def updateProductLocal():
test_searcher = searcher(settings.FULLTEXT_DIR)
csvfile = csv.writer(open('product_hits.csv', 'wb') )
count = 0
with open('../../../data/products.csv', 'rU') as csvinputfile:
spamreader = csv.reader(csvinputfile)
for row in spamreader:
count = count + 1
print count
hits = getHits(test_searcher, row[0].strip())
if len(hits) > 1:
csvfile.writerow([row[0].strip(), "; ".join(hits), len(hits)])
'''cur1 = db.cursor()
def test6():
b = chessboard()
b.loads(
'1:CJ 2:DJ 1:dk 1:DL 1:EH 1:EI 2:EJ 2:EK 2:FH 2:FI 2:FJ 1:FK 2:FL 1:FM 2:GF 1:GG 2:GH 2:GI 2:GJ 1:GK 1:GL 2:GM 1:HE 2:HF 2:HG 2:HH 2:HI 1:HJ 2:HK 2:HL 1:IF 1:IG 1:IH 2:II 1:IJ 2:IL 2:JG 1:JH 1:JI 1:JJ 1:JK 2:JL 1:JM 1:KI 2:KJ 1:KL 1:LJ 2:MK'
)
#b.loads('1:HH,1:HI,1:HJ,1:HK')
s = searcher()
s.board = b.board()
t = time.time()
score, row, col = s.search(2, 3)
t = time.time() - t
b[row][col] = 2
print b
print score, t
print chr(ord('A') + row) + chr(ord('A') + col)
def main(): while( True ): # input print "Please input the Image:" curName = raw_input() if int(curName) > 1000 or int(curName) < 0: break # search imgs = sr.getImgs() imgNameArr,resDetial,checkRate = sr.searcher( "images/"+curName+".jpg", 'images/', curName, 1000, 100, imgs ) startGUI( imgNameArr ) print "===========================================" print "The check rate of image "+curName+".jpg is:" print checkRate print "===========================================" print "Exit"
def __init__(self):
self.SIZE = 13 # The number of locations/cross-points in row or column
self.TEXT = ' A B C D E F G H I J K L M'
self.b = chessboard(SIZE=self.SIZE, TEXT=self.TEXT)
self.s = searcher(self.SIZE)
self.s.board = self.b.board()
self.turn = 2
self.history = []
# self.undo = False
# 设置难度
self.DEPTH = 2
# speed up
self._psyco_speedup()
def test7():
b = chessboard()
s = searcher()
s.board = b.board()
b.loads('2:HH 1:JF')
turn = 2
while 1:
score, row, col = s.search(2, 2)
print 'robot move %s%s (%d)' % (chr(ord('A') + row),
chr(ord('A') + col), score)
b[row][col] = 2
if b.check() == 2:
print b
print b.dumps()
print 'you lose !!'
return 0
while 1:
print b
print 'your move (pos):',
text = raw_input().strip('\r\n\t ')
if len(text) == 2:
tr = ord(text[0].upper()) - ord('A')
tc = ord(text[1].upper()) - ord('A')
if tr >= 0 and tc >= 0 and tr < 15 and tc < 15:
if b[tr][tc] == 0:
row, col = tr, tc
break
else:
print 'can not move there'
else:
print 'bad position'
elif text.upper() == 'Q':
print b.dumps()
return 0
b[row][col] = 1
if b.check() == 1:
print b
print b.dumps()
print 'you win !!'
return 0
return 0
def updateProduct():
test_searcher = searcher(settings.FULLTEXT_DIR)
csvfile = csv.writer(open('product_hits.csv', 'wb') )
db = dbconnector().getNewCon("product")
cur = db.cursor()
cur.execute("select product from products ")
count = 0
for (product, ) in cur :
count = count + 1
print count
hits = getHits(test_searcher, product)
csvfile.writerow([product, "; ".join(hits), len(hits)])
'''cur1 = db.cursor()
insert_query = ("update products set hits = %s , num_hits = %s where product = %s")
data_query = ("; ".join(hits), len(hits), product)
cur1.execute(insert_query, data_query)
cur1.close()
db.commit()'''
cur.close()
db.close()
def searcherLoad():
pm = persistenceManager()
tokenSet = set(pm.csv2map(term_count_csv_path, ['term', 'count']).keys())
ids = np.load(id_mat_path)
q = 'bitcoin cryptocurrency speculation bubble wallstreet bank dollar'
idfMat = np.load(idf_vec_mat_path)
sr = searcher(tokenSet, idfMat, ids)
r = sr.query(q, 1)
print(r)
gc.collect()
lrma50 = np.load('d:/db/persistence5k/lrma50.npy')
sr = searcher(tokenSet, lrma50, ids)
r = sr.query(q, 1)
print(r)
gc.collect()
lrma100 = np.load('d:/db/persistence5k/lrma100.npy')
sr = searcher(tokenSet, lrma100, ids)
r = sr.query(q, 1)
print(r)
gc.collect()
lrma200 = np.load('d:/db/persistence5k/lrma200.npy')
sr = searcher(tokenSet, lrma200, ids)
r = sr.query(q, 1)
print(r)
gc.collect()
lrma500 = np.load('d:/db/lrma500.npy')
sr = searcher(tokenSet, lrma500, ids)
r = sr.query(q, 1)
print(r)
gc.collect()
lrma750 = np.load('d:/db/persistence5k/lrma750.npy')
sr = searcher(tokenSet, lrma750, ids)
r = sr.query(q, 1)
print(r)
gc.collect()
def gamemain():
b = chessboard()
s = searcher()
s.board = b.board()
opening = [
'1:HH 2:II',
#'2:IG 2:GI 1:HH',
'1:IH 2:GI',
'1:HG 2:HI',
#'2:HG 2:HI 1:HH',
#'1:HH 2:IH 2:GI',
#'1:HH 2:IH 2:HI',
#'1:HH 2:IH 2:HJ',
#'1:HG 2:HH 2:HI',
#'1:GH 2:HH 2:HI',
]
import random
openid = random.randint(0, len(opening) - 1)
b.loads(opening[openid])
turn = 2
history = []
undo = False
# 设置难度
DEPTH = 1
if len(sys.argv) > 1:
if sys.argv[1].lower() == 'hard':
DEPTH = 2
while 1:
print ''
while 1:
print '<ROUND %d>'%(len(history) + 1)
b.show()
print 'Your move (u:undo, q:quit):',
text = raw_input().strip('\r\n\t ')
if len(text) == 2:
tr = ord(text[0].upper()) - ord('A')
tc = ord(text[1].upper()) - ord('A')
if tr >= 0 and tc >= 0 and tr < 15 and tc < 15:
if b[tr][tc] == 0:
row, col = tr, tc
break
else:
print 'can not move there'
else:
print 'bad position'
elif text.upper() == 'U':
undo = True
break
elif text.upper() == 'Q':
print b.dumps()
return 0
if undo == True:
undo = False
if len(history) == 0:
print 'no history to undo'
else:
print 'rollback from history ...'
move = history.pop()
b.loads(move)
else:
history.append(b.dumps())
b[row][col] = 1
if b.check() == 1:
b.show()
print b.dumps()
print ''
print 'YOU WIN !!'
return 0
print 'robot is thinking now ...'
score, row, col = s.search(2, DEPTH)
cord = '%s%s'%(chr(ord('A') + row), chr(ord('A') + col))
print 'robot move to %s (%d)'%(cord, score)
b[row][col] = 2
if b.check() == 2:
b.show()
print b.dumps()
print ''
print 'YOU LOSE.'
return 0
return 0
#----------------------------------------------------------------------
# testing case
#----------------------------------------------------------------------
import crawler
import searcher
import sys
reload(searcher)
e = searcher.searcher('searchindex.db')
# e.getmatchrows('get set')
# e.query( 'get set')
# e.calculatepagerank()
cur = e.con.execute( 'select * from pagerank order by score desc' )
# for i in range( 10 ): print cur.next()
e.query( 'get set')
# e.geturlname( )
import searcher
import data_load
import indexer
import WEBcrawler
import weather
weather.weather()
visit_url.visit_url()
indexer.indexer()
searcher.searcher()
data_load.traverser()
d = indexer.indexer("raw_data.pickle","shelve")
searcher.search(d)
def edit(data):
content = ""
while content != "end":
content = input("id: ")
if content == "end":
continue
if content[:2] == "ls":
ls(content, data)
continue
if content == "search":
se = ""
while se != "end":
se = input("search: ")
if se == "end":
continue
if isint(se):
from mapper import reload
get(data, reload(data), id = int(se))
for n in searcher(se, data):
print(str(n.id) + ": " + n.title)
continue
try:
id = int(content)
except ValueError:
print("INVALID ID")
continue
cur_node = data[id]
cur = ""
while cur != "end":
cur = input(str(id) + ": ")
if cur == "end":
continue
if cur == "ls":
cur_node.printNode()
if cur == "description":
new_descr = input("\n" + str(id) + ".description: " + str(cur_node.description) + "\n")
if new_descr == "end":
continue
else:
if "+a" == cur[:-2]:
new_descr = cur_node.description + ". " + new_descr
cur_node.description = new_descr
print("\n" + str(id) + ".description: " + str(cur_node.description) + "\n")
if cur == "past":
p = ""
print("\npast: " + str(cur_node.past) + "\n")
while p != "end":
p = input()
if p == "end":
continue
if p[:2] == "ls":
print("\npast: " + str(cur_node.past) + "\n")
ls(p, data)
continue
if p == "search":
se = ""
while se != "end":
se = input("search: ")
if se == "end":
continue
if isint(se):
from mapper import reload
get(data, reload(data), id = int(se))
for n in searcher(se, data):
print(str(n.id) + ": " + n.title)
continue
try:
ind = p[0]
newID = int(p[1:])
except:
print("INVALID ID")
p = input("\npast: " + str(cur_node.past) + "\n")
continue
if ind == "-":
cur_node.past.remove(newID)
data[newID].future.remove(id)
print("past: " + str(cur_node.past) + "\n")
if ind == "+":
cur_node.past.append(newID)
data[newID].future.append(id)
print("past: " + str(cur_node.past) + "\n")
if cur == "future":
p = ""
print("\nfuture: " + str(cur_node.future) + "\n")
while p != "end":
p = input()
if p == "end":
continue
if p[:2] == "ls":
print("\nfuture: " + str(cur_node.future) + "\n")
ls(p, data)
continue
if p == "search":
se = ""
while se != "end":
se = input("search: ")
if se == "end":
continue
if isint(se):
from mapper import reload
get(data, reload(data), id = int(se))
for n in searcher(se, data):
print(str(n.id) + ": " + n.title)
continue
try:
ind = p[0]
newID = int(p[1:])
except:
print("INVALID ID")
print("\nfuture: " + str(cur_node.future) + "\n")
continue
if ind == "-":
cur_node.future.remove(newID)
data[newID].past.remove(id)
print("future: " + str(cur_node.future) + "\n")
if ind == "+":
cur_node.future.append(newID)
data[newID].past.append(id)
print("future: " + str(cur_node.future) + "\n")
if cur == "related":
pa = ""
while pa != "end":
pa = input("\nid: " + str(id) + "\n" + ", ".join(cur_node.related) + "\n\n: ")
if pa == "end":
continue
p = list(pa)
if p[0] == "-":
cur_node.related.remove(p[1])
data[int(p[1])].related.remove(p[1])
if p[0] == "+":
cur_node.related.append(p[1])
data[int(p[1])].related.append(p[1])
print("\nid: " + str(id) + "\n" + ", ".join(cur_node.related))
if cur == "keywords":
pa = ""
while pa != "end":
pa = input("\nid: " + str(id) + "\n" + ", ".join(cur_node.keywords) + "\n\n: ")
if pa == "end":
continue
p = list(pa)
if p[0] == "-":
cur_node.keywords.remove(p[1])
if p[0] == "+":
cur_node.keywords.append(p[1])
print("\nid: " + str(id) + "\n" + ", ".join(cur_node.keywords))
if "title" in cur:
titleNew = input("\n" + str(id) + ".title: " + cur_node.title + "\n")
if titleNew == "end":
continue
else:
if "+a" == cur[:-2]:
titleNew = cur_node.title + ". " + titleNew
cur_node.title = titleNew
print("\n" + str(id) + ".title: " + cur_node.title + "\n")
# if cur == "type":
#
# typeNew = input("\nid: " + str(id) + "\n" + cur_node.type + "\n\n: ")
# if descrNew == "end":
# continue
# else:
# cur_node.description = descrNew
# print "\nid: " + str(id) + "\n" + cur_node.type
return data
import crawler
import searcher
pages = ['https://www.codechef.com/']
C = crawler.crawler('codechef.db')
C.createindextables()
print "Crawling :: \n"
C.crawl(pages)
print "Ranking Pages :: \n"
C.calculatepagerank()
S = searcher.searcher('codechef.db')
searchQuery = 'Saturday'
S.query(searchQuery)
test_y[i][j] *= (1 + np.random.uniform(-1 * noise_level, noise_level, len(test_x)))
#Run the tests and characterize the results
fits = []
guesses = []
degrees = []
for i in range(0, len(test_functions)):
print(" ")
print("Test: " + str(i) + " | f(x) = " + test_names[i])
tStart = time.time()
fits.append([])
guesses.append([])
degrees.append([])
for j in range(0,n_tests_per_function):
fit, guess, degree = searcher(test_functions[i], test_x, test_y[i][j], p_min, p_max)
fits[i].append(fit)
guesses[i].append(guess)
degrees[i].append(degree)
print("DEBUG: time taken = " + str(time.time() - tStart) + " s")
for j in range(0, n_tests_per_function):
print("True parameters: " + str(test_parameters[i][j]))
print("Best fit parameters: " + str(fits[i][j][0]))
print("Guessed parameters: " + str(guesses[i][j]) + " | Degree: " + str(degrees[i][j]))
pl.plot(test_x,test_y[i][j],'bo',alpha=0.2,label="Original data ")
pl.plot(test_x,test_functions[i](test_x, *(fits[i][j][0])), 'g-', label="Best fit" )
pl.plot(test_x,test_functions[i](test_x, *(guesses[i][j])),'m-',
label="Best guess," + " degree = " + str(degrees[i][j]))
pl.legend(loc=2)
pl.suptitle("f(x) = " + str(test_names[i]))
pl.title("Goodness of guess = "
"""
URL redirection
"""
import BaseHTTPServer
from SocketServer import ThreadingMixIn
import time
# import threading
from searcher import searcher
search = searcher(50)
class searchHandler(BaseHTTPServer.BaseHTTPRequestHandler, searcher):
def do_HEAD(self):
searchQuery = self.path
print searchQuery
try:
a, b = search.search(searchQuery, 20, 10)
except:
a, b = [], []
print a, b
# clusters = open('/opt/bitnami/apache2/cgi-bin/clusters.csv','w')
clusters = open("../../data/clusters.csv", "w")
for t in a:
try:
clusters.write(t + "\n")
except:
pass
DG = reload(data)
#WRITING CONTENT
if start == "write":
writer(topic)
data = reader(topic)
DG = init(data)
DG = cleanPred(data, DG)
if start == "search":
se = ""
while se != "end":
if se == "end":
continue
se = input("search: ")
for n in searcher(se, data):
print(str(n.id) + ": " + n.title)
if start == "ls":
for n in data:
if isinstance(n, int):
continue
print(str(n.id) + ": " + str(n.title))
if start == "graph":
draw_all(data, DG)
#summarize data
#degree centrality, pred nodes, suc nodes (page rank)
if start == "summarize":
size = int(len(DG.nodes()) / 10)
def interface(init_topic=""):
from mapper import reload
topic = ""
while topic != "end":
#loading topic
if init_topic == "":
topic = input("topic: ")
if topic == "end":
continue
if topic == "ls":
for n in [
n.replace(".json", "") for n in os.listdir("../data/")
if ".json" in n
]:
print(n)
continue
if len(searcher(topic, list(os.listdir("../data/")))) > 0:
print()
for n in [
n.replace(".json", "")
for n in searcher(topic, list(os.listdir("../data/")))
if ".json" in n
]:
print(n)
else:
topic = init_topic
file = "../data/" + topic + ".json"
if topic + ".json" not in set(os.listdir("../data/")):
print("NEW")
conf = input("confirm: ")
#need a confirm option
if conf == "y" or conf == "yes":
with open(file, "w+") as cur_file:
cur_file.write(json.dumps([]))
else:
continue
start = ""
data = reader(topic)
DG = reload(data)
#for the purpose of recording changes to length of dataset
preLen = len(data)
path = ""
walker = 0
SET_OF_COMMANDS = ["end", "print", "edit", "write", "search"]
#actions
while start != "end":
start = input(topic + ": ")
if start == "end":
continue
#print the new data? useless method because it writes to file everytime
if start == "print":
for i in range(preLen + 1, len(data)):
print(str(data[i].id) + ": " + data[i].title)
print(data)
conf = input("confirm?: ")
if conf == "y" or conf == "yes":
writeToFile(file, data)
else:
continue
if start == "edit":
data = edit(data)
writeToFile(file, data)
DG = reload(data)
#WRITING CONTENT
if start == "write":
writer(topic)
data = reader(topic)
DG = reload(data)
if start == "search":
se = ""
while se != "end":
se = input("search: ")
if se == "end":
continue
if isint(se):
get(data, DG, id=int(se))
for n in searcher(se, data):
print(str(n.id) + ": " + n.title)
if isint(start):
get(data, DG, id=int(start))
if start[:2] == "ls":
ls(start, data)
continue
if start == "graph":
draw_all(data, DG)
#summarize data
#degree centrality, pred nodes, suc nodes (page rank)
if start == "summarize":
size = int(len(DG.nodes()) / 10)
print("Size = " + str(size))
centralnodes = [
n[0] for n in most_degree_centrality(DG, limit=size)
]
suc = mostPopularSuc(data, DG, limit=size)
pred = mostPopularPred(data, DG, limit=size)
totalNodes = []
totalNodes.extend(centralnodes)
totalNodes.extend(suc)
totalNodes.extend(pred)
print("Pred Nodes: ")
print()
for n in pred:
print(str(n.id) + ": " + str(n.title))
print()
print("Central Nodes: ")
print()
for n in centralnodes:
print(str(n.id) + ": " + str(n.title))
print()
print("Suc Nodes: ")
print()
for n in suc:
print(str(n.id) + ": " + str(n.title))
p = input("plot? ")
if p == "y" or p == "yes":
subDG = DG.subgraph(totalNodes)
labels = labeler(data)
pos = nx.spring_layout(subDG)
labelDict = {
n: lab
for n, lab in labels.items() if n in pos
}
nx.draw(subDG,
pos,
with_labels=True,
font_size=12,
labels=labelDict)
plt.draw()
plt.show()
if start == "get":
get(data, DG)
if start == "axioms":
leaves = [n for n, d in DG.out_degree() if d == 0]
print(len(leaves))
dprint(leaves)
if start == "cycle":
isCycle(DG)
if start == "project":
get_project(data, DG)
if start == "branch":
branch(data, DG)
if start == "pyvis":
from net_vis import net_vis
net_vis(data)
if start == "load":
from load import file_finder, term_text_editor, pdf_loader, txt_loader
if len(path) > 0:
s = input("LOADED PATH: " + path + "\n")
if s == "new":
path = file_finder()
if ".txt" in path:
t_data = txt_loader(path)
elif ".pdf" in path:
t_data = pdf_loader(path)
else:
print("NO VALID FILE")
term_text_editor(path, from_topic=topic)
data = reader(topic)
DG = reload(data)
else:
walker = term_text_editor(t_data,
init_index=walker,
from_topic=topic)
data = reader(topic)
DG = reload(data)
else:
path = file_finder()
if ".txt" in path:
t_data = txt_loader(path)
elif ".pdf" in path:
t_data = pdf_loader(path)
else:
print("NO VALID FILE")
walker = term_text_editor(t_data, from_topic=topic)
data = reader(topic)
DG = reload(data)
import crawler
import searcher
import sys
reload(searcher)
e = searcher.searcher('searchindex.db')
# e.getmatchrows('get set')
# e.query( 'get set')
# e.calculatepagerank()
cur = e.con.execute('select * from pagerank order by score desc')
# for i in range( 10 ): print cur.next()
e.query('get set')
# e.geturlname( )
def term_text_editor(data, init_index=0, from_topic=""):
from writer import writer
from searcher import searcher
i = ""
walker = init_index
return_string = ""
if walker == 0:
print("LOADING")
print("PRESS ENTER TO CONTINUE")
input()
while i != "end" or (walker > 0 and walker < len(data)):
cur_sentence = str(data[walker])
i = input(cur_sentence + '.' + '\n')
if i == "end":
continue
if "add" in i:
if i[:-1] == "-":
return_string = cur_sentence + return_string + ". "
else:
return_string += cur_sentence + ". "
print("ADDED")
print()
walker += 1
if i == "" or "+" in i:
try:
num = int(i.replace("+", ""))
except:
num = 1
walker += num
continue
if i == "-" or i == "back":
try:
num = int(i.replace("+", ""))
except:
num = 1
walker -= num
print()
continue
if i == "ls":
print(return_string)
print()
if i == "search":
search = input("search: ")
list_search = searcher(search, data, index=True)
if len(list_search) > 0:
print(str(len(list_search)) + " ITEMS FOUND")
for n in list_search:
s = input(data[n] + ": \n")
if s == "jump":
walker = n
break
if s == "end":
break
if i == "write":
if from_topic == "":
topic = input("topic: ")
writer(topic, init_description=return_string)
else:
writer(from_topic, init_description=return_string)
continue
if i == "interface" or i == "map":
break
return walker
def file_finder():
from searcher import searcher
import os
SUPPORTED_FILE_TYPES = ['.pdf', '.txt']
w = ""
path = os.getcwd()
def reload_dir(path):
with os.scandir(path) as dire:
cur_directory = [n for n in dire]
return cur_directory
cur_directory = reload_dir(path)
def aprint(array, tab='\t'):
for n in array:
if isinstance(n, os.DirEntry):
print(tab + n.name)
else:
print(tab + n)
while w != "end":
w = input("load: ")
if w == "end":
continue
if w == "ls":
aprint(cur_directory)
continue
if w == "":
cur_directory = reload_dir(path)
aprint(cur_directory)
continue
if w in SUPPORTED_FILE_TYPES:
file_type = w
cur_directory = [n for n in cur_directory if file_type in n.name]
aprint(cur_directory)
continue
if "cd .." == w or ".." == w:
arr = path.split('/')
if len(arr) > 1:
path = "/".join(arr[:-1])
print(path)
cur_directory = reload_dir(path)
aprint(cur_directory)
else:
aprint(cur_directory)
continue
if "cd" in w:
if w[3:] in [n.name for n in cur_directory]:
path += "/" + w[3:]
cur_directory = reload_dir(path)
aprint(cur_directory)
else:
print("/" + w[3:] + " NOT IN DIRECTORY")
continue
if w == "path":
print(path)
continue
else:
s = searcher(w, [n.name for n in cur_directory])
if len(s) == 0:
print("NO SIMILAR FILES")
aprint(cur_directory)
continue
cur_directory = [n for n in cur_directory if n.name in s]
if len(s) > 1:
cur_directory = [n for n in cur_directory if n.name in s]
aprint(cur_directory)
elif cur_directory[0].is_file():
aprint(cur_directory)
i = input("load? ")
if i == "y" or i == "yes":
path = cur_directory[0].path
break
#term_text_editor(path, from_topic = "")
else:
path = cur_directory[0].path
cur_directory = reload_dir(path)
aprint(cur_directory)
return path
def writer(topic, data=0, init_description=""):
from writer import writeToFile, isint
#cleaning function making sure each node is properly linked
def clean(data, curNode):
for n in curNode.future:
if n >= len(data):
continue
pastArray = data[n].past
if n not in pastArray:
data[n].flashback(curNode.id)
for n in curNode.past:
if n >= len(data):
continue
futureArray = data[n].future
if n not in futureArray:
data[n].flashforward(curNode.id)
for n in curNode.related:
if n >= len(data):
continue
relatedArray = data[n].related
if n not in relatedArray:
data[n].relate(curNode.id)
file = "../data/" + topic + ".json"
data = reader(topic)
DG = init(data)
DG = cleanPred(data, DG)
max = len(data)
content = ""
summary = init_description
print(topic + ".write: " + summary)
while content != "end":
content = input("")
if content == "end":
continue
#summary function
if content == "ls":
print(summary)
continue
#enter
if content == "\n":
summary += "\n"
continue
#premature break
if content == "break":
break
#writing the actual content
summary += content + " "
#premature break
if content == "break":
return ""
#connecting the content
#get title
print("Title: ")
title = input("")
if title == "up":
title = summary
print("Type: ")
type = []
t = ""
while t != "end":
t = input("")
if t == "end":
continue
type.append(t)
print("Past: ")
past_temp = ""
back = []
while past_temp != "end":
past_temp = input("")
if past_temp == "end":
continue
if past_temp[:2] == "ls":
ls(past_temp, data)
continue
if past_temp == "search":
se = ""
while se != "end":
se = input("search: ")
if se == "end":
continue
if isint(se):
get(data, DG, id=int(se))
for n in searcher(se, data):
print(str(n.id) + ": " + n.title)
continue
if past_temp == "suc":
for n in mostPopularSuc(data, DG, limit=10):
print(str(n.id) + ": " + n.title)
continue
if past_temp == "pre":
for n in mostPopularPred(data, DG, limit=10):
print(str(n.id) + ": " + n.title)
continue
if past_temp == "cen":
for n in most_degree_centrality(DG, limit=10):
print(str(n[0].id) + ": " + n[0].title)
continue
if past_temp == "project":
get_project(data, DG)
continue
if past_temp == "branch":
branch(data, DG)
continue
if past_temp == "get":
get(data, DG)
continue
if isint(past_temp):
result = int(past_temp)
back.append(result)
else:
print([
str(n.id) + ": " + str(n.title)
for n in searcher(past_temp, data)
])
print(back)
print("Future: ")
future_temp = ""
future = []
while future_temp != "end":
future_temp = input("")
if future_temp == "end":
continue
if future_temp[:2] == "ls":
if future_temp[:2] == "ls":
ls(future_temp, data)
continue
if future_temp == "search":
se = ""
while se != "end":
se = input("search: ")
if se == "end":
continue
if isint(se):
get(data, DG, id=int(se))
for n in searcher(se, data):
print(str(n.id) + ": " + n.title)
continue
if future_temp == "suc":
for n in mostPopularSuc(data, DG, limit=10):
print(str(n.id) + ": " + n.title)
if future_temp == "pre":
for n in mostPopularPred(data, DG, limit=10):
print(str(n.id) + ": " + n.title)
if future_temp == "cen":
for n in most_degree_centrality(DG, limit=10):
print(str(n[0].id) + ": " + n[0].title)
if future_temp == "get":
get(data, DG)
if isint(future_temp):
result = int(future_temp)
future.append(result)
else:
print([
str(n.id) + ": " + str(n.title)
for n in searcher(future_temp, data)
])
print(future)
#simplify things, break things up into if you want to add related
c = ""
related = []
keyword = []
while c != "end":
c = input("")
if c == "end":
continue
if c == "break":
break
#if you want to add related
if c == "related":
print("Related: ")
r_temp = ""
while r_temp != "end":
r_temp = input("")
if r_temp == "end":
continue
if isint(r_temp):
result = int(r_temp)
related.append(result)
else:
print([
str(n.id) + ": " + str(n.title)
for n in searcher(r_temp, data)
])
print(related)
#if you want to add keywords
if c == "keywords":
print("Keywords: ")
k_temp = ""
while k_temp != "end":
k_temp = input("")
if k_temp == "end":
continue
keyword.append(k_temp)
if c == "edit":
data = edit(data)
if c == "break":
return ""
print(title)
print(type)
print(summary)
#CLEANING
current_Node = Node(title, type, summary, keyword, back, future, related,
max)
clean(data, current_Node)
data.append(current_Node)
max += 1
#WRITING BACK TO TXT FILE
writeToFile(file, data)
#!/usr/bin/env python
import sys
from searcher import searcher
if __name__ == "__main__":
if len(sys.argv) > 1:
searchQuery = " ".join(sys.argv[1:])
else:
print "Please specify Search Query"
exit()
search = searcher(200, "/home/bitnami/8Q/")
print searchQuery
try:
a, b = search.search(searchQuery, 20, 10)
except:
a, b = [], []
print "Papers = %d, Clusters = %d" % (len(a), len(b))
clusters = open("/opt/bitnami/apache2/cgi-bin/clusters.csv", "w")
# clusters = open('../../data/clusters.csv','w')
for i, cluster in enumerate(b):
for s in cluster:
try:
clusters.write(s)
except:
pass
if i < len(b) - 1:
