Elasticsearch Version: 5.3.1
kuromoji_stemmer token filterとkuromoji_readingform token filterを使って、最後の長音の除去とカタカナ読みへの変換を同時に設定しようとしたのですが、kuromoji_stemmerの後にkuromoji_readingformを設定すると、kuromoji_stemmerで除去されたはずの長音がkuromoji_readingformで再び追加されてしまいます。
設定例:
PUT http://localhost:9200/my_index
{
"settings": {
"analysis": {
"filter": {
"katakana_readingform": {
"type": "kuromoji_readingform",
"use_romaji": false
}
},
"analyzer": {
"stemmer": {
"type": "custom",
"tokenizer": "kuromoji_tokenizer",
"filter": [
"kuromoji_stemmer"
]
},
"reading": {
"type": "custom",
"tokenizer": "kuromoji_tokenizer",
"filter": [
"katakana_readingform"
]
},
"stemmer_reading": {
"type": "custom",
"tokenizer": "kuromoji_tokenizer",
"filter": [
"kuromoji_stemmer",
"katakana_readingform"
]
},
"reading_stemmer": {
"type": "custom",
"tokenizer": "kuromoji_tokenizer",
"filter": [
"katakana_readingform",
"kuromoji_stemmer"
]
}
}
}
}
}
クエリ例:
POST http://localhost:9200/my_index/_analyze
{
"analyzer": "stemmer_reading",
"text": "パーカー"
}
クエリ結果:
{
"tokens": [
{
"token": "パーカー",
"start_offset": 0,
"end_offset": 4,
"type": "word",
"position": 0
}
]
}
クエリ例（explain=true）:
POST http://localhost:9200/my_index/_analyze
{
"analyzer": "stemmer_reading",
"text": "パーカー",
"explain": true
}
クエリ結果（explain=true）:
{
"detail": {
"custom_analyzer": true,
"charfilters": [],
"tokenizer": {
"name": "kuromoji_tokenizer",
"tokens": [
{
"token": "パーカー",
"start_offset": 0,
"end_offset": 4,
"type": "word",
"position": 0,
"baseForm": null,
"bytes": "[e3 83 91 e3 83 bc e3 82 ab e3 83 bc]",
"inflectionForm": null,
"inflectionForm (en)": null,
"inflectionType": null,
"inflectionType (en)": null,
"partOfSpeech": "名詞-一般",
"partOfSpeech (en)": "noun-common",
"positionLength": 1,
"pronunciation": "パーカー",
"pronunciation (en)": "paka",
"reading": "パーカー",
"reading (en)": "paka"
}
]
},
"tokenfilters": [
{
"name": "kuromoji_stemmer",
"tokens": [
{
"token": "パーカ",
"start_offset": 0,
"end_offset": 4,
"type": "word",
"position": 0,
"baseForm": null,
"bytes": "[e3 83 91 e3 83 bc e3 82 ab]",
"inflectionForm": null,
"inflectionForm (en)": null,
"inflectionType": null,
"inflectionType (en)": null,
"keyword": false,
"partOfSpeech": "名詞-一般",
"partOfSpeech (en)": "noun-common",
"positionLength": 1,
"pronunciation": "パーカー",
"pronunciation (en)": "paka",
"reading": "パーカー",
"reading (en)": "paka"
}
]
},
{
"name": "katakana_readingform",
"tokens": [
{
"token": "パーカー",
"start_offset": 0,
"end_offset": 4,
"type": "word",
"position": 0,
"baseForm": null,
"bytes": "[e3 83 91 e3 83 bc e3 82 ab e3 83 bc]",
"inflectionForm": null,
"inflectionForm (en)": null,
"inflectionType": null,
"inflectionType (en)": null,
"keyword": false,
"partOfSpeech": "名詞-一般",
"partOfSpeech (en)": "noun-common",
"positionLength": 1,
"pronunciation": "パーカー",
"pronunciation (en)": "paka",
"reading": "パーカー",
"reading (en)": "paka"
}
]
}
]
}
}
この問題は、kuromoji_stemmerとkuromoji_readingformの順番を逆にすることでひとまず回避できそうですが、もし原因がわかれば教えていただきたいです。
POST http://localhost:9200/my_index/_analyze
{
"analyzer": "reading_stemmer",
"text": "パーカー"
}
{
"tokens": [
{
"token": "パーカ",
"start_offset": 0,
"end_offset": 4,
"type": "word",
"position": 0
}
]
}
よろしくお願いいたします。