combine xlsx and xls to excel, replace openpxyl/xlrd with calamine

microsoft · Jan 3, 2025 · b953121 · b953121
1 parent 731b39e
commit b953121
Show file tree

Hide file tree

Showing 5 changed files with 16 additions and 36 deletions.
diff --git a/pyproject.toml b/pyproject.toml
@@ -31,8 +31,7 @@ dependencies = [
   "numpy",
   "python-pptx",
   "pandas",
-  "openpyxl",
-  "xlrd",
+  "python-calamine",
   "pdfminer.six",
   "puremagic",
   "pydub",

diff --git a/src/markitdown/_markitdown.py b/src/markitdown/_markitdown.py
@@ -715,42 +715,18 @@ def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]:
         return result
 
 
-class XlsxConverter(HtmlConverter):
+class ExcelConverter(HtmlConverter):
     """
-    Converts XLSX files to Markdown, with each sheet presented as a separate Markdown table.
+    Converts Excel (XLSX, XLS, XLSM or XLSB) 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 XLSX
+        # Bail if not a XLSX, XLS, XLSM or XLSB
         extension = kwargs.get("file_extension", "")
-        if extension.lower() != ".xlsx":
+        if extension.lower() not in [".xlsx", ".xls", ".xlsb", ".xlsm"]:
             return 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")
+        sheets = pd.read_excel(local_path, sheet_name=None, engine="calamine")
         md_content = ""
         for s in sheets:
             md_content += f"## {s}\n"
@@ -1376,8 +1352,7 @@ def __init__(
         self.register_page_converter(YouTubeConverter())
         self.register_page_converter(BingSerpConverter())
         self.register_page_converter(DocxConverter())
-        self.register_page_converter(XlsxConverter())
-        self.register_page_converter(XlsConverter())
+        self.register_page_converter(ExcelConverter())
         self.register_page_converter(PptxConverter())
         self.register_page_converter(WavConverter())
         self.register_page_converter(Mp3Converter())

diff --git a/tests/test_files/test.xlsb b/tests/test_files/test.xlsb
diff --git a/tests/test_files/test.xlsm b/tests/test_files/test.xlsm
diff --git a/tests/test_markitdown.py b/tests/test_markitdown.py
@@ -191,11 +191,17 @@ def test_markitdown_local() -> None:
     result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.xlsx"))
     validate_strings(result, XLSX_TEST_STRINGS)
 
+    # Test XLSB processing
+    result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.xlsb"))
+    validate_strings(result, XLSX_TEST_STRINGS)
+
+    # Test XLSM processing
+    result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.xlsm"))
+    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
+    validate_strings(result, XLSX_TEST_STRINGS)
 
     # Test DOCX processing
     result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.docx"))