X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/eed74133841b43ce901ee0dd31c7dad5a234bd48..d317bf370d3cbd2231f3d6b1970e0a86fddc4e5b:/youtube_dl/compat.py?ds=sidebyside diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index 9d33a8e..0c57c7a 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -1,55 +1,55 @@ 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: @@ -70,53 +70,110 @@ except ImportError: compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w') try: - from urllib.parse import unquote as compat_urllib_parse_unquote + import http.server as compat_http_server except ImportError: - def compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'): - if string == '': + import BaseHTTPServer as compat_http_server + +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 + _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) + + 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, unicode): + string = string.encode('utf-8') + bits = string.split(b'%') + if len(bits) == 1: return string - res = string.split('%') - if len(res) == 1: + res = [bits[0]] + append = res.append + for item in bits[1:]: + try: + append(compat_urllib_parse._hextochr[item[:2]]) + append(item[2:]) + except KeyError: + append(b'%') + append(item) + return b''.join(res) + + def 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' - # 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 + bits = _asciire.split(string) + res = [bits[0]] + append = res.append + for i in range(1, len(bits), 2): + append(compat_urllib_parse_unquote_to_bytes(bits[i]).decode(encoding, errors)) + append(bits[i + 1]) + return ''.join(res) + + 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_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: @@ -144,10 +201,10 @@ except ImportError: # Python 2 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) @@ -155,31 +212,21 @@ except ImportError: # Python 2 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): @@ -241,7 +288,7 @@ else: 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: @@ -250,7 +297,7 @@ else: 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:] @@ -264,7 +311,7 @@ if sys.version_info < (3, 0): print(s.encode(preferredencoding(), 'xmlcharrefreplace')) else: def compat_print(s): - assert type(s) == type(u'') + assert isinstance(s, compat_str) print(s) @@ -291,7 +338,9 @@ else: # 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()) @@ -299,6 +348,32 @@ else: 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(): @@ -319,26 +394,68 @@ def workaround_optparse_bug9161(): 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', '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', 'compat_urlparse',