-
Notifications
You must be signed in to change notification settings - Fork 0
/
functions.php
346 lines (283 loc) · 9.69 KB
/
functions.php
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
<?php
// This function parse the document using Regex and read all content from <Body> tag and return a string
function parseDocument($fileName)
{
global $reutersFolder;
if(file_exists($reutersFolder.$fileName))
{
$myfile = fopen($reutersFolder.$fileName, "r") or die("Unable to open file!");
$tempContent = fread($myfile,filesize($reutersFolder.$fileName));
fclose($myfile);
//regular expression to get document ID from NEWID tag
preg_match_all('/\<REUTERS[^>]*NEWID=\"([0-9]+)\"\>(.*?)<\/REUTERS>/is', $tempContent, $doc_ids);
unset($doc_ids[1]);
unset($doc_ids[2]);
$cn = count($doc_ids[0]);
for($i=0;$i<=$cn;$i++)
{
preg_match("/<body[^>]*>(.*?)<\/body>/is", $doc_ids[0][$i], $b);
if(empty($b))
{
unset($doc_ids[0][$i]);
}
}
$ncn = count($doc_ids[0]);
for($i=0;$i<=$cn;$i++)
{
preg_match('/\<REUTERS[^>]*NEWID=\"([0-9]+)\"\>/is', $doc_ids[0][$i], $n);
preg_match("/<body[^>]*>(.*?)<\/body>/is", $doc_ids[0][$i], $b);
$ft[1][] = $b[1];
$ft[2][] = $n[1];
}
return $ft;
}
else
return "File not found.";
}
// This function makes tokens using space and remove StopWords, apply lowercase, remove numeric keywords and remove stop words
function makeTokens($content,$doc_ids)
{
$arrayCount = count($content);
$resultArray = Array();
$main = Array();
$c =0;
for($i=0;$i<=$arrayCount;$i++)
{
$temp_did = $doc_ids[$i];
// applying Case Folding
$content[$i] = applyLowerCase($content[$i]);
// Separating words on basis of whitespace
$tokens = explode(" ",$content[$i]);
//removing whitespaces
$finalTokens = removeWhiteSpaces($tokens);
// removing unwanted characters
$finalTokens = stripPunctuations($finalTokens);
// removing strop words
$finalTokens = removeStopWords($finalTokens);
// removing Numerical tokens
$finalTokens = removeNumericTokens($finalTokens);
$cnt = count($finalTokens);
for($k=0;$k<=$cnt;$k++)
{
$terms[$finalTokens[$k]] = $temp_did;
}
foreach ($terms as $key=>$val)
{
if($key != NULL || $key != '')
{
if(array_key_exists($key, $main) == TRUE)
{
if(checkValuesExist($main[$key], $val) == FALSE)
$main[$key] = $main[$key].",".$val;
}
else
{
$main[$key] = $val;
}
}
}
}//END of arrayCount loop
// tokens array
$result['tokens'] = $main;
// total number of tokens generated in the document
$result['total_count'] = count($main);
return $result;
}
function removeDuplicateElements($content)
{
return array_unique($content);
}
// This function convert uppercase characters to lowercase
function applyLowerCase($content)
{
return strtolower($content);
}
// This function is removing whitespaces in terms
function removeWhiteSpaces($content)
{
return array_map('trim', $content);
}
function stripPunctuations($content)
{
$whatToStrip = array("?","!",",",";",'"','"...');
$tokensCount = count($content); // counting tokens
// Performing actions of each token
for($k=0;$k<=$tokensCount;$k++)
{
$content[$k] = str_replace($whatToStrip, "", $content[$k]);
}//END of tokenCount loop
return $content;
}
// This function check if the given word is stropword or not
function removeStopWords($tokens)
{
// 177 stop words
$stopWords = Array("will", "i", "a", "about", "above", "after", "again", "against", "all", "am", "an", "and", "any", "are", "aren't", "as", "at", "be", "because", "been", "before", "being", "below", "between", "both", "but", "by", "can't", "cannot", "could", "couldn't", "did", "didn't", "do", "does", "doesn't", "doing", "don't", "down", "during", "each", "few", "for", "from", "further", "had", "hadn't", "has", "hasn't", "have", "haven't", "having", "he", "he'd", "he'll", "he's", "her", "here", "here's", "hers", "herself", "him", "himself", "his", "how", "how's", "i", "i'd", "i'll", "i'm", "i've", "if", "in", "into", "is", "isn't", "it", "it's", "its", "itself", "let's", "me", "more", "most", "mustn't", "my", "myself", "no", "nor", "not", "of", "off", "on", "once", "only", "or", "other", "ought", "our", "ours", "ourselves", "out", "over", "own", "same", "shan't", "she", "she'd", "she'll", "she's", "should", "shouldn't", "so", "some", "such", "than", "that", "that's", "the", "their", "theirs", "them", "themselves", "then", "there", "there's", "these", "they", "they'd", "they'll", "they're", "they've", "this", "those", "through", "to", "too", "under", "until", "up", "very", "was", "wasn't", "we", "we'd", "we'll", "we're", "we've", "were", "weren't", "what", "what's", "when", "when's", "where", "where's", "which", "while", "who", "who's", "whom", "why", "why's", "with", "won't", "would", "wouldn't", "you", "you'd", "you'll", "you're", "you've", "your", "yours", "yourself", "yourselves", ' ');
$tokensCount = count($tokens); // counting tokens
// Performing actions of each token
for($k=0;$k<=$tokensCount;$k++)
{
$word = $tokens[$k];
if(in_array($word, $stopWords))
{
unset($tokens[$k]);
} // END if
}//END of tokenCount loop
$tokens = array_values($tokens);
return $tokens;
}
// This function remove numerical words from tokens
function removeNumericTokens($tokens)
{
$tokensCount = count($tokens); // counting tokens
// Performing actions of each token
for($k=0;$k<=$tokensCount;$k++)
{
$word = $tokens[$k];
if(is_numeric($word) || empty($word) || !ctype_alpha($word))
{
unset($tokens[$k]);
} // END if
}//END of tokenCount loop
$tokens = array_values($tokens);
return $tokens;
}
// This function save the data to a file. Used for saving postings list
function saveToFile($data,$fileName)
{
if(file_put_contents('blocks/'.$fileName.'.json', json_encode($data)))
return true;
else
return false;
}
// This function will merge all the blocks and create final index
function mergeBlocks()
{
$final_file = "final_index.json";
$a1 = file_get_contents("blocks/1.json");
$a2 = file_get_contents("blocks/2.json");
$a3 = file_get_contents("blocks/3.json");
$a4 = file_get_contents("blocks/4.json");
$a5 = file_get_contents("blocks/5.json");
$a6 = file_get_contents("blocks/6.json");
$a7 = file_get_contents("blocks/7.json");
$a8 = file_get_contents("blocks/8.json");
$a9 = file_get_contents("blocks/9.json");
$a10 = file_get_contents("blocks/10.json");
$a11 = file_get_contents("blocks/11.json");
$a12 = file_get_contents("blocks/12.json");
$a13 = file_get_contents("blocks/13.json");
$a14 = file_get_contents("blocks/14.json");
$a15 = file_get_contents("blocks/15.json");
$a16 = file_get_contents("blocks/16.json");
$a17 = file_get_contents("blocks/17.json");
$a18 = file_get_contents("blocks/18.json");
$a19 = file_get_contents("blocks/19.json");
$a20 = file_get_contents("blocks/20.json");
$a21 = file_get_contents("blocks/21.json");
$arr1 = json_decode($a1,true);
$arr2 = json_decode($a2,true);
$arr3 = json_decode($a3,true);
$arr4 = json_decode($a4,true);
$arr5 = json_decode($a5,true);
$arr6 = json_decode($a6,true);
$arr7 = json_decode($a7,true);
$arr8 = json_decode($a8,true);
$arr9 = json_decode($a9,true);
$arr10 = json_decode($a10,true);
$arr11 = json_decode($a11,true);
$arr12 = json_decode($a12,true);
$arr13 = json_decode($a13,true);
$arr14 = json_decode($a14,true);
$arr15 = json_decode($a15,true);
$arr16 = json_decode($a16,true);
$arr17 = json_decode($a17,true);
$arr18 = json_decode($a18,true);
$arr19 = json_decode($a19,true);
$arr20 = json_decode($a20,true);
$arr21 = json_decode($a21,true);
$final_index = array();
$final_index = mergingBlocks($final_index, $arr1['tokens']);
$final_index = mergingBlocks($final_index, $arr2['tokens']);
$final_index = mergingBlocks($final_index, $arr3['tokens']);
$final_index = mergingBlocks($final_index, $arr4['tokens']);
$final_index = mergingBlocks($final_index, $arr5['tokens']);
$final_index = mergingBlocks($final_index, $arr6['tokens']);
$final_index = mergingBlocks($final_index, $arr7['tokens']);
$final_index = mergingBlocks($final_index, $arr8['tokens']);
$final_index = mergingBlocks($final_index, $arr9['tokens']);
$final_index = mergingBlocks($final_index, $arr10['tokens']);
$final_index = mergingBlocks($final_index, $arr11['tokens']);
$final_index = mergingBlocks($final_index, $arr12['tokens']);
$final_index = mergingBlocks($final_index, $arr13['tokens']);
$final_index = mergingBlocks($final_index, $arr14['tokens']);
$final_index = mergingBlocks($final_index, $arr15['tokens']);
$final_index = mergingBlocks($final_index, $arr16['tokens']);
$final_index = mergingBlocks($final_index, $arr17['tokens']);
$final_index = mergingBlocks($final_index, $arr18['tokens']);
$final_index = mergingBlocks($final_index, $arr19['tokens']);
$final_index = mergingBlocks($final_index, $arr20['tokens']);
$final_index = mergingBlocks($final_index, $arr21['tokens']);
ksort($final_index);
if(file_put_contents($final_file, json_encode($final_index)))
return true;
else
return false;
}
function mergingBlocks($main,$temp)
{
if(empty($main))
{
$main = array_merge($main,$temp);
}
else
{
foreach ($temp as $key=>$val)
{
if(array_key_exists($key, $main) == TRUE)
{
if(checkValuesExist($main[$key], $val) == FALSE)
{
$main[$key] = $main[$key].",".$val;
}
}
else
{
$main[$key] = $val;
}
}
}
return $main;
}
function checkValuesExist($main,$temp)
{
$ex = explode(",", $main);
if(!empty($ex))
{
foreach ($ex as $val)
{
if($val == $temp)
return true;
}
}
return false;
}
function makeQueryTokens($query)
{
$t = explode(" ", $query);
return $t;
}
function doSearch($word)
{
$final_index = file_get_contents("final_index.json");
$final_arr = json_decode($final_index,true);
if(array_key_exists($word, $final_arr))
{
return $final_arr[$word];
}
else
{
return false;
}
}
?>