def create_corpus(self):
#create a corpus
corpus = Node(name=self.query,
user_id=self.user_id,
parent_id=self.project_id,
typename='CORPUS',
hyperdata={
"action": "Scrapping data",
"language_id": self.type["default_language"],
})
self.corpus_id = corpus.id
if len(self.paths) > 0:
for path in self.paths:
#add the resource
corpus.add_resource(type=self.type["type"],
name=self.type["name"],
path=path)
session.add(corpus)
session.commit()
scheduled(parse_extract_indexhyperdata(corpus.id))
else:
#add the resource
corpus.add_resource(type=self.type["type"],
name=self.type["name"],
path=self.path)
session.add(corpus)
session.commit()
scheduled(parse_extract_indexhyperdata(corpus.id))
return corpus
def post(self, request):
"""
Merge the lists of a corpus with other lists from a CSV source
or from another corpus
params in request.GET:
onto_corpus: the corpus whose lists are getting patched
params in request.data:
csvfile: the csv file
/!\ We assume we checked the file size client-side before upload
"""
if not request.user.is_authenticated():
res = HttpResponse("Unauthorized")
res.status_code = 401
return res
# the corpus with the target lists to be patched
params = get_parameters(request)
corpus_id = int(params.pop("onto_corpus"))
corpus_node = cache.Node[corpus_id]
if request.user.id != corpus_node.user_id:
res = HttpResponse("Unauthorized")
res.status_code = 401
return res
# request also contains the file
# csv_file has type django.core.files.uploadedfile.InMemoryUploadedFile
# ----------------------
csv_file = request.data['csvfile']
csv_contents = csv_file.read().decode("UTF-8").split("\n")
csv_file.close()
del csv_file
# import the csv
# try:
log_msg = "Async generation"
corpus_node_id = corpus_node.id
scheduled(import_and_merge_ngramlists)(csv_contents,
corpus_node_id,
overwrite=bool(
params.get('overwrite')))
return JsonHttpResponse({
'log': log_msg,
}, 200)
def patch(self, request, corpusnode_id):
"""
PATCH triggers recount of metrics for the specified corpus.
ex PATCH http://localhost:8000/api/metrics/14072
-----
corpus_id
"""
print("==> update metrics request on ", corpusnode_id)
if not request.user.is_authenticated():
# can't use @requires_auth because of positional 'self' within class
return HttpResponse('Unauthorized', status=401)
try:
corpus = cache.Node[int(corpusnode_id)]
except:
corpus = None
if corpus is None:
raise ValidationException("%s is not a valid corpus node id." %
corpusnode_id)
else:
t_before = datetime.now()
# =============
scheduled(recount)(corpus.id)
# =============
t_after = datetime.now()
return JsonHttpResponse({
'corpus_id':
corpusnode_id,
'took':
"%f s." % (t_after - t_before).total_seconds()
})
def save(request, project_id):
'''save'''
if request.method == "POST":
query = request.POST.get("query")
try:
N = int(request.POST.get("N"))
except:
N = 0
print(query, N)
#for next time
#ids = request.POST["ids"]
source = get_resource(RESOURCE_TYPE_SCOAP)
if N == 0:
raise Http404()
if N > QUERY_SIZE_N_MAX:
N = QUERY_SIZE_N_MAX
try:
project_id = int(project_id)
except ValueError:
raise Http404()
# do we have a valid project?
project = session.query(Node).filter(Node.id == project_id).first()
if project is None:
raise Http404()
user = cache.User[request.user.id]
if not user.owns(project):
return HttpResponseForbidden()
# corpus node instanciation as a Django model
corpus = Node(name=query,
user_id=request.user.id,
parent_id=project_id,
typename='CORPUS',
hyperdata={
"action": "Scrapping data",
"language_id": "en"
})
#download_file
crawler_bot = load_crawler(source)()
#for now no way to force downloading X records
#the long running command
filename = crawler_bot.download(query)
corpus.add_resource(
type=source["type"]
#, name = source["name"]
,
path=crawler_bot.path)
session.add(corpus)
session.commit()
#corpus_id = corpus.id
try:
scheduled(parse_extract_indexhyperdata)(corpus.id)
except Exception as error:
print('WORKFLOW ERROR')
print(error)
try:
print_tb(error.__traceback__)
except:
pass
# IMPORTANT ---------------------------------
# sanitize session after interrupted transact
session.rollback()
# --------------------------------------------
return render(
template_name='pages/projects/wait.html',
request=request,
context={
'user': request.user,
'project': project,
},
)
data = [query_string, query, N]
print(data)
return JsonHttpResponse(data)
def project(request, project_id):
# security check
project = session.query(Node).filter(Node.id == project_id).first()
user = cache.User[request.user.id]
if project is None:
raise Http404()
if not user.owns(project):
return HttpResponseForbidden()
# end of security check
# new corpus
if request.method == 'POST':
corpus = project.add_child(
name=request.POST['name'],
typename='CORPUS',
)
corpus.add_resource(
type=int(request.POST['type']),
path=upload(request.FILES['file']),
)
session.add(corpus)
session.commit()
# parse_extract: fileparsing -> ngram extraction -> lists
scheduled(parse_extract_indexhyperdata)(corpus.id)
wait = True
else:
wait = False
# corpora within this project
corpora = project.children('CORPUS', order=True).all()
sourcename2corpora = defaultdict(list)
for corpus in corpora:
# we only consider the first resource of the corpus to determine its type
resources = corpus.resources()
if len(resources):
resource = resources[0]
#resource_type_name = RESOURCETYPES[resource['type']]['name']
resource_type_name = get_resource(resource["type"])["name"]
else:
print("(WARNING) PROJECT view: no listed resource")
# add some data for the viewer
corpus.count = corpus.children('DOCUMENT').count()
status = corpus.status()
if status is not None and not status['complete']:
if not status['error']:
corpus.status_message = '(in progress: %s, %d complete)' % (
status['action'].replace('_', ' '),
status['progress'],
)
else:
corpus.status_message = '(aborted: "%s" after %i docs)' % (
status['error'][-1], status['progress'])
else:
corpus.status_message = ''
# add
sourcename2corpora[resource_type_name].append(corpus)
# source & their respective counts
total_documentscount = 0
sourcename2documentscount = defaultdict(int)
for sourcename, corpora in sourcename2corpora.items():
sourcename = re.sub(' \(.*$', '', sourcename)
for corpus in corpora:
count = corpus.children('DOCUMENT').count()
sourcename2documentscount[sourcename] += count
total_documentscount += count
donut = [{
'source':
sourcename,
'count':
count,
'part':
round(count * 100.0 /
total_documentscount, 1) if total_documentscount else 0,
} for sourcename, count in sourcename2documentscount.items()]
if wait:
return render(
template_name='pages/projects/wait.html',
request=request,
context={
'form': NewCorpusForm,
'user': request.user,
'date': datetime.now(),
'project': project,
'donut': donut,
'list_corpora': dict(sourcename2corpora),
'whitelists': [],
'blacklists': [],
'cooclists': [],
'number': len(corpora),
'query_size': QUERY_SIZE_N_DEFAULT,
# status refreshing params (when active workflows)
'status_refresh_initial_interval':
PROJECT_VIEW_REFRESH_INTERVAL,
'status_refresh_max_attempts':
PROJECT_VIEW_MAX_REFRESH_ATTEMPTS,
},
)
# response!
return render(
template_name='pages/projects/project.html',
request=request,
context={
'form': NewCorpusForm,
'user': request.user,
'date': datetime.now(),
'project': project,
'donut': donut,
'list_corpora': dict(sourcename2corpora),
'whitelists': [],
'blacklists': [],
'cooclists': [],
'number': len(corpora),
'query_size': QUERY_SIZE_N_DEFAULT,
# status refreshing params (when active workflows)
'status_refresh_initial_interval': PROJECT_VIEW_REFRESH_INTERVAL,
'status_refresh_max_attempts': PROJECT_VIEW_MAX_REFRESH_ATTEMPTS,
},
)
def save(request, project_id, return_corpus=False):
print("testISTEX:")
print(request.method)
alist = ["bar", "foo"]
# implicit global session
# do we have a valid project id?
try:
project_id = int(project_id)
except ValueError:
raise Http404()
# do we have a valid project?
project = (session.query(Node).filter(Node.id == project_id).filter(
Node.typename == 'PROJECT')).first()
if project is None:
raise Http404()
# do we have a valid user?
user = request.user
if not user.is_authenticated():
return redirect('/auth/?next=%s' % request.path)
if project.user_id != user.id:
return HttpResponseForbidden()
query_string = ""
if request.method == "POST":
query = "-"
query_string = "-"
#N = QUERY_SIZE_N_MAX
if "query" in request.POST:
query = request.POST["query"]
query_string = query.replace(" ", "+") # url encoded q
if "N" in request.POST:
if request.POST["N"] == "NaN":
N = QUERY_SIZE_N_MAX
else:
N = int(request.POST["N"]) # query_size from views_opti
if N > QUERY_SIZE_N_MAX:
N = QUERY_SIZE_N_MAX
#msg = "Invalid sample size N = %i (max = %i)" % (N, QUERY_SIZE_N_MAX)
#print("ERROR (scrap: istex d/l ): ",msg)
#raise ValueError(msg)
print("Scrapping Istex: '%s' (%i)" % (query_string, N))
urlreqs = []
pagesize = 50
tasks = Scraper()
chunks = list(tasks.chunks(range(N), pagesize))
for k in chunks:
if (k[0] + pagesize) > N: pagesize = N - k[0]
urlreqs.append(
"http://api.istex.fr/document/?q=" + query_string +
"&output=id,corpusName,title,genre,language,doi,host,publicationDate,abstract,author&"
+ "from=" + str(k[0]) + "&size=" + str(pagesize))
# corpus node instanciation as a Django model
corpus = Node(name=query,
user_id=request.user.id,
parent_id=project_id,
typename='CORPUS',
hyperdata={
"action": "Scrapping data",
"language_id": None
})
tasks = Scraper()
for i in range(8):
t = threading.Thread(target=tasks.worker2) #thing to do
t.daemon = True # thread dies when main thread (only non-daemon thread) exits.
t.start()
for url in urlreqs:
tasks.q.put(url) #put a task in th queue
tasks.q.join() # wait until everything is finished
dwnldsOK = 0
for filename in tasks.firstResults:
if filename != False:
# add the uploaded resource to the corpus
corpus.add_resource(
type=get_resource(RESOURCE_TYPE_ISTEX)["type"],
path=filename)
dwnldsOK += 1
session.add(corpus)
session.commit()
#corpus_id = corpus.id
if dwnldsOK == 0:
return JsonHttpResponse(["fail"])
###########################
###########################
try:
scheduled(parse_extract_indexhyperdata)(corpus.id)
except Exception as error:
print('WORKFLOW ERROR')
print(error)
try:
print_tb(error.__traceback__)
except:
pass
# IMPORTANT ---------------------------------
# sanitize session after interrupted transact
session.rollback()
# --------------------------------------------
if return_corpus:
return corpus
return render(
template_name='pages/projects/wait.html',
request=request,
context={
'user': request.user,
'project': project,
},
)
data = [query_string, query, N]
print(data)
return JsonHttpResponse(data)
def save( request , project_id ) :
# implicit global session
# do we have a valid project id?
try:
project_id = int(project_id)
except ValueError:
raise Http404()
# do we have a valid project?
project = session.query( Node ).filter(Node.id == project_id).first()
if project is None:
raise Http404()
user = cache.User[request.user.id]
if not user.owns(project):
return HttpResponseForbidden()
if request.method == "POST":
queries = request.POST["query"]
name = request.POST["string"]
# here we just realize queries already prepared by getGlobalStats
# ===> no need to repeat N parameter like in testISTEX <===
instancia = Scraper()
thequeries = json.loads(queries)
# fyi the sum of our prepared yearly proportional quotas
sampled_sum = sum([year_q['retmax'] for year_q in thequeries])
print("Scrapping Pubmed: '%s' (N=%i)" % (name,sampled_sum))
urlreqs = []
for yearquery in thequeries:
urlreqs.append( instancia.medlineEfetchRAW( yearquery ) )
alist = ["tudo fixe" , "tudo bem"]
# corpus node instanciation as a Django model
corpus = project.add_child( name=name
, typename = "CORPUS"
)
# """
# urlreqs: List of urls to query.
# - Then, to each url in urlreqs you do:
# eFetchResult = urlopen(url)
# eFetchResult.read() # this will output the XML... normally you write this to a XML-file.
# """
tasks = Scraper()
for i in range(8):
t = threading.Thread(target=tasks.worker2) #thing to do
t.daemon = True # thread dies when main thread (only non-daemon thread) exits.
t.start()
for url in urlreqs:
tasks.q.put( url ) #put a task in the queue
tasks.q.join() # wait until everything is finished
dwnldsOK = 0
for filename in tasks.firstResults :
print(filename)
if filename != False:
# add the uploaded resource to the corpus
corpus.add_resource( type = get_resource_by_name('Pubmed [XML]')["type"]
, path = filename
, url = None
)
print("Adding the resource")
dwnldsOK+=1
session.add(corpus)
session.commit()
corpus_id = corpus.id
if dwnldsOK == 0 :
return JsonHttpResponse(["fail"])
try:
scheduled(parse_extract_indexhyperdata)(corpus_id)
except Exception as error:
print('WORKFLOW ERROR')
print(error)
try:
print_tb(error.__traceback__)
except:
pass
# IMPORTANT ---------------------------------
# sanitize session after interrupted transact
session.rollback()
# --------------------------------------------
sleep(1)
return HttpResponseRedirect('/projects/' + str(project_id))
data = alist
return JsonHttpResponse(data)
def get_graph(request=None,
corpus=None,
field1='ngrams',
field2='ngrams',
mapList_id=None,
groupList_id=None,
cooc_id=None,
type='node_link',
start=None,
end=None,
distance='conditional',
bridgeness=5,
threshold=1,
isMonopartite=True,
saveOnly=True):
'''
Get_graph : main steps:
0) Check the parameters
get_graph :: GraphParameters -> Either (Dic Nodes Links) (Dic State Length)
where type Length = Int
get_graph first checks the parameters and return either graph data or a dict with
state "type" with an integer to indicate the size of the parameter
(maybe we could add a String in that step to factor and give here the error message)
1) compute_graph (see function above)
2) return graph
'''
overwrite_node_contents = False
# Case of graph has been computed already
if cooc_id is not None:
print("GRAPH#%d ... Loading data already computed." % int(cooc_id))
node = session.query(Node).filter(Node.id == cooc_id).first()
# Structure of the Node.hyperdata[distance][bridbeness]
# All parameters (but distance and bridgeness)
# are in Node.hyperdata["parameters"]
# Check distance of the graph
if node.hyperdata.get(distance, None) is not None:
graph = node.hyperdata[distance]
# Check bridgeness of the graph
if graph.get(str(bridgeness), None) is not None:
return graph[str(bridgeness)]
# new graph: we give it an empty node with new id and status
elif saveOnly:
# NB: we do creation already here (instead of same in countCooccurrences)
# to guarantee a unique ref id to the saveOnly graph (async generation)
new_node = corpus.add_child(typename="COOCCURRENCES",
name="GRAPH (in corpus %s)" % corpus.id)
session.add(new_node)
session.commit()
cooc_id = new_node.id
cooc_name = new_node.name
cooc_date = new_node.date
# and the empty content will need redoing by countCooccurrences
overwrite_node_contents = True
print("GRAPH #%d ... Created new empty data node for saveOnly" %
int(cooc_id))
# Case of graph has not been computed already
# First, check the parameters
# Case of mapList not big enough
# ==============================
# if we do not have any mapList_id already
if mapList_id is None:
mapList_id = session.query(
Node.id).filter(Node.typename == "MAPLIST").first()[0]
mapList_size = session.query(NodeNgram).filter(
NodeNgram.node_id == mapList_id).count()
if mapList_size < graph_constraints['mapList']:
# Do not compute the graph if mapList is not big enough
return {'state': "mapListError", "length": mapList_size}
# Instantiate query for case of corpus not big enough
# ===================================================
corpus_size_query = (session.query(Node).filter(
Node.typename == "DOCUMENT").filter(Node.parent_id == corpus.id))
# Filter corpus by date if any start date
# ---------------------------------------
if start is not None:
#date_start = datetime.datetime.strptime ("2001-2-3 10:11:12", "%Y-%m-%d %H:%M:%S")
date_start = datetime.strptime(str(start), "%Y-%m-%d")
date_start_utc = date_start.strftime("%Y-%m-%d %H:%M:%S")
Start = aliased(NodeHyperdata)
corpus_size_query = (corpus_size_query.join(
Start, Start.node_id == Node.id).filter(
Start.key == 'publication_date').filter(
Start.value_utc >= date_start_utc))
# Filter corpus by date if any end date
# -------------------------------------
if end is not None:
date_end = datetime.strptime(str(end), "%Y-%m-%d")
date_end_utc = date_end.strftime("%Y-%m-%d %H:%M:%S")
End = aliased(NodeHyperdata)
corpus_size_query = (corpus_size_query.join(
End, End.node_id == Node.id).filter(
End.key == 'publication_date').filter(
End.value_utc <= date_end_utc))
# Finally test if the size of the corpora is big enough
# --------------------------------
corpus_size = corpus_size_query.count()
if saveOnly is not None and saveOnly == "True":
scheduled(compute_graph)(
corpus_id=corpus.id,
cooc_id=cooc_id
#, field1="ngrams", field2="ngrams"
,
start=start,
end=end,
mapList_id=mapList_id,
groupList_id=groupList_id,
isMonopartite=True,
threshold=threshold,
distance=distance,
bridgeness=bridgeness,
save_on_db=True,
reset=overwrite_node_contents
#, limit=size
)
return {
"state": "saveOnly",
"target_id": cooc_id,
"target_name": cooc_name,
"target_date": cooc_date
}
elif corpus_size > graph_constraints['corpusMax']:
# Then compute cooc asynchronously with celery
scheduled(compute_graph)(
corpus_id=corpus.id,
cooc_id=cooc_id
#, field1="ngrams", field2="ngrams"
,
start=start,
end=end,
mapList_id=mapList_id,
groupList_id=groupList_id,
isMonopartite=True,
threshold=threshold,
distance=distance,
bridgeness=bridgeness,
save_on_db=True,
reset=overwrite_node_contents
#, limit=size
)
# Dict to inform user that corpus maximum is reached
# then graph is computed asynchronously
return {"state": "corpusMax", "length": corpus_size}
elif corpus_size <= graph_constraints['corpusMin']:
# Do not compute the graph if corpus is not big enough
return {"state": "corpusMin", "length": corpus_size}
else:
# If graph_constraints are ok then compute the graph in live
data = compute_graph(
corpus_id=corpus.id,
cooc_id=cooc_id
#, field1="ngrams", field2="ngrams"
,
start=start,
end=end,
mapList_id=mapList_id,
groupList_id=groupList_id,
isMonopartite=True,
threshold=threshold,
distance=distance,
bridgeness=bridgeness,
save_on_db=True,
reset=overwrite_node_contents
#, limit=size
)
# case when 0 coocs are observed (usually b/c not enough ngrams in maplist)
if len(data) == 0:
print("GRAPH # ... GET_GRAPH: 0 coocs in matrix")
data = {'nodes': [], 'links': []} # empty data
return data
