from __future__ import unicode_literals
+import collections
import getpass
import optparse
import os
+import re
+import shutil
+import socket
import subprocess
import sys
+import itertools
try:
import urllib.request as compat_urllib_request
-except ImportError: # Python 2
+except ImportError: # Python 2
import urllib2 as compat_urllib_request
try:
import urllib.error as compat_urllib_error
-except ImportError: # Python 2
+except ImportError: # Python 2
import urllib2 as compat_urllib_error
try:
import urllib.parse as compat_urllib_parse
-except ImportError: # Python 2
+except ImportError: # Python 2
import urllib as compat_urllib_parse
try:
from urllib.parse import urlparse as compat_urllib_parse_urlparse
-except ImportError: # Python 2
+except ImportError: # Python 2
from urlparse import urlparse as compat_urllib_parse_urlparse
try:
import urllib.parse as compat_urlparse
-except ImportError: # Python 2
+except ImportError: # Python 2
import urlparse as compat_urlparse
try:
import http.cookiejar as compat_cookiejar
-except ImportError: # Python 2
+except ImportError: # Python 2
import cookielib as compat_cookiejar
try:
import html.entities as compat_html_entities
-except ImportError: # Python 2
+except ImportError: # Python 2
import htmlentitydefs as compat_html_entities
-try:
- import html.parser as compat_html_parser
-except ImportError: # Python 2
- import HTMLParser as compat_html_parser
-
try:
import http.client as compat_http_client
-except ImportError: # Python 2
+except ImportError: # Python 2
import httplib as compat_http_client
try:
except ImportError:
compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')
+try:
+ import http.server as compat_http_server
+except ImportError:
+ import BaseHTTPServer as compat_http_server
+
try:
from urllib.parse import unquote as compat_urllib_parse_unquote
except ImportError:
- def compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'):
+ def compat_urllib_parse_unquote_to_bytes(string):
+ """unquote_to_bytes('abc%20def') -> b'abc def'."""
+ # Note: strings are encoded as UTF-8. This is only an issue if it contains
+ # unescaped non-ASCII characters, which URIs should not.
+ if not string:
+ # Is it a string-like object?
+ string.split
+ return b''
+ if isinstance(string, str):
+ string = string.encode('utf-8')
+ # string = encode('utf-8')
+
+ # python3 -> 2: must implicitly convert to bits
+ bits = bytes(string).split(b'%')
+
+ if len(bits) == 1:
+ return string
+ res = [bits[0]]
+ append = res.append
+
+ for item in bits[1:]:
+ try:
+ append(item[:2].decode('hex'))
+ append(item[2:])
+ except:
+ append(b'%')
+ append(item)
+ return b''.join(res)
+
+ compat_urllib_parse_asciire = re.compile('([\x00-\x7f]+)')
+
+ def new_compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'):
+ """Replace %xx escapes by their single-character equivalent. The optional
+ encoding and errors parameters specify how to decode percent-encoded
+ sequences into Unicode characters, as accepted by the bytes.decode()
+ method.
+ By default, percent-encoded sequences are decoded with UTF-8, and invalid
+ sequences are replaced by a placeholder character.
+
+ unquote('abc%20def') -> 'abc def'.
+ """
+
+ if '%' not in string:
+ string.split
+ return string
+ if encoding is None:
+ encoding = 'utf-8'
+ if errors is None:
+ errors = 'replace'
+
+ bits = compat_urllib_parse_asciire.split(string)
+ res = [bits[0]]
+ append = res.append
+ for i in range(1, len(bits), 2):
+ foo = compat_urllib_parse_unquote_to_bytes(bits[i])
+ foo = foo.decode(encoding, errors)
+ append(foo)
+
+ if bits[i + 1]:
+ bar = bits[i + 1]
+ if not isinstance(bar, unicode):
+ bar = bar.decode('utf-8')
+ append(bar)
+ return ''.join(res)
+
+ def old_compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'):
if string == '':
return string
res = string.split('%')
try:
if not item:
raise ValueError
+ if not re.match('[0-9a-fA-F][0-9a-fA-F]',item[:2]):
+ raise ValueError
pct_sequence += item[:2].decode('hex')
rest = item[2:]
if not rest:
string += pct_sequence.decode(encoding, errors)
return string
+ compat_urllib_parse_unquote = new_compat_urllib_parse_unquote
+
+try:
+ compat_str = unicode # Python 2
+except NameError:
+ compat_str = str
+
+try:
+ compat_basestring = basestring # Python 2
+except NameError:
+ compat_basestring = str
+
+try:
+ compat_chr = unichr # Python 2
+except NameError:
+ compat_chr = chr
+
+try:
+ from xml.etree.ElementTree import ParseError as compat_xml_parse_error
+except ImportError: # Python 2.6
+ from xml.parsers.expat import ExpatError as compat_xml_parse_error
+
try:
from urllib.parse import parse_qs as compat_parse_qs
-except ImportError: # Python 2
+except ImportError: # Python 2
# HACK: The following is the correct parse_qs implementation from cpython 3's stdlib.
# Python 2's version is apparently totally broken
def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
- encoding='utf-8', errors='replace'):
- qs, _coerce_result = qs, unicode
+ encoding='utf-8', errors='replace'):
+ qs, _coerce_result = qs, compat_str
pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
r = []
for name_value in pairs:
return r
def compat_parse_qs(qs, keep_blank_values=False, strict_parsing=False,
- encoding='utf-8', errors='replace'):
+ encoding='utf-8', errors='replace'):
parsed_result = {}
pairs = _parse_qsl(qs, keep_blank_values, strict_parsing,
- encoding=encoding, errors=errors)
+ encoding=encoding, errors=errors)
for name, value in pairs:
if name in parsed_result:
parsed_result[name].append(value)
parsed_result[name] = [value]
return parsed_result
-try:
- compat_str = unicode # Python 2
-except NameError:
- compat_str = str
-
-try:
- compat_chr = unichr # Python 2
-except NameError:
- compat_chr = chr
-
-try:
- from xml.etree.ElementTree import ParseError as compat_xml_parse_error
-except ImportError: # Python 2.6
- from xml.parsers.expat import ExpatError as compat_xml_parse_error
-
try:
from shlex import quote as shlex_quote
except ImportError: # Python < 3.3
def shlex_quote(s):
- return "'" + s.replace("'", "'\"'\"'") + "'"
+ if re.match(r'^[-_\w./]+$', s):
+ return s
+ else:
+ return "'" + s.replace("'", "'\"'\"'") + "'"
def compat_ord(c):
- if type(c) is int: return c
- else: return ord(c)
+ if type(c) is int:
+ return c
+ else:
+ return ord(c)
if sys.version_info >= (3, 0):
userhome = compat_getenv('HOME')
elif 'USERPROFILE' in os.environ:
userhome = compat_getenv('USERPROFILE')
- elif not 'HOMEPATH' in os.environ:
+ elif 'HOMEPATH' not in os.environ:
return path
else:
try:
drive = ''
userhome = os.path.join(drive, compat_getenv('HOMEPATH'))
- if i != 1: #~user
+ if i != 1: # ~user
userhome = os.path.join(os.path.dirname(userhome), path[1:i])
return userhome + path[i:]
print(s.encode(preferredencoding(), 'xmlcharrefreplace'))
else:
def compat_print(s):
- assert type(s) == type(u'')
+ assert isinstance(s, compat_str)
print(s)
# Old 2.6 and 2.7 releases require kwargs to be bytes
try:
- (lambda x: x)(**{'x': 0})
+ def _testfunc(x):
+ pass
+ _testfunc(**{'x': 0})
except TypeError:
def compat_kwargs(kwargs):
return dict((bytes(k), v) for k, v in kwargs.items())
compat_kwargs = lambda kwargs: kwargs
+if sys.version_info < (2, 7):
+ def compat_socket_create_connection(address, timeout, source_address=None):
+ host, port = address
+ err = None
+ for res in socket.getaddrinfo(host, port, 0, socket.SOCK_STREAM):
+ af, socktype, proto, canonname, sa = res
+ sock = None
+ try:
+ sock = socket.socket(af, socktype, proto)
+ sock.settimeout(timeout)
+ if source_address:
+ sock.bind(source_address)
+ sock.connect(sa)
+ return sock
+ except socket.error as _:
+ err = _
+ if sock is not None:
+ sock.close()
+ if err is not None:
+ raise err
+ else:
+ raise socket.error("getaddrinfo returns an empty list")
+else:
+ compat_socket_create_connection = socket.create_connection
+
+
# Fix https://github.com/rg3/youtube-dl/issues/4223
# See http://bugs.python.org/issue9161 for what is broken
def workaround_optparse_bug9161():
og = optparse.OptionGroup(op, 'foo')
try:
og.add_option('-t')
- except TypeError as te:
+ except TypeError:
real_add_option = optparse.OptionGroup.add_option
def _compat_add_option(self, *args, **kwargs):
return real_add_option(self, *bargs, **bkwargs)
optparse.OptionGroup.add_option = _compat_add_option
+if hasattr(shutil, 'get_terminal_size'): # Python >= 3.3
+ compat_get_terminal_size = shutil.get_terminal_size
+else:
+ _terminal_size = collections.namedtuple('terminal_size', ['columns', 'lines'])
+
+ def compat_get_terminal_size():
+ columns = compat_getenv('COLUMNS', None)
+ if columns:
+ columns = int(columns)
+ else:
+ columns = None
+ lines = compat_getenv('LINES', None)
+ if lines:
+ lines = int(lines)
+ else:
+ lines = None
+
+ try:
+ sp = subprocess.Popen(
+ ['stty', 'size'],
+ stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+ out, err = sp.communicate()
+ lines, columns = map(int, out.split())
+ except Exception:
+ pass
+ return _terminal_size(columns, lines)
+
+try:
+ itertools.count(start=0, step=1)
+ compat_itertools_count = itertools.count
+except TypeError: # Python 2.6
+ def compat_itertools_count(start=0, step=1):
+ n = start
+ while True:
+ yield n
+ n += step
__all__ = [
'compat_HTTPError',
+ 'compat_basestring',
'compat_chr',
'compat_cookiejar',
'compat_expanduser',
+ 'compat_get_terminal_size',
'compat_getenv',
'compat_getpass',
'compat_html_entities',
- 'compat_html_parser',
'compat_http_client',
+ 'compat_http_server',
+ 'compat_itertools_count',
'compat_kwargs',
'compat_ord',
'compat_parse_qs',
'compat_print',
+ 'compat_socket_create_connection',
'compat_str',
'compat_subprocess_get_DEVNULL',
'compat_urllib_error',
projects / youtube-dl.git / blobdiff