summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorPetri Lehtinen <petri@digip.org>2012-09-01 04:27:58 (GMT)
committerPetri Lehtinen <petri@digip.org>2012-09-01 04:29:06 (GMT)
commitf9e1f1128b1d040cabb519ab18f770aa0c456744 (patch)
tree2fba2ebfc23e2ba6ebf744a9527a436da23ecd2d
parent201018718fc55fada8fd159b86bc038c3d297597 (diff)
downloadcpython-f9e1f1128b1d040cabb519ab18f770aa0c456744.zip
cpython-f9e1f1128b1d040cabb519ab18f770aa0c456744.tar.gz
cpython-f9e1f1128b1d040cabb519ab18f770aa0c456744.tar.bz2
#13769: Enhance docs for ensure_ascii semantics in JSON decoding functions
-rw-r--r--Doc/library/json.rst30
-rw-r--r--Lib/json/__init__.py18
-rw-r--r--Lib/json/encoder.py9
-rw-r--r--Misc/NEWS3
4 files changed, 37 insertions, 23 deletions
diff --git a/Doc/library/json.rst b/Doc/library/json.rst
index 69ebc4f..ed5cf21 100644
--- 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 d3b8b0b..4f3f6c5 100644
--- 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 b0d745b..169450d 100644
--- 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 bdfd0b7..13e8b00 100644
--- 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.