geo-rep: Fix syncing of files with non-ascii filenames

Problem:
  Creation of files/directories with non-ascii names fails
  to sync to the slave. It crashes with below traceback on
  slave.
  ...
  File "/usr/lib/x86_64-linux-gnu/glusterfs/python/syncdaemon/repce.py", line 118, in worker
    res = getattr(self.obj, rmeth)(*in_data[2:])
  File "/usr/lib/x86_64-linux-gnu/glusterfs/python/syncdaemon/resource.py", line 709, in entry_ops
    [ESTALE, EINVAL, EBUSY])
  File "/usr/lib/x86_64-linux-gnu/glusterfs/python/syncdaemon/syncdutils.py", line 546, in errno_wrap
    return call(*arg)
  File "/usr/lib/x86_64-linux-gnu/glusterfs/python/syncdaemon/libcxattr.py", line 83, in lsetxattr
    cls.raise_oserr()
  File "/usr/lib/x86_64-linux-gnu/glusterfs/python/syncdaemon/libcxattr.py", line 38, in raise_oserr
    raise OSError(errn, os.strerror(errn))
  OSError: [Errno 12] Cannot allocate memory

Cause:
  The length calculation arguments passed to blob creation was done before encoding. Hence
  was failing in gfid-access layer.

Fix:
  It appears that the calculating lenght properly fixes this issue. But it will cause
  issues in other places in 'python2' and not in 'python3'. So encoding and decoding
  each required string to make geo-rep compatible with both 'python2' and 'python3'
  is a nightmare and is not fool proof. Hence kept 'python2' code as is with out
  encode/decode and applied encode/decode only to 'python3'

Added non-ascii filename tests to regression

fixes: bz#1650893
Change-Id: I35cfaf848e07b1a0b5cb93c01b98b472f08271a6
Signed-off-by: Kotresh HR <khiremat@redhat.com>

1 files changed, 16 insertions, 14 deletions

diff --git a/geo-replication/syncdaemon/libgfchangelog.py b/geo-replication/syncdaemon/libgfchangelog.py
index cc40fd5475d..fff9d24e54f 100644
--- a/geo-replication/syncdaemon/libgfchangelog.py
+++ b/geo-replication/syncdaemon/libgfchangelog.py
@@ -9,9 +9,10 @@
 #
 
 import os
-from ctypes import CDLL, RTLD_GLOBAL, create_string_buffer, \
-    get_errno, byref, c_ulong
+from ctypes import CDLL, RTLD_GLOBAL, get_errno, byref, c_ulong
 from syncdutils import ChangelogException, ChangelogHistoryNotAvailable
+from py2py3 import gr_cl_history_changelog, gr_cl_done, gr_create_string_buffer
+from py2py3 import gr_cl_register, gr_cl_history_done, bytearray_to_str
 
 
 class Changes(object):
@@ -39,9 +40,7 @@ class Changes(object):
 
     @classmethod
     def cl_register(cls, brick, path, log_file, log_level, retries=0):
-        ret = cls._get_api('gf_changelog_register')(brick.encode(), path.encode(),
-                                                    log_file.encode(),
-                                                    log_level, retries)
+        ret = gr_cl_register(cls, brick, path, log_file, log_level, retries)
         if ret == -1:
             cls.raise_changelog_err()
 
@@ -63,14 +62,16 @@ class Changes(object):
         def clsort(f):
             return f.split('.')[-1]
         changes = []
-        buf = create_string_buffer(b'\0' * 4096)
+        buf = gr_create_string_buffer(4096)
         call = cls._get_api('gf_changelog_next_change')
 
         while True:
             ret = call(buf, 4096)
             if ret in (0, -1):
                 break
-            changes.append(buf.raw[:ret - 1].decode())
+            # py2 and py3 compatibility
+            result = bytearray_to_str(buf.raw[:ret - 1])
+            changes.append(result)
         if ret == -1:
             cls.raise_changelog_err()
         # cleanup tracker
@@ -79,7 +80,7 @@ class Changes(object):
 
     @classmethod
     def cl_done(cls, clfile):
-        ret = cls._get_api('gf_changelog_done')(clfile.encode())
+        ret = gr_cl_done(cls, clfile)
         if ret == -1:
             cls.raise_changelog_err()
 
@@ -94,9 +95,8 @@ class Changes(object):
     @classmethod
     def cl_history_changelog(cls, changelog_path, start, end, num_parallel):
         actual_end = c_ulong()
-        ret = cls._get_api('gf_history_changelog')(changelog_path.encode(), start, end,
-                                                   num_parallel,
-                                                   byref(actual_end))
+        ret = gr_cl_history_changelog(cls, changelog_path, start, end,
+                                      num_parallel, byref(actual_end))
         if ret == -1:
             cls.raise_changelog_err()
 
@@ -118,14 +118,16 @@ class Changes(object):
             return f.split('.')[-1]
 
         changes = []
-        buf = create_string_buffer(b'\0' * 4096)
+        buf = gr_create_string_buffer(4096)
         call = cls._get_api('gf_history_changelog_next_change')
 
         while True:
             ret = call(buf, 4096)
             if ret in (0, -1):
                 break
-            changes.append(buf.raw[:ret - 1].decode())
+            # py2 and py3 compatibility
+            result = bytearray_to_str(buf.raw[:ret - 1])
+            changes.append(result)
         if ret == -1:
             cls.raise_changelog_err()
 
@@ -133,6 +135,6 @@ class Changes(object):
 
     @classmethod
     def cl_history_done(cls, clfile):
-        ret = cls._get_api('gf_history_changelog_done')(clfile.encode())
+        ret = gr_cl_history_done(cls, clfile)
         if ret == -1:
             cls.raise_changelog_err()