View | Details | Raw Unified | Return to bug 21357
Collapse All | Expand All

(-)a/admin/searchengine/elasticsearch/index_config.yaml (-3 / +25 lines)
Lines 7-18 index: Link Here
7
      analyzer_phrase:
7
      analyzer_phrase:
8
        tokenizer: keyword
8
        tokenizer: keyword
9
        filter:
9
        filter:
10
          - elision
10
          - icu_folding
11
          - icu_folding
12
          # Since the char_filter left apostrophes alone, remove them now
13
          - apostrophe
11
        char_filter:
14
        char_filter:
12
          - punctuation
15
          - punctuation
13
      analyzer_standard:
16
      analyzer_standard:
14
        tokenizer: icu_tokenizer
17
        tokenizer: icu_tokenizer
15
        filter:
18
        filter:
19
          - elision
16
          - icu_folding
20
          - icu_folding
17
      analyzer_stdno:
21
      analyzer_stdno:
18
        tokenizer: whitespace
22
        tokenizer: whitespace
Lines 24-29 index: Link Here
24
      icu_folding_normalizer:
28
      icu_folding_normalizer:
25
        type: custom
29
        type: custom
26
        filter:
30
        filter:
31
          - elision
27
          - icu_folding
32
          - icu_folding
28
      nfkc_cf_normalizer:
33
      nfkc_cf_normalizer:
29
        type: custom
34
        type: custom
Lines 32-38 index: Link Here
32
      # The punctuation filter is used to remove any punctuation chars in fields that don't use icu_tokenizer.
37
      # The punctuation filter is used to remove any punctuation chars in fields that don't use icu_tokenizer.
33
      punctuation:
38
      punctuation:
34
        type: pattern_replace
39
        type: pattern_replace
35
        # The pattern contains all ASCII punctuation characters.
40
        # The pattern contains all ASCII punctuation characters apart from apostrophe (\x27) since it's needed
36
        pattern: '([\x00-\x1F,\x21-\x2F,\x3A-\x40,\x5B-\x60,\x7B-\x89,\x8B,\x8D,\x8F,\x90-\x99,\x9B,\x9D,\xA0-\xBF,\xD7,\xF7])'
41
        # for the elision filter (char_filter always runs before other filters).
42
        pattern: '([\x00-\x1F,\x21-\x26,\x28-\x2F,\x3A-\x40,\x5B-\x60,\x7B-\x89,\x8B,\x8D,\x8F,\x90-\x99,\x9B,\x9D,\xA0-\xBF,\xD7,\xF7])'
43
        replacement: ''
44
    filter:
45
      elision:
46
        type: elision
47
        articles:
48
          - 'c'
49
          - 'd'
50
          - 'j'
51
          - 'l'
52
          - 'm'
53
          - 'n'
54
          - 'qu'
55
          - 's'
56
          - 't'
57
      apostrophe:
58
        type: pattern_replace
59
        pattern: "'"
37
        replacement: ''
60
        replacement: ''
38
index.mapping.total_fields.limit: 10000
61
index.mapping.total_fields.limit: 10000
39
- 

Return to bug 21357