(cls, data_path: Path, content_col="content", meta_col="metadata")
| 121 | |
| 122 | @classmethod |
| 123 | def from_path(cls, data_path: Path, content_col="content", meta_col="metadata"): |
| 124 | if not data_path.exists(): |
| 125 | raise FileNotFoundError(f"File {data_path} not found.") |
| 126 | data = read_data(data_path) |
| 127 | if isinstance(data, pd.DataFrame): |
| 128 | validate_cols(content_col, data) |
| 129 | return cls(data=data, content=str(data), content_col=content_col, meta_col=meta_col) |
| 130 | try: |
| 131 | content = data_path.read_text() |
| 132 | except Exception as e: |
| 133 | logger.debug(f"Load {str(data_path)} error: {e}") |
| 134 | content = "" |
| 135 | return cls(data=data, content=content, content_col=content_col, meta_col=meta_col) |
| 136 | |
| 137 | def _get_docs_and_metadatas_by_df(self) -> (list, list): |
| 138 | df = self.data |
nothing calls this directly
no test coverage detected