json-repair 0.29.0__tar.gz → 0.29.2__tar.gz

{json_repair-0.29.0/src/json_repair.egg-info → json_repair-0.29.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: json_repair
-Version: 0.29.0
+Version: 0.29.2
 Summary: A package to repair broken json strings
 Author-email: Stefano Baccianella <4247706+mangiucugna@users.noreply.github.com>
 License: MIT License
@@ -156,24 +156,24 @@ Install the library for command-line with:
 ```
 pipx install json-repair
 ```
-then run
+to know all options available:
 ```
 $ json_repair -h
-
-usage: json_repair [-h] [-i] [--ensure_ascii] [--indent INDENT] filename
+usage: json_repair [-h] [-i] [-o TARGET] [--ensure_ascii] [--indent INDENT] filename
 
 Repair and parse JSON files.
 
 positional arguments:
-  filename         The JSON file to repair
+  filename              The JSON file to repair
 
 options:
-  -h, --help       show this help message and exit
-  -i, --inline     Replace the file inline instead of returning the output to stdout
-  --ensure_ascii   Pass the ensure_ascii parameter to json.dumps()
-  --indent INDENT  Number of spaces for indentation (Default 2)
+  -h, --help            show this help message and exit
+  -i, --inline          Replace the file inline instead of returning the output to stdout
+  -o TARGET, --output TARGET
+                        If specified, the output will be written to TARGET filename instead of stdout
+  --ensure_ascii        Pass ensure_ascii=True to json.dumps()
+  --indent INDENT       Number of spaces for indentation (Default 2)
 ```
-to learn how to use it
 
 ## Adding to requirements
 **Please pin this library only on the major version!**

{json_repair-0.29.0 → json_repair-0.29.2}/README.md

@@ -118,24 +118,24 @@ Install the library for command-line with:
 ```
 pipx install json-repair
 ```
-then run
+to know all options available:
 ```
 $ json_repair -h
-
-usage: json_repair [-h] [-i] [--ensure_ascii] [--indent INDENT] filename
+usage: json_repair [-h] [-i] [-o TARGET] [--ensure_ascii] [--indent INDENT] filename
 
 Repair and parse JSON files.
 
 positional arguments:
-  filename         The JSON file to repair
+  filename              The JSON file to repair
 
 options:
-  -h, --help       show this help message and exit
-  -i, --inline     Replace the file inline instead of returning the output to stdout
-  --ensure_ascii   Pass the ensure_ascii parameter to json.dumps()
-  --indent INDENT  Number of spaces for indentation (Default 2)
+  -h, --help            show this help message and exit
+  -i, --inline          Replace the file inline instead of returning the output to stdout
+  -o TARGET, --output TARGET
+                        If specified, the output will be written to TARGET filename instead of stdout
+  --ensure_ascii        Pass ensure_ascii=True to json.dumps()
+  --indent INDENT       Number of spaces for indentation (Default 2)
 ```
-to learn how to use it
 
 ## Adding to requirements
 **Please pin this library only on the major version!**

{json_repair-0.29.0 → json_repair-0.29.2}/pyproject.toml

@@ -3,7 +3,7 @@ requires = ["setuptools>=61.0"]
 build-backend = "setuptools.build_meta"
 [project]
 name = "json_repair"
-version = "0.29.0"
+version = "0.29.2"
 license = {file = "LICENSE"}
 authors = [
   { name="Stefano Baccianella", email="4247706+mangiucugna@users.noreply.github.com" },

{json_repair-0.29.0 → json_repair-0.29.2}/src/json_repair/json_repair.py

@@ -384,38 +384,39 @@ class JSONParser:
         # * If we are fixing missing quotes in an object, when it finds the special terminators
         char = self.get_char_at()
         while char and char != rstring_delimiter:
-            if missing_quotes:
-                if self.get_context() == "object_key" and (
-                    char == ":" or char.isspace()
-                ):
+            if (
+                missing_quotes
+                and self.get_context() == "object_key"
+                and (char == ":" or char.isspace())
+            ):
+                self.log(
+                    "While parsing a string missing the left delimiter in object key context, we found a :, stopping here",
+                    "info",
+                )
+                break
+            if self.get_context() == "object_value" and char in [",", "}"]:
+                rstring_delimiter_missing = True
+                # check if this is a case in which the closing comma is NOT missing instead
+                i = 1
+                next_c = self.get_char_at(i)
+                while next_c and next_c != rstring_delimiter:
+                    i += 1
+                    next_c = self.get_char_at(i)
+                if next_c:
+                    i += 1
+                    next_c = self.get_char_at(i)
+                    # found a delimiter, now we need to check that is followed strictly by a comma or brace
+                    while next_c and next_c.isspace():
+                        i += 1
+                        next_c = self.get_char_at(i)
+                    if next_c and next_c in [",", "}"]:
+                        rstring_delimiter_missing = False
+                if rstring_delimiter_missing:
                     self.log(
-                        "While parsing a string missing the left delimiter in object key context, we found a :, stopping here",
+                        "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",
                         "info",
                     )
                     break
-                elif self.get_context() == "object_value" and char in [",", "}"]:
-                    rstring_delimiter_missing = True
-                    # check if this is a case in which the closing comma is NOT missing instead
-                    i = 1
-                    next_c = self.get_char_at(i)
-                    while next_c and next_c != rstring_delimiter:
-                        i += 1
-                        next_c = self.get_char_at(i)
-                    if next_c:
-                        i += 1
-                        next_c = self.get_char_at(i)
-                        # found a delimiter, now we need to check that is followed strictly by a comma or brace
-                        while next_c and next_c.isspace():
-                            i += 1
-                            next_c = self.get_char_at(i)
-                        if next_c and next_c in [",", "}"]:
-                            rstring_delimiter_missing = False
-                    if rstring_delimiter_missing:
-                        self.log(
-                            "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",
-                            "info",
-                        )
-                        break
             string_acc += char
             self.index += 1
             char = self.get_char_at()
@@ -507,7 +508,7 @@ class JSONParser:
                         if next_c == "}":
                             # OK this is valid then
                             self.log(
-                                "While parsing a string, we a misplaced quote that would have closed the string but has a different meaning here since this is the last element of the object, ignoring it",
+                                "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",
                                 "info",
                             )
                             string_acc += str(char)
@@ -760,7 +761,7 @@ def from_file(
     return jsonobj
 
 
-def cli():  # pragma: no cover
+def cli(inline_args: Optional[List[str]] = None) -> int:
     parser = argparse.ArgumentParser(description="Repair and parse JSON files.")
     parser.add_argument("filename", help="The JSON file to repair")
     parser.add_argument(
@@ -769,10 +770,16 @@ def cli():  # pragma: no cover
         action="store_true",
         help="Replace the file inline instead of returning the output to stdout",
     )
+    parser.add_argument(
+        "-o",
+        "--output",
+        metavar="TARGET",
+        help="If specified, the output will be written to TARGET filename instead of stdout",
+    )
     parser.add_argument(
         "--ensure_ascii",
         action="store_true",
-        help="Pass the ensure_ascii parameter to json.dumps()",
+        help="Pass ensure_ascii=True to json.dumps()",
     )
     parser.add_argument(
         "--indent",
@@ -781,24 +788,36 @@ def cli():  # pragma: no cover
         help="Number of spaces for indentation (Default 2)",
     )
 
-    args = parser.parse_args()
+    if inline_args is None:  # pragma: no cover
+        args = parser.parse_args()
+    else:
+        args = parser.parse_args(
+            inline_args
+        )  # This is needed so this function is testable
+
+    if args.inline and args.output:  # pragma: no cover
+        print("Error: You cannot pass both --inline and --output", file=sys.stderr)
+        sys.exit(1)
 
     ensure_ascii = False
     if args.ensure_ascii:
         ensure_ascii = True
+
     try:
         result = from_file(args.filename)
 
-        if args.inline:
-            fd = open(args.filename, mode="w")
+        if args.inline or args.output:
+            fd = open(args.output or args.filename, mode="w")
             json.dump(result, fd, indent=args.indent, ensure_ascii=ensure_ascii)
             fd.close()
         else:
             print(json.dumps(result, indent=args.indent, ensure_ascii=ensure_ascii))
-    except Exception as e:
+    except Exception as e:  # pragma: no cover
         print(f"Error: {str(e)}", file=sys.stderr)
         sys.exit(1)
 
+    return 0  # Success
+
 
 if __name__ == "__main__":  # pragma: no cover
-    cli()
+    sys.exit(cli())

{json_repair-0.29.0 → json_repair-0.29.2/src/json_repair.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: json_repair
-Version: 0.29.0
+Version: 0.29.2
 Summary: A package to repair broken json strings
 Author-email: Stefano Baccianella <4247706+mangiucugna@users.noreply.github.com>
 License: MIT License
@@ -156,24 +156,24 @@ Install the library for command-line with:
 ```
 pipx install json-repair
 ```
-then run
+to know all options available:
 ```
 $ json_repair -h
-
-usage: json_repair [-h] [-i] [--ensure_ascii] [--indent INDENT] filename
+usage: json_repair [-h] [-i] [-o TARGET] [--ensure_ascii] [--indent INDENT] filename
 
 Repair and parse JSON files.
 
 positional arguments:
-  filename         The JSON file to repair
+  filename              The JSON file to repair
 
 options:
-  -h, --help       show this help message and exit
-  -i, --inline     Replace the file inline instead of returning the output to stdout
-  --ensure_ascii   Pass the ensure_ascii parameter to json.dumps()
-  --indent INDENT  Number of spaces for indentation (Default 2)
+  -h, --help            show this help message and exit
+  -i, --inline          Replace the file inline instead of returning the output to stdout
+  -o TARGET, --output TARGET
+                        If specified, the output will be written to TARGET filename instead of stdout
+  --ensure_ascii        Pass ensure_ascii=True to json.dumps()
+  --indent INDENT       Number of spaces for indentation (Default 2)
 ```
-to learn how to use it
 
 ## Adding to requirements
 **Please pin this library only on the major version!**

{json_repair-0.29.0 → json_repair-0.29.2}/tests/test_json_repair.py

@@ -1,4 +1,8 @@
-from src.json_repair.json_repair import from_file, repair_json, loads
+from src.json_repair.json_repair import from_file, repair_json, loads, cli
+from unittest.mock import patch
+import os.path
+import pathlib
+import tempfile
 
 def test_basic_types_valid():
     assert repair_json("True", return_objects=True) == ""
@@ -94,6 +98,8 @@ def test_missing_and_mixed_quotes():
         repair_json('{"name": "John", "age": 30, "city": "New')
         == '{"name": "John", "age": 30, "city": "New"}'
     )
+    assert repair_json('{"name": "John", "age": 30, "city": "New York, "gender": "male"}')  == '{"name": "John", "age": 30, "city": "New York", "gender": "male"}'
+
     assert repair_json('[{"key": "value", COMMENT "notes": "lorem "ipsum", sic." }]') == '[{"key": "value", "notes": "lorem \\"ipsum\\", sic."}]'
     assert repair_json('{"key": ""value"}') == '{"key": "value"}'
     assert repair_json('{"key": "value", 5: "value"}') == '{"key": "value", "5": "value"}'
@@ -225,10 +231,6 @@ def test_repair_json_skip_json_loads():
 
 
 def test_repair_json_from_file():
-    import os.path
-    import pathlib
-    import tempfile
-
     path = pathlib.Path(__file__).parent.resolve()
 
     # Use chunk_length 2 to test the buffering feature
@@ -263,3 +265,50 @@ def test_repair_json_from_file():
 
 def test_ensure_ascii():
     assert repair_json("{'test_中国人_ascii':'统一码'}", ensure_ascii=False) == '{"test_中国人_ascii": "统一码"}'
+
+
+
+def test_cli(capsys):
+    # Create a temporary file
+    temp_fd, temp_path = tempfile.mkstemp(suffix=".json")
+    try:
+        # Write content to the temporary file
+        with os.fdopen(temp_fd, 'w') as tmp:
+            tmp.write("{key:value")
+        cli(inline_args=[temp_path, '--indent', 0, '--ensure_ascii'])
+        captured = capsys.readouterr()
+        assert captured.out == '{\n"key": "value"\n}\n'
+        
+        # Test the output option
+        tempout_fd, tempout_path = tempfile.mkstemp(suffix=".json")
+        cli(inline_args=[temp_path, '--indent', 0, '-o', tempout_path])
+        with open(tempout_path, 'r') as tmp:
+            out = tmp.read()
+        assert out == '{\n"key": "value"\n}'
+
+        # Test the inline option
+        cli(inline_args=[temp_path, '--indent', 0, '-i'])
+        with open(temp_path, 'r') as tmp:
+            out = tmp.read()
+        assert out == '{\n"key": "value"\n}'
+
+
+    finally:
+        # Clean up - delete the temporary file
+        os.remove(temp_path)
+        os.remove(tempout_path)
+
+"""
+def test_cli_inline(sample_json_file):
+    with patch('sys.argv', ['json_repair', sample_json_file, '-i']):
+        cli()
+    with open(sample_json_file, 'r') as f:
+        assert json.load(f) == {"key": "value"}
+
+def test_cli_output_file(sample_json_file, tmp_path):
+    output_file = tmp_path / "output.json"
+    with patch('sys.argv', ['json_repair', sample_json_file, '-o', str(output_file)]):
+        cli()
+    with open(output_file, 'r') as f:
+        assert json.load(f) == {"key": "value"}
+"""

{json_repair-0.29.0 → json_repair-0.29.2}/tests/test_performance.py

@@ -19,7 +19,7 @@ def test_true_true_correct(benchmark):
   mean_time = benchmark.stats.get("median")
 
   # Define your time threshold in seconds
-  max_time = 15 / 10 ** 4  # 1.5 millisecond
+  max_time = 2 / 10 ** 3  # 2 millisecond
 
   # Assert that the average time is below the threshold
   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):
   mean_time = benchmark.stats.get("median")
 
   # Define your time threshold in seconds
-  max_time = 15 / 10 ** 4  # 1.5 millisecond
+  max_time = 2 / 10 ** 3  # 2 millisecond
 
   # Assert that the average time is below the threshold
   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):
   mean_time = benchmark.stats.get("median")
 
   # Define your time threshold in seconds
-  max_time = 15 / 10 ** 4  # 1.5 millisecond
+  max_time = 2 / 10 ** 3  # 2 millisecond
 
   # Assert that the average time is below the threshold
   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):
   mean_time = benchmark.stats.get("median")
 
   # Define your time threshold in seconds
-  max_time = 15 / 10 ** 4  # 1.5 millisecond
+  max_time = 2 / 10 ** 3  # 2 millisecond
 
   # Assert that the average time is below the threshold
   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):
   mean_time = benchmark.stats.get("median")
   
   # Define your time threshold in seconds
-  max_time = 15 / 10 ** 4  # 1.5 millisecond
+  max_time = 2 / 10 ** 3  # 2 millisecond
 
   # Assert that the average time is below the threshold
   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):
   mean_time = benchmark.stats.get("median")
 
   # Define your time threshold in seconds
-  max_time = 15 / 10 ** 4  # 1.5 millisecond
+  max_time = 2 / 10 ** 3  # 2 millisecond
 
   # Assert that the average time is below the threshold
   assert mean_time < max_time, f"Benchmark exceeded threshold: {mean_time:.3f}s > {max_time:.3f}s"