BUG: to_clipboard text truncated for Python 3 on Windows for UTF-16 text (#25040)

Author: david-liu-brattle-1

doc/source/whatsnew/v0.25.0.rst

@@ -165,6 +165,7 @@ MultiIndex
 I/O
 ^^^
 
+- Fixed bug in missing text when using :meth:`to_clipboard` if copying utf-16 characters in Python 3 on Windows (:issue:`25040`)
 -
 -
 -

pandas/io/clipboard/windows.py

@@ -29,6 +29,7 @@ def init_windows_clipboard():
                                  HINSTANCE, HMENU, BOOL, UINT, HANDLE)
 
     windll = ctypes.windll
+    msvcrt = ctypes.CDLL('msvcrt')
 
     safeCreateWindowExA = CheckedCall(windll.user32.CreateWindowExA)
     safeCreateWindowExA.argtypes = [DWORD, LPCSTR, LPCSTR, DWORD, INT, INT,
@@ -71,6 +72,10 @@ def init_windows_clipboard():
     safeGlobalUnlock.argtypes = [HGLOBAL]
     safeGlobalUnlock.restype = BOOL
 
+    wcslen = CheckedCall(msvcrt.wcslen)
+    wcslen.argtypes = [c_wchar_p]
+    wcslen.restype = UINT
+
     GMEM_MOVEABLE = 0x0002
     CF_UNICODETEXT = 13
 
@@ -129,13 +134,13 @@ def copy_windows(text):
                     # If the hMem parameter identifies a memory object,
                     # the object must have been allocated using the
                     # function with the GMEM_MOVEABLE flag.
-                    count = len(text) + 1
+                    count = wcslen(text) + 1
                     handle = safeGlobalAlloc(GMEM_MOVEABLE,
                                              count * sizeof(c_wchar))
                     locked_handle = safeGlobalLock(handle)
 
-                    ctypes.memmove(c_wchar_p(locked_handle),
-                                   c_wchar_p(text), count * sizeof(c_wchar))
+                    ctypes.memmove(c_wchar_p(locked_handle), c_wchar_p(text),
+                                   count * sizeof(c_wchar))
 
                     safeGlobalUnlock(handle)
                     safeSetClipboardData(CF_UNICODETEXT, handle)

pandas/tests/io/test_clipboard.py

@@ -12,6 +12,7 @@
 from pandas.util import testing as tm
 from pandas.util.testing import makeCustomDataframe as mkdf
 
+from pandas.io.clipboard import clipboard_get, clipboard_set
 from pandas.io.clipboard.exceptions import PyperclipException
 
 try:
@@ -30,8 +31,8 @@ def build_kwargs(sep, excel):
     return kwargs
 
 
-@pytest.fixture(params=['delims', 'utf8', 'string', 'long', 'nonascii',
-                        'colwidth', 'mixed', 'float', 'int'])
+@pytest.fixture(params=['delims', 'utf8', 'utf16', 'string', 'long',
+                        'nonascii', 'colwidth', 'mixed', 'float', 'int'])
 def df(request):
     data_type = request.param
 
@@ -41,6 +42,10 @@ def df(request):
     elif data_type == 'utf8':
         return pd.DataFrame({'a': ['µasd', 'Ωœ∑´'],
                              'b': ['øπ∆˚¬', 'œ∑´®']})
+    elif data_type == 'utf16':
+        return pd.DataFrame({'a': ['\U0001f44d\U0001f44d',
+                                   '\U0001f44d\U0001f44d'],
+                             'b': ['abc', 'def']})
     elif data_type == 'string':
         return mkdf(5, 3, c_idx_type='s', r_idx_type='i',
                     c_idx_names=[None], r_idx_names=[None])
@@ -225,3 +230,14 @@ def test_invalid_encoding(self, df):
     @pytest.mark.parametrize('enc', ['UTF-8', 'utf-8', 'utf8'])
     def test_round_trip_valid_encodings(self, enc, df):
         self.check_round_trip_frame(df, encoding=enc)
+
+
+@pytest.mark.single
+@pytest.mark.clipboard
+@pytest.mark.skipif(not _DEPS_INSTALLED,
+                    reason="clipboard primitives not installed")
+@pytest.mark.parametrize('data', [u'\U0001f44d...', u'Ωœ∑´...', 'abcd...'])
+def test_raw_roundtrip(data):
+    # PR #25040 wide unicode wasn't copied correctly on PY3 on windows
+    clipboard_set(data)
+    assert data == clipboard_get()