[PATCH V2] fsmonitor: match watchman and filesystem encoding

[Olivier Trempe]

# HG changeset patch
# User Olivier Trempe <oliviertrempe at gmail.com>
# Date 1488981822 18000
#      Wed Mar 08 09:03:42 2017 -0500
# Branch stable
# Node ID 2021c3032968bef6b8d1cd7bea5a22996ced994c
# Parent  68f263f52d2e3e2798b4f1e55cb665c6b043f93b
fsmonitor: match watchman and filesystem encoding

watchman's paths encoding can differ from filesystem encoding. For example,
on Windows, it's always utf-8.

Before this patch, on Windows, mismatch in path comparison between fsmonitor
state and osutil.statfiles would yield a clean status for added/modified files.

In addition to status reporting wrong results, this leads to files being
discarded from changesets while doing history editing operations such as rebase.

diff --git a/hgext/fsmonitor/__init__.py b/hgext/fsmonitor/__init__.py
--- a/hgext/fsmonitor/__init__.py
+++ b/hgext/fsmonitor/__init__.py
@@ -91,6 +91,7 @@
 
 from __future__ import absolute_import
 
+import codecs
 import hashlib
 import os
 import stat
@@ -99,6 +100,7 @@
 from mercurial import (
     context,
     encoding,
+    error,
     extensions,
     localrepo,
     merge,
@@ -110,6 +112,7 @@
 from mercurial import match as matchmod
 
 from . import (
+    pywatchman,
     state,
     watchmanclient,
 )
@@ -159,6 +162,23 @@
     sha1.update('\0')
     return sha1.hexdigest()
 
+_watchmanencoding = pywatchman.encoding.get_local_encoding()
+_fsencoding = sys.getfilesystemencoding() or sys.getdefaultencoding()
+_fixencoding = codecs.lookup(_watchmanencoding) != codecs.lookup(_fsencoding)
+
+def _watchmantofsencoding(path):
+    """Fix path to match watchman and local filesystem encoding
+
+    watchman's paths encoding can differ from filesystem encoding. For example,
+    on Windows, it's always utf-8.
+    """
+    try:
+        decoded = path.decode(_watchmanencoding)
+    except UnicodeDecodeError as e:
+        raise error.Abort(e, hint='watchman encoding error')
+
+    return decoded.encode(_fsencoding, 'replace')
+
 def overridewalk(orig, self, match, subrepos, unknown, ignored, full=True):
     '''Replacement for dirstate.walk, hooking into Watchman.
 
@@ -303,6 +323,8 @@
     # for name case changes.
     for entry in result['files']:
         fname = entry['name']
+        if _fixencoding:
+            fname = _watchmantofsencoding(fname)
         if switch_slashes:
             fname = fname.replace('\\', '/')
         if normalize: