chore(deps): bump pyarrow from 12.0.1 to 14.0.1 (#2515)

* chore(deps): bump pyarrow from 12.0.1 to 14.0.1

Bumps [pyarrow](https://github.com/apache/arrow) from 12.0.1 to 14.0.1.
- [Commits](apache/arrow@go/v12.0.1...apache-arrow-14.0.1)

---
updated-dependencies:
- dependency-name: pyarrow
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <[email protected]>

* fix: adapt tests to pyarrow 14

---------

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Abdel Jaidi <[email protected]>

Author: dependabot[bot]

awswrangler/redshift/_read.py

@@ -346,7 +346,6 @@ def unload_to_files(
             f"{max_file_size_str}"
             f"{manifest_str};"
         )
-        _logger.debug("Executing unload query:\n%s", unload_sql)
         cursor.execute(unload_sql)
 
 

awswrangler/redshift/_write.py

@@ -58,7 +58,6 @@ def _copy(
     if sql_copy_extra_params:
         for param in sql_copy_extra_params:
             sql += f"\n{param}"
-    _logger.debug("Executing copy query:\n%s", sql)
     cursor.execute(sql)
 
 

poetry.lock

@@ -377,8 +377,8 @@ def ensure_data_types(df: pd.DataFrame, has_list: bool = False, has_category: bo
     if "string_object" in df.columns:
         assert str(df["string_object"].dtype) == "string"
     assert str(df["string"].dtype) == "string"
-    assert str(df["date"].dtype) in ("object", "O", "datetime64[ns]")
-    assert str(df["timestamp"].dtype) in ("object", "O", "datetime64[ns]")
+    assert str(df["date"].dtype) in ("object", "O") or str(df["date"].dtype).startswith("datetime64")
+    assert str(df["timestamp"].dtype) in ("object", "O") or str(df["timestamp"].dtype).startswith("datetime64")
     assert str(df["bool"].dtype) in ("boolean", "Int64", "object")
     if "binary" in df.columns:
         assert str(df["binary"].dtype) == "object"

tests/_utils.py

@@ -526,7 +526,7 @@ def test_read_items_schema(params, dynamodb_table: str, chunked: bool):
     wr.dynamodb.put_df(df=df, table_name=dynamodb_table)
 
     if not is_ray_modin:
-        with pytest.raises(pa.ArrowInvalid):
+        with pytest.raises((pa.ArrowInvalid, pa.ArrowTypeError)):
             wr.dynamodb.read_items(table_name=dynamodb_table, allow_full_scan=True)
 
     schema = pa.schema([("id", pa.decimal128(7, 4)), ("word", pa.string()), ("char_count", pa.int8())])

tests/unit/test_dynamodb.py

@@ -5,6 +5,7 @@
 import pg8000
 import pyarrow as pa
 import pytest
+from packaging import version
 from pg8000.dbapi import ProgrammingError
 
 import awswrangler as wr
@@ -522,6 +523,7 @@ def test_insert_ignore_duplicate_multiple_columns(postgresql_table, postgresql_c
     assert pandas_equals(df6, df7)
 
 
+@pytest.mark.skipif(version.parse(pa.__version__) > version.parse("14.0.0"), reason="Fixed in pyarrow 14+")
 def test_timestamp_overflow(postgresql_table, postgresql_con):
     df = pd.DataFrame({"c0": [datetime.strptime("1677-01-01 00:00:00.0", "%Y-%m-%d %H:%M:%S.%f")]})
     wr.postgresql.to_sql(df=df, con=postgresql_con, schema="public", table=postgresql_table)

tests/unit/test_postgresql.py

@@ -7,4 +7,4 @@ ruff awswrangler
 mypy --install-types --non-interactive awswrangler
 pylint -j 0 --disable=all --enable=R0911,R0912,R0913,R0915 awswrangler
 doc8 --ignore-path docs/source/stubs --max-line-length 120 docs/source
-poetry lock --check
+poetry check --lock