249 lines
9.7 KiB
Python
249 lines
9.7 KiB
Python
# -*- coding: utf-8 -*-
|
||
"""环境变量解析"""
|
||
import os
|
||
import json
|
||
from pathlib import Path
|
||
from copy import deepcopy
|
||
|
||
ENV_MAP = {
|
||
"TIMEZONE": ("app.timezone",),
|
||
"BUSINESS_DAY_START_HOUR": ("app.business_day_start_hour",),
|
||
"STORE_ID": ("app.store_id",),
|
||
"SCHEMA_OLTP": ("app.schema_oltp",),
|
||
"SCHEMA_ETL": ("app.schema_etl",),
|
||
"PG_DSN": ("db.dsn",),
|
||
"PG_HOST": ("db.host",),
|
||
"PG_PORT": ("db.port",),
|
||
"PG_NAME": ("db.name",),
|
||
"PG_USER": ("db.user",),
|
||
"PG_PASSWORD": ("db.password",),
|
||
"PG_CONNECT_TIMEOUT": ("db.connect_timeout_sec",),
|
||
"API_BASE": ("api.base_url",),
|
||
"API_TOKEN": ("api.token",),
|
||
"FICOO_TOKEN": ("api.token",),
|
||
"API_TIMEOUT": ("api.timeout_sec",),
|
||
"API_PAGE_SIZE": ("api.page_size",),
|
||
"API_RETRY_MAX": ("api.retries.max_attempts",),
|
||
"API_RETRY_BACKOFF": ("api.retries.backoff_sec",),
|
||
"API_PARAMS": ("api.params",),
|
||
"EXPORT_ROOT": ("io.export_root",),
|
||
"LOG_ROOT": ("io.log_root",),
|
||
"MANIFEST_NAME": ("io.manifest_name",),
|
||
"INGEST_REPORT_NAME": ("io.ingest_report_name",),
|
||
"WRITE_PRETTY_JSON": ("io.write_pretty_json",),
|
||
"RUN_TASKS": ("run.tasks",),
|
||
"RUN_DWS_TASKS": ("run.dws_tasks",),
|
||
"RUN_INDEX_TASKS": ("run.index_tasks",),
|
||
"INDEX_LOOKBACK_DAYS": ("run.index_lookback_days",),
|
||
"OVERLAP_SECONDS": ("run.overlap_seconds",),
|
||
"WINDOW_BUSY_MIN": ("run.window_minutes.default_busy",),
|
||
"WINDOW_IDLE_MIN": ("run.window_minutes.default_idle",),
|
||
"IDLE_START": ("run.idle_window.start",),
|
||
"IDLE_END": ("run.idle_window.end",),
|
||
"IDLE_WINDOW_START": ("run.idle_window.start",),
|
||
"IDLE_WINDOW_END": ("run.idle_window.end",),
|
||
"ALLOW_EMPTY_RESULT_ADVANCE": ("run.allow_empty_result_advance",),
|
||
"ALLOW_EMPTY_ADVANCE": ("run.allow_empty_result_advance",),
|
||
"SNAPSHOT_MISSING_DELETE": ("run.snapshot_missing_delete",),
|
||
"SNAPSHOT_ALLOW_EMPTY_DELETE": ("run.snapshot_allow_empty_delete",),
|
||
"WINDOW_START": ("run.window_override.start",),
|
||
"WINDOW_END": ("run.window_override.end",),
|
||
"WINDOW_SPLIT_UNIT": ("run.window_split.unit",),
|
||
"WINDOW_SPLIT_DAYS": ("run.window_split.days",),
|
||
"WINDOW_COMPENSATION_HOURS": ("run.window_split.compensation_hours",),
|
||
"PIPELINE_FLOW": ("pipeline.flow",),
|
||
"JSON_FETCH_ROOT": ("pipeline.fetch_root",),
|
||
"JSON_SOURCE_DIR": ("pipeline.ingest_source_dir",),
|
||
"FETCH_ROOT": ("pipeline.fetch_root", "io.fetch_root"),
|
||
"INGEST_SOURCE_DIR": ("pipeline.ingest_source_dir",),
|
||
"INTEGRITY_MODE": ("integrity.mode",),
|
||
"INTEGRITY_HISTORY_START": ("integrity.history_start",),
|
||
"INTEGRITY_HISTORY_END": ("integrity.history_end",),
|
||
"INTEGRITY_INCLUDE_DIMENSIONS": ("integrity.include_dimensions",),
|
||
"INTEGRITY_AUTO_CHECK": ("integrity.auto_check",),
|
||
"INTEGRITY_AUTO_BACKFILL": ("integrity.auto_backfill",),
|
||
"INTEGRITY_COMPARE_CONTENT": ("integrity.compare_content",),
|
||
"INTEGRITY_CONTENT_SAMPLE_LIMIT": ("integrity.content_sample_limit",),
|
||
"INTEGRITY_BACKFILL_MISMATCH": ("integrity.backfill_mismatch",),
|
||
"INTEGRITY_RECHECK_AFTER_BACKFILL": ("integrity.recheck_after_backfill",),
|
||
"INTEGRITY_ODS_TASK_CODES": ("integrity.ods_task_codes",),
|
||
"VERIFY_SKIP_ODS_ON_FETCH": ("verification.skip_ods_when_fetch_before_verify",),
|
||
"VERIFY_ODS_LOCAL_JSON": ("verification.ods_use_local_json",),
|
||
"DWD_FACT_UPSERT": ("dwd.fact_upsert",),
|
||
# DWS 月度/薪资配置
|
||
"DWS_MONTHLY_ALLOW_HISTORY": ("dws.monthly.allow_history",),
|
||
"DWS_MONTHLY_PREV_GRACE_DAYS": ("dws.monthly.prev_month_grace_days",),
|
||
"DWS_MONTHLY_HISTORY_MONTHS": ("dws.monthly.history_months",),
|
||
"DWS_MONTHLY_NEW_HIRE_CAP_EFFECTIVE_FROM": ("dws.monthly.new_hire_cap_effective_from",),
|
||
"DWS_MONTHLY_NEW_HIRE_CAP_DAY": ("dws.monthly.new_hire_cap_day",),
|
||
"DWS_MONTHLY_NEW_HIRE_MAX_TIER_LEVEL": ("dws.monthly.new_hire_max_tier_level",),
|
||
"DWS_SALARY_RUN_DAYS": ("dws.salary.run_days",),
|
||
"DWS_SALARY_ALLOW_OUT_OF_CYCLE": ("dws.salary.allow_out_of_cycle",),
|
||
"DWS_SALARY_ROOM_COURSE_PRICE": ("dws.salary.room_course_price",),
|
||
# ODS 离线回放配置
|
||
"ODS_JSON_DOC_DIR": ("ods.json_doc_dir",),
|
||
"ODS_INCLUDE_FILES": ("ods.include_files",),
|
||
"ODS_DROP_SCHEMA_FIRST": ("ods.drop_schema_first",),
|
||
# ── 以下为 2026-02-16 补齐：defaults.py 中有定义但此前缺少 ENV 映射的参数 ──
|
||
# 数据库会话参数
|
||
"DB_SESSION_TIMEZONE": ("db.session.timezone",),
|
||
"DB_STATEMENT_TIMEOUT_MS": ("db.session.statement_timeout_ms",),
|
||
"DB_LOCK_TIMEOUT_MS": ("db.session.lock_timeout_ms",),
|
||
"DB_IDLE_IN_TX_TIMEOUT_MS": ("db.session.idle_in_tx_timeout_ms",),
|
||
# 清洗配置
|
||
"CLEAN_LOG_UNKNOWN_FIELDS": ("clean.log_unknown_fields",),
|
||
"CLEAN_UNKNOWN_FIELDS_LIMIT": ("clean.unknown_fields_limit",),
|
||
"CLEAN_HASH_ALGO": ("clean.hash_key.algo",),
|
||
"CLEAN_HASH_SALT": ("clean.hash_key.salt",),
|
||
"CLEAN_STRICT_NUMERIC": ("clean.strict_numeric",),
|
||
"CLEAN_ROUND_MONEY_SCALE": ("clean.round_money_scale",),
|
||
# 安全配置
|
||
"SECURITY_REDACT_IN_LOGS": ("security.redact_in_logs",),
|
||
"SECURITY_REDACT_KEYS": ("security.redact_keys",),
|
||
"SECURITY_ECHO_TOKEN_IN_LOGS": ("security.echo_token_in_logs",),
|
||
# IO 文件大小限制
|
||
"MAX_FILE_BYTES": ("io.max_file_bytes",),
|
||
# 完整性检查：强制按月切分
|
||
"INTEGRITY_FORCE_MONTHLY_SPLIT": ("integrity.force_monthly_split",),
|
||
# DWD 事实表 UPSERT 批量参数
|
||
"DWD_FACT_UPSERT_BATCH_SIZE": ("dwd.fact_upsert_batch_size",),
|
||
"DWD_FACT_UPSERT_MIN_BATCH_SIZE": ("dwd.fact_upsert_min_batch_size",),
|
||
"DWD_FACT_UPSERT_MAX_RETRIES": ("dwd.fact_upsert_max_retries",),
|
||
"DWD_FACT_UPSERT_RETRY_BACKOFF": ("dwd.fact_upsert_retry_backoff_sec",),
|
||
"DWD_FACT_UPSERT_LOCK_TIMEOUT_MS": ("dwd.fact_upsert_lock_timeout_ms",),
|
||
# 运行模式（直接设置，不经旧 pipeline.flow 配置键映射；配置键名保留以兼容旧配置）
|
||
"DATA_SOURCE": ("run.data_source",),
|
||
# API 额外请求头（JSON 对象格式）
|
||
"API_HEADERS_EXTRA": ("api.headers_extra",),
|
||
# Pipeline 管道限流参数
|
||
"PIPELINE_RATE_MIN": ("pipeline.rate_min",),
|
||
"PIPELINE_RATE_MAX": ("pipeline.rate_max",),
|
||
}
|
||
|
||
|
||
def _deep_set(d, dotted_keys, value):
|
||
cur = d
|
||
for k in dotted_keys[:-1]:
|
||
cur = cur.setdefault(k, {})
|
||
cur[dotted_keys[-1]] = value
|
||
|
||
|
||
def _coerce_env(v: str):
|
||
if v is None:
|
||
return None
|
||
s = v.strip()
|
||
if s.lower() in ("true", "false"):
|
||
return s.lower() == "true"
|
||
try:
|
||
if s.isdigit() or (s.startswith("-") and s[1:].isdigit()):
|
||
return int(s)
|
||
except Exception:
|
||
pass
|
||
if (s.startswith("{") and s.endswith("}")) or (s.startswith("[") and s.endswith("]")):
|
||
try:
|
||
return json.loads(s)
|
||
except Exception:
|
||
return s
|
||
return s
|
||
|
||
|
||
def _strip_inline_comment(value: str) -> str:
|
||
"""去掉未被引号包裹的内联注释"""
|
||
result = []
|
||
in_quote = False
|
||
quote_char = ""
|
||
escape = False
|
||
for ch in value:
|
||
if escape:
|
||
result.append(ch)
|
||
escape = False
|
||
continue
|
||
if ch == "\\":
|
||
escape = True
|
||
result.append(ch)
|
||
continue
|
||
if ch in ("'", '"'):
|
||
if not in_quote:
|
||
in_quote = True
|
||
quote_char = ch
|
||
elif quote_char == ch:
|
||
in_quote = False
|
||
quote_char = ""
|
||
result.append(ch)
|
||
continue
|
||
if ch == "#" and not in_quote:
|
||
break
|
||
result.append(ch)
|
||
return "".join(result).rstrip()
|
||
|
||
|
||
def _unquote_value(value: str) -> str:
|
||
"""处理引号/原始字符串以及尾随逗号"""
|
||
trimmed = value.strip()
|
||
trimmed = _strip_inline_comment(trimmed)
|
||
trimmed = trimmed.rstrip(",").rstrip()
|
||
if not trimmed:
|
||
return trimmed
|
||
if len(trimmed) >= 2 and trimmed[0] in ("'", '"') and trimmed[-1] == trimmed[0]:
|
||
return trimmed[1:-1]
|
||
if (
|
||
len(trimmed) >= 3
|
||
and trimmed[0] in ("r", "R")
|
||
and trimmed[1] in ("'", '"')
|
||
and trimmed[-1] == trimmed[1]
|
||
):
|
||
return trimmed[2:-1]
|
||
return trimmed
|
||
|
||
|
||
def _parse_dotenv_line(line: str) -> tuple[str, str] | None:
|
||
"""解析 .env 文件中的单行"""
|
||
stripped = line.strip()
|
||
if not stripped or stripped.startswith("#"):
|
||
return None
|
||
if stripped.startswith("export "):
|
||
stripped = stripped[len("export ") :].strip()
|
||
if "=" not in stripped:
|
||
return None
|
||
key, value = stripped.split("=", 1)
|
||
key = key.strip()
|
||
value = _unquote_value(value)
|
||
return key, value
|
||
|
||
|
||
def _load_dotenv_values() -> dict:
|
||
"""从项目根目录读取 .env 文件键值"""
|
||
if os.environ.get("ETL_SKIP_DOTENV") in ("1", "true", "TRUE", "True"):
|
||
return {}
|
||
root = Path(__file__).resolve().parents[1]
|
||
dotenv_path = root / ".env"
|
||
if not dotenv_path.exists():
|
||
return {}
|
||
values: dict[str, str] = {}
|
||
for line in dotenv_path.read_text(encoding="utf-8", errors="ignore").splitlines():
|
||
parsed = _parse_dotenv_line(line)
|
||
if parsed:
|
||
key, value = parsed
|
||
values[key] = value
|
||
return values
|
||
|
||
|
||
def _apply_env_values(cfg: dict, source: dict):
|
||
for env_key, dotted in ENV_MAP.items():
|
||
val = source.get(env_key)
|
||
if val is None:
|
||
continue
|
||
v2 = _coerce_env(val)
|
||
for path in dotted:
|
||
if path in ("run.tasks", "run.dws_tasks", "run.index_tasks") and isinstance(v2, str):
|
||
v2 = [item.strip() for item in v2.split(",") if item.strip()]
|
||
_deep_set(cfg, path.split("."), v2)
|
||
|
||
|
||
def load_env_overrides(defaults: dict) -> dict:
|
||
cfg = deepcopy(defaults)
|
||
# 先读取 .env，再读取真实环境变量，确保 CLI 仍然最高优先级
|
||
_apply_env_values(cfg, _load_dotenv_values())
|
||
_apply_env_values(cfg, os.environ)
|
||
return cfg
|