mirror of
https://github.com/datahub-project/datahub.git
synced 2025-12-28 02:17:53 +00:00
241 lines
5.8 KiB
JSON
241 lines
5.8 KiB
JSON
{
|
|
"settings": {
|
|
"index": {
|
|
"analysis": {
|
|
"filter": {
|
|
"autocomplete_filter": {
|
|
"type": "edge_ngram",
|
|
"min_gram": "3",
|
|
"max_gram": "50"
|
|
},
|
|
"custom_delimiter": {
|
|
"split_on_numerics": "false",
|
|
"split_on_case_change": "false",
|
|
"type": "word_delimiter",
|
|
"preserve_original": "true",
|
|
"catenate_words": "false"
|
|
}
|
|
},
|
|
"char_filter": {
|
|
"dataset_pattern": {
|
|
"pattern": "[.]",
|
|
"type": "pattern_replace",
|
|
"replacement": "/"
|
|
}
|
|
},
|
|
"normalizer": {
|
|
"my_normalizer": {
|
|
"filter": [
|
|
"lowercase"
|
|
],
|
|
"type": "custom"
|
|
}
|
|
},
|
|
"analyzer": {
|
|
"whitespace_lowercase": {
|
|
"filter": [
|
|
"lowercase"
|
|
],
|
|
"tokenizer": "whitespace"
|
|
},
|
|
"slash_pattern": {
|
|
"filter": [
|
|
"lowercase"
|
|
],
|
|
"type": "custom",
|
|
"tokenizer": "slash_tokenizer"
|
|
},
|
|
"dataset_pattern": {
|
|
"filter": [
|
|
"lowercase"
|
|
],
|
|
"type": "custom",
|
|
"tokenizer": "dataset_pattern"
|
|
},
|
|
"comma_pattern": {
|
|
"filter": [
|
|
"lowercase"
|
|
],
|
|
"type": "custom",
|
|
"tokenizer": "comma_tokenizer"
|
|
},
|
|
"custom_browse": {
|
|
"filter": [
|
|
"lowercase"
|
|
],
|
|
"type": "custom",
|
|
"tokenizer": "path_hierarchy_tokenizer"
|
|
},
|
|
"custom_ngram": {
|
|
"filter": [
|
|
"lowercase"
|
|
],
|
|
"type": "custom",
|
|
"tokenizer": "custom_ngram"
|
|
},
|
|
"custom_keyword": {
|
|
"filter": [
|
|
"lowercase"
|
|
],
|
|
"type": "custom",
|
|
"tokenizer": "keyword"
|
|
},
|
|
"comma_pattern_ngram": {
|
|
"filter": [
|
|
"lowercase",
|
|
"autocomplete_filter"
|
|
],
|
|
"type": "custom",
|
|
"tokenizer": "comma_tokenizer"
|
|
},
|
|
"delimit": {
|
|
"filter": [
|
|
"lowercase",
|
|
"custom_delimiter"
|
|
],
|
|
"tokenizer": "whitespace"
|
|
},
|
|
"dataset_pattern_ngram": {
|
|
"filter": [
|
|
"lowercase",
|
|
"autocomplete_filter"
|
|
],
|
|
"type": "custom",
|
|
"tokenizer": "dataset_pattern"
|
|
},
|
|
"custom_browse_slash": {
|
|
"filter": [
|
|
"lowercase"
|
|
],
|
|
"type": "custom",
|
|
"tokenizer": "path_hierarchy"
|
|
}
|
|
},
|
|
"tokenizer": {
|
|
"path_hierarchy_tokenizer": {
|
|
"type": "path_hierarchy",
|
|
"replacement": "/",
|
|
"delimiter": "."
|
|
},
|
|
"custom_ngram": {
|
|
"type": "ngram",
|
|
"min_gram": "3",
|
|
"max_gram": "50"
|
|
},
|
|
"slash_tokenizer": {
|
|
"pattern": "[/]",
|
|
"type": "pattern"
|
|
},
|
|
"comma_tokenizer": {
|
|
"pattern": ",",
|
|
"type": "pattern"
|
|
},
|
|
"dataset_pattern": {
|
|
"pattern": "[./]",
|
|
"type": "pattern"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"mappings": {
|
|
"doc": {
|
|
"properties": {
|
|
"browsePaths": {
|
|
"type": "text",
|
|
"fields": {
|
|
"length": {
|
|
"type": "token_count",
|
|
"analyzer": "slash_pattern"
|
|
}
|
|
},
|
|
"analyzer": "custom_browse_slash",
|
|
"fielddata": true
|
|
},
|
|
"origin": {
|
|
"type": "keyword",
|
|
"fields": {
|
|
"ngram": {
|
|
"type": "text",
|
|
"analyzer": "custom_ngram"
|
|
}
|
|
},
|
|
"normalizer": "my_normalizer"
|
|
},
|
|
"deprecated": {
|
|
"type": "boolean"
|
|
},
|
|
"description": {
|
|
"type": "text",
|
|
"fields": {
|
|
"keyword": {
|
|
"type": "keyword"
|
|
}
|
|
}
|
|
},
|
|
"hasOwners": {
|
|
"type": "boolean"
|
|
},
|
|
"hasSchema": {
|
|
"type": "boolean"
|
|
},
|
|
"name": {
|
|
"type": "keyword",
|
|
"fields": {
|
|
"dataset_pattern_ngram": {
|
|
"type": "text",
|
|
"analyzer": "dataset_pattern_ngram"
|
|
},
|
|
"delimited": {
|
|
"type": "text",
|
|
"analyzer": "delimit"
|
|
},
|
|
"ngram": {
|
|
"type": "text",
|
|
"analyzer": "custom_ngram"
|
|
},
|
|
"pattern": {
|
|
"type": "text",
|
|
"analyzer": "dataset_pattern"
|
|
}
|
|
},
|
|
"normalizer": "my_normalizer"
|
|
},
|
|
"num_downstream_datasets": {
|
|
"type": "long"
|
|
},
|
|
"owners": {
|
|
"type": "text",
|
|
"fields": {
|
|
"ngram": {
|
|
"type": "text",
|
|
"analyzer": "comma_pattern_ngram"
|
|
}
|
|
},
|
|
"analyzer": "comma_pattern"
|
|
},
|
|
"platform": {
|
|
"type": "keyword",
|
|
"fields": {
|
|
"ngram": {
|
|
"type": "text",
|
|
"analyzer": "custom_ngram"
|
|
}
|
|
},
|
|
"normalizer": "my_normalizer"
|
|
},
|
|
"removed": {
|
|
"type": "boolean"
|
|
},
|
|
"urn": {
|
|
"type": "keyword",
|
|
"normalizer": "my_normalizer"
|
|
},
|
|
"upstreams": {
|
|
"type": "keyword",
|
|
"normalizer": "my_normalizer"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
} |