def test_single_valued_datespan():
# dating: -68 to -68
# EDCS-ID: EDCS-24900077
args = argparse.Namespace(EDCS='24900077',
publication=None,
province=None,
place=None,
operator='and',
term2=None,
dating_from=None,
dating_to=None,
inscription_genus=None,
and_not_inscription_genus=None,
to_file=None,
from_file=None,
debug=True,
term1='%')
test_output = scrape(args, prevent_write=True)
assert test_output[0]['dating from'] == -68
assert test_output[0]['dating to'] == -68
assert test_output[0]['date not before'] == -68
assert test_output[0]['date not after'] == -68
def test_missing_first_date():
# dating: to 100
# EDCS-ID: EDCS-34901010
args = argparse.Namespace(EDCS='34901010',
publication=None,
province=None,
place=None,
operator='and',
term2=None,
dating_from=None,
dating_to=None,
inscription_genus=None,
and_not_inscription_genus=None,
to_file=None,
from_file=None,
debug=True,
term1='%')
test_output = scrape(args, prevent_write=True)
assert test_output[0]['dating from'] == None
assert test_output[0]['dating to'] == 100
assert test_output[0]['date not before'] == None
assert test_output[0]['date not after'] == 100
def test_inscription_vir():
# ./parse.py -e 24900101 % --debug
args = argparse.Namespace(EDCS='24900101',
publication=None,
province=None,
place=None,
operator='and',
term2=None,
dating_from=None,
dating_to=None,
inscription_genus=None,
and_not_inscription_genus=None,
to_file=None,
from_file=None,
debug=True,
term1='%')
test_output = scrape(args,
prevent_write=True,
show_inscription_transform=True)
assert "IIIIvir" in test_output[0]['inscription']
assert "IIIIvir" not in test_output[0]['inscription conservative cleaning']
assert "IIIIvir" not in test_output[0]['inscription interpretive cleaning']
assert "IIII vir " in test_output[0]['inscription conservative cleaning']
assert "IIII vir " in test_output[0]['inscription interpretive cleaning']
def test_inscription_three_middle():
# ./parse.py -e 09000264 20700224 % --debug
args = argparse.Namespace(EDCS='20700224',
publication=None,
province=None,
place=None,
operator='and',
term2=None,
dating_from=None,
dating_to=None,
inscription_genus=None,
and_not_inscription_genus=None,
to_file=None,
from_file=None,
debug=True,
term1='%')
test_output = scrape(args,
prevent_write=True,
show_inscription_transform=True)
assert "mo[numentum 3 vi]/olaverit" in test_output[0]['inscription']
assert "mo[numentum 3 vi]/olaverit" not in test_output[0][
'inscription conservative cleaning']
assert "mo[numentum 3 vi]/olaverit" not in test_output[0][
'inscription interpretive cleaning']
def test_inscription_substitution():
# ./parse.py -e 34100092 % --debug
args = argparse.Namespace(EDCS='15300609',
publication=None,
province=None,
place=None,
operator='and',
term2=None,
dating_from=None,
dating_to=None,
inscription_genus=None,
and_not_inscription_genus=None,
to_file=None,
from_file=None,
debug=True,
term1='%')
test_output = scrape(args,
prevent_write=True,
show_inscription_transform=True)
assert "sanc<t=I>issi<ma=AM>" in test_output[0]['inscription']
assert "sanc<t=I>issi<ma=AM>" not in test_output[0][
'inscription conservative cleaning']
assert "sanc<t=I>issi<ma=AM>" not in test_output[0][
'inscription interpretive cleaning']
def test_inscription_expanded_abbreviations():
# ./parse.py -e 27000432 % --debug
args = argparse.Namespace(EDCS='27000432',
publication=None,
province=None,
place=None,
operator='and',
term2=None,
dating_from=None,
dating_to=None,
inscription_genus=None,
and_not_inscription_genus=None,
to_file=None,
from_file=None,
debug=True,
term1='%')
test_output = scrape(args,
prevent_write=True,
show_inscription_transform=True)
assert "D(is) M(anibus)" in test_output[0]['inscription']
assert "D(is) M(anibus)" not in test_output[0][
'inscription conservative cleaning']
assert "D M " in test_output[0]['inscription conservative cleaning']
assert "Dis Manibus" in test_output[0]['inscription interpretive cleaning']
def test_inscription_restoration():
# ./parse.py -e 34100092 % --debug
args = argparse.Namespace(EDCS='34100092',
publication=None,
province=None,
place=None,
operator='and',
term2=None,
dating_from=None,
dating_to=None,
inscription_genus=None,
and_not_inscription_genus=None,
to_file=None,
from_file=None,
debug=True,
term1='%')
test_output = scrape(args,
prevent_write=True,
show_inscription_transform=True)
assert "nillae c[oniugi]" in test_output[0]['inscription']
assert "nillae c[oniugi]" not in test_output[0][
'inscription conservative cleaning']
assert "nillae c " in test_output[0]['inscription conservative cleaning']
assert "nillae coniugi" in test_output[0][
'inscription interpretive cleaning']
def test_random__middle_date():
# # dating: a: ; b: 71 to 100; c: ; d:
# EDCS-ID: EDCS-32001032
args = argparse.Namespace(EDCS='32001032',
publication=None,
province=None,
place=None,
operator='and',
term2=None,
dating_from=None,
dating_to=None,
inscription_genus=None,
and_not_inscription_genus=None,
to_file=None,
from_file=None,
debug=True,
term1='%')
test_output = scrape(args, prevent_write=True)
assert test_output[0]['dating from'] == 71
assert test_output[0]['dating to'] == 100
assert test_output[0]['date not before'] == 71
assert test_output[0]['date not after'] == 100
def test_language_with_trailing_imbalanced_doublequote():
# ./parse.py -e 78800166 % --debug
# csvcut -t -c 10,17 output/2021-07-30-EDCS_78800166+term1_%-1.tsv | csvlook
# | inscription | language |
# | ----------- | -------- |
# | // GR" | PALMYR |
args = argparse.Namespace(EDCS='78800166',
publication=None,
province=None,
place=None,
operator='and',
term2=None,
dating_from=None,
dating_to=None,
inscription_genus=None,
and_not_inscription_genus=None,
to_file=None,
from_file=None,
debug=True,
term1='%')
test_output = scrape(args,
prevent_write=True,
show_inscription_transform=True)
assert 'GR"' not in test_output[0]['inscription']
assert "PALMYR, GR" in test_output[0]['language']
def test_no_letter():
# 'raw dating': 'b: 96 to 96; 81 to 96',
args = argparse.Namespace(EDCS='72300077',
publication=None,
province=None,
place=None,
operator='and',
term2=None,
dating_from=None,
dating_to=None,
inscription_genus=None,
and_not_inscription_genus=None,
to_file=None,
from_file=None,
debug=True,
term1='%')
test_output = scrape(args, prevent_write=True)
assert test_output[0]['dating from'] == 96
assert test_output[0]['dating to'] == 96
assert test_output[0]['date not before'] == 81
assert test_output[0]['date not after'] == 96
def test_place():
# ./parse.py -e 16201127 % --debug
args = argparse.Namespace(EDCS='16201127',
publication=None,
province=None,
place=None,
operator='and',
term2=None,
dating_from=None,
dating_to=None,
inscription_genus=None,
and_not_inscription_genus=None,
to_file=None,
from_file=None,
debug=True,
term1='%')
test_output = scrape(args,
prevent_write=True,
show_inscription_transform=True)
assert '[]' not in test_output[0]['place']
assert "Acireale / Acium" in test_output[0]['place']
def test_material():
# ./parse.py -e 32001159 % --debug
args = argparse.Namespace(EDCS='32001159',
publication=None,
province=None,
place=None,
operator='and',
term2=None,
dating_from=None,
dating_to=None,
inscription_genus=None,
and_not_inscription_genus=None,
to_file=None,
from_file=None,
debug=True,
term1='%')
test_output = scrape(args,
prevent_write=True,
show_inscription_transform=True)
assert '[]' not in test_output[0]['Material']
assert "lapis" in test_output[0]['Material']
def test_publication():
# ./parse.py -e 78800166 % --debug
args = argparse.Namespace(EDCS='78800166',
publication=None,
province=None,
place=None,
operator='and',
term2=None,
dating_from=None,
dating_to=None,
inscription_genus=None,
and_not_inscription_genus=None,
to_file=None,
from_file=None,
debug=True,
term1='%')
test_output = scrape(args,
prevent_write=True,
show_inscription_transform=True)
assert "AE 1937, 00075" in test_output[0]['publication']
assert "[]" not in test_output[0]['publication']
def test_EDCS_ID():
# ./parse.py -e EDCS-07600345 % --debug
args = argparse.Namespace(EDCS='07600345',
publication=None,
province=None,
place=None,
operator='and',
term2=None,
dating_from=None,
dating_to=None,
inscription_genus=None,
and_not_inscription_genus=None,
to_file=None,
from_file=None,
debug=True,
term1='%')
test_output = scrape(args,
prevent_write=True,
show_inscription_transform=True)
assert "[]" not in test_output[0]['EDCS-ID']
assert re.match(r"EDCS-[0-9]{8,8}", test_output[0]['EDCS-ID'])
def test_no_letters_at_all():
# 'raw dating': '163 to 170; 163 to 163',
# ./parse.py -e 01000244 % --debug
args = argparse.Namespace(EDCS='01000244',
publication=None,
province=None,
place=None,
operator='and',
term2=None,
dating_from=None,
dating_to=None,
inscription_genus=None,
and_not_inscription_genus=None,
to_file=None,
from_file=None,
debug=True,
term1='%')
test_output = scrape(args, prevent_write=True)
assert test_output[0]['dating from'] == 163
assert test_output[0]['dating to'] == 170
assert test_output[0]['date not before'] == 163
assert test_output[0]['date not after'] == 170
def test_a_k_dates():
# dating: a: 196 to 196; b: 198 to 200; c: 171 to 300; d: 208 to 218; e: 180 to 222; f: 228 to 228; g: 234 to 234; h: 297 to 297; i: 171 to 300; j: 171 to 300; k: 171 to 300
# EDCS-ID: EDCS-72200182
args = argparse.Namespace(EDCS='72200182',
publication=None,
province=None,
place=None,
operator='and',
term2=None,
dating_from=None,
dating_to=None,
inscription_genus=None,
and_not_inscription_genus=None,
to_file=None,
from_file=None,
debug=True,
term1='%')
test_output = scrape(args, prevent_write=True)
assert test_output[0]['dating from'] == 196
assert test_output[0]['dating to'] == 196
assert test_output[0]['date not before'] == 171
assert test_output[0]['date not after'] == 300
def test_comment():
# ./parse.py -e 36400015 % --debug
args = argparse.Namespace(EDCS='36400015',
publication=None,
province=None,
place=None,
operator='and',
term2=None,
dating_from=None,
dating_to=None,
inscription_genus=None,
and_not_inscription_genus=None,
to_file=None,
from_file=None,
debug=True,
term1='%')
test_output = scrape(args,
prevent_write=True,
show_inscription_transform=True)
assert "comment DOI: 10.3406/crai.2005.22934" not in test_output[0][
'inscription']
assert "comment DOI: 10.3406/crai.2005.22934" in test_output[0]['Comment']
def test_status():
# ./parse.py -e 55701594 % --debug
args = argparse.Namespace(EDCS='55701594',
publication=None,
province=None,
place=None,
operator='and',
term2=None,
dating_from=None,
dating_to=None,
inscription_genus=None,
and_not_inscription_genus=None,
to_file=None,
from_file=None,
debug=True,
term1='%')
test_output = scrape(args,
prevent_write=True,
show_inscription_transform=True)
assert '[]' not in test_output[0]['status']
assert "sigilla impressa; tituli fabricationis" in test_output[0][
'status']
def test_digit_colon():
# digit with colon 3: ; -27 to 37
# EDCS-75100087
args = argparse.Namespace(EDCS='75100087',
publication=None,
province=None,
place=None,
operator='and',
term2=None,
dating_from=None,
dating_to=None,
inscription_genus=None,
and_not_inscription_genus=None,
to_file=None,
from_file=None,
debug=True,
term1='%')
test_output = scrape(args, prevent_write=True)
assert test_output[0]['dating from'] == -27
assert test_output[0]['dating to'] == 37
assert test_output[0]['date not before'] == -27
assert test_output[0]['date not after'] == 37
def test_inscription_substitution_edh():
# ./parse.py -e 63600442 % --debug
args = argparse.Namespace(EDCS='63600442',
publication=None,
province=None,
place=None,
operator='and',
term2=None,
dating_from=None,
dating_to=None,
inscription_genus=None,
and_not_inscription_genus=None,
to_file=None,
from_file=None,
debug=True,
term1='%')
test_output = scrape(args,
prevent_write=True,
show_inscription_transform=True)
assert "<F=P>urius" in test_output[0]['inscription']
assert "Purius" in test_output[0]['inscription conservative cleaning']
assert "Furius" in test_output[0]['inscription interpretive cleaning']
def on_button_clicked(b):
with out:
out.clear_output(wait=True)
if and_not_inscription_genus.value:
args.and_not_inscription_genus = and_not_inscription_genus.value
and_not_inscription_genus.value = ""
if dating_from.value:
args.dating_from = dating_from.value
dating_from.value = ""
if dating_to.value:
args.dating_to = dating_to.value
dating_to.value = ""
if EDCS.value:
args.EDCS = EDCS.value
EDCS.value = ""
if inscription_genus.value:
args.inscription_genus = inscription_genus.value
inscription_genus.value = ""
if operator.value:
args.operator = operator.value
if place.value:
args.place = place.value
place.value = ""
if province.value:
args.province = province.value
province.value = ""
if publication.value:
args.publication = [publication.value]
publication.value = []
if term1.value:
args.term1 = term1.value
term1.value = ""
if term2.value:
args.term2 = term2.value
term2.value = ""
# with widgets.Output(layout={'border': '1px solid black'}) as out:
display(
HTML(
"<p>Getting the inscriptions. This may take a few minutes (or hours), depending on the number of search results.</p>"
))
filename = parse.scrape(args)
OUTPUTS = Path("output")
file_outputs = {}
for output in OUTPUTS.glob("*.tsv"):
file_outputs[output.stat().st_mtime] = (output.name, output)
output_keys = sorted(file_outputs, reverse=True)
filenames = []
for key in output_keys:
filenames.append(file_outputs[key])
#print(filename)
# display(HTML("<a href='/tree/output/' target='_blank'>Full File List</a>"))
display(HTML("<ul>"))
for zipfile in filenames:
display(
HTML(f"<li><a href='{zipfile[1]}'>{zipfile[0]}</a></li>"))
display(HTML("</ul>"))
