【发布时间】：2016-07-17 03:48:59
【问题描述】：
我目前在本地服务器上使用 solr 5x 并使用 Drupal 实例生成所有索引。经过大量配置后，我对 solr 的实现感到相当满意。
但是，我刚刚注意到的一个问题是，正确的拼写仍然被视为拼写错误，并且仍然被提供建议。
"correctlySpelled":false
正如您在 JSON 输出 中所见，两个词：license 和 vehicle 拼写正确，仍被归类为 不正确。
"spellcheck":{
"suggestions":[
"license",
{
"numFound":3,
"startOffset":0,
"endOffset":7,
"suggestion":[
"licensed",
"licensee",
"licenser"
]
},
"vehicle",
{
"numFound":3,
"startOffset":8,
"endOffset":15,
"suggestion":[
"chicle",
"pedicle",
"vehiculate"
]
}
],
"correctlySpelled":false,
"collations":[
"collation",
"licensed chicle",
"collation",
"licensed pedicle",
"collation",
"licensed vehiculate",
"collation",
"licenser chicle",
"collation",
"licenser pedicle"
]
}
有人知道为什么会产生误报吗？
网址编码查询：
http://192.168.33.10:8983/solr/drupal/spell?q=license+vehicle&spellcheck=true&spellcheck.accuracy=0.7&spellcheck.collate=true&defType=edismax&json.nl=flat&omitHeader=true&qf=ts_title^1&fl=*,score&start=0&fq=index_id:"new_index"&fq=hash:"96z3wm"&rows=10&wt=json&stopwords=true&lowercaseOperators=true
查询：
q = license+vehicle
spellcheck = true
spellcheck.accuracy = 0.7
spellcheck.collate = true
defType = edismax
json.nl = flat
omitHeader = true
qf = ts_title^1
fl = *,score
start = 0
fq = index_id:"new_index"
fq = hash:"96z3wm"
rows = 10
wt = json
stopwords = true
lowercaseOperators = true
schema.xml 的相关部分：
<fieldType name="text" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!-- <filter class="solr.EdgeNGramFilterFactory" minGramSize="3" maxGramSize="15" /> -->
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!-- Case insensitive stop word removal. -->
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="stopwords.txt"
/>
<filter class="solr.WordDelimiterFilterFactory"
protected="protwords.txt"
generateWordParts="1"
generateNumberParts="1"
catenateWords="1"
catenateNumbers="1"
catenateAll="0"
splitOnCaseChange="0"
preserveOriginal="1"/>
<filter class="solr.LengthFilterFactory" min="2" max="100" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!-- <filter class="solr.EdgeNGramFilterFactory" minGramSize="3" maxGramSize="15" /> -->
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="stopwords.txt"
/>
<filter class="solr.WordDelimiterFilterFactory"
protected="protwords.txt"
generateWordParts="1"
generateNumberParts="1"
catenateWords="0"
catenateNumbers="0"
catenateAll="0"
splitOnCaseChange="0"
preserveOriginal="1"/>
<filter class="solr.LengthFilterFactory" min="2" max="100" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="multiterm">
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!-- <filter class="solr.EdgeNGramFilterFactory" minGramSize="3" maxGramSize="15" /> -->
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="stopwords.txt"
/>
<filter class="solr.WordDelimiterFilterFactory"
protected="protwords.txt"
generateWordParts="1"
generateNumberParts="1"
catenateWords="0"
catenateNumbers="0"
catenateAll="0"
splitOnCaseChange="1"
preserveOriginal="1"/>
<filter class="solr.LengthFilterFactory" min="2" max="100" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
solrconfig.xml 的相关部分
<requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
<lst name="defaults">
<str name="df">spell</str> <!--The default field for spell checking. -->
<str name="spellcheck.dictionary">file</str> <!--default or file or jarowinkler as mentioned above. -->
<str name="spellcheck">on</str>
<str name="spellcheck.extendedResults">true</str>
<str name="spellcheck.count">3</str>
<str name="spellcheck.maxResultsForSuggest">5</str>
<str name="spellcheck.collate">false</str>
<str name="spellcheck.collateExtendedResults">false</str>
<str name="spellcheck.maxCollationTries">10</str>
<str name="spellcheck.maxCollations">5</str>
</lst>
<arr name="last-components">
<str>spellcheck</str>
</arr>
</requestHandler>
<searchComponent name="spellcheck" class="solr.SpellCheckComponent">
<str name="queryAnalyzerFieldType">textSpell</str>
<lst name="spellchecker">
<str name="name">default</str>
<str name="field">spell</str>
<str name="spellcheckIndexDir">spellchecker</str>
<str name="buildOnOptimize">true</str>
</lst>
<lst name="spellchecker">
<str name="classname">solr.FileBasedSpellChecker</str>
<str name="name">file</str>
<str name="sourceLocation">spellings.txt</str>
<str name="characterEncoding">UTF-8</str>
<str name="spellcheckIndexDir">spellcheckerFile</str>
</lst>
</searchComponent>
【问题讨论】：
-
您是否尝试过使用非词干字段作为拼写更正的来源？您可能实际上没有您认为索引中包含的术语。此外，来自旧 wiki：如果未指定“spellcheck.maxResultsForSuggest”，则默认行为是生成建议，如果至少 1 个术语不在索引中，则默认行为将“正确拼写”报告为“假”（文档频率 == 0 ) 与返回的结果数无关。
-
@MatsLindh - 在
solr.SearchHandler中有spellcheck.maxResultsForSuggest的引用。如上所述，结果返回正常，因此正在对这些术语进行索引。只是拼写检查器的值忽略了正确的拼写。 -
那么token的命中数是否大于maxResultsForSuggest？