Skip to content

read Library of Congress author name authority control from MARC #11262

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Sep 12, 2025
Merged

read Library of Congress author name authority control from MARC #11262

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 6 additions & 1 deletion openlibrary/catalog/marc/parse.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@
re_date = re.compile(r'^[0-9]+u*$')
re_question = re.compile(r'^\?+$')
re_lccn = re.compile(r'([ \dA-Za-z\-]{3}[\d/-]+).*')
re_lcnaf = re.compile(r'.*id.loc.gov/authorities/names/(n\w*\d)')
re_oclc = re.compile(r'^\(OCoLC\).*?0*(\d+)')
re_ocolc = re.compile('^ocolc *$', re.IGNORECASE)
re_ocn_or_ocm = re.compile(r'^oc[nm]0*(\d+) *$')
Expand Down Expand Up @@ -463,7 +464,7 @@ def read_author_person(field: MarcFieldBase, tag: str = '100') -> dict[str, Any]
and returns an author import dict.
"""
author: dict[str, Any] = {}
contents = field.get_contents('abcde46')
contents = field.get_contents('abcde046')
if 'a' not in contents and 'c' not in contents:
# Should have at least a name or title.
return author
Expand All @@ -486,6 +487,10 @@ def read_author_person(field: MarcFieldBase, tag: str = '100') -> dict[str, Any]
del author['personal_name'] # DRY names
if 'q' in contents:
author['fuller_name'] = ' '.join(contents['q'])
if '0' in contents: # Authority record control number or standard number
for value in contents['0']:
if m := re_lcnaf.match(value):
author['remote_ids'] = {'lc_naf': m.group(1)}
if '6' in contents: # noqa: SIM102 - alternate script name exists
if (link := field.rec.get_linkage(tag, contents['6'][0])) and (
name := link.get_subfield_values('a')
Expand Down
9 changes: 6 additions & 3 deletions openlibrary/catalog/marc/tests/test_data/bin_expect/880_Nihon_no_chasho.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,14 +20,16 @@
"birth_date": "1914",
"death_date": "1998",
"name": "林屋 辰三郎",
"entity_type": "person"
"entity_type": "person",
"remote_ids": {"lc_naf": "n81047233"}
},
{
"alternate_names": [
"Yokoi, Kiyoshi"
],
"name": "横井 清.",
"entity_type": "person"
"entity_type": "person",
"remote_ids": {"lc_naf": "n81089234"}
},
{
"alternate_names": [
Expand All @@ -36,7 +38,8 @@
"birth_date": "1940",
"death_date": "1960",
"name": "楢林 忠男",
"entity_type": "person"
"entity_type": "person",
"remote_ids": {"lc_naf": "n85206624"}
}
],
"subjects": [
Expand Down
3 changes: 3 additions & 0 deletions openlibrary/catalog/marc/tests/test_data/bin_expect/880_arabic_french_many_linkages.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,20 +22,23 @@
{
"name": "مودن، عبد الرحمن",
"entity_type": "person",
"remote_ids": {"lc_naf": "nr92001540"},
"alternate_names": [
"El Moudden, Abderrahmane"
]
},
{
"name": "بنحادة، عبد الرحيم",
"entity_type": "person",
"remote_ids": {"lc_naf": "nr97026593"},
"alternate_names": [
"Bin-Ḥāddah, ʻAbd al-Raḥīm"
]
},
{
"name": "غربي، محمد لزهر",
"entity_type": "person",
"remote_ids": {"lc_naf": "nr96019749"},
"alternate_names": [
"Gharbi, Mohamed Lazhar"
]
Expand Down
3 changes: 3 additions & 0 deletions openlibrary/catalog/marc/tests/test_parse.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -176,6 +176,8 @@ def test_read_author_person(self):
<datafield xmlns="http://www.loc.gov/MARC21/slim" tag="100" ind1="1" ind2="0">
<subfield code="a">Rein, Wilhelm,</subfield>
<subfield code="d">1809-1865.</subfield>
<subfield code="0">(uri) http://id.loc.gov/authorities/names/no2003007242</subfield>
<subfield code="0">(uri) http://viaf.org/viaf/sourceID/LC|no2003007242</subfield>
</datafield>"""
test_field = DataField(
None,
Expand All @@ -190,3 +192,4 @@ def test_read_author_person(self):
assert result['birth_date'] == '1809'
assert result['death_date'] == '1865'
assert result['entity_type'] == 'person'
assert result['remote_ids'] == {'lc_naf': 'no2003007242'}
Loading