def issue_pages_json(request, lccn, date, edition):
title, issue, page = _get_tip(lccn, date, edition)
host = request.get_host()
if issue:
return HttpResponse(issue.json(host=host), mimetype='application/json')
else:
return HttpResponseNotFound()
def page_ocr_txt(request, lccn, date, edition, sequence):
title, issue, page = _get_tip(lccn, date, edition, sequence)
try:
text = page.ocr.text
return HttpResponse(text, mimetype='text/plain')
except models.OCR.DoesNotExist, e:
raise Http404("No OCR for %s" % page)
def issue_pages_rdf(request, lccn, date, edition):
title, issue, page = _get_tip(lccn, date, edition)
graph = issue_to_graph(issue)
response = HttpResponse(graph.serialize(base=_rdf_base(request),
include_base=True),
content_type='application/rdf+xml')
return add_cache_tag(response, "lccn=%s" % lccn)
def issue_pages_rdf(request, lccn, date, edition):
title, issue, page = _get_tip(lccn, date, edition)
graph = issue_to_graph(issue)
response = HttpResponse(graph.serialize(base=_rdf_base(request),
include_base=True),
mimetype='application/rdf+xml')
return response
def page_json(request, lccn, date, edition, sequence):
title, issue, page = _get_tip(lccn, date, edition, sequence)
host = request.get_host()
if page:
return HttpResponse(page.json(host=host), mimetype='application/json')
else:
return HttpResponseNotFound()
def page_ocr(request, lccn, date, edition, sequence):
title, issue, page = _get_tip(lccn, date, edition, sequence)
page_title = "%s, %s, %s" % (label(title), label(issue), label(page))
crumbs = create_crumbs(title, issue, date, edition, page)
host = request.get_host()
return render_to_response('page_text.html', dictionary=locals(),
context_instance=RequestContext(request))
def page_ocr(request, lccn, date, edition, sequence):
title, issue, page = _get_tip(lccn, date, edition, sequence)
page_title = "%s, %s, %s" % (label(title), label(issue), label(page))
crumbs = create_crumbs(title, issue, date, edition, page)
host = request.get_host()
return render_to_response('page_text.html', dictionary=locals(),
context_instance=RequestContext(request))
def issue_pages_rdf(request, lccn, date, edition):
title, issue, page = _get_tip(lccn, date, edition)
graph = issue_to_graph(issue)
response = HttpResponse(graph.serialize(base=_rdf_base(request),
include_base=True),
mimetype='application/rdf+xml')
return response
def page_ocr_txt(request, lccn, date, edition, sequence):
title, issue, page = _get_tip(lccn, date, edition, sequence)
try:
text = page.ocr.text
return HttpResponse(text, mimetype='text/plain')
except models.OCR.DoesNotExist, e:
raise Http404("No OCR for %s" % page)
def issue_pages_json(request, lccn, date, edition):
title, issue, page = _get_tip(lccn, date, edition)
host = request.get_host()
if issue:
return HttpResponse(issue.json(host=host), mimetype='application/json')
else:
return HttpResponseNotFound()
def page_json(request, lccn, date, edition, sequence):
title, issue, page = _get_tip(lccn, date, edition, sequence)
host = request.get_host()
if page:
return HttpResponse(page.json(host=host), content_type='application/json')
else:
return HttpResponseNotFound()
def chronam_topic(request, topic_id):
topic = get_object_or_404(models.Topic, pk=topic_id)
page_title = topic.name
crumbs = list(settings.BASE_CRUMBS)
if urlresolvers.reverse('recommended_topics') in request.META.get('HTTP_REFERER'):
crumbs.extend([{'label': 'Recommended Topics',
'href': urlresolvers.reverse('recommended_topics')},
{'label': topic.name,
'href': urlresolvers.reverse('chronam_topic',
kwargs={'topic_id': topic.pk})}])
else:
referer = re.sub('^https?:\/\/', '', request.META.get('HTTP_REFERER')).split('/')
try:
lccn, date, edition, sequence = referer[2], referer[3], referer[4][-1], referer[5][-1]
page = get_page(lccn, date, edition, sequence)
if page:
title, issue, page = _get_tip(lccn, date, edition, sequence)
crumbs = create_crumbs(title, issue, date, edition, page)
crumbs.extend([{'label': topic.name,
'href': urlresolvers.reverse('chronam_topic',
kwargs={'topic_id': topic.pk})}])
except:
pass
important_dates = filter(lambda s: not s.isspace(), topic.important_dates.split('\n '))
search_suggestions = topic.suggested_search_terms.split('\t')
chronam_pages = [{'title': t.title, 'description': t.description.lstrip(t.title),
'url': t.url} for t in topic.topicpages_set.all()]
return render_to_response('topic.html', dictionary=locals(),
context_instance=RequestContext(request))
def issue_pages_rdf(request, lccn, date, edition):
title, issue, page = _get_tip(lccn, date, edition)
graph = issue_to_graph(issue)
response = HttpResponse(graph.serialize(base=_rdf_base(request),
include_base=True),
content_type='application/rdf+xml')
return add_cache_tag(response, "lccn=%s" % lccn)
def page_ocr_xml(request, lccn, date, edition, sequence):
title, issue, page = _get_tip(lccn, date, edition, sequence)
if page.ocr_abs_filename:
response = sendfile(request, page.ocr_abs_filename)
return add_cache_tag(response, "lccn=%s" % lccn)
else:
raise Http404("No ocr for page %s" % page)
def page_ocr_xml(request, lccn, date, edition, sequence):
title, issue, page = _get_tip(lccn, date, edition, sequence)
if page.ocr_abs_filename:
response = sendfile(request, page.ocr_abs_filename)
return add_cache_tag(response, "lccn=%s" % lccn)
else:
raise Http404("No ocr for page %s" % page)
def issue_pages_json(request, lccn, date, edition):
title, issue, page = _get_tip(lccn, date, edition)
if issue:
return HttpResponse(issue.json(request),
content_type="application/json")
else:
return HttpResponseNotFound()
def page_ocr_txt(request, lccn, date, edition, sequence):
title, issue, page = _get_tip(lccn, date, edition, sequence)
try:
text = get_page_text(page)
except models.OCR.DoesNotExist:
raise Http404("No OCR for %s" % page)
response = HttpResponse(text, content_type='text/plain')
return add_cache_tag(response, "lccn=%s" % lccn)
def page_ocr_txt(request, lccn, date, edition, sequence):
title, issue, page = _get_tip(lccn, date, edition, sequence)
try:
text = get_page_text(page)
except models.OCR.DoesNotExist:
raise Http404("No OCR for %s" % page)
response = HttpResponse(text, content_type='text/plain')
return add_cache_tag(response, "lccn=%s" % lccn)
def page_ocr_txt(request, lccn, date, edition, sequence):
title, issue, page = _get_tip(lccn, date, edition, sequence)
if not issue.batch.api_available:
return HttpResponse(status=403)
else:
try:
text = page.ocr.text
return HttpResponse(text, content_type='text/plain')
except models.OCR.DoesNotExist:
raise Http404("No OCR for %s" % page)
def test_getting_text_from_solr_slovenia(self):
"""
tests get_page_text() with batch batch_iune_oriole_ver01.
First creates a page object 'page' with _get_tip()
then uses it as an argument to get_page_text()
"""
batch_dir = os.path.join(settings.BATCH_STORAGE, 'batch_iune_oriole_ver01')
self.assertTrue(os.path.isdir(batch_dir))
loader = BatchLoader(process_ocr=True)
batch = loader.load_batch(batch_dir)
self.assertEqual(batch.name, 'batch_iune_oriole_ver01')
title, issue, page = _get_tip('sn83045377', '1906-03-01', 1, 1)
text = get_page_text(page)
self.assertIn("Od Mizo in dale", text[0])
self.assertIn("To je preecj inoettii tobak! Marsi", text[0])
# purge the batch and make sure it's gone from the db
loader.purge_batch('batch_iune_oriole_ver01')
self.assertEqual(Batch.objects.all().count(), 0)
self.assertEqual(Title.objects.get(lccn='sn83045377').has_issues, False)
def page(request, lccn, date, edition, sequence, words=None):
fragments = []
if words:
fragments.append("words=" + words)
qs = request.META.get('QUERY_STRING')
if qs:
fragments.append(qs)
if fragments:
path_parts = dict(lccn=lccn, date=date, edition=edition,
sequence=sequence)
url = urlresolvers.reverse('chronam_page',
kwargs=path_parts)
return HttpResponseRedirect(url + "#" + "&".join(fragments))
title, issue, page = _get_tip(lccn, date, edition, sequence)
if not page.jp2_filename:
notes = page.notes.filter(type="noteAboutReproduction")
num_notes = notes.count()
if num_notes >= 1:
explanation = notes[0].text
else:
explanation = ""
# if no word highlights were requests, see if the user came
# from search engine results and attempt to highlight words from their
# query by redirecting to a url that has the highlighted words in it
if not words:
try:
words = _search_engine_words(request)
words = '+'.join(words)
if len(words) > 0:
path_parts = dict(lccn=lccn, date=date, edition=edition,
sequence=sequence, words=words)
url = urlresolvers.reverse('chronam_page_words',
kwargs=path_parts)
return HttpResponseRedirect(url)
except Exception, e:
if settings.DEBUG:
raise e
def page(request, lccn, date, edition, sequence, words=None):
fragments = []
if words:
fragments.append("words=" + words)
qs = request.META.get('QUERY_STRING')
if qs:
fragments.append(qs)
if fragments:
path_parts = dict(lccn=lccn, date=date, edition=edition,
sequence=sequence)
url = urlresolvers.reverse('chronam_page',
kwargs=path_parts)
return HttpResponseRedirect(url + "#" + "&".join(fragments))
title, issue, page = _get_tip(lccn, date, edition, sequence)
if not page.jp2_filename:
notes = page.notes.filter(type="noteAboutReproduction")
num_notes = notes.count()
if num_notes >= 1:
explanation = notes[0].text
else:
explanation = ""
# if no word highlights were requests, see if the user came
# from search engine results and attempt to highlight words from their
# query by redirecting to a url that has the highlighted words in it
if not words:
try:
words = _search_engine_words(request)
words = '+'.join(words)
if len(words) > 0:
path_parts = dict(lccn=lccn, date=date, edition=edition,
sequence=sequence, words=words)
url = urlresolvers.reverse('chronam_page_words',
kwargs=path_parts)
return HttpResponseRedirect(url)
except Exception, e:
if settings.DEBUG:
raise e
def test_getting_text_from_solr_utah(self):
"""
tests get_page_text() with batch batch_uuml_thys_ver01.
First creates a page object 'page' with _get_tip()
then uses it as an argument to get_page_text()
"""
batch_dir = os.path.join(settings.BATCH_STORAGE, 'batch_uuml_thys_ver01')
self.assertTrue(os.path.isdir(batch_dir))
loader = BatchLoader(process_ocr=True)
batch = loader.load_batch(batch_dir)
self.assertEqual(batch.name, 'batch_uuml_thys_ver01')
title, issue, page = _get_tip('sn83045396', '1911-09-17', 1, 1)
text = get_page_text(page)
self.assertIn("Uc nice at tlio slate fair track", text[0])
self.assertIn("PAGES FIVE CENTS", text[0])
self.assertIn('gBter ho had left the grounds that', text[0])
# purge the batch and make sure it's gone from the db
loader.purge_batch('batch_uuml_thys_ver01')
self.assertEqual(Batch.objects.all().count(), 0)
self.assertEqual(Title.objects.get(lccn='sn83045396').has_issues, False)
def test_getting_text_from_solr_slovenia(self):
"""
tests get_page_text() with batch batch_iune_oriole_ver01.
First creates a page object 'page' with _get_tip()
then uses it as an argument to get_page_text()
"""
batch_dir = os.path.join(settings.BATCH_STORAGE,
'batch_iune_oriole_ver01')
self.assertTrue(os.path.isdir(batch_dir))
loader = BatchLoader(process_ocr=True)
batch = loader.load_batch(batch_dir)
self.assertEqual(batch.name, 'batch_iune_oriole_ver01')
title, issue, page = _get_tip('sn83045377', '1906-03-01', 1, 1)
text = get_page_text(page)
self.assertIn("Od Mizo in dale", text[0])
self.assertIn("To je preecj inoettii tobak! Marsi", text[0])
# purge the batch and make sure it's gone from the db
loader.purge_batch('batch_iune_oriole_ver01')
self.assertEqual(Batch.objects.all().count(), 0)
self.assertEqual(
Title.objects.get(lccn='sn83045377').has_issues, False)
def test_getting_text_from_solr_utah(self):
"""
tests get_page_text() with batch batch_uuml_thys_ver01.
First creates a page object 'page' with _get_tip()
then uses it as an argument to get_page_text()
"""
batch_dir = os.path.join(settings.BATCH_STORAGE,
'batch_uuml_thys_ver01')
self.assertTrue(os.path.isdir(batch_dir))
loader = BatchLoader(process_ocr=True)
batch = loader.load_batch(batch_dir)
self.assertEqual(batch.name, 'batch_uuml_thys_ver01')
title, issue, page = _get_tip('sn83045396', '1911-09-17', 1, 1)
text = get_page_text(page)
self.assertIn("Uc nice at tlio slate fair track", text[0])
self.assertIn("PAGES FIVE CENTS", text[0])
self.assertIn('gBter ho had left the grounds that', text[0])
# purge the batch and make sure it's gone from the db
loader.purge_batch('batch_uuml_thys_ver01')
self.assertEqual(Batch.objects.all().count(), 0)
self.assertEqual(
Title.objects.get(lccn='sn83045396').has_issues, False)
def page(request, lccn, date, edition, sequence):
title, issue, page = _get_tip(lccn, date, edition, sequence)
if not page.jp2_filename:
notes = page.notes.filter(type="noteAboutReproduction")
num_notes = notes.count()
if num_notes >= 1:
explanation = notes[0].text
else:
explanation = ""
# see if the user came from search engine results and attempt to
# highlight words from their query by redirecting to a url that
# has the highlighted words in it
try:
words = _search_engine_words(request)
words = '+'.join(words)
if len(words) > 0:
path_parts = dict(lccn=lccn,
date=date,
edition=edition,
sequence=sequence)
url = '%s?%s#%s' % (urlresolvers.reverse('chronam_page_words',
kwargs=path_parts),
request.GET.urlencode(), words)
response = HttpResponseRedirect(url)
return add_cache_tag(response, "lccn=%s" % lccn)
except Exception as exc:
LOGGER.error(
"Failed to add search highlighting based on the referred search engine query: %s",
exc,
exc_info=True)
if settings.DEBUG:
raise
# else squish the exception so the page will still get
# served up minus the highlights
# Calculate the previous_issue_first_page. Note: it was decided
# that we want to skip over issues with missing pages. See ticket
# #383.
_issue = issue
while True:
previous_issue_first_page = None
_issue = _issue.previous
if not _issue:
break
previous_issue_first_page = _issue.first_page
if previous_issue_first_page:
break
# do the same as above but for next_issue this time.
_issue = issue
while True:
next_issue_first_page = None
_issue = _issue.next
if not _issue:
break
next_issue_first_page = _issue.first_page
if next_issue_first_page:
break
page_title = "%s, %s, %s" % (label(title), label(issue), label(page))
page_head_heading = "%s, %s, %s" % (title.display_name, label(issue),
label(page))
page_head_subheading = label(title)
crumbs = create_crumbs(title, issue, date, edition, page)
filename = page.jp2_abs_filename
if filename:
try:
im = os.path.getsize(filename)
image_size = filesizeformat(im)
except OSError:
image_size = "Unknown"
image_credit = issue.batch.awardee.name
host = request.get_host()
profile_uri = 'http://www.openarchives.org/ore/html/'
template = "page.html"
text = get_page_text(page)
response = render_to_response(template,
dictionary=locals(),
context_instance=RequestContext(request))
return add_cache_tag(response, "lccn=%s" % lccn)
def page_ocr_xml(request, lccn, date, edition, sequence):
title, issue, page = _get_tip(lccn, date, edition, sequence)
return _stream_file(page.ocr_abs_filename, 'application/xml')
def page_jp2(request, lccn, date, edition, sequence):
title, issue, page = _get_tip(lccn, date, edition, sequence)
return _stream_file(page.jp2_abs_filename, 'image/jp2')
def page_pdf(request, lccn, date, edition, sequence):
title, issue, page = _get_tip(lccn, date, edition, sequence)
return _stream_file(page.pdf_abs_filename, 'application/pdf')
def page_jp2(request, lccn, date, edition, sequence):
title, issue, page = _get_tip(lccn, date, edition, sequence)
return _stream_file(page.jp2_abs_filename, 'image/jp2')
def page_ocr_xml(request, lccn, date, edition, sequence):
title, issue, page = _get_tip(lccn, date, edition, sequence)
return _stream_file(page.ocr_abs_filename, 'application/xml')
def page(request, lccn, date, edition, sequence):
title, issue, page = _get_tip(lccn, date, edition, sequence)
if not page.jp2_filename:
notes = page.notes.filter(type="noteAboutReproduction")
num_notes = notes.count()
if num_notes >= 1:
explanation = notes[0].text
else:
explanation = ""
# see if the user came from search engine results and attempt to
# highlight words from their query by redirecting to a url that
# has the highlighted words in it
try:
words = _search_engine_words(request)
words = '+'.join(words)
if len(words) > 0:
path_parts = dict(lccn=lccn, date=date, edition=edition, sequence=sequence)
url = '%s?%s#%s' % (urlresolvers.reverse('chronam_page_words',
kwargs=path_parts), request.GET.urlencode(), words)
response = HttpResponseRedirect(url)
return add_cache_tag(response, "lccn=%s" % lccn)
except Exception as exc:
LOGGER.error("Failed to add search highlighting based on the referred search engine query: %s",
exc, exc_info=True)
if settings.DEBUG:
raise
# else squish the exception so the page will still get
# served up minus the highlights
# Calculate the previous_issue_first_page. Note: it was decided
# that we want to skip over issues with missing pages. See ticket
# #383.
_issue = issue
while True:
previous_issue_first_page = None
_issue = _issue.previous
if not _issue:
break
previous_issue_first_page = _issue.first_page
if previous_issue_first_page:
break
# do the same as above but for next_issue this time.
_issue = issue
while True:
next_issue_first_page = None
_issue = _issue.next
if not _issue:
break
next_issue_first_page = _issue.first_page
if next_issue_first_page:
break
page_title = "%s, %s, %s" % (label(title), label(issue), label(page))
page_head_heading = "%s, %s, %s" % (title.display_name, label(issue), label(page))
page_head_subheading = label(title)
crumbs = create_crumbs(title, issue, date, edition, page)
filename = page.jp2_abs_filename
if filename:
try:
im = os.path.getsize(filename)
image_size = filesizeformat(im)
except OSError:
image_size = "Unknown"
image_credit = issue.batch.awardee.name
host = request.get_host()
profile_uri = 'http://www.openarchives.org/ore/html/'
template = "page.html"
text = get_page_text(page)
response = render_to_response(template, dictionary=locals(),
context_instance=RequestContext(request))
return add_cache_tag(response, "lccn=%s" % lccn)
def page_ocr_xml(request, lccn, date, edition, sequence):
title, issue, page = _get_tip(lccn, date, edition, sequence)
if not issue.batch.api_available:
return HttpResponse(status=403)
else:
return _stream_file(page.ocr_abs_filename, 'application/xml')
def page_pdf(request, lccn, date, edition, sequence):
title, issue, page = _get_tip(lccn, date, edition, sequence)
return _stream_file(page.pdf_abs_filename, 'application/pdf')
def page_jp2(request, lccn, date, edition, sequence):
title, issue, page = _get_tip(lccn, date, edition, sequence)
if not issue.batch.api_available:
return HttpResponse(status=403)
else:
return _stream_file(page.jp2_abs_filename, 'image/jp2')