def test_book_info_with_sample(self):
raw, info = self.sample_json("has_sample.json")
metadata = OverdriveRepresentationExtractor.book_info_to_metadata(info)
[sample] = [x for x in metadata.links if x.rel == Hyperlink.SAMPLE]
eq_(
"http://excerpts.contentreserve.com/FormatType-410/1071-1/9BD/24F/82/BridesofConvenienceBundle9781426803697.epub",
sample.href)
def process_identifier(self, identifier):
# What is the correct medium?
correct_medium = None
lp = identifier.licensed_through
for lpdm in lp.delivery_mechanisms:
correct_medium = lpdm.delivery_mechanism.implicit_medium
if correct_medium:
break
if not correct_medium and identifier.type == Identifier.OVERDRIVE_ID:
content = self.overdrive.metadata_lookup(identifier)
metadata = OverdriveRepresentationExtractor.book_info_to_metadata(
content)
correct_medium = metadata.medium
if not correct_medium and identifier.type == Identifier.THREEM_ID:
metadata = self.threem.bibliographic_lookup(identifier)
correct_medium = metadata.medium
if not correct_medium:
set_trace()
if lp.edition.medium != correct_medium:
print "%s is actually %s, not %s" % (
lp.edition.title, correct_medium, lp.edition.medium)
lp.edition.medium = correct_medium or Edition.BOOK_MEDIUM
def test_availability_info(self):
data, raw = self.sample_json("overdrive_book_list.json")
availability = OverdriveRepresentationExtractor.availability_link_list(
raw)
for item in availability:
for key in 'availability_link', 'id', 'title':
assert key in item
def test_availability_info_missing_data(self):
data, raw = self.sample_json("overdrive_book_list_missing_data.json")
[item] = OverdriveRepresentationExtractor.availability_link_list(raw)
# We got a data structure for the item that has an ID but no title.
# We did not get a data structure for the item that has a title
# but no ID.
eq_('title is missing', item['id'])
eq_(None, item['title'])
def test_book_info_with_awards(self):
raw, info = self.sample_json("has_awards.json")
metadata = OverdriveRepresentationExtractor.book_info_to_metadata(info)
[awards] = [
x for x in metadata.measurements
if Measurement.AWARDS == x.quantity_measured
]
eq_(1, awards.value)
eq_(1, awards.weight)
def test_book_info_with_grade_levels(self):
raw, info = self.sample_json("has_grade_levels.json")
metadata = OverdriveRepresentationExtractor.book_info_to_metadata(info)
grade_levels = sorted([
x.identifier for x in metadata.subjects
if x.type == Subject.GRADE_LEVEL
])
eq_([u'Grade 4', u'Grade 5', u'Grade 6', u'Grade 7', u'Grade 8'],
grade_levels)
def test_book_info_with_circulationdata(self):
# Tests that can convert an overdrive json block into a CirculationData object.
raw, info = self.sample_json("overdrive_availability_information.json")
circulationdata = OverdriveRepresentationExtractor.book_info_to_circulation(
info)
# Related IDs.
identifier = circulationdata.primary_identifier(self._db)
eq_((Identifier.OVERDRIVE_ID, '2a005d55-a417-4053-b90d-7a38ca6d2065'),
(identifier.type, identifier.identifier))
def process_identifier(self, identifier):
content = self.api.metadata_lookup(identifier)
metadata = OverdriveRepresentationExtractor.book_info_to_metadata(content)
if not metadata:
return
license_pool = identifier.licensed_through
for format in metadata.formats:
print "%s: %s - %s" % (identifier.identifier, format.content_type, format.drm_scheme)
mech = license_pool.set_delivery_mechanism(
format.content_type,
format.drm_scheme,
format.link
)
def process_identifier(self, identifier):
content = self.api.metadata_lookup(identifier)
metadata = OverdriveRepresentationExtractor.book_info_to_metadata(
content)
if not metadata:
return
license_pool = identifier.licensed_through
for format in metadata.formats:
print "%s: %s - %s" % (identifier.identifier, format.content_type,
format.drm_scheme)
mech = license_pool.set_delivery_mechanism(format.content_type,
format.drm_scheme,
format.link)
def process_identifier(self, identifier):
# What is the correct medium?
correct_medium = None
lp = identifier.licensed_through
for lpdm in lp.delivery_mechanisms:
correct_medium = lpdm.delivery_mechanism.implicit_medium
if correct_medium:
break
if not correct_medium and identifier.type==Identifier.OVERDRIVE_ID:
content = self.overdrive.metadata_lookup(identifier)
metadata = OverdriveRepresentationExtractor.book_info_to_metadata(content)
correct_medium = metadata.medium
if not correct_medium and identifier.type==Identifier.THREEM_ID:
metadata = self.threem.bibliographic_lookup(identifier)
correct_medium = metadata.medium
if not correct_medium:
set_trace()
if lp.edition.medium != correct_medium:
print "%s is actually %s, not %s" % (lp.edition.title, correct_medium, lp.edition.medium)
lp.edition.medium = correct_medium or Edition.BOOK_MEDIUM
def test_book_info_with_metadata(self):
# Tests that can convert an overdrive json block into a Metadata object.
raw, info = self.sample_json("overdrive_metadata.json")
metadata = OverdriveRepresentationExtractor.book_info_to_metadata(info)
eq_("Agile Documentation", metadata.title)
eq_(
"Agile Documentation A Pattern Guide to Producing Lightweight Documents for Software Projects",
metadata.sort_title)
eq_(
"A Pattern Guide to Producing Lightweight Documents for Software Projects",
metadata.subtitle)
eq_(Edition.BOOK_MEDIUM, metadata.medium)
eq_("Wiley Software Patterns", metadata.series)
eq_("eng", metadata.language)
eq_("Wiley", metadata.publisher)
eq_("John Wiley & Sons, Inc.", metadata.imprint)
eq_(2005, metadata.published.year)
eq_(1, metadata.published.month)
eq_(31, metadata.published.day)
[author] = metadata.contributors
eq_(u"Rüping, Andreas", author.sort_name)
eq_("Andreas Rüping", author.display_name)
eq_([Contributor.AUTHOR_ROLE], author.roles)
subjects = sorted(metadata.subjects, key=lambda x: x.identifier)
eq_([
("Computer Technology", Subject.OVERDRIVE, 100),
("Nonfiction", Subject.OVERDRIVE, 100),
('Object Technologies - Miscellaneous', 'tag', 1),
], [(x.identifier, x.type, x.weight) for x in subjects])
# Related IDs.
eq_((Identifier.OVERDRIVE_ID, '3896665d-9d81-4cac-bd43-ffc5066de1f5'),
(metadata.primary_identifier.type,
metadata.primary_identifier.identifier))
ids = [(x.type, x.identifier) for x in metadata.identifiers]
# The original data contains a blank ASIN in addition to the
# actual ASIN, but it doesn't show up here.
eq_([
(Identifier.ASIN, "B000VI88N2"),
(Identifier.ISBN, "9780470856246"),
(Identifier.OVERDRIVE_ID, '3896665d-9d81-4cac-bd43-ffc5066de1f5'),
], sorted(ids))
# Available formats.
[kindle, pdf] = sorted(metadata.circulation.formats,
key=lambda x: x.content_type)
eq_(DeliveryMechanism.KINDLE_CONTENT_TYPE, kindle.content_type)
eq_(DeliveryMechanism.KINDLE_DRM, kindle.drm_scheme)
eq_(Representation.PDF_MEDIA_TYPE, pdf.content_type)
eq_(DeliveryMechanism.ADOBE_DRM, pdf.drm_scheme)
# Links to various resources.
shortd, image, longd = sorted(metadata.links, key=lambda x: x.rel)
eq_(Hyperlink.DESCRIPTION, longd.rel)
assert longd.content.startswith("<p>Software documentation")
eq_(Hyperlink.SHORT_DESCRIPTION, shortd.rel)
assert shortd.content.startswith("<p>Software documentation")
assert len(shortd.content) < len(longd.content)
eq_(Hyperlink.IMAGE, image.rel)
eq_(
'http://images.contentreserve.com/ImageType-100/0128-1/%7B3896665D-9D81-4CAC-BD43-FFC5066DE1F5%7DImg100.jpg',
image.href)
thumbnail = image.thumbnail
eq_(Hyperlink.THUMBNAIL_IMAGE, thumbnail.rel)
eq_(
'http://images.contentreserve.com/ImageType-200/0128-1/%7B3896665D-9D81-4CAC-BD43-FFC5066DE1F5%7DImg200.jpg',
thumbnail.href)
# Measurements associated with the book.
measurements = metadata.measurements
popularity = [
x for x in measurements
if x.quantity_measured == Measurement.POPULARITY
][0]
eq_(2, popularity.value)
rating = [
x for x in measurements
if x.quantity_measured == Measurement.RATING
][0]
eq_(1, rating.value)
# Request only the bibliographic information.
metadata = OverdriveRepresentationExtractor.book_info_to_metadata(
info, include_bibliographic=True, include_formats=False)
eq_("Agile Documentation", metadata.title)
eq_(None, metadata.circulation)
# Request only the format information.
metadata = OverdriveRepresentationExtractor.book_info_to_metadata(
info, include_bibliographic=False, include_formats=True)
eq_(None, metadata.title)
[kindle, pdf] = sorted(metadata.circulation.formats,
key=lambda x: x.content_type)
eq_(DeliveryMechanism.KINDLE_CONTENT_TYPE, kindle.content_type)
eq_(DeliveryMechanism.KINDLE_DRM, kindle.drm_scheme)
eq_(Representation.PDF_MEDIA_TYPE, pdf.content_type)
eq_(DeliveryMechanism.ADOBE_DRM, pdf.drm_scheme)
def test_link(self):
data, raw = self.sample_json("overdrive_book_list.json")
expect = OverdriveAPI.make_link_safe(
"http://api.overdrive.com/v1/collections/collection-id/products?limit=300&offset=0&lastupdatetime=2014-04-28%2009:25:09&sort=popularity:desc&formats=ebook-epub-open,ebook-epub-adobe,ebook-pdf-adobe,ebook-pdf-open"
)
eq_(expect, OverdriveRepresentationExtractor.link(raw, "first"))
from threem import ThreeMAPI
from core.opds_import import SimplifiedOPDSLookup
lookup = SimplifiedOPDSLookup("http://metadata.alpha.librarysimplified.org/")
_db = production_session()
overdrive = OverdriveAPI(_db)
threem = ThreeMAPI(_db)
q = _db.query(Edition).join(Edition.data_source).filter(
DataSource.name.in_([DataSource.OVERDRIVE])).filter(Edition.author == '')
print "Fixing %s books." % q.count()
for edition in q:
if edition.data_source.name == DataSource.OVERDRIVE:
data = overdrive.metadata_lookup(edition.primary_identifier)
metadata = OverdriveRepresentationExtractor.book_info_to_metadata(data)
else:
metadata = threem.bibliographic_lookup(edition.primary_identifier)
metadata.update_contributions(_db,
edition,
metadata_client=lookup,
replace_contributions=True)
if edition.work:
edition.work.calculate_presentation()
else:
edition.calculate_presentation()
for c in edition.contributions:
print "%s = %s (%s)" % (c.role, c.contributor.display_name,
c.contributor.name)
print edition.author, edition.sort_author
OverdriveRepresentationExtractor
)
from threem import ThreeMAPI
from core.opds_import import SimplifiedOPDSLookup
lookup = SimplifiedOPDSLookup("http://metadata.alpha.librarysimplified.org/")
_db = production_session()
overdrive = OverdriveAPI(_db)
threem = ThreeMAPI(_db)
q = _db.query(Edition).join(Edition.data_source).filter(DataSource.name.in_([DataSource.OVERDRIVE])).filter(Edition.author=='')
print "Fixing %s books." % q.count()
for edition in q:
if edition.data_source.name==DataSource.OVERDRIVE:
data = overdrive.metadata_lookup(edition.primary_identifier)
metadata = OverdriveRepresentationExtractor.book_info_to_metadata(data)
else:
metadata = threem.bibliographic_lookup(edition.primary_identifier)
metadata.update_contributions(_db, edition, metadata_client=lookup,
replace_contributions=True)
if edition.work:
edition.work.calculate_presentation()
else:
edition.calculate_presentation()
for c in edition.contributions:
print "%s = %s (%s)" % (
c.role, c.contributor.display_name, c.contributor.name
)
print edition.author, edition.sort_author
_db.commit()