out/js/search.js

/**
 search.js searchs an XML index to HTML files.

 A part of the jsfind project (http://projects.elucidsoft.net/jsfind)
 Copyright (C) 2003 Shawn Garbett

 This program is free software; you can redistribute it and/or
 modify it under the terms of the GNU General Public License
 as published by the Free Software Foundation; either version 2
 of the License, or (at your option) any later version.
 
 This program is distributed in the hope that it will be useful,
 but WITHOUT ANY WARRANTY; without even the implied warranty of
 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 GNU General Public License for more details.
 
 You should have received a copy of the GNU General Public License
 along with this program; if not, write to the Free Software
 Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
 
 Contact Info:
 Shawn Garbett <Shawn@eLucidSoft.net>
 http://www.elucidsoft.net
 4037 General Bate Drive
 Nashville, TN 37204
*/

// Constants
var conversion = new String
      ("0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXY");

// State variables
var query_left = "";
var search_err = "";
var results    = null;
var index_path = "";

var watchdog_id = 0;
var watchdog_callback = null;

// Object to hold search results
function Result(title, link, freq)
{
  this.title=title;
  this.link=link;
  this.frequency=Number(freq);
}

// Function to merge (intersect) two result sets
function intersect_results(data)
{
  // If there are no stored results, then these are the results
  if(!results)
  {
    results = data;
    return;
  }

  var output=new Array();

  // There are existing results, to do an intersect...
  for(var i=0; i<results.length; i++)
  {
    for(var j=0; j<data.length; j++)
    {
      if(data[j].title == results[i].title)
      {
        results[i].frequency += data[j].frequency;
        output.push(results[i]);  
        break;
      }
    }
  }

  results = output;
}

/*
 From David Flanagan's, _Javascript:_The Definitive_Guide_, pg. 294-5,
  published by O'Reilly, 4th edition, 2002
*/
function debug(msg)
{
//  return; // Disable debugging

  if(!debug.box)
  {
    debug.box = document.createElement("div");
    debug.box.setAttribute("style",
                           "background-color:white" + 
                           "font-family: monospace; " +
                           "border: solid black 3px; "+
                           "padding: 10px;");

    document.body.appendChild(debug.box);
    debug.box.innerHTML = "<h1 style='test-align:cent'>Debugging Output</h1>";
  }

  var p = document.createElement("p");
  p.appendChild(document.createTextNode(msg));
  debug.box.appendChild(p);
}

// 

// Convert a number into a base 62 alphanumeric number string
function convert(num)
{
  var base = conversion.length;
  var pow = 1;
  var pos = 0;
  var out = "";  

  if(num == 0)
  {
    return "0";
  }

  while (num > 0)
  {
    pos = num % base;
    out = conversion.charAt(pos) + out;
    num = Math.floor(num/base);
    pow *= base;
  }

  return out;
}

function watchdog()
{
  debug ("TIMEOUT!");
  watchdog_callback(new Array());
}

// This function loads the XML document from the specified URL, and when
// it is fully loaded, passes that document and the url to the specified
// handler function.  This function works with any XML document
function loadXML(url, handler, data, result_handler)
{
  debug("loadXML("+url+","+data+")");

  // Timeout operation in 10 seconds
  watchdog_callback = result_handler;
  watchdog_id=setTimeout("watchdog()", 20000);

  debug("setTimeout = "+watchdog_id);

  try 
  {
    var xmldoc;
    // Use the standard DOM Level 2 technique, if it is supported
    if (document.implementation && document.implementation.createDocument)
    {
     // Create a new Document object
      xmldoc = document.implementation.createDocument("", "", null);

      // Specify what should happen when it finishes loading
      xmldoc.onload = function() { handler(xmldoc, url, data, result_handler); }

      //xmldoc.onerror = docError;
      //xmldoc.addEventListener("load",docError,false);

      // And tell it what URL to load
      xmldoc.load(url);
    }
    // Otherwise use Microsoft's proprietary API for Internet Explorer
    // Something about not following standards once again
    else if (window.ActiveXObject)
    {  
      xmldoc = new ActiveXObject("Microsoft.XMLDOM");   // Create doc.
      if (! xmldoc) xmldoc = new ActiveXObject("MSXML2.DOMDocument");   // Create doc.
      // Specify onload
      xmldoc.onreadystatechange = function()
      {              
        if (xmldoc.readyState == 4) handler(xmldoc, url, data, result_handler);
      }
      xmldoc.load(url);                                     // Start loading!
    }
  }
  catch(ex)
  {
    clearTimeout(watchdog_id);
    debug("clearTimeout = "+watchdog_id);
    debug ("CAUGHT EXCEPTION!");
    result_handler(new Array());
    return false;
  }

  return true;
}

function loadData(xmldoc, url, pos, result_handler)
{
  clearTimeout(watchdog_id);
  debug("clearTimeout = "+watchdog_id);

  debug ("loadData("+url+","+pos+")");

  var data = new Array();

  // Get all entries
  var entries = xmldoc.getElementsByTagName("e");

  if(entries.length > pos)
  {
    // Get the links associated with this query
    var links = entries[pos].getElementsByTagName("l");

    // Dynamically append results to output
    for(var i=0; i<links.length; i++)
    {
      data.push(new Result(links[i].getAttribute("t"),
                           links[i].firstChild.data,
                           links[i].getAttribute("f")));
    }

    intersect_results(data); 

    if(query_left.length > 0)
    {
      doSearch(index_path, query_left, result_handler);  
    }
    else
    {
      results.sort(sortResults);
      result_handler(results);
    }
  }
  else
  {
    debug("INTERNAL ERROR, Inconsistent index");
    search_err="INTERNAL ERROR, Inconsistent index";
  }
}

function sortResults(a, b)
{
  return a.frequency - b.frequency;
}

function traverseTree(xmldoc, url, query, result_handler)
{
  clearTimeout(watchdog_id);
  debug("clearTimeout = "+watchdog_id);
 
  debug("traverseTree("+xmldoc+","+url+","+query+")");

  var keys = xmldoc.getElementsByTagName("k");
  var i;

  for(i = 0; i < keys.length; i++)
  {
    var key = keys[i].firstChild.data;
    debug("traverseTree: key="+key+" query="+query);
    if(key != '' && key != null)
    {
      // Case where current key is greater than query, descend
      if(key > query)
      {
        if(key != '' && key != null)
        {
          if(!loadXML(url.replace(".xml","/"+convert(i)+".xml"),
                      traverseTree,query,result_handler))
          {
            debug("Unable to locate key "+query);
            result_handler(new Array());
          }
          // make sure of garbage collection
          xmldoc=null;
          return;
        }
      }
      // Found it!
      else if(key==query)
      {
        if(!loadXML(url.replace(/(\w+\.xml)/, "_$1"),
                    loadData, i, result_handler))
        {
          debug("ERROR: Unable to locate data "+query);
          result_handler(new Array());
        }
        // make sure of garbage collection
        xmldoc=null;
        return;
      }
    }
  }
  // Look past the end...
  if(keys.length == 0 || !loadXML(url.replace(".xml","/"+convert(i)+".xml"),
              traverseTree,query,result_handler))
  {
    debug("Unable to locate key "+query);
    result_handler(new Array());
  }
  // make sure of garbage collection
  xmldoc=null;
  return;
}

function doSearch(index_name,query, result_func)
{
  //alert("doSearch("+index_name+","+query+")");
  var pos=query.search(/[\s\+]/);
  if (index_name) index_path = index_name+'/';

  if(pos < 0)
  {
    query_left = "";
  }
  else
  {
    query_left = query.slice(pos+1);
    query = query.slice(0,pos);
  } 

  if(!loadXML(index_path+"0.xml", traverseTree, query.toLowerCase(), result_func))
  {
    debug("ERROR: Couldn't find main index 0.xml");
    search_err = "INTERNAL ERROR: Unable to load main index 0.xml";
  }
}
1	/**
2	search.js searchs an XML index to HTML files.
3
4	A part of the jsfind project (http://projects.elucidsoft.net/jsfind)
5	Copyright (C) 2003 Shawn Garbett
6
7	This program is free software; you can redistribute it and/or
8	modify it under the terms of the GNU General Public License
9	as published by the Free Software Foundation; either version 2
10	of the License, or (at your option) any later version.
11
12	This program is distributed in the hope that it will be useful,
13	but WITHOUT ANY WARRANTY; without even the implied warranty of
14	MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15	GNU General Public License for more details.
16
17	You should have received a copy of the GNU General Public License
18	along with this program; if not, write to the Free Software
19	Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
20
21	Contact Info:
22	Shawn Garbett <Shawn@eLucidSoft.net>
23	http://www.elucidsoft.net
24	4037 General Bate Drive
25	Nashville, TN 37204
26	*/
27
28	// Constants
29	var conversion = new String
30	("0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXY");
31
32	// State variables
33	var query_left = "";
34	var search_err = "";
35	var results = null;
36	var index_path = "";
37
38	var watchdog_id = 0;
39	var watchdog_callback = null;
40
41	// Object to hold search results
42	function Result(title, link, freq)
43	{
44	this.title=title;
45	this.link=link;
46	this.frequency=Number(freq);
47	}
48
49	// Function to merge (intersect) two result sets
50	function intersect_results(data)
51	{
52	// If there are no stored results, then these are the results
53	if(!results)
54	{
55	results = data;
56	return;
57	}
58
59	var output=new Array();
60
61	// There are existing results, to do an intersect...
62	for(var i=0; i<results.length; i++)
63	{
64	for(var j=0; j<data.length; j++)
65	{
66	if(data[j].title == results[i].title)
67	{
68	results[i].frequency += data[j].frequency;
69	output.push(results[i]);
70	break;
71	}
72	}
73	}
74
75	results = output;
76	}
77
78	/*
79	From David Flanagan's, _Javascript:_The Definitive_Guide_, pg. 294-5,
80	published by O'Reilly, 4th edition, 2002
81	*/
82	function debug(msg)
83	{
84	// return; // Disable debugging
85
86	if(!debug.box)
87	{
88	debug.box = document.createElement("div");
89	debug.box.setAttribute("style",
90	"background-color:white" +
91	"font-family: monospace; " +
92	"border: solid black 3px; "+
93	"padding: 10px;");
94
95	document.body.appendChild(debug.box);
96	debug.box.innerHTML = "<h1 style='test-align:cent'>Debugging Output</h1>";
97	}
98
99	var p = document.createElement("p");
100	p.appendChild(document.createTextNode(msg));
101	debug.box.appendChild(p);
102	}
103
104	//
105
106	// Convert a number into a base 62 alphanumeric number string
107	function convert(num)
108	{
109	var base = conversion.length;
110	var pow = 1;
111	var pos = 0;
112	var out = "";
113
114	if(num == 0)
115	{
116	return "0";
117	}
118
119	while (num > 0)
120	{
121	pos = num % base;
122	out = conversion.charAt(pos) + out;
123	num = Math.floor(num/base);
124	pow *= base;
125	}
126
127	return out;
128	}
129
130	function watchdog()
131	{
132	debug ("TIMEOUT!");
133	watchdog_callback(new Array());
134	}
135
136	// This function loads the XML document from the specified URL, and when
137	// it is fully loaded, passes that document and the url to the specified
138	// handler function. This function works with any XML document
139	function loadXML(url, handler, data, result_handler)
140	{
141	debug("loadXML("+url+","+data+")");
142
143	// Timeout operation in 10 seconds
144	watchdog_callback = result_handler;
145	watchdog_id=setTimeout("watchdog()", 20000);
146
147	debug("setTimeout = "+watchdog_id);
148
149	try
150	{
151	var xmldoc;
152	// Use the standard DOM Level 2 technique, if it is supported
153	if (document.implementation && document.implementation.createDocument)
154	{
155	// Create a new Document object
156	xmldoc = document.implementation.createDocument("", "", null);
157
158	// Specify what should happen when it finishes loading
159	xmldoc.onload = function() { handler(xmldoc, url, data, result_handler); }
160
161	//xmldoc.onerror = docError;
162	//xmldoc.addEventListener("load",docError,false);
163
164	// And tell it what URL to load
165	xmldoc.load(url);
166	}
167	// Otherwise use Microsoft's proprietary API for Internet Explorer
168	// Something about not following standards once again
169	else if (window.ActiveXObject)
170	{
171	xmldoc = new ActiveXObject("Microsoft.XMLDOM"); // Create doc.
172	if (! xmldoc) xmldoc = new ActiveXObject("MSXML2.DOMDocument"); // Create doc.
173	// Specify onload
174	xmldoc.onreadystatechange = function()
175	{
176	if (xmldoc.readyState == 4) handler(xmldoc, url, data, result_handler);
177	}
178	xmldoc.load(url); // Start loading!
179	}
180	}
181	catch(ex)
182	{
183	clearTimeout(watchdog_id);
184	debug("clearTimeout = "+watchdog_id);
185	debug ("CAUGHT EXCEPTION!");
186	result_handler(new Array());
187	return false;
188	}
189
190	return true;
191	}
192
193	function loadData(xmldoc, url, pos, result_handler)
194	{
195	clearTimeout(watchdog_id);
196	debug("clearTimeout = "+watchdog_id);
197
198	debug ("loadData("+url+","+pos+")");
199
200	var data = new Array();
201
202	// Get all entries
203	var entries = xmldoc.getElementsByTagName("e");
204
205	if(entries.length > pos)
206	{
207	// Get the links associated with this query
208	var links = entries[pos].getElementsByTagName("l");
209
210	// Dynamically append results to output
211	for(var i=0; i<links.length; i++)
212	{
213	data.push(new Result(links[i].getAttribute("t"),
214	links[i].firstChild.data,
215	links[i].getAttribute("f")));
216	}
217
218	intersect_results(data);
219
220	if(query_left.length > 0)
221	{
222	doSearch(index_path, query_left, result_handler);
223	}
224	else
225	{
226	results.sort(sortResults);
227	result_handler(results);
228	}
229	}
230	else
231	{
232	debug("INTERNAL ERROR, Inconsistent index");
233	search_err="INTERNAL ERROR, Inconsistent index";
234	}
235	}
236
237	function sortResults(a, b)
238	{
239	return a.frequency - b.frequency;
240	}
241
242	function traverseTree(xmldoc, url, query, result_handler)
243	{
244	clearTimeout(watchdog_id);
245	debug("clearTimeout = "+watchdog_id);
246
247	debug("traverseTree("+xmldoc+","+url+","+query+")");
248
249	var keys = xmldoc.getElementsByTagName("k");
250	var i;
251
252	for(i = 0; i < keys.length; i++)
253	{
254	var key = keys[i].firstChild.data;
255	debug("traverseTree: key="+key+" query="+query);
256	if(key != '' && key != null)
257	{
258	// Case where current key is greater than query, descend
259	if(key > query)
260	{
261	if(key != '' && key != null)
262	{
263	if(!loadXML(url.replace(".xml","/"+convert(i)+".xml"),
264	traverseTree,query,result_handler))
265	{
266	debug("Unable to locate key "+query);
267	result_handler(new Array());
268	}
269	// make sure of garbage collection
270	xmldoc=null;
271	return;
272	}
273	}
274	// Found it!
275	else if(key==query)
276	{
277	if(!loadXML(url.replace(/(\w+\.xml)/, "_$1"),
278	loadData, i, result_handler))
279	{
280	debug("ERROR: Unable to locate data "+query);
281	result_handler(new Array());
282	}
283	// make sure of garbage collection
284	xmldoc=null;
285	return;
286	}
287	}
288	}
289	// Look past the end...
290	if(keys.length == 0 \|\| !loadXML(url.replace(".xml","/"+convert(i)+".xml"),
291	traverseTree,query,result_handler))
292	{
293	debug("Unable to locate key "+query);
294	result_handler(new Array());
295	}
296	// make sure of garbage collection
297	xmldoc=null;
298	return;
299	}
300
301	function doSearch(index_name,query, result_func)
302	{
303	//alert("doSearch("+index_name+","+query+")");
304	var pos=query.search(/[\s\+]/);
305	if (index_name) index_path = index_name+'/';
306
307	if(pos < 0)
308	{
309	query_left = "";
310	}
311	else
312	{
313	query_left = query.slice(pos+1);
314	query = query.slice(0,pos);
315	}
316
317	if(!loadXML(index_path+"0.xml", traverseTree, query.toLowerCase(), result_func))
318	{
319	debug("ERROR: Couldn't find main index 0.xml");
320	search_err = "INTERNAL ERROR: Unable to load main index 0.xml";
321	}
322	}