def chr(self, t):
assert t[0] == "<" or t[0] == 'U'
if t[0] == "<":
assert t[-1] == ">"
if t not in ECMASCRIPT_CODE_POINTS:
raise ValueError("unrecognized character abbreviation {!r}".format(t))
return ECMASCRIPT_CODE_POINTS[t]
else:
assert t[1] == "+"
return grammar.Literal(chr(int(t[2:], base=16)))
def expand_lexical_rhs(self, rhs):
body, reducer, condition = rhs
out = []
for e in body:
if isinstance(e, str):
# The terminal symbols of the lexical grammar are characters, so
# add each character of this string as a separate element.
out += [grammar.Literal(ch) for ch in e]
else:
out.append(e)
return [out, reducer, condition]
# the spec also gives a few productions names
RUSTCOMMENT=r'//.*\n',
)
ESGrammarParser = gen.compile(
parse_pgen.load_grammar(
os.path.join(os.path.dirname(__file__), "esgrammar.pgen")))
SIGIL_FALSE = '~'
SIGIL_TRUE = '+'
# Abbreviations for single-character terminals, used in the lexical grammar.
ECMASCRIPT_CODE_POINTS = {
# From <https://tc39.es/ecma262/#table-31>
'<ZWNJ>': grammar.Literal('\u200c'),
'<ZWJ>': grammar.Literal('\u200d'),
'<ZWNBSP>': grammar.Literal('\ufeff'),
# From <https://tc39.es/ecma262/#table-32>
'<TAB>': grammar.Literal('\t'),
'<VT>': grammar.Literal('\u000b'),
'<FF>': grammar.Literal('\u000c'),
'<SP>': grammar.Literal(' '),
'<NBSP>': grammar.Literal('\u00a0'),
# <ZWNBSP> already defined above
'<USP>': grammar.UnicodeCategory('Zs'),
# From <https://tc39.es/ecma262/#table-33>
'<LF>': grammar.Literal('\u000a'),
'<CR>': grammar.Literal('\u000d'),