bpo-21474: Update IDLE word/identifier definition from ascii to unicode. (GH-6643)


In text and entry boxes, this affects selection by double-click,
movement left/right by control-left/right, and deletion left/right
by control-BACKSPACE/DEL.
(cherry picked from commit 5ff3a161c8a6b525c5e5b3e36e9c43f5a95bda60)

Co-authored-by: Terry Jan Reedy <tjreedy@udel.edu>
diff --git a/Lib/idlelib/editor.py b/Lib/idlelib/editor.py
index ab9c7e6..892b64b 100644
--- a/Lib/idlelib/editor.py
+++ b/Lib/idlelib/editor.py
@@ -1658,12 +1658,12 @@
 
 
 def fixwordbreaks(root):
-    # Make sure that Tk's double-click and next/previous word
-    # operations use our definition of a word (i.e. an identifier)
+    # On Windows, tcl/tk breaks 'words' only on spaces, as in Command Prompt.
+    # We want Motif style everywhere. See #21474, msg218992 and followup.
     tk = root.tk
     tk.call('tcl_wordBreakAfter', 'a b', 0) # make sure word.tcl is loaded
-    tk.call('set', 'tcl_wordchars', '[a-zA-Z0-9_]')
-    tk.call('set', 'tcl_nonwordchars', '[^a-zA-Z0-9_]')
+    tk.call('set', 'tcl_wordchars', r'\w')
+    tk.call('set', 'tcl_nonwordchars', r'\W')
 
 
 def _editor_window(parent):  # htest #