def parse(self):
src = self.archive.read(self.workbook_part_name)
node = fromstring(src)
package = WorkbookPackage.from_tree(node)
if package.properties.date1904:
self.wb.epoch = CALENDAR_MAC_1904
self.wb.code_name = package.properties.codeName
self.wb.active = package.active
self.wb.views = package.bookViews
self.sheets = package.sheets
self.wb.calculation = package.calcPr
self.caches = package.pivotCaches
#external links contain cached worksheets and can be very big
if not self.keep_links:
package.externalReferences = []
for ext_ref in package.externalReferences:
rel = self.rels[ext_ref.id]
self.wb._external_links.append(
read_external_link(self.archive, rel.Target))
if package.definedNames:
package.definedNames._cleanup()
self.wb.defined_names = package.definedNames
self.wb.security = package.workbookProtection
def test_broken_sheet_ref(self, datadir, recwarn, WorkbookParser):
from openpyxl.packaging.workbook import WorkbookPackage
datadir.chdir()
with open("workbook_missing_id.xml", "rb") as src:
xml = src.read()
node = fromstring(xml)
wb = WorkbookPackage.from_tree(node)
archive = ZipFile(BytesIO(), "a")
archive.write("workbook_links.xml", ARC_WORKBOOK)
archive.writestr(ARC_WORKBOOK_RELS, b"<root />")
parser = WorkbookParser(archive, ARC_WORKBOOK)
parser.sheets = wb.sheets
sheets = parser.find_sheets()
list(sheets)
w = recwarn.pop()
assert issubclass(w.category, UserWarning)