Yaltik/hy
2
0
Fork 0
Code Pull Requests Releases Activity

Simplify string parsing with unicode_literals

Browse Source 
I switched from `ast.literal_eval` back to `eval` because the former doesn't respect `unicode_literals`.
This commit is contained in:
Kodi Arfer 2017-08-28 10:28:19 -07:00
parent 3db13ec71f
commit 98fb33d0a3
1 changed files with 7 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
hy/lex/parser.py
View File

@ -2,12 +2,13 @@
# This file is part of Hy, which is free software licensed under the Expat # This file is part of Hy, which is free software licensed under the Expat
# license. See the LICENSE. # license. See the LICENSE.
from __future__ import unicode_literals
from functools import wraps from functools import wraps
from ast import literal_eval
from rply import ParserGenerator from rply import ParserGenerator
from hy._compat import PY3, str_type from hy._compat import str_type
from hy.models import (HyBytes, HyComplex, HyCons, HyDict, HyExpression, from hy.models import (HyBytes, HyComplex, HyCons, HyDict, HyExpression,
HyFloat, HyInteger, HyKeyword, HyList, HySet, HyString, HyFloat, HyInteger, HyKeyword, HyList, HySet, HyString,
HySymbol) HySymbol)
@ -265,38 +266,13 @@ def t_empty_list(p):
return HyList([]) return HyList([])
if PY3:
def uni_hystring(s):
return HyString(literal_eval(s))
def hybytes(s):
return HyBytes(literal_eval('b'+s))
else:
def uni_hystring(s):
return HyString(literal_eval('u'+s))
def hybytes(s):
return HyBytes(literal_eval(s))
@pg.production("string : STRING") @pg.production("string : STRING")
@set_boundaries @set_boundaries
def t_string(p): def t_string(p):
# remove trailing quote # Replace the single double quotes with triple double quotes to allow
s = p[0].value[:-1] # embedded newlines.
# get the header s = eval(p[0].value.replace('"', '"""', 1)[:-1] + '"""')
header, s = s.split('"', 1) return (HyString if isinstance(s, str_type) else HyBytes)(s)
# remove unicode marker (this is redundant because Hy string
# literals already, by default, generate Unicode literals
# under Python 2)
header = header.replace("u", "")
# remove bytes marker, since we'll need to exclude it for Python 2
is_bytestring = "b" in header
header = header.replace("b", "")
# build python string
s = header + '"""' + s + '"""'
return (hybytes if is_bytestring else uni_hystring)(s)
@pg.production("string : PARTIAL_STRING") @pg.production("string : PARTIAL_STRING")