You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@@ -52,11 +52,11 @@ export class CompoundWordTokenFilterBase extends TokenFilterBase {
52
52
/** If `true`, only include the longest matching subword. Defaults to `false`. */
53
53
only_longest_match?: boolean
54
54
/** A list of subwords to look for in the token stream. If found, the subword is included in the token output.
55
-
* Either this parameter or `word_list_path` must be specified.*/
55
+
* Either this parameter or `word_list_path` must be specified.*/
56
56
word_list?: string[]
57
57
/** Path to a file that contains a list of subwords to find in the token stream. If found, the subword is included in the token output.
58
-
* This path must be absolute or relative to the config location, and the file must be UTF-8 encoded. Each token in the file must be separated by a line break.
59
-
* Either this parameter or `word_list` must be specified. */
58
+
* This path must be absolute or relative to the config location, and the file must be UTF-8 encoded. Each token in the file must be separated by a line break.
59
+
* Either this parameter or `word_list` must be specified. */
60
60
word_list_path?: string
61
61
}
62
62
@@ -67,7 +67,7 @@ export class DictionaryDecompounderTokenFilter extends CompoundWordTokenFilterBa
/** Path to an Apache FOP (Formatting Objects Processor) XML hyphenation pattern file.
70
-
* This path must be absolute or relative to the `config` location. Only FOP v1.2 compatible files are supported. */
70
+
* This path must be absolute or relative to the `config` location. Only FOP v1.2 compatible files are supported. */
71
71
hyphenation_patterns_path: string
72
72
/** If `true`, do not match sub tokens in tokens that are in the word list. Defaults to `false`. */
73
73
no_sub_matches?: boolean
@@ -131,7 +131,7 @@ export class StopTokenFilter extends TokenFilterBase {
131
131
/** Language value, such as `_arabic_` or `_thai_`. Defaults to `_english_`. */
132
132
stopwords?: StopWords
133
133
/** Path to a file that contains a list of stop words to remove.
134
-
* This path must be absolute or relative to the `config` location, and the file must be UTF-8 encoded. Each stop word in the file must be separated by a line break. */
134
+
* This path must be absolute or relative to the `config` location, and the file must be UTF-8 encoded. Each stop word in the file must be separated by a line break. */
135
135
stopwords_path?: string
136
136
}
137
137
@@ -184,7 +184,7 @@ export class WordDelimiterTokenFilterBase extends TokenFilterBase {
184
184
/** Array of tokens the filter won’t split. */
185
185
protected_words?: string[]
186
186
/** Path to a file that contains a list of tokens the filter won’t split.
187
-
* This path must be absolute or relative to the `config` location, and the file must be UTF-8 encoded. Each token in the file must be separated by a line break. */
187
+
* This path must be absolute or relative to the `config` location, and the file must be UTF-8 encoded. Each token in the file must be separated by a line break. */
188
188
protected_words_path?: string
189
189
/** If `true`, the filter splits tokens at letter case transitions. For example: camelCase -> [ camel, Case ]. Defaults to `true`. */
190
190
split_on_case_change?: boolean
@@ -219,18 +219,18 @@ export class AsciiFoldingTokenFilter extends TokenFilterBase {
/** A list of tokens. The filter generates bigrams for these tokens.
222
-
* Either this or the `common_words_path` parameter is required. */
222
+
* Either this or the `common_words_path` parameter is required. */
223
223
common_words?: string[]
224
224
/** Path to a file containing a list of tokens. The filter generates bigrams for these tokens.
225
-
* This path must be absolute or relative to the `config` location. The file must be UTF-8 encoded. Each token in the file must be separated by a line break.
226
-
* Either this or the `common_words` parameter is required. */
225
+
* This path must be absolute or relative to the `config` location. The file must be UTF-8 encoded. Each token in the file must be separated by a line break.
226
+
* Either this or the `common_words` parameter is required. */
227
227
common_words_path?: string
228
228
/** If `true`, matches for common words matching are case-insensitive. Defaults to `false`. */
229
229
ignore_case?: boolean
230
230
/** If `true`, the filter excludes the following tokens from the output:
231
-
* - Unigrams for common words
232
-
* - Unigrams for terms followed by common words
233
-
* Defaults to `false`. We recommend enabling this parameter for search analyzers. */
231
+
* - Unigrams for common words
232
+
* - Unigrams for terms followed by common words
233
+
* Defaults to `false`. We recommend enabling this parameter for search analyzers. */
234
234
query_mode?: boolean
235
235
}
236
236
@@ -245,13 +245,13 @@ export class ConditionTokenFilter extends TokenFilterBase {
* To be removed, the elision must be at the beginning of a token and be immediately followed by an apostrophe. Both the elision and apostrophe are removed.
249
-
* For custom `elision` filters, either this parameter or `articles_path` must be specified. */
248
+
* To be removed, the elision must be at the beginning of a token and be immediately followed by an apostrophe. Both the elision and apostrophe are removed.
249
+
* For custom `elision` filters, either this parameter or `articles_path` must be specified. */
250
250
articles?: string[]
251
251
/** Path to a file that contains a list of elisions to remove.
252
-
* This path must be absolute or relative to the `config` location, and the file must be UTF-8 encoded. Each elision in the file must be separated by a line break.
253
-
* To be removed, the elision must be at the beginning of a token and be immediately followed by an apostrophe. Both the elision and apostrophe are removed.
254
-
* For custom `elision` filters, either this parameter or `articles` must be specified. */
252
+
* This path must be absolute or relative to the `config` location, and the file must be UTF-8 encoded. Each elision in the file must be separated by a line break.
253
+
* To be removed, the elision must be at the beginning of a token and be immediately followed by an apostrophe. Both the elision and apostrophe are removed.
254
+
* For custom `elision` filters, either this parameter or `articles` must be specified. */
255
255
articles_path?: string
256
256
/** If `true`, elision matching is case insensitive. If `false`, elision matching is case sensitive. Defaults to `false`. */
257
257
articles_case?: Stringified<boolean>
@@ -270,10 +270,10 @@ export class HunspellTokenFilter extends TokenFilterBase {
270
270
/** If `true`, duplicate tokens are removed from the filter’s output. Defaults to `true`. */
271
271
dedup?: boolean
272
272
/** One or more `.dic` files (e.g, `en_US.dic`, my_custom.dic) to use for the Hunspell dictionary.
273
-
* By default, the `hunspell` filter uses all `.dic` files in the `<$ES_PATH_CONF>/hunspell/<locale>` directory specified using the `lang`, `language`, or `locale` parameter. */
273
+
* By default, the `hunspell` filter uses all `.dic` files in the `<$ES_PATH_CONF>/hunspell/<locale>` directory specified using the `lang`, `language`, or `locale` parameter. */
274
274
dictionary?: string
275
275
/** Locale directory used to specify the `.aff` and `.dic` files for a Hunspell dictionary.
276
-
* @aliases lang, language */
276
+
* @aliases lang, language */
277
277
locale: string
278
278
/** If `true`, only the longest stemmed version of each token is included in the output. If `false`, all stemmed versions of the token are included. Defaults to `false`. */
279
279
longest_only?: boolean
@@ -295,13 +295,13 @@ export class KeepTypesTokenFilter extends TokenFilterBase {
/** List of words to keep. Only tokens that match words in this list are included in the output.
298
-
* Either this parameter or `keep_words_path` must be specified. */
298
+
* Either this parameter or `keep_words_path` must be specified. */
299
299
keep_words?: string[]
300
300
/** If `true`, lowercase all keep words. Defaults to `false`. */
301
301
keep_words_case?: boolean
302
302
/** Path to a file that contains a list of words to keep. Only tokens that match words in this list are included in the output.
303
-
* This path must be absolute or relative to the `config` location, and the file must be UTF-8 encoded. Each word in the file must be separated by a line break.
304
-
* Either this parameter or `keep_words` must be specified. */
303
+
* This path must be absolute or relative to the `config` location, and the file must be UTF-8 encoded. Each word in the file must be separated by a line break.
304
+
* Either this parameter or `keep_words` must be specified. */
305
305
keep_words_path?: string
306
306
}
307
307
@@ -310,14 +310,14 @@ export class KeywordMarkerTokenFilter extends TokenFilterBase {
310
310
/** If `true`, matching for the `keywords` and `keywords_path` parameters ignores letter case. Defaults to `false`. */
311
311
ignore_case?: boolean
312
312
/** Array of keywords. Tokens that match these keywords are not stemmed.
313
-
* This parameter, `keywords_path`, or `keywords_pattern` must be specified. You cannot specify this parameter and `keywords_pattern`. */
313
+
* This parameter, `keywords_path`, or `keywords_pattern` must be specified. You cannot specify this parameter and `keywords_pattern`. */
314
314
keywords?: string|string[]
315
315
/** Path to a file that contains a list of keywords. Tokens that match these keywords are not stemmed.
316
-
* This path must be absolute or relative to the `config` location, and the file must be UTF-8 encoded. Each word in the file must be separated by a line break.
317
-
* This parameter, `keywords`, or `keywords_pattern` must be specified. You cannot specify this parameter and `keywords_pattern`. */
316
+
* This path must be absolute or relative to the `config` location, and the file must be UTF-8 encoded. Each word in the file must be separated by a line break.
317
+
* This parameter, `keywords`, or `keywords_pattern` must be specified. You cannot specify this parameter and `keywords_pattern`. */
318
318
keywords_path?: string
319
319
/** Java regular expression used to match tokens. Tokens that match this expression are marked as keywords and not stemmed.
320
-
* This parameter, `keywords`, or `keywords_path` must be specified. You cannot specify this parameter and `keywords` or `keywords_pattern`. */
320
+
* This parameter, `keywords`, or `keywords_path` must be specified. You cannot specify this parameter and `keywords` or `keywords_pattern`. */
321
321
keywords_pattern?: string
322
322
}
323
323
@@ -509,7 +509,7 @@ export class MinHashTokenFilter extends TokenFilterBase {
509
509
/** Number of ways to hash each token in the stream. Defaults to `1`. */
510
510
hash_count?: integer
511
511
/** Number of hashes to keep from each bucket. Defaults to `1`.
512
-
* Hashes are retained by ascending size, starting with the bucket’s smallest hash first. */
512
+
* Hashes are retained by ascending size, starting with the bucket’s smallest hash first. */
513
513
hash_set_size?: integer
514
514
/** If `true`, the filter fills empty buckets with the value of the first non-empty bucket to its circular right if the `hash_set_size` is `1`. If the `bucket_count` argument is greater than 1, this parameter defaults to `true`. Otherwise, this parameter defaults to `false`. */
0 commit comments