Files
ecm_sync_system/sync_state_machine/config/builder.py
T
2026-04-01 11:52:57 +08:00

232 lines
8.3 KiB
Python

from __future__ import annotations
from pathlib import Path
from typing import Any, Dict, Mapping, Optional, Union
from pydantic import BaseModel
from ..common.registry import DomainRegistry
from .datasource_config import DataSourceConfig
from .pipeline_config import PipelineRunConfig
from .run_presets import load_overrides_from_file
from .strategy_config import ConfigPresets, StrategyRuntimeConfig, resolve_domain_option_config
def _deep_merge(base: Mapping[str, Any], override: Mapping[str, Any]) -> Dict[str, Any]:
merged: Dict[str, Any] = dict(base)
for key, value in override.items():
if isinstance(value, dict) and isinstance(merged.get(key), dict):
if key in {"local_datasource", "remote_datasource"}:
current_type = merged[key].get("type")
next_type = value.get("type", current_type)
if current_type != next_type:
merged[key] = dict(value)
continue
merged[key] = _deep_merge(merged[key], value)
else:
merged[key] = value
return merged
def _build_default_strategy_runtime_config(node_type: str) -> StrategyRuntimeConfig | None:
strategy_class = DomainRegistry.get_strategy_class(node_type)
if strategy_class is None:
return None
config = strategy_class.default_config.model_copy(deep=True)
config.domain_option = resolve_domain_option_config(
getattr(strategy_class, "domain_option_model", None),
config.domain_option,
)
return StrategyRuntimeConfig(
node_type=node_type,
config=config,
)
def _default_strategy_map(node_types: list[str]) -> Dict[str, StrategyRuntimeConfig]:
strategy_map: Dict[str, StrategyRuntimeConfig] = {}
for node_type in node_types:
runtime_cfg = _build_default_strategy_runtime_config(node_type)
if runtime_cfg is None:
continue
strategy_map[node_type] = runtime_cfg
return strategy_map
def _merge_strategy_runtime_config(
runtime_cfg: StrategyRuntimeConfig,
raw_override: Any,
) -> StrategyRuntimeConfig:
override = dict(raw_override or {})
override.pop("node_type", None)
deprecated_keys = [key for key in ("force_sync", "load_mode") if key in override]
if deprecated_keys:
joined = ", ".join(deprecated_keys)
raise ValueError(
f"Strategy override for {runtime_cfg.node_type!r} contains unsupported legacy keys: {joined}. "
"Use skip_sync under strategies.<node_type> or datasource.handler_configs instead."
)
preset = override.pop("preset", None)
if preset:
runtime_cfg.config = runtime_cfg.config.model_validate(
_deep_merge(
runtime_cfg.config.model_dump(),
ConfigPresets.get_preset(str(preset)).model_dump(exclude_defaults=True),
)
)
if "config" in override and isinstance(override["config"], dict):
runtime_cfg.config = runtime_cfg.config.model_validate(
_deep_merge(runtime_cfg.config.model_dump(), override.pop("config"))
)
if override:
runtime_cfg.config = runtime_cfg.config.model_validate(
_deep_merge(runtime_cfg.config.model_dump(), override)
)
strategy_class = DomainRegistry.get_strategy_class(runtime_cfg.node_type)
runtime_cfg.config.domain_option = resolve_domain_option_config(
getattr(strategy_class, "domain_option_model", None) if strategy_class is not None else None,
runtime_cfg.config.domain_option,
)
return runtime_cfg
def _apply_strategy_overrides(
node_types: list[str],
strategy_overrides: Any,
) -> list[StrategyRuntimeConfig]:
strategy_map = _default_strategy_map(node_types)
if isinstance(strategy_overrides, list):
for item in strategy_overrides:
raw_item = dict(item or {})
node_type = str(raw_item.get("node_type") or "")
if not node_type:
raise ValueError("Strategy override list item missing required node_type")
runtime_cfg = strategy_map.get(node_type)
if runtime_cfg is None:
runtime_cfg = _build_default_strategy_runtime_config(node_type) or StrategyRuntimeConfig(node_type=node_type)
strategy_map[node_type] = _merge_strategy_runtime_config(runtime_cfg, raw_item)
return [strategy_map[n] for n in node_types if n in strategy_map]
if not isinstance(strategy_overrides, dict):
return [strategy_map[n] for n in node_types if n in strategy_map]
for node_type, raw_override in strategy_overrides.items():
if node_type not in strategy_map:
strategy_map[node_type] = _build_default_strategy_runtime_config(node_type) or StrategyRuntimeConfig(node_type=node_type)
runtime_cfg = strategy_map[node_type]
strategy_map[node_type] = _merge_strategy_runtime_config(runtime_cfg, raw_override)
return [strategy_map[n] for n in node_types if n in strategy_map]
def config_snapshot(config: PipelineRunConfig) -> Dict[str, Any]:
snap = config.model_dump(mode="json")
for key in ("local_datasource", "remote_datasource"):
ds = snap.get(key) or {}
if ds.get("api_secret"):
ds["api_secret"] = "***"
return snap
def build_default_config(project_root: Path) -> PipelineRunConfig:
defaults = {
"local_datasource": {
"type": "jsonl",
"jsonl_dir": str(project_root / "filtered_datasource" / "datasource" / "ecm-2025-12-02"),
"read_only": False,
"handler_configs": {},
},
"remote_datasource": {
"type": "jsonl",
"jsonl_dir": str(project_root / "remote_datasource" / "datasource"),
"read_only": False,
"handler_configs": {},
},
"persist": {
"db_path": str(project_root / "test_results" / "sync_state_machine" / "pipeline_default.db"),
"enable": True,
"wipe_on_start": False,
},
"logging": {
"initialize": True,
"file_path": None,
"level": 20,
"suppress_node_logs": True,
},
}
config = PipelineRunConfig.model_validate(defaults)
config.strategies = _apply_strategy_overrides(config.node_types, {})
return config
def apply_config_overrides(config: PipelineRunConfig, overrides: Dict[str, Any]) -> PipelineRunConfig:
merged = _deep_merge(config.model_dump(), overrides)
raw_strategies = merged.pop("strategies", None)
resolved = PipelineRunConfig.model_validate(merged)
if raw_strategies is not None:
resolved.strategies = _apply_strategy_overrides(resolved.node_types, raw_strategies)
else:
resolved.strategies = _apply_strategy_overrides(resolved.node_types, {})
return resolved
def build_config(
*,
project_root: Path,
local_datasource: Optional[Union[DataSourceConfig, Dict[str, Any]]] = None,
remote_datasource: Optional[Union[DataSourceConfig, Dict[str, Any]]] = None,
overrides: Optional[Dict[str, Any]] = None,
overrides_file: Optional[Union[str, Path]] = None,
dotenv_file: Optional[Union[str, Path]] = None,
) -> PipelineRunConfig:
if dotenv_file is not None:
raise ValueError("dotenv_file is no longer supported; use overrides_file instead")
config = build_default_config(project_root)
if local_datasource is not None:
local_payload = (
local_datasource.model_dump() if isinstance(local_datasource, BaseModel) else dict(local_datasource)
)
config = apply_config_overrides(config, {"local_datasource": local_payload})
if remote_datasource is not None:
remote_payload = (
remote_datasource.model_dump() if isinstance(remote_datasource, BaseModel) else dict(remote_datasource)
)
config = apply_config_overrides(config, {"remote_datasource": remote_payload})
if overrides_file:
override_path = Path(overrides_file)
file_data = load_overrides_from_file(override_path, project_root)
config = apply_config_overrides(config, file_data)
if overrides:
config = apply_config_overrides(config, overrides)
return config
def build_config_from_file(
*,
project_root: Path,
file_path: Union[str, Path],
) -> PipelineRunConfig:
return build_config(project_root=project_root, overrides_file=Path(file_path))