Merge branch 'compat-getenv-and-expanduser' of https://github.com/dstftw/youtube-dl into dstftw-compat-getenv-and-expanduser

Conflicts:
	test/test_utils.py
	youtube_dl/__init__.py

1 files changed, 83 insertions, 4 deletions

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index d7ae5a90a..9287edd8d 100644
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -203,6 +203,82 @@ def compat_ord(c):
     if type(c) is int: return c
     else: return ord(c)
 
+
+if sys.version_info >= (3, 0):
+    compat_getenv = os.getenv
+    compat_expanduser = os.path.expanduser
+else:
+    # Environment variables should be decoded with filesystem encoding.
+    # Otherwise it will fail if any non-ASCII characters present (see #3854 #3217 #2918)
+
+    def compat_getenv(key, default=None):
+        env = os.getenv(key, default)
+        if env:
+            env = env.decode(get_filesystem_encoding())
+        return env
+
+    # HACK: The default implementations of os.path.expanduser from cpython do not decode
+    # environment variables with filesystem encoding. We will work around this by
+    # providing adjusted implementations.
+    # The following are os.path.expanduser implementations from cpython 2.7.8 stdlib
+    # for different platforms with correct environment variables decoding.
+
+    if os.name == 'posix':
+        def compat_expanduser(path):
+            """Expand ~ and ~user constructions.  If user or $HOME is unknown,
+            do nothing."""
+            if not path.startswith('~'):
+                return path
+            i = path.find('/', 1)
+            if i < 0:
+                i = len(path)
+            if i == 1:
+                if 'HOME' not in os.environ:
+                    import pwd
+                    userhome = pwd.getpwuid(os.getuid()).pw_dir
+                else:
+                    userhome = compat_getenv('HOME')
+            else:
+                import pwd
+                try:
+                    pwent = pwd.getpwnam(path[1:i])
+                except KeyError:
+                    return path
+                userhome = pwent.pw_dir
+            userhome = userhome.rstrip('/')
+            return (userhome + path[i:]) or '/'
+    elif os.name == 'nt' or os.name == 'ce':
+        def compat_expanduser(path):
+            """Expand ~ and ~user constructs.
+
+            If user or $HOME is unknown, do nothing."""
+            if path[:1] != '~':
+                return path
+            i, n = 1, len(path)
+            while i < n and path[i] not in '/\\':
+                i = i + 1
+
+            if 'HOME' in os.environ:
+                userhome = compat_getenv('HOME')
+            elif 'USERPROFILE' in os.environ:
+                userhome = compat_getenv('USERPROFILE')
+            elif not 'HOMEPATH' in os.environ:
+                return path
+            else:
+                try:
+                    drive = compat_getenv('HOMEDRIVE')
+                except KeyError:
+                    drive = ''
+                userhome = os.path.join(drive, compat_getenv('HOMEPATH'))
+
+            if i != 1: #~user
+                userhome = os.path.join(os.path.dirname(userhome), path[1:i])
+
+            return userhome + path[i:]
+    else:
+        compat_expanduser = os.path.expanduser
+
+
 # This is not clearly defined otherwise
 compiled_regex_type = type(re.compile(''))
 
@@ -1207,11 +1283,14 @@ class locked_file(object):
         return self.f.read(*args)
 
 
+def get_filesystem_encoding():
+    encoding = sys.getfilesystemencoding()
+    return encoding if encoding is not None else 'utf-8'
+
+
 def shell_quote(args):
     quoted_args = []
-    encoding = sys.getfilesystemencoding()
-    if encoding is None:
-        encoding = 'utf-8'
+    encoding = get_filesystem_encoding()
     for a in args:
         if isinstance(a, bytes):
             # We may get a filename encoded with 'encodeFilename'
@@ -1261,7 +1340,7 @@ def format_bytes(bytes):
 
 
 def get_term_width():
-    columns = os.environ.get('COLUMNS', None)
+    columns = compat_getenv('COLUMNS', None)
     if columns:
         return int(columns)