From 4346d0178571501727ba021016b4066c0d17eb19 Mon Sep 17 00:00:00 2001 From: Nick Garlis Date: Thu, 28 Dec 2017 20:56:10 +0200 Subject: [PATCH] Update Lunr (#1419) * Update Lunr to 2.1.5 * Remove colons from query string Fixes #1419 --- assets/js/lunr-en.js | 45 +- assets/js/lunr.min.js | 2980 ++++++++++++++++++++++++++++++++++++++++- 2 files changed, 3003 insertions(+), 22 deletions(-) diff --git a/assets/js/lunr-en.js b/assets/js/lunr-en.js index a515c19..8df45b8 100644 --- a/assets/js/lunr-en.js +++ b/assets/js/lunr-en.js @@ -3,27 +3,27 @@ layout: null --- var idx = lunr(function () { - this.field('title', {boost: 10}) + this.field('title') this.field('excerpt') this.field('categories') this.field('tags') this.ref('id') -}); -{% assign count = 0 %} -{% for c in site.collections %} - {% assign docs = c.docs | where_exp:'doc','doc.search != false' %} - {% for doc in docs %} - idx.add({ - title: {{ doc.title | jsonify }}, - excerpt: {{ doc.content | strip_html | truncatewords: 20 | jsonify }}, - categories: {{ doc.categories | jsonify }}, - tags: {{ doc.tags | jsonify }}, - id: {{ count }} - }); - {% assign count = count | plus: 1 %} + {% assign count = 0 %} + {% for c in site.collections %} + {% assign docs = c.docs | where_exp:'doc','doc.search != false' %} + {% for doc in docs %} + this.add({ + title: {{ doc.title | jsonify }}, + excerpt: {{ doc.content | strip_html | truncatewords: 20 | jsonify }}, + categories: {{ doc.categories | jsonify }}, + tags: {{ doc.tags | jsonify }}, + id: {{ count }} + }) + {% assign count = count | plus: 1 %} + {% endfor %} {% endfor %} -{% endfor %} +}); console.log( jQuery.type(idx) ); @@ -56,8 +56,19 @@ var store = [ $(document).ready(function() { $('input#search').on('keyup', function () { var resultdiv = $('#results'); - var query = $(this).val(); - var result = idx.search(query); + var query = $(this).val().toLowerCase().replace(":", ""); + var result = + idx.query(function (q) { + query.split(lunr.tokenizer.separator).forEach(function (term) { + q.term(term, { boost: 100 }) + if(query.lastIndexOf(" ") != query.length-1){ + q.term(term, { usePipeline: false, wildcard: lunr.Query.wildcard.TRAILING, boost: 10 }) + } + if (term != ""){ + q.term(term, { usePipeline: false, editDistance: 1, boost: 1 }) + } + }) + }); resultdiv.empty(); resultdiv.prepend('

'+result.length+' {{ site.data.ui-text[site.locale].results_found | default: "Result(s) found" }}

'); for (var item in result) { diff --git a/assets/js/lunr.min.js b/assets/js/lunr.min.js index 914dcc6..f208eba 100644 --- a/assets/js/lunr.min.js +++ b/assets/js/lunr.min.js @@ -1,7 +1,2977 @@ /** - * lunr - http://lunrjs.com - A bit like Solr, but much smaller and not as bright - 0.5.12 - * Copyright (C) 2015 Oliver Nightingale - * MIT Licensed - * @license + * lunr - http://lunrjs.com - A bit like Solr, but much smaller and not as bright - 2.1.5 + * Copyright (C) 2017 Oliver Nightingale + * @license MIT */ -!function(){var t=function(e){var n=new t.Index;return n.pipeline.add(t.trimmer,t.stopWordFilter,t.stemmer),e&&e.call(n,n),n};t.version="0.5.12",t.utils={},t.utils.warn=function(t){return function(e){t.console&&console.warn&&console.warn(e)}}(this),t.EventEmitter=function(){this.events={}},t.EventEmitter.prototype.addListener=function(){var t=Array.prototype.slice.call(arguments),e=t.pop(),n=t;if("function"!=typeof e)throw new TypeError("last argument must be a function");n.forEach(function(t){this.hasHandler(t)||(this.events[t]=[]),this.events[t].push(e)},this)},t.EventEmitter.prototype.removeListener=function(t,e){if(this.hasHandler(t)){var n=this.events[t].indexOf(e);this.events[t].splice(n,1),this.events[t].length||delete this.events[t]}},t.EventEmitter.prototype.emit=function(t){if(this.hasHandler(t)){var e=Array.prototype.slice.call(arguments,1);this.events[t].forEach(function(t){t.apply(void 0,e)})}},t.EventEmitter.prototype.hasHandler=function(t){return t in this.events},t.tokenizer=function(t){return arguments.length&&null!=t&&void 0!=t?Array.isArray(t)?t.map(function(t){return t.toLowerCase()}):t.toString().trim().toLowerCase().split(/[\s\-]+/):[]},t.Pipeline=function(){this._stack=[]},t.Pipeline.registeredFunctions={},t.Pipeline.registerFunction=function(e,n){n in this.registeredFunctions&&t.utils.warn("Overwriting existing registered function: "+n),e.label=n,t.Pipeline.registeredFunctions[e.label]=e},t.Pipeline.warnIfFunctionNotRegistered=function(e){var n=e.label&&e.label in this.registeredFunctions;n||t.utils.warn("Function is not registered with pipeline. This may cause problems when serialising the index.\n",e)},t.Pipeline.load=function(e){var n=new t.Pipeline;return e.forEach(function(e){var i=t.Pipeline.registeredFunctions[e];if(!i)throw new Error("Cannot load un-registered function: "+e);n.add(i)}),n},t.Pipeline.prototype.add=function(){var e=Array.prototype.slice.call(arguments);e.forEach(function(e){t.Pipeline.warnIfFunctionNotRegistered(e),this._stack.push(e)},this)},t.Pipeline.prototype.after=function(e,n){t.Pipeline.warnIfFunctionNotRegistered(n);var i=this._stack.indexOf(e);if(-1==i)throw new Error("Cannot find existingFn");i+=1,this._stack.splice(i,0,n)},t.Pipeline.prototype.before=function(e,n){t.Pipeline.warnIfFunctionNotRegistered(n);var i=this._stack.indexOf(e);if(-1==i)throw new Error("Cannot find existingFn");this._stack.splice(i,0,n)},t.Pipeline.prototype.remove=function(t){var e=this._stack.indexOf(t);-1!=e&&this._stack.splice(e,1)},t.Pipeline.prototype.run=function(t){for(var e=[],n=t.length,i=this._stack.length,o=0;n>o;o++){for(var r=t[o],s=0;i>s&&(r=this._stack[s](r,o,t),void 0!==r);s++);void 0!==r&&e.push(r)}return e},t.Pipeline.prototype.reset=function(){this._stack=[]},t.Pipeline.prototype.toJSON=function(){return this._stack.map(function(e){return t.Pipeline.warnIfFunctionNotRegistered(e),e.label})},t.Vector=function(){this._magnitude=null,this.list=void 0,this.length=0},t.Vector.Node=function(t,e,n){this.idx=t,this.val=e,this.next=n},t.Vector.prototype.insert=function(e,n){this._magnitude=void 0;var i=this.list;if(!i)return this.list=new t.Vector.Node(e,n,i),this.length++;if(en.idx?n=n.next:(i+=e.val*n.val,e=e.next,n=n.next);return i},t.Vector.prototype.similarity=function(t){return this.dot(t)/(this.magnitude()*t.magnitude())},t.SortedSet=function(){this.length=0,this.elements=[]},t.SortedSet.load=function(t){var e=new this;return e.elements=t,e.length=t.length,e},t.SortedSet.prototype.add=function(){var t,e;for(t=0;t1;){if(r===t)return o;t>r&&(e=o),r>t&&(n=o),i=n-e,o=e+Math.floor(i/2),r=this.elements[o]}return r===t?o:-1},t.SortedSet.prototype.locationFor=function(t){for(var e=0,n=this.elements.length,i=n-e,o=e+Math.floor(i/2),r=this.elements[o];i>1;)t>r&&(e=o),r>t&&(n=o),i=n-e,o=e+Math.floor(i/2),r=this.elements[o];return r>t?o:t>r?o+1:void 0},t.SortedSet.prototype.intersect=function(e){for(var n=new t.SortedSet,i=0,o=0,r=this.length,s=e.length,a=this.elements,h=e.elements;;){if(i>r-1||o>s-1)break;a[i]!==h[o]?a[i]h[o]&&o++:(n.add(a[i]),i++,o++)}return n},t.SortedSet.prototype.clone=function(){var e=new t.SortedSet;return e.elements=this.toArray(),e.length=e.elements.length,e},t.SortedSet.prototype.union=function(t){var e,n,i;return this.length>=t.length?(e=this,n=t):(e=t,n=this),i=e.clone(),i.add.apply(i,n.toArray()),i},t.SortedSet.prototype.toJSON=function(){return this.toArray()},t.Index=function(){this._fields=[],this._ref="id",this.pipeline=new t.Pipeline,this.documentStore=new t.Store,this.tokenStore=new t.TokenStore,this.corpusTokens=new t.SortedSet,this.eventEmitter=new t.EventEmitter,this._idfCache={},this.on("add","remove","update",function(){this._idfCache={}}.bind(this))},t.Index.prototype.on=function(){var t=Array.prototype.slice.call(arguments);return this.eventEmitter.addListener.apply(this.eventEmitter,t)},t.Index.prototype.off=function(t,e){return this.eventEmitter.removeListener(t,e)},t.Index.load=function(e){e.version!==t.version&&t.utils.warn("version mismatch: current "+t.version+" importing "+e.version);var n=new this;return n._fields=e.fields,n._ref=e.ref,n.documentStore=t.Store.load(e.documentStore),n.tokenStore=t.TokenStore.load(e.tokenStore),n.corpusTokens=t.SortedSet.load(e.corpusTokens),n.pipeline=t.Pipeline.load(e.pipeline),n},t.Index.prototype.field=function(t,e){var e=e||{},n={name:t,boost:e.boost||1};return this._fields.push(n),this},t.Index.prototype.ref=function(t){return this._ref=t,this},t.Index.prototype.add=function(e,n){var i={},o=new t.SortedSet,r=e[this._ref],n=void 0===n?!0:n;this._fields.forEach(function(n){var r=this.pipeline.run(t.tokenizer(e[n.name]));i[n.name]=r,t.SortedSet.prototype.add.apply(o,r)},this),this.documentStore.set(r,o),t.SortedSet.prototype.add.apply(this.corpusTokens,o.toArray());for(var s=0;s0&&(i=1+Math.log(this.documentStore.length/n)),this._idfCache[e]=i},t.Index.prototype.search=function(e){var n=this.pipeline.run(t.tokenizer(e)),i=new t.Vector,o=[],r=this._fields.reduce(function(t,e){return t+e.boost},0),s=n.some(function(t){return this.tokenStore.has(t)},this);if(!s)return[];n.forEach(function(e,n,s){var a=1/s.length*this._fields.length*r,h=this,l=this.tokenStore.expand(e).reduce(function(n,o){var r=h.corpusTokens.indexOf(o),s=h.idf(o),l=1,u=new t.SortedSet;if(o!==e){var c=Math.max(3,o.length-e.length);l=1/Math.log(c)}return r>-1&&i.insert(r,a*s*l),Object.keys(h.tokenStore.get(o)).forEach(function(t){u.add(t)}),n.union(u)},new t.SortedSet);o.push(l)},this);var a=o.reduce(function(t,e){return t.intersect(e)});return a.map(function(t){return{ref:t,score:i.similarity(this.documentVector(t))}},this).sort(function(t,e){return e.score-t.score})},t.Index.prototype.documentVector=function(e){for(var n=this.documentStore.get(e),i=n.length,o=new t.Vector,r=0;i>r;r++){var s=n.elements[r],a=this.tokenStore.get(s)[e].tf,h=this.idf(s);o.insert(this.corpusTokens.indexOf(s),a*h)}return o},t.Index.prototype.toJSON=function(){return{version:t.version,fields:this._fields,ref:this._ref,documentStore:this.documentStore.toJSON(),tokenStore:this.tokenStore.toJSON(),corpusTokens:this.corpusTokens.toJSON(),pipeline:this.pipeline.toJSON()}},t.Index.prototype.use=function(t){var e=Array.prototype.slice.call(arguments,1);e.unshift(this),t.apply(this,e)},t.Store=function(){this.store={},this.length=0},t.Store.load=function(e){var n=new this;return n.length=e.length,n.store=Object.keys(e.store).reduce(function(n,i){return n[i]=t.SortedSet.load(e.store[i]),n},{}),n},t.Store.prototype.set=function(t,e){this.has(t)||this.length++,this.store[t]=e},t.Store.prototype.get=function(t){return this.store[t]},t.Store.prototype.has=function(t){return t in this.store},t.Store.prototype.remove=function(t){this.has(t)&&(delete this.store[t],this.length--)},t.Store.prototype.toJSON=function(){return{store:this.store,length:this.length}},t.stemmer=function(){var t={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"},e={icate:"ic",ative:"",alize:"al",iciti:"ic",ical:"ic",ful:"",ness:""},n="[^aeiou]",i="[aeiouy]",o=n+"[^aeiouy]*",r=i+"[aeiou]*",s="^("+o+")?"+r+o,a="^("+o+")?"+r+o+"("+r+")?$",h="^("+o+")?"+r+o+r+o,l="^("+o+")?"+i,u=new RegExp(s),c=new RegExp(h),f=new RegExp(a),d=new RegExp(l),p=/^(.+?)(ss|i)es$/,m=/^(.+?)([^s])s$/,v=/^(.+?)eed$/,y=/^(.+?)(ed|ing)$/,g=/.$/,S=/(at|bl|iz)$/,w=new RegExp("([^aeiouylsz])\\1$"),x=new RegExp("^"+o+i+"[^aeiouwxy]$"),k=/^(.+?[^aeiou])y$/,b=/^(.+?)(ational|tional|enci|anci|izer|bli|alli|entli|eli|ousli|ization|ation|ator|alism|iveness|fulness|ousness|aliti|iviti|biliti|logi)$/,E=/^(.+?)(icate|ative|alize|iciti|ical|ful|ness)$/,_=/^(.+?)(al|ance|ence|er|ic|able|ible|ant|ement|ment|ent|ou|ism|ate|iti|ous|ive|ize)$/,F=/^(.+?)(s|t)(ion)$/,O=/^(.+?)e$/,P=/ll$/,N=new RegExp("^"+o+i+"[^aeiouwxy]$"),T=function(n){var i,o,r,s,a,h,l;if(n.length<3)return n;if(r=n.substr(0,1),"y"==r&&(n=r.toUpperCase()+n.substr(1)),s=p,a=m,s.test(n)?n=n.replace(s,"$1$2"):a.test(n)&&(n=n.replace(a,"$1$2")),s=v,a=y,s.test(n)){var T=s.exec(n);s=u,s.test(T[1])&&(s=g,n=n.replace(s,""))}else if(a.test(n)){var T=a.exec(n);i=T[1],a=d,a.test(i)&&(n=i,a=S,h=w,l=x,a.test(n)?n+="e":h.test(n)?(s=g,n=n.replace(s,"")):l.test(n)&&(n+="e"))}if(s=k,s.test(n)){var T=s.exec(n);i=T[1],n=i+"i"}if(s=b,s.test(n)){var T=s.exec(n);i=T[1],o=T[2],s=u,s.test(i)&&(n=i+t[o])}if(s=E,s.test(n)){var T=s.exec(n);i=T[1],o=T[2],s=u,s.test(i)&&(n=i+e[o])}if(s=_,a=F,s.test(n)){var T=s.exec(n);i=T[1],s=c,s.test(i)&&(n=i)}else if(a.test(n)){var T=a.exec(n);i=T[1]+T[2],a=c,a.test(i)&&(n=i)}if(s=O,s.test(n)){var T=s.exec(n);i=T[1],s=c,a=f,h=N,(s.test(i)||a.test(i)&&!h.test(i))&&(n=i)}return s=P,a=c,s.test(n)&&a.test(n)&&(s=g,n=n.replace(s,"")),"y"==r&&(n=r.toLowerCase()+n.substr(1)),n};return T}(),t.Pipeline.registerFunction(t.stemmer,"stemmer"),t.stopWordFilter=function(e){return e&&t.stopWordFilter.stopWords[e]!==e?e:void 0},t.stopWordFilter.stopWords={a:"a",able:"able",about:"about",across:"across",after:"after",all:"all",almost:"almost",also:"also",am:"am",among:"among",an:"an",and:"and",any:"any",are:"are",as:"as",at:"at",be:"be",because:"because",been:"been",but:"but",by:"by",can:"can",cannot:"cannot",could:"could",dear:"dear",did:"did","do":"do",does:"does",either:"either","else":"else",ever:"ever",every:"every","for":"for",from:"from",get:"get",got:"got",had:"had",has:"has",have:"have",he:"he",her:"her",hers:"hers",him:"him",his:"his",how:"how",however:"however",i:"i","if":"if","in":"in",into:"into",is:"is",it:"it",its:"its",just:"just",least:"least",let:"let",like:"like",likely:"likely",may:"may",me:"me",might:"might",most:"most",must:"must",my:"my",neither:"neither",no:"no",nor:"nor",not:"not",of:"of",off:"off",often:"often",on:"on",only:"only",or:"or",other:"other",our:"our",own:"own",rather:"rather",said:"said",say:"say",says:"says",she:"she",should:"should",since:"since",so:"so",some:"some",than:"than",that:"that",the:"the",their:"their",them:"them",then:"then",there:"there",these:"these",they:"they","this":"this",tis:"tis",to:"to",too:"too",twas:"twas",us:"us",wants:"wants",was:"was",we:"we",were:"were",what:"what",when:"when",where:"where",which:"which","while":"while",who:"who",whom:"whom",why:"why",will:"will","with":"with",would:"would",yet:"yet",you:"you",your:"your"},t.Pipeline.registerFunction(t.stopWordFilter,"stopWordFilter"),t.trimmer=function(t){var e=t.replace(/^\W+/,"").replace(/\W+$/,"");return""===e?void 0:e},t.Pipeline.registerFunction(t.trimmer,"trimmer"),t.TokenStore=function(){this.root={docs:{}},this.length=0},t.TokenStore.load=function(t){var e=new this;return e.root=t.root,e.length=t.length,e},t.TokenStore.prototype.add=function(t,e,n){var n=n||this.root,i=t[0],o=t.slice(1);return i in n||(n[i]={docs:{}}),0===o.length?(n[i].docs[e.ref]=e,void(this.length+=1)):this.add(o,e,n[i])},t.TokenStore.prototype.has=function(t){if(!t)return!1;for(var e=this.root,n=0;n 0) { + tokens.push( + new lunr.Token (str.slice(sliceStart, sliceEnd), { + position: [sliceStart, sliceLength], + index: tokens.length + }) + ) + } + + sliceStart = sliceEnd + 1 + } + + } + + return tokens +} + +/** + * The separator used to split a string into tokens. Override this property to change the behaviour of + * `lunr.tokenizer` behaviour when tokenizing strings. By default this splits on whitespace and hyphens. + * + * @static + * @see lunr.tokenizer + */ +lunr.tokenizer.separator = /[\s\-]+/ +/*! + * lunr.Pipeline + * Copyright (C) 2017 Oliver Nightingale + */ + +/** + * lunr.Pipelines maintain an ordered list of functions to be applied to all + * tokens in documents entering the search index and queries being ran against + * the index. + * + * An instance of lunr.Index created with the lunr shortcut will contain a + * pipeline with a stop word filter and an English language stemmer. Extra + * functions can be added before or after either of these functions or these + * default functions can be removed. + * + * When run the pipeline will call each function in turn, passing a token, the + * index of that token in the original list of all tokens and finally a list of + * all the original tokens. + * + * The output of functions in the pipeline will be passed to the next function + * in the pipeline. To exclude a token from entering the index the function + * should return undefined, the rest of the pipeline will not be called with + * this token. + * + * For serialisation of pipelines to work, all functions used in an instance of + * a pipeline should be registered with lunr.Pipeline. Registered functions can + * then be loaded. If trying to load a serialised pipeline that uses functions + * that are not registered an error will be thrown. + * + * If not planning on serialising the pipeline then registering pipeline functions + * is not necessary. + * + * @constructor + */ +lunr.Pipeline = function () { + this._stack = [] +} + +lunr.Pipeline.registeredFunctions = Object.create(null) + +/** + * A pipeline function maps lunr.Token to lunr.Token. A lunr.Token contains the token + * string as well as all known metadata. A pipeline function can mutate the token string + * or mutate (or add) metadata for a given token. + * + * A pipeline function can indicate that the passed token should be discarded by returning + * null. This token will not be passed to any downstream pipeline functions and will not be + * added to the index. + * + * Multiple tokens can be returned by returning an array of tokens. Each token will be passed + * to any downstream pipeline functions and all will returned tokens will be added to the index. + * + * Any number of pipeline functions may be chained together using a lunr.Pipeline. + * + * @interface lunr.PipelineFunction + * @param {lunr.Token} token - A token from the document being processed. + * @param {number} i - The index of this token in the complete list of tokens for this document/field. + * @param {lunr.Token[]} tokens - All tokens for this document/field. + * @returns {(?lunr.Token|lunr.Token[])} + */ + +/** + * Register a function with the pipeline. + * + * Functions that are used in the pipeline should be registered if the pipeline + * needs to be serialised, or a serialised pipeline needs to be loaded. + * + * Registering a function does not add it to a pipeline, functions must still be + * added to instances of the pipeline for them to be used when running a pipeline. + * + * @param {lunr.PipelineFunction} fn - The function to check for. + * @param {String} label - The label to register this function with + */ +lunr.Pipeline.registerFunction = function (fn, label) { + if (label in this.registeredFunctions) { + lunr.utils.warn('Overwriting existing registered function: ' + label) + } + + fn.label = label + lunr.Pipeline.registeredFunctions[fn.label] = fn +} + +/** + * Warns if the function is not registered as a Pipeline function. + * + * @param {lunr.PipelineFunction} fn - The function to check for. + * @private + */ +lunr.Pipeline.warnIfFunctionNotRegistered = function (fn) { + var isRegistered = fn.label && (fn.label in this.registeredFunctions) + + if (!isRegistered) { + lunr.utils.warn('Function is not registered with pipeline. This may cause problems when serialising the index.\n', fn) + } +} + +/** + * Loads a previously serialised pipeline. + * + * All functions to be loaded must already be registered with lunr.Pipeline. + * If any function from the serialised data has not been registered then an + * error will be thrown. + * + * @param {Object} serialised - The serialised pipeline to load. + * @returns {lunr.Pipeline} + */ +lunr.Pipeline.load = function (serialised) { + var pipeline = new lunr.Pipeline + + serialised.forEach(function (fnName) { + var fn = lunr.Pipeline.registeredFunctions[fnName] + + if (fn) { + pipeline.add(fn) + } else { + throw new Error('Cannot load unregistered function: ' + fnName) + } + }) + + return pipeline +} + +/** + * Adds new functions to the end of the pipeline. + * + * Logs a warning if the function has not been registered. + * + * @param {lunr.PipelineFunction[]} functions - Any number of functions to add to the pipeline. + */ +lunr.Pipeline.prototype.add = function () { + var fns = Array.prototype.slice.call(arguments) + + fns.forEach(function (fn) { + lunr.Pipeline.warnIfFunctionNotRegistered(fn) + this._stack.push(fn) + }, this) +} + +/** + * Adds a single function after a function that already exists in the + * pipeline. + * + * Logs a warning if the function has not been registered. + * + * @param {lunr.PipelineFunction} existingFn - A function that already exists in the pipeline. + * @param {lunr.PipelineFunction} newFn - The new function to add to the pipeline. + */ +lunr.Pipeline.prototype.after = function (existingFn, newFn) { + lunr.Pipeline.warnIfFunctionNotRegistered(newFn) + + var pos = this._stack.indexOf(existingFn) + if (pos == -1) { + throw new Error('Cannot find existingFn') + } + + pos = pos + 1 + this._stack.splice(pos, 0, newFn) +} + +/** + * Adds a single function before a function that already exists in the + * pipeline. + * + * Logs a warning if the function has not been registered. + * + * @param {lunr.PipelineFunction} existingFn - A function that already exists in the pipeline. + * @param {lunr.PipelineFunction} newFn - The new function to add to the pipeline. + */ +lunr.Pipeline.prototype.before = function (existingFn, newFn) { + lunr.Pipeline.warnIfFunctionNotRegistered(newFn) + + var pos = this._stack.indexOf(existingFn) + if (pos == -1) { + throw new Error('Cannot find existingFn') + } + + this._stack.splice(pos, 0, newFn) +} + +/** + * Removes a function from the pipeline. + * + * @param {lunr.PipelineFunction} fn The function to remove from the pipeline. + */ +lunr.Pipeline.prototype.remove = function (fn) { + var pos = this._stack.indexOf(fn) + if (pos == -1) { + return + } + + this._stack.splice(pos, 1) +} + +/** + * Runs the current list of functions that make up the pipeline against the + * passed tokens. + * + * @param {Array} tokens The tokens to run through the pipeline. + * @returns {Array} + */ +lunr.Pipeline.prototype.run = function (tokens) { + var stackLength = this._stack.length + + for (var i = 0; i < stackLength; i++) { + var fn = this._stack[i] + + tokens = tokens.reduce(function (memo, token, j) { + var result = fn(token, j, tokens) + + if (result === void 0 || result === '') return memo + + return memo.concat(result) + }, []) + } + + return tokens +} + +/** + * Convenience method for passing a string through a pipeline and getting + * strings out. This method takes care of wrapping the passed string in a + * token and mapping the resulting tokens back to strings. + * + * @param {string} str - The string to pass through the pipeline. + * @returns {string[]} + */ +lunr.Pipeline.prototype.runString = function (str) { + var token = new lunr.Token (str) + + return this.run([token]).map(function (t) { + return t.toString() + }) +} + +/** + * Resets the pipeline by removing any existing processors. + * + */ +lunr.Pipeline.prototype.reset = function () { + this._stack = [] +} + +/** + * Returns a representation of the pipeline ready for serialisation. + * + * Logs a warning if the function has not been registered. + * + * @returns {Array} + */ +lunr.Pipeline.prototype.toJSON = function () { + return this._stack.map(function (fn) { + lunr.Pipeline.warnIfFunctionNotRegistered(fn) + + return fn.label + }) +} +/*! + * lunr.Vector + * Copyright (C) 2017 Oliver Nightingale + */ + +/** + * A vector is used to construct the vector space of documents and queries. These + * vectors support operations to determine the similarity between two documents or + * a document and a query. + * + * Normally no parameters are required for initializing a vector, but in the case of + * loading a previously dumped vector the raw elements can be provided to the constructor. + * + * For performance reasons vectors are implemented with a flat array, where an elements + * index is immediately followed by its value. E.g. [index, value, index, value]. This + * allows the underlying array to be as sparse as possible and still offer decent + * performance when being used for vector calculations. + * + * @constructor + * @param {Number[]} [elements] - The flat list of element index and element value pairs. + */ +lunr.Vector = function (elements) { + this._magnitude = 0 + this.elements = elements || [] +} + + +/** + * Calculates the position within the vector to insert a given index. + * + * This is used internally by insert and upsert. If there are duplicate indexes then + * the position is returned as if the value for that index were to be updated, but it + * is the callers responsibility to check whether there is a duplicate at that index + * + * @param {Number} insertIdx - The index at which the element should be inserted. + * @returns {Number} + */ +lunr.Vector.prototype.positionForIndex = function (index) { + // For an empty vector the tuple can be inserted at the beginning + if (this.elements.length == 0) { + return 0 + } + + var start = 0, + end = this.elements.length / 2, + sliceLength = end - start, + pivotPoint = Math.floor(sliceLength / 2), + pivotIndex = this.elements[pivotPoint * 2] + + while (sliceLength > 1) { + if (pivotIndex < index) { + start = pivotPoint + } + + if (pivotIndex > index) { + end = pivotPoint + } + + if (pivotIndex == index) { + break + } + + sliceLength = end - start + pivotPoint = start + Math.floor(sliceLength / 2) + pivotIndex = this.elements[pivotPoint * 2] + } + + if (pivotIndex == index) { + return pivotPoint * 2 + } + + if (pivotIndex > index) { + return pivotPoint * 2 + } + + if (pivotIndex < index) { + return (pivotPoint + 1) * 2 + } +} + +/** + * Inserts an element at an index within the vector. + * + * Does not allow duplicates, will throw an error if there is already an entry + * for this index. + * + * @param {Number} insertIdx - The index at which the element should be inserted. + * @param {Number} val - The value to be inserted into the vector. + */ +lunr.Vector.prototype.insert = function (insertIdx, val) { + this.upsert(insertIdx, val, function () { + throw "duplicate index" + }) +} + +/** + * Inserts or updates an existing index within the vector. + * + * @param {Number} insertIdx - The index at which the element should be inserted. + * @param {Number} val - The value to be inserted into the vector. + * @param {function} fn - A function that is called for updates, the existing value and the + * requested value are passed as arguments + */ +lunr.Vector.prototype.upsert = function (insertIdx, val, fn) { + this._magnitude = 0 + var position = this.positionForIndex(insertIdx) + + if (this.elements[position] == insertIdx) { + this.elements[position + 1] = fn(this.elements[position + 1], val) + } else { + this.elements.splice(position, 0, insertIdx, val) + } +} + +/** + * Calculates the magnitude of this vector. + * + * @returns {Number} + */ +lunr.Vector.prototype.magnitude = function () { + if (this._magnitude) return this._magnitude + + var sumOfSquares = 0, + elementsLength = this.elements.length + + for (var i = 1; i < elementsLength; i += 2) { + var val = this.elements[i] + sumOfSquares += val * val + } + + return this._magnitude = Math.sqrt(sumOfSquares) +} + +/** + * Calculates the dot product of this vector and another vector. + * + * @param {lunr.Vector} otherVector - The vector to compute the dot product with. + * @returns {Number} + */ +lunr.Vector.prototype.dot = function (otherVector) { + var dotProduct = 0, + a = this.elements, b = otherVector.elements, + aLen = a.length, bLen = b.length, + aVal = 0, bVal = 0, + i = 0, j = 0 + + while (i < aLen && j < bLen) { + aVal = a[i], bVal = b[j] + if (aVal < bVal) { + i += 2 + } else if (aVal > bVal) { + j += 2 + } else if (aVal == bVal) { + dotProduct += a[i + 1] * b[j + 1] + i += 2 + j += 2 + } + } + + return dotProduct +} + +/** + * Calculates the cosine similarity between this vector and another + * vector. + * + * @param {lunr.Vector} otherVector - The other vector to calculate the + * similarity with. + * @returns {Number} + */ +lunr.Vector.prototype.similarity = function (otherVector) { + return this.dot(otherVector) / (this.magnitude() * otherVector.magnitude()) +} + +/** + * Converts the vector to an array of the elements within the vector. + * + * @returns {Number[]} + */ +lunr.Vector.prototype.toArray = function () { + var output = new Array (this.elements.length / 2) + + for (var i = 1, j = 0; i < this.elements.length; i += 2, j++) { + output[j] = this.elements[i] + } + + return output +} + +/** + * A JSON serializable representation of the vector. + * + * @returns {Number[]} + */ +lunr.Vector.prototype.toJSON = function () { + return this.elements +} +/* eslint-disable */ +/*! + * lunr.stemmer + * Copyright (C) 2017 Oliver Nightingale + * Includes code from - http://tartarus.org/~martin/PorterStemmer/js.txt + */ + +/** + * lunr.stemmer is an english language stemmer, this is a JavaScript + * implementation of the PorterStemmer taken from http://tartarus.org/~martin + * + * @static + * @implements {lunr.PipelineFunction} + * @param {lunr.Token} token - The string to stem + * @returns {lunr.Token} + * @see {@link lunr.Pipeline} + */ +lunr.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" + }, + + step3list = { + "icate" : "ic", + "ative" : "", + "alize" : "al", + "iciti" : "ic", + "ical" : "ic", + "ful" : "", + "ness" : "" + }, + + c = "[^aeiou]", // consonant + v = "[aeiouy]", // vowel + C = c + "[^aeiouy]*", // consonant sequence + V = v + "[aeiou]*", // vowel sequence + + mgr0 = "^(" + C + ")?" + V + C, // [C]VC... is m>0 + meq1 = "^(" + C + ")?" + V + C + "(" + V + ")?$", // [C]VC[V] is m=1 + mgr1 = "^(" + C + ")?" + V + C + V + C, // [C]VCVC... is m>1 + s_v = "^(" + C + ")?" + v; // vowel in stem + + var re_mgr0 = new RegExp(mgr0); + var re_mgr1 = new RegExp(mgr1); + var re_meq1 = new RegExp(meq1); + var re_s_v = new RegExp(s_v); + + var re_1a = /^(.+?)(ss|i)es$/; + var re2_1a = /^(.+?)([^s])s$/; + var re_1b = /^(.+?)eed$/; + var re2_1b = /^(.+?)(ed|ing)$/; + var re_1b_2 = /.$/; + var re2_1b_2 = /(at|bl|iz)$/; + var re3_1b_2 = new RegExp("([^aeiouylsz])\\1$"); + var re4_1b_2 = new RegExp("^" + C + v + "[^aeiouwxy]$"); + + var re_1c = /^(.+?[^aeiou])y$/; + var re_2 = /^(.+?)(ational|tional|enci|anci|izer|bli|alli|entli|eli|ousli|ization|ation|ator|alism|iveness|fulness|ousness|aliti|iviti|biliti|logi)$/; + + var re_3 = /^(.+?)(icate|ative|alize|iciti|ical|ful|ness)$/; + + var re_4 = /^(.+?)(al|ance|ence|er|ic|able|ible|ant|ement|ment|ent|ou|ism|ate|iti|ous|ive|ize)$/; + var re2_4 = /^(.+?)(s|t)(ion)$/; + + var re_5 = /^(.+?)e$/; + var re_5_1 = /ll$/; + var re3_5 = new RegExp("^" + C + v + "[^aeiouwxy]$"); + + var porterStemmer = function porterStemmer(w) { + var stem, + suffix, + firstch, + re, + re2, + re3, + re4; + + if (w.length < 3) { return w; } + + firstch = w.substr(0,1); + if (firstch == "y") { + w = firstch.toUpperCase() + w.substr(1); + } + + // Step 1a + re = re_1a + re2 = re2_1a; + + if (re.test(w)) { w = w.replace(re,"$1$2"); } + else if (re2.test(w)) { w = w.replace(re2,"$1$2"); } + + // Step 1b + re = re_1b; + re2 = re2_1b; + if (re.test(w)) { + var fp = re.exec(w); + re = re_mgr0; + if (re.test(fp[1])) { + re = re_1b_2; + w = w.replace(re,""); + } + } else if (re2.test(w)) { + var fp = re2.exec(w); + stem = fp[1]; + re2 = re_s_v; + if (re2.test(stem)) { + w = stem; + re2 = re2_1b_2; + re3 = re3_1b_2; + re4 = re4_1b_2; + if (re2.test(w)) { w = w + "e"; } + else if (re3.test(w)) { re = re_1b_2; w = w.replace(re,""); } + else if (re4.test(w)) { w = w + "e"; } + } + } + + // Step 1c - replace suffix y or Y by i if preceded by a non-vowel which is not the first letter of the word (so cry -> cri, by -> by, say -> say) + re = re_1c; + if (re.test(w)) { + var fp = re.exec(w); + stem = fp[1]; + w = stem + "i"; + } + + // Step 2 + re = re_2; + if (re.test(w)) { + var fp = re.exec(w); + stem = fp[1]; + suffix = fp[2]; + re = re_mgr0; + if (re.test(stem)) { + w = stem + step2list[suffix]; + } + } + + // Step 3 + re = re_3; + if (re.test(w)) { + var fp = re.exec(w); + stem = fp[1]; + suffix = fp[2]; + re = re_mgr0; + if (re.test(stem)) { + w = stem + step3list[suffix]; + } + } + + // Step 4 + re = re_4; + re2 = re2_4; + if (re.test(w)) { + var fp = re.exec(w); + stem = fp[1]; + re = re_mgr1; + if (re.test(stem)) { + w = stem; + } + } else if (re2.test(w)) { + var fp = re2.exec(w); + stem = fp[1] + fp[2]; + re2 = re_mgr1; + if (re2.test(stem)) { + w = stem; + } + } + + // Step 5 + re = re_5; + if (re.test(w)) { + var fp = re.exec(w); + stem = fp[1]; + re = re_mgr1; + re2 = re_meq1; + re3 = re3_5; + if (re.test(stem) || (re2.test(stem) && !(re3.test(stem)))) { + w = stem; + } + } + + re = re_5_1; + re2 = re_mgr1; + if (re.test(w) && re2.test(w)) { + re = re_1b_2; + w = w.replace(re,""); + } + + // and turn initial Y back to y + + if (firstch == "y") { + w = firstch.toLowerCase() + w.substr(1); + } + + return w; + }; + + return function (token) { + return token.update(porterStemmer); + } +})(); + +lunr.Pipeline.registerFunction(lunr.stemmer, 'stemmer') +/*! + * lunr.stopWordFilter + * Copyright (C) 2017 Oliver Nightingale + */ + +/** + * lunr.generateStopWordFilter builds a stopWordFilter function from the provided + * list of stop words. + * + * The built in lunr.stopWordFilter is built using this generator and can be used + * to generate custom stopWordFilters for applications or non English languages. + * + * @param {Array} token The token to pass through the filter + * @returns {lunr.PipelineFunction} + * @see lunr.Pipeline + * @see lunr.stopWordFilter + */ +lunr.generateStopWordFilter = function (stopWords) { + var words = stopWords.reduce(function (memo, stopWord) { + memo[stopWord] = stopWord + return memo + }, {}) + + return function (token) { + if (token && words[token.toString()] !== token.toString()) return token + } +} + +/** + * lunr.stopWordFilter is an English language stop word list filter, any words + * contained in the list will not be passed through the filter. + * + * This is intended to be used in the Pipeline. If the token does not pass the + * filter then undefined will be returned. + * + * @implements {lunr.PipelineFunction} + * @params {lunr.Token} token - A token to check for being a stop word. + * @returns {lunr.Token} + * @see {@link lunr.Pipeline} + */ +lunr.stopWordFilter = lunr.generateStopWordFilter([ + 'a', + 'able', + 'about', + 'across', + 'after', + 'all', + 'almost', + 'also', + 'am', + 'among', + 'an', + 'and', + 'any', + 'are', + 'as', + 'at', + 'be', + 'because', + 'been', + 'but', + 'by', + 'can', + 'cannot', + 'could', + 'dear', + 'did', + 'do', + 'does', + 'either', + 'else', + 'ever', + 'every', + 'for', + 'from', + 'get', + 'got', + 'had', + 'has', + 'have', + 'he', + 'her', + 'hers', + 'him', + 'his', + 'how', + 'however', + 'i', + 'if', + 'in', + 'into', + 'is', + 'it', + 'its', + 'just', + 'least', + 'let', + 'like', + 'likely', + 'may', + 'me', + 'might', + 'most', + 'must', + 'my', + 'neither', + 'no', + 'nor', + 'not', + 'of', + 'off', + 'often', + 'on', + 'only', + 'or', + 'other', + 'our', + 'own', + 'rather', + 'said', + 'say', + 'says', + 'she', + 'should', + 'since', + 'so', + 'some', + 'than', + 'that', + 'the', + 'their', + 'them', + 'then', + 'there', + 'these', + 'they', + 'this', + 'tis', + 'to', + 'too', + 'twas', + 'us', + 'wants', + 'was', + 'we', + 'were', + 'what', + 'when', + 'where', + 'which', + 'while', + 'who', + 'whom', + 'why', + 'will', + 'with', + 'would', + 'yet', + 'you', + 'your' +]) + +lunr.Pipeline.registerFunction(lunr.stopWordFilter, 'stopWordFilter') +/*! + * lunr.trimmer + * Copyright (C) 2017 Oliver Nightingale + */ + +/** + * lunr.trimmer is a pipeline function for trimming non word + * characters from the beginning and end of tokens before they + * enter the index. + * + * This implementation may not work correctly for non latin + * characters and should either be removed or adapted for use + * with languages with non-latin characters. + * + * @static + * @implements {lunr.PipelineFunction} + * @param {lunr.Token} token The token to pass through the filter + * @returns {lunr.Token} + * @see lunr.Pipeline + */ +lunr.trimmer = function (token) { + return token.update(function (s) { + return s.replace(/^\W+/, '').replace(/\W+$/, '') + }) +} + +lunr.Pipeline.registerFunction(lunr.trimmer, 'trimmer') +/*! + * lunr.TokenSet + * Copyright (C) 2017 Oliver Nightingale + */ + +/** + * A token set is used to store the unique list of all tokens + * within an index. Token sets are also used to represent an + * incoming query to the index, this query token set and index + * token set are then intersected to find which tokens to look + * up in the inverted index. + * + * A token set can hold multiple tokens, as in the case of the + * index token set, or it can hold a single token as in the + * case of a simple query token set. + * + * Additionally token sets are used to perform wildcard matching. + * Leading, contained and trailing wildcards are supported, and + * from this edit distance matching can also be provided. + * + * Token sets are implemented as a minimal finite state automata, + * where both common prefixes and suffixes are shared between tokens. + * This helps to reduce the space used for storing the token set. + * + * @constructor + */ +lunr.TokenSet = function () { + this.final = false + this.edges = {} + this.id = lunr.TokenSet._nextId + lunr.TokenSet._nextId += 1 +} + +/** + * Keeps track of the next, auto increment, identifier to assign + * to a new tokenSet. + * + * TokenSets require a unique identifier to be correctly minimised. + * + * @private + */ +lunr.TokenSet._nextId = 1 + +/** + * Creates a TokenSet instance from the given sorted array of words. + * + * @param {String[]} arr - A sorted array of strings to create the set from. + * @returns {lunr.TokenSet} + * @throws Will throw an error if the input array is not sorted. + */ +lunr.TokenSet.fromArray = function (arr) { + var builder = new lunr.TokenSet.Builder + + for (var i = 0, len = arr.length; i < len; i++) { + builder.insert(arr[i]) + } + + builder.finish() + return builder.root +} + +/** + * Creates a token set from a query clause. + * + * @private + * @param {Object} clause - A single clause from lunr.Query. + * @param {string} clause.term - The query clause term. + * @param {number} [clause.editDistance] - The optional edit distance for the term. + * @returns {lunr.TokenSet} + */ +lunr.TokenSet.fromClause = function (clause) { + if ('editDistance' in clause) { + return lunr.TokenSet.fromFuzzyString(clause.term, clause.editDistance) + } else { + return lunr.TokenSet.fromString(clause.term) + } +} + +/** + * Creates a token set representing a single string with a specified + * edit distance. + * + * Insertions, deletions, substitutions and transpositions are each + * treated as an edit distance of 1. + * + * Increasing the allowed edit distance will have a dramatic impact + * on the performance of both creating and intersecting these TokenSets. + * It is advised to keep the edit distance less than 3. + * + * @param {string} str - The string to create the token set from. + * @param {number} editDistance - The allowed edit distance to match. + * @returns {lunr.Vector} + */ +lunr.TokenSet.fromFuzzyString = function (str, editDistance) { + var root = new lunr.TokenSet + + var stack = [{ + node: root, + editsRemaining: editDistance, + str: str + }] + + while (stack.length) { + var frame = stack.pop() + + // no edit + if (frame.str.length > 0) { + var char = frame.str.charAt(0), + noEditNode + + if (char in frame.node.edges) { + noEditNode = frame.node.edges[char] + } else { + noEditNode = new lunr.TokenSet + frame.node.edges[char] = noEditNode + } + + if (frame.str.length == 1) { + noEditNode.final = true + } else { + stack.push({ + node: noEditNode, + editsRemaining: frame.editsRemaining, + str: frame.str.slice(1) + }) + } + } + + // deletion + // can only do a deletion if we have enough edits remaining + // and if there are characters left to delete in the string + if (frame.editsRemaining > 0 && frame.str.length > 1) { + var char = frame.str.charAt(1), + deletionNode + + if (char in frame.node.edges) { + deletionNode = frame.node.edges[char] + } else { + deletionNode = new lunr.TokenSet + frame.node.edges[char] = deletionNode + } + + if (frame.str.length <= 2) { + deletionNode.final = true + } else { + stack.push({ + node: deletionNode, + editsRemaining: frame.editsRemaining - 1, + str: frame.str.slice(2) + }) + } + } + + // deletion + // just removing the last character from the str + if (frame.editsRemaining > 0 && frame.str.length == 1) { + frame.node.final = true + } + + // substitution + // can only do a substitution if we have enough edits remaining + // and if there are characters left to substitute + if (frame.editsRemaining > 0 && frame.str.length >= 1) { + if ("*" in frame.node.edges) { + var substitutionNode = frame.node.edges["*"] + } else { + var substitutionNode = new lunr.TokenSet + frame.node.edges["*"] = substitutionNode + } + + if (frame.str.length == 1) { + substitutionNode.final = true + } else { + stack.push({ + node: substitutionNode, + editsRemaining: frame.editsRemaining - 1, + str: frame.str.slice(1) + }) + } + } + + // insertion + // can only do insertion if there are edits remaining + if (frame.editsRemaining > 0) { + if ("*" in frame.node.edges) { + var insertionNode = frame.node.edges["*"] + } else { + var insertionNode = new lunr.TokenSet + frame.node.edges["*"] = insertionNode + } + + if (frame.str.length == 0) { + insertionNode.final = true + } else { + stack.push({ + node: insertionNode, + editsRemaining: frame.editsRemaining - 1, + str: frame.str + }) + } + } + + // transposition + // can only do a transposition if there are edits remaining + // and there are enough characters to transpose + if (frame.editsRemaining > 0 && frame.str.length > 1) { + var charA = frame.str.charAt(0), + charB = frame.str.charAt(1), + transposeNode + + if (charB in frame.node.edges) { + transposeNode = frame.node.edges[charB] + } else { + transposeNode = new lunr.TokenSet + frame.node.edges[charB] = transposeNode + } + + if (frame.str.length == 1) { + transposeNode.final = true + } else { + stack.push({ + node: transposeNode, + editsRemaining: frame.editsRemaining - 1, + str: charA + frame.str.slice(2) + }) + } + } + } + + return root +} + +/** + * Creates a TokenSet from a string. + * + * The string may contain one or more wildcard characters (*) + * that will allow wildcard matching when intersecting with + * another TokenSet. + * + * @param {string} str - The string to create a TokenSet from. + * @returns {lunr.TokenSet} + */ +lunr.TokenSet.fromString = function (str) { + var node = new lunr.TokenSet, + root = node, + wildcardFound = false + + /* + * Iterates through all characters within the passed string + * appending a node for each character. + * + * As soon as a wildcard character is found then a self + * referencing edge is introduced to continually match + * any number of any characters. + */ + for (var i = 0, len = str.length; i < len; i++) { + var char = str[i], + final = (i == len - 1) + + if (char == "*") { + wildcardFound = true + node.edges[char] = node + node.final = final + + } else { + var next = new lunr.TokenSet + next.final = final + + node.edges[char] = next + node = next + + // TODO: is this needed anymore? + if (wildcardFound) { + node.edges["*"] = root + } + } + } + + return root +} + +/** + * Converts this TokenSet into an array of strings + * contained within the TokenSet. + * + * @returns {string[]} + */ +lunr.TokenSet.prototype.toArray = function () { + var words = [] + + var stack = [{ + prefix: "", + node: this + }] + + while (stack.length) { + var frame = stack.pop(), + edges = Object.keys(frame.node.edges), + len = edges.length + + if (frame.node.final) { + words.push(frame.prefix) + } + + for (var i = 0; i < len; i++) { + var edge = edges[i] + + stack.push({ + prefix: frame.prefix.concat(edge), + node: frame.node.edges[edge] + }) + } + } + + return words +} + +/** + * Generates a string representation of a TokenSet. + * + * This is intended to allow TokenSets to be used as keys + * in objects, largely to aid the construction and minimisation + * of a TokenSet. As such it is not designed to be a human + * friendly representation of the TokenSet. + * + * @returns {string} + */ +lunr.TokenSet.prototype.toString = function () { + // NOTE: Using Object.keys here as this.edges is very likely + // to enter 'hash-mode' with many keys being added + // + // avoiding a for-in loop here as it leads to the function + // being de-optimised (at least in V8). From some simple + // benchmarks the performance is comparable, but allowing + // V8 to optimize may mean easy performance wins in the future. + + if (this._str) { + return this._str + } + + var str = this.final ? '1' : '0', + labels = Object.keys(this.edges).sort(), + len = labels.length + + for (var i = 0; i < len; i++) { + var label = labels[i], + node = this.edges[label] + + str = str + label + node.id + } + + return str +} + +/** + * Returns a new TokenSet that is the intersection of + * this TokenSet and the passed TokenSet. + * + * This intersection will take into account any wildcards + * contained within the TokenSet. + * + * @param {lunr.TokenSet} b - An other TokenSet to intersect with. + * @returns {lunr.TokenSet} + */ +lunr.TokenSet.prototype.intersect = function (b) { + var output = new lunr.TokenSet, + frame = undefined + + var stack = [{ + qNode: b, + output: output, + node: this + }] + + while (stack.length) { + frame = stack.pop() + + // NOTE: As with the #toString method, we are using + // Object.keys and a for loop instead of a for-in loop + // as both of these objects enter 'hash' mode, causing + // the function to be de-optimised in V8 + var qEdges = Object.keys(frame.qNode.edges), + qLen = qEdges.length, + nEdges = Object.keys(frame.node.edges), + nLen = nEdges.length + + for (var q = 0; q < qLen; q++) { + var qEdge = qEdges[q] + + for (var n = 0; n < nLen; n++) { + var nEdge = nEdges[n] + + if (nEdge == qEdge || qEdge == '*') { + var node = frame.node.edges[nEdge], + qNode = frame.qNode.edges[qEdge], + final = node.final && qNode.final, + next = undefined + + if (nEdge in frame.output.edges) { + // an edge already exists for this character + // no need to create a new node, just set the finality + // bit unless this node is already final + next = frame.output.edges[nEdge] + next.final = next.final || final + + } else { + // no edge exists yet, must create one + // set the finality bit and insert it + // into the output + next = new lunr.TokenSet + next.final = final + frame.output.edges[nEdge] = next + } + + stack.push({ + qNode: qNode, + output: next, + node: node + }) + } + } + } + } + + return output +} +lunr.TokenSet.Builder = function () { + this.previousWord = "" + this.root = new lunr.TokenSet + this.uncheckedNodes = [] + this.minimizedNodes = {} +} + +lunr.TokenSet.Builder.prototype.insert = function (word) { + var node, + commonPrefix = 0 + + if (word < this.previousWord) { + throw new Error ("Out of order word insertion") + } + + for (var i = 0; i < word.length && i < this.previousWord.length; i++) { + if (word[i] != this.previousWord[i]) break + commonPrefix++ + } + + this.minimize(commonPrefix) + + if (this.uncheckedNodes.length == 0) { + node = this.root + } else { + node = this.uncheckedNodes[this.uncheckedNodes.length - 1].child + } + + for (var i = commonPrefix; i < word.length; i++) { + var nextNode = new lunr.TokenSet, + char = word[i] + + node.edges[char] = nextNode + + this.uncheckedNodes.push({ + parent: node, + char: char, + child: nextNode + }) + + node = nextNode + } + + node.final = true + this.previousWord = word +} + +lunr.TokenSet.Builder.prototype.finish = function () { + this.minimize(0) +} + +lunr.TokenSet.Builder.prototype.minimize = function (downTo) { + for (var i = this.uncheckedNodes.length - 1; i >= downTo; i--) { + var node = this.uncheckedNodes[i], + childKey = node.child.toString() + + if (childKey in this.minimizedNodes) { + node.parent.edges[node.char] = this.minimizedNodes[childKey] + } else { + // Cache the key for this node since + // we know it can't change anymore + node.child._str = childKey + + this.minimizedNodes[childKey] = node.child + } + + this.uncheckedNodes.pop() + } +} +/*! + * lunr.Index + * Copyright (C) 2017 Oliver Nightingale + */ + +/** + * An index contains the built index of all documents and provides a query interface + * to the index. + * + * Usually instances of lunr.Index will not be created using this constructor, instead + * lunr.Builder should be used to construct new indexes, or lunr.Index.load should be + * used to load previously built and serialized indexes. + * + * @constructor + * @param {Object} attrs - The attributes of the built search index. + * @param {Object} attrs.invertedIndex - An index of term/field to document reference. + * @param {Object} attrs.documentVectors - Document vectors keyed by document reference. + * @param {lunr.TokenSet} attrs.tokenSet - An set of all corpus tokens. + * @param {string[]} attrs.fields - The names of indexed document fields. + * @param {lunr.Pipeline} attrs.pipeline - The pipeline to use for search terms. + */ +lunr.Index = function (attrs) { + this.invertedIndex = attrs.invertedIndex + this.fieldVectors = attrs.fieldVectors + this.tokenSet = attrs.tokenSet + this.fields = attrs.fields + this.pipeline = attrs.pipeline +} + +/** + * A result contains details of a document matching a search query. + * @typedef {Object} lunr.Index~Result + * @property {string} ref - The reference of the document this result represents. + * @property {number} score - A number between 0 and 1 representing how similar this document is to the query. + * @property {lunr.MatchData} matchData - Contains metadata about this match including which term(s) caused the match. + */ + +/** + * Although lunr provides the ability to create queries using lunr.Query, it also provides a simple + * query language which itself is parsed into an instance of lunr.Query. + * + * For programmatically building queries it is advised to directly use lunr.Query, the query language + * is best used for human entered text rather than program generated text. + * + * At its simplest queries can just be a single term, e.g. `hello`, multiple terms are also supported + * and will be combined with OR, e.g `hello world` will match documents that contain either 'hello' + * or 'world', though those that contain both will rank higher in the results. + * + * Wildcards can be included in terms to match one or more unspecified characters, these wildcards can + * be inserted anywhere within the term, and more than one wildcard can exist in a single term. Adding + * wildcards will increase the number of documents that will be found but can also have a negative + * impact on query performance, especially with wildcards at the beginning of a term. + * + * Terms can be restricted to specific fields, e.g. `title:hello`, only documents with the term + * hello in the title field will match this query. Using a field not present in the index will lead + * to an error being thrown. + * + * Modifiers can also be added to terms, lunr supports edit distance and boost modifiers on terms. A term + * boost will make documents matching that term score higher, e.g. `foo^5`. Edit distance is also supported + * to provide fuzzy matching, e.g. 'hello~2' will match documents with hello with an edit distance of 2. + * Avoid large values for edit distance to improve query performance. + * + * To escape special characters the backslash character '\' can be used, this allows searches to include + * characters that would normally be considered modifiers, e.g. `foo\~2` will search for a term "foo~2" instead + * of attempting to apply a boost of 2 to the search term "foo". + * + * @typedef {string} lunr.Index~QueryString + * @example Simple single term query + * hello + * @example Multiple term query + * hello world + * @example term scoped to a field + * title:hello + * @example term with a boost of 10 + * hello^10 + * @example term with an edit distance of 2 + * hello~2 + */ + +/** + * Performs a search against the index using lunr query syntax. + * + * Results will be returned sorted by their score, the most relevant results + * will be returned first. + * + * For more programmatic querying use lunr.Index#query. + * + * @param {lunr.Index~QueryString} queryString - A string containing a lunr query. + * @throws {lunr.QueryParseError} If the passed query string cannot be parsed. + * @returns {lunr.Index~Result[]} + */ +lunr.Index.prototype.search = function (queryString) { + return this.query(function (query) { + var parser = new lunr.QueryParser(queryString, query) + parser.parse() + }) +} + +/** + * A query builder callback provides a query object to be used to express + * the query to perform on the index. + * + * @callback lunr.Index~queryBuilder + * @param {lunr.Query} query - The query object to build up. + * @this lunr.Query + */ + +/** + * Performs a query against the index using the yielded lunr.Query object. + * + * If performing programmatic queries against the index, this method is preferred + * over lunr.Index#search so as to avoid the additional query parsing overhead. + * + * A query object is yielded to the supplied function which should be used to + * express the query to be run against the index. + * + * Note that although this function takes a callback parameter it is _not_ an + * asynchronous operation, the callback is just yielded a query object to be + * customized. + * + * @param {lunr.Index~queryBuilder} fn - A function that is used to build the query. + * @returns {lunr.Index~Result[]} + */ +lunr.Index.prototype.query = function (fn) { + // for each query clause + // * process terms + // * expand terms from token set + // * find matching documents and metadata + // * get document vectors + // * score documents + + var query = new lunr.Query(this.fields), + matchingFields = Object.create(null), + queryVectors = Object.create(null), + termFieldCache = Object.create(null) + + fn.call(query, query) + + for (var i = 0; i < query.clauses.length; i++) { + /* + * Unless the pipeline has been disabled for this term, which is + * the case for terms with wildcards, we need to pass the clause + * term through the search pipeline. A pipeline returns an array + * of processed terms. Pipeline functions may expand the passed + * term, which means we may end up performing multiple index lookups + * for a single query term. + */ + var clause = query.clauses[i], + terms = null + + if (clause.usePipeline) { + terms = this.pipeline.runString(clause.term) + } else { + terms = [clause.term] + } + + for (var m = 0; m < terms.length; m++) { + var term = terms[m] + + /* + * Each term returned from the pipeline needs to use the same query + * clause object, e.g. the same boost and or edit distance. The + * simplest way to do this is to re-use the clause object but mutate + * its term property. + */ + clause.term = term + + /* + * From the term in the clause we create a token set which will then + * be used to intersect the indexes token set to get a list of terms + * to lookup in the inverted index + */ + var termTokenSet = lunr.TokenSet.fromClause(clause), + expandedTerms = this.tokenSet.intersect(termTokenSet).toArray() + + for (var j = 0; j < expandedTerms.length; j++) { + /* + * For each term get the posting and termIndex, this is required for + * building the query vector. + */ + var expandedTerm = expandedTerms[j], + posting = this.invertedIndex[expandedTerm], + termIndex = posting._index + + for (var k = 0; k < clause.fields.length; k++) { + /* + * For each field that this query term is scoped by (by default + * all fields are in scope) we need to get all the document refs + * that have this term in that field. + * + * The posting is the entry in the invertedIndex for the matching + * term from above. + */ + var field = clause.fields[k], + fieldPosting = posting[field], + matchingDocumentRefs = Object.keys(fieldPosting), + termField = expandedTerm + "/" + field + + /* + * To support field level boosts a query vector is created per + * field. This vector is populated using the termIndex found for + * the term and a unit value with the appropriate boost applied. + * + * If the query vector for this field does not exist yet it needs + * to be created. + */ + if (queryVectors[field] === undefined) { + queryVectors[field] = new lunr.Vector + } + + /* + * Using upsert because there could already be an entry in the vector + * for the term we are working with. In that case we just add the scores + * together. + */ + queryVectors[field].upsert(termIndex, 1 * clause.boost, function (a, b) { return a + b }) + + /** + * If we've already seen this term, field combo then we've already collected + * the matching documents and metadata, no need to go through all that again + */ + if (termFieldCache[termField]) { + continue + } + + for (var l = 0; l < matchingDocumentRefs.length; l++) { + /* + * All metadata for this term/field/document triple + * are then extracted and collected into an instance + * of lunr.MatchData ready to be returned in the query + * results + */ + var matchingDocumentRef = matchingDocumentRefs[l], + matchingFieldRef = new lunr.FieldRef (matchingDocumentRef, field), + metadata = fieldPosting[matchingDocumentRef], + fieldMatch + + if ((fieldMatch = matchingFields[matchingFieldRef]) === undefined) { + matchingFields[matchingFieldRef] = new lunr.MatchData (expandedTerm, field, metadata) + } else { + fieldMatch.add(expandedTerm, field, metadata) + } + + } + + termFieldCache[termField] = true + } + } + } + } + + var matchingFieldRefs = Object.keys(matchingFields), + results = [], + matches = Object.create(null) + + for (var i = 0; i < matchingFieldRefs.length; i++) { + /* + * Currently we have document fields that match the query, but we + * need to return documents. The matchData and scores are combined + * from multiple fields belonging to the same document. + * + * Scores are calculated by field, using the query vectors created + * above, and combined into a final document score using addition. + */ + var fieldRef = lunr.FieldRef.fromString(matchingFieldRefs[i]), + docRef = fieldRef.docRef, + fieldVector = this.fieldVectors[fieldRef], + score = queryVectors[fieldRef.fieldName].similarity(fieldVector), + docMatch + + if ((docMatch = matches[docRef]) !== undefined) { + docMatch.score += score + docMatch.matchData.combine(matchingFields[fieldRef]) + } else { + var match = { + ref: docRef, + score: score, + matchData: matchingFields[fieldRef] + } + matches[docRef] = match + results.push(match) + } + } + + /* + * Sort the results objects by score, highest first. + */ + return results.sort(function (a, b) { + return b.score - a.score + }) +} + +/** + * Prepares the index for JSON serialization. + * + * The schema for this JSON blob will be described in a + * separate JSON schema file. + * + * @returns {Object} + */ +lunr.Index.prototype.toJSON = function () { + var invertedIndex = Object.keys(this.invertedIndex) + .sort() + .map(function (term) { + return [term, this.invertedIndex[term]] + }, this) + + var fieldVectors = Object.keys(this.fieldVectors) + .map(function (ref) { + return [ref, this.fieldVectors[ref].toJSON()] + }, this) + + return { + version: lunr.version, + fields: this.fields, + fieldVectors: fieldVectors, + invertedIndex: invertedIndex, + pipeline: this.pipeline.toJSON() + } +} + +/** + * Loads a previously serialized lunr.Index + * + * @param {Object} serializedIndex - A previously serialized lunr.Index + * @returns {lunr.Index} + */ +lunr.Index.load = function (serializedIndex) { + var attrs = {}, + fieldVectors = {}, + serializedVectors = serializedIndex.fieldVectors, + invertedIndex = {}, + serializedInvertedIndex = serializedIndex.invertedIndex, + tokenSetBuilder = new lunr.TokenSet.Builder, + pipeline = lunr.Pipeline.load(serializedIndex.pipeline) + + if (serializedIndex.version != lunr.version) { + lunr.utils.warn("Version mismatch when loading serialised index. Current version of lunr '" + lunr.version + "' does not match serialized index '" + serializedIndex.version + "'") + } + + for (var i = 0; i < serializedVectors.length; i++) { + var tuple = serializedVectors[i], + ref = tuple[0], + elements = tuple[1] + + fieldVectors[ref] = new lunr.Vector(elements) + } + + for (var i = 0; i < serializedInvertedIndex.length; i++) { + var tuple = serializedInvertedIndex[i], + term = tuple[0], + posting = tuple[1] + + tokenSetBuilder.insert(term) + invertedIndex[term] = posting + } + + tokenSetBuilder.finish() + + attrs.fields = serializedIndex.fields + + attrs.fieldVectors = fieldVectors + attrs.invertedIndex = invertedIndex + attrs.tokenSet = tokenSetBuilder.root + attrs.pipeline = pipeline + + return new lunr.Index(attrs) +} +/*! + * lunr.Builder + * Copyright (C) 2017 Oliver Nightingale + */ + +/** + * lunr.Builder performs indexing on a set of documents and + * returns instances of lunr.Index ready for querying. + * + * All configuration of the index is done via the builder, the + * fields to index, the document reference, the text processing + * pipeline and document scoring parameters are all set on the + * builder before indexing. + * + * @constructor + * @property {string} _ref - Internal reference to the document reference field. + * @property {string[]} _fields - Internal reference to the document fields to index. + * @property {object} invertedIndex - The inverted index maps terms to document fields. + * @property {object} documentTermFrequencies - Keeps track of document term frequencies. + * @property {object} documentLengths - Keeps track of the length of documents added to the index. + * @property {lunr.tokenizer} tokenizer - Function for splitting strings into tokens for indexing. + * @property {lunr.Pipeline} pipeline - The pipeline performs text processing on tokens before indexing. + * @property {lunr.Pipeline} searchPipeline - A pipeline for processing search terms before querying the index. + * @property {number} documentCount - Keeps track of the total number of documents indexed. + * @property {number} _b - A parameter to control field length normalization, setting this to 0 disabled normalization, 1 fully normalizes field lengths, the default value is 0.75. + * @property {number} _k1 - A parameter to control how quickly an increase in term frequency results in term frequency saturation, the default value is 1.2. + * @property {number} termIndex - A counter incremented for each unique term, used to identify a terms position in the vector space. + * @property {array} metadataWhitelist - A list of metadata keys that have been whitelisted for entry in the index. + */ +lunr.Builder = function () { + this._ref = "id" + this._fields = [] + this.invertedIndex = Object.create(null) + this.fieldTermFrequencies = {} + this.fieldLengths = {} + this.tokenizer = lunr.tokenizer + this.pipeline = new lunr.Pipeline + this.searchPipeline = new lunr.Pipeline + this.documentCount = 0 + this._b = 0.75 + this._k1 = 1.2 + this.termIndex = 0 + this.metadataWhitelist = [] +} + +/** + * Sets the document field used as the document reference. Every document must have this field. + * The type of this field in the document should be a string, if it is not a string it will be + * coerced into a string by calling toString. + * + * The default ref is 'id'. + * + * The ref should _not_ be changed during indexing, it should be set before any documents are + * added to the index. Changing it during indexing can lead to inconsistent results. + * + * @param {string} ref - The name of the reference field in the document. + */ +lunr.Builder.prototype.ref = function (ref) { + this._ref = ref +} + +/** + * Adds a field to the list of document fields that will be indexed. Every document being + * indexed should have this field. Null values for this field in indexed documents will + * not cause errors but will limit the chance of that document being retrieved by searches. + * + * All fields should be added before adding documents to the index. Adding fields after + * a document has been indexed will have no effect on already indexed documents. + * + * @param {string} field - The name of a field to index in all documents. + */ +lunr.Builder.prototype.field = function (field) { + this._fields.push(field) +} + +/** + * A parameter to tune the amount of field length normalisation that is applied when + * calculating relevance scores. A value of 0 will completely disable any normalisation + * and a value of 1 will fully normalise field lengths. The default is 0.75. Values of b + * will be clamped to the range 0 - 1. + * + * @param {number} number - The value to set for this tuning parameter. + */ +lunr.Builder.prototype.b = function (number) { + if (number < 0) { + this._b = 0 + } else if (number > 1) { + this._b = 1 + } else { + this._b = number + } +} + +/** + * A parameter that controls the speed at which a rise in term frequency results in term + * frequency saturation. The default value is 1.2. Setting this to a higher value will give + * slower saturation levels, a lower value will result in quicker saturation. + * + * @param {number} number - The value to set for this tuning parameter. + */ +lunr.Builder.prototype.k1 = function (number) { + this._k1 = number +} + +/** + * Adds a document to the index. + * + * Before adding fields to the index the index should have been fully setup, with the document + * ref and all fields to index already having been specified. + * + * The document must have a field name as specified by the ref (by default this is 'id') and + * it should have all fields defined for indexing, though null or undefined values will not + * cause errors. + * + * @param {object} doc - The document to add to the index. + */ +lunr.Builder.prototype.add = function (doc) { + var docRef = doc[this._ref] + + this.documentCount += 1 + + for (var i = 0; i < this._fields.length; i++) { + var fieldName = this._fields[i], + field = doc[fieldName], + tokens = this.tokenizer(field), + terms = this.pipeline.run(tokens), + fieldRef = new lunr.FieldRef (docRef, fieldName), + fieldTerms = Object.create(null) + + this.fieldTermFrequencies[fieldRef] = fieldTerms + this.fieldLengths[fieldRef] = 0 + + // store the length of this field for this document + this.fieldLengths[fieldRef] += terms.length + + // calculate term frequencies for this field + for (var j = 0; j < terms.length; j++) { + var term = terms[j] + + if (fieldTerms[term] == undefined) { + fieldTerms[term] = 0 + } + + fieldTerms[term] += 1 + + // add to inverted index + // create an initial posting if one doesn't exist + if (this.invertedIndex[term] == undefined) { + var posting = Object.create(null) + posting["_index"] = this.termIndex + this.termIndex += 1 + + for (var k = 0; k < this._fields.length; k++) { + posting[this._fields[k]] = Object.create(null) + } + + this.invertedIndex[term] = posting + } + + // add an entry for this term/fieldName/docRef to the invertedIndex + if (this.invertedIndex[term][fieldName][docRef] == undefined) { + this.invertedIndex[term][fieldName][docRef] = Object.create(null) + } + + // store all whitelisted metadata about this token in the + // inverted index + for (var l = 0; l < this.metadataWhitelist.length; l++) { + var metadataKey = this.metadataWhitelist[l], + metadata = term.metadata[metadataKey] + + if (this.invertedIndex[term][fieldName][docRef][metadataKey] == undefined) { + this.invertedIndex[term][fieldName][docRef][metadataKey] = [] + } + + this.invertedIndex[term][fieldName][docRef][metadataKey].push(metadata) + } + } + + } +} + +/** + * Calculates the average document length for this index + * + * @private + */ +lunr.Builder.prototype.calculateAverageFieldLengths = function () { + + var fieldRefs = Object.keys(this.fieldLengths), + numberOfFields = fieldRefs.length, + accumulator = {}, + documentsWithField = {} + + for (var i = 0; i < numberOfFields; i++) { + var fieldRef = lunr.FieldRef.fromString(fieldRefs[i]), + field = fieldRef.fieldName + + documentsWithField[field] || (documentsWithField[field] = 0) + documentsWithField[field] += 1 + + accumulator[field] || (accumulator[field] = 0) + accumulator[field] += this.fieldLengths[fieldRef] + } + + for (var i = 0; i < this._fields.length; i++) { + var field = this._fields[i] + accumulator[field] = accumulator[field] / documentsWithField[field] + } + + this.averageFieldLength = accumulator +} + +/** + * Builds a vector space model of every document using lunr.Vector + * + * @private + */ +lunr.Builder.prototype.createFieldVectors = function () { + var fieldVectors = {}, + fieldRefs = Object.keys(this.fieldTermFrequencies), + fieldRefsLength = fieldRefs.length, + termIdfCache = Object.create(null) + + for (var i = 0; i < fieldRefsLength; i++) { + var fieldRef = lunr.FieldRef.fromString(fieldRefs[i]), + field = fieldRef.fieldName, + fieldLength = this.fieldLengths[fieldRef], + fieldVector = new lunr.Vector, + termFrequencies = this.fieldTermFrequencies[fieldRef], + terms = Object.keys(termFrequencies), + termsLength = terms.length + + for (var j = 0; j < termsLength; j++) { + var term = terms[j], + tf = termFrequencies[term], + termIndex = this.invertedIndex[term]._index, + idf, score, scoreWithPrecision + + if (termIdfCache[term] === undefined) { + idf = lunr.idf(this.invertedIndex[term], this.documentCount) + termIdfCache[term] = idf + } else { + idf = termIdfCache[term] + } + + score = idf * ((this._k1 + 1) * tf) / (this._k1 * (1 - this._b + this._b * (fieldLength / this.averageFieldLength[field])) + tf) + scoreWithPrecision = Math.round(score * 1000) / 1000 + // Converts 1.23456789 to 1.234. + // Reducing the precision so that the vectors take up less + // space when serialised. Doing it now so that they behave + // the same before and after serialisation. Also, this is + // the fastest approach to reducing a number's precision in + // JavaScript. + + fieldVector.insert(termIndex, scoreWithPrecision) + } + + fieldVectors[fieldRef] = fieldVector + } + + this.fieldVectors = fieldVectors +} + +/** + * Creates a token set of all tokens in the index using lunr.TokenSet + * + * @private + */ +lunr.Builder.prototype.createTokenSet = function () { + this.tokenSet = lunr.TokenSet.fromArray( + Object.keys(this.invertedIndex).sort() + ) +} + +/** + * Builds the index, creating an instance of lunr.Index. + * + * This completes the indexing process and should only be called + * once all documents have been added to the index. + * + * @returns {lunr.Index} + */ +lunr.Builder.prototype.build = function () { + this.calculateAverageFieldLengths() + this.createFieldVectors() + this.createTokenSet() + + return new lunr.Index({ + invertedIndex: this.invertedIndex, + fieldVectors: this.fieldVectors, + tokenSet: this.tokenSet, + fields: this._fields, + pipeline: this.searchPipeline + }) +} + +/** + * Applies a plugin to the index builder. + * + * A plugin is a function that is called with the index builder as its context. + * Plugins can be used to customise or extend the behaviour of the index + * in some way. A plugin is just a function, that encapsulated the custom + * behaviour that should be applied when building the index. + * + * The plugin function will be called with the index builder as its argument, additional + * arguments can also be passed when calling use. The function will be called + * with the index builder as its context. + * + * @param {Function} plugin The plugin to apply. + */ +lunr.Builder.prototype.use = function (fn) { + var args = Array.prototype.slice.call(arguments, 1) + args.unshift(this) + fn.apply(this, args) +} +/** + * Contains and collects metadata about a matching document. + * A single instance of lunr.MatchData is returned as part of every + * lunr.Index~Result. + * + * @constructor + * @param {string} term - The term this match data is associated with + * @param {string} field - The field in which the term was found + * @param {object} metadata - The metadata recorded about this term in this field + * @property {object} metadata - A cloned collection of metadata associated with this document. + * @see {@link lunr.Index~Result} + */ +lunr.MatchData = function (term, field, metadata) { + var clonedMetadata = Object.create(null), + metadataKeys = Object.keys(metadata) + + // Cloning the metadata to prevent the original + // being mutated during match data combination. + // Metadata is kept in an array within the inverted + // index so cloning the data can be done with + // Array#slice + for (var i = 0; i < metadataKeys.length; i++) { + var key = metadataKeys[i] + clonedMetadata[key] = metadata[key].slice() + } + + this.metadata = Object.create(null) + this.metadata[term] = Object.create(null) + this.metadata[term][field] = clonedMetadata +} + +/** + * An instance of lunr.MatchData will be created for every term that matches a + * document. However only one instance is required in a lunr.Index~Result. This + * method combines metadata from another instance of lunr.MatchData with this + * objects metadata. + * + * @param {lunr.MatchData} otherMatchData - Another instance of match data to merge with this one. + * @see {@link lunr.Index~Result} + */ +lunr.MatchData.prototype.combine = function (otherMatchData) { + var terms = Object.keys(otherMatchData.metadata) + + for (var i = 0; i < terms.length; i++) { + var term = terms[i], + fields = Object.keys(otherMatchData.metadata[term]) + + if (this.metadata[term] == undefined) { + this.metadata[term] = Object.create(null) + } + + for (var j = 0; j < fields.length; j++) { + var field = fields[j], + keys = Object.keys(otherMatchData.metadata[term][field]) + + if (this.metadata[term][field] == undefined) { + this.metadata[term][field] = Object.create(null) + } + + for (var k = 0; k < keys.length; k++) { + var key = keys[k] + + if (this.metadata[term][field][key] == undefined) { + this.metadata[term][field][key] = otherMatchData.metadata[term][field][key] + } else { + this.metadata[term][field][key] = this.metadata[term][field][key].concat(otherMatchData.metadata[term][field][key]) + } + + } + } + } +} + +/** + * Add metadata for a term/field pair to this instance of match data. + * + * @param {string} term - The term this match data is associated with + * @param {string} field - The field in which the term was found + * @param {object} metadata - The metadata recorded about this term in this field + */ +lunr.MatchData.prototype.add = function (term, field, metadata) { + if (!(term in this.metadata)) { + this.metadata[term] = Object.create(null) + this.metadata[term][field] = metadata + return + } + + if (!(field in this.metadata[term])) { + this.metadata[term][field] = metadata + return + } + + var metadataKeys = Object.keys(metadata) + + for (var i = 0; i < metadataKeys.length; i++) { + var key = metadataKeys[i] + + if (key in this.metadata[term][field]) { + this.metadata[term][field][key] = this.metadata[term][field][key].concat(metadata[key]) + } else { + this.metadata[term][field][key] = metadata[key] + } + } +} +/** + * A lunr.Query provides a programmatic way of defining queries to be performed + * against a {@link lunr.Index}. + * + * Prefer constructing a lunr.Query using the {@link lunr.Index#query} method + * so the query object is pre-initialized with the right index fields. + * + * @constructor + * @property {lunr.Query~Clause[]} clauses - An array of query clauses. + * @property {string[]} allFields - An array of all available fields in a lunr.Index. + */ +lunr.Query = function (allFields) { + this.clauses = [] + this.allFields = allFields +} + +/** + * Constants for indicating what kind of automatic wildcard insertion will be used when constructing a query clause. + * + * This allows wildcards to be added to the beginning and end of a term without having to manually do any string + * concatenation. + * + * The wildcard constants can be bitwise combined to select both leading and trailing wildcards. + * + * @constant + * @default + * @property {number} wildcard.NONE - The term will have no wildcards inserted, this is the default behaviour + * @property {number} wildcard.LEADING - Prepend the term with a wildcard, unless a leading wildcard already exists + * @property {number} wildcard.TRAILING - Append a wildcard to the term, unless a trailing wildcard already exists + * @see lunr.Query~Clause + * @see lunr.Query#clause + * @see lunr.Query#term + * @example query term with trailing wildcard + * query.term('foo', { wildcard: lunr.Query.wildcard.TRAILING }) + * @example query term with leading and trailing wildcard + * query.term('foo', { + * wildcard: lunr.Query.wildcard.LEADING | lunr.Query.wildcard.TRAILING + * }) + */ +lunr.Query.wildcard = new String ("*") +lunr.Query.wildcard.NONE = 0 +lunr.Query.wildcard.LEADING = 1 +lunr.Query.wildcard.TRAILING = 2 + +/** + * A single clause in a {@link lunr.Query} contains a term and details on how to + * match that term against a {@link lunr.Index}. + * + * @typedef {Object} lunr.Query~Clause + * @property {string[]} fields - The fields in an index this clause should be matched against. + * @property {number} [boost=1] - Any boost that should be applied when matching this clause. + * @property {number} [editDistance] - Whether the term should have fuzzy matching applied, and how fuzzy the match should be. + * @property {boolean} [usePipeline] - Whether the term should be passed through the search pipeline. + * @property {number} [wildcard=0] - Whether the term should have wildcards appended or prepended. + */ + +/** + * Adds a {@link lunr.Query~Clause} to this query. + * + * Unless the clause contains the fields to be matched all fields will be matched. In addition + * a default boost of 1 is applied to the clause. + * + * @param {lunr.Query~Clause} clause - The clause to add to this query. + * @see lunr.Query~Clause + * @returns {lunr.Query} + */ +lunr.Query.prototype.clause = function (clause) { + if (!('fields' in clause)) { + clause.fields = this.allFields + } + + if (!('boost' in clause)) { + clause.boost = 1 + } + + if (!('usePipeline' in clause)) { + clause.usePipeline = true + } + + if (!('wildcard' in clause)) { + clause.wildcard = lunr.Query.wildcard.NONE + } + + if ((clause.wildcard & lunr.Query.wildcard.LEADING) && (clause.term.charAt(0) != lunr.Query.wildcard)) { + clause.term = "*" + clause.term + } + + if ((clause.wildcard & lunr.Query.wildcard.TRAILING) && (clause.term.slice(-1) != lunr.Query.wildcard)) { + clause.term = "" + clause.term + "*" + } + + this.clauses.push(clause) + + return this +} + +/** + * Adds a term to the current query, under the covers this will create a {@link lunr.Query~Clause} + * to the list of clauses that make up this query. + * + * @param {string} term - The term to add to the query. + * @param {Object} [options] - Any additional properties to add to the query clause. + * @returns {lunr.Query} + * @see lunr.Query#clause + * @see lunr.Query~Clause + * @example adding a single term to a query + * query.term("foo") + * @example adding a single term to a query and specifying search fields, term boost and automatic trailing wildcard + * query.term("foo", { + * fields: ["title"], + * boost: 10, + * wildcard: lunr.Query.wildcard.TRAILING + * }) + */ +lunr.Query.prototype.term = function (term, options) { + var clause = options || {} + clause.term = term + + this.clause(clause) + + return this +} +lunr.QueryParseError = function (message, start, end) { + this.name = "QueryParseError" + this.message = message + this.start = start + this.end = end +} + +lunr.QueryParseError.prototype = new Error +lunr.QueryLexer = function (str) { + this.lexemes = [] + this.str = str + this.length = str.length + this.pos = 0 + this.start = 0 + this.escapeCharPositions = [] +} + +lunr.QueryLexer.prototype.run = function () { + var state = lunr.QueryLexer.lexText + + while (state) { + state = state(this) + } +} + +lunr.QueryLexer.prototype.sliceString = function () { + var subSlices = [], + sliceStart = this.start, + sliceEnd = this.pos + + for (var i = 0; i < this.escapeCharPositions.length; i++) { + sliceEnd = this.escapeCharPositions[i] + subSlices.push(this.str.slice(sliceStart, sliceEnd)) + sliceStart = sliceEnd + 1 + } + + subSlices.push(this.str.slice(sliceStart, this.pos)) + this.escapeCharPositions.length = 0 + + return subSlices.join('') +} + +lunr.QueryLexer.prototype.emit = function (type) { + this.lexemes.push({ + type: type, + str: this.sliceString(), + start: this.start, + end: this.pos + }) + + this.start = this.pos +} + +lunr.QueryLexer.prototype.escapeCharacter = function () { + this.escapeCharPositions.push(this.pos - 1) + this.pos += 1 +} + +lunr.QueryLexer.prototype.next = function () { + if (this.pos >= this.length) { + return lunr.QueryLexer.EOS + } + + var char = this.str.charAt(this.pos) + this.pos += 1 + return char +} + +lunr.QueryLexer.prototype.width = function () { + return this.pos - this.start +} + +lunr.QueryLexer.prototype.ignore = function () { + if (this.start == this.pos) { + this.pos += 1 + } + + this.start = this.pos +} + +lunr.QueryLexer.prototype.backup = function () { + this.pos -= 1 +} + +lunr.QueryLexer.prototype.acceptDigitRun = function () { + var char, charCode + + do { + char = this.next() + charCode = char.charCodeAt(0) + } while (charCode > 47 && charCode < 58) + + if (char != lunr.QueryLexer.EOS) { + this.backup() + } +} + +lunr.QueryLexer.prototype.more = function () { + return this.pos < this.length +} + +lunr.QueryLexer.EOS = 'EOS' +lunr.QueryLexer.FIELD = 'FIELD' +lunr.QueryLexer.TERM = 'TERM' +lunr.QueryLexer.EDIT_DISTANCE = 'EDIT_DISTANCE' +lunr.QueryLexer.BOOST = 'BOOST' + +lunr.QueryLexer.lexField = function (lexer) { + lexer.backup() + lexer.emit(lunr.QueryLexer.FIELD) + lexer.ignore() + return lunr.QueryLexer.lexText +} + +lunr.QueryLexer.lexTerm = function (lexer) { + if (lexer.width() > 1) { + lexer.backup() + lexer.emit(lunr.QueryLexer.TERM) + } + + lexer.ignore() + + if (lexer.more()) { + return lunr.QueryLexer.lexText + } +} + +lunr.QueryLexer.lexEditDistance = function (lexer) { + lexer.ignore() + lexer.acceptDigitRun() + lexer.emit(lunr.QueryLexer.EDIT_DISTANCE) + return lunr.QueryLexer.lexText +} + +lunr.QueryLexer.lexBoost = function (lexer) { + lexer.ignore() + lexer.acceptDigitRun() + lexer.emit(lunr.QueryLexer.BOOST) + return lunr.QueryLexer.lexText +} + +lunr.QueryLexer.lexEOS = function (lexer) { + if (lexer.width() > 0) { + lexer.emit(lunr.QueryLexer.TERM) + } +} + +// This matches the separator used when tokenising fields +// within a document. These should match otherwise it is +// not possible to search for some tokens within a document. +// +// It is possible for the user to change the separator on the +// tokenizer so it _might_ clash with any other of the special +// characters already used within the search string, e.g. :. +// +// This means that it is possible to change the separator in +// such a way that makes some words unsearchable using a search +// string. +lunr.QueryLexer.termSeparator = lunr.tokenizer.separator + +lunr.QueryLexer.lexText = function (lexer) { + while (true) { + var char = lexer.next() + + if (char == lunr.QueryLexer.EOS) { + return lunr.QueryLexer.lexEOS + } + + // Escape character is '\' + if (char.charCodeAt(0) == 92) { + lexer.escapeCharacter() + continue + } + + if (char == ":") { + return lunr.QueryLexer.lexField + } + + if (char == "~") { + lexer.backup() + if (lexer.width() > 0) { + lexer.emit(lunr.QueryLexer.TERM) + } + return lunr.QueryLexer.lexEditDistance + } + + if (char == "^") { + lexer.backup() + if (lexer.width() > 0) { + lexer.emit(lunr.QueryLexer.TERM) + } + return lunr.QueryLexer.lexBoost + } + + if (char.match(lunr.QueryLexer.termSeparator)) { + return lunr.QueryLexer.lexTerm + } + } +} + +lunr.QueryParser = function (str, query) { + this.lexer = new lunr.QueryLexer (str) + this.query = query + this.currentClause = {} + this.lexemeIdx = 0 +} + +lunr.QueryParser.prototype.parse = function () { + this.lexer.run() + this.lexemes = this.lexer.lexemes + + var state = lunr.QueryParser.parseFieldOrTerm + + while (state) { + state = state(this) + } + + return this.query +} + +lunr.QueryParser.prototype.peekLexeme = function () { + return this.lexemes[this.lexemeIdx] +} + +lunr.QueryParser.prototype.consumeLexeme = function () { + var lexeme = this.peekLexeme() + this.lexemeIdx += 1 + return lexeme +} + +lunr.QueryParser.prototype.nextClause = function () { + var completedClause = this.currentClause + this.query.clause(completedClause) + this.currentClause = {} +} + +lunr.QueryParser.parseFieldOrTerm = function (parser) { + var lexeme = parser.peekLexeme() + + if (lexeme == undefined) { + return + } + + switch (lexeme.type) { + case lunr.QueryLexer.FIELD: + return lunr.QueryParser.parseField + case lunr.QueryLexer.TERM: + return lunr.QueryParser.parseTerm + default: + var errorMessage = "expected either a field or a term, found " + lexeme.type + + if (lexeme.str.length >= 1) { + errorMessage += " with value '" + lexeme.str + "'" + } + + throw new lunr.QueryParseError (errorMessage, lexeme.start, lexeme.end) + } +} + +lunr.QueryParser.parseField = function (parser) { + var lexeme = parser.consumeLexeme() + + if (lexeme == undefined) { + return + } + + if (parser.query.allFields.indexOf(lexeme.str) == -1) { + var possibleFields = parser.query.allFields.map(function (f) { return "'" + f + "'" }).join(', '), + errorMessage = "unrecognised field '" + lexeme.str + "', possible fields: " + possibleFields + + throw new lunr.QueryParseError (errorMessage, lexeme.start, lexeme.end) + } + + parser.currentClause.fields = [lexeme.str] + + var nextLexeme = parser.peekLexeme() + + if (nextLexeme == undefined) { + var errorMessage = "expecting term, found nothing" + throw new lunr.QueryParseError (errorMessage, lexeme.start, lexeme.end) + } + + switch (nextLexeme.type) { + case lunr.QueryLexer.TERM: + return lunr.QueryParser.parseTerm + default: + var errorMessage = "expecting term, found '" + nextLexeme.type + "'" + throw new lunr.QueryParseError (errorMessage, nextLexeme.start, nextLexeme.end) + } +} + +lunr.QueryParser.parseTerm = function (parser) { + var lexeme = parser.consumeLexeme() + + if (lexeme == undefined) { + return + } + + parser.currentClause.term = lexeme.str.toLowerCase() + + if (lexeme.str.indexOf("*") != -1) { + parser.currentClause.usePipeline = false + } + + var nextLexeme = parser.peekLexeme() + + if (nextLexeme == undefined) { + parser.nextClause() + return + } + + switch (nextLexeme.type) { + case lunr.QueryLexer.TERM: + parser.nextClause() + return lunr.QueryParser.parseTerm + case lunr.QueryLexer.FIELD: + parser.nextClause() + return lunr.QueryParser.parseField + case lunr.QueryLexer.EDIT_DISTANCE: + return lunr.QueryParser.parseEditDistance + case lunr.QueryLexer.BOOST: + return lunr.QueryParser.parseBoost + default: + var errorMessage = "Unexpected lexeme type '" + nextLexeme.type + "'" + throw new lunr.QueryParseError (errorMessage, nextLexeme.start, nextLexeme.end) + } +} + +lunr.QueryParser.parseEditDistance = function (parser) { + var lexeme = parser.consumeLexeme() + + if (lexeme == undefined) { + return + } + + var editDistance = parseInt(lexeme.str, 10) + + if (isNaN(editDistance)) { + var errorMessage = "edit distance must be numeric" + throw new lunr.QueryParseError (errorMessage, lexeme.start, lexeme.end) + } + + parser.currentClause.editDistance = editDistance + + var nextLexeme = parser.peekLexeme() + + if (nextLexeme == undefined) { + parser.nextClause() + return + } + + switch (nextLexeme.type) { + case lunr.QueryLexer.TERM: + parser.nextClause() + return lunr.QueryParser.parseTerm + case lunr.QueryLexer.FIELD: + parser.nextClause() + return lunr.QueryParser.parseField + case lunr.QueryLexer.EDIT_DISTANCE: + return lunr.QueryParser.parseEditDistance + case lunr.QueryLexer.BOOST: + return lunr.QueryParser.parseBoost + default: + var errorMessage = "Unexpected lexeme type '" + nextLexeme.type + "'" + throw new lunr.QueryParseError (errorMessage, nextLexeme.start, nextLexeme.end) + } +} + +lunr.QueryParser.parseBoost = function (parser) { + var lexeme = parser.consumeLexeme() + + if (lexeme == undefined) { + return + } + + var boost = parseInt(lexeme.str, 10) + + if (isNaN(boost)) { + var errorMessage = "boost must be numeric" + throw new lunr.QueryParseError (errorMessage, lexeme.start, lexeme.end) + } + + parser.currentClause.boost = boost + + var nextLexeme = parser.peekLexeme() + + if (nextLexeme == undefined) { + parser.nextClause() + return + } + + switch (nextLexeme.type) { + case lunr.QueryLexer.TERM: + parser.nextClause() + return lunr.QueryParser.parseTerm + case lunr.QueryLexer.FIELD: + parser.nextClause() + return lunr.QueryParser.parseField + case lunr.QueryLexer.EDIT_DISTANCE: + return lunr.QueryParser.parseEditDistance + case lunr.QueryLexer.BOOST: + return lunr.QueryParser.parseBoost + default: + var errorMessage = "Unexpected lexeme type '" + nextLexeme.type + "'" + throw new lunr.QueryParseError (errorMessage, nextLexeme.start, nextLexeme.end) + } +} + + /** + * export the module via AMD, CommonJS or as a browser global + * Export code from https://github.com/umdjs/umd/blob/master/returnExports.js + */ + ;(function (root, factory) { + if (typeof define === 'function' && define.amd) { + // AMD. Register as an anonymous module. + define(factory) + } else if (typeof exports === 'object') { + /** + * Node. Does not work with strict CommonJS, but + * only CommonJS-like enviroments that support module.exports, + * like Node. + */ + module.exports = factory() + } else { + // Browser globals (root is window) + root.lunr = factory() + } + }(this, function () { + /** + * Just return a value to define the module export. + * This example returns an object, but the module + * can return a function as the exported value. + */ + return lunr + })) +})(); -- 2.43.0