def test_range():
"""Parses YYYY/YYYY into a range of years."""
assert year_parser.integer_years(["1937/1939", "1942/1943"]) == [
1937,
1938,
1939,
1942,
1943,
]
#Parses YYY/YYYY into a range of years.
assert year_parser.integer_years(["990/1000"]) == [
990,
991,
992,
993,
994,
995,
996,
997,
998,
999,
1000
]
def test_duplicates():
"""Deduplicates elements in output."""
assert year_parser.integer_years(["1934-06/1935-07", "1934-06-01", "1934"]) == [
1934,
1935,
]
def test_multiple_dates():
"""Parses multiple input values into a list of outputs."""
assert year_parser.integer_years(["1941-10-01", "1935", "1945"]) == [
1935,
1941,
1945,
]
def test_range():
"""Parses YYYY/YYYY into a range of years."""
assert year_parser.integer_years(["1937/1939", "1942/1943"]) == [
1937,
1938,
1939,
1942,
1943,
]
def map_record(row: DLCSRecord, config: typing.Dict) -> UrsusRecord:
"""Maps a metadata record from CSV to Ursus Solr.
Args:
record: A mapping representing the CSV record.
Returns:
A mapping representing the record to submit to Solr.
"""
record: UrsusRecord = {
field_name: map_field_value(row, field_name, config=config)
for field_name in mapper.FIELD_MAPPING
}
# thumbnail
record["thumbnail_url_ss"] = (record.get("thumbnail_url_ss")
or thumbnail_from_child(record,
config=config)
or thumbnail_from_manifest(record))
# collection name
if "Parent ARK" in row and row["Parent ARK"] in config["collection_names"]:
dlcs_collection_name = config["collection_names"][row["Parent ARK"]]
record["dlcs_collection_name_tesim"] = [dlcs_collection_name]
# facet fields
record["features_sim"] = record.get("features_tesim")
record["genre_sim"] = record.get("genre_tesim")
record["human_readable_language_sim"] = record.get(
"human_readable_language_tesim")
record["human_readable_resource_type_sim"] = record.get(
"resource_type_tesim")
record["location_sim"] = record.get("location_tesim")
record["member_of_collections_ssim"] = record.get(
"dlcs_collection_name_tesim")
record["named_subject_sim"] = record.get("named_subject_tesim")
record["place_of_origin_sim"] = record.get("place_of_origin_tesim")
record["script_sim"] = record.get("script_tesim")
record["subject_sim"] = record.get("subject_tesim")
record["support_sim"] = record.get("support_tesim")
record["writing_system_sim"] = record.get("writing_system_tesim")
record["year_isim"] = year_parser.integer_years(
record.get("normalized_date_tesim"))
# sort fields
titles = record.get("title_tesim")
if isinstance(titles, typing.Sequence) and len(titles) >= 1:
record["sort_title_ssort"] = titles[0]
years = record.get("year_isim")
if isinstance(years, typing.Sequence) and len(years) >= 1:
record["sort_year_isi"] = min(years)
return record
def map_record(row: DLCSRecord, solr_client: Solr,
config: typing.Dict) -> UrsusRecord:
"""Maps a metadata record from CSV to Ursus Solr.
Args:
record: A mapping representing the CSV record.
Returns:
A mapping representing the record to submit to Solr.
"""
record: UrsusRecord = {
field_name: map_field_value(row, field_name, config=config)
for field_name in mapper.FIELD_MAPPING
}
# THUMBNAIL
record["thumbnail_url_ss"] = (record.get("thumbnail_url_ss")
or thumbnail_from_child(record,
config=config)
or thumbnail_from_manifest(record))
# COLLECTION NAME
if "Parent ARK" in row and row["Parent ARK"] in config["collection_names"]:
dlcs_collection_name = config["collection_names"][row["Parent ARK"]]
record["dlcs_collection_name_tesim"] = [dlcs_collection_name]
# FIELDS
record["uniform_title_sim"] = record.get("uniform_title_tesim")
record["architect_sim"] = record.get("architect_tesim")
record["author_sim"] = record.get("author_tesim")
record["illuminator_sim"] = record.get("illuminator_tesim")
record["scribe_sim"] = record.get("scribe_tesim")
record["rubricator_sim"] = record.get("rubricator_tesim")
record["commentator_sim"] = record.get("commentator_tesim")
record["translator_sim"] = record.get("translator_tesim")
record["lyricist_sim"] = record.get("lyricist_tesim")
record["composer_sim"] = record.get("composer_tesim")
record["illustrator_sim"] = record.get("illustrator_tesim")
record["editor_sim"] = record.get("editor_tesim")
record["calligrapher_sim"] = record.get("calligrapher_tesim")
record["engraver_sim"] = record.get("engraver_tesim")
record["printmaker_sim"] = record.get("printmaker_tesim")
record["human_readable_language_sim"] = record.get(
"human_readable_language_tesim")
record["names_sim"] = name_fields(record)
record["keywords_sim"] = keywords_fields(record)
# explicit
record["features_sim"] = record.get("features_tesim")
# incipit
# inscription
record["script_sim"] = record.get("script_tesim")
record["writing_system_sim"] = record.get("writing_system_tesim")
record["year_isim"] = year_parser.integer_years(
record.get("normalized_date_tesim"))
record["date_dtsim"] = solr_transformed_dates(
solr_client,
(date_parser.get_dates(record.get("normalized_date_tesim"))))
record["place_of_origin_sim"] = record.get("place_of_origin_tesim")
record["associated_name_sim"] = record.get("associated_name_tesim")
record["form_sim"] = record.get("form_ssi")
record["support_sim"] = record.get("support_tesim")
record["genre_sim"] = record.get("genre_tesim")
record["subject_sim"] = record.get("subject_tesim")
record["location_sim"] = record.get("location_tesim")
record["named_subject_sim"] = record.get("named_subject_tesim")
record["human_readable_resource_type_sim"] = record.get(
"resource_type_tesim")
record["member_of_collections_ssim"] = record.get(
"dlcs_collection_name_tesim")
# SINAI INDEX
record["header_index_tesim"] = header_fields(record)
record["name_fields_index_tesim"] = name_fields_index(record)
# SORT FIELDS
titles = record.get("title_tesim")
if isinstance(titles, typing.Sequence) and len(titles) >= 1:
record["sort_title_ssort"] = titles[0]
# used a solr copyfield for shelfmark sorting
# shelfmarks = record.get("shelfmark_ssi")
# print(shelfmarks)
# if isinstance(shelfmarks, typing.Sequence) and len(shelfmarks) >= 1:
# print(shelfmarks[0])
# record["shelfmark_aplha_numeric_ssort"] = shelfmarks[0]
# -----------------------------------------------------------------------
years = record.get("year_isim")
if isinstance(years, typing.Sequence) and len(years) >= 1:
record["sort_year_isi"] = min(years)
dates = record.get("date_dtsim")
if isinstance(dates, typing.Sequence) and len(dates) >= 1:
record["date_dtsort"] = dates[0]
return record
def test_iso_8601():
"""Parses an iso 8601 standard string"""
assert year_parser.integer_years(["1941-10-01"]) == [1941]
def test_range_with_months():
"""Months can be included in range elements, but are ingored."""
assert year_parser.integer_years(["1934-06/1934-07"]) == [1934]
def test_unparseable():
"""Doesn't return anything for unparseable values, but still parses other elements in input."""
assert year_parser.integer_years(["1953", "[between 1928-1939]"]) == [1953]
def test_empty():
"""Returns an empty list if given an empty input."""
assert year_parser.integer_years([]) == []
def test_year_and_month():
"""Parses YYYY-MM"""
assert year_parser.integer_years(["1953-10"]) == [1953]
def test_just_year():
"""Parses a bare year."""
assert year_parser.integer_years(["1953"]) == [1953]