            model = apps.get_model(f"bookwyrm.{model_name}") if model_name else None
+            if obj := self.object.to_model(
+                model=model,
+                save=False,
+                allow_create=False,
+                allow_external_connections=allow_external_connections,
+            ):
+                # Reject the first model that can be built.
+                obj.reject()
+                break
 
 
 @dataclass(init=False)

bookwyrm/activitystreams.py

@@ -139,14 +139,14 @@ class ActivityStream(RedisStore):
                 | (
                     Q(following=status.user) & Q(following=status.reply_parent.user)
                 )  # if the user is following both authors
-            ).distinct()
+            )
 
         # only visible to the poster's followers and tagged users
         elif status.privacy == "followers":
             audience = audience.filter(
                 Q(following=status.user)  # if the user is following the author
             )
-        return audience.distinct()
+        return audience.distinct("id")
 
     @tracer.start_as_current_span("ActivityStream.get_audience")
     def get_audience(self, status):
@@ -156,7 +156,7 @@ class ActivityStream(RedisStore):
         status_author = models.User.objects.filter(
             is_active=True, local=True, id=status.user.id
         ).values_list("id", flat=True)
-        return list(set(list(audience) + list(status_author)))
+        return list(set(audience) | set(status_author))
 
     def get_stores_for_users(self, user_ids):
         """convert a list of user ids into redis store ids"""
@@ -183,15 +183,13 @@ class HomeStream(ActivityStream):
     def get_audience(self, status):
         trace.get_current_span().set_attribute("stream_id", self.key)
         audience = super()._get_audience(status)
-        if not audience:
-            return []
         # if the user is following the author
         audience = audience.filter(following=status.user).values_list("id", flat=True)
         # if the user is the post's author
         status_author = models.User.objects.filter(
             is_active=True, local=True, id=status.user.id
         ).values_list("id", flat=True)
-        return list(set(list(audience) + list(status_author)))
+        return list(set(audience) | set(status_author))
 
     def get_statuses_for_user(self, user):
         return models.Status.privacy_filter(
@@ -239,9 +237,7 @@ class BooksStream(ActivityStream):
         )
 
         audience = super()._get_audience(status)
-        if not audience:
-            return models.User.objects.none()
-        return audience.filter(shelfbook__book__parent_work=work).distinct()
+        return audience.filter(shelfbook__book__parent_work=work)
 
     def get_audience(self, status):
         # only show public statuses on the books feed,

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):

bookwyrm/book_search.py

@@ -43,6 +43,7 @@ def search(
     min_confidence: float = 0,
     filters: Optional[list[Any]] = None,
     return_first: bool = False,
+    books: Optional[QuerySet[models.Edition]] = None,
 ) -> Union[Optional[models.Edition], QuerySet[models.Edition]]:
     """search your local database"""
     filters = filters or []
@@ -54,13 +55,15 @@ def search(
     # first, try searching unique identifiers
     # unique identifiers never have spaces, title/author usually do
     if not " " in query:
-        results = search_identifiers(query, *filters, return_first=return_first)
+        results = search_identifiers(
+            query, *filters, return_first=return_first, books=books
+        )
 
     # if there were no identifier results...
     if not results:
         # then try searching title/author
         results = search_title_author(
-            query, min_confidence, *filters, return_first=return_first
+            query, min_confidence, *filters, return_first=return_first, books=books
         )
     return results
 
@@ -98,9 +101,17 @@ def format_search_result(search_result):
 
 
 def search_identifiers(
-    query, *filters, return_first=False
+    query,
+    *filters,
+    return_first=False,
+    books=None,
 ) -> Union[Optional[models.Edition], QuerySet[models.Edition]]:
-    """tries remote_id, isbn; defined as dedupe fields on the model"""
+    """search Editions by deduplication fields
+
+    Best for cases when we can assume someone is searching for an exact match on
+    commonly unique data identifiers like isbn or specific library ids.
+    """
+    books = books or models.Edition.objects
     if connectors.maybe_isbn(query):
         # Oh did you think the 'S' in ISBN stood for 'standard'?
         normalized_isbn = query.strip().upper().rjust(10, "0")
@@ -111,7 +122,7 @@ def search_identifiers(
         for f in models.Edition._meta.get_fields()
         if hasattr(f, "deduplication_field") and f.deduplication_field
     ]
-    results = models.Edition.objects.filter(
+    results = books.filter(
         *filters, reduce(operator.or_, (Q(**f) for f in or_filters))
     ).distinct()
 
@@ -121,12 +132,17 @@ def search_identifiers(
 
 
 def search_title_author(
-    query, min_confidence, *filters, return_first=False
+    query,
+    min_confidence,
+    *filters,
+    return_first=False,
+    books=None,
 ) -> QuerySet[models.Edition]:
     """searches for title and author"""
+    books = books or models.Edition.objects
     query = SearchQuery(query, config="simple") | SearchQuery(query, config="english")
     results = (
-        models.Edition.objects.filter(*filters, search_vector=query)
+        books.filter(*filters, search_vector=query)
         .annotate(rank=SearchRank(F("search_vector"), query))
         .filter(rank__gt=min_confidence)
         .order_by("-rank")
@@ -137,7 +153,7 @@ def search_title_author(
 
     # filter out multiple editions of the same work
     list_results = []
-    for work_id in set(editions_of_work[:30]):
+    for work_id in editions_of_work[:30]:
         result = (
             results.filter(parent_work=work_id)
             .order_by("-rank", "-edition_rank")

bookwyrm/connectors/abstract_connector.py

@@ -3,7 +3,9 @@ from __future__ import annotations
 from abc import ABC, abstractmethod
 from typing import Optional, TypedDict, Any, Callable, Union, Iterator
 from urllib.parse import quote_plus
-import imghdr
+
+# pylint: disable-next=deprecated-module
+import imghdr  # Deprecated in 3.11 for removal in 3.13; no good alternative yet
 import logging
 import re
 import asyncio

bookwyrm/connectors/connector_manager.py

@@ -118,9 +118,11 @@ def get_connectors() -> Iterator[abstract_connector.AbstractConnector]:
 def get_or_create_connector(remote_id: str) -> abstract_connector.AbstractConnector:
     """get the connector related to the object's server"""
     url = urlparse(remote_id)
-    identifier = url.netloc
+    identifier = url.hostname
     if not identifier:
-        raise ValueError("Invalid remote id")
+        raise ValueError(f"Invalid remote id: {remote_id}")
+
+    base_url = f"{url.scheme}://{url.netloc}"
 
     try:
         connector_info = models.Connector.objects.get(identifier=identifier)
@@ -128,10 +130,10 @@ def get_or_create_connector(remote_id: str) -> abstract_connector.AbstractConnec
         connector_info = models.Connector.objects.create(
             identifier=identifier,
             connector_file="bookwyrm_connector",
-            base_url=f"https://{identifier}",
-            books_url=f"https://{identifier}/book",
-            covers_url=f"https://{identifier}/images/covers",
-            search_url=f"https://{identifier}/search?q=",
+            base_url=base_url,
+            books_url=f"{base_url}/book",
+            covers_url=f"{base_url}/images/covers",
+            search_url=f"{base_url}/search?q=",
             priority=2,
         )
 
@@ -143,7 +145,9 @@ def load_more_data(connector_id: str, book_id: str) -> None:
     """background the work of getting all 10,000 editions of LoTR"""
     connector_info = models.Connector.objects.get(id=connector_id)
     connector = load_connector(connector_info)
-    book = models.Book.objects.select_subclasses().get(id=book_id)
+    book = models.Book.objects.select_subclasses().get(  # type: ignore[no-untyped-call]
+        id=book_id
+    )
     connector.expand_book_data(book)
 
 
@@ -154,7 +158,9 @@ def create_edition_task(
     """separate task for each of the 10,000 editions of LoTR"""
     connector_info = models.Connector.objects.get(id=connector_id)
     connector = load_connector(connector_info)
-    work = models.Work.objects.select_subclasses().get(id=work_id)
+    work = models.Work.objects.select_subclasses().get(  # type: ignore[no-untyped-call]
+        id=work_id
+    )
     connector.create_edition_from_data(work, data)
 
 
@@ -188,8 +194,11 @@ def raise_not_valid_url(url: str) -> None:
     if not parsed.scheme in ["http", "https"]:
         raise ConnectorException("Invalid scheme: ", url)
 
+    if not parsed.hostname:
+        raise ConnectorException("Hostname missing: ", url)
+
     try:
-        ipaddress.ip_address(parsed.netloc)
+        ipaddress.ip_address(parsed.hostname)
         raise ConnectorException("Provided url is an IP address: ", url)
     except ValueError:
         # it's not an IP address, which is good

bookwyrm/connectors/inventaire.py

@@ -229,7 +229,7 @@ class Connector(AbstractConnector):
             data = get_data(url)
         except ConnectorException:
             return ""
-        return data.get("extract", "")
+        return str(data.get("extract", ""))
 
     def get_remote_id_from_model(self, obj: models.BookDataModel) -> str:
         """use get_remote_id to figure out the link from a model obj"""

bookwyrm/emailing.py

@@ -4,7 +4,7 @@ from django.template.loader import get_template
 
 from bookwyrm import models, settings
 from bookwyrm.tasks import app, EMAIL
-from bookwyrm.settings import DOMAIN
+from bookwyrm.settings import DOMAIN, BASE_URL
 
 
 def email_data():
@@ -14,6 +14,7 @@ def email_data():
         "site_name": site.name,
         "logo": site.logo_small_url,
         "domain": DOMAIN,
+        "base_url": BASE_URL,
         "user": None,
     }
 

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"}),

bookwyrm/forms/books.py

@@ -1,8 +1,9 @@
 """ using django model forms """
 from django import forms
 
+from file_resubmit.widgets import ResubmitImageWidget
+
 from bookwyrm import models
-from bookwyrm.models.fields import ClearableFileInputWithWarning
 from .custom_form import CustomForm
 from .widgets import ArrayWidget, SelectDateWidget, Select
 
@@ -70,9 +71,7 @@ class EditionForm(CustomForm):
             "published_date": SelectDateWidget(
                 attrs={"aria-describedby": "desc_published_date"}
             ),
-            "cover": ClearableFileInputWithWarning(
-                attrs={"aria-describedby": "desc_cover"}
-            ),
+            "cover": ResubmitImageWidget(attrs={"aria-describedby": "desc_cover"}),
             "physical_format": Select(
                 attrs={"aria-describedby": "desc_physical_format"}
             ),

bookwyrm/forms/forms.py

@@ -25,6 +25,10 @@ class ImportForm(forms.Form):
     csv_file = forms.FileField()
 
 
+class ImportUserForm(forms.Form):
+    archive_file = forms.FileField()
+
+
 class ShelfForm(CustomForm):
     class Meta:
         model = models.Shelf

bookwyrm/forms/links.py

@@ -1,4 +1,5 @@
 """ using django model forms """
+
 from urllib.parse import urlparse
 
 from django.utils.translation import gettext_lazy as _
@@ -25,7 +26,7 @@ class FileLinkForm(CustomForm):
         url = cleaned_data.get("url")
         filetype = cleaned_data.get("filetype")
         book = cleaned_data.get("book")
-        domain = urlparse(url).netloc
+        domain = urlparse(url).hostname
         if models.LinkDomain.objects.filter(domain=domain).exists():
             status = models.LinkDomain.objects.get(domain=domain).status
             if status == "blocked":
@@ -37,10 +38,9 @@ class FileLinkForm(CustomForm):
                     ),
                 )
         if (
-            not self.instance
-            and models.FileLink.objects.filter(
-                url=url, book=book, filetype=filetype
-            ).exists()
+            models.FileLink.objects.filter(url=url, book=book, filetype=filetype)
+            .exclude(pk=self.instance)
+            .exists()
         ):
             # pylint: disable=line-too-long
             self.add_error(

bookwyrm/importers/__init__.py

@@ -1,7 +1,7 @@
 """ import classes """
 
 from .importer import Importer
-from .bookwyrm_import import BookwyrmBooksImporter
+from .bookwyrm_import import BookwyrmImporter
 from .calibre_import import CalibreImporter
 from .goodreads_import import GoodreadsImporter
 from .librarything_import import LibrarythingImporter

bookwyrm/importers/bookwyrm_import.py

@@ -1,14 +1,24 @@
-""" handle reading a csv from BookWyrm """
+"""Import data from Bookwyrm export files"""
+from django.http import QueryDict
 
-from typing import Any
-from . import Importer
+from bookwyrm.models import User
+from bookwyrm.models.bookwyrm_import_job import BookwyrmImportJob
 
 
-class BookwyrmBooksImporter(Importer):
-    """Goodreads is the default importer, we basically just use the same structure"""
+class BookwyrmImporter:
+    """Import a Bookwyrm User export file.
+    This is kind of a combination of an importer and a connector.
+    """
 
-    service = "BookWyrm"
+    # pylint: disable=no-self-use
+    def process_import(
+        self, user: User, archive_file: bytes, settings: QueryDict
+    ) -> BookwyrmImportJob:
+        """import user data from a Bookwyrm export file"""
 
-    def __init__(self, *args: Any, **kwargs: Any):
-        self.row_mappings_guesses.append(("shelf_name", ["shelf_name"]))
-        super().__init__(*args, **kwargs)
+        required = [k for k in settings if settings.get(k) == "on"]
+
+        job = BookwyrmImportJob.objects.create(
+            user=user, archive_file=archive_file, required=required
+        )
+        return job

bookwyrm/importers/calibre_import.py

@@ -14,15 +14,10 @@ class CalibreImporter(Importer):
     def __init__(self, *args: Any, **kwargs: Any):
         # Add timestamp to row_mappings_guesses for date_added to avoid
         # integrity error
-        row_mappings_guesses = []
-
-        for field, mapping in self.row_mappings_guesses:
-            if field in ("date_added",):
-                row_mappings_guesses.append((field, mapping + ["timestamp"]))
-            else:
-                row_mappings_guesses.append((field, mapping))
-
-        self.row_mappings_guesses = row_mappings_guesses
+        self.row_mappings_guesses = [
+            (field, mapping + (["timestamp"] if field == "date_added" else []))
+            for field, mapping in self.row_mappings_guesses
+        ]
         super().__init__(*args, **kwargs)
 
     def get_shelf(self, normalized_row: dict[str, Optional[str]]) -> Optional[str]:

bookwyrm/isbn/isbn.py

@@ -26,7 +26,7 @@ class IsbnHyphenator:
 
     def update_range_message(self) -> None:
         """Download the range message xml file and save it locally"""
-        response = requests.get(self.__range_message_url)
+        response = requests.get(self.__range_message_url, timeout=15)
         with open(self.__range_file_path, "w", encoding="utf-8") as file:
             file.write(response.text)
         self.__element_tree = None

bookwyrm/management/commands/deduplicate_book_data.py

@@ -1,13 +1,14 @@
 """ PROCEED WITH CAUTION: uses deduplication fields to permanently
 merge book data objects """
+
 from django.core.management.base import BaseCommand
 from django.db.models import Count
 from bookwyrm import models
-from bookwyrm.management.merge import merge_objects
 
 
-def dedupe_model(model):
+def dedupe_model(model, dry_run=False):
     """combine duplicate editions and update related models"""
+    print(f"deduplicating {model.__name__}:")
     fields = model._meta.get_fields()
     dedupe_fields = [
         f for f in fields if hasattr(f, "deduplication_field") and f.deduplication_field
@@ -16,30 +17,42 @@ def dedupe_model(model):
         dupes = (
             model.objects.values(field.name)
             .annotate(Count(field.name))
-            .filter(**{"%s__count__gt" % field.name: 1})
+            .filter(**{f"{field.name}__count__gt": 1})
+            .exclude(**{field.name: ""})
+            .exclude(**{f"{field.name}__isnull": True})
         )
 
         for dupe in dupes:
             value = dupe[field.name]
-            if not value or value == "":
-                continue
             print("----------")
-            print(dupe)
             objs = model.objects.filter(**{field.name: value}).order_by("id")
             canonical = objs.first()
-            print("keeping", canonical.remote_id)
+            action = "would merge" if dry_run else "merging"
+            print(
+                f"{action} into {model.__name__} {canonical.remote_id} based on {field.name} {value}:"
+            )
             for obj in objs[1:]:
-                print(obj.remote_id)
-                merge_objects(canonical, obj)
+                print(f"- {obj.remote_id}")
+                absorbed_fields = obj.merge_into(canonical, dry_run=dry_run)
+                print(f"  absorbed fields: {absorbed_fields}")
 
 
 class Command(BaseCommand):
     """deduplicate allllll the book data models"""
 
     help = "merges duplicate book data"
+
+    def add_arguments(self, parser):
+        """add the arguments for this command"""
+        parser.add_argument(
+            "--dry_run",
+            action="store_true",
+            help="don't actually merge, only print what would happen",
+        )
+
     # pylint: disable=no-self-use,unused-argument
     def handle(self, *args, **options):
         """run deduplications"""
-        dedupe_model(models.Edition)
-        dedupe_model(models.Work)
-        dedupe_model(models.Author)
+        dedupe_model(models.Edition, dry_run=options["dry_run"])
+        dedupe_model(models.Work, dry_run=options["dry_run"])
+        dedupe_model(models.Author, dry_run=options["dry_run"])

bookwyrm/management/commands/erase_deleted_user_data.py

@@ -0,0 +1,43 @@
+""" Erase any data stored about deleted users """
+import sys
+from django.core.management.base import BaseCommand, CommandError
+from bookwyrm import models
+from bookwyrm.models.user import erase_user_data
+
+# pylint: disable=missing-function-docstring
+class Command(BaseCommand):
+    """command-line options"""
+
+    help = "Remove Two Factor Authorisation from user"
+
+    def add_arguments(self, parser):  # pylint: disable=no-self-use
+        parser.add_argument(
+            "--dryrun",
+            action="store_true",
+            help="Preview users to be cleared without altering the database",
+        )
+
+    def handle(self, *args, **options):  # pylint: disable=unused-argument
+
+        # Check for anything fishy
+        bad_state = models.User.objects.filter(is_deleted=True, is_active=True)
+        if bad_state.exists():
+            raise CommandError(
+                f"{bad_state.count()} user(s) marked as both active and deleted"
+            )
+
+        deleted_users = models.User.objects.filter(is_deleted=True)
+        self.stdout.write(f"Found {deleted_users.count()} deleted users")
+        if options["dryrun"]:
+            self.stdout.write("\n".join(u.username for u in deleted_users[:5]))
+            if deleted_users.count() > 5:
+                self.stdout.write("... and more")
+            sys.exit()
+
+        self.stdout.write("Erasing user data:")
+        for user_id in deleted_users.values_list("id", flat=True):
+            erase_user_data.delay(user_id)
+            self.stdout.write(".", ending="")
+
+        self.stdout.write("")
+        self.stdout.write("Tasks created successfully")

bookwyrm/management/commands/instance_version.py

@@ -1,54 +0,0 @@
-""" Get your admin code to allow install """
-from django.core.management.base import BaseCommand
-
-from bookwyrm import models
-from bookwyrm.settings import VERSION
-
-
-# pylint: disable=no-self-use
-class Command(BaseCommand):
-    """command-line options"""
-
-    help = "What version is this?"
-
-    def add_arguments(self, parser):
-        """specify which function to run"""
-        parser.add_argument(
-            "--current",
-            action="store_true",
-            help="Version stored in database",
-        )
-        parser.add_argument(
-            "--target",
-            action="store_true",
-            help="Version stored in settings",
-        )
-        parser.add_argument(
-            "--update",
-            action="store_true",
-            help="Update database version",
-        )
-
-    # pylint: disable=unused-argument
-    def handle(self, *args, **options):
-        """execute init"""
-        site = models.SiteSettings.objects.get()
-        current = site.version or "0.0.1"
-        target = VERSION
-        if options.get("current"):
-            print(current)
-            return
-
-        if options.get("target"):
-            print(target)
-            return
-
-        if options.get("update"):
-            site.version = target
-            site.save()
-            return
-
-        if current != target:
-            print(f"{current}/{target}")
-        else:
-            print(current)

bookwyrm/management/merge.py

@@ -1,50 +0,0 @@
-from django.db.models import ManyToManyField
-
-
-def update_related(canonical, obj):
-    """update all the models with fk to the object being removed"""
-    # move related models to canonical
-    related_models = [
-        (r.remote_field.name, r.related_model) for r in canonical._meta.related_objects
-    ]
-    for (related_field, related_model) in related_models:
-        # Skip the ManyToMany fields that aren’t auto-created. These
-        # should have a corresponding OneToMany field in the model for
-        # the linking table anyway. If we update it through that model
-        # instead then we won’t lose the extra fields in the linking
-        # table.
-        related_field_obj = related_model._meta.get_field(related_field)
-        if isinstance(related_field_obj, ManyToManyField):
-            through = related_field_obj.remote_field.through
-            if not through._meta.auto_created:
-                continue
-        related_objs = related_model.objects.filter(**{related_field: obj})
-        for related_obj in related_objs:
-            print("replacing in", related_model.__name__, related_field, related_obj.id)
-            try:
-                setattr(related_obj, related_field, canonical)
-                related_obj.save()
-            except TypeError:
-                getattr(related_obj, related_field).add(canonical)
-                getattr(related_obj, related_field).remove(obj)
-
-
-def copy_data(canonical, obj):
-    """try to get the most data possible"""
-    for data_field in obj._meta.get_fields():
-        if not hasattr(data_field, "activitypub_field"):
-            continue
-        data_value = getattr(obj, data_field.name)
-        if not data_value:
-            continue
-        if not getattr(canonical, data_field.name):
-            print("setting data field", data_field.name, data_value)
-            setattr(canonical, data_field.name, data_value)
-    canonical.save()
-
-
-def merge_objects(canonical, obj):
-    copy_data(canonical, obj)
-    update_related(canonical, obj)
-    # remove the outdated entry
-    obj.delete()

bookwyrm/management/merge_command.py

@@ -1,4 +1,3 @@
-from bookwyrm.management.merge import merge_objects
 from django.core.management.base import BaseCommand
 
 
@@ -9,6 +8,11 @@ class MergeCommand(BaseCommand):
         """add the arguments for this command"""
         parser.add_argument("--canonical", type=int, required=True)
         parser.add_argument("--other", type=int, required=True)
+        parser.add_argument(
+            "--dry_run",
+            action="store_true",
+            help="don't actually merge, only print what would happen",
+        )
 
     # pylint: disable=no-self-use,unused-argument
     def handle(self, *args, **options):
@@ -26,4 +30,8 @@ class MergeCommand(BaseCommand):
             print("other book doesn’t exist!")
             return
 
-        merge_objects(canonical, other)
+        absorbed_fields = other.merge_into(canonical, dry_run=options["dry_run"])
+
+        action = "would be" if options["dry_run"] else "has been"
+        print(f"{other.remote_id} {action} merged into {canonical.remote_id}")
+        print(f"absorbed fields: {absorbed_fields}")

bookwyrm/middleware/__init__.py

@@ -1,3 +1,4 @@
 """ look at all this nice middleware! """
 from .timezone_middleware import TimezoneMiddleware
 from .ip_middleware import IPBlocklistMiddleware
+from .file_too_big import FileTooBig

bookwyrm/middleware/file_too_big.py

@@ -0,0 +1,30 @@
+"""Middleware to display a custom 413 error page"""
+
+from django.http import HttpResponse
+from django.shortcuts import render
+from django.core.exceptions import RequestDataTooBig
+
+
+class FileTooBig:
+    """Middleware to display a custom page when a
+    RequestDataTooBig exception is thrown"""
+
+    def __init__(self, get_response):
+        """boilerplate __init__ from Django docs"""
+
+        self.get_response = get_response
+
+    def __call__(self, request):
+        """If RequestDataTooBig is thrown, render the 413 error page"""
+
+        try:
+            body = request.body  # pylint: disable=unused-variable
+
+        except RequestDataTooBig:
+
+            rendered = render(request, "413.html")
+            response = HttpResponse(rendered)
+            return response
+
+        response = self.get_response(request)
+        return response

bookwyrm/middleware/timezone_middleware.py

@@ -1,5 +1,5 @@
 """ Makes the app aware of the users timezone """
-import pytz
+import zoneinfo
 
 from django.utils import timezone
 
@@ -12,9 +12,7 @@ class TimezoneMiddleware:
 
     def __call__(self, request):
         if request.user.is_authenticated:
-            timezone.activate(pytz.timezone(request.user.preferred_timezone))
+            timezone.activate(zoneinfo.ZoneInfo(request.user.preferred_timezone))
         else:
-            timezone.activate(pytz.utc)
-        response = self.get_response(request)
-        timezone.deactivate()
-        return response
+            timezone.deactivate()
+        return self.get_response(request)

bookwyrm/migrations/0171_alter_user_preferred_timezone.py

@@ -10,6 +10,7 @@ class Migration(migrations.Migration):
     ]
 
     operations = [
+        # The new timezones are "Factory" and "localtime"
         migrations.AlterField(
             model_name="user",
             name="preferred_timezone",

bookwyrm/migrations/0184_auto_20231106_0421.py

@@ -22,17 +22,6 @@ def update_deleted_users(apps, schema_editor):
     ).update(is_deleted=True)
 
 
-def erase_deleted_user_data(apps, schema_editor):
-    """Retroactively clear user data"""
-    for user in User.objects.filter(is_deleted=True):
-        user.erase_user_data()
-        user.save(
-            broadcast=False,
-            update_fields=["email", "avatar", "preview_image", "summary", "name"],
-        )
-        user.erase_user_statuses(broadcast=False)
-
-
 class Migration(migrations.Migration):
 
     dependencies = [
@@ -43,7 +32,4 @@ class Migration(migrations.Migration):
         migrations.RunPython(
             update_deleted_users, reverse_code=migrations.RunPython.noop
         ),
-        migrations.RunPython(
-            erase_deleted_user_data, reverse_code=migrations.RunPython.noop
-        ),
     ]

bookwyrm/migrations/0186_auto_20231116_0048.py

@@ -0,0 +1,212 @@
+# Generated by Django 3.2.20 on 2023-11-16 00:48
+
+from django.conf import settings
+import django.contrib.postgres.fields
+from django.db import migrations, models
+import django.db.models.deletion
+import django.utils.timezone
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0185_alter_notification_notification_type"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="ParentJob",
+            fields=[
+                (
+                    "id",
+                    models.AutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                ("task_id", models.UUIDField(blank=True, null=True, unique=True)),
+                (
+                    "created_date",
+                    models.DateTimeField(default=django.utils.timezone.now),
+                ),
+                (
+                    "updated_date",
+                    models.DateTimeField(default=django.utils.timezone.now),
+                ),
+                ("complete", models.BooleanField(default=False)),
+                (
+                    "status",
+                    models.CharField(
+                        choices=[
+                            ("pending", "Pending"),
+                            ("active", "Active"),
+                            ("complete", "Complete"),
+                            ("stopped", "Stopped"),
+                            ("failed", "Failed"),
+                        ],
+                        default="pending",
+                        max_length=50,
+                        null=True,
+                    ),
+                ),
+                (
+                    "user",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE,
+                        to=settings.AUTH_USER_MODEL,
+                    ),
+                ),
+            ],
+            options={
+                "abstract": False,
+            },
+        ),
+        migrations.AddField(
+            model_name="sitesettings",
+            name="user_import_time_limit",
+            field=models.IntegerField(default=48),
+        ),
+        migrations.AlterField(
+            model_name="notification",
+            name="notification_type",
+            field=models.CharField(
+                choices=[
+                    ("FAVORITE", "Favorite"),
+                    ("BOOST", "Boost"),
+                    ("REPLY", "Reply"),
+                    ("MENTION", "Mention"),
+                    ("TAG", "Tag"),
+                    ("FOLLOW", "Follow"),
+                    ("FOLLOW_REQUEST", "Follow Request"),
+                    ("IMPORT", "Import"),
+                    ("USER_IMPORT", "User Import"),
+                    ("USER_EXPORT", "User Export"),
+                    ("ADD", "Add"),
+                    ("REPORT", "Report"),
+                    ("LINK_DOMAIN", "Link Domain"),
+                    ("INVITE", "Invite"),
+                    ("ACCEPT", "Accept"),
+                    ("JOIN", "Join"),
+                    ("LEAVE", "Leave"),
+                    ("REMOVE", "Remove"),
+                    ("GROUP_PRIVACY", "Group Privacy"),
+                    ("GROUP_NAME", "Group Name"),
+                    ("GROUP_DESCRIPTION", "Group Description"),
+                    ("MOVE", "Move"),
+                ],
+                max_length=255,
+            ),
+        ),
+        migrations.CreateModel(
+            name="BookwyrmExportJob",
+            fields=[
+                (
+                    "parentjob_ptr",
+                    models.OneToOneField(
+                        auto_created=True,
+                        on_delete=django.db.models.deletion.CASCADE,
+                        parent_link=True,
+                        primary_key=True,
+                        serialize=False,
+                        to="bookwyrm.parentjob",
+                    ),
+                ),
+                ("export_data", models.FileField(null=True, upload_to="")),
+            ],
+            options={
+                "abstract": False,
+            },
+            bases=("bookwyrm.parentjob",),
+        ),
+        migrations.CreateModel(
+            name="BookwyrmImportJob",
+            fields=[
+                (
+                    "parentjob_ptr",
+                    models.OneToOneField(
+                        auto_created=True,
+                        on_delete=django.db.models.deletion.CASCADE,
+                        parent_link=True,
+                        primary_key=True,
+                        serialize=False,
+                        to="bookwyrm.parentjob",
+                    ),
+                ),
+                ("archive_file", models.FileField(blank=True, null=True, upload_to="")),
+                ("import_data", models.JSONField(null=True)),
+                (
+                    "required",
+                    django.contrib.postgres.fields.ArrayField(
+                        base_field=models.CharField(blank=True, max_length=50),
+                        blank=True,
+                        size=None,
+                    ),
+                ),
+            ],
+            options={
+                "abstract": False,
+            },
+            bases=("bookwyrm.parentjob",),
+        ),
+        migrations.CreateModel(
+            name="ChildJob",
+            fields=[
+                (
+                    "id",
+                    models.AutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                ("task_id", models.UUIDField(blank=True, null=True, unique=True)),
+                (
+                    "created_date",
+                    models.DateTimeField(default=django.utils.timezone.now),
+                ),
+                (
+                    "updated_date",
+                    models.DateTimeField(default=django.utils.timezone.now),
+                ),
+                ("complete", models.BooleanField(default=False)),
+                (
+                    "status",
+                    models.CharField(
+                        choices=[
+                            ("pending", "Pending"),
+                            ("active", "Active"),
+                            ("complete", "Complete"),
+                            ("stopped", "Stopped"),
+                            ("failed", "Failed"),
+                        ],
+                        default="pending",
+                        max_length=50,
+                        null=True,
+                    ),
+                ),
+                (
+                    "parent_job",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE,
+                        related_name="child_jobs",
+                        to="bookwyrm.parentjob",
+                    ),
+                ),
+            ],
+            options={
+                "abstract": False,
+            },
+        ),
+        migrations.AddField(
+            model_name="notification",
+            name="related_user_export",
+            field=models.ForeignKey(
+                null=True,
+                on_delete=django.db.models.deletion.CASCADE,
+                to="bookwyrm.bookwyrmexportjob",
+            ),
+        ),
+    ]

bookwyrm/migrations/0189_alter_user_preferred_language.py

@@ -0,0 +1,45 @@
+# Generated by Django 3.2.23 on 2023-12-12 23:42
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0188_theme_loads"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="user",
+            name="preferred_language",
+            field=models.CharField(
+                blank=True,
+                choices=[
+                    ("en-us", "English"),
+                    ("ca-es", "Català (Catalan)"),
+                    ("de-de", "Deutsch (German)"),
+                    ("eo-uy", "Esperanto (Esperanto)"),
+                    ("es-es", "Español (Spanish)"),
+                    ("eu-es", "Euskara (Basque)"),
+                    ("gl-es", "Galego (Galician)"),
+                    ("it-it", "Italiano (Italian)"),
+                    ("fi-fi", "Suomi (Finnish)"),
+                    ("fr-fr", "Français (French)"),
+                    ("lt-lt", "Lietuvių (Lithuanian)"),
+                    ("nl-nl", "Nederlands (Dutch)"),
+                    ("no-no", "Norsk (Norwegian)"),
+                    ("pl-pl", "Polski (Polish)"),
+                    ("pt-br", "Português do Brasil (Brazilian Portuguese)"),
+                    ("pt-pt", "Português Europeu (European Portuguese)"),
+                    ("ro-ro", "Română (Romanian)"),
+                    ("sv-se", "Svenska (Swedish)"),
+                    ("uk-ua", "Українська (Ukrainian)"),
+                    ("zh-hans", "简体中文 (Simplified Chinese)"),
+                    ("zh-hant", "繁體中文 (Traditional Chinese)"),
+                ],
+                max_length=255,
+                null=True,
+            ),
+        ),
+    ]

bookwyrm/migrations/0189_merge_0186_auto_20231116_0048_0188_theme_loads.py

@@ -0,0 +1,13 @@
+# Generated by Django 3.2.23 on 2023-11-22 10:16
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0186_auto_20231116_0048"),
+        ("bookwyrm", "0188_theme_loads"),
+    ]
+
+    operations = []

bookwyrm/migrations/0190_alter_notification_notification_type.py

@@ -0,0 +1,45 @@
+# Generated by Django 3.2.23 on 2023-11-23 19:49
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0189_merge_0186_auto_20231116_0048_0188_theme_loads"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="notification",
+            name="notification_type",
+            field=models.CharField(
+                choices=[
+                    ("FAVORITE", "Favorite"),
+                    ("BOOST", "Boost"),
+                    ("REPLY", "Reply"),
+                    ("MENTION", "Mention"),
+                    ("TAG", "Tag"),
+                    ("FOLLOW", "Follow"),
+                    ("FOLLOW_REQUEST", "Follow Request"),
+                    ("IMPORT", "Import"),
+                    ("USER_IMPORT", "User Import"),
+                    ("USER_EXPORT", "User Export"),
+                    ("ADD", "Add"),
+                    ("REPORT", "Report"),
+                    ("LINK_DOMAIN", "Link Domain"),
+                    ("INVITE_REQUEST", "Invite Request"),
+                    ("INVITE", "Invite"),
+                    ("ACCEPT", "Accept"),
+                    ("JOIN", "Join"),
+                    ("LEAVE", "Leave"),
+                    ("REMOVE", "Remove"),
+                    ("GROUP_PRIVACY", "Group Privacy"),
+                    ("GROUP_NAME", "Group Name"),
+                    ("GROUP_DESCRIPTION", "Group Description"),
+                    ("MOVE", "Move"),
+                ],
+                max_length=255,
+            ),
+        ),
+    ]

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",
+        ),
+    ]

bookwyrm/migrations/0191_merge_20240102_0326.py

@@ -0,0 +1,13 @@
+# Generated by Django 3.2.23 on 2024-01-02 03:26
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0189_alter_user_preferred_language"),
+        ("bookwyrm", "0190_alter_notification_notification_type"),
+    ]
+
+    operations = []

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,
+        ),
+    ]

bookwyrm/migrations/0192_make_page_positions_text.py

@@ -0,0 +1,23 @@
+# Generated by Django 3.2.23 on 2024-01-04 23:56
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0191_merge_20240102_0326"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="quotation",
+            name="endposition",
+            field=models.TextField(blank=True, null=True),
+        ),
+        migrations.AlterField(
+            model_name="quotation",
+            name="position",
+            field=models.TextField(blank=True, null=True),
+        ),
+    ]

bookwyrm/migrations/0192_rename_version_sitesettings_available_version.py

@@ -0,0 +1,18 @@
+# Generated by Django 3.2.23 on 2024-01-02 19:36
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0191_merge_20240102_0326"),
+    ]
+
+    operations = [
+        migrations.RenameField(
+            model_name="sitesettings",
+            old_name="version",
+            new_name="available_version",
+        ),
+    ]

bookwyrm/migrations/0192_sitesettings_user_exports_enabled.py

@@ -0,0 +1,18 @@
+# Generated by Django 3.2.23 on 2024-01-16 10:28
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0191_merge_20240102_0326"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="sitesettings",
+            name="user_exports_enabled",
+            field=models.BooleanField(default=False),
+        ),
+    ]

bookwyrm/migrations/0193_auto_20240128_0249.py

@@ -0,0 +1,92 @@
+# Generated by Django 3.2.23 on 2024-01-28 02:49
+
+import django.core.serializers.json
+from django.db import migrations, models
+import django.db.models.deletion
+from django.core.files.storage import storages
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0192_sitesettings_user_exports_enabled"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="bookwyrmexportjob",
+            name="export_json",
+            field=models.JSONField(
+                encoder=django.core.serializers.json.DjangoJSONEncoder, null=True
+            ),
+        ),
+        migrations.AddField(
+            model_name="bookwyrmexportjob",
+            name="json_completed",
+            field=models.BooleanField(default=False),
+        ),
+        migrations.AlterField(
+            model_name="bookwyrmexportjob",
+            name="export_data",
+            field=models.FileField(
+                null=True,
+                storage=storages["exports"],
+                upload_to="",
+            ),
+        ),
+        migrations.CreateModel(
+            name="AddFileToTar",
+            fields=[
+                (
+                    "childjob_ptr",
+                    models.OneToOneField(
+                        auto_created=True,
+                        on_delete=django.db.models.deletion.CASCADE,
+                        parent_link=True,
+                        primary_key=True,
+                        serialize=False,
+                        to="bookwyrm.childjob",
+                    ),
+                ),
+                (
+                    "parent_export_job",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE,
+                        related_name="child_edition_export_jobs",
+                        to="bookwyrm.bookwyrmexportjob",
+                    ),
+                ),
+            ],
+            options={
+                "abstract": False,
+            },
+            bases=("bookwyrm.childjob",),
+        ),
+        migrations.CreateModel(
+            name="AddBookToUserExportJob",
+            fields=[
+                (
+                    "childjob_ptr",
+                    models.OneToOneField(
+                        auto_created=True,
+                        on_delete=django.db.models.deletion.CASCADE,
+                        parent_link=True,
+                        primary_key=True,
+                        serialize=False,
+                        to="bookwyrm.childjob",
+                    ),
+                ),
+                (
+                    "edition",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE,
+                        to="bookwyrm.edition",
+                    ),
+                ),
+            ],
+            options={
+                "abstract": False,
+            },
+            bases=("bookwyrm.childjob",),
+        ),
+    ]

bookwyrm/migrations/0193_merge_20240203_1539.py

@@ -0,0 +1,13 @@
+# Generated by Django 3.2.23 on 2024-02-03 15:39
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0192_make_page_positions_text"),
+        ("bookwyrm", "0192_sitesettings_user_exports_enabled"),
+    ]
+
+    operations = []

bookwyrm/migrations/0194_merge_20240203_1619.py

@@ -0,0 +1,13 @@
+# Generated by Django 3.2.23 on 2024-02-03 16:19
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0192_rename_version_sitesettings_available_version"),
+        ("bookwyrm", "0193_merge_20240203_1539"),
+    ]
+
+    operations = []

bookwyrm/migrations/0195_alter_user_preferred_language.py

@@ -0,0 +1,46 @@
+# Generated by Django 3.2.23 on 2024-02-21 00:45
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0194_merge_20240203_1619"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="user",
+            name="preferred_language",
+            field=models.CharField(
+                blank=True,
+                choices=[
+                    ("en-us", "English"),
+                    ("ca-es", "Català (Catalan)"),
+                    ("de-de", "Deutsch (German)"),
+                    ("eo-uy", "Esperanto (Esperanto)"),
+                    ("es-es", "Español (Spanish)"),
+                    ("eu-es", "Euskara (Basque)"),
+                    ("gl-es", "Galego (Galician)"),
+                    ("it-it", "Italiano (Italian)"),
+                    ("ko-kr", "한국어 (Korean)"),
+                    ("fi-fi", "Suomi (Finnish)"),
+                    ("fr-fr", "Français (French)"),
+                    ("lt-lt", "Lietuvių (Lithuanian)"),
+                    ("nl-nl", "Nederlands (Dutch)"),
+                    ("no-no", "Norsk (Norwegian)"),
+                    ("pl-pl", "Polski (Polish)"),
+                    ("pt-br", "Português do Brasil (Brazilian Portuguese)"),
+                    ("pt-pt", "Português Europeu (European Portuguese)"),
+                    ("ro-ro", "Română (Romanian)"),
+                    ("sv-se", "Svenska (Swedish)"),
+                    ("uk-ua", "Українська (Ukrainian)"),
+                    ("zh-hans", "简体中文 (Simplified Chinese)"),
+                    ("zh-hant", "繁體中文 (Traditional Chinese)"),
+                ],
+                max_length=255,
+                null=True,
+            ),
+        ),
+    ]

bookwyrm/migrations/0196_merge_20240318_1737.py

@@ -0,0 +1,13 @@
+# Generated by Django 3.2.23 on 2024-03-18 17:37
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0193_auto_20240128_0249"),
+        ("bookwyrm", "0195_alter_user_preferred_language"),
+    ]
+
+    operations = []

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 = []

bookwyrm/migrations/0197_author_search_vector.py

@@ -0,0 +1,41 @@
+# Generated by Django 3.2.25 on 2024-03-20 15:15
+
+import django.contrib.postgres.indexes
+from django.db import migrations
+import pgtrigger.compiler
+import pgtrigger.migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0196_merge_pr3134_into_main"),
+    ]
+
+    operations = [
+        migrations.AddIndex(
+            model_name="author",
+            index=django.contrib.postgres.indexes.GinIndex(
+                fields=["search_vector"], name="bookwyrm_au_search__b050a8_gin"
+            ),
+        ),
+        pgtrigger.migrations.AddTrigger(
+            model_name="author",
+            trigger=pgtrigger.compiler.Trigger(
+                name="update_search_vector_on_author_edit",
+                sql=pgtrigger.compiler.UpsertTriggerSql(
+                    func="new.search_vector := setweight(to_tsvector('simple', new.name), 'A') || setweight(to_tsvector('simple', coalesce(array_to_string(new.aliases, ' '), '')), 'B');RETURN NEW;",
+                    hash="b97919016236d74d0ade51a0769a173ea269da64",
+                    operation='INSERT OR UPDATE OF "name", "aliases", "search_vector"',
+                    pgid="pgtrigger_update_search_vector_on_author_edit_c61cb",
+                    table="bookwyrm_author",
+                    when="BEFORE",
+                ),
+            ),
+        ),
+        migrations.RunSQL(
+            # Calculate search vector for all Authors.
+            sql="UPDATE bookwyrm_author SET search_vector = NULL;",
+            reverse_sql="UPDATE bookwyrm_author SET search_vector = NULL;",
+        ),
+    ]

bookwyrm/migrations/0197_merge_20240324_0235.py

@@ -0,0 +1,13 @@
+# Generated by Django 3.2.25 on 2024-03-24 02:35
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0196_merge_20240318_1737"),
+        ("bookwyrm", "0196_merge_pr3134_into_main"),
+    ]
+
+    operations = []

bookwyrm/migrations/0197_mergedauthor_mergedbook.py

@@ -0,0 +1,48 @@
+# Generated by Django 3.2.24 on 2024-02-28 21:30
+
+from django.db import migrations, models
+import django.db.models.deletion
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0196_merge_pr3134_into_main"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="MergedBook",
+            fields=[
+                ("deleted_id", models.IntegerField(primary_key=True, serialize=False)),
+                (
+                    "merged_into",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.PROTECT,
+                        related_name="absorbed",
+                        to="bookwyrm.book",
+                    ),
+                ),
+            ],
+            options={
+                "abstract": False,
+            },
+        ),
+        migrations.CreateModel(
+            name="MergedAuthor",
+            fields=[
+                ("deleted_id", models.IntegerField(primary_key=True, serialize=False)),
+                (
+                    "merged_into",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.PROTECT,
+                        related_name="absorbed",
+                        to="bookwyrm.author",
+                    ),
+                ),
+            ],
+            options={
+                "abstract": False,
+            },
+        ),
+    ]

bookwyrm/migrations/0198_alter_bookwyrmexportjob_export_data.py

@@ -0,0 +1,23 @@
+# Generated by Django 3.2.25 on 2024-03-26 11:37
+
+import bookwyrm.models.bookwyrm_export_job
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0197_merge_20240324_0235"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="bookwyrmexportjob",
+            name="export_data",
+            field=models.FileField(
+                null=True,
+                storage=bookwyrm.models.bookwyrm_export_job.select_exports_storage,
+                upload_to="",
+            ),
+        ),
+    ]

bookwyrm/migrations/0198_book_search_vector_author_aliases.py

@@ -0,0 +1,57 @@
+# Generated by Django 3.2.25 on 2024-03-20 15:52
+
+from django.db import migrations
+import pgtrigger.compiler
+import pgtrigger.migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0197_author_search_vector"),
+    ]
+
+    operations = [
+        pgtrigger.migrations.RemoveTrigger(
+            model_name="author",
+            name="reset_search_vector_on_author_edit",
+        ),
+        pgtrigger.migrations.RemoveTrigger(
+            model_name="book",
+            name="update_search_vector_on_book_edit",
+        ),
+        pgtrigger.migrations.AddTrigger(
+            model_name="author",
+            trigger=pgtrigger.compiler.Trigger(
+                name="reset_book_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="68422c0f29879c5802b82159dde45297eff53e73",
+                    operation='UPDATE OF "name", "aliases"',
+                    pgid="pgtrigger_reset_book_search_vector_on_author_edit_a50c7",
+                    table="bookwyrm_author",
+                    when="AFTER",
+                ),
+            ),
+        ),
+        pgtrigger.migrations.AddTrigger(
+            model_name="book",
+            trigger=pgtrigger.compiler.Trigger(
+                name="update_search_vector_on_book_edit",
+                sql=pgtrigger.compiler.UpsertTriggerSql(
+                    func="WITH author_names AS (SELECT array_to_string(bookwyrm_author.name || bookwyrm_author.aliases, ' ') AS name_and_aliases 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 ) SELECT 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(name_and_aliases), ' '), '')), 'C') FROM author_names) || setweight(to_tsvector('english', coalesce(new.series, '')), 'D') INTO new.search_vector;RETURN NEW;",
+                    hash="9324f5ca76a6f5e63931881d62d11da11f595b2c",
+                    operation='INSERT OR UPDATE OF "title", "subtitle", "series", "search_vector"',
+                    pgid="pgtrigger_update_search_vector_on_book_edit_bec58",
+                    table="bookwyrm_book",
+                    when="BEFORE",
+                ),
+            ),
+        ),
+        migrations.RunSQL(
+            # Recalculate search vector for all Books because it now includes
+            # Author aliases.
+            sql="UPDATE bookwyrm_book SET search_vector = NULL;",
+            reverse_sql="UPDATE bookwyrm_book SET search_vector = NULL;",
+        ),
+    ]

bookwyrm/migrations/0199_alter_userblocks_user_object_and_more.py

@@ -0,0 +1,70 @@
+# Generated by Django 4.2.11 on 2024-03-29 19:25
+
+import bookwyrm.models.fields
+from django.conf import settings
+from django.db import migrations
+import django.db.models.deletion
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0198_book_search_vector_author_aliases"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="userblocks",
+            name="user_object",
+            field=bookwyrm.models.fields.ForeignKey(
+                on_delete=django.db.models.deletion.PROTECT,
+                related_name="%(class)s_user_object",
+                to=settings.AUTH_USER_MODEL,
+            ),
+        ),
+        migrations.AlterField(
+            model_name="userblocks",
+            name="user_subject",
+            field=bookwyrm.models.fields.ForeignKey(
+                on_delete=django.db.models.deletion.PROTECT,
+                related_name="%(class)s_user_subject",
+                to=settings.AUTH_USER_MODEL,
+            ),
+        ),
+        migrations.AlterField(
+            model_name="userfollowrequest",
+            name="user_object",
+            field=bookwyrm.models.fields.ForeignKey(
+                on_delete=django.db.models.deletion.PROTECT,
+                related_name="%(class)s_user_object",
+                to=settings.AUTH_USER_MODEL,
+            ),
+        ),
+        migrations.AlterField(
+            model_name="userfollowrequest",
+            name="user_subject",
+            field=bookwyrm.models.fields.ForeignKey(
+                on_delete=django.db.models.deletion.PROTECT,
+                related_name="%(class)s_user_subject",
+                to=settings.AUTH_USER_MODEL,
+            ),
+        ),
+        migrations.AlterField(
+            model_name="userfollows",
+            name="user_object",
+            field=bookwyrm.models.fields.ForeignKey(
+                on_delete=django.db.models.deletion.PROTECT,
+                related_name="%(class)s_user_object",
+                to=settings.AUTH_USER_MODEL,
+            ),
+        ),
+        migrations.AlterField(
+            model_name="userfollows",
+            name="user_subject",
+            field=bookwyrm.models.fields.ForeignKey(
+                on_delete=django.db.models.deletion.PROTECT,
+                related_name="%(class)s_user_subject",
+                to=settings.AUTH_USER_MODEL,
+            ),
+        ),
+    ]

bookwyrm/migrations/0199_merge_20240326_1217.py

@@ -0,0 +1,13 @@
+# Generated by Django 3.2.25 on 2024-03-26 12:17
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0198_alter_bookwyrmexportjob_export_data"),
+        ("bookwyrm", "0198_book_search_vector_author_aliases"),
+    ]
+
+    operations = []

bookwyrm/migrations/0199_status_bookwyrm_st_remote__06aeba_idx.py

@@ -0,0 +1,19 @@
+# Generated by Django 3.2.25 on 2024-04-02 19:53
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0198_book_search_vector_author_aliases"),
+    ]
+
+    operations = [
+        migrations.AddIndex(
+            model_name="status",
+            index=models.Index(
+                fields=["remote_id"], name="bookwyrm_st_remote__06aeba_idx"
+            ),
+        ),
+    ]

bookwyrm/migrations/0200_alter_user_preferred_timezone.py

@@ -0,0 +1,633 @@
+# Generated by Django 4.2.11 on 2024-04-01 20:19
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0199_alter_userblocks_user_object_and_more"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="user",
+            name="preferred_timezone",
+            field=models.CharField(
+                choices=[
+                    ("Africa/Abidjan", "Africa/Abidjan"),
+                    ("Africa/Accra", "Africa/Accra"),
+                    ("Africa/Addis_Ababa", "Africa/Addis_Ababa"),
+                    ("Africa/Algiers", "Africa/Algiers"),
+                    ("Africa/Asmara", "Africa/Asmara"),
+                    ("Africa/Asmera", "Africa/Asmera"),
+                    ("Africa/Bamako", "Africa/Bamako"),
+                    ("Africa/Bangui", "Africa/Bangui"),
+                    ("Africa/Banjul", "Africa/Banjul"),
+                    ("Africa/Bissau", "Africa/Bissau"),
+                    ("Africa/Blantyre", "Africa/Blantyre"),
+                    ("Africa/Brazzaville", "Africa/Brazzaville"),
+                    ("Africa/Bujumbura", "Africa/Bujumbura"),
+                    ("Africa/Cairo", "Africa/Cairo"),
+                    ("Africa/Casablanca", "Africa/Casablanca"),
+                    ("Africa/Ceuta", "Africa/Ceuta"),
+                    ("Africa/Conakry", "Africa/Conakry"),
+                    ("Africa/Dakar", "Africa/Dakar"),
+                    ("Africa/Dar_es_Salaam", "Africa/Dar_es_Salaam"),
+                    ("Africa/Djibouti", "Africa/Djibouti"),
+                    ("Africa/Douala", "Africa/Douala"),
+                    ("Africa/El_Aaiun", "Africa/El_Aaiun"),
+                    ("Africa/Freetown", "Africa/Freetown"),
+                    ("Africa/Gaborone", "Africa/Gaborone"),
+                    ("Africa/Harare", "Africa/Harare"),
+                    ("Africa/Johannesburg", "Africa/Johannesburg"),
+                    ("Africa/Juba", "Africa/Juba"),
+                    ("Africa/Kampala", "Africa/Kampala"),
+                    ("Africa/Khartoum", "Africa/Khartoum"),
+                    ("Africa/Kigali", "Africa/Kigali"),
+                    ("Africa/Kinshasa", "Africa/Kinshasa"),
+                    ("Africa/Lagos", "Africa/Lagos"),
+                    ("Africa/Libreville", "Africa/Libreville"),
+                    ("Africa/Lome", "Africa/Lome"),
+                    ("Africa/Luanda", "Africa/Luanda"),
+                    ("Africa/Lubumbashi", "Africa/Lubumbashi"),
+                    ("Africa/Lusaka", "Africa/Lusaka"),
+                    ("Africa/Malabo", "Africa/Malabo"),
+                    ("Africa/Maputo", "Africa/Maputo"),
+                    ("Africa/Maseru", "Africa/Maseru"),
+                    ("Africa/Mbabane", "Africa/Mbabane"),
+                    ("Africa/Mogadishu", "Africa/Mogadishu"),
+                    ("Africa/Monrovia", "Africa/Monrovia"),
+                    ("Africa/Nairobi", "Africa/Nairobi"),
+                    ("Africa/Ndjamena", "Africa/Ndjamena"),
+                    ("Africa/Niamey", "Africa/Niamey"),
+                    ("Africa/Nouakchott", "Africa/Nouakchott"),
+                    ("Africa/Ouagadougou", "Africa/Ouagadougou"),
+                    ("Africa/Porto-Novo", "Africa/Porto-Novo"),
+                    ("Africa/Sao_Tome", "Africa/Sao_Tome"),
+                    ("Africa/Timbuktu", "Africa/Timbuktu"),
+                    ("Africa/Tripoli", "Africa/Tripoli"),
+                    ("Africa/Tunis", "Africa/Tunis"),
+                    ("Africa/Windhoek", "Africa/Windhoek"),
+                    ("America/Adak", "America/Adak"),
+                    ("America/Anchorage", "America/Anchorage"),
+                    ("America/Anguilla", "America/Anguilla"),
+                    ("America/Antigua", "America/Antigua"),
+                    ("America/Araguaina", "America/Araguaina"),
+                    (
+                        "America/Argentina/Buenos_Aires",
+                        "America/Argentina/Buenos_Aires",
+                    ),
+                    ("America/Argentina/Catamarca", "America/Argentina/Catamarca"),
+                    (
+                        "America/Argentina/ComodRivadavia",
+                        "America/Argentina/ComodRivadavia",
+                    ),
+                    ("America/Argentina/Cordoba", "America/Argentina/Cordoba"),
+                    ("America/Argentina/Jujuy", "America/Argentina/Jujuy"),
+                    ("America/Argentina/La_Rioja", "America/Argentina/La_Rioja"),
+                    ("America/Argentina/Mendoza", "America/Argentina/Mendoza"),
+                    (
+                        "America/Argentina/Rio_Gallegos",
+                        "America/Argentina/Rio_Gallegos",
+                    ),
+                    ("America/Argentina/Salta", "America/Argentina/Salta"),
+                    ("America/Argentina/San_Juan", "America/Argentina/San_Juan"),
+                    ("America/Argentina/San_Luis", "America/Argentina/San_Luis"),
+                    ("America/Argentina/Tucuman", "America/Argentina/Tucuman"),
+                    ("America/Argentina/Ushuaia", "America/Argentina/Ushuaia"),
+                    ("America/Aruba", "America/Aruba"),
+                    ("America/Asuncion", "America/Asuncion"),
+                    ("America/Atikokan", "America/Atikokan"),
+                    ("America/Atka", "America/Atka"),
+                    ("America/Bahia", "America/Bahia"),
+                    ("America/Bahia_Banderas", "America/Bahia_Banderas"),
+                    ("America/Barbados", "America/Barbados"),
+                    ("America/Belem", "America/Belem"),
+                    ("America/Belize", "America/Belize"),
+                    ("America/Blanc-Sablon", "America/Blanc-Sablon"),
+                    ("America/Boa_Vista", "America/Boa_Vista"),
+                    ("America/Bogota", "America/Bogota"),
+                    ("America/Boise", "America/Boise"),
+                    ("America/Buenos_Aires", "America/Buenos_Aires"),
+                    ("America/Cambridge_Bay", "America/Cambridge_Bay"),
+                    ("America/Campo_Grande", "America/Campo_Grande"),
+                    ("America/Cancun", "America/Cancun"),
+                    ("America/Caracas", "America/Caracas"),
+                    ("America/Catamarca", "America/Catamarca"),
+                    ("America/Cayenne", "America/Cayenne"),
+                    ("America/Cayman", "America/Cayman"),
+                    ("America/Chicago", "America/Chicago"),
+                    ("America/Chihuahua", "America/Chihuahua"),
+                    ("America/Ciudad_Juarez", "America/Ciudad_Juarez"),
+                    ("America/Coral_Harbour", "America/Coral_Harbour"),
+                    ("America/Cordoba", "America/Cordoba"),
+                    ("America/Costa_Rica", "America/Costa_Rica"),
+                    ("America/Creston", "America/Creston"),
+                    ("America/Cuiaba", "America/Cuiaba"),
+                    ("America/Curacao", "America/Curacao"),
+                    ("America/Danmarkshavn", "America/Danmarkshavn"),
+                    ("America/Dawson", "America/Dawson"),
+                    ("America/Dawson_Creek", "America/Dawson_Creek"),
+                    ("America/Denver", "America/Denver"),
+                    ("America/Detroit", "America/Detroit"),
+                    ("America/Dominica", "America/Dominica"),
+                    ("America/Edmonton", "America/Edmonton"),
+                    ("America/Eirunepe", "America/Eirunepe"),
+                    ("America/El_Salvador", "America/El_Salvador"),
+                    ("America/Ensenada", "America/Ensenada"),
+                    ("America/Fort_Nelson", "America/Fort_Nelson"),
+                    ("America/Fort_Wayne", "America/Fort_Wayne"),
+                    ("America/Fortaleza", "America/Fortaleza"),
+                    ("America/Glace_Bay", "America/Glace_Bay"),
+                    ("America/Godthab", "America/Godthab"),
+                    ("America/Goose_Bay", "America/Goose_Bay"),
+                    ("America/Grand_Turk", "America/Grand_Turk"),
+                    ("America/Grenada", "America/Grenada"),
+                    ("America/Guadeloupe", "America/Guadeloupe"),
+                    ("America/Guatemala", "America/Guatemala"),
+                    ("America/Guayaquil", "America/Guayaquil"),
+                    ("America/Guyana", "America/Guyana"),
+                    ("America/Halifax", "America/Halifax"),
+                    ("America/Havana", "America/Havana"),
+                    ("America/Hermosillo", "America/Hermosillo"),
+                    ("America/Indiana/Indianapolis", "America/Indiana/Indianapolis"),
+                    ("America/Indiana/Knox", "America/Indiana/Knox"),
+                    ("America/Indiana/Marengo", "America/Indiana/Marengo"),
+                    ("America/Indiana/Petersburg", "America/Indiana/Petersburg"),
+                    ("America/Indiana/Tell_City", "America/Indiana/Tell_City"),
+                    ("America/Indiana/Vevay", "America/Indiana/Vevay"),
+                    ("America/Indiana/Vincennes", "America/Indiana/Vincennes"),
+                    ("America/Indiana/Winamac", "America/Indiana/Winamac"),
+                    ("America/Indianapolis", "America/Indianapolis"),
+                    ("America/Inuvik", "America/Inuvik"),
+                    ("America/Iqaluit", "America/Iqaluit"),
+                    ("America/Jamaica", "America/Jamaica"),
+                    ("America/Jujuy", "America/Jujuy"),
+                    ("America/Juneau", "America/Juneau"),
+                    ("America/Kentucky/Louisville", "America/Kentucky/Louisville"),
+                    ("America/Kentucky/Monticello", "America/Kentucky/Monticello"),
+                    ("America/Knox_IN", "America/Knox_IN"),
+                    ("America/Kralendijk", "America/Kralendijk"),
+                    ("America/La_Paz", "America/La_Paz"),
+                    ("America/Lima", "America/Lima"),
+                    ("America/Los_Angeles", "America/Los_Angeles"),
+                    ("America/Louisville", "America/Louisville"),
+                    ("America/Lower_Princes", "America/Lower_Princes"),
+                    ("America/Maceio", "America/Maceio"),
+                    ("America/Managua", "America/Managua"),
+                    ("America/Manaus", "America/Manaus"),
+                    ("America/Marigot", "America/Marigot"),
+                    ("America/Martinique", "America/Martinique"),
+                    ("America/Matamoros", "America/Matamoros"),
+                    ("America/Mazatlan", "America/Mazatlan"),
+                    ("America/Mendoza", "America/Mendoza"),
+                    ("America/Menominee", "America/Menominee"),
+                    ("America/Merida", "America/Merida"),
+                    ("America/Metlakatla", "America/Metlakatla"),
+                    ("America/Mexico_City", "America/Mexico_City"),
+                    ("America/Miquelon", "America/Miquelon"),
+                    ("America/Moncton", "America/Moncton"),
+                    ("America/Monterrey", "America/Monterrey"),
+                    ("America/Montevideo", "America/Montevideo"),
+                    ("America/Montreal", "America/Montreal"),
+                    ("America/Montserrat", "America/Montserrat"),
+                    ("America/Nassau", "America/Nassau"),
+                    ("America/New_York", "America/New_York"),
+                    ("America/Nipigon", "America/Nipigon"),
+                    ("America/Nome", "America/Nome"),
+                    ("America/Noronha", "America/Noronha"),
+                    ("America/North_Dakota/Beulah", "America/North_Dakota/Beulah"),
+                    ("America/North_Dakota/Center", "America/North_Dakota/Center"),
+                    (
+                        "America/North_Dakota/New_Salem",
+                        "America/North_Dakota/New_Salem",
+                    ),
+                    ("America/Nuuk", "America/Nuuk"),
+                    ("America/Ojinaga", "America/Ojinaga"),
+                    ("America/Panama", "America/Panama"),
+                    ("America/Pangnirtung", "America/Pangnirtung"),
+                    ("America/Paramaribo", "America/Paramaribo"),
+                    ("America/Phoenix", "America/Phoenix"),
+                    ("America/Port-au-Prince", "America/Port-au-Prince"),
+                    ("America/Port_of_Spain", "America/Port_of_Spain"),
+                    ("America/Porto_Acre", "America/Porto_Acre"),
+                    ("America/Porto_Velho", "America/Porto_Velho"),
+                    ("America/Puerto_Rico", "America/Puerto_Rico"),
+                    ("America/Punta_Arenas", "America/Punta_Arenas"),
+                    ("America/Rainy_River", "America/Rainy_River"),
+                    ("America/Rankin_Inlet", "America/Rankin_Inlet"),
+                    ("America/Recife", "America/Recife"),
+                    ("America/Regina", "America/Regina"),
+                    ("America/Resolute", "America/Resolute"),
+                    ("America/Rio_Branco", "America/Rio_Branco"),
+                    ("America/Rosario", "America/Rosario"),
+                    ("America/Santa_Isabel", "America/Santa_Isabel"),
+                    ("America/Santarem", "America/Santarem"),
+                    ("America/Santiago", "America/Santiago"),
+                    ("America/Santo_Domingo", "America/Santo_Domingo"),
+                    ("America/Sao_Paulo", "America/Sao_Paulo"),
+                    ("America/Scoresbysund", "America/Scoresbysund"),
+                    ("America/Shiprock", "America/Shiprock"),
+                    ("America/Sitka", "America/Sitka"),
+                    ("America/St_Barthelemy", "America/St_Barthelemy"),
+                    ("America/St_Johns", "America/St_Johns"),
+                    ("America/St_Kitts", "America/St_Kitts"),
+                    ("America/St_Lucia", "America/St_Lucia"),
+                    ("America/St_Thomas", "America/St_Thomas"),
+                    ("America/St_Vincent", "America/St_Vincent"),
+                    ("America/Swift_Current", "America/Swift_Current"),
+                    ("America/Tegucigalpa", "America/Tegucigalpa"),
+                    ("America/Thule", "America/Thule"),
+                    ("America/Thunder_Bay", "America/Thunder_Bay"),
+                    ("America/Tijuana", "America/Tijuana"),
+                    ("America/Toronto", "America/Toronto"),
+                    ("America/Tortola", "America/Tortola"),
+                    ("America/Vancouver", "America/Vancouver"),
+                    ("America/Virgin", "America/Virgin"),
+                    ("America/Whitehorse", "America/Whitehorse"),
+                    ("America/Winnipeg", "America/Winnipeg"),
+                    ("America/Yakutat", "America/Yakutat"),
+                    ("America/Yellowknife", "America/Yellowknife"),
+                    ("Antarctica/Casey", "Antarctica/Casey"),
+                    ("Antarctica/Davis", "Antarctica/Davis"),
+                    ("Antarctica/DumontDUrville", "Antarctica/DumontDUrville"),
+                    ("Antarctica/Macquarie", "Antarctica/Macquarie"),
+                    ("Antarctica/Mawson", "Antarctica/Mawson"),
+                    ("Antarctica/McMurdo", "Antarctica/McMurdo"),
+                    ("Antarctica/Palmer", "Antarctica/Palmer"),
+                    ("Antarctica/Rothera", "Antarctica/Rothera"),
+                    ("Antarctica/South_Pole", "Antarctica/South_Pole"),
+                    ("Antarctica/Syowa", "Antarctica/Syowa"),
+                    ("Antarctica/Troll", "Antarctica/Troll"),
+                    ("Antarctica/Vostok", "Antarctica/Vostok"),
+                    ("Arctic/Longyearbyen", "Arctic/Longyearbyen"),
+                    ("Asia/Aden", "Asia/Aden"),
+                    ("Asia/Almaty", "Asia/Almaty"),
+                    ("Asia/Amman", "Asia/Amman"),
+                    ("Asia/Anadyr", "Asia/Anadyr"),
+                    ("Asia/Aqtau", "Asia/Aqtau"),
+                    ("Asia/Aqtobe", "Asia/Aqtobe"),
+                    ("Asia/Ashgabat", "Asia/Ashgabat"),
+                    ("Asia/Ashkhabad", "Asia/Ashkhabad"),
+                    ("Asia/Atyrau", "Asia/Atyrau"),
+                    ("Asia/Baghdad", "Asia/Baghdad"),
+                    ("Asia/Bahrain", "Asia/Bahrain"),
+                    ("Asia/Baku", "Asia/Baku"),
+                    ("Asia/Bangkok", "Asia/Bangkok"),
+                    ("Asia/Barnaul", "Asia/Barnaul"),
+                    ("Asia/Beirut", "Asia/Beirut"),
+                    ("Asia/Bishkek", "Asia/Bishkek"),
+                    ("Asia/Brunei", "Asia/Brunei"),
+                    ("Asia/Calcutta", "Asia/Calcutta"),
+                    ("Asia/Chita", "Asia/Chita"),
+                    ("Asia/Choibalsan", "Asia/Choibalsan"),
+                    ("Asia/Chongqing", "Asia/Chongqing"),
+                    ("Asia/Chungking", "Asia/Chungking"),
+                    ("Asia/Colombo", "Asia/Colombo"),
+                    ("Asia/Dacca", "Asia/Dacca"),
+                    ("Asia/Damascus", "Asia/Damascus"),
+                    ("Asia/Dhaka", "Asia/Dhaka"),
+                    ("Asia/Dili", "Asia/Dili"),
+                    ("Asia/Dubai", "Asia/Dubai"),
+                    ("Asia/Dushanbe", "Asia/Dushanbe"),
+                    ("Asia/Famagusta", "Asia/Famagusta"),
+                    ("Asia/Gaza", "Asia/Gaza"),
+                    ("Asia/Harbin", "Asia/Harbin"),
+                    ("Asia/Hebron", "Asia/Hebron"),
+                    ("Asia/Ho_Chi_Minh", "Asia/Ho_Chi_Minh"),
+                    ("Asia/Hong_Kong", "Asia/Hong_Kong"),
+                    ("Asia/Hovd", "Asia/Hovd"),
+                    ("Asia/Irkutsk", "Asia/Irkutsk"),
+                    ("Asia/Istanbul", "Asia/Istanbul"),
+                    ("Asia/Jakarta", "Asia/Jakarta"),
+                    ("Asia/Jayapura", "Asia/Jayapura"),
+                    ("Asia/Jerusalem", "Asia/Jerusalem"),
+                    ("Asia/Kabul", "Asia/Kabul"),
+                    ("Asia/Kamchatka", "Asia/Kamchatka"),
+                    ("Asia/Karachi", "Asia/Karachi"),
+                    ("Asia/Kashgar", "Asia/Kashgar"),
+                    ("Asia/Kathmandu", "Asia/Kathmandu"),
+                    ("Asia/Katmandu", "Asia/Katmandu"),
+                    ("Asia/Khandyga", "Asia/Khandyga"),
+                    ("Asia/Kolkata", "Asia/Kolkata"),
+                    ("Asia/Krasnoyarsk", "Asia/Krasnoyarsk"),
+                    ("Asia/Kuala_Lumpur", "Asia/Kuala_Lumpur"),
+                    ("Asia/Kuching", "Asia/Kuching"),
+                    ("Asia/Kuwait", "Asia/Kuwait"),
+                    ("Asia/Macao", "Asia/Macao"),
+                    ("Asia/Macau", "Asia/Macau"),
+                    ("Asia/Magadan", "Asia/Magadan"),
+                    ("Asia/Makassar", "Asia/Makassar"),
+                    ("Asia/Manila", "Asia/Manila"),
+                    ("Asia/Muscat", "Asia/Muscat"),
+                    ("Asia/Nicosia", "Asia/Nicosia"),
+                    ("Asia/Novokuznetsk", "Asia/Novokuznetsk"),
+                    ("Asia/Novosibirsk", "Asia/Novosibirsk"),
+                    ("Asia/Omsk", "Asia/Omsk"),
+                    ("Asia/Oral", "Asia/Oral"),
+                    ("Asia/Phnom_Penh", "Asia/Phnom_Penh"),
+                    ("Asia/Pontianak", "Asia/Pontianak"),
+                    ("Asia/Pyongyang", "Asia/Pyongyang"),
+                    ("Asia/Qatar", "Asia/Qatar"),
+                    ("Asia/Qostanay", "Asia/Qostanay"),
+                    ("Asia/Qyzylorda", "Asia/Qyzylorda"),
+                    ("Asia/Rangoon", "Asia/Rangoon"),
+                    ("Asia/Riyadh", "Asia/Riyadh"),
+                    ("Asia/Saigon", "Asia/Saigon"),
+                    ("Asia/Sakhalin", "Asia/Sakhalin"),
+                    ("Asia/Samarkand", "Asia/Samarkand"),
+                    ("Asia/Seoul", "Asia/Seoul"),
+                    ("Asia/Shanghai", "Asia/Shanghai"),
+                    ("Asia/Singapore", "Asia/Singapore"),
+                    ("Asia/Srednekolymsk", "Asia/Srednekolymsk"),
+                    ("Asia/Taipei", "Asia/Taipei"),
+                    ("Asia/Tashkent", "Asia/Tashkent"),
+                    ("Asia/Tbilisi", "Asia/Tbilisi"),
+                    ("Asia/Tehran", "Asia/Tehran"),
+                    ("Asia/Tel_Aviv", "Asia/Tel_Aviv"),
+                    ("Asia/Thimbu", "Asia/Thimbu"),
+                    ("Asia/Thimphu", "Asia/Thimphu"),
+                    ("Asia/Tokyo", "Asia/Tokyo"),
+                    ("Asia/Tomsk", "Asia/Tomsk"),
+                    ("Asia/Ujung_Pandang", "Asia/Ujung_Pandang"),
+                    ("Asia/Ulaanbaatar", "Asia/Ulaanbaatar"),
+                    ("Asia/Ulan_Bator", "Asia/Ulan_Bator"),
+                    ("Asia/Urumqi", "Asia/Urumqi"),
+                    ("Asia/Ust-Nera", "Asia/Ust-Nera"),
+                    ("Asia/Vientiane", "Asia/Vientiane"),
+                    ("Asia/Vladivostok", "Asia/Vladivostok"),
+                    ("Asia/Yakutsk", "Asia/Yakutsk"),
+                    ("Asia/Yangon", "Asia/Yangon"),
+                    ("Asia/Yekaterinburg", "Asia/Yekaterinburg"),
+                    ("Asia/Yerevan", "Asia/Yerevan"),
+                    ("Atlantic/Azores", "Atlantic/Azores"),
+                    ("Atlantic/Bermuda", "Atlantic/Bermuda"),
+                    ("Atlantic/Canary", "Atlantic/Canary"),
+                    ("Atlantic/Cape_Verde", "Atlantic/Cape_Verde"),
+                    ("Atlantic/Faeroe", "Atlantic/Faeroe"),
+                    ("Atlantic/Faroe", "Atlantic/Faroe"),
+                    ("Atlantic/Jan_Mayen", "Atlantic/Jan_Mayen"),
+                    ("Atlantic/Madeira", "Atlantic/Madeira"),
+                    ("Atlantic/Reykjavik", "Atlantic/Reykjavik"),
+                    ("Atlantic/South_Georgia", "Atlantic/South_Georgia"),
+                    ("Atlantic/St_Helena", "Atlantic/St_Helena"),
+                    ("Atlantic/Stanley", "Atlantic/Stanley"),
+                    ("Australia/ACT", "Australia/ACT"),
+                    ("Australia/Adelaide", "Australia/Adelaide"),
+                    ("Australia/Brisbane", "Australia/Brisbane"),
+                    ("Australia/Broken_Hill", "Australia/Broken_Hill"),
+                    ("Australia/Canberra", "Australia/Canberra"),
+                    ("Australia/Currie", "Australia/Currie"),
+                    ("Australia/Darwin", "Australia/Darwin"),
+                    ("Australia/Eucla", "Australia/Eucla"),
+                    ("Australia/Hobart", "Australia/Hobart"),
+                    ("Australia/LHI", "Australia/LHI"),
+                    ("Australia/Lindeman", "Australia/Lindeman"),
+                    ("Australia/Lord_Howe", "Australia/Lord_Howe"),
+                    ("Australia/Melbourne", "Australia/Melbourne"),
+                    ("Australia/NSW", "Australia/NSW"),
+                    ("Australia/North", "Australia/North"),
+                    ("Australia/Perth", "Australia/Perth"),
+                    ("Australia/Queensland", "Australia/Queensland"),
+                    ("Australia/South", "Australia/South"),
+                    ("Australia/Sydney", "Australia/Sydney"),
+                    ("Australia/Tasmania", "Australia/Tasmania"),
+                    ("Australia/Victoria", "Australia/Victoria"),
+                    ("Australia/West", "Australia/West"),
+                    ("Australia/Yancowinna", "Australia/Yancowinna"),
+                    ("Brazil/Acre", "Brazil/Acre"),
+                    ("Brazil/DeNoronha", "Brazil/DeNoronha"),
+                    ("Brazil/East", "Brazil/East"),
+                    ("Brazil/West", "Brazil/West"),
+                    ("CET", "CET"),
+                    ("CST6CDT", "CST6CDT"),
+                    ("Canada/Atlantic", "Canada/Atlantic"),
+                    ("Canada/Central", "Canada/Central"),
+                    ("Canada/Eastern", "Canada/Eastern"),
+                    ("Canada/Mountain", "Canada/Mountain"),
+                    ("Canada/Newfoundland", "Canada/Newfoundland"),
+                    ("Canada/Pacific", "Canada/Pacific"),
+                    ("Canada/Saskatchewan", "Canada/Saskatchewan"),
+                    ("Canada/Yukon", "Canada/Yukon"),
+                    ("Chile/Continental", "Chile/Continental"),
+                    ("Chile/EasterIsland", "Chile/EasterIsland"),
+                    ("Cuba", "Cuba"),
+                    ("EET", "EET"),
+                    ("EST", "EST"),
+                    ("EST5EDT", "EST5EDT"),
+                    ("Egypt", "Egypt"),
+                    ("Eire", "Eire"),
+                    ("Etc/GMT", "Etc/GMT"),
+                    ("Etc/GMT+0", "Etc/GMT+0"),
+                    ("Etc/GMT+1", "Etc/GMT+1"),
+                    ("Etc/GMT+10", "Etc/GMT+10"),
+                    ("Etc/GMT+11", "Etc/GMT+11"),
+                    ("Etc/GMT+12", "Etc/GMT+12"),
+                    ("Etc/GMT+2", "Etc/GMT+2"),
+                    ("Etc/GMT+3", "Etc/GMT+3"),
+                    ("Etc/GMT+4", "Etc/GMT+4"),
+                    ("Etc/GMT+5", "Etc/GMT+5"),
+                    ("Etc/GMT+6", "Etc/GMT+6"),
+                    ("Etc/GMT+7", "Etc/GMT+7"),
+                    ("Etc/GMT+8", "Etc/GMT+8"),
+                    ("Etc/GMT+9", "Etc/GMT+9"),
+                    ("Etc/GMT-0", "Etc/GMT-0"),
+                    ("Etc/GMT-1", "Etc/GMT-1"),
+                    ("Etc/GMT-10", "Etc/GMT-10"),
+                    ("Etc/GMT-11", "Etc/GMT-11"),
+                    ("Etc/GMT-12", "Etc/GMT-12"),
+                    ("Etc/GMT-13", "Etc/GMT-13"),
+                    ("Etc/GMT-14", "Etc/GMT-14"),
+                    ("Etc/GMT-2", "Etc/GMT-2"),
+                    ("Etc/GMT-3", "Etc/GMT-3"),
+                    ("Etc/GMT-4", "Etc/GMT-4"),
+                    ("Etc/GMT-5", "Etc/GMT-5"),
+                    ("Etc/GMT-6", "Etc/GMT-6"),
+                    ("Etc/GMT-7", "Etc/GMT-7"),
+                    ("Etc/GMT-8", "Etc/GMT-8"),
+                    ("Etc/GMT-9", "Etc/GMT-9"),
+                    ("Etc/GMT0", "Etc/GMT0"),
+                    ("Etc/Greenwich", "Etc/Greenwich"),
+                    ("Etc/UCT", "Etc/UCT"),
+                    ("Etc/UTC", "Etc/UTC"),
+                    ("Etc/Universal", "Etc/Universal"),
+                    ("Etc/Zulu", "Etc/Zulu"),
+                    ("Europe/Amsterdam", "Europe/Amsterdam"),
+                    ("Europe/Andorra", "Europe/Andorra"),
+                    ("Europe/Astrakhan", "Europe/Astrakhan"),
+                    ("Europe/Athens", "Europe/Athens"),
+                    ("Europe/Belfast", "Europe/Belfast"),
+                    ("Europe/Belgrade", "Europe/Belgrade"),
+                    ("Europe/Berlin", "Europe/Berlin"),
+                    ("Europe/Bratislava", "Europe/Bratislava"),
+                    ("Europe/Brussels", "Europe/Brussels"),
+                    ("Europe/Bucharest", "Europe/Bucharest"),
+                    ("Europe/Budapest", "Europe/Budapest"),
+                    ("Europe/Busingen", "Europe/Busingen"),
+                    ("Europe/Chisinau", "Europe/Chisinau"),
+                    ("Europe/Copenhagen", "Europe/Copenhagen"),
+                    ("Europe/Dublin", "Europe/Dublin"),
+                    ("Europe/Gibraltar", "Europe/Gibraltar"),
+                    ("Europe/Guernsey", "Europe/Guernsey"),
+                    ("Europe/Helsinki", "Europe/Helsinki"),
+                    ("Europe/Isle_of_Man", "Europe/Isle_of_Man"),
+                    ("Europe/Istanbul", "Europe/Istanbul"),
+                    ("Europe/Jersey", "Europe/Jersey"),
+                    ("Europe/Kaliningrad", "Europe/Kaliningrad"),
+                    ("Europe/Kiev", "Europe/Kiev"),
+                    ("Europe/Kirov", "Europe/Kirov"),
+                    ("Europe/Kyiv", "Europe/Kyiv"),
+                    ("Europe/Lisbon", "Europe/Lisbon"),
+                    ("Europe/Ljubljana", "Europe/Ljubljana"),
+                    ("Europe/London", "Europe/London"),
+                    ("Europe/Luxembourg", "Europe/Luxembourg"),
+                    ("Europe/Madrid", "Europe/Madrid"),
+                    ("Europe/Malta", "Europe/Malta"),
+                    ("Europe/Mariehamn", "Europe/Mariehamn"),
+                    ("Europe/Minsk", "Europe/Minsk"),
+                    ("Europe/Monaco", "Europe/Monaco"),
+                    ("Europe/Moscow", "Europe/Moscow"),
+                    ("Europe/Nicosia", "Europe/Nicosia"),
+                    ("Europe/Oslo", "Europe/Oslo"),
+                    ("Europe/Paris", "Europe/Paris"),
+                    ("Europe/Podgorica", "Europe/Podgorica"),
+                    ("Europe/Prague", "Europe/Prague"),
+                    ("Europe/Riga", "Europe/Riga"),
+                    ("Europe/Rome", "Europe/Rome"),
+                    ("Europe/Samara", "Europe/Samara"),
+                    ("Europe/San_Marino", "Europe/San_Marino"),
+                    ("Europe/Sarajevo", "Europe/Sarajevo"),
+                    ("Europe/Saratov", "Europe/Saratov"),
+                    ("Europe/Simferopol", "Europe/Simferopol"),
+                    ("Europe/Skopje", "Europe/Skopje"),
+                    ("Europe/Sofia", "Europe/Sofia"),
+                    ("Europe/Stockholm", "Europe/Stockholm"),
+                    ("Europe/Tallinn", "Europe/Tallinn"),
+                    ("Europe/Tirane", "Europe/Tirane"),
+                    ("Europe/Tiraspol", "Europe/Tiraspol"),
+                    ("Europe/Ulyanovsk", "Europe/Ulyanovsk"),
+                    ("Europe/Uzhgorod", "Europe/Uzhgorod"),
+                    ("Europe/Vaduz", "Europe/Vaduz"),
+                    ("Europe/Vatican", "Europe/Vatican"),
+                    ("Europe/Vienna", "Europe/Vienna"),
+                    ("Europe/Vilnius", "Europe/Vilnius"),
+                    ("Europe/Volgograd", "Europe/Volgograd"),
+                    ("Europe/Warsaw", "Europe/Warsaw"),
+                    ("Europe/Zagreb", "Europe/Zagreb"),
+                    ("Europe/Zaporozhye", "Europe/Zaporozhye"),
+                    ("Europe/Zurich", "Europe/Zurich"),
+                    ("Factory", "Factory"),
+                    ("GB", "GB"),
+                    ("GB-Eire", "GB-Eire"),
+                    ("GMT", "GMT"),
+                    ("GMT+0", "GMT+0"),
+                    ("GMT-0", "GMT-0"),
+                    ("GMT0", "GMT0"),
+                    ("Greenwich", "Greenwich"),
+                    ("HST", "HST"),
+                    ("Hongkong", "Hongkong"),
+                    ("Iceland", "Iceland"),
+                    ("Indian/Antananarivo", "Indian/Antananarivo"),
+                    ("Indian/Chagos", "Indian/Chagos"),
+                    ("Indian/Christmas", "Indian/Christmas"),
+                    ("Indian/Cocos", "Indian/Cocos"),
+                    ("Indian/Comoro", "Indian/Comoro"),
+                    ("Indian/Kerguelen", "Indian/Kerguelen"),
+                    ("Indian/Mahe", "Indian/Mahe"),
+                    ("Indian/Maldives", "Indian/Maldives"),
+                    ("Indian/Mauritius", "Indian/Mauritius"),
+                    ("Indian/Mayotte", "Indian/Mayotte"),
+                    ("Indian/Reunion", "Indian/Reunion"),
+                    ("Iran", "Iran"),
+                    ("Israel", "Israel"),
+                    ("Jamaica", "Jamaica"),
+                    ("Japan", "Japan"),
+                    ("Kwajalein", "Kwajalein"),
+                    ("Libya", "Libya"),
+                    ("MET", "MET"),
+                    ("MST", "MST"),
+                    ("MST7MDT", "MST7MDT"),
+                    ("Mexico/BajaNorte", "Mexico/BajaNorte"),
+                    ("Mexico/BajaSur", "Mexico/BajaSur"),
+                    ("Mexico/General", "Mexico/General"),
+                    ("NZ", "NZ"),
+                    ("NZ-CHAT", "NZ-CHAT"),
+                    ("Navajo", "Navajo"),
+                    ("PRC", "PRC"),
+                    ("PST8PDT", "PST8PDT"),
+                    ("Pacific/Apia", "Pacific/Apia"),
+                    ("Pacific/Auckland", "Pacific/Auckland"),
+                    ("Pacific/Bougainville", "Pacific/Bougainville"),
+                    ("Pacific/Chatham", "Pacific/Chatham"),
+                    ("Pacific/Chuuk", "Pacific/Chuuk"),
+                    ("Pacific/Easter", "Pacific/Easter"),
+                    ("Pacific/Efate", "Pacific/Efate"),
+                    ("Pacific/Enderbury", "Pacific/Enderbury"),
+                    ("Pacific/Fakaofo", "Pacific/Fakaofo"),
+                    ("Pacific/Fiji", "Pacific/Fiji"),
+                    ("Pacific/Funafuti", "Pacific/Funafuti"),
+                    ("Pacific/Galapagos", "Pacific/Galapagos"),
+                    ("Pacific/Gambier", "Pacific/Gambier"),
+                    ("Pacific/Guadalcanal", "Pacific/Guadalcanal"),
+                    ("Pacific/Guam", "Pacific/Guam"),
+                    ("Pacific/Honolulu", "Pacific/Honolulu"),
+                    ("Pacific/Johnston", "Pacific/Johnston"),
+                    ("Pacific/Kanton", "Pacific/Kanton"),
+                    ("Pacific/Kiritimati", "Pacific/Kiritimati"),
+                    ("Pacific/Kosrae", "Pacific/Kosrae"),
+                    ("Pacific/Kwajalein", "Pacific/Kwajalein"),
+                    ("Pacific/Majuro", "Pacific/Majuro"),
+                    ("Pacific/Marquesas", "Pacific/Marquesas"),
+                    ("Pacific/Midway", "Pacific/Midway"),
+                    ("Pacific/Nauru", "Pacific/Nauru"),
+                    ("Pacific/Niue", "Pacific/Niue"),
+                    ("Pacific/Norfolk", "Pacific/Norfolk"),
+                    ("Pacific/Noumea", "Pacific/Noumea"),
+                    ("Pacific/Pago_Pago", "Pacific/Pago_Pago"),
+                    ("Pacific/Palau", "Pacific/Palau"),
+                    ("Pacific/Pitcairn", "Pacific/Pitcairn"),
+                    ("Pacific/Pohnpei", "Pacific/Pohnpei"),
+                    ("Pacific/Ponape", "Pacific/Ponape"),
+                    ("Pacific/Port_Moresby", "Pacific/Port_Moresby"),
+                    ("Pacific/Rarotonga", "Pacific/Rarotonga"),
+                    ("Pacific/Saipan", "Pacific/Saipan"),
+                    ("Pacific/Samoa", "Pacific/Samoa"),
+                    ("Pacific/Tahiti", "Pacific/Tahiti"),
+                    ("Pacific/Tarawa", "Pacific/Tarawa"),
+                    ("Pacific/Tongatapu", "Pacific/Tongatapu"),
+                    ("Pacific/Truk", "Pacific/Truk"),
+                    ("Pacific/Wake", "Pacific/Wake"),
+                    ("Pacific/Wallis", "Pacific/Wallis"),
+                    ("Pacific/Yap", "Pacific/Yap"),
+                    ("Poland", "Poland"),
+                    ("Portugal", "Portugal"),
+                    ("ROC", "ROC"),
+                    ("ROK", "ROK"),
+                    ("Singapore", "Singapore"),
+                    ("Turkey", "Turkey"),
+                    ("UCT", "UCT"),
+                    ("US/Alaska", "US/Alaska"),
+                    ("US/Aleutian", "US/Aleutian"),
+                    ("US/Arizona", "US/Arizona"),
+                    ("US/Central", "US/Central"),
+                    ("US/East-Indiana", "US/East-Indiana"),
+                    ("US/Eastern", "US/Eastern"),
+                    ("US/Hawaii", "US/Hawaii"),
+                    ("US/Indiana-Starke", "US/Indiana-Starke"),
+                    ("US/Michigan", "US/Michigan"),
+                    ("US/Mountain", "US/Mountain"),
+                    ("US/Pacific", "US/Pacific"),
+                    ("US/Samoa", "US/Samoa"),
+                    ("UTC", "UTC"),
+                    ("Universal", "Universal"),
+                    ("W-SU", "W-SU"),
+                    ("WET", "WET"),
+                    ("Zulu", "Zulu"),
+                    ("localtime", "localtime"),
+                ],
+                default="UTC",
+                max_length=255,
+            ),
+        ),
+    ]

bookwyrm/migrations/0200_auto_20240327_1914.py

@@ -0,0 +1,27 @@
+# Generated by Django 3.2.25 on 2024-03-27 19:14
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0199_merge_20240326_1217"),
+    ]
+
+    operations = [
+        migrations.RemoveField(
+            model_name="addfiletotar",
+            name="childjob_ptr",
+        ),
+        migrations.RemoveField(
+            model_name="addfiletotar",
+            name="parent_export_job",
+        ),
+        migrations.DeleteModel(
+            name="AddBookToUserExportJob",
+        ),
+        migrations.DeleteModel(
+            name="AddFileToTar",
+        ),
+    ]

bookwyrm/migrations/0200_status_bookwyrm_st_thread__cf064f_idx.py

@@ -0,0 +1,19 @@
+# Generated by Django 3.2.25 on 2024-04-03 19:05
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0199_status_bookwyrm_st_remote__06aeba_idx"),
+    ]
+
+    operations = [
+        migrations.AddIndex(
+            model_name="status",
+            index=models.Index(
+                fields=["thread_id"], name="bookwyrm_st_thread__cf064f_idx"
+            ),
+        ),
+    ]

bookwyrm/migrations/0201_alter_hashtag_name_alter_user_localname.py

@@ -0,0 +1,39 @@
+# Generated by Django 4.2.11 on 2024-04-01 21:09
+
+import bookwyrm.models.fields
+from django.db import migrations, models
+from django.contrib.postgres.operations import CreateCollation
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0200_alter_user_preferred_timezone"),
+    ]
+
+    operations = [
+        CreateCollation(
+            "case_insensitive",
+            provider="icu",
+            locale="und-u-ks-level2",
+            deterministic=False,
+        ),
+        migrations.AlterField(
+            model_name="hashtag",
+            name="name",
+            field=bookwyrm.models.fields.CharField(
+                db_collation="case_insensitive", max_length=256
+            ),
+        ),
+        migrations.AlterField(
+            model_name="user",
+            name="localname",
+            field=models.CharField(
+                db_collation="case_insensitive",
+                max_length=255,
+                null=True,
+                unique=True,
+                validators=[bookwyrm.models.fields.validate_localname],
+            ),
+        ),
+    ]

bookwyrm/migrations/0201_keypair_bookwyrm_ke_remote__472927_idx.py

@@ -0,0 +1,19 @@
+# Generated by Django 3.2.25 on 2024-04-03 19:10
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0200_status_bookwyrm_st_thread__cf064f_idx"),
+    ]
+
+    operations = [
+        migrations.AddIndex(
+            model_name="keypair",
+            index=models.Index(
+                fields=["remote_id"], name="bookwyrm_ke_remote__472927_idx"
+            ),
+        ),
+    ]

bookwyrm/migrations/0202_user_bookwyrm_us_usernam_b2546d_idx.py

@@ -0,0 +1,19 @@
+# Generated by Django 3.2.25 on 2024-04-03 19:14
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0201_keypair_bookwyrm_ke_remote__472927_idx"),
+    ]
+
+    operations = [
+        migrations.AddIndex(
+            model_name="user",
+            index=models.Index(
+                fields=["username"], name="bookwyrm_us_usernam_b2546d_idx"
+            ),
+        ),
+    ]

bookwyrm/migrations/0203_user_bookwyrm_us_is_acti_972dc4_idx.py

@@ -0,0 +1,19 @@
+# Generated by Django 3.2.25 on 2024-04-03 19:22
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0202_user_bookwyrm_us_usernam_b2546d_idx"),
+    ]
+
+    operations = [
+        migrations.AddIndex(
+            model_name="user",
+            index=models.Index(
+                fields=["is_active", "local"], name="bookwyrm_us_is_acti_972dc4_idx"
+            ),
+        ),
+    ]

bookwyrm/migrations/0204_merge_20240409_1042.py

@@ -0,0 +1,13 @@
+# Generated by Django 3.2.25 on 2024-04-09 10:42
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0197_mergedauthor_mergedbook"),
+        ("bookwyrm", "0203_user_bookwyrm_us_is_acti_972dc4_idx"),
+    ]
+
+    operations = []

bookwyrm/migrations/0205_merge_20240410_2022.py

@@ -0,0 +1,13 @@
+# Generated by Django 4.2.11 on 2024-04-10 20:22
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0201_alter_hashtag_name_alter_user_localname"),
+        ("bookwyrm", "0204_merge_20240409_1042"),
+    ]
+
+    operations = []

bookwyrm/migrations/0205_merge_20240413_0232.py

@@ -0,0 +1,13 @@
+# Generated by Django 3.2.25 on 2024-04-13 02:32
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0200_auto_20240327_1914"),
+        ("bookwyrm", "0204_merge_20240409_1042"),
+    ]
+
+    operations = []

bookwyrm/migrations/0206_merge_20240415_1537.py

@@ -0,0 +1,13 @@
+# Generated by Django 4.2.11 on 2024-04-15 15:37
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bookwyrm", "0205_merge_20240410_2022"),
+        ("bookwyrm", "0205_merge_20240413_0232"),
+    ]
+
+    operations = []

bookwyrm/models/__init__.py

@@ -26,6 +26,8 @@ from .federated_server import FederatedServer
 from .group import Group, GroupMember, GroupMemberInvitation
 
 from .import_job import ImportJob, ImportItem
+from .bookwyrm_import_job import BookwyrmImportJob
+from .bookwyrm_export_job import BookwyrmExportJob
 
 from .move import MoveUser
 

bookwyrm/models/activitypub_mixin.py

@@ -152,8 +152,9 @@ class ActivitypubMixin:
         # find anyone who's tagged in a status, for example
         mentions = self.recipients if hasattr(self, "recipients") else []
 
-        # we always send activities to explicitly mentioned users' inboxes
-        recipients = [u.inbox for u in mentions or [] if not u.local]
+        # we always send activities to explicitly mentioned users (using shared inboxes
+        # where available to avoid duplicate submissions to a given instance)
+        recipients = {u.shared_inbox or u.inbox for u in mentions if not u.local}
 
         # unless it's a dm, all the followers should receive the activity
         if privacy != "direct":
@@ -168,23 +169,23 @@ class ActivitypubMixin:
             # filter users first by whether they're using the desired software
             # this lets us send book updates only to other bw servers
             if software:
-                queryset = queryset.filter(bookwyrm_user=(software == "bookwyrm"))
+                queryset = queryset.filter(bookwyrm_user=software == "bookwyrm")
             # if there's a user, we only want to send to the user's followers
             if user:
                 queryset = queryset.filter(following=user)
 
-            # ideally, we will send to shared inboxes for efficiency
-            shared_inboxes = (
-                queryset.filter(shared_inbox__isnull=False)
-                .values_list("shared_inbox", flat=True)
-                .distinct()
+            # as above, we prefer shared inboxes if available
+            recipients.update(
+                queryset.filter(shared_inbox__isnull=False).values_list(
+                    "shared_inbox", flat=True
+                )
             )
-            # but not everyone has a shared inbox
-            inboxes = queryset.filter(shared_inbox__isnull=True).values_list(
-                "inbox", flat=True
+            recipients.update(
+                queryset.filter(shared_inbox__isnull=True).values_list(
+                    "inbox", flat=True
+                )
             )
-            recipients += list(shared_inboxes) + list(inboxes)
-        return list(set(recipients))
+        return list(recipients)
 
     def to_activity_dataclass(self):
         """convert from a model to an activity"""
@@ -205,14 +206,10 @@ class ObjectMixin(ActivitypubMixin):
         created: Optional[bool] = None,
         software: Any = None,
         priority: str = BROADCAST,
+        broadcast: bool = True,
         **kwargs: Any,
     ) -> None:
         """broadcast created/updated/deleted objects as appropriate"""
-        broadcast = kwargs.get("broadcast", True)
-        # this bonus kwarg would cause an error in the base save method
-        if "broadcast" in kwargs:
-            del kwargs["broadcast"]
-
         created = created or not bool(self.id)
         # first off, we want to save normally no matter what
         super().save(*args, **kwargs)
@@ -602,7 +599,7 @@ def to_ordered_collection_page(
     if activity_page.has_next():
         next_page = f"{remote_id}?page={activity_page.next_page_number()}"
     if activity_page.has_previous():
-        prev_page = f"{remote_id}?page=%d{activity_page.previous_page_number()}"
+        prev_page = f"{remote_id}?page={activity_page.previous_page_number()}"
     return activitypub.OrderedCollectionPage(
         id=f"{remote_id}?page={page}",
         partOf=remote_id,

bookwyrm/models/author.py

@@ -1,20 +1,25 @@
 """ database schema for info about authors """
-import re
-from typing import Tuple, Any
 
-from django.contrib.postgres.indexes import GinIndex
+import re
+from typing import Any
+
 from django.db import models
+from django.contrib.postgres.indexes import GinIndex
+import pgtrigger
 
 from bookwyrm import activitypub
-from bookwyrm.settings import DOMAIN
+from bookwyrm.settings import BASE_URL
+from bookwyrm.utils.db import format_trigger
 
-from .book import BookDataModel
+from .book import BookDataModel, MergedAuthor
 from . import fields
 
 
 class Author(BookDataModel):
     """basic biographic info"""
 
+    merged_model = MergedAuthor
+
     wikipedia_link = fields.CharField(
         max_length=255, blank=True, null=True, deduplication_field=True
     )
@@ -40,12 +45,12 @@ class Author(BookDataModel):
     )
     bio = fields.HtmlField(null=True, blank=True)
 
-    def save(self, *args: Tuple[Any, ...], **kwargs: dict[str, Any]) -> None:
+    def save(self, *args: Any, **kwargs: Any) -> None:
         """normalize isni format"""
-        if self.isni:
+        if self.isni is not None:
             self.isni = re.sub(r"\s", "", self.isni)
 
-        return super().save(*args, **kwargs)
+        super().save(*args, **kwargs)
 
     @property
     def isni_link(self):
@@ -65,11 +70,48 @@ class Author(BookDataModel):
 
     def get_remote_id(self):
         """editions and works both use "book" instead of model_name"""
-        return f"https://{DOMAIN}/author/{self.id}"
-
-    activity_serializer = activitypub.Author
+        return f"{BASE_URL}/author/{self.id}"
 
     class Meta:
-        """sets up postgres GIN index field"""
+        """sets up indexes and triggers"""
+
+        # pylint: disable=line-too-long
 
         indexes = (GinIndex(fields=["search_vector"]),)
+        triggers = [
+            pgtrigger.Trigger(
+                name="update_search_vector_on_author_edit",
+                when=pgtrigger.Before,
+                operation=pgtrigger.Insert
+                | pgtrigger.UpdateOf("name", "aliases", "search_vector"),
+                func=format_trigger(
+                    """new.search_vector :=
+                    -- author name, with priority A
+                    setweight(to_tsvector('simple', new.name), 'A') ||
+                    -- author aliases, with priority B
+                    setweight(to_tsvector('simple', coalesce(array_to_string(new.aliases, ' '), '')), 'B');
+                    RETURN new;
+                """
+                ),
+            ),
+            pgtrigger.Trigger(
+                name="reset_book_search_vector_on_author_edit",
+                when=pgtrigger.After,
+                operation=pgtrigger.UpdateOf("name", "aliases"),
+                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

bookwyrm/models/base_model.py

@@ -10,7 +10,7 @@ from django.http import Http404
 from django.utils.translation import gettext_lazy as _
 from django.utils.text import slugify
 
-from bookwyrm.settings import DOMAIN
+from bookwyrm.settings import BASE_URL
 from .fields import RemoteIdField
 
 
@@ -38,7 +38,7 @@ class BookWyrmModel(models.Model):
 
     def get_remote_id(self):
         """generate the url that resolves to the local object, without a slug"""
-        base_path = f"https://{DOMAIN}"
+        base_path = BASE_URL
         if hasattr(self, "user"):
             base_path = f"{base_path}{self.user.local_path}"
 
@@ -53,7 +53,7 @@ class BookWyrmModel(models.Model):
     @property
     def local_path(self):
         """how to link to this object in the local app, with a slug"""
-        local = self.get_remote_id().replace(f"https://{DOMAIN}", "")
+        local = self.get_remote_id().replace(BASE_URL, "")
 
         name = None
         if hasattr(self, "name_field"):

bookwyrm/models/book.py

@@ -1,29 +1,33 @@
 """ database schema for books and shelves """
+
 from itertools import chain
 import re
-from typing import Any
+from typing import Any, Dict, Optional, Iterable
+from typing_extensions import Self
 
 from django.contrib.postgres.search import SearchVectorField
 from django.contrib.postgres.indexes import GinIndex
 from django.core.cache import cache
 from django.db import models, transaction
-from django.db.models import Prefetch
+from django.db.models import Prefetch, ManyToManyField
 from django.dispatch import receiver
 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
 from bookwyrm.preview_images import generate_edition_preview_image_task
 from bookwyrm.settings import (
-    DOMAIN,
+    BASE_URL,
     DEFAULT_LANGUAGE,
     LANGUAGE_ARTICLES,
     ENABLE_PREVIEW_IMAGES,
     ENABLE_THUMBNAIL_GENERATION,
 )
+from bookwyrm.utils.db import format_trigger, add_update_fields
 
 from .activitypub_mixin import OrderedCollectionPageMixin, ObjectMixin
 from .base_model import BookWyrmModel
@@ -92,24 +96,134 @@ class BookDataModel(ObjectMixin, BookWyrmModel):
 
         abstract = True
 
-    def save(self, *args: Any, **kwargs: Any) -> None:
+    def save(
+        self, *args: Any, update_fields: Optional[Iterable[str]] = None, **kwargs: Any
+    ) -> None:
         """ensure that the remote_id is within this instance"""
         if self.id:
             self.remote_id = self.get_remote_id()
+            update_fields = add_update_fields(update_fields, "remote_id")
         else:
             self.origin_id = self.remote_id
             self.remote_id = None
-        return super().save(*args, **kwargs)
+            update_fields = add_update_fields(update_fields, "origin_id", "remote_id")
+
+        super().save(*args, update_fields=update_fields, **kwargs)
 
     # pylint: disable=arguments-differ
     def broadcast(self, activity, sender, software="bookwyrm", **kwargs):
         """only send book data updates to other bookwyrm instances"""
         super().broadcast(activity, sender, software=software, **kwargs)
 
+    def merge_into(self, canonical: Self, dry_run=False) -> Dict[str, Any]:
+        """merge this entity into another entity"""
+        if canonical.id == self.id:
+            raise ValueError(f"Cannot merge {self} into itself")
+
+        absorbed_fields = canonical.absorb_data_from(self, dry_run=dry_run)
+
+        if dry_run:
+            return absorbed_fields
+
+        canonical.save()
+
+        self.merged_model.objects.create(deleted_id=self.id, merged_into=canonical)
+
+        # move related models to canonical
+        related_models = [
+            (r.remote_field.name, r.related_model) for r in self._meta.related_objects
+        ]
+        # pylint: disable=protected-access
+        for related_field, related_model in related_models:
+            # Skip the ManyToMany fields that aren’t auto-created. These
+            # should have a corresponding OneToMany field in the model for
+            # the linking table anyway. If we update it through that model
+            # instead then we won’t lose the extra fields in the linking
+            # table.
+            # pylint: disable=protected-access
+            related_field_obj = related_model._meta.get_field(related_field)
+            if isinstance(related_field_obj, ManyToManyField):
+                through = related_field_obj.remote_field.through
+                if not through._meta.auto_created:
+                    continue
+            related_objs = related_model.objects.filter(**{related_field: self})
+            for related_obj in related_objs:
+                try:
+                    setattr(related_obj, related_field, canonical)
+                    related_obj.save()
+                except TypeError:
+                    getattr(related_obj, related_field).add(canonical)
+                    getattr(related_obj, related_field).remove(self)
+
+        self.delete()
+        return absorbed_fields
+
+    def absorb_data_from(self, other: Self, dry_run=False) -> Dict[str, Any]:
+        """fill empty fields with values from another entity"""
+        absorbed_fields = {}
+        for data_field in self._meta.get_fields():
+            if not hasattr(data_field, "activitypub_field"):
+                continue
+            canonical_value = getattr(self, data_field.name)
+            other_value = getattr(other, data_field.name)
+            if not other_value:
+                continue
+            if isinstance(data_field, fields.ArrayField):
+                if new_values := list(set(other_value) - set(canonical_value)):
+                    # append at the end (in no particular order)
+                    if not dry_run:
+                        setattr(self, data_field.name, canonical_value + new_values)
+                    absorbed_fields[data_field.name] = new_values
+            elif isinstance(data_field, fields.PartialDateField):
+                if (
+                    (not canonical_value)
+                    or (other_value.has_day and not canonical_value.has_day)
+                    or (other_value.has_month and not canonical_value.has_month)
+                ):
+                    if not dry_run:
+                        setattr(self, data_field.name, other_value)
+                    absorbed_fields[data_field.name] = other_value
+            else:
+                if not canonical_value:
+                    if not dry_run:
+                        setattr(self, data_field.name, other_value)
+                    absorbed_fields[data_field.name] = other_value
+        return absorbed_fields
+
+
+class MergedBookDataModel(models.Model):
+    """a BookDataModel instance that has been merged into another instance. kept
+    to be able to redirect old URLs"""
+
+    deleted_id = models.IntegerField(primary_key=True)
+
+    class Meta:
+        """abstract just like BookDataModel"""
+
+        abstract = True
+
+
+class MergedBook(MergedBookDataModel):
+    """an Book that has been merged into another one"""
+
+    merged_into = models.ForeignKey(
+        "Book", on_delete=models.PROTECT, related_name="absorbed"
+    )
+
+
+class MergedAuthor(MergedBookDataModel):
+    """an Author that has been merged into another one"""
+
+    merged_into = models.ForeignKey(
+        "Author", on_delete=models.PROTECT, related_name="absorbed"
+    )
+
 
 class Book(BookDataModel):
     """a generic book, which can mean either an edition or a work"""
 
+    merged_model = MergedBook
+
     connector = models.ForeignKey("Connector", on_delete=models.PROTECT, null=True)
 
     # book/work metadata
@@ -190,9 +304,13 @@ class Book(BookDataModel):
         """properties of this edition, as a string"""
         items = [
             self.physical_format if hasattr(self, "physical_format") else None,
-            f"{self.languages[0]} language"
-            if self.languages and self.languages[0] and self.languages[0] != "English"
-            else None,
+            (
+                f"{self.languages[0]} language"
+                if self.languages
+                and self.languages[0]
+                and self.languages[0] != "English"
+                else None
+            ),
             str(self.published_date.year) if self.published_date else None,
             ", ".join(self.publishers) if hasattr(self, "publishers") else None,
         ]
@@ -210,11 +328,11 @@ class Book(BookDataModel):
         if not isinstance(self, (Edition, Work)):
             raise ValueError("Books should be added as Editions or Works")
 
-        return super().save(*args, **kwargs)
+        super().save(*args, **kwargs)
 
     def get_remote_id(self):
         """editions and works both use "book" instead of model_name"""
-        return f"https://{DOMAIN}/book/{self.id}"
+        return f"{BASE_URL}/book/{self.id}"
 
     def guess_sort_title(self):
         """Get a best-guess sort title for the current book"""
@@ -232,9 +350,49 @@ 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(
+                    """
+                    WITH author_names AS (
+                        SELECT array_to_string(bookwyrm_author.name || bookwyrm_author.aliases, ' ') AS name_and_aliases
+                            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
+                    )
+                    SELECT
+                        -- 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 names and aliases (with priority C)
+                        (SELECT setweight(to_tsvector('simple', COALESCE(array_to_string(ARRAY_AGG(name_and_aliases), ' '), '')), 'C')
+                            FROM author_names
+                        ) ||
+
+                        --- last: series name, with lowest priority
+                        setweight(to_tsvector('english', COALESCE(new.series, '')), 'D')
+
+                        INTO new.search_vector;
+                    RETURN new;
+                    """
+                ),
+            )
+        ]
 
 
 class Work(OrderedCollectionPageMixin, Book):
@@ -247,10 +405,11 @@ class Work(OrderedCollectionPageMixin, Book):
 
     def save(self, *args, **kwargs):
         """set some fields on the edition object"""
+        super().save(*args, **kwargs)
+
         # set rank
         for edition in self.editions.all():
             edition.save()
-        return super().save(*args, **kwargs)
 
     @property
     def default_edition(self):
@@ -356,33 +515,48 @@ class Edition(Book):
         # max rank is 9
         return rank
 
-    def save(self, *args: Any, **kwargs: Any) -> None:
+    def save(
+        self, *args: Any, update_fields: Optional[Iterable[str]] = None, **kwargs: Any
+    ) -> None:
         """set some fields on the edition object"""
         # calculate isbn 10/13
-        if self.isbn_13 and self.isbn_13[:3] == "978" and not self.isbn_10:
+        if (
+            self.isbn_10 is None
+            and self.isbn_13 is not None
+            and self.isbn_13[:3] == "978"
+        ):
             self.isbn_10 = isbn_13_to_10(self.isbn_13)
-        if self.isbn_10 and not self.isbn_13:
+            update_fields = add_update_fields(update_fields, "isbn_10")
+        if self.isbn_13 is None and self.isbn_10 is not None:
             self.isbn_13 = isbn_10_to_13(self.isbn_10)
+            update_fields = add_update_fields(update_fields, "isbn_13")
 
         # normalize isbn format
-        if self.isbn_10:
+        if self.isbn_10 is not None:
             self.isbn_10 = normalize_isbn(self.isbn_10)
-        if self.isbn_13:
+        if self.isbn_13 is not None:
             self.isbn_13 = normalize_isbn(self.isbn_13)
 
         # set rank
-        self.edition_rank = self.get_rank()
-
-        # clear author cache
-        if self.id:
-            for author_id in self.authors.values_list("id", flat=True):
-                cache.delete(f"author-books-{author_id}")
+        if (new := self.get_rank()) != self.edition_rank:
+            self.edition_rank = new
+            update_fields = add_update_fields(update_fields, "edition_rank")
 
         # Create sort title by removing articles from title
         if self.sort_title in [None, ""]:
             self.sort_title = self.guess_sort_title()
+            update_fields = add_update_fields(update_fields, "sort_title")
 
-        return super().save(*args, **kwargs)
+        super().save(*args, update_fields=update_fields, **kwargs)
+
+        # clear author cache
+        if self.id:
+            cache.delete_many(
+                [
+                    f"author-books-{author_id}"
+                    for author_id in self.authors.values_list("id", flat=True)
+                ]
+            )
 
     @transaction.atomic
     def repair(self):

bookwyrm/models/bookwyrm_export_job.py

@@ -0,0 +1,341 @@
+"""Export user account to tar.gz file for import into another Bookwyrm instance"""
+
+import logging
+import os
+
+from boto3.session import Session as BotoSession
+from s3_tar import S3Tar
+
+from django.db.models import BooleanField, FileField, JSONField
+from django.core.serializers.json import DjangoJSONEncoder
+from django.core.files.base import ContentFile
+from django.core.files.storage import storages
+
+from bookwyrm import settings
+
+from bookwyrm.models import AnnualGoal, ReadThrough, ShelfBook, ListItem
+from bookwyrm.models import Review, Comment, Quotation
+from bookwyrm.models import Edition
+from bookwyrm.models import UserFollows, User, UserBlocks
+from bookwyrm.models.job import ParentJob
+from bookwyrm.tasks import app, IMPORTS
+from bookwyrm.utils.tar import BookwyrmTarFile
+
+logger = logging.getLogger(__name__)
+
+
+class BookwyrmAwsSession(BotoSession):
+    """a boto session that always uses settings.AWS_S3_ENDPOINT_URL"""
+
+    def client(self, *args, **kwargs):  # pylint: disable=arguments-differ
+        kwargs["endpoint_url"] = settings.AWS_S3_ENDPOINT_URL
+        return super().client("s3", *args, **kwargs)
+
+
+def select_exports_storage():
+    """callable to allow for dependency on runtime configuration"""
+    return storages["exports"]
+
+
+class BookwyrmExportJob(ParentJob):
+    """entry for a specific request to export a bookwyrm user"""
+
+    export_data = FileField(null=True, storage=select_exports_storage)
+    export_json = JSONField(null=True, encoder=DjangoJSONEncoder)
+    json_completed = BooleanField(default=False)
+
+    def start_job(self):
+        """schedule the first task"""
+
+        task = create_export_json_task.delay(job_id=self.id)
+        self.task_id = task.id
+        self.save(update_fields=["task_id"])
+
+
+@app.task(queue=IMPORTS)
+def create_export_json_task(job_id):
+    """create the JSON data for the export"""
+
+    job = BookwyrmExportJob.objects.get(id=job_id)
+
+    # don't start the job if it was stopped from the UI
+    if job.complete:
+        return
+
+    try:
+        job.set_status("active")
+
+        # generate JSON structure
+        job.export_json = export_json(job.user)
+        job.save(update_fields=["export_json"])
+
+        # create archive in separate task
+        create_archive_task.delay(job_id=job.id)
+    except Exception as err:  # pylint: disable=broad-except
+        logger.exception(
+            "create_export_json_task for %s failed with error: %s", job, err
+        )
+        job.set_status("failed")
+
+
+def archive_file_location(file, directory="") -> str:
+    """get the relative location of a file inside the archive"""
+    return os.path.join(directory, file.name)
+
+
+def add_file_to_s3_tar(s3_tar: S3Tar, storage, file, directory=""):
+    """
+    add file to S3Tar inside directory, keeping any directories under its
+    storage location
+    """
+    s3_tar.add_file(
+        os.path.join(storage.location, file.name),
+        folder=os.path.dirname(archive_file_location(file, directory=directory)),
+    )
+
+
+@app.task(queue=IMPORTS)
+def create_archive_task(job_id):
+    """create the archive containing the JSON file and additional files"""
+
+    job = BookwyrmExportJob.objects.get(id=job_id)
+
+    # don't start the job if it was stopped from the UI
+    if job.complete:
+        return
+
+    try:
+        export_task_id = str(job.task_id)
+        archive_filename = f"{export_task_id}.tar.gz"
+        export_json_bytes = DjangoJSONEncoder().encode(job.export_json).encode("utf-8")
+
+        user = job.user
+        editions = get_books_for_user(user)
+
+        if settings.USE_S3:
+            # Storage for writing temporary files
+            exports_storage = storages["exports"]
+
+            # Handle for creating the final archive
+            s3_tar = S3Tar(
+                exports_storage.bucket_name,
+                os.path.join(exports_storage.location, archive_filename),
+                session=BookwyrmAwsSession(),
+            )
+
+            # Save JSON file to a temporary location
+            export_json_tmp_file = os.path.join(export_task_id, "archive.json")
+            exports_storage.save(
+                export_json_tmp_file,
+                ContentFile(export_json_bytes),
+            )
+            s3_tar.add_file(
+                os.path.join(exports_storage.location, export_json_tmp_file)
+            )
+
+            # Add images to TAR
+            images_storage = storages["default"]
+
+            if user.avatar:
+                add_file_to_s3_tar(s3_tar, images_storage, user.avatar)
+
+            for edition in editions:
+                if edition.cover:
+                    add_file_to_s3_tar(
+                        s3_tar, images_storage, edition.cover, directory="images"
+                    )
+
+            # Create archive and store file name
+            s3_tar.tar()
+            job.export_data = archive_filename
+            job.save(update_fields=["export_data"])
+
+            # Delete temporary files
+            exports_storage.delete(export_json_tmp_file)
+
+        else:
+            job.export_data = archive_filename
+            with job.export_data.open("wb") as tar_file:
+                with BookwyrmTarFile.open(mode="w:gz", fileobj=tar_file) as tar:
+                    # save json file
+                    tar.write_bytes(export_json_bytes)
+
+                    # Add avatar image if present
+                    if user.avatar:
+                        tar.add_image(user.avatar)
+
+                    for edition in editions:
+                        if edition.cover:
+                            tar.add_image(edition.cover, directory="images")
+            job.save(update_fields=["export_data"])
+
+        job.set_status("completed")
+
+    except Exception as err:  # pylint: disable=broad-except
+        logger.exception("create_archive_task for %s failed with error: %s", job, err)
+        job.set_status("failed")
+
+
+def export_json(user: User):
+    """create export JSON"""
+    data = export_user(user)  # in the root of the JSON structure
+    data["settings"] = export_settings(user)
+    data["goals"] = export_goals(user)
+    data["books"] = export_books(user)
+    data["saved_lists"] = export_saved_lists(user)
+    data["follows"] = export_follows(user)
+    data["blocks"] = export_blocks(user)
+    return data
+
+
+def export_user(user: User):
+    """export user data"""
+    data = user.to_activity()
+    if user.avatar:
+        data["icon"]["url"] = archive_file_location(user.avatar)
+    else:
+        data["icon"] = {}
+    return data
+
+
+def export_settings(user: User):
+    """Additional settings - can't be serialized as AP"""
+    vals = [
+        "show_goal",
+        "preferred_timezone",
+        "default_post_privacy",
+        "show_suggested_users",
+    ]
+    return {k: getattr(user, k) for k in vals}
+
+
+def export_saved_lists(user: User):
+    """add user saved lists to export JSON"""
+    return [l.remote_id for l in user.saved_lists.all()]
+
+
+def export_follows(user: User):
+    """add user follows to export JSON"""
+    follows = UserFollows.objects.filter(user_subject=user).distinct()
+    following = User.objects.filter(userfollows_user_object__in=follows).distinct()
+    return [f.remote_id for f in following]
+
+
+def export_blocks(user: User):
+    """add user blocks to export JSON"""
+    blocks = UserBlocks.objects.filter(user_subject=user).distinct()
+    blocking = User.objects.filter(userblocks_user_object__in=blocks).distinct()
+    return [b.remote_id for b in blocking]
+
+
+def export_goals(user: User):
+    """add user reading goals to export JSON"""
+    reading_goals = AnnualGoal.objects.filter(user=user).distinct()
+    return [
+        {"goal": goal.goal, "year": goal.year, "privacy": goal.privacy}
+        for goal in reading_goals
+    ]
+
+
+def export_books(user: User):
+    """add books to export JSON"""
+    editions = get_books_for_user(user)
+    return [export_book(user, edition) for edition in editions]
+
+
+def export_book(user: User, edition: Edition):
+    """add book to export JSON"""
+    data = {}
+    data["work"] = edition.parent_work.to_activity()
+    data["edition"] = edition.to_activity()
+
+    if edition.cover:
+        data["edition"]["cover"]["url"] = archive_file_location(
+            edition.cover, directory="images"
+        )
+
+    # authors
+    data["authors"] = [author.to_activity() for author in edition.authors.all()]
+
+    # Shelves this book is on
+    # Every ShelfItem is this book so we don't other serializing
+    shelf_books = (
+        ShelfBook.objects.select_related("shelf")
+        .filter(user=user, book=edition)
+        .distinct()
+    )
+    data["shelves"] = [shelfbook.shelf.to_activity() for shelfbook in shelf_books]
+
+    # Lists and ListItems
+    # ListItems include "notes" and "approved" so we need them
+    # even though we know it's this book
+    list_items = ListItem.objects.filter(book=edition, user=user).distinct()
+
+    data["lists"] = []
+    for item in list_items:
+        list_info = item.book_list.to_activity()
+        list_info[
+            "privacy"
+        ] = item.book_list.privacy  # this isn't serialized so we add it
+        list_info["list_item"] = item.to_activity()
+        data["lists"].append(list_info)
+
+    # Statuses
+    # Can't use select_subclasses here because
+    # we need to filter on the "book" value,
+    # which is not available on an ordinary Status
+    for status in ["comments", "quotations", "reviews"]:
+        data[status] = []
+
+    comments = Comment.objects.filter(user=user, book=edition).all()
+    for status in comments:
+        obj = status.to_activity()
+        obj["progress"] = status.progress
+        obj["progress_mode"] = status.progress_mode
+        data["comments"].append(obj)
+
+    quotes = Quotation.objects.filter(user=user, book=edition).all()
+    for status in quotes:
+        obj = status.to_activity()
+        obj["position"] = status.position
+        obj["endposition"] = status.endposition
+        obj["position_mode"] = status.position_mode
+        data["quotations"].append(obj)
+
+    reviews = Review.objects.filter(user=user, book=edition).all()
+    data["reviews"] = [status.to_activity() for status in reviews]
+
+    # readthroughs can't be serialized to activity
+    book_readthroughs = (
+        ReadThrough.objects.filter(user=user, book=edition).distinct().values()
+    )
+    data["readthroughs"] = list(book_readthroughs)
+    return data
+
+
+def get_books_for_user(user):
+    """
+    Get all the books and editions related to a user.
+
+    We use union() instead of Q objects because it creates
+    multiple simple queries in stead of a much more complex DB query
+    that can time out.
+
+    """
+
+    shelf_eds = Edition.objects.select_related("parent_work").filter(shelves__user=user)
+    rt_eds = Edition.objects.select_related("parent_work").filter(
+        readthrough__user=user
+    )
+    review_eds = Edition.objects.select_related("parent_work").filter(review__user=user)
+    list_eds = Edition.objects.select_related("parent_work").filter(list__user=user)
+    comment_eds = Edition.objects.select_related("parent_work").filter(
+        comment__user=user
+    )
+    quote_eds = Edition.objects.select_related("parent_work").filter(
+        quotation__user=user
+    )
+
+    editions = shelf_eds.union(rt_eds, review_eds, list_eds, comment_eds, quote_eds)
+
+    return editions

bookwyrm/models/bookwyrm_import_job.py

@@ -0,0 +1,462 @@
+"""Import a user from another Bookwyrm instance"""
+
+import json
+import logging
+
+from django.db.models import FileField, JSONField, CharField
+from django.utils import timezone
+from django.utils.html import strip_tags
+from django.contrib.postgres.fields import ArrayField as DjangoArrayField
+
+from bookwyrm import activitypub
+from bookwyrm import models
+from bookwyrm.tasks import app, IMPORTS
+from bookwyrm.models.job import ParentJob, ParentTask, SubTask
+from bookwyrm.utils.tar import BookwyrmTarFile
+
+logger = logging.getLogger(__name__)
+
+
+class BookwyrmImportJob(ParentJob):
+    """entry for a specific request for importing a bookwyrm user backup"""
+
+    archive_file = FileField(null=True, blank=True)
+    import_data = JSONField(null=True)
+    required = DjangoArrayField(CharField(max_length=50, blank=True), blank=True)
+
+    def start_job(self):
+        """Start the job"""
+        start_import_task.delay(job_id=self.id, no_children=True)
+
+
+@app.task(queue=IMPORTS, base=ParentTask)
+def start_import_task(**kwargs):
+    """trigger the child import tasks for each user data"""
+    job = BookwyrmImportJob.objects.get(id=kwargs["job_id"])
+    archive_file = job.archive_file
+
+    # don't start the job if it was stopped from the UI
+    if job.complete:
+        return
+
+    try:
+        archive_file.open("rb")
+        with BookwyrmTarFile.open(mode="r:gz", fileobj=archive_file) as tar:
+            json_filename = next(
+                filter(lambda n: n.startswith("archive"), tar.getnames())
+            )
+            job.import_data = json.loads(tar.read(json_filename).decode("utf-8"))
+
+            if "include_user_profile" in job.required:
+                update_user_profile(job.user, tar, job.import_data)
+            if "include_user_settings" in job.required:
+                update_user_settings(job.user, job.import_data)
+            if "include_goals" in job.required:
+                update_goals(job.user, job.import_data.get("goals", []))
+            if "include_saved_lists" in job.required:
+                upsert_saved_lists(job.user, job.import_data.get("saved_lists", []))
+            if "include_follows" in job.required:
+                upsert_follows(job.user, job.import_data.get("follows", []))
+            if "include_blocks" in job.required:
+                upsert_user_blocks(job.user, job.import_data.get("blocks", []))
+
+            process_books(job, tar)
+
+            job.set_status("complete")
+        archive_file.close()
+
+    except Exception as err:  # pylint: disable=broad-except
+        logger.exception("User Import Job %s Failed with error: %s", job.id, err)
+        job.set_status("failed")
+
+
+def process_books(job, tar):
+    """
+    Process user import data related to books
+    We always import the books even if not assigning
+    them to shelves, lists etc
+    """
+
+    books = job.import_data.get("books")
+
+    for data in books:
+        book = get_or_create_edition(data, tar)
+
+        if "include_shelves" in job.required:
+            upsert_shelves(book, job.user, data)
+
+        if "include_readthroughs" in job.required:
+            upsert_readthroughs(data.get("readthroughs"), job.user, book.id)
+
+        if "include_comments" in job.required:
+            upsert_statuses(
+                job.user, models.Comment, data.get("comments"), book.remote_id
+            )
+        if "include_quotations" in job.required:
+            upsert_statuses(
+                job.user, models.Quotation, data.get("quotations"), book.remote_id
+            )
+
+        if "include_reviews" in job.required:
+            upsert_statuses(
+                job.user, models.Review, data.get("reviews"), book.remote_id
+            )
+
+        if "include_lists" in job.required:
+            upsert_lists(job.user, data.get("lists"), book.id)
+
+
+def get_or_create_edition(book_data, tar):
+    """Take a JSON string of work and edition data,
+    find or create the edition and work in the database and
+    return an edition instance"""
+
+    edition = book_data.get("edition")
+    existing = models.Edition.find_existing(edition)
+    if existing:
+        return existing
+
+    # make sure we have the authors in the local DB
+    # replace the old author ids in the edition JSON
+    edition["authors"] = []
+    for author in book_data.get("authors"):
+        parsed_author = activitypub.parse(author)
+        instance = parsed_author.to_model(
+            model=models.Author, save=True, overwrite=True
+        )
+
+        edition["authors"].append(instance.remote_id)
+
+    # we will add the cover later from the tar
+    # don't try to load it from the old server
+    cover = edition.get("cover", {})
+    cover_path = cover.get("url", None)
+    edition["cover"] = {}
+
+    # first we need the parent work to exist
+    work = book_data.get("work")
+    work["editions"] = []
+    parsed_work = activitypub.parse(work)
+    work_instance = parsed_work.to_model(model=models.Work, save=True, overwrite=True)
+
+    # now we have a work we can add it to the edition
+    # and create the edition model instance
+    edition["work"] = work_instance.remote_id
+    parsed_edition = activitypub.parse(edition)
+    book = parsed_edition.to_model(model=models.Edition, save=True, overwrite=True)
+
+    # set the cover image from the tar
+    if cover_path:
+        tar.write_image_to_file(cover_path, book.cover)
+
+    return book
+
+
+def upsert_readthroughs(data, user, book_id):
+    """Take a JSON string of readthroughs and
+    find or create the instances in the database"""
+
+    for read_through in data:
+
+        obj = {}
+        keys = [
+            "progress_mode",
+            "start_date",
+            "finish_date",
+            "stopped_date",
+            "is_active",
+        ]
+        for key in keys:
+            obj[key] = read_through[key]
+        obj["user_id"] = user.id
+        obj["book_id"] = book_id
+
+        existing = models.ReadThrough.objects.filter(**obj).first()
+        if not existing:
+            models.ReadThrough.objects.create(**obj)
+
+
+def upsert_statuses(user, cls, data, book_remote_id):
+    """Take a JSON string of a status and
+    find or create the instances in the database"""
+
+    for status in data:
+        if is_alias(
+            user, status["attributedTo"]
+        ):  # don't let l33t hax0rs steal other people's posts
+            # update ids and remove replies
+            status["attributedTo"] = user.remote_id
+            status["to"] = update_followers_address(user, status["to"])
+            status["cc"] = update_followers_address(user, status["cc"])
+            status[
+                "replies"
+            ] = (
+                {}
+            )  # this parses incorrectly but we can't set it without knowing the new id
+            status["inReplyToBook"] = book_remote_id
+            parsed = activitypub.parse(status)
+            if not status_already_exists(
+                user, parsed
+            ):  # don't duplicate posts on multiple import
+
+                instance = parsed.to_model(model=cls, save=True, overwrite=True)
+
+                for val in [
+                    "progress",
+                    "progress_mode",
+                    "position",
+                    "endposition",
+                    "position_mode",
+                ]:
+                    if status.get(val):
+                        instance.val = status[val]
+
+                instance.remote_id = instance.get_remote_id()  # update the remote_id
+                instance.save()  # save and broadcast
+
+        else:
+            logger.warning("User does not have permission to import statuses")
+
+
+def upsert_lists(user, lists, book_id):
+    """Take a list of objects each containing
+    a list and list item as AP objects
+
+    Because we are creating new IDs we can't assume the id
+    will exist or be accurate, so we only use to_model for
+    adding new items after checking whether they exist  .
+
+    """
+
+    book = models.Edition.objects.get(id=book_id)
+
+    for blist in lists:
+        booklist = models.List.objects.filter(name=blist["name"], user=user).first()
+        if not booklist:
+
+            blist["owner"] = user.remote_id
+            parsed = activitypub.parse(blist)
+            booklist = parsed.to_model(model=models.List, save=True, overwrite=True)
+
+            booklist.privacy = blist["privacy"]
+            booklist.save()
+
+        item = models.ListItem.objects.filter(book=book, book_list=booklist).exists()
+        if not item:
+            count = booklist.books.count()
+            models.ListItem.objects.create(
+                book=book,
+                book_list=booklist,
+                user=user,
+                notes=blist["list_item"]["notes"],
+                approved=blist["list_item"]["approved"],
+                order=count + 1,
+            )
+
+
+def upsert_shelves(book, user, book_data):
+    """Take shelf JSON objects and create
+    DB entries if they don't already exist"""
+
+    shelves = book_data["shelves"]
+    for shelf in shelves:
+
+        book_shelf = models.Shelf.objects.filter(name=shelf["name"], user=user).first()
+
+        if not book_shelf:
+            book_shelf = models.Shelf.objects.create(name=shelf["name"], user=user)
+
+        # add the book as a ShelfBook if needed
+        if not models.ShelfBook.objects.filter(
+            book=book, shelf=book_shelf, user=user
+        ).exists():
+            models.ShelfBook.objects.create(
+                book=book, shelf=book_shelf, user=user, shelved_date=timezone.now()
+            )
+
+
+def update_user_profile(user, tar, data):
+    """update the user's profile from import data"""
+    name = data.get("name", None)
+    username = data.get("preferredUsername")
+    user.name = name if name else username
+    user.summary = strip_tags(data.get("summary", None))
+    user.save(update_fields=["name", "summary"])
+    if data["icon"].get("url"):
+        avatar_filename = next(filter(lambda n: n.startswith("avatar"), tar.getnames()))
+        tar.write_image_to_file(avatar_filename, user.avatar)
+
+
+def update_user_settings(user, data):
+    """update the user's settings from import data"""
+
+    update_fields = ["manually_approves_followers", "hide_follows", "discoverable"]
+
+    ap_fields = [
+        ("manuallyApprovesFollowers", "manually_approves_followers"),
+        ("hideFollows", "hide_follows"),
+        ("discoverable", "discoverable"),
+    ]
+
+    for (ap_field, bw_field) in ap_fields:
+        setattr(user, bw_field, data[ap_field])
+
+    bw_fields = [
+        "show_goal",
+        "show_suggested_users",
+        "default_post_privacy",
+        "preferred_timezone",
+    ]
+
+    for field in bw_fields:
+        update_fields.append(field)
+        setattr(user, field, data["settings"][field])
+
+    user.save(update_fields=update_fields)
+
+
+@app.task(queue=IMPORTS, base=SubTask)
+def update_user_settings_task(job_id):
+    """wrapper task for user's settings import"""
+    parent_job = BookwyrmImportJob.objects.get(id=job_id)
+
+    return update_user_settings(parent_job.user, parent_job.import_data.get("user"))
+
+
+def update_goals(user, data):
+    """update the user's goals from import data"""
+
+    for goal in data:
+        # edit the existing goal if there is one
+        existing = models.AnnualGoal.objects.filter(
+            year=goal["year"], user=user
+        ).first()
+        if existing:
+            for k in goal.keys():
+                setattr(existing, k, goal[k])
+            existing.save()
+        else:
+            goal["user"] = user
+            models.AnnualGoal.objects.create(**goal)
+
+
+@app.task(queue=IMPORTS, base=SubTask)
+def update_goals_task(job_id):
+    """wrapper task for user's goals import"""
+    parent_job = BookwyrmImportJob.objects.get(id=job_id)
+
+    return update_goals(parent_job.user, parent_job.import_data.get("goals"))
+
+
+def upsert_saved_lists(user, values):
+    """Take a list of remote ids and add as saved lists"""
+
+    for remote_id in values:
+        book_list = activitypub.resolve_remote_id(remote_id, models.List)
+        if book_list:
+            user.saved_lists.add(book_list)
+
+
+@app.task(queue=IMPORTS, base=SubTask)
+def upsert_saved_lists_task(job_id):
+    """wrapper task for user's saved lists import"""
+    parent_job = BookwyrmImportJob.objects.get(id=job_id)
+
+    return upsert_saved_lists(
+        parent_job.user, parent_job.import_data.get("saved_lists")
+    )
+
+
+def upsert_follows(user, values):
+    """Take a list of remote ids and add as follows"""
+
+    for remote_id in values:
+        followee = activitypub.resolve_remote_id(remote_id, models.User)
+        if followee:
+            (follow_request, created,) = models.UserFollowRequest.objects.get_or_create(
+                user_subject=user,
+                user_object=followee,
+            )
+
+            if not created:
+                # this request probably failed to connect with the remote
+                # and should save to trigger a re-broadcast
+                follow_request.save()
+
+
+@app.task(queue=IMPORTS, base=SubTask)
+def upsert_follows_task(job_id):
+    """wrapper task for user's follows import"""
+    parent_job = BookwyrmImportJob.objects.get(id=job_id)
+
+    return upsert_follows(parent_job.user, parent_job.import_data.get("follows"))
+
+
+def upsert_user_blocks(user, user_ids):
+    """block users"""
+
+    for user_id in user_ids:
+        user_object = activitypub.resolve_remote_id(user_id, models.User)
+        if user_object:
+            exists = models.UserBlocks.objects.filter(
+                user_subject=user, user_object=user_object
+            ).exists()
+            if not exists:
+                models.UserBlocks.objects.create(
+                    user_subject=user, user_object=user_object
+                )
+                # remove the blocked users's lists from the groups
+                models.List.remove_from_group(user, user_object)
+                # remove the blocked user from all blocker's owned groups
+                models.GroupMember.remove(user, user_object)
+
+
+@app.task(queue=IMPORTS, base=SubTask)
+def upsert_user_blocks_task(job_id):
+    """wrapper task for user's blocks import"""
+    parent_job = BookwyrmImportJob.objects.get(id=job_id)
+
+    return upsert_user_blocks(
+        parent_job.user, parent_job.import_data.get("blocked_users")
+    )
+
+
+def update_followers_address(user, field):
+    """statuses to or cc followers need to have the followers
+    address updated to the new local user"""
+
+    for i, audience in enumerate(field):
+        if audience.rsplit("/")[-1] == "followers":
+            field[i] = user.followers_url
+
+    return field
+
+
+def is_alias(user, remote_id):
+    """check that the user is listed as movedTo or also_known_as
+    in the remote user's profile"""
+
+    remote_user = activitypub.resolve_remote_id(
+        remote_id=remote_id, model=models.User, save=False
+    )
+
+    if remote_user:
+
+        if remote_user.moved_to:
+            return user.remote_id == remote_user.moved_to
+
+        if remote_user.also_known_as:
+            return user in remote_user.also_known_as.all()
+
+    return False
+
+
+def status_already_exists(user, status):
+    """check whether this status has already been published
+    by this user. We can't rely on to_model() because it
+    only matches on remote_id, which we have to change
+    *after* saving because it needs the primary key (id)"""
+
+    return models.Status.objects.filter(
+        user=user, content=status.content, published_date=status.published
+    ).exists()

bookwyrm/models/connector.py

@@ -11,7 +11,7 @@ ConnectorFiles = models.TextChoices("ConnectorFiles", CONNECTORS)
 class Connector(BookWyrmModel):
     """book data source connectors"""
 
-    identifier = models.CharField(max_length=255, unique=True)
+    identifier = models.CharField(max_length=255, unique=True)  # domain
     priority = models.IntegerField(default=2)
     name = models.CharField(max_length=255, null=True, blank=True)
     connector_file = models.CharField(max_length=255, choices=ConnectorFiles.choices)

bookwyrm/models/federated_server.py

@@ -16,7 +16,7 @@ FederationStatus = [
 class FederatedServer(BookWyrmModel):
     """store which servers we federate with"""
 
-    server_name = models.CharField(max_length=255, unique=True)
+    server_name = models.CharField(max_length=255, unique=True)  # domain
     status = models.CharField(
         max_length=255, default="federated", choices=FederationStatus
     )
@@ -64,5 +64,4 @@ class FederatedServer(BookWyrmModel):
     def is_blocked(cls, url: str) -> bool:
         """look up if a domain is blocked"""
         url = urlparse(url)
-        domain = url.netloc
-        return cls.objects.filter(server_name=domain, status="blocked").exists()
+        return cls.objects.filter(server_name=url.hostname, status="blocked").exists()

bookwyrm/models/fields.py

@@ -260,12 +260,12 @@ class PrivacyField(ActivitypubFieldMixin, models.CharField):
 
         if to == [self.public]:
             setattr(instance, self.name, "public")
+        elif self.public in cc:
+            setattr(instance, self.name, "unlisted")
         elif to == [user.followers_url]:
             setattr(instance, self.name, "followers")
         elif cc == []:
             setattr(instance, self.name, "direct")
-        elif self.public in cc:
-            setattr(instance, self.name, "unlisted")
         else:
             setattr(instance, self.name, "followers")
         return original == getattr(instance, self.name)
@@ -482,7 +482,7 @@ class ImageField(ActivitypubFieldMixin, models.ImageField):
         if not url:
             return None
 
-        return activitypub.Document(url=url, name=alt)
+        return activitypub.Image(url=url, name=alt)
 
     def field_from_activity(self, value, allow_external_connections=True):
         image_slug = value

bookwyrm/models/group.py

@@ -1,7 +1,7 @@
 """ do book related things with other users """
 from django.db import models, IntegrityError, transaction
 from django.db.models import Q
-from bookwyrm.settings import DOMAIN
+from bookwyrm.settings import BASE_URL
 from .base_model import BookWyrmModel
 from . import fields
 from .relationship import UserBlocks
@@ -17,7 +17,7 @@ class Group(BookWyrmModel):
 
     def get_remote_id(self):
         """don't want the user to be in there in this case"""
-        return f"https://{DOMAIN}/group/{self.id}"
+        return f"{BASE_URL}/group/{self.id}"
 
     @classmethod
     def followers_filter(cls, queryset, viewer):

bookwyrm/models/hashtag.py

@@ -2,18 +2,19 @@
 from bookwyrm import activitypub
 from .activitypub_mixin import ActivitypubMixin
 from .base_model import BookWyrmModel
-from .fields import CICharField
+from .fields import CharField
 
 
 class Hashtag(ActivitypubMixin, BookWyrmModel):
     "a hashtag which can be used in statuses"
 
-    name = CICharField(
+    name = CharField(
         max_length=256,
         blank=False,
         null=False,
         activitypub_field="name",
         deduplication_field=True,
+        db_collation="case_insensitive",
     )
 
     name_field = "name"

bookwyrm/models/job.py

@@ -0,0 +1,307 @@
+"""Everything needed for Celery to multi-thread complex tasks."""
+
+from django.db import models
+from django.db import transaction
+from django.utils.translation import gettext_lazy as _
+from django.utils import timezone
+from bookwyrm.models.user import User
+
+from bookwyrm.tasks import app
+
+
+class Job(models.Model):
+    """Abstract model to store the state of a Task."""
+
+    class Status(models.TextChoices):
+        """Possible job states."""
+
+        PENDING = "pending", _("Pending")
+        ACTIVE = "active", _("Active")
+        COMPLETE = "complete", _("Complete")
+        STOPPED = "stopped", _("Stopped")
+        FAILED = "failed", _("Failed")
+
+    task_id = models.UUIDField(unique=True, null=True, blank=True)
+
+    created_date = models.DateTimeField(default=timezone.now)
+    updated_date = models.DateTimeField(default=timezone.now)
+    complete = models.BooleanField(default=False)
+    status = models.CharField(
+        max_length=50, choices=Status.choices, default=Status.PENDING, null=True
+    )
+
+    class Meta:
+        """Make it abstract"""
+
+        abstract = True
+
+    def complete_job(self):
+        """Report that the job has completed"""
+        if self.complete:
+            return
+
+        self.status = self.Status.COMPLETE
+        self.complete = True
+        self.updated_date = timezone.now()
+
+        self.save(update_fields=["status", "complete", "updated_date"])
+
+    def stop_job(self, reason=None):
+        """Stop the job"""
+        if self.complete:
+            return
+
+        self.__terminate_job()
+
+        if reason and reason == "failed":
+            self.status = self.Status.FAILED
+        else:
+            self.status = self.Status.STOPPED
+        self.complete = True
+        self.updated_date = timezone.now()
+
+        self.save(update_fields=["status", "complete", "updated_date"])
+
+    def set_status(self, status):
+        """Set job status"""
+        if self.complete:
+            return
+
+        if self.status == status:
+            return
+
+        if status == self.Status.COMPLETE:
+            self.complete_job()
+            return
+
+        if status == self.Status.STOPPED:
+            self.stop_job()
+            return
+
+        if status == self.Status.FAILED:
+            self.stop_job(reason="failed")
+            return
+
+        self.updated_date = timezone.now()
+        self.status = status
+
+        self.save(update_fields=["status", "updated_date"])
+
+    def __terminate_job(self):
+        """Tell workers to ignore and not execute this task."""
+        app.control.revoke(self.task_id, terminate=True)
+
+
+class ParentJob(Job):
+    """Store the state of a Task which can spawn many :model:`ChildJob`s to spread
+    resource load.
+
+    Intended to be sub-classed if necessary via proxy or
+    multi-table inheritance.
+    Extends :model:`Job`.
+    """
+
+    user = models.ForeignKey(User, on_delete=models.CASCADE)
+
+    def complete_job(self):
+        """Report that the job has completed and stop pending
+        children. Extend.
+        """
+        super().complete_job()
+        self.__terminate_pending_child_jobs()
+
+    def notify_child_job_complete(self):
+        """let the job know when the items get work done"""
+        if self.complete:
+            return
+
+        self.updated_date = timezone.now()
+        self.save(update_fields=["updated_date"])
+
+        if not self.complete and self.has_completed:
+            self.complete_job()
+
+    def __terminate_job(self):  # pylint: disable=unused-private-member
+        """Tell workers to ignore and not execute this task
+        & pending child tasks. Extend.
+        """
+        super().__terminate_job()
+        self.__terminate_pending_child_jobs()
+
+    def __terminate_pending_child_jobs(self):
+        """Tell workers to ignore and not execute any pending child tasks."""
+        tasks = self.pending_child_jobs.filter(task_id__isnull=False).values_list(
+            "task_id", flat=True
+        )
+        app.control.revoke(list(tasks))
+
+        self.pending_child_jobs.update(status=self.Status.STOPPED)
+
+    @property
+    def has_completed(self):
+        """has this job finished"""
+        return not self.pending_child_jobs.exists()
+
+    @property
+    def pending_child_jobs(self):
+        """items that haven't been processed yet"""
+        return self.child_jobs.filter(complete=False)
+
+
+class ChildJob(Job):
+    """Stores the state of a Task for the related :model:`ParentJob`.
+
+    Intended to be sub-classed if necessary via proxy or
+    multi-table inheritance.
+    Extends :model:`Job`.
+    """
+
+    parent_job = models.ForeignKey(
+        ParentJob, on_delete=models.CASCADE, related_name="child_jobs"
+    )
+
+    def set_status(self, status):
+        """Set job and parent_job status. Extend."""
+        super().set_status(status)
+
+        if (
+            status == self.Status.ACTIVE
+            and self.parent_job.status == self.Status.PENDING
+        ):
+            self.parent_job.set_status(self.Status.ACTIVE)
+
+    def complete_job(self):
+        """Report to parent_job that the job has completed. Extend."""
+        super().complete_job()
+        self.parent_job.notify_child_job_complete()
+
+
+class ParentTask(app.Task):
+    """Used with ParentJob, Abstract Tasks execute code at specific points in
+    a Task's lifecycle, applying to all Tasks with the same 'base'.
+
+    All status & ParentJob.task_id assignment is managed here for you.
+    Usage e.g. @app.task(base=ParentTask)
+    """
+
+    def before_start(
+        self, task_id, args, kwargs
+    ):  # pylint: disable=no-self-use, unused-argument
+        """Handler called before the task starts. Override.
+
+        Prepare ParentJob before the task starts.
+
+        Arguments:
+            task_id (str): Unique id of the task to execute.
+            args (Tuple): Original arguments for the task to execute.
+            kwargs (Dict): Original keyword arguments for the task to execute.
+
+        Keyword Arguments:
+            job_id (int): Unique 'id' of the ParentJob.
+            no_children (bool): If 'True' this is the only Task expected to run
+                for the given ParentJob.
+
+        Returns:
+            None: The return value of this handler is ignored.
+        """
+        job = ParentJob.objects.get(id=kwargs["job_id"])
+        job.task_id = task_id
+        job.save(update_fields=["task_id"])
+
+        if kwargs["no_children"]:
+            job.set_status(ChildJob.Status.ACTIVE)
+
+    def on_success(
+        self, retval, task_id, args, kwargs
+    ):  # pylint: disable=no-self-use, unused-argument
+        """Run by the worker if the task executes successfully. Override.
+
+        Update ParentJob on Task complete.
+
+        Arguments:
+            retval (Any): The return value of the task.
+            task_id (str): Unique id of the executed task.
+            args (Tuple): Original arguments for the executed task.
+            kwargs (Dict): Original keyword arguments for the executed task.
+
+        Keyword Arguments:
+            job_id (int): Unique 'id' of the ParentJob.
+            no_children (bool): If 'True' this is the only Task expected to run
+                for the given ParentJob.
+
+        Returns:
+            None: The return value of this handler is ignored.
+        """
+
+        if kwargs["no_children"]:
+            job = ParentJob.objects.get(id=kwargs["job_id"])
+            job.complete_job()
+
+
+class SubTask(app.Task):
+    """Used with ChildJob, Abstract Tasks execute code at specific points in
+    a Task's lifecycle, applying to all Tasks with the same 'base'.
+
+    All status & ChildJob.task_id assignment is managed here for you.
+    Usage e.g. @app.task(base=SubTask)
+    """
+
+    def before_start(
+        self, task_id, *args, **kwargs
+    ):  # pylint: disable=no-self-use, unused-argument
+        """Handler called before the task starts. Override.
+
+        Prepare ChildJob before the task starts.
+
+        Arguments:
+            task_id (str): Unique id of the task to execute.
+            args (Tuple): Original arguments for the task to execute.
+            kwargs (Dict): Original keyword arguments for the task to execute.
+
+        Keyword Arguments:
+            job_id (int): Unique 'id' of the ParentJob.
+            child_id (int): Unique 'id' of the ChildJob.
+
+        Returns:
+            None: The return value of this handler is ignored.
+        """
+        child_job = ChildJob.objects.get(id=kwargs["child_id"])
+        child_job.task_id = task_id
+        child_job.save(update_fields=["task_id"])
+        child_job.set_status(ChildJob.Status.ACTIVE)
+
+    def on_success(
+        self, retval, task_id, *args, **kwargs
+    ):  # pylint: disable=no-self-use, unused-argument
+        """Run by the worker if the task executes successfully. Override.
+
+        Notify ChildJob of task completion.
+
+        Arguments:
+            retval (Any): The return value of the task.
+            task_id (str): Unique id of the executed task.
+            args (Tuple): Original arguments for the executed task.
+            kwargs (Dict): Original keyword arguments for the executed task.
+
+        Keyword Arguments:
+            job_id (int): Unique 'id' of the ParentJob.
+            child_id (int): Unique 'id' of the ChildJob.
+
+        Returns:
+            None: The return value of this handler is ignored.
+        """
+        subtask = ChildJob.objects.get(id=kwargs["child_id"])
+        subtask.complete_job()
+
+
+@transaction.atomic
+def create_child_job(parent_job, task_callback):
+    """Utility method for creating a ChildJob
+    and running a task to avoid DB race conditions
+    """
+    child_job = ChildJob.objects.create(parent_job=parent_job)
+    transaction.on_commit(
+        lambda: task_callback.delay(job_id=parent_job.id, child_id=child_job.id)
+    )
+
+    return child_job

bookwyrm/models/link.py

@@ -1,4 +1,5 @@
 """ outlink data """
+from typing import Optional, Iterable
 from urllib.parse import urlparse
 
 from django.core.exceptions import PermissionDenied
@@ -6,6 +7,7 @@ from django.db import models
 from django.utils.translation import gettext_lazy as _
 
 from bookwyrm import activitypub
+from bookwyrm.utils.db import add_update_fields
 from .activitypub_mixin import ActivitypubMixin
 from .base_model import BookWyrmModel
 from . import fields
@@ -34,17 +36,19 @@ class Link(ActivitypubMixin, BookWyrmModel):
         """link name via the associated domain"""
         return self.domain.name
 
-    def save(self, *args, **kwargs):
+    def save(self, *args, update_fields: Optional[Iterable[str]] = None, **kwargs):
         """create a link"""
         # get or create the associated domain
         if not self.domain:
-            domain = urlparse(self.url).netloc
+            domain = urlparse(self.url).hostname
             self.domain, _ = LinkDomain.objects.get_or_create(domain=domain)
+            update_fields = add_update_fields(update_fields, "domain")
 
         # this is never broadcast, the owning model broadcasts an update
         if "broadcast" in kwargs:
             del kwargs["broadcast"]
-        return super().save(*args, **kwargs)
+
+        super().save(*args, update_fields=update_fields, **kwargs)
 
 
 AvailabilityChoices = [
@@ -88,8 +92,10 @@ class LinkDomain(BookWyrmModel):
             return
         raise PermissionDenied()
 
-    def save(self, *args, **kwargs):
+    def save(self, *args, update_fields: Optional[Iterable[str]] = None, **kwargs):
         """set a default name"""
         if not self.name:
             self.name = self.domain
-        super().save(*args, **kwargs)
+            update_fields = add_update_fields(update_fields, "name")
+
+        super().save(*args, update_fields=update_fields, **kwargs)

bookwyrm/models/list.py

@@ -1,4 +1,5 @@
 """ make a list of books!! """
+from typing import Optional, Iterable
 import uuid
 
 from django.core.exceptions import PermissionDenied
@@ -7,7 +8,8 @@ from django.db.models import Q
 from django.utils import timezone
 
 from bookwyrm import activitypub
-from bookwyrm.settings import DOMAIN
+from bookwyrm.settings import BASE_URL
+from bookwyrm.utils.db import add_update_fields
 
 from .activitypub_mixin import CollectionItemMixin, OrderedCollectionMixin
 from .base_model import BookWyrmModel
@@ -50,7 +52,7 @@ class List(OrderedCollectionMixin, BookWyrmModel):
 
     def get_remote_id(self):
         """don't want the user to be in there in this case"""
-        return f"https://{DOMAIN}/list/{self.id}"
+        return f"{BASE_URL}/list/{self.id}"
 
     @property
     def collection_queryset(self):
@@ -124,11 +126,13 @@ class List(OrderedCollectionMixin, BookWyrmModel):
             group=None, curation="closed"
         )
 
-    def save(self, *args, **kwargs):
+    def save(self, *args, update_fields: Optional[Iterable[str]] = None, **kwargs):
         """on save, update embed_key and avoid clash with existing code"""
         if not self.embed_key:
             self.embed_key = uuid.uuid4()
-        super().save(*args, **kwargs)
+            update_fields = add_update_fields(update_fields, "embed_key")
+
+        super().save(*args, update_fields=update_fields, **kwargs)
 
 
 class ListItem(CollectionItemMixin, BookWyrmModel):

bookwyrm/models/move.py

@@ -10,7 +10,7 @@ from .notification import Notification, NotificationType
 
 
 class Move(ActivityMixin, BookWyrmModel):
-    """migrating an activitypub user account"""
+    """migrating an activitypub object"""
 
     user = fields.ForeignKey(
         "User", on_delete=models.PROTECT, activitypub_field="actor"
@@ -48,24 +48,21 @@ class MoveUser(Move):
         """update user info and broadcast it"""
 
         # only allow if the source is listed in the target's alsoKnownAs
-        if self.user in self.target.also_known_as.all():
-            self.user.also_known_as.add(self.target.id)
-            self.user.update_active_date()
-            self.user.moved_to = self.target.remote_id
-            self.user.save(update_fields=["moved_to"])
-
-            if self.user.local:
-                kwargs[
-                    "broadcast"
-                ] = True  # Only broadcast if we are initiating the Move
-
-            super().save(*args, **kwargs)
-
-            for follower in self.user.followers.all():
-                if follower.local:
-                    Notification.notify(
-                        follower, self.user, notification_type=NotificationType.MOVE
-                    )
-
-        else:
+        if self.user not in self.target.also_known_as.all():
             raise PermissionDenied()
+
+        self.user.also_known_as.add(self.target.id)
+        self.user.update_active_date()
+        self.user.moved_to = self.target.remote_id
+        self.user.save(update_fields=["moved_to"])
+
+        if self.user.local:
+            kwargs["broadcast"] = True  # Only broadcast if we are initiating the Move
+
+        super().save(*args, **kwargs)
+
+        for follower in self.user.followers.all():
+            if follower.local:
+                Notification.notify(
+                    follower, self.user, notification_type=NotificationType.MOVE
+                )

bookwyrm/models/notification.py

@@ -1,8 +1,16 @@
 """ alert a user to activity """
 from django.db import models, transaction
 from django.dispatch import receiver
+from bookwyrm.models.bookwyrm_export_job import BookwyrmExportJob
 from .base_model import BookWyrmModel
-from . import Boost, Favorite, GroupMemberInvitation, ImportJob, LinkDomain
+from . import (
+    Boost,
+    Favorite,
+    GroupMemberInvitation,
+    ImportJob,
+    BookwyrmImportJob,
+    LinkDomain,
+)
 from . import ListItem, Report, Status, User, UserFollowRequest
 from .site import InviteRequest
 
@@ -23,6 +31,8 @@ class NotificationType(models.TextChoices):
 
     # Imports
     IMPORT = "IMPORT"
+    USER_IMPORT = "USER_IMPORT"
+    USER_EXPORT = "USER_EXPORT"
 
     # List activity
     ADD = "ADD"
@@ -63,6 +73,9 @@ class Notification(BookWyrmModel):
     )
     related_status = models.ForeignKey("Status", on_delete=models.CASCADE, null=True)
     related_import = models.ForeignKey("ImportJob", on_delete=models.CASCADE, null=True)
+    related_user_export = models.ForeignKey(
+        "BookwyrmExportJob", on_delete=models.CASCADE, null=True
+    )
     related_list_items = models.ManyToManyField(
         "ListItem", symmetrical=False, related_name="notifications"
     )
@@ -226,6 +239,36 @@ def notify_user_on_import_complete(
     )
 
 
+@receiver(models.signals.post_save, sender=BookwyrmImportJob)
+# pylint: disable=unused-argument
+def notify_user_on_user_import_complete(
+    sender, instance, *args, update_fields=None, **kwargs
+):
+    """we imported your user details! aren't you proud of us"""
+    update_fields = update_fields or []
+    if not instance.complete or "complete" not in update_fields:
+        return
+    Notification.objects.create(
+        user=instance.user, notification_type=NotificationType.USER_IMPORT
+    )
+
+
+@receiver(models.signals.post_save, sender=BookwyrmExportJob)
+# pylint: disable=unused-argument
+def notify_user_on_user_export_complete(
+    sender, instance, *args, update_fields=None, **kwargs
+):
+    """we exported your user details! aren't you proud of us"""
+    update_fields = update_fields or []
+    if not instance.complete or "complete" not in update_fields:
+        return
+    Notification.objects.create(
+        user=instance.user,
+        notification_type=NotificationType.USER_EXPORT,
+        related_user_export=instance,
+    )
+
+
 @receiver(models.signals.post_save, sender=Report)
 @transaction.atomic
 # pylint: disable=unused-argument

bookwyrm/models/readthrough.py

@@ -1,9 +1,13 @@
 """ progress in a book """
+from typing import Optional, Iterable
+
 from django.core import validators
 from django.core.cache import cache
 from django.db import models
 from django.db.models import F, Q
 
+from bookwyrm.utils.db import add_update_fields
+
 from .base_model import BookWyrmModel
 
 
@@ -30,14 +34,17 @@ class ReadThrough(BookWyrmModel):
     stopped_date = models.DateTimeField(blank=True, null=True)
     is_active = models.BooleanField(default=True)
 
-    def save(self, *args, **kwargs):
+    def save(self, *args, update_fields: Optional[Iterable[str]] = None, **kwargs):
         """update user active time"""
-        cache.delete(f"latest_read_through-{self.user_id}-{self.book_id}")
-        self.user.update_active_date()
         # an active readthrough must have an unset finish date
         if self.finish_date or self.stopped_date:
             self.is_active = False
-        super().save(*args, **kwargs)
+            update_fields = add_update_fields(update_fields, "is_active")
+
+        super().save(*args, update_fields=update_fields, **kwargs)
+
+        cache.delete(f"latest_read_through-{self.user_id}-{self.book_id}")
+        self.user.update_active_date()
 
     def create_update(self):
         """add update to the readthrough"""

bookwyrm/models/relationship.py

@@ -38,14 +38,16 @@ class UserRelationship(BookWyrmModel):
 
     def save(self, *args, **kwargs):
         """clear the template cache"""
-        clear_cache(self.user_subject, self.user_object)
         super().save(*args, **kwargs)
 
+        clear_cache(self.user_subject, self.user_object)
+
     def delete(self, *args, **kwargs):
         """clear the template cache"""
-        clear_cache(self.user_subject, self.user_object)
         super().delete(*args, **kwargs)
 
+        clear_cache(self.user_subject, self.user_object)
+
     class Meta:
         """relationships should be unique"""
 
@@ -65,6 +67,13 @@ class UserRelationship(BookWyrmModel):
         base_path = self.user_subject.remote_id
         return f"{base_path}#follows/{self.id}"
 
+    def get_accept_reject_id(self, status):
+        """get id for sending an accept or reject of a local user"""
+
+        base_path = self.user_object.remote_id
+        status_id = self.id or 0
+        return f"{base_path}#{status}/{status_id}"
+
 
 class UserFollows(ActivityMixin, UserRelationship):
     """Following a user"""
@@ -105,6 +114,20 @@ class UserFollows(ActivityMixin, UserRelationship):
         )
         return obj
 
+    def reject(self):
+        """generate a Reject for this follow. This would normally happen
+        when a user deletes a follow they previously accepted"""
+
+        if self.user_object.local:
+            activity = activitypub.Reject(
+                id=self.get_accept_reject_id(status="rejects"),
+                actor=self.user_object.remote_id,
+                object=self.to_activity(),
+            ).serialize()
+            self.broadcast(activity, self.user_object)
+
+        self.delete()
+
 
 class UserFollowRequest(ActivitypubMixin, UserRelationship):
     """following a user requires manual or automatic confirmation"""
@@ -148,13 +171,6 @@ class UserFollowRequest(ActivitypubMixin, UserRelationship):
             if not manually_approves:
                 self.accept()
 
-    def get_accept_reject_id(self, status):
-        """get id for sending an accept or reject of a local user"""
-
-        base_path = self.user_object.remote_id
-        status_id = self.id or 0
-        return f"{base_path}#{status}/{status_id}"
-
     def accept(self, broadcast_only=False):
         """turn this request into the real deal"""
         user = self.user_object

bookwyrm/models/report.py

@@ -3,7 +3,7 @@ from django.core.exceptions import PermissionDenied
 from django.db import models
 from django.utils.translation import gettext_lazy as _
 
-from bookwyrm.settings import DOMAIN
+from bookwyrm.settings import BASE_URL
 from .base_model import BookWyrmModel
 
 
@@ -46,7 +46,7 @@ class Report(BookWyrmModel):
         raise PermissionDenied()
 
     def get_remote_id(self):
-        return f"https://{DOMAIN}/settings/reports/{self.id}"
+        return f"{BASE_URL}/settings/reports/{self.id}"
 
     def comment(self, user, note):
         """comment on a report"""

bookwyrm/models/shelf.py

@@ -1,13 +1,15 @@
 """ puttin' books on shelves """
 import re
+from typing import Optional, Iterable
 from django.core.cache import cache
 from django.core.exceptions import PermissionDenied
 from django.db import models
 from django.utils import timezone
 
 from bookwyrm import activitypub
-from bookwyrm.settings import DOMAIN
+from bookwyrm.settings import BASE_URL
 from bookwyrm.tasks import BROADCAST
+from bookwyrm.utils.db import add_update_fields
 from .activitypub_mixin import CollectionItemMixin, OrderedCollectionMixin
 from .base_model import BookWyrmModel
 from . import fields
@@ -44,8 +46,9 @@ class Shelf(OrderedCollectionMixin, BookWyrmModel):
         """set the identifier"""
         super().save(*args, priority=priority, **kwargs)
         if not self.identifier:
+            # this needs the auto increment ID from the save() above
             self.identifier = self.get_identifier()
-            super().save(*args, **kwargs, broadcast=False)
+            super().save(*args, **kwargs, broadcast=False, update_fields={"identifier"})
 
     def get_identifier(self):
         """custom-shelf-123 for the url"""
@@ -71,7 +74,7 @@ class Shelf(OrderedCollectionMixin, BookWyrmModel):
     @property
     def local_path(self):
         """No slugs"""
-        return self.get_remote_id().replace(f"https://{DOMAIN}", "")
+        return self.get_remote_id().replace(BASE_URL, "")
 
     def raise_not_deletable(self, viewer):
         """don't let anyone delete a default shelf"""
@@ -100,10 +103,21 @@ class ShelfBook(CollectionItemMixin, BookWyrmModel):
     activity_serializer = activitypub.ShelfItem
     collection_field = "shelf"
 
-    def save(self, *args, priority=BROADCAST, **kwargs):
+    def save(
+        self,
+        *args,
+        priority=BROADCAST,
+        update_fields: Optional[Iterable[str]] = None,
+        **kwargs,
+    ):
         if not self.user:
             self.user = self.shelf.user
-        if self.id and self.user.local:
+            update_fields = add_update_fields(update_fields, "user")
+
+        is_update = self.id is not None
+        super().save(*args, priority=priority, update_fields=update_fields, **kwargs)
+
+        if is_update and self.user.local:
             # remove all caches related to all editions of this book
             cache.delete_many(
                 [
@@ -111,7 +125,6 @@ class ShelfBook(CollectionItemMixin, BookWyrmModel):
                     for book in self.book.parent_work.editions.all()
                 ]
             )
-        super().save(*args, priority=priority, **kwargs)
 
     def delete(self, *args, **kwargs):
         if self.id and self.user.local: