Issue #28596: The preferred encoding is UTF-8 on Android.

3 files changed, 29 insertions, 14 deletions

diff --git a/Lib/_bootlocale.py b/Lib/_bootlocale.py
index 4bccac1..0c61b0d 100644
--- a/Lib/_bootlocale.py
+++ b/Lib/_bootlocale.py
@@ -14,11 +14,17 @@ else:
     try:
         _locale.CODESET
     except AttributeError:
-        def getpreferredencoding(do_setlocale=True):
-            # This path for legacy systems needs the more complex
-            # getdefaultlocale() function, import the full locale module.
-            import locale
-            return locale.getpreferredencoding(do_setlocale)
+        if hasattr(sys, 'getandroidapilevel'):
+            # On Android langinfo.h and CODESET are missing, and UTF-8 is
+            # always used in mbstowcs() and wcstombs().
+            def getpreferredencoding(do_setlocale=True):
+                return 'UTF-8'
+        else:
+            def getpreferredencoding(do_setlocale=True):
+                # This path for legacy systems needs the more complex
+                # getdefaultlocale() function, import the full locale module.
+                import locale
+                return locale.getpreferredencoding(do_setlocale)
     else:
         def getpreferredencoding(do_setlocale=True):
             assert not do_setlocale
diff --git a/Lib/locale.py b/Lib/locale.py
index 4de0090..f8d1d78 100644
--- a/Lib/locale.py
+++ b/Lib/locale.py
@@ -618,15 +618,21 @@ else:
     try:
         CODESET
     except NameError:
-        # Fall back to parsing environment variables :-(
-        def getpreferredencoding(do_setlocale = True):
-            """Return the charset that the user is likely using,
-            by looking at environment variables."""
-            res = getdefaultlocale()[1]
-            if res is None:
-                # LANG not set, default conservatively to ASCII
-                res = 'ascii'
-            return res
+        if hasattr(sys, 'getandroidapilevel'):
+            # On Android langinfo.h and CODESET are missing, and UTF-8 is
+            # always used in mbstowcs() and wcstombs().
+            def getpreferredencoding(do_setlocale = True):
+                return 'UTF-8'
+        else:
+            # Fall back to parsing environment variables :-(
+            def getpreferredencoding(do_setlocale = True):
+                """Return the charset that the user is likely using,
+                by looking at environment variables."""
+                res = getdefaultlocale()[1]
+                if res is None:
+                    # LANG not set, default conservatively to ASCII
+                    res = 'ascii'
+                return res
     else:
         def getpreferredencoding(do_setlocale = True):
             """Return the charset that the user is likely using,
diff --git a/Misc/NEWS b/Misc/NEWS
index 3ef25b6..b2cbad1 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -13,6 +13,9 @@ Core and Builtins
 - Issue #18896: Python function can now have more than 255 parameters.
   collections.namedtuple() now supports tuples with more than 255 elements.
 
+- Issue #28596: The preferred encoding is UTF-8 on Android. Patch written by
+  Chi Hsuan Yen.
+
 - Issue #26919: On Android, operating system data is now always encoded/decoded
   to/from UTF-8, instead of the locale encoding to avoid inconsistencies with
   os.fsencode() and os.fsdecode() which are already using UTF-8.