Author: Amaury Forgeot d'Arc <[email protected]>
Branch: py3k
Changeset: r57111:2851a02c2eba
Date: 2012-09-02 23:18 +0200
http://bitbucket.org/pypy/pypy/changeset/2851a02c2eba/
Log: The \u is no more an escape sequence in raw unicode strings: r'\u'
is a string of two characters.
diff --git a/pypy/interpreter/pyparser/parsestring.py
b/pypy/interpreter/pyparser/parsestring.py
--- a/pypy/interpreter/pyparser/parsestring.py
+++ b/pypy/interpreter/pyparser/parsestring.py
@@ -48,7 +48,7 @@
'unmatched triple quotes in literal')
q -= 2
- if unicode_literal: # XXX Py_UnicodeFlag is ignored for now
+ if unicode_literal and not rawmode: # XXX Py_UnicodeFlag is ignored for now
if encoding is None or encoding == "iso-8859-1":
# 'unicode_escape' expects latin-1 bytes, string is ready.
buf = s
@@ -87,29 +87,19 @@
bufq = len(buf)
assert 0 <= bufp <= bufq
substr = buf[bufp:bufq]
- if rawmode:
- v = unicodehelper.PyUnicode_DecodeRawUnicodeEscape(space, substr)
- else:
- v = unicodehelper.PyUnicode_DecodeUnicodeEscape(space, substr)
+ v = unicodehelper.PyUnicode_DecodeUnicodeEscape(space, substr)
return space.wrap(v)
- need_encoding = (encoding is not None and
- encoding != "utf-8" and encoding != "utf8" and
- encoding != "iso-8859-1")
assert 0 <= ps <= q
substr = s[ps : q]
- if rawmode or '\\' not in s[ps:]:
- if need_encoding:
- w_u = space.wrap(unicodehelper.PyUnicode_DecodeUTF8(space, substr))
- w_v = unicodehelper.PyUnicode_AsEncodedString(space, w_u,
space.wrap(encoding))
- return w_v
+ if rawmode or '\\' not in substr:
+ if not unicode_literal:
+ return space.wrapbytes(substr)
else:
- return space.wrapbytes(substr)
+ v = unicodehelper.PyUnicode_DecodeUTF8(space, substr)
+ return space.wrap(v)
- enc = None
- if need_encoding:
- enc = encoding
- v = PyString_DecodeEscape(space, substr, enc)
+ v = PyString_DecodeEscape(space, substr, encoding)
return space.wrapbytes(v)
def hexbyte(val):
diff --git a/pypy/interpreter/pyparser/test/test_parsestring.py
b/pypy/interpreter/pyparser/test/test_parsestring.py
--- a/pypy/interpreter/pyparser/test/test_parsestring.py
+++ b/pypy/interpreter/pyparser/test/test_parsestring.py
@@ -62,6 +62,11 @@
w_ret = parsestring.parsestr(space, None, "r'hi'")
assert space.isinstance_w(w_ret, space.w_unicode)
+ def test_raw_unicode_literals(self):
+ space = self.space
+ w_ret = parsestring.parsestr(space, None, "r'\u'")
+ assert space.int_w(space.len(w_ret)) == 2
+
def test_bytes(self):
space = self.space
b = "b'hello'"
_______________________________________________
pypy-commit mailing list
[email protected]
http://mail.python.org/mailman/listinfo/pypy-commit
