[yt-dlp.git] / youtube_dl / compat.py

from __future__ import unicode_literals

import getpass
import os
import subprocess
import sys


try:
    import urllib.request as compat_urllib_request
except ImportError: # Python 2
    import urllib2 as compat_urllib_request

try:
    import urllib.error as compat_urllib_error
except ImportError: # Python 2
    import urllib2 as compat_urllib_error

try:
    import urllib.parse as compat_urllib_parse
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
    from urlparse import urlparse as compat_urllib_parse_urlparse

try:
    import urllib.parse as compat_urlparse
except ImportError: # Python 2
    import urlparse as compat_urlparse

try:
    import http.cookiejar as compat_cookiejar
except ImportError: # Python 2
    import cookielib as compat_cookiejar

try:
    import html.entities as compat_html_entities
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
    import httplib as compat_http_client

try:
    from urllib.error import HTTPError as compat_HTTPError
except ImportError:  # Python 2
    from urllib2 import HTTPError as compat_HTTPError

try:
    from urllib.request import urlretrieve as compat_urlretrieve
except ImportError:  # Python 2
    from urllib import urlretrieve as compat_urlretrieve


try:
    from subprocess import DEVNULL
    compat_subprocess_get_DEVNULL = lambda: DEVNULL
except ImportError:
    compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')

try:
    from urllib.parse import unquote as compat_urllib_parse_unquote
except ImportError:
    def compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'):
        if string == '':
            return string
        res = string.split('%')
        if len(res) == 1:
            return string
        if encoding is None:
            encoding = 'utf-8'
        if errors is None:
            errors = 'replace'
        # pct_sequence: contiguous sequence of percent-encoded bytes, decoded
        pct_sequence = b''
        string = res[0]
        for item in res[1:]:
            try:
                if not item:
                    raise ValueError
                pct_sequence += item[:2].decode('hex')
                rest = item[2:]
                if not rest:
                    # This segment was just a single percent-encoded character.
                    # May be part of a sequence of code units, so delay decoding.
                    # (Stored in pct_sequence).
                    continue
            except ValueError:
                rest = '%' + item
            # Encountered non-percent-encoded characters. Flush the current
            # pct_sequence.
            string += pct_sequence.decode(encoding, errors) + rest
            pct_sequence = b''
        if pct_sequence:
            # Flush the final pct_sequence
            string += pct_sequence.decode(encoding, errors)
        return string


try:
    from urllib.parse import parse_qs as compat_parse_qs
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
        pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
        r = []
        for name_value in pairs:
            if not name_value and not strict_parsing:
                continue
            nv = name_value.split('=', 1)
            if len(nv) != 2:
                if strict_parsing:
                    raise ValueError("bad query field: %r" % (name_value,))
                # Handle case of a control-name with no equal sign
                if keep_blank_values:
                    nv.append('')
                else:
                    continue
            if len(nv[1]) or keep_blank_values:
                name = nv[0].replace('+', ' ')
                name = compat_urllib_parse_unquote(
                    name, encoding=encoding, errors=errors)
                name = _coerce_result(name)
                value = nv[1].replace('+', ' ')
                value = compat_urllib_parse_unquote(
                    value, encoding=encoding, errors=errors)
                value = _coerce_result(value)
                r.append((name, value))
        return r

    def compat_parse_qs(qs, keep_blank_values=False, strict_parsing=False,
                encoding='utf-8', errors='replace'):
        parsed_result = {}
        pairs = _parse_qsl(qs, keep_blank_values, strict_parsing,
                        encoding=encoding, errors=errors)
        for name, value in pairs:
            if name in parsed_result:
                parsed_result[name].append(value)
            else:
                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("'", "'\"'\"'") + "'"


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):
        from .utils import get_filesystem_encoding
        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


if sys.version_info < (3, 0):
    def compat_print(s):
        from .utils import preferredencoding
        print(s.encode(preferredencoding(), 'xmlcharrefreplace'))
else:
    def compat_print(s):
        assert type(s) == type(u'')
        print(s)


try:
    subprocess_check_output = subprocess.check_output
except AttributeError:
    def subprocess_check_output(*args, **kwargs):
        assert 'input' not in kwargs
        p = subprocess.Popen(*args, stdout=subprocess.PIPE, **kwargs)
        output, _ = p.communicate()
        ret = p.poll()
        if ret:
            raise subprocess.CalledProcessError(ret, p.args, output=output)
        return output

if sys.version_info < (3, 0) and sys.platform == 'win32':
    def compat_getpass(prompt, *args, **kwargs):
        if isinstance(prompt, compat_str):
            from .utils import preferredencoding
            prompt = prompt.encode(preferredencoding())
        return getpass.getpass(prompt, *args, **kwargs)
else:
    compat_getpass = getpass.getpass

# Old 2.6 and 2.7 releases require kwargs to be bytes
try:
    (lambda x: x)(**{'x': 0})
except TypeError:
    def compat_kwargs(kwargs):
        return dict((bytes(k), v) for k, v in kwargs.items())
else:
    compat_kwargs = lambda kwargs: kwargs

__all__ = [
    'compat_HTTPError',
    'compat_chr',
    'compat_cookiejar',
    'compat_expanduser',
    'compat_getenv',
    'compat_getpass',
    'compat_html_entities',
    'compat_html_parser',
    'compat_http_client',
    'compat_kwargs',
    'compat_ord',
    'compat_parse_qs',
    'compat_print',
    'compat_str',
    'compat_subprocess_get_DEVNULL',
    'compat_urllib_error',
    'compat_urllib_parse',
    'compat_urllib_parse_unquote',
    'compat_urllib_parse_urlparse',
    'compat_urllib_request',
    'compat_urlparse',
    'compat_urlretrieve',
    'compat_xml_parse_error',
    'shlex_quote',
    'subprocess_check_output',
]
Commit	Line	Data
451948b2 PH	1	from __future__ import unicode_literals
451948b2 PH	2
8c25f81b PH	3	import getpass
	4	import os
	5	import subprocess
	6	import sys
	7
	8
	9	try:
	10	import urllib.request as compat_urllib_request
	11	except ImportError: # Python 2
	12	import urllib2 as compat_urllib_request
	13
	14	try:
	15	import urllib.error as compat_urllib_error
	16	except ImportError: # Python 2
	17	import urllib2 as compat_urllib_error
	18
	19	try:
	20	import urllib.parse as compat_urllib_parse
	21	except ImportError: # Python 2
	22	import urllib as compat_urllib_parse
	23
	24	try:
	25	from urllib.parse import urlparse as compat_urllib_parse_urlparse
	26	except ImportError: # Python 2
	27	from urlparse import urlparse as compat_urllib_parse_urlparse
	28
	29	try:
	30	import urllib.parse as compat_urlparse
	31	except ImportError: # Python 2
	32	import urlparse as compat_urlparse
	33
	34	try:
	35	import http.cookiejar as compat_cookiejar
	36	except ImportError: # Python 2
	37	import cookielib as compat_cookiejar
	38
	39	try:
	40	import html.entities as compat_html_entities
	41	except ImportError: # Python 2
	42	import htmlentitydefs as compat_html_entities
	43
	44	try:
	45	import html.parser as compat_html_parser
	46	except ImportError: # Python 2
	47	import HTMLParser as compat_html_parser
	48
	49	try:
	50	import http.client as compat_http_client
	51	except ImportError: # Python 2
	52	import httplib as compat_http_client
	53
	54	try:
	55	from urllib.error import HTTPError as compat_HTTPError
	56	except ImportError: # Python 2
	57	from urllib2 import HTTPError as compat_HTTPError
	58
	59	try:
	60	from urllib.request import urlretrieve as compat_urlretrieve
	61	except ImportError: # Python 2
	62	from urllib import urlretrieve as compat_urlretrieve
	63
	64
	65	try:
	66	from subprocess import DEVNULL
67	compat_subprocess_get_DEVNULL = lambda: DEVNULL
68	except ImportError:
69	compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')
70
71	try:
72	from urllib.parse import unquote as compat_urllib_parse_unquote
73	except ImportError:
74	def compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'):
75	if string == '':
76	return string
77	res = string.split('%')
78	if len(res) == 1:
79	return string
80	if encoding is None:
81	encoding = 'utf-8'
82	if errors is None:
83	errors = 'replace'
84	# pct_sequence: contiguous sequence of percent-encoded bytes, decoded
85	pct_sequence = b''
86	string = res[0]
87	for item in res[1:]:
88	try:
89	if not item:
90	raise ValueError
91	pct_sequence += item[:2].decode('hex')
92	rest = item[2:]
93	if not rest:
94	# This segment was just a single percent-encoded character.
95	# May be part of a sequence of code units, so delay decoding.
96	# (Stored in pct_sequence).
97	continue
98	except ValueError:
99	rest = '%' + item
100	# Encountered non-percent-encoded characters. Flush the current
101	# pct_sequence.
102	string += pct_sequence.decode(encoding, errors) + rest
103	pct_sequence = b''
104	if pct_sequence:
105	# Flush the final pct_sequence
106	string += pct_sequence.decode(encoding, errors)
107	return string
108
109
110	try:
111	from urllib.parse import parse_qs as compat_parse_qs
112	except ImportError: # Python 2
113	# HACK: The following is the correct parse_qs implementation from cpython 3's stdlib.
114	# Python 2's version is apparently totally broken
115
116	def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
117	encoding='utf-8', errors='replace'):
118	qs, _coerce_result = qs, unicode
119	pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
120	r = []
121	for name_value in pairs:
122	if not name_value and not strict_parsing:
123	continue
124	nv = name_value.split('=', 1)
125	if len(nv) != 2:
126	if strict_parsing:
127	raise ValueError("bad query field: %r" % (name_value,))
128	# Handle case of a control-name with no equal sign
129	if keep_blank_values:
130	nv.append('')
131	else:
132	continue
133	if len(nv[1]) or keep_blank_values:
134	name = nv[0].replace('+', ' ')
135	name = compat_urllib_parse_unquote(
136	name, encoding=encoding, errors=errors)
137	name = _coerce_result(name)
138	value = nv[1].replace('+', ' ')
139	value = compat_urllib_parse_unquote(
140	value, encoding=encoding, errors=errors)
141	value = _coerce_result(value)
142	r.append((name, value))
143	return r
144
145	def compat_parse_qs(qs, keep_blank_values=False, strict_parsing=False,
146	encoding='utf-8', errors='replace'):
147	parsed_result = {}
148	pairs = _parse_qsl(qs, keep_blank_values, strict_parsing,
149	encoding=encoding, errors=errors)
150	for name, value in pairs:
151	if name in parsed_result:
152	parsed_result[name].append(value)
153	else:
154	parsed_result[name] = [value]
155	return parsed_result
156
157	try:
158	compat_str = unicode # Python 2
159	except NameError:
160	compat_str = str
161
162	try:
163	compat_chr = unichr # Python 2
164	except NameError:
165	compat_chr = chr
166
167	try:
168	from xml.etree.ElementTree import ParseError as compat_xml_parse_error
169	except ImportError: # Python 2.6
170	from xml.parsers.expat import ExpatError as compat_xml_parse_error
171
172	try:
173	from shlex import quote as shlex_quote
174	except ImportError: # Python < 3.3
175	def shlex_quote(s):
176	return "'" + s.replace("'", "'\"'\"'") + "'"
177
178
179	def compat_ord(c):
180	if type(c) is int: return c
181	else: return ord(c)
182
183
184	if sys.version_info >= (3, 0):
185	compat_getenv = os.getenv
186	compat_expanduser = os.path.expanduser
187	else:
188	# Environment variables should be decoded with filesystem encoding.
189	# Otherwise it will fail if any non-ASCII characters present (see #3854 #3217 #2918)
190
191	def compat_getenv(key, default=None):
192	from .utils import get_filesystem_encoding
193	env = os.getenv(key, default)
194	if env:
195	env = env.decode(get_filesystem_encoding())
196	return env
197
198	# HACK: The default implementations of os.path.expanduser from cpython do not decode
199	# environment variables with filesystem encoding. We will work around this by
200	# providing adjusted implementations.
201	# The following are os.path.expanduser implementations from cpython 2.7.8 stdlib
202	# for different platforms with correct environment variables decoding.
203
204	if os.name == 'posix':
205	def compat_expanduser(path):
206	"""Expand ~ and ~user constructions. If user or $HOME is unknown,
207	do nothing."""
208	if not path.startswith('~'):
209	return path
210	i = path.find('/', 1)
211	if i < 0:
212	i = len(path)
213	if i == 1:
214	if 'HOME' not in os.environ:
215	import pwd
216	userhome = pwd.getpwuid(os.getuid()).pw_dir
217	else:
218	userhome = compat_getenv('HOME')
219	else:
220	import pwd
221	try:
222	pwent = pwd.getpwnam(path[1:i])
223	except KeyError:
224	return path
225	userhome = pwent.pw_dir
226	userhome = userhome.rstrip('/')
227	return (userhome + path[i:]) or '/'
228	elif os.name == 'nt' or os.name == 'ce':
229	def compat_expanduser(path):
230	"""Expand ~ and ~user constructs.
231
232	If user or $HOME is unknown, do nothing."""
233	if path[:1] != '~':
234	return path
235	i, n = 1, len(path)
236	while i < n and path[i] not in '/\\':
237	i = i + 1
238
239	if 'HOME' in os.environ:
240	userhome = compat_getenv('HOME')
241	elif 'USERPROFILE' in os.environ:
242	userhome = compat_getenv('USERPROFILE')
243	elif not 'HOMEPATH' in os.environ:
244	return path
245	else:
246	try:
247	drive = compat_getenv('HOMEDRIVE')
248	except KeyError:
249	drive = ''
250	userhome = os.path.join(drive, compat_getenv('HOMEPATH'))
251
252	if i != 1: #~user
253	userhome = os.path.join(os.path.dirname(userhome), path[1:i])
254
255	return userhome + path[i:]
256	else:
257	compat_expanduser = os.path.expanduser
258
259
260	if sys.version_info < (3, 0):
261	def compat_print(s):
262	from .utils import preferredencoding
263	print(s.encode(preferredencoding(), 'xmlcharrefreplace'))
264	else:
265	def compat_print(s):
266	assert type(s) == type(u'')
267	print(s)
268
269
270	try:
271	subprocess_check_output = subprocess.check_output
272	except AttributeError:
273	def subprocess_check_output(args, *kwargs):
274	assert 'input' not in kwargs
275	p = subprocess.Popen(args, stdout=subprocess.PIPE, *kwargs)
276	output, _ = p.communicate()
277	ret = p.poll()
278	if ret:
279	raise subprocess.CalledProcessError(ret, p.args, output=output)
280	return output
281
282	if sys.version_info < (3, 0) and sys.platform == 'win32':
283	def compat_getpass(prompt, args, *kwargs):
284	if isinstance(prompt, compat_str):
baa70803	285	from .utils import preferredencoding
8c25f81b PH	286	prompt = prompt.encode(preferredencoding())
	287	return getpass.getpass(prompt, args, *kwargs)
	288	else:
	289	compat_getpass = getpass.getpass
	290
c7b0add8 PH	291	# Old 2.6 and 2.7 releases require kwargs to be bytes
	292	try:
	293	(lambda x: x)(**{'x': 0})
	294	except TypeError:
	295	def compat_kwargs(kwargs):
	296	return dict((bytes(k), v) for k, v in kwargs.items())
	297	else:
	298	compat_kwargs = lambda kwargs: kwargs
8c25f81b PH	299
	300	__all__ = [
	301	'compat_HTTPError',
	302	'compat_chr',
	303	'compat_cookiejar',
	304	'compat_expanduser',
	305	'compat_getenv',
	306	'compat_getpass',
	307	'compat_html_entities',
	308	'compat_html_parser',
	309	'compat_http_client',
c7b0add8	310	'compat_kwargs',
8c25f81b PH	311	'compat_ord',
	312	'compat_parse_qs',
	313	'compat_print',
	314	'compat_str',
	315	'compat_subprocess_get_DEVNULL',
	316	'compat_urllib_error',
	317	'compat_urllib_parse',
	318	'compat_urllib_parse_unquote',
	319	'compat_urllib_parse_urlparse',
	320	'compat_urllib_request',
	321	'compat_urlparse',
	322	'compat_urlretrieve',
	323	'compat_xml_parse_error',
	324	'shlex_quote',
	325	'subprocess_check_output',
	326	]