def _title_range(reel):
agg = models.Issue.objects.filter(pages__reel=reel).distinct().aggregate(
mn=Min('date_issued'), mx=Max('date_issued'))
if agg['mn'] and agg['mx']:
mn = strftime_safe(agg['mn'], '%b %d, %Y')
mx = strftime_safe(agg['mx'], '%b %d, %Y')
return "%s - %s" % (mn, mx)
else:
return ""
def __str__(self):
parts = ['%s' % self.issue.title]
parts.append(strftime_safe(self.issue.date_issued, '%B %d, %Y'))
if self.issue.edition_label:
parts.append(self.issue.edition_label)
if self.section_label:
parts.append(self.section_label)
parts.append('Image %s' % self.sequence)
return ', '.join(parts)
def label(instance):
if isinstance(instance, models.Title):
return '%s (%s) %s-%s' % (instance.display_name,
instance.place_of_publication,
instance.start_year, instance.end_year)
elif isinstance(instance, models.Issue):
parts = []
parts.append(strftime_safe(instance.date_issued, '%B %d, %Y'))
if instance.edition_label:
parts.append("%s" % instance.edition_label)
return ', '.join(parts)
elif isinstance(instance, models.Page):
parts = []
if instance.section_label:
parts.append(instance.section_label)
if instance.number:
parts.append('Page %s' % instance.number)
parts.append('Image %s' % instance.sequence)
return ', '.join(parts)
else:
return "%s" % instance
def json(self, host, serialize=True):
j = {
"@context": "http://iiif.io/api/presentation/2/context.json",
"@id": settings.BASE_URL + self.json_url,
"@type": "sc:Collection",
"label": self.display_name,
"manifests": [],
"metadata": self.metadata
}
for issue in self.issues.all():
j["manifests"].append({
"@id":
settings.BASE_URL + issue.json_url,
"@type":
"sc:Manifest",
"label":
strftime_safe(issue.date_issued, '%Y-%m-%d')
})
if serialize:
return json.dumps(j, indent=2)
return j
def test_load_batch(self):
# Extract mini-batch tarball to /tmp somewhere
tarpath = os.path.join(os.path.dirname(core.__file__), 'test-data', 'testbatch.tgz')
tar = tarfile.open(tarpath)
tar.extractall(path = BatchLoaderTest.batchDir)
tar.close()
settings.BATCH_STORAGE = BatchLoaderTest.batchDir
batch_dir = os.path.join(BatchLoaderTest.batchDir, "batch_oru_testbatch_ver01")
loader = BatchLoader(process_ocr=False)
batch = loader.load_batch(batch_dir)
self.assertTrue(isinstance(batch, Batch))
self.assertEqual(batch.name, 'batch_oru_testbatch_ver01')
self.assertEqual(len(batch.issues.all()), 4)
title = Title.objects.get(lccn = 'sn83030214')
self.assertTrue(title.has_issues)
issue = batch.issues.all()[0]
self.assertEqual(issue.volume, '1')
self.assertEqual(issue.number, '1')
self.assertEqual(issue.edition, 1)
self.assertEqual(issue.title.lccn, 'sn83030214')
self.assertEqual(strftime_safe(issue.date_issued, '%Y-%m-%d'), '1999-06-15')
self.assertEqual(len(issue.pages.all()), 15)
page = issue.pages.all()[0]
self.assertEqual(page.sequence, 1)
self.assertEqual(page.url, '/lccn/sn83030214/1999-06-15/ed-1/seq-1/')
notes = page.notes.order_by("type").all()
self.assertEqual(len(notes), 2)
note = page.notes.all()[0]
self.assertEqual(note.type, "noteAboutReproduction")
self.assertEqual(note.text, "Present")
note = page.notes.all()[1]
self.assertEqual(note.type, "agencyResponsibleForReproduction")
self.assertEqual(note.text, "oru")
# Validate page 1's metadata
self.assertEqual(page.sequence, 1)
self.assertEqual(page.jp2_filename, 'sn83030214/print/1999061501/0001.jp2')
self.assertEqual(page.jp2_length, 411)
self.assertEqual(page.jp2_width, 411)
self.assertEqual(page.ocr_filename, 'sn83030214/print/1999061501/0001.xml')
self.assertEqual(page.pdf_filename, 'sn83030214/print/1999061501/0001.pdf')
# extract ocr data just for this page
loader.process_ocr(page, index=False)
self.assertTrue(page.ocr != None)
self.assertTrue(len(page.ocr.text) > 0)
p = Title.objects.get(lccn='sn83030214').issues.all()[0].pages.all()[0]
self.assertTrue(p.ocr != None)
# check that the solr_doc looks legit
solr_doc = page.solr_doc
self.assertEqual(solr_doc['id'], '/lccn/sn83030214/1999-06-15/ed-1/seq-1/')
self.assertEqual(solr_doc['type'], 'page')
self.assertEqual(solr_doc['sequence'], 1)
self.assertEqual(solr_doc['lccn'], 'sn83030214')
self.assertEqual(solr_doc['title'], 'New-York tribune.')
self.assertEqual(solr_doc['date'], '19990615')
self.assertEqual(solr_doc['batch'], 'batch_oru_testbatch_ver01')
self.assertEqual(solr_doc['subject'], [
'New York (N.Y.)--Newspapers.',
'New York County (N.Y.)--Newspapers.'])
self.assertEqual(solr_doc['place'], [
'New York--Brooklyn--New York City',
'New York--Queens--New York City'])
self.assertEqual(solr_doc['note'], [
"I'll take Manhattan",
'The Big Apple'])
self.assertTrue('essay' not in solr_doc)
self.assertEqual(solr_doc['ocr_eng'], 'LCCNsn83030214Page1')
# purge the batch and make sure it's gone from the db
loader.purge_batch('batch_oru_testbatch_ver01')
self.assertEqual(Batch.objects.all().count(), 0)
self.assertEqual(Title.objects.get(lccn='sn83030214').has_issues, False)