ENH: Improved error message and raise new error for small-string NaN … (#60907)

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)

Co-authored-by: Jake Thomas Trevallion <[email protected]>

Author: rhshadrach

pandas/io/pytables.py

@@ -3464,6 +3464,12 @@ def validate(self, other) -> None:
                     # Value of type "Optional[Any]" is not indexable  [index]
                     oax = ov[i]  # type: ignore[index]
                     if sax != oax:
+                        if c == "values_axes" and sax.kind != oax.kind:
+                            raise ValueError(
+                                f"Cannot serialize the column [{oax.values[0]}] "
+                                f"because its data contents are not [{sax.kind}] "
+                                f"but [{oax.kind}] object dtype"
+                            )
                         raise ValueError(
                             f"invalid combination of [{c}] on appending data "
                             f"[{sax}] vs current table [{oax}]"
@@ -5111,6 +5117,9 @@ def _maybe_convert_for_string_atom(
     data = bvalues.copy()
     data[mask] = nan_rep
 
+    if existing_col and mask.any() and len(nan_rep) > existing_col.itemsize:
+        raise ValueError("NaN representation is too large for existing column size")
+
     # see if we have a valid string type
     inferred_type = lib.infer_dtype(data, skipna=False)
     if inferred_type != "string":

pandas/tests/io/pytables/test_append.py

@@ -818,12 +818,9 @@ def test_append_raise(setup_path):
         store.append("df", df)
         df["foo"] = "bar"
         msg = re.escape(
-            "invalid combination of [values_axes] on appending data "
-            "[name->values_block_1,cname->values_block_1,"
-            "dtype->bytes24,kind->string,shape->(1, 30)] "
-            "vs current table "
-            "[name->values_block_1,cname->values_block_1,"
-            "dtype->datetime64[s],kind->datetime64[s],shape->None]"
+            "Cannot serialize the column [foo] "
+            "because its data contents are not [string] "
+            "but [datetime64[s]] object dtype"
         )
         with pytest.raises(ValueError, match=msg):
             store.append("df", df)
@@ -989,3 +986,29 @@ def test_append_to_multiple_min_itemsize(setup_path):
         )
         result = store.select_as_multiple(["index", "nums", "strs"])
         tm.assert_frame_equal(result, expected, check_index_type=True)
+
+
+def test_append_string_nan_rep(setup_path):
+    # GH 16300
+    df = DataFrame({"A": "a", "B": "foo"}, index=np.arange(10))
+    df_nan = df.copy()
+    df_nan.loc[0:4, :] = np.nan
+    msg = "NaN representation is too large for existing column size"
+
+    with ensure_clean_store(setup_path) as store:
+        # string column too small
+        store.append("sa", df["A"])
+        with pytest.raises(ValueError, match=msg):
+            store.append("sa", df_nan["A"])
+
+        # nan_rep too big
+        store.append("sb", df["B"], nan_rep="bars")
+        with pytest.raises(ValueError, match=msg):
+            store.append("sb", df_nan["B"])
+
+        # smaller modified nan_rep
+        store.append("sc", df["A"], nan_rep="n")
+        store.append("sc", df_nan["A"])
+        result = store["sc"]
+        expected = concat([df["A"], df_nan["A"]])
+        tm.assert_series_equal(result, expected)

pandas/tests/io/pytables/test_round_trip.py

@@ -213,12 +213,9 @@ def test_table_values_dtypes_roundtrip(setup_path):
 
         # incompatible dtype
         msg = re.escape(
-            "invalid combination of [values_axes] on appending data "
-            "[name->values_block_0,cname->values_block_0,"
-            "dtype->float64,kind->float,shape->(1, 3)] vs "
-            "current table [name->values_block_0,"
-            "cname->values_block_0,dtype->int64,kind->integer,"
-            "shape->None]"
+            "Cannot serialize the column [a] "
+            "because its data contents are not [float] "
+            "but [integer] object dtype"
         )
         with pytest.raises(ValueError, match=msg):
             store.append("df_i8", df1)