Class ExcelParser

docreader/parser/excel_parser.py:45–120

Parser for Excel files (.xlsx, .xls). This parser extracts text content from Excel files by processing all sheets and converting each row into a structured text format. Each row becomes a separate chunk with key-value pairs. Features: - Supports multiple sheets in a

class ExcelParser(BaseParser):
    """Parser for Excel files (.xlsx, .xls).
    
    This parser extracts text content from Excel files by processing all sheets
    and converting each row into a structured text format. Each row becomes a
    separate chunk with key-value pairs.
    
    Features:
        - Supports multiple sheets in a single Excel file
        - Automatically removes completely empty rows
        - Converts each row to "column: value" format
        - Creates individual chunks for each row for better granularity
        
    Example:
        >>> parser = ExcelParser()
        >>> with open("data.xlsx", "rb") as f:
        ...     content = f.read()
        ...     document = parser.parse_into_text(content)
        >>> print(document.content)
        Name: John,Age: 30,City: NYC
        Name: Jane,Age: 25,City: LA
    """
    
    def parse_into_text(self, content: bytes) -> Document:
        """Parse Excel file bytes into a Document object.
        
        Args:
            content: Raw bytes of the Excel file
            
        Returns:
            Document: Parsed document containing:
                - content: Full text with all rows from all sheets
                - chunks: List of Chunk objects, one per row
                
        Note:
            - Empty rows (all NaN values) are automatically skipped
            - Each row is formatted as: "col1: val1,col2: val2,..."
            - Chunks maintain sequential ordering across all sheets
        """
        chunks: List[Chunk] = []
        text: List[str] = []
        start, end = 0, 0

        excel_file = _open_excel_file(content, file_type=self.file_type)
        
        # Process each sheet in the Excel file
        for excel_sheet_name in excel_file.sheet_names:
            df = _read_sheet_dataframe(excel_file, excel_sheet_name)
            # Remove rows where all values are NaN (completely empty rows)
            df.dropna(how="all", inplace=True)

            # Process each row in the DataFrame
            for _, row in df.iterrows():
                page_content = []
                # Build key-value pairs for non-null values
                for k, v in row.items():
                    if pd.notna(v) and not _is_image_function(v):
                        page_content.append(f"{k}: {v}")