fix: preserve currency number format when converting xlsx to markdown

.gitignore

@@ -166,3 +166,7 @@ cython_debug/
 src/.DS_Store
 .DS_Store
 .cursorrules
+
+
+create_test_file.py
+test_currency.xlsx

packages/markitdown/src/markitdown/converters/_xlsx_converter.py

@@ -10,7 +10,7 @@
 _xlsx_dependency_exc_info = None
 try:
     import pandas as pd
-    import openpyxl  # noqa: F401
+    import openpyxl
 except ImportError:
     _xlsx_dependency_exc_info = sys.exc_info()
 
@@ -33,9 +33,44 @@
 ACCEPTED_XLS_FILE_EXTENSIONS = [".xls"]
 
 
+def _apply_cell_formats(wb, sheets):
+    """
+    Use openpyxl to detect currency-formatted cells and override
+    the raw numeric values that pandas extracted.
+    """
+    for sheet_name in sheets:
+        ws = wb[sheet_name]
+        df = sheets[sheet_name]
+
+        for row in ws.iter_rows():
+            for cell in row:
+                if cell.value is None:
+                    continue
+                fmt = cell.number_format or ""
+                value = cell.value
+                if not isinstance(value, (int, float)):
+                    continue
+
+                # Detect currency symbols in the format string
+                for symbol in ['$', '€', '¥', '£']:
+                    if symbol in fmt:
+                        row_idx = cell.row - 2  # Convert to DataFrame row index
+                        col_idx = cell.column - 1  # Convert to DataFrame column index
+                        if 0 <= row_idx < len(df):
+                            # Convert column to object type first to allow string values
+                            col_name = df.columns[col_idx]
+                            df[col_name] = df[col_name].astype(object)
+                            if '.00' in fmt or '.0' in fmt:
+                                formatted = f"{symbol}{value:,.2f}"
+                            else:
+                                formatted = f"{symbol}{int(value):,}"
+                            df.iloc[row_idx, col_idx] = formatted
+                        break
+
 class XlsxConverter(DocumentConverter):
     """
     Converts XLSX files to Markdown, with each sheet presented as a separate Markdown table.
+    Currency and other number formats are preserved using openpyxl.
     """
 
     def __init__(self):
@@ -46,7 +81,7 @@ def accepts(
         self,
         file_stream: BinaryIO,
         stream_info: StreamInfo,
-        **kwargs: Any,  # Options to pass to the converter
+        **kwargs: Any,
     ) -> bool:
         mimetype = (stream_info.mimetype or "").lower()
         extension = (stream_info.extension or "").lower()
@@ -64,7 +99,7 @@ def convert(
         self,
         file_stream: BinaryIO,
         stream_info: StreamInfo,
-        **kwargs: Any,  # Options to pass to the converter
+        **kwargs: Any,
     ) -> DocumentConverterResult:
         # Check the dependencies
         if _xlsx_dependency_exc_info is not None:
@@ -80,7 +115,16 @@ def convert(
                 _xlsx_dependency_exc_info[2]
             )
 
+        # Read format info with openpyxl first
+        wb = openpyxl.load_workbook(file_stream, data_only=True)
+
+        # Seek back to start before pandas reads the same stream
+        file_stream.seek(0)
         sheets = pd.read_excel(file_stream, sheet_name=None, engine="openpyxl")
+
+        # Apply currency and number formatting
+        _apply_cell_formats(wb, sheets)
+
         md_content = ""
         for s in sheets:
             md_content += f"## {s}\n"
@@ -108,7 +152,7 @@ def accepts(
         self,
         file_stream: BinaryIO,
         stream_info: StreamInfo,
-        **kwargs: Any,  # Options to pass to the converter
+        **kwargs: Any,
     ) -> bool:
         mimetype = (stream_info.mimetype or "").lower()
         extension = (stream_info.extension or "").lower()
@@ -126,7 +170,7 @@ def convert(
         self,
         file_stream: BinaryIO,
         stream_info: StreamInfo,
-        **kwargs: Any,  # Options to pass to the converter
+        **kwargs: Any,
     ) -> DocumentConverterResult:
         # Load the dependencies
         if _xls_dependency_exc_info is not None:
@@ -154,4 +198,4 @@ def convert(
                 + "\n\n"
             )
 
-        return DocumentConverterResult(markdown=md_content.strip())
+        return DocumentConverterResult(markdown=md_content.strip())