diff options
Diffstat (limited to 'search-data-service/appconfig/analysis-config.json')
| -rw-r--r-- | search-data-service/appconfig/analysis-config.json | 32 |
1 files changed, 32 insertions, 0 deletions
diff --git a/search-data-service/appconfig/analysis-config.json b/search-data-service/appconfig/analysis-config.json new file mode 100644 index 0000000..f98ea37 --- /dev/null +++ b/search-data-service/appconfig/analysis-config.json @@ -0,0 +1,32 @@ +[ + { + "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" + ] + } +]
\ No newline at end of file |