Merge branch 'main' into main

pyproject.toml

@@ -32,6 +32,7 @@ dependencies = [
   "python-pptx",
   "pandas",
   "openpyxl",
+  "xlrd",
   "pdfminer.six",
   "puremagic",
   "pydub",

src/markitdown/_markitdown.py

@@ -173,7 +173,10 @@ def convert(
         # 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())
@@ -760,7 +763,31 @@ def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]:
         if extension.lower() != ".xlsx":
             return None
 
-        sheets = pd.read_excel(local_path, sheet_name=None)
+        sheets = pd.read_excel(local_path, sheet_name=None, engine="openpyxl")
+        md_content = ""
+        for s in sheets:
+            md_content += f"## {s}\n"
+            html_content = sheets[s].to_html(index=False)
+            md_content += self._convert(html_content).text_content.strip() + "\n\n"
+
+        return DocumentConverterResult(
+            title=None,
+            text_content=md_content.strip(),
+        )
+
+
+class XlsConverter(HtmlConverter):
+    """
+    Converts XLS files to Markdown, with each sheet presented as a separate Markdown table.
+    """
+
+    def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]:
+        # Bail if not a XLS
+        extension = kwargs.get("file_extension", "")
+        if extension.lower() != ".xls":
+            return None
+
+        sheets = pd.read_excel(local_path, sheet_name=None, engine="xlrd")
         md_content = ""
         for s in sheets:
             md_content += f"## {s}\n"
@@ -1387,6 +1414,7 @@ def __init__(
         self.register_page_converter(BingSerpConverter())
         self.register_page_converter(DocxConverter())
         self.register_page_converter(XlsxConverter())
+        self.register_page_converter(XlsConverter())
         self.register_page_converter(PptxConverter())
         self.register_page_converter(WavConverter())
         self.register_page_converter(Mp3Converter())
@@ -1603,6 +1631,25 @@ def _guess_ext_magic(self, path):
         # Use puremagic to guess
         try:
             guesses = puremagic.magic_file(path)
+
+            # Fix for: https://github.com/microsoft/markitdown/issues/222
+            # If there are no guesses, then try again after trimming leading ASCII whitespaces.
+            # ASCII whitespace characters are those byte values in the sequence b' \t\n\r\x0b\f'
+            # (space, tab, newline, carriage return, vertical tab, form feed).
+            if len(guesses) == 0:
+                with open(path, "rb") as file:
+                    while True:
+                        char = file.read(1)
+                        if not char:  # End of file
+                            break
+                        if not char.isspace():
+                            file.seek(file.tell() - 1)
+                            break
+                    try:
+                        guesses = puremagic.magic_stream(file)
+                    except puremagic.main.PureError:
+                        pass
+
             extensions = list()
             for g in guesses:
                 ext = g.extension.strip()

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"
+}

tests/test_markitdown.py

@@ -54,6 +54,12 @@
     "affc7dad-52dc-4b98-9b5d-51e65d8a8ad0",
 ]
 
+XLS_TEST_STRINGS = [
+    "## 09060124-b5e7-4717-9d07-3c046eb",
+    "6ff4173b-42a5-4784-9b19-f49caff4d93d",
+    "affc7dad-52dc-4b98-9b5d-51e65d8a8ad0",
+]
+
 DOCX_TEST_STRINGS = [
     "314b0a30-5b04-470b-b9f7-eed2c2bec74a",
     "49e168b7-d2ae-407f-a055-2167576f39a1",
@@ -139,6 +145,11 @@
     "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):
@@ -185,6 +196,12 @@ def test_markitdown_local() -> None:
     result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.xlsx"))
     validate_strings(result, XLSX_TEST_STRINGS)
 
+    # Test XLS processing
+    result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.xls"))
+    for test_string in XLS_TEST_STRINGS:
+        text_content = result.text_content.replace("\\", "")
+        assert test_string in text_content
+
     # Test DOCX processing
     result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.docx"))
     validate_strings(result, DOCX_TEST_STRINGS)
@@ -245,6 +262,15 @@ 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))
+    assert "# Test" in result.text_content
+
 
 @pytest.mark.skipif(
     skip_exiftool,