From 4c88a67b124f703b9238d4900d292de371a25cf7 Mon Sep 17 00:00:00 2001
From: Hugo van Kemenade <1324225+hugovk@users.noreply.github.com>
Date: Fri, 9 Feb 2024 18:29:11 +0200
Subject: [PATCH 1/7] Add tests to increase json coverage

---
 Lib/test/test_json/test_decode.py            | 17 +++++-
 Lib/test/test_json/test_detect_encoding.py   | 38 +++++++++++++
 Lib/test/test_json/test_encode_basestring.py | 56 ++++++++++++++++++++
 3 files changed, 109 insertions(+), 2 deletions(-)
 create mode 100644 Lib/test/test_json/test_detect_encoding.py
 create mode 100644 Lib/test/test_json/test_encode_basestring.py

diff --git a/Lib/test/test_json/test_decode.py b/Lib/test/test_json/test_decode.py
index 124045b13184b3..150811e18789ea 100644
--- a/Lib/test/test_json/test_decode.py
+++ b/Lib/test/test_json/test_decode.py
@@ -8,14 +8,27 @@
 class TestDecode:
     def test_decimal(self):
         rval = self.loads('1.1', parse_float=decimal.Decimal)
-        self.assertTrue(isinstance(rval, decimal.Decimal))
+        self.assertIsInstance(rval, decimal.Decimal)
         self.assertEqual(rval, decimal.Decimal('1.1'))
 
     def test_float(self):
         rval = self.loads('1', parse_int=float)
-        self.assertTrue(isinstance(rval, float))
+        self.assertIsInstance(rval, float)
         self.assertEqual(rval, 1.0)
 
+    def test_bytes(self):
+        self.assertEqual(self.loads(b"1"), 1)
+
+    def test_constant(self):
+        for constant, expected in [
+            ("Infinity", "INFINITY"),
+            ("-Infinity", "-INFINITY"),
+            ("NaN", "NAN"),
+        ]:
+            self.assertEqual(
+                self.loads(constant, parse_constant=str.upper), expected
+            )
+
     def test_empty_objects(self):
         self.assertEqual(self.loads('{}'), {})
         self.assertEqual(self.loads('[]'), [])
diff --git a/Lib/test/test_json/test_detect_encoding.py b/Lib/test/test_json/test_detect_encoding.py
new file mode 100644
index 00000000000000..b92e4a335ab29c
--- /dev/null
+++ b/Lib/test/test_json/test_detect_encoding.py
@@ -0,0 +1,38 @@
+import codecs
+
+from test.test_json import PyTest, CTest
+
+
+class TestDetectEncoding:
+    def test_utf32(self):
+        # Arrange
+        for test_input, expected_encoding in [
+            (codecs.BOM_UTF32_BE + "abc".encode("utf-32-be"), "utf-32"),
+            (codecs.BOM_UTF32_LE + "abc".encode("utf-32-le"), "utf-32"),
+            (codecs.BOM_UTF16_BE + "abc".encode("utf-16-be"), "utf-16"),
+            (codecs.BOM_UTF16_LE + "abc".encode("utf-16-le"), "utf-16"),
+            (codecs.BOM_UTF8 + "abc".encode("utf-8-sig"), "utf-8-sig"),
+            (b"\x00\x00\x00a\x00\x00\x00b\x00\x00\x00c", "utf-32-be"),
+            (b"\x00a\x00b\x00c", "utf-16-be"),
+            (b"a\x00\x00\x00b\x00\x00\x00c\x00\x00\x00", "utf-32-le"),
+            (b"a\x00\x00b\x00c\x00", "utf-16-le"),
+            (b"a\x00b\x00c\x00", "utf-16-le"),
+            (b"\x00a", "utf-16-be"),
+            (b"a\x00", "utf-16-le"),
+            (b"abcd", "utf-8"),
+            (b"abc", "utf-8"),
+            (b"ab", "utf-8"),
+        ]:
+            # Act
+            result = self.json.detect_encoding(test_input)
+
+            # Assert
+            self.assertEqual(result, expected_encoding)
+
+
+class TestPyTestDetectEncoding(TestDetectEncoding, PyTest):
+    pass
+
+
+class TestCTestDetectEncoding(TestDetectEncoding, CTest):
+    pass
diff --git a/Lib/test/test_json/test_encode_basestring.py b/Lib/test/test_json/test_encode_basestring.py
new file mode 100644
index 00000000000000..2ae1ce64707fe8
--- /dev/null
+++ b/Lib/test/test_json/test_encode_basestring.py
@@ -0,0 +1,56 @@
+from test.test_json import PyTest, CTest
+from test.support import bigaddrspacetest
+
+
+CASES = [
+    (
+        '/\\"\ucafe\ubabe\uab98\ufcde\ubcda\uef4a\x08\x0c\n\r\t`1~!@#$%^&*()_+-=[]{}|;:\',./<>?',
+        '"/\\\\\\"\ucafe\ubabe\uab98\ufcde\ubcda\uef4a\\b\\f\\n\\r\\t`1~!@#$%^&*()_+-=[]{}|;:\',./<>?"',
+    ),
+    (
+        '\u0123\u4567\u89ab\ucdef\uabcd\uef4a',
+        '"\u0123\u4567\u89ab\ucdef\uabcd\uef4a"',
+    ),
+    ('controls', '"controls"'),
+    ('\x08\x0c\n\r\t', '"\\b\\f\\n\\r\\t"'),
+    (
+        '{"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', '"\U0001d120"'),
+    ('\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 TestEncodeBasestring:
+    def test_encode_basestring(self):
+        filename = self.json.encoder.encode_basestring.__name__
+        for input_string, expect in CASES:
+            result = self.json.encoder.encode_basestring(input_string)
+            self.assertEqual(
+                result,
+                expect,
+                '{0!r} != {1!r} for {2}({3!r})'.format(
+                    result, expect, filename, input_string
+                ),
+            )
+
+
+class TestPyEncodeBasestring(TestEncodeBasestring, PyTest):
+    pass
+
+
+class TestCEncodeBasestring(TestEncodeBasestring, CTest):
+    @bigaddrspacetest
+    def test_overflow(self):
+        size = (2**32) // 6 + 1
+        s = "\x00" * size
+        with self.assertRaises(OverflowError):
+            self.json.encoder.encode_basestring(s)

From 5ac05a9b407912481af6b3b143907af77fef45d3 Mon Sep 17 00:00:00 2001
From: Hugo van Kemenade <1324225+hugovk@users.noreply.github.com>
Date: Tue, 26 Mar 2024 17:00:45 +0200
Subject: [PATCH 2/7] Use f-strings

---
 Lib/test/test_json/test_decode.py                  | 2 +-
 Lib/test/test_json/test_encode_basestring.py       | 4 +---
 Lib/test/test_json/test_encode_basestring_ascii.py | 3 +--
 Lib/test/test_json/test_fail.py                    | 2 +-
 Lib/test/test_json/test_unicode.py                 | 8 ++++----
 5 files changed, 8 insertions(+), 11 deletions(-)

diff --git a/Lib/test/test_json/test_decode.py b/Lib/test/test_json/test_decode.py
index 150811e18789ea..8b29a0985954b8 100644
--- a/Lib/test/test_json/test_decode.py
+++ b/Lib/test/test_json/test_decode.py
@@ -101,7 +101,7 @@ def test_string_with_utf8_bom(self):
             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
-        bom_in_str = '"{}"'.format(''.encode('utf-8-sig').decode('utf-8'))
+        bom_in_str = f"\"{''.encode('utf-8-sig').decode('utf-8')}\""
         self.assertEqual(self.loads(bom_in_str), '\ufeff')
         self.assertEqual(self.json.load(StringIO(bom_in_str)), '\ufeff')
 
diff --git a/Lib/test/test_json/test_encode_basestring.py b/Lib/test/test_json/test_encode_basestring.py
index 2ae1ce64707fe8..d305821d46f6e3 100644
--- a/Lib/test/test_json/test_encode_basestring.py
+++ b/Lib/test/test_json/test_encode_basestring.py
@@ -37,9 +37,7 @@ def test_encode_basestring(self):
             self.assertEqual(
                 result,
                 expect,
-                '{0!r} != {1!r} for {2}({3!r})'.format(
-                    result, expect, filename, input_string
-                ),
+                f'{result!r} != {expect!r} for {filename}({input_string!r})',
             )
 
 
diff --git a/Lib/test/test_json/test_encode_basestring_ascii.py b/Lib/test/test_json/test_encode_basestring_ascii.py
index 4bbc6c71489a83..6a39b72a09df35 100644
--- a/Lib/test/test_json/test_encode_basestring_ascii.py
+++ b/Lib/test/test_json/test_encode_basestring_ascii.py
@@ -23,8 +23,7 @@ def test_encode_basestring_ascii(self):
         for input_string, expect in CASES:
             result = self.json.encoder.encode_basestring_ascii(input_string)
             self.assertEqual(result, expect,
-                '{0!r} != {1!r} for {2}({3!r})'.format(
-                    result, expect, fname, input_string))
+                f'{result!r} != {expect!r} for {fname}({input_string!r})')
 
     def test_ordered_dict(self):
         # See issue 6105
diff --git a/Lib/test/test_json/test_fail.py b/Lib/test/test_json/test_fail.py
index d6bce605e21463..a74240f1107de3 100644
--- a/Lib/test/test_json/test_fail.py
+++ b/Lib/test/test_json/test_fail.py
@@ -89,7 +89,7 @@ def test_failures(self):
             except self.JSONDecodeError:
                 pass
             else:
-                self.fail("Expected failure for fail{0}.json: {1!r}".format(idx, doc))
+                self.fail(f"Expected failure for fail{idx}.json: {doc!r}")
 
     def test_non_string_keys_dict(self):
         data = {'a' : 1, (1, 2) : 2}
diff --git a/Lib/test/test_json/test_unicode.py b/Lib/test/test_json/test_unicode.py
index 2e8bba2775256a..533894e094f7b7 100644
--- a/Lib/test/test_json/test_unicode.py
+++ b/Lib/test/test_json/test_unicode.py
@@ -20,12 +20,12 @@ def test_encoding4(self):
     def test_encoding5(self):
         u = '\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
         j = self.dumps(u, ensure_ascii=False)
-        self.assertEqual(j, '"{0}"'.format(u))
+        self.assertEqual(j, f'"{u}"')
 
     def test_encoding6(self):
         u = '\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
         j = self.dumps([u], ensure_ascii=False)
-        self.assertEqual(j, '["{0}"]'.format(u))
+        self.assertEqual(j, f'["{u}"]')
 
     def test_big_unicode_encode(self):
         u = '\U0001d120'
@@ -34,13 +34,13 @@ def test_big_unicode_encode(self):
 
     def test_big_unicode_decode(self):
         u = 'z\U0001d120x'
-        self.assertEqual(self.loads('"' + u + '"'), u)
+        self.assertEqual(self.loads(f'"{u}"'), u)
         self.assertEqual(self.loads('"z\\ud834\\udd20x"'), u)
 
     def test_unicode_decode(self):
         for i in range(0, 0xd7ff):
             u = chr(i)
-            s = '"\\u{0:04x}"'.format(i)
+            s = f'"\\u{i:04x}"'
             self.assertEqual(self.loads(s), u)
 
     def test_unicode_preservation(self):

From b305f13cfacfb3512538dc34f3bd58a96d4bd197 Mon Sep 17 00:00:00 2001
From: Hugo van Kemenade <1324225+hugovk@users.noreply.github.com>
Date: Tue, 26 Mar 2024 17:02:58 +0200
Subject: [PATCH 3/7] Test incorrect 'NaN' and 'Infinity' cases fail

---
 Lib/test/test_json/test_decode.py | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/Lib/test/test_json/test_decode.py b/Lib/test/test_json/test_decode.py
index 8b29a0985954b8..0a5d23b2e18f86 100644
--- a/Lib/test/test_json/test_decode.py
+++ b/Lib/test/test_json/test_decode.py
@@ -29,6 +29,13 @@ def test_constant(self):
                 self.loads(constant, parse_constant=str.upper), expected
             )
 
+    def test_constant_invalid_case(self):
+        for constant in [
+            "nan", "NAN", "naN", "infinity", "INFINITY", "inFiniTy"
+        ]:
+            with self.assertRaises(self.JSONDecodeError):
+                self.loads(constant)
+
     def test_empty_objects(self):
         self.assertEqual(self.loads('{}'), {})
         self.assertEqual(self.loads('[]'), [])

From d8815e142921c72f74b6319a11f332bfaaba163b Mon Sep 17 00:00:00 2001
From: Hugo van Kemenade <1324225+hugovk@users.noreply.github.com>
Date: Wed, 27 Mar 2024 17:36:30 +0200
Subject: [PATCH 4/7] Rename test

---
 Lib/test/test_json/test_decode.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Lib/test/test_json/test_decode.py b/Lib/test/test_json/test_decode.py
index 0a5d23b2e18f86..3700d9acfcb8e8 100644
--- a/Lib/test/test_json/test_decode.py
+++ b/Lib/test/test_json/test_decode.py
@@ -19,7 +19,7 @@ def test_float(self):
     def test_bytes(self):
         self.assertEqual(self.loads(b"1"), 1)
 
-    def test_constant(self):
+    def test_parse_constant(self):
         for constant, expected in [
             ("Infinity", "INFINITY"),
             ("-Infinity", "-INFINITY"),

From 5aa4e963d83b082ff47fcf14b009528d151aad37 Mon Sep 17 00:00:00 2001
From: Hugo van Kemenade <1324225+hugovk@users.noreply.github.com>
Date: Wed, 27 Mar 2024 17:37:56 +0200
Subject: [PATCH 5/7] Remove, detect_encoding not part of public API, already
 covered by test_bytes_decode

---
 Lib/test/test_json/test_detect_encoding.py | 38 ----------------------
 1 file changed, 38 deletions(-)
 delete mode 100644 Lib/test/test_json/test_detect_encoding.py

diff --git a/Lib/test/test_json/test_detect_encoding.py b/Lib/test/test_json/test_detect_encoding.py
deleted file mode 100644
index b92e4a335ab29c..00000000000000
--- a/Lib/test/test_json/test_detect_encoding.py
+++ /dev/null
@@ -1,38 +0,0 @@
-import codecs
-
-from test.test_json import PyTest, CTest
-
-
-class TestDetectEncoding:
-    def test_utf32(self):
-        # Arrange
-        for test_input, expected_encoding in [
-            (codecs.BOM_UTF32_BE + "abc".encode("utf-32-be"), "utf-32"),
-            (codecs.BOM_UTF32_LE + "abc".encode("utf-32-le"), "utf-32"),
-            (codecs.BOM_UTF16_BE + "abc".encode("utf-16-be"), "utf-16"),
-            (codecs.BOM_UTF16_LE + "abc".encode("utf-16-le"), "utf-16"),
-            (codecs.BOM_UTF8 + "abc".encode("utf-8-sig"), "utf-8-sig"),
-            (b"\x00\x00\x00a\x00\x00\x00b\x00\x00\x00c", "utf-32-be"),
-            (b"\x00a\x00b\x00c", "utf-16-be"),
-            (b"a\x00\x00\x00b\x00\x00\x00c\x00\x00\x00", "utf-32-le"),
-            (b"a\x00\x00b\x00c\x00", "utf-16-le"),
-            (b"a\x00b\x00c\x00", "utf-16-le"),
-            (b"\x00a", "utf-16-be"),
-            (b"a\x00", "utf-16-le"),
-            (b"abcd", "utf-8"),
-            (b"abc", "utf-8"),
-            (b"ab", "utf-8"),
-        ]:
-            # Act
-            result = self.json.detect_encoding(test_input)
-
-            # Assert
-            self.assertEqual(result, expected_encoding)
-
-
-class TestPyTestDetectEncoding(TestDetectEncoding, PyTest):
-    pass
-
-
-class TestCTestDetectEncoding(TestDetectEncoding, CTest):
-    pass

From 05a220cb3c57a8ed2ddab7728aaa667675dae7a7 Mon Sep 17 00:00:00 2001
From: Hugo van Kemenade <1324225+hugovk@users.noreply.github.com>
Date: Wed, 27 Mar 2024 17:39:23 +0200
Subject: [PATCH 6/7] Replace tests for encode_basestring (not part of public
 API) with test for dumps

---
 Lib/test/test_json/test_encode_basestring.py | 54 --------------------
 Lib/test/test_json/test_unicode.py           |  5 ++
 2 files changed, 5 insertions(+), 54 deletions(-)
 delete mode 100644 Lib/test/test_json/test_encode_basestring.py

diff --git a/Lib/test/test_json/test_encode_basestring.py b/Lib/test/test_json/test_encode_basestring.py
deleted file mode 100644
index d305821d46f6e3..00000000000000
--- a/Lib/test/test_json/test_encode_basestring.py
+++ /dev/null
@@ -1,54 +0,0 @@
-from test.test_json import PyTest, CTest
-from test.support import bigaddrspacetest
-
-
-CASES = [
-    (
-        '/\\"\ucafe\ubabe\uab98\ufcde\ubcda\uef4a\x08\x0c\n\r\t`1~!@#$%^&*()_+-=[]{}|;:\',./<>?',
-        '"/\\\\\\"\ucafe\ubabe\uab98\ufcde\ubcda\uef4a\\b\\f\\n\\r\\t`1~!@#$%^&*()_+-=[]{}|;:\',./<>?"',
-    ),
-    (
-        '\u0123\u4567\u89ab\ucdef\uabcd\uef4a',
-        '"\u0123\u4567\u89ab\ucdef\uabcd\uef4a"',
-    ),
-    ('controls', '"controls"'),
-    ('\x08\x0c\n\r\t', '"\\b\\f\\n\\r\\t"'),
-    (
-        '{"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', '"\U0001d120"'),
-    ('\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 TestEncodeBasestring:
-    def test_encode_basestring(self):
-        filename = self.json.encoder.encode_basestring.__name__
-        for input_string, expect in CASES:
-            result = self.json.encoder.encode_basestring(input_string)
-            self.assertEqual(
-                result,
-                expect,
-                f'{result!r} != {expect!r} for {filename}({input_string!r})',
-            )
-
-
-class TestPyEncodeBasestring(TestEncodeBasestring, PyTest):
-    pass
-
-
-class TestCEncodeBasestring(TestEncodeBasestring, CTest):
-    @bigaddrspacetest
-    def test_overflow(self):
-        size = (2**32) // 6 + 1
-        s = "\x00" * size
-        with self.assertRaises(OverflowError):
-            self.json.encoder.encode_basestring(s)
diff --git a/Lib/test/test_json/test_unicode.py b/Lib/test/test_json/test_unicode.py
index 533894e094f7b7..68629cceeb9be9 100644
--- a/Lib/test/test_json/test_unicode.py
+++ b/Lib/test/test_json/test_unicode.py
@@ -27,6 +27,11 @@ def test_encoding6(self):
         j = self.dumps([u], ensure_ascii=False)
         self.assertEqual(j, f'["{u}"]')
 
+    def test_encoding7(self):
+        u = '\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
+        j = self.dumps(u + "\n", ensure_ascii=False)
+        self.assertEqual(j, f'"{u}\\n"')
+
     def test_big_unicode_encode(self):
         u = '\U0001d120'
         self.assertEqual(self.dumps(u), '"\\ud834\\udd20"')

From b9ca3c254c0618fcacb1f2fc8d17e18db3d3b3ad Mon Sep 17 00:00:00 2001
From: Hugo van Kemenade <1324225+hugovk@users.noreply.github.com>
Date: Mon, 8 Apr 2024 17:40:26 +0300
Subject: [PATCH 7/7] Apply suggestions from code review

Co-authored-by: Petr Viktorin <encukou@gmail.com>
---
 Lib/test/test_json/test_decode.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Lib/test/test_json/test_decode.py b/Lib/test/test_json/test_decode.py
index 3700d9acfcb8e8..79fb239b35d3f2 100644
--- a/Lib/test/test_json/test_decode.py
+++ b/Lib/test/test_json/test_decode.py
@@ -108,7 +108,8 @@ def test_string_with_utf8_bom(self):
             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
-        bom_in_str = f"\"{''.encode('utf-8-sig').decode('utf-8')}\""
+        bom = ''.encode('utf-8-sig').decode('utf-8')
+        bom_in_str = f'"{bom}"'
         self.assertEqual(self.loads(bom_in_str), '\ufeff')
         self.assertEqual(self.json.load(StringIO(bom_in_str)), '\ufeff')