#13769: Enhance docs for ensure_ascii semantics in JSON decoding functions

diff --git a/Doc/library/json.rst b/Doc/library/json.rst
index 69ebc4fc9c9763c8c01a36489dc8501d96577972..ed5cf2165ac947581653c32bc13529c22c85826c 100644 (file)
--- a/Doc/library/json.rst
+++ b/Doc/library/json.rst
@@ -127,11 +127,14 @@ Basic Usage
    :class:`float`, :class:`bool`, ``None``) will be skipped instead of raising a
    :exc:`TypeError`.
 
-   If *ensure_ascii* is ``False`` (default: ``True``), then some chunks written
-   to *fp* may be :class:`unicode` instances, subject to normal Python
-   :class:`str` to :class:`unicode` coercion rules.  Unless ``fp.write()``
-   explicitly understands :class:`unicode` (as in :func:`codecs.getwriter`) this
-   is likely to cause an error.
+   If *ensure_ascii* is ``True`` (the default), all non-ASCII characters in the
+   output are escaped with ``\uXXXX`` sequences, and the result is a
+   :class:`str` instance consisting of ASCII characters only.  If
+   *ensure_ascii* is ``False``, some chunks written to *fp* may be
+   :class:`unicode` instances.  This usually happens because the input contains
+   unicode strings or the *encoding* parameter is used.  Unless ``fp.write()``
+   explicitly understands :class:`unicode` (as in :func:`codecs.getwriter`)
+   this is likely to cause an error.
 
    If *check_circular* is ``False`` (default: ``True``), then the circular
    reference check for container types will be skipped and a circular reference
@@ -168,11 +171,11 @@ Basic Usage
 
 .. function:: dumps(obj[, skipkeys[, ensure_ascii[, check_circular[, allow_nan[, cls[, indent[, separators[, encoding[, default[, **kw]]]]]]]]]])
 
-   Serialize *obj* to a JSON formatted :class:`str`.
+   Serialize *obj* to a JSON formatted :class:`str`.  If *ensure_ascii* is
+   ``False``, the result may contain non-ASCII characters and the return value
+   may be a :class:`unicode` instance.
 
-   If *ensure_ascii* is ``False``, then the return value will be a
-   :class:`unicode` instance.  The other arguments have the same meaning as in
-   :func:`dump`.
+   The arguments have the same meaning as in :func:`dump`.
 
    .. note::
 
@@ -371,9 +374,12 @@ Encoders and Decoders
    attempt encoding of keys that are not str, int, long, float or None.  If
    *skipkeys* is ``True``, such items are simply skipped.
 
-   If *ensure_ascii* is ``True`` (the default), the output is guaranteed to be
-   :class:`str` objects with all incoming unicode characters escaped.  If
-   *ensure_ascii* is ``False``, the output will be a unicode object.
+   If *ensure_ascii* is ``True`` (the default), all non-ASCII characters in the
+   output are escaped with ``\uXXXX`` sequences, and the results are
+   :class:`str` instances consisting of ASCII characters only. If
+   *ensure_ascii* is ``False``, a result may be a :class:`unicode`
+   instance. This usually happens if the input contains unicode strings or the
+   *encoding* parameter is used.
 
    If *check_circular* is ``True`` (the default), then lists, dicts, and custom
    encoded objects will be checked for circular references during encoding to

diff --git a/Lib/json/__init__.py b/Lib/json/__init__.py
index d3b8b0b8764d90d8290e1d8448ca161eb0ebc249..4f3f6c57da06dfd971e848091ae6c1516487c66e 100644 (file)
--- a/Lib/json/__init__.py
+++ b/Lib/json/__init__.py
@@ -129,11 +129,14 @@ def dump(obj, fp, skipkeys=False, ensure_ascii=True, check_circular=True,
     (``str``, ``unicode``, ``int``, ``long``, ``float``, ``bool``, ``None``)
     will be skipped instead of raising a ``TypeError``.
 
-    If ``ensure_ascii`` is false, then the some chunks written to ``fp``
-    may be ``unicode`` instances, subject to normal Python ``str`` to
-    ``unicode`` coercion rules. Unless ``fp.write()`` explicitly
-    understands ``unicode`` (as in ``codecs.getwriter()``) this is likely
-    to cause an error.
+    If ``ensure_ascii`` is true (the default), all non-ASCII characters in the
+    output are escaped with ``\uXXXX`` sequences, and the result is a ``str``
+    instance consisting of ASCII characters only.  If ``ensure_ascii`` is
+    ``False``, some chunks written to ``fp`` may be ``unicode`` instances.
+    This usually happens because the input contains unicode strings or the
+    ``encoding`` parameter is used. Unless ``fp.write()`` explicitly
+    understands ``unicode`` (as in ``codecs.getwriter``) this is likely to
+    cause an error.
 
     If ``check_circular`` is false, then the circular reference check
     for container types will be skipped and a circular reference will
@@ -191,9 +194,8 @@ def dumps(obj, skipkeys=False, ensure_ascii=True, check_circular=True,
     (``str``, ``unicode``, ``int``, ``long``, ``float``, ``bool``, ``None``)
     will be skipped instead of raising a ``TypeError``.
 
-    If ``ensure_ascii`` is false, then the return value will be a
-    ``unicode`` instance subject to normal Python ``str`` to ``unicode``
-    coercion rules instead of being escaped to an ASCII ``str``.
+    If ``ensure_ascii`` is false, all non-ASCII characters are not escaped, and
+    the return value may be a ``unicode`` instance. See ``dump`` for details.
 
     If ``check_circular`` is false, then the circular reference check
     for container types will be skipped and a circular reference will

diff --git a/Lib/json/encoder.py b/Lib/json/encoder.py
index b0d745b5dc059acac5bd6a0af5b78353855e93eb..169450d68ecd69e429df044ce8d83131ef79162c 100644 (file)
--- a/Lib/json/encoder.py
+++ b/Lib/json/encoder.py
@@ -107,9 +107,12 @@ class JSONEncoder(object):
         encoding of keys that are not str, int, long, float or None.  If
         skipkeys is True, such items are simply skipped.
 
-        If ensure_ascii is true, the output is guaranteed to be str
-        objects with all incoming unicode characters escaped.  If
-        ensure_ascii is false, the output will be unicode object.
+        If *ensure_ascii* is true (the default), all non-ASCII
+        characters in the output are escaped with \uXXXX sequences,
+        and the results are str instances consisting of ASCII
+        characters only.  If ensure_ascii is False, a result may be a
+        unicode instance.  This usually happens if the input contains
+        unicode strings or the *encoding* parameter is used.
 
         If check_circular is true, then lists, dicts, and custom encoded
         objects will be checked for circular references during encoding to

diff --git a/Misc/NEWS b/Misc/NEWS
index bdfd0b797ad8351e671a484f782b9f19a853d510..13e8b00129ee1f754251065e44c13b0f65e3bb5a 100644 (file)
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -393,6 +393,9 @@ Build
 Documentation
 -------------
 
+- Issue #13769: Document the effect of ensure_ascii to the return type
+  of JSON decoding functions.
+
 - Issue #14880: Fix kwargs notation in csv.reader, .writer & .register_dialect.
   Patch by Chris Rebert.