lidb 1.1.0__tar.gz → 1.1.2__tar.gz

{lidb-1.1.0 → lidb-1.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: lidb
-Version: 1.1.0
+Version: 1.1.2
 Requires-Python: >=3.12
 Description-Content-Type: text/markdown
 Requires-Dist: dynaconf>=3.2.11

{lidb-1.1.0 → lidb-1.1.2}/lidb/__init__.py

@@ -15,8 +15,9 @@ from .database import (
     tb_path,
     read_mysql,
     read_ck,
+    scan,
 )
 
 from .parse import parse_hive_partition_structure
 
-__version__ = "1.1.0"
+__version__ = "1.1.2"

{lidb-1.1.0 → lidb-1.1.2}/lidb/database.py

@@ -12,6 +12,7 @@ from pathlib import Path
 from .parse import extract_table_names_from_sql
 from .init import DB_PATH, logger, get_settings
 import urllib
+import polars as pl
 
 # ======================== 本地数据库 catdb ========================
 def tb_path(tb_name: str) -> Path:
@@ -111,6 +112,13 @@ def sql(query: str, abs_path: bool = False):
     new_query = pattern.sub(lambda m: convertor[m.group(0)], query)
     return pl.sql(new_query)
 
+def scan(tb: str, abs_path: bool = False) -> pl.LazyFrame:
+    """polars.scan_parquet"""
+
+    if not abs_path:
+        tb = tb_path(tb)
+    return pl.scan_parquet(tb)
+
 def read_mysql(query: str, db_conf: str = "DATABASES.mysql"):
     """
     从MySQL数据库中读取数据。

{lidb-1.1.0 → lidb-1.1.2}/lidb/parse.py

@@ -9,11 +9,8 @@ Email: yundi.xxii@outlook.com
 """
 import re
 from pathlib import Path
-from typing import Dict, Set
 from urllib.parse import unquote
-from collections import defaultdict
 
-import polars
 import polars as pl
 import sqlparse
 
@@ -72,7 +69,7 @@ def extract_table_names_from_sql(sql_query):
     return table_names
 
 
-def parse_hive_partition_structure(root_path: Path | str, file_pattern: str = "*.parquet") -> polars.DataFrame:
+def parse_hive_partition_structure(root_path: Path | str, file_pattern: str = "*.parquet") -> pl.DataFrame:
     """
     通用Hive分区结构解析器
 
@@ -101,7 +98,7 @@ def parse_hive_partition_structure(root_path: Path | str, file_pattern: str = "*
                 partition_dict[key] = value
 
         # 记录分区组合
-        combination = tuple(sorted(partition_dict.items()))
+        combination = tuple(partition_dict.items())
         partition_combinations.add(combination)
 
     # 转换为普通dict

{lidb-1.1.0 → lidb-1.1.2}/lidb.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: lidb
-Version: 1.1.0
+Version: 1.1.2
 Requires-Python: >=3.12
 Description-Content-Type: text/markdown
 Requires-Dist: dynaconf>=3.2.11

{lidb-1.1.0 → lidb-1.1.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "lidb"
-version = "1.1.0"
+version = "1.1.2"
 description = ""
 readme = "README.md"
 requires-python = ">=3.12"