feilian 1.2.3__tar.gz → 1.2.5__tar.gz

{feilian-1.2.3 → feilian-1.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: feilian
-Version: 1.2.3
+Version: 1.2.5
 Summary: General data processing tool.
 Author-email: darkpeath <darkpeath@gmail.com>
 Project-URL: Homepage, https://github.com/darkpeath/feilian

{feilian-1.2.3 → feilian-1.2.5}/feilian/_dist_ver.py

@@ -1,5 +1,5 @@
 # -*- coding: utf-8 -*-
 # file generated by setuptools_scm
 # don't change, don't track in version control
-VERSION = (1, 2, 3)
-__version__ = '1.2.3'
+VERSION = (1, 2, 5)
+__version__ = '1.2.5'

{feilian-1.2.3 → feilian-1.2.5}/feilian/dataframe.py

@@ -76,7 +76,14 @@ def read_dataframe(file: str, *args, sheet_name=0,
     elif file_format == 'xlsx':
         df = pd.read_excel(file, *args, sheet_name=sheet_name, dtype=dtype, **kwargs)
     elif file_format == 'json':
-        df = pd.read_json(file, *args, lines=jsonl, dtype=dtype, **kwargs)
+        try:
+            df = pd.read_json(file, *args, lines=jsonl, dtype=dtype, **kwargs)
+        except Exception as e:
+            # if failed, try again with different arg `lines`
+            try:
+                df = pd.read_json(file, *args, lines=not jsonl, dtype=dtype, **kwargs)
+            except Exception:
+                raise e
     elif file_format == 'parquet':
         df = pd.read_parquet(file, *args, **kwargs)
     else:
@@ -97,7 +104,7 @@ def save_dataframe(file: Union[str, 'pd.WriteBuffer[bytes]',  'pd.WriteBuffer[st
                    index=False, index_label=None,
                    encoding='utf-8', newline='\n',
                    force_ascii=False,
-                   orient='records', jsonl=True,
+                   orient='records', jsonl=True, indent=None,
                    column_mapper: Union[Dict[str, str], Sequence[str]] = None,
                    include_columns: Sequence[str] = None,
                    exclude_columns: Sequence[str] = None,
@@ -119,6 +126,7 @@ def save_dataframe(file: Union[str, 'pd.WriteBuffer[bytes]',  'pd.WriteBuffer[st
     :param force_ascii:         `force_ascii` for json format
     :param orient:              `orient` for json format
     :param jsonl:               jsonl format or not
+    :param indent:              indent for json format
     :param column_mapper:       rename columns; if set, columns not list here will be ignored
     :param include_columns:     if set, columns not list here will be ignored
     :param exclude_columns:     if set, columns list here will be ignored
@@ -180,7 +188,7 @@ def save_dataframe(file: Union[str, 'pd.WriteBuffer[bytes]',  'pd.WriteBuffer[st
             index = True
         df.to_json(file, *args, compression=compression, index=index,
                    force_ascii=force_ascii, orient=orient, lines=jsonl,
-                   **kwargs)
+                   indent=indent, **kwargs)
     elif file_format == 'parquet':
         df.to_parquet(file, *args, compression=compression, index=index, **kwargs)
     else:

{feilian-1.2.3 → feilian-1.2.5}/feilian/process.py

@@ -61,11 +61,13 @@ class BaseProcessor(abc.ABC):
             self.save_result(output_path or input_path, result)
 
 class DataframeProcessor(BaseProcessor, abc.ABC):
-    def __init__(self, input_dtype=None, progress=False, read_args: Dict[str, Any] = None):
+    def __init__(self, input_dtype=None, progress=False, read_args: Dict[str, Any] = None,
+                 write_args: Dict[str, Any] = None):
         self.progress = progress
         self.read_args = read_args or {}
         if input_dtype is not None:
             self.read_args['dtype'] = input_dtype
+        self.write_args = write_args or {}
 
     def read_single_file(self, filepath: str) -> pd.DataFrame:
         return read_dataframe(filepath, **self.read_args)
@@ -77,7 +79,7 @@ class DataframeProcessor(BaseProcessor, abc.ABC):
         return super().read_data(filepath)
 
     def save_result(self, filepath: str, result: pd.DataFrame):
-        save_dataframe(filepath, result)
+        save_dataframe(filepath, result, **self.write_args)
 
     @abc.abstractmethod
     def process_row(self, i: Hashable, row: pd.Series) -> Optional[Dict[str, Any]]:

{feilian-1.2.3 → feilian-1.2.5}/feilian.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: feilian
-Version: 1.2.3
+Version: 1.2.5
 Summary: General data processing tool.
 Author-email: darkpeath <darkpeath@gmail.com>
 Project-URL: Homepage, https://github.com/darkpeath/feilian