fix(#353): Accept encoding input

tests/json/chinese.json

@@ -0,0 +1,6 @@
+{
+  "title": "测试文件",
+  "content": "这是一个中文测试",
+  "greeting": "你好世界",
+  "items": ["一", "二", "三"]
+}

tests/json/chinese.txt

@@ -0,0 +1 @@
+这是一个中文测试 你好世界 一 二 三  测试文件

tests/json/cyrillic.json

@@ -0,0 +1,9 @@
+{
+  "name": "Тестовый файл",
+  "description": "Это тест на кириллице",
+  "nested": {
+    "value": "Значение",
+    "greeting": "Привет мир"
+  },
+  "items": ["один", "два", "три"]
+}

tests/json/cyrillic.txt

@@ -0,0 +1 @@
+Это тест на кириллице один два три  Тестовый файл Привет мир Значение

tests/json/emoji.json

@@ -0,0 +1,5 @@
+{
+  "message": "Hello 😀 World",
+  "status": "✅ success",
+  "items": ["🚀", "🎉", "❤️"]
+}

tests/json/emoji.txt

@@ -0,0 +1 @@
+🚀 🎉 ❤️  Hello 😀 World ✅ success 

tests/json/mixed_scripts.json

@@ -0,0 +1,7 @@
+{
+  "english": "Hello",
+  "russian": "Привет",
+  "chinese": "你好",
+  "emoji": "👋",
+  "combined": "Mixed: Привет 你好 👋"
+}

tests/json/mixed_scripts.txt

@@ -0,0 +1 @@
+你好 Mixed: Привет 你好 👋 👋 Hello Привет

tests/test_json.py

@@ -3,5 +3,43 @@
 from . import base
 
 
+_ENCODING_TEST_CASES: list[tuple[str, str]] = [
+    ("cyrillic", ""),
+    ("chinese", ""),
+    ("emoji", ""),
+    ("mixed_scripts", ""),
+]
 class JsonTestCase(base.BaseParserTestCase, unittest.TestCase):
     extension = "json"
+
+
+
+    def test_character_sets_python(self):
+        """Test JSON parser with various character encodings via Python API."""
+        d = self.get_extension_directory()
+        for charset, skip_reason in _ENCODING_TEST_CASES:
+            with self.subTest(charset=charset):
+                if skip_reason:
+                    self.skipTest(skip_reason)
+                filename = f"{d}/{charset}.json"
+                expected_filename = f"{d}/{charset}.txt"
+                self.compare_python_output(filename, expected_filename)
+
+    def test_character_sets_cli(self):
+        """Test JSON parser with various character encodings via CLI."""
+        d = self.get_extension_directory()
+        for charset, skip_reason in _ENCODING_TEST_CASES:
+            with self.subTest(charset=charset):
+                if skip_reason:
+                    self.skipTest(skip_reason)
+                filename = f"{d}/{charset}.json"
+                expected_filename = f"{d}/{charset}.txt"
+                self.compare_cli_output(filename, expected_filename)
+
+
+    def test_explicit_encoding_parameter(self):
+        """Test that encoding parameter is respected."""
+        filename = self.get_extension_directory() + "/cyrillic.json"
+        expected_filename = self.get_extension_directory() + "/cyrillic.txt"
+        # Test with explicit UTF-8 encoding
+        self.compare_python_output(filename, expected_filename, encoding='utf-8')

textract/parsers/json_parser.py

@@ -10,8 +10,8 @@ class Parser(BaseParser):
     from mongodb dumps, for example.
     """
 
-    def extract(self, filename, **kwargs):
-        with Path(filename).open(encoding="utf-8") as raw:
+    def extract(self, filename, encoding='utf-8', **kwargs):
+        with Path(filename).open(encoding=encoding) as raw:
             deserialized_json = json.load(raw)
         return self.get_text(deserialized_json)