py3: introduce a wrapper for __builtins__.{raw_,}input()

In order to make this work, we have to wrap the io streams in a
TextIOWrapper so that __builtins__.input() can do unicode IO on Python
3. We can't just restore the original (unicode) sys.std* because we
might be running a cmdserver, and if we blindly restore sys.* to the
original values then we end up breaking the cmdserver. Sadly,
TextIOWrapper tries to close the underlying stream during its __del__,
so we have to make a sublcass to prevent that.

If you see errors like:

TypeError: a bytes-like object is required, not 'str'

On an input() or print() call on Python 3, the substitution of
sys.std* is probably the root cause.

A previous version of this change tried to put the bytesinput() method
in pycompat - it turns out we need to do some encoding handling, so we
have to be in a higher layer that's allowed to use
mercurial.encoding.encoding. As a result, this is in util for now,
with the TextIOWrapper subclass hiding in encoding.py. I'm not sure of
a better place for the time being.

Differential Revision: https://phab.mercurial-scm.org/D299

hgext/hgk.py

@@ -50,6 +50,7 b' from mercurial import ('
     patch,
     registrar,
     scmutil,
+    util,
 )
 
 cmdtable = {}
@@ -96,7 +97,7 b' def difftree(ui, repo, node1=None, node2'
     while True:
         if opts['stdin']:
             try:
-                line = raw_input().split(' ')
+                line = util.bytesinput(ui.fin, ui.fout).split(' ')
                 node1 = line[0]
                 if len(line) > 1:
                     node2 = line[1]
@@ -177,7 +178,7 b' def catfile(ui, repo, type=None, r=None,'
     prefix = ""
     if opts['stdin']:
         try:
-            (type, r) = raw_input().split(' ')
+            (type, r) = util.bytesinput(ui.fin, ui.fout).split(' ')
             prefix = "    "
         except EOFError:
             return
@@ -195,7 +196,7 b' def catfile(ui, repo, type=None, r=None,'
         catcommit(ui, repo, n, prefix)
         if opts['stdin']:
             try:
-                (type, r) = raw_input().split(' ')
+                (type, r) = util.bytesinput(ui.fin, ui.fout).split(' ')
             except EOFError:
                 break
         else:

mercurial/encoding.py

@@ -8,6 +8,7 b''
 from __future__ import absolute_import
 
 import array
+import io
 import locale
 import os
 import unicodedata
@@ -573,3 +574,16 b' def fromutf8b(s):'
             c = chr(ord(c.decode("utf-8")) & 0xff)
         r += c
     return r
+
+class strio(io.TextIOWrapper):
+    """Wrapper around TextIOWrapper that respects hg's encoding assumptions.
+
+    Also works around Python closing streams.
+    """
+
+    def __init__(self, buffer, **kwargs):
+        kwargs[r'encoding'] = _sysstr(encoding)
+        super(strio, self).__init__(buffer, **kwargs)
+
+    def __del__(self):
+        """Override __del__ so it doesn't close the underlying stream."""

mercurial/ui.py

@@ -1217,18 +1217,10 b' class ui(object):'
         self.write(prompt, prompt=True)
         self.flush()
 
-        # instead of trying to emulate raw_input, swap (self.fin,
-        # self.fout) with (sys.stdin, sys.stdout)
-        oldin = sys.stdin
-        oldout = sys.stdout
-        sys.stdin = self.fin
-        sys.stdout = self.fout
         # prompt ' ' must exist; otherwise readline may delete entire line
         # - http://bugs.python.org/issue12833
         with self.timeblockedsection('stdio'):
-            line = raw_input(' ')
-        sys.stdin = oldin
-        sys.stdout = oldout
+            line = util.bytesinput(self.fin, self.fout, r' ')
 
         # When stdin is in binary mode on Windows, it can cause
         # raw_input() to emit an extra trailing carriage return

mercurial/util.py

@@ -172,6 +172,18 b' os.stat_float_times(False)'
 def safehasattr(thing, attr):
     return getattr(thing, attr, _notset) is not _notset
 
+def bytesinput(fin, fout, *args, **kwargs):
+    sin, sout = sys.stdin, sys.stdout
+    try:
+        if pycompat.ispy3:
+            sys.stdin, sys.stdout = encoding.strio(fin), encoding.strio(fout)
+            return encoding.strtolocal(input(*args, **kwargs))
+        else:
+            sys.stdin, sys.stdout = fin, fout
+            return raw_input(*args, **kwargs)
+    finally:
+        sys.stdin, sys.stdout = sin, sout
+
 def bitsfrom(container):
     bits = 0
     for bit in container: