R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[jsinterp] Compatibility fix

Browse Source
This commit is contained in:
sulyi 2016-12-07 19:41:06 +01:00
parent c426efd5b5
commit c2f280d5cc
2 changed files with 58 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
youtube_dl/jsinterp/jsgrammar.py
View File

@ -1,12 +1,10 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
from enum import Enum
# ALERT enum34 package dependency
# it's backported
class Token(Enum): class T(object):
COPEN, CCLOSE, POPEN, PCLOSE, SOPEN, SCLOSE = range(0,6) COPEN, CCLOSE, POPEN, PCLOSE, SOPEN, SCLOSE = range(0,6)
DOT, END, COMMA, HOOK, COLON = range(6, 11) DOT, END, COMMA, HOOK, COLON = range(6, 11)
AND, OR, INC, DEC, NOT, BNOT, DEL, VOID, TYPE = range(11, 20) AND, OR, INC, DEC, NOT, BNOT, DEL, VOID, TYPE = range(11, 20)
@ -22,6 +20,10 @@ class Token(Enum):
ASSIGN, MEMBER, FIELD, ELEM, CALL, ARRAY, COND, OPEXPR = range(70, 78) ASSIGN, MEMBER, FIELD, ELEM, CALL, ARRAY, COND, OPEXPR = range(70, 78)
RSV = 78 RSV = 78
def __getitem__(self, item):
return self.__getattribute__(item)
Token = T()
__DECIMAL_RE = r'(?:[1-9][0-9]*)|0' __DECIMAL_RE = r'(?:[1-9][0-9]*)|0'
__OCTAL_RE = r'0[0-7]+' __OCTAL_RE = r'0[0-7]+'
@ -58,28 +60,28 @@ _NULL_RE = r'null'
# r'''/(?!\*) # r'''/(?!\*)
# (?:(?:\\(?:[tnvfr0.\\+*?^$\[\]{}()|/]|[0-7]{3}|x[0-9A-Fa-f]{2}|u[0-9A-Fa-f]{4}|c[A-Z]|))|[^/\n])* # (?:(?:\\(?:[tnvfr0.\\+*?^$\[\]{}()|/]|[0-7]{3}|x[0-9A-Fa-f]{2}|u[0-9A-Fa-f]{4}|c[A-Z]|))|[^/\n])*
# /(?:(?![gimy]*(?P<flag>[gimy])[gimy]*(?P=flag))[gimy]{0,4}\b|\s|$)''' # /(?:(?![gimy]*(?P<flag>[gimy])[gimy]*(?P=flag))[gimy]{0,4}\b|\s|$)'''
_REGEX_FLAGS_RE = r'(?![gimy]*(?P<reflag>[gimy])[gimy]*(?P=reflag))(?P<%s>[gimy]{0,4}\b)' % Token.REFLAGS.name _REGEX_FLAGS_RE = r'(?![gimy]*(?P<reflag>[gimy])[gimy]*(?P=reflag))(?P<%s>[gimy]{0,4}\b)' % 'REFLAGS'
_REGEX_RE = r'/(?!\*)(?P<%s>(?:[^/\n]|(?:\\/))*)/(?:(?:%s)|(?:\s|$))' % (Token.REBODY.name, _REGEX_FLAGS_RE) _REGEX_RE = r'/(?!\*)(?P<%s>(?:[^/\n]|(?:\\/))*)/(?:(?:%s)|(?:\s|$))' % ('REBODY', _REGEX_FLAGS_RE)
_TOKENS = [ _TOKENS = [
(Token.NULL, _NULL_RE), ('NULL', _NULL_RE),
(Token.BOOL, _BOOL_RE), ('BOOL', _BOOL_RE),
(Token.ID, _NAME_RE), ('ID', _NAME_RE),
(Token.STR, _STRING_RE), ('STR', _STRING_RE),
(Token.INT, _INTEGER_RE), ('INT', _INTEGER_RE),
(Token.FLOAT, _FLOAT_RE), ('FLOAT', _FLOAT_RE),
(Token.REGEX, _REGEX_RE) ('REGEX', _REGEX_RE)
] ]
COMMENT_RE = r'(?P<%s>/\*(?:(?!\*/)(?:\n|.))*\*/)' % Token.COMMENT.name COMMENT_RE = r'(?P<%s>/\*(?:(?!\*/)(?:\n|.))*\*/)' % 'COMMENT'
TOKENS_RE = r'|'.join('(?P<%(id)s>%(value)s)' % {'id': name.name, 'value': value} TOKENS_RE = r'|'.join('(?P<%(id)s>%(value)s)' % {'id': name, 'value': value}
for name, value in _TOKENS) for name, value in _TOKENS)
LOGICAL_OPERATORS_RE = r'(?P<%s>%s)' % (Token.LOP.name, r'|'.join(re.escape(value) for value in _logical_operator)) LOGICAL_OPERATORS_RE = r'(?P<%s>%s)' % ('LOP', r'|'.join(re.escape(value) for value in _logical_operator))
UNARY_OPERATORS_RE = r'(?P<%s>%s)' % (Token.UOP.name, r'|'.join(re.escape(value) for value in _unary_operator)) UNARY_OPERATORS_RE = r'(?P<%s>%s)' % ('UOP', r'|'.join(re.escape(value) for value in _unary_operator))
ASSIGN_OPERATORS_RE = r'(?P<%s>%s)' % (Token.AOP.name, ASSIGN_OPERATORS_RE = r'(?P<%s>%s)' % ('AOP',
r'|'.join(re.escape(value) if value != '=' else re.escape(value) + r'(?!\=)' r'|'.join(re.escape(value) if value != '=' else re.escape(value) + r'(?!\=)'
for value in _assign_operator)) for value in _assign_operator))
OPERATORS_RE = r'(?P<%s>%s)' % (Token.OP.name, r'|'.join(re.escape(value) for value in _operator)) OPERATORS_RE = r'(?P<%s>%s)' % ('OP', r'|'.join(re.escape(value) for value in _operator))
RELATIONS_RE = r'(?P<%s>%s)' % (Token.REL.name, r'|'.join(re.escape(value) for value in _relation)) RELATIONS_RE = r'(?P<%s>%s)' % ('REL', r'|'.join(re.escape(value) for value in _relation))
PUNCTUATIONS_RE = r'(?P<%s>%s)' % (Token.PUNCT.name, r'|'.join(re.escape(value) for value in _punctuations)) PUNCTUATIONS_RE = r'(?P<%s>%s)' % ('PUNCT', r'|'.join(re.escape(value) for value in _punctuations))

55
youtube_dl/jsinterp/jsinterp.py
View File

@ -444,7 +444,7 @@ class JSInterpreter(object):
# TODO use context instead local_vars in argument # TODO use context instead local_vars in argument
def getvalue(self, ref, local_vars): def getvalue(self, ref, local_vars):
if ref is None or ref is self.undefined or isinstance(ref, (int, float, str)): # not Token if ref is None or ref is self.undefined or isinstance(ref, (int, float, str)):
return ref return ref
ref_id, ref_value = ref ref_id, ref_value = ref
if ref_id is Token.ID: if ref_id is Token.ID:
@ -452,8 +452,20 @@ class JSInterpreter(object):
elif ref_id in _token_keys: elif ref_id in _token_keys:
return ref_value return ref_value
elif ref_id is Token.EXPR: elif ref_id is Token.EXPR:
ref, abort = self.interpret_statement(ref_value, local_vars) ref, _ = self.interpret_statement(ref_value, local_vars)
return self.getvalue(ref, local_vars) return self.getvalue(ref, local_vars)
elif ref_id is Token.ARRAY:
array = []
for expr in ref_value:
array.append(self.interpret_expression(expr, local_vars))
return array
else:
raise ExtractorError('Unable to get value of reference type %s' % ref_id)
def putvalue(self, ref, value, local_vars):
ref_id, ref_value = ref
if ref_id is Token.ID:
local_vars[ref_value] = value
def interpret_statement(self, stmt, local_vars): def interpret_statement(self, stmt, local_vars):
if stmt is None: if stmt is None:
@ -483,6 +495,10 @@ class JSInterpreter(object):
# TODO use context instead returning abort # TODO use context instead returning abort
ref, abort = self.interpret_statement(stmt[1], local_vars) ref, abort = self.interpret_statement(stmt[1], local_vars)
ref = self.getvalue(ref, local_vars) ref = self.getvalue(ref, local_vars)
if isinstance(ref, list):
# TODO deal with nested arrays
ref = [self.getvalue(elem, local_vars) for elem in ref]
abort = True abort = True
# with # with
# label # label
@ -501,16 +517,19 @@ class JSInterpreter(object):
if op is None: if op is None:
return self.interpret_expression(left, local_vars) return self.interpret_expression(left, local_vars)
else: else:
left = self.interpret_expression(left, local_vars)
# TODO handle undeclared variables (create propery) # TODO handle undeclared variables (create propery)
leftvalue = self.getvalue(left, local_vars) leftref = self.interpret_expression(left, local_vars)
leftvalue = self.getvalue(leftref, local_vars)
rightvalue = self.getvalue(self.interpret_expression(right, local_vars), local_vars) rightvalue = self.getvalue(self.interpret_expression(right, local_vars), local_vars)
local_vars[left[1]] = op(leftvalue, rightvalue) # TODO set array element
return left leftref = op(leftvalue, rightvalue)
return leftref
elif name is Token.EXPR:
ref, _ = self.interpret_statement(expr, local_vars)
return ref
elif name is Token.OPEXPR: elif name is Token.OPEXPR:
stack = [] stack = []
rpn = expr[1] rpn = expr[1][:]
while rpn: while rpn:
token = rpn.pop(0) token = rpn.pop(0)
if token[0] in (Token.OP, Token.AOP, Token.UOP, Token.LOP, Token.REL): if token[0] in (Token.OP, Token.AOP, Token.UOP, Token.LOP, Token.REL):
@ -538,24 +557,20 @@ class JSInterpreter(object):
raise ExtractorError('''Can't interpret expression called %s''' % tail_name) raise ExtractorError('''Can't interpret expression called %s''' % tail_name)
elif tail_name is Token.ELEM: elif tail_name is Token.ELEM:
# TODO interpret element # TODO interpret element
raise ExtractorError('''Can't interpret expression called %s''' % tail_name) # raise ExtractorError('''Can't interpret expression called %s''' % tail_name)
ret, _ = self.interpret_statement(tail_value, local_vars)
index = self.getvalue(ret, local_vars)
target = self.getvalue(target, local_vars)
target = self.interpret_expression((Token.MEMBER, target[index], args, tail), local_vars)
elif tail_name is Token.CALL: elif tail_name is Token.CALL:
# TODO interpret call # TODO interpret call
raise ExtractorError('''Can't interpret expression called %s''' % tail_name) raise ExtractorError('''Can't interpret expression called %s''' % tail_name)
return target return target
elif name is Token.ID: elif name in (Token.ID, Token.ARRAY):
return local_vars[expr[1]] return self.getvalue(expr, local_vars)
# literal # literal
elif name in _token_keys: elif name in _token_keys:
return expr[1] return expr
elif name is Token.ARRAY:
array = []
elms = expr[1]
for expr in elms:
array.append(self.interpret_expression(expr, local_vars))
return array
else: else:
raise ExtractorError('''Can't interpret expression called %s''' % name) raise ExtractorError('''Can't interpret expression called %s''' % name)