Backport PR #60943: BUG(string dtype): Resolve pytables xfail when re…

…ading with condition (#60967)

* ENH: Improved error message and raise new error for small-string NaN edge case in HDFStore.append (#60829)

* Add clearer error messages for datatype mismatch in HDFStore.append. Raise ValueError when nan_rep too large for pytable column. Add and modify applicable test code.

* Fix missed tests and correct mistake in error message.

* Remove excess comments. Reverse error type change to avoid api changes. Move nan_rep tests into separate function.

(cherry picked from commit 57340ec)

* TST(string dtype): Resolve xfails in pytables (#60795)

(cherry picked from commit 4511251)

* BUG(string dtype): Resolve pytables xfail when reading with condition (#60943)

(cherry picked from commit 0ec5f26)

---------

Co-authored-by: Jake Thomas Trevallion <136272202+JakeTT404@users.noreply.github.com>

pandas/io/pytables.py

@@ -4093,6 +4093,8 @@ def _create_axes(
                 ordered = data_converted.ordered
                 meta = "category"
                 metadata = np.asarray(data_converted.categories).ravel()
+            elif isinstance(blk.dtype, StringDtype):
+                meta = str(blk.dtype)
 
             data, dtype_name = _get_data_and_dtype_name(data_converted)
 
@@ -4360,7 +4362,9 @@ def read_column(
                     encoding=self.encoding,
                     errors=self.errors,
                 )
-                return Series(_set_tz(col_values[1], a.tz), name=column, copy=False)
+                cvs = _set_tz(col_values[1], a.tz)
+                dtype = getattr(self.table.attrs, f"{column}_meta", None)
+                return Series(cvs, name=column, copy=False, dtype=dtype)
 
         raise KeyError(f"column [{column}] not found in the table")
 
@@ -4708,8 +4712,18 @@ def read(
                 df = DataFrame._from_arrays([values], columns=cols_, index=index_)
             if not (using_string_dtype() and values.dtype.kind == "O"):
                 assert (df.dtypes == values.dtype).all(), (df.dtypes, values.dtype)
+
+            # If str / string dtype is stored in meta, use that.
+            converted = False
+            for column in cols_:
+                dtype = getattr(self.table.attrs, f"{column}_meta", None)
+                if dtype in ["str", "string"]:
+                    df[column] = df[column].astype(dtype)
+                    converted = True
+            # Otherwise try inference.
             if (
-                using_string_dtype()
+                not converted
+                and using_string_dtype()
                 and isinstance(values, np.ndarray)
                 and is_string_array(
                     values,

pandas/tests/io/pytables/test_append.py

@@ -5,8 +5,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas._libs.tslibs import Timestamp
 import pandas.util._test_decorators as td
 
@@ -507,7 +505,6 @@ def test_append_with_empty_string(setup_path):
         tm.assert_frame_equal(store.select("df"), df)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_append_with_data_columns(setup_path):
     with ensure_clean_store(setup_path) as store:
         df = DataFrame(

pandas/tests/io/pytables/test_categorical.py

@@ -1,8 +1,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas import (
     Categorical,
     DataFrame,
@@ -140,7 +138,6 @@ def test_categorical(setup_path):
             store.select("df3/meta/s/meta")
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_categorical_conversion(tmp_path, setup_path):
     # GH13322
     # Check that read_hdf with categorical columns doesn't return rows if

pandas/tests/io/pytables/test_read.py

@@ -5,8 +5,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas._libs.tslibs import Timestamp
 from pandas.compat import is_platform_windows
 
@@ -74,7 +72,6 @@ def test_read_missing_key_opened_store(tmp_path, setup_path):
         read_hdf(store, "k1")
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_read_column(setup_path):
     df = DataFrame(
         np.random.default_rng(2).standard_normal((10, 4)),

pandas/tests/io/pytables/test_select.py

@@ -1,8 +1,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas._libs.tslibs import Timestamp
 
 import pandas as pd
@@ -651,7 +649,6 @@ def test_frame_select(setup_path):
         #     store.select('frame', [crit1, crit2])
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_frame_select_complex(setup_path):
     # select via complex criteria
 
@@ -965,7 +962,6 @@ def test_query_long_float_literal(setup_path):
         tm.assert_frame_equal(expected, result)
 
 
-@pytest.mark.xfail(using_string_dtype(), reason="TODO(infer_string)")
 def test_query_compare_column_type(setup_path):
     # GH 15492
     df = DataFrame(