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
|
<?php
/**
* indexing.lib.php
*
* Author: Steve Bourgeois <owl@bozzit.com>
* Project Founder: Chris Vincent <cvincent@project802.net>
*
* Copyright (c) 1999-2006 The Owl Project Team
* Licensed under the GNU GPL. For full terms see the file COPYING.
*
* $Id: indexing.lib.php,v 1.2 2006/03/20 20:15:54 b0zz Exp $
*/
function DoesFileIDContainKeyword($fileid, $keyword)
{
global $default;
$sql = new Owl_DB;
$sql->query("SELECT * from $default->owl_wordidx where word='$keyword'");
$sql->query("SELECT * from $default->owl_wordidx where word like '%$keyword%'");
if ($sql->num_rows() > 0)
{
$glue = "";
while($sql->next_record())
{
$query .= $glue . " wordid = '" . $sql->f("wordid") . "'";
$glue = " OR ";
}
}
else
{
$query = "wordid = '-1'";
}
$sql->query("SELECT * from $default->owl_searchidx where ($query) and owlfileid = '$fileid'");
return $sql->num_rows();
}
function IndexATextFile($filename, $owlfileid)
{
global $default;
$fileidnum = $owlfileid;
$sql = new Owl_DB;
$sql->query("SELECT * from $default->owl_wordidx"); //Import all words and indexes
$nextwordindex = 0;
$wordindex = array();
while ($sql->next_record()) // this may get ugly, we could have 100K words and indexes, they gotta go into memory.
{
$wordindex[$sql->f("word")] = $sql->f("wordid");
if ($sql->f("wordid") > $nextwordindex)
{
$nextwordindex = $sql->f("wordid"); //get largest word index in table
}
}
$nextwordindex++;
// Note: again, here we've just read in the big wordidx, we should index as many
// files as possible while we have this index in memory, here we
// only index a single filename, but if someone wants to greatly improve performance,
// index an array of filenames here...
if (file_exists($filename))
{
$fp = fopen($filename, "rb");
while (!feof($fp))
{
$line = fgets($fp, 1024);
$line = strtolower($line);
// this line added to deal with WORD Tables
$line = str_replace("|", " ",$line);
// remove long _____________________________ lines
$line = preg_replace('*__*', '', $line);
//$wordtemp = preg_split("/\W/", $line); //split line into words a word is any # of A-Za-z's separated by somethign not a-zA-Z
$wordtemp = preg_split("/\s+/", $line); //split line into words a word is any # of A-Za-z's separated by somethign not a-zA-Z
if (!isset($wordtemp)) continue;
foreach($wordtemp as $wd)
{
$wd = stripslashes(ereg_replace("[$default->list_of_chars_to_remove_from_wordidx]","",str_replace("]", "", str_replace("[", "",$wd))));
if (strlen(trim($wd)) > 0 and strlen(trim($wd)) < 128)
{
$words[$wd]++; //keep a count of how often each word is seen
//print("WORDS: $words[$wd] ---- ");
if ($words[$wd] == 1) // if this is the first time we've seen this word in this document...
{
if ($wordindex[$wd]) // if this word was already in the wordidx table...
{
$sql->query("INSERT INTO $default->owl_searchidx VALUES('$wordindex[$wd]','$fileidnum')"); //add a searchidx table entry for this fileidnum (owlidnum)
}
else // if word not in word index, add to both wordidx and searchidx
{
if (!empty($default->words_to_exclude_from_wordidx))
{
array($WordList);
$WordList = $default->words_to_exclude_from_wordidx;
$checkword = str_replace("+", "\+", $wd);
$checkword = str_replace("'", "\'", $checkword);
$checkword = str_replace("{", "\{", $checkword);
$checkword = str_replace("}", "\}", $checkword);
if (!(preg_grep("/$checkword/", $WordList)))
{
$wordindex[$wd] = $nextwordindex; //first remember this word as being in the wordindex
$sql->query("INSERT into $default->owl_searchidx values('$wordindex[$wd]', '$fileidnum')"); //add pointer to owlidnum for this wordindexnum
$wd = ereg_replace("'", "\\'" , $wd);
$sql->query("SELECT wordid from $default->owl_wordidx where word = '$wd'");
$numrows = $sql->num_rows($sql);
if ( $numrows == 0 )
{
$sql->query("INSERT into $default->owl_wordidx values('$nextwordindex', '$wd')");
$nextwordindex++;
}
}
}
else
{
$wordindex[$wd] = $nextwordindex; //first remember this word as being in the wordindex
$sql->query("INSERT into $default->owl_searchidx values('$wordindex[$wd]', '$fileidnum')"); //add pointer to owlidnum for this wordindexnum
$wd = ereg_replace("'", "\\'" , $wd);
$sql->query("SELECT wordid from $default->owl_wordidx where word = '$wd'");
$numrows = $sql->num_rows($sql);
if ( $numrows == 0 )
{
$sql->query("INSERT into $default->owl_wordidx values('$nextwordindex', '$wd')");
$nextwordindex++;
}
}
}
} //if first instance of this word...
}
} //for each word
} //while!feof
}
else
{
if ($default->debug == true)
{
printError("DEBUG: $owl_lang->err_file_indexing");
}
}
}
function IndexABigString($bigstring, $owlfileid)
{
global $default;
$fileidnum = $owlfileid;
$sql = new Owl_DB;
$sql->query("SELECT * from $default->owl_wordidx"); //Import all words and indexes
$nextwordindex = 0;
$wordindex = array();
while ($sql->next_record()) // this may get ugly, we could have 100K words and indexes, they gotta go into memory.
{
$wordindex[$sql->f("word")] = $sql->f("wordid");
if ($sql->f("wordid") > $nextwordindex)
{
$nextwordindex = $sql->f("wordid"); //get largest word index in table
}
}
$nextwordindex++;
// Note: again, here we've just read in the big wordidx, we should index as many
// files as possible while we have this index in memory, here we
// only index a single filename, but if someone wants to greatly improve performance,
// index an array of filenames here...
$wordtemp = preg_split("/\s+/", strtolower($bigstring)); //split line into words a word is any # of A-Za-z's separated by somethign not a-zA-Z
if (!isset($wordtemp)) return;
foreach($wordtemp as $wd)
{
$wd = ereg_replace("[$default->list_of_chars_to_remove_from_wordidx]","",$wd);
if (strlen(trim($wd)) > 0 and strlen(trim($wd)) < 128)
{
$words[$wd]++; //keep a count of how often each word is seen
//print("WORDS: $words[$wd] ---- ");
if ($words[$wd] == 1) // if this is the first time we've seen this word in this document...
{
if ($wordindex[$wd]) // if this word was already in the wordidx table...
{
$sql->query("INSERT into $default->owl_searchidx values('$wordindex[$wd]','$fileidnum')"); //add a searchidx table entry for this fileidnum (owlidnum)
}
else // if word not in word index, add to both wordidx and searchidx
{
$wordindex[$wd] = $nextwordindex; //first remember this word as being in the wordindex
$sql->query("INSERT into $default->owl_searchidx values('$wordindex[$wd]', '$fileidnum')"); //add pointer to owlidnum for this wordindexnum
$wd = ereg_replace("'", "\\'" , $wd);
$sql->query("SELECT wordid from $default->owl_wordidx where word = '$wd'");
$numrows = $sql->num_rows($sql);
if ( $numrows == 0 )
{
$sql->query("INSERT into $default->owl_wordidx values('$nextwordindex', '$wd')");
$nextwordindex++;
}
}
} //if first instance of this word...
}
} //for each word
}
// When a file gets delete/removed, this should be called to update the indexing
// tables
function fDeleteFileIndexID($fidtoremove)
{
global $default;
$sql = new Owl_DB;
$sql->query("DELETE from $default->owl_searchidx where owlfileid = $fidtoremove");
// Note, I'm leaving the wordidx table alone, it can only grow so large as
// there are only so many words in the language, will make indexing future items a bit faster methinks
}
function fIndexAFile($new_name, $newpath, $id)
{
global $default, $sess, $index_file;
if ($index_file == "1")
{
// IF the file was inserted in the database now INDEX it for SEARCH.
$sSearchExtension = fFindFileExtension($new_name);
if ($sSearchExtension == 'pdf' || $sSearchExtension == 'c' || $sSearchExtension == 'html' || $sSearchExtension == 'htm' || $sSearchExtension == 'php' || $sSearchExtension == 'pl' || $sSearchExtension == 'txt' || $sSearchExtension == 'doc' || $sSearchExtension == 'xls' or $sSearchExtension == 'sxw' or $sSearchExtension == 'rtf' or $sSearchExtension == 'log')
{
if(file_exists($default->pdftotext_path) and $sSearchExtension == 'pdf')
{
$command = $default->pdftotext_path . ' "' . $newpath . '" "' . $default->owl_tmpdir . "/" . $new_name . '.text"';
$last_line = system($command, $retval);
if ($retval > 0)
{
if ($default->debug == true)
{
switch ($retval)
{
case "1":
$sPdfError = "Error opening a PDF file. (Not A PDF File?)";
break;
case "2":
$sPdfError = "Error opening an ouput file. ($default->owl_tmpdir Writeable by the webserver?)";
break;
}
printError('DEBUG: Indexing PDF File \'' . $newpath . '\' Failed:' , $sPdfError. "<br />COMMAND: $command");
}
}
IndexATextFile($default->owl_tmpdir . "/" . $new_name . '.text', $id);
unlink($default->owl_tmpdir . "/" . $new_name . '.text');
}
elseif (file_exists($default->wordtotext_path) and $sSearchExtension == 'doc')
{
//$command = "/bin/sh -c" . ' "' . $default->wordtotext_path . ' ' . $newpath . '"' . ' > "' . $default->owl_tmpdir . "/" . $new_name . '.text"';
$command = $default->wordtotext_path . ' "' . $newpath . '" > "' . $default->owl_tmpdir . "/" . $new_name . '.text"';
//print("C: $command");
//exit;
$last_line = system($command, $retval);
if ($retval > 0)
{
if ($default->debug == true)
{
$sPdfError = "Return: $retval $last_line";
printError('DEBUG: Indexing MS WORD File \'' . $newpath . '\' Failed:' , $sPdfError. "<br />COMMAND: $command");
}
}
IndexATextFile($default->owl_tmpdir . "/" . $new_name . '.text', $id);
unlink($default->owl_tmpdir . "/" . $new_name . '.text');
}
elseif (file_exists($default->rtftotext_path) and $sSearchExtension == 'rtf')
{
$command = "unrtf --text " . ' "' . $newpath . '" > "' . $default->owl_tmpdir . "/" . $new_name . '.text"';
$last_line = system($command, $retval);
if ($retval > 0)
{
if ($default->debug == true)
{
$sPdfError = "Return: $retval $last_line";
printError('DEBUG: Indexing RTFFile \'' . $newpath . '\' Failed:' , $sPdfError . "<br />COMMAND: $command");
}
}
IndexATextFile($default->owl_tmpdir . "/" . $new_name . '.text', $id);
unlink($default->owl_tmpdir . "/" . $new_name . '.text');
}
elseif($sSearchExtension == 'sxw')
{
$tmpDir = $default->owl_tmpdir . "/owltmp.$sess";
if (file_exists($tmpDir))
{
myDelete($tmpDir);
}
mkdir($tmpDir,$default->directory_mask);
$archive = new PclZip($newpath);
$aListOfFiles = $archive->listContent();
while ($aFileDetails = current($aListOfFiles)) {
if($aFileDetails["filename"] == "content.xml")
{
$iContentFileIndex = $aFileDetails["index"];
break;
}
next($aListOfFiles);
}
if ($archive->extractByIndex($iContentFileIndex, $tmpDir) == 0)
{
printError("DEBUG: " .$archive->errorInfo(true), "N: $newpath P: $tmpDir");
}
$text = file_get_contents("$tmpDir/content.xml");
$fp = fopen($tmpDir ."/content.xml.text", "w");
fwrite($fp, strip_tags($text));
fclose($fp);
IndexATextFile($tmpDir ."/content.xml.text", $id);
myDelete($tmpDir);
}
elseif($sSearchExtension == 'xls')
{
$xlwords = '';
require_once('scripts/Excel/reader.php');
$xl = new Spreadsheet_Excel_Reader();
$xl->read($newpath);
for ($k = count($xl->sheets)-1; $k>=0; $k--)
{
for ($i = 1; $i <= $xl->sheets[$k]['numRows']; $i++)
{
for ($j = 1; $j <= $xl->sheets[$k]['numCols']; $j++)
{
$xlwords .= $xl->sheets[$k]['cells'][$i][$j] . ' ';
}
}
}
$xlwords = preg_replace('# +#si',' ',$xlwords);
$xlwords = preg_replace('# $#si','',$xlwords);
IndexABigString($xlwords, $id);
}
else
{
if ($sSearchExtension == 'c' || $sSearchExtension == 'html' || $sSearchExtension == 'htm' || $sSearchExtension == 'php' || $sSearchExtension == 'pl' || $sSearchExtension == 'txt' or $sSearchExtension == 'log')
{
IndexATextFile($newpath, $id);
}
}
}
}
}
?>
|
