fix #1091 add locales

This commit is contained in:
Shinsuke Sugaya 2017-06-06 23:42:24 +09:00
parent 44b0e94f87
commit 34808d856a
11 changed files with 527 additions and 278 deletions

View file

@ -522,16 +522,20 @@ public interface FessConfig extends FessEnv, org.codelibs.fess.mylasta.direction
de=de
el=el
en=en
en-ie=en-ie
es=es
et=et
eu=eu
fa=fa
fi=fi
fr=fr
gl=gl
gu=gu
he=he
hi=hi
hr=hr
hu=hu
hy=hy
id=id
it=it
ja=ja
@ -545,6 +549,7 @@ public interface FessConfig extends FessEnv, org.codelibs.fess.mylasta.direction
pa=pa
pl=pl
pt=pt
pt-br=pt-br
ro=ro
ru=ru
si=si
@ -2779,16 +2784,20 @@ public interface FessConfig extends FessEnv, org.codelibs.fess.mylasta.direction
de=de
el=el
en=en
en-ie=en-ie
es=es
et=et
eu=eu
fa=fa
fi=fi
fr=fr
gl=gl
gu=gu
he=he
hi=hi
hr=hr
hu=hu
hy=hy
id=id
it=it
ja=ja
@ -2802,6 +2811,7 @@ public interface FessConfig extends FessEnv, org.codelibs.fess.mylasta.direction
pa=pa
pl=pl
pt=pt
pt-br=pt-br
ro=ro
ru=ru
si=si

View file

@ -12,37 +12,17 @@
<arg>"fess"</arg>
<arg>"synonym.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"fa/mapping.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"ja/mapping.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"ja/kuromoji.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"ko/seunjeon.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"de/protwords.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"ar/protwords.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"ro/protwords.txt"</arg>
<arg>"ca/protwords.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"ca/protwords.txt"</arg>
<arg>"ckb-iq/protwords.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
@ -54,12 +34,28 @@
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"es/protwords.txt"</arg>
<arg>"de/protwords.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"el/protwords.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"en-ie/protwords.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"es/protwords.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"eu/protwords.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"fa/mapping.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"fa/protwords.txt"</arg>
@ -72,6 +68,10 @@
<arg>"fess"</arg>
<arg>"fr/protwords.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"gl/protwords.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"hi/protwords.txt"</arg>
@ -80,6 +80,10 @@
<arg>"fess"</arg>
<arg>"hu/protwords.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"hy/protwords.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"id/protwords.txt"</arg>
@ -88,6 +92,18 @@
<arg>"fess"</arg>
<arg>"it/protwords.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"ja/kuromoji.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"ja/mapping.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"ko/seunjeon.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"lt/protwords.txt"</arg>
@ -104,10 +120,18 @@
<arg>"fess"</arg>
<arg>"no/protwords.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"pt-br/protwords.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"pt/protwords.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"ro/protwords.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"ru/protwords.txt"</arg>
@ -116,6 +140,10 @@
<arg>"fess"</arg>
<arg>"sv/protwords.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"th/protwords.txt"</arg>
</postConstruct>
<postConstruct name="addConfigFile">
<arg>"fess"</arg>
<arg>"tr/protwords.txt"</arg>

View file

@ -243,16 +243,20 @@ da=da\n\
de=de\n\
el=el\n\
en=en\n\
en-ie=en-ie\n\
es=es\n\
et=et\n\
eu=eu\n\
fa=fa\n\
fi=fi\n\
fr=fr\n\
gl=gl\n\
gu=gu\n\
he=he\n\
hi=hi\n\
hr=hr\n\
hu=hu\n\
hy=hy\n\
id=id\n\
it=it\n\
ja=ja\n\
@ -266,6 +270,7 @@ no=no\n\
pa=pa\n\
pl=pl\n\
pt=pt\n\
pt-br=pt-br\n\
ro=ro\n\
ru=ru\n\
si=si\n\
@ -283,7 +288,6 @@ zh=zh-cn\n\
zh-cn=zh-cn\n\
zh-tw=zh-tw\n\
# boost
query.boost.title=0.2
query.boost.title.lang=1.0

View file

@ -38,106 +38,6 @@
"type": "stop",
"stopwords": "_english_"
},
"japanese_pos_filter" : {
"type" : "fess_japanese_part_of_speech",
"stoptags" : [
"その他",
"その他-間投",
"フィラー",
"感動詞",
"記号",
"記号-アルファベット",
"記号-一般",
"記号-括弧開",
"記号-括弧閉",
"記号-句点",
"記号-空白",
"記号-読点",
"形容詞",
"形容詞-接尾",
"形容詞-非自立",
"語断片",
"助詞",
"助詞-格助詞",
"助詞-格助詞-一般",
"助詞-格助詞-引用",
"助詞-格助詞-連語",
"助詞-間投助詞",
"助詞-係助詞",
"助詞-終助詞",
"助詞-接続助詞",
"助詞-特殊",
"助詞-副詞化",
"助詞-副助詞",
"助詞-副助詞/並立助詞/終助詞",
"助詞-並立助詞",
"助詞-連体化",
"助動詞",
"接続詞",
"接頭詞",
"接頭詞-形容詞接続",
"接頭詞-数接続",
"接頭詞-動詞接続",
"接頭詞-名詞接続",
"動詞-接尾",
"非言語音",
"連体詞"
]
},
"german_stop": {
"type": "stop",
"stopwords": "_german_"
},
"german_keywords": {
"type": "keyword_marker",
"keywords_path": "${fess.dictionary.path}de/protwords.txt"
},
"german_stemmer": {
"type": "stemmer",
"language": "light_german"
},
"french_elision": {
"type": "elision",
"articles_case": true,
"articles": [
"l", "m", "t", "qu", "n", "s",
"j", "d", "c", "jusqu", "quoiqu",
"lorsqu", "puisqu"
]
},
"french_stop": {
"type": "stop",
"stopwords": "_french_"
},
"french_keywords": {
"type": "keyword_marker",
"keywords_path": "${fess.dictionary.path}fr/protwords.txt"
},
"french_stemmer": {
"type": "stemmer",
"language": "light_french"
},
"italian_elision": {
"type": "elision",
"articles": [
"c", "l", "all", "dall", "dell",
"nell", "sull", "coll", "pell",
"gl", "agl", "dagl", "degl", "negl",
"sugl", "un", "m", "t", "s", "v", "d"
]
},
"italian_stop": {
"type": "stop",
"stopwords": "_italian_"
},
"italian_keywords": {
"type": "keyword_marker",
"keywords_path": "${fess.dictionary.path}it/protwords.txt"
},
"italian_stemmer": {
"type": "stemmer",
"language": "light_italian"
},
"arabic_stop": {
"type": "stop",
"stopwords": "_arabic_"
@ -150,17 +50,41 @@
"type": "stemmer",
"language": "arabic"
},
"romanian_stop": {
"armenian_stop": {
"type": "stop",
"stopwords": "_romanian_"
"stopwords": "_armenian_"
},
"romanian_keywords": {
"armenian_keywords": {
"type": "keyword_marker",
"keywords_path": "${fess.dictionary.path}ro/protwords.txt"
"keywords_path": "${fess.dictionary.path}hy/protwords.txt"
},
"romanian_stemmer": {
"armenian_stemmer": {
"type": "stemmer",
"language": "romanian"
"language": "armenian"
},
"basque_stop": {
"type": "stop",
"stopwords": "_basque_"
},
"basque_keywords": {
"type": "keyword_marker",
"keywords_path": "${fess.dictionary.path}eu/protwords.txt"
},
"basque_stemmer": {
"type": "stemmer",
"language": "basque"
},
"brazilian_stop": {
"type": "stop",
"stopwords": "_brazilian_"
},
"brazilian_keywords": {
"type": "keyword_marker",
"keywords_path": "${fess.dictionary.path}pt-br/protwords.txt"
},
"brazilian_stemmer": {
"type": "stemmer",
"language": "brazilian"
},
"bulgarian_stop": {
"type": "stop",
@ -214,17 +138,83 @@
"type": "stemmer",
"language": "danish"
},
"spanish_stop": {
"dutch_stop": {
"type": "stop",
"stopwords": "_spanish_"
"stopwords": "_dutch_"
},
"spanish_keywords": {
"dutch_keywords": {
"type": "keyword_marker",
"keywords_path": "${fess.dictionary.path}es/protwords.txt"
"keywords_path": "${fess.dictionary.path}nl/protwords.txt"
},
"spanish_stemmer": {
"dutch_stemmer": {
"type": "stemmer",
"language": "light_spanish"
"language": "dutch"
},
"dutch_override": {
"type": "stemmer_override",
"rules": [
"fiets=>fiets",
"bromfiets=>bromfiets",
"ei=>eier",
"kind=>kinder"
]
},
"finnish_stop": {
"type": "stop",
"stopwords": "_finnish_"
},
"finnish_keywords": {
"type": "keyword_marker",
"keywords_path": "${fess.dictionary.path}fi/protwords.txt"
},
"finnish_stemmer": {
"type": "stemmer",
"language": "finnish"
},
"french_elision": {
"type": "elision",
"articles_case": true,
"articles": [
"l", "m", "t", "qu", "n", "s",
"j", "d", "c", "jusqu", "quoiqu",
"lorsqu", "puisqu"
]
},
"french_stop": {
"type": "stop",
"stopwords": "_french_"
},
"french_keywords": {
"type": "keyword_marker",
"keywords_path": "${fess.dictionary.path}fr/protwords.txt"
},
"french_stemmer": {
"type": "stemmer",
"language": "light_french"
},
"galician_stop": {
"type": "stop",
"stopwords": "_galician_"
},
"galician_keywords": {
"type": "keyword_marker",
"keywords_path": "${fess.dictionary.path}gl/protwords.txt"
},
"galician_stemmer": {
"type": "stemmer",
"language": "galician"
},
"german_stop": {
"type": "stop",
"stopwords": "_german_"
},
"german_keywords": {
"type": "keyword_marker",
"keywords_path": "${fess.dictionary.path}de/protwords.txt"
},
"german_stemmer": {
"type": "stemmer",
"language": "light_german"
},
"greek_stop": {
"type": "stop",
@ -242,22 +232,6 @@
"type": "stemmer",
"language": "greek"
},
"persian_stop": {
"type": "stop",
"stopwords": "_persian_"
},
"finnish_stop": {
"type": "stop",
"stopwords": "_finnish_"
},
"finnish_keywords": {
"type": "keyword_marker",
"keywords_path": "${fess.dictionary.path}fi/protwords.txt"
},
"finnish_stemmer": {
"type": "stemmer",
"language": "finnish"
},
"hindi_stop": {
"type": "stop",
"stopwords": "_hindi_"
@ -294,17 +268,92 @@
"type": "stemmer",
"language": "indonesian"
},
"lithuanian_stop": {
"irish_elision": {
"type": "elision",
"articles": [ "h", "n", "t" ]
},
"irish_stop": {
"type": "stop",
"stopwords": "_lithuanian_"
"stopwords": "_irish_"
},
"lithuanian_keywords": {
"irish_lowercase": {
"type": "lowercase",
"language": "irish"
},
"irish_keywords": {
"type": "keyword_marker",
"keywords_path": "${fess.dictionary.path}lt/protwords.txt"
"keywords_path": "${fess.dictionary.path}en-ie/protwords.txt"
},
"lithuanian_stemmer": {
"irish_stemmer": {
"type": "stemmer",
"language": "lithuanian"
"language": "irish"
},
"italian_elision": {
"type": "elision",
"articles": [
"c", "l", "all", "dall", "dell",
"nell", "sull", "coll", "pell",
"gl", "agl", "dagl", "degl", "negl",
"sugl", "un", "m", "t", "s", "v", "d"
]
},
"italian_stop": {
"type": "stop",
"stopwords": "_italian_"
},
"italian_keywords": {
"type": "keyword_marker",
"keywords_path": "${fess.dictionary.path}it/protwords.txt"
},
"italian_stemmer": {
"type": "stemmer",
"language": "light_italian"
},
"japanese_pos_filter" : {
"type" : "fess_japanese_part_of_speech",
"stoptags" : [
"その他",
"その他-間投",
"フィラー",
"感動詞",
"記号",
"記号-アルファベット",
"記号-一般",
"記号-括弧開",
"記号-括弧閉",
"記号-句点",
"記号-空白",
"記号-読点",
"形容詞",
"形容詞-接尾",
"形容詞-非自立",
"語断片",
"助詞",
"助詞-格助詞",
"助詞-格助詞-一般",
"助詞-格助詞-引用",
"助詞-格助詞-連語",
"助詞-間投助詞",
"助詞-係助詞",
"助詞-終助詞",
"助詞-接続助詞",
"助詞-特殊",
"助詞-副詞化",
"助詞-副助詞",
"助詞-副助詞/並立助詞/終助詞",
"助詞-並立助詞",
"助詞-連体化",
"助動詞",
"接続詞",
"接頭詞",
"接頭詞-形容詞接続",
"接頭詞-数接続",
"接頭詞-動詞接続",
"接頭詞-名詞接続",
"動詞-接尾",
"非言語音",
"連体詞"
]
},
"latvian_stop": {
"type": "stop",
@ -318,26 +367,17 @@
"type": "stemmer",
"language": "latvian"
},
"dutch_stop": {
"lithuanian_stop": {
"type": "stop",
"stopwords": "_dutch_"
"stopwords": "_lithuanian_"
},
"dutch_keywords": {
"lithuanian_keywords": {
"type": "keyword_marker",
"keywords_path": "${fess.dictionary.path}nl/protwords.txt"
"keywords_path": "${fess.dictionary.path}lt/protwords.txt"
},
"dutch_stemmer": {
"lithuanian_stemmer": {
"type": "stemmer",
"language": "dutch"
},
"dutch_override": {
"type": "stemmer_override",
"rules": [
"fiets=>fiets",
"bromfiets=>bromfiets",
"ei=>eier",
"kind=>kinder"
]
"language": "lithuanian"
},
"norwegian_stop": {
"type": "stop",
@ -351,6 +391,10 @@
"type": "stemmer",
"language": "norwegian"
},
"persian_stop": {
"type": "stop",
"stopwords": "_persian_"
},
"portuguese_stop": {
"type": "stop",
"stopwords": "_portuguese_"
@ -363,6 +407,18 @@
"type": "stemmer",
"language": "light_portuguese"
},
"romanian_stop": {
"type": "stop",
"stopwords": "_romanian_"
},
"romanian_keywords": {
"type": "keyword_marker",
"keywords_path": "${fess.dictionary.path}ro/protwords.txt"
},
"romanian_stemmer": {
"type": "stemmer",
"language": "romanian"
},
"russian_stop": {
"type": "stop",
"stopwords": "_russian_"
@ -375,6 +431,30 @@
"type": "stemmer",
"language": "russian"
},
"sorani_stop": {
"type": "stop",
"stopwords": "_sorani_"
},
"sorani_keywords": {
"type": "keyword_marker",
"keywords_path": "${fess.dictionary.path}ckb-iq/protwords.txt"
},
"sorani_stemmer": {
"type": "stemmer",
"language": "sorani"
},
"spanish_stop": {
"type": "stop",
"stopwords": "_spanish_"
},
"spanish_keywords": {
"type": "keyword_marker",
"keywords_path": "${fess.dictionary.path}es/protwords.txt"
},
"spanish_stemmer": {
"type": "stemmer",
"language": "light_spanish"
},
"swedish_stop": {
"type": "stop",
"stopwords": "_swedish_"
@ -456,69 +536,6 @@
}
},
"analyzer": {
"japanese_analyzer": {
"type": "custom",
"char_filter": [
"mapping_ja_filter",
"fess_japanese_iteration_mark"
],
"tokenizer": "japanese_tokenizer",
"filter": [
"truncate10_filter",
"fess_japanese_baseform",
"fess_japanese_stemmer",
"japanese_pos_filter",
"lowercase"
]
},
"english_analyzer": {
"type": "custom",
"tokenizer": "standard",
"filter": [
"truncate20_filter",
"lowercase",
"possessive_stemmer_en_filter"
]
},
"korean_analyzer": {
"type": "custom",
"tokenizer":"korean_tokenizer"
},
"german_analyzer": {
"type": "custom",
"tokenizer": "standard",
"filter": [
"truncate20_filter",
"lowercase",
"german_stop",
"german_normalization",
"german_stemmer"
]
},
"french_analyzer": {
"type": "custom",
"tokenizer": "standard",
"filter": [
"truncate20_filter",
"french_elision",
"lowercase",
"french_stop",
"french_keywords",
"french_stemmer"
]
},
"italian_analyzer": {
"type": "custom",
"tokenizer": "standard",
"filter": [
"truncate20_filter",
"italian_elision",
"lowercase",
"italian_stop",
"italian_keywords",
"italian_stemmer"
]
},
"arabic_analyzer": {
"type": "custom",
"tokenizer": "standard",
@ -531,19 +548,40 @@
"arabic_stemmer"
]
},
"romanian_analyzer": {
"type": "custom",
"tokenizer": "standard",
"armenian_analyzer": {
"tokenizer": "standard",
"filter": [
"truncate20_filter",
"lowercase",
"romanian_stop",
"romanian_stemmer"
"armenian_stop",
"armenian_keywords",
"armenian_stemmer"
]
},
"basque_analyzer": {
"tokenizer": "standard",
"filter": [
"truncate20_filter",
"lowercase",
"basque_stop",
"basque_keywords",
"basque_stemmer"
]
},
"brazilian_analyzer": {
"tokenizer": "standard",
"filter": [
"truncate20_filter",
"lowercase",
"brazilian_stop",
"brazilian_keywords",
"brazilian_stemmer"
]
},
"bulgarian_analyzer": {
"tokenizer": "standard",
"filter": [
"truncate20_filter",
"lowercase",
"bulgarian_stop",
"bulgarian_keywords",
@ -584,38 +622,25 @@
"danish_stemmer"
]
},
"spanish_analyzer": {
"dutch_analyzer": {
"type": "custom",
"tokenizer": "standard",
"filter": [
"truncate20_filter",
"lowercase",
"spanish_stop",
"spanish_keywords",
"spanish_stemmer"
"dutch_stop",
"dutch_keywords",
"dutch_override",
"dutch_stemmer"
]
},
"greek_analyzer": {
"english_analyzer": {
"type": "custom",
"tokenizer": "standard",
"filter": [
"truncate20_filter",
"greek_lowercase",
"greek_stop",
"greek_keywords",
"greek_stemmer"
]
},
"persian_analyzer": {
"type": "custom",
"tokenizer": "standard",
"char_filter": [ "mapping_fa_filter" ],
"filter": [
"truncate20_filter",
"lowercase",
"arabic_normalization",
"persian_normalization",
"persian_stop"
"possessive_stemmer_en_filter"
]
},
"finnish_analyzer": {
@ -629,6 +654,50 @@
"finnish_stemmer"
]
},
"french_analyzer": {
"type": "custom",
"tokenizer": "standard",
"filter": [
"truncate20_filter",
"french_elision",
"lowercase",
"french_stop",
"french_keywords",
"french_stemmer"
]
},
"galician_analyzer": {
"tokenizer": "standard",
"filter": [
"truncate20_filter",
"lowercase",
"galician_stop",
"galician_keywords",
"galician_stemmer"
]
},
"german_analyzer": {
"type": "custom",
"tokenizer": "standard",
"filter": [
"truncate20_filter",
"lowercase",
"german_stop",
"german_normalization",
"german_stemmer"
]
},
"greek_analyzer": {
"type": "custom",
"tokenizer": "standard",
"filter": [
"truncate20_filter",
"greek_lowercase",
"greek_stop",
"greek_keywords",
"greek_stemmer"
]
},
"hindi_analyzer": {
"type": "custom",
"tokenizer": "standard",
@ -664,15 +733,50 @@
"indonesian_stemmer"
]
},
"lithuanian_analyzer": {
"irish_analyzer": {
"tokenizer": "standard",
"filter": [
"truncate20_filter",
"irish_stop",
"irish_elision",
"irish_lowercase",
"irish_keywords",
"irish_stemmer"
]
},
"italian_analyzer": {
"type": "custom",
"tokenizer": "standard",
"filter": [
"truncate20_filter",
"italian_elision",
"lowercase",
"lithuanian_stop",
"lithuanian_keywords",
"lithuanian_stemmer"
"italian_stop",
"italian_keywords",
"italian_stemmer"
]
},
"japanese_analyzer": {
"type": "custom",
"char_filter": [
"mapping_ja_filter",
"fess_japanese_iteration_mark"
],
"tokenizer": "japanese_tokenizer",
"filter": [
"truncate10_filter",
"fess_japanese_baseform",
"fess_japanese_stemmer",
"japanese_pos_filter",
"lowercase"
]
},
"korean_analyzer": {
"type": "custom",
"tokenizer":"korean_tokenizer",
"filter": [
"truncate10_filter",
"lowercase"
]
},
"latvian_analyzer": {
@ -686,16 +790,15 @@
"latvian_stemmer"
]
},
"dutch_analyzer": {
"lithuanian_analyzer": {
"type": "custom",
"tokenizer": "standard",
"tokenizer": "standard",
"filter": [
"truncate20_filter",
"lowercase",
"dutch_stop",
"dutch_keywords",
"dutch_override",
"dutch_stemmer"
"lithuanian_stop",
"lithuanian_keywords",
"lithuanian_stemmer"
]
},
"norwegian_analyzer": {
@ -709,6 +812,18 @@
"norwegian_stemmer"
]
},
"persian_analyzer": {
"type": "custom",
"tokenizer": "standard",
"char_filter": [ "mapping_fa_filter" ],
"filter": [
"truncate20_filter",
"lowercase",
"arabic_normalization",
"persian_normalization",
"persian_stop"
]
},
"portuguese_analyzer": {
"type": "custom",
"tokenizer": "standard",
@ -720,6 +835,16 @@
"portuguese_stemmer"
]
},
"romanian_analyzer": {
"type": "custom",
"tokenizer": "standard",
"filter": [
"truncate20_filter",
"lowercase",
"romanian_stop",
"romanian_stemmer"
]
},
"russian_analyzer": {
"type": "custom",
"tokenizer": "standard",
@ -731,6 +856,28 @@
"russian_stemmer"
]
},
"sorani_analyzer": {
"tokenizer": "standard",
"filter": [
"truncate20_filter",
"sorani_normalization",
"lowercase",
"sorani_stop",
"sorani_keywords",
"sorani_stemmer"
]
},
"spanish_analyzer": {
"type": "custom",
"tokenizer": "standard",
"filter": [
"truncate20_filter",
"lowercase",
"spanish_stop",
"spanish_keywords",
"spanish_stemmer"
]
},
"swedish_analyzer": {
"type": "custom",
"tokenizer": "standard",
@ -763,13 +910,6 @@
"turkish_stemmer"
]
},
"empty_analyzer": {
"type": "custom",
"tokenizer": "standard",
"char_filter": [
"removeall_filter"
]
},
"standard_analyzer": {
"type": "custom",
"char_filter": [
@ -784,6 +924,13 @@
"stemmer_en_filter"
]
},
"empty_analyzer": {
"type": "custom",
"tokenizer": "standard",
"char_filter": [
"removeall_filter"
]
},
"minhash_analyzer": {
"type": "custom",
"char_filter": [

View file

@ -0,0 +1 @@
mînak

View file

@ -43,6 +43,15 @@
}
}
},
{
"lang_ca": {
"match": "*_ckb-iq",
"mapping": {
"type": "text",
"analyzer": "sorani_analyzer"
}
}
},
{
"lang_cs": {
"match": "*_cs",
@ -88,6 +97,15 @@
}
}
},
{
"lang_en": {
"match": "*_en-ie",
"mapping": {
"type": "text",
"analyzer": "irish_analyzer"
}
}
},
{
"lang_es": {
"match": "*_es",
@ -106,6 +124,15 @@
}
}
},
{
"lang_et": {
"match": "*_eu",
"mapping": {
"type": "text",
"analyzer": "basque_analyzer"
}
}
},
{
"lang_fa": {
"match": "*_fa",
@ -133,6 +160,15 @@
}
}
},
{
"lang_gl": {
"match": "*_gl",
"mapping": {
"type": "text",
"analyzer": "galician_analyzer"
}
}
},
{
"lang_gu": {
"match": "*_gu",
@ -178,6 +214,15 @@
}
}
},
{
"lang_hu": {
"match": "*_hy",
"mapping": {
"type": "text",
"analyzer": "armenian_analyzer"
}
}
},
{
"lang_id": {
"match": "*_id",
@ -295,6 +340,15 @@
}
}
},
{
"lang_pt-br": {
"match": "*_pt-br",
"mapping": {
"type": "text",
"analyzer": "brazilian_analyzer"
}
}
},
{
"lang_ro": {
"match": "*_ro",

View file

@ -0,0 +1 @@
sampla

View file

@ -0,0 +1 @@
Adibidez

View file

@ -0,0 +1 @@
exemplo

View file

@ -0,0 +1 @@
օրինակ

View file

@ -0,0 +1 @@
exemplo