gh-140793: Improve documentatation and tests for the ensure_ascii option in the json module (GH-140906)

* Document that ensure_ascii=True forces escaping not only non-ASCII, but also
  non-printable characters (the only affected ASCII character is U+007F).
* Ensure that the help output for the json module does not exceed 80
  columns (except one long line in an example and generated lines).
* Add more tests.

Author: serhiy-storchaka

Doc/library/json.rst

@@ -183,8 +183,10 @@ Basic Usage
 
    :param bool ensure_ascii:
       If ``True`` (the default), the output is guaranteed to
-      have all incoming non-ASCII characters escaped.
-      If ``False``, these characters will be outputted as-is.
+      have all incoming non-ASCII and non-printable characters escaped.
+      If ``False``, all characters will be outputted as-is, except for
+      the characters that must be escaped: quotation mark, reverse solidus,
+      and the control characters U+0000 through U+001F.
 
    :param bool check_circular:
       If ``False``, the circular reference check for container types is skipped
@@ -495,8 +497,10 @@ Encoders and Decoders
    :class:`bool` or ``None``.  If *skipkeys* is true, such items are simply skipped.
 
    If *ensure_ascii* is true (the default), the output is guaranteed to
-   have all incoming non-ASCII characters escaped.  If *ensure_ascii* is
-   false, these characters will be output as-is.
+   have all incoming non-ASCII and non-printable characters escaped.
+   If *ensure_ascii* is false, all characters will be output as-is, except for
+   the characters that must be escaped: quotation mark, reverse solidus,
+   and the control characters U+0000 through U+001F.
 
    If *check_circular* is true (the default), then lists, dicts, and custom
    encoded objects will be checked for circular references during encoding to
@@ -636,7 +640,7 @@ UTF-32, with UTF-8 being the recommended default for maximum interoperability.
 
 As permitted, though not required, by the RFC, this module's serializer sets
 *ensure_ascii=True* by default, thus escaping the output so that the resulting
-strings only contain ASCII characters.
+strings only contain printable ASCII characters.
 
 Other than the *ensure_ascii* parameter, this module is defined strictly in
 terms of conversion between Python objects and

Lib/json/__init__.py

@@ -127,8 +127,9 @@ def dump(obj, fp, *, skipkeys=False, ensure_ascii=True, check_circular=True,
     instead of raising a ``TypeError``.
 
     If ``ensure_ascii`` is false, then the strings written to ``fp`` can
-    contain non-ASCII characters if they appear in strings contained in
-    ``obj``. Otherwise, all such characters are escaped in JSON strings.
+    contain non-ASCII and non-printable characters if they appear in strings
+    contained in ``obj``. Otherwise, all such characters are escaped in JSON
+    strings.
 
     If ``check_circular`` is false, then the circular reference check
     for container types will be skipped and a circular reference will
@@ -144,10 +145,11 @@ def dump(obj, fp, *, skipkeys=False, ensure_ascii=True, check_circular=True,
     level of 0 will only insert newlines. ``None`` is the most compact
     representation.
 
-    If specified, ``separators`` should be an ``(item_separator, key_separator)``
-    tuple.  The default is ``(', ', ': ')`` if *indent* is ``None`` and
-    ``(',', ': ')`` otherwise.  To get the most compact JSON representation,
-    you should specify ``(',', ':')`` to eliminate whitespace.
+    If specified, ``separators`` should be an ``(item_separator,
+    key_separator)`` tuple.  The default is ``(', ', ': ')`` if *indent* is
+    ``None`` and ``(',', ': ')`` otherwise.  To get the most compact JSON
+    representation, you should specify ``(',', ':')`` to eliminate
+    whitespace.
 
     ``default(obj)`` is a function that should return a serializable version
     of obj or raise TypeError. The default simply raises TypeError.
@@ -188,9 +190,10 @@ def dumps(obj, *, skipkeys=False, ensure_ascii=True, check_circular=True,
     (``str``, ``int``, ``float``, ``bool``, ``None``) will be skipped
     instead of raising a ``TypeError``.
 
-    If ``ensure_ascii`` is false, then the return value can contain non-ASCII
-    characters if they appear in strings contained in ``obj``. Otherwise, all
-    such characters are escaped in JSON strings.
+    If ``ensure_ascii`` is false, then the return value can contain
+    non-ASCII and non-printable characters if they appear in strings
+    contained in ``obj``.  Otherwise, all such characters are escaped in
+    JSON strings.
 
     If ``check_circular`` is false, then the circular reference check
     for container types will be skipped and a circular reference will
@@ -206,10 +209,11 @@ def dumps(obj, *, skipkeys=False, ensure_ascii=True, check_circular=True,
     level of 0 will only insert newlines. ``None`` is the most compact
     representation.
 
-    If specified, ``separators`` should be an ``(item_separator, key_separator)``
-    tuple.  The default is ``(', ', ': ')`` if *indent* is ``None`` and
-    ``(',', ': ')`` otherwise.  To get the most compact JSON representation,
-    you should specify ``(',', ':')`` to eliminate whitespace.
+    If specified, ``separators`` should be an ``(item_separator,
+    key_separator)`` tuple.  The default is ``(', ', ': ')`` if *indent* is
+    ``None`` and ``(',', ': ')`` otherwise.  To get the most compact JSON
+    representation, you should specify ``(',', ':')`` to eliminate
+    whitespace.
 
     ``default(obj)`` is a function that should return a serializable version
     of obj or raise TypeError. The default simply raises TypeError.
@@ -280,11 +284,12 @@ def load(fp, *, cls=None, object_hook=None, parse_float=None,
     ``object_hook`` will be used instead of the ``dict``. This feature
     can be used to implement custom decoders (e.g. JSON-RPC class hinting).
 
-    ``object_pairs_hook`` is an optional function that will be called with the
-    result of any object literal decoded with an ordered list of pairs.  The
-    return value of ``object_pairs_hook`` will be used instead of the ``dict``.
-    This feature can be used to implement custom decoders.  If ``object_hook``
-    is also defined, the ``object_pairs_hook`` takes priority.
+    ``object_pairs_hook`` is an optional function that will be called with
+    the result of any object literal decoded with an ordered list of pairs.
+    The return value of ``object_pairs_hook`` will be used instead of the
+    ``dict``.  This feature can be used to implement custom decoders.  If
+    ``object_hook`` is also defined, the ``object_pairs_hook`` takes
+    priority.
 
     To use a custom ``JSONDecoder`` subclass, specify it with the ``cls``
     kwarg; otherwise ``JSONDecoder`` is used.
@@ -305,11 +310,12 @@ def loads(s, *, cls=None, object_hook=None, parse_float=None,
     ``object_hook`` will be used instead of the ``dict``. This feature
     can be used to implement custom decoders (e.g. JSON-RPC class hinting).
 
-    ``object_pairs_hook`` is an optional function that will be called with the
-    result of any object literal decoded with an ordered list of pairs.  The
-    return value of ``object_pairs_hook`` will be used instead of the ``dict``.
-    This feature can be used to implement custom decoders.  If ``object_hook``
-    is also defined, the ``object_pairs_hook`` takes priority.
+    ``object_pairs_hook`` is an optional function that will be called with
+    the result of any object literal decoded with an ordered list of pairs.
+    The return value of ``object_pairs_hook`` will be used instead of the
+    ``dict``.  This feature can be used to implement custom decoders.  If
+    ``object_hook`` is also defined, the ``object_pairs_hook`` takes
+    priority.
 
     ``parse_float``, if specified, will be called with the string
     of every JSON float to be decoded. By default this is equivalent to

Lib/json/decoder.py

@@ -297,10 +297,10 @@ def __init__(self, *, object_hook=None, parse_float=None,
         place of the given ``dict``.  This can be used to provide custom
         deserializations (e.g. to support JSON-RPC class hinting).
 
-        ``object_pairs_hook``, if specified will be called with the result of
-        every JSON object decoded with an ordered list of pairs.  The return
-        value of ``object_pairs_hook`` will be used instead of the ``dict``.
-        This feature can be used to implement custom decoders.
+        ``object_pairs_hook``, if specified will be called with the result
+        of every JSON object decoded with an ordered list of pairs.  The
+        return value of ``object_pairs_hook`` will be used instead of the
+        ``dict``.  This feature can be used to implement custom decoders.
         If ``object_hook`` is also defined, the ``object_pairs_hook`` takes
         priority.
 

Lib/json/encoder.py

@@ -111,9 +111,10 @@ def __init__(self, *, skipkeys=False, ensure_ascii=True,
         encoding of keys that are not str, int, float, bool 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 non-ASCII characters escaped.  If
-        ensure_ascii is false, the output can contain non-ASCII characters.
+        If ensure_ascii is true, the output is guaranteed to be str objects
+        with all incoming non-ASCII and non-printable characters escaped.
+        If ensure_ascii is false, the output can contain non-ASCII and
+        non-printable characters.
 
         If check_circular is true, then lists, dicts, and custom encoded
         objects will be checked for circular references during encoding to
@@ -134,14 +135,15 @@ def __init__(self, *, skipkeys=False, ensure_ascii=True,
         indent level.  An indent level of 0 will only insert newlines.
         None is the most compact representation.
 
-        If specified, separators should be an (item_separator, key_separator)
-        tuple.  The default is (', ', ': ') if *indent* is ``None`` and
-        (',', ': ') otherwise.  To get the most compact JSON representation,
-        you should specify (',', ':') to eliminate whitespace.
+        If specified, separators should be an (item_separator,
+        key_separator) tuple.  The default is (', ', ': ') if *indent* is
+        ``None`` and (',', ': ') otherwise.  To get the most compact JSON
+        representation, you should specify (',', ':') to eliminate
+        whitespace.
 
         If specified, default is a function that gets called for objects
-        that can't otherwise be serialized.  It should return a JSON encodable
-        version of the object or raise a ``TypeError``.
+        that can't otherwise be serialized.  It should return a JSON
+        encodable version of the object or raise a ``TypeError``.
 
         """
 

Lib/test/test_json/test_encode_basestring_ascii.py

@@ -8,13 +8,12 @@
     ('\u0123\u4567\u89ab\ucdef\uabcd\uef4a', '"\\u0123\\u4567\\u89ab\\ucdef\\uabcd\\uef4a"'),
     ('controls', '"controls"'),
     ('\x08\x0c\n\r\t', '"\\b\\f\\n\\r\\t"'),
+    ('\x00\x1f\x7f', '"\\u0000\\u001f\\u007f"'),
     ('{"object with 1 member":["array with 1 element"]}', '"{\\"object with 1 member\\":[\\"array with 1 element\\"]}"'),
     (' s p a c e d ', '" s p a c e d "'),
     ('\U0001d120', '"\\ud834\\udd20"'),
     ('\u03b1\u03a9', '"\\u03b1\\u03a9"'),
     ("`1~!@#$%^&*()_+-={':[,]}|;.</>?", '"`1~!@#$%^&*()_+-={\':[,]}|;.</>?"'),
-    ('\x08\x0c\n\r\t', '"\\b\\f\\n\\r\\t"'),
-    ('\u0123\u4567\u89ab\ucdef\uabcd\uef4a', '"\\u0123\\u4567\\u89ab\\ucdef\\uabcd\\uef4a"'),
 ]
 
 class TestEncodeBasestringAscii:

Lib/test/test_json/test_unicode.py

@@ -32,6 +32,29 @@ def test_encoding7(self):
         j = self.dumps(u + "\n", ensure_ascii=False)
         self.assertEqual(j, f'"{u}\\n"')
 
+    def test_ascii_non_printable_encode(self):
+        u = '\b\t\n\f\r\x00\x1f\x7f'
+        self.assertEqual(self.dumps(u),
+                         '"\\b\\t\\n\\f\\r\\u0000\\u001f\\u007f"')
+        self.assertEqual(self.dumps(u, ensure_ascii=False),
+                         '"\\b\\t\\n\\f\\r\\u0000\\u001f\x7f"')
+
+    def test_ascii_non_printable_decode(self):
+        self.assertEqual(self.loads('"\\b\\t\\n\\f\\r"'),
+                         '\b\t\n\f\r')
+        s = ''.join(map(chr, range(32)))
+        for c in s:
+            self.assertRaises(self.JSONDecodeError, self.loads, f'"{c}"')
+        self.assertEqual(self.loads(f'"{s}"', strict=False), s)
+        self.assertEqual(self.loads('"\x7f"'), '\x7f')
+
+    def test_escaped_decode(self):
+        self.assertEqual(self.loads('"\\b\\t\\n\\f\\r"'), '\b\t\n\f\r')
+        self.assertEqual(self.loads('"\\"\\\\\\/"'), '"\\/')
+        for c in set(map(chr, range(0x100))) - set('"\\/bfnrt'):
+            self.assertRaises(self.JSONDecodeError, self.loads, f'"\\{c}"')
+            self.assertRaises(self.JSONDecodeError, self.loads, f'"\\{c}"', strict=False)
+
     def test_big_unicode_encode(self):
         u = '\U0001d120'
         self.assertEqual(self.dumps(u), '"\\ud834\\udd20"')
@@ -48,6 +71,18 @@ def test_unicode_decode(self):
             s = f'"\\u{i:04x}"'
             self.assertEqual(self.loads(s), u)
 
+    def test_single_surrogate_encode(self):
+        self.assertEqual(self.dumps('\uD83D'), '"\\ud83d"')
+        self.assertEqual(self.dumps('\uD83D', ensure_ascii=False), '"\ud83d"')
+        self.assertEqual(self.dumps('\uDC0D'), '"\\udc0d"')
+        self.assertEqual(self.dumps('\uDC0D', ensure_ascii=False), '"\udc0d"')
+
+    def test_single_surrogate_decode(self):
+        self.assertEqual(self.loads('"\uD83D"'), '\ud83d')
+        self.assertEqual(self.loads('"\\uD83D"'), '\ud83d')
+        self.assertEqual(self.loads('"\udc0d"'), '\udc0d')
+        self.assertEqual(self.loads('"\\udc0d"'), '\udc0d')
+
     def test_unicode_preservation(self):
         self.assertEqual(type(self.loads('""')), str)
         self.assertEqual(type(self.loads('"a"')), str)