fix: encoding should be kept as None by default + pin pandas to v1.2.5

peakina/datasource.py

@@ -90,7 +90,7 @@ def _get_single_df(
         allowed_params = get_reader_allowed_params(filetype)
 
         # Check encoding
-        encoding = kwargs.get("encoding", "utf-8")
+        encoding = kwargs.get("encoding")
         if "encoding" in allowed_params:
             if not validate_encoding(stream.name, encoding):
                 encoding = detect_encoding(stream.name)

peakina/helpers.py

@@ -145,7 +145,7 @@ def detect_sep(filepath: str, encoding: Optional[str] = None) -> str:
     return csv.Sniffer().sniff(str_head(filepath, 100, encoding)).delimiter
 
 
-def validate_sep(filepath: str, sep: str = ",", encoding: str = "utf-8") -> bool:
+def validate_sep(filepath: str, sep: str = ",", encoding: Optional[str] = None) -> bool:
     """
     Validates if the `sep` is a right separator of a CSV file
     (i.e. the dataframe has more than one column).

pyproject.toml

@@ -25,7 +25,7 @@ chardet = "^4.0.0"
 fastparquet = "^0.8.0"
 jq = "^1.2.1"
 openpyxl = "^3.0.9"
-pandas = "^1.2.5"
+pandas = "1.2.5"
 paramiko = "^2.9.2"
 pydantic = "^1.9.0"
 python-slugify = ">=5.0.2,<7.0.0"