blob: 9146e4539b8e204df4b4c43d5e12955293b4077a (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
|
# Copyright Yahoo. Licensed under the terms of the Apache 2.0 license. See LICENSE in the project root.
namespace=vespa.config.search.summary
## Set the length (in #characters) of the dynamically generated
## summaries. This is a hint to the module that generates the
## dynamic summary - the actual size will depend on the available text
## and the query. You may find that you need to set this length
## substantially longer than your actual desired average length -
## setting this about twice as long is often appropriate.
length int default=256
## The number of (possibly partial) set of keywords
## matching the query, to attempt to include in the summary. The larger this
## value compared is set relative to the length parameter, the more
## dense the keywords may appear in the summary.
max_matches int default=3
## Minimal desired length of the generated summary in
## bytes. This is the shortest summary length for which the number of
## matches will be respected. Eg. if
## a summary appear to become shorter than min_length bytes with
## max_matches matches, then additional matches will be used if available.
min_length int default=128
## Make sure the prefix (length controlled by 'juniper.dynsum.length')
## of all fields with summary: dynamic are returned in the dynamic
## summary if a query does not hit in those fields
prefix bool default=true
## The maximal number of bytes of context to prepend and append to
## each of the selected query keyword hits. This parameter defines the
## max size a summary would become if there are few keyword hits
## (max_matches set low or document contained few matches of the keywords).
surround_max int default=128
## The size of the sliding window used to determine if
## multiple query terms occur together. The larger the value, the more
## likely the system will find (and present in dynamic summary) complete
## matches containing all the search terms. The downside is a potential
## performance overhead of keeping candidates for matches longer during
## matching, and consequently updating more candidates that eventually
## gets thrown.
winsize int default=200
## This value multiplied with the winsize gives the size of a fallback
## window used to break out when searching for phrase term matches.
winsize_fallback_multiplier double default=10.0
## This value specifies the maximum number of match candidates that are
## managed for a non-leaf query node when matching the query against the
## input text.
max_match_candidates int default=1000
## The minimal number of bytes in a query keyword for
## it to be subject to the simple Juniper stemming algorithm. Keywords
## that are shorter than or equal to this limit will only yield exact
## matches in the dynamic summaries.
stem_min_length int default=5
## The maximal number of bytes that a word in the document
## can be longer than the keyword itself to yield a match. Eg. for
## the default values, if the keyword is 7 bytes long, it will match any
## word with length less than or equal to 10 for which the keyword is a prefix.
stem_max_extend int default=3
## The parameters above may also be overriden on a per-field basis
## using the following array.
override[].fieldname string
override[].length int default=256
override[].max_matches int default=3
override[].min_length int default=128
override[].prefix bool default=true
override[].surround_max int default=128
override[].winsize int default=200
override[].winsize_fallback_multiplier double default=10.0
override[].max_match_candidates int default=1000
override[].stem_min_length int default=5
override[].stem_max_extend int default=3
|
