07088e60e9
Phase 1 Backend Implementation: - ✅ MongoDB data models (Keyword, Pipeline, User, Application) - ✅ Pydantic schemas for all models with validation - ✅ KeywordService: Full CRUD, filtering, pagination, stats, toggle status - ✅ PipelineService: Full CRUD, start/stop/restart, logs, config management - ✅ Keywords API: 8 endpoints with complete functionality - ✅ Pipelines API: 11 endpoints with complete functionality - ✅ Updated TODO.md to reflect completion Key Features: - Async MongoDB operations with Motor - Comprehensive filtering and pagination support - Pipeline logging system - Statistics tracking for keywords and pipelines - Proper error handling with HTTP status codes - Type-safe request/response models Files Added: - models/: 4 data models with PyObjectId support - schemas/: 4 schema modules with Create/Update/Response patterns - services/: KeywordService (234 lines) + PipelineService (332 lines) Files Modified: - api/keywords.py: 40 → 212 lines (complete implementation) - api/pipelines.py: 25 → 300 lines (complete implementation) - TODO.md: Updated checklist with completed items Next Steps: - UserService with authentication - ApplicationService for OAuth2 - MonitoringService - Redis integration - Frontend implementation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
71 lines
2.4 KiB
Python
71 lines
2.4 KiB
Python
from datetime import datetime
|
|
from typing import Optional, Dict, Any
|
|
from pydantic import BaseModel, Field
|
|
from bson import ObjectId
|
|
|
|
|
|
class PyObjectId(ObjectId):
|
|
"""Custom ObjectId type for Pydantic"""
|
|
@classmethod
|
|
def __get_validators__(cls):
|
|
yield cls.validate
|
|
|
|
@classmethod
|
|
def validate(cls, v):
|
|
if not ObjectId.is_valid(v):
|
|
raise ValueError("Invalid ObjectId")
|
|
return ObjectId(v)
|
|
|
|
@classmethod
|
|
def __get_pydantic_json_schema__(cls, field_schema):
|
|
field_schema.update(type="string")
|
|
|
|
|
|
class PipelineStats(BaseModel):
|
|
"""Pipeline statistics"""
|
|
total_processed: int = Field(default=0)
|
|
success_count: int = Field(default=0)
|
|
error_count: int = Field(default=0)
|
|
last_run: Optional[datetime] = None
|
|
average_duration_seconds: Optional[float] = None
|
|
|
|
|
|
class Pipeline(BaseModel):
|
|
"""Pipeline data model for process management"""
|
|
|
|
id: Optional[PyObjectId] = Field(default=None, alias="_id")
|
|
name: str = Field(..., min_length=1, max_length=100)
|
|
type: str = Field(..., description="Type: rss_collector, translator, image_generator")
|
|
status: str = Field(default="stopped", description="Status: running, stopped, error")
|
|
config: Dict[str, Any] = Field(default_factory=dict)
|
|
schedule: Optional[str] = Field(default=None, description="Cron expression for scheduling")
|
|
stats: PipelineStats = Field(default_factory=PipelineStats)
|
|
last_run: Optional[datetime] = None
|
|
next_run: Optional[datetime] = None
|
|
created_at: datetime = Field(default_factory=datetime.utcnow)
|
|
updated_at: datetime = Field(default_factory=datetime.utcnow)
|
|
|
|
class Config:
|
|
populate_by_name = True
|
|
arbitrary_types_allowed = True
|
|
json_encoders = {ObjectId: str}
|
|
json_schema_extra = {
|
|
"example": {
|
|
"name": "RSS Collector - Politics",
|
|
"type": "rss_collector",
|
|
"status": "running",
|
|
"config": {
|
|
"interval_minutes": 30,
|
|
"max_articles": 100,
|
|
"categories": ["politics"]
|
|
},
|
|
"schedule": "*/30 * * * *",
|
|
"stats": {
|
|
"total_processed": 1523,
|
|
"success_count": 1500,
|
|
"error_count": 23,
|
|
"average_duration_seconds": 45.2
|
|
}
|
|
}
|
|
}
|