[pypy-commit] pypy default: 'string-escape' codec always escape single quotes

[amauryfa]

Author: Amaury Forgeot d'Arc <amauryfa at gmail.com>
Branch: 
Changeset: r46906:47a43db15b5b
Date: 2011-08-23 22:52 +0200
http://bitbucket.org/pypy/pypy/changeset/47a43db15b5b/

Log:	'string-escape' codec always escape single quotes

diff --git a/pypy/module/_codecs/interp_codecs.py b/pypy/module/_codecs/interp_codecs.py
--- a/pypy/module/_codecs/interp_codecs.py
+++ b/pypy/module/_codecs/interp_codecs.py
@@ -687,11 +687,15 @@
 # support for the "string escape" codec
 # This is a bytes-to bytes transformation
 
- at unwrap_spec(errors='str_or_None')
-def escape_encode(space, w_string, errors='strict'):
-    w_repr = space.repr(w_string)
-    w_result = space.getslice(w_repr, space.wrap(1), space.wrap(-1))
-    return space.newtuple([w_result, space.len(w_string)])
+ at unwrap_spec(data=str, errors='str_or_None')
+def escape_encode(space, data, errors='strict'):
+    from pypy.objspace.std.stringobject import string_escape_encode
+    result = string_escape_encode(data, quote="'")
+    start = 1
+    end = len(result) - 1
+    assert end >= 0
+    w_result = space.wrap(result[start:end])
+    return space.newtuple([w_result, space.wrap(len(data))])
 
 @unwrap_spec(data=str, errors='str_or_None')
 def escape_decode(space, data, errors='strict'):
diff --git a/pypy/module/_codecs/test/test_codecs.py b/pypy/module/_codecs/test/test_codecs.py
--- a/pypy/module/_codecs/test/test_codecs.py
+++ b/pypy/module/_codecs/test/test_codecs.py
@@ -102,7 +102,6 @@
     
     def test_indexerror(self):
         test =   "\\"     # trailing backslash
-             
         raises (ValueError, test.decode,'string-escape')
 
     def test_charmap_decode(self):
@@ -292,6 +291,10 @@
         assert '\\0f'.decode('string_escape') == chr(0) + 'f'
         assert '\\08'.decode('string_escape') == chr(0) + '8'
 
+    def test_escape_encode(self):
+        assert '"'.encode('string_escape') == '"'
+        assert "'".encode('string_escape') == "\\'"
+
     def test_decode_utf8_different_case(self):
         constant = u"a"
         assert constant.encode("utf-8") == constant.encode("UTF-8")
diff --git a/pypy/objspace/std/stringobject.py b/pypy/objspace/std/stringobject.py
--- a/pypy/objspace/std/stringobject.py
+++ b/pypy/objspace/std/stringobject.py
@@ -913,12 +913,16 @@
 def repr__String(space, w_str):
     s = w_str._value
 
-    buf = StringBuilder(len(s) + 2)
-
     quote = "'"
     if quote in s and '"' not in s:
         quote = '"'
 
+    return space.wrap(string_escape_encode(s, quote))
+
+def string_escape_encode(s, quote):
+
+    buf = StringBuilder(len(s) + 2)
+
     buf.append(quote)
     startslice = 0
 
@@ -959,7 +963,7 @@
 
     buf.append(quote)
 
-    return space.wrap(buf.build())
+    return buf.build()
 
 
 DEFAULT_NOOP_TABLE = ''.join([chr(i) for i in range(256)])