xlin 0.1.19__tar.gz → 0.1.21__tar.gz

{xlin-0.1.19 → xlin-0.1.21}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: xlin
-Version: 0.1.19
+Version: 0.1.21
 Summary: toolbox for LinXueyuan
 License: MIT
 Author: LinXueyuanStdio

{xlin-0.1.19 → xlin-0.1.21}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "xlin"
-version = "0.1.19"
+version = "0.1.21"
 description = "toolbox for LinXueyuan"
 authors = ["LinXueyuanStdio <23211526+LinXueyuanStdio@users.noreply.github.com>"]
 license = "MIT"

{xlin-0.1.19 → xlin-0.1.21}/xlin/jsonl.py

@@ -246,3 +246,14 @@ def row_to_json(row: dict) -> dict:
 
     return new_row
 
+
+def generator_from_json(path):
+    jsonlist = load_json(path)
+    for line in jsonlist:
+        yield line
+
+
+def generator_from_jsonl(path):
+    jsonlist = load_json_list(path)
+    for line in jsonlist:
+        yield line

{xlin-0.1.19 → xlin-0.1.21}/xlin/read_as_dataframe.py

@@ -13,7 +13,7 @@ from xlin.xls2xlsx import is_xslx
 
 
 def read_as_dataframe(
-    filepath: Union[str, Path],
+    filepath: Union[str, Path, list[str], list[Path]],
     sheet_name: Optional[str] = None,
     fill_empty_str_to_na=True,
     filter=lambda x: True,
@@ -21,11 +21,9 @@ def read_as_dataframe(
     """
     读取文件为表格。如果是文件夹，则读取文件夹下的所有文件为表格并拼接
     """
-    filepath = Path(filepath)
-    if filepath.is_dir():
-        paths = ls(filepath, filter=filter, expand_all_subdir=True)
+    if isinstance(filepath, list):
         df_list = []
-        for path in paths:
+        for path in filepath:
             try:
                 df = read_as_dataframe(path, sheet_name, fill_empty_str_to_na, filter)
                 df["数据来源"] = path.name
@@ -36,6 +34,10 @@ def read_as_dataframe(
         if fill_empty_str_to_na:
             df.fillna("", inplace=True)
         return df
+    filepath = Path(filepath)
+    if filepath.is_dir():
+        paths = ls(filepath, filter=filter, expand_all_subdir=True)
+        return read_as_dataframe(paths, sheet_name, fill_empty_str_to_na, filter)
     filename = filepath.name
     if filename.endswith(".json") or filename.endswith(".jsonl"):
         try: