def iter_rows(workbook_name, sheet_name, xml_source, shared_date, string_table, range_string='', row_offset=0, column_offset=0): archive = get_archive_file(workbook_name) source = xml_source if range_string: min_col, min_row, max_col, max_row = get_range_boundaries( range_string, row_offset, column_offset) else: min_col, min_row, max_col, max_row = read_dimension(xml_source=source) min_col = column_index_from_string(min_col) max_col = column_index_from_string(max_col) + 1 max_row += 6 style_table = read_style_table(archive.read(ARC_STYLE)) source.seek(0) p = iterparse(source) return get_squared_range(p, min_col, min_row, max_col, max_row, string_table, style_table, shared_date)
def _load_workbook(wb, archive, filename, use_iterators): valid_files = archive.namelist() # get workbook-level information try: wb.properties = read_properties_core(archive.read(ARC_CORE)) except KeyError: wb.properties = DocumentProperties() try: string_table = read_string_table(archive.read(ARC_SHARED_STRINGS)) except KeyError: string_table = {} try: wb.loaded_theme = archive.read( ARC_THEME ) # some writers don't output a theme, live with it (fixes #160) except KeyError: assert wb.loaded_theme == None, "even though the theme information is missing there is a theme object ?" style_table = read_style_table(archive.read(ARC_STYLE)) wb.properties.excel_base_date = read_excel_base_date( xml_source=archive.read(ARC_WORKBOOK)) # get worksheets wb.worksheets = [] # remove preset worksheet sheet_names = read_sheets_titles(archive.read(ARC_WORKBOOK)) for i, sheet_name in enumerate(sheet_names): sheet_codename = 'sheet%d.xml' % (i + 1) worksheet_path = '%s/%s' % (PACKAGE_WORKSHEETS, sheet_codename) if not worksheet_path in valid_files: continue if not use_iterators: new_ws = read_worksheet(archive.read(worksheet_path), wb, sheet_name, string_table, style_table) else: xml_source = unpack_worksheet(archive, worksheet_path) new_ws = read_worksheet(xml_source, wb, sheet_name, string_table, style_table, filename, sheet_codename) wb.add_sheet(new_ws, index=i) wb._named_ranges = read_named_ranges(archive.read(ARC_WORKBOOK), wb)
def _load_workbook(wb, archive, filename, use_iterators): valid_files = archive.namelist() # get workbook-level information try: wb.properties = read_properties_core(archive.read(ARC_CORE)) except KeyError: wb.properties = DocumentProperties() try: string_table = read_string_table(archive.read(ARC_SHARED_STRINGS)) except KeyError: string_table = {} try: wb.loaded_theme = archive.read(ARC_THEME) # some writers don't output a theme, live with it (fixes #160) except KeyError: assert wb.loaded_theme == None, "even though the theme information is missing there is a theme object ?" style_table = read_style_table(archive.read(ARC_STYLE)) wb.properties.excel_base_date = read_excel_base_date(xml_source=archive.read(ARC_WORKBOOK)) # get worksheets wb.worksheets = [] # remove preset worksheet sheet_names = read_sheets_titles(archive.read(ARC_WORKBOOK)) for i, sheet_name in enumerate(sheet_names): sheet_codename = "sheet%d.xml" % (i + 1) worksheet_path = "%s/%s" % (PACKAGE_WORKSHEETS, sheet_codename) if not worksheet_path in valid_files: continue if not use_iterators: new_ws = read_worksheet(archive.read(worksheet_path), wb, sheet_name, string_table, style_table) else: xml_source = unpack_worksheet(archive, worksheet_path) new_ws = read_worksheet(xml_source, wb, sheet_name, string_table, style_table, filename, sheet_codename) wb.add_sheet(new_ws, index=i) wb._named_ranges = read_named_ranges(archive.read(ARC_WORKBOOK), wb)
def iter_rows( workbook_name, sheet_name, xml_source, shared_date, string_table, range_string="", row_offset=0, column_offset=0 ): archive = get_archive_file(workbook_name) source = xml_source if range_string: min_col, min_row, max_col, max_row = get_range_boundaries(range_string, row_offset, column_offset) else: min_col, min_row, max_col, max_row = read_dimension(xml_source=source) min_col = column_index_from_string(min_col) max_col = column_index_from_string(max_col) + 1 max_row += 6 style_table = read_style_table(archive.read(ARC_STYLE)) source.seek(0) p = iterparse(source) return get_squared_range(p, min_col, min_row, max_col, max_row, string_table, style_table, shared_date)