X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fcompat.py;h=1ff42d94b95d9098cf270b883176bb2a06e54297;hb=857421024daf810e92036149cc02bcf1c337da5c;hp=54ccf1d28773dcc975ed43e8dd3704da77e4d4b4;hpb=13fc7f3a05e0cb8b111e62540a4795611cc0a9dd;p=youtube-dl

diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py
index 54ccf1d28..1ff42d94b 100644
--- a/youtube_dl/compat.py
+++ b/youtube_dl/compat.py
@@ -5,6 +5,7 @@ import getpass
 import optparse
 import os
 import re
+import shlex
 import shutil
 import socket
 import subprocess
@@ -42,6 +43,11 @@ try:
 except ImportError:  # Python 2
     import cookielib as compat_cookiejar
 
+try:
+    import http.cookies as compat_cookies
+except ImportError:  # Python 2
+    import Cookie as compat_cookies
+
 try:
     import html.entities as compat_html_entities
 except ImportError:  # Python 2
@@ -74,11 +80,20 @@ try:
 except ImportError:
     import BaseHTTPServer as compat_http_server
 
+try:
+    compat_str = unicode  # Python 2
+except NameError:
+    compat_str = str
+
 try:
     from urllib.parse import unquote_to_bytes as compat_urllib_parse_unquote_to_bytes
     from urllib.parse import unquote as compat_urllib_parse_unquote
+    from urllib.parse import unquote_plus as compat_urllib_parse_unquote_plus
 except ImportError:  # Python 2
-    # HACK: The following are the correct unquote_to_bytes and unquote
+    _asciire = (compat_urllib_parse._asciire if hasattr(compat_urllib_parse, '_asciire')
+                else re.compile('([\x00-\x7f]+)'))
+
+    # HACK: The following are the correct unquote_to_bytes, unquote and unquote_plus
     # implementations from cpython 3.4.3's stdlib. Python 2's version
     # is apparently broken (see https://github.com/rg3/youtube-dl/pull/6244)
 
@@ -90,7 +105,7 @@ except ImportError:  # Python 2
             # Is it a string-like object?
             string.split
             return b''
-        if isinstance(string, unicode):
+        if isinstance(string, compat_str):
             string = string.encode('utf-8')
         bits = string.split(b'%')
         if len(bits) == 1:
@@ -123,7 +138,7 @@ except ImportError:  # Python 2
             encoding = 'utf-8'
         if errors is None:
             errors = 'replace'
-        bits = compat_urllib_parse._asciire.split(string)
+        bits = _asciire.split(string)
         res = [bits[0]]
         append = res.append
         for i in range(1, len(bits), 2):
@@ -131,10 +146,14 @@ except ImportError:  # Python 2
             append(bits[i + 1])
         return ''.join(res)
 
-try:
-    compat_str = unicode  # Python 2
-except NameError:
-    compat_str = str
+    def compat_urllib_parse_unquote_plus(string, encoding='utf-8', errors='replace'):
+        """Like unquote(), but also replace plus signs by spaces, as required for
+        unquoting HTML form values.
+
+        unquote_plus('%7e/abc+def') -> '~/abc def'
+        """
+        string = string.replace('+', ' ')
+        return compat_urllib_parse_unquote(string, encoding, errors)
 
 try:
     compat_basestring = basestring  # Python 2
@@ -209,6 +228,17 @@ except ImportError:  # Python < 3.3
             return "'" + s.replace("'", "'\"'\"'") + "'"
 
 
+if sys.version_info >= (2, 7, 3):
+    compat_shlex_split = shlex.split
+else:
+    # Working around shlex issue with unicode strings on some python 2
+    # versions (see http://bugs.python.org/issue1548891)
+    def compat_shlex_split(s, comments=False, posix=True):
+        if isinstance(s, compat_str):
+            s = s.encode('utf-8')
+        return shlex.split(s, comments, posix)
+
+
 def compat_ord(c):
     if type(c) is int:
         return c
@@ -418,11 +448,17 @@ except TypeError:  # Python 2.6
             yield n
             n += step
 
+if sys.version_info >= (3, 0):
+    from tokenize import tokenize as compat_tokenize_tokenize
+else:
+    from tokenize import generate_tokens as compat_tokenize_tokenize
+
 __all__ = [
     'compat_HTTPError',
     'compat_basestring',
     'compat_chr',
     'compat_cookiejar',
+    'compat_cookies',
     'compat_expanduser',
     'compat_get_terminal_size',
     'compat_getenv',
@@ -435,12 +471,15 @@ __all__ = [
     'compat_ord',
     'compat_parse_qs',
     'compat_print',
+    'compat_shlex_split',
     'compat_socket_create_connection',
     'compat_str',
     'compat_subprocess_get_DEVNULL',
+    'compat_tokenize_tokenize',
     'compat_urllib_error',
     'compat_urllib_parse',
     'compat_urllib_parse_unquote',
+    'compat_urllib_parse_unquote_plus',
     'compat_urllib_parse_unquote_to_bytes',
     'compat_urllib_parse_urlparse',
     'compat_urllib_request',