def get_cells(self, min_row, min_col, max_row, max_col):
p = iterparse(self.xml_source)
for _event, element in p:
if element.tag == '{%s}c' % SHEET_MAIN_NS:
coord = element.get('r')
column_str, row = RE_COORDINATE.match(coord).groups()
row = int(row)
column = column_index_from_string(column_str)
if min_col <= column <= max_col and min_row <= row <= max_row:
data_type = element.get('t', 'n')
style_id = element.get('s')
formula = element.findtext('{%s}f' % SHEET_MAIN_NS)
value = element.findtext('{%s}v' % SHEET_MAIN_NS)
if formula is not None and not self.parent.data_only:
data_type = Cell.TYPE_FORMULA
value = "=" + formula
if not (value or formula or style_id):
# this cell is pointless and should not have been
# written in the first place
continue
yield RawCell(row, column_str, coord, value, data_type,
style_id, None)
# sub-elements of cells should be skipped
if (element.tag == '{%s}v' % SHEET_MAIN_NS
or element.tag == '{%s}f' % SHEET_MAIN_NS):
continue
element.clear()
def get_cells(self, min_row, min_col, max_row, max_col):
p = iterparse(self.xml_source)
for _event, element in p:
if element.tag == '{%s}c' % SHEET_MAIN_NS:
coord = element.get('r')
column_str, row = RE_COORDINATE.match(coord).groups()
row = int(row)
column = column_index_from_string(column_str)
if min_col <= column <= max_col and min_row <= row <= max_row:
data_type = element.get('t', 'n')
style_id = element.get('s')
formula = element.findtext('{%s}f' % SHEET_MAIN_NS)
value = element.findtext('{%s}v' % SHEET_MAIN_NS)
if formula is not None and not self.parent.data_only:
data_type = Cell.TYPE_FORMULA
value = "=" + formula
if not (value or formula or style_id):
# this cell is pointless and should not have been
# written in the first place
continue
yield RawCell(row, column_str, coord, value, data_type, style_id, None)
# sub-elements of cells should be skipped
if (element.tag == '{%s}v' % SHEET_MAIN_NS
or element.tag == '{%s}f' % SHEET_MAIN_NS):
continue
element.clear()
def read_dimension(xml_source):
min_row = min_col = max_row = max_col = None
source = _get_xml_iter(xml_source)
it = iterparse(source)
for event, el in it:
if el.tag == '{%s}dimension' % SHEET_MAIN_NS:
dim = el.get("ref")
if ':' in dim:
start, stop = dim.split(':')
else:
start = stop = dim
min_col, min_row = coordinate_from_string(start)
max_col, max_row = coordinate_from_string(stop)
return min_col, min_row, max_col, max_row
if el.tag == '{%s}row' % SHEET_MAIN_NS:
row = el.get("r")
if min_row is None:
min_row = int(row)
span = el.get("spans")
if ":" in span:
start, stop = span.split(":")
if min_col is None:
min_col = int(start)
max_col = int(stop)
else:
min_col = min(min_col, int(start))
max_col = max(max_col, int(stop))
max_row = int(row)
warn("Unsized worksheet")
return get_column_letter(min_col), min_row, get_column_letter(max_col), max_row
def read_dimension(xml_source):
min_row = min_col = max_row = max_col = None
source = _get_xml_iter(xml_source)
it = iterparse(source)
for event, el in it:
if el.tag == '{%s}dimension' % SHEET_MAIN_NS:
dim = el.get("ref")
if ':' in dim:
start, stop = dim.split(':')
else:
start = stop = dim
min_col, min_row = coordinate_from_string(start)
max_col, max_row = coordinate_from_string(stop)
return min_col, min_row, max_col, max_row
elif el.tag == '{%s}row' % SHEET_MAIN_NS:
row = el.get("r")
if min_row is None:
min_row = int(row)
span = el.get("spans", "")
if ":" in span:
start, stop = span.split(":")
if min_col is None:
min_col = int(start)
max_col = int(stop)
else:
min_col = min(min_col, int(start))
max_col = max(max_col, int(stop))
elif el.tag == '{%s}c' % SHEET_MAIN_NS:
coord = el.get('r')
column_str, row = coordinate_from_string(coord)
column = column_index_from_string(column_str)
if min_col is None:
min_col = column
else:
min_col = min(column, min_col)
if max_col is None:
max_col = column
else:
max_col = max(column, max_col)
el.clear()
max_row = int(row)
warn("Unsized worksheet")
return get_column_letter(min_col), min_row, get_column_letter(max_col), max_row
def read_dimension(xml_source):
min_row = min_col = max_row = max_col = None
source = _get_xml_iter(xml_source)
it = iterparse(source)
for event, el in it:
if el.tag == "{%s}dimension" % SHEET_MAIN_NS:
dim = el.get("ref")
if ":" in dim:
start, stop = dim.split(":")
else:
start = stop = dim
min_col, min_row = coordinate_from_string(start)
max_col, max_row = coordinate_from_string(stop)
return min_col, min_row, max_col, max_row
elif el.tag == "{%s}row" % SHEET_MAIN_NS:
row = el.get("r")
if min_row is None:
min_row = int(row)
span = el.get("spans", "")
if ":" in span:
start, stop = span.split(":")
if min_col is None:
min_col = int(start)
max_col = int(stop)
else:
min_col = min(min_col, int(start))
max_col = max(max_col, int(stop))
elif el.tag == "{%s}c" % SHEET_MAIN_NS:
coord = el.get("r")
column_str, row = coordinate_from_string(coord)
column = column_index_from_string(column_str)
if min_col is None:
min_col = column
else:
min_col = min(column, min_col)
if max_col is None:
max_col = column
else:
max_col = max(column, max_col)
el.clear()
max_row = int(row)
warn("Unsized worksheet")
return get_column_letter(min_col), min_row, get_column_letter(max_col), max_row
def parse(self):
stream = _get_xml_iter(self.source)
it = iterparse(stream)
dispatcher = {
'{%s}c' % SHEET_MAIN_NS: self.parse_cell,
'{%s}mergeCells' % SHEET_MAIN_NS: self.parse_merge,
'{%s}cols' % SHEET_MAIN_NS: self.parse_column_dimensions,
'{%s}sheetData' % SHEET_MAIN_NS: self.parse_row_dimensions,
'{%s}printOptions' % SHEET_MAIN_NS: self.parse_print_options,
'{%s}pageMargins' % SHEET_MAIN_NS: self.parse_margins,
'{%s}pageSetup' % SHEET_MAIN_NS: self.parse_page_setup,
'{%s}headerFooter' % SHEET_MAIN_NS: self.parse_header_footer,
'{%s}conditionalFormatting' % SHEET_MAIN_NS: self.parser_conditional_formatting
}
for event, element in it:
tag_name = element.tag
if tag_name in dispatcher:
dispatcher[tag_name](element)
element.clear()
def parse(self):
stream = _get_xml_iter(self.source)
it = iterparse(stream)
dispatcher = {
"{%s}c" % SHEET_MAIN_NS: self.parse_cell,
"{%s}mergeCells" % SHEET_MAIN_NS: self.parse_merge,
"{%s}cols" % SHEET_MAIN_NS: self.parse_column_dimensions,
"{%s}sheetData" % SHEET_MAIN_NS: self.parse_row_dimensions,
"{%s}printOptions" % SHEET_MAIN_NS: self.parse_print_options,
"{%s}pageMargins" % SHEET_MAIN_NS: self.parse_margins,
"{%s}pageSetup" % SHEET_MAIN_NS: self.parse_page_setup,
"{%s}headerFooter" % SHEET_MAIN_NS: self.parse_header_footer,
"{%s}conditionalFormatting" % SHEET_MAIN_NS: self.parser_conditional_formatting,
}
for event, element in it:
tag_name = element.tag
if tag_name in dispatcher:
dispatcher[tag_name](element)
element.clear()
