def get_start_end_date(environ, start_response):
status = "200 OK"
headers = [("Content-type", "text/html; charset=UTF-8"), ("Access-Control-Allow-Origin", "*")]
start_response(status, headers)
config = WebConfig(os.path.abspath(os.path.dirname(__file__)).replace("scripts", ""))
db = DB(config.db_path + "/data/")
request = WSGIHandler(environ, config)
start_date, end_date = start_end_date(db, config, start_date=request.start_date, end_date=request.end_date)
request.metadata["year"] = "{}-{}".format(start_date, end_date)
request["start_date"] = ""
request["end_date"] = ""
hits = db.query(request["q"], request["method"], request["arg"], **request.metadata)
total_results = 0
hits.finish()
total_results = len(hits)
yield json.dumps({"start_date": start_date, "end_date": end_date, "total_results": total_results}).encode("utf8")
def bibliography(environ, start_response):
config = WebConfig(os.path.abspath(os.path.dirname(__file__)).replace('reports', ''))
request = WSGIHandler(environ, config)
headers = [('Content-type', 'application/json; charset=UTF-8'),
("Access-Control-Allow-Origin", "*")]
start_response('200 OK', headers)
bibliography_object, hits = bibliography_results(request, config)
yield simplejson.dumps(bibliography_object)
def get_bibliography(environ, start_response):
status = '200 OK'
headers = [('Content-type', 'application/json; charset=UTF-8'),
("Access-Control-Allow-Origin", "*")]
start_response(status, headers)
config = WebConfig(os.path.abspath(os.path.dirname(__file__)).replace('scripts', ''))
request = WSGIHandler(environ, config)
results = landing_page_bibliography(request, config)
yield json.dumps(results).encode('utf8')
def alignment_to_text(environ, start_response):
status = '200 OK'
headers = [('Content-type', 'application/json; charset=UTF-8'),
("Access-Control-Allow-Origin", "*")]
start_response(status, headers)
config = WebConfig(os.path.abspath(os.path.dirname(__file__)).replace('scripts', ''))
db = DB(config.db_path + '/data/')
request = WSGIHandler(environ, config)
link = byte_range_to_link(db, config, request)
yield simplejson.dumps({"link": link})
def metadata_list(environ, start_response):
status = "200 OK"
headers = [("Content-type", "application/json; charset=UTF-8"),
("Access-Control-Allow-Origin", "*")]
start_response(status, headers)
config = WebConfig(
os.path.abspath(os.path.dirname(__file__)).replace("scripts", ""))
db = DB(config.db_path + "/data/")
request = WSGIHandler(environ, config)
metadata = request.term
field = request.field
yield autocomplete_metadata(metadata, field, db).encode("utf8")
def get_start_end_date(environ, start_response):
status = '200 OK'
headers = [('Content-type', 'text/html; charset=UTF-8'),
("Access-Control-Allow-Origin", "*")]
start_response(status, headers)
config = WebConfig(
os.path.abspath(os.path.dirname(__file__)).replace('scripts', ''))
db = DB(config.db_path + '/data/')
request = WSGIHandler(environ, config)
start_date, end_date = start_end_date(db,
config,
start_date=request.start_date,
end_date=request.end_date)
yield json.dumps({
"start_date": start_date,
"end_date": end_date
}).encode('utf8')
def landing_page_content(environ, start_response):
status = "200 OK"
headers = [("Content-type", "application/json; charset=UTF-8"),
("Access-Control-Allow-Origin", "*")]
start_response(status, headers)
config = WebConfig(
os.path.abspath(os.path.dirname(__file__)).replace("scripts", ""))
request = WSGIHandler(environ, config)
if request.is_range == "true":
if isinstance(request.query, bytes):
request_range = request.query.decode("utf8")
request_range = request.query.lower().split("-")
if len(request_range) == 1:
request_range.append(request_range[0])
results = group_by_range(request_range, request, config)
else:
results = group_by_metadata(request, config)
yield results.encode("utf8")
def access_request(environ, start_response):
status = '200 OK'
headers = [('Content-type', 'application/json; charset=UTF-8'),
("Access-Control-Allow-Origin", "*")]
config = WebConfig(
os.path.abspath(os.path.dirname(__file__)).replace('scripts', ''))
db = DB(config.db_path + '/data/')
request = WSGIHandler(environ, config)
access, headers = login_access(environ, request, config, headers)
start_response(status, headers)
if access:
yield json.dumps({'access': True})
else:
incoming_address, domain_name = access_control.get_client_info(environ)
yield json.dumps({
'access': False,
"incoming_address": incoming_address,
"domain_name": domain_name
}).encode('utf8')
def resolve_cite_service(environ, start_response):
config = WebConfig(
os.path.abspath(os.path.dirname(__file__)).replace("scripts", ""))
db = DB(config.db_path + "/data/")
request = WSGIHandler(environ, config)
c = db.dbh.cursor()
q = request.q
best_url = config["db_url"]
if " - " in q:
milestone = q.split(" - ")[0]
else:
milestone = q
milestone_segments = []
last_segment = 0
milestone_prefixes = []
for separator in re.finditer(r" (?!\.)|\.(?! )", milestone):
milestone_prefixes += [milestone[:separator.start()]]
milestone_segments += [milestone[last_segment:separator.start()]]
last_segment = separator.end()
milestone_segments += [milestone[last_segment:]]
milestone_prefixes += [milestone]
print("SEGMENTS", repr(milestone_segments), file=sys.stderr)
print("PREFIXES", repr(milestone_prefixes), file=sys.stderr)
abbrev_match = None
for pos, v in enumerate(milestone_prefixes):
print("QUERYING for abbrev = ", v, file=sys.stderr)
abbrev_q = c.execute("SELECT * FROM toms WHERE abbrev = ?;",
(v, )).fetchone()
if abbrev_q:
abbrev_match = abbrev_q
print("ABBREV",
abbrev_match["abbrev"],
abbrev_match["philo_id"],
file=sys.stderr)
doc_obj = ObjectWrapper(abbrev_match["philo_id"].split(), db)
nav = nav_query(doc_obj, db)
best_match = None
for n in nav:
if n["head"] == request.q:
print("MATCH", n["philo_id"], n["n"], n["head"], file=sys.stderr)
best_match = n
break
if best_match:
type_offsets = {"doc": 1, "div1": 2, "div2": 3, "div3": 4, "para": 5}
t = best_match["philo_type"]
short_id = best_match["philo_id"].split()[:type_offsets[t]]
best_url = f.make_absolute_object_link(config, short_id)
print("BEST_URL", best_url, file=sys.stderr)
status = "302 Found"
redirect = config["db_url"]
headers = [("Location", best_url)]
start_response(status, headers)
return ""
def get_neighboring_words(environ, start_response):
status = '200 OK'
headers = [('Content-type', 'application/json; charset=UTF-8'),
("Access-Control-Allow-Origin", "*")]
start_response(status, headers)
config = WebConfig(
os.path.abspath(os.path.dirname(__file__)).replace('scripts', ''))
db = DB(config.db_path + '/data/')
request = WSGIHandler(environ, config)
try:
index = int(request.hits_done)
except:
index = 0
max_time = int(request.max_time)
kwic_words = []
start_time = timeit.default_timer()
hits = db.query(request["q"], request["method"], request["arg"],
**request.metadata)
cursor = db.dbh.cursor()
for hit in hits[index:]:
word_id = ' '.join([str(i) for i in hit.philo_id])
query = 'select rowid, philo_name, parent from words where philo_id="%s" limit 1' % word_id
cursor.execute(query)
results = cursor.fetchone()
highlighted_text = kwic_hit_object(hit, config, db)["highlighted_text"]
highlighted_text = highlighted_text.translate(remove_punctuation_map)
highlighted_text = highlighted_text.strip()
result_obj = {
"left": "",
"right": "",
"index": index,
"q": highlighted_text
}
left_rowid = results["rowid"] - 10
right_rowid = results["rowid"] + 10
cursor.execute(
'select philo_name, philo_id from words where rowid between ? and ?',
(left_rowid, results['rowid'] - 1))
result_obj["left"] = []
for i in cursor:
result_obj["left"].append(i['philo_name'])
result_obj["left"].reverse()
result_obj["left"] = ' '.join(result_obj["left"])
cursor.execute(
'select philo_name, philo_id from words where rowid between ? and ?',
(results['rowid'] + 1, right_rowid))
result_obj["right"] = []
for i in cursor:
result_obj["right"].append(i['philo_name'])
result_obj["right"] = ' '.join(result_obj["right"])
for metadata in config.kwic_metadata_sorting_fields:
result_obj[metadata] = hit[metadata].lower()
kwic_words.append(result_obj)
index += 1
elapsed = timeit.default_timer() - start_time
if elapsed > max_time: # avoid timeouts by splitting the query if more than 10 seconds has been spent in the loop
break
yield json.dumps({
"results": kwic_words,
"hits_done": index
}).encode('utf8')