mirror of
https://gitlab.com/SIGBUS/nyaa.git
synced 2024-12-22 19:19:59 +00:00
91 lines
2.1 KiB
YAML
91 lines
2.1 KiB
YAML
|
---
|
||
|
# CREATE DTABASE/TABLE equivalent for elasticsearch, in yaml
|
||
|
# fo inline comments.
|
||
|
settings:
|
||
|
analysis:
|
||
|
analyzer:
|
||
|
my_search_analyzer:
|
||
|
type: custom
|
||
|
tokenizer: standard
|
||
|
char_filter:
|
||
|
- my_char_filter
|
||
|
filter:
|
||
|
- standard
|
||
|
- lowercase
|
||
|
my_index_analyzer:
|
||
|
type: custom
|
||
|
tokenizer: standard
|
||
|
char_filter:
|
||
|
- my_char_filter
|
||
|
filter:
|
||
|
- lowercase
|
||
|
- my_ngram
|
||
|
filter:
|
||
|
my_ngram:
|
||
|
type: edgeNGram
|
||
|
min_gram: 1
|
||
|
max_gram: 15
|
||
|
char_filter:
|
||
|
my_char_filter:
|
||
|
type: mapping
|
||
|
mappings: ["-=>_", "!=>_"]
|
||
|
index:
|
||
|
# we're running a single es node, so no sharding necessary,
|
||
|
# plus replicas don't really help either.
|
||
|
number_of_shards: 1
|
||
|
number_of_replicas : 0
|
||
|
mapper:
|
||
|
# disable elasticsearch's "helpful" autoschema
|
||
|
dynamic: false
|
||
|
# since we disabled the _all field, default query the
|
||
|
# name of the torrent.
|
||
|
query:
|
||
|
default_field: display_name
|
||
|
mappings:
|
||
|
torrent:
|
||
|
# don't want everything concatenated
|
||
|
_all:
|
||
|
enabled: false
|
||
|
properties:
|
||
|
id:
|
||
|
type: long
|
||
|
display_name:
|
||
|
# TODO could do a fancier tokenizer here to parse out the
|
||
|
# the scene convention of stuff in brackets, plus stuff like k-on
|
||
|
type: text
|
||
|
analyzer: my_index_analyzer
|
||
|
fielddata: true
|
||
|
created_time:
|
||
|
type: date
|
||
|
# Only in the ES index for generating magnet links
|
||
|
info_hash:
|
||
|
enabled: false
|
||
|
filesize:
|
||
|
type: long
|
||
|
anonymous:
|
||
|
type: boolean
|
||
|
trusted:
|
||
|
type: boolean
|
||
|
remake:
|
||
|
type: boolean
|
||
|
complete:
|
||
|
type: boolean
|
||
|
hidden:
|
||
|
type: boolean
|
||
|
deleted:
|
||
|
type: boolean
|
||
|
has_torrent:
|
||
|
type: boolean
|
||
|
download_count:
|
||
|
type: long
|
||
|
leech_count:
|
||
|
type: long
|
||
|
seed_count:
|
||
|
type: long
|
||
|
# these ids are really only for filtering, thus keyword
|
||
|
uploader_id:
|
||
|
type: keyword
|
||
|
main_category_id:
|
||
|
type: keyword
|
||
|
sub_category_id:
|
||
|
type: keyword
|