def test_prop_doesnt_exist():
"""Should return original JSON when prop doesn't exist."""
x = {"aaa": "BBB"}
r, c = _get_server_response(json.dumps(x), 'aaa%2Fddd')
pinfo(x,r,c)
print_error_log()
assert_same_jsons(c, x)
def test_setting_empty_type_from_format():
"Should set empty type according to format field according to type mapping."
DATA = [
{"in": {"format": "audio/mp3"}, "out": {"type": "sound"}},
{"in": {"format": "image/jpg"}, "out": {"type": "image"}},
{"in": {"format": "video/mpeg"}, "out": {"type": "moving image"}},
{"in": {"format": "text/calendar"}, "out": {"type": "text"}},
{"in": {"format": "audio"}, "out": {"format": "audio"}},
{"in": {"format": "something strange"}, "out": {"format": "something strange"}},
]
FORMATS = ["audio"]
EXPECTED_TYPES = []
INPUT = {"sourceResource": {"format": "FORMAT", "type": ""}}
EXPECTED = {"sourceResource": {"format": "FORMAT", "type": "TYPE"}}
for d in DATA:
INPUT["sourceResource"] = d["in"]
js = json.dumps(INPUT)
url = server() + "enrich-format?prop=sourceResource/format"
resp, content = H.request(url, "POST", body=js)
# pinfo(content)
pinfo(INPUT)
assert str(resp.status).startswith("2")
EXPECTED["sourceResource"] = d["out"]
assert_same_jsons(EXPECTED, content)
def test_prop_doesnt_exist():
"""Should return original JSON when prop doesn't exist."""
x = {"aaa": "BBB"}
r, c = _get_server_response(json.dumps(x), 'aaa%2Fddd')
pinfo(x, r, c)
print_error_log()
assert_same_jsons(c, x)
def test_populating_publisher_field():
INPUT = {
"freetext": {
"publisher": [
{
"#text": "Glossary of Coins and Currency Terms",
"@label": "Publication title"
},
{
"#text": "http://americanhistory.si.edu/coins/glossary.cfm",
"@label": "Publication URL"
},
{
"#text": "xx",
"@label": "Publisher"
}
],
}
}
EXPECTED_PUBLISHER = {
"publisher": ["xx"]
}
resp, content = _get_server_response(INPUT)
print_error_log()
assert resp["status"].startswith("2")
CONTENT = json.loads(content)
pinfo(content)
assert_same_jsons(EXPECTED_PUBLISHER, CONTENT["sourceResource"])
def test_substitute_with_list_of_dictionaries():
"""
Should convert all dicts in a list.
"""
data = {
"xxx": "yyy",
"aaa": {
"bbb": "ccc",
"xxx": [
{"eee": "aaa"},
{"xxx": "eee"},
{"eee": "bbb"}
]
}
}
INPUT = json.dumps(data)
data["aaa"]["xxx"] = [
{"eee": "AAA222"},
{"xxx": "eee"},
{"eee": "BBB222"},
]
EXPECTED_OUTPUT = json.dumps(data)
resp, content = _get_server_response(INPUT, "aaa/xxx/eee", "aaa/xxx/eee", "test2")
print_error_log()
pinfo(resp, content)
assert resp.status == 200
assert_same_jsons(content, EXPECTED_OUTPUT)
def test_missing_value_in_dict():
"""Should do nothing when there is no such value in dictionary."""
INPUT = {"a": "b"}
resp, content = _get_server_response(json.dumps(INPUT), "a", "x", "test")
print_error_log()
pinfo(resp, content)
assert resp.status == 200
assert_same_jsons(content, INPUT)
def test_missing_value_in_dict():
"""Should do nothing when there is no such value in dictionary."""
INPUT = {"a": "b"}
resp, content = _get_server_response(json.dumps(INPUT), "a", "x", "test")
print_error_log()
pinfo(resp, content)
assert resp.status == 200
assert_same_jsons(content, INPUT)
def test_substitution_with_missing_key():
"""
Should return the same JSON when the key is missing from substitution.
"""
INPUT = '{"aaa":"bbb"}'
resp, content = _get_server_response(INPUT, "bbb", "bbb", "test")
print_error_log()
pinfo(content)
assert resp.status == 200
assert_same_jsons(INPUT, content)
def test_substitution_with_missing_key():
"""
Should return the same JSON when the key is missing from substitution.
"""
INPUT = '{"aaa":"bbb"}'
resp, content = _get_server_response(INPUT, "bbb", "bbb", "test")
print_error_log()
pinfo(content)
assert resp.status == 200
assert_same_jsons(INPUT, content)
def test_setting_missing_type_for_missing_format():
"Should not change anything."
INPUT = {"format": None, "type": ""}
js = json.dumps(INPUT)
url = server() + "enrich-format?prop=format&type_field=type"
resp, content = H.request(url, "POST", body=js)
pinfo(content)
assert str(resp.status).startswith("2")
result = json.loads(content)
assert_same_jsons(INPUT, content)
def test_populating_data_provider_field():
INPUT = {
"descriptiveNonRepeating": {
"data_source": "Smithsonian Institution Archives",
}
}
resp, content = _get_server_response(INPUT)
pinfo(content)
print_error_log()
assert resp["status"].startswith("2")
CONTENT = json.loads(content)
assert CONTENT["dataProvider"] == "Smithsonian Institution Archives"
def test_setting_missing_type_for_missing_format():
"Should not change anything."
INPUT = {"format": None, "type": ""}
js = json.dumps(INPUT)
url = server() + "enrich-format?prop=format&type_field=type"
resp, content = H.request(url, "POST", body=js)
pinfo(content)
assert str(resp.status).startswith("2")
result = json.loads(content)
assert_same_jsons(INPUT, content)
def test_setting_missing_type_from_format():
"Should set type according to format field."
INPUT = {"sourceResource": {"format": "image/jpg"}}
EXPECTED = {"sourceResource": {"type": "image"}}
js = json.dumps(INPUT)
url = server() + "enrich-format?prop=sourceResource/format&type_field=sourceResource/type"
resp, content = H.request(url, "POST", body=js)
pinfo(content)
assert str(resp.status).startswith("2")
result = json.loads(content)
assert_same_jsons(EXPECTED, content)
def test_enrich_date_date_parse_format_yyyy_mm_dd():
"""Correctly transform a date of format YYYY-MM-DD"""
INPUT = {"date": "1928-05-20"}
EXPECTED = {"date": {"begin": u"1928-05-20", "end": u"1928-05-20", "displayDate": "1928-05-20"}}
url = server() + "enrich_earliest_date?prop=date"
resp, content = H.request(url, "POST", body=json.dumps(INPUT))
assert str(resp.status).startswith("2")
pinfo(resp, content)
result = json.loads(content)
assert result["date"] == EXPECTED["date"]
def test_dc_data_provider():
"""Should convert data providers for Digital Commonwealth."""
data = [
("Beverly High School", "Beverly High School Digital Collection"),
("Brookline Public Library", "Brookline Photograph Collection"),
("C/W MARS", "Amherst Collection"),
("Essex Agricultural and Technical High School", "Essex Aggie Digital Collection"),
("Framingham State University", "Henry Whittemore Library"),
]
for d in data:
INPUT = {"a": d[1]}
EXPECTED_OUTPUT = {"a": d[1], "b": d[0]}
resp, content = _get_server_response(json.dumps(INPUT), "a", "b", "dc_data_provider")
print_error_log()
pinfo(resp, content)
assert resp.status == 200
assert_same_jsons(content, EXPECTED_OUTPUT)
def test_setting_missing_type_from_format():
"Should set type according to format field."
INPUT = {
"sourceResource": {
"format": "image/jpg",
}
}
EXPECTED = {"sourceResource": {"type": "image"}}
js = json.dumps(INPUT)
url = server(
) + "enrich-format?prop=sourceResource/format&type_field=sourceResource/type"
resp, content = H.request(url, "POST", body=js)
pinfo(content)
assert str(resp.status).startswith("2")
result = json.loads(content)
assert_same_jsons(EXPECTED, content)
def test_enrich_type_cleanup():
"Test type normalization"
INPUT = {
"type": ["Still Images", "Moving Images", "Moving Image", "Text", "Statue"]
}
EXPECTED = {
u'type': ["image", "moving image", "moving image", "text"],
u'TBD_physicalformat': ["Statue"]
}
url = server() + "enrich-type?prop=type&format_field=TBD_physicalformat"
resp, content = H.request(url, "POST", body=json.dumps(INPUT))
print_error_log()
assert str(resp.status).startswith("2")
result = json.loads(content)
pinfo(content)
assert result['type'] == EXPECTED['type']
def test_enrich_type_cleanup():
"Test type normalization"
INPUT = {
"type":
["Still Images", "Moving Images", "Moving Image", "Text", "Statue"]
}
EXPECTED = {
u'type': ["image", "moving image", "moving image", "text"],
u'TBD_physicalformat': ["Statue"]
}
url = server() + "enrich-type?prop=type&format_field=TBD_physicalformat"
resp, content = H.request(url, "POST", body=json.dumps(INPUT))
print_error_log()
assert str(resp.status).startswith("2")
result = json.loads(content)
pinfo(content)
assert result['type'] == EXPECTED['type']
def test_enrich_date_date_parse_format_yyyy_mm_dd():
"""Correctly transform a date of format YYYY-MM-DD"""
INPUT = {"date": "1928-05-20"}
EXPECTED = {
'date': {
'begin': u'1928-05-20',
'end': u'1928-05-20',
'displayDate': '1928-05-20'
}
}
url = server() + "enrich_earliest_date?prop=date"
resp, content = H.request(url, "POST", body=json.dumps(INPUT))
assert str(resp.status).startswith("2")
pinfo(resp, content)
result = json.loads(content)
assert result['date'] == EXPECTED['date']
def test_enrich_date_date_parse_format_yyyy_00_00():
"""Strip off bogus MM-DD from YYYY-00-00"""
INPUT = {"date": "1990-00-00"}
EXPECTED = {
'date': [{
'begin': u'1990',
'end': u'1990',
'displayDate': '1990'
}]
}
url = server() + "enrich_earliest_date?prop=date"
resp, content = H.request(url, "POST", body=json.dumps(INPUT))
assert str(resp.status).startswith("2")
pinfo(resp, content)
result = json.loads(content)
assert result['date'] == EXPECTED['date']
def test_dc_data_provider():
"""Should convert data providers for Digital Commonwealth."""
data = [
("Beverly High School", "Beverly High School Digital Collection"),
("Brookline Public Library", "Brookline Photograph Collection"),
("C/W MARS", "Amherst Collection"),
("Essex Agricultural and Technical High School",
"Essex Aggie Digital Collection"),
("Framingham State University", "Henry Whittemore Library"),
]
for d in data:
INPUT = {"a": d[1]}
EXPECTED_OUTPUT = {"a": d[1], "b": d[0]}
resp, content = _get_server_response(json.dumps(INPUT), "a", "b",
"dc_data_provider")
print_error_log()
pinfo(resp, content)
assert resp.status == 200
assert_same_jsons(content, EXPECTED_OUTPUT)
def test_substitute_with_list_of_dictionaries():
"""
Should convert all dicts in a list.
"""
data = {
"xxx": "yyy",
"aaa": {
"bbb": "ccc",
"xxx": [{
"eee": "aaa"
}, {
"xxx": "eee"
}, {
"eee": "bbb"
}]
}
}
INPUT = json.dumps(data)
data["aaa"]["xxx"] = [
{
"eee": "AAA222"
},
{
"xxx": "eee"
},
{
"eee": "BBB222"
},
]
EXPECTED_OUTPUT = json.dumps(data)
resp, content = _get_server_response(INPUT, "aaa/xxx/eee", "aaa/xxx/eee",
"test2")
print_error_log()
pinfo(resp, content)
assert resp.status == 200
assert_same_jsons(content, EXPECTED_OUTPUT)
def test_populating_title():
LABELS = (True, "Title"), (True, "title"), (False, "aaa"), (False, "bbb")
INPUT = {
"descriptiveNonRepeating": {
"title": {
"@label": "",
"#text": "tt",
}
}
}
for d in LABELS:
INPUT["descriptiveNonRepeating"]["title"]["@label"] = d[1]
resp, content = _get_server_response(INPUT)
#print_error_log()
pinfo(resp, content)
assert resp["status"].startswith("2")
CONTENT = json.loads(content)
if d[0]:
assert_same_jsons({"title": "tt"}, CONTENT["sourceResource"])
else:
assert "sourceResource" not in CONTENT
def test_setting_empty_type_from_format():
"Should set empty type according to format field according to type mapping."
DATA = [{
"in": {
"format": "audio/mp3"
},
"out": {
"type": "sound"
}
}, {
"in": {
"format": "image/jpg"
},
"out": {
"type": "image"
}
}, {
"in": {
"format": "video/mpeg"
},
"out": {
"type": "moving image"
}
}, {
"in": {
"format": "text/calendar"
},
"out": {
"type": "text"
}
}, {
"in": {
"format": "audio"
},
"out": {
"format": "audio"
}
}, {
"in": {
"format": "something strange"
},
"out": {
"format": "something strange"
}
}]
FORMATS = ["audio"]
EXPECTED_TYPES = []
INPUT = {"sourceResource": {"format": "FORMAT", "type": ""}}
EXPECTED = {"sourceResource": {"format": "FORMAT", "type": "TYPE"}}
for d in DATA:
INPUT["sourceResource"] = d["in"]
js = json.dumps(INPUT)
url = server() + "enrich-format?prop=sourceResource/format"
resp, content = H.request(url, "POST", body=js)
#pinfo(content)
pinfo(INPUT)
assert str(resp.status).startswith("2")
EXPECTED["sourceResource"] = d["out"]
assert_same_jsons(EXPECTED, content)
def test_populating_collection_name():
INPUT = {
"collection": {
"@id": "http://dp.la/api/collections/smithsonian--nmafa_files_1964-2008_[national_museum_of_african_art_u.s._office_of_the_director]",
"title": "nmafa_files_1964-2008_[national_museum_of_african_art_u.s._office_of_the_director]"
},
"freetext": {
"physicalDescription": {
"#text": "4 cu. ft. (4 record storage boxes)",
"@label": "Physical description"
},
"name": [
{
"#text": "National Museum of African Art (U.S.) Office of the Director",
"@label": "Creator"
},
{
"#text": "Fiske, Patricia L",
"@label": "Subject"
},
{
"#text": "Patton, Sharon F",
"@label": "Subject"
},
{
"#text": "Robbins, Warren M",
"@label": "Subject"
},
{
"#text": "Walker, Roslyn A",
"@label": "Subject"
},
{
"#text": "Williams, Sylvia H",
"@label": "Subject"
},
{
"#text": "Reinhardt, John E",
"@label": "Subject"
},
{
"#text": "Museum of African Art (U.S.)",
"@label": "Subject"
},
{
"#text": "Quadrangle Complex Quadrangle Museum Project",
"@label": "Subject"
}
],
"setName": {
"#text": "NMAfA Files 1964-2008 [National Museum of African Art (U.S.) Office of the Director]",
"@label": "See more items in"
},
}
}
EXPECTED_COLLECTION = {
"@id": "http://dp.la/api/collections/smithsonian--nmafa_files_1964-2008_[national_museum_of_african_art_u.s._office_of_the_director]",
"title": "NMAfA Files 1964-2008 [National Museum of African Art (U.S.) Office of the Director]",
}
resp, content = _get_server_response(INPUT)
assert resp["status"].startswith("2")
CONTENT = json.loads(content)
pinfo(content,CONTENT["sourceResource"]["collection"])
assert_same_jsons(EXPECTED_COLLECTION, CONTENT["sourceResource"]["collection"])