From 55111ddeccbecf869d3f9fd739bebfbccff3073e Mon Sep 17 00:00:00 2001
From: Shinsuke Sugaya <shinsuke@apache.org>
Date: Sun, 7 Aug 2022 13:02:22 +0900
Subject: [PATCH] fix #2671 replace with synonym graph
---
src/main/resources/fess_indices/fess.json | 47 ++++++++++-------------
1 file changed, 21 insertions(+), 26 deletions(-)
diff --git a/src/main/resources/fess_indices/fess.json b/src/main/resources/fess_indices/fess.json
index 46e78e5fb..862dde3a6 100644
--- a/src/main/resources/fess_indices/fess.json
+++ b/src/main/resources/fess_indices/fess.json
@@ -677,28 +677,22 @@
"ambiguities_resolved": false
},
"unigram_tokenizer": {
- "type": "ngram_synonym",
- "n": "1",
- "synonyms_path": "${fess.dictionary.path}synonym.txt",
- "dynamic_reload": true,
- "expand": true,
- "reload_interval": "1m"
+ "type": "ngram",
+ "min_gram": 1,
+ "max_gram": 1,
+ "token_chars": []
},
"unigram_search_tokenizer": {
- "type": "ngram_synonym",
- "n": "1",
- "synonyms_path": "${fess.dictionary.path}synonym.txt",
- "dynamic_reload": true,
- "expand": false,
- "reload_interval": "1m"
+ "type": "ngram",
+ "min_gram": 1,
+ "max_gram": 1,
+ "token_chars": []
},
"bigram_tokenizer": {
- "type": "ngram_synonym",
- "n": "2",
- "synonyms_path": "${fess.dictionary.path}synonym.txt",
- "dynamic_reload": true,
- "expand": false,
- "reload_interval": "1m"
+ "type": "ngram",
+ "min_gram": 2,
+ "max_gram": 2,
+ "token_chars": []
}
},
"analyzer": {
@@ -1139,13 +1133,12 @@
"char_filter": [
"mapping_filter"
],
- "tokenizer": "unigram_tokenizer",
+ "tokenizer": "standard",
"filter": [
- "disable_graph",
+ "asciifolding",
"alphanum_word_filter",
- "cjk_bigram",
"lowercase",
- "asciifolding",
+ "cjk_bigram",
"stopword_en_filter",
"english_keywords",
"english_override",
@@ -1159,10 +1152,11 @@
],
"tokenizer": "unigram_search_tokenizer",
"filter": [
- "disable_graph",
+ "asciifolding",
"alphanum_word_filter",
- "cjk_bigram",
"lowercase",
+ "cjk_bigram",
+ "synonym_filter",
"stopword_en_filter",
"english_keywords",
"english_override",
@@ -1181,11 +1175,12 @@
"char_filter": [
"mapping_ja_filter"
],
- "tokenizer": "unigram_search_tokenizer",
+ "tokenizer": "standard",
"filter": [
+ "asciifolding",
"alphanum_word_filter",
- "cjk_bigram",
"lowercase",
+ "cjk_bigram",
"stopword_en_filter",
"english_keywords",
"english_override",
--
GitLab