fixed #449964: sre.sub raises an exception if the template contains a
\g<x> group reference followed by a character escape
(also restructured a few things on the way to fixing #449000)
diff --git a/Lib/sre.py b/Lib/sre.py
index a87870e..7a640f9 100644
--- a/Lib/sre.py
+++ b/Lib/sre.py
@@ -251,11 +251,13 @@
else:
template = _compile_repl(template, pattern)
literals = template[1]
- sub = 0 # temporarly disabled, see bug #449000
- if (sub and not count and pattern._isliteral() and
- len(literals) == 1 and literals[0]):
- # shortcut: both pattern and string are literals
- return string.replace(text, pattern.pattern, literals[0]), 0
+ if sub and not count:
+ literal = pattern._getliteral()
+ if literal and "\\" in literal:
+ literal = None # may contain untranslated escapes
+ if literal is not None and len(literals) == 1 and literals[0]:
+ # shortcut: both pattern and string are literals
+ return string.replace(text, pattern.pattern, literals[0]), 0
def filter(match, template=template):
return sre_parse.expand_template(template, match)
n = i = 0
diff --git a/Lib/sre_parse.py b/Lib/sre_parse.py
index af1edbf..7d9b889 100644
--- a/Lib/sre_parse.py
+++ b/Lib/sre_parse.py
@@ -647,9 +647,9 @@
p.append((LITERAL, literal))
sep = source[:0]
if type(sep) is type(""):
- char = chr
+ makechar = chr
else:
- char = unichr
+ makechar = unichr
while 1:
this = s.get()
if this is None:
@@ -693,14 +693,14 @@
break
if not code:
this = this[1:]
- code = LITERAL, char(atoi(this[-6:], 8) & 0xff)
+ code = LITERAL, makechar(atoi(this[-6:], 8) & 0xff)
if code[0] is LITERAL:
literal(code[1])
else:
a(code)
else:
try:
- this = char(ESCAPES[this][1])
+ this = makechar(ESCAPES[this][1])
except KeyError:
pass
literal(this)
diff --git a/Lib/test/test_sre.py b/Lib/test/test_sre.py
index 49fe4c6..4a71447 100644
--- a/Lib/test/test_sre.py
+++ b/Lib/test/test_sre.py
@@ -104,6 +104,9 @@
test(r"""sre.sub(r'(?P<unk>x)', '\g<unk>\g<unk>', 'xx')""", 'xxxx')
test(r"""sre.sub(r'(?P<unk>x)', '\g<1>\g<1>', 'xx')""", 'xxxx')
+# bug 449964: fails for group followed by other escape
+test(r"""sre.sub(r'(?P<unk>x)', '\g<1>\g<1>\\b', 'xx')""", 'xx\bxx\b')
+
test(r"""sre.sub(r'a', r'\t\n\v\r\f\a\b\B\Z\a\A\w\W\s\S\d\D', 'a')""", '\t\n\v\r\f\a\b\\B\\Z\a\\A\\w\\W\\s\\S\\d\\D')
test(r"""sre.sub(r'a', '\t\n\v\r\f\a', 'a')""", '\t\n\v\r\f\a')
test(r"""sre.sub(r'a', '\t\n\v\r\f\a', 'a')""", (chr(9)+chr(10)+chr(11)+chr(13)+chr(12)+chr(7)))