Creating module for routine tests.

Author: igorborgest

awswrangler/athena/_read.py

@@ -622,7 +622,7 @@ def read_sql_query(
         Should Wrangler delete or keep the staging files produced by Athena?
     ctas_temp_table_name : str, optional
         The name of the temporary table and also the directory name on S3 where the CTAS result is stored.
-        If None, it will use the follow random pattern: `f"temp_table_{pyarrow.compat.guid()}"`.
+        If None, it will use the follow random pattern: `f"temp_table_{uuid.uuid4().hex()}"`.
         On S3 this directory will be under under the pattern: `f"{s3_output}/{ctas_temp_table_name}/"`.
     use_threads : bool
         True to enable concurrent requests, False to disable multiple threads.
@@ -814,7 +814,7 @@ def read_sql_table(
         Should Wrangler delete or keep the staging files produced by Athena?
     ctas_temp_table_name : str, optional
         The name of the temporary table and also the directory name on S3 where the CTAS result is stored.
-        If None, it will use the follow random pattern: `f"temp_table_{pyarrow.compat.guid()}"`.
+        If None, it will use the follow random pattern: `f"temp_table_{uuid.uuid4().hex}"`.
         On S3 this directory will be under under the pattern: `f"{s3_output}/{ctas_temp_table_name}/"`.
     use_threads : bool
         True to enable concurrent requests, False to disable multiple threads.

awswrangler/db.py

@@ -2,6 +2,7 @@
 
 import json
 import logging
+import uuid
 from typing import Any, Dict, Iterator, List, Optional, Tuple, Union
 from urllib.parse import quote_plus as _quote_plus
 
@@ -754,7 +755,7 @@ def _rs_create_table(
     else:
         if _rs_does_table_exist(con=con, schema=schema, table=table) is True:
             if mode == "upsert":
-                guid: str = pa.compat.guid()
+                guid: str = uuid.uuid4().hex
                 temp_table: str = f"temp_redshift_{guid}"
                 sql: str = f"CREATE TEMPORARY TABLE {temp_table} (LIKE {schema}.{table})"
                 _logger.debug(sql)

awswrangler/s3/_read_parquet.py

@@ -412,7 +412,7 @@ def read_parquet(
     partition_filter: Optional[Callable[[Dict[str, str]], bool]]
         Callback Function filters to apply on PARTITION columns (PUSH-DOWN filter).
         This function MUST receive a single argument (Dict[str, str]) where keys are partitions
-        names and values are partitions values.
+        names and values are partitions values. Partitions values will be always strings extracted from S3.
         This function MUST return a bool, True to read the partition or False to ignore it.
         Ignored if `dataset=False`.
         E.g ``lambda x: True if x["year"] == "2020" and x["month"] == "1" else False``
@@ -595,7 +595,7 @@ def read_parquet_table(
     partition_filter: Optional[Callable[[Dict[str, str]], bool]]
         Callback Function filters to apply on PARTITION columns (PUSH-DOWN filter).
         This function MUST receive a single argument (Dict[str, str]) where keys are partitions
-        names and values are partitions values.
+        names and values are partitions values. Partitions values will be always strings extracted from S3.
         This function MUST return a bool, True to read the partition or False to ignore it.
         Ignored if `dataset=False`.
         E.g ``lambda x: True if x["year"] == "2020" and x["month"] == "1" else False``

awswrangler/s3/_read_text.py

@@ -191,7 +191,7 @@ def read_csv(
     partition_filter: Optional[Callable[[Dict[str, str]], bool]]
         Callback Function filters to apply on PARTITION columns (PUSH-DOWN filter).
         This function MUST receive a single argument (Dict[str, str]) where keys are partitions
-        names and values are partitions values.
+        names and values are partitions values. Partitions values will be always strings extracted from S3.
         This function MUST return a bool, True to read the partition or False to ignore it.
         Ignored if `dataset=False`.
         E.g ``lambda x: True if x["year"] == "2020" and x["month"] == "1" else False``
@@ -319,7 +319,7 @@ def read_fwf(
     partition_filter: Optional[Callable[[Dict[str, str]], bool]]
         Callback Function filters to apply on PARTITION columns (PUSH-DOWN filter).
         This function MUST receive a single argument (Dict[str, str]) where keys are partitions
-        names and values are partitions values.
+        names and values are partitions values. Partitions values will be always strings extracted from S3.
         This function MUST return a bool, True to read the partition or False to ignore it.
         Ignored if `dataset=False`.
         E.g ``lambda x: True if x["year"] == "2020" and x["month"] == "1" else False``
@@ -451,7 +451,7 @@ def read_json(
     partition_filter: Optional[Callable[[Dict[str, str]], bool]]
         Callback Function filters to apply on PARTITION columns (PUSH-DOWN filter).
         This function MUST receive a single argument (Dict[str, str]) where keys are partitions
-        names and values are partitions values.
+        names and values are partitions values. Partitions values will be always strings extracted from S3.
         This function MUST return a bool, True to read the partition or False to ignore it.
         Ignored if `dataset=False`.
         E.g ``lambda x: True if x["year"] == "2020" and x["month"] == "1" else False``