Do not warn about \u escapes in string literals when Unicode literals

are used for Python 2.*. Fixes BitBucket issue #151.

4 files changed, 17 insertions, 3 deletions

diff --git a/ChangeLog b/ChangeLog
index d57133d..371b0ba 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -11,6 +11,9 @@ ChangeLog for Pylint
     * Added a new warning for closing over variables that are
       defined in loops. Fixes Bitbucket issue #176.
 
+    * Do not warn about \u escapes in string literals when Unicode literals
+      are used for Python 2.*. Fixes BitBucket issue #151.
+
     * Extend the checking for unbalanced-tuple-unpacking and
       unpacking-non-sequence to instance attribute unpacking as well.
 
diff --git a/checkers/strings.py b/checkers/strings.py
index 663d61d..04cf1bc 100644
--- a/checkers/strings.py
+++ b/checkers/strings.py
@@ -23,7 +23,7 @@ import tokenize
 
 import astroid
 
-from pylint.interfaces import ITokenChecker, IAstroidChecker
+from pylint.interfaces import ITokenChecker, IAstroidChecker, IRawChecker
 from pylint.checkers import BaseChecker, BaseTokenChecker
 from pylint.checkers import utils
 from pylint.checkers.utils import check_messages
@@ -195,7 +195,7 @@ class StringMethodsChecker(BaseChecker):
 
 class StringConstantChecker(BaseTokenChecker):
     """Check string literals"""
-    __implements__ = (ITokenChecker,)
+    __implements__ = (ITokenChecker, IRawChecker)
     name = 'string_constant'
     msgs = {
         'W1401': ('Anomalous backslash in string: \'%s\'. '
@@ -221,6 +221,9 @@ class StringConstantChecker(BaseTokenChecker):
     # Unicode strings.
     UNICODE_ESCAPE_CHARACTERS = 'uUN'
 
+    def process_module(self, module):
+        self._unicode_literals = 'unicode_literals' in module.future_imports
+
     def process_tokens(self, tokens):
         for (tok_type, token, (start_row, start_col), _, _) in tokens:
             if tok_type == tokenize.STRING:
@@ -279,7 +282,7 @@ class StringConstantChecker(BaseTokenChecker):
             if next_char in self.UNICODE_ESCAPE_CHARACTERS:
                 if 'u' in prefix:
                     pass
-                elif _PY3K and 'b' not in prefix:
+                elif (_PY3K or self._unicode_literals) and 'b' not in prefix:
                     pass  # unicode by default
                 else:
                     self.add_message('anomalous-unicode-escape-in-string', 
diff --git a/test/input/func_unicode_literal_py_30.py b/test/input/func_unicode_literal_py_30.py
new file mode 100644
index 0000000..fa47902
--- /dev/null
+++ b/test/input/func_unicode_literal_py_30.py
@@ -0,0 +1,7 @@
+"""Unicode literals in Python 2.*"""
+from __future__ import unicode_literals
+
+__revision__ = 0
+
+BAD_STRING = b'\u1234'
+GOOD_STRING = '\u1234'
diff --git a/test/messages/func_unicode_literal_py_30.txt b/test/messages/func_unicode_literal_py_30.txt
new file mode 100644
index 0000000..25efa99
--- /dev/null
+++ b/test/messages/func_unicode_literal_py_30.txt
@@ -0,0 +1 @@
+W:  6: Anomalous Unicode escape in byte string: '\u'. String constant might be missing an r or u prefix.