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

[test] Adding support for signed values (hopefully)

Browse Source
This commit is contained in:
sulyi 2016-12-15 10:56:45 +01:00
parent ab37e2b811
commit c4c2aa274b
4 changed files with 19 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
test/jstests/unshift.py
View File

@ -1,6 +1,4 @@
skip = {'p': 'Signed integers not yet supported'}
tests = [
{
'code': '''

16
youtube_dl/jsinterp/jsgrammar.py
View File

@ -6,7 +6,7 @@ from collections import namedtuple
_token_keys = ('COPEN', 'CCLOSE', 'POPEN', 'PCLOSE', 'SOPEN', 'SCLOSE',
'DOT', 'END', 'COMMA', 'HOOK', 'COLON',
'AND', 'OR', 'INC', 'DEC', 'NOT', 'BNOT', 'DEL', 'VOID', 'TYPE',
'AND', 'OR', 'PLUS', 'NEG', 'INC', 'DEC', 'NOT', 'BNOT', 'DEL', 'VOID', 'TYPE',
'LT', 'GT', 'LE', 'GE', 'EQ', 'NE', 'SEQ', 'SNE', 'IN', 'INSTANCEOF',
'BOR', 'BXOR', 'BAND', 'RSHIFT', 'LSHIFT', 'URSHIFT', 'SUB', 'ADD', 'MOD', 'DIV', 'MUL',
'OP', 'AOP', 'UOP', 'LOP', 'REL',
@ -48,7 +48,6 @@ _SINGLE_QUOTED_RE = r"""'(?:(?:\\'|\n)|[^'\n])*'"""
_DOUBLE_QUOTED_RE = r'''"(?:(?:\\"|\n)|[^"\n])*"'''
_STRING_RE = r'(?:%s)|(?:%s)' % (_SINGLE_QUOTED_RE, _DOUBLE_QUOTED_RE)
# FIXME signed values
_INTEGER_RE = r'(?:%(hex)s)|(?:%(dec)s)|(?:%(oct)s)' % {'hex': __HEXADECIMAL_RE, 'dec': __DECIMAL_RE, 'oct': __OCTAL_RE}
_FLOAT_RE = r'(?:(?:%(dec)s\.[0-9]*)|(?:\.[0-9]+))(?:[eE][+-]?[0-9]+)?' % {'dec': __DECIMAL_RE}
@ -62,15 +61,10 @@ _NULL_RE = r'null'
_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|$))' % ('REBODY', _REGEX_FLAGS_RE)
_TOKENS = [
(Token.NULL, _NULL_RE),
(Token.BOOL, _BOOL_RE),
(Token.ID, _NAME_RE),
(Token.STR, _STRING_RE),
(Token.INT, _INTEGER_RE),
(Token.FLOAT, _FLOAT_RE),
(Token.REGEX, _REGEX_RE)
]
token_keys = Token.NULL, Token.BOOL, Token.ID, Token.STR, Token.INT, Token.FLOAT, Token.REGEX
_TOKENS = zip(token_keys, (_NULL_RE, _BOOL_RE, _NAME_RE, _STRING_RE, _INTEGER_RE, _FLOAT_RE, _REGEX_RE))
COMMENT_RE = r'(?P<%s>/\*(?:(?!\*/)(?:\n|.))*\*/)' % Token.COMMENT
TOKENS_RE = r'|'.join('(?P<%(id)s>%(value)s)' % {'id': name, 'value': value}

8
youtube_dl/jsinterp/jsinterp.py
View File

@ -4,9 +4,7 @@ import re
from ..utils import ExtractorError
from .tstream import TokenStream
from .jsgrammar import Token
_token_keys = set((Token.NULL, Token.BOOL, Token.ID, Token.STR, Token.INT, Token.FLOAT, Token.REGEX))
from .jsgrammar import Token, token_keys
class Context(object):
@ -497,7 +495,7 @@ class JSInterpreter(object):
# TODO support let
peek_id, peek_value, peek_pos = token_stream.peek()
if peek_id in _token_keys:
if peek_id in token_keys:
if peek_id is Token.ID:
# this
if peek_value == 'this':
@ -924,7 +922,7 @@ class JSInterpreter(object):
self.global_vars[expr[1]])
# literal
elif name in _token_keys:
elif name in token_keys:
ref = Reference(expr[1])
elif name is Token.ARRAY:

17
youtube_dl/jsinterp/tstream.py
View File

@ -13,7 +13,8 @@ from .jsgrammar import (
RELATIONS_RE,
ASSIGN_OPERATORS_RE,
OPERATORS_RE,
Token
Token,
token_keys
)
_PUNCTUATIONS = {
@ -34,10 +35,12 @@ _LOGICAL_OPERATORS = {
'||': (Token.OR, lambda cur, right: cur or right)
}
_UNARY_OPERATORS = {
'+': (Token.PLUS, lambda cur: cur),
'-': (Token.NEG, lambda cur: cur * -1),
'++': (Token.INC, lambda cur: cur + 1),
'--': (Token.DEC, lambda cur: cur - 1),
'!': (Token.NOT, operator.not_),
'~': (Token.BNOT, lambda cur: cur ^ -1),
'~': (Token.BNOT, operator.invert),
# XXX define these operators
'delete': (Token.DEL, None),
'void': (Token.VOID, None),
@ -53,9 +56,8 @@ _RELATIONS = {
'!=': (Token.NE, operator.ne),
'===': (Token.SEQ, lambda cur, right: cur == right and type(cur) == type(right)),
'!==': (Token.SNE, lambda cur, right: not cur == right or not type(cur) == type(right)),
# XXX define instanceof and in operators
'in': (Token.IN, None),
'instanceof': (Token.INSTANCEOF, None)
'in': (Token.IN, operator.contains),
'instanceof': (Token.INSTANCEOF, lambda cur, right: isinstance(cur, right))
}
_OPERATORS = {
'|': (Token.BOR, operator.or_),
@ -124,7 +126,6 @@ class TokenStream(object):
elif token_id is Token.STR:
yield (token_id, token_value[1:-1], pos)
elif token_id is Token.INT:
# FIXME signed values
root = ((16 if len(token_value) > 2 and token_value[1] in 'xX' else 8)
if token_value.startswith('0') else 10)
yield (token_id, int(token_value, root), pos)
@ -137,6 +138,10 @@ class TokenStream(object):
elif token_id is Token.ID:
yield (token_id, token_value, pos)
elif token_id in _operator_lookup:
# FIXME signed values
if (token_id is Token.OP and token_value in ('-', '+') and
self._last[0] not in token_keys and self._last[0] is not Token.PCLOSE):
token_id = Token.UOP
yield (token_id if token_value != 'in' else Token.IN,
_operator_lookup[token_id][token_value],
pos)