def load_paper_json():
global_config = load_gloabl_config()
filename = "paper-excel.json"
filename = os.path.join(global_config["home"],"output", filename)
with open(filename, 'r') as f:
content = f.read()
list_paper_excel = lib_data.text2json(content)
print len(list_paper_excel)
map_paper_excel = {}
map_paper_excel_no = {}
for paper in list_paper_excel:
map_paper_excel[str(paper["paper_id"])] = paper
map_paper_excel_no[str(paper["paper_no"])] = paper
map_name_session = {}
filename = "paper-industry.json"
filename = os.path.join(global_config["home"],"output", filename)
with open(filename, 'r') as f:
content = f.read()
list_paper_industry = lib_data.text2json(content)
set_session_name = set()
for paper in list_paper_industry:
paper_id = str(paper["paper_id"])
map_paper_excel[paper_id] = paper
session_name = paper["session_name"]
set_session_name.add(session_name)
default_session_id = 100 + len(set_session_name)
default_entry = {
"session_time": paper["session_time"],
"session_name": session_name,
"session_id" : default_session_id,
"session_index" : default_session_id,
}
entry = map_name_session.get(session_name, default_entry)
map_name_session[session_name]=entry
paper_list = entry.get("paper_list",[])
lib_data.list_append_unique(paper_list, paper_id)
entry["paper_list"] =paper_list
entry["paper_count"]= len(entry["paper_list"])
filename = "paper-pdf.json"
filename = os.path.join(global_config["home"],"output", filename)
with open(filename, 'r') as f:
content = f.read()
list_paper_pdf = lib_data.text2json(content)
print len(list_paper_pdf)
map_paper_pdf = {}
for paper in list_paper_pdf:
map_paper_pdf[str(paper["paper_id"])] = paper
filename = "session.csv"
filename = os.path.join(global_config["home"],"data", filename)
map_paper_session = {}
with open(filename,'r') as f:
csvreader = UnicodeReader(f)
headers = csvreader.next()
session_no = None
session_name = None
session_index = 1
for row in csvreader:
entry = dict(zip(headers, row))
if entry.get("Paper no."):
entry["session_no"] = session_no
entry["session_id"] = int(session_no.split(" ")[-1])
entry["session_name"] = session_name
entry["session_index"] = session_index
session_index+=1
map_paper_session[entry["Paper no."]]=entry
map_name_session[session_name]=entry
else:
session_no = entry["Session no"]
session_name = entry["Title"].strip()
session_index = 1
print len(map_paper_session)
filename = "event.csv"
filename = os.path.join(global_config["home"],"data", filename)
map_event_session = {}
with open(filename,'r') as f:
csvreader = UnicodeReader(f)
headers = csvreader.next()
for row in csvreader:
if row[0].startswith("#"):
continue
entry = dict(zip(headers, row))
print entry
event_start, event_end = entry["Time"].split("-")
event_day = entry["day"]
for k,v in entry.items():
if k in ["Time","day"]:
continue
if v:
event_id = (len(map_event_session)+1)
event = {
"day":event_day,
"start":event_start.strip(),
"end": event_end.strip(),
"name": v.strip(),
"location": k,
"id": event_id,
}
if "Session" in v or "Industry Track:" in v:
session_name = v.replace("Session:","")
session_name = session_name.replace("Industry Track:","")
session_name = re.sub("\([^\)]+\)","", session_name)
session_name = session_name.strip()
if session_name not in map_name_session:
print session_name
assert session_name in map_name_session
event["session_name"] = session_name
map_event_session[event_id] = event
print len(map_paper_session)
return map_paper_excel, map_paper_excel_no, map_paper_pdf, map_paper_session, map_name_session, map_event_session
def create_json():
map_paper_excel, map_paper_excel_no, map_paper_pdf, map_paper_session, map_name_session, map_event_session = load_paper_json()
ret = {}
#event_index
list_event = sorted(map_event_session.values(), key=lambda event: event["id"])
#print lib_data.json2text(list_session)
ret["events"]= list_event
map_session_event = {}
for event in map_event_session.values():
if "session_name" in event:
map_session_event[event["session_name"]] = event
#session_index
map_session = {}
for paper in sorted(map_paper_session.values(), key=lambda paper: paper["session_index"]):
session_id = paper["session_id"]
session_info = map_session.get(session_id, lib_data.json_update({},paper, ["session_no","session_name","session_id"]))
map_session[session_id] =session_info
paper_no = paper["Paper no."]
paper_id = map_paper_excel_no[paper_no]['paper_id']
paper_list = session_info.get("paper_list",[])
lib_data.list_append_unique(paper_list, paper_id)
session_info["paper_list"] =paper_list
session_info["paper_count"]= len(session_info["paper_list"])
list_session = map_session.values()
for session in map_name_session.values():
if "paper_list" in session:
list_session.append(session)
list_session = sorted(list_session, key=lambda paper: paper["session_id"])
#print lib_data.json2text(list_session)
ret["sessions"]= list_session
#Track_index
map_track = {}
TRACK_MAP=[
{"track_id":"In Use", "track_name":"In Use Track", "category": "Semantic Web In Use Track Paper"},
{"track_id":"RDBS", "track_name":"Replication, Benchmark, Data and Software Track","category": "Replication, Benchmark, Data and Software Track Paper"},
{"track_id":"Research", "track_name":"Research Track","category": "Research Track Paper"},
{"track_id":"DC", "track_name":"Doctoral Consortium", "category":"Doctoral Consortium Paper"},
{"track_id":"Industry", "track_name":"Industry Track","category": "Industry Track Paper"},
]
for paper in map_paper_excel.values():
category = paper["category"]
track = map_track.get(category, {"category": category})
map_track[category]=track
paper_id = paper['paper_id']
paper_list = track.get("paper_list",[])
lib_data.list_append_unique(paper_list, paper_id)
track["paper_list"] = sorted(paper_list)
print lib_data.json2text(map_track.keys())
for track in TRACK_MAP:
if track["category"] in map_track:
track["paper_list"]= map_track[track["category"]]["paper_list"]
track["paper_count"]= len(track["paper_list"])
ret["tracks"] = TRACK_MAP
#print lib_data.json2text(TRACK_MAP)
#map_paper_id2info
for paper_id, paper in map_paper_excel.items():
if paper_id.startswith("industry"):
continue
paper_pdf = map_paper_pdf.get(paper_id)
lib_data.json_update(paper, paper_pdf, ["keywords", "abstract","number_of_pages"])
if "pages" in paper:
end_page = int(paper["start_page"])+ paper_pdf["number_of_pages"] - 1
paper["pages"]= "{}-{}".format(paper["start_page"], end_page)
list_paper = sorted(map_paper_excel.values(), key=lambda paper: paper["paper_id"])
ret["papers"] = list_paper
list_talk = []
for session_info in ret["sessions"]:
session_name = session_info["session_name"]
start_diff = 0
for paper_id in session_info["paper_list"]:
paper_info = map_paper_excel[paper_id]
event = map_session_event[session_name]
if "Regular Talks" in session_name:
diff_len = 15
elif "Pechakucha" in session_name:
diff_len = 10
elif paper_info["paper_no"].endswith("*"):
diff_len= 10
else:
diff_len= 20
talk = {
"day": event["day"],
"start": time_add(event["start"], start_diff),
"end": time_add(event["start"], start_diff+diff_len),
"event": event["id"],
"paper": paper_id,
"paper_title": paper_info["title"],
"paper_author": paper_info["author"],
"id": paper_id,
}
print talk
list_talk.append(talk)
start_diff +=diff_len
ret["talks"] = list_talk
print lib_data.json2text(ret)
return ret
