data-linter 6.3.0__tar.gz → 6.3.2__tar.gz

{data_linter-6.3.0 → data_linter-6.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: data_linter
-Version: 6.3.0
+Version: 6.3.2
 Summary: data linter
 Author: Thomas Hirsch
 Author-email: thomas.hirsch@digital.justice.gov.uk

data_linter-6.3.2/data_linter/__init__.py

@@ -0,0 +1 @@
+__version__ = "6.3.2"

{data_linter-6.3.0 → data_linter-6.3.2}/data_linter/validation.py

@@ -43,7 +43,7 @@ from data_linter.utils import (
     get_filepaths_from_local_folder,
     local_file_to_s3,
     read_all_file_body,
-    get_file_lengths
+    get_file_lengths,
 )
 
 from data_linter.validators import (
@@ -439,6 +439,7 @@ def validate_data(config: dict) -> ValidatorResult:
         else:
             msg4 = f"SKIPPING {table_name}. No files found."
             log.info(msg4)
+            return None
 
     if all_table_responses:
         save_completion_status(config, all_table_responses)

{data_linter-6.3.0 → data_linter-6.3.2}/data_linter/validators/pandas_validator.py

@@ -469,8 +469,10 @@ def _parse_data_to_pandas(filepath: str, table_params: dict, metadata: Metadata)
         raise ColumnError(err_msg)
 
     # sample the data, if required
-    if table_params.get("row-limit"):
-        df = df.sample(table_params.get("row-limit"))
+    row_limit = table_params.get("row-limit", None)
+    if row_limit:
+        row_limit = row_limit if row_limit <= len(df) else len(df)
+        df = df.sample(row_limit)
 
     if metadata.file_format not in ["parquet", "snappy.parquet"]:
         df = cast_pandas_table_to_schema(df, metadata)

{data_linter-6.3.0 → data_linter-6.3.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "data_linter"
-version = "6.3.0"
+version = "6.3.2"
 description = "data linter"
 authors = ["Thomas Hirsch <thomas.hirsch@digital.justice.gov.uk>",
            "George Kelly <george.kelly@digital.justice.gov.uk>",

data_linter-6.3.0/data_linter/__init__.py

@@ -1 +0,0 @@
-__version__ = "6.3.0"