| [ | |
| { | |
| "name": "whitespace_analyzer", | |
| "description": "A standard whitespace analyzer.", | |
| "behaviours": [ | |
| "Tokenize the text using white space characters as delimeters.", | |
| "Convert all characters to lower case.", | |
| "Convert all alphanumeric and symbolic Unicode characters above the first 127 ASCII characters into their ASCII equivalents." | |
| ], | |
| "tokenizer": "whitespace", | |
| "filters": [ | |
| "lowercase", | |
| "asciifolding" | |
| ] | |
| }, | |
| { | |
| "name": "ngram_analyzer", | |
| "description": "An analyzer which performs ngram filtering on the data stream.", | |
| "behaviours": [ | |
| "Tokenize the text using white space characters as delimeters.", | |
| "Convert all characters to lower case.", | |
| "Convert all alphanumeric and symbolic Unicode characters above the first 127 ASCII characters into their ASCII equivalents.", | |
| "Apply ngram filtering using the following values for minimum and maximum size in codepoints of a single n-gram: minimum = 1, maximum = 2." | |
| ], | |
| "tokenizer": "whitespace", | |
| "filters": [ | |
| "lowercase", | |
| "asciifolding", | |
| "ngram_filter" | |
| ] | |
| } | |
| ] |