golang_str: Move everything related to pickling to golang_str_pickle.pyx

In the future we will be adding more functionality and tests related to
pickling. So it makes sense to keep pickle-related functionality in its
own unit.

-> Move the code to golang_str_pickle* as a preparatory step for that.

golang/_golang.pyx

@@ -3,7 +3,7 @@
 # cython: binding=False
 # cython: c_string_type=str, c_string_encoding=utf8
 # distutils: language = c++
-# distutils: depends = libgolang.h os/signal.h unicode/utf8.h _golang_str.pyx
+# distutils: depends = libgolang.h os/signal.h unicode/utf8.h _golang_str.pyx _golang_str_pickle.pyx
 #
 # Copyright (C) 2018-2024  Nexedi SA and Contributors.
 #                          Kirill Smelkov <kirr@nexedi.com>

golang/_golang_str.pyx

@@ -78,10 +78,6 @@ import string as pystring
 import types as pytypes
 import functools as pyfunctools
 import re as pyre
-if PY_MAJOR_VERSION >= 3:
-    import copyreg as pycopyreg
-else:
-    import copy_reg as pycopyreg
 
 
 # zbytes/zunicode point to original std bytes/unicode types even if they will be patched.
@@ -331,18 +327,8 @@ cdef class _pybstr(bytes):   # https://github.com/cython/cython/issues/711
             # [b('β')] goes as ['β'] when under _bstringify for %s
             return qself
 
-
-    # override reduce for protocols < 2. Builtin handler for that goes through
-    # copyreg._reduce_ex which eventually calls bytes(bstr-instance) to
-    # retrieve state, which gives bstr, not bytes. Fix state to be bytes ourselves.
     def __reduce_ex__(self, protocol):
-        if protocol >= 2:
-            return zbytes.__reduce_ex__(self, protocol)
-        return (
-            pycopyreg._reconstructor,
-            (self.__class__, self.__class__, _bdata(self))
-        )
-
+        return _bstr__reduce_ex__(self, protocol)
 
     def __hash__(self):
         # hash of the same unicode and UTF-8 encoded bytes is generally different
@@ -724,18 +710,8 @@ cdef class _pyustr(unicode):
             # [u('β')] goes as ['β'] when under _bstringify for %s
             return qself
 
-
-    # override reduce for protocols < 2. Builtin handler for that goes through
-    # copyreg._reduce_ex which eventually calls unicode(ustr-instance) to
-    # retrieve state, which gives ustr, not unicode. Fix state to be unicode ourselves.
     def __reduce_ex__(self, protocol):
-        if protocol >= 2:
-            return zunicode.__reduce_ex__(self, protocol)
-        return (
-            pycopyreg._reconstructor,
-            (self.__class__, self.__class__, _udata(self))
-        )
-
+        return _ustr__reduce_ex__(self, protocol)
 
     def __hash__(self):
         # see _pybstr.__hash__ for why we stick to hash of current str
@@ -2197,3 +2173,8 @@ cdef unicode _xunichr(rune i):
         uh = i - 0x10000
         return unichr(0xd800 + (uh >> 10)) + \
                unichr(0xdc00 + (uh & 0x3ff))
+
+
+# ---- pickle ----
+
+include '_golang_str_pickle.pyx'

golang/_golang_str_pickle.pyx

+# -*- coding: utf-8 -*-
+# Copyright (C) 2023-2024  Nexedi SA and Contributors.
+#                          Kirill Smelkov <kirr@nexedi.com>
+#
+# This program is free software: you can Use, Study, Modify and Redistribute
+# it under the terms of the GNU General Public License version 3, or (at your
+# option) any later version, as published by the Free Software Foundation.
+#
+# You can also Link and Combine this program with other software covered by
+# the terms of any of the Free Software licenses or any of the Open Source
+# Initiative approved licenses and Convey the resulting work. Corresponding
+# source of such a combination shall include the source code for all other
+# software used.
+#
+# This program is distributed WITHOUT ANY WARRANTY; without even the implied
+# warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+#
+# See COPYING file for full licensing terms.
+# See https://www.nexedi.com/licensing for rationale and options.
+"""_golang_str_pickle.pyx complements _golang_str.pyx and keeps everything
+related to pickling strings.
+
+It is included from _golang_str.pyx .
+"""
+
+if PY_MAJOR_VERSION >= 3:
+    import copyreg as pycopyreg
+else:
+    import copy_reg as pycopyreg
+
+
+# support for pickling bstr/ustr as standalone types.
+cdef _bstr__reduce_ex__(self, protocol):
+    # override reduce for protocols < 2. Builtin handler for that goes through
+    # copyreg._reduce_ex which eventually calls bytes(bstr-instance) to
+    # retrieve state, which gives bstr, not bytes. Fix state to be bytes ourselves.
+    if protocol >= 2:
+        return zbytes.__reduce_ex__(self, protocol)
+    return (
+        pycopyreg._reconstructor,
+        (self.__class__, self.__class__, _bdata(self))
+    )
+
+cdef _ustr__reduce_ex__(self, protocol):
+    # override reduce for protocols < 2. Builtin handler for that goes through
+    # copyreg._reduce_ex which eventually calls unicode(ustr-instance) to
+    # retrieve state, which gives ustr, not unicode. Fix state to be unicode ourselves.
+    if protocol >= 2:
+        return zunicode.__reduce_ex__(self, protocol)
+    return (
+        pycopyreg._reconstructor,
+        (self.__class__, self.__class__, _udata(self))
+    )

golang/golang_str_pickle_test.py

+# -*- coding: utf-8 -*-
+# Copyright (C) 2022-2024  Nexedi SA and Contributors.
+#                          Kirill Smelkov <kirr@nexedi.com>
+#
+# This program is free software: you can Use, Study, Modify and Redistribute
+# it under the terms of the GNU General Public License version 3, or (at your
+# option) any later version, as published by the Free Software Foundation.
+#
+# You can also Link and Combine this program with other software covered by
+# the terms of any of the Free Software licenses or any of the Open Source
+# Initiative approved licenses and Convey the resulting work. Corresponding
+# source of such a combination shall include the source code for all other
+# software used.
+#
+# This program is distributed WITHOUT ANY WARRANTY; without even the implied
+# warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+#
+# See COPYING file for full licensing terms.
+# See https://www.nexedi.com/licensing for rationale and options.
+
+from __future__ import print_function, absolute_import
+
+from golang import b, u, bstr, ustr
+import pickle
+
+
+# verify that bstr/ustr can be pickled/unpickled correctly.
+def test_strings_pickle():
+    bs = b("мир")
+    us = u("май")
+
+    #from pickletools import dis
+    for proto in range(0, pickle.HIGHEST_PROTOCOL+1):
+        p_bs = pickle.dumps(bs, proto)
+        #dis(p_bs)
+        bs_ = pickle.loads(p_bs)
+        assert type(bs_) is bstr
+        assert bs_ == bs
+
+        p_us = pickle.dumps(us, proto)
+        #dis(p_us)
+        us_ = pickle.loads(p_us)
+        assert type(us_) is ustr
+        assert us_ == us

golang/golang_str_test.py

@@ -334,26 +334,6 @@ def test_strings_memoryview():
     assert _(5) == 0x80
 
 
-# verify that bstr/ustr can be pickled/unpickled correctly.
-def test_strings_pickle():
-    bs = b("мир")
-    us = u("май")
-
-    #from pickletools import dis
-    for proto in range(0, pickle.HIGHEST_PROTOCOL+1):
-        p_bs = pickle.dumps(bs, proto)
-        #dis(p_bs)
-        bs_ = pickle.loads(p_bs)
-        assert type(bs_) is bstr
-        assert bs_ == bs
-
-        p_us = pickle.dumps(us, proto)
-        #dis(p_us)
-        us_ = pickle.loads(p_us)
-        assert type(us_) is ustr
-        assert us_ == us
-
-
 # verify that ord on bstr/ustr works as expected.
 def test_strings_ord():
     with raises(TypeError): ord(b(''))

setup.py

@@ -268,7 +268,9 @@ setup(
     ext_modules = [
                     Ext('golang._golang',
                         ['golang/_golang.pyx'],
-                        depends = ['golang/_golang_str.pyx']),
+                        depends = [
+                            'golang/_golang_str.pyx',
+                            'golang/_golang_str_pickle.pyx']),
 
                     Ext('golang.runtime._runtime_thread',
                         ['golang/runtime/_runtime_thread.pyx']),