From d3d0669c0dac7fc683c5a8382be4d9f855a0b2aa Mon Sep 17 00:00:00 2001 From: koirand Date: Mon, 29 Oct 2018 23:50:33 +0900 Subject: [PATCH] Changed full-text search library from lune.js to fuse.js --- layouts/_default/list.html | 5 +- static/js/fuse.min.js | 9 + static/js/lunr.ja.js | 188 -- static/js/lunr.js | 3484 ----------------------------- static/js/lunr.stemmer.support.js | 304 --- static/js/search.js | 59 +- static/js/tinyseg.js | 207 -- 7 files changed, 29 insertions(+), 4227 deletions(-) create mode 100644 static/js/fuse.min.js delete mode 100644 static/js/lunr.ja.js delete mode 100644 static/js/lunr.js delete mode 100644 static/js/lunr.stemmer.support.js delete mode 100644 static/js/tinyseg.js diff --git a/layouts/_default/list.html b/layouts/_default/list.html index 10b8677..3394cf1 100644 --- a/layouts/_default/list.html +++ b/layouts/_default/list.html @@ -17,9 +17,6 @@ - - - - + {{ end }} diff --git a/static/js/fuse.min.js b/static/js/fuse.min.js new file mode 100644 index 0000000..0c7ae7d --- /dev/null +++ b/static/js/fuse.min.js @@ -0,0 +1,9 @@ +/*! + * Fuse.js v3.2.1 - Lightweight fuzzy-search (http://fusejs.io) + * + * Copyright (c) 2012-2017 Kirollos Risk (http://kiro.me) + * All Rights Reserved. Apache Software License 2.0 + * + * http://www.apache.org/licenses/LICENSE-2.0 + */ +!function(e,t){"object"==typeof exports&&"object"==typeof module?module.exports=t():"function"==typeof define&&define.amd?define("Fuse",[],t):"object"==typeof exports?exports.Fuse=t():e.Fuse=t()}(this,function(){return function(e){function t(n){if(r[n])return r[n].exports;var o=r[n]={i:n,l:!1,exports:{}};return e[n].call(o.exports,o,o.exports,t),o.l=!0,o.exports}var r={};return t.m=e,t.c=r,t.i=function(e){return e},t.d=function(e,r,n){t.o(e,r)||Object.defineProperty(e,r,{configurable:!1,enumerable:!0,get:n})},t.n=function(e){var r=e&&e.__esModule?function(){return e.default}:function(){return e};return t.d(r,"a",r),r},t.o=function(e,t){return Object.prototype.hasOwnProperty.call(e,t)},t.p="",t(t.s=8)}([function(e,t,r){"use strict";e.exports=function(e){return Array.isArray?Array.isArray(e):"[object Array]"===Object.prototype.toString.call(e)}},function(e,t,r){"use strict";function n(e,t){if(!(e instanceof t))throw new TypeError("Cannot call a class as a function")}var o=function(){function e(e,t){for(var r=0;rr)return i(e,this.pattern,n);var o=this.options,s=o.location,c=o.distance,h=o.threshold,l=o.findAllMatches,u=o.minMatchCharLength;return a(e,this.pattern,this.patternAlphabet,{location:s,distance:c,threshold:h,findAllMatches:l,minMatchCharLength:u})}}]),e}();e.exports=c},function(e,t,r){"use strict";var n=r(0),o=function e(t,r,o){if(r){var i=r.indexOf("."),a=r,s=null;-1!==i&&(a=r.slice(0,i),s=r.slice(i+1));var c=t[a];if(null!==c&&void 0!==c)if(s||"string"!=typeof c&&"number"!=typeof c)if(n(c))for(var h=0,l=c.length;h0&&void 0!==arguments[0]?arguments[0]:[],t=arguments.length>1&&void 0!==arguments[1]?arguments[1]:1,r=[],n=-1,o=-1,i=0,a=e.length;i=t&&r.push([n,o]),n=-1)}return e[i-1]&&i-n>=t&&r.push([n,i-1]),r}},function(e,t,r){"use strict";e.exports=function(e){for(var t={},r=e.length,n=0;n2&&void 0!==arguments[2]?arguments[2]:/ +/g,n=new RegExp(t.replace(/[\-\[\]\/\{\}\(\)\*\+\?\.\\\^\$\|]/g,"\\$&").replace(r,"|")),o=e.match(n),i=!!o,a=[];if(i)for(var s=0,c=o.length;s=P;T-=1){var E=T-1,K=r[e.charAt(E)];if(K&&(S[E]=1),z[T]=(z[T+1]<<1|1)&K,0!==I&&(z[T]|=(L[T+1]|L[T])<<1|1|L[T+1]),z[T]&C&&(w=n(t,{errors:I,currentLocation:E,expectedLocation:g,distance:h}))<=m){if(m=w,(k=E)<=g)break;P=Math.max(1,2*g-k)}}if(n(t,{errors:I+1,currentLocation:g,expectedLocation:g,distance:h})>m)break;L=z}return{isMatch:k>=0,score:0===w?.001:w,matchedIndices:o(S,p)}}},function(e,t,r){"use strict";function n(e,t){if(!(e instanceof t))throw new TypeError("Cannot call a class as a function")}var o=function(){function e(e,t){for(var r=0;r0&&void 0!==arguments[0]?arguments[0]:"",t=[];if(this.options.tokenize)for(var r=e.split(this.options.tokenSeparator),n=0,o=r.length;n0&&void 0!==arguments[0]?arguments[0]:[],t=arguments[1],r=this.list,n={},o=[];if("string"==typeof r[0]){for(var i=0,a=r.length;i1)throw new Error("Key weight has to be > 0 and <= 1");d=d.name}else s[d]={weight:1};this._analyze({key:d,value:this.options.getFn(l,d),record:l,index:c},{resultMap:n,results:o,tokenSearchers:e,fullSearcher:t})}return{weights:s,results:o}}},{key:"_analyze",value:function(e,t){var r=e.key,n=e.arrayIndex,o=void 0===n?-1:n,i=e.value,a=e.record,c=e.index,h=t.tokenSearchers,l=void 0===h?[]:h,u=t.fullSearcher,f=void 0===u?[]:u,d=t.resultMap,v=void 0===d?{}:d,p=t.results,g=void 0===p?[]:p;if(void 0!==i&&null!==i){var y=!1,m=-1,k=0;if("string"==typeof i){this._log("\nKey: "+(""===r?"-":r));var x=f.search(i);if(this._log('Full text: "'+i+'", score: '+x.score),this.options.tokenize){for(var S=i.split(this.options.tokenSeparator),M=[],b=0;b-1&&(P=(P+m)/2),this._log("Score average:",P);var j=!this.options.tokenize||!this.options.matchAllTokens||k>=l.length;if(this._log("\nCheck Matches: "+j),(y||x.isMatch)&&j){var z=v[c];z?z.output.push({key:r,arrayIndex:o,value:i,score:P,matchedIndices:x.matchedIndices}):(v[c]={item:a,output:[{key:r,arrayIndex:o,value:i,score:P,matchedIndices:x.matchedIndices}]},g.push(v[c]))}}else if(s(i))for(var T=0,E=i.length;T-1&&(a.arrayIndex=i.arrayIndex),t.matches.push(a)}}}),this.options.includeScore&&r.push(function(e,t){t.score=e.score});for(var n=0,o=e.length;n 1.0.0 - this.tokenizerFn = lunr.ja.tokenizer; - } - } - }; - var segmenter = new lunr.TinySegmenter(); // インスタンス生成 - - lunr.ja.tokenizer = function(obj) { - var i; - var str; - var len; - var segs; - var tokens; - var char; - var sliceLength; - var sliceStart; - var sliceEnd; - var segStart; - - if (!arguments.length || obj == null || obj == undefined) - return []; - - if (Array.isArray(obj)) { - return obj.map( - function(t) { - return isLunr2 ? new lunr.Token(t.toLowerCase()) : t.toLowerCase(); - } - ); - } - - str = obj.toString().toLowerCase().replace(/^\s+/, ''); - for (i = str.length - 1; i >= 0; i--) { - if (/\S/.test(str.charAt(i))) { - str = str.substring(0, i + 1); - break; - } - } - - tokens = []; - len = str.length; - for (sliceEnd = 0, sliceStart = 0; sliceEnd <= len; sliceEnd++) { - char = str.charAt(sliceEnd); - sliceLength = sliceEnd - sliceStart; - - if ((char.match(/\s/) || sliceEnd == len)) { - if (sliceLength > 0) { - segs = segmenter.segment(str.slice(sliceStart, sliceEnd)).filter( - function(token) { - return !!token; - } - ); - - segStart = sliceStart; - for (i = 0; i < segs.length; i++) { - if (isLunr2) { - tokens.push( - new lunr.Token( - segs[i], { - position: [segStart, segs[i].length], - index: tokens.length - } - ) - ); - } else { - tokens.push(segs[i]); - } - segStart += segs[i].length; - } - } - - sliceStart = sliceEnd + 1; - } - } - - return tokens; - } - - /* lunr stemmer function */ - lunr.ja.stemmer = (function() { - - /* TODO japanese stemmer */ - return function(word) { - return word; - } - })(); - lunr.Pipeline.registerFunction(lunr.ja.stemmer, 'stemmer-ja'); - - /* lunr trimmer function */ - lunr.ja.wordCharacters = "一二三四五六七八九十百千万億兆一-龠々〆ヵヶぁ-んァ-ヴーｱ-ﾝﾞa-zA-Zａ-ｚＡ-Ｚ0-9０-９"; - lunr.ja.trimmer = lunr.trimmerSupport.generateTrimmer(lunr.ja.wordCharacters); - lunr.Pipeline.registerFunction(lunr.ja.trimmer, 'trimmer-ja'); - - /* lunr stop word filter. see http://www.ranks.nl/stopwords/japanese */ - lunr.ja.stopWordFilter = lunr.generateStopWordFilter( - 'これ それ あれ この その あの ここ そこ あそこ こちら どこ だれ なに なん 何 私 貴方 貴方方 我々 私達 あの人 あのかた 彼女 彼 です あります おります います は が の に を で え から まで より も どの と し それで しかし'.split(' ')); - lunr.Pipeline.registerFunction(lunr.ja.stopWordFilter, 'stopWordFilter-ja'); - - // alias ja => jp for backward-compatibility. - // jp is the country code, while ja is the language code - // a new lunr.ja.js has been created, but in order to - // keep the backward compatibility, we'll leave the lunr.jp.js - // here for a while, and just make it use the new lunr.ja.js - lunr.jp = lunr.ja; - lunr.Pipeline.registerFunction(lunr.jp.stemmer, 'stemmer-jp'); - lunr.Pipeline.registerFunction(lunr.jp.trimmer, 'trimmer-jp'); - lunr.Pipeline.registerFunction(lunr.jp.stopWordFilter, 'stopWordFilter-jp'); - }; -})) \ No newline at end of file diff --git a/static/js/lunr.js b/static/js/lunr.js deleted file mode 100644 index 8f0c4a1..0000000 --- a/static/js/lunr.js +++ /dev/null @@ -1,3484 +0,0 @@ -/** - * lunr - http://lunrjs.com - A bit like Solr, but much smaller and not as bright - 2.3.3 - * Copyright (C) 2018 Oliver Nightingale - * @license MIT - */ - -;(function(){ - -/** - * A convenience function for configuring and constructing - * a new lunr Index. - * - * A lunr.Builder instance is created and the pipeline setup - * with a trimmer, stop word filter and stemmer. - * - * This builder object is yielded to the configuration function - * that is passed as a parameter, allowing the list of fields - * and other builder parameters to be customised. - * - * All documents _must_ be added within the passed config function. - * - * @example - * var idx = lunr(function () { - * this.field('title') - * this.field('body') - * this.ref('id') - * - * documents.forEach(function (doc) { - * this.add(doc) - * }, this) - * }) - * - * @see {@link lunr.Builder} - * @see {@link lunr.Pipeline} - * @see {@link lunr.trimmer} - * @see {@link lunr.stopWordFilter} - * @see {@link lunr.stemmer} - * @namespace {function} lunr - */ -var lunr = function (config) { - var builder = new lunr.Builder - - builder.pipeline.add( - lunr.trimmer, - lunr.stopWordFilter, - lunr.stemmer - ) - - builder.searchPipeline.add( - lunr.stemmer - ) - - config.call(builder, builder) - return builder.build() -} - -lunr.version = "2.3.3" -/*! - * lunr.utils - * Copyright (C) 2018 Oliver Nightingale - */ - -/** - * A namespace containing utils for the rest of the lunr library - * @namespace lunr.utils - */ -lunr.utils = {} - -/** - * Print a warning message to the console. - * - * @param {String} message The message to be printed. - * @memberOf lunr.utils - * @function - */ -lunr.utils.warn = (function (global) { - /* eslint-disable no-console */ - return function (message) { - if (global.console && console.warn) { - console.warn(message) - } - } - /* eslint-enable no-console */ -})(this) - -/** - * Convert an object to a string. - * - * In the case of `null` and `undefined` the function returns - * the empty string, in all other cases the result of calling - * `toString` on the passed object is returned. - * - * @param {Any} obj The object to convert to a string. - * @return {String} string representation of the passed object. - * @memberOf lunr.utils - */ -lunr.utils.asString = function (obj) { - if (obj === void 0 || obj === null) { - return "" - } else { - return obj.toString() - } -} - -/** - * Clones an object. - * - * Will create a copy of an existing object such that any mutations - * on the copy cannot affect the original. - * - * Only shallow objects are supported, passing a nested object to this - * function will cause a TypeError. - * - * Objects with primitives, and arrays of primitives are supported. - * - * @param {Object} obj The object to clone. - * @return {Object} a clone of the passed object. - * @throws {TypeError} when a nested object is passed. - * @memberOf Utils - */ -lunr.utils.clone = function (obj) { - if (obj === null || obj === undefined) { - return obj - } - - var clone = Object.create(null), - keys = Object.keys(obj) - - for (var i = 0; i < keys.length; i++) { - var key = keys[i], - val = obj[key] - - if (Array.isArray(val)) { - clone[key] = val.slice() - continue - } - - if (typeof val === 'string' || - typeof val === 'number' || - typeof val === 'boolean') { - clone[key] = val - continue - } - - throw new TypeError("clone is not deep and does not support nested objects") - } - - return clone -} -lunr.FieldRef = function (docRef, fieldName, stringValue) { - this.docRef = docRef - this.fieldName = fieldName - this._stringValue = stringValue -} - -lunr.FieldRef.joiner = "/" - -lunr.FieldRef.fromString = function (s) { - var n = s.indexOf(lunr.FieldRef.joiner) - - if (n === -1) { - throw "malformed field ref string" - } - - var fieldRef = s.slice(0, n), - docRef = s.slice(n + 1) - - return new lunr.FieldRef (docRef, fieldRef, s) -} - -lunr.FieldRef.prototype.toString = function () { - if (this._stringValue == undefined) { - this._stringValue = this.fieldName + lunr.FieldRef.joiner + this.docRef - } - - return this._stringValue -} -/*! - * lunr.Set - * Copyright (C) 2018 Oliver Nightingale - */ - -/** - * A lunr set. - * - * @constructor - */ -lunr.Set = function (elements) { - this.elements = Object.create(null) - - if (elements) { - this.length = elements.length - - for (var i = 0; i < this.length; i++) { - this.elements[elements[i]] = true - } - } else { - this.length = 0 - } -} - -/** - * A complete set that contains all elements. - * - * @static - * @readonly - * @type {lunr.Set} - */ -lunr.Set.complete = { - intersect: function (other) { - return other - }, - - union: function (other) { - return other - }, - - contains: function () { - return true - } -} - -/** - * An empty set that contains no elements. - * - * @static - * @readonly - * @type {lunr.Set} - */ -lunr.Set.empty = { - intersect: function () { - return this - }, - - union: function (other) { - return other - }, - - contains: function () { - return false - } -} - -/** - * Returns true if this set contains the specified object. - * - * @param {object} object - Object whose presence in this set is to be tested. - * @returns {boolean} - True if this set contains the specified object. - */ -lunr.Set.prototype.contains = function (object) { - return !!this.elements[object] -} - -/** - * Returns a new set containing only the elements that are present in both - * this set and the specified set. - * - * @param {lunr.Set} other - set to intersect with this set. - * @returns {lunr.Set} a new set that is the intersection of this and the specified set. - */ - -lunr.Set.prototype.intersect = function (other) { - var a, b, elements, intersection = [] - - if (other === lunr.Set.complete) { - return this - } - - if (other === lunr.Set.empty) { - return other - } - - if (this.length < other.length) { - a = this - b = other - } else { - a = other - b = this - } - - elements = Object.keys(a.elements) - - for (var i = 0; i < elements.length; i++) { - var element = elements[i] - if (element in b.elements) { - intersection.push(element) - } - } - - return new lunr.Set (intersection) -} - -/** - * Returns a new set combining the elements of this and the specified set. - * - * @param {lunr.Set} other - set to union with this set. - * @return {lunr.Set} a new set that is the union of this and the specified set. - */ - -lunr.Set.prototype.union = function (other) { - if (other === lunr.Set.complete) { - return lunr.Set.complete - } - - if (other === lunr.Set.empty) { - return this - } - - return new lunr.Set(Object.keys(this.elements).concat(Object.keys(other.elements))) -} -/** - * A function to calculate the inverse document frequency for - * a posting. This is shared between the builder and the index - * - * @private - * @param {object} posting - The posting for a given term - * @param {number} documentCount - The total number of documents. - */ -lunr.idf = function (posting, documentCount) { - var documentsWithTerm = 0 - - for (var fieldName in posting) { - if (fieldName == '_index') continue // Ignore the term index, its not a field - documentsWithTerm += Object.keys(posting[fieldName]).length - } - - var x = (documentCount - documentsWithTerm + 0.5) / (documentsWithTerm + 0.5) - - return Math.log(1 + Math.abs(x)) -} - -/** - * A token wraps a string representation of a token - * as it is passed through the text processing pipeline. - * - * @constructor - * @param {string} [str=''] - The string token being wrapped. - * @param {object} [metadata={}] - Metadata associated with this token. - */ -lunr.Token = function (str, metadata) { - this.str = str || "" - this.metadata = metadata || {} -} - -/** - * Returns the token string that is being wrapped by this object. - * - * @returns {string} - */ -lunr.Token.prototype.toString = function () { - return this.str -} - -/** - * A token update function is used when updating or optionally - * when cloning a token. - * - * @callback lunr.Token~updateFunction - * @param {string} str - The string representation of the token. - * @param {Object} metadata - All metadata associated with this token. - */ - -/** - * Applies the given function to the wrapped string token. - * - * @example - * token.update(function (str, metadata) { - * return str.toUpperCase() - * }) - * - * @param {lunr.Token~updateFunction} fn - A function to apply to the token string. - * @returns {lunr.Token} - */ -lunr.Token.prototype.update = function (fn) { - this.str = fn(this.str, this.metadata) - return this -} - -/** - * Creates a clone of this token. Optionally a function can be - * applied to the cloned token. - * - * @param {lunr.Token~updateFunction} [fn] - An optional function to apply to the cloned token. - * @returns {lunr.Token} - */ -lunr.Token.prototype.clone = function (fn) { - fn = fn || function (s) { return s } - return new lunr.Token (fn(this.str, this.metadata), this.metadata) -} -/*! - * lunr.tokenizer - * Copyright (C) 2018 Oliver Nightingale - */ - -/** - * A function for splitting a string into tokens ready to be inserted into - * the search index. Uses `lunr.tokenizer.separator` to split strings, change - * the value of this property to change how strings are split into tokens. - * - * This tokenizer will convert its parameter to a string by calling `toString` and - * then will split this string on the character in `lunr.tokenizer.separator`. - * Arrays will have their elements converted to strings and wrapped in a lunr.Token. - * - * Optional metadata can be passed to the tokenizer, this metadata will be cloned and - * added as metadata to every token that is created from the object to be tokenized. - * - * @static - * @param {?(string|object|object[])} obj - The object to convert into tokens - * @param {?object} metadata - Optional metadata to associate with every token - * @returns {lunr.Token[]} - * @see {@link lunr.Pipeline} - */ -lunr.tokenizer = function (obj, metadata) { - if (obj == null || obj == undefined) { - return [] - } - - if (Array.isArray(obj)) { - return obj.map(function (t) { - return new lunr.Token( - lunr.utils.asString(t).toLowerCase(), - lunr.utils.clone(metadata) - ) - }) - } - - var str = obj.toString().trim().toLowerCase(), - len = str.length, - tokens = [] - - for (var sliceEnd = 0, sliceStart = 0; sliceEnd <= len; sliceEnd++) { - var char = str.charAt(sliceEnd), - sliceLength = sliceEnd - sliceStart - - if ((char.match(lunr.tokenizer.separator) || sliceEnd == len)) { - - if (sliceLength > 0) { - var tokenMetadata = lunr.utils.clone(metadata) || {} - tokenMetadata["position"] = [sliceStart, sliceLength] - tokenMetadata["index"] = tokens.length - - tokens.push( - new lunr.Token ( - str.slice(sliceStart, sliceEnd), - tokenMetadata - ) - ) - } - - 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) 2018 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] - var memo = [] - - for (var j = 0; j < tokens.length; j++) { - var result = fn(tokens[j], j, tokens) - - if (result === void 0 || result === '') continue - - if (result instanceof Array) { - for (var k = 0; k < result.length; k++) { - memo.push(result[k]) - } - } else { - memo.push(result) - } - } - - tokens = memo - } - - 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. - * @param {?object} metadata - Optional metadata to associate with the token - * passed to the pipeline. - * @returns {string[]} - */ -lunr.Pipeline.prototype.runString = function (str, metadata) { - var token = new lunr.Token (str, metadata) - - 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) 2018 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 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() || 0 -} - -/** - * 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) 2018 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} - * @function - */ -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) 2018 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. - * - * @function - * @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. - * - * @function - * @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) 2018 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) 2018 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 - - /* - * Iterates through all characters within the passed string - * appending a node for each character. - * - * When 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 == "*") { - node.edges[char] = node - node.final = final - - } else { - var next = new lunr.TokenSet - next.final = final - - node.edges[char] = next - node = next - } - } - - 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) { - /* In Safari, at this point the prefix is sometimes corrupted, see: - * https://github.com/olivernn/lunr.js/issues/279 Calling any - * String.prototype method forces Safari to "cast" this string to what - * it's supposed to be, fixing the bug. */ - frame.prefix.charAt(0) - 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) 2018 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.fieldVectors - Field vectors - * @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. - * - * Each term also supports a presence modifier. By default a term's presence in document is optional, however - * this can be changed to either required or prohibited. For a term's presence to be required in a document the - * term should be prefixed with a '+', e.g. `+foo bar` is a search for documents that must contain 'foo' and - * optionally contain 'bar'. Conversely a leading '-' sets the terms presence to prohibited, i.e. it must not - * appear in a document, e.g. `-foo bar` is a search for documents that do not contain 'foo' but may contain 'bar'. - * - * 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 - * @example terms with presence modifiers - * -foo +bar baz - */ - -/** - * 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 details on how the score is calculated, please see - * the {@link https://lunrjs.com/guides/searching.html#scoring|guide}. - * - * 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), - requiredMatches = Object.create(null), - prohibitedMatches = Object.create(null) - - /* - * To support field level boosts a query vector is created per - * field. An empty vector is eagerly created to support negated - * queries. - */ - for (var i = 0; i < this.fields.length; i++) { - queryVectors[this.fields[i]] = new lunr.Vector - } - - 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, - clauseMatches = lunr.Set.complete - - if (clause.usePipeline) { - terms = this.pipeline.runString(clause.term, { - fields: clause.fields - }) - } 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() - - /* - * If a term marked as required does not exist in the tokenSet it is - * impossible for the search to return any matches. We set all the field - * scoped required matches set to empty and stop examining any further - * clauses. - */ - if (expandedTerms.length === 0 && clause.presence === lunr.Query.presence.REQUIRED) { - for (var k = 0; k < clause.fields.length; k++) { - var field = clause.fields[k] - requiredMatches[field] = lunr.Set.empty - } - - break - } - - 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, - matchingDocumentsSet = new lunr.Set(matchingDocumentRefs) - - /* - * if the presence of this term is required ensure that the matching - * documents are added to the set of required matches for this clause. - * - */ - if (clause.presence == lunr.Query.presence.REQUIRED) { - clauseMatches = clauseMatches.union(matchingDocumentsSet) - - if (requiredMatches[field] === undefined) { - requiredMatches[field] = lunr.Set.complete - } - } - - /* - * if the presence of this term is prohibited ensure that the matching - * documents are added to the set of prohibited matches for this field, - * creating that set if it does not yet exist. - */ - if (clause.presence == lunr.Query.presence.PROHIBITED) { - if (prohibitedMatches[field] === undefined) { - prohibitedMatches[field] = lunr.Set.empty - } - - prohibitedMatches[field] = prohibitedMatches[field].union(matchingDocumentsSet) - - /* - * Prohibited matches should not be part of the query vector used for - * similarity scoring and no metadata should be extracted so we continue - * to the next field - */ - continue - } - - /* - * The query field vector is populated using the termIndex found for - * the term and a unit value with the appropriate boost applied. - * 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, 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 - } - } - } - - /** - * If the presence was required we need to update the requiredMatches field sets. - * We do this after all fields for the term have collected their matches because - * the clause terms presence is required in _any_ of the fields not _all_ of the - * fields. - */ - if (clause.presence === lunr.Query.presence.REQUIRED) { - for (var k = 0; k < clause.fields.length; k++) { - var field = clause.fields[k] - requiredMatches[field] = requiredMatches[field].intersect(clauseMatches) - } - } - } - - /** - * Need to combine the field scoped required and prohibited - * matching documents into a global set of required and prohibited - * matches - */ - var allRequiredMatches = lunr.Set.complete, - allProhibitedMatches = lunr.Set.empty - - for (var i = 0; i < this.fields.length; i++) { - var field = this.fields[i] - - if (requiredMatches[field]) { - allRequiredMatches = allRequiredMatches.intersect(requiredMatches[field]) - } - - if (prohibitedMatches[field]) { - allProhibitedMatches = allProhibitedMatches.union(prohibitedMatches[field]) - } - } - - var matchingFieldRefs = Object.keys(matchingFields), - results = [], - matches = Object.create(null) - - /* - * If the query is negated (contains only prohibited terms) - * we need to get _all_ fieldRefs currently existing in the - * index. This is only done when we know that the query is - * entirely prohibited terms to avoid any cost of getting all - * fieldRefs unnecessarily. - * - * Additionally, blank MatchData must be created to correctly - * populate the results. - */ - if (query.isNegated()) { - matchingFieldRefs = Object.keys(this.fieldVectors) - - for (var i = 0; i < matchingFieldRefs.length; i++) { - var matchingFieldRef = matchingFieldRefs[i] - var fieldRef = lunr.FieldRef.fromString(matchingFieldRef) - matchingFields[matchingFieldRef] = new lunr.MatchData - } - } - - 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 - - if (!allRequiredMatches.contains(docRef)) { - continue - } - - if (allProhibitedMatches.contains(docRef)) { - continue - } - - var 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) 2018 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 = Object.create(null) - this._documents = Object.create(null) - 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 -} - -/** - * A function that is used to extract a field from a document. - * - * Lunr expects a field to be at the top level of a document, if however the field - * is deeply nested within a document an extractor function can be used to extract - * the right field for indexing. - * - * @callback fieldExtractor - * @param {object} doc - The document being added to the index. - * @returns {?(string|object|object[])} obj - The object that will be indexed for this field. - * @example Extracting a nested field - * function (doc) { return doc.nested.field } - */ - -/** - * 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. - * - * Fields can be boosted at build time. This allows terms within that field to have more - * importance when ranking search results. Use a field boost to specify that matches within - * one field are more important than other fields. - * - * @param {string} fieldName - The name of a field to index in all documents. - * @param {object} attributes - Optional attributes associated with this field. - * @param {number} [attributes.boost=1] - Boost applied to all terms within this field. - * @param {fieldExtractor} [attributes.extractor] - Function to extract a field from a document. - * @throws {RangeError} fieldName cannot contain unsupported characters '/' - */ -lunr.Builder.prototype.field = function (fieldName, attributes) { - if (/\//.test(fieldName)) { - throw new RangeError ("Field '" + fieldName + "' contains illegal character '/'") - } - - this._fields[fieldName] = attributes || {} -} - -/** - * 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. - * - * Entire documents can be boosted at build time. Applying a boost to a document indicates that - * this document should rank higher in search results than other documents. - * - * @param {object} doc - The document to add to the index. - * @param {object} attributes - Optional attributes associated with this document. - * @param {number} [attributes.boost=1] - Boost applied to all terms within this document. - */ -lunr.Builder.prototype.add = function (doc, attributes) { - var docRef = doc[this._ref], - fields = Object.keys(this._fields) - - this._documents[docRef] = attributes || {} - this.documentCount += 1 - - for (var i = 0; i < fields.length; i++) { - var fieldName = fields[i], - extractor = this._fields[fieldName].extractor, - field = extractor ? extractor(doc) : doc[fieldName], - tokens = this.tokenizer(field, { - fields: [fieldName] - }), - 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 < fields.length; k++) { - posting[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] - } - - var fields = Object.keys(this._fields) - - for (var i = 0; i < fields.length; i++) { - var fieldName = fields[i] - accumulator[fieldName] = accumulator[fieldName] / documentsWithField[fieldName] - } - - 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]), - fieldName = fieldRef.fieldName, - fieldLength = this.fieldLengths[fieldRef], - fieldVector = new lunr.Vector, - termFrequencies = this.fieldTermFrequencies[fieldRef], - terms = Object.keys(termFrequencies), - termsLength = terms.length - - - var fieldBoost = this._fields[fieldName].boost || 1, - docBoost = this._documents[fieldRef.docRef].boost || 1 - - 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[fieldName])) + tf) - score *= fieldBoost - score *= docBoost - 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: Object.keys(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) - - if (term !== undefined) { - 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 - -/** - * Constants for indicating what kind of presence a term must have in matching documents. - * - * @constant - * @enum {number} - * @see lunr.Query~Clause - * @see lunr.Query#clause - * @see lunr.Query#term - * @example query term with required presence - * query.term('foo', { presence: lunr.Query.presence.REQUIRED }) - */ -lunr.Query.presence = { - /** - * Term's presence in a document is optional, this is the default value. - */ - OPTIONAL: 1, - - /** - * Term's presence in a document is required, documents that do not contain - * this term will not be returned. - */ - REQUIRED: 2, - - /** - * Term's presence in a document is prohibited, documents that do contain - * this term will not be returned. - */ - PROHIBITED: 3 -} - -/** - * 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=lunr.Query.wildcard.NONE] - Whether the term should have wildcards appended or prepended. - * @property {number} [presence=lunr.Query.presence.OPTIONAL] - The terms presence in any matching documents. - */ - -/** - * 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 + "*" - } - - if (!('presence' in clause)) { - clause.presence = lunr.Query.presence.OPTIONAL - } - - this.clauses.push(clause) - - return this -} - -/** - * A negated query is one in which every clause has a presence of - * prohibited. These queries require some special processing to return - * the expected results. - * - * @returns boolean - */ -lunr.Query.prototype.isNegated = function () { - for (var i = 0; i < this.clauses.length; i++) { - if (this.clauses[i].presence != lunr.Query.presence.PROHIBITED) { - return false - } - } - - return true -} - -/** - * 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. - * - * The term is used as is, i.e. no tokenization will be performed by this method. Instead conversion - * to a token or token-like string should be done before calling this method. - * - * The term will be converted to a string by calling `toString`. Multiple terms can be passed as an - * array, each term in the array will share the same options. - * - * @param {object|object[]} term - The term(s) 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 - * }) - * @example using lunr.tokenizer to convert a string to tokens before using them as terms - * query.term(lunr.tokenizer("foo bar")) - */ -lunr.Query.prototype.term = function (term, options) { - if (Array.isArray(term)) { - term.forEach(function (t) { this.term(t, lunr.utils.clone(options)) }, this) - return this - } - - var clause = options || {} - clause.term = term.toString() - - 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.PRESENCE = 'PRESENCE' - -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 - } - - // "+" indicates term presence is required - // checking for length to ensure that only - // leading "+" are considered - if (char == "+" && lexer.width() === 1) { - lexer.emit(lunr.QueryLexer.PRESENCE) - return lunr.QueryLexer.lexText - } - - // "-" indicates term presence is prohibited - // checking for length to ensure that only - // leading "-" are considered - if (char == "-" && lexer.width() === 1) { - lexer.emit(lunr.QueryLexer.PRESENCE) - return lunr.QueryLexer.lexText - } - - 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.parseClause - - 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.parseClause = function (parser) { - var lexeme = parser.peekLexeme() - - if (lexeme == undefined) { - return - } - - switch (lexeme.type) { - case lunr.QueryLexer.PRESENCE: - return lunr.QueryParser.parsePresence - 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.parsePresence = function (parser) { - var lexeme = parser.consumeLexeme() - - if (lexeme == undefined) { - return - } - - switch (lexeme.str) { - case "-": - parser.currentClause.presence = lunr.Query.presence.PROHIBITED - break - case "+": - parser.currentClause.presence = lunr.Query.presence.REQUIRED - break - default: - var errorMessage = "unrecognised presence operator'" + lexeme.str + "'" - throw new lunr.QueryParseError (errorMessage, lexeme.start, lexeme.end) - } - - var nextLexeme = parser.peekLexeme() - - if (nextLexeme == undefined) { - var errorMessage = "expecting term or field, found nothing" - throw new lunr.QueryParseError (errorMessage, lexeme.start, lexeme.end) - } - - switch (nextLexeme.type) { - case lunr.QueryLexer.FIELD: - return lunr.QueryParser.parseField - case lunr.QueryLexer.TERM: - return lunr.QueryParser.parseTerm - default: - var errorMessage = "expecting term or field, found '" + nextLexeme.type + "'" - throw new lunr.QueryParseError (errorMessage, nextLexeme.start, nextLexeme.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 - case lunr.QueryLexer.PRESENCE: - parser.nextClause() - return lunr.QueryParser.parsePresence - 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 - case lunr.QueryLexer.PRESENCE: - parser.nextClause() - return lunr.QueryParser.parsePresence - 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 - case lunr.QueryLexer.PRESENCE: - parser.nextClause() - return lunr.QueryParser.parsePresence - 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 - })) -})(); diff --git a/static/js/lunr.stemmer.support.js b/static/js/lunr.stemmer.support.js deleted file mode 100644 index 896476a..0000000 --- a/static/js/lunr.stemmer.support.js +++ /dev/null @@ -1,304 +0,0 @@ -/*! - * Snowball JavaScript Library v0.3 - * http://code.google.com/p/urim/ - * http://snowball.tartarus.org/ - * - * Copyright 2010, Oleg Mazko - * http://www.mozilla.org/MPL/ - */ - -/** - * 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 environments that support module.exports, - * like Node. - */ - module.exports = factory() - } else { - // Browser globals (root is window) - factory()(root.lunr); - } -}(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 function(lunr) { - /* provides utilities for the included stemmers */ - lunr.stemmerSupport = { - Among: function(s, substring_i, result, method) { - this.toCharArray = function(s) { - var sLength = s.length, charArr = new Array(sLength); - for (var i = 0; i < sLength; i++) - charArr[i] = s.charCodeAt(i); - return charArr; - }; - - if ((!s && s != "") || (!substring_i && (substring_i != 0)) || !result) - throw ("Bad Among initialisation: s:" + s + ", substring_i: " - + substring_i + ", result: " + result); - this.s_size = s.length; - this.s = this.toCharArray(s); - this.substring_i = substring_i; - this.result = result; - this.method = method; - }, - SnowballProgram: function() { - var current; - return { - bra : 0, - ket : 0, - limit : 0, - cursor : 0, - limit_backward : 0, - setCurrent : function(word) { - current = word; - this.cursor = 0; - this.limit = word.length; - this.limit_backward = 0; - this.bra = this.cursor; - this.ket = this.limit; - }, - getCurrent : function() { - var result = current; - current = null; - return result; - }, - in_grouping : function(s, min, max) { - if (this.cursor < this.limit) { - var ch = current.charCodeAt(this.cursor); - if (ch <= max && ch >= min) { - ch -= min; - if (s[ch >> 3] & (0X1 << (ch & 0X7))) { - this.cursor++; - return true; - } - } - } - return false; - }, - in_grouping_b : function(s, min, max) { - if (this.cursor > this.limit_backward) { - var ch = current.charCodeAt(this.cursor - 1); - if (ch <= max && ch >= min) { - ch -= min; - if (s[ch >> 3] & (0X1 << (ch & 0X7))) { - this.cursor--; - return true; - } - } - } - return false; - }, - out_grouping : function(s, min, max) { - if (this.cursor < this.limit) { - var ch = current.charCodeAt(this.cursor); - if (ch > max || ch < min) { - this.cursor++; - return true; - } - ch -= min; - if (!(s[ch >> 3] & (0X1 << (ch & 0X7)))) { - this.cursor++; - return true; - } - } - return false; - }, - out_grouping_b : function(s, min, max) { - if (this.cursor > this.limit_backward) { - var ch = current.charCodeAt(this.cursor - 1); - if (ch > max || ch < min) { - this.cursor--; - return true; - } - ch -= min; - if (!(s[ch >> 3] & (0X1 << (ch & 0X7)))) { - this.cursor--; - return true; - } - } - return false; - }, - eq_s : function(s_size, s) { - if (this.limit - this.cursor < s_size) - return false; - for (var i = 0; i < s_size; i++) - if (current.charCodeAt(this.cursor + i) != s.charCodeAt(i)) - return false; - this.cursor += s_size; - return true; - }, - eq_s_b : function(s_size, s) { - if (this.cursor - this.limit_backward < s_size) - return false; - for (var i = 0; i < s_size; i++) - if (current.charCodeAt(this.cursor - s_size + i) != s - .charCodeAt(i)) - return false; - this.cursor -= s_size; - return true; - }, - find_among : function(v, v_size) { - var i = 0, j = v_size, c = this.cursor, l = this.limit, common_i = 0, common_j = 0, first_key_inspected = false; - while (true) { - var k = i + ((j - i) >> 1), diff = 0, common = common_i < common_j - ? common_i - : common_j, w = v[k]; - for (var i2 = common; i2 < w.s_size; i2++) { - if (c + common == l) { - diff = -1; - break; - } - diff = current.charCodeAt(c + common) - w.s[i2]; - if (diff) - break; - common++; - } - if (diff < 0) { - j = k; - common_j = common; - } else { - i = k; - common_i = common; - } - if (j - i <= 1) { - if (i > 0 || j == i || first_key_inspected) - break; - first_key_inspected = true; - } - } - while (true) { - var w = v[i]; - if (common_i >= w.s_size) { - this.cursor = c + w.s_size; - if (!w.method) - return w.result; - var res = w.method(); - this.cursor = c + w.s_size; - if (res) - return w.result; - } - i = w.substring_i; - if (i < 0) - return 0; - } - }, - find_among_b : function(v, v_size) { - var i = 0, j = v_size, c = this.cursor, lb = this.limit_backward, common_i = 0, common_j = 0, first_key_inspected = false; - while (true) { - var k = i + ((j - i) >> 1), diff = 0, common = common_i < common_j - ? common_i - : common_j, w = v[k]; - for (var i2 = w.s_size - 1 - common; i2 >= 0; i2--) { - if (c - common == lb) { - diff = -1; - break; - } - diff = current.charCodeAt(c - 1 - common) - w.s[i2]; - if (diff) - break; - common++; - } - if (diff < 0) { - j = k; - common_j = common; - } else { - i = k; - common_i = common; - } - if (j - i <= 1) { - if (i > 0 || j == i || first_key_inspected) - break; - first_key_inspected = true; - } - } - while (true) { - var w = v[i]; - if (common_i >= w.s_size) { - this.cursor = c - w.s_size; - if (!w.method) - return w.result; - var res = w.method(); - this.cursor = c - w.s_size; - if (res) - return w.result; - } - i = w.substring_i; - if (i < 0) - return 0; - } - }, - replace_s : function(c_bra, c_ket, s) { - var adjustment = s.length - (c_ket - c_bra), left = current - .substring(0, c_bra), right = current.substring(c_ket); - current = left + s + right; - this.limit += adjustment; - if (this.cursor >= c_ket) - this.cursor += adjustment; - else if (this.cursor > c_bra) - this.cursor = c_bra; - return adjustment; - }, - slice_check : function() { - if (this.bra < 0 || this.bra > this.ket || this.ket > this.limit - || this.limit > current.length) - throw ("faulty slice operation"); - }, - slice_from : function(s) { - this.slice_check(); - this.replace_s(this.bra, this.ket, s); - }, - slice_del : function() { - this.slice_from(""); - }, - insert : function(c_bra, c_ket, s) { - var adjustment = this.replace_s(c_bra, c_ket, s); - if (c_bra <= this.bra) - this.bra += adjustment; - if (c_bra <= this.ket) - this.ket += adjustment; - }, - slice_to : function() { - this.slice_check(); - return current.substring(this.bra, this.ket); - }, - eq_v_b : function(s) { - return this.eq_s_b(s.length, s); - } - }; - } - }; - - lunr.trimmerSupport = { - generateTrimmer: function(wordCharacters) { - var startRegex = new RegExp("^[^" + wordCharacters + "]+") - var endRegex = new RegExp("[^" + wordCharacters + "]+$") - - return function(token) { - // for lunr version 2 - if (typeof token.update === "function") { - return token.update(function (s) { - return s - .replace(startRegex, '') - .replace(endRegex, ''); - }) - } else { // for lunr version 1 - return token - .replace(startRegex, '') - .replace(endRegex, ''); - } - }; - } - } - } -})); diff --git a/static/js/search.js b/static/js/search.js index 03760e5..b29d406 100644 --- a/static/js/search.js +++ b/static/js/search.js @@ -1,43 +1,25 @@ -var lunrIndex -var lunrResult -var pagesIndex +var fuse /** - * Preparation for using lunr.js + * Preparation for searching */ -function initLunr () { +function initSearch () { $.getJSON('index.json').done(function (index) { - pagesIndex = index - lunrIndex = lunr(function () { - this.use(lunr.ja) - this.ref('ref') - this.field('title', { boost: 10 }) - this.field('body') - this.metadataWhitelist = ['position'] - pagesIndex.forEach(function (page) { - this.add(page) - }, this) - }) + var options = { + shouldSort: true, + tokenize: true, + matchAllTokens: true, + threshold: 0.3, + minMatchCharLength: 5, + keys: ['title', 'body'] + } + fuse = new Fuse(index, options) }).fail(function (jqxhr, textStatus, error) { var err = textStatus + ', ' + error console.error('Error getting Hugo index flie:', err) }) } -/** - * Searching pages using lunr - * @param {String} query Query string for searching - * @return {Object[]} Array of search results - */ -function search (query) { - lunrResult = lunrIndex.search(query) - return lunrResult.map(function (result) { - return pagesIndex.filter(function (page) { - return page.ref === result.ref - })[0] - }) -} - /** * Setup UI for Search */ @@ -51,7 +33,7 @@ function initUI () { // Event when chenging query $('#searchBox').keyup(function () { var $searchResults = $('#searchResults') - var query = $(this).val() + var query = $(this).val().trim() // Icon switching if (query.length) { @@ -69,7 +51,7 @@ function initUI () { } // Display search results - renderResults(search(query)) + renderResults(fuse.search(query)) $searchResults.show() }) @@ -84,7 +66,7 @@ function initUI () { function renderResults (results) { var $searchResults = $('#searchResults') var query = $('#searchBox').val() - var BODY_LENGTH = 100 + var SUMMARY_INCLUDE = 100 var MAX_PAGES = 10 // Clear search result @@ -99,13 +81,10 @@ function renderResults (results) { // Only show the ten first results results.slice(0, MAX_PAGES).forEach(function (result, idx) { var $searchResultPage = $('
') - var metadata = lunrResult[idx].matchData.metadata - var matchPosition = metadata[Object.keys(metadata)[0]].body ? metadata[Object.keys(metadata)[0]].body.position[0][0] : 0 - var bodyStartPosition = (matchPosition - (BODY_LENGTH / 2) > 0) ? matchPosition - (BODY_LENGTH / 2) : 0 - + var matchPosition = result.body.indexOf(query.split(' ')[0]) + var bodyStartPosition = matchPosition - SUMMARY_INCLUDE > 0 ? matchPosition - SUMMARY_INCLUDE : 0 $searchResultPage.append('' + result.title + '') - - $searchResultPage.append('
' + result.body.substr(bodyStartPosition, BODY_LENGTH) + '
') + $searchResultPage.append('
' + result.body.substr(bodyStartPosition, SUMMARY_INCLUDE) + '
') $searchResults.append($searchResultPage) // Highlight keyword @@ -113,7 +92,7 @@ function renderResults (results) { }) } -initLunr() +initSearch() $(function () { initUI() diff --git a/static/js/tinyseg.js b/static/js/tinyseg.js deleted file mode 100644 index 0b07714..0000000 --- a/static/js/tinyseg.js +++ /dev/null @@ -1,207 +0,0 @@ -/** - * 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 environments that support module.exports, - * like Node. - */ - module.exports = factory() - } else { - // Browser globals (root is window) - factory()(root.lunr); - } -}(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 function(lunr) { - // TinySegmenter 0.1 -- Super compact Japanese tokenizer in Javascript - // (c) 2008 Taku Kudo - // TinySegmenter is freely distributable under the terms of a new BSD licence. - // For details, see http://chasen.org/~taku/software/TinySegmenter/LICENCE.txt - - function TinySegmenter() { - var patterns = { - "[一二三四五六七八九十百千万億兆]":"M", - "[一-龠々〆ヵヶ]":"H", - "[ぁ-ん]":"I", - "[ァ-ヴーｱ-ﾝﾞｰ]":"K", - "[a-zA-Zａ-ｚＡ-Ｚ]":"A", - "[0-9０-９]":"N" - } - this.chartype_ = []; - for (var i in patterns) { - var regexp = new RegExp; - regexp.compile(i) - this.chartype_.push([regexp, patterns[i]]); - } - - this.BIAS__ = -332 - this.BC1__ = {"HH":6,"II":2461,"KH":406,"OH":-1378}; - this.BC2__ = {"AA":-3267,"AI":2744,"AN":-878,"HH":-4070,"HM":-1711,"HN":4012,"HO":3761,"IA":1327,"IH":-1184,"II":-1332,"IK":1721,"IO":5492,"KI":3831,"KK":-8741,"MH":-3132,"MK":3334,"OO":-2920}; - this.BC3__ = {"HH":996,"HI":626,"HK":-721,"HN":-1307,"HO":-836,"IH":-301,"KK":2762,"MK":1079,"MM":4034,"OA":-1652,"OH":266}; - this.BP1__ = {"BB":295,"OB":304,"OO":-125,"UB":352}; - this.BP2__ = {"BO":60,"OO":-1762}; - this.BQ1__ = {"BHH":1150,"BHM":1521,"BII":-1158,"BIM":886,"BMH":1208,"BNH":449,"BOH":-91,"BOO":-2597,"OHI":451,"OIH":-296,"OKA":1851,"OKH":-1020,"OKK":904,"OOO":2965}; - this.BQ2__ = {"BHH":118,"BHI":-1159,"BHM":466,"BIH":-919,"BKK":-1720,"BKO":864,"OHH":-1139,"OHM":-181,"OIH":153,"UHI":-1146}; - this.BQ3__ = {"BHH":-792,"BHI":2664,"BII":-299,"BKI":419,"BMH":937,"BMM":8335,"BNN":998,"BOH":775,"OHH":2174,"OHM":439,"OII":280,"OKH":1798,"OKI":-793,"OKO":-2242,"OMH":-2402,"OOO":11699}; - this.BQ4__ = {"BHH":-3895,"BIH":3761,"BII":-4654,"BIK":1348,"BKK":-1806,"BMI":-3385,"BOO":-12396,"OAH":926,"OHH":266,"OHK":-2036,"ONN":-973}; - this.BW1__ = {",と":660,",同":727,"B1あ":1404,"B1同":542,"、と":660,"、同":727,"」と":1682,"あっ":1505,"いう":1743,"いっ":-2055,"いる":672,"うし":-4817,"うん":665,"から":3472,"がら":600,"こう":-790,"こと":2083,"こん":-1262,"さら":-4143,"さん":4573,"した":2641,"して":1104,"すで":-3399,"そこ":1977,"それ":-871,"たち":1122,"ため":601,"った":3463,"つい":-802,"てい":805,"てき":1249,"でき":1127,"です":3445,"では":844,"とい":-4915,"とみ":1922,"どこ":3887,"ない":5713,"なっ":3015,"など":7379,"なん":-1113,"にし":2468,"には":1498,"にも":1671,"に対":-912,"の一":-501,"の中":741,"ませ":2448,"まで":1711,"まま":2600,"まる":-2155,"やむ":-1947,"よっ":-2565,"れた":2369,"れで":-913,"をし":1860,"を見":731,"亡く":-1886,"京都":2558,"取り":-2784,"大き":-2604,"大阪":1497,"平方":-2314,"引き":-1336,"日本":-195,"本当":-2423,"毎日":-2113,"目指":-724,"Ｂ１あ":1404,"Ｂ１同":542,"｣と":1682}; - this.BW2__ = {"..":-11822,"11":-669,"――":-5730,"−−":-13175,"いう":-1609,"うか":2490,"かし":-1350,"かも":-602,"から":-7194,"かれ":4612,"がい":853,"がら":-3198,"きた":1941,"くな":-1597,"こと":-8392,"この":-4193,"させ":4533,"され":13168,"さん":-3977,"しい":-1819,"しか":-545,"した":5078,"して":972,"しな":939,"その":-3744,"たい":-1253,"たた":-662,"ただ":-3857,"たち":-786,"たと":1224,"たは":-939,"った":4589,"って":1647,"っと":-2094,"てい":6144,"てき":3640,"てく":2551,"ては":-3110,"ても":-3065,"でい":2666,"でき":-1528,"でし":-3828,"です":-4761,"でも":-4203,"とい":1890,"とこ":-1746,"とと":-2279,"との":720,"とみ":5168,"とも":-3941,"ない":-2488,"なが":-1313,"など":-6509,"なの":2614,"なん":3099,"にお":-1615,"にし":2748,"にな":2454,"によ":-7236,"に対":-14943,"に従":-4688,"に関":-11388,"のか":2093,"ので":-7059,"のに":-6041,"のの":-6125,"はい":1073,"はが":-1033,"はず":-2532,"ばれ":1813,"まし":-1316,"まで":-6621,"まれ":5409,"めて":-3153,"もい":2230,"もの":-10713,"らか":-944,"らし":-1611,"らに":-1897,"りし":651,"りま":1620,"れた":4270,"れて":849,"れば":4114,"ろう":6067,"われ":7901,"を通":-11877,"んだ":728,"んな":-4115,"一人":602,"一方":-1375,"一日":970,"一部":-1051,"上が":-4479,"会社":-1116,"出て":2163,"分の":-7758,"同党":970,"同日":-913,"大阪":-2471,"委員":-1250,"少な":-1050,"年度":-8669,"年間":-1626,"府県":-2363,"手権":-1982,"新聞":-4066,"日新":-722,"日本":-7068,"日米":3372,"曜日":-601,"朝鮮":-2355,"本人":-2697,"東京":-1543,"然と":-1384,"社会":-1276,"立て":-990,"第に":-1612,"米国":-4268,"１１":-669}; - this.BW3__ = {"あた":-2194,"あり":719,"ある":3846,"い.":-1185,"い。":-1185,"いい":5308,"いえ":2079,"いく":3029,"いた":2056,"いっ":1883,"いる":5600,"いわ":1527,"うち":1117,"うと":4798,"えと":1454,"か.":2857,"か。":2857,"かけ":-743,"かっ":-4098,"かに":-669,"から":6520,"かり":-2670,"が,":1816,"が、":1816,"がき":-4855,"がけ":-1127,"がっ":-913,"がら":-4977,"がり":-2064,"きた":1645,"けど":1374,"こと":7397,"この":1542,"ころ":-2757,"さい":-714,"さを":976,"し,":1557,"し、":1557,"しい":-3714,"した":3562,"して":1449,"しな":2608,"しま":1200,"す.":-1310,"す。":-1310,"する":6521,"ず,":3426,"ず、":3426,"ずに":841,"そう":428,"た.":8875,"た。":8875,"たい":-594,"たの":812,"たり":-1183,"たる":-853,"だ.":4098,"だ。":4098,"だっ":1004,"った":-4748,"って":300,"てい":6240,"てお":855,"ても":302,"です":1437,"でに":-1482,"では":2295,"とう":-1387,"とし":2266,"との":541,"とも":-3543,"どう":4664,"ない":1796,"なく":-903,"など":2135,"に,":-1021,"に、":-1021,"にし":1771,"にな":1906,"には":2644,"の,":-724,"の、":-724,"の子":-1000,"は,":1337,"は、":1337,"べき":2181,"まし":1113,"ます":6943,"まっ":-1549,"まで":6154,"まれ":-793,"らし":1479,"られ":6820,"るる":3818,"れ,":854,"れ、":854,"れた":1850,"れて":1375,"れば":-3246,"れる":1091,"われ":-605,"んだ":606,"んで":798,"カ月":990,"会議":860,"入り":1232,"大会":2217,"始め":1681,"市":965,"新聞":-5055,"日,":974,"日、":974,"社会":2024,"ｶ月":990}; - this.TC1__ = {"AAA":1093,"HHH":1029,"HHM":580,"HII":998,"HOH":-390,"HOM":-331,"IHI":1169,"IOH":-142,"IOI":-1015,"IOM":467,"MMH":187,"OOI":-1832}; - this.TC2__ = {"HHO":2088,"HII":-1023,"HMM":-1154,"IHI":-1965,"KKH":703,"OII":-2649}; - this.TC3__ = {"AAA":-294,"HHH":346,"HHI":-341,"HII":-1088,"HIK":731,"HOH":-1486,"IHH":128,"IHI":-3041,"IHO":-1935,"IIH":-825,"IIM":-1035,"IOI":-542,"KHH":-1216,"KKA":491,"KKH":-1217,"KOK":-1009,"MHH":-2694,"MHM":-457,"MHO":123,"MMH":-471,"NNH":-1689,"NNO":662,"OHO":-3393}; - this.TC4__ = {"HHH":-203,"HHI":1344,"HHK":365,"HHM":-122,"HHN":182,"HHO":669,"HIH":804,"HII":679,"HOH":446,"IHH":695,"IHO":-2324,"IIH":321,"III":1497,"IIO":656,"IOO":54,"KAK":4845,"KKA":3386,"KKK":3065,"MHH":-405,"MHI":201,"MMH":-241,"MMM":661,"MOM":841}; - this.TQ1__ = {"BHHH":-227,"BHHI":316,"BHIH":-132,"BIHH":60,"BIII":1595,"BNHH":-744,"BOHH":225,"BOOO":-908,"OAKK":482,"OHHH":281,"OHIH":249,"OIHI":200,"OIIH":-68}; - this.TQ2__ = {"BIHH":-1401,"BIII":-1033,"BKAK":-543,"BOOO":-5591}; - this.TQ3__ = {"BHHH":478,"BHHM":-1073,"BHIH":222,"BHII":-504,"BIIH":-116,"BIII":-105,"BMHI":-863,"BMHM":-464,"BOMH":620,"OHHH":346,"OHHI":1729,"OHII":997,"OHMH":481,"OIHH":623,"OIIH":1344,"OKAK":2792,"OKHH":587,"OKKA":679,"OOHH":110,"OOII":-685}; - this.TQ4__ = {"BHHH":-721,"BHHM":-3604,"BHII":-966,"BIIH":-607,"BIII":-2181,"OAAA":-2763,"OAKK":180,"OHHH":-294,"OHHI":2446,"OHHO":480,"OHIH":-1573,"OIHH":1935,"OIHI":-493,"OIIH":626,"OIII":-4007,"OKAK":-8156}; - this.TW1__ = {"につい":-4681,"東京都":2026}; - this.TW2__ = {"ある程":-2049,"いった":-1256,"ころが":-2434,"しょう":3873,"その後":-4430,"だって":-1049,"ていた":1833,"として":-4657,"ともに":-4517,"もので":1882,"一気に":-792,"初めて":-1512,"同時に":-8097,"大きな":-1255,"対して":-2721,"社会党":-3216}; - this.TW3__ = {"いただ":-1734,"してい":1314,"として":-4314,"につい":-5483,"にとっ":-5989,"に当た":-6247,"ので,":-727,"ので、":-727,"のもの":-600,"れから":-3752,"十二月":-2287}; - this.TW4__ = {"いう.":8576,"いう。":8576,"からな":-2348,"してい":2958,"たが,":1516,"たが、":1516,"ている":1538,"という":1349,"ました":5543,"ません":1097,"ようと":-4258,"よると":5865}; - this.UC1__ = {"A":484,"K":93,"M":645,"O":-505}; - this.UC2__ = {"A":819,"H":1059,"I":409,"M":3987,"N":5775,"O":646}; - this.UC3__ = {"A":-1370,"I":2311}; - this.UC4__ = {"A":-2643,"H":1809,"I":-1032,"K":-3450,"M":3565,"N":3876,"O":6646}; - this.UC5__ = {"H":313,"I":-1238,"K":-799,"M":539,"O":-831}; - this.UC6__ = {"H":-506,"I":-253,"K":87,"M":247,"O":-387}; - this.UP1__ = {"O":-214}; - this.UP2__ = {"B":69,"O":935}; - this.UP3__ = {"B":189}; - this.UQ1__ = {"BH":21,"BI":-12,"BK":-99,"BN":142,"BO":-56,"OH":-95,"OI":477,"OK":410,"OO":-2422}; - this.UQ2__ = {"BH":216,"BI":113,"OK":1759}; - this.UQ3__ = {"BA":-479,"BH":42,"BI":1913,"BK":-7198,"BM":3160,"BN":6427,"BO":14761,"OI":-827,"ON":-3212}; - this.UW1__ = {",":156,"、":156,"「":-463,"あ":-941,"う":-127,"が":-553,"き":121,"こ":505,"で":-201,"と":-547,"ど":-123,"に":-789,"の":-185,"は":-847,"も":-466,"や":-470,"よ":182,"ら":-292,"り":208,"れ":169,"を":-446,"ん":-137,"・":-135,"主":-402,"京":-268,"区":-912,"午":871,"国":-460,"大":561,"委":729,"市":-411,"日":-141,"理":361,"生":-408,"県":-386,"都":-718,"｢":-463,"･":-135}; - this.UW2__ = {",":-829,"、":-829,"〇":892,"「":-645,"」":3145,"あ":-538,"い":505,"う":134,"お":-502,"か":1454,"が":-856,"く":-412,"こ":1141,"さ":878,"ざ":540,"し":1529,"す":-675,"せ":300,"そ":-1011,"た":188,"だ":1837,"つ":-949,"て":-291,"で":-268,"と":-981,"ど":1273,"な":1063,"に":-1764,"の":130,"は":-409,"ひ":-1273,"べ":1261,"ま":600,"も":-1263,"や":-402,"よ":1639,"り":-579,"る":-694,"れ":571,"を":-2516,"ん":2095,"ア":-587,"カ":306,"キ":568,"ッ":831,"三":-758,"不":-2150,"世":-302,"中":-968,"主":-861,"事":492,"人":-123,"会":978,"保":362,"入":548,"初":-3025,"副":-1566,"北":-3414,"区":-422,"大":-1769,"天":-865,"太":-483,"子":-1519,"学":760,"実":1023,"小":-2009,"市":-813,"年":-1060,"強":1067,"手":-1519,"揺":-1033,"政":1522,"文":-1355,"新":-1682,"日":-1815,"明":-1462,"最":-630,"朝":-1843,"本":-1650,"東":-931,"果":-665,"次":-2378,"民":-180,"気":-1740,"理":752,"発":529,"目":-1584,"相":-242,"県":-1165,"立":-763,"第":810,"米":509,"自":-1353,"行":838,"西":-744,"見":-3874,"調":1010,"議":1198,"込":3041,"開":1758,"間":-1257,"｢":-645,"｣":3145,"ｯ":831,"ｱ":-587,"ｶ":306,"ｷ":568}; - this.UW3__ = {",":4889,"1":-800,"−":-1723,"、":4889,"々":-2311,"〇":5827,"」":2670,"〓":-3573,"あ":-2696,"い":1006,"う":2342,"え":1983,"お":-4864,"か":-1163,"が":3271,"く":1004,"け":388,"げ":401,"こ":-3552,"ご":-3116,"さ":-1058,"し":-395,"す":584,"せ":3685,"そ":-5228,"た":842,"ち":-521,"っ":-1444,"つ":-1081,"て":6167,"で":2318,"と":1691,"ど":-899,"な":-2788,"に":2745,"の":4056,"は":4555,"ひ":-2171,"ふ":-1798,"へ":1199,"ほ":-5516,"ま":-4384,"み":-120,"め":1205,"も":2323,"や":-788,"よ":-202,"ら":727,"り":649,"る":5905,"れ":2773,"わ":-1207,"を":6620,"ん":-518,"ア":551,"グ":1319,"ス":874,"ッ":-1350,"ト":521,"ム":1109,"ル":1591,"ロ":2201,"ン":278,"・":-3794,"一":-1619,"下":-1759,"世":-2087,"両":3815,"中":653,"主":-758,"予":-1193,"二":974,"人":2742,"今":792,"他":1889,"以":-1368,"低":811,"何":4265,"作":-361,"保":-2439,"元":4858,"党":3593,"全":1574,"公":-3030,"六":755,"共":-1880,"円":5807,"再":3095,"分":457,"初":2475,"別":1129,"前":2286,"副":4437,"力":365,"動":-949,"務":-1872,"化":1327,"北":-1038,"区":4646,"千":-2309,"午":-783,"協":-1006,"口":483,"右":1233,"各":3588,"合":-241,"同":3906,"和":-837,"員":4513,"国":642,"型":1389,"場":1219,"外":-241,"妻":2016,"学":-1356,"安":-423,"実":-1008,"家":1078,"小":-513,"少":-3102,"州":1155,"市":3197,"平":-1804,"年":2416,"広":-1030,"府":1605,"度":1452,"建":-2352,"当":-3885,"得":1905,"思":-1291,"性":1822,"戸":-488,"指":-3973,"政":-2013,"教":-1479,"数":3222,"文":-1489,"新":1764,"日":2099,"旧":5792,"昨":-661,"時":-1248,"曜":-951,"最":-937,"月":4125,"期":360,"李":3094,"村":364,"東":-805,"核":5156,"森":2438,"業":484,"氏":2613,"民":-1694,"決":-1073,"法":1868,"海":-495,"無":979,"物":461,"特":-3850,"生":-273,"用":914,"町":1215,"的":7313,"直":-1835,"省":792,"県":6293,"知":-1528,"私":4231,"税":401,"立":-960,"第":1201,"米":7767,"系":3066,"約":3663,"級":1384,"統":-4229,"総":1163,"線":1255,"者":6457,"能":725,"自":-2869,"英":785,"見":1044,"調":-562,"財":-733,"費":1777,"車":1835,"軍":1375,"込":-1504,"通":-1136,"選":-681,"郎":1026,"郡":4404,"部":1200,"金":2163,"長":421,"開":-1432,"間":1302,"関":-1282,"雨":2009,"電":-1045,"非":2066,"駅":1620,"１":-800,"｣":2670,"･":-3794,"ｯ":-1350,"ｱ":551,"ｸﾞ":1319,"ｽ":874,"ﾄ":521,"ﾑ":1109,"ﾙ":1591,"ﾛ":2201,"ﾝ":278}; - this.UW4__ = {",":3930,".":3508,"―":-4841,"、":3930,"。":3508,"〇":4999,"「":1895,"」":3798,"〓":-5156,"あ":4752,"い":-3435,"う":-640,"え":-2514,"お":2405,"か":530,"が":6006,"き":-4482,"ぎ":-3821,"く":-3788,"け":-4376,"げ":-4734,"こ":2255,"ご":1979,"さ":2864,"し":-843,"じ":-2506,"す":-731,"ず":1251,"せ":181,"そ":4091,"た":5034,"だ":5408,"ち":-3654,"っ":-5882,"つ":-1659,"て":3994,"で":7410,"と":4547,"な":5433,"に":6499,"ぬ":1853,"ね":1413,"の":7396,"は":8578,"ば":1940,"ひ":4249,"び":-4134,"ふ":1345,"へ":6665,"べ":-744,"ほ":1464,"ま":1051,"み":-2082,"む":-882,"め":-5046,"も":4169,"ゃ":-2666,"や":2795,"ょ":-1544,"よ":3351,"ら":-2922,"り":-9726,"る":-14896,"れ":-2613,"ろ":-4570,"わ":-1783,"を":13150,"ん":-2352,"カ":2145,"コ":1789,"セ":1287,"ッ":-724,"ト":-403,"メ":-1635,"ラ":-881,"リ":-541,"ル":-856,"ン":-3637,"・":-4371,"ー":-11870,"一":-2069,"中":2210,"予":782,"事":-190,"井":-1768,"人":1036,"以":544,"会":950,"体":-1286,"作":530,"側":4292,"先":601,"党":-2006,"共":-1212,"内":584,"円":788,"初":1347,"前":1623,"副":3879,"力":-302,"動":-740,"務":-2715,"化":776,"区":4517,"協":1013,"参":1555,"合":-1834,"和":-681,"員":-910,"器":-851,"回":1500,"国":-619,"園":-1200,"地":866,"場":-1410,"塁":-2094,"士":-1413,"多":1067,"大":571,"子":-4802,"学":-1397,"定":-1057,"寺":-809,"小":1910,"屋":-1328,"山":-1500,"島":-2056,"川":-2667,"市":2771,"年":374,"庁":-4556,"後":456,"性":553,"感":916,"所":-1566,"支":856,"改":787,"政":2182,"教":704,"文":522,"方":-856,"日":1798,"時":1829,"最":845,"月":-9066,"木":-485,"来":-442,"校":-360,"業":-1043,"氏":5388,"民":-2716,"気":-910,"沢":-939,"済":-543,"物":-735,"率":672,"球":-1267,"生":-1286,"産":-1101,"田":-2900,"町":1826,"的":2586,"目":922,"省":-3485,"県":2997,"空":-867,"立":-2112,"第":788,"米":2937,"系":786,"約":2171,"経":1146,"統":-1169,"総":940,"線":-994,"署":749,"者":2145,"能":-730,"般":-852,"行":-792,"規":792,"警":-1184,"議":-244,"谷":-1000,"賞":730,"車":-1481,"軍":1158,"輪":-1433,"込":-3370,"近":929,"道":-1291,"選":2596,"郎":-4866,"都":1192,"野":-1100,"銀":-2213,"長":357,"間":-2344,"院":-2297,"際":-2604,"電":-878,"領":-1659,"題":-792,"館":-1984,"首":1749,"高":2120,"｢":1895,"｣":3798,"･":-4371,"ｯ":-724,"ｰ":-11870,"ｶ":2145,"ｺ":1789,"ｾ":1287,"ﾄ":-403,"ﾒ":-1635,"ﾗ":-881,"ﾘ":-541,"ﾙ":-856,"ﾝ":-3637}; - this.UW5__ = {",":465,".":-299,"1":-514,"E2":-32768,"]":-2762,"、":465,"。":-299,"「":363,"あ":1655,"い":331,"う":-503,"え":1199,"お":527,"か":647,"が":-421,"き":1624,"ぎ":1971,"く":312,"げ":-983,"さ":-1537,"し":-1371,"す":-852,"だ":-1186,"ち":1093,"っ":52,"つ":921,"て":-18,"で":-850,"と":-127,"ど":1682,"な":-787,"に":-1224,"の":-635,"は":-578,"べ":1001,"み":502,"め":865,"ゃ":3350,"ょ":854,"り":-208,"る":429,"れ":504,"わ":419,"を":-1264,"ん":327,"イ":241,"ル":451,"ン":-343,"中":-871,"京":722,"会":-1153,"党":-654,"務":3519,"区":-901,"告":848,"員":2104,"大":-1296,"学":-548,"定":1785,"嵐":-1304,"市":-2991,"席":921,"年":1763,"思":872,"所":-814,"挙":1618,"新":-1682,"日":218,"月":-4353,"査":932,"格":1356,"機":-1508,"氏":-1347,"田":240,"町":-3912,"的":-3149,"相":1319,"省":-1052,"県":-4003,"研":-997,"社":-278,"空":-813,"統":1955,"者":-2233,"表":663,"語":-1073,"議":1219,"選":-1018,"郎":-368,"長":786,"間":1191,"題":2368,"館":-689,"１":-514,"Ｅ２":-32768,"｢":363,"ｲ":241,"ﾙ":451,"ﾝ":-343}; - this.UW6__ = {",":227,".":808,"1":-270,"E1":306,"、":227,"。":808,"あ":-307,"う":189,"か":241,"が":-73,"く":-121,"こ":-200,"じ":1782,"す":383,"た":-428,"っ":573,"て":-1014,"で":101,"と":-105,"な":-253,"に":-149,"の":-417,"は":-236,"も":-206,"り":187,"る":-135,"を":195,"ル":-673,"ン":-496,"一":-277,"中":201,"件":-800,"会":624,"前":302,"区":1792,"員":-1212,"委":798,"学":-960,"市":887,"広":-695,"後":535,"業":-697,"相":753,"社":-507,"福":974,"空":-822,"者":1811,"連":463,"郎":1082,"１":-270,"Ｅ１":306,"ﾙ":-673,"ﾝ":-496}; - - return this; - } - TinySegmenter.prototype.ctype_ = function(str) { - for (var i in this.chartype_) { - if (str.match(this.chartype_[i][0])) { - return this.chartype_[i][1]; - } - } - return "O"; - } - - TinySegmenter.prototype.ts_ = function(v) { - if (v) { return v; } - return 0; - } - - TinySegmenter.prototype.segment = function(input) { - if (input == null || input == undefined || input == "") { - return []; - } - var result = []; - var seg = ["B3","B2","B1"]; - var ctype = ["O","O","O"]; - var o = input.split(""); - for (i = 0; i < o.length; ++i) { - seg.push(o[i]); - ctype.push(this.ctype_(o[i])) - } - seg.push("E1"); - seg.push("E2"); - seg.push("E3"); - ctype.push("O"); - ctype.push("O"); - ctype.push("O"); - var word = seg[3]; - var p1 = "U"; - var p2 = "U"; - var p3 = "U"; - for (var i = 4; i < seg.length - 3; ++i) { - var score = this.BIAS__; - var w1 = seg[i-3]; - var w2 = seg[i-2]; - var w3 = seg[i-1]; - var w4 = seg[i]; - var w5 = seg[i+1]; - var w6 = seg[i+2]; - var c1 = ctype[i-3]; - var c2 = ctype[i-2]; - var c3 = ctype[i-1]; - var c4 = ctype[i]; - var c5 = ctype[i+1]; - var c6 = ctype[i+2]; - score += this.ts_(this.UP1__[p1]); - score += this.ts_(this.UP2__[p2]); - score += this.ts_(this.UP3__[p3]); - score += this.ts_(this.BP1__[p1 + p2]); - score += this.ts_(this.BP2__[p2 + p3]); - score += this.ts_(this.UW1__[w1]); - score += this.ts_(this.UW2__[w2]); - score += this.ts_(this.UW3__[w3]); - score += this.ts_(this.UW4__[w4]); - score += this.ts_(this.UW5__[w5]); - score += this.ts_(this.UW6__[w6]); - score += this.ts_(this.BW1__[w2 + w3]); - score += this.ts_(this.BW2__[w3 + w4]); - score += this.ts_(this.BW3__[w4 + w5]); - score += this.ts_(this.TW1__[w1 + w2 + w3]); - score += this.ts_(this.TW2__[w2 + w3 + w4]); - score += this.ts_(this.TW3__[w3 + w4 + w5]); - score += this.ts_(this.TW4__[w4 + w5 + w6]); - score += this.ts_(this.UC1__[c1]); - score += this.ts_(this.UC2__[c2]); - score += this.ts_(this.UC3__[c3]); - score += this.ts_(this.UC4__[c4]); - score += this.ts_(this.UC5__[c5]); - score += this.ts_(this.UC6__[c6]); - score += this.ts_(this.BC1__[c2 + c3]); - score += this.ts_(this.BC2__[c3 + c4]); - score += this.ts_(this.BC3__[c4 + c5]); - score += this.ts_(this.TC1__[c1 + c2 + c3]); - score += this.ts_(this.TC2__[c2 + c3 + c4]); - score += this.ts_(this.TC3__[c3 + c4 + c5]); - score += this.ts_(this.TC4__[c4 + c5 + c6]); - // score += this.ts_(this.TC5__[c4 + c5 + c6]); - score += this.ts_(this.UQ1__[p1 + c1]); - score += this.ts_(this.UQ2__[p2 + c2]); - score += this.ts_(this.UQ3__[p3 + c3]); - score += this.ts_(this.BQ1__[p2 + c2 + c3]); - score += this.ts_(this.BQ2__[p2 + c3 + c4]); - score += this.ts_(this.BQ3__[p3 + c2 + c3]); - score += this.ts_(this.BQ4__[p3 + c3 + c4]); - score += this.ts_(this.TQ1__[p2 + c1 + c2 + c3]); - score += this.ts_(this.TQ2__[p2 + c2 + c3 + c4]); - score += this.ts_(this.TQ3__[p3 + c1 + c2 + c3]); - score += this.ts_(this.TQ4__[p3 + c2 + c3 + c4]); - var p = "O"; - if (score > 0) { - result.push(word); - word = ""; - p = "B"; - } - p1 = p2; - p2 = p3; - p3 = p; - word += seg[i]; - } - result.push(word); - - return result; - } - - lunr.TinySegmenter = TinySegmenter; - }; - -})); \ No newline at end of file