diff --git a/config/_default/outputs.toml b/config/_default/outputs.toml index e07b0a9..4cb2b88 100644 --- a/config/_default/outputs.toml +++ b/config/_default/outputs.toml @@ -1,4 +1,4 @@ - home = ["HTML", "RSS"] + home = ["HTML", "RSS", "JSON"] section = ["HTML", "RSS"] page = ["HTML"] taxonomy = ["HTML", "RSS"] diff --git a/content/search/_index.de.md b/content/search/_index.de.md new file mode 100644 index 0000000..d183f4e --- /dev/null +++ b/content/search/_index.de.md @@ -0,0 +1,7 @@ +--- +title: "Volltextsuche" +summary: "Seite nach Stichworten durchsuchen" +date: 2020-10-29 +layout: "search" +--- +{{< search >}} diff --git a/themes/buha/layouts/_default/index.json b/themes/buha/layouts/_default/index.json new file mode 100644 index 0000000..4217717 --- /dev/null +++ b/themes/buha/layouts/_default/index.json @@ -0,0 +1,8 @@ +[ {{- $i := 0 -}} +{{- range where .Site.RegularPages "Section" "ne" "" -}} + {{- if not .Params.noSearch -}} + {{- if gt $i 0 }},{{ end -}} + {"date":"{{ .Date.Unix }}", "url":"{{ .Permalink }}", "title":{{ .Title | jsonify }}, "summary":{{ with .Description}}{{ . | plainify | jsonify }}{{ else }}{{ .Summary | plainify | jsonify }}{{ end }}, "content":{{ .Content | plainify | jsonify }},"tags":[ {{- $t := 0 }}{{- range .Param "tags" -}}{{ if gt $t 0 }},{{ end }}{{ . | jsonify }}{{ $t = add $t 1 }}{{ end -}} ], "section": {{ .Section | jsonify -}} } + {{- $i = add $i 1 -}} + {{- end -}} +{{- end -}} ] diff --git a/themes/buha/layouts/partials/layout/search.html b/themes/buha/layouts/partials/layout/search.html new file mode 100644 index 0000000..e69de29 diff --git a/themes/buha/layouts/shortcodes/search.html b/themes/buha/layouts/shortcodes/search.html new file mode 100644 index 0000000..a18727f --- /dev/null +++ b/themes/buha/layouts/shortcodes/search.html @@ -0,0 +1,58 @@ + + +
+ + + diff --git a/themes/buha/static/js/lunr.js b/themes/buha/static/js/lunr.js new file mode 100644 index 0000000..e7cdb2e --- /dev/null +++ b/themes/buha/static/js/lunr.js @@ -0,0 +1,2742 @@ +/** + * lunr - http://lunrjs.com - A bit like Solr, but much smaller and not as bright - 2.0.2 + * Copyright (C) 2017 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 = "2.0.2" +/*! + * lunr.utils + * Copyright (C) 2017 Oliver Nightingale + */ + +/** + * A namespace containing utils for the rest of the lunr library + */ +lunr.utils = {} + +/** + * Print a warning message to the console. + * + * @param {String} message The message to be printed. + * @memberOf Utils + */ +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 Utils + */ +lunr.utils.asString = function (obj) { + if (obj === void 0 || obj === null) { + return "" + } else { + return obj.toString() + } +} +/** + * 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 + } + + return (documentCount - documentsWithTerm + 0.5) / (documentsWithTerm + 0.5) +} + +/** + * 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) 2017 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. + * + * @static + * @param {?(string|object|object[])} obj - The object to convert into tokens + * @returns {lunr.Token[]} + */ +lunr.tokenizer = function (obj) { + if (obj == null || obj == undefined) { + return [] + } + + if (Array.isArray(obj)) { + return obj.map(function (t) { + return new lunr.Token(lunr.utils.asString(t).toLowerCase()) + }) + } + + 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) { + tokens.push( + new lunr.Token (str.slice(sliceStart, sliceEnd), { + position: [sliceStart, sliceLength], + index: tokens.length + }) + ) + } + + sliceStart = sliceEnd + 1 + } + + } + + return tokens +} + +/** + * The separator used to split a string into tokens. Override this property to change the behaviour of + * `lunr.tokenizer` behaviour when tokenizing strings. By default this splits on whitespace and hyphens. + * + * @static + * @see lunr.tokenizer + */ +lunr.tokenizer.separator = /[\s\-]+/ +/*! + * lunr.Pipeline + * Copyright (C) 2017 Oliver Nightingale + */ + +/** + * lunr.Pipelines maintain an ordered list of functions to be applied to all + * tokens in documents entering the search index and queries being ran against + * the index. + * + * An instance of lunr.Index created with the lunr shortcut will contain a + * pipeline with a stop word filter and an English language stemmer. Extra + * functions can be added before or after either of these functions or these + * default functions can be removed. + * + * When run the pipeline will call each function in turn, passing a token, the + * index of that token in the original list of all tokens and finally a list of + * all the original tokens. + * + * The output of functions in the pipeline will be passed to the next function + * in the pipeline. To exclude a token from entering the index the function + * should return undefined, the rest of the pipeline will not be called with + * this token. + * + * For serialisation of pipelines to work, all functions used in an instance of + * a pipeline should be registered with lunr.Pipeline. Registered functions can + * then be loaded. If trying to load a serialised pipeline that uses functions + * that are not registered an error will be thrown. + * + * If not planning on serialising the pipeline then registering pipeline functions + * is not necessary. + * + * @constructor + */ +lunr.Pipeline = function () { + this._stack = [] +} + +lunr.Pipeline.registeredFunctions = Object.create(null) + +/** + * A pipeline function maps lunr.Token to lunr.Token. A lunr.Token contains the token + * string as well as all known metadata. A pipeline function can mutate the token string + * or mutate (or add) metadata for a given token. + * + * A pipeline function can indicate that the passed token should be discarded by returning + * null. This token will not be passed to any downstream pipeline functions and will not be + * added to the index. + * + * Multiple tokens can be returned by returning an array of tokens. Each token will be passed + * to any downstream pipeline functions and all will returned tokens will be added to the index. + * + * Any number of pipeline functions may be chained together using a lunr.Pipeline. + * + * @interface lunr.PipelineFunction + * @param {lunr.Token} token - A token from the document being processed. + * @param {number} i - The index of this token in the complete list of tokens for this document/field. + * @param {lunr.Token[]} tokens - All tokens for this document/field. + * @returns {(?lunr.Token|lunr.Token[])} + */ + +/** + * Register a function with the pipeline. + * + * Functions that are used in the pipeline should be registered if the pipeline + * needs to be serialised, or a serialised pipeline needs to be loaded. + * + * Registering a function does not add it to a pipeline, functions must still be + * added to instances of the pipeline for them to be used when running a pipeline. + * + * @param {lunr.PipelineFunction} fn - The function to check for. + * @param {String} label - The label to register this function with + */ +lunr.Pipeline.registerFunction = function (fn, label) { + if (label in this.registeredFunctions) { + lunr.utils.warn('Overwriting existing registered function: ' + label) + } + + fn.label = label + lunr.Pipeline.registeredFunctions[fn.label] = fn +} + +/** + * Warns if the function is not registered as a Pipeline function. + * + * @param {lunr.PipelineFunction} fn - The function to check for. + * @private + */ +lunr.Pipeline.warnIfFunctionNotRegistered = function (fn) { + var isRegistered = fn.label && (fn.label in this.registeredFunctions) + + if (!isRegistered) { + lunr.utils.warn('Function is not registered with pipeline. This may cause problems when serialising the index.\n', fn) + } +} + +/** + * Loads a previously serialised pipeline. + * + * All functions to be loaded must already be registered with lunr.Pipeline. + * If any function from the serialised data has not been registered then an + * error will be thrown. + * + * @param {Object} serialised - The serialised pipeline to load. + * @returns {lunr.Pipeline} + */ +lunr.Pipeline.load = function (serialised) { + var pipeline = new lunr.Pipeline + + serialised.forEach(function (fnName) { + var fn = lunr.Pipeline.registeredFunctions[fnName] + + if (fn) { + pipeline.add(fn) + } else { + throw new Error('Cannot load unregistered function: ' + fnName) + } + }) + + return pipeline +} + +/** + * Adds new functions to the end of the pipeline. + * + * Logs a warning if the function has not been registered. + * + * @param {lunr.PipelineFunction[]} functions - Any number of functions to add to the pipeline. + */ +lunr.Pipeline.prototype.add = function () { + var fns = Array.prototype.slice.call(arguments) + + fns.forEach(function (fn) { + lunr.Pipeline.warnIfFunctionNotRegistered(fn) + this._stack.push(fn) + }, this) +} + +/** + * Adds a single function after a function that already exists in the + * pipeline. + * + * Logs a warning if the function has not been registered. + * + * @param {lunr.PipelineFunction} existingFn - A function that already exists in the pipeline. + * @param {lunr.PipelineFunction} newFn - The new function to add to the pipeline. + */ +lunr.Pipeline.prototype.after = function (existingFn, newFn) { + lunr.Pipeline.warnIfFunctionNotRegistered(newFn) + + var pos = this._stack.indexOf(existingFn) + if (pos == -1) { + throw new Error('Cannot find existingFn') + } + + pos = pos + 1 + this._stack.splice(pos, 0, newFn) +} + +/** + * Adds a single function before a function that already exists in the + * pipeline. + * + * Logs a warning if the function has not been registered. + * + * @param {lunr.PipelineFunction} existingFn - A function that already exists in the pipeline. + * @param {lunr.PipelineFunction} newFn - The new function to add to the pipeline. + */ +lunr.Pipeline.prototype.before = function (existingFn, newFn) { + lunr.Pipeline.warnIfFunctionNotRegistered(newFn) + + var pos = this._stack.indexOf(existingFn) + if (pos == -1) { + throw new Error('Cannot find existingFn') + } + + this._stack.splice(pos, 0, newFn) +} + +/** + * Removes a function from the pipeline. + * + * @param {lunr.PipelineFunction} fn The function to remove from the pipeline. + */ +lunr.Pipeline.prototype.remove = function (fn) { + var pos = this._stack.indexOf(fn) + if (pos == -1) { + return + } + + this._stack.splice(pos, 1) +} + +/** + * Runs the current list of functions that make up the pipeline against the + * passed tokens. + * + * @param {Array} tokens The tokens to run through the pipeline. + * @returns {Array} + */ +lunr.Pipeline.prototype.run = function (tokens) { + var stackLength = this._stack.length + + for (var i = 0; i < stackLength; i++) { + var fn = this._stack[i] + + tokens = tokens.reduce(function (memo, token, j) { + var result = fn(token, j, tokens) + + if (result === void 0 || result === '') return memo + + return memo.concat(result) + }, []) + } + + return tokens +} + +/** + * Convenience method for passing a string through a pipeline and getting + * strings out. This method takes care of wrapping the passed string in a + * token and mapping the resulting tokens back to strings. + * + * @param {string} str - The string to pass through the pipeline. + * @returns {string[]} + */ +lunr.Pipeline.prototype.runString = function (str) { + var token = new lunr.Token (str) + + return this.run([token]).map(function (t) { + return t.toString() + }) +} + +/** + * Resets the pipeline by removing any existing processors. + * + */ +lunr.Pipeline.prototype.reset = function () { + this._stack = [] +} + +/** + * Returns a representation of the pipeline ready for serialisation. + * + * Logs a warning if the function has not been registered. + * + * @returns {Array} + */ +lunr.Pipeline.prototype.toJSON = function () { + return this._stack.map(function (fn) { + lunr.Pipeline.warnIfFunctionNotRegistered(fn) + + return fn.label + }) +} +/*! + * lunr.Vector + * Copyright (C) 2017 Oliver Nightingale + */ + +/** + * A vector is used to construct the vector space of documents and queries. These + * vectors support operations to determine the similarity between two documents or + * a document and a query. + * + * Normally no parameters are required for initializing a vector, but in the case of + * loading a previously dumped vector the raw elements can be provided to the constructor. + * + * For performance reasons vectors are implemented with a flat array, where an elements + * index is immediately followed by its value. E.g. [index, value, index, value]. This + * allows the underlying array to be as sparse as possible and still offer decent + * performance when being used for vector calculations. + * + * @constructor + * @param {Number[]} [elements] - The flat list of element index and element value pairs. + */ +lunr.Vector = function (elements) { + this._magnitude = 0 + this.elements = elements || [] +} + +/** + * Inserts an element at an 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. + */ +lunr.Vector.prototype.insert = function (insertIdx, val) { + this._magnitude = 0 + + if (this.elements.length == 0) { + this.elements.push(insertIdx, val) + return + } + + var start = 0, + end = this.elements.length, + sliceLength = end - start, + pivot = Math.floor((sliceLength / 2) / 2) * 2, + pivotIdx = this.elements[pivot] + + while (sliceLength > 2) { + if (pivotIdx == insertIdx) { + throw "duplicate index" + } + + if (insertIdx > pivotIdx) { + start = pivot + } + + if (insertIdx < pivotIdx) { + end = pivot + } + + sliceLength = end - start + pivot = start + Math.floor((sliceLength / 2) / 2) * 2 + pivotIdx = this.elements[pivot] + } + + if (pivotIdx > insertIdx) { + this.elements.splice(pivot, 0, insertIdx, val) + } + + if (pivotIdx < insertIdx) { + this.elements.splice(pivot + 2, 0, insertIdx, val) + } +} + +/** + * Calculates the magnitude of this vector. + * + * @returns {Number} + */ +lunr.Vector.prototype.magnitude = function () { + if (this._magnitude) return this._magnitude + + var sumOfSquares = 0, + elementsLength = this.elements.length + + for (var i = 1; i < elementsLength; i += 2) { + var val = this.elements[i] + sumOfSquares += val * val + } + + return this._magnitude = Math.sqrt(sumOfSquares) +} + +/** + * Calculates the dot product of this vector and another vector. + * + * @param {lunr.Vector} otherVector - The vector to compute the dot product with. + * @returns {Number} + */ +lunr.Vector.prototype.dot = function (otherVector) { + var dotProduct = 0, + a = this.elements, b = otherVector.elements, + aLen = a.length, bLen = b.length, + aVal = 0, bVal = 0, + i = 0, j = 0 + + while (i < aLen && j < bLen) { + aVal = a[i], bVal = b[j] + if (aVal < bVal) { + i += 2 + } else if (aVal > bVal) { + j += 2 + } else if (aVal == bVal) { + dotProduct += a[i + 1] * b[j + 1] + i += 2 + j += 2 + } + } + + return dotProduct +} + +/** + * Calculates the cosine similarity between this vector and another + * vector. + * + * @param {lunr.Vector} otherVector - The other vector to calculate the + * similarity with. + * @returns {Number} + */ +lunr.Vector.prototype.similarity = function (otherVector) { + return this.dot(otherVector) / (this.magnitude() * otherVector.magnitude()) +} + +/** + * Converts the vector to an array of the elements within the vector. + * + * @returns {Number[]} + */ +lunr.Vector.prototype.toArray = function () { + var output = new Array (this.elements.length / 2) + + for (var i = 1, j = 0; i < this.elements.length; i += 2, j++) { + output[j] = this.elements[i] + } + + return output +} + +/** + * A JSON serializable representation of the vector. + * + * @returns {Number[]} + */ +lunr.Vector.prototype.toJSON = function () { + return this.elements +} +/* eslint-disable */ +/*! + * lunr.stemmer + * Copyright (C) 2017 Oliver Nightingale + * Includes code from - http://tartarus.org/~martin/PorterStemmer/js.txt + */ + +/** + * lunr.stemmer is an english language stemmer, this is a JavaScript + * implementation of the PorterStemmer taken from http://tartarus.org/~martin + * + * @static + * @implements {lunr.PipelineFunction} + * @param {lunr.Token} token - The string to stem + * @returns {lunr.Token} + * @see {@link lunr.Pipeline} + */ +lunr.stemmer = (function(){ + var step2list = { + "ational" : "ate", + "tional" : "tion", + "enci" : "ence", + "anci" : "ance", + "izer" : "ize", + "bli" : "ble", + "alli" : "al", + "entli" : "ent", + "eli" : "e", + "ousli" : "ous", + "ization" : "ize", + "ation" : "ate", + "ator" : "ate", + "alism" : "al", + "iveness" : "ive", + "fulness" : "ful", + "ousness" : "ous", + "aliti" : "al", + "iviti" : "ive", + "biliti" : "ble", + "logi" : "log" + }, + + step3list = { + "icate" : "ic", + "ative" : "", + "alize" : "al", + "iciti" : "ic", + "ical" : "ic", + "ful" : "", + "ness" : "" + }, + + c = "[^aeiou]", // consonant + v = "[aeiouy]", // vowel + C = c + "[^aeiouy]*", // consonant sequence + V = v + "[aeiou]*", // vowel sequence + + mgr0 = "^(" + C + ")?" + V + C, // [C]VC... is m>0 + meq1 = "^(" + C + ")?" + V + C + "(" + V + ")?$", // [C]VC[V] is m=1 + mgr1 = "^(" + C + ")?" + V + C + V + C, // [C]VCVC... is m>1 + s_v = "^(" + C + ")?" + v; // vowel in stem + + var re_mgr0 = new RegExp(mgr0); + var re_mgr1 = new RegExp(mgr1); + var re_meq1 = new RegExp(meq1); + var re_s_v = new RegExp(s_v); + + var re_1a = /^(.+?)(ss|i)es$/; + var re2_1a = /^(.+?)([^s])s$/; + var re_1b = /^(.+?)eed$/; + var re2_1b = /^(.+?)(ed|ing)$/; + var re_1b_2 = /.$/; + var re2_1b_2 = /(at|bl|iz)$/; + var re3_1b_2 = new RegExp("([^aeiouylsz])\\1$"); + var re4_1b_2 = new RegExp("^" + C + v + "[^aeiouwxy]$"); + + var re_1c = /^(.+?[^aeiou])y$/; + var re_2 = /^(.+?)(ational|tional|enci|anci|izer|bli|alli|entli|eli|ousli|ization|ation|ator|alism|iveness|fulness|ousness|aliti|iviti|biliti|logi)$/; + + var re_3 = /^(.+?)(icate|ative|alize|iciti|ical|ful|ness)$/; + + var re_4 = /^(.+?)(al|ance|ence|er|ic|able|ible|ant|ement|ment|ent|ou|ism|ate|iti|ous|ive|ize)$/; + var re2_4 = /^(.+?)(s|t)(ion)$/; + + var re_5 = /^(.+?)e$/; + var re_5_1 = /ll$/; + var re3_5 = new RegExp("^" + C + v + "[^aeiouwxy]$"); + + var porterStemmer = function porterStemmer(w) { + var stem, + suffix, + firstch, + re, + re2, + re3, + re4; + + if (w.length < 3) { return w; } + + firstch = w.substr(0,1); + if (firstch == "y") { + w = firstch.toUpperCase() + w.substr(1); + } + + // Step 1a + re = re_1a + re2 = re2_1a; + + if (re.test(w)) { w = w.replace(re,"$1$2"); } + else if (re2.test(w)) { w = w.replace(re2,"$1$2"); } + + // Step 1b + re = re_1b; + re2 = re2_1b; + if (re.test(w)) { + var fp = re.exec(w); + re = re_mgr0; + if (re.test(fp[1])) { + re = re_1b_2; + w = w.replace(re,""); + } + } else if (re2.test(w)) { + var fp = re2.exec(w); + stem = fp[1]; + re2 = re_s_v; + if (re2.test(stem)) { + w = stem; + re2 = re2_1b_2; + re3 = re3_1b_2; + re4 = re4_1b_2; + if (re2.test(w)) { w = w + "e"; } + else if (re3.test(w)) { re = re_1b_2; w = w.replace(re,""); } + else if (re4.test(w)) { w = w + "e"; } + } + } + + // Step 1c - replace suffix y or Y by i if preceded by a non-vowel which is not the first letter of the word (so cry -> cri, by -> by, say -> say) + re = re_1c; + if (re.test(w)) { + var fp = re.exec(w); + stem = fp[1]; + w = stem + "i"; + } + + // Step 2 + re = re_2; + if (re.test(w)) { + var fp = re.exec(w); + stem = fp[1]; + suffix = fp[2]; + re = re_mgr0; + if (re.test(stem)) { + w = stem + step2list[suffix]; + } + } + + // Step 3 + re = re_3; + if (re.test(w)) { + var fp = re.exec(w); + stem = fp[1]; + suffix = fp[2]; + re = re_mgr0; + if (re.test(stem)) { + w = stem + step3list[suffix]; + } + } + + // Step 4 + re = re_4; + re2 = re2_4; + if (re.test(w)) { + var fp = re.exec(w); + stem = fp[1]; + re = re_mgr1; + if (re.test(stem)) { + w = stem; + } + } else if (re2.test(w)) { + var fp = re2.exec(w); + stem = fp[1] + fp[2]; + re2 = re_mgr1; + if (re2.test(stem)) { + w = stem; + } + } + + // Step 5 + re = re_5; + if (re.test(w)) { + var fp = re.exec(w); + stem = fp[1]; + re = re_mgr1; + re2 = re_meq1; + re3 = re3_5; + if (re.test(stem) || (re2.test(stem) && !(re3.test(stem)))) { + w = stem; + } + } + + re = re_5_1; + re2 = re_mgr1; + if (re.test(w) && re2.test(w)) { + re = re_1b_2; + w = w.replace(re,""); + } + + // and turn initial Y back to y + + if (firstch == "y") { + w = firstch.toLowerCase() + w.substr(1); + } + + return w; + }; + + return function (token) { + return token.update(porterStemmer); + } +})(); + +lunr.Pipeline.registerFunction(lunr.stemmer, 'stemmer') +/*! + * lunr.stopWordFilter + * Copyright (C) 2017 Oliver Nightingale + */ + +/** + * lunr.generateStopWordFilter builds a stopWordFilter function from the provided + * list of stop words. + * + * The built in lunr.stopWordFilter is built using this generator and can be used + * to generate custom stopWordFilters for applications or non English languages. + * + * @param {Array} token The token to pass through the filter + * @returns {lunr.PipelineFunction} + * @see lunr.Pipeline + * @see lunr.stopWordFilter + */ +lunr.generateStopWordFilter = function (stopWords) { + var words = stopWords.reduce(function (memo, stopWord) { + memo[stopWord] = stopWord + return memo + }, {}) + + return function (token) { + if (token && words[token.toString()] !== token.toString()) return token + } +} + +/** + * lunr.stopWordFilter is an English language stop word list filter, any words + * contained in the list will not be passed through the filter. + * + * This is intended to be used in the Pipeline. If the token does not pass the + * filter then undefined will be returned. + * + * @implements {lunr.PipelineFunction} + * @params {lunr.Token} token - A token to check for being a stop word. + * @returns {lunr.Token} + * @see {@link lunr.Pipeline} + */ +lunr.stopWordFilter = lunr.generateStopWordFilter([ + 'a', + 'able', + 'about', + 'across', + 'after', + 'all', + 'almost', + 'also', + 'am', + 'among', + 'an', + 'and', + 'any', + 'are', + 'as', + 'at', + 'be', + 'because', + 'been', + 'but', + 'by', + 'can', + 'cannot', + 'could', + 'dear', + 'did', + 'do', + 'does', + 'either', + 'else', + 'ever', + 'every', + 'for', + 'from', + 'get', + 'got', + 'had', + 'has', + 'have', + 'he', + 'her', + 'hers', + 'him', + 'his', + 'how', + 'however', + 'i', + 'if', + 'in', + 'into', + 'is', + 'it', + 'its', + 'just', + 'least', + 'let', + 'like', + 'likely', + 'may', + 'me', + 'might', + 'most', + 'must', + 'my', + 'neither', + 'no', + 'nor', + 'not', + 'of', + 'off', + 'often', + 'on', + 'only', + 'or', + 'other', + 'our', + 'own', + 'rather', + 'said', + 'say', + 'says', + 'she', + 'should', + 'since', + 'so', + 'some', + 'than', + 'that', + 'the', + 'their', + 'them', + 'then', + 'there', + 'these', + 'they', + 'this', + 'tis', + 'to', + 'too', + 'twas', + 'us', + 'wants', + 'was', + 'we', + 'were', + 'what', + 'when', + 'where', + 'which', + 'while', + 'who', + 'whom', + 'why', + 'will', + 'with', + 'would', + 'yet', + 'you', + 'your' +]) + +lunr.Pipeline.registerFunction(lunr.stopWordFilter, 'stopWordFilter') +/*! + * lunr.trimmer + * Copyright (C) 2017 Oliver Nightingale + */ + +/** + * lunr.trimmer is a pipeline function for trimming non word + * characters from the beginning and end of tokens before they + * enter the index. + * + * This implementation may not work correctly for non latin + * characters and should either be removed or adapted for use + * with languages with non-latin characters. + * + * @static + * @implements {lunr.PipelineFunction} + * @param {lunr.Token} token The token to pass through the filter + * @returns {lunr.Token} + * @see lunr.Pipeline + */ +lunr.trimmer = function (token) { + return token.update(function (s) { + return s.replace(/^\W+/, '').replace(/\W+$/, '') + }) +} + +lunr.Pipeline.registerFunction(lunr.trimmer, 'trimmer') +/*! + * lunr.TokenSet + * Copyright (C) 2017 Oliver Nightingale + */ + +/** + * A token set is used to store the unique list of all tokens + * within an index. Token sets are also used to represent an + * incoming query to the index, this query token set and index + * token set are then intersected to find which tokens to look + * up in the inverted index. + * + * A token set can hold multiple tokens, as in the case of the + * index token set, or it can hold a single token as in the + * case of a simple query token set. + * + * Additionally token sets are used to perform wildcard matching. + * Leading, contained and trailing wildcards are supported, and + * from this edit distance matching can also be provided. + * + * Token sets are implemented as a minimal finite state automata, + * where both common prefixes and suffixes are shared between tokens. + * This helps to reduce the space used for storing the token set. + * + * @constructor + */ +lunr.TokenSet = function () { + this.final = false + this.edges = {} + this.id = lunr.TokenSet._nextId + lunr.TokenSet._nextId += 1 +} + +/** + * Keeps track of the next, auto increment, identifier to assign + * to a new tokenSet. + * + * TokenSets require a unique identifier to be correctly minimised. + * + * @private + */ +lunr.TokenSet._nextId = 1 + +/** + * Creates a TokenSet instance from the given sorted array of words. + * + * @param {String[]} arr - A sorted array of strings to create the set from. + * @returns {lunr.TokenSet} + * @throws Will throw an error if the input array is not sorted. + */ +lunr.TokenSet.fromArray = function (arr) { + var builder = new lunr.TokenSet.Builder + + for (var i = 0, len = arr.length; i < len; i++) { + builder.insert(arr[i]) + } + + builder.finish() + return builder.root +} + +/** + * Creates a token set from a query clause. + * + * @private + * @param {Object} clause - A single clause from lunr.Query. + * @param {string} clause.term - The query clause term. + * @param {number} [clause.editDistance] - The optional edit distance for the term. + * @returns {lunr.TokenSet} + */ +lunr.TokenSet.fromClause = function (clause) { + if ('editDistance' in clause) { + return lunr.TokenSet.fromFuzzyString(clause.term, clause.editDistance) + } else { + return lunr.TokenSet.fromString(clause.term) + } +} + +/** + * Creates a token set representing a single string with a specified + * edit distance. + * + * Insertions, deletions, substitutions and transpositions are each + * treated as an edit distance of 1. + * + * Increasing the allowed edit distance will have a dramatic impact + * on the performance of both creating and intersecting these TokenSets. + * It is advised to keep the edit distance less than 3. + * + * @param {string} str - The string to create the token set from. + * @param {number} editDistance - The allowed edit distance to match. + * @returns {lunr.Vector} + */ +lunr.TokenSet.fromFuzzyString = function (str, editDistance) { + var root = new lunr.TokenSet + + var stack = [{ + node: root, + editsRemaining: editDistance, + str: str + }] + + while (stack.length) { + var frame = stack.pop() + + // no edit + if (frame.str.length > 0) { + var char = frame.str.charAt(0), + noEditNode + + if (char in frame.node.edges) { + noEditNode = frame.node.edges[char] + } else { + noEditNode = new lunr.TokenSet + frame.node.edges[char] = noEditNode + } + + if (frame.str.length == 1) { + noEditNode.final = true + } else { + stack.push({ + node: noEditNode, + editsRemaining: frame.editsRemaining, + str: frame.str.slice(1) + }) + } + } + + // deletion + // can only do a deletion if we have enough edits remaining + // and if there are characters left to delete in the string + if (frame.editsRemaining > 0 && frame.str.length > 1) { + var char = frame.str.charAt(1), + deletionNode + + if (char in frame.node.edges) { + deletionNode = frame.node.edges[char] + } else { + deletionNode = new lunr.TokenSet + frame.node.edges[char] = deletionNode + } + + if (frame.str.length <= 2) { + deletionNode.final = true + } else { + stack.push({ + node: deletionNode, + editsRemaining: frame.editsRemaining - 1, + str: frame.str.slice(2) + }) + } + } + + // deletion + // just removing the last character from the str + if (frame.editsRemaining > 0 && frame.str.length == 1) { + frame.node.final = true + } + + // substitution + // can only do a substitution if we have enough edits remaining + // and if there are characters left to substitute + if (frame.editsRemaining > 0 && frame.str.length >= 1) { + if ("*" in frame.node.edges) { + var substitutionNode = frame.node.edges["*"] + } else { + var substitutionNode = new lunr.TokenSet + frame.node.edges["*"] = substitutionNode + } + + if (frame.str.length == 1) { + substitutionNode.final = true + } else { + stack.push({ + node: substitutionNode, + editsRemaining: frame.editsRemaining - 1, + str: frame.str.slice(1) + }) + } + } + + // insertion + // can only do insertion if there are edits remaining + if (frame.editsRemaining > 0) { + if ("*" in frame.node.edges) { + var insertionNode = frame.node.edges["*"] + } else { + var insertionNode = new lunr.TokenSet + frame.node.edges["*"] = insertionNode + } + + if (frame.str.length == 0) { + insertionNode.final = true + } else { + stack.push({ + node: insertionNode, + editsRemaining: frame.editsRemaining - 1, + str: frame.str + }) + } + } + + // transposition + // can only do a transposition if there are edits remaining + // and there are enough characters to transpose + if (frame.editsRemaining > 0 && frame.str.length > 1) { + var charA = frame.str.charAt(0), + charB = frame.str.charAt(1), + transposeNode + + if (charB in frame.node.edges) { + transposeNode = frame.node.edges[charB] + } else { + transposeNode = new lunr.TokenSet + frame.node.edges[charB] = transposeNode + } + + if (frame.str.length == 1) { + transposeNode.final = true + } else { + stack.push({ + node: transposeNode, + editsRemaining: frame.editsRemaining - 1, + str: charA + frame.str.slice(2) + }) + } + } + } + + return root +} + +/** + * Creates a TokenSet from a string. + * + * The string may contain one or more wildcard characters (*) + * that will allow wildcard matching when intersecting with + * another TokenSet. + * + * @param {string} str - The string to create a TokenSet from. + * @returns {lunr.TokenSet} + */ +lunr.TokenSet.fromString = function (str) { + var node = new lunr.TokenSet, + root = node, + wildcardFound = false + + /* + * Iterates through all characters within the passed string + * appending a node for each character. + * + * As soon as a wildcard character is found then a self + * referencing edge is introduced to continually match + * any number of any characters. + */ + for (var i = 0, len = str.length; i < len; i++) { + var char = str[i], + final = (i == len - 1) + + if (char == "*") { + wildcardFound = true + node.edges[char] = node + node.final = final + + } else { + var next = new lunr.TokenSet + next.final = final + + node.edges[char] = next + node = next + + // TODO: is this needed anymore? + if (wildcardFound) { + node.edges["*"] = root + } + } + } + + return root +} + +/** + * Converts this TokenSet into an array of strings + * contained within the TokenSet. + * + * @returns {string[]} + */ +lunr.TokenSet.prototype.toArray = function () { + var words = [] + + var stack = [{ + prefix: "", + node: this + }] + + while (stack.length) { + var frame = stack.pop(), + edges = Object.keys(frame.node.edges), + len = edges.length + + if (frame.node.final) { + words.push(frame.prefix) + } + + for (var i = 0; i < len; i++) { + var edge = edges[i] + + stack.push({ + prefix: frame.prefix.concat(edge), + node: frame.node.edges[edge] + }) + } + } + + return words +} + +/** + * Generates a string representation of a TokenSet. + * + * This is intended to allow TokenSets to be used as keys + * in objects, largely to aid the construction and minimisation + * of a TokenSet. As such it is not designed to be a human + * friendly representation of the TokenSet. + * + * @returns {string} + */ +lunr.TokenSet.prototype.toString = function () { + // NOTE: Using Object.keys here as this.edges is very likely + // to enter 'hash-mode' with many keys being added + // + // avoiding a for-in loop here as it leads to the function + // being de-optimised (at least in V8). From some simple + // benchmarks the performance is comparable, but allowing + // V8 to optimize may mean easy performance wins in the future. + + if (this._str) { + return this._str + } + + var str = this.final ? '1' : '0', + labels = Object.keys(this.edges).sort(), + len = labels.length + + for (var i = 0; i < len; i++) { + var label = labels[i], + node = this.edges[label] + + str = str + label + node.id + } + + return str +} + +/** + * Returns a new TokenSet that is the intersection of + * this TokenSet and the passed TokenSet. + * + * This intersection will take into account any wildcards + * contained within the TokenSet. + * + * @param {lunr.TokenSet} b - An other TokenSet to intersect with. + * @returns {lunr.TokenSet} + */ +lunr.TokenSet.prototype.intersect = function (b) { + var output = new lunr.TokenSet, + frame = undefined + + var stack = [{ + qNode: b, + output: output, + node: this + }] + + while (stack.length) { + frame = stack.pop() + + // NOTE: As with the #toString method, we are using + // Object.keys and a for loop instead of a for-in loop + // as both of these objects enter 'hash' mode, causing + // the function to be de-optimised in V8 + var qEdges = Object.keys(frame.qNode.edges), + qLen = qEdges.length, + nEdges = Object.keys(frame.node.edges), + nLen = nEdges.length + + for (var q = 0; q < qLen; q++) { + var qEdge = qEdges[q] + + for (var n = 0; n < nLen; n++) { + var nEdge = nEdges[n] + + if (nEdge == qEdge || qEdge == '*') { + var node = frame.node.edges[nEdge], + qNode = frame.qNode.edges[qEdge], + final = node.final && qNode.final, + next = undefined + + if (nEdge in frame.output.edges) { + // an edge already exists for this character + // no need to create a new node, just set the finality + // bit unless this node is already final + next = frame.output.edges[nEdge] + next.final = next.final || final + + } else { + // no edge exists yet, must create one + // set the finality bit and insert it + // into the output + next = new lunr.TokenSet + next.final = final + frame.output.edges[nEdge] = next + } + + stack.push({ + qNode: qNode, + output: next, + node: node + }) + } + } + } + } + + return output +} +lunr.TokenSet.Builder = function () { + this.previousWord = "" + this.root = new lunr.TokenSet + this.uncheckedNodes = [] + this.minimizedNodes = {} +} + +lunr.TokenSet.Builder.prototype.insert = function (word) { + var node, + commonPrefix = 0 + + if (word < this.previousWord) { + throw new Error ("Out of order word insertion") + } + + for (var i = 0; i < word.length && i < this.previousWord.length; i++) { + if (word[i] != this.previousWord[i]) break + commonPrefix++ + } + + this.minimize(commonPrefix) + + if (this.uncheckedNodes.length == 0) { + node = this.root + } else { + node = this.uncheckedNodes[this.uncheckedNodes.length - 1].child + } + + for (var i = commonPrefix; i < word.length; i++) { + var nextNode = new lunr.TokenSet, + char = word[i] + + node.edges[char] = nextNode + + this.uncheckedNodes.push({ + parent: node, + char: char, + child: nextNode + }) + + node = nextNode + } + + node.final = true + this.previousWord = word +} + +lunr.TokenSet.Builder.prototype.finish = function () { + this.minimize(0) +} + +lunr.TokenSet.Builder.prototype.minimize = function (downTo) { + for (var i = this.uncheckedNodes.length - 1; i >= downTo; i--) { + var node = this.uncheckedNodes[i], + childKey = node.child.toString() + + if (childKey in this.minimizedNodes) { + node.parent.edges[node.char] = this.minimizedNodes[childKey] + } else { + // Cache the key for this node since + // we know it can't change anymore + node.child._str = childKey + + this.minimizedNodes[childKey] = node.child + } + + this.uncheckedNodes.pop() + } +} +/*! + * lunr.Index + * Copyright (C) 2017 Oliver Nightingale + */ + +/** + * An index contains the built index of all documents and provides a query interface + * to the index. + * + * Usually instances of lunr.Index will not be created using this constructor, instead + * lunr.Builder should be used to construct new indexes, or lunr.Index.load should be + * used to load previously built and serialized indexes. + * + * @constructor + * @param {Object} attrs - The attributes of the built search index. + * @param {Object} attrs.invertedIndex - An index of term/field to document reference. + * @param {Object} attrs.documentVectors - Document vectors keyed by document reference. + * @param {lunr.TokenSet} attrs.tokenSet - An set of all corpus tokens. + * @param {number} attrs.documentCount - The total number of documents held in the index. + * @param {number} attrs.averageDocumentLength - The average length of all documents in the index. + * @param {number} attrs.b - A parameter for the document scoring algorithm. + * @param {number} attrs.k1 - A parameter for the document scoring algorithm. + * @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.documentVectors = attrs.documentVectors + this.tokenSet = attrs.tokenSet + this.documentCount = attrs.documentCount + this.averageDocumentLength = attrs.averageDocumentLength + this.b = attrs.b + this.k1 = attrs.k1 + 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. + * + * @typedef {string} lunr.Index~QueryString + * @example Simple single term query + * hello + * @example Multiple term query + * hello world + * @example term scoped to a field + * title:hello + * @example term with a boost of 10 + * hello^10 + * @example term with an edit distance of 2 + * hello~2 + */ + +/** + * Performs a search against the index using lunr query syntax. + * + * Results will be returned sorted by their score, the most relevant results + * will be returned first. + * + * For more programmatic querying use lunr.Index#query. + * + * @param {lunr.Index~QueryString} queryString - A string containing a lunr query. + * @throws {lunr.QueryParseError} If the passed query string cannot be parsed. + * @returns {lunr.Index~Result[]} + */ +lunr.Index.prototype.search = function (queryString) { + return this.query(function (query) { + var parser = new lunr.QueryParser(queryString, query) + parser.parse() + }) +} + +/** + * A query builder callback provides a query object to be used to express + * the query to perform on the index. + * + * @callback lunr.Index~queryBuilder + * @param {lunr.Query} query - The query object to build up. + * @this lunr.Query + */ + +/** + * Performs a query against the index using the yielded lunr.Query object. + * + * If performing programmatic queries against the index, this method is preferred + * over lunr.Index#search so as to avoid the additional query parsing overhead. + * + * A query object is yielded to the supplied function which should be used to + * express the query to be run against the index. + * + * Note that although this function takes a callback parameter it is _not_ an + * asynchronous operation, the callback is just yielded a query object to be + * customized. + * + * @param {lunr.Index~queryBuilder} fn - A function that is used to build the query. + * @returns {lunr.Index~Result[]} + */ +lunr.Index.prototype.query = function (fn) { + // for each query clause + // * process terms + // * expand terms from token set + // * find matching documents and metadata + // * get document vectors + // * score documents + + var query = new lunr.Query(this.fields), + matchingDocuments = Object.create(null), + queryVector = 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 + + if (clause.usePipeline) { + terms = this.pipeline.runString(clause.term) + } else { + terms = [clause.term] + } + + for (var m = 0; m < terms.length; m++) { + var term = terms[m] + + /* + * Each term returned from the pipeline needs to use the same query + * clause object, e.g. the same boost and or edit distance. The + * simplest way to do this is to re-use the clause object but mutate + * its term property. + */ + clause.term = term + + /* + * From the term in the clause we create a token set which will then + * be used to intersect the indexes token set to get a list of terms + * to lookup in the inverted index + */ + var termTokenSet = lunr.TokenSet.fromClause(clause), + expandedTerms = this.tokenSet.intersect(termTokenSet).toArray() + + for (var j = 0; j < expandedTerms.length; j++) { + /* + * For each term calculate the score as the term relates to the + * query using the same calculation used to score documents during + * indexing. This score will be used to build a vector space + * representation of the query. + * + * Also need to discover the terms index to insert into the query + * vector at the right position + */ + var expandedTerm = expandedTerms[j], + posting = this.invertedIndex[expandedTerm], + termIndex = posting._index, + idf = lunr.idf(posting, this.documentCount), + tf = 1, + score = idf * ((this.k1 + 1) * tf) / (this.k1 * (1 - this.b + this.b * (query.clauses.length / this.averageDocumentLength)) + tf) + + /* + * Inserting the found query term, along with its term index + * into the vector representing the query. It is here that + * any boosts are applied to the score. They could have been + * applied when calculating the score above, but that expression + * is already quite busy. + */ + queryVector.insert(termIndex, score * clause.boost) + + 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) + + 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], + documentMetadata, matchData + + documentMetadata = fieldPosting[matchingDocumentRef] + matchData = new lunr.MatchData (expandedTerm, field, documentMetadata) + + if (matchingDocumentRef in matchingDocuments) { + matchingDocuments[matchingDocumentRef].combine(matchData) + } else { + matchingDocuments[matchingDocumentRef] = matchData + } + + } + } + } + } + } + + var matchingDocumentRefs = Object.keys(matchingDocuments), + results = [] + + for (var i = 0; i < matchingDocumentRefs.length; i++) { + /* + * With all the matching documents found they now need + * to be sorted by their relevance to the query. This + * is done by retrieving the documents vector representation + * and then finding its similarity with the query vector + * that was constructed earlier. + * + * This score, along with the document ref and any metadata + * we collected into a lunr.MatchData instance are stored + * in the results array ready for returning to the caller + */ + var ref = matchingDocumentRefs[i], + documentVector = this.documentVectors[ref], + score = queryVector.similarity(documentVector) + + results.push({ + ref: ref, + score: score, + matchData: matchingDocuments[ref] + }) + } + + 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 documentVectors = Object.keys(this.documentVectors) + .map(function (ref) { + return [ref, this.documentVectors[ref].toJSON()] + }, this) + + return { + version: lunr.version, + averageDocumentLength: this.averageDocumentLength, + b: this.b, + k1: this.k1, + fields: this.fields, + documentVectors: documentVectors, + 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 = {}, + documentVectors = {}, + serializedVectors = serializedIndex.documentVectors, + documentCount = 0, + 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++, documentCount++) { + var tuple = serializedVectors[i], + ref = tuple[0], + elements = tuple[1] + + documentVectors[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.b = serializedIndex.b + attrs.k1 = serializedIndex.k1 + attrs.fields = serializedIndex.fields + attrs.averageDocumentLength = serializedIndex.averageDocumentLength + + attrs.documentCount = documentCount + attrs.documentVectors = documentVectors + attrs.invertedIndex = invertedIndex + attrs.tokenSet = tokenSetBuilder.root + attrs.pipeline = pipeline + + return new lunr.Index(attrs) +} +/*! + * lunr.Builder + * Copyright (C) 2017 Oliver Nightingale + */ + +/** + * lunr.Builder performs indexing on a set of documents and + * returns instances of lunr.Index ready for querying. + * + * All configuration of the index is done via the builder, the + * fields to index, the document reference, the text processing + * pipeline and document scoring parameters are all set on the + * builder before indexing. + * + * @constructor + * @property {string} _ref - Internal reference to the document reference field. + * @property {string[]} _fields - Internal reference to the document fields to index. + * @property {object} invertedIndex - The inverted index maps terms to document fields. + * @property {object} documentTermFrequencies - Keeps track of document term frequencies. + * @property {object} documentLengths - Keeps track of the length of documents added to the index. + * @property {lunr.tokenizer} tokenizer - Function for splitting strings into tokens for indexing. + * @property {lunr.Pipeline} pipeline - The pipeline performs text processing on tokens before indexing. + * @property {lunr.Pipeline} searchPipeline - A pipeline for processing search terms before querying the index. + * @property {number} documentCount - Keeps track of the total number of documents indexed. + * @property {number} _b - A parameter to control field length normalization, setting this to 0 disabled normalization, 1 fully normalizes field lengths, the default value is 0.75. + * @property {number} _k1 - A parameter to control how quickly an increase in term frequency results in term frequency saturation, the default value is 1.2. + * @property {number} termIndex - A counter incremented for each unique term, used to identify a terms position in the vector space. + * @property {array} metadataWhitelist - A list of metadata keys that have been whitelisted for entry in the index. + */ +lunr.Builder = function () { + this._ref = "id" + this._fields = [] + this.invertedIndex = Object.create(null) + this.documentTermFrequencies = {} + this.documentLengths = {} + this.tokenizer = lunr.tokenizer + this.pipeline = new lunr.Pipeline + this.searchPipeline = new lunr.Pipeline + this.documentCount = 0 + this._b = 0.75 + this._k1 = 1.2 + this.termIndex = 0 + this.metadataWhitelist = [] +} + +/** + * Sets the document field used as the document reference. Every document must have this field. + * The type of this field in the document should be a string, if it is not a string it will be + * coerced into a string by calling toString. + * + * The default ref is 'id'. + * + * The ref should _not_ be changed during indexing, it should be set before any documents are + * added to the index. Changing it during indexing can lead to inconsistent results. + * + * @param {string} ref - The name of the reference field in the document. + */ +lunr.Builder.prototype.ref = function (ref) { + this._ref = ref +} + +/** + * Adds a field to the list of document fields that will be indexed. Every document being + * indexed should have this field. Null values for this field in indexed documents will + * not cause errors but will limit the chance of that document being retrieved by searches. + * + * All fields should be added before adding documents to the index. Adding fields after + * a document has been indexed will have no effect on already indexed documents. + * + * @param {string} field - The name of a field to index in all documents. + */ +lunr.Builder.prototype.field = function (field) { + this._fields.push(field) +} + +/** + * A parameter to tune the amount of field length normalisation that is applied when + * calculating relevance scores. A value of 0 will completely disable any normalisation + * and a value of 1 will fully normalise field lengths. The default is 0.75. Values of b + * will be clamped to the range 0 - 1. + * + * @param {number} number - The value to set for this tuning parameter. + */ +lunr.Builder.prototype.b = function (number) { + if (number < 0) { + this._b = 0 + } else if (number > 1) { + this._b = 1 + } else { + this._b = number + } +} + +/** + * A parameter that controls the speed at which a rise in term frequency results in term + * frequency saturation. The default value is 1.2. Setting this to a higher value will give + * slower saturation levels, a lower value will result in quicker saturation. + * + * @param {number} number - The value to set for this tuning parameter. + */ +lunr.Builder.prototype.k1 = function (number) { + this._k1 = number +} + +/** + * Adds a document to the index. + * + * Before adding fields to the index the index should have been fully setup, with the document + * ref and all fields to index already having been specified. + * + * The document must have a field name as specified by the ref (by default this is 'id') and + * it should have all fields defined for indexing, though null or undefined values will not + * cause errors. + * + * @param {object} doc - The document to add to the index. + */ +lunr.Builder.prototype.add = function (doc) { + var docRef = doc[this._ref], + documentTerms = {} + + this.documentCount += 1 + this.documentTermFrequencies[docRef] = documentTerms + this.documentLengths[docRef] = 0 + + for (var i = 0; i < this._fields.length; i++) { + var fieldName = this._fields[i], + field = doc[fieldName], + tokens = this.tokenizer(field), + terms = this.pipeline.run(tokens) + + // store the length of this field for this document + this.documentLengths[docRef] += terms.length + + // calculate term frequencies for this field + for (var j = 0; j < terms.length; j++) { + var term = terms[j] + + if (documentTerms[term] == undefined) { + documentTerms[term] = 0 + } + + documentTerms[term] += 1 + + // add to inverted index + // create an initial posting if one doesn't exist + if (this.invertedIndex[term] == undefined) { + var posting = Object.create(null) + posting["_index"] = this.termIndex + this.termIndex += 1 + + for (var k = 0; k < this._fields.length; k++) { + posting[this._fields[k]] = Object.create(null) + } + + this.invertedIndex[term] = posting + } + + // add an entry for this term/fieldName/docRef to the invertedIndex + if (this.invertedIndex[term][fieldName][docRef] == undefined) { + this.invertedIndex[term][fieldName][docRef] = Object.create(null) + } + + // store all whitelisted metadata about this token in the + // inverted index + for (var l = 0; l < this.metadataWhitelist.length; l++) { + var metadataKey = this.metadataWhitelist[l], + metadata = term.metadata[metadataKey] + + if (this.invertedIndex[term][fieldName][docRef][metadataKey] == undefined) { + this.invertedIndex[term][fieldName][docRef][metadataKey] = [] + } + + this.invertedIndex[term][fieldName][docRef][metadataKey].push(metadata) + } + } + + } +} + +/** + * Calculates the average document length for this index + * + * @private + */ +lunr.Builder.prototype.calculateAverageDocumentLengths = function () { + + var documentRefs = Object.keys(this.documentLengths), + numberOfDocuments = documentRefs.length, + allDocumentsLength = 0 + + for (var i = 0; i < numberOfDocuments; i++) { + var documentRef = documentRefs[i] + allDocumentsLength += this.documentLengths[documentRef] + } + + this.averageDocumentLength = allDocumentsLength / numberOfDocuments +} + +/** + * Builds a vector space model of every document using lunr.Vector + * + * @private + */ +lunr.Builder.prototype.createDocumentVectors = function () { + var documentVectors = {}, + docRefs = Object.keys(this.documentTermFrequencies), + docRefsLength = docRefs.length + + for (var i = 0; i < docRefsLength; i++) { + var docRef = docRefs[i], + documentLength = this.documentLengths[docRef], + documentVector = new lunr.Vector, + termFrequencies = this.documentTermFrequencies[docRef], + terms = Object.keys(termFrequencies), + termsLength = terms.length + + for (var j = 0; j < termsLength; j++) { + var term = terms[j], + tf = termFrequencies[term], + termIndex = this.invertedIndex[term]._index, + idf = lunr.idf(this.invertedIndex[term], this.documentCount), + score = idf * ((this._k1 + 1) * tf) / (this._k1 * (1 - this._b + this._b * (documentLength / this.averageDocumentLength)) + tf), + scoreWithPrecision = Math.round(score * 1000) / 1000 + // Converts 1.23456789 to 1.234. + // Reducing the precision so that the vectors take up less + // space when serialised. Doing it now so that they behave + // the same before and after serialisation. Also, this is + // the fastest approach to reducing a number's precision in + // JavaScript. + + documentVector.insert(termIndex, scoreWithPrecision) + } + + documentVectors[docRef] = documentVector + } + + this.documentVectors = documentVectors +} + +/** + * 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. + * + * @private + * @returns {lunr.Index} + */ +lunr.Builder.prototype.build = function () { + this.calculateAverageDocumentLengths() + this.createDocumentVectors() + this.createTokenSet() + + return new lunr.Index({ + invertedIndex: this.invertedIndex, + documentVectors: this.documentVectors, + tokenSet: this.tokenSet, + averageDocumentLength: this.averageDocumentLength, + documentCount: this.documentCount, + fields: this._fields, + pipeline: this.searchPipeline, + b: this._b, + k1: this._k1 + }) +} + +/** + * 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 + * @property {object} metadata - A collection of metadata associated with this document. + * @see {@link lunr.Index~Result} + */ +lunr.MatchData = function (term, field, metadata) { + this.metadata = {} + this.metadata[term] = {} + this.metadata[term][field] = metadata +} + +/** + * 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] = {} + } + + 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] = {} + } + + 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]) + } + + } + } + } +} +/** + * 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 +} + +/** + * 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 - 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. + */ + +/** + * 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. + * @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 + } + + this.clauses.push(clause) + + return this +} + +/** + * Adds a term to the current query, under the covers this will create a {@link lunr.Query~Clause} + * to the list of clauses that make up this query. + * + * @param {string} term - The term to add to the query. + * @param {Object} [options] - Any additional properties to add to the query clause. + * @returns {lunr.Query} + */ +lunr.Query.prototype.term = function (term, options) { + var clause = options || {} + clause.term = term + + this.clause(clause) + + return this +} +lunr.QueryParseError = function (message, start, end) { + this.name = "QueryParseError" + this.message = message + this.start = start + this.end = end +} + +lunr.QueryParseError.prototype = new Error +lunr.QueryLexer = function (str) { + this.lexemes = [] + this.str = str + this.length = str.length + this.pos = 0 + this.start = 0 +} + +lunr.QueryLexer.prototype.run = function () { + var state = lunr.QueryLexer.lexText + + while (state) { + state = state(this) + } +} + +lunr.QueryLexer.prototype.emit = function (type) { + this.lexemes.push({ + type: type, + str: this.str.slice(this.start, this.pos), + start: this.start, + end: this.pos + }) + + this.start = this.pos +} + +lunr.QueryLexer.prototype.next = function () { + if (this.pos == this.length) { + return lunr.QueryLexer.EOS + } + + var char = this.str.charAt(this.pos) + this.pos += 1 + return char +} + +lunr.QueryLexer.prototype.width = function () { + return this.pos - this.start +} + +lunr.QueryLexer.prototype.ignore = function () { + if (this.start == this.pos) { + this.pos += 1 + } + + this.start = this.pos +} + +lunr.QueryLexer.prototype.backup = function () { + this.pos -= 1 +} + +lunr.QueryLexer.prototype.acceptDigitRun = function () { + var char, charCode + + do { + char = this.next() + charCode = char.charCodeAt(0) + } while (charCode > 47 && charCode < 58) + + if (char != lunr.QueryLexer.EOS) { + this.backup() + } +} + +lunr.QueryLexer.prototype.more = function () { + return this.pos < this.length +} + +lunr.QueryLexer.EOS = 'EOS' +lunr.QueryLexer.FIELD = 'FIELD' +lunr.QueryLexer.TERM = 'TERM' +lunr.QueryLexer.EDIT_DISTANCE = 'EDIT_DISTANCE' +lunr.QueryLexer.BOOST = 'BOOST' + +lunr.QueryLexer.lexField = function (lexer) { + lexer.backup() + lexer.emit(lunr.QueryLexer.FIELD) + lexer.ignore() + return lunr.QueryLexer.lexText +} + +lunr.QueryLexer.lexTerm = function (lexer) { + if (lexer.width() > 1) { + lexer.backup() + lexer.emit(lunr.QueryLexer.TERM) + } + + lexer.ignore() + + if (lexer.more()) { + return lunr.QueryLexer.lexText + } +} + +lunr.QueryLexer.lexEditDistance = function (lexer) { + lexer.ignore() + lexer.acceptDigitRun() + lexer.emit(lunr.QueryLexer.EDIT_DISTANCE) + return lunr.QueryLexer.lexText +} + +lunr.QueryLexer.lexBoost = function (lexer) { + lexer.ignore() + lexer.acceptDigitRun() + lexer.emit(lunr.QueryLexer.BOOST) + return lunr.QueryLexer.lexText +} + +lunr.QueryLexer.lexEOS = function (lexer) { + if (lexer.width() > 0) { + lexer.emit(lunr.QueryLexer.TERM) + } +} + +// This matches the separator used when tokenising fields +// within a document. These should match otherwise it is +// not possible to search for some tokens within a document. +// +// It is possible for the user to change the separator on the +// tokenizer so it _might_ clash with any other of the special +// characters already used within the search string, e.g. :. +// +// This means that it is possible to change the separator in +// such a way that makes some words unsearchable using a search +// string. +lunr.QueryLexer.termSeparator = lunr.tokenizer.separator + +lunr.QueryLexer.lexText = function (lexer) { + while (true) { + var char = lexer.next() + + if (char == lunr.QueryLexer.EOS) { + return lunr.QueryLexer.lexEOS + } + + if (char == ":") { + return lunr.QueryLexer.lexField + } + + if (char == "~") { + lexer.backup() + if (lexer.width() > 0) { + lexer.emit(lunr.QueryLexer.TERM) + } + return lunr.QueryLexer.lexEditDistance + } + + if (char == "^") { + lexer.backup() + if (lexer.width() > 0) { + lexer.emit(lunr.QueryLexer.TERM) + } + return lunr.QueryLexer.lexBoost + } + + if (char.match(lunr.QueryLexer.termSeparator)) { + return lunr.QueryLexer.lexTerm + } + } +} + +lunr.QueryParser = function (str, query) { + this.lexer = new lunr.QueryLexer (str) + this.query = query + this.currentClause = {} + this.lexemeIdx = 0 +} + +lunr.QueryParser.prototype.parse = function () { + this.lexer.run() + this.lexemes = this.lexer.lexemes + + var state = lunr.QueryParser.parseFieldOrTerm + + while (state) { + state = state(this) + } + + return this.query +} + +lunr.QueryParser.prototype.peekLexeme = function () { + return this.lexemes[this.lexemeIdx] +} + +lunr.QueryParser.prototype.consumeLexeme = function () { + var lexeme = this.peekLexeme() + this.lexemeIdx += 1 + return lexeme +} + +lunr.QueryParser.prototype.nextClause = function () { + var completedClause = this.currentClause + this.query.clause(completedClause) + this.currentClause = {} +} + +lunr.QueryParser.parseFieldOrTerm = function (parser) { + var lexeme = parser.peekLexeme() + + if (lexeme == undefined) { + return + } + + switch (lexeme.type) { + case lunr.QueryLexer.FIELD: + return lunr.QueryParser.parseField + case lunr.QueryLexer.TERM: + return lunr.QueryParser.parseTerm + default: + var errorMessage = "expected either a field or a term, found " + lexeme.type + " with value '" + lexeme.str + "'" + throw new lunr.QueryParseError (errorMessage, lexeme.start, lexeme.end) + } +} + +lunr.QueryParser.parseField = function (parser) { + var lexeme = parser.consumeLexeme() + + if (lexeme == undefined) { + return + } + + if (parser.query.allFields.indexOf(lexeme.str) == -1) { + var possibleFields = parser.query.allFields.map(function (f) { return "'" + f + "'" }).join(), + errorMessage = "unrecognised field '" + lexeme.str + "', possible fields: " + possibleFields + + throw new lunr.QueryParseError (errorMessage, lexeme.start, lexeme.end) + } + + parser.currentClause.fields = [lexeme.str] + + var nextLexeme = parser.peekLexeme() + + if (nextLexeme == undefined) { + var errorMessage = "expecting term, found nothing" + throw new lunr.QueryParseError (errorMessage, lexeme.start, lexeme.end) + } + + switch (nextLexeme.type) { + case lunr.QueryLexer.TERM: + return lunr.QueryParser.parseTerm + default: + var errorMessage = "expecting a field, found '" + nextLexeme.type + "'" + throw new lunr.QueryParseError (errorMessage, nextLexeme.start, nextLexeme.end) + } +} + +lunr.QueryParser.parseTerm = function (parser) { + var lexeme = parser.consumeLexeme() + + if (lexeme == undefined) { + return + } + + parser.currentClause.term = lexeme.str.toLowerCase() + + if (lexeme.str.indexOf("*") != -1) { + parser.currentClause.usePipeline = false + } + + var nextLexeme = parser.peekLexeme() + + if (nextLexeme == undefined) { + parser.nextClause() + return + } + + switch (nextLexeme.type) { + case lunr.QueryLexer.TERM: + parser.nextClause() + return lunr.QueryParser.parseTerm + case lunr.QueryLexer.FIELD: + parser.nextClause() + return lunr.QueryParser.parseField + case lunr.QueryLexer.EDIT_DISTANCE: + return lunr.QueryParser.parseEditDistance + case lunr.QueryLexer.BOOST: + return lunr.QueryParser.parseBoost + default: + var errorMessage = "Unexpected lexeme type '" + nextLexeme.type + "'" + throw new lunr.QueryParseError (errorMessage, nextLexeme.start, nextLexeme.end) + } +} + +lunr.QueryParser.parseEditDistance = function (parser) { + var lexeme = parser.consumeLexeme() + + if (lexeme == undefined) { + return + } + + var editDistance = parseInt(lexeme.str, 10) + + if (isNaN(editDistance)) { + var errorMessage = "edit distance must be numeric" + throw new lunr.QueryParseError (errorMessage, lexeme.start, lexeme.end) + } + + parser.currentClause.editDistance = editDistance + + var nextLexeme = parser.peekLexeme() + + if (nextLexeme == undefined) { + parser.nextClause() + return + } + + switch (nextLexeme.type) { + case lunr.QueryLexer.TERM: + parser.nextClause() + return lunr.QueryParser.parseTerm + case lunr.QueryLexer.FIELD: + parser.nextClause() + return lunr.QueryParser.parseField + case lunr.QueryLexer.EDIT_DISTANCE: + return lunr.QueryParser.parseEditDistance + case lunr.QueryLexer.BOOST: + return lunr.QueryParser.parseBoost + default: + var errorMessage = "Unexpected lexeme type '" + nextLexeme.type + "'" + throw new lunr.QueryParseError (errorMessage, nextLexeme.start, nextLexeme.end) + } +} + +lunr.QueryParser.parseBoost = function (parser) { + var lexeme = parser.consumeLexeme() + + if (lexeme == undefined) { + return + } + + var boost = parseInt(lexeme.str, 10) + + if (isNaN(boost)) { + var errorMessage = "boost must be numeric" + throw new lunr.QueryParseError (errorMessage, lexeme.start, lexeme.end) + } + + parser.currentClause.boost = boost + + var nextLexeme = parser.peekLexeme() + + if (nextLexeme == undefined) { + parser.nextClause() + return + } + + switch (nextLexeme.type) { + case lunr.QueryLexer.TERM: + parser.nextClause() + return lunr.QueryParser.parseTerm + case lunr.QueryLexer.FIELD: + parser.nextClause() + return lunr.QueryParser.parseField + case lunr.QueryLexer.EDIT_DISTANCE: + return lunr.QueryParser.parseEditDistance + case lunr.QueryLexer.BOOST: + return lunr.QueryParser.parseBoost + default: + var errorMessage = "Unexpected lexeme type '" + nextLexeme.type + "'" + throw new lunr.QueryParseError (errorMessage, nextLexeme.start, nextLexeme.end) + } +} + + /** + * export the module via AMD, CommonJS or as a browser global + * Export code from https://github.com/umdjs/umd/blob/master/returnExports.js + */ + ;(function (root, factory) { + if (typeof define === 'function' && define.amd) { + // AMD. Register as an anonymous module. + define(factory) + } else if (typeof exports === 'object') { + /** + * Node. Does not work with strict CommonJS, but + * only CommonJS-like enviroments that support module.exports, + * like Node. + */ + module.exports = factory() + } else { + // Browser globals (root is window) + root.lunr = factory() + } + }(this, function () { + /** + * Just return a value to define the module export. + * This example returns an object, but the module + * can return a function as the exported value. + */ + return lunr + })) +})(); diff --git a/themes/buha/static/js/search.js b/themes/buha/static/js/search.js new file mode 100644 index 0000000..9679de1 --- /dev/null +++ b/themes/buha/static/js/search.js @@ -0,0 +1,388 @@ +// JSON based simple full text search with vanilla javascript via XMLHttpRequest, +// (c) 2020 by Tanja Becker - Webdeveleopment, http://tanjabecker.de/ + + +// pass query string by CGI parameter: [URL]?query=[search string] +var query = new URLSearchParams(window.location.search).get("query"); +if ((query != '') && (query != null)) { + document.getElementById("custom-search-field").value = query; +} + +// Debug mode: shows number of hits in the search result. [URL]?debug=1 +let debug = new URLSearchParams(window.location.search).get("debug"); + +let merge_data = []; + +window.addEventListener('load', function() { + document.getElementById("custom-search").querySelectorAll("input").forEach(item => { + item.disabled = 'disabled'; + }); + if (!merge_data.length) { + document.getElementById("custom-search-results").innerHTML = params['json_wait']; + + if (params['json_src'] != '') { + var json_src_str = params['json_src'].replace("/\s/g", ""); + var json_sources = json_src_str.split(","); + + var src_count = 0; + for (var i = 0; i < json_sources.length; i++) { + var xmlhttp = new XMLHttpRequest(); + var url = json_sources[i]; + xmlhttp.onreadystatechange = function() { + if (this.readyState == 4 && this.status == 200) { + var data = JSON.parse(this.responseText); + for (var i = 0; i < data.length; i++) { + merge_data.push(data[i]); + } + src_count++; + + if (src_count == json_sources.length) { + document.getElementById("custom-search").querySelectorAll("input").forEach(item => { + item.disabled = ''; + }); + + document.getElementById("custom-search-field").focus(); + document.getElementById("custom-search-results").innerHTML = params['json_ready']; + + if ((query != '') && (query != null)) { + customSearchResults(); + } + } + } + if (this.status == 404) { + document.getElementById("custom-search-results").innerHTML = params['err_filefailed']; + } + }; + xmlhttp.open("GET", url, true); + xmlhttp.send(); + } + } + } +}, false); + +document.getElementById("custom-search-field").addEventListener('keyup', function(e) { + if (params['autocomplete'] == 1) { + document.getElementById("custom-search-results").innerHTML = ''; + if (this.value == '') { + document.getElementById("custom-search-results").innerHTML = params['err_nostring']; + return false; + } else if (this.value.length < params['minlength']) { + document.getElementById("custom-search-results").innerHTML = params['err_badstring']; + return false; + } else if (this.value.length >= params['minlength']) { + customSearchResults(); + } + } else { + if (this.value == '') { + document.getElementById("custom-search-results").innerHTML = params['err_nostring']; + } + } +}); + +let sForm = document.getElementById("custom-search"); + +if (params['defaultsearch'] != '') { + sForm.querySelectorAll("input[name='option']").forEach(item => { + item.addEventListener('click', event => { + customSearchResults(); + }); + }); +} + +let sSection = ''; +if ((params['section_search'] == 1) && (sForm.elements["section[]"])) { + sSection = sForm.elements["section[]"]; + sForm.querySelectorAll("input[name='section[]']").forEach(item => { + item.addEventListener('click', event => { + if (item.value == 'site') { + if (item.checked) { + sForm.querySelectorAll("input[name='section[]']").forEach(node => { + node.checked = false; + }); + sForm.querySelector("input[value='site']").checked = true; + customSearchResults(); + } + } else { + if (item.checked) { + sForm.querySelector("input[value='site']").checked = false; + } else { + var section_checked = []; + for (var i = 0; i < sSection.length; i++) { + if ((sSection[i].checked) && (sSection[i].value != 'site')) { + section_checked.push(sSection[i].value); + } else { + continue; + } + } + if (section_checked.length < 1) sForm.querySelector("input[value='site']").checked = true; + } + } + if (document.getElementById("custom-search-field").value != '') { + customSearchResults(); + } + }); + }); +} + +function customSearchResults() { + if (!merge_data.length) { + return false; + } + var sOutput = document.getElementById("custom-search-results"); + var sString = document.getElementById("custom-search-field").value; + if (sString == '') { + sOutput.innerHTML = params['err_nostring']; + return false; + } + if (sString.length < params['minlength']) { + sOutput.innerHTML = params['err_badstring']; + return false; + } + + var data = merge_data; + + var add_searchlink = params['add_searchlink']; + if ((add_searchlink) && (add_searchlink != '')) { + add_searchlink = add_searchlink.replace(/\[QUERY\]/g, sString); + } + + var sOption = ''; + var optionField = document.forms["custom-search"]["option"]; + if (optionField) { + sOption = optionField.value; + } else { + sOption = params['defaultsearch']; + } + + var badwords = []; + if (params['badwords'] != '') { + var badwords_str = params['badwords']; + badwords_str = badwords_str.replace("/\s/g", ""); + badwords = badwords_str.split(","); + } + + var words = []; + var search_words = sString.split(" "); + for (var i = 0; i < search_words.length; i++) { + if (badwords.includes(search_words[i])) { + continue; + } else { + words.push(search_words[i]); + } + } + if (!words.length) { + sOutput.innerHTML = params['err_badstring']; + return false; + } + + var section_filter = []; + if (sSection != '') { + for (var i = 0; i < sSection.length; i++) { + if ((sSection[i].checked) && (sSection[i].value != 'site')) { + section_filter.push(sSection[i].value); + } else { + continue; + } + } + } + + var results = []; + for (var i = 0; i < data.length; i++) { + var title = data[i].title; + var summary = data[i].summary; + var content = data[i].content; + var tags = data[i].tags; + var section = data[i].section; + + if (section_filter.length >= 1) { + if (!section_filter.includes(section)) { + continue; + } + } + + var searchtext = ''; + if (title != '') searchtext += title; + if (summary != '') searchtext += ' '+summary; + if (content != '') searchtext += ' '+content; + if (tags != '') searchtext += ' '+tags; + + var matched = 0; + var matches = 0; + var matches_calc = 0; + var title_matches = 0; + var tags_matches = 0; + var summary_matches = 0; + var content_matches = 0; + for (var y = 0; y < words.length; y++) { + var searchword = new RegExp(words[y], 'gi'); + if (searchword.test(searchtext) === true) { + var wordmatches = searchtext.match(searchword); + matches = matches + wordmatches.length; + matches_calc = matches; + + for (var key in searchfield_weight) { + var val = searchfield_weight[key]; + var searchstr = ''; + var count = ''; + if (key == 'title') searchstr = title; + if ((key == 'tags') && (tags != '')) searchstr = tags.join(","); + if (key == 'summary') searchstr = summary; + if (key == 'content') searchstr = content; + + if (searchword.test(searchstr) === true) { + matches_calc = matches_calc + val; + count = searchstr.match(searchword).length; + if (key == 'title') title_matches = title_matches + count; + if ((key == 'tags') && (tags != '')) tags_matches = tags_matches + count; + if (key == 'summary') summary_matches = summary_matches + count; + if (key == 'content') content_matches = content_matches + count; + } + } + matched++; + } + } + data[i]['matches_calc'] = matches_calc; + if ((debug != '') && (debug != null)) { + data[i]['matches'] = matches; + data[i]['title_matches'] = title_matches; + data[i]['tags_matches'] = tags_matches; + data[i]['summary_matches'] = summary_matches; + data[i]['content_matches'] = content_matches; + } + if (sOption == 'OR') { + if (matched >= 1) { + results.push(data[i]); + } + } else { + if (matched == words.length) { + results.push(data[i]); + } + } + } + + // results + if (results.length >= 1) { + results.sort(function(a, b) { + if (params['sort_date'] == 'DESC') { + return b.matches_calc - a.matches_calc || b.date - a.date; + } else { + return b.matches_calc - a.matches_calc || a.date - b.date; + } + }); + + var results_header = ''; + if (results.length > 1) { + results_header = params['res_more_items']; + } else { + results_header = params['res_one_item']; + } + results_header = results_header.replace("[CNT]", results.length); + if ((add_searchlink) && (add_searchlink != '')) { + results_header += add_searchlink; + } + + var tag_top = params['res_out_top']; + var tag_bottom = params['res_out_bottom']; + + var results_content = ''; + for (var i = 0; i < results.length; i++) { + var title = results[i].title; + var summary = results[i].summary; + var date = results[i].date; + var url = results[i].url; + var tags = results[i].tags; + var section = results[i].section; + var extern = results[i].extern; + + // only for debug mode + var infos = ''; + if ((debug != '') && (debug != null)) { + var matches = results[i].matches; + var matches_calc = results[i].matches_calc; + var title_matches = results[i].title_matches; + var tags_matches = results[i].tags_matches; + var summary_matches = results[i].summary_matches; + var content_matches = results[i].content_matches; + + var plus_title = title_matches >=1 ? '+ '+searchfield_weight['title'] : '+ 0'; + var plus_tags = tags_matches >=1 ? '+ '+searchfield_weight['tags'] : '+ 0'; + var plus_summary = summary_matches >=1 ? '+ '+searchfield_weight['summary'] : '+ 0'; + var plus_content = content_matches >=1 ? '+ '+searchfield_weight['content'] : '+ 0'; + + infos += ''; + infos += ''; + infos += ''; + infos += ''; + infos += ''; + infos += ''; + infos += ''; + infos += '
Gesamt:'+matches+'
Title ('+title_matches+'):'+plus_title+'
Tags ('+tags_matches+'):'+plus_tags+'
Summary ('+summary_matches+'):'+plus_summary+'
Content ('+content_matches+'):'+plus_content+'
Gesamt neu:'+matches_calc+'

'; + } + + if ((extern == 1) && (params['extern_icon'])) { + title += ' '+params['extern_icon']; + url = url + '" target="_blank"'; + } + + if (section != '') { + if (section_trans[section] != undefined) { + section = section_trans[section]; + } + } + + var newdate = new Date(date*1000); + var datestr = newdate.toLocaleDateString(); + + var templ = params['res_item_tpl']; + + if (templ) { + templ = templ.replace("[TITLE]", title); + templ = templ.replace(/\[URL\]/g, url); + + if (templ.includes("[DATE]")) { + if (date != '') { + templ = templ.replace("[DATE]", datestr); + } else { + templ = templ.replace("[DATE]", ''); + } + } + if (templ.includes("[SUMMARY]")) { + if (summary != '') { + templ = templ.replace("[SUMMARY]", summary); + } else { + templ = templ.replace("[SUMMARY]", ''); + } + } + if (templ.includes("[TAGS]")) { + if (tags != '') { + tags = tags.join(","); + tags = tags.replace(/,/g, ", "); + templ = templ.replace("[TAGS]", tags); + } else { + templ = templ.replace("[TAGS]", ''); + } + } + if (templ.includes("[SECTION]")) { + if (section != '') { + templ = templ.replace("[SECTION]", '['+section+'] '); + } else { + templ = templ.replace("[SECTION]", ''); + } + } + results_content += templ; + if (infos != '') { + results_content += '
  • '+infos+'
    • '; + } + } + } + sOutput.innerHTML = results_header+tag_top+results_content+tag_bottom; + } else { + var noresult = ''; + if ((add_searchlink) && (add_searchlink != '')) { + noresult += add_searchlink; + } + noresult += params['err_noresult']; + sOutput.innerHTML = noresult; + } +} +