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 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 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)
from utilities.utilities import EADDir
ead_dir = EADDir(
input_dir=
r"C:\Users\wboyle\PycharmProjects\without-reservations\Real_Masters_all")
def fix_portions(ead):
for did in ead.tree.xpath("//did"):
physdescs = did.xpath("physdesc")
# if len(physdescs) > 1:
# if all([len(physdesc.xpath("extent")) > 0 for physdesc in physdescs]):
# for physdesc in physdescs:
# physdesc.attrib["altrender"] = "part"
if len(physdescs) == 1:
if any([tag.tag == "extent" for tag in list(physdescs[0])]):
physdescs[0].attrib["altrender"] = "whole"
def fix_lone_container_summaries(ead):
for did in ead.tree.xpath("//did"):
physdescs = did.xpath("physdesc")
if len(physdescs) <= 1:
continue
last_extent_altrender = ""
for i, physdesc in enumerate(physdescs):
if len(list(physdesc)) != 1:
last_extent_altrender = ""
continue
from utilities.utilities import EADDir
ead_dir = EADDir(input_dir=r"C:\Users\wboyle\PycharmProjects\without-reservations\Real_Masters_all")
def fix_portions(ead):
for did in ead.tree.xpath("//did"):
physdescs = did.xpath("physdesc")
# if len(physdescs) > 1:
# if all([len(physdesc.xpath("extent")) > 0 for physdesc in physdescs]):
# for physdesc in physdescs:
# physdesc.attrib["altrender"] = "part"
if len(physdescs) == 1:
if any([tag.tag == "extent" for tag in list(physdescs[0])]):
physdescs[0].attrib["altrender"] = "whole"
def fix_lone_container_summaries(ead):
for did in ead.tree.xpath("//did"):
physdescs = did.xpath("physdesc")
if len(physdescs) <= 1:
continue
last_extent_altrender = ""
for i, physdesc in enumerate(physdescs):
if len(list(physdesc)) != 1:
last_extent_altrender = ""
continue
if physdesc[0].tag != "extent":
last_extent_altrender = ""
continue
