diff options
Diffstat (limited to 'search')
-rw-r--r-- | search/lunr.js | 3475 | ||||
-rw-r--r-- | search/main.js | 109 | ||||
-rw-r--r-- | search/search_index.json | 1 | ||||
-rw-r--r-- | search/worker.js | 133 |
4 files changed, 3718 insertions, 0 deletions
diff --git a/search/lunr.js b/search/lunr.js new file mode 100644 index 00000000..aca0a167 --- /dev/null +++ b/search/lunr.js @@ -0,0 +1,3475 @@ +/** + * lunr - http://lunrjs.com - A bit like Solr, but much smaller and not as bright - 2.3.9 + * Copyright (C) 2020 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 = "2.3.9" +/*! + * lunr.utils + * Copyright (C) 2020 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) 2020 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 () { + return this + }, + + 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) 2020 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().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) 2020 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, undefined or an empty string. 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 === null || result === void 0 || result === '') continue + + if (Array.isArray(result)) { + 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) 2020 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) 2020 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) 2020 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.Pi |