[PATCH stable] fsmonitor: match watchman and local encoding

[Olivier Trempe]

# HG changeset patch
# User Olivier Trempe <oliviertrempe at gmail.com>
# Date 1488810111 18000
#      Mon Mar 06 09:21:51 2017 -0500
# Branch stable
# Node ID c9d3f8d1a57346228f5c3bb749acdff90d37e194
# Parent  6b00c3ecd15b26587de8cca6fab811069cba3b2f
fsmonitor: match watchman and local encoding

watchman's paths encoding is os dependant. For example, on Windows, it's
always utf-8. This causes paths comparison mismatch when paths contain non ascii
characters.

diff -r 6b00c3ecd15b -r c9d3f8d1a573 hgext/fsmonitor/__init__.py
--- a/hgext/fsmonitor/__init__.py	Thu Mar 02 20:19:45 2017 -0500
+++ b/hgext/fsmonitor/__init__.py	Mon Mar 06 09:21:51 2017 -0500
@@ -99,6 +99,7 @@
 from mercurial import (
     context,
     encoding,
+    error,
     extensions,
     localrepo,
     merge,
@@ -110,6 +111,7 @@
 from mercurial import match as matchmod
 
 from . import (
+    pywatchman,
     state,
     watchmanclient,
 )
@@ -159,6 +161,20 @@
     sha1.update('\0')
     return sha1.hexdigest()
 
+def _watchmanencodingtolocal(path):
+    """Fix path to match watchman and local encoding
+
+    watchman's paths encoding is os dependant. For example, on Windows, it's
+    always utf-8. This converts watchman encoded paths to local encoding to
+    avoid paths comparison mismatch.
+    """
+    try:
+        decoded = pywatchman.encoding.decode_local(path)
+    except UnicodeDecodeError as e:
+        raise error.Abort(e, hint='watchman encoding error')
+
+    return decoded.encode(encoding.encoding, 'replace')
+
 def overridewalk(orig, self, match, subrepos, unknown, ignored, full=True):
     '''Replacement for dirstate.walk, hooking into Watchman.
 
@@ -302,7 +318,7 @@
     # Watchman tracks files.  We use this property to reconcile deletes
     # for name case changes.
     for entry in result['files']:
-        fname = entry['name']
+        fname = _watchmanencodingtolocal(entry['name'])
         if switch_slashes:
             fname = fname.replace('\\', '/')
         if normalize: