feat(data-process): 支持任务重新生成

backend/app/modules/data_process/store.py

@@ -20,6 +20,28 @@ from app.modules.data_process.algorithms import estimate_token_count, stable_spl
 TASK_STATUSES = {"pending", "running", "completed", "failed", "stopped"}
 EDITABLE_STATUSES = {"pending", "failed", "stopped", "completed"}
 
+_PREVIEW_CONFIG_ALIASES = {
+    "preprocess_options": "preprocessOptions",
+    "chunk_method": "chunkMethod",
+    "chunk_size": "chunkSize",
+    "chunk_overlap": "chunkOverlap",
+    "min_chunk_size": "minChunkSize",
+    "semantic_breakpoint_percentile": "semanticBreakpointPercentile",
+    "preserve_tables": "preserveTables",
+    "preserve_code_blocks": "preserveCodeBlocks",
+    "preserve_lists": "preserveLists",
+}
+_UNSTRUCTURED_PREVIEW_DEFAULTS: dict[str, Any] = {
+    "chunk_method": "layout_hybrid",
+    "chunk_size": 800,
+    "chunk_overlap": 100,
+    "min_chunk_size": 100,
+    "semantic_breakpoint_percentile": 95,
+    "preserve_tables": True,
+    "preserve_code_blocks": True,
+    "preserve_lists": True,
+}
+
 
 class DataProcessStoreError(RuntimeError):
     pass
@@ -64,6 +86,49 @@ def _json_value(value: Any, default: Any) -> Any:
         return default
 
 
+def _preview_config_value(config: dict[str, Any], key: str, default: Any) -> Any:
+    if key in config:
+        return config[key]
+    return config.get(_PREVIEW_CONFIG_ALIASES[key], default)
+
+
+def _normalized_preprocess_options(config: dict[str, Any]) -> Any:
+    value = _preview_config_value(config, "preprocess_options", [])
+    if isinstance(value, (list, tuple, set)):
+        return tuple(sorted({str(item) for item in value}))
+    return value
+
+
+def _preview_config_projection(
+    process_type: str,
+    config: dict[str, Any],
+) -> dict[str, Any]:
+    """只投影会改变预览切片的配置。
+
+    生成模型、提示词、温度等参数不影响源文切片，因此不应该
+    破坏用户已经校对过的预览内容。
+    """
+
+    projection: dict[str, Any] = {
+        "preprocess_options": _normalized_preprocess_options(config),
+    }
+    if process_type != "unstructured":
+        return projection
+    for key, default in _UNSTRUCTURED_PREVIEW_DEFAULTS.items():
+        projection[key] = _preview_config_value(config, key, default)
+    return projection
+
+
+def _preview_config_changed(
+    process_type: str,
+    current_config: dict[str, Any],
+    next_config: dict[str, Any],
+) -> bool:
+    return _preview_config_projection(process_type, current_config) != _preview_config_projection(
+        process_type, next_config
+    )
+
+
 def _serialize_value(value: Any) -> Any:
     if isinstance(value, (datetime, date)):
         return value.isoformat().replace("+00:00", "Z")
@@ -361,6 +426,102 @@ class DataProcessStore:
             raise ConflictError("data process task name already exists") from exc
         return _decode_row(row) or {}
 
+    def prepare_regeneration(
+        self,
+        task_id: str,
+        payload: dict[str, Any],
+    ) -> dict[str, Any]:
+        """在一个事务中将已有任务恢复为可重新生成状态。
+
+        已发布数据集是可被其他任务使用的独立产物，此处只解除当前任务的
+        输出指针，不删除数据集实体。用户完成新一轮生成后，可再次发布
+        以原子替换三个分割数据集的内容。
+        """
+
+        try:
+            with self.connect() as conn:
+                task = self._task_in_connection(conn, task_id, for_update=True)
+                if task["status"] == "running":
+                    raise ConflictError("running task cannot be prepared for regeneration")
+
+                current_updated_at = _serialize_value(task.get("updated_at"))
+                if payload["expected_updated_at"] != current_updated_at:
+                    raise ConflictError("data process task was modified by another request")
+
+                process_type = str(payload["process_type"])
+                if process_type != str(task["process_type"]):
+                    raise InvalidStateError("process_type cannot be changed during regeneration")
+
+                current_config = dict(task.get("config") or {})
+                next_config = dict(payload.get("config") or {})
+                preview_invalidated = _preview_config_changed(
+                    process_type,
+                    current_config,
+                    next_config,
+                )
+                published_row = conn.execute(
+                    """
+                    SELECT EXISTS(
+                        SELECT 1 FROM datasets
+                        WHERE source_task_id=%s AND source='task'
+                    ) AS exists
+                    """,
+                    (task_id,),
+                ).fetchone()
+                published_outputs_preserved = bool(task.get("output_dataset_id")) or bool(
+                    published_row and published_row.get("exists")
+                )
+
+                # 删除顺序保证结果不再指向即将被替换的切片。
+                conn.execute(
+                    "DELETE FROM data_process_results WHERE task_id=%s",
+                    (task_id,),
+                )
+                if preview_invalidated:
+                    conn.execute(
+                        "DELETE FROM data_process_preview_items WHERE task_id=%s",
+                        (task_id,),
+                    )
+                    preview_count = 0
+                else:
+                    preview_row = conn.execute(
+                        """
+                        SELECT COUNT(*) AS count FROM data_process_preview_items
+                        WHERE task_id=%s
+                        """,
+                        (task_id,),
+                    ).fetchone()
+                    preview_count = int((preview_row or {}).get("count") or 0)
+
+                now = utcnow()
+                row = conn.execute(
+                    """
+                    UPDATE data_process_tasks
+                    SET name=%s, description=%s, config=%s, status='pending', progress=%s,
+                        output_dataset_id=NULL, output_count=0, filtered_count=0,
+                        duplicate_count=0, error_count=0, failure_reason=NULL,
+                        generation_run_id=NULL, started_at=NULL, completed_at=NULL,
+                        updated_at=%s
+                    WHERE id=%s
+                    RETURNING *
+                    """,
+                    (
+                        payload["name"],
+                        payload.get("description") or "",
+                        json_dumps(next_config),
+                        20 if preview_count else 0,
+                        now,
+                        task_id,
+                    ),
+                ).fetchone()
+        except psycopg.errors.UniqueViolation as exc:
+            raise ConflictError("data process task name already exists") from exc
+        return {
+            "task": _decode_row(row) or {},
+            "preview_invalidated": preview_invalidated,
+            "published_outputs_preserved": published_outputs_preserved,
+        }
+
     def delete_task(self, task_id: str, *, deleted_by: str | None = None) -> None:
         with self.connect() as conn:
             task = self._task_in_connection(conn, task_id, for_update=True)
@@ -480,12 +641,21 @@ class DataProcessStore:
                         ),
                     ).fetchone()
                     created.append(_decode_row(row) or {})
+                # 前端会只对本次新增的源文件构建预览，因此必须保留旧
+                # 文件的切片。任何源文件增加都会使旧生成结果失效。
                 conn.execute("DELETE FROM data_process_results WHERE task_id=%s", (task_id,))
-                conn.execute("DELETE FROM data_process_preview_items WHERE task_id=%s", (task_id,))
+                preview_row = conn.execute(
+                    """
+                    SELECT COUNT(*) AS count FROM data_process_preview_items
+                    WHERE task_id=%s
+                    """,
+                    (task_id,),
+                ).fetchone()
+                preview_count = int((preview_row or {}).get("count") or 0)
                 conn.execute(
                     """
                     UPDATE data_process_tasks
-                    SET status='pending', progress=0, output_count=0, filtered_count=0,
+                    SET status='pending', progress=%s, output_count=0, filtered_count=0,
                         duplicate_count=0, error_count=0, failure_reason=NULL,
                         generation_run_id=NULL, started_at=NULL, completed_at=NULL, input_count=(
                         SELECT COALESCE(SUM(record_count), 0)
@@ -494,7 +664,7 @@ class DataProcessStore:
                     ), updated_at=%s
                     WHERE id=%s
                     """,
-                    (task_id, now, task_id),
+                    (20 if preview_count else 0, task_id, now, task_id),
                 )
         except psycopg.errors.UniqueViolation as exc:
             raise ConflictError(