def get(self, request, page): # page does nothing here, just ignore it
if len(request.GET) < 1:
# QueryFormset = formset_factory(QueryForm, extra=2)
return render_to_response('search.html',
context_instance=RequestContext(request))
else:
query = request.GET
subcorpus, subcorpus_sents, subcorpus_words, flag = get_subcorpus(
query)
# print subcorpus.count()
# subcorpus_sents = [sent.id for doc in subcorpus[0] for sent in doc.sentence_set.all()]
count_data = {
'total_docs': Document.objects.count(),
'total_sents': Sentence.objects.count(),
'total_tokens': Token.objects.count(),
'subcorpus_docs': len(subcorpus),
'subcorpus_sents': subcorpus_sents,
'subcorpus_words': subcorpus_words
}
per_page = int(query.get(u'per_page'))
page = request.GET.get('page')
page = int(page) if page else 1
expand = int(query.get(u'expand')[-1])
if query["exact_word"] != '':
jq, sent_list, word, res_docs, res_num = exact_search(
request.GET["exact_word"].lower().encode('utf-8'),
subcorpus, flag, expand, page, per_page)
else:
# todo rewrite this part of search
jq, sent_list, word, res_docs, res_num = lex_search(
query, subcorpus, flag, expand, page, per_page)
paginator = Paginator([''] * res_num, per_page)
start = page - 10 if page > 10 else 1
end = page + 10 if page + 10 <= paginator.num_pages else paginator.num_pages
paginator.page_range2 = range(start, end + 1)
try:
sents = paginator.page(page)
except PageNotAnInteger:
# If page is not an integer, deliver first page.
sents = paginator.page(1)
except EmptyPage:
# If page is out of range (e.g. 9999), deliver last page of results.
sents = paginator.page(paginator.num_pages)
full_path = rePage.sub('', request.get_full_path())
d_path = full_path.replace('19thcentury/search/',
'19thcentury/search/download/')
#word = re.sub('\s', '_', word)
return render_to_response('result.html', {
'query': word,
'result': sent_list,
'pages': sents,
'numbers': count_data,
'total': res_num,
'total_docs': res_docs,
'path': full_path,
'd_path': d_path,
'j': jq,
'olstart': (page - 1) * per_page + 1
},
context_instance=RequestContext(request))
def get(self, request, page): # page does nothing here, just ignore it
if len(request.GET) < 1:
QueryFormset = formset_factory(QueryForm, extra=2)
return render_to_response('search.html', {'form': QueryFormset},
context_instance=RequestContext(request))
else:
# print request.GET
query = request.GET
subcorpus, subcorpus_sents, subcorpus_words, flag = get_subcorpus(query)
# print subcorpus.count()
# subcorpus_sents = [sent.id for doc in subcorpus[0] for sent in doc.sentence_set.all()]
count_data = {'total_docs': Document.objects.count(),
'total_sents': Sentence.objects.count(),
'total_tokens': Token.objects.count(),
'subcorpus_docs': len(subcorpus),
'subcorpus_sents': subcorpus_sents,
'subcorpus_words': subcorpus_words}
per_page = int(query.get(u'per_page'))
expand = int(query.get(u'expand')[-1])
if query["exact_word"] != '':
jq, sent_list, word, res_docs = exact_search(request.GET["exact_word"].lower().encode('utf-8'), subcorpus, flag, expand)
else:
# QueryFormset = formset_factory(QueryForm)
# formset = QueryFormset(request.GET, request.FILES)
# if formset.is_valid():
# todo rewrite this part of search
jq, sent_list, word, res_docs = lex_search(query, subcorpus, flag, expand)
page = request.GET.get('page')
paginator = Paginator(sent_list, per_page)
jq_paginator = Paginator(jq, per_page)
if page:
page = int(page)
start = page - 10 if page > 10 else 1
end = page + 10 if page + 10 <= paginator.num_pages else paginator.num_pages
else:
start = 1
end = 11 if paginator.num_pages > 10 else paginator.num_pages + 1
paginator.page_range2 = range(start, end)
try:
sents = paginator.page(page)
jq = jq_paginator.page(page)
except PageNotAnInteger:
# If page is not an integer, deliver first page.
sents = paginator.page(1)
jq = jq_paginator.page(1)
except EmptyPage:
# If page is out of range (e.g. 9999), deliver last page of results.
sents = paginator.page(paginator.num_pages)
jq = jq_paginator.page(jq_paginator.num_pages)
full_path = rePage.sub('', request.get_full_path())
return render_to_response('result.html',
{'query': word, 'result': sents,
'numbers': count_data,
'total': len(sent_list), 'total_docs': res_docs,
'path':full_path, 'j':jq},
context_instance=RequestContext(request))
def get(self, request, page): # page does nothing here, just ignore it
if len(request.GET) < 1:
# QueryFormset = formset_factory(QueryForm, extra=2)
return render_to_response('search.html',
context_instance=RequestContext(request))
else:
query = request.GET
subcorpus, subcorpus_sents, subcorpus_words, flag = get_subcorpus(query)
# print subcorpus.count()
# subcorpus_sents = [sent.id for doc in subcorpus[0] for sent in doc.sentence_set.all()]
count_data = {'total_docs': Document.objects.count(),
'total_sents': Sentence.objects.count(),
'total_tokens': Token.objects.count(),
'subcorpus_docs': len(subcorpus),
'subcorpus_sents': subcorpus_sents,
'subcorpus_words': subcorpus_words}
per_page = int(query.get(u'per_page'))
page = request.GET.get('page')
page = int(page) if page else 1
expand = int(query.get(u'expand')[-1])
if query["exact_word"] != '':
jq, sent_list, word, res_docs, res_num = exact_search(request.GET["exact_word"].lower().encode('utf-8'), subcorpus, flag, expand, page, per_page)
else:
# todo rewrite this part of search
jq, sent_list, word, res_docs, res_num = lex_search(query, subcorpus, flag, expand, page, per_page)
paginator = Paginator([''] * res_num, per_page)
start = page - 10 if page > 10 else 1
end = page + 10 if page + 10 <= paginator.num_pages else paginator.num_pages
paginator.page_range2 = range(start, end + 1)
try:
sents = paginator.page(page)
except PageNotAnInteger:
# If page is not an integer, deliver first page.
sents = paginator.page(1)
except EmptyPage:
# If page is out of range (e.g. 9999), deliver last page of results.
sents = paginator.page(paginator.num_pages)
full_path = rePage.sub('', request.get_full_path())
d_path = full_path.replace('19thcentury/search/', '19thcentury/search/download/')
#word = re.sub('\s', '_', word)
return render_to_response('result.html',
{'query': word, 'result': sent_list, 'pages': sents,
'numbers': count_data,
'total': res_num, 'total_docs': res_docs,
'path': full_path, 'd_path': d_path, 'j': jq, 'olstart': (page - 1) * per_page + 1},
context_instance=RequestContext(request))
def get(self, request): # page does nothing here, just ignore it
if len(request.GET) < 1:
# QueryFormset = formset_factory(QueryForm, extra=2)
return render(request, 'search/search.html')
else:
# print request.GET
# u_groups = request.user.groups
query = request.GET
# print(query)
subcorpus, subcorpus_sents, subcorpus_words, flag = get_subcorpus(query) #, u_groups)
# print subcorpus.count()
# subcorpus_sents = [sent.id for doc in subcorpus[0] for sent in doc.sentence_set.all()]
count_data = {'total_docs': Document.objects.count(),
'total_sents': Sentence.objects.count(),
'total_tokens': Token.objects.count(),
'subcorpus_docs': len(subcorpus),
'subcorpus_sents': subcorpus_sents,
'subcorpus_words': subcorpus_words}
per_page = int(query.get(u'per_page'))
page = request.GET.get('page')
page = int(page) if page else 1
expand = int(query.get(u'expand')[-1])
if "exact_search" in query:
jq, sent_list, word, res_docs, res_num = exact_full_search(request.GET["exact_word"].lower().encode('utf-8'), subcorpus, flag, expand, page, per_page)
elif "orig_search" in query:
jq, sent_list, word, res_docs, res_num = orig_exact_search(request.GET["orig_word"].lower().encode('utf-8'), subcorpus, flag, expand, page, per_page)
else:
# todo rewrite this part of search
jq, sent_list, word, res_docs, res_num = lex_search(query, subcorpus, flag, expand, page, per_page)
paginator = Paginator(['']*res_num, per_page)
start = page - 10 if page > 10 else 1
end = page + 10 if page + 10 <= paginator.num_pages else paginator.num_pages
paginator.page_range2 = range(start, end+1)
try:
sents = paginator.page(page)
except PageNotAnInteger:
# If page is not an integer, deliver first page.
sents = paginator.page(1)
except EmptyPage:
# If page is out of range (e.g. 9999), deliver last page of results.
sents = paginator.page(paginator.num_pages)
full_path = rePage.sub('', request.get_full_path())
PREFIX = 'translator_corpus' if PROD else ''
d_path = full_path.replace(PREFIX + '/search/', PREFIX + '/search/download/')
if not "orig_search" in query:
result = sent_dict(sent_list)
return render(request, 'search/result.html',
{'query': word, 'result': result, 'pages': sents,
'numbers': count_data,
'total': res_num, 'total_docs': res_docs,
'path':full_path, 'd_path':d_path, 'j':jq, 'olstart': (page-1)*per_page + 1})
else:
# fw = open('log.txt', 'w')
# fw.write(str(sent_list))
# fw.close()
# for k in sent_list:
# print(sent_list[k].text)
return render(request, 'search/result_orig.html',
{'query': word, 'result': sent_list, 'pages': sents,
'numbers': count_data,
'total': res_num, 'total_docs': res_docs,
'path':full_path, 'd_path':d_path, 'j':jq, 'olstart': (page-1)*per_page + 1})
def get(self, request):
if len(request.GET) < 1:
# QueryFormset = formset_factory(QueryForm, extra=2)
return render_to_response('download_search.html',
context_instance=RequestContext(request))
else:
# print request.GET
# u_groups = request.user.groups
query = request.GET
subcorpus, subcorpus_sents, subcorpus_words, flag = get_subcorpus(
query) #, u_groups)
# print subcorpus.count()
# subcorpus_sents = [sent.id for doc in subcorpus[0] for sent in doc.sentence_set.all()]
count_data = {
'total_docs': Document.objects.count(),
'total_sents': Sentence.objects.count(),
'total_tokens': Token.objects.count(),
'subcorpus_docs': len(subcorpus),
'subcorpus_sents': subcorpus_sents,
'subcorpus_words': subcorpus_words
}
per_page = int(query.get(u'per_page'))
page = request.GET.get('page')
page = int(page) if page else 1
expand = int(query.get(u'expand')[-1])
if "exact_search" in query:
jq, sent_list, word, res_docs, res_num = exact_full_search(
request.GET["exact_word"].lower().encode('utf-8'),
subcorpus, flag, expand, page, per_page)
else:
# todo rewrite this part of search
jq, sent_list, word, res_docs, res_num = lex_search(
query, subcorpus, flag, expand, page, per_page)
paginator = Paginator([''] * res_num, per_page)
start = page - 10 if page > 10 else 1
end = page + 10 if page + 10 <= paginator.num_pages else paginator.num_pages
paginator.page_range2 = range(start, end + 1)
try:
sents = paginator.page(page)
except PageNotAnInteger:
# If page is not an integer, deliver first page.
sents = paginator.page(1)
except EmptyPage:
# If page is out of range (e.g. 9999), deliver last page of results.
sents = paginator.page(paginator.num_pages)
full_path = rePage.sub('', request.get_full_path())
rows = []
rows.append([
u'Номер примера', u'Название текста', u'Язык', u'Русский язык',
u'Уровень', u'Год', u'Оригинальное предложение',
u'Исправленное предложение', u'Тег', u'Ошибка', u'Исправление',
u'Разметчик', u'Комментарий'
])
for ind, sent in enumerate(sent_list):
anns = Sentence.get_annotations(sent.id)
if not anns:
rows.append([(page - 1) * per_page + 1 + ind,
sent.doc_id.title, sent.doc_id.native,
sent.doc_id.language_background,
sent.doc_id.level, sent.doc_id.date_displayed,
reSpan.sub('\\2', sent.tagged).replace(
'<b>', '{{').replace('</b>', '}}'),
reSpan.sub('\\2', sent.correct).replace(
'<span class="correction">',
'*').replace('</span>',
'*'), '', '', '', '', ''])
else:
for an in anns:
rows.append([
(page - 1) * per_page + 1 + ind, sent.doc_id.title,
sent.doc_id.native,
sent.doc_id.language_background, sent.doc_id.level,
sent.doc_id.date_displayed,
reSpan.sub('\\2', sent.tagged).replace(
'<b>', '{{').replace('</b>', '}}'),
reSpan.sub('\\2', sent.correct).replace(
'<span class="correction">',
'*').replace('</span>',
'*'), an['tag'], an['quote'],
an['corr'], an['owner'].username, an['comment']
])
output = StringIO.StringIO()
book = xlsxwriter.Workbook(output)
sheet = book.add_worksheet()
for row_num, row in enumerate(rows):
for col_num, item in enumerate(row):
sheet.write(row_num, col_num, item)
book.close()
# construct response
output.seek(0)
response = HttpResponse(
output.read(),
content_type=
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
)
response[
'Content-Disposition'] = 'attachment; filename="rlc_search_results.xlsx"'
return response
def get(self, request, page): # page does nothing here, just ignore it
if len(request.GET) < 1:
QueryFormset = formset_factory(QueryForm, extra=2)
d = {}
# d['genres'] = set([i.genre for i in Document.objects.all() if i.genre not in [u"", None, ' ']])
# d['course'] = set([i.course for i in Document.objects.all() if i.course not in [u"", None, ' ']])
# d['major'] = set([i.major for i in Document.objects.all() if i.major not in [u"", None, ' ']])
# d['domain'] = set([i.domain for i in Document.objects.all() if i.domain not in [u"", None, ' ']])
return render_to_response('search.html', {
'form': QueryFormset,
'd': d
},
context_instance=RequestContext(request))
else:
query = request.GET
subcorpus, subcorpus_sents, subcorpus_words, flag = get_subcorpus(
query)
# print subcorpus.count()
# subcorpus_sents = [sent.id for doc in subcorpus[0] for sent in doc.sentence_set.all()]
count_data = {
'total_docs': Document.objects.count(),
'total_sents': Sentence.objects.count(),
'total_tokens': Token.objects.count(),
'subcorpus_docs': len(subcorpus),
'subcorpus_sents': subcorpus_sents,
'subcorpus_words': subcorpus_words
}
per_page = int(query.get(u'per_page'))
page = request.GET.get('page')
page = int(page) if page else 1
expand = int(query.get(u'expand')[-1])
if query["exact_word"] != '':
jq, sent_list, word, res_docs, res_num = exact_search(
request.GET["exact_word"].lower().encode('utf-8'),
subcorpus, flag, expand, page, per_page)
else:
# QueryFormset = formset_factory(QueryForm)
# formset = QueryFormset(request.GET, request.FILES)
# if formset.is_valid():
# todo rewrite this part of search
jq, sent_list, word, res_docs, res_num = lex_search(
query, subcorpus, flag, expand, page, per_page)
paginator = Paginator([''] * res_num, per_page)
start = page - 10 if page > 10 else 1
end = page + 10 if page + 10 <= paginator.num_pages else paginator.num_pages
paginator.page_range2 = range(start, end + 1)
try:
sents = paginator.page(page)
except PageNotAnInteger:
# If page is not an integer, deliver first page.
sents = paginator.page(1)
except EmptyPage:
# If page is out of range (e.g. 9999), deliver last page of results.
sents = paginator.page(paginator.num_pages)
full_path = rePage.sub('', request.get_full_path())
return render_to_response('result.html', {
'query': word,
'result': sent_list,
'pages': sents,
'numbers': count_data,
'total': res_num,
'total_docs': res_docs,
'path': full_path,
'j': jq,
'olstart': (page - 1) * per_page + 1
},
context_instance=RequestContext(request))