json-repair 0.29.1__tar.gz → 0.29.2__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {json_repair-0.29.1/src/json_repair.egg-info → json_repair-0.29.2}/PKG-INFO +1 -1
- {json_repair-0.29.1 → json_repair-0.29.2}/pyproject.toml +1 -1
- {json_repair-0.29.1 → json_repair-0.29.2}/src/json_repair/json_repair.py +30 -29
- {json_repair-0.29.1 → json_repair-0.29.2/src/json_repair.egg-info}/PKG-INFO +1 -1
- {json_repair-0.29.1 → json_repair-0.29.2}/tests/test_json_repair.py +2 -0
- {json_repair-0.29.1 → json_repair-0.29.2}/tests/test_performance.py +6 -6
- {json_repair-0.29.1 → json_repair-0.29.2}/LICENSE +0 -0
- {json_repair-0.29.1 → json_repair-0.29.2}/README.md +0 -0
- {json_repair-0.29.1 → json_repair-0.29.2}/setup.cfg +0 -0
- {json_repair-0.29.1 → json_repair-0.29.2}/src/json_repair/__init__.py +0 -0
- {json_repair-0.29.1 → json_repair-0.29.2}/src/json_repair/__main__.py +0 -0
- {json_repair-0.29.1 → json_repair-0.29.2}/src/json_repair/py.typed +0 -0
- {json_repair-0.29.1 → json_repair-0.29.2}/src/json_repair.egg-info/SOURCES.txt +0 -0
- {json_repair-0.29.1 → json_repair-0.29.2}/src/json_repair.egg-info/dependency_links.txt +0 -0
- {json_repair-0.29.1 → json_repair-0.29.2}/src/json_repair.egg-info/entry_points.txt +0 -0
- {json_repair-0.29.1 → json_repair-0.29.2}/src/json_repair.egg-info/top_level.txt +0 -0
- {json_repair-0.29.1 → json_repair-0.29.2}/tests/test_coverage.py +0 -0
@@ -3,7 +3,7 @@ requires = ["setuptools>=61.0"]
|
|
3
3
|
build-backend = "setuptools.build_meta"
|
4
4
|
[project]
|
5
5
|
name = "json_repair"
|
6
|
-
version = "0.29.
|
6
|
+
version = "0.29.2"
|
7
7
|
license = {file = "LICENSE"}
|
8
8
|
authors = [
|
9
9
|
{ name="Stefano Baccianella", email="4247706+mangiucugna@users.noreply.github.com" },
|
@@ -384,38 +384,39 @@ class JSONParser:
|
|
384
384
|
# * If we are fixing missing quotes in an object, when it finds the special terminators
|
385
385
|
char = self.get_char_at()
|
386
386
|
while char and char != rstring_delimiter:
|
387
|
-
if
|
388
|
-
|
389
|
-
|
390
|
-
)
|
387
|
+
if (
|
388
|
+
missing_quotes
|
389
|
+
and self.get_context() == "object_key"
|
390
|
+
and (char == ":" or char.isspace())
|
391
|
+
):
|
392
|
+
self.log(
|
393
|
+
"While parsing a string missing the left delimiter in object key context, we found a :, stopping here",
|
394
|
+
"info",
|
395
|
+
)
|
396
|
+
break
|
397
|
+
if self.get_context() == "object_value" and char in [",", "}"]:
|
398
|
+
rstring_delimiter_missing = True
|
399
|
+
# check if this is a case in which the closing comma is NOT missing instead
|
400
|
+
i = 1
|
401
|
+
next_c = self.get_char_at(i)
|
402
|
+
while next_c and next_c != rstring_delimiter:
|
403
|
+
i += 1
|
404
|
+
next_c = self.get_char_at(i)
|
405
|
+
if next_c:
|
406
|
+
i += 1
|
407
|
+
next_c = self.get_char_at(i)
|
408
|
+
# found a delimiter, now we need to check that is followed strictly by a comma or brace
|
409
|
+
while next_c and next_c.isspace():
|
410
|
+
i += 1
|
411
|
+
next_c = self.get_char_at(i)
|
412
|
+
if next_c and next_c in [",", "}"]:
|
413
|
+
rstring_delimiter_missing = False
|
414
|
+
if rstring_delimiter_missing:
|
391
415
|
self.log(
|
392
|
-
"While parsing a string missing the left delimiter in object
|
416
|
+
"While parsing a string missing the left delimiter in object value context, we found a , or } and we couldn't determine that a right delimiter was present. Stopping here",
|
393
417
|
"info",
|
394
418
|
)
|
395
419
|
break
|
396
|
-
elif self.get_context() == "object_value" and char in [",", "}"]:
|
397
|
-
rstring_delimiter_missing = True
|
398
|
-
# check if this is a case in which the closing comma is NOT missing instead
|
399
|
-
i = 1
|
400
|
-
next_c = self.get_char_at(i)
|
401
|
-
while next_c and next_c != rstring_delimiter:
|
402
|
-
i += 1
|
403
|
-
next_c = self.get_char_at(i)
|
404
|
-
if next_c:
|
405
|
-
i += 1
|
406
|
-
next_c = self.get_char_at(i)
|
407
|
-
# found a delimiter, now we need to check that is followed strictly by a comma or brace
|
408
|
-
while next_c and next_c.isspace():
|
409
|
-
i += 1
|
410
|
-
next_c = self.get_char_at(i)
|
411
|
-
if next_c and next_c in [",", "}"]:
|
412
|
-
rstring_delimiter_missing = False
|
413
|
-
if rstring_delimiter_missing:
|
414
|
-
self.log(
|
415
|
-
"While parsing a string missing the left delimiter in object value context, we found a , or } and we couldn't determine that a right delimiter was present. Stopping here",
|
416
|
-
"info",
|
417
|
-
)
|
418
|
-
break
|
419
420
|
string_acc += char
|
420
421
|
self.index += 1
|
421
422
|
char = self.get_char_at()
|
@@ -507,7 +508,7 @@ class JSONParser:
|
|
507
508
|
if next_c == "}":
|
508
509
|
# OK this is valid then
|
509
510
|
self.log(
|
510
|
-
"While parsing a string, we a
|
511
|
+
"While parsing a string, we misplaced a quote that would have closed the string but has a different meaning here since this is the last element of the object, ignoring it",
|
511
512
|
"info",
|
512
513
|
)
|
513
514
|
string_acc += str(char)
|
@@ -98,6 +98,8 @@ def test_missing_and_mixed_quotes():
|
|
98
98
|
repair_json('{"name": "John", "age": 30, "city": "New')
|
99
99
|
== '{"name": "John", "age": 30, "city": "New"}'
|
100
100
|
)
|
101
|
+
assert repair_json('{"name": "John", "age": 30, "city": "New York, "gender": "male"}') == '{"name": "John", "age": 30, "city": "New York", "gender": "male"}'
|
102
|
+
|
101
103
|
assert repair_json('[{"key": "value", COMMENT "notes": "lorem "ipsum", sic." }]') == '[{"key": "value", "notes": "lorem \\"ipsum\\", sic."}]'
|
102
104
|
assert repair_json('{"key": ""value"}') == '{"key": "value"}'
|
103
105
|
assert repair_json('{"key": "value", 5: "value"}') == '{"key": "value", "5": "value"}'
|
@@ -19,7 +19,7 @@ def test_true_true_correct(benchmark):
|
|
19
19
|
mean_time = benchmark.stats.get("median")
|
20
20
|
|
21
21
|
# Define your time threshold in seconds
|
22
|
-
max_time =
|
22
|
+
max_time = 2 / 10 ** 3 # 2 millisecond
|
23
23
|
|
24
24
|
# Assert that the average time is below the threshold
|
25
25
|
assert mean_time < max_time, f"Benchmark exceeded threshold: {mean_time:.3f}s > {max_time:.3f}s"
|
@@ -31,7 +31,7 @@ def test_true_true_incorrect(benchmark):
|
|
31
31
|
mean_time = benchmark.stats.get("median")
|
32
32
|
|
33
33
|
# Define your time threshold in seconds
|
34
|
-
max_time =
|
34
|
+
max_time = 2 / 10 ** 3 # 2 millisecond
|
35
35
|
|
36
36
|
# Assert that the average time is below the threshold
|
37
37
|
assert mean_time < max_time, f"Benchmark exceeded threshold: {mean_time:.3f}s > {max_time:.3f}s"
|
@@ -53,7 +53,7 @@ def test_true_false_incorrect(benchmark):
|
|
53
53
|
mean_time = benchmark.stats.get("median")
|
54
54
|
|
55
55
|
# Define your time threshold in seconds
|
56
|
-
max_time =
|
56
|
+
max_time = 2 / 10 ** 3 # 2 millisecond
|
57
57
|
|
58
58
|
# Assert that the average time is below the threshold
|
59
59
|
assert mean_time < max_time, f"Benchmark exceeded threshold: {mean_time:.3f}s > {max_time:.3f}s"
|
@@ -64,7 +64,7 @@ def test_false_true_correct(benchmark):
|
|
64
64
|
mean_time = benchmark.stats.get("median")
|
65
65
|
|
66
66
|
# Define your time threshold in seconds
|
67
|
-
max_time =
|
67
|
+
max_time = 2 / 10 ** 3 # 2 millisecond
|
68
68
|
|
69
69
|
# Assert that the average time is below the threshold
|
70
70
|
assert mean_time < max_time, f"Benchmark exceeded threshold: {mean_time:.3f}s > {max_time:.3f}s"
|
@@ -75,7 +75,7 @@ def test_false_true_incorrect(benchmark):
|
|
75
75
|
mean_time = benchmark.stats.get("median")
|
76
76
|
|
77
77
|
# Define your time threshold in seconds
|
78
|
-
max_time =
|
78
|
+
max_time = 2 / 10 ** 3 # 2 millisecond
|
79
79
|
|
80
80
|
# Assert that the average time is below the threshold
|
81
81
|
assert mean_time < max_time, f"Benchmark exceeded threshold: {mean_time:.3f}s > {max_time:.3f}s"
|
@@ -97,7 +97,7 @@ def test_false_false_incorrect(benchmark):
|
|
97
97
|
mean_time = benchmark.stats.get("median")
|
98
98
|
|
99
99
|
# Define your time threshold in seconds
|
100
|
-
max_time =
|
100
|
+
max_time = 2 / 10 ** 3 # 2 millisecond
|
101
101
|
|
102
102
|
# Assert that the average time is below the threshold
|
103
103
|
assert mean_time < max_time, f"Benchmark exceeded threshold: {mean_time:.3f}s > {max_time:.3f}s"
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|