wip

old/TODO_fs_migrations.md

@@ -743,7 +743,7 @@ def update(filter_patterns: Iterable[str] = (),
     from archivebox.config.django import setup_django
     setup_django()
 
-    from core.models import Snapshot
+    from archivebox.core.models import Snapshot
     from django.utils import timezone
 
     while True:
@@ -790,7 +790,7 @@ def import_orphans_from_archive(resume_from: str = None, batch_size: int = 100)
     Skip symlinks (already migrated).
     Create DB records and trigger migration on save().
     """
-    from core.models import Snapshot
+    from archivebox.core.models import Snapshot
     from archivebox.config import CONSTANTS
     from django.db import transaction
 
@@ -858,7 +858,7 @@ def process_all_db_snapshots(batch_size: int = 100) -> dict:
     Process all snapshots in DB.
     Reconcile index.json and queue for archiving.
     """
-    from core.models import Snapshot
+    from archivebox.core.models import Snapshot
     from django.db import transaction
     from django.utils import timezone
 
@@ -896,7 +896,7 @@ def process_filtered_snapshots(
     batch_size: int
 ) -> dict:
     """Process snapshots matching filters (DB query only)."""
-    from core.models import Snapshot
+    from archivebox.core.models import Snapshot
     from django.db import transaction
     from django.utils import timezone
     from datetime import datetime
@@ -1042,7 +1042,7 @@ def search(filter_patterns: list[str] | None=None,
            with_headers: bool=False):
     """List, filter, and export information about archive entries"""
 
-    from core.models import Snapshot
+    from archivebox.core.models import Snapshot
 
     if with_headers and not (json or html or csv):
         stderr('[X] --with-headers requires --json, --html or --csv\n', color='red')

old/TODO_hook_architecture.md

@@ -658,7 +658,7 @@ def create_model_record(record: dict) -> Any:
     Returns:
         Created/updated model instance
     """
-    from machine.models import Binary, Dependency
+    from archivebox.machine.models import Binary, Dependency
 
     model_type = record.pop('type')
 
@@ -917,7 +917,7 @@ def find_binary_for_cmd(cmd: List[str], machine_id: str) -> Optional[str]:
     if not cmd:
         return None
 
-    from machine.models import Binary
+    from archivebox.machine.models import Binary
 
     bin_path_or_name = cmd[0]
 
@@ -977,7 +977,7 @@ def run_hook(
     """
     import time
     from datetime import datetime, timezone
-    from machine.models import Machine
+    from archivebox.machine.models import Machine
 
     start_time = time.time()
 
@@ -1125,7 +1125,7 @@ def run(self):
     """
     from django.utils import timezone
     from archivebox.hooks import BUILTIN_PLUGINS_DIR, USER_PLUGINS_DIR, run_hook, find_binary_for_cmd, create_model_record
-    from machine.models import Machine
+    from archivebox.machine.models import Machine
 
     config_objects = [self.snapshot.crawl, self.snapshot] if self.snapshot.crawl else [self.snapshot]
 
@@ -1458,7 +1458,7 @@ def finalize_background_hook(archiveresult: 'ArchiveResult') -> None:
         archiveresult: ArchiveResult instance to finalize
     """
     from django.utils import timezone
-    from machine.models import Machine
+    from archivebox.machine.models import Machine
 
     extractor_dir = Path(archiveresult.pwd)
     stdout_file = extractor_dir / 'stdout.log'

old/TODO_hook_statemachine_cleanup.md

@@ -173,15 +173,15 @@ def process_hook_records(records: List[Dict], overrides: Dict = None) -> Dict[st
 
         # Dispatch to appropriate model
         if record_type == 'Snapshot':
-            from core.models import Snapshot
+            from archivebox.core.models import Snapshot
             Snapshot.from_jsonl(record, overrides)
             stats['Snapshot'] = stats.get('Snapshot', 0) + 1
         elif record_type == 'Tag':
-            from core.models import Tag
+            from archivebox.core.models import Tag
             Tag.from_jsonl(record, overrides)
             stats['Tag'] = stats.get('Tag', 0) + 1
         elif record_type == 'Binary':
-            from machine.models import Binary
+            from archivebox.machine.models import Binary
             Binary.from_jsonl(record, overrides)
             stats['Binary'] = stats.get('Binary', 0) + 1
         # ... etc
@@ -526,7 +526,7 @@ class Model:
             # Update children from filesystem
             child.update_from_output()
 
-    def update_for_workers(self, **fields):
+    def update_and_requeue(self, **fields):
         """Update fields and bump modified_at."""
         for field, value in fields.items():
             setattr(self, field, value)
@@ -575,7 +575,7 @@ All core models (Crawl, Snapshot, ArchiveResult) now follow the unified pattern:
 - State machines orchestrate transitions
 - `.run()` methods execute hooks and process JSONL
 - `.cleanup()` methods kill background hooks
-- `.update_for_workers()` methods update state for worker coordination
+- `.update_and_requeue()` methods update state for worker coordination
 - Consistent use of `process_hook_records()` for JSONL dispatching
 
 ### ✅ Phases 7-8: Binary State Machine (Dependency Model Eliminated)