def create_structmap(workspace, divs, structmap, filegrp, path=''):
"""Create structmap based on directory structure
"""
fptr_list = []
div_list = []
for div in divs.keys():
# It's a file if there is "-techmd.xml", lets create file+fptr
# elements
if div.endswith('-techmd.xml'):
div = div[:-len('-techmd.xml')]
div_path = encode_path(os.path.join(decode_path(path), div))
amdids = get_links_event_agent(workspace, div_path)
fileid = add_file_to_filesec(workspace, div_path, filegrp, amdids)
fptr = mets.fptr(fileid)
fptr_list.append(fptr)
# It's not a file, lets create a div element
else:
div_path = encode_path(os.path.join(decode_path(path), div))
amdids = get_links_event_agent(workspace, div_path)
_, dmdsec_id = ids_for_files(workspace, div_path, 'dmdsec.xml')
div_el = mets.div(type_attr=div, dmdid=dmdsec_id, admid=amdids)
div_list.append(div_el)
create_structmap(workspace, divs[div], div_el, filegrp, div_path)
# Add fptr list first, then div list
for fptr_elem in fptr_list:
structmap.append(fptr_elem)
for div_elem in div_list:
structmap.append(div_elem)
def test_decode_path():
"""Tests for the decode_path function."""
decoded_path = utils.decode_path('tests%2Ftestpath')
assert decoded_path == 'tests/testpath'
decoded_path = utils.decode_path('tests%2Ftestpath-testsuffix',
suffix='-testsuffix')
assert decoded_path == 'tests/testpath'
decoded_path = utils.decode_path('t%C3%A4sts%2Ft%C3%B8stpath')
assert decoded_path == 't\u00e4sts/t\u00f8stpath'
def div_structure(workspace):
"""Create div structure for directory-based structmap
"""
workspace_files = [fname.name for fname in scandir.scandir(workspace)]
techmd_files = [x for x in workspace_files if 'techmd' in x]
divs = tree()
for techmd_file in techmd_files:
add(divs, decode_path(techmd_file).split('/'))
return divs
def copy_files(workspace, data_dir):
"""Copy digital objects to workspace
"""
for entry in scandir(workspace):
if entry.name.endswith('-techmd.xml') and entry.is_file():
source = decode_path(entry.name, '-techmd.xml')
target = os.path.join(workspace, source)
if not os.path.exists(os.path.dirname(target)):
os.makedirs(os.path.dirname(target))
copyfile(os.path.join(data_dir, source), target)
def test_create_addml_with_flatfile(is_header):
"""Tests that ``create_addml`` adds flatFile element if optional
parameter flatfile_name is provided.
"""
addml_etree = create_addml.create_addml_metadata(
CSV_FILE, DELIMITER, is_header,
CHARSET, RECORDSEPARATOR, QUOTINGCHAR,
flatfile_name="path/to/test"
)
# Check that URL encoded path is written to flatFile element
flatfile = addml_etree.find(ADDML_NS + "flatFile")
assert decode_path(flatfile.get("name")) == "path/to/test"
def test_create_addml_with_flatfile(is_header):
"""Tests that ``create_addml`` adds flatFile element if optional
parameter flatfile_name is provided.
"""
addml_etree = create_addml.create_addml_metadata(
csv_file=CSV_FILE, delimiter=DELIMITER, isheader=is_header,
charset=CHARSET, record_separator=RECORDSEPARATOR,
quoting_char=QUOTINGCHAR, flatfile_name="path/to/test"
)
# Check that URL encoded path is written to flatFile element
flatfile = addml_etree.find(ADDML_NS + "flatFile")
assert decode_path(flatfile.get("name")) == "path/to/test"
def add_file_to_filesec(workspace, path, filegrp, amdids):
"""Add file element to fileSec.
"""
othermd_types = ['addml', 'mix', 'videomd', 'audiomd', 'textmd']
techmd_files, techmd_ids = ids_for_files(workspace, path, 'techmd.xml')
fileid = '_' + str(uuid4())
filepath = decode_path(techmd_files[0], '-techmd.xml')
othermd_ids = []
for mdtype in othermd_types:
othermd_ids = read_temp_othermdfile(workspace, mdtype, filepath,
othermd_ids)
file_el = mets.file_elem(fileid,
admid_elements=techmd_ids + amdids + othermd_ids,
loctype='URL',
xlink_href='file://%s' % filepath,
xlink_type='simple',
groupid=None)
filegrp.append(file_el)
return fileid
def test_create_addml_creator(testpath, isheader, exp_amd_files, exp_fields):
"""
Test that ``create_addml`` creates addml files and
md-reference file without unnecessary duplication.
"""
# Common expectations
exp_csvs = [
['tests/data/simple_csv.csv', 'tests/data/simple_csv_2.csv'],
['tests/data/csvfile.csv']
]
exp_flatfiles_child_count = [4, 3]
_create_addml(testpath, isheader)
# Check that md-reference and the ADDML-amd files with correct content
# are created
assert os.path.isfile(
os.path.join(testpath, 'create-addml-md-references.jsonl')
)
for amd_file_index, exp_amd_file in enumerate(exp_amd_files):
amd_file = os.path.join(testpath, exp_amd_file)
assert os.path.isfile(amd_file)
root = ET.parse(amd_file)
flat_files = root.find(ADDML_NS + "flatFiles")
# Verify the number of child elements in flatFiles
assert len(flat_files) == exp_flatfiles_child_count[amd_file_index]
# Verify that right CSV files are in flatFiles
for index, exp_csv in enumerate(exp_csvs[amd_file_index]):
assert decode_path(flat_files[index].get('name')) == exp_csv
# Verify fields within flatFiles
field_definitions = root.find(ADDML_NS + "fieldDefinitions")
for index, field in enumerate(field_definitions):
assert field.get('name') == exp_fields[amd_file_index][index]