Add CP→CA→PI platform foundation on MapMil monorepo.

Unify parsing workers, analytics API with PostgreSQL, map UI, and PI distribution into centers/ with Docker Compose.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
2026-06-30 11:43:27 +03:00
co-authored by Cursor
commit 9dfe713668
88 changed files with 6587 additions and 0 deletions
+28
View File
@@ -0,0 +1,28 @@
import os
from sqlalchemy import create_engine
from sqlalchemy.orm import DeclarativeBase, sessionmaker
DATABASE_URL = os.getenv(
"DATABASE_URL",
"postgresql://mapmil:mapmil@ca-db:5432/mapmil",
)
connect_args: dict = {}
if DATABASE_URL.startswith("sqlite"):
connect_args = {"check_same_thread": False}
engine = create_engine(DATABASE_URL, connect_args=connect_args)
SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
class Base(DeclarativeBase):
pass
def get_db():
db = SessionLocal()
try:
yield db
finally:
db.close()
+11
View File
@@ -0,0 +1,11 @@
import os
from fastapi import Header, HTTPException
def verify_internal_token(
x_internal_token: str | None = Header(default=None, alias="X-Internal-Token"),
) -> None:
expected = os.getenv("INTERNAL_TOKEN", "dev-internal-token")
if not x_internal_token or x_internal_token != expected:
raise HTTPException(status_code=401, detail="Invalid internal token")
+38
View File
@@ -0,0 +1,38 @@
from contextlib import asynccontextmanager
from fastapi import FastAPI
from fastapi.middleware.cors import CORSMiddleware
from .database import Base, engine, get_db
from .routers import admin, internal, objects, v1
from .seed import seed_objects, seed_test_consumer
from .storage import ensure_upload_dir
@asynccontextmanager
async def lifespan(_: FastAPI):
ensure_upload_dir()
Base.metadata.create_all(bind=engine)
db = next(get_db())
try:
seed_objects(db)
seed_test_consumer(db)
finally:
db.close()
yield
app = FastAPI(title="CA API (Analytics Center)", lifespan=lifespan)
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
app.include_router(objects.router)
app.include_router(internal.router)
app.include_router(admin.router)
app.include_router(v1.router)
+145
View File
@@ -0,0 +1,145 @@
from datetime import datetime, timezone
from sqlalchemy import (
JSON,
Boolean,
DateTime,
Float,
ForeignKey,
Integer,
String,
Text,
UniqueConstraint,
)
from sqlalchemy.orm import Mapped, mapped_column, relationship
from .database import Base
class MapObject(Base):
__tablename__ = "map_objects"
id: Mapped[int] = mapped_column(Integer, primary_key=True, index=True)
name: Mapped[str] = mapped_column(String(255), nullable=False)
description: Mapped[str] = mapped_column(Text, default="")
type: Mapped[str] = mapped_column(String(50), nullable=False)
latitude: Mapped[float] = mapped_column(Float, nullable=False)
longitude: Mapped[float] = mapped_column(Float, nullable=False)
event_id: Mapped[int | None] = mapped_column(
ForeignKey("events.id", ondelete="SET NULL"),
nullable=True,
index=True,
)
created_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True),
default=lambda: datetime.now(timezone.utc),
)
media: Mapped[list["ObjectMedia"]] = relationship(
back_populates="object",
cascade="all, delete-orphan",
)
event: Mapped["Event | None"] = relationship(back_populates="map_object")
class ObjectMedia(Base):
__tablename__ = "object_media"
id: Mapped[int] = mapped_column(Integer, primary_key=True, index=True)
object_id: Mapped[int] = mapped_column(
ForeignKey("map_objects.id", ondelete="CASCADE"),
nullable=False,
index=True,
)
stored_name: Mapped[str] = mapped_column(String(255), nullable=False)
original_name: Mapped[str] = mapped_column(String(255), nullable=False)
content_type: Mapped[str] = mapped_column(String(100), nullable=False)
size: Mapped[int] = mapped_column(Integer, nullable=False)
created_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True),
default=lambda: datetime.now(timezone.utc),
)
object: Mapped["MapObject"] = relationship(back_populates="media")
class Event(Base):
__tablename__ = "events"
__table_args__ = (UniqueConstraint("source_url", name="uq_events_source_url"),)
id: Mapped[int] = mapped_column(Integer, primary_key=True, index=True)
source_type: Mapped[str] = mapped_column(String(50), nullable=False, index=True)
source_url: Mapped[str] = mapped_column(String(512), nullable=False)
raw_text: Mapped[str] = mapped_column(Text, default="")
title: Mapped[str] = mapped_column(String(512), default="")
description: Mapped[str] = mapped_column(Text, default="")
locality: Mapped[str] = mapped_column(String(255), default="")
latitude: Mapped[float | None] = mapped_column(Float, nullable=True)
longitude: Mapped[float | None] = mapped_column(Float, nullable=True)
event_date: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
ingested_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True),
default=lambda: datetime.now(timezone.utc),
index=True,
)
region: Mapped[str | None] = mapped_column(String(100), nullable=True, index=True)
topic: Mapped[str | None] = mapped_column(String(100), nullable=True, index=True)
tags: Mapped[list | None] = mapped_column(JSON, nullable=True)
metadata_: Mapped[dict | None] = mapped_column("metadata", JSON, nullable=True)
map_object: Mapped["MapObject | None"] = relationship(
back_populates="event",
uselist=False,
)
class ParseJob(Base):
__tablename__ = "parse_jobs"
id: Mapped[int] = mapped_column(Integer, primary_key=True, index=True)
source_type: Mapped[str] = mapped_column(String(50), nullable=False)
source_config: Mapped[dict] = mapped_column(JSON, nullable=False, default=dict)
schedule: Mapped[str | None] = mapped_column(String(100), nullable=True)
status: Mapped[str] = mapped_column(String(50), default="pending", index=True)
last_run_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
last_error: Mapped[str | None] = mapped_column(Text, nullable=True)
created_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True),
default=lambda: datetime.now(timezone.utc),
)
class Consumer(Base):
__tablename__ = "consumers"
id: Mapped[int] = mapped_column(Integer, primary_key=True, index=True)
name: Mapped[str] = mapped_column(String(255), nullable=False, unique=True)
api_key_hash: Mapped[str] = mapped_column(String(64), nullable=False, unique=True)
is_active: Mapped[bool] = mapped_column(Boolean, default=True)
created_at: Mapped[datetime] = mapped_column(
DateTime(timezone=True),
default=lambda: datetime.now(timezone.utc),
)
filter: Mapped["ConsumerFilter | None"] = relationship(
back_populates="consumer",
uselist=False,
cascade="all, delete-orphan",
)
class ConsumerFilter(Base):
__tablename__ = "consumer_filters"
id: Mapped[int] = mapped_column(Integer, primary_key=True, index=True)
consumer_id: Mapped[int] = mapped_column(
ForeignKey("consumers.id", ondelete="CASCADE"),
nullable=False,
unique=True,
)
regions: Mapped[list | None] = mapped_column(JSON, nullable=True)
topics: Mapped[list | None] = mapped_column(JSON, nullable=True)
min_access_level: Mapped[int] = mapped_column(Integer, default=0)
date_from: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
consumer: Mapped["Consumer"] = relationship(back_populates="filter")
@@ -0,0 +1,78 @@
from fastapi import APIRouter, Depends, HTTPException, Query
from sqlalchemy.orm import Session
from ..database import get_db
from ..models import Event, ParseJob
from ..schemas import (
ConsumerCreate,
ConsumerRead,
EventRead,
ParseJobCreate,
ParseJobRead,
)
from ..services.filtering import create_consumer
from ..services.jobs import enqueue_job
router = APIRouter(prefix="/admin", tags=["admin"])
@router.post("/jobs", response_model=ParseJobRead, status_code=201)
def create_parse_job(payload: ParseJobCreate, db: Session = Depends(get_db)):
job = ParseJob(
source_type=payload.source_type,
source_config=payload.source_config,
schedule=payload.schedule,
status="queued",
)
db.add(job)
db.commit()
db.refresh(job)
enqueue_job(job.id, job.source_type, job.source_config)
return job
@router.get("/jobs", response_model=list[ParseJobRead])
def list_parse_jobs(db: Session = Depends(get_db)):
return db.query(ParseJob).order_by(ParseJob.id.desc()).all()
@router.get("/jobs/{job_id}", response_model=ParseJobRead)
def get_parse_job(job_id: int, db: Session = Depends(get_db)):
job = db.query(ParseJob).filter(ParseJob.id == job_id).first()
if not job:
raise HTTPException(status_code=404, detail="Job not found")
return job
@router.get("/events", response_model=list[EventRead])
def list_events(
limit: int = Query(default=100, ge=1, le=1000),
offset: int = Query(default=0, ge=0),
db: Session = Depends(get_db),
):
return (
db.query(Event)
.order_by(Event.ingested_at.desc())
.offset(offset)
.limit(limit)
.all()
)
@router.post("/consumers", response_model=ConsumerRead, status_code=201)
def create_pi_consumer(payload: ConsumerCreate, db: Session = Depends(get_db)):
consumer, api_key = create_consumer(
db,
name=payload.name,
regions=payload.regions,
topics=payload.topics,
date_from=payload.date_from,
)
return ConsumerRead(
id=consumer.id,
name=consumer.name,
is_active=consumer.is_active,
created_at=consumer.created_at,
api_key=api_key,
)
@@ -0,0 +1,45 @@
from datetime import datetime, timezone
from fastapi import APIRouter, Depends, HTTPException
from sqlalchemy.orm import Session
from ..database import get_db
from ..deps import verify_internal_token
from ..models import ParseJob
from ..schemas import IngestRequest, IngestResponse
from ..services.ingest import ingest_events
router = APIRouter(prefix="/internal", tags=["internal"])
@router.post("/ingest", response_model=IngestResponse)
def internal_ingest(
payload: IngestRequest,
_: None = Depends(verify_internal_token),
db: Session = Depends(get_db),
):
ingested, updated, map_synced = ingest_events(db, payload.events, payload.job_id)
return IngestResponse(
ingested=ingested,
updated=updated,
map_objects_synced=map_synced,
)
@router.patch("/jobs/{job_id}")
def update_job_status(
job_id: int,
status: str,
error: str | None = None,
_: None = Depends(verify_internal_token),
db: Session = Depends(get_db),
):
job = db.query(ParseJob).filter(ParseJob.id == job_id).first()
if not job:
raise HTTPException(status_code=404, detail="Job not found")
job.status = status
job.last_run_at = datetime.now(timezone.utc)
job.last_error = error
db.commit()
return {"id": job.id, "status": job.status}
@@ -0,0 +1,169 @@
from fastapi import APIRouter, Depends, File, HTTPException, UploadFile
from fastapi.responses import FileResponse
from sqlalchemy.orm import Session
from ..database import get_db
from ..models import MapObject, ObjectMedia
from ..schemas import MapObjectCreate, MapObjectRead, MapObjectUpdate, ObjectMediaRead
from ..storage import (
ALLOWED_CONTENT_TYPES,
MAX_FILE_SIZE,
build_stored_name,
is_allowed_content_type,
media_file_path,
remove_media_file,
)
router = APIRouter(tags=["objects"])
def media_to_read(media: ObjectMedia) -> ObjectMediaRead:
return ObjectMediaRead(
id=media.id,
object_id=media.object_id,
original_name=media.original_name,
content_type=media.content_type,
size=media.size,
created_at=media.created_at,
url=f"/api/media/{media.id}/file",
)
@router.get("/api/health")
def health():
return {"status": "ok"}
@router.get("/api/objects", response_model=list[MapObjectRead])
def list_objects(db: Session = Depends(get_db)):
return db.query(MapObject).order_by(MapObject.id).all()
@router.get("/api/objects/{object_id}", response_model=MapObjectRead)
def get_object(object_id: int, db: Session = Depends(get_db)):
obj = db.query(MapObject).filter(MapObject.id == object_id).first()
if not obj:
raise HTTPException(status_code=404, detail="Объект не найден")
return obj
@router.post("/api/objects", response_model=MapObjectRead, status_code=201)
def create_object(payload: MapObjectCreate, db: Session = Depends(get_db)):
data = payload.model_dump()
created_at = data.pop("created_at", None)
obj = MapObject(**data)
if created_at is not None:
obj.created_at = created_at
db.add(obj)
db.commit()
db.refresh(obj)
return obj
@router.patch("/api/objects/{object_id}", response_model=MapObjectRead)
def update_object(
object_id: int,
payload: MapObjectUpdate,
db: Session = Depends(get_db),
):
obj = db.query(MapObject).filter(MapObject.id == object_id).first()
if not obj:
raise HTTPException(status_code=404, detail="Объект не найден")
for field, value in payload.model_dump(exclude_unset=True).items():
setattr(obj, field, value)
db.commit()
db.refresh(obj)
return obj
@router.delete("/api/objects/{object_id}", status_code=204)
def delete_object(object_id: int, db: Session = Depends(get_db)):
obj = db.query(MapObject).filter(MapObject.id == object_id).first()
if not obj:
raise HTTPException(status_code=404, detail="Объект не найден")
for media in obj.media:
remove_media_file(media.stored_name)
db.delete(obj)
db.commit()
@router.get("/api/objects/{object_id}/media", response_model=list[ObjectMediaRead])
def list_object_media(object_id: int, db: Session = Depends(get_db)):
obj = db.query(MapObject).filter(MapObject.id == object_id).first()
if not obj:
raise HTTPException(status_code=404, detail="Объект не найден")
media_items = (
db.query(ObjectMedia)
.filter(ObjectMedia.object_id == object_id)
.order_by(ObjectMedia.id)
.all()
)
return [media_to_read(item) for item in media_items]
@router.post("/api/objects/{object_id}/media", response_model=ObjectMediaRead, status_code=201)
async def upload_object_media(
object_id: int,
file: UploadFile = File(...),
db: Session = Depends(get_db),
):
obj = db.query(MapObject).filter(MapObject.id == object_id).first()
if not obj:
raise HTTPException(status_code=404, detail="Объект не найден")
content_type = file.content_type or "application/octet-stream"
if not is_allowed_content_type(content_type):
raise HTTPException(
status_code=400,
detail=f"Неподдерживаемый тип файла. Разрешены: {', '.join(sorted(ALLOWED_CONTENT_TYPES))}",
)
content = await file.read()
if len(content) > MAX_FILE_SIZE:
raise HTTPException(status_code=400, detail="Файл слишком большой (макс. 20 МБ)")
original_name = file.filename or "file"
stored_name = build_stored_name(original_name)
path = media_file_path(stored_name)
path.write_bytes(content)
media = ObjectMedia(
object_id=object_id,
stored_name=stored_name,
original_name=original_name,
content_type=content_type,
size=len(content),
)
db.add(media)
db.commit()
db.refresh(media)
return media_to_read(media)
@router.get("/api/media/{media_id}/file")
def get_media_file(media_id: int, db: Session = Depends(get_db)):
media = db.query(ObjectMedia).filter(ObjectMedia.id == media_id).first()
if not media:
raise HTTPException(status_code=404, detail="Медиафайл не найден")
path = media_file_path(media.stored_name)
if not path.exists():
raise HTTPException(status_code=404, detail="Файл не найден на диске")
return FileResponse(path, media_type=media.content_type, filename=media.original_name)
@router.delete("/api/media/{media_id}", status_code=204)
def delete_media(media_id: int, db: Session = Depends(get_db)):
media = db.query(ObjectMedia).filter(ObjectMedia.id == media_id).first()
if not media:
raise HTTPException(status_code=404, detail="Медиафайл не найден")
remove_media_file(media.stored_name)
db.delete(media)
db.commit()
+33
View File
@@ -0,0 +1,33 @@
from fastapi import APIRouter, Depends, Header, HTTPException, Query
from sqlalchemy.orm import Session
from ..database import get_db
from ..schemas import EventRead
from ..services.filtering import apply_consumer_filter, find_consumer_by_api_key
router = APIRouter(prefix="/api/v1", tags=["distribution"])
def get_consumer_from_api_key(
authorization: str | None = Header(default=None),
db: Session = Depends(get_db),
):
if not authorization or not authorization.startswith("Bearer "):
raise HTTPException(status_code=401, detail="Missing or invalid Authorization header")
api_key = authorization.removeprefix("Bearer ").strip()
consumer = find_consumer_by_api_key(db, api_key)
if not consumer:
raise HTTPException(status_code=401, detail="Invalid API key")
return consumer
@router.get("/events", response_model=list[EventRead])
def list_filtered_events(
limit: int = Query(default=100, ge=1, le=1000),
offset: int = Query(default=0, ge=0),
consumer=Depends(get_consumer_from_api_key),
db: Session = Depends(get_db),
):
events = apply_consumer_filter(db, consumer)
return events[offset : offset + limit]
+132
View File
@@ -0,0 +1,132 @@
from datetime import datetime
from typing import Any, Literal
from pydantic import BaseModel, ConfigDict, Field
ObjectType = Literal["point", "marker", "zone", "other"]
class MapObjectCreate(BaseModel):
name: str = Field(min_length=1, max_length=255)
description: str = ""
type: ObjectType
latitude: float = Field(ge=-90, le=90)
longitude: float = Field(ge=-180, le=180)
created_at: datetime | None = None
class MapObjectRead(BaseModel):
model_config = ConfigDict(from_attributes=True)
id: int
name: str
description: str
type: ObjectType
latitude: float
longitude: float
event_id: int | None = None
created_at: datetime
class MapObjectUpdate(BaseModel):
name: str | None = Field(default=None, min_length=1, max_length=255)
description: str | None = None
type: ObjectType | None = None
latitude: float | None = Field(default=None, ge=-90, le=90)
longitude: float | None = Field(default=None, ge=-180, le=180)
created_at: datetime | None = None
class ObjectMediaRead(BaseModel):
model_config = ConfigDict(from_attributes=True)
id: int
object_id: int
original_name: str
content_type: str
size: int
created_at: datetime
url: str
class EventRead(BaseModel):
model_config = ConfigDict(from_attributes=True)
id: int
source_type: str
source_url: str
raw_text: str
title: str
description: str
locality: str
latitude: float | None
longitude: float | None
event_date: datetime | None
ingested_at: datetime
region: str | None
topic: str | None
tags: list[str] | None
metadata: dict[str, Any] | None = Field(validation_alias="metadata_")
class IngestEventItem(BaseModel):
source_type: str = "telegram"
source_url: str
raw_text: str = ""
title: str = ""
description: str = ""
locality: str = ""
latitude: float | None = None
longitude: float | None = None
event_date: datetime | None = None
region: str | None = None
topic: str | None = None
tags: list[str] | None = None
metadata: dict[str, Any] | None = None
class IngestRequest(BaseModel):
job_id: int | None = None
events: list[IngestEventItem] = Field(default_factory=list)
class IngestResponse(BaseModel):
ingested: int
updated: int
map_objects_synced: int
class ParseJobCreate(BaseModel):
source_type: str = "telegram"
source_config: dict[str, Any] = Field(default_factory=dict)
schedule: str | None = None
class ParseJobRead(BaseModel):
model_config = ConfigDict(from_attributes=True)
id: int
source_type: str
source_config: dict[str, Any]
schedule: str | None
status: str
last_run_at: datetime | None
last_error: str | None
created_at: datetime
class ConsumerCreate(BaseModel):
name: str
regions: list[str] | None = None
topics: list[str] | None = None
date_from: datetime | None = None
class ConsumerRead(BaseModel):
model_config = ConfigDict(from_attributes=True)
id: int
name: str
is_active: bool
created_at: datetime
api_key: str | None = None
+68
View File
@@ -0,0 +1,68 @@
import os
from datetime import datetime, timezone
from sqlalchemy.orm import Session
from .models import Consumer, ConsumerFilter, MapObject
from .services.filtering import hash_api_key
SEED_OBJECTS = [
{
"name": "Красная площадь",
"description": "Главная площадь Москвы, исторический центр города.",
"type": "marker",
"latitude": 55.7539,
"longitude": 37.6208,
"created_at": datetime(2018, 5, 9, 12, 0, tzinfo=timezone.utc),
},
{
"name": "ВДНХ",
"description": "Выставка достижений народного хозяйства — крупный выставочный комплекс.",
"type": "zone",
"latitude": 55.8298,
"longitude": 37.6361,
"created_at": datetime(2020, 8, 15, 10, 30, tzinfo=timezone.utc),
},
{
"name": "МГУ",
"description": "Московский государственный университет имени М.В. Ломоносова.",
"type": "point",
"latitude": 55.7033,
"longitude": 37.5307,
"created_at": datetime(2022, 2, 12, 14, 0, tzinfo=timezone.utc),
},
{
"name": "Парк Горького",
"description": "Центральный парк культуры и отдыха имени М. Горького.",
"type": "other",
"latitude": 55.7312,
"longitude": 37.6013,
"created_at": datetime(2024, 6, 1, 9, 0, tzinfo=timezone.utc),
},
]
def seed_objects(db: Session) -> None:
if db.query(MapObject).count() > 0:
return
for item in SEED_OBJECTS:
db.add(MapObject(**item))
db.commit()
def seed_test_consumer(db: Session) -> None:
if db.query(Consumer).filter(Consumer.name == "test-pi").first():
return
api_key = os.getenv("TEST_PI_API_KEY", "test-pi-api-key-change-me")
consumer = Consumer(
name="test-pi",
api_key_hash=hash_api_key(api_key),
is_active=True,
)
db.add(consumer)
db.flush()
db.add(ConsumerFilter(consumer_id=consumer.id, regions=None, topics=None))
db.commit()
@@ -0,0 +1,109 @@
import hashlib
import secrets
from datetime import datetime
from sqlalchemy.orm import Session
from ..models import Consumer, ConsumerFilter, Event, MapObject
def hash_api_key(api_key: str) -> str:
return hashlib.sha256(api_key.encode()).hexdigest()
def generate_api_key() -> str:
return secrets.token_urlsafe(32)
def create_consumer(
db: Session,
name: str,
regions: list[str] | None = None,
topics: list[str] | None = None,
date_from: datetime | None = None,
) -> tuple[Consumer, str]:
api_key = generate_api_key()
consumer = Consumer(name=name, api_key_hash=hash_api_key(api_key), is_active=True)
db.add(consumer)
db.flush()
consumer_filter = ConsumerFilter(
consumer_id=consumer.id,
regions=regions,
topics=topics,
date_from=date_from,
)
db.add(consumer_filter)
db.commit()
db.refresh(consumer)
return consumer, api_key
def find_consumer_by_api_key(db: Session, api_key: str) -> Consumer | None:
key_hash = hash_api_key(api_key)
return (
db.query(Consumer)
.filter(Consumer.api_key_hash == key_hash, Consumer.is_active.is_(True))
.first()
)
def apply_consumer_filter(db: Session, consumer: Consumer) -> list[Event]:
query = db.query(Event).order_by(Event.ingested_at.desc())
consumer_filter = consumer.filter
if consumer_filter:
if consumer_filter.regions:
query = query.filter(Event.region.in_(consumer_filter.regions))
if consumer_filter.topics:
query = query.filter(Event.topic.in_(consumer_filter.topics))
if consumer_filter.date_from:
query = query.filter(Event.event_date >= consumer_filter.date_from)
return query.all()
def sync_event_to_map_object(db: Session, event: Event) -> MapObject | None:
if event.latitude is None or event.longitude is None:
return None
name = event.title or event.locality or f"Событие #{event.id}"
description = event.description or event.raw_text or ""
existing = (
db.query(MapObject)
.filter(MapObject.event_id == event.id)
.first()
)
if existing:
existing.name = name
existing.description = description
existing.latitude = event.latitude
existing.longitude = event.longitude
return existing
by_url = (
db.query(MapObject)
.join(Event, MapObject.event_id == Event.id)
.filter(Event.source_url == event.source_url)
.first()
)
if by_url:
by_url.event_id = event.id
by_url.name = name
by_url.description = description
by_url.latitude = event.latitude
by_url.longitude = event.longitude
return by_url
obj = MapObject(
name=name,
description=description,
type="marker",
latitude=event.latitude,
longitude=event.longitude,
event_id=event.id,
created_at=event.event_date or event.ingested_at,
)
db.add(obj)
return obj
@@ -0,0 +1,72 @@
from sqlalchemy.orm import Session
from ..models import Event, ParseJob
from ..schemas import IngestEventItem
from .filtering import sync_event_to_map_object
def ingest_events(
db: Session,
items: list[IngestEventItem],
job_id: int | None = None,
) -> tuple[int, int, int]:
ingested = 0
updated = 0
map_synced = 0
for item in items:
existing = (
db.query(Event)
.filter(Event.source_url == item.source_url)
.first()
)
if existing:
existing.source_type = item.source_type
existing.raw_text = item.raw_text
existing.title = item.title
existing.description = item.description
existing.locality = item.locality
existing.latitude = item.latitude
existing.longitude = item.longitude
existing.event_date = item.event_date
existing.region = item.region
existing.topic = item.topic
existing.tags = item.tags
existing.metadata_ = item.metadata
event = existing
updated += 1
else:
event = Event(
source_type=item.source_type,
source_url=item.source_url,
raw_text=item.raw_text,
title=item.title,
description=item.description,
locality=item.locality,
latitude=item.latitude,
longitude=item.longitude,
event_date=item.event_date,
region=item.region,
topic=item.topic,
tags=item.tags,
metadata_=item.metadata,
)
db.add(event)
ingested += 1
db.flush()
if sync_event_to_map_object(db, event):
map_synced += 1
if job_id is not None:
job = db.query(ParseJob).filter(ParseJob.id == job_id).first()
if job:
from datetime import datetime, timezone
job.status = "completed"
job.last_run_at = datetime.now(timezone.utc)
job.last_error = None
db.commit()
return ingested, updated, map_synced
@@ -0,0 +1,20 @@
import json
import os
import redis
REDIS_URL = os.getenv("REDIS_URL", "redis://redis:6379/0")
JOB_QUEUE_KEY = "cp:jobs"
def get_redis() -> redis.Redis:
return redis.from_url(REDIS_URL, decode_responses=True)
def enqueue_job(job_id: int, source_type: str, source_config: dict) -> None:
payload = {
"job_id": job_id,
"source_type": source_type,
"source_config": source_config,
}
get_redis().rpush(JOB_QUEUE_KEY, json.dumps(payload))
+39
View File
@@ -0,0 +1,39 @@
import os
import uuid
from pathlib import Path
UPLOAD_DIR = Path(os.getenv("UPLOAD_DIR", "/data/uploads"))
ALLOWED_CONTENT_TYPES = {
"image/jpeg",
"image/png",
"image/gif",
"image/webp",
"video/mp4",
"video/webm",
}
MAX_FILE_SIZE = 20 * 1024 * 1024
def ensure_upload_dir() -> None:
UPLOAD_DIR.mkdir(parents=True, exist_ok=True)
def is_allowed_content_type(content_type: str) -> bool:
return content_type in ALLOWED_CONTENT_TYPES
def build_stored_name(original_name: str) -> str:
suffix = Path(original_name).suffix.lower()
return f"{uuid.uuid4().hex}{suffix}"
def media_file_path(stored_name: str) -> Path:
return UPLOAD_DIR / stored_name
def remove_media_file(stored_name: str) -> None:
path = media_file_path(stored_name)
if path.exists():
path.unlink()