"""正文提取数据模型"""

from pydantic import BaseModel, Field


class ProcessedArticle(BaseModel):
    """经过正文提取清洗后的文章"""

    source_id: str
    source_name: str
    url: str
    url_hash: str
    title: str = ""
    content: str = ""                    # 清洗后的正文（英文）
    publish_time: str = ""               # ISO 8601
    author: str = ""
    word_count: int = 0
    md_path: str = ""                    # 原始 Markdown 路径
    html_path: str = ""                  # 原始 HTML 路径
    status: str = "success"              # success | no_content | failed
    extractor: str = "trafilatura"       # trafilatura | crawl4ai_md | none
    error: str = ""
    source_ids: list[str] = Field(
        default_factory=list,
        description="去重合并后的所有来源 ID（M3 去重时跨源命中重复会追加；"
        "首个来源始终为 source_id）",
    )