def test_add_simplified_genres(self):
work = self._work(with_license_pool=True)
fantasy, ignore = Genre.lookup(self._db, "Fantasy", autocreate=True)
romance, ignore = Genre.lookup(self._db, "Romance", autocreate=True)
work.genres = [fantasy, romance]
record = Record()
Annotator.add_simplified_genres(record, work)
fields = record.get_fields("650")
[fantasy_field, romance_field] = sorted(fields, key=lambda x: x.get_subfields("a")[0])
eq_(["0", "7"], fantasy_field.indicators)
eq_("Fantasy", fantasy_field.get_subfields("a")[0])
eq_("Library Simplified", fantasy_field.get_subfields("2")[0])
eq_(["0", "7"], romance_field.indicators)
eq_("Romance", romance_field.get_subfields("a")[0])
eq_("Library Simplified", romance_field.get_subfields("2")[0])
# It also works with a materialized work.
self.add_to_materialized_view([work])
# The work is in the materialized view twice since it has two genres,
# but we can use either one.
[mw, ignore] = self._db.query(MaterializedWorkWithGenre).all()
record = Record()
Annotator.add_simplified_genres(record, mw)
fields = record.get_fields("650")
[fantasy_field, romance_field] = sorted(fields, key=lambda x: x.get_subfields("a")[0])
eq_(["0", "7"], fantasy_field.indicators)
eq_("Fantasy", fantasy_field.get_subfields("a")[0])
eq_("Library Simplified", fantasy_field.get_subfields("2")[0])
eq_(["0", "7"], romance_field.indicators)
eq_("Romance", romance_field.get_subfields("a")[0])
eq_("Library Simplified", romance_field.get_subfields("2")[0])
def test_add_series(self):
edition = self._edition()
edition.series = self._str
edition.series_position = 5
record = Record()
Annotator.add_series(record, edition)
self._check_field(record, "490", {
"a": edition.series,
"v": str(edition.series_position),
}, ["0", " "])
# If there's no series position, the same field is used without
# the v subfield.
edition.series_position = None
record = Record()
Annotator.add_series(record, edition)
self._check_field(record, "490", {
"a": edition.series,
}, ["0", " "])
[field] = record.get_fields("490")
eq_([], field.get_subfields("v"))
# If there's no series, the field is left out.
edition.series = None
record = Record()
Annotator.add_series(record, edition)
eq_([], record.get_fields("490"))
def test_add_title(self):
edition = self._edition()
edition.title = "The Good Soldier"
edition.sort_title = "Good Soldier, The"
edition.subtitle = "A Tale of Passion"
record = Record()
Annotator.add_title(record, edition)
[field] = record.get_fields("245")
self._check_field(
record, "245", {
"a": edition.title,
"b": edition.subtitle,
"c": edition.author,
}, ["0", "4"])
# If there's no subtitle or no author, those subfields are left out.
edition.subtitle = None
edition.author = None
record = Record()
Annotator.add_title(record, edition)
[field] = record.get_fields("245")
self._check_field(
record, "245", {
"a": edition.title,
}, ["0", "4"])
eq_([], field.get_subfields("b"))
eq_([], field.get_subfields("c"))
def test_add_contributors(self):
author = "a"
author2 = "b"
translator = "c"
# Edition with one author gets a 100 field and no 700 fields.
edition = self._edition(authors=[author])
edition.sort_author = "sorted"
record = Record()
Annotator.add_contributors(record, edition)
eq_([], record.get_fields("700"))
self._check_field(record, "100", {"a": edition.sort_author}, ["1", " "])
# Edition with two authors and a translator gets three 700 fields and no 100 fields.
edition = self._edition(authors=[author, author2])
edition.add_contributor(translator, Contributor.TRANSLATOR_ROLE)
record = Record()
Annotator.add_contributors(record, edition)
eq_([], record.get_fields("100"))
fields = record.get_fields("700")
for field in fields:
eq_(["1", " "], field.indicators)
[author_field, author2_field, translator_field] = sorted(fields, key=lambda x: x.get_subfields("a")[0])
eq_(author, author_field.get_subfields("a")[0])
eq_(Contributor.PRIMARY_AUTHOR_ROLE, author_field.get_subfields("e")[0])
eq_(author2, author2_field.get_subfields("a")[0])
eq_(Contributor.AUTHOR_ROLE, author2_field.get_subfields("e")[0])
eq_(translator, translator_field.get_subfields("a")[0])
eq_(Contributor.TRANSLATOR_ROLE, translator_field.get_subfields("e")[0])
def test_add_series(self):
edition = self._edition()
edition.series = self._str
edition.series_position = 5
record = Record()
Annotator.add_series(record, edition)
self._check_field(record, "490", {
"a": edition.series,
"v": str(edition.series_position),
}, ["0", " "])
# If there's no series position, the same field is used without
# the v subfield.
edition.series_position = None
record = Record()
Annotator.add_series(record, edition)
self._check_field(record, "490", {
"a": edition.series,
}, ["0", " "])
[field] = record.get_fields("490")
eq_([], field.get_subfields("v"))
# If there's no series, the field is left out.
edition.series = None
record = Record()
Annotator.add_series(record, edition)
eq_([], record.get_fields("490"))
def test_add_simplified_genres(self):
work = self._work(with_license_pool=True)
fantasy, ignore = Genre.lookup(self._db, "Fantasy", autocreate=True)
romance, ignore = Genre.lookup(self._db, "Romance", autocreate=True)
work.genres = [fantasy, romance]
record = Record()
Annotator.add_simplified_genres(record, work)
fields = record.get_fields("650")
[fantasy_field,
romance_field] = sorted(fields, key=lambda x: x.get_subfields("a")[0])
eq_(["0", "7"], fantasy_field.indicators)
eq_("Fantasy", fantasy_field.get_subfields("a")[0])
eq_("Library Simplified", fantasy_field.get_subfields("2")[0])
eq_(["0", "7"], romance_field.indicators)
eq_("Romance", romance_field.get_subfields("a")[0])
eq_("Library Simplified", romance_field.get_subfields("2")[0])
# It also works with a materialized work.
self.add_to_materialized_view([work])
# The work is in the materialized view twice since it has two genres,
# but we can use either one.
[mw, ignore] = self._db.query(MaterializedWorkWithGenre).all()
record = Record()
Annotator.add_simplified_genres(record, mw)
fields = record.get_fields("650")
[fantasy_field,
romance_field] = sorted(fields, key=lambda x: x.get_subfields("a")[0])
eq_(["0", "7"], fantasy_field.indicators)
eq_("Fantasy", fantasy_field.get_subfields("a")[0])
eq_("Library Simplified", fantasy_field.get_subfields("2")[0])
eq_(["0", "7"], romance_field.indicators)
eq_("Romance", romance_field.get_subfields("a")[0])
eq_("Library Simplified", romance_field.get_subfields("2")[0])
def test_add_title(self):
edition = self._edition()
edition.title = "The Good Soldier"
edition.sort_title = "Good Soldier, The"
edition.subtitle = "A Tale of Passion"
record = Record()
Annotator.add_title(record, edition)
[field] = record.get_fields("245")
self._check_field(record, "245", {
"a": edition.title,
"b": edition.subtitle,
"c": edition.author,
}, ["0", "4"])
# If there's no subtitle or no author, those subfields are left out.
edition.subtitle = None
edition.author = None
record = Record()
Annotator.add_title(record, edition)
[field] = record.get_fields("245")
self._check_field(record, "245", {
"a": edition.title,
}, ["0", "4"])
eq_([], field.get_subfields("b"))
eq_([], field.get_subfields("c"))
def test_add_web_client_urls(self):
# Web client URLs can come from either the MARC export integration or
# a library registry integration.
annotator = LibraryAnnotator(self._default_library)
# If no web catalog URLs are set for the library, nothing will be changed.
record = Record()
identifier = self._identifier(foreign_id="identifier")
annotator.add_web_client_urls(record, self._default_library,
identifier)
eq_([], record.get_fields("856"))
# Add a URL from a library registry.
registry = self._external_integration(
ExternalIntegration.OPDS_REGISTRATION,
ExternalIntegration.DISCOVERY_GOAL,
libraries=[self._default_library])
ConfigurationSetting.for_library_and_externalintegration(
self._db, Registration.LIBRARY_REGISTRATION_WEB_CLIENT,
self._default_library, registry).value = "http://web_catalog"
record = Record()
annotator.add_web_client_urls(record, self._default_library,
identifier)
[field] = record.get_fields("856")
eq_(["4", "0"], field.indicators)
eq_("http://web_catalog/book/Gutenberg%20ID%2Fidentifier",
field.get_subfields("u")[0])
# Add a manually configured URL on a MARC export integration.
integration = self._external_integration(
ExternalIntegration.MARC_EXPORT,
ExternalIntegration.CATALOG_GOAL,
libraries=[self._default_library])
ConfigurationSetting.for_library_and_externalintegration(
self._db, MARCExporter.WEB_CLIENT_URL, self._default_library,
integration).value = "http://another_web_catalog"
record = Record()
annotator.add_web_client_urls(record, self._default_library,
identifier, integration)
[field1, field2] = record.get_fields("856")
eq_(["4", "0"], field1.indicators)
eq_("http://another_web_catalog/book/Gutenberg%20ID%2Fidentifier",
field1.get_subfields("u")[0])
eq_(["4", "0"], field2.indicators)
eq_("http://web_catalog/book/Gutenberg%20ID%2Fidentifier",
field2.get_subfields("u")[0])
def faulty015(record: Record) -> bool:
found = False
for f in record.get_fields("015"):
if "a" in f:
if len(f["a"].split(' ')) > 1:
found = True
return found
async def get_terms_to_search_and_references_to_raw_flds(
marc_record: pymarc.Record,
for_omnis: bool = False) -> Dict[str, List[pymarc.Field]]:
# create empty dict for results
terms_fields_ids = {}
# switch between fields to check
fields_to_check = FIELDS_TO_CHECK_FOR_OMNIS if for_omnis else FIELDS_TO_CHECK
# iterate over constant: fields to check in marc record
for marc_field_and_subfields in fields_to_check:
# get field tag and subfields tags
fld, subflds = marc_field_and_subfields[0], marc_field_and_subfields[1]
# check if field present in marc record
if fld in marc_record:
# get list of raw field objects (pymarc.Field)
raw_objects_flds_list = marc_record.get_fields(fld)
# iterate over raw field objects
for raw_fld in raw_objects_flds_list:
# get term from raw field and normalize it
term_to_search = prepare_name_for_indexing(' '.join(
subfld for subfld in raw_fld.get_subfields(*subflds)))
# create new entry in dict if necessary and/or append raw fld to list
terms_fields_ids.setdefault(term_to_search,
{}).setdefault('raw_flds',
[]).append(raw_fld)
return terms_fields_ids
def decode_record(self, record):
r"""
>>> reader = Reader('http://opac.uthsc.edu', 2)
>>> raw = "\nLEADER 00000cas 2200517 a 4500 \n001 1481253 \n003 OCoLC \n005 19951109120000.0 \n008 750727c19589999fr qrzp b 0 b0fre d \n010 sn 86012727 \n022 0003-3995 \n030 AGTQAH \n035 0062827|bMULS|aPITT NO. 0639600000|asa64872000|bFULS \n040 MUL|cMUL|dFUL|dOCL|dCOO|dNYG|dHUL|dSER|dAIP|dNST|dAGL|dDLC\n |dTUM \n041 0 engfre|bgeritaspa \n042 nsdp \n049 TUMS \n069 1 A32025000 \n210 0 Ann. genet. \n222 0 Annales de genetique \n229 00 Annales de genetique \n229 Ann Genet \n242 00 Annals on genetics \n245 00 Annales de genetique. \n260 Paris :|bExpansion scientifique,|c1958-2004. \n300 v. :|bill. ;|c28 cm. \n310 Quarterly \n321 Two no. a year \n362 0 1,1958-47,2004. \n510 1 Excerpta medica \n510 1 Index medicus|x0019-3879 \n510 2 Biological abstracts|x0006-3169 \n510 2 Chemical abstracts|x0009-2258 \n510 2 Life sciences collection \n510 0 Bulletin signaletique \n510 0 Current contents \n546 French and English, with summaries in German, Italian, and\n Spanish. \n550 Journal of the Societe francaise de genetique. \n650 2 Genetics|vPeriodicals. \n710 2 Societ\xe9 fran\xe7aise de genetique. \n785 00 |tEuropean journal of medical genetics. \n856 41 |uhttp://library.uthsc.edu/ems/eresource/3581|zFull text \n at ScienceDirect: 43(1) Jan 2000 - 47(4) Dec 2004 \n936 Unknown|ajuin 1977 \n"
>>> record = reader.decode_record(raw)
>>> print record.title
Annales de genetique
"""
pseudo_marc = record.strip().split('\n')
raw_fields = []
if pseudo_marc[0][0:6] == 'LEADER':
record = Record()
record.leader = pseudo_marc[0][7:].strip()
else:
return None
for field in pseudo_marc[1:]:
tag = field[:3]
data = unescape_entities(field[6:].decode('latin1')).encode('utf8')
if tag.startswith(' '):
# Additional field data needs to be prepended with an extra space
# for certain fields ...
#for special_tag in ('55','260'):
# data = " %s" % (data,) if tag.startswith(special_tag) else data
data = " %s" % (data.strip(),)
raw_fields[-1]['value'] = "%s%s" % (raw_fields[-1]['value'], data)
raw_fields[-1]['raw'] = "%s%s" % (raw_fields[-1]['raw'], field.strip())
else:
data = data if (tag < '010' and tag.isdigit()) else "a%s" % (data,)
raw_fields.append({
'tag': tag,
'indicator1': field[3],
'indicator2': field[4],
'value': data.strip(),
'raw': field.strip()
})
for raw in raw_fields:
tag = raw['tag']
data = raw['value'].strip()
field = Field(tag=tag, indicators=[raw['indicator1'], raw['indicator2']], data=data)
if not field.is_control_field():
for sub in data.split('|'):
try:
field.add_subfield(sub[0].strip(), sub[1:].strip())
except Exception:
# Skip blank/empty subfields
continue
record.add_field(field)
record.parse_leader()
# Disregard record if no title present
if not record.get_fields('245'):
return None
else:
return record
def test_add_physical_description(self):
book = self._edition()
book.medium = Edition.BOOK_MEDIUM
audio = self._edition()
audio.medium = Edition.AUDIO_MEDIUM
record = Record()
Annotator.add_physical_description(record, book)
self._check_field(record, "300", {"a": "1 online resource"})
self._check_field(record, "336", {
"a": "text",
"b": "txt",
"2": "rdacontent",
})
self._check_field(record, "337", {
"a": "computer",
"b": "c",
"2": "rdamedia",
})
self._check_field(record, "338", {
"a": "online resource",
"b": "cr",
"2": "rdacarrier",
})
self._check_field(record, "347", {
"a": "text file",
"2": "rda",
})
self._check_field(record, "380", {
"a": "eBook",
"2": "tlcgt",
})
record = Record()
Annotator.add_physical_description(record, audio)
self._check_field(record, "300", {
"a": "1 sound file",
"b": "digital",
})
self._check_field(record, "336", {
"a": "spoken word",
"b": "spw",
"2": "rdacontent",
})
self._check_field(record, "337", {
"a": "computer",
"b": "c",
"2": "rdamedia",
})
self._check_field(record, "338", {
"a": "online resource",
"b": "cr",
"2": "rdacarrier",
})
self._check_field(record, "347", {
"a": "audio file",
"2": "rda",
})
eq_([], record.get_fields("380"))
def test_add_physical_description(self):
book = self._edition()
book.medium = Edition.BOOK_MEDIUM
audio = self._edition()
audio.medium = Edition.AUDIO_MEDIUM
record = Record()
Annotator.add_physical_description(record, book)
self._check_field(record, "300", {"a": "1 online resource"})
self._check_field(record, "336", {
"a": "text",
"b": "txt",
"2": "rdacontent",
})
self._check_field(record, "337", {
"a": "computer",
"b": "c",
"2": "rdamedia",
})
self._check_field(record, "338", {
"a": "online resource",
"b": "cr",
"2": "rdacarrier",
})
self._check_field(record, "347", {
"a": "text file",
"2": "rda",
})
self._check_field(record, "380", {
"a": "eBook",
"2": "tlcgt",
})
record = Record()
Annotator.add_physical_description(record, audio)
self._check_field(record, "300", {
"a": "1 sound file",
"b": "digital",
})
self._check_field(record, "336", {
"a": "spoken word",
"b": "spw",
"2": "rdacontent",
})
self._check_field(record, "337", {
"a": "computer",
"b": "c",
"2": "rdamedia",
})
self._check_field(record, "338", {
"a": "online resource",
"b": "cr",
"2": "rdacarrier",
})
self._check_field(record, "347", {
"a": "audio file",
"2": "rda",
})
eq_([], record.get_fields("380"))
def test_add_web_client_urls(self):
# Web client URLs can come from either the MARC export integration or
# a library registry integration.
annotator = LibraryAnnotator(self._default_library)
# If no web catalog URLs are set for the library, nothing will be changed.
record = Record()
identifier = self._identifier(foreign_id="identifier")
annotator.add_web_client_urls(record, self._default_library, identifier)
eq_([], record.get_fields("856"))
# Add a URL from a library registry.
registry = self._external_integration(
ExternalIntegration.OPDS_REGISTRATION, ExternalIntegration.DISCOVERY_GOAL,
libraries=[self._default_library])
ConfigurationSetting.for_library_and_externalintegration(
self._db, Registration.LIBRARY_REGISTRATION_WEB_CLIENT,
self._default_library, registry).value = "http://web_catalog"
record = Record()
annotator.add_web_client_urls(record, self._default_library, identifier)
[field] = record.get_fields("856")
eq_(["4", "0"], field.indicators)
eq_("http://web_catalog/book/Gutenberg%20ID%2Fidentifier",
field.get_subfields("u")[0])
# Add a manually configured URL on a MARC export integration.
integration = self._external_integration(
ExternalIntegration.MARC_EXPORT, ExternalIntegration.CATALOG_GOAL,
libraries=[self._default_library])
ConfigurationSetting.for_library_and_externalintegration(
self._db, MARCExporter.WEB_CLIENT_URL,
self._default_library, integration).value = "http://another_web_catalog"
record = Record()
annotator.add_web_client_urls(record, self._default_library, identifier, integration)
[field1, field2] = record.get_fields("856")
eq_(["4", "0"], field1.indicators)
eq_("http://another_web_catalog/book/Gutenberg%20ID%2Fidentifier",
field1.get_subfields("u")[0])
eq_(["4", "0"], field2.indicators)
eq_("http://web_catalog/book/Gutenberg%20ID%2Fidentifier",
field2.get_subfields("u")[0])
def empty020a(record: Record) -> bool:
sf020a = []
if "020" in record:
fields = record.get_fields("020")
for f in fields:
if "a" in f:
sf020a.append(f.get_subfields("a").pop())
return sf020a == [""]
def periodsMissing(record: Record) -> bool:
fields = record.get_fields("100", "110", "700", "710")
for f in fields:
if "e" in f:
functions = f.get_subfields("e")
for func in functions:
if func[-1].isalpha():
return True
return False
def test_bib_with_vendor_910_tag(self):
bib = Record()
bib.add_field(
Field(tag="910", indicators=[" ", " "], subfields=["a", "foo"]))
patches.bib_patches("nypl", "research", "acq", "Amalivre", bib)
tags_910 = bib.get_fields("910")
self.assertEqual(len(tags_910), 1)
self.assertEqual(str(bib["910"]), "=910 \\\\$aRL")
def phrasesInFields(record: Record, phrases: list, fields: list) -> bool:
'''Takes a record object, a list of strings and a list of fields (as strings).
Returns a boolean.'''
for f in fields:
for rf in record.get_fields(f):
for p in phrases:
if p in rf.value().lower():
return True
return False
def callZ3950(search_id, target, depth=0):
if target == 'UIU':
print "UIUC NUMBER: ", search_id
query = zoom.Query('PQF', '@attr 1=12 %s' % str(search_id))
database_address = 'z3950.carli.illinois.edu'
username = '******'
database_name = 'voyager'
else:
print "LC NUMBER: ", search_id
query = zoom.Query('PQF', '@attr 1=9 %s' % str(formatLCCN(search_id)))
database_address = 'lx2.loc.gov'
username = ''
if 'n' in search_id:
database_name = 'NAF'
else:
database_name = 'SAF'
# conn = establishZ3950Connection(database_address,210,username,database_name)
res = queryZ3950(database_address, username, database_name, query)
print len(res)
print res
if len(res) > 0:
for r in res:
valid_leader = checkLeader(r.data[:24])
if valid_leader:
if len(res) > 1:
try:
new_record = Record(data=r.data)
except UnicodeDecodeError:
return (False, 'BROKEN CHARACTER IN RECORD')
lccn = new_record.get_fields('001')[0].data.replace(
" ", "")
if lccn == search_id:
marc_record = new_record
fixNames(marc_record)
else:
try:
marc_record = Record(data=r.data)
except UnicodeDecodeError:
return (False, 'BROKEN CHARACTER IN RECORD')
fixNames(marc_record)
else:
return (False, 'BROKEN LEADER')
return (marc_record, None)
elif depth < 20:
waitSixSeconds(datetime.datetime.now().time())
return callZ3950(search_id, target, depth=depth + 1)
else:
return (None, 'RECORD NOT FOUND')
def record_sorted(record: Record) -> Record:
result = Record()
result.leader = record.leader
for i in range(1000):
field_name = str(i)
while len(field_name) < 3:
field_name = "0" + field_name
# 先寻出旧数据中所有的字段名下字段
old_fields = record.get_fields(field_name)
for field in old_fields:
result.add_field(field)
return result
def test_add_control_fields(self):
# This edition has one format and was published before 1900.
edition, pool = self._edition(with_license_pool=True)
identifier = pool.identifier
edition.issued = datetime_utc(956, 1, 1)
now = utc_now()
record = Record()
Annotator.add_control_fields(record, identifier, pool, edition)
self._check_control_field(record, "001", identifier.urn)
assert now.strftime("%Y%m%d") in record.get_fields("005")[0].value()
self._check_control_field(record, "006", "m d ")
self._check_control_field(record, "007", "cr cn ---anuuu")
self._check_control_field(
record, "008",
now.strftime("%y%m%d") + "s0956 xxu eng ")
# This French edition has two formats and was published in 2018.
edition2, pool2 = self._edition(with_license_pool=True)
identifier2 = pool2.identifier
edition2.issued = datetime_utc(2018, 2, 3)
edition2.language = "fre"
LicensePoolDeliveryMechanism.set(
pool2.data_source,
identifier2,
Representation.PDF_MEDIA_TYPE,
DeliveryMechanism.ADOBE_DRM,
RightsStatus.IN_COPYRIGHT,
)
record = Record()
Annotator.add_control_fields(record, identifier2, pool2, edition2)
self._check_control_field(record, "001", identifier2.urn)
assert now.strftime("%Y%m%d") in record.get_fields("005")[0].value()
self._check_control_field(record, "006", "m d ")
self._check_control_field(record, "007", "cr cn ---mnuuu")
self._check_control_field(
record, "008",
now.strftime("%y%m%d") + "s2018 xxu fre ")
def textIn020z(record: Record) -> bool:
sf020z = []
if "020" in record:
fields = record.get_fields("020")
for f in fields:
if "z" in f:
sf020z.append(f.get_subfields("z").pop())
if len(sf020z) > 0:
alpha = 0
for f in sf020z:
alpha += len([x for x in f if x.isalpha()])
return alpha > 1
return False
def test_add_control_fields(self):
# This edition has one format and was published before 1900.
edition, pool = self._edition(with_license_pool=True)
identifier = pool.identifier
edition.issued = datetime.datetime(956, 1, 1)
now = datetime.datetime.now()
record = Record()
Annotator.add_control_fields(record, identifier, pool, edition)
self._check_control_field(record, "001", identifier.urn)
assert now.strftime("%Y%m%d") in record.get_fields("005")[0].value()
self._check_control_field(record, "006", "m d ")
self._check_control_field(record, "007", "cr cn ---anuuu")
self._check_control_field(
record, "008",
now.strftime("%y%m%d") + "s0956 xxu eng ")
# This French edition has two formats and was published in 2018.
edition2, pool2 = self._edition(with_license_pool=True)
identifier2 = pool2.identifier
edition2.issued = datetime.datetime(2018, 2, 3)
edition2.language = "fre"
LicensePoolDeliveryMechanism.set(
pool2.data_source, identifier2, Representation.PDF_MEDIA_TYPE,
DeliveryMechanism.ADOBE_DRM, RightsStatus.IN_COPYRIGHT)
record = Record()
Annotator.add_control_fields(record, identifier2, pool2, edition2)
self._check_control_field(record, "001", identifier2.urn)
assert now.strftime("%Y%m%d") in record.get_fields("005")[0].value()
self._check_control_field(record, "006", "m d ")
self._check_control_field(record, "007", "cr cn ---mnuuu")
self._check_control_field(
record, "008",
now.strftime("%y%m%d") + "s2018 xxu fre ")
def test_add_contributors(self):
author = "a"
author2 = "b"
translator = "c"
# Edition with one author gets a 100 field and no 700 fields.
edition = self._edition(authors=[author])
edition.sort_author = "sorted"
record = Record()
Annotator.add_contributors(record, edition)
eq_([], record.get_fields("700"))
self._check_field(record, "100", {"a": edition.sort_author},
["1", " "])
# Edition with two authors and a translator gets three 700 fields and no 100 fields.
edition = self._edition(authors=[author, author2])
edition.add_contributor(translator, Contributor.TRANSLATOR_ROLE)
record = Record()
Annotator.add_contributors(record, edition)
eq_([], record.get_fields("100"))
fields = record.get_fields("700")
for field in fields:
eq_(["1", " "], field.indicators)
[author_field, author2_field,
translator_field] = sorted(fields,
key=lambda x: x.get_subfields("a")[0])
eq_(author, author_field.get_subfields("a")[0])
eq_(Contributor.PRIMARY_AUTHOR_ROLE,
author_field.get_subfields("e")[0])
eq_(author2, author2_field.get_subfields("a")[0])
eq_(Contributor.AUTHOR_ROLE, author2_field.get_subfields("e")[0])
eq_(translator, translator_field.get_subfields("a")[0])
eq_(Contributor.TRANSLATOR_ROLE,
translator_field.get_subfields("e")[0])
def has_overdrive_access_point_tag(record: Record) -> bool:
"""
Determines if the record has 710 2 $a Overdrive, Inc. tag
Args:
record: pymarc.field.Field instance
Returns:
bool
"""
found = False
for tag in record.get_fields("710"):
if "overdrive" in tag.value().lower():
found = True
break
return found
def test_add_simplified_genres(self):
work = self._work(with_license_pool=True)
fantasy, ignore = Genre.lookup(self._db, "Fantasy", autocreate=True)
romance, ignore = Genre.lookup(self._db, "Romance", autocreate=True)
work.genres = [fantasy, romance]
record = Record()
Annotator.add_simplified_genres(record, work)
fields = record.get_fields("650")
[fantasy_field,
romance_field] = sorted(fields, key=lambda x: x.get_subfields("a")[0])
eq_(["0", "7"], fantasy_field.indicators)
eq_("Fantasy", fantasy_field.get_subfields("a")[0])
eq_("Library Simplified", fantasy_field.get_subfields("2")[0])
eq_(["0", "7"], romance_field.indicators)
eq_("Romance", romance_field.get_subfields("a")[0])
eq_("Library Simplified", romance_field.get_subfields("2")[0])
def test_add_formats(self):
edition, pool = self._edition(with_license_pool=True)
epub_no_drm, ignore = DeliveryMechanism.lookup(
self._db, Representation.EPUB_MEDIA_TYPE, DeliveryMechanism.NO_DRM)
pool.delivery_mechanisms[0].delivery_mechanism = epub_no_drm
LicensePoolDeliveryMechanism.set(
pool.data_source, pool.identifier, Representation.PDF_MEDIA_TYPE,
DeliveryMechanism.ADOBE_DRM, RightsStatus.IN_COPYRIGHT)
record = Record()
Annotator.add_formats(record, pool)
fields = record.get_fields("538")
eq_(2, len(fields))
[pdf, epub] = sorted(fields, key=lambda x: x.get_subfields("a")[0])
eq_("Adobe PDF eBook", pdf.get_subfields("a")[0])
eq_([" ", " "], pdf.indicators)
eq_("EPUB eBook", epub.get_subfields("a")[0])
eq_([" ", " "], epub.indicators)
def test_add_formats(self):
edition, pool = self._edition(with_license_pool=True)
epub_no_drm, ignore = DeliveryMechanism.lookup(
self._db, Representation.EPUB_MEDIA_TYPE, DeliveryMechanism.NO_DRM)
pool.delivery_mechanisms[0].delivery_mechanism = epub_no_drm
LicensePoolDeliveryMechanism.set(pool.data_source, pool.identifier,
Representation.PDF_MEDIA_TYPE,
DeliveryMechanism.ADOBE_DRM,
RightsStatus.IN_COPYRIGHT)
record = Record()
Annotator.add_formats(record, pool)
fields = record.get_fields("538")
eq_(2, len(fields))
[pdf, epub] = sorted(fields, key=lambda x: x.get_subfields("a")[0])
eq_("Adobe PDF eBook", pdf.get_subfields("a")[0])
eq_([" ", " "], pdf.indicators)
eq_("EPUB eBook", epub.get_subfields("a")[0])
eq_([" ", " "], epub.indicators)
def test_add_publisher(self):
edition = self._edition()
edition.publisher = self._str
edition.issued = datetime.datetime(1894, 4, 5)
record = Record()
Annotator.add_publisher(record, edition)
self._check_field(
record, "264", {
"a": "[Place of publication not identified]",
"b": edition.publisher,
"c": "1894",
}, [" ", "1"])
# If there's no publisher, the field is left out.
record = Record()
edition.publisher = None
Annotator.add_publisher(record, edition)
eq_([], record.get_fields("264"))
def test_add_publisher(self):
edition = self._edition()
edition.publisher = self._str
edition.issued = datetime.datetime(1894, 4, 5)
record = Record()
Annotator.add_publisher(record, edition)
self._check_field(
record, "264", {
"a": "[Place of publication not identified]",
"b": edition.publisher,
"c": "1894",
}, [" ", "1"])
# If there's no publisher, the field is left out.
record = Record()
edition.publisher = None
Annotator.add_publisher(record, edition)
eq_([], record.get_fields("264"))
def test_add_isbn(self):
isbn = self._identifier(identifier_type=Identifier.ISBN)
record = Record()
Annotator.add_isbn(record, isbn)
self._check_field(record, "020", {"a": isbn.identifier})
# If the identifier isn't an ISBN, but has an equivalent that is, it still
# works.
equivalent = self._identifier()
data_source = DataSource.lookup(self._db, DataSource.OCLC)
equivalent.equivalent_to(data_source, isbn, 1)
record = Record()
Annotator.add_isbn(record, equivalent)
self._check_field(record, "020", {"a": isbn.identifier})
# If there is no ISBN, the field is left out.
non_isbn = self._identifier()
record = Record()
Annotator.add_isbn(record, non_isbn)
eq_([], record.get_fields("020"))
def test_add_isbn(self):
isbn = self._identifier(identifier_type=Identifier.ISBN)
record = Record()
Annotator.add_isbn(record, isbn)
self._check_field(record, "020", {"a": isbn.identifier})
# If the identifier isn't an ISBN, but has an equivalent that is, it still
# works.
equivalent = self._identifier()
data_source = DataSource.lookup(self._db, DataSource.OCLC)
equivalent.equivalent_to(data_source, isbn, 1)
record = Record()
Annotator.add_isbn(record, equivalent)
self._check_field(record, "020", {"a": isbn.identifier})
# If there is no ISBN, the field is left out.
non_isbn = self._identifier()
record = Record()
Annotator.add_isbn(record, non_isbn)
eq_([], record.get_fields("020"))
def test_read_records(self):
self.yc.read_records()
output_reader = MARCReader(open(self.output_path, 'rb'),
to_unicode=True)
test_reader = MARCReader(open("test/converted_records.mrc", 'rb'),
to_unicode=True)
test_record = Record()
while test_record:
output_record = next(output_reader, None)
test_record = next(test_reader, None)
if output_record:
output_fields = []
test_fields = []
for field in output_record.get_fields():
output_fields.append(str(field))
for field in test_record.get_fields():
test_fields.append(str(field))
self.assertCountEqual(output_fields, test_fields)
self.assertListEqual(output_fields, test_fields)
output_reader.close()
test_reader.close()
def test_add_web_client_urls(self):
# Web client URLs can come from either the MARC export integration or
# a library registry integration.
identifier = self._identifier(foreign_id="identifier")
lib_short_name = self._default_library.short_name
# The URL for a work is constructed as:
# - <cm-base>/<lib-short-name>/works/<qualified-identifier>
work_link_template = "{cm_base}/{lib}/works/{qid}"
# It is then encoded and the web client URL is constructed in this form:
# - <web-client-base>/book/<encoded-work-url>
client_url_template = "{client_base}/book/{work_link}"
qualified_identifier = urllib.parse.quote(
identifier.type + "/" + identifier.identifier, safe=""
)
cm_base_url = "http://test-circulation-manager"
expected_work_link = work_link_template.format(
cm_base=cm_base_url, lib=lib_short_name, qid=qualified_identifier
)
encoded_work_link = urllib.parse.quote(expected_work_link, safe="")
client_base_1 = "http://web_catalog"
client_base_2 = "http://another_web_catalog"
expected_client_url_1 = client_url_template.format(
client_base=client_base_1, work_link=encoded_work_link
)
expected_client_url_2 = client_url_template.format(
client_base=client_base_2, work_link=encoded_work_link
)
# A few checks to ensure that our setup is useful.
assert len(lib_short_name) > 0
assert client_base_1 != client_base_2
assert expected_client_url_1 != expected_client_url_2
assert expected_client_url_1.startswith(client_base_1)
assert expected_client_url_2.startswith(client_base_2)
ConfigurationSetting.sitewide(
self._db, Configuration.BASE_URL_KEY
).value = cm_base_url
annotator = LibraryAnnotator(self._default_library)
# If no web catalog URLs are set for the library, nothing will be changed.
record = Record()
annotator.add_web_client_urls(record, self._default_library, identifier)
assert [] == record.get_fields("856")
# Add a URL from a library registry.
registry = self._external_integration(
ExternalIntegration.OPDS_REGISTRATION,
ExternalIntegration.DISCOVERY_GOAL,
libraries=[self._default_library],
)
ConfigurationSetting.for_library_and_externalintegration(
self._db,
Registration.LIBRARY_REGISTRATION_WEB_CLIENT,
self._default_library,
registry,
).value = client_base_1
record = Record()
annotator.add_web_client_urls(record, self._default_library, identifier)
[field] = record.get_fields("856")
assert ["4", "0"] == field.indicators
assert expected_client_url_1 == field.get_subfields("u")[0]
# Add a manually configured URL on a MARC export integration.
integration = self._external_integration(
ExternalIntegration.MARC_EXPORT,
ExternalIntegration.CATALOG_GOAL,
libraries=[self._default_library],
)
ConfigurationSetting.for_library_and_externalintegration(
self._db, MARCExporter.WEB_CLIENT_URL, self._default_library, integration
).value = client_base_2
record = Record()
annotator.add_web_client_urls(
record, self._default_library, identifier, integration
)
[field1, field2] = record.get_fields("856")
assert ["4", "0"] == field1.indicators
assert expected_client_url_2 == field1.get_subfields("u")[0]
assert ["4", "0"] == field2.indicators
assert expected_client_url_1 == field2.get_subfields("u")[0]
def getId(record: Record) -> str:
return [x.value() for x in record.get_fields("001")].pop()
def field020ContainsAbbreviation(record: Record) -> bool:
abbrevs = ["sid.", "nid.", "inb.", "hft."]
if "020" in record:
return len([x for x in abbrevs if x in str(record.get_fields("020").pop()).lower()]) > 0
return False
def hasLCSHfields(record: Record) -> bool:
if "650" in record:
for f in record.get_fields("650"):
return getSecondIndicator(f) == "0"
return False
def wrongIndicatorIn245(record: Record) -> bool:
return has130Field(record) and getFirstIndicator(record.get_fields("245").pop()) == "0"
def test_bib_without_vendor_910_tag(self):
bib = Record()
patches.bib_patches("nypl", "branches", "cat", "BT SERIES", bib)
tags_910 = bib.get_fields("910")
self.assertEqual(len(tags_910), 1)
self.assertEqual(str(bib["910"]), "=910 \\\\$aBL")
def contains024c(record: Record) -> bool:
if "024" in record:
return "c" in record.get_fields("024").pop()
return False
