def try_merge(e1, edition_key, existing):
thing_type = existing.type.key
if thing_type == '/type/delete':
return False
assert thing_type == '/type/edition'
rec2 = {}
rec2['full_title'] = existing.title
if existing.subtitle:
rec2['full_title'] += ' ' + existing.subtitle
for f in 'isbn', 'isbn_10', 'isbn_13', 'lccn', 'publish_country', 'publishers', 'publish_date':
if existing.get(f):
rec2[f] = existing[f]
if existing.authors:
rec2['authors'] = []
for a in existing.authors:
author_type = a.type.key
while author_type == '/type/delete' or author_type == '/type/redirect':
if author_type == '/type/delete':
a = undelete_author(a)
author_type = a.type.key
continue
if author_type == '/type/redirect':
a = web.ctx.site.get(a.location)
author_type = a.type.key
continue
assert author_type == '/type/author'
assert a['name']
rec2['authors'].append({'name': a['name'], 'db_name': db_name(a)})
e2 = build_marc(rec2)
return attempt_merge(e1, e2, threshold, debug=False)
def test_merge():
bpl = {'authors': [{'birth_date': u'1897',
'db_name': u'Green, Constance McLaughlin 1897-',
'entity_type': 'person',
'name': u'Green, Constance McLaughlin',
'personal_name': u'Green, Constance McLaughlin'}],
'full_title': u'Eli Whitney and the birth of American technology',
'isbn': [u'188674632X'],
'normalized_title': u'eli whitney and the birth of american technology',
'number_of_pages': 215,
'publish_date': '1956',
'publishers': [u'HarperCollins', u'[distributed by Talman Pub.]'],
'short_title': u'eli whitney and the birth',
'source_record_loc': 'bpl101.mrc:0:1226',
'titles': [u'Eli Whitney and the birth of American technology',
u'eli whitney and the birth of american technology']}
lc = {'authors': [{'birth_date': u'1897',
'db_name': u'Green, Constance McLaughlin 1897-',
'entity_type': 'person',
'name': u'Green, Constance McLaughlin',
'personal_name': u'Green, Constance McLaughlin'}],
'full_title': u'Eli Whitney and the birth of American technology.',
'isbn': [],
'normalized_title': u'eli whitney and the birth of american technology',
'number_of_pages': 215,
'publish_date': '1956',
'publishers': ['Little, Brown'],
'short_title': u'eli whitney and the birth',
'source_record_loc': 'marc_records_scriblio_net/part04.dat:119539872:591',
'titles': [u'Eli Whitney and the birth of American technology.',
u'eli whitney and the birth of american technology']}
assert compare_authors(bpl, lc) == ('authors', 'exact match', 125)
threshold = 875
assert attempt_merge(bpl, lc, threshold) is True
def try_merge(e1, edition_key, existing):
thing_type = existing.type.key
if thing_type == '/type/delete':
return False
assert thing_type == '/type/edition'
rec2 = {}
rec2['full_title'] = existing.title
if existing.subtitle:
rec2['full_title'] += ' ' + existing.subtitle
if existing.lccn:
rec2['lccn'] = existing.lccn
rec2['authors'] = [{
'name': a.name,
'db_name': db_name(a)
} for a in existing.authors]
if existing.publishers:
rec2['publishers'] = existing.publishers
if existing.publish_date:
rec2['publisher_date'] = existing.publish_date
e2 = build_marc(rec2)
print
print 'e1:', e1
print 'e2:', e2
return attempt_merge(e1, e2, threshold, debug=True)
def try_merge(e1, edition_key, existing):
thing_type = existing.type.key
if thing_type == '/type/delete':
return False
assert thing_type == '/type/edition'
rec2 = {}
rec2['full_title'] = existing.title
if existing.subtitle:
rec2['full_title'] += ' ' + existing.subtitle
for f in 'isbn', 'isbn_10', 'isbn_13', 'lccn', 'publish_country', 'publishers', 'publish_date':
if existing.get(f):
rec2[f] = existing[f]
if existing.authors:
rec2['authors'] = []
for a in existing.authors:
author_type = a.type.key
while author_type == '/type/delete' or author_type == '/type/redirect':
if author_type == '/type/delete':
a = undelete_author(a)
author_type = a.type.key
continue
if author_type == '/type/redirect':
a = web.ctx.site.get(a.location)
author_type = a.type.key
continue
assert author_type == '/type/author'
assert a['name']
rec2['authors'].append({'name': a['name'], 'db_name': db_name(a)})
e2 = build_marc(rec2)
return attempt_merge(e1, e2, threshold, debug=False)
def try_merge(e1, edition_key, existing):
"""
Converts the existing edition into a comparable dict and performs a
thresholded comparison to decide whether they are the same.
:param dict e1:
:param str edition_key:
:param Thing existing: Edition object that most likely matches e1, the object of edition_key
:rtype: bool
:return: Whether e1 is sufficiently the same as the 'existing' edition
"""
thing_type = existing.type.key
if thing_type == '/type/delete':
return False
assert thing_type == '/type/edition'
rec2 = {}
rec2['full_title'] = existing.title
if existing.subtitle:
rec2['full_title'] += ' ' + existing.subtitle
for f in 'isbn', 'isbn_10', 'isbn_13', 'lccn', 'publish_country', 'publishers', 'publish_date':
if existing.get(f):
rec2[f] = existing[f]
if existing.authors:
rec2['authors'] = []
for a in existing.authors:
while a.type.key == '/type/redirect':
a = web.ctx.site.get(a.location)
if a.type.key == '/type/author':
assert a['name']
rec2['authors'].append({
'name': a['name'],
'db_name': db_name(a)
})
e2 = build_marc(rec2)
return attempt_merge(e1, e2, threshold)
def test_merge2():
amazon = {'publishers': [u'Collins'], 'isbn_10': ['0002167530'], 'number_of_pages': 287, 'short_title': u'sea birds britain ireland', 'normalized_title': u'sea birds britain ireland', 'full_title': u'Sea Birds Britain Ireland', 'titles': [u'Sea Birds Britain Ireland', u'sea birds britain ireland'], 'publish_date': u'1975',
'authors': [{'name': 'Stanley Cramp', 'db_name': 'Cramp, Stanley'}]}
marc = {'publisher': [u'Collins'], 'isbn_10': [u'0002167530'], 'short_title': u'seabirds of britain and i', 'normalized_title': u'seabirds of britain and ireland', 'full_title': u'seabirds of Britain and Ireland', 'titles': [u'seabirds of Britain and Ireland', u'seabirds of britain and ireland'], 'publish_date': '1974', 'authors': [{'db_name': u'Cramp, Stanley.', 'entity_type': 'person', 'name': u'Cramp, Stanley.', 'personal_name': u'Cramp, Stanley.'}], 'source_record_loc': 'marc_records_scriblio_net/part08.dat:61449973:855'}
threshold = 875
# build_marc() will place all isbn_ types in the 'isbn' field.
# compare_author_fields() expects all authors to have a db_name
assert attempt_merge(build_marc(amazon), build_marc(marc), threshold, debug=True)
def try_merge(e1, edition_key, existing):
"""
Converts the existing edition into a comparable dict and performs a
thresholded comparison to decide whether they are the same.
Used by add_book.load() -> add_book.find_match() to check whether two
editions match.
:param dict e1: Output of build_marc(import record candidate)
:param str edition_key: edition key of existing
:param Thing existing: Edition object to be tested against e1, the object of edition_key
:rtype: bool
:return: Whether e1 is sufficiently the same as the 'existing' edition
"""
thing_type = existing.type.key
if thing_type == '/type/delete':
return False
# FIXME: will fail if existing is a redirect.
assert thing_type == '/type/edition'
rec2 = {}
rec2['full_title'] = existing.title
if existing.subtitle:
rec2['full_title'] += ' ' + existing.subtitle
for f in 'isbn', 'isbn_10', 'isbn_13', 'lccn', 'publish_country', 'publishers', 'publish_date':
if existing.get(f):
rec2[f] = existing[f]
if existing.authors:
rec2['authors'] = []
for a in existing.authors:
while a.type.key == '/type/redirect':
a = web.ctx.site.get(a.location)
if a.type.key == '/type/author':
assert a['name']
rec2['authors'].append({
'name': a['name'],
'db_name': db_name(a)
})
e2 = build_marc(rec2)
return attempt_merge(e1, e2, threshold)
def test_author_contrib():
rec1 = {'authors': [{'db_name': u'Bruner, Jerome S.', 'name': u'Bruner, Jerome S.'}],
'full_title': u'Contemporary approaches to cognition a symposium held at the University of Colorado.',
'number_of_pages': 210,
'publish_country': 'xxu',
'publish_date': '1957',
'publishers': [u'Harvard U.P']}
rec2 = {'authors': [{'db_name': u'University of Colorado (Boulder campus). Dept. of Psychology.',
'name': u'University of Colorado (Boulder campus). Dept. of Psychology.'}],
'contribs': [{'db_name': u'Bruner, Jerome S.', 'name': u'Bruner, Jerome S.'}],
'full_title': u'Contemporary approaches to cognition a symposium held at the University of Colorado',
'lccn': ['57012963'],
'number_of_pages': 210,
'publish_country': 'mau',
'publish_date': '1957',
'publishers': [u'Harvard University Press']}
e1 = build_marc(rec1)
e2 = build_marc(rec2)
assert compare_authors(e1, e2) == ('authors', 'exact match', 125)
threshold = 875
assert attempt_merge(e1, e2, threshold) is True
def try_merge(e1, edition_key, existing):
thing_type = existing.type.key
if thing_type == '/type/delete':
return False
assert thing_type == '/type/edition'
rec2 = {}
rec2['full_title'] = existing.title
if existing.subtitle:
rec2['full_title'] += ' ' + existing.subtitle
if existing.lccn:
rec2['lccn'] = existing.lccn
rec2['authors'] = [{'name': a.name, 'db_name': db_name(a)}
for a in existing.authors]
if existing.publishers:
rec2['publishers'] = existing.publishers
if existing.publish_date:
rec2['publisher_date'] = existing.publish_date
e2 = build_marc(rec2)
print
print 'e1:', e1
print 'e2:', e2
return attempt_merge(e1, e2, threshold, debug=True)