如果我搜索“agua”没有结果忽略搜索中的重音符号（á，ã，ç）？
#city数据库（id，name，uf，province_id）
1 Águas Clara PR 3
2 águas PR 4
3 Áraguaia PR 3
＃schema.xml中
<fieldType name="text" class="solr.TextField" omitNorms="false">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StandardFilterFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EdgeNGramFilterFactory" minGramSize="1" maxGramSize="15" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StandardFilterFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
答案 0 :(得分：5)
在过滤器链中使用ASCIIFoldingFilterFactory，用于索引和查询。使用您的示例：
<fieldType name="text" class="solr.TextField" omitNorms="false">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StandardFilterFactory"/>
<filter class="solr.ASCIIFoldingFilterFactory" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EdgeNGramFilterFactory" minGramSize="1" maxGramSize="15" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.ASCIIFoldingFilterFactory" />
<filter class="solr.StandardFilterFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
答案 1 :(得分：0)
尝试运行分析以查看查询时和索引时发生的情况。
尝试类似的东西，调整主机，核心和字段名称：
http://localhost:8983/solr/core1/analysis/field?wt=json&analysis.showmatch=true&analysis.fieldvalue=%C3%A1guas&analysis.query=%C3%A1guas&analysis.fieldname=name
结果将显示如何在分析的所有步骤中处理您的查询字词
{
responseHeader:{
status:0,
QTime:2
},
analysis:{
field_types:{
},
field_names:{
Noms:{
index:[
"org.apache.lucene.analysis.standard.StandardTokenizer",
[
{
text:"état",
raw_bytes:"[c3 a9 74 61 74]",
start:0,
end:4,
type:"<ALPHANUM>",
position:1,
positionHistory:[
1
]
}
],
"org.apache.lucene.analysis.miscellaneous.ASCIIFoldingFilter",
[
{
text:"etat",
raw_bytes:"[65 74 61 74]",
match:true,
position:1,
positionHistory:[
1,
1
],
start:0,
end:4,
type:"<ALPHANUM>"
}
],
"org.apache.lucene.analysis.core.StopFilter",
[
{
text:"etat",
raw_bytes:"[65 74 61 74]",
match:true,
position:1,
positionHistory:[
1,
1,
1
],
start:0,
end:4,
type:"<ALPHANUM>"
}
],
"org.apache.lucene.analysis.core.LowerCaseFilter",
[
{
text:"etat",
raw_bytes:"[65 74 61 74]",
match:true,
position:1,
positionHistory:[
1,
1,
1,
1
],
start:0,
end:4,
type:"<ALPHANUM>"
}
]
],
query:[
"org.apache.lucene.analysis.standard.StandardTokenizer",
[
{
text:"état",
raw_bytes:"[c3 a9 74 61 74]",
start:0,
end:4,
type:"<ALPHANUM>",
position:1,
positionHistory:[
1
]
}
],
"org.apache.lucene.analysis.miscellaneous.ASCIIFoldingFilter",
[
{
text:"etat",
raw_bytes:"[65 74 61 74]",
position:1,
positionHistory:[
1,
1
],
start:0,
end:4,
type:"<ALPHANUM>"
}
],
"org.apache.lucene.analysis.synonym.SynonymFilter",
[
{
text:"etat",
raw_bytes:"[65 74 61 74]",
org.apache.lucene.analysis.tokenattributes.PositionLengthAttribute#positionLength:1,
type:"<ALPHANUM>",
start:0,
end:4,
position:1,
positionHistory:[
1,
1,
1
]
}
],
"org.apache.lucene.analysis.core.StopFilter",
[
{
text:"etat",
raw_bytes:"[65 74 61 74]",
position:1,
positionHistory:[
1,
1,
1,
1
],
start:0,
end:4,
type:"<ALPHANUM>",
org.apache.lucene.analysis.tokenattributes.PositionLengthAttribute#positionLength:1
}
],
"org.apache.lucene.analysis.core.LowerCaseFilter",
[
{
text:"etat",
raw_bytes:"[65 74 61 74]",
position:1,
positionHistory:[
1,
1,
1,
1,
1
],
start:0,
end:4,
type:"<ALPHANUM>",
org.apache.lucene.analysis.tokenattributes.PositionLengthAttribute#positionLength:1
}
]
]
}
}
}
}