ФУНКЦИИ - МЕЖПРОЕКТНАЯ КОММУНИКАЦИЯ: blob-дедупликация файлов

This commit is contained in:
DCCONSTRUCTIONS
2026-04-27 09:45:16 +03:00
parent b945bc4d31
commit 490aa1bc04
18 changed files with 827 additions and 114 deletions
@@ -0,0 +1,112 @@
# Generated by Codex on 2026-04-26
import uuid
from django.conf import settings
from django.db import migrations, models
import django.db.models.deletion
class Migration(migrations.Migration):
dependencies = [
("db", "0127_issue_detail_layout"),
migrations.swappable_dependency(settings.AUTH_USER_MODEL),
]
operations = [
migrations.CreateModel(
name="StoredBlob",
fields=[
("created_at", models.DateTimeField(auto_now_add=True, verbose_name="Created At")),
("updated_at", models.DateTimeField(auto_now=True, verbose_name="Last Modified At")),
("deleted_at", models.DateTimeField(blank=True, null=True, verbose_name="Deleted At")),
(
"id",
models.UUIDField(
db_index=True,
default=uuid.uuid4,
editable=False,
primary_key=True,
serialize=False,
unique=True,
),
),
("sha256", models.CharField(db_index=True, max_length=64)),
("size", models.PositiveBigIntegerField(default=0)),
("mime_type", models.CharField(blank=True, default="", max_length=255)),
("canonical_object_key", models.CharField(max_length=800)),
(
"status",
models.CharField(
choices=[("active", "Active"), ("orphaned", "Orphaned"), ("missing", "Missing")],
default="active",
max_length=32,
),
),
("ref_count", models.PositiveIntegerField(default=0)),
("storage_metadata", models.JSONField(blank=True, default=dict, null=True)),
(
"created_by",
models.ForeignKey(
null=True,
on_delete=django.db.models.deletion.SET_NULL,
related_name="%(class)s_created_by",
to=settings.AUTH_USER_MODEL,
verbose_name="Created By",
),
),
(
"updated_by",
models.ForeignKey(
null=True,
on_delete=django.db.models.deletion.SET_NULL,
related_name="%(class)s_updated_by",
to=settings.AUTH_USER_MODEL,
verbose_name="Last Modified By",
),
),
(
"workspace",
models.ForeignKey(
on_delete=django.db.models.deletion.CASCADE,
related_name="stored_blobs",
to="db.workspace",
),
),
],
options={
"verbose_name": "Stored Blob",
"verbose_name_plural": "Stored Blobs",
"db_table": "stored_blobs",
"ordering": ("-created_at",),
},
),
migrations.AddField(
model_name="fileasset",
name="blob",
field=models.ForeignKey(
blank=True,
null=True,
on_delete=django.db.models.deletion.SET_NULL,
related_name="assets",
to="db.storedblob",
),
),
migrations.AddIndex(
model_name="storedblob",
index=models.Index(fields=["workspace", "sha256"], name="stored_blob_workspace_sha_idx"),
),
migrations.AddIndex(
model_name="storedblob",
index=models.Index(fields=["status"], name="stored_blob_status_idx"),
),
migrations.AddConstraint(
model_name="storedblob",
constraint=models.UniqueConstraint(
condition=models.Q(("deleted_at__isnull", True), ("status", "active")),
fields=("workspace", "sha256", "size"),
name="stored_blob_unique_active_hash_size",
),
),
]
@@ -4,7 +4,7 @@
from .analytic import AnalyticView
from .api import APIActivityLog, APIToken
from .asset import FileAsset
from .asset import FileAsset, StoredBlob
from .base import BaseModel
from .cycle import Cycle, CycleIssue, CycleUserProperties
from .deploy_board import DeployBoard
@@ -60,6 +60,13 @@ class FileAsset(BaseModel):
size = models.FloatField(default=0)
is_uploaded = models.BooleanField(default=False)
storage_metadata = models.JSONField(default=dict, null=True, blank=True)
blob = models.ForeignKey(
"db.StoredBlob",
on_delete=models.SET_NULL,
null=True,
blank=True,
related_name="assets",
)
class Meta:
verbose_name = "File Asset"
@@ -98,3 +105,43 @@ class FileAsset(BaseModel):
return f"/api/assets/v2/workspaces/{self.workspace.slug}/projects/{self.project_id}/{self.id}/"
return None
class StoredBlob(BaseModel):
"""
Canonical stored object shared by one or more FileAsset records.
"""
class Status(models.TextChoices):
ACTIVE = "active", "Active"
ORPHANED = "orphaned", "Orphaned"
MISSING = "missing", "Missing"
workspace = models.ForeignKey("db.Workspace", on_delete=models.CASCADE, related_name="stored_blobs")
sha256 = models.CharField(max_length=64, db_index=True)
size = models.PositiveBigIntegerField(default=0)
mime_type = models.CharField(max_length=255, blank=True, default="")
canonical_object_key = models.CharField(max_length=800)
status = models.CharField(max_length=32, choices=Status.choices, default=Status.ACTIVE)
ref_count = models.PositiveIntegerField(default=0)
storage_metadata = models.JSONField(default=dict, null=True, blank=True)
class Meta:
verbose_name = "Stored Blob"
verbose_name_plural = "Stored Blobs"
db_table = "stored_blobs"
ordering = ("-created_at",)
indexes = [
models.Index(fields=["workspace", "sha256"], name="stored_blob_workspace_sha_idx"),
models.Index(fields=["status"], name="stored_blob_status_idx"),
]
constraints = [
models.UniqueConstraint(
fields=["workspace", "sha256", "size"],
condition=models.Q(deleted_at__isnull=True, status="active"),
name="stored_blob_unique_active_hash_size",
)
]
def __str__(self):
return self.canonical_object_key