import csv
from utilities.utilities import EADDir
def find_nested_tags(ead):
results = []
for node in ead.tree.iter():
tag = node.tag
if len(list(node)) != 1:
continue
if list(node)[0].tag == tag and not node.text.strip():
results.append([ead.filename, ead.tree.getpath(node), tag])
return results
if __name__ == "__main__":
e = EADDir()
results = e.characterize_dir(find_nested_tags)
with open("eads_with_nested_tags.csv", mode="wb") as f:
writer = csv.writer(f)
for result in results:
writer.writerows(result)
import csv
from utilities.utilities import EADDir
def get_multiple_accruals(ead):
accruals = ead.tree.xpath("//accruals")
if len(accruals) > 1:
return [ead.filename, "{} accruals".format(len(accruals))]
return ""
if __name__ == "__main__":
ead_dir = EADDir()
results = list(filter(None, ead_dir.characterize_dir(get_multiple_accruals)))
with open("multiple_accruals.csv", mode="wb") as f:
writer = csv.writer(f)
writer.writerow(["filename", "accrual number"])
writer.writerows(results)
import csv
from utilities.utilities import EADDir
def find_nested_tags(ead):
results = []
for node in ead.tree.iter():
tag = node.tag
if len(list(node)) != 1:
continue
if list(node)[0].tag == tag and not node.text.strip():
results.append([ead.filename, ead.tree.getpath(node), tag])
return results
if __name__ == "__main__":
e = EADDir()
results = e.characterize_dir(find_nested_tags)
with open("eads_with_nested_tags.csv", mode="wb") as f:
writer = csv.writer(f)
for result in results:
writer.writerows(result)
import csv
from utilities.utilities import EADDir
def get_multiple_accruals(ead):
accruals = ead.tree.xpath("//accruals")
if len(accruals) > 1:
return [ead.filename, "{} accruals".format(len(accruals))]
return ""
if __name__ == "__main__":
ead_dir = EADDir()
results = list(
filter(None, ead_dir.characterize_dir(get_multiple_accruals)))
with open("multiple_accruals.csv", mode="wb") as f:
writer = csv.writer(f)
writer.writerow(["filename", "accrual number"])
writer.writerows(results)
