Skip to content

Python tool for converting files and office documents to Markdown.

Recognize json as plain text (if no other handlers are present). (#261)

afourney05b78e7ce18c
diff --git a/src/markitdown/_markitdown.py b/src/markitdown/_markitdown.py
index aceaa86d..b6acfe80 100644
--- a/src/markitdown/_markitdown.py
+++ b/src/markitdown/_markitdown.py
@@ -173,7 +173,10 @@ class PlainTextConverter(DocumentConverter):
# Only accept text files
if content_type is None:
return None
- elif "text/" not in content_type.lower():
+ elif all(
+ not content_type.lower().startswith(type_prefix)
+ for type_prefix in ["text/", "application/json"]
+ ):
return None
text_content = str(from_path(local_path).best())
diff --git a/tests/test_files/test.json b/tests/test_files/test.json
new file mode 100644
index 00000000..eba30594
--- /dev/null
+++ b/tests/test_files/test.json
@@ -0,0 +1,10 @@
+{
+ "key1": "string_value",
+ "key2": 1234,
+ "key3": [
+ "list_value1",
+ "list_value2"
+ ],
+ "5b64c88c-b3c3-4510-bcb8-da0b200602d8": "uuid_key",
+ "uuid_value": "9700dc99-6685-40b4-9a3a-5e406dcb37f3"
+}
diff --git a/tests/test_markitdown.py b/tests/test_markitdown.py
index e2d2e75f..3333bcbc 100644
--- a/tests/test_markitdown.py
+++ b/tests/test_markitdown.py
@@ -145,6 +145,11 @@ LLM_TEST_STRINGS = [
"5bda1dd6",
]
+JSON_TEST_STRINGS = [
+ "5b64c88c-b3c3-4510-bcb8-da0b200602d8",
+ "9700dc99-6685-40b4-9a3a-5e406dcb37f3",
+]
+
# --- Helper Functions ---
def validate_strings(result, expected_strings, exclude_strings=None):
@@ -257,6 +262,10 @@ def test_markitdown_local() -> None:
result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test_outlook_msg.msg"))
validate_strings(result, MSG_TEST_STRINGS)
+ # Test JSON processing
+ result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.json"))
+ validate_strings(result, JSON_TEST_STRINGS)
+
# Test input with leading blank characters
input_data = b" \n\n\n<html><body><h1>Test</h1></body></html>"
result = markitdown.convert_stream(io.BytesIO(input_data))