Refactor Snapshot and ArchiveResult to use ulid and typeid instead of uuidv4 (#1430)

Fixes: https://github.com/ArchiveBox/ArchiveBox/issues/74

.gitignore

@@ -29,6 +29,7 @@ dist/
 data/
 data*/
 output/
+index.sqlite3
 
 # vim
 *.sw?

archivebox/__init__.py

@@ -1,7 +1,4 @@
 __package__ = 'archivebox'
 
 
-# monkey patch django timezone to add back utc (it was removed in Django 5.0)
-import datetime
-from django.utils import timezone
-timezone.utc = datetime.timezone.utc
+from .monkey_patches import *

archivebox/abid_utils/__init__.py

@@ -0,0 +1 @@
+__package__ = 'abid_utils'

archivebox/abid_utils/abid.py

@@ -0,0 +1,191 @@
+from typing import NamedTuple, Any, Union, Optional
+
+import ulid
+import uuid6
+import hashlib
+from urllib.parse import urlparse
+
+from uuid import UUID
+from typeid import TypeID            # type: ignore[import-untyped]
+from datetime import datetime
+
+
+
+ABID_PREFIX_LEN = 4
+ABID_SUFFIX_LEN = 26
+ABID_LEN = 30
+ABID_TS_LEN = 10
+ABID_URI_LEN = 8
+ABID_SUBTYPE_LEN = 2
+ABID_RAND_LEN = 6
+
+DEFAULT_ABID_PREFIX = 'obj_'
+
+
+class ABID(NamedTuple):
+    """
+    e.g. ABID('obj_01HX9FPYTRE4A5CCD901ZYEBQE')
+    """
+    prefix: str            # e.g. obj_
+    ts: str                # e.g. 01HX9FPYTR
+    uri: str               # e.g. E4A5CCD9
+    subtype: str           # e.g. 01
+    rand: str              # e.g. ZYEBQE
+
+    def __getattr__(self, attr: str) -> Any:
+        return getattr(self.ulid, attr)
+
+    def __eq__(self, other: Any) -> bool:
+        try:
+            return self.ulid == other.ulid
+        except AttributeError:
+            return NotImplemented
+
+    def __str__(self) -> str:
+        return self.prefix + self.suffix
+
+    def __len__(self) -> int:
+        return len(self.prefix + self.suffix)
+
+    @classmethod
+    def parse(cls, buffer: Union[str, UUID, ulid.ULID, TypeID, 'ABID'], prefix=DEFAULT_ABID_PREFIX) -> 'ABID':
+        assert buffer, f'Attempted to create ABID from null value {buffer}'
+
+        buffer = str(buffer)
+        if '_' in buffer:
+            prefix, suffix = buffer.split('_')
+        else:
+            prefix, suffix = prefix.strip('_'), buffer
+
+        assert len(prefix) == ABID_PREFIX_LEN - 1   # length without trailing _
+        assert len(suffix) == ABID_SUFFIX_LEN, f'Suffix {suffix} from {buffer} was not {ABID_SUFFIX_LEN} chars long'
+
+        return cls(
+            prefix=abid_part_from_prefix(prefix),
+            ts=suffix[0:10].upper(),
+            uri=suffix[10:18].upper(),
+            subtype=suffix[18:20].upper(),
+            rand=suffix[20:26].upper(),
+        )
+
+    @property
+    def suffix(self):
+        return ''.join((self.ts, self.uri, self.subtype, self.rand))
+    
+    @property
+    def ulid(self) -> ulid.ULID:
+        return ulid.parse(self.suffix)
+
+    @property
+    def uuid(self) -> UUID:
+        return self.ulid.uuid
+
+    @property
+    def uuid6(self) -> uuid6.UUID:
+        return uuid6.UUID(hex=self.uuid.hex)
+
+    @property
+    def typeid(self) -> TypeID:
+        return TypeID.from_uuid(prefix=self.prefix.strip('_'), suffix=self.uuid6)
+
+    @property
+    def datetime(self) -> datetime:
+        return self.ulid.timestamp().datetime
+
+
+
+####################################################
+
+
+def uri_hash(uri: Union[str, bytes]) -> str:
+    """
+    'E4A5CCD9AF4ED2A6E0954DF19FD274E9CDDB4853051F033FD518BFC90AA1AC25'
+    """
+    if isinstance(uri, bytes):
+        uri_str: str = uri.decode()
+    else:
+        uri_str = uri
+
+    # only hash the domain part of URLs
+    if '://' in uri_str:
+        try:
+            domain = urlparse(uri_str).netloc
+            if domain:
+                uri_str = domain
+        except AttributeError:
+            pass
+    
+    uri_bytes = uri_str.encode('utf-8')
+
+    return hashlib.sha256(uri_bytes).hexdigest().upper()
+
+def abid_part_from_prefix(prefix: Optional[str]) -> str:
+    """
+    'snp_'
+    """
+    if prefix is None:
+        return 'obj_'
+
+    prefix = prefix.strip('_').lower()
+    assert len(prefix) == 3
+    return prefix + '_'
+
+def abid_part_from_uri(uri: str) -> str:
+    """
+    'E4A5CCD9'     # takes first 8 characters of sha256(url)
+    """
+    uri = str(uri)
+    return uri_hash(uri)[:ABID_URI_LEN]
+
+def abid_part_from_ts(ts: Optional[datetime]) -> str:
+    """
+    '01HX9FPYTR'   # produces 10 character Timestamp section of ulid based on added date
+    """
+    return str(ulid.from_timestamp(ts) if ts else ulid.new())[:ABID_TS_LEN]
+
+def abid_part_from_subtype(subtype: str) -> str:
+    """
+    Snapshots have 01 type, other objects have other subtypes like wget/media/etc.
+    Also allows us to change the ulid spec later by putting special sigil values here.
+    """
+    subtype = str(subtype)
+    if len(subtype) == ABID_SUBTYPE_LEN:
+        return subtype
+
+    return hashlib.sha256(subtype.encode('utf-8')).hexdigest()[:ABID_SUBTYPE_LEN].upper()
+
+def abid_part_from_rand(rand: Union[str, UUID, None, int]) -> str:
+    """
+    'ZYEBQE'   # takes last 6 characters of randomness from existing legacy uuid db field
+    """
+    if rand is None:
+        # if it's None we generate a new random 6 character hex string
+        return str(ulid.new())[-ABID_RAND_LEN:]
+    elif isinstance(rand, UUID):
+        # if it's a uuid we take the last 6 characters of the ULID represation of it
+        return str(ulid.from_uuid(rand))[-ABID_RAND_LEN:]
+    elif isinstance(rand, int):
+        # if it's a BigAutoInteger field we convert it from an int to a 0-padded string
+        rand_str = str(rand)[-ABID_RAND_LEN:]
+        padding_needed = ABID_RAND_LEN - len(rand_str)
+        rand_str = ('0'*padding_needed) + rand_str
+        return rand_str
+
+    # otherwise treat it as a string, take the last 6 characters of it verbatim
+    return str(rand)[-ABID_RAND_LEN:].upper()
+
+
+def abid_from_values(prefix, ts, uri, subtype, rand) -> ABID:
+    """
+    Return a freshly derived ABID (assembled from attrs defined in ABIDModel.abid_*_src).
+    """
+
+    abid = ABID(
+        prefix=abid_part_from_prefix(prefix),
+        ts=abid_part_from_ts(ts),
+        uri=abid_part_from_uri(uri),
+        subtype=abid_part_from_subtype(subtype),
+        rand=abid_part_from_rand(rand),
+    )
+    assert abid.ulid and abid.uuid and abid.typeid, f'Failed to calculate {prefix}_ABID for ts={ts} uri={uri} subtyp={subtype} rand={rand}'
+    return abid

archivebox/abid_utils/apps.py

@@ -0,0 +1,7 @@
+from django.apps import AppConfig
+
+
+class AbidUtilsConfig(AppConfig):
+    default_auto_field = 'django.db.models.BigAutoField'
+    
+    name = 'abid_utils'

archivebox/abid_utils/models.py

@@ -0,0 +1,314 @@
+"""
+This file provides the Django ABIDField and ABIDModel base model to inherit from.
+
+It implements the ArchiveBox ID (ABID) interfaces including abid_values, get_abid, .abid, .uuid, .id.
+"""
+
+from typing import Any, Dict, Union, List, Set, NamedTuple, cast
+
+from ulid import ULID
+from uuid import uuid4, UUID
+from typeid import TypeID            # type: ignore[import-untyped]
+from datetime import datetime
+from functools import partial
+from charidfield import CharIDField  # type: ignore[import-untyped]
+
+from django.conf import settings
+from django.db import models
+from django.db.utils import OperationalError
+from django.contrib.auth import get_user_model
+
+from django_stubs_ext.db.models import TypedModelMeta
+
+from .abid import (
+    ABID,
+    ABID_LEN,
+    ABID_RAND_LEN,
+    ABID_SUFFIX_LEN,
+    DEFAULT_ABID_PREFIX,
+    abid_part_from_prefix,
+    abid_from_values
+)
+
+####################################################
+
+
+# Database Field for typeid/ulid style IDs with a prefix, e.g. snp_01BJQMF54D093DXEAWZ6JYRPAQ
+ABIDField = partial(
+    CharIDField,
+    max_length=ABID_LEN,
+    help_text="ABID-format identifier for this entity (e.g. snp_01BJQMF54D093DXEAWZ6JYRPAQ)",
+    default=None,
+    null=True,
+    blank=True,
+    db_index=True,
+    unique=True,
+)
+
+def get_or_create_system_user_pk(username='system'):
+    """Get or create a system user with is_superuser=True to be the default owner for new DB rows"""
+
+    User = get_user_model()
+
+    # if only one user exists total, return that user
+    if User.objects.filter(is_superuser=True).count() == 1:
+        return User.objects.filter(is_superuser=True).values_list('pk', flat=True)[0]
+
+    # otherwise, create a dedicated "system" user
+    user, created = User.objects.get_or_create(username=username, is_staff=True, is_superuser=True, defaults={'email': '', 'password': ''})
+    return user.pk
+
+
+class ABIDModel(models.Model):
+    """
+    Abstract Base Model for other models to depend on. Provides ArchiveBox ID (ABID) interface.
+    """
+    abid_prefix: str = DEFAULT_ABID_PREFIX  # e.g. 'tag_'
+    abid_ts_src = 'None'                    # e.g. 'self.created'
+    abid_uri_src = 'None'                   # e.g. 'self.uri'
+    abid_subtype_src = 'None'               # e.g. 'self.extractor'
+    abid_rand_src = 'None'                  # e.g. 'self.uuid' or 'self.id'
+
+    id = models.UUIDField(primary_key=True, default=uuid4, editable=True)
+    uuid = models.UUIDField(blank=True, null=True, editable=True, unique=True)
+    abid = ABIDField(prefix=abid_prefix)
+
+    created_by = models.ForeignKey(settings.AUTH_USER_MODEL, on_delete=models.CASCADE, default=get_or_create_system_user_pk)
+    created = models.DateTimeField(auto_now_add=True)
+    modified = models.DateTimeField(auto_now=True)
+
+    class Meta(TypedModelMeta):
+        abstract = True
+
+    def save(self, *args: Any, **kwargs: Any) -> None:
+        if hasattr(self, 'abid'):
+            # self.abid = ABID.parse(self.abid) if self.abid else self.get_abid()
+            self.abid = self.get_abid()
+        else:
+            print(f'[!] WARNING: {self.__class__.__name__}.abid is not a DB field so ABID will not be persisted!')
+            self.abid = self.get_abid()
+        
+        super().save(*args, **kwargs)
+
+    @property
+    def abid_values(self) -> Dict[str, Any]:
+        return {
+            'prefix': self.abid_prefix,
+            'ts': eval(self.abid_ts_src),
+            'uri': eval(self.abid_uri_src),
+            'subtype': eval(self.abid_subtype_src),
+            'rand': eval(self.abid_rand_src),
+        }
+
+    def get_abid(self) -> ABID:
+        """
+        Return a freshly derived ABID (assembled from attrs defined in ABIDModel.abid_*_src).
+        """
+        prefix, ts, uri, subtype, rand = self.abid_values.values()
+
+        if (not prefix) or prefix == DEFAULT_ABID_PREFIX:
+            suggested_abid = self.__class__.__name__[:3].lower()
+            raise Exception(f'{self.__class__.__name__}.abid_prefix must be defined to calculate ABIDs (suggested: {suggested_abid})')
+
+        if not ts:
+            ts = datetime.utcfromtimestamp(0)
+            print(f'[!] WARNING: Generating ABID with ts=0000000000 placeholder because {self.__class__.__name__}.abid_ts_src={self.abid_ts_src} is unset!', ts.isoformat())
+
+        if not uri:
+            uri = str(self)
+            print(f'[!] WARNING: Generating ABID with uri=str(self) placeholder because {self.__class__.__name__}.abid_uri_src={self.abid_uri_src} is unset!', uri)
+
+        if not subtype:
+            subtype = self.__class__.__name__
+            print(f'[!] WARNING: Generating ABID with subtype={subtype} placeholder because {self.__class__.__name__}.abid_subtype_src={self.abid_subtype_src} is unset!', subtype)
+
+        if not rand:
+            rand = getattr(self, 'uuid', None) or getattr(self, 'id', None) or getattr(self, 'pk')
+            print(f'[!] WARNING: Generating ABID with rand=self.id placeholder because {self.__class__.__name__}.abid_rand_src={self.abid_rand_src} is unset!', rand)
+
+        abid = abid_from_values(
+            prefix=prefix,
+            ts=ts,
+            uri=uri,
+            subtype=subtype,
+            rand=rand,
+        )
+        assert abid.ulid and abid.uuid and abid.typeid, f'Failed to calculate {prefix}_ABID for {self.__class__.__name__}'
+        return abid
+
+    @property
+    def ABID(self) -> ABID:
+        """
+        ULIDParts(timestamp='01HX9FPYTR', url='E4A5CCD9', subtype='00', randomness='ZYEBQE')
+        """
+        return ABID.parse(self.abid) if getattr(self, 'abid', None) else self.get_abid()
+
+    @property
+    def ULID(self) -> ULID:
+        """
+        Get a ulid.ULID representation of the object's ABID.
+        """
+        return self.ABID.ulid
+
+    @property
+    def UUID(self) -> UUID:
+        """
+        Get a uuid.UUID (v4) representation of the object's ABID.
+        """
+        return self.ABID.uuid
+
+    @property
+    def TypeID(self) -> TypeID:
+        """
+        Get a typeid.TypeID (stripe-style) representation of the object's ABID.
+        """
+        return self.ABID.typeid
+
+
+
+####################################################
+
+# Django helpers
+def find_all_abid_prefixes() -> Dict[str, type[models.Model]]:
+    """
+    Return the mapping of all ABID prefixes to their models.
+    e.g. {'tag_': core.models.Tag, 'snp_': core.models.Snapshot, ...}
+    """
+    import django.apps
+    prefix_map = {}
+
+    for model in django.apps.apps.get_models():
+        abid_prefix = getattr(model, 'abid_prefix', None)
+        if abid_prefix:
+            prefix_map[abid_prefix] = model
+    return prefix_map
+
+def find_prefix_for_abid(abid: ABID) -> str:
+    """
+    Find the correct prefix for a given ABID that may have be missing a prefix (slow).
+    e.g. ABID('obj_01BJQMF54D093DXEAWZ6JYRPAQ') -> 'snp_'
+    """
+    # if existing abid prefix is correct, lookup is easy
+    model = find_model_from_abid(abid)
+    if model:
+        assert issubclass(model, ABIDModel)
+        return model.abid_prefix
+
+    # prefix might be obj_ or missing, fuzzy-search to find any object that matches
+    return find_obj_from_abid_rand(abid)[0].abid_prefix
+
+def find_model_from_abid_prefix(prefix: str) -> type[ABIDModel] | None:
+    """
+    Return the Django Model that corresponds to a given ABID prefix.
+    e.g. 'tag_' -> core.models.Tag
+    """
+    prefix = abid_part_from_prefix(prefix)
+
+    import django.apps
+
+    for model in django.apps.apps.get_models():
+        if not issubclass(model, ABIDModel): continue   # skip non-ABID-enabled models
+        if not hasattr(model, 'objects'): continue      # skip abstract models
+
+        if (model.abid_prefix == prefix):
+            return model
+
+    return None
+
+def find_model_from_abid(abid: ABID) -> type[models.Model] | None:
+    """
+    Shortcut for find_model_from_abid_prefix(abid.prefix)
+    """
+    return find_model_from_abid_prefix(abid.prefix)
+
+def find_obj_from_abid_rand(rand: Union[ABID, str], model=None) -> List[ABIDModel]:
+    """
+    Find an object corresponding to an ABID by exhaustively searching using its random suffix (slow).
+    e.g. 'obj_....................JYRPAQ' -> Snapshot('snp_01BJQMF54D093DXEAWZ6JYRPAQ')
+    """
+
+    # convert str to ABID if necessary
+    if isinstance(rand, ABID):
+        abid: ABID = rand
+    else:
+        rand = str(rand)
+        if len(rand) < ABID_SUFFIX_LEN:
+            padding_needed = ABID_SUFFIX_LEN - len(rand)
+            rand = ('0'*padding_needed) + rand
+        abid = ABID.parse(rand)
+
+    import django.apps
+
+    partial_matches: List[ABIDModel] = []
+
+    models_to_try = cast(Set[type[models.Model]], set(filter(bool, (
+        model,
+        find_model_from_abid(abid),
+        *django.apps.apps.get_models(),
+    ))))
+    # print(abid, abid.rand, abid.uuid, models_to_try)
+
+    for model in models_to_try:
+        if not issubclass(model, ABIDModel): continue   # skip Models that arent ABID-enabled
+        if not hasattr(model, 'objects'): continue      # skip abstract Models
+        assert hasattr(model, 'objects')                # force-fix for type hint nit about missing manager https://github.com/typeddjango/django-stubs/issues/1684
+
+        # continue on to try fuzzy searching by randomness portion derived from uuid field
+        try:
+            qs = []
+            if hasattr(model, 'abid'):
+                qs = model.objects.filter(abid__endswith=abid.rand)
+            elif hasattr(model, 'uuid'):
+                qs = model.objects.filter(uuid__endswith=str(abid.uuid)[-ABID_RAND_LEN:])
+            elif hasattr(model, 'id'):
+                # NOTE: this only works on SQLite where every column is a string
+                # other DB backends like postgres dont let you do __endswith if this is a BigAutoInteger field
+                
+                # try to search for uuid=...-2354352
+                # try to search for id=...2354352
+                # try to search for id=2354352
+                qs = model.objects.filter(
+                    models.Q(id__endswith=str(abid.uuid)[-ABID_RAND_LEN:])
+                    | models.Q(id__endswith=abid.rand)
+                    | models.Q(id__startswith=str(int(abid.rand)) if abid.rand.isdigit() else abid.rand)
+                )
+
+            for obj in qs:
+                if obj.get_abid() == abid:
+                    # found exact match, no need to keep iterating
+                    return [obj]
+                partial_matches.append(obj)
+        except OperationalError as err:
+            print(f'[!] WARNING: Got error while trying to iterate through QuerySet for {model}:', err, '\n')
+
+    return partial_matches
+
+def find_obj_from_abid(abid: ABID, model=None, fuzzy=False) -> Any:
+    """
+    Find an object with a given ABID by filtering possible models for a matching abid/uuid/id (fast).
+    e.g. 'snp_01BJQMF54D093DXEAWZ6JYRPAQ' -> Snapshot('snp_01BJQMF54D093DXEAWZ6JYRPAQ')
+    """
+
+    model = model or find_model_from_abid(abid)
+    assert model, f'Could not find model that could match this ABID type: {abid}'
+
+    try:
+        if hasattr(model, 'abid'):
+            return model.objects.get(abid__endswith=abid.suffix)
+        if hasattr(model, 'uuid'):
+            return model.objects.get(uuid=abid.uuid)
+        return model.objects.get(id=abid.uuid)
+    except model.DoesNotExist:
+        # if the model has an abid field then it shouldve matched, pointless to fuzzy search in that case
+        if hasattr(model, 'abid') or (not fuzzy):
+            raise
+
+    # continue on to try fuzzy searching by randomness portion derived from uuid field
+    match_by_rand = find_obj_from_abid_rand(abid, model=model)
+    if match_by_rand:
+        if match_by_rand[0].abid_prefix != abid.prefix:
+            print(f'[!] WARNING: fetched object {match_by_rand} even though prefix {abid.prefix} doesnt match!', abid, '\n')
+        return match_by_rand
+
+    raise model.DoesNotExist
+

archivebox/abid_utils/tests.py

@@ -0,0 +1,3 @@
+from django.test import TestCase
+
+# Create your tests here.

archivebox/api/apps.py

@@ -3,5 +3,9 @@ __package__ = 'archivebox.api'
 from django.apps import AppConfig
 
 
+
 class APIConfig(AppConfig):
     name = 'api'
+
+    def ready(self):
+        pass

archivebox/api/migrations/0003_outboundwebhook_apitoken_abid_apitoken_uuid_and_more.py

@@ -0,0 +1,60 @@
+# Generated by Django 5.0.6 on 2024-05-13 10:58
+
+import charidfield.fields
+import signal_webhooks.fields
+import signal_webhooks.utils
+import uuid
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('api', '0002_alter_apitoken_options'),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name='OutboundWebhook',
+            fields=[
+                ('name', models.CharField(db_index=True, help_text='Give your webhook a descriptive name (e.g. Notify ACME Slack channel of any new ArchiveResults).', max_length=255, unique=True, verbose_name='name')),
+                ('signal', models.CharField(choices=[('CREATE', 'Create'), ('UPDATE', 'Update'), ('DELETE', 'Delete'), ('M2M', 'M2M changed'), ('CREATE_OR_UPDATE', 'Create or Update'), ('CREATE_OR_DELETE', 'Create or Delete'), ('CREATE_OR_M2M', 'Create or M2M changed'), ('UPDATE_OR_DELETE', 'Update or Delete'), ('UPDATE_OR_M2M', 'Update or M2M changed'), ('DELETE_OR_M2M', 'Delete or M2M changed'), ('CREATE_UPDATE_OR_DELETE', 'Create, Update or Delete'), ('CREATE_UPDATE_OR_M2M', 'Create, Update or M2M changed'), ('CREATE_DELETE_OR_M2M', 'Create, Delete or M2M changed'), ('UPDATE_DELETE_OR_M2M', 'Update, Delete or M2M changed'), ('CREATE_UPDATE_DELETE_OR_M2M', 'Create, Update or Delete, or M2M changed')], help_text='The type of event the webhook should fire for (e.g. Create, Update, Delete).', max_length=255, verbose_name='signal')),
+                ('ref', models.CharField(db_index=True, help_text='Dot import notation of the model the webhook should fire for (e.g. core.models.Snapshot or core.models.ArchiveResult).', max_length=1023, validators=[signal_webhooks.utils.model_from_reference], verbose_name='referenced model')),
+                ('endpoint', models.URLField(help_text='External URL to POST the webhook notification to (e.g. https://someapp.example.com/webhook/some-webhook-receiver).', max_length=2047, verbose_name='endpoint')),
+                ('headers', models.JSONField(blank=True, default=dict, help_text='Headers to send with the webhook request.', validators=[signal_webhooks.utils.is_dict], verbose_name='headers')),
+                ('auth_token', signal_webhooks.fields.TokenField(blank=True, default='', help_text='Authentication token to use in an Authorization header.', max_length=8000, validators=[signal_webhooks.utils.decode_cipher_key], verbose_name='authentication token')),
+                ('enabled', models.BooleanField(default=True, help_text='Is this webhook enabled?', verbose_name='enabled')),
+                ('keep_last_response', models.BooleanField(default=False, help_text='Should the webhook keep a log of the latest response it got?', verbose_name='keep last response')),
+                ('created', models.DateTimeField(auto_now_add=True, help_text='When the webhook was created.', verbose_name='created')),
+                ('updated', models.DateTimeField(auto_now=True, help_text='When the webhook was last updated.', verbose_name='updated')),
+                ('last_response', models.CharField(blank=True, default='', help_text='Latest response to this webhook.', max_length=8000, verbose_name='last response')),
+                ('last_success', models.DateTimeField(default=None, help_text='When the webhook last succeeded.', null=True, verbose_name='last success')),
+                ('last_failure', models.DateTimeField(default=None, help_text='When the webhook last failed.', null=True, verbose_name='last failure')),
+                ('uuid', models.UUIDField(default=uuid.uuid4, primary_key=True, serialize=False)),
+                ('abid', charidfield.fields.CharIDField(blank=True, db_index=True, default=None, help_text='ABID-format identifier for this entity (e.g. snp_01BJQMF54D093DXEAWZ6JYRPAQ)', max_length=30, null=True, prefix='whk', unique=True)),
+            ],
+            options={
+                'verbose_name': 'API Outbound Webhook',
+                'abstract': False,
+            },
+        ),
+        migrations.AddField(
+            model_name='apitoken',
+            name='abid',
+            field=charidfield.fields.CharIDField(blank=True, db_index=True, default=None, help_text='ABID-format identifier for this entity (e.g. snp_01BJQMF54D093DXEAWZ6JYRPAQ)', max_length=30, null=True, prefix='apt', unique=True),
+        ),
+        migrations.AddField(
+            model_name='apitoken',
+            name='uuid',
+            field=models.UUIDField(blank=True, null=True, unique=True),
+        ),
+        migrations.AlterField(
+            model_name='apitoken',
+            name='id',
+            field=models.UUIDField(default=uuid.uuid4, primary_key=True, serialize=False),
+        ),
+        migrations.AddConstraint(
+            model_name='outboundwebhook',
+            constraint=models.UniqueConstraint(fields=('ref', 'endpoint'), name='prevent_duplicate_hooks_api_outboundwebhook'),
+        ),
+    ]

archivebox/api/migrations/0004_rename_user_apitoken_created_by_apitoken_modified_and_more.py

@@ -0,0 +1,58 @@
+# Generated by Django 5.0.6 on 2024-05-13 14:36
+
+import abid_utils.models
+import charidfield.fields
+import django.db.models.deletion
+from django.conf import settings
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('api', '0003_outboundwebhook_apitoken_abid_apitoken_uuid_and_more'),
+        migrations.swappable_dependency(settings.AUTH_USER_MODEL),
+    ]
+
+    operations = [
+        migrations.RenameField(
+            model_name='apitoken',
+            old_name='user',
+            new_name='created_by',
+        ),
+        migrations.AddField(
+            model_name='apitoken',
+            name='modified',
+            field=models.DateTimeField(auto_now=True),
+        ),
+        migrations.AddField(
+            model_name='outboundwebhook',
+            name='created_by',
+            field=models.ForeignKey(default=abid_utils.models.get_or_create_system_user_pk, on_delete=django.db.models.deletion.CASCADE, to=settings.AUTH_USER_MODEL),
+        ),
+        migrations.AddField(
+            model_name='outboundwebhook',
+            name='id',
+            field=models.UUIDField(blank=True, null=True, unique=True),
+        ),
+        migrations.AddField(
+            model_name='outboundwebhook',
+            name='modified',
+            field=models.DateTimeField(auto_now=True),
+        ),
+        migrations.AlterField(
+            model_name='apitoken',
+            name='abid',
+            field=charidfield.fields.CharIDField(blank=True, db_index=True, default=None, help_text='ABID-format identifier for this entity (e.g. snp_01BJQMF54D093DXEAWZ6JYRPAQ)', max_length=30, null=True, prefix='apt_', unique=True),
+        ),
+        migrations.AlterField(
+            model_name='outboundwebhook',
+            name='abid',
+            field=charidfield.fields.CharIDField(blank=True, db_index=True, default=None, help_text='ABID-format identifier for this entity (e.g. snp_01BJQMF54D093DXEAWZ6JYRPAQ)', max_length=30, null=True, prefix='whk_', unique=True),
+        ),
+        migrations.AlterField(
+            model_name='outboundwebhook',
+            name='created',
+            field=models.DateTimeField(auto_now_add=True),
+        ),
+    ]

archivebox/api/models.py

@@ -8,23 +8,40 @@ from django.conf import settings
 from django.db import models
 from django.utils import timezone
 
+from signal_webhooks.models import WebhookBase
+
 from django_stubs_ext.db.models import TypedModelMeta
 
+from abid_utils.models import ABIDModel, ABIDField
+
 
 def generate_secret_token() -> str:
     # returns cryptographically secure string with len() == 32
     return secrets.token_hex(16)
 
 
-class APIToken(models.Model):
-    id = models.UUIDField(primary_key=True, default=uuid.uuid4, editable=False)
+class APIToken(ABIDModel):
+    """
+    A secret key generated by a User that's used to authenticate REST API requests to ArchiveBox.
+    """
+    # ABID: apt_<created_ts>_<token_hash>_<user_id_hash>_<uuid_rand>
+    abid_prefix = 'apt_'
+    abid_ts_src = 'self.created'
+    abid_uri_src = 'self.token'
+    abid_subtype_src = 'self.user_id'
+    abid_rand_src = 'self.id'
 
-    user = models.ForeignKey(settings.AUTH_USER_MODEL, on_delete=models.CASCADE)
+    id = models.UUIDField(primary_key=True, default=uuid.uuid4, editable=True)
+    uuid = models.UUIDField(blank=True, null=True, editable=True, unique=True)
+    abid = ABIDField(prefix=abid_prefix)
+
+    created_by = models.ForeignKey(settings.AUTH_USER_MODEL, on_delete=models.CASCADE)
     token = models.CharField(max_length=32, default=generate_secret_token, unique=True)
     
     created = models.DateTimeField(auto_now_add=True)
     expires = models.DateTimeField(null=True, blank=True)
     
+
     class Meta(TypedModelMeta):
         verbose_name = "API Key"
         verbose_name_plural = "API Keys"
@@ -38,7 +55,8 @@ class APIToken(models.Model):
     def __json__(self) -> dict:
         return {
             "TYPE":             "APIToken",    
-            "id":               str(self.id),
+            "uuid":             str(self.id),
+            "abid":             str(self.get_abid()),
             "user_id":          str(self.user.id),
             "user_username":    self.user.username,
             "token":            self.token,
@@ -61,3 +79,37 @@ class APIToken(models.Model):
 
         return True
 
+
+
+
+
+
+# monkey patch django-signals-webhooks to change how it shows up in Admin UI
+
+class OutboundWebhook(ABIDModel, WebhookBase):
+    """
+    Model used in place of (extending) signals_webhooks.models.WebhookModel. Swapped using:
+        settings.SIGNAL_WEBHOOKS_CUSTOM_MODEL = 'api.models.OutboundWebhook'
+    """
+    abid_prefix = 'whk_'
+    abid_ts_src = 'self.created'
+    abid_uri_src = 'self.endpoint'
+    abid_subtype_src = 'self.ref'
+    abid_rand_src = 'self.id'
+
+    id = models.UUIDField(blank=True, null=True, unique=True, editable=True)
+    uuid = models.UUIDField(primary_key=True, default=uuid.uuid4, editable=True)
+    abid = ABIDField(prefix=abid_prefix)
+
+    WebhookBase._meta.get_field('name').help_text = (
+        'Give your webhook a descriptive name (e.g. Notify ACME Slack channel of any new ArchiveResults).')
+    WebhookBase._meta.get_field('signal').help_text = (
+        'The type of event the webhook should fire for (e.g. Create, Update, Delete).')
+    WebhookBase._meta.get_field('ref').help_text = (
+        'Dot import notation of the model the webhook should fire for (e.g. core.models.Snapshot or core.models.ArchiveResult).')
+    WebhookBase._meta.get_field('endpoint').help_text = (
+        'External URL to POST the webhook notification to (e.g. https://someapp.example.com/webhook/some-webhook-receiver).')
+
+    class Meta(WebhookBase.Meta):
+        verbose_name = 'API Outbound Webhook'
+

archivebox/api/v1_auth.py

@@ -47,6 +47,6 @@ def check_api_token(request, token_data: TokenAuthSchema):
         request=request,
     )
     if user:
-        return {"success": True, "user_id": str(user.id)}
+        return {"success": True, "user_id": str(user.pk)}
     
     return {"success": False, "user_id": None}

archivebox/api/v1_core.py

@@ -4,13 +4,14 @@ from uuid import UUID
 from typing import List, Optional
 from datetime import datetime
 
+from django.db.models import Q
 from django.shortcuts import get_object_or_404
 
 from ninja import Router, Schema, FilterSchema, Field, Query
 from ninja.pagination import paginate
 
 from core.models import Snapshot, ArchiveResult, Tag
-
+from abid_utils.abid import ABID
 
 router = Router(tags=['Core Models'])
 
@@ -20,24 +21,39 @@ router = Router(tags=['Core Models'])
 ### ArchiveResult #########################################################################
 
 class ArchiveResultSchema(Schema):
-    id: UUID
+    abid: str
+    uuid: UUID
+    pk: str
+    modified: datetime
+    created: datetime
+    created_by_id: str
 
-    snapshot_id: UUID
+    snapshot_abid: str
     snapshot_url: str
     snapshot_tags: str
 
     extractor: str
+    cmd_version: str
     cmd: List[str]
     pwd: str
-    cmd_version: str
-    output: str
     status: str
-
-    created: datetime
+    output: str
 
     @staticmethod
-    def resolve_id(obj):
-        return obj.uuid
+    def resolve_created_by_id(obj):
+        return str(obj.created_by_id)
+
+    @staticmethod
+    def resolve_pk(obj):
+        return str(obj.pk)
+
+    @staticmethod
+    def resolve_uuid(obj):
+        return str(obj.uuid)
+
+    @staticmethod
+    def resolve_abid(obj):
+        return str(obj.ABID)
 
     @staticmethod
     def resolve_created(obj):
@@ -47,18 +63,23 @@ class ArchiveResultSchema(Schema):
     def resolve_snapshot_url(obj):
         return obj.snapshot.url
 
+    @staticmethod
+    def resolve_snapshot_abid(obj):
+        return str(obj.snapshot.ABID)
+
     @staticmethod
     def resolve_snapshot_tags(obj):
         return obj.snapshot.tags_str()
 
 
 class ArchiveResultFilterSchema(FilterSchema):
-    id: Optional[UUID] = Field(None, q='uuid')
+    uuid: Optional[UUID] = Field(None, q='uuid')
+    # abid: Optional[str] = Field(None, q='abid')
 
     search: Optional[str] = Field(None, q=['snapshot__url__icontains', 'snapshot__title__icontains', 'snapshot__tags__name__icontains', 'extractor', 'output__icontains'])
-    snapshot_id: Optional[UUID] = Field(None, q='snapshot_id')
-    snapshot_url: Optional[str] = Field(None, q='snapshot__url')
-    snapshot_tag: Optional[str] = Field(None, q='snapshot__tags__name')
+    snapshot_uuid: Optional[UUID] = Field(None, q='snapshot_uuid__icontains')
+    snapshot_url: Optional[str] = Field(None, q='snapshot__url__icontains')
+    snapshot_tag: Optional[str] = Field(None, q='snapshot__tags__name__icontains')
     
     status: Optional[str] = Field(None, q='status')
     output: Optional[str] = Field(None, q='output__icontains')
@@ -75,6 +96,7 @@ class ArchiveResultFilterSchema(FilterSchema):
 @router.get("/archiveresults", response=List[ArchiveResultSchema])
 @paginate
 def list_archiveresults(request, filters: ArchiveResultFilterSchema = Query(...)):
+    """List all ArchiveResult entries matching these filters."""
     qs = ArchiveResult.objects.all()
     results = filters.filter(qs)
     return results
@@ -82,8 +104,8 @@ def list_archiveresults(request, filters: ArchiveResultFilterSchema = Query(...)
 
 @router.get("/archiveresult/{archiveresult_id}", response=ArchiveResultSchema)
 def get_archiveresult(request, archiveresult_id: str):
-    archiveresult = get_object_or_404(ArchiveResult, id=archiveresult_id)
-    return archiveresult
+    """Get a specific ArchiveResult by abid, uuid, or pk."""
+    return ArchiveResult.objects.get(Q(pk__icontains=archiveresult_id) | Q(abid__icontains=archiveresult_id) | Q(uuid__icontains=archiveresult_id))
 
 
 # @router.post("/archiveresult", response=ArchiveResultSchema)
@@ -115,27 +137,50 @@ def get_archiveresult(request, archiveresult_id: str):
 
 
 class SnapshotSchema(Schema):
-    id: UUID
+    abid: str
+    uuid: UUID
+    pk: str
+    modified: datetime
+    created: datetime
+    created_by_id: str
 
     url: str
     tags: str
     title: Optional[str]
     timestamp: str
-    bookmarked: datetime
-    added: datetime
-    updated: datetime
     archive_path: str
 
+    bookmarked: datetime
+    added: datetime
+    updated: Optional[datetime]
+
+    num_archiveresults: int
     archiveresults: List[ArchiveResultSchema]
 
-    # @staticmethod
-    # def resolve_id(obj):
-    #     return str(obj.id)
+    @staticmethod
+    def resolve_created_by_id(obj):
+        return str(obj.created_by_id)
+
+    @staticmethod
+    def resolve_pk(obj):
+        return str(obj.pk)
+
+    @staticmethod
+    def resolve_uuid(obj):
+        return str(obj.uuid)
+
+    @staticmethod
+    def resolve_abid(obj):
+        return str(obj.ABID)
 
     @staticmethod
     def resolve_tags(obj):
         return obj.tags_str()
 
+    @staticmethod
+    def resolve_num_archiveresults(obj, context):
+        return obj.archiveresult_set.all().distinct().count()
+
     @staticmethod
     def resolve_archiveresults(obj, context):
         if context['request'].with_archiveresults:
@@ -144,23 +189,32 @@ class SnapshotSchema(Schema):
 
 
 class SnapshotFilterSchema(FilterSchema):
-    id: Optional[UUID] = Field(None, q='id')
+    abid: Optional[str] = Field(None, q='abid__icontains')
+    uuid: Optional[str] = Field(None, q='uuid__icontains')
+    pk: Optional[str] = Field(None, q='pk__icontains')
+    created_by_id: str = Field(None, q='created_by_id__icontains')
+    created__gte: datetime = Field(None, q='created__gte')
+    created__lt: datetime = Field(None, q='created__lt')
+    created: datetime = Field(None, q='created')
+    modified: datetime = Field(None, q='modified')
+    modified__gte: datetime = Field(None, q='modified__gte')
+    modified__lt: datetime = Field(None, q='modified__lt')
 
-    search: Optional[str] = Field(None, q=['url__icontains', 'title__icontains', 'tags__name__icontains'])
+    search: Optional[str] = Field(None, q=['url__icontains', 'title__icontains', 'tags__name__icontains', 'abid__icontains', 'uuid__icontains'])
     url: Optional[str] = Field(None, q='url')
     tag: Optional[str] = Field(None, q='tags__name')
     title: Optional[str] = Field(None, q='title__icontains')
-    
     timestamp: Optional[str] = Field(None, q='timestamp__startswith')
     
-    added: Optional[datetime] = Field(None, q='added')
     added__gte: Optional[datetime] = Field(None, q='added__gte')
     added__lt: Optional[datetime] = Field(None, q='added__lt')
 
 
+
 @router.get("/snapshots", response=List[SnapshotSchema])
 @paginate
 def list_snapshots(request, filters: SnapshotFilterSchema = Query(...), with_archiveresults: bool=True):
+    """List all Snapshot entries matching these filters."""
     request.with_archiveresults = with_archiveresults
 
     qs = Snapshot.objects.all()
@@ -169,8 +223,24 @@ def list_snapshots(request, filters: SnapshotFilterSchema = Query(...), with_arc
 
 @router.get("/snapshot/{snapshot_id}", response=SnapshotSchema)
 def get_snapshot(request, snapshot_id: str, with_archiveresults: bool=True):
+    """Get a specific Snapshot by abid, uuid, or pk."""
     request.with_archiveresults = with_archiveresults
-    snapshot = get_object_or_404(Snapshot, id=snapshot_id)
+    snapshot = None
+    try:
+        snapshot = Snapshot.objects.get(Q(uuid__startswith=snapshot_id) | Q(abid__startswith=snapshot_id)| Q(pk__startswith=snapshot_id))
+    except Snapshot.DoesNotExist:
+        pass
+
+    try:
+        snapshot = snapshot or Snapshot.objects.get()
+    except Snapshot.DoesNotExist:
+        pass
+
+    try:
+        snapshot = snapshot or Snapshot.objects.get(Q(uuid__icontains=snapshot_id) | Q(abid__icontains=snapshot_id))
+    except Snapshot.DoesNotExist:
+        pass
+
     return snapshot
 
 
@@ -179,9 +249,9 @@ def get_snapshot(request, snapshot_id: str, with_archiveresults: bool=True):
 #     snapshot = Snapshot.objects.create(**payload.dict())
 #     return snapshot
 #
-# @router.put("/snapshot/{snapshot_id}", response=SnapshotSchema)
-# def update_snapshot(request, snapshot_id: str, payload: SnapshotSchema):
-#     snapshot = get_object_or_404(Snapshot, id=snapshot_id)
+# @router.put("/snapshot/{snapshot_uuid}", response=SnapshotSchema)
+# def update_snapshot(request, snapshot_uuid: str, payload: SnapshotSchema):
+#     snapshot = get_object_or_404(Snapshot, uuid=snapshot_uuid)
 #
 #     for attr, value in payload.dict().items():
 #         setattr(snapshot, attr, value)
@@ -189,9 +259,9 @@ def get_snapshot(request, snapshot_id: str, with_archiveresults: bool=True):
 #
 #     return snapshot
 #
-# @router.delete("/snapshot/{snapshot_id}")
-# def delete_snapshot(request, snapshot_id: str):
-#     snapshot = get_object_or_404(Snapshot, id=snapshot_id)
+# @router.delete("/snapshot/{snapshot_uuid}")
+# def delete_snapshot(request, snapshot_uuid: str):
+#     snapshot = get_object_or_404(Snapshot, uuid=snapshot_uuid)
 #     snapshot.delete()
 #     return {"success": True}
 
@@ -201,10 +271,21 @@ def get_snapshot(request, snapshot_id: str, with_archiveresults: bool=True):
 
 
 class TagSchema(Schema):
+    abid: Optional[UUID] = Field(None, q='abid')
+    uuid: Optional[UUID] = Field(None, q='uuid')
+    pk: Optional[UUID] = Field(None, q='pk')
+    modified: datetime
+    created: datetime
+    created_by_id: str
+
     name: str
     slug: str
 
 
+    @staticmethod
+    def resolve_created_by_id(obj):
+        return str(obj.created_by_id)
+
 @router.get("/tags", response=List[TagSchema])
 def list_tags(request):
     return Tag.objects.all()

archivebox/cli/__init__.py

@@ -37,7 +37,10 @@ is_valid_cli_module = lambda module, subcommand: (
 )
 
 
-def wait_for_bg_threads_to_exit(thread_names: Iterable[str]=(), ignore_names: Iterable[str]=('MainThread', 'ThreadPoolExecutor'), timeout: int=60) -> int:
+IGNORED_BG_THREADS = ('MainThread', 'ThreadPoolExecutor', 'IPythonHistorySavingThread')  # threads we dont have to wait for before exiting
+
+
+def wait_for_bg_threads_to_exit(thread_names: Iterable[str]=(), ignore_names: Iterable[str]=IGNORED_BG_THREADS, timeout: int=60) -> int:
     """
     Block until the specified threads exit. e.g. pass thread_names=('default_hook_handler',) to wait for webhooks.
     Useful for waiting for signal handlers, webhooks, etc. to finish running after a mgmt command completes.

archivebox/config.py

@@ -37,7 +37,7 @@ from sqlite3 import dbapi2 as sqlite3
 from hashlib import md5
 from pathlib import Path
 from datetime import datetime, timezone
-from typing import Optional, Type, Tuple, Dict, Union, List
+from typing import Optional, Type, Tuple, Dict, Union, List, Any
 from subprocess import run, PIPE, DEVNULL
 from configparser import ConfigParser
 from collections import defaultdict

archivebox/core/admin.py

@@ -15,8 +15,7 @@ from django.contrib.auth import get_user_model
 from django import forms
 
 
-from signal_webhooks.apps import DjangoSignalWebhooksConfig
-from signal_webhooks.admin import WebhookAdmin, WebhookModel
+from signal_webhooks.admin import WebhookAdmin, get_webhook_model
 
 from ..util import htmldecode, urldecode, ansi_to_html
 
@@ -104,23 +103,14 @@ class ArchiveBoxAdmin(admin.AdminSite):
         return render(template_name='add.html', request=request, context=context)
 
 
-# monkey patch django-signals-webhooks to change how it shows up in Admin UI
-DjangoSignalWebhooksConfig.verbose_name = 'API'
-WebhookModel._meta.get_field('name').help_text = 'Give your webhook a descriptive name (e.g. Notify ACME Slack channel of any new ArchiveResults).'
-WebhookModel._meta.get_field('signal').help_text = 'The type of event the webhook should fire for (e.g. Create, Update, Delete).'
-WebhookModel._meta.get_field('ref').help_text = 'Dot import notation of the model the webhook should fire for (e.g. core.models.Snapshot or core.models.ArchiveResult).'
-WebhookModel._meta.get_field('endpoint').help_text = 'External URL to POST the webhook notification to (e.g. https://someapp.example.com/webhook/some-webhook-receiver).'
-WebhookModel._meta.app_label = 'api'
-
-
 archivebox_admin = ArchiveBoxAdmin()
 archivebox_admin.register(get_user_model())
 archivebox_admin.register(APIToken)
-archivebox_admin.register(WebhookModel, WebhookAdmin)
+archivebox_admin.register(get_webhook_model(), WebhookAdmin)
 archivebox_admin.disable_action('delete_selected')
 
 
-# patch admin with methods to add data views
+# patch admin with methods to add data views (implemented by admin_data_views package)
 from admin_data_views.admin import get_app_list, admin_data_index_view, get_admin_data_urls, get_urls
 
 archivebox_admin.get_app_list = get_app_list.__get__(archivebox_admin, ArchiveBoxAdmin)
@@ -170,14 +160,41 @@ class SnapshotActionForm(ActionForm):
     # )
 
 
+def get_abid_info(self, obj):
+    return format_html(
+        # URL Hash: <code style="font-size: 10px; user-select: all">{}</code><br/>
+        '''
+        &nbsp; &nbsp; ABID:&nbsp; <code style="font-size: 16px; user-select: all"><b>{}</b></code><br/>
+        &nbsp; &nbsp; TS: &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;<code style="font-size: 10px; user-select: all"><b>{}</b></code> ({})<br/>
+        &nbsp; &nbsp; URI: &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <code style="font-size: 10px; user-select: all"><b>{}</b></code> ({})<br/>
+        &nbsp; &nbsp; SUBTYPE: &nbsp; &nbsp; &nbsp; <code style="font-size: 10px; user-select: all"><b>{}</b></code> ({})<br/>
+        &nbsp; &nbsp; RAND: &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;&nbsp; <code style="font-size: 10px; user-select: all"><b>{}</b></code> ({})<br/><br/>
+        &nbsp; &nbsp; ABID AS UUID:&nbsp; <code style="font-size: 10px; user-select: all">{}</code> &nbsp; &nbsp;<br/><br/>
+
+        &nbsp; &nbsp; .uuid: &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <code style="font-size: 10px; user-select: all">{}</code> &nbsp; &nbsp;<br/>
+        &nbsp; &nbsp; .id: &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;&nbsp; <code style="font-size: 10px; user-select: all">{}</code> &nbsp; &nbsp;<br/>
+        &nbsp; &nbsp; .pk: &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <code style="font-size: 10px; user-select: all">{}</code> &nbsp; &nbsp;<br/><br/>
+        ''',
+        obj.abid,
+        obj.ABID.ts, obj.abid_values['ts'].isoformat() if isinstance(obj.abid_values['ts'], datetime) else obj.abid_values['ts'],
+        obj.ABID.uri, str(obj.abid_values['uri']),
+        obj.ABID.subtype, str(obj.abid_values['subtype']),
+        obj.ABID.rand, str(obj.abid_values['rand'])[-7:],
+        obj.ABID.uuid,
+        obj.uuid,
+        obj.id,
+        obj.pk,
+    )
+
+
 @admin.register(Snapshot, site=archivebox_admin)
 class SnapshotAdmin(SearchResultsAdminMixin, admin.ModelAdmin):
     list_display = ('added', 'title_str', 'files', 'size', 'url_str')
     sort_fields = ('title_str', 'url_str', 'added', 'files')
-    readonly_fields = ('info', 'bookmarked', 'added', 'updated')
-    search_fields = ('id', 'url', 'timestamp', 'title', 'tags__name')
-    fields = ('timestamp', 'url', 'title', 'tags', *readonly_fields)
-    list_filter = ('added', 'updated', 'tags', 'archiveresult__status')
+    readonly_fields = ('admin_actions', 'status_info', 'bookmarked', 'added', 'updated', 'created', 'modified', 'identifiers')
+    search_fields = ('id', 'url', 'abid', 'uuid', 'timestamp', 'title', 'tags__name')
+    fields = ('url', 'timestamp', 'created_by', 'tags', 'title', *readonly_fields)
+    list_filter = ('added', 'updated', 'tags', 'archiveresult__status', 'created_by')
     ordering = ['-added']
     actions = ['add_tags', 'remove_tags', 'update_titles', 'update_snapshots', 'resnapshot_snapshot', 'overwrite_snapshots', 'delete_snapshots']
     autocomplete_fields = ['tags']
@@ -223,40 +240,46 @@ class SnapshotAdmin(SearchResultsAdminMixin, admin.ModelAdmin):
     #             </form>
     #         ''',
     #         csrf.get_token(self.request),
-    #         obj.id,
+    #         obj.pk,
     #     )
 
-    def info(self, obj):
+    def admin_actions(self, obj):
         return format_html(
+            # URL Hash: <code style="font-size: 10px; user-select: all">{}</code><br/>
+            '''
+            <a class="btn" style="font-size: 18px; display: inline-block; border-radius: 10px; border: 3px solid #eee; padding: 4px 8px" href="/archive/{}">Summary page ➡️</a> &nbsp; &nbsp;
+            <a class="btn" style="font-size: 18px; display: inline-block; border-radius: 10px; border: 3px solid #eee; padding: 4px 8px" href="/archive/{}/index.html#all">Result files 📑</a> &nbsp; &nbsp;
+            <a class="btn" style="font-size: 18px; display: inline-block; border-radius: 10px; border: 3px solid #eee; padding: 4px 8px" href="/admin/core/snapshot/?id__exact={}">Admin actions ⚙️</a>
+            ''',
+            obj.timestamp,
+            obj.timestamp,
+            obj.pk,
+        )
+
+    def status_info(self, obj):
+        return format_html(
+            # URL Hash: <code style="font-size: 10px; user-select: all">{}</code><br/>
             '''
-            UUID: <code style="font-size: 10px; user-select: all">{}</code> &nbsp; &nbsp;
-            Timestamp: <code style="font-size: 10px; user-select: all">{}</code> &nbsp; &nbsp;
-            URL Hash: <code style="font-size: 10px; user-select: all">{}</code><br/>
             Archived: {} ({} files {}) &nbsp; &nbsp;
             Favicon: <img src="{}" style="height: 20px"/> &nbsp; &nbsp;
-            Status code: {} &nbsp; &nbsp;
+            Status code: {} &nbsp; &nbsp;<br/>
             Server: {} &nbsp; &nbsp;
             Content type: {} &nbsp; &nbsp;
             Extension: {} &nbsp; &nbsp;
-            <br/><br/>
-            <a href="/archive/{}">View Snapshot index ➡️</a> &nbsp; &nbsp;
-            <a href="/admin/core/snapshot/?id__exact={}">View actions ⚙️</a>
             ''',
-            obj.id,
-            obj.timestamp,
-            obj.url_hash,
             '✅' if obj.is_archived else '❌',
             obj.num_outputs,
-            self.size(obj),
+            self.size(obj) or '0kb',
             f'/archive/{obj.timestamp}/favicon.ico',
-            obj.status_code or '?',
-            obj.headers and obj.headers.get('Server') or '?',
-            obj.headers and obj.headers.get('Content-Type') or '?',
-            obj.extension or '?',
-            obj.timestamp,
-            obj.id,
+            obj.status_code or '-',
+            obj.headers and obj.headers.get('Server') or '-',
+            obj.headers and obj.headers.get('Content-Type') or '-',
+            obj.extension or '-',
         )
 
+    def identifiers(self, obj):
+        return get_abid_info(self, obj)
+
     @admin.display(
         description='Title',
         ordering='title',
@@ -316,7 +339,7 @@ class SnapshotAdmin(SearchResultsAdminMixin, admin.ModelAdmin):
         return format_html(
             '<a href="{}"><code style="user-select: all;">{}</code></a>',
             obj.url,
-            obj.url,
+            obj.url[:128],
         )
 
     def grid_view(self, request, extra_context=None):
@@ -419,42 +442,45 @@ class SnapshotAdmin(SearchResultsAdminMixin, admin.ModelAdmin):
 
 @admin.register(Tag, site=archivebox_admin)
 class TagAdmin(admin.ModelAdmin):
-    list_display = ('slug', 'name', 'num_snapshots', 'snapshots', 'id')
-    sort_fields = ('id', 'name', 'slug')
-    readonly_fields = ('id', 'num_snapshots', 'snapshots')
-    search_fields = ('id', 'name', 'slug')
-    fields = (*readonly_fields, 'name', 'slug')
+    list_display = ('slug', 'name', 'num_snapshots', 'snapshots', 'abid')
+    sort_fields = ('id', 'name', 'slug', 'abid')
+    readonly_fields = ('created', 'modified', 'identifiers', 'num_snapshots', 'snapshots')
+    search_fields = ('id', 'abid', 'uuid', 'name', 'slug')
+    fields = ('name', 'slug', 'created_by', *readonly_fields, )
     actions = ['delete_selected']
     ordering = ['-id']
 
-    def num_snapshots(self, obj):
+    def identifiers(self, obj):
+        return get_abid_info(self, obj)
+
+    def num_snapshots(self, tag):
         return format_html(
             '<a href="/admin/core/snapshot/?tags__id__exact={}">{} total</a>',
-            obj.id,
-            obj.snapshot_set.count(),
+            tag.id,
+            tag.snapshot_set.count(),
         )
 
-    def snapshots(self, obj):
-        total_count = obj.snapshot_set.count()
+    def snapshots(self, tag):
+        total_count = tag.snapshot_set.count()
         return mark_safe('<br/>'.join(
             format_html(
                 '{} <code><a href="/admin/core/snapshot/{}/change"><b>[{}]</b></a> {}</code>',
                 snap.updated.strftime('%Y-%m-%d %H:%M') if snap.updated else 'pending...',
-                snap.id,
-                snap.timestamp,
+                snap.pk,
+                snap.abid,
                 snap.url,
             )
-            for snap in obj.snapshot_set.order_by('-updated')[:10]
-        ) + (f'<br/><a href="/admin/core/snapshot/?tags__id__exact={obj.id}">and {total_count-10} more...<a>' if obj.snapshot_set.count() > 10 else ''))
+            for snap in tag.snapshot_set.order_by('-updated')[:10]
+        ) + (f'<br/><a href="/admin/core/snapshot/?tags__id__exact={tag.id}">and {total_count-10} more...<a>' if tag.snapshot_set.count() > 10 else ''))
 
 
 @admin.register(ArchiveResult, site=archivebox_admin)
 class ArchiveResultAdmin(admin.ModelAdmin):
-    list_display = ('id', 'start_ts', 'extractor', 'snapshot_str', 'tags_str', 'cmd_str', 'status', 'output_str')
+    list_display = ('start_ts', 'snapshot_info', 'tags_str', 'extractor', 'cmd_str', 'status', 'output_str')
     sort_fields = ('start_ts', 'extractor', 'status')
-    readonly_fields = ('id', 'uuid', 'snapshot_str', 'tags_str')
-    search_fields = ('id', 'uuid', 'snapshot__url', 'extractor', 'output', 'cmd_version', 'cmd', 'snapshot__timestamp')
-    fields = (*readonly_fields, 'snapshot', 'extractor', 'status', 'start_ts', 'end_ts', 'output', 'pwd', 'cmd', 'cmd_version')
+    readonly_fields = ('snapshot_info', 'tags_str', 'created_by', 'created', 'modified', 'identifiers')
+    search_fields = ('id', 'uuid', 'abid', 'snapshot__url', 'extractor', 'output', 'cmd_version', 'cmd', 'snapshot__timestamp')
+    fields = ('snapshot', 'extractor', 'status', 'output', 'pwd', 'cmd',  'start_ts', 'end_ts', 'cmd_version', *readonly_fields)
     autocomplete_fields = ['snapshot']
 
     list_filter = ('status', 'extractor', 'start_ts', 'cmd_version')
@@ -462,33 +488,36 @@ class ArchiveResultAdmin(admin.ModelAdmin):
     list_per_page = SNAPSHOTS_PER_PAGE
 
     @admin.display(
-        description='snapshot'
+        description='Snapshot Info'
     )
-    def snapshot_str(self, obj):
+    def snapshot_info(self, result):
         return format_html(
-            '<a href="/archive/{}/index.html"><b><code>[{}]</code></b></a><br/>'
-            '<small>{}</small>',
-            obj.snapshot.timestamp,
-            obj.snapshot.timestamp,
-            obj.snapshot.url[:128],
+            '<a href="/archive/{}/index.html"><b><code>[{}]</code></b> &nbsp; {} &nbsp; {}</a><br/>',
+            result.snapshot.timestamp,
+            result.snapshot.abid,
+            result.snapshot.added.strftime('%Y-%m-%d %H:%M'),
+            result.snapshot.url[:128],
         )
 
+    def identifiers(self, obj):
+        return get_abid_info(self, obj)
+
     @admin.display(
-        description='tags'
+        description='Snapshot Tags'
     )
-    def tags_str(self, obj):
-        return obj.snapshot.tags_str()
+    def tags_str(self, result):
+        return result.snapshot.tags_str()
 
-    def cmd_str(self, obj):
+    def cmd_str(self, result):
         return format_html(
             '<pre>{}</pre>',
-            ' '.join(obj.cmd) if isinstance(obj.cmd, list) else str(obj.cmd),
+            ' '.join(result.cmd) if isinstance(result.cmd, list) else str(result.cmd),
         )
 
-    def output_str(self, obj):
+    def output_str(self, result):
         return format_html(
             '<a href="/archive/{}/{}" class="output-link">↗️</a><pre>{}</pre>',
-            obj.snapshot.timestamp,
-            obj.output if (obj.status == 'succeeded') and obj.extractor not in ('title', 'archive_org') else 'index.html',
-            obj.output,
+            result.snapshot.timestamp,
+            result.output if (result.status == 'succeeded') and result.extractor not in ('title', 'archive_org') else 'index.html',
+            result.output,
         )

archivebox/core/migrations/0023_alter_archiveresult_options_archiveresult_abid_and_more.py

@@ -0,0 +1,43 @@
+# Generated by Django 5.0.6 on 2024-05-13 10:56
+
+import charidfield.fields
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('core', '0022_auto_20231023_2008'),
+    ]
+
+    operations = [
+        migrations.AlterModelOptions(
+            name='archiveresult',
+            options={'verbose_name': 'Result'},
+        ),
+        migrations.AddField(
+            model_name='archiveresult',
+            name='abid',
+            field=charidfield.fields.CharIDField(blank=True, db_index=True, default=None, help_text='ABID-format identifier for this entity (e.g. snp_01BJQMF54D093DXEAWZ6JYRPAQ)', max_length=30, null=True, prefix='res_', unique=True),
+        ),
+        migrations.AddField(
+            model_name='snapshot',
+            name='abid',
+            field=charidfield.fields.CharIDField(blank=True, db_index=True, default=None, help_text='ABID-format identifier for this entity (e.g. snp_01BJQMF54D093DXEAWZ6JYRPAQ)', max_length=30, null=True, prefix='snp_', unique=True),
+        ),
+        migrations.AddField(
+            model_name='snapshot',
+            name='uuid',
+            field=models.UUIDField(blank=True, null=True, unique=True),
+        ),
+        migrations.AddField(
+            model_name='tag',
+            name='abid',
+            field=charidfield.fields.CharIDField(blank=True, db_index=True, default=None, help_text='ABID-format identifier for this entity (e.g. snp_01BJQMF54D093DXEAWZ6JYRPAQ)', max_length=30, null=True, prefix='tag_', unique=True),
+        ),
+        migrations.AlterField(
+            model_name='archiveresult',
+            name='extractor',
+            field=models.CharField(choices=[('htmltotext', 'htmltotext'), ('git', 'git'), ('singlefile', 'singlefile'), ('media', 'media'), ('archive_org', 'archive_org'), ('readability', 'readability'), ('mercury', 'mercury'), ('favicon', 'favicon'), ('pdf', 'pdf'), ('headers', 'headers'), ('screenshot', 'screenshot'), ('dom', 'dom'), ('title', 'title'), ('wget', 'wget')], max_length=32),
+        ),
+    ]

archivebox/core/migrations/0024_auto_20240513_1143.py

@@ -0,0 +1,95 @@
+# Generated by Django 5.0.6 on 2024-05-13 11:43
+
+from django.db import migrations
+from datetime import datetime
+from abid_utils.abid import abid_from_values
+
+
+def calculate_abid(self):
+    """
+    Return a freshly derived ABID (assembled from attrs defined in ABIDModel.abid_*_src).
+    """
+    prefix = self.abid_prefix
+    ts = eval(self.abid_ts_src)
+    uri = eval(self.abid_uri_src)
+    subtype = eval(self.abid_subtype_src)
+    rand = eval(self.abid_rand_src)
+
+    if (not prefix) or prefix == 'obj_':
+        suggested_abid = self.__class__.__name__[:3].lower()
+        raise Exception(f'{self.__class__.__name__}.abid_prefix must be defined to calculate ABIDs (suggested: {suggested_abid})')
+
+    if not ts:
+        ts = datetime.utcfromtimestamp(0)
+        print(f'[!] WARNING: Generating ABID with ts=0000000000 placeholder because {self.__class__.__name__}.abid_ts_src={self.abid_ts_src} is unset!', ts.isoformat())
+
+    if not uri:
+        uri = str(self)
+        print(f'[!] WARNING: Generating ABID with uri=str(self) placeholder because {self.__class__.__name__}.abid_uri_src={self.abid_uri_src} is unset!', uri)
+
+    if not subtype:
+        subtype = self.__class__.__name__
+        print(f'[!] WARNING: Generating ABID with subtype={subtype} placeholder because {self.__class__.__name__}.abid_subtype_src={self.abid_subtype_src} is unset!', subtype)
+
+    if not rand:
+        rand = getattr(self, 'uuid', None) or getattr(self, 'id', None) or getattr(self, 'pk')
+        print(f'[!] WARNING: Generating ABID with rand=self.id placeholder because {self.__class__.__name__}.abid_rand_src={self.abid_rand_src} is unset!', rand)
+
+    abid = abid_from_values(
+        prefix=prefix,
+        ts=ts,
+        uri=uri,
+        subtype=subtype,
+        rand=rand,
+    )
+    assert abid.ulid and abid.uuid and abid.typeid, f'Failed to calculate {prefix}_ABID for {self.__class__.__name__}'
+    return abid
+
+
+def copy_snapshot_uuids(apps, schema_editor):
+    Snapshot = apps.get_model("core", "Snapshot")
+    for snapshot in Snapshot.objects.all():
+        snapshot.uuid = snapshot.id
+        snapshot.save(update_fields=["uuid"])
+
+def generate_snapshot_abids(apps, schema_editor):
+    Snapshot = apps.get_model("core", "Snapshot")
+    for snapshot in Snapshot.objects.all():
+        snapshot.abid_prefix = 'snp_'
+        snapshot.abid_ts_src = 'self.added'
+        snapshot.abid_uri_src = 'self.url'
+        snapshot.abid_subtype_src = '"01"'
+        snapshot.abid_rand_src = 'self.uuid'
+
+        snapshot.abid = calculate_abid(snapshot)
+        snapshot.save(update_fields=["abid"])
+
+def generate_archiveresult_abids(apps, schema_editor):
+    ArchiveResult = apps.get_model("core", "ArchiveResult")
+    Snapshot = apps.get_model("core", "Snapshot")
+    for result in ArchiveResult.objects.all():
+        result.abid_prefix = 'res_'
+        result.snapshot = Snapshot.objects.get(pk=result.snapshot_id)
+        result.snapshot_added = result.snapshot.added
+        result.snapshot_url = result.snapshot.url
+        result.abid_ts_src = 'self.snapshot_added'
+        result.abid_uri_src = 'self.snapshot_url'
+        result.abid_subtype_src = 'self.extractor'
+        result.abid_rand_src = 'self.id'
+
+        result.abid = calculate_abid(result)
+        result.uuid = result.abid.uuid
+        result.save(update_fields=["abid", "uuid"])
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('core', '0023_alter_archiveresult_options_archiveresult_abid_and_more'),
+    ]
+
+    operations = [
+        migrations.RunPython(copy_snapshot_uuids, reverse_code=migrations.RunPython.noop),
+        migrations.RunPython(generate_snapshot_abids, reverse_code=migrations.RunPython.noop),
+        migrations.RunPython(generate_archiveresult_abids, reverse_code=migrations.RunPython.noop),
+    ]

archivebox/core/migrations/0025_alter_archiveresult_uuid.py

@@ -0,0 +1,19 @@
+# Generated by Django 5.0.6 on 2024-05-13 12:08
+
+import uuid
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('core', '0024_auto_20240513_1143'),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name='archiveresult',
+            name='uuid',
+            field=models.UUIDField(default=uuid.uuid4, editable=False, unique=True),
+        ),
+    ]

archivebox/core/migrations/0026_archiveresult_created_archiveresult_created_by_and_more.py

@@ -0,0 +1,76 @@
+# Generated by Django 5.0.6 on 2024-05-13 13:01
+
+import abid_utils.models
+import django.db.models.deletion
+import django.utils.timezone
+from django.conf import settings
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('core', '0025_alter_archiveresult_uuid'),
+        migrations.swappable_dependency(settings.AUTH_USER_MODEL),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name='archiveresult',
+            name='created',
+            field=models.DateTimeField(auto_now_add=True, default=django.utils.timezone.now),
+            preserve_default=False,
+        ),
+        migrations.AddField(
+            model_name='archiveresult',
+            name='created_by',
+            field=models.ForeignKey(default=abid_utils.models.get_or_create_system_user_pk, on_delete=django.db.models.deletion.CASCADE, to=settings.AUTH_USER_MODEL),
+        ),
+        migrations.AddField(
+            model_name='archiveresult',
+            name='modified',
+            field=models.DateTimeField(auto_now=True),
+        ),
+        migrations.AddField(
+            model_name='snapshot',
+            name='created',
+            field=models.DateTimeField(auto_now_add=True, default=django.utils.timezone.now),
+            preserve_default=False,
+        ),
+        migrations.AddField(
+            model_name='snapshot',
+            name='created_by',
+            field=models.ForeignKey(default=abid_utils.models.get_or_create_system_user_pk, on_delete=django.db.models.deletion.CASCADE, to=settings.AUTH_USER_MODEL),
+        ),
+        migrations.AddField(
+            model_name='snapshot',
+            name='modified',
+            field=models.DateTimeField(auto_now=True),
+        ),
+        migrations.AddField(
+            model_name='tag',
+            name='created',
+            field=models.DateTimeField(auto_now_add=True, default=django.utils.timezone.now),
+            preserve_default=False,
+        ),
+        migrations.AddField(
+            model_name='tag',
+            name='created_by',
+            field=models.ForeignKey(default=abid_utils.models.get_or_create_system_user_pk, on_delete=django.db.models.deletion.CASCADE, to=settings.AUTH_USER_MODEL),
+        ),
+        migrations.AddField(
+            model_name='tag',
+            name='modified',
+            field=models.DateTimeField(auto_now=True),
+        ),
+        migrations.AddField(
+            model_name='tag',
+            name='uuid',
+            field=models.UUIDField(blank=True, null=True, unique=True),
+        ),
+        migrations.AlterField(
+            model_name='archiveresult',
+            name='uuid',
+            field=models.UUIDField(blank=True, null=True, unique=True),
+        ),
+    ]

archivebox/core/models.py

@@ -1,12 +1,14 @@
 __package__ = 'archivebox.core'
 
 
-import uuid
+from typing import Optional, List, Dict
+from django_stubs_ext.db.models import TypedModelMeta
+
 import json
 
+import uuid
+from uuid import uuid4
 from pathlib import Path
-from typing import Optional, List
-from importlib import import_module
 
 from django.db import models
 from django.utils.functional import cached_property
@@ -16,12 +18,15 @@ from django.urls import reverse
 from django.db.models import Case, When, Value, IntegerField
 from django.contrib.auth.models import User   # noqa
 
+from abid_utils.models import ABIDModel, ABIDField
+
 from ..config import ARCHIVE_DIR, ARCHIVE_DIR_NAME
 from ..system import get_dir_size
-from ..util import parse_date, base_url, hashurl
+from ..util import parse_date, base_url
 from ..index.schema import Link
 from ..index.html import snapshot_icons
-from ..extractors import get_default_archive_methods, ARCHIVE_METHODS_INDEXING_PRECEDENCE, EXTRACTORS
+from ..extractors import ARCHIVE_METHODS_INDEXING_PRECEDENCE, EXTRACTORS
+
 
 EXTRACTOR_CHOICES = [(extractor_name, extractor_name) for extractor_name in EXTRACTORS.keys()]
 STATUS_CHOICES = [
@@ -30,26 +35,41 @@ STATUS_CHOICES = [
     ("skipped", "skipped")
 ]
 
-try:
-    JSONField = models.JSONField
-except AttributeError:
-    import jsonfield
-    JSONField = jsonfield.JSONField
 
 
-class Tag(models.Model):
+# class BaseModel(models.Model):
+#     # TODO: migrate all models to a shared base class with all our standard fields and helpers:
+#     #       ulid/created/modified/owner/is_deleted/as_json/from_json/etc.
+#     #
+#     # id = models.AutoField(primary_key=True, serialize=False, verbose_name='ID')
+#     # ulid = models.CharField(max_length=26, null=True, blank=True, db_index=True, unique=True)
+
+#     class Meta(TypedModelMeta):
+#         abstract = True
+
+
+class Tag(ABIDModel):
     """
-    Based on django-taggit model
+    Based on django-taggit model + ABID base.
     """
+    abid_prefix = 'tag_'
+    abid_ts_src = 'self.created'          # TODO: add created/modified time
+    abid_uri_src = 'self.name'
+    abid_subtype_src = '"03"'
+    abid_rand_src = 'self.id'
+
+    # id = models.UUIDField(primary_key=True, default=uuid.uuid4, editable=True)
     id = models.AutoField(primary_key=True, serialize=False, verbose_name='ID')
+    uuid = models.UUIDField(blank=True, null=True, editable=True, unique=True)
+    abid = ABIDField(prefix=abid_prefix)
+
 
     name = models.CharField(unique=True, blank=False, max_length=100)
-
-    # slug is autoset on save from name, never set it manually
     slug = models.SlugField(unique=True, blank=True, max_length=100)
+    # slug is autoset on save from name, never set it manually
 
 
-    class Meta:
+    class Meta(TypedModelMeta):
         verbose_name = "Tag"
         verbose_name_plural = "Tags"
 
@@ -85,8 +105,16 @@ class Tag(models.Model):
             return super().save(*args, **kwargs)
 
 
-class Snapshot(models.Model):
-    id = models.UUIDField(primary_key=True, default=uuid.uuid4, editable=False)
+class Snapshot(ABIDModel):
+    abid_prefix = 'snp_'
+    abid_ts_src = 'self.added'
+    abid_uri_src = 'self.url'
+    abid_subtype_src = '"01"'
+    abid_rand_src = 'self.id'
+
+    id = models.UUIDField(primary_key=True, default=uuid.uuid4, editable=False)  # legacy pk
+    uuid = models.UUIDField(blank=True, null=True, editable=True, unique=True)
+    abid = ABIDField(prefix=abid_prefix)
 
     url = models.URLField(unique=True, db_index=True)
     timestamp = models.CharField(max_length=32, unique=True, db_index=True)
@@ -99,6 +127,7 @@ class Snapshot(models.Model):
 
     keys = ('url', 'timestamp', 'title', 'tags', 'updated')
 
+
     def __repr__(self) -> str:
         title = self.title or '-'
         return f'[{self.timestamp}] {self.url[:64]} ({title[:64]})'
@@ -127,8 +156,8 @@ class Snapshot(models.Model):
         from ..index import load_link_details
         return load_link_details(self.as_link())
 
-    def tags_str(self, nocache=True) -> str:
-        cache_key = f'{self.id}-{(self.updated or self.added).timestamp()}-tags'
+    def tags_str(self, nocache=True) -> str | None:
+        cache_key = f'{self.pk}-{(self.updated or self.added).timestamp()}-tags'
         calc_tags_str = lambda: ','.join(self.tags.order_by('name').values_list('name', flat=True))
         if nocache:
             tags_str = calc_tags_str()
@@ -158,13 +187,9 @@ class Snapshot(models.Model):
         return self.as_link().is_archived
 
     @cached_property
-    def num_outputs(self):
+    def num_outputs(self) -> int:
         return self.archiveresult_set.filter(status='succeeded').count()
 
-    @cached_property
-    def url_hash(self):
-        return hashurl(self.url)
-
     @cached_property
     def base_url(self):
         return base_url(self.url)
@@ -179,7 +204,7 @@ class Snapshot(models.Model):
 
     @cached_property
     def archive_size(self):
-        cache_key = f'{str(self.id)[:12]}-{(self.updated or self.added).timestamp()}-size'
+        cache_key = f'{str(self.pk)[:12]}-{(self.updated or self.added).timestamp()}-size'
 
         def calc_dir_size():
             try:
@@ -200,7 +225,7 @@ class Snapshot(models.Model):
         return None
 
     @cached_property
-    def headers(self) -> Optional[dict]:
+    def headers(self) -> Optional[Dict[str, str]]:
         try:
             return json.loads((Path(self.link_dir) / 'headers.json').read_text(encoding='utf-8').strip())
         except Exception:
@@ -251,11 +276,37 @@ class Snapshot(models.Model):
         tags_id = []
         for tag in tags:
             if tag.strip():
-                tags_id.append(Tag.objects.get_or_create(name=tag)[0].id)
+                tags_id.append(Tag.objects.get_or_create(name=tag)[0].pk)
         self.tags.clear()
         self.tags.add(*tags_id)
 
 
+    # def get_storage_dir(self, create=True, symlink=True) -> Path:
+    #     date_str = self.added.strftime('%Y%m%d')
+    #     domain_str = domain(self.url)
+    #     abs_storage_dir = Path(ARCHIVE_DIR) / 'snapshots' / date_str / domain_str / str(self.ulid)
+
+    #     if create and not abs_storage_dir.is_dir():
+    #         abs_storage_dir.mkdir(parents=True, exist_ok=True)
+
+    #     if symlink:
+    #         LINK_PATHS = [
+    #             Path(ARCHIVE_DIR).parent / 'index' / 'all_by_id' / str(self.ulid),
+    #             # Path(ARCHIVE_DIR).parent / 'index' / 'snapshots_by_id' / str(self.ulid),
+    #             Path(ARCHIVE_DIR).parent / 'index' / 'snapshots_by_date' / date_str / domain_str / str(self.ulid),
+    #             Path(ARCHIVE_DIR).parent / 'index' / 'snapshots_by_domain' / domain_str / date_str / str(self.ulid),
+    #         ]
+    #         for link_path in LINK_PATHS:
+    #             link_path.parent.mkdir(parents=True, exist_ok=True)
+    #             try:
+    #                 link_path.symlink_to(abs_storage_dir)
+    #             except FileExistsError:
+    #                 link_path.unlink()
+    #                 link_path.symlink_to(abs_storage_dir)
+
+    #     return abs_storage_dir
+
+
 class ArchiveResultManager(models.Manager):
     def indexable(self, sorted: bool = True):
         INDEXABLE_METHODS = [ r[0] for r in ARCHIVE_METHODS_INDEXING_PRECEDENCE ]
@@ -267,15 +318,22 @@ class ArchiveResultManager(models.Manager):
         return qs
 
 
-class ArchiveResult(models.Model):
+class ArchiveResult(ABIDModel):
+    abid_prefix = 'res_'
+    abid_ts_src = 'self.snapshot.added'
+    abid_uri_src = 'self.snapshot.url'
+    abid_subtype_src = 'self.extractor'
+    abid_rand_src = 'self.uuid'
     EXTRACTOR_CHOICES = EXTRACTOR_CHOICES
 
-    id = models.AutoField(primary_key=True, serialize=False, verbose_name='ID')
-    uuid = models.UUIDField(default=uuid.uuid4, editable=False)
+    # id = models.UUIDField(primary_key=True, default=uuid.uuid4, editable=False)
+    id = models.AutoField(primary_key=True, serialize=False, verbose_name='ID')   # legacy pk
+    uuid = models.UUIDField(blank=True, null=True, editable=True, unique=True)
+    abid = ABIDField(prefix=abid_prefix)
 
     snapshot = models.ForeignKey(Snapshot, on_delete=models.CASCADE)
     extractor = models.CharField(choices=EXTRACTOR_CHOICES, max_length=32)
-    cmd = JSONField()
+    cmd = models.JSONField()
     pwd = models.CharField(max_length=256)
     cmd_version = models.CharField(max_length=128, default=None, null=True, blank=True)
     output = models.CharField(max_length=1024)
@@ -285,6 +343,9 @@ class ArchiveResult(models.Model):
 
     objects = ArchiveResultManager()
 
+    class Meta(TypedModelMeta):
+        verbose_name = 'Result'
+
     def __str__(self):
         return self.extractor
 
@@ -318,3 +379,33 @@ class ArchiveResult(models.Model):
 
     def output_exists(self) -> bool:
         return Path(self.output_path()).exists()
+
+
+    # def get_storage_dir(self, create=True, symlink=True):
+    #     date_str = self.snapshot.added.strftime('%Y%m%d')
+    #     domain_str = domain(self.snapshot.url)
+    #     abs_storage_dir = Path(ARCHIVE_DIR) / 'results' / date_str / domain_str / self.extractor / str(self.ulid)
+
+    #     if create and not abs_storage_dir.is_dir():
+    #         abs_storage_dir.mkdir(parents=True, exist_ok=True)
+
+    #     if symlink:
+    #         LINK_PATHS = [
+    #             Path(ARCHIVE_DIR).parent / 'index' / 'all_by_id' / str(self.ulid),
+    #             # Path(ARCHIVE_DIR).parent / 'index' / 'results_by_id' / str(self.ulid),
+    #             # Path(ARCHIVE_DIR).parent / 'index' / 'results_by_date' / date_str / domain_str / self.extractor / str(self.ulid),
+    #             Path(ARCHIVE_DIR).parent / 'index' / 'results_by_domain' / domain_str / date_str / self.extractor / str(self.ulid),
+    #             Path(ARCHIVE_DIR).parent / 'index' / 'results_by_type' / self.extractor / date_str / domain_str / str(self.ulid),
+    #         ]
+    #         for link_path in LINK_PATHS:
+    #             link_path.parent.mkdir(parents=True, exist_ok=True)
+    #             try:
+    #                 link_path.symlink_to(abs_storage_dir)
+    #             except FileExistsError:
+    #                 link_path.unlink()
+    #                 link_path.symlink_to(abs_storage_dir)
+
+    #     return abs_storage_dir
+
+    # def symlink_index(self, create=True):
+    #     abs_result_dir = self.get_storage_dir(create=create)

archivebox/core/settings.py

@@ -10,6 +10,7 @@ from pathlib import Path
 from django.utils.crypto import get_random_string
 
 from ..config import (
+    CONFIG,
     DEBUG,
     SECRET_KEY,
     ALLOWED_HOSTS,
@@ -62,12 +63,13 @@ INSTALLED_APPS = [
     'django.contrib.staticfiles',
     'django.contrib.admin',
 
+    'signal_webhooks',
+    'abid_utils',
     'core',
     'api',
 
     'admin_data_views',
 
-    'signal_webhooks',
     'django_extensions',
 ]
 
@@ -247,22 +249,26 @@ DATABASES = {
         'TIME_ZONE': TIMEZONE,
         # DB setup is sometimes modified at runtime by setup_django() in config.py
     },
-    'cache': {
-        'ENGINE': 'django.db.backends.sqlite3',
-        'NAME': CACHE_DB_PATH,
-        'OPTIONS': {
-            'timeout': 60,
-            'check_same_thread': False,
-        },
-        'TIME_ZONE': TIMEZONE,
-    },
+    # 'cache': {
+    #     'ENGINE': 'django.db.backends.sqlite3',
+    #     'NAME': CACHE_DB_PATH,
+    #     'OPTIONS': {
+    #         'timeout': 60,
+    #         'check_same_thread': False,
+    #     },
+    #     'TIME_ZONE': TIMEZONE,
+    # },
 }
+MIGRATION_MODULES = {'signal_webhooks': None}
+
+# as much as I'd love this to be a UUID or ULID field, it's not supported yet as of Django 5.0
+DEFAULT_AUTO_FIELD = 'django.db.models.BigAutoField'
 
 
 CACHES = {
-    'default': {'BACKEND': 'django.core.cache.backends.db.DatabaseCache', 'LOCATION': 'cache'},
-    'dummy': {'BACKEND': 'django.core.cache.backends.dummy.DummyCache'},
-    'locmem': {'BACKEND': 'django.core.cache.backends.locmem.LocMemCache'},
+    'default': {'BACKEND': 'django.core.cache.backends.locmem.LocMemCache'},
+    # 'sqlite': {'BACKEND': 'django.core.cache.backends.db.DatabaseCache', 'LOCATION': 'cache'},
+    # 'dummy': {'BACKEND': 'django.core.cache.backends.dummy.DummyCache'},
     # 'filebased': {"BACKEND": "django.core.cache.backends.filebased.FileBasedCache", "LOCATION": CACHE_DIR / 'cache_filebased'},
 }
 
@@ -421,9 +427,11 @@ LOGGING = {
 
 
 # Add default webhook configuration to the User model
+SIGNAL_WEBHOOKS_CUSTOM_MODEL = 'api.models.OutboundWebhook'
 SIGNAL_WEBHOOKS = {
     "HOOKS": {
-        "django.contrib.auth.models.User": ...,  # ... is a special value that means "use the default autogenerated hooks"
+        # ... is a special sigil value that means "use the default autogenerated hooks"
+        "django.contrib.auth.models.User": ...,
         "core.models.Snapshot": ...,
         "core.models.ArchiveResult": ...,
         "core.models.Tag": ...,

archivebox/core/views.py

@@ -226,8 +226,8 @@ class SnapshotView(View):
                             '<i><b>Next steps:</i></b><br/>'
                             f'- list all the <a href="/archive/{snapshot.timestamp}/" target="_top">Snapshot files <code>.*</code></a><br/>'
                             f'- view the <a href="/archive/{snapshot.timestamp}/index.html" target="_top">Snapshot <code>./index.html</code></a><br/>'
-                            f'- go to the <a href="/admin/core/snapshot/{snapshot.id}/change/" target="_top">Snapshot admin</a> to edit<br/>'
-                            f'- go to the <a href="/admin/core/snapshot/?id__startswith={snapshot.id}" target="_top">Snapshot actions</a> to re-archive<br/>'
+                            f'- go to the <a href="/admin/core/snapshot/{snapshot.pk}/change/" target="_top">Snapshot admin</a> to edit<br/>'
+                            f'- go to the <a href="/admin/core/snapshot/?uuid__startswith={snapshot.uuid}" target="_top">Snapshot actions</a> to re-archive<br/>'
                             '- or return to <a href="/" target="_top">the main index...</a></div>'
                             '</center>'
                         ),
@@ -455,7 +455,7 @@ def live_config_list_view(request: HttpRequest, **kwargs) -> TableContext:
 
     for section in CONFIG_SCHEMA.keys():
         for key in CONFIG_SCHEMA[section].keys():
-            rows['Section'].append(section.replace('_', ' ').title().replace(' Config', ''))
+            rows['Section'].append(section)   # section.replace('_', ' ').title().replace(' Config', '')
             rows['Key'].append(ItemLink(key, key=key))
             rows['Type'].append(mark_safe(f'<code>{find_config_type(key)}</code>'))
             rows['Value'].append(mark_safe(f'<code>{CONFIG[key]}</code>') if key_is_safe(key) else '******** (redacted)')
@@ -465,7 +465,7 @@ def live_config_list_view(request: HttpRequest, **kwargs) -> TableContext:
 
     section = 'DYNAMIC'
     for key in DYNAMIC_CONFIG_SCHEMA.keys():
-        rows['Section'].append(section.replace('_', ' ').title().replace(' Config', ''))
+        rows['Section'].append(section)   # section.replace('_', ' ').title().replace(' Config', '')
         rows['Key'].append(ItemLink(key, key=key))
         rows['Type'].append(mark_safe(f'<code>{find_config_type(key)}</code>'))
         rows['Value'].append(mark_safe(f'<code>{CONFIG[key]}</code>') if key_is_safe(key) else '******** (redacted)')

archivebox/extractors/__init__.py

@@ -160,7 +160,7 @@ def archive_link(link: Link, overwrite: bool=False, methods: Optional[Iterable[s
                     # bump the updated time on the main Snapshot here, this is critical
                     # to be able to cache summaries of the ArchiveResults for a given
                     # snapshot without having to load all the results from the DB each time.
-                    # (we use {Snapshot.id}-{Snapshot.updated} as the cache key and assume
+                    # (we use {Snapshot.pk}-{Snapshot.updated} as the cache key and assume
                     # ArchiveResults are unchanged as long as the updated timestamp is unchanged)
                     snapshot.save()
                 else:

archivebox/extractors/singlefile.py

@@ -94,7 +94,8 @@ def save_singlefile(link: Link, out_dir: Optional[Path]=None, timeout: int=TIMEO
         status = 'failed'
         # TODO: Make this prettier. This is necessary to run the command (escape JSON internal quotes).
         cmd[2] = browser_args.replace('"', "\\\"")
-        err.hints = (result.stdout + result.stderr).decode().split('\n')
+        if result:
+            err.hints = (result.stdout + result.stderr).decode().split('\n')
         output = err
     finally:
         timer.end()

archivebox/index/html.py

@@ -118,7 +118,7 @@ def render_django_template(template: str, context: Mapping[str, str]) -> str:
 
 
 def snapshot_icons(snapshot) -> str:
-    cache_key = f'{snapshot.id}-{(snapshot.updated or snapshot.added).timestamp()}-snapshot-icons'
+    cache_key = f'{snapshot.pk}-{(snapshot.updated or snapshot.added).timestamp()}-snapshot-icons'
     
     def calc_snapshot_icons():
         from core.models import EXTRACTOR_CHOICES

archivebox/index/schema.py

@@ -192,6 +192,9 @@ class Link:
         if extended:
             info.update({
                 'snapshot_id': self.snapshot_id,
+                'snapshot_uuid': self.snapshot_uuid,
+                'snapshot_abid': self.snapshot_abid,
+
                 'link_dir': self.link_dir,
                 'archive_path': self.archive_path,
                 
@@ -261,9 +264,21 @@ class Link:
         return to_csv(self, cols=cols or self.field_names(), separator=separator, ljust=ljust)
 
     @cached_property
-    def snapshot_id(self):
+    def snapshot(self):
         from core.models import Snapshot
-        return str(Snapshot.objects.only('id').get(url=self.url).id)
+        return Snapshot.objects.only('uuid').get(url=self.url)
+
+    @cached_property
+    def snapshot_id(self):
+        return str(self.snapshot.pk)
+
+    @cached_property
+    def snapshot_uuid(self):
+        return str(self.snapshot.uuid)
+
+    @cached_property
+    def snapshot_abid(self):
+        return str(self.snapshot.ABID)
 
     @classmethod
     def field_names(cls):

archivebox/index/sql.py

@@ -45,7 +45,8 @@ def write_link_to_sql_index(link: Link):
     info.pop('tags')
 
     try:
-        info["timestamp"] = Snapshot.objects.get(url=link.url).timestamp
+        snapshot = Snapshot.objects.get(url=link.url)
+        info["timestamp"] = snapshot.timestamp
     except Snapshot.DoesNotExist:
         while Snapshot.objects.filter(timestamp=info["timestamp"]).exists():
             info["timestamp"] = str(float(info["timestamp"]) + 1.0)
@@ -57,7 +58,7 @@ def write_link_to_sql_index(link: Link):
         for entry in entries:
             if isinstance(entry, dict):
                 result, _ = ArchiveResult.objects.get_or_create(
-                    snapshot_id=snapshot.id,
+                    snapshot_id=snapshot.pk,
                     extractor=extractor,
                     start_ts=parse_date(entry['start_ts']),
                     defaults={
@@ -71,7 +72,7 @@ def write_link_to_sql_index(link: Link):
                 )
             else:
                 result, _ = ArchiveResult.objects.update_or_create(
-                    snapshot_id=snapshot.id,
+                    snapshot_id=snapshot.pk,
                     extractor=extractor,
                     start_ts=parse_date(entry.start_ts),
                     defaults={

archivebox/monkey_patches.py

@@ -0,0 +1,16 @@
+__package__ = 'archivebox'
+
+import django_stubs_ext
+
+django_stubs_ext.monkeypatch()
+
+
+# monkey patch django timezone to add back utc (it was removed in Django 5.0)
+import datetime
+from django.utils import timezone
+timezone.utc = datetime.timezone.utc
+
+
+# monkey patch django-signals-webhooks to change how it shows up in Admin UI
+# from signal_webhooks.apps import DjangoSignalWebhooksConfig
+# DjangoSignalWebhooksConfig.verbose_name = 'API'

archivebox/search/__init__.py

@@ -39,7 +39,7 @@ def write_search_index(link: Link, texts: Union[List[str], None]=None, out_dir:
         backend = import_backend()
         if snap:
             try:
-                backend.index(snapshot_id=str(snap.id), texts=texts)
+                backend.index(snapshot_id=str(snap.pk), texts=texts)
             except Exception as err:
                 stderr()
                 stderr(
@@ -54,7 +54,7 @@ def query_search_index(query: str, out_dir: Path=OUTPUT_DIR) -> QuerySet:
     if search_backend_enabled():
         backend = import_backend()
         try:
-            snapshot_ids = backend.search(query)
+            snapshot_pks = backend.search(query)
         except Exception as err:
             stderr()
             stderr(
@@ -64,7 +64,7 @@ def query_search_index(query: str, out_dir: Path=OUTPUT_DIR) -> QuerySet:
             raise
         else:
             # TODO preserve ordering from backend
-            qsearch = Snapshot.objects.filter(pk__in=snapshot_ids)
+            qsearch = Snapshot.objects.filter(pk__in=snapshot_pks)
             return qsearch
     
     return Snapshot.objects.none()
@@ -74,9 +74,9 @@ def flush_search_index(snapshots: QuerySet):
     if not indexing_enabled() or not snapshots:
         return
     backend = import_backend()
-    snapshot_ids=(str(pk) for pk in snapshots.values_list('pk',flat=True))
+    snapshot_pks = (str(pk) for pk in snapshots.values_list('pk', flat=True))
     try:
-        backend.flush(snapshot_ids)
+        backend.flush(snapshot_pks)
     except Exception as err:
         stderr()
         stderr(

archivebox/templates/admin/snapshots_grid.html

@@ -147,7 +147,7 @@
     {% for obj in results %}
       <div class="card">
           <div class="card-info">
-            <a href="{% url 'admin:core_snapshot_change' obj.id %}">
+            <a href="{% url 'admin:core_snapshot_change' obj.pk %}">
               <span class="timestamp">{{obj.added}}</span>
             </a>
             <label>

archivebox/templates/core/snapshot_live.html

@@ -405,7 +405,7 @@
                                     </a>
                                     <!--<a href="{{result.path}}" target="preview"><h4 class="card-title">{{result.name}}</h4></a>-->
                                 </div>
-                                <iframe class="card-img-top" src="{{result.path}}" sandbox="allow-scripts allow-forms" scrolling="no" loading="lazy"></iframe>
+                                <iframe class="card-img-top" src="{{result.path}}" sandbox="allow-same-origin allow-top-navigation-by-user-activation allow-scripts allow-forms" scrolling="no" loading="lazy"></iframe>
                             </div>
                         </div>
                     {% endfor %}
@@ -463,7 +463,7 @@
                     if (target.endsWith('.pdf')) {
                         jQuery('#main-frame')[0].removeAttribute('sandbox')
                     } else {
-                        jQuery('#main-frame')[0].sandbox = "allow-scripts allow-forms allow-top-navigation-by-user-activation"
+                        jQuery('#main-frame')[0].sandbox = "allow-same-origin allow-top-navigation-by-user-activation allow-scripts allow-forms"
                     }
                     window.location.hash = getPreviewTypeFromPath(event.currentTarget.querySelector('a'))
 

pyproject.toml

@@ -37,6 +37,9 @@ dependencies = [
     #  - See Github issues for more...
     "django-signal-webhooks>=0.3.0",
     "django-admin-data-views>=0.3.1",
+    "ulid-py>=1.1.0",
+    "typeid-python>=0.3.0",
+    "django-charid-field>=0.4",
 ]
 
 homepage = "https://github.com/ArchiveBox/ArchiveBox"