From 6cf77526210c5cbd586a77ed55258e510d436854 Mon Sep 17 00:00:00 2001
From: Steph Prince <40640337+stephprince@users.noreply.github.com>
Date: Mon, 11 Nov 2024 13:28:42 -0800
Subject: [PATCH] add string dataset condition for data type conversion on
 export (#1205)

* add strdataset condition for dtype conversion

* add strdataset conversion test

* update CHANGELOG
---
 CHANGELOG.md                                 |  1 +
 src/hdmf/build/objectmapper.py               |  7 +++++--
 tests/unit/build_tests/test_convert_dtype.py | 18 ++++++++++++++++++
 3 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index b4f0fde80..9ac153581 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -8,6 +8,7 @@
 
 ### Bug fixes
 - Fixed inaccurate error message when validating reference data types. @stephprince [#1199](https://github.com/hdmf-dev/hdmf/pull/1199)
+- Fixed incorrect dtype conversion of a StrDataset. @stephprince [#1205](https://github.com/hdmf-dev/hdmf/pull/1205)
 
 ## HDMF 3.14.5 (October 6, 2024)
 
diff --git a/src/hdmf/build/objectmapper.py b/src/hdmf/build/objectmapper.py
index 493a55bab..3394ebb91 100644
--- a/src/hdmf/build/objectmapper.py
+++ b/src/hdmf/build/objectmapper.py
@@ -21,7 +21,7 @@
 from ..query import ReferenceResolver
 from ..spec import Spec, AttributeSpec, DatasetSpec, GroupSpec, LinkSpec, RefSpec
 from ..spec.spec import BaseStorageSpec
-from ..utils import docval, getargs, ExtenderMeta, get_docval, get_data_shape
+from ..utils import docval, getargs, ExtenderMeta, get_docval, get_data_shape, StrDataset
 
 _const_arg = '__constructor_arg'
 
@@ -212,7 +212,10 @@ def convert_dtype(cls, spec, value, spec_dtype=None):  # noqa: C901
         if (isinstance(value, np.ndarray) or
                 (hasattr(value, 'astype') and hasattr(value, 'dtype'))):
             if spec_dtype_type is _unicode:
-                ret = value.astype('U')
+                if isinstance(value, StrDataset):
+                    ret = value
+                else:
+                    ret = value.astype('U')
                 ret_dtype = "utf8"
             elif spec_dtype_type is _ascii:
                 ret = value.astype('S')
diff --git a/tests/unit/build_tests/test_convert_dtype.py b/tests/unit/build_tests/test_convert_dtype.py
index 8f9e49239..8f30386d8 100644
--- a/tests/unit/build_tests/test_convert_dtype.py
+++ b/tests/unit/build_tests/test_convert_dtype.py
@@ -1,12 +1,17 @@
 from datetime import datetime, date
 
 import numpy as np
+import h5py
+import unittest
+
 from hdmf.backends.hdf5 import H5DataIO
 from hdmf.build import ObjectMapper
 from hdmf.data_utils import DataChunkIterator
 from hdmf.spec import DatasetSpec, RefSpec, DtypeSpec
 from hdmf.testing import TestCase
+from hdmf.utils import StrDataset
 
+H5PY_3 = h5py.__version__.startswith('3')
 
 class TestConvertDtype(TestCase):
 
@@ -321,6 +326,19 @@ def test_text_spec(self):
                 self.assertIs(ret, value)
                 self.assertEqual(ret_dtype, 'utf8')
 
+    @unittest.skipIf(not H5PY_3, "Use StrDataset only for h5py 3+")
+    def test_text_spec_str_dataset(self):
+        text_spec_types = ['text', 'utf', 'utf8', 'utf-8']
+        for spec_type in text_spec_types:
+            with self.subTest(spec_type=spec_type):
+                with h5py.File("test.h5", "w", driver="core", backing_store=False) as f:
+                    spec = DatasetSpec('an example dataset', spec_type, name='data')
+
+                    value = StrDataset(f.create_dataset('data', data=['a', 'b', 'c']), None)
+                    ret, ret_dtype = ObjectMapper.convert_dtype(spec, value)  # no conversion
+                    self.assertIs(ret, value)
+                    self.assertEqual(ret_dtype, 'utf8')
+
     def test_ascii_spec(self):
         ascii_spec_types = ['ascii', 'bytes']
         for spec_type in ascii_spec_types: