Issue #19361: JSON decoder now raises JSONDecodeError instead of ValueError.

Doc/library/json.rst

@@ -250,7 +250,7 @@ Basic Usage
    will be passed to the constructor of the class.
 
    If the data being deserialized is not a valid JSON document, a
-   :exc:`ValueError` will be raised.
+   :exc:`JSONDecodeError` will be raised.
 
 .. function:: loads(s, encoding=None, cls=None, object_hook=None, parse_float=None, parse_int=None, parse_constant=None, object_pairs_hook=None, **kw)
 
@@ -261,7 +261,7 @@ Basic Usage
    *encoding* which is ignored and deprecated.
 
    If the data being deserialized is not a valid JSON document, a
-   :exc:`ValueError` will be raised.
+   :exc:`JSONDecodeError` will be raised.
 
 Encoders and Decoders
 ---------------------
@@ -334,13 +334,16 @@ Encoders and Decoders
    ``'\n'``, ``'\r'`` and ``'\0'``.
 
    If the data being deserialized is not a valid JSON document, a
-   :exc:`ValueError` will be raised.
+   :exc:`JSONDecodeError` will be raised.
 
    .. method:: decode(s)
 
       Return the Python representation of *s* (a :class:`str` instance
       containing a JSON document)
 
+      :exc:`JSONDecodeError` will be raised if the given JSON document is not
+      valid.
+
    .. method:: raw_decode(s)
 
       Decode a JSON document from *s* (a :class:`str` beginning with a
@@ -469,6 +472,36 @@ Encoders and Decoders
                 mysocket.write(chunk)
 
 
+Exceptions
+----------
+
+.. exception:: JSONDecodeError(msg, doc, pos, end=None)
+
+    Subclass of :exc:`ValueError` with the following additional attributes:
+
+    .. attribute:: msg
+
+        The unformatted error message.
+
+    .. attribute:: doc
+
+        The JSON document being parsed.
+
+    .. attribute:: pos
+
+        The start index of *doc* where parsing failed.
+
+    .. attribute:: lineno
+
+        The line corresponding to *pos*.
+
+    .. attribute:: colno
+
+        The column corresponding to *pos*.
+
+   .. versionadded:: 3.5
+
+
 Standard Compliance and Interoperability
 ----------------------------------------
 

Doc/whatsnew/3.5.rst

@@ -230,6 +230,9 @@ json
   of dictionaries alphabetically by key.  (Contributed by Berker Peksag in
   :issue:`21650`.)
 
+* JSON decoder now raises :exc:`json.JSONDecodeError` instead of
+  :exc:`ValueError`.   (Contributed by Serhiy Storchaka in :issue:`19361`.)
+
 os
 --
 

Lib/json/__init__.py

@@ -98,12 +98,12 @@ Using json.tool from the shell to validate and pretty-print::
 __version__ = '2.0.9'
 __all__ = [
     'dump', 'dumps', 'load', 'loads',
-    'JSONDecoder', 'JSONEncoder',
+    'JSONDecoder', 'JSONDecodeError', 'JSONEncoder',
 ]
 
 __author__ = 'Bob Ippolito <bob@redivi.com>'
 
-from .decoder import JSONDecoder
+from .decoder import JSONDecoder, JSONDecodeError
 from .encoder import JSONEncoder
 
 _default_encoder = JSONEncoder(
@@ -311,7 +311,8 @@ def loads(s, encoding=None, cls=None, object_hook=None, parse_float=None,
         raise TypeError('the JSON object must be str, not {!r}'.format(
                             s.__class__.__name__))
     if s.startswith(u'\ufeff'):
-        raise ValueError("Unexpected UTF-8 BOM (decode using utf-8-sig)")
+        raise JSONDecodeError("Unexpected UTF-8 BOM (decode using utf-8-sig)",
+                              s, 0)
     if (cls is None and object_hook is None and
             parse_int is None and parse_float is None and
             parse_constant is None and object_pairs_hook is None and not kw):

Lib/json/decoder.py

@@ -8,7 +8,7 @@ try:
 except ImportError:
     c_scanstring = None
 
-__all__ = ['JSONDecoder']
+__all__ = ['JSONDecoder', 'JSONDecodeError']
 
 FLAGS = re.VERBOSE | re.MULTILINE | re.DOTALL
 
@@ -17,32 +17,30 @@ PosInf = float('inf')
 NegInf = float('-inf')
 
 
-def linecol(doc, pos):
-    if isinstance(doc, bytes):
-        newline = b'\n'
-    else:
-        newline = '\n'
-    lineno = doc.count(newline, 0, pos) + 1
-    if lineno == 1:
-        colno = pos + 1
-    else:
-        colno = pos - doc.rindex(newline, 0, pos)
-    return lineno, colno
-
-
-def errmsg(msg, doc, pos, end=None):
-    # Note that this function is called from _json
-    lineno, colno = linecol(doc, pos)
-    if end is None:
-        fmt = '{0}: line {1} column {2} (char {3})'
-        return fmt.format(msg, lineno, colno, pos)
-        #fmt = '%s: line %d column %d (char %d)'
-        #return fmt % (msg, lineno, colno, pos)
-    endlineno, endcolno = linecol(doc, end)
-    fmt = '{0}: line {1} column {2} - line {3} column {4} (char {5} - {6})'
-    return fmt.format(msg, lineno, colno, endlineno, endcolno, pos, end)
-    #fmt = '%s: line %d column %d - line %d column %d (char %d - %d)'
-    #return fmt % (msg, lineno, colno, endlineno, endcolno, pos, end)
+class JSONDecodeError(ValueError):
+    """Subclass of ValueError with the following additional properties:
+
+    msg: The unformatted error message
+    doc: The JSON document being parsed
+    pos: The start index of doc where parsing failed
+    lineno: The line corresponding to pos
+    colno: The column corresponding to pos
+
+    """
+    # Note that this exception is used from _json
+    def __init__(self, msg, doc, pos):
+        lineno = doc.count('\n', 0, pos) + 1
+        colno = pos - doc.rfind('\n', 0, pos)
+        errmsg = '%s: line %d column %d (char %d)' % (msg, lineno, colno, pos)
+        ValueError.__init__(self, errmsg)
+        self.msg = msg
+        self.doc = doc
+        self.pos = pos
+        self.lineno = lineno
+        self.colno = colno
+
+    def __reduce__(self):
+        return self.__class__, (self.msg, self.doc, self.pos)
 
 
 _CONSTANTS = {
@@ -66,7 +64,7 @@ def _decode_uXXXX(s, pos):
         except ValueError:
             pass
     msg = "Invalid \\uXXXX escape"
-    raise ValueError(errmsg(msg, s, pos))
+    raise JSONDecodeError(msg, s, pos)
 
 def py_scanstring(s, end, strict=True,
         _b=BACKSLASH, _m=STRINGCHUNK.match):
@@ -84,8 +82,7 @@ def py_scanstring(s, end, strict=True,
     while 1:
         chunk = _m(s, end)
         if chunk is None:
-            raise ValueError(
-                errmsg("Unterminated string starting at", s, begin))
+            raise JSONDecodeError("Unterminated string starting at", s, begin)
         end = chunk.end()
         content, terminator = chunk.groups()
         # Content is contains zero or more unescaped string characters
@@ -99,22 +96,21 @@ def py_scanstring(s, end, strict=True,
             if strict:
                 #msg = "Invalid control character %r at" % (terminator,)
                 msg = "Invalid control character {0!r} at".format(terminator)
-                raise ValueError(errmsg(msg, s, end))
+                raise JSONDecodeError(msg, s, end)
             else:
                 _append(terminator)
                 continue
         try:
             esc = s[end]
         except IndexError:
-            raise ValueError(
-                errmsg("Unterminated string starting at", s, begin))
+            raise JSONDecodeError("Unterminated string starting at", s, begin)
         # If not a unicode escape sequence, must be in the lookup table
         if esc != 'u':
             try:
                 char = _b[esc]
             except KeyError:
                 msg = "Invalid \\escape: {0!r}".format(esc)
-                raise ValueError(errmsg(msg, s, end))
+                raise JSONDecodeError(msg, s, end)
             end += 1
         else:
             uni = _decode_uXXXX(s, end)
@@ -163,8 +159,8 @@ def JSONObject(s_and_end, strict, scan_once, object_hook, object_pairs_hook,
                 pairs = object_hook(pairs)
             return pairs, end + 1
         elif nextchar != '"':
-            raise ValueError(errmsg(
-                "Expecting property name enclosed in double quotes", s, end))
+            raise JSONDecodeError(
+                "Expecting property name enclosed in double quotes", s, end)
     end += 1
     while True:
         key, end = scanstring(s, end, strict)
@@ -174,7 +170,7 @@ def JSONObject(s_and_end, strict, scan_once, object_hook, object_pairs_hook,
         if s[end:end + 1] != ':':
             end = _w(s, end).end()
             if s[end:end + 1] != ':':
-                raise ValueError(errmsg("Expecting ':' delimiter", s, end))
+                raise JSONDecodeError("Expecting ':' delimiter", s, end)
         end += 1
 
         try:
@@ -188,7 +184,7 @@ def JSONObject(s_and_end, strict, scan_once, object_hook, object_pairs_hook,
         try:
             value, end = scan_once(s, end)
         except StopIteration as err:
-            raise ValueError(errmsg("Expecting value", s, err.value)) from None
+            raise JSONDecodeError("Expecting value", s, err.value) from None
         pairs_append((key, value))
         try:
             nextchar = s[end]
@@ -202,13 +198,13 @@ def JSONObject(s_and_end, strict, scan_once, object_hook, object_pairs_hook,
         if nextchar == '}':
             break
         elif nextchar != ',':
-            raise ValueError(errmsg("Expecting ',' delimiter", s, end - 1))
+            raise JSONDecodeError("Expecting ',' delimiter", s, end - 1)
         end = _w(s, end).end()
         nextchar = s[end:end + 1]
         end += 1
         if nextchar != '"':
-            raise ValueError(errmsg(
-                "Expecting property name enclosed in double quotes", s, end - 1))
+            raise JSONDecodeError(
+                "Expecting property name enclosed in double quotes", s, end - 1)
     if object_pairs_hook is not None:
         result = object_pairs_hook(pairs)
         return result, end
@@ -232,7 +228,7 @@ def JSONArray(s_and_end, scan_once, _w=WHITESPACE.match, _ws=WHITESPACE_STR):
         try:
             value, end = scan_once(s, end)
         except StopIteration as err:
-            raise ValueError(errmsg("Expecting value", s, err.value)) from None
+            raise JSONDecodeError("Expecting value", s, err.value) from None
         _append(value)
         nextchar = s[end:end + 1]
         if nextchar in _ws:
@@ -242,7 +238,7 @@ def JSONArray(s_and_end, scan_once, _w=WHITESPACE.match, _ws=WHITESPACE_STR):
         if nextchar == ']':
             break
         elif nextchar != ',':
-            raise ValueError(errmsg("Expecting ',' delimiter", s, end - 1))
+            raise JSONDecodeError("Expecting ',' delimiter", s, end - 1)
         try:
             if s[end] in _ws:
                 end += 1
@@ -343,7 +339,7 @@ class JSONDecoder(object):
         obj, end = self.raw_decode(s, idx=_w(s, 0).end())
         end = _w(s, end).end()
         if end != len(s):
-            raise ValueError(errmsg("Extra data", s, end, len(s)))
+            raise JSONDecodeError("Extra data", s, end)
         return obj
 
     def raw_decode(self, s, idx=0):
@@ -358,5 +354,5 @@ class JSONDecoder(object):
         try:
             obj, end = self.scan_once(s, idx)
         except StopIteration as err:
-            raise ValueError(errmsg("Expecting value", s, err.value)) from None
+            raise JSONDecodeError("Expecting value", s, err.value) from None
         return obj, end

Lib/test/test_json/__init__.py

@@ -9,12 +9,15 @@ from test import support
 # import json with and without accelerations
 cjson = support.import_fresh_module('json', fresh=['_json'])
 pyjson = support.import_fresh_module('json', blocked=['_json'])
+# JSONDecodeError is cached inside the _json module
+cjson.JSONDecodeError = cjson.decoder.JSONDecodeError = json.JSONDecodeError
 
 # create two base classes that will be used by the other tests
 class PyTest(unittest.TestCase):
     json = pyjson
     loads = staticmethod(pyjson.loads)
     dumps = staticmethod(pyjson.dumps)
+    JSONDecodeError = staticmethod(pyjson.JSONDecodeError)
 
 @unittest.skipUnless(cjson, 'requires _json')
 class CTest(unittest.TestCase):
@@ -22,6 +25,7 @@ class CTest(unittest.TestCase):
         json = cjson
         loads = staticmethod(cjson.loads)
         dumps = staticmethod(cjson.dumps)
+        JSONDecodeError = staticmethod(cjson.JSONDecodeError)
 
 # test PyTest and CTest checking if the functions come from the right module
 class TestPyTest(PyTest):

Lib/test/test_json/test_decode.py

@@ -63,12 +63,12 @@ class TestDecode:
     def test_extra_data(self):
         s = '[1, 2, 3]5'
         msg = 'Extra data'
-        self.assertRaisesRegex(ValueError, msg, self.loads, s)
+        self.assertRaisesRegex(self.JSONDecodeError, msg, self.loads, s)
 
     def test_invalid_escape(self):
         s = '["abc\\y"]'
         msg = 'escape'
-        self.assertRaisesRegex(ValueError, msg, self.loads, s)
+        self.assertRaisesRegex(self.JSONDecodeError, msg, self.loads, s)
 
     def test_invalid_input_type(self):
         msg = 'the JSON object must be str'
@@ -80,10 +80,10 @@ class TestDecode:
     def test_string_with_utf8_bom(self):
         # see #18958
         bom_json = "[1,2,3]".encode('utf-8-sig').decode('utf-8')
-        with self.assertRaises(ValueError) as cm:
+        with self.assertRaises(self.JSONDecodeError) as cm:
             self.loads(bom_json)
         self.assertIn('BOM', str(cm.exception))
-        with self.assertRaises(ValueError) as cm:
+        with self.assertRaises(self.JSONDecodeError) as cm:
             self.json.load(StringIO(bom_json))
         self.assertIn('BOM', str(cm.exception))
         # make sure that the BOM is not detected in the middle of a string

Lib/test/test_json/test_fail.py

@@ -87,7 +87,7 @@ class TestFail:
                 continue
             try:
                 self.loads(doc)
-            except ValueError:
+            except self.JSONDecodeError:
                 pass
             else:
                 self.fail("Expected failure for fail{0}.json: {1!r}".format(idx, doc))
@@ -124,10 +124,16 @@ class TestFail:
             ('"spam', 'Unterminated string starting at', 0),
         ]
         for data, msg, idx in test_cases:
-            self.assertRaisesRegex(ValueError,
-                r'^{0}: line 1 column {1} \(char {2}\)'.format(
-                    re.escape(msg), idx + 1, idx),
-                self.loads, data)
+            with self.assertRaises(self.JSONDecodeError) as cm:
+                self.loads(data)
+            err = cm.exception
+            self.assertEqual(err.msg, msg)
+            self.assertEqual(err.pos, idx)
+            self.assertEqual(err.lineno, 1)
+            self.assertEqual(err.colno, idx + 1)
+            self.assertEqual(str(err),
+                             '%s: line 1 column %d (char %d)' %
+                             (msg, idx + 1, idx))
 
     def test_unexpected_data(self):
         test_cases = [
@@ -154,10 +160,16 @@ class TestFail:
             ('{"spam":42,}', 'Expecting property name enclosed in double quotes', 11),
         ]
         for data, msg, idx in test_cases:
-            self.assertRaisesRegex(ValueError,
-                r'^{0}: line 1 column {1} \(char {2}\)'.format(
-                    re.escape(msg), idx + 1, idx),
-                self.loads, data)
+            with self.assertRaises(self.JSONDecodeError) as cm:
+                self.loads(data)
+            err = cm.exception
+            self.assertEqual(err.msg, msg)
+            self.assertEqual(err.pos, idx)
+            self.assertEqual(err.lineno, 1)
+            self.assertEqual(err.colno, idx + 1)
+            self.assertEqual(str(err),
+                             '%s: line 1 column %d (char %d)' %
+                             (msg, idx + 1, idx))
 
     def test_extra_data(self):
         test_cases = [
@@ -171,11 +183,16 @@ class TestFail:
             ('"spam",42', 'Extra data', 6),
         ]
         for data, msg, idx in test_cases:
-            self.assertRaisesRegex(ValueError,
-                r'^{0}: line 1 column {1} - line 1 column {2}'
-                r' \(char {3} - {4}\)'.format(
-                    re.escape(msg), idx + 1, len(data) + 1, idx, len(data)),
-                self.loads, data)
+            with self.assertRaises(self.JSONDecodeError) as cm:
+                self.loads(data)
+            err = cm.exception
+            self.assertEqual(err.msg, msg)
+            self.assertEqual(err.pos, idx)
+            self.assertEqual(err.lineno, 1)
+            self.assertEqual(err.colno, idx + 1)
+            self.assertEqual(str(err),
+                             '%s: line 1 column %d (char %d)' %
+                             (msg, idx + 1, idx))
 
     def test_linecol(self):
         test_cases = [
@@ -185,10 +202,16 @@ class TestFail:
             ('\n  \n\n     !', 4, 6, 10),
         ]
         for data, line, col, idx in test_cases:
-            self.assertRaisesRegex(ValueError,
-                r'^Expecting value: line {0} column {1}'
-                r' \(char {2}\)$'.format(line, col, idx),
-                self.loads, data)
+            with self.assertRaises(self.JSONDecodeError) as cm:
+                self.loads(data)
+            err = cm.exception
+            self.assertEqual(err.msg, 'Expecting value')
+            self.assertEqual(err.pos, idx)
+            self.assertEqual(err.lineno, line)
+            self.assertEqual(err.colno, col)
+            self.assertEqual(str(err),
+                             'Expecting value: line %s column %d (char %d)' %
+                             (line, col, idx))
 
 class TestPyFail(TestFail, PyTest): pass
 class TestCFail(TestFail, CTest): pass

Lib/test/test_json/test_scanstring.py

@@ -129,7 +129,7 @@ class TestScanstring:
             '"\\ud834\\u0X20"',
         ]
         for s in bad_escapes:
-            with self.assertRaises(ValueError, msg=s):
+            with self.assertRaises(self.JSONDecodeError, msg=s):
                 scanstring(s, 1, True)
 
     def test_overflow(self):

Misc/NEWS

@@ -218,6 +218,8 @@ Core and Builtins
 Library
 -------
 
+- Issue #19361: JSON decoder now raises JSONDecodeError instead of ValueError.
+
 - Issue #18518: timeit now rejects statements which can't be compiled outside
   a function or a loop (e.g. "return" or "break").
 

Modules/_json.c

@@ -312,23 +312,22 @@ escape_unicode(PyObject *pystr)
 static void
 raise_errmsg(char *msg, PyObject *s, Py_ssize_t end)
 {
-    /* Use the Python function json.decoder.errmsg to raise a nice
-    looking ValueError exception */
-    static PyObject *errmsg_fn = NULL;
-    PyObject *pymsg;
-    if (errmsg_fn == NULL) {
+    /* Use JSONDecodeError exception to raise a nice looking ValueError subclass */
+    static PyObject *JSONDecodeError = NULL;
+    PyObject *exc;
+    if (JSONDecodeError == NULL) {
         PyObject *decoder = PyImport_ImportModule("json.decoder");
         if (decoder == NULL)
             return;
-        errmsg_fn = PyObject_GetAttrString(decoder, "errmsg");
+        JSONDecodeError = PyObject_GetAttrString(decoder, "JSONDecodeError");
         Py_DECREF(decoder);
-        if (errmsg_fn == NULL)
+        if (JSONDecodeError == NULL)
             return;
     }
-    pymsg = PyObject_CallFunction(errmsg_fn, "(zOn)", msg, s, end);
-    if (pymsg) {
-        PyErr_SetObject(PyExc_ValueError, pymsg);
-        Py_DECREF(pymsg);
+    exc = PyObject_CallFunction(JSONDecodeError, "(zOn)", msg, s, end);
+    if (exc) {
+        PyErr_SetObject(JSONDecodeError, exc);
+        Py_DECREF(exc);
     }
 }