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, content_type='text/plain')
except models.OCR.DoesNotExist:
raise Http404("No OCR for %s" % page)
def openoni_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('openoni_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('openoni_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')
openoni_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 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),
content_type='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), content_type='application/json')
else:
return HttpResponseNotFound()
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('openoni_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('openoni_page_words',
kwargs=path_parts)
return HttpResponseRedirect(url)
except Exception, e:
if settings.DEBUG:
raise e
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')