#16009: JSON error messages now provide more information. Patch by Serhiy Storchaka.

3 files changed, 86 insertions, 9 deletions

diff --git a/Lib/json/decoder.py b/Lib/json/decoder.py
index 9b7438cd5b..7e5a099b5f 100644
--- a/Lib/json/decoder.py
+++ b/Lib/json/decoder.py
@@ -188,8 +188,8 @@ def JSONObject(s_and_end, strict, scan_once, object_hook, object_pairs_hook,
 
         try:
             value, end = scan_once(s, end)
-        except StopIteration:
-            raise ValueError(errmsg("Expecting object", s, end))
+        except StopIteration as err:
+            raise ValueError(errmsg("Expecting value", s, err.value)) from None
         pairs_append((key, value))
         try:
             nextchar = s[end]
@@ -232,8 +232,8 @@ def JSONArray(s_and_end, scan_once, _w=WHITESPACE.match, _ws=WHITESPACE_STR):
     while True:
         try:
             value, end = scan_once(s, end)
-        except StopIteration:
-            raise ValueError(errmsg("Expecting object", s, end))
+        except StopIteration as err:
+            raise ValueError(errmsg("Expecting value", s, err.value)) from None
         _append(value)
         nextchar = s[end:end + 1]
         if nextchar in _ws:
@@ -243,7 +243,7 @@ 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))
+            raise ValueError(errmsg("Expecting ',' delimiter", s, end - 1))
         try:
             if s[end] in _ws:
                 end += 1
@@ -358,6 +358,6 @@ class JSONDecoder(object):
         """
         try:
             obj, end = self.scan_once(s, idx)
-        except StopIteration:
-            raise ValueError("No JSON object could be decoded")
+        except StopIteration as err:
+            raise ValueError(errmsg("Expecting value", s, err.value)) from None
         return obj, end
diff --git a/Lib/json/scanner.py b/Lib/json/scanner.py
index 23eef61b94..86426cde1a 100644
--- a/Lib/json/scanner.py
+++ b/Lib/json/scanner.py
@@ -29,7 +29,7 @@ def py_make_scanner(context):
         try:
             nextchar = string[idx]
         except IndexError:
-            raise StopIteration
+            raise StopIteration(idx)
 
         if nextchar == '"':
             return parse_string(string, idx + 1, strict)
@@ -60,7 +60,7 @@ def py_make_scanner(context):
         elif nextchar == '-' and string[idx:idx + 9] == '-Infinity':
             return parse_constant('-Infinity'), idx + 9
         else:
-            raise StopIteration
+            raise StopIteration(idx)
 
     def scan_once(string, idx):
         try:
diff --git a/Lib/test/json_tests/test_fail.py b/Lib/test/json_tests/test_fail.py
index 7809056a73..a2dc29a29d 100644
--- a/Lib/test/json_tests/test_fail.py
+++ b/Lib/test/json_tests/test_fail.py
@@ -1,4 +1,5 @@
 from test.json_tests import PyTest, CTest
+import re
 
 # 2007-10-05
 JSONDOCS = [
@@ -100,6 +101,82 @@ class TestFail:
         #This is for python encoder
         self.assertRaises(TypeError, self.dumps, data, indent=True)
 
+    def test_truncated_input(self):
+        test_cases = [
+            ('', 'Expecting value', 0),
+            ('[', 'Expecting value', 1),
+            ('[42', "Expecting ',' delimiter", 3),
+            ('[42,', 'Expecting value', 4),
+            ('["', 'Unterminated string starting at', 1),
+            ('["spam', 'Unterminated string starting at', 1),
+            ('["spam"', "Expecting ',' delimiter", 7),
+            ('["spam",', 'Expecting value', 8),
+            ('{', 'Expecting property name enclosed in double quotes', 1),
+            ('{"', 'Unterminated string starting at', 1),
+            ('{"spam', 'Unterminated string starting at', 1),
+            ('{"spam"', "Expecting ':' delimiter", 7),
+            ('{"spam":', 'Expecting value', 8),
+            ('{"spam":42', "Expecting ',' delimiter", 10),
+            ('{"spam":42,', 'Expecting property name enclosed in double quotes', 11),
+        ]
+        test_cases += [
+            ('"', 'Unterminated string starting at', 0),
+            ('"spam', 'Unterminated string starting at', 0),
+        ]
+        for data, msg, idx in test_cases:
+            self.assertRaisesRegex(ValueError,
+                r'^{0}: line 1 column {1} \(char {1}\)'.format(
+                    re.escape(msg), idx),
+                self.loads, data)
+
+    def test_unexpected_data(self):
+        test_cases = [
+            ('[,', 'Expecting value', 1),
+            ('{"spam":[}', 'Expecting value', 9),
+            ('[42:', "Expecting ',' delimiter", 3),
+            ('[42 "spam"', "Expecting ',' delimiter", 4),
+            ('[42,]', 'Expecting value', 4),
+            ('{"spam":[42}', "Expecting ',' delimiter", 11),
+            ('["]', 'Unterminated string starting at', 1),
+            ('["spam":', "Expecting ',' delimiter", 7),
+            ('["spam",]', 'Expecting value', 8),
+            ('{:', 'Expecting property name enclosed in double quotes', 1),
+            ('{,', 'Expecting property name enclosed in double quotes', 1),
+            ('{42', 'Expecting property name enclosed in double quotes', 1),
+            ('[{]', 'Expecting property name enclosed in double quotes', 2),
+            ('{"spam",', "Expecting ':' delimiter", 7),
+            ('{"spam"}', "Expecting ':' delimiter", 7),
+            ('[{"spam"]', "Expecting ':' delimiter", 8),
+            ('{"spam":}', 'Expecting value', 8),
+            ('[{"spam":]', 'Expecting value', 9),
+            ('{"spam":42 "ham"', "Expecting ',' delimiter", 11),
+            ('[{"spam":42]', "Expecting ',' delimiter", 11),
+            ('{"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} \(char {1}\)'.format(
+                    re.escape(msg), idx),
+                self.loads, data)
+
+    def test_extra_data(self):
+        test_cases = [
+            ('[]]', 'Extra data', 2),
+            ('{}}', 'Extra data', 2),
+            ('[],[]', 'Extra data', 2),
+            ('{},{}', 'Extra data', 2),
+        ]
+        test_cases += [
+            ('42,"spam"', 'Extra data', 2),
+            ('"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' \(char {1} - {2}\)'.format(
+                    re.escape(msg), idx, len(data)),
+                self.loads, data)
+
 
 class TestPyFail(TestFail, PyTest): pass
 class TestCFail(TestFail, CTest): pass