651 lines
18 KiB
JavaScript
651 lines
18 KiB
JavaScript
/*
|
|
* searchtools.js_t
|
|
* ~~~~~~~~~~~~~~~~
|
|
*
|
|
* Sphinx JavaScript utilities for the full-text search.
|
|
*
|
|
* :copyright: Copyright 2007-2016 by the Sphinx team, see AUTHORS.
|
|
* :license: BSD, see LICENSE for details.
|
|
*
|
|
*/
|
|
|
|
|
|
/* Non-minified version JS is _stemmer.js if file is provided */
|
|
/**
|
|
* Porter Stemmer
|
|
*/
|
|
var Stemmer = function() {
|
|
|
|
var step2list = {
|
|
ational: 'ate',
|
|
tional: 'tion',
|
|
enci: 'ence',
|
|
anci: 'ance',
|
|
izer: 'ize',
|
|
bli: 'ble',
|
|
alli: 'al',
|
|
entli: 'ent',
|
|
eli: 'e',
|
|
ousli: 'ous',
|
|
ization: 'ize',
|
|
ation: 'ate',
|
|
ator: 'ate',
|
|
alism: 'al',
|
|
iveness: 'ive',
|
|
fulness: 'ful',
|
|
ousness: 'ous',
|
|
aliti: 'al',
|
|
iviti: 'ive',
|
|
biliti: 'ble',
|
|
logi: 'log'
|
|
};
|
|
|
|
var step3list = {
|
|
icate: 'ic',
|
|
ative: '',
|
|
alize: 'al',
|
|
iciti: 'ic',
|
|
ical: 'ic',
|
|
ful: '',
|
|
ness: ''
|
|
};
|
|
|
|
var c = "[^aeiou]"; // consonant
|
|
var v = "[aeiouy]"; // vowel
|
|
var C = c + "[^aeiouy]*"; // consonant sequence
|
|
var V = v + "[aeiou]*"; // vowel sequence
|
|
|
|
var mgr0 = "^(" + C + ")?" + V + C; // [C]VC... is m>0
|
|
var meq1 = "^(" + C + ")?" + V + C + "(" + V + ")?$"; // [C]VC[V] is m=1
|
|
var mgr1 = "^(" + C + ")?" + V + C + V + C; // [C]VCVC... is m>1
|
|
var s_v = "^(" + C + ")?" + v; // vowel in stem
|
|
|
|
this.stemWord = function (w) {
|
|
var stem;
|
|
var suffix;
|
|
var firstch;
|
|
var origword = w;
|
|
|
|
if (w.length < 3)
|
|
return w;
|
|
|
|
var re;
|
|
var re2;
|
|
var re3;
|
|
var re4;
|
|
|
|
firstch = w.substr(0,1);
|
|
if (firstch == "y")
|
|
w = firstch.toUpperCase() + w.substr(1);
|
|
|
|
// Step 1a
|
|
re = /^(.+?)(ss|i)es$/;
|
|
re2 = /^(.+?)([^s])s$/;
|
|
|
|
if (re.test(w))
|
|
w = w.replace(re,"$1$2");
|
|
else if (re2.test(w))
|
|
w = w.replace(re2,"$1$2");
|
|
|
|
// Step 1b
|
|
re = /^(.+?)eed$/;
|
|
re2 = /^(.+?)(ed|ing)$/;
|
|
if (re.test(w)) {
|
|
var fp = re.exec(w);
|
|
re = new RegExp(mgr0);
|
|
if (re.test(fp[1])) {
|
|
re = /.$/;
|
|
w = w.replace(re,"");
|
|
}
|
|
}
|
|
else if (re2.test(w)) {
|
|
var fp = re2.exec(w);
|
|
stem = fp[1];
|
|
re2 = new RegExp(s_v);
|
|
if (re2.test(stem)) {
|
|
w = stem;
|
|
re2 = /(at|bl|iz)$/;
|
|
re3 = new RegExp("([^aeiouylsz])\\1$");
|
|
re4 = new RegExp("^" + C + v + "[^aeiouwxy]$");
|
|
if (re2.test(w))
|
|
w = w + "e";
|
|
else if (re3.test(w)) {
|
|
re = /.$/;
|
|
w = w.replace(re,"");
|
|
}
|
|
else if (re4.test(w))
|
|
w = w + "e";
|
|
}
|
|
}
|
|
|
|
// Step 1c
|
|
re = /^(.+?)y$/;
|
|
if (re.test(w)) {
|
|
var fp = re.exec(w);
|
|
stem = fp[1];
|
|
re = new RegExp(s_v);
|
|
if (re.test(stem))
|
|
w = stem + "i";
|
|
}
|
|
|
|
// Step 2
|
|
re = /^(.+?)(ational|tional|enci|anci|izer|bli|alli|entli|eli|ousli|ization|ation|ator|alism|iveness|fulness|ousness|aliti|iviti|biliti|logi)$/;
|
|
if (re.test(w)) {
|
|
var fp = re.exec(w);
|
|
stem = fp[1];
|
|
suffix = fp[2];
|
|
re = new RegExp(mgr0);
|
|
if (re.test(stem))
|
|
w = stem + step2list[suffix];
|
|
}
|
|
|
|
// Step 3
|
|
re = /^(.+?)(icate|ative|alize|iciti|ical|ful|ness)$/;
|
|
if (re.test(w)) {
|
|
var fp = re.exec(w);
|
|
stem = fp[1];
|
|
suffix = fp[2];
|
|
re = new RegExp(mgr0);
|
|
if (re.test(stem))
|
|
w = stem + step3list[suffix];
|
|
}
|
|
|
|
// Step 4
|
|
re = /^(.+?)(al|ance|ence|er|ic|able|ible|ant|ement|ment|ent|ou|ism|ate|iti|ous|ive|ize)$/;
|
|
re2 = /^(.+?)(s|t)(ion)$/;
|
|
if (re.test(w)) {
|
|
var fp = re.exec(w);
|
|
stem = fp[1];
|
|
re = new RegExp(mgr1);
|
|
if (re.test(stem))
|
|
w = stem;
|
|
}
|
|
else if (re2.test(w)) {
|
|
var fp = re2.exec(w);
|
|
stem = fp[1] + fp[2];
|
|
re2 = new RegExp(mgr1);
|
|
if (re2.test(stem))
|
|
w = stem;
|
|
}
|
|
|
|
// Step 5
|
|
re = /^(.+?)e$/;
|
|
if (re.test(w)) {
|
|
var fp = re.exec(w);
|
|
stem = fp[1];
|
|
re = new RegExp(mgr1);
|
|
re2 = new RegExp(meq1);
|
|
re3 = new RegExp("^" + C + v + "[^aeiouwxy]$");
|
|
if (re.test(stem) || (re2.test(stem) && !(re3.test(stem))))
|
|
w = stem;
|
|
}
|
|
re = /ll$/;
|
|
re2 = new RegExp(mgr1);
|
|
if (re.test(w) && re2.test(w)) {
|
|
re = /.$/;
|
|
w = w.replace(re,"");
|
|
}
|
|
|
|
// and turn initial Y back to y
|
|
if (firstch == "y")
|
|
w = firstch.toLowerCase() + w.substr(1);
|
|
return w;
|
|
}
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
* Simple result scoring code.
|
|
*/
|
|
var Scorer = {
|
|
// Implement the following function to further tweak the score for each result
|
|
// The function takes a result array [filename, title, anchor, descr, score]
|
|
// and returns the new score.
|
|
/*
|
|
score: function(result) {
|
|
return result[4];
|
|
},
|
|
*/
|
|
|
|
// query matches the full name of an object
|
|
objNameMatch: 11,
|
|
// or matches in the last dotted part of the object name
|
|
objPartialMatch: 6,
|
|
// Additive scores depending on the priority of the object
|
|
objPrio: {0: 15, // used to be importantResults
|
|
1: 5, // used to be objectResults
|
|
2: -5}, // used to be unimportantResults
|
|
// Used when the priority is not in the mapping.
|
|
objPrioDefault: 0,
|
|
|
|
// query found in title
|
|
title: 15,
|
|
// query found in terms
|
|
term: 5
|
|
};
|
|
|
|
|
|
/**
|
|
* Search Module
|
|
*/
|
|
var Search = {
|
|
|
|
_index : null,
|
|
_queued_query : null,
|
|
_pulse_status : -1,
|
|
|
|
init : function() {
|
|
var params = $.getQueryParameters();
|
|
if (params.q) {
|
|
var query = params.q[0];
|
|
$('input[name="q"]')[0].value = query;
|
|
this.performSearch(query);
|
|
}
|
|
},
|
|
|
|
loadIndex : function(url) {
|
|
$.ajax({type: "GET", url: url, data: null,
|
|
dataType: "script", cache: true,
|
|
complete: function(jqxhr, textstatus) {
|
|
if (textstatus != "success") {
|
|
document.getElementById("searchindexloader").src = url;
|
|
}
|
|
}});
|
|
},
|
|
|
|
setIndex : function(index) {
|
|
var q;
|
|
this._index = index;
|
|
if ((q = this._queued_query) !== null) {
|
|
this._queued_query = null;
|
|
Search.query(q);
|
|
}
|
|
},
|
|
|
|
hasIndex : function() {
|
|
return this._index !== null;
|
|
},
|
|
|
|
deferQuery : function(query) {
|
|
this._queued_query = query;
|
|
},
|
|
|
|
stopPulse : function() {
|
|
this._pulse_status = 0;
|
|
},
|
|
|
|
startPulse : function() {
|
|
if (this._pulse_status >= 0)
|
|
return;
|
|
function pulse() {
|
|
var i;
|
|
Search._pulse_status = (Search._pulse_status + 1) % 4;
|
|
var dotString = '';
|
|
for (i = 0; i < Search._pulse_status; i++)
|
|
dotString += '.';
|
|
Search.dots.text(dotString);
|
|
if (Search._pulse_status > -1)
|
|
window.setTimeout(pulse, 500);
|
|
}
|
|
pulse();
|
|
},
|
|
|
|
/**
|
|
* perform a search for something (or wait until index is loaded)
|
|
*/
|
|
performSearch : function(query) {
|
|
// create the required interface elements
|
|
this.out = $('#search-results');
|
|
this.title = $('<h2>' + _('Searching') + '</h2>').appendTo(this.out);
|
|
this.dots = $('<span></span>').appendTo(this.title);
|
|
this.status = $('<p style="display: none"></p>').appendTo(this.out);
|
|
this.output = $('<ul class="search"/>').appendTo(this.out);
|
|
|
|
$('#search-progress').text(_('Preparing search...'));
|
|
this.startPulse();
|
|
|
|
// index already loaded, the browser was quick!
|
|
if (this.hasIndex())
|
|
this.query(query);
|
|
else
|
|
this.deferQuery(query);
|
|
},
|
|
|
|
/**
|
|
* execute search (requires search index to be loaded)
|
|
*/
|
|
query : function(query) {
|
|
var i;
|
|
var stopwords = ["a","and","are","as","at","be","but","by","for","if","in","into","is","it","near","no","not","of","on","or","such","that","the","their","then","there","these","they","this","to","was","will","with"];
|
|
|
|
// stem the searchterms and add them to the correct list
|
|
var stemmer = new Stemmer();
|
|
var searchterms = [];
|
|
var excluded = [];
|
|
var hlterms = [];
|
|
var tmp = query.split(/\W+/);
|
|
var objectterms = [];
|
|
for (i = 0; i < tmp.length; i++) {
|
|
if (tmp[i] !== "") {
|
|
objectterms.push(tmp[i].toLowerCase());
|
|
}
|
|
|
|
if ($u.indexOf(stopwords, tmp[i].toLowerCase()) != -1 || tmp[i].match(/^\d+$/) ||
|
|
tmp[i] === "") {
|
|
// skip this "word"
|
|
continue;
|
|
}
|
|
// stem the word
|
|
var word = stemmer.stemWord(tmp[i].toLowerCase());
|
|
var toAppend;
|
|
// select the correct list
|
|
if (word[0] == '-') {
|
|
toAppend = excluded;
|
|
word = word.substr(1);
|
|
}
|
|
else {
|
|
toAppend = searchterms;
|
|
hlterms.push(tmp[i].toLowerCase());
|
|
}
|
|
// only add if not already in the list
|
|
if (!$u.contains(toAppend, word))
|
|
toAppend.push(word);
|
|
}
|
|
var highlightstring = '?highlight=' + $.urlencode(hlterms.join(" "));
|
|
|
|
// console.debug('SEARCH: searching for:');
|
|
// console.info('required: ', searchterms);
|
|
// console.info('excluded: ', excluded);
|
|
|
|
// prepare search
|
|
var terms = this._index.terms;
|
|
var titleterms = this._index.titleterms;
|
|
|
|
// array of [filename, title, anchor, descr, score]
|
|
var results = [];
|
|
$('#search-progress').empty();
|
|
|
|
// lookup as object
|
|
for (i = 0; i < objectterms.length; i++) {
|
|
var others = [].concat(objectterms.slice(0, i),
|
|
objectterms.slice(i+1, objectterms.length));
|
|
results = results.concat(this.performObjectSearch(objectterms[i], others));
|
|
}
|
|
|
|
// lookup as search terms in fulltext
|
|
results = results.concat(this.performTermsSearch(searchterms, excluded, terms, titleterms));
|
|
|
|
// let the scorer override scores with a custom scoring function
|
|
if (Scorer.score) {
|
|
for (i = 0; i < results.length; i++)
|
|
results[i][4] = Scorer.score(results[i]);
|
|
}
|
|
|
|
// now sort the results by score (in opposite order of appearance, since the
|
|
// display function below uses pop() to retrieve items) and then
|
|
// alphabetically
|
|
results.sort(function(a, b) {
|
|
var left = a[4];
|
|
var right = b[4];
|
|
if (left > right) {
|
|
return 1;
|
|
} else if (left < right) {
|
|
return -1;
|
|
} else {
|
|
// same score: sort alphabetically
|
|
left = a[1].toLowerCase();
|
|
right = b[1].toLowerCase();
|
|
return (left > right) ? -1 : ((left < right) ? 1 : 0);
|
|
}
|
|
});
|
|
|
|
// for debugging
|
|
//Search.lastresults = results.slice(); // a copy
|
|
//console.info('search results:', Search.lastresults);
|
|
|
|
// print the results
|
|
var resultCount = results.length;
|
|
function displayNextItem() {
|
|
// results left, load the summary and display it
|
|
if (results.length) {
|
|
var item = results.pop();
|
|
var listItem = $('<li style="display:none"></li>');
|
|
if (DOCUMENTATION_OPTIONS.FILE_SUFFIX === '') {
|
|
// dirhtml builder
|
|
var dirname = item[0] + '/';
|
|
if (dirname.match(/\/index\/$/)) {
|
|
dirname = dirname.substring(0, dirname.length-6);
|
|
} else if (dirname == 'index/') {
|
|
dirname = '';
|
|
}
|
|
listItem.append($('<a/>').attr('href',
|
|
DOCUMENTATION_OPTIONS.URL_ROOT + dirname +
|
|
highlightstring + item[2]).html(item[1]));
|
|
} else {
|
|
// normal html builders
|
|
listItem.append($('<a/>').attr('href',
|
|
item[0] + DOCUMENTATION_OPTIONS.FILE_SUFFIX +
|
|
highlightstring + item[2]).html(item[1]));
|
|
}
|
|
if (item[3]) {
|
|
listItem.append($('<span> (' + item[3] + ')</span>'));
|
|
Search.output.append(listItem);
|
|
listItem.slideDown(5, function() {
|
|
displayNextItem();
|
|
});
|
|
} else if (DOCUMENTATION_OPTIONS.HAS_SOURCE) {
|
|
$.ajax({url: DOCUMENTATION_OPTIONS.URL_ROOT + '_sources/' + item[0] + '.txt',
|
|
dataType: "text",
|
|
complete: function(jqxhr, textstatus) {
|
|
var data = jqxhr.responseText;
|
|
if (data !== '' && data !== undefined) {
|
|
listItem.append(Search.makeSearchSummary(data, searchterms, hlterms));
|
|
}
|
|
Search.output.append(listItem);
|
|
listItem.slideDown(5, function() {
|
|
displayNextItem();
|
|
});
|
|
}});
|
|
} else {
|
|
// no source available, just display title
|
|
Search.output.append(listItem);
|
|
listItem.slideDown(5, function() {
|
|
displayNextItem();
|
|
});
|
|
}
|
|
}
|
|
// search finished, update title and status message
|
|
else {
|
|
Search.stopPulse();
|
|
Search.title.text(_('Search Results'));
|
|
if (!resultCount)
|
|
Search.status.text(_('Your search did not match any documents. Please make sure that all words are spelled correctly and that you\'ve selected enough categories.'));
|
|
else
|
|
Search.status.text(_('Search finished, found %s page(s) matching the search query.').replace('%s', resultCount));
|
|
Search.status.fadeIn(500);
|
|
}
|
|
}
|
|
displayNextItem();
|
|
},
|
|
|
|
/**
|
|
* search for object names
|
|
*/
|
|
performObjectSearch : function(object, otherterms) {
|
|
var filenames = this._index.filenames;
|
|
var objects = this._index.objects;
|
|
var objnames = this._index.objnames;
|
|
var titles = this._index.titles;
|
|
|
|
var i;
|
|
var results = [];
|
|
|
|
for (var prefix in objects) {
|
|
for (var name in objects[prefix]) {
|
|
var fullname = (prefix ? prefix + '.' : '') + name;
|
|
if (fullname.toLowerCase().indexOf(object) > -1) {
|
|
var score = 0;
|
|
var parts = fullname.split('.');
|
|
// check for different match types: exact matches of full name or
|
|
// "last name" (i.e. last dotted part)
|
|
if (fullname == object || parts[parts.length - 1] == object) {
|
|
score += Scorer.objNameMatch;
|
|
// matches in last name
|
|
} else if (parts[parts.length - 1].indexOf(object) > -1) {
|
|
score += Scorer.objPartialMatch;
|
|
}
|
|
var match = objects[prefix][name];
|
|
var objname = objnames[match[1]][2];
|
|
var title = titles[match[0]];
|
|
// If more than one term searched for, we require other words to be
|
|
// found in the name/title/description
|
|
if (otherterms.length > 0) {
|
|
var haystack = (prefix + ' ' + name + ' ' +
|
|
objname + ' ' + title).toLowerCase();
|
|
var allfound = true;
|
|
for (i = 0; i < otherterms.length; i++) {
|
|
if (haystack.indexOf(otherterms[i]) == -1) {
|
|
allfound = false;
|
|
break;
|
|
}
|
|
}
|
|
if (!allfound) {
|
|
continue;
|
|
}
|
|
}
|
|
var descr = objname + _(', in ') + title;
|
|
|
|
var anchor = match[3];
|
|
if (anchor === '')
|
|
anchor = fullname;
|
|
else if (anchor == '-')
|
|
anchor = objnames[match[1]][1] + '-' + fullname;
|
|
// add custom score for some objects according to scorer
|
|
if (Scorer.objPrio.hasOwnProperty(match[2])) {
|
|
score += Scorer.objPrio[match[2]];
|
|
} else {
|
|
score += Scorer.objPrioDefault;
|
|
}
|
|
results.push([filenames[match[0]], fullname, '#'+anchor, descr, score]);
|
|
}
|
|
}
|
|
}
|
|
|
|
return results;
|
|
},
|
|
|
|
/**
|
|
* search for full-text terms in the index
|
|
*/
|
|
performTermsSearch : function(searchterms, excluded, terms, titleterms) {
|
|
var filenames = this._index.filenames;
|
|
var titles = this._index.titles;
|
|
|
|
var i, j, file;
|
|
var fileMap = {};
|
|
var scoreMap = {};
|
|
var results = [];
|
|
|
|
// perform the search on the required terms
|
|
for (i = 0; i < searchterms.length; i++) {
|
|
var word = searchterms[i];
|
|
var files = [];
|
|
var _o = [
|
|
{files: terms[word], score: Scorer.term},
|
|
{files: titleterms[word], score: Scorer.title}
|
|
];
|
|
|
|
// no match but word was a required one
|
|
if ($u.every(_o, function(o){return o.files === undefined;})) {
|
|
break;
|
|
}
|
|
// found search word in contents
|
|
$u.each(_o, function(o) {
|
|
var _files = o.files;
|
|
if (_files === undefined)
|
|
return
|
|
|
|
if (_files.length === undefined)
|
|
_files = [_files];
|
|
files = files.concat(_files);
|
|
|
|
// set score for the word in each file to Scorer.term
|
|
for (j = 0; j < _files.length; j++) {
|
|
file = _files[j];
|
|
if (!(file in scoreMap))
|
|
scoreMap[file] = {}
|
|
scoreMap[file][word] = o.score;
|
|
}
|
|
});
|
|
|
|
// create the mapping
|
|
for (j = 0; j < files.length; j++) {
|
|
file = files[j];
|
|
if (file in fileMap)
|
|
fileMap[file].push(word);
|
|
else
|
|
fileMap[file] = [word];
|
|
}
|
|
}
|
|
|
|
// now check if the files don't contain excluded terms
|
|
for (file in fileMap) {
|
|
var valid = true;
|
|
|
|
// check if all requirements are matched
|
|
if (fileMap[file].length != searchterms.length)
|
|
continue;
|
|
|
|
// ensure that none of the excluded terms is in the search result
|
|
for (i = 0; i < excluded.length; i++) {
|
|
if (terms[excluded[i]] == file ||
|
|
titleterms[excluded[i]] == file ||
|
|
$u.contains(terms[excluded[i]] || [], file) ||
|
|
$u.contains(titleterms[excluded[i]] || [], file)) {
|
|
valid = false;
|
|
break;
|
|
}
|
|
}
|
|
|
|
// if we have still a valid result we can add it to the result list
|
|
if (valid) {
|
|
// select one (max) score for the file.
|
|
// for better ranking, we should calculate ranking by using words statistics like basic tf-idf...
|
|
var score = $u.max($u.map(fileMap[file], function(w){return scoreMap[file][w]}));
|
|
results.push([filenames[file], titles[file], '', null, score]);
|
|
}
|
|
}
|
|
return results;
|
|
},
|
|
|
|
/**
|
|
* helper function to return a node containing the
|
|
* search summary for a given text. keywords is a list
|
|
* of stemmed words, hlwords is the list of normal, unstemmed
|
|
* words. the first one is used to find the occurrence, the
|
|
* latter for highlighting it.
|
|
*/
|
|
makeSearchSummary : function(text, keywords, hlwords) {
|
|
var textLower = text.toLowerCase();
|
|
var start = 0;
|
|
$.each(keywords, function() {
|
|
var i = textLower.indexOf(this.toLowerCase());
|
|
if (i > -1)
|
|
start = i;
|
|
});
|
|
start = Math.max(start - 120, 0);
|
|
var excerpt = ((start > 0) ? '...' : '') +
|
|
$.trim(text.substr(start, 240)) +
|
|
((start + 240 - text.length) ? '...' : '');
|
|
var rv = $('<div class="context"></div>').text(excerpt);
|
|
$.each(hlwords, function() {
|
|
rv = rv.highlightText(this, 'highlighted');
|
|
});
|
|
return rv;
|
|
}
|
|
};
|
|
|
|
$(document).ready(function() {
|
|
Search.init();
|
|
}); |