1 files changed, 54 insertions, 0 deletions
diff --git a/bleach/encoding.py b/bleach/encoding.py
new file mode 100644
index 0000000..b9a989d
--- /dev/null
+++ b/bleach/encoding.py
@@ -0,0 +1,54 @@
+import datetime
+from decimal import Decimal
+import types
+
+
+def is_protected_type(obj):
+    """Determine if the object instance is of a protected type.
+
+    Objects of protected types are preserved as-is when passed to
+    force_unicode(strings_only=True).
+    """
+    return isinstance(obj, (
+        types.NoneType,
+        int, long,
+        datetime.datetime, datetime.date, datetime.time,
+        float, Decimal)
+    )
+
+
+def force_unicode(s, encoding='utf-8', strings_only=False, errors='strict'):
+    """
+    Similar to smart_unicode, except that lazy instances are resolved to
+    strings, rather than kept as lazy objects.
+
+    If strings_only is True, don't convert (some) non-string-like objects.
+    """
+    if strings_only and is_protected_type(s):
+        return s
+    try:
+        if not isinstance(s, basestring,):
+            if hasattr(s, '__unicode__'):
+                s = unicode(s)
+            else:
+                try:
+                    s = unicode(str(s), encoding, errors)
+                except UnicodeEncodeError:
+                    if not isinstance(s, Exception):
+                        raise
+                    # If we get to here, the caller has passed in an Exception
+                    # subclass populated with non-ASCII data without special
+                    # handling to display as a string. We need to handle this
+                    # without raising a further exception. We do an
+                    # approximation to what the Exception's standard str()
+                    # output should be.
+                    s = ' '.join([force_unicode(arg, encoding, strings_only,
+                            errors) for arg in s])
+        elif not isinstance(s, unicode):
+            # Note: We use .decode() here, instead of unicode(s, encoding,
+            # errors), so that if s is a SafeString, it ends up being a
+            # SafeUnicode at the end.
+            s = s.decode(encoding, errors)
+    except UnicodeDecodeError, e:
+        raise UnicodeDecodeError(*e.args)
+    return s