1 | // Type definitions for lunr.js 2.3
|
2 | // Project: https://github.com/olivernn/lunr.js, http://lunrjs.com
|
3 | // Definitions by: Sean Tan <https://github.com/seantanly>, Andrés Pérez <https://github.com/hokiegeek>
|
4 | // Definitions: https://github.com/DefinitelyTyped/DefinitelyTyped
|
5 | // TypeScript Version: 2.3
|
6 |
|
7 | export as namespace lunr;
|
8 | export = lunr;
|
9 |
|
10 | /**
|
11 | * lunr - http://lunrjs.com - A bit like Solr, but much smaller and not as bright
|
12 | * Copyright (C) 2014 Oliver Nightingale
|
13 | * MIT Licensed
|
14 | * @license
|
15 | */
|
16 | declare namespace lunr {
|
17 | namespace Builder {
|
18 | /**
|
19 | * A plugin is a function that is called with the index builder as its context.
|
20 | * Plugins can be used to customise or extend the behaviour of the index
|
21 | * in some way. A plugin is just a function, that encapsulated the custom
|
22 | * behaviour that should be applied when building the index.
|
23 | *
|
24 | * The plugin function will be called with the index builder as its argument, additional
|
25 | * arguments can also be passed when calling use. The function will be called
|
26 | * with the index builder as its context.
|
27 | */
|
28 | type Plugin = (this: Builder, ...args: any[]) => void;
|
29 | }
|
30 |
|
31 | /**
|
32 | * lunr.Builder performs indexing on a set of documents and
|
33 | * returns instances of lunr.Index ready for querying.
|
34 | *
|
35 | * All configuration of the index is done via the builder, the
|
36 | * fields to index, the document reference, the text processing
|
37 | * pipeline and document scoring parameters are all set on the
|
38 | * builder before indexing.
|
39 | */
|
40 | class Builder {
|
41 | /**
|
42 | * Internal reference to the document reference field.
|
43 | */
|
44 | _ref: string;
|
45 |
|
46 | /**
|
47 | * Internal reference to the document fields to index.
|
48 | */
|
49 | _fields: string[];
|
50 |
|
51 | /**
|
52 | * The inverted index maps terms to document fields.
|
53 | */
|
54 | invertedIndex: object;
|
55 |
|
56 | /**
|
57 | * Keeps track of document term frequencies.
|
58 | */
|
59 | documentTermFrequencies: object;
|
60 |
|
61 | /**
|
62 | * Keeps track of the length of documents added to the index.
|
63 | */
|
64 | documentLengths: object;
|
65 |
|
66 | /**
|
67 | * Function for splitting strings into tokens for indexing.
|
68 | */
|
69 | tokenizer: typeof tokenizer;
|
70 |
|
71 | /**
|
72 | * The pipeline performs text processing on tokens before indexing.
|
73 | */
|
74 | pipeline: Pipeline;
|
75 |
|
76 | /**
|
77 | * A pipeline for processing search terms before querying the index.
|
78 | */
|
79 | searchPipeline: Pipeline;
|
80 |
|
81 | /**
|
82 | * Keeps track of the total number of documents indexed.
|
83 | */
|
84 | documentCount: number;
|
85 |
|
86 | /**
|
87 | * A parameter to control field length normalization, setting this to 0 disabled normalization, 1 fully normalizes field lengths, the default value is 0.75.
|
88 | */
|
89 | _b: number;
|
90 |
|
91 | /**
|
92 | * A parameter to control how quickly an increase in term frequency results in term frequency saturation, the default value is 1.2.
|
93 | */
|
94 | _k1: number;
|
95 |
|
96 | /**
|
97 | * A counter incremented for each unique term, used to identify a terms position in the vector space.
|
98 | */
|
99 | termIndex: number;
|
100 |
|
101 | /**
|
102 | * A list of metadata keys that have been whitelisted for entry in the index.
|
103 | */
|
104 | metadataWhitelist: string[];
|
105 |
|
106 | constructor()
|
107 |
|
108 | /**
|
109 | * Sets the document field used as the document reference. Every document must have this field.
|
110 | * The type of this field in the document should be a string, if it is not a string it will be
|
111 | * coerced into a string by calling toString.
|
112 | *
|
113 | * The default ref is 'id'.
|
114 | *
|
115 | * The ref should _not_ be changed during indexing, it should be set before any documents are
|
116 | * added to the index. Changing it during indexing can lead to inconsistent results.
|
117 | *
|
118 | * @param ref - The name of the reference field in the document.
|
119 | */
|
120 | ref(ref: string): void;
|
121 |
|
122 | /**
|
123 | * Adds a field to the list of document fields that will be indexed. Every document being
|
124 | * indexed should have this field. Null values for this field in indexed documents will
|
125 | * not cause errors but will limit the chance of that document being retrieved by searches.
|
126 | *
|
127 | * All fields should be added before adding documents to the index. Adding fields after
|
128 | * a document has been indexed will have no effect on already indexed documents.
|
129 | *
|
130 | * Fields can be boosted at build time. This allows terms within that field to have more
|
131 | * importance when ranking search results. Use a field boost to specify that matches
|
132 | * within one field are more important than other fields.
|
133 | *
|
134 | * @param fieldName - The name of a field to index in all documents.
|
135 | * @param attributes - Optional attributes associated with this field.
|
136 | */
|
137 | field(fieldName: string, attributes?: { boost?: number | undefined, extractor?: ((doc: object) => string | object | object[]) | undefined }): void;
|
138 |
|
139 | /**
|
140 | * A parameter to tune the amount of field length normalisation that is applied when
|
141 | * calculating relevance scores. A value of 0 will completely disable any normalisation
|
142 | * and a value of 1 will fully normalise field lengths. The default is 0.75. Values of b
|
143 | * will be clamped to the range 0 - 1.
|
144 | *
|
145 | * @param number - The value to set for this tuning parameter.
|
146 | */
|
147 | b(number: number): void;
|
148 |
|
149 | /**
|
150 | * A parameter that controls the speed at which a rise in term frequency results in term
|
151 | * frequency saturation. The default value is 1.2. Setting this to a higher value will give
|
152 | * slower saturation levels, a lower value will result in quicker saturation.
|
153 | *
|
154 | * @param number - The value to set for this tuning parameter.
|
155 | */
|
156 | k1(number: number): void;
|
157 |
|
158 | /**
|
159 | * Adds a document to the index.
|
160 | *
|
161 | * Before adding fields to the index the index should have been fully setup, with the document
|
162 | * ref and all fields to index already having been specified.
|
163 | *
|
164 | * The document must have a field name as specified by the ref (by default this is 'id') and
|
165 | * it should have all fields defined for indexing, though null or undefined values will not
|
166 | * cause errors.
|
167 | *
|
168 | * Entire documents can be boosted at build time. Applying a boost to a document indicates that
|
169 | * this document should rank higher in search results than other documents.
|
170 | *
|
171 | * @param doc - The document to add to the index.
|
172 | * @param attributes - Optional attributes associated with this document.
|
173 | */
|
174 | add(doc: object, attributes?: { boost?: number | undefined }): void;
|
175 |
|
176 | /**
|
177 | * Builds the index, creating an instance of lunr.Index.
|
178 | *
|
179 | * This completes the indexing process and should only be called
|
180 | * once all documents have been added to the index.
|
181 | *
|
182 | */
|
183 | build(): Index;
|
184 |
|
185 | /**
|
186 | * Applies a plugin to the index builder.
|
187 | *
|
188 | * A plugin is a function that is called with the index builder as its context.
|
189 | * Plugins can be used to customise or extend the behaviour of the index
|
190 | * in some way. A plugin is just a function, that encapsulated the custom
|
191 | * behaviour that should be applied when building the index.
|
192 | *
|
193 | * The plugin function will be called with the index builder as its argument, additional
|
194 | * arguments can also be passed when calling use. The function will be called
|
195 | * with the index builder as its context.
|
196 | *
|
197 | * @param plugin The plugin to apply.
|
198 | */
|
199 | use(plugin: Builder.Plugin, ...args: any[]): void;
|
200 | }
|
201 |
|
202 | namespace Index {
|
203 | interface Attributes {
|
204 | /**
|
205 | * An index of term/field to document reference.
|
206 | */
|
207 | invertedIndex: object;
|
208 | /**
|
209 | * Document vectors keyed by document reference.
|
210 | */
|
211 | documentVectors: { [docRef: string]: Vector };
|
212 | /**
|
213 | * An set of all corpus tokens.
|
214 | */
|
215 | tokenSet: TokenSet;
|
216 | /**
|
217 | * The names of indexed document fields.
|
218 | */
|
219 | fields: string[];
|
220 | /**
|
221 | * The pipeline to use for search terms.
|
222 | */
|
223 | pipeline: Pipeline;
|
224 | }
|
225 |
|
226 | /**
|
227 | * A result contains details of a document matching a search query.
|
228 | */
|
229 | interface Result {
|
230 | /**
|
231 | * The reference of the document this result represents.
|
232 | */
|
233 | ref: string;
|
234 |
|
235 | /**
|
236 | * A number between 0 and 1 representing how similar this document is to the query.
|
237 | */
|
238 | score: number;
|
239 |
|
240 | /**
|
241 | * Contains metadata about this match including which term(s) caused the match.
|
242 | */
|
243 | matchData: MatchData;
|
244 | }
|
245 |
|
246 | /**
|
247 | * A query builder callback provides a query object to be used to express
|
248 | * the query to perform on the index.
|
249 | *
|
250 | * @param query - The query object to build up.
|
251 | */
|
252 | type QueryBuilder = (this: Query, query: Query) => void;
|
253 |
|
254 | /**
|
255 | * Although lunr provides the ability to create queries using lunr.Query, it also provides a simple
|
256 | * query language which itself is parsed into an instance of lunr.Query.
|
257 | *
|
258 | * For programmatically building queries it is advised to directly use lunr.Query, the query language
|
259 | * is best used for human entered text rather than program generated text.
|
260 | *
|
261 | * At its simplest queries can just be a single term, e.g. `hello`, multiple terms are also supported
|
262 | * and will be combined with OR, e.g `hello world` will match documents that contain either 'hello'
|
263 | * or 'world', though those that contain both will rank higher in the results.
|
264 | *
|
265 | * Wildcards can be included in terms to match one or more unspecified characters, these wildcards can
|
266 | * be inserted anywhere within the term, and more than one wildcard can exist in a single term. Adding
|
267 | * wildcards will increase the number of documents that will be found but can also have a negative
|
268 | * impact on query performance, especially with wildcards at the beginning of a term.
|
269 | *
|
270 | * Terms can be restricted to specific fields, e.g. `title:hello`, only documents with the term
|
271 | * hello in the title field will match this query. Using a field not present in the index will lead
|
272 | * to an error being thrown.
|
273 | *
|
274 | * Modifiers can also be added to terms, lunr supports edit distance and boost modifiers on terms. A term
|
275 | * boost will make documents matching that term score higher, e.g. `foo^5`. Edit distance is also supported
|
276 | * to provide fuzzy matching, e.g. 'hello~2' will match documents with hello with an edit distance of 2.
|
277 | * Avoid large values for edit distance to improve query performance.
|
278 | *
|
279 | * To escape special characters the backslash character '\' can be used, this allows searches to include
|
280 | * characters that would normally be considered modifiers, e.g. `foo\~2` will search for a term "foo~2" instead
|
281 | * of attempting to apply a boost of 2 to the search term "foo".
|
282 | *
|
283 | * @example <caption>Simple single term query</caption>
|
284 | * hello
|
285 | * @example <caption>Multiple term query</caption>
|
286 | * hello world
|
287 | * @example <caption>term scoped to a field</caption>
|
288 | * title:hello
|
289 | * @example <caption>term with a boost of 10</caption>
|
290 | * hello^10
|
291 | * @example <caption>term with an edit distance of 2</caption>
|
292 | * hello~2
|
293 | */
|
294 | type QueryString = string;
|
295 | }
|
296 |
|
297 | /**
|
298 | * An index contains the built index of all documents and provides a query interface
|
299 | * to the index.
|
300 | *
|
301 | * Usually instances of lunr.Index will not be created using this constructor, instead
|
302 | * lunr.Builder should be used to construct new indexes, or lunr.Index.load should be
|
303 | * used to load previously built and serialized indexes.
|
304 | */
|
305 | class Index {
|
306 | /**
|
307 | * @param attrs The attributes of the built search index.
|
308 | */
|
309 | constructor(attrs: Index.Attributes)
|
310 |
|
311 | /**
|
312 | * Performs a search against the index using lunr query syntax.
|
313 | *
|
314 | * Results will be returned sorted by their score, the most relevant results
|
315 | * will be returned first.
|
316 | *
|
317 | * For more programmatic querying use lunr.Index#query.
|
318 | *
|
319 | * @param queryString - A string containing a lunr query.
|
320 | * @throws {lunr.QueryParseError} If the passed query string cannot be parsed.
|
321 | */
|
322 | search(queryString: Index.QueryString): Index.Result[];
|
323 |
|
324 | /**
|
325 | * Performs a query against the index using the yielded lunr.Query object.
|
326 | *
|
327 | * If performing programmatic queries against the index, this method is preferred
|
328 | * over lunr.Index#search so as to avoid the additional query parsing overhead.
|
329 | *
|
330 | * A query object is yielded to the supplied function which should be used to
|
331 | * express the query to be run against the index.
|
332 | *
|
333 | * Note that although this function takes a callback parameter it is _not_ an
|
334 | * asynchronous operation, the callback is just yielded a query object to be
|
335 | * customized.
|
336 | *
|
337 | * @param fn - A function that is used to build the query.
|
338 | */
|
339 | query(fn: Index.QueryBuilder): Index.Result[];
|
340 |
|
341 | /**
|
342 | * Prepares the index for JSON serialization.
|
343 | *
|
344 | * The schema for this JSON blob will be described in a
|
345 | * separate JSON schema file.
|
346 | *
|
347 | */
|
348 | toJSON(): object;
|
349 |
|
350 | /**
|
351 | * Loads a previously serialized lunr.Index
|
352 | *
|
353 | * @param serializedIndex - A previously serialized lunr.Index
|
354 | */
|
355 | static load(serializedIndex: object): Index;
|
356 | }
|
357 |
|
358 | /**
|
359 | * Contains and collects metadata about a matching document.
|
360 | * A single instance of lunr.MatchData is returned as part of every
|
361 | * lunr.IndexResult.
|
362 | */
|
363 | class MatchData {
|
364 | /**
|
365 | * A cloned collection of metadata associated with this document.
|
366 | */
|
367 | metadata: object;
|
368 |
|
369 | /**
|
370 | * @param term - The term this match data is associated with
|
371 | * @param field - The field in which the term was found
|
372 | * @param metadata - The metadata recorded about this term in this field
|
373 | */
|
374 | constructor(term: string, field: string, metadata: object)
|
375 |
|
376 | /**
|
377 | * An instance of lunr.MatchData will be created for every term that matches a
|
378 | * document. However only one instance is required in a lunr.Index~Result. This
|
379 | * method combines metadata from another instance of lunr.MatchData with this
|
380 | * objects metadata.
|
381 | *
|
382 | * @param otherMatchData - Another instance of match data to merge with this one.
|
383 | * @see { lunr.Index~Result}
|
384 | */
|
385 | combine(otherMatchData: MatchData): void;
|
386 | }
|
387 |
|
388 | /**
|
389 | * A pipeline function maps lunr.Token to lunr.Token. A lunr.Token contains the token
|
390 | * string as well as all known metadata. A pipeline function can mutate the token string
|
391 | * or mutate (or add) metadata for a given token.
|
392 | *
|
393 | * A pipeline function can indicate that the passed token should be discarded by returning
|
394 | * null. This token will not be passed to any downstream pipeline functions and will not be
|
395 | * added to the index.
|
396 | *
|
397 | * Multiple tokens can be returned by returning an array of tokens. Each token will be passed
|
398 | * to any downstream pipeline functions and all will returned tokens will be added to the index.
|
399 | *
|
400 | * Any number of pipeline functions may be chained together using a lunr.Pipeline.
|
401 | *
|
402 | * @param token - A token from the document being processed.
|
403 | * @param i - The index of this token in the complete list of tokens for this document/field.
|
404 | * @param tokens - All tokens for this document/field.
|
405 | */
|
406 | type PipelineFunction = (
|
407 | token: Token,
|
408 | i: number,
|
409 | tokens: Token[]
|
410 | ) => null | Token | Token[];
|
411 |
|
412 | /**
|
413 | * lunr.Pipelines maintain an ordered list of functions to be applied to all
|
414 | * tokens in documents entering the search index and queries being ran against
|
415 | * the index.
|
416 | *
|
417 | * An instance of lunr.Index created with the lunr shortcut will contain a
|
418 | * pipeline with a stop word filter and an English language stemmer. Extra
|
419 | * functions can be added before or after either of these functions or these
|
420 | * default functions can be removed.
|
421 | *
|
422 | * When run the pipeline will call each function in turn, passing a token, the
|
423 | * index of that token in the original list of all tokens and finally a list of
|
424 | * all the original tokens.
|
425 | *
|
426 | * The output of functions in the pipeline will be passed to the next function
|
427 | * in the pipeline. To exclude a token from entering the index the function
|
428 | * should return undefined, the rest of the pipeline will not be called with
|
429 | * this token.
|
430 | *
|
431 | * For serialisation of pipelines to work, all functions used in an instance of
|
432 | * a pipeline should be registered with lunr.Pipeline. Registered functions can
|
433 | * then be loaded. If trying to load a serialised pipeline that uses functions
|
434 | * that are not registered an error will be thrown.
|
435 | *
|
436 | * If not planning on serialising the pipeline then registering pipeline functions
|
437 | * is not necessary.
|
438 | */
|
439 | class Pipeline {
|
440 | constructor()
|
441 |
|
442 | /**
|
443 | * Register a function with the pipeline.
|
444 | *
|
445 | * Functions that are used in the pipeline should be registered if the pipeline
|
446 | * needs to be serialised, or a serialised pipeline needs to be loaded.
|
447 | *
|
448 | * Registering a function does not add it to a pipeline, functions must still be
|
449 | * added to instances of the pipeline for them to be used when running a pipeline.
|
450 | *
|
451 | * @param fn - The function to check for.
|
452 | * @param label - The label to register this function with
|
453 | */
|
454 | static registerFunction(fn: PipelineFunction, label: string): void;
|
455 |
|
456 | /**
|
457 | * Loads a previously serialised pipeline.
|
458 | *
|
459 | * All functions to be loaded must already be registered with lunr.Pipeline.
|
460 | * If any function from the serialised data has not been registered then an
|
461 | * error will be thrown.
|
462 | *
|
463 | * @param serialised - The serialised pipeline to load.
|
464 | */
|
465 | static load(serialised: object): Pipeline;
|
466 |
|
467 | /**
|
468 | * Adds new functions to the end of the pipeline.
|
469 | *
|
470 | * Logs a warning if the function has not been registered.
|
471 | *
|
472 | * @param functions - Any number of functions to add to the pipeline.
|
473 | */
|
474 | add(...functions: PipelineFunction[]): void;
|
475 |
|
476 | /**
|
477 | * Adds a single function after a function that already exists in the
|
478 | * pipeline.
|
479 | *
|
480 | * Logs a warning if the function has not been registered.
|
481 | *
|
482 | * @param existingFn - A function that already exists in the pipeline.
|
483 | * @param newFn - The new function to add to the pipeline.
|
484 | */
|
485 | after(existingFn: PipelineFunction, newFn: PipelineFunction): void;
|
486 |
|
487 | /**
|
488 | * Adds a single function before a function that already exists in the
|
489 | * pipeline.
|
490 | *
|
491 | * Logs a warning if the function has not been registered.
|
492 | *
|
493 | * @param existingFn - A function that already exists in the pipeline.
|
494 | * @param newFn - The new function to add to the pipeline.
|
495 | */
|
496 | before(existingFn: PipelineFunction, newFn: PipelineFunction): void;
|
497 |
|
498 | /**
|
499 | * Removes a function from the pipeline.
|
500 | *
|
501 | * @param fn The function to remove from the pipeline.
|
502 | */
|
503 | remove(fn: PipelineFunction): void;
|
504 |
|
505 | /**
|
506 | * Runs the current list of functions that make up the pipeline against the
|
507 | * passed tokens.
|
508 | *
|
509 | * @param tokens The tokens to run through the pipeline.
|
510 | */
|
511 | run(tokens: Token[]): Token[];
|
512 |
|
513 | /**
|
514 | * Convenience method for passing a string through a pipeline and getting
|
515 | * strings out. This method takes care of wrapping the passed string in a
|
516 | * token and mapping the resulting tokens back to strings.
|
517 | *
|
518 | * @param str - The string to pass through the pipeline.
|
519 | */
|
520 | runString(str: string): string[];
|
521 |
|
522 | /**
|
523 | * Resets the pipeline by removing any existing processors.
|
524 | *
|
525 | */
|
526 | reset(): void;
|
527 |
|
528 | /**
|
529 | * Returns a representation of the pipeline ready for serialisation.
|
530 | *
|
531 | * Logs a warning if the function has not been registered.
|
532 | *
|
533 | */
|
534 | toJSON(): PipelineFunction[];
|
535 | }
|
536 |
|
537 | namespace Query {
|
538 | /**
|
539 | * Constants for indicating what kind of presence a term must have in matching documents.
|
540 | */
|
541 | enum presence {
|
542 | /**
|
543 | * Term's presence in a document is optional, this is the default value.
|
544 | */
|
545 | OPTIONAL = 1,
|
546 | /**
|
547 | * Term's presence in a document is required, documents that do not contain this term will not be returned.
|
548 | */
|
549 | REQUIRED = 2,
|
550 | /**
|
551 | * Term's presence in a document is prohibited, documents that do contain this term will not be returned.
|
552 | */
|
553 | PROHIBITED = 3
|
554 | }
|
555 |
|
556 | enum wildcard {
|
557 | NONE = 0,
|
558 | LEADING = 1 << 0,
|
559 | TRAILING = 1 << 1
|
560 | }
|
561 |
|
562 | /**
|
563 | * A single clause in a {@link lunr.Query} contains a term and details on how to
|
564 | * match that term against a {@link lunr.Index}.
|
565 | */
|
566 | interface Clause {
|
567 | term: string;
|
568 | /** The fields in an index this clause should be matched against. */
|
569 | fields: string[];
|
570 | /** Any boost that should be applied when matching this clause. */
|
571 | boost: number;
|
572 | /** Whether the term should have fuzzy matching applied, and how fuzzy the match should be. */
|
573 | editDistance: number;
|
574 | /** Whether the term should be passed through the search pipeline. */
|
575 | usePipeline: boolean;
|
576 | /** Whether the term should have wildcards appended or prepended. */
|
577 | wildcard: number;
|
578 | }
|
579 | }
|
580 |
|
581 | /**
|
582 | * A lunr.Query provides a programmatic way of defining queries to be performed
|
583 | * against a {@link lunr.Index}.
|
584 | *
|
585 | * Prefer constructing a lunr.Query using the {@link lunr.Index#query} method
|
586 | * so the query object is pre-initialized with the right index fields.
|
587 | */
|
588 | class Query {
|
589 | /**
|
590 | * An array of query clauses.
|
591 | */
|
592 | clauses: Query.Clause[];
|
593 |
|
594 | /**
|
595 | * An array of all available fields in a lunr.Index.
|
596 | */
|
597 | allFields: string[];
|
598 |
|
599 | /**
|
600 | * @param allFields An array of all available fields in a lunr.Index.
|
601 | */
|
602 | constructor(allFields: string[])
|
603 |
|
604 | /**
|
605 | * Adds a {this query.
lunr.Query~Clause} to |
606 | *
|
607 | * Unless the clause contains the fields to be matched all fields will be matched. In addition
|
608 | * a default boost of 1 is applied to the clause.
|
609 | *
|
610 | * this query.
clause - The clause to add to |
611 | * lunr.Query~Clause
|
612 | */
|
613 | clause(clause: Query.Clause): Query;
|
614 |
|
615 | /**
|
616 | * Adds a term to the current query, under the covers this will create a {@link lunr.Query~Clause}
|
617 | * to the list of clauses that make up this query.
|
618 | *
|
619 | * The term is used as is, i.e. no tokenization will be performed by this method. Instead conversion
|
620 | * to a token or token-like string should be done before calling this method.
|
621 | *
|
622 | * The term will be converted to a string by calling `toString`. Multiple terms can be passed as an
|
623 | * array, each term in the array will share the same options.
|
624 | *
|
625 | * @param term - The term to add to the query.
|
626 | * @param [options] - Any additional properties to add to the query clause.
|
627 | * @see lunr.Query#clause
|
628 | * @see lunr.Query~Clause
|
629 | * @example <caption>adding a single term to a query</caption>
|
630 | * query.term("foo")
|
631 | * @example <caption>adding a single term to a query and specifying search fields, term boost and automatic trailing wildcard</caption>
|
632 | * query.term("foo", {
|
633 | * fields: ["title"],
|
634 | * boost: 10,
|
635 | * wildcard: lunr.Query.wildcard.TRAILING
|
636 | * })
|
637 | */
|
638 | term(term: string | string[] | Token | Token[], options: object): Query;
|
639 | }
|
640 |
|
641 | class QueryParseError extends Error {
|
642 | name: "QueryParseError";
|
643 | message: string;
|
644 | start: number;
|
645 | end: number;
|
646 |
|
647 | constructor(message: string, start: string, end: string)
|
648 | }
|
649 |
|
650 | /**
|
651 | * lunr.stemmer is an english language stemmer, this is a JavaScript
|
652 | * implementation of the PorterStemmer taken from http://tartarus.org/~martin
|
653 | *
|
654 | * Implements {lunr.PipelineFunction}
|
655 | *
|
656 | * string to stem
token - The |
657 | * { lunr.Pipeline}
|
658 | */
|
659 | function stemmer(token: Token): Token;
|
660 |
|
661 | /**
|
662 | * lunr.generateStopWordFilter builds a stopWordFilter function from the provided
|
663 | * list of stop words.
|
664 | *
|
665 | * The built in lunr.stopWordFilter is built using this generator and can be used
|
666 | * to generate custom stopWordFilters for applications or non English languages.
|
667 | *
|
668 | * @param stopWords - The list of stop words
|
669 | * @see lunr.Pipeline
|
670 | * @see lunr.stopWordFilter
|
671 | */
|
672 | function generateStopWordFilter(stopWords: string[]): PipelineFunction;
|
673 |
|
674 | /**
|
675 | * lunr.stopWordFilter is an English language stop word list filter, any words
|
676 | * contained in the list will not be passed through the filter.
|
677 | *
|
678 | * This is intended to be used in the Pipeline. If the token does not pass the
|
679 | * filter then undefined will be returned.
|
680 | *
|
681 | * Implements {lunr.PipelineFunction}
|
682 | *
|
683 | * @param token - A token to check for being a stop word.
|
684 | * @see {@link lunr.Pipeline}
|
685 | */
|
686 | function stopWordFilter(token: Token): Token;
|
687 |
|
688 | namespace Token {
|
689 | /**
|
690 | * A token update function is used when updating or optionally
|
691 | * when cloning a token.
|
692 | *
|
693 | * @param str - The string representation of the token.
|
694 | * @param metadata - All metadata associated with this token.
|
695 | */
|
696 | type UpdateFunction = (str: string, metadata: object) => void;
|
697 | }
|
698 |
|
699 | /**
|
700 | * A token wraps a string representation of a token
|
701 | * as it is passed through the text processing pipeline.
|
702 | */
|
703 | class Token {
|
704 | /**
|
705 | * @param [str=''] - The string token being wrapped.
|
706 | * @param [metadata={}] - Metadata associated with this token.
|
707 | */
|
708 | constructor(str: string, metadata: object)
|
709 |
|
710 | /**
|
711 | * Returns the token string that is being wrapped by this object.
|
712 | *
|
713 | */
|
714 | toString(): string;
|
715 |
|
716 | /**
|
717 | * Applies the given function to the wrapped string token.
|
718 | *
|
719 | * @example
|
720 | * token.update(function (str, metadata) {
|
721 | * return str.toUpperCase()
|
722 | * })
|
723 | *
|
724 | * @param fn - A function to apply to the token string.
|
725 | */
|
726 | update(fn: Token.UpdateFunction): Token;
|
727 |
|
728 | /**
|
729 | * Creates a clone of this token. Optionally a function can be
|
730 | * applied to the cloned token.
|
731 | *
|
732 | * @param fn - An optional function to apply to the cloned token.
|
733 | */
|
734 | clone(fn?: Token.UpdateFunction): Token;
|
735 | }
|
736 |
|
737 | /**
|
738 | * A token set is used to store the unique list of all tokens
|
739 | * within an index. Token sets are also used to represent an
|
740 | * incoming query to the index, this query token set and index
|
741 | * token set are then intersected to find which tokens to look
|
742 | * up in the inverted index.
|
743 | *
|
744 | * A token set can hold multiple tokens, as in the case of the
|
745 | * index token set, or it can hold a single token as in the
|
746 | * case of a simple query token set.
|
747 | *
|
748 | * Additionally token sets are used to perform wildcard matching.
|
749 | * Leading, contained and trailing wildcards are supported, and
|
750 | * from this edit distance matching can also be provided.
|
751 | *
|
752 | * Token sets are implemented as a minimal finite state automata,
|
753 | * where both common prefixes and suffixes are shared between tokens.
|
754 | * This helps to reduce the space used for storing the token set.
|
755 | */
|
756 | class TokenSet {
|
757 | constructor()
|
758 |
|
759 | /**
|
760 | * Creates a TokenSet instance from the given sorted array of words.
|
761 | *
|
762 | * @param arr - A sorted array of strings to create the set from.
|
763 | * @throws Will throw an error if the input array is not sorted.
|
764 | */
|
765 | fromArray(arr: string[]): TokenSet;
|
766 |
|
767 | /**
|
768 | * Creates a token set representing a single string with a specified
|
769 | * edit distance.
|
770 | *
|
771 | * Insertions, deletions, substitutions and transpositions are each
|
772 | * treated as an edit distance of 1.
|
773 | *
|
774 | * Increasing the allowed edit distance will have a dramatic impact
|
775 | * on the performance of both creating and intersecting these TokenSets.
|
776 | * It is advised to keep the edit distance less than 3.
|
777 | *
|
778 | * @param str - The string to create the token set from.
|
779 | * @param editDistance - The allowed edit distance to match.
|
780 | */
|
781 | fromFuzzyString(str: string, editDistance: number): Vector;
|
782 |
|
783 | /**
|
784 | * Creates a TokenSet from a string.
|
785 | *
|
786 | * The string may contain one or more wildcard characters (*)
|
787 | * that will allow wildcard matching when intersecting with
|
788 | * another TokenSet.
|
789 | *
|
790 | * @param str - The string to create a TokenSet from.
|
791 | */
|
792 | fromString(str: string): TokenSet;
|
793 |
|
794 | /**
|
795 | * Converts this TokenSet into an array of strings
|
796 | * contained within the TokenSet.
|
797 | *
|
798 | */
|
799 | toArray(): string[];
|
800 |
|
801 | /**
|
802 | * Generates a string representation of a TokenSet.
|
803 | *
|
804 | * This is intended to allow TokenSets to be used as keys
|
805 | * in objects, largely to aid the construction and minimisation
|
806 | * of a TokenSet. As such it is not designed to be a human
|
807 | * friendly representation of the TokenSet.
|
808 | *
|
809 | */
|
810 | toString(): string;
|
811 |
|
812 | /**
|
813 | * Returns a new TokenSet that is the intersection of
|
814 | * this TokenSet and the passed TokenSet.
|
815 | *
|
816 | * This intersection will take into account any wildcards
|
817 | * contained within the TokenSet.
|
818 | *
|
819 | * @param b - An other TokenSet to intersect with.
|
820 | */
|
821 | intersect(b: TokenSet): TokenSet;
|
822 | }
|
823 |
|
824 | namespace tokenizer {
|
825 | /**
|
826 | * The separator used to split a string into tokens. Override this property to change the behaviour of
|
827 | * `lunr.tokenizer` behaviour when tokenizing strings. By default this splits on whitespace and hyphens.
|
828 | *
|
829 | * @see lunr.tokenizer
|
830 | */
|
831 | let separator: RegExp;
|
832 | }
|
833 |
|
834 | /**
|
835 | * A function for splitting a string into tokens ready to be inserted into
|
836 | * the search index. Uses `lunr.tokenizer.separator` to split strings, change
|
837 | * the value of this property to change how strings are split into tokens.
|
838 | *
|
839 | * This tokenizer will convert its parameter to a string by calling `toString` and
|
840 | * then will split this string on the character in `lunr.tokenizer.separator`.
|
841 | * Arrays will have their elements converted to strings and wrapped in a lunr.Token.
|
842 | *
|
843 | * @param obj - The object to convert into tokens
|
844 | */
|
845 | function tokenizer(obj?: null | string | object | object[]): Token[];
|
846 |
|
847 | /**
|
848 | * lunr.trimmer is a pipeline function for trimming non word
|
849 | * characters from the beginning and end of tokens before they
|
850 | * enter the index.
|
851 | *
|
852 | * This implementation may not work correctly for non latin
|
853 | * characters and should either be removed or adapted for use
|
854 | * with languages with non-latin characters.
|
855 | *
|
856 | * Implements {lunr.PipelineFunction}
|
857 | *
|
858 | * @param token The token to pass through the filter
|
859 | * @see lunr.Pipeline
|
860 | */
|
861 | function trimmer(token: Token): Token;
|
862 |
|
863 | /**
|
864 | * A namespace containing utils for the rest of the lunr library
|
865 | */
|
866 | namespace utils {
|
867 | /**
|
868 | * Print a warning message to the console.
|
869 | *
|
870 | * @param message The message to be printed.
|
871 | */
|
872 | function warn(message: string): void;
|
873 |
|
874 | /**
|
875 | * Convert an object to a string.
|
876 | *
|
877 | * In the case of `null` and `undefined` the function returns
|
878 | * the empty string, in all other cases the result of calling
|
879 | * `toString` on the passed object is returned.
|
880 | *
|
881 | * @param obj The object to convert to a string.
|
882 | * @return string representation of the passed object.
|
883 | */
|
884 | function asString(obj: any): string;
|
885 | }
|
886 |
|
887 | /**
|
888 | * A vector is used to construct the vector space of documents and queries. These
|
889 | * vectors support operations to determine the similarity between two documents or
|
890 | * a document and a query.
|
891 | *
|
892 | * Normally no parameters are required for initializing a vector, but in the case of
|
893 | * loading a previously dumped vector the raw elements can be provided to the constructor.
|
894 | *
|
895 | * For performance reasons vectors are implemented with a flat array, where an elements
|
896 | * index is immediately followed by its value. E.g. [index, value, index, value]. This
|
897 | * allows the underlying array to be as sparse as possible and still offer decent
|
898 | * performance when being used for vector calculations.
|
899 | */
|
900 | class Vector {
|
901 | /**
|
902 | * @param [elements] - The flat list of element index and element value pairs.
|
903 | */
|
904 | constructor(elements: number[])
|
905 |
|
906 | /**
|
907 | * Calculates the position within the vector to insert a given index.
|
908 | *
|
909 | * This is used internally by insert and upsert. If there are duplicate indexes then
|
910 | * the position is returned as if the value for that index were to be updated, but it
|
911 | * is the callers responsibility to check whether there is a duplicate at that index
|
912 | *
|
913 | * @param insertIdx - The index at which the element should be inserted.
|
914 | */
|
915 | positionForIndex(index: number): number;
|
916 |
|
917 | /**
|
918 | * Inserts an element at an index within the vector.
|
919 | *
|
920 | * Does not allow duplicates, will throw an error if there is already an entry
|
921 | * for this index.
|
922 | *
|
923 | * @param insertIdx - The index at which the element should be inserted.
|
924 | * @param val - The value to be inserted into the vector.
|
925 | */
|
926 | insert(insertIdx: number, val: number): void;
|
927 |
|
928 | /**
|
929 | * Inserts or updates an existing index within the vector.
|
930 | *
|
931 | * @param insertIdx - The index at which the element should be inserted.
|
932 | * @param val - The value to be inserted into the vector.
|
933 | * @param fn - A function that is called for updates, the existing value and the
|
934 | * requested value are passed as arguments
|
935 | */
|
936 | upsert(
|
937 | insertIdx: number,
|
938 | val: number,
|
939 | fn: (existingVal: number, val: number) => number
|
940 | ): void;
|
941 |
|
942 | /**
|
943 | * Calculates the magnitude of this vector.
|
944 | *
|
945 | */
|
946 | magnitude(): number;
|
947 |
|
948 | /**
|
949 | * Calculates the dot product of this vector and another vector.
|
950 | *
|
951 | * @param otherVector - The vector to compute the dot product with.
|
952 | */
|
953 | dot(otherVector: Vector): number;
|
954 |
|
955 | /**
|
956 | * Calculates the cosine similarity between this vector and another
|
957 | * vector.
|
958 | *
|
959 | * @param otherVector - The other vector to calculate the
|
960 | * similarity with.
|
961 | */
|
962 | similarity(otherVector: Vector): number;
|
963 |
|
964 | /**
|
965 | * Converts the vector to an array of the elements within the vector.
|
966 | *
|
967 | */
|
968 | toArray(): number[];
|
969 |
|
970 | /**
|
971 | * A JSON serializable representation of the vector.
|
972 | *
|
973 | */
|
974 | toJSON(): number[];
|
975 | }
|
976 |
|
977 | const version: string;
|
978 | type ConfigFunction = (this: Builder, builder: Builder) => void;
|
979 | }
|
980 |
|
981 | /**
|
982 | * Convenience function for instantiating a new lunr index and configuring it with the default
|
983 | * pipeline functions and the passed config function.
|
984 | *
|
985 | * When using this convenience function a new index will be created with the following functions
|
986 | * already in the pipeline:
|
987 | *
|
988 | * * lunr.StopWordFilter - filters out any stop words before they enter the index
|
989 | *
|
990 | * * lunr.stemmer - stems the tokens before entering the index.
|
991 | *
|
992 | * Example:
|
993 | *
|
994 | * ```javascript
|
995 | * var idx = lunr(function () {
|
996 | * this.field('title', 10);
|
997 | * this.field('tags', 100);
|
998 | * this.field('body');
|
999 | *
|
1000 | * this.ref('cid');
|
1001 | *
|
1002 | * this.pipeline.add(function () {
|
1003 | * // some custom pipeline function
|
1004 | * });
|
1005 | * });
|
1006 | * ```
|
1007 | */
|
1008 | declare function lunr(config: lunr.ConfigFunction): lunr.Index;
|