schemas.py

from __future__ import annotations
from pydantic import BaseModel
from typing import Optional, List
from datetime import datetime


class DatasetInfo(BaseModel):
    id: int
    name: str
    file_name: Optional[str] = None
    sheet_name: Optional[str] = None
    dataset_role: str
    data_scope: str
    vector_fields: Optional[str] = None
    row_count: int = 0

    class Config:
        from_attributes = True


class TaskCreate(BaseModel):
    match_mode: str = "two_file"
    top_k: int = 3
    min_threshold: float = 0.70
    candidate_scope: str = "current_task_target"


class TaskProgress(BaseModel):
    id: int
    task_code: str
    status: str
    source_row_count: int
    target_row_count: int
    reused_vectors: int
    new_vectors: int
    progress_parse_source: int
    progress_parse_target: int
    progress_vectorize: int
    progress_load_candidates: int
    progress_similarity: int
    progress_rerank: int = 0
    progress_save_results: int

    class Config:
        from_attributes = True


class TaskDetail(BaseModel):
    id: int
    task_code: str
    match_mode: str
    candidate_scope: str
    top_k: int
    min_threshold: float
    status: str
    source_row_count: int
    target_row_count: int
    high_match_count: int
    low_confidence_count: int
    reused_vectors: int
    new_vectors: int
    source_dataset: Optional[DatasetInfo] = None
    target_dataset: Optional[DatasetInfo] = None
    created_time: Optional[datetime] = None
    updated_time: Optional[datetime] = None

    class Config:
        from_attributes = True


class TaskListItem(BaseModel):
    id: int
    task_code: str
    match_mode: str
    candidate_scope: str
    source_dataset_name: Optional[str] = None
    target_dataset_name: Optional[str] = None
    status: str
    is_archived: int = 0
    is_delete: int = 0
    created_time: Optional[datetime] = None


class MatchResultItem(BaseModel):
    id: int
    source_row_id: int
    source_row_number: int
    source_text: str
    target_text: str
    similarity_score: float
    rerank_score: Optional[float] = None
    match_level: str
    candidate_scope: Optional[str] = None
    is_confirmed: int = 0


class MatchResultPage(BaseModel):
    items: List[MatchResultItem]
    total: int
    page: int
    page_size: int


class CandidateDetail(BaseModel):
    rank: int
    rerank_rank: Optional[int] = None
    target_row_id: int
    target_text: str
    similarity_score: float
    rerank_score: Optional[float] = None
    match_level: str
    dataset_role: str
    candidate_scope: Optional[str] = None
    data_row_id: int
    is_confirmed: int = 0


class SourceWithCandidates(BaseModel):
    source_row_id: int
    source_text: str
    source_row_number: int
    dataset_role: str
    data_row_id: int
    candidates: List[CandidateDetail]


class SheetInfo(BaseModel):
    sheet_names: List[str]
    columns: dict


class UploadResponse(BaseModel):
    dataset_id: int
    file_name: str
    sheet_names: List[str]
    columns: dict
    all_columns: dict = {}


class SettingItem(BaseModel):
    key: str
    value: str


class SettingsResponse(BaseModel):
    settings: dict