Merge pull request #1092 from centricular/always-use-utf-8-py3

Always use utf-8 to write configured file and warn if the encoding is not UTF-8 compatible

2 files changed, 14 insertions, 3 deletions

diff --git a/meson.py b/meson.py
index 8c223e5..6dc5c7a 100755
--- a/meson.py
+++ b/meson.py
@@ -14,10 +14,21 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from mesonbuild import mesonmain
-import sys, os
+from mesonbuild import mlog, mesonmain
+import sys, os, locale
 
 def main():
+    # Warn if the locale is not UTF-8. This can cause various unfixable issues
+    # such as os.stat not being able to decode filenames with unicode in them.
+    # There is no way to reset both the preferred encoding and the filesystem
+    # encoding, so we can just warn about it.
+    e = locale.getpreferredencoding()
+    if e.upper() != 'UTF-8':
+        mlog.warning('You are using {!r} which is not a a Unicode-compatible '
+                     'locale.'.format(e))
+        mlog.warning('You might see errors if you use UTF-8 strings as '
+                     'filenames, as strings, or as file contents.')
+        mlog.warning('Please switch to a UTF-8 locale for your platform.')
     # Always resolve the command path so Ninja can find it for regen, tests, etc.
     launcher = os.path.realpath(sys.argv[0])
     return mesonmain.run(launcher, sys.argv[1:])
diff --git a/mesonbuild/mesonlib.py b/mesonbuild/mesonlib.py
index b92be5f..4d9cc69 100644
--- a/mesonbuild/mesonlib.py
+++ b/mesonbuild/mesonlib.py
@@ -303,7 +303,7 @@ def do_conf_file(src, dst, confdata):
     replace_if_different(dst, dst_tmp)
 
 def dump_conf_header(ofilename, cdata):
-    with open(ofilename, 'w') as ofile:
+    with open(ofilename, 'w', encoding='utf-8') as ofile:
         ofile.write('''/*
  * Autogenerated by the Meson build system.
  * Do not edit, your changes will be lost.