/
searchEngine.py
622 lines (515 loc) · 22.2 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
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
"""
Author: Kristofer Stensland
Date Last Modified: October, 1 2012
Description: A search engine over a series of web-page meta-data that is stored
in a python dictionary. Searches are performed using different
methods of boolean retrieval queries: single token; two token;
AND; OR; and near.
"""
import sqlite3
import pickle
import os
# The stemmer will stem the queries.
from portStemmer import PorterStemmer
# Creates the dictionary if it is not found.
from makeBigDict import scanCleanDir
"""
Handles all search queries, makes database queries and runs the user interface
for all searches.
Properties: tokens - the dictionary of meta-data for all the tokens and documents.
Methods: dbQuery - Handles SQL queries to the sqlite database
singleToken - Single token search query
orQuery - Performs an OR search query containing two tokens
andQuery - Performs an AND search query containing two tokens
phraseQuery - Performs a regular query with a two-token phrase.
nearQuery - Performs a query using two tokens, based on how near
to each other they are in the document.
"""
class Searcher:
# Constructor. Opens the dictionary of token meta-data
def __init__(self):
self.stemmer = PorterStemmer()
"""
self.tokens is a dictionary containing all the meta-data for all of the tokens and documents.
It has the structure:
{(Token):
{(Document Number):
[(list of all the positions of the token in that document.)]
}
}
"""
try:
f = open(os.getcwd() + "/data/tokensDict.p", "r")
self.tokens = pickle.load(f)
except:
print "Pickle file not found"
print "Creating the dictionary of meta-data."
self.tokens = scanCleanDir()
f = open(os.getcwd() + "/data/tokensDict.p", "w")
pickle.dump(self.tokens, f)
# Connects to the sqlite database, performs a given search query and
# returns a list conaining each row of the resulting table.
def dbQuery(self, query, args = ()):
conn = sqlite3.connect(os.getcwd() + '/data/cache.db')
db = conn.cursor()
# args should be a tuple of the arguments in the query
db.execute(query, args)
# get all the rows of the results from the sql query.
rows = db.fetchall()
conn.close()
return rows
"""
Searches for a single token in all the databases and displays all the
resulting documents, how many times the token occured in each document,
and which document had the most instances of that token.
"""
def singleToken(self):
# Get the token from the user, format it correctly and stem it.
print
word = raw_input("Enter your one word query: ")
token = word.lower()
token = self.stemmer.stem(token, 0, len(token) - 1)
# If the token is not found in any of the documents, end the search.
try:
wordDict = self.tokens[token]
except:
print word, "does not seem to exist in our files. Please try a different word"
print
return
# The number of times the token occurs across all documents.
occurenceTotal = 0
# Contains the documents with the highest frequency of document occurences.
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;
"""
# Get the URL for each valid web-page document found.
linksRow = self.dbQuery(linksQuery, (doc,))
# Display the current document and it's frequency
print
print i,"\t",linksRow[0][0]
print "\t item: ",linksRow[0][1]
print "\t occured ",freq,"times"
i += 1
# Update the document[s] with the highest frequency
if freq > highestFreq['freq']:
highestFreq['freq'] = freq
highestFreq['docs'] = [linksRow[0][0]]
elif freq == highestFreq['freq']:
highestFreq['docs'].append(doc)
# Display the most relevant document[s]
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
"""
Takes two tokens, gets all the documents that either or both tokens
appear in and displays the results.
"""
def orQuery(self):
print
# Get the two tokens, format and stem them.
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
# Collect all documents where either or both tokens appear in.
# Store them in keys
for doc in docs2:
if doc not in docs:
docs.append(doc)
# Total number of times either token occurs accross all documents.
occurenceTotal = 0
i = 1
# Keep track of which documents have the highest token frequency
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
# Combine the frequency of each token for the current document.
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;
"""
# Get the URL for each valid web-page document found.
linksRow = self.dbQuery(linksQuery, (doc,))
# Display the current document and it's frequency
print
print i,"\t",linksRow[0][0]
print "\t item: ",linksRow[0][1]
print "\t occured ",freq,"times"
i += 1
# Update which document[s] have the highest frequency for both tokens
if freq > highestFreq['freq']:
highestFreq['freq'] = freq
highestFreq['docs'] = [linksRow[0][0]]
elif freq == highestFreq['freq']:
highestFreq['docs'].append(doc)
# Display which Document[s] have the highest frequency for both tokens
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
"""
Takes two tokens, gets all the documents that ONLY BOTH tokens
appear in and displays the results.
"""
def andQuery(self):
print
# Get each token, format and stem both of them.
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)
# Will contain all documents where both tokens appear in
docs = []
# If either of the tokens is not found in any document, stop the search
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
# Collect all documents where both tokens appear in.
# Store them in keys
for doc in docs1:
if doc in docs2:
docs.append(doc)
# Total number of times either token occurs accross all documents
# that contain both tokens.
occurenceTotal = 0
i = 1
# Keep track of which documents have the highest token frequency
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
# Combine the frequency of each token for the current document.
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;
"""
# Get the URL for each valid web-page document found.
linksRow = self.dbQuery(linksQuery, (doc,))
# Display the current document and it's frequency
print
print i,"\t",linksRow[0][0]
print "\t item: ",linksRow[0][1]
print "\t occured ",freq,"times"
i += 1
# Update which document[s] have the highest frequency for both tokens
if freq > highestFreq['freq']:
highestFreq['freq'] = freq
highestFreq['docs'] = [linksRow[0][0]]
elif freq == highestFreq['freq']:
highestFreq['docs'].append(doc)
#Display which Document[s] have the highest frequency for both tokens
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
"""
Takes a two token phrase and finds all the documents where that phrase occurs
exactly as it is in the query (token1 followed by token2).
Works exactly like the andQuery, except that it checks to make sure the
position of token2 occurs immediately after token1.
"""
def phraseQuery(self):
print
# Get the two-word phrase and get each token from it.
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'): ")
# Format and stem each token.
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)
# Will contain all documents where both tokens appear in
docs = []
# If either of the tokens is not found in any document, stop the search
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
# Collect all documents where both tokens appear.
# Store 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
# Keep track of only the docuements where the phrase occurs.
if freq > 0:
phraseDict[doc] = freq
#Total number of times the phrase occurs
occurenceTotal = 0
i = 1
# Keep track of the documents with the highest frequency
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;
"""
# Get the URL for each valid web-page document found.
linksRow = self.dbQuery(linksQuery, (doc,))
# Display the current document and it's frequency
print
print i,"\t",linksRow[0][0]
print "\t item: ",linksRow[0][1]
print "\t occured ",freq,"times"
i += 1
# Update which document[s] have the highest frequency for both tokens
if freq > highestFreq['freq']:
highestFreq['freq'] = freq
highestFreq['docs'] = [linksRow[0][0]]
elif freq == highestFreq['freq']:
highestFreq['docs'].append(doc)
# Displat the document[s] with the highest frequency for the two-token phrase.
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
"""
Performs a query using two tokens and an integer. The integer represents
a distance between two words.
Collects all the documents where both tokens occur within the given
distance from each other and displays the results. For example in the
document, "and i think to myself what a wonderful world" The two tokens "think"
and "myself" occur within a distance of two words from each other.
"""
def nearQuery(self):
print
# Get both tokens and the distance
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: ")
# Format and stem each token
token1 = word1.lower()
token1 = self.stemmer.stem(token1, 0, len(token1) - 1)
token2 = word2.lower()
token2 = self.stemmer.stem(token2, 0, len(token2) - 1)
# Will contain all documents where both tokens appear in, within the given
# distance of each other.
docs = []
# If either token does not appear in any document, stop the search.
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
# Collect all documents where both tokens appear.
# Store 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
#Total number of times the two tokens occur within each other across all docs
occurenceTotal = 0
i = 1
# Keep track of the documents with the highest frequency
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;
"""
# Get the URL for each valid web-page document found.
linksRow = self.dbQuery(linksQuery, (doc,))
# Display the current document and it's frequency
print
print i,"\t",linksRow[0][0]
print "\t item: ",linksRow[0][1]
print "\t occured ",freq,"times"
i += 1
# Update the document with the highest frequency.
if freq > highestFreq['freq']:
highestFreq['freq'] = freq
highestFreq['docs'] = [linksRow[0][0]]
elif freq == highestFreq['freq']:
highestFreq['docs'].append(doc)
# Display the document with the highest frequency.
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():
print "Preparing the search engine..."
stenslandipedia = Searcher()
stenslandipedia.searchMenu()
if __name__ == "__main__":
main()