etc/searchengine/elasticsearch/index_config.yaml

   1 ---
   2 # Index configuration that defines how different analyzers work.
   3 index:
   4   analysis:
   5     analyzer:
   6       # Phrase analyzer is used for phrases (phrase match, sorting)
   7       analyser_phrase:
   8         tokenizer: keyword
   9         filter:
  10           - icu_folding
  11         char_filter:
  12           - punctuation
  13       analyser_standard:
  14         tokenizer: icu_tokenizer
  15         filter:
  16           - icu_folding
  17       analyser_stdno:
  18         tokenizer: whitespace
  19         filter:
  20           - icu_folding
  21         char_filter:
  22           - punctuation
  23     normalizer:
  24       normalizer_keyword:
  25         type: custom
  26         filter:
  27           - icu_folding
  28     char_filter:
  29       # The punctuation filter is used to remove any punctuation chars in fields that don't use icu_tokenizer.
  30       punctuation:
  31         type: pattern_replace
  32         # The pattern contains all ASCII punctuation characters.
  33         pattern: '([\x00-\x1F,\x21-\x2F,\x3A-\x40,\x5B-\x60,\x7B-\x89,\x8B,\x8D,\x8F,\x90-\x99,\x9B,\x9D,\xA0-\xBF,\xD7,\xF7])'
  34         replacement: ''