/
searchEngine.py
505 lines (408 loc) · 16.3 KB
/
searchEngine.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
import sqlite3
import pickle
import os
from portStemmer import PorterStemmer
from makeBigDict import scanCleanDir
class Searcher:
def __init__(self):
self.stemmer = PorterStemmer()
try:
f = open(os.getcwd()+"/data/tokensDict.p", "r")
self.tokens = pickle.load(f)
except:
print "Pickle file not found"
print "Creating the Dirctionary"
self.tokens = scanCleanDir()
f = open(os.getcwd()+"/data/tokensDict.p", "w")
pickle.dump(self.tokens, f)
def dbQuery(self, query, args = ()):
conn = sqlite3.connect('/Users/kristofer/comp_490/2lab/data/cache.db')
db = conn.cursor()
#args should be a tuple of the arguments in the query
db.execute(query, args)
rows = db.fetchall()
conn.close()
return rows
def singleToken(self):
print
word = raw_input("Enter your one word query: ")
token = word.lower()
token = self.stemmer.stem(token, 0, len(token) - 1)
try:
wordDict = self.tokens[token]
except:
print word, "does not seem to exist in our files. Please try a different word"
print
return
occurenceTotal = 0
highestFreq = {'freq': 0, 'docs':[]}
i = 1
for doc in wordDict.keys():
freq = len(wordDict[doc])
occurenceTotal += freq
linksQuery = """
SELECT webPage.linkText, item.itemName FROM (
SElECT itemToWebPage.webPageId, itemToWebPage.itemId
FROM itemToWebPage
WHERE webPageId = ?) AS linkItem
JOIN item
ON item.itemId = linkItem.itemId
JOIN webPage
ON webPage.webPageId = linkItem.webPageId;
"""
linksRow = self.dbQuery(linksQuery, (doc,))
print
print i,"\t",linksRow[0][0]
print "\t item: ",linksRow[0][1]
print "\t occured ",freq,"times"
i += 1
if freq > highestFreq['freq']:
highestFreq['freq'] = freq
highestFreq['docs'] = [linksRow[0][0]]
elif freq == highestFreq['freq']:
highestFreq['docs'].append(doc)
print
print "Total occurence of", word, "is", occurenceTotal, "times"
print "Highest frequency: ", highestFreq['freq'], " times in: ",
for i in range(len(highestFreq['docs'])):
if i > 0:
print "and"
print highestFreq['docs'][i]
print
def orQuery(self):
print
word1 = raw_input("Enter the first word of your query: ")
word2 = raw_input("Enter the second word of your query: ")
token1 = word1.lower()
token1 = self.stemmer.stem(token1, 0, len(token1) - 1)
token2 = word2.lower()
token2 = self.stemmer.stem(token2, 0, len(token2) - 1)
try:
docs = self.tokens[token1].keys()
except:
print word1, "does not seem to exist in our files. Please try a different word"
print
return
try:
docs2 = self.tokens[token2].keys()
except:
print word2, "does not seem to exist in our files. Please try a different word"
print
return
#Perform a logical or on the elements of both lists.
#Storing them in keys
for doc in docs2:
if doc not in docs:
docs.append(doc)
occurenceTotal = 0
i = 1
highestFreq = {'freq': 0, 'docs':[]}
for doc in docs:
freq1 = 0
freq2 = 0
try:
freq1 = len(self.tokens[token1][doc])
except:
None
try:
freq2 = len(self.tokens[token2][doc])
except:
None
freq = freq1 + freq2
occurenceTotal += freq
linksQuery = """
SELECT webPage.linkText, item.itemName FROM (
SElECT itemToWebPage.webPageId, itemToWebPage.itemId
FROM itemToWebPage
WHERE webPageId = ?) AS linkItem
JOIN item
ON item.itemId = linkItem.itemId
JOIN webPage
ON webPage.webPageId = linkItem.webPageId;
"""
linksRow = self.dbQuery(linksQuery, (doc,))
print
print i,"\t",linksRow[0][0]
print "\t item: ",linksRow[0][1]
print "\t occured ",freq,"times"
i += 1
if freq > highestFreq['freq']:
highestFreq['freq'] = freq
highestFreq['docs'] = [linksRow[0][0]]
elif freq == highestFreq['freq']:
highestFreq['docs'].append(doc)
print
print "Total occurence of", word1, "or", word2, "is", occurenceTotal, "times"
print "Highest frequency: ", highestFreq['freq'], " times in: ",
for i in range(len(highestFreq['docs'])):
if i > 0:
print "and"
print highestFreq['docs'][i]
print
def andQuery(self):
print
word1 = raw_input("Enter the first word of your query: ")
word2 = raw_input("Enter the second word of your query: ")
token1 = word1.lower()
token1 = self.stemmer.stem(token1, 0, len(token1) - 1)
token2 = word2.lower()
token2 = self.stemmer.stem(token2, 0, len(token2) - 1)
#Get the keys from both lists
docs = []
try:
docs1 = self.tokens[token1].keys()
except:
print word1, "does not seem to exist in our files. Please try a different word"
print
return
try:
docs2 = self.tokens[token2].keys()
except:
print word2, "does not seem to exist in our files. Please try a different word"
print
return
#Perform a logical and on the elements of both lists.
#Storing them in keys
for doc in docs1:
if doc in docs2:
docs.append(doc)
occurenceTotal = 0
i = 1
highestFreq = {'freq': 0, 'docs':[]}
for doc in docs:
freq1 = 0
freq2 = 0
try:
freq1 = len(self.tokens[token1][doc])
except:
None
try:
freq2 = len(self.tokens[token2][doc])
except:
None
freq = freq1 + freq2
occurenceTotal += freq
linksQuery = """
SELECT webPage.linkText, item.itemName FROM (
SElECT itemToWebPage.webPageId, itemToWebPage.itemId
FROM itemToWebPage
WHERE webPageId = ?) AS linkItem
JOIN item
ON item.itemId = linkItem.itemId
JOIN webPage
ON webPage.webPageId = linkItem.webPageId;
"""
linksRow = self.dbQuery(linksQuery, (doc,))
print
print i,"\t",linksRow[0][0]
print "\t item: ",linksRow[0][1]
print "\t occured ",freq,"times"
i += 1
if freq > highestFreq['freq']:
highestFreq['freq'] = freq
highestFreq['docs'] = [linksRow[0][0]]
elif freq == highestFreq['freq']:
highestFreq['docs'].append(doc)
print
print "Total occurence of", word1, "and", word2, "is", occurenceTotal, "times"
print "Highest frequency: ", highestFreq['freq'], " times in: ",
for i in range(len(highestFreq['docs'])):
if i > 0:
print "and"
print highestFreq['docs'][i]
print
def phraseQuery(self):
print
phrase = raw_input("Enter a two word phrase: ")
while len(phrase.split(' ')) != 2:
phrase = raw_input("Make sure your phrase is two words (e.g. 'hello goodbye'): ")
words = phrase.split(' ')
word1 = words[0]
word2 = words[1]
token1 = word1.lower()
token1 = self.stemmer.stem(token1, 0, len(token1) - 1)
token2 = word2.lower()
token2 = self.stemmer.stem(token2, 0, len(token2) - 1)
#Get the keys from both lists
docs = []
try:
docs1 = self.tokens[token1].keys()
except:
print word1, "does not seem to exist in our files. Please try a different word"
print
return
try:
docs2 = self.tokens[token2].keys()
except:
print word2, "does not seem to exist in our files. Please try a different word"
print
return
#Perform a logical and on the elements of both lists.
#Storing them in keys
phraseDict = {}
#Check which documents have both words
for doc in docs1:
if doc in docs2:
doc1Pos = self.tokens[token1][doc]
doc2Pos = self.tokens[token2][doc]
#check which documents have the phrase in the correct order
freq = 0
for pos1 in doc1Pos:
for pos2 in doc2Pos:
if pos2 == pos1 + 1:
freq += 1
if freq > 0:
phraseDict[doc] = freq
occurenceTotal = 0
i = 1
highestFreq = {'freq': 0, 'docs':[]}
for doc in phraseDict.keys():
freq = phraseDict[doc]
occurenceTotal += freq
linksQuery = """
SELECT webPage.linkText, item.itemName FROM (
SElECT itemToWebPage.webPageId, itemToWebPage.itemId
FROM itemToWebPage
WHERE webPageId = ?) AS linkItem
JOIN item
ON item.itemId = linkItem.itemId
JOIN webPage
ON webPage.webPageId = linkItem.webPageId;
"""
linksRow = self.dbQuery(linksQuery, (doc,))
print
print i,"\t",linksRow[0][0]
print "\t item: ",linksRow[0][1]
print "\t occured ",freq,"times"
i += 1
if freq > highestFreq['freq']:
highestFreq['freq'] = freq
highestFreq['docs'] = [linksRow[0][0]]
elif freq == highestFreq['freq']:
highestFreq['docs'].append(doc)
print
print "Total occurence of",phrase, "is", occurenceTotal, "times"
print "Highest frequency: ", highestFreq['freq'], " times in: ",
for i in range(len(highestFreq['docs'])):
if i > 0:
print "and"
print highestFreq['docs'][i]
print
def nearQuery(self):
print
word1 = raw_input("Enter the first word: ")
word2 = raw_input("Enter the second word: ")
distance = input ("Enter the number of positions away you want to look: ")
token1 = word1.lower()
token1 = self.stemmer.stem(token1, 0, len(token1) - 1)
token2 = word2.lower()
token2 = self.stemmer.stem(token2, 0, len(token2) - 1)
#Get the keys from both lists
docs = []
try:
docs1 = self.tokens[token1].keys()
except:
print word1, "does not seem to exist in our files. Please try a different word"
print
return
try:
docs2 = self.tokens[token2].keys()
except:
print word2, "does not seem to exist in our files. Please try a different word"
print
return
#Perform a logical and on the elements of both lists.
#Storing them in keys
phraseDict = {}
#Check which documents have both words
for doc in docs1:
if doc in docs2:
doc1Pos = self.tokens[token1][doc]
doc2Pos = self.tokens[token2][doc]
#check which documents have the words within the allotted distance of each other
freq = 0
for pos1 in doc1Pos:
for pos2 in doc2Pos:
if (pos2 - pos1 >= 0 - distance) and (pos2 - pos1 <= distance):
freq += 1
if freq > 0:
phraseDict[doc] = freq
occurenceTotal = 0
i = 1
highestFreq = {'freq': 0, 'docs':[]}
for doc in phraseDict.keys():
freq = phraseDict[doc]
occurenceTotal += freq
linksQuery = """
SELECT webPage.linkText, item.itemName FROM (
SElECT itemToWebPage.webPageId, itemToWebPage.itemId
FROM itemToWebPage
WHERE webPageId = ?) AS linkItem
JOIN item
ON item.itemId = linkItem.itemId
JOIN webPage
ON webPage.webPageId = linkItem.webPageId;
"""
linksRow = self.dbQuery(linksQuery, (doc,))
print
print i,"\t",linksRow[0][0]
print "\t item: ",linksRow[0][1]
print "\t occured ",freq,"times"
i += 1
if freq > highestFreq['freq']:
highestFreq['freq'] = freq
highestFreq['docs'] = [linksRow[0][0]]
elif freq == highestFreq['freq']:
highestFreq['docs'].append(doc)
print
print "Total occurence of",word1, "within ", distance, "positions of", word2, "was",occurenceTotal, "times"
print "Highest frequency: ", highestFreq['freq'], " times in: ",
for i in range(len(highestFreq['docs'])):
if i > 0:
print "and"
print highestFreq['docs'][i]
print
def searchMenu(self):
print
print "-----------------------------------------------------------"
print "\t Welcome to Stensland-ipedia!"
print "\tWhere you can search to your hearts content!"
print "-----------------------------------------------------------"
print
menu = True
while menu:
print "Choose the number corresponding to the query you would like to perform"
print "---------------------------------------------------------------------"
print "1.\tSingle token query."
print "2.\tAND query."
print "3.\tOR query."
print "4.\t2-Token query."
print "5.\tNear query."
print "6.\tQuit"
choice = raw_input("Enter your choice: ")
if choice == '1':
self.singleToken()
elif choice == '2':
self.andQuery()
elif choice == '3':
self.orQuery()
elif choice == '4':
self.phraseQuery()
elif choice == '5':
self.nearQuery()
elif choice == '6':
menu = False
print "\n"
else:
print "That is not a thing I understand."
print
print
print "Thank you for being my friend!"
print
def main():
#os.chdir('/Users/kristofer/comp_490/2lab')
print "Preparing the search engine..."
stenslandipedia = Searcher()
stenslandipedia.searchMenu()
if __name__ == "__main__":
main()