Files
ss-tools/backend/src/core/migration_engine.py
2026-02-25 13:35:09 +03:00

223 lines
11 KiB
Python

# [DEF:backend.src.core.migration_engine:Module]
#
# @SEMANTICS: migration, engine, zip, yaml, transformation
# @PURPOSE: Handles the interception and transformation of Superset asset ZIP archives.
# @LAYER: Core
# @RELATION: DEPENDS_ON -> PyYAML
#
# @INVARIANT: ZIP structure must be preserved after transformation.
# [SECTION: IMPORTS]
import zipfile
import yaml
import os
import json
import re
import tempfile
from pathlib import Path
from typing import Dict, Optional, List
from .logger import logger, belief_scope
from src.core.mapping_service import IdMappingService
from src.models.mapping import ResourceType
# [/SECTION]
# [DEF:MigrationEngine:Class]
# @PURPOSE: Engine for transforming Superset export ZIPs.
class MigrationEngine:
# [DEF:__init__:Function]
# @PURPOSE: Initializes the migration engine with optional ID mapping service.
# @PARAM: mapping_service (Optional[IdMappingService]) - Used for resolving target environment integer IDs.
def __init__(self, mapping_service: Optional[IdMappingService] = None):
self.mapping_service = mapping_service
# [/DEF:__init__:Function]
# [DEF:transform_zip:Function]
# @PURPOSE: Extracts ZIP, replaces database UUIDs in YAMLs, patches cross-filters, and re-packages.
# @PARAM: zip_path (str) - Path to the source ZIP file.
# @PARAM: output_path (str) - Path where the transformed ZIP will be saved.
# @PARAM: db_mapping (Dict[str, str]) - Mapping of source UUID to target UUID.
# @PARAM: strip_databases (bool) - Whether to remove the databases directory from the archive.
# @PARAM: target_env_id (Optional[str]) - Used if fix_cross_filters is True to know which environment map to use.
# @PARAM: fix_cross_filters (bool) - Whether to patch dashboard json_metadata.
# @PRE: zip_path must point to a valid Superset export archive.
# @POST: Transformed archive is saved to output_path.
# @RETURN: bool - True if successful.
def transform_zip(self, zip_path: str, output_path: str, db_mapping: Dict[str, str], strip_databases: bool = True, target_env_id: Optional[str] = None, fix_cross_filters: bool = False) -> bool:
"""
Transform a Superset export ZIP by replacing database UUIDs and optionally fixing cross-filters.
"""
with belief_scope("MigrationEngine.transform_zip"):
with tempfile.TemporaryDirectory() as temp_dir_str:
temp_dir = Path(temp_dir_str)
try:
# 1. Extract
logger.info(f"[MigrationEngine.transform_zip][Action] Extracting ZIP: {zip_path}")
with zipfile.ZipFile(zip_path, 'r') as zf:
zf.extractall(temp_dir)
# 2. Transform YAMLs (Databases)
dataset_files = list(temp_dir.glob("**/datasets/**/*.yaml")) + list(temp_dir.glob("**/datasets/*.yaml"))
dataset_files = list(set(dataset_files))
logger.info(f"[MigrationEngine.transform_zip][State] Found {len(dataset_files)} dataset files.")
for ds_file in dataset_files:
logger.info(f"[MigrationEngine.transform_zip][Action] Transforming dataset: {ds_file}")
self._transform_yaml(ds_file, db_mapping)
# 2.5 Patch Cross-Filters (Dashboards)
if fix_cross_filters and self.mapping_service and target_env_id:
dash_files = list(temp_dir.glob("**/dashboards/**/*.yaml")) + list(temp_dir.glob("**/dashboards/*.yaml"))
dash_files = list(set(dash_files))
logger.info(f"[MigrationEngine.transform_zip][State] Found {len(dash_files)} dashboard files for patching.")
# Gather all source UUID-to-ID mappings from the archive first
source_id_to_uuid_map = self._extract_chart_uuids_from_archive(temp_dir)
for dash_file in dash_files:
logger.info(f"[MigrationEngine.transform_zip][Action] Patching dashboard: {dash_file}")
self._patch_dashboard_metadata(dash_file, target_env_id, source_id_to_uuid_map)
# 3. Re-package
logger.info(f"[MigrationEngine.transform_zip][Action] Re-packaging ZIP to: {output_path} (strip_databases={strip_databases})")
with zipfile.ZipFile(output_path, 'w', zipfile.ZIP_DEFLATED) as zf:
for root, dirs, files in os.walk(temp_dir):
rel_root = Path(root).relative_to(temp_dir)
if strip_databases and "databases" in rel_root.parts:
logger.info(f"[MigrationEngine.transform_zip][Action] Skipping file in databases directory: {rel_root}")
continue
for file in files:
file_path = Path(root) / file
arcname = file_path.relative_to(temp_dir)
zf.write(file_path, arcname)
return True
except Exception as e:
logger.error(f"[MigrationEngine.transform_zip][Coherence:Failed] Error transforming ZIP: {e}")
return False
# [/DEF:transform_zip:Function]
# [DEF:_transform_yaml:Function]
# @PURPOSE: Replaces database_uuid in a single YAML file.
# @PARAM: file_path (Path) - Path to the YAML file.
# @PARAM: db_mapping (Dict[str, str]) - UUID mapping dictionary.
# @PRE: file_path must exist and be readable.
# @POST: File is modified in-place if source UUID matches mapping.
def _transform_yaml(self, file_path: Path, db_mapping: Dict[str, str]):
with open(file_path, 'r') as f:
data = yaml.safe_load(f)
if not data:
return
# Superset dataset YAML structure:
# database_uuid: ...
source_uuid = data.get('database_uuid')
if source_uuid in db_mapping:
data['database_uuid'] = db_mapping[source_uuid]
with open(file_path, 'w') as f:
yaml.dump(data, f)
# [/DEF:_transform_yaml:Function]
# [DEF:_extract_chart_uuids_from_archive:Function]
# @PURPOSE: Scans the unpacked ZIP to map local exported integer IDs back to their UUIDs.
# @PARAM: temp_dir (Path) - Root dir of unpacked archive
# @RETURN: Dict[int, str] - Mapping of source Integer ID to UUID.
def _extract_chart_uuids_from_archive(self, temp_dir: Path) -> Dict[int, str]:
# Implementation Note: This is a placeholder for the logic that extracts
# actual Source IDs. In a real scenario, this involves parsing chart YAMLs
# or manifesting the export metadata structure where source IDs are stored.
# For simplicity in US1 MVP, we assume it's read from chart files if present.
mapping = {}
chart_files = list(temp_dir.glob("**/charts/**/*.yaml")) + list(temp_dir.glob("**/charts/*.yaml"))
for cf in set(chart_files):
try:
with open(cf, 'r') as f:
cdata = yaml.safe_load(f)
if cdata and 'id' in cdata and 'uuid' in cdata:
mapping[cdata['id']] = cdata['uuid']
except Exception:
pass
return mapping
# [/DEF:_extract_chart_uuids_from_archive:Function]
# [DEF:_patch_dashboard_metadata:Function]
# @PURPOSE: Replaces integer IDs in json_metadata.
# @PARAM: file_path (Path)
# @PARAM: target_env_id (str)
# @PARAM: source_map (Dict[int, str])
def _patch_dashboard_metadata(self, file_path: Path, target_env_id: str, source_map: Dict[int, str]):
with belief_scope("MigrationEngine._patch_dashboard_metadata"):
try:
with open(file_path, 'r') as f:
data = yaml.safe_load(f)
if not data or 'json_metadata' not in data:
return
metadata_str = data['json_metadata']
if not metadata_str:
return
metadata = json.loads(metadata_str)
modified = False
# We need to deeply traverse and replace. For MVP, string replacement over the raw JSON is an option,
# but careful dict traversal is safer.
# Fetch target UUIDs for everything we know:
uuids_needed = list(source_map.values())
target_ids = self.mapping_service.get_remote_ids_batch(target_env_id, ResourceType.CHART, uuids_needed)
if not target_ids:
logger.info("[MigrationEngine._patch_dashboard_metadata][Reflect] No remote target IDs found in mapping database.")
return
# Map Source Int -> Target Int
source_to_target = {}
missing_targets = []
for s_id, s_uuid in source_map.items():
if s_uuid in target_ids:
source_to_target[s_id] = target_ids[s_uuid]
else:
missing_targets.append(s_id)
if missing_targets:
logger.warning(f"[MigrationEngine._patch_dashboard_metadata][Coherence:Recoverable] Missing target IDs for source IDs: {missing_targets}. Cross-filters for these IDs might break.")
if not source_to_target:
logger.info("[MigrationEngine._patch_dashboard_metadata][Reflect] No source IDs matched remotely. Skipping patch.")
return
# Complex metadata traversal would go here (e.g. for native_filter_configuration)
# We use regex replacement over the string for safety over unknown nested dicts.
new_metadata_str = metadata_str
# Replace chartId and datasetId assignments explicitly.
# Pattern: "datasetId": 42 or "chartId": 42
for s_id, t_id in source_to_target.items():
# Replace in native_filter_configuration targets
new_metadata_str = re.sub(r'("datasetId"\s*:\s*)' + str(s_id) + r'(\b)', r'\g<1>' + str(t_id) + r'\g<2>', new_metadata_str)
new_metadata_str = re.sub(r'("chartId"\s*:\s*)' + str(s_id) + r'(\b)', r'\g<1>' + str(t_id) + r'\g<2>', new_metadata_str)
# Re-parse to validate valid JSON
data['json_metadata'] = json.dumps(json.loads(new_metadata_str))
with open(file_path, 'w') as f:
yaml.dump(data, f)
logger.info(f"[MigrationEngine._patch_dashboard_metadata][Reason] Re-serialized modified JSON metadata for dashboard.")
except Exception as e:
logger.error(f"[MigrationEngine._patch_dashboard_metadata][Coherence:Failed] Metadata patch failed: {e}")
# [/DEF:_patch_dashboard_metadata:Function]
# [/DEF:MigrationEngine:Class]
# [/DEF:backend.src.core.migration_engine:Module]