我目前正在为电子商务网站开发使用 Solr 的搜索引擎。所以我在我的 schema.xml 中得到了这两个字段:
<field name="sku" type="string" indexed="true" stored="true" required="false" />
<field name="collection" type="string" indexed="true" stored="true" required="false" />
(下面提供了完整的 schema.xml)
有关信息:
- sku 看起来像这样:959620, 929345, 912365, ...
- 集合看起来像这样:Alcott、Spigrim、Tantal、...
它们的索引很好。例如,当我寻找:
http://localhost:8080/solr/myindex/select/?q=Alcott
我得到了所有带有“Alcott”系列的产品。
但是当我寻找时;
http://localhost:8080/solr/myindex/select/?q=959620
我什么都没有。
然而,当我深入提出这个要求时,
http://localhost:8080/solr/myindex/select/?q=sku:969520
我确实将产品附加到此 sku。
有没有办法让“q=969520”工作?甚至更好:“q=96”导致所有 sku 以“96”开头的产品?
感谢您的帮助 !
架构.xml:
<?xml version="1.0" encoding="UTF-8" ?>
<schema name="example" version="1.2">
<types>
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
<!-- boolean type: "true" or "false" -->
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
<!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
<fieldtype name="binary" class="solr.BinaryField"/>
<fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/>
<!-- A Trie based date field for faster date range queries and date faceting. -->
<fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
<fieldType name="pint" class="solr.IntField" omitNorms="true"/>
<fieldType name="plong" class="solr.LongField" omitNorms="true"/>
<fieldType name="pfloat" class="solr.FloatField" omitNorms="true"/>
<fieldType name="pdouble" class="solr.DoubleField" omitNorms="true"/>
<fieldType name="pdate" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
<!-- A text field that only splits on whitespace for exact matching of words -->
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldType>
<fieldType name="text" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!-- 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.
add enablePositionIncrements=true in both the index and query
analyzers to leave a 'gap' for more accurate phrase queries.
-->
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="stopwords.txt"
enablePositionIncrements="true"
/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="stopwords.txt"
enablePositionIncrements="true"
/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
</analyzer>
</fieldType>
<fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
<analyzer type="query">
<!-- normalisation des accents, cédilles, e dans l'o,... -->
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
<!-- découpage selon les espaces -->
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!-- suppression de la ponctuation -->
<filter class="solr.PatternReplaceFilterFactory" pattern="^(\p{Punct}*)(.*?)(\p{Punct}*)$" replacement="$2"/>
<!-- suppression des tokens vides et des mots démesurés -->
<filter class="solr.LengthFilterFactory" min="1" max="100" />
<!-- passage en minuscules -->
<filter class="solr.LowerCaseFilterFactory"/>
<!-- suppression des élisions (l', qu',...) -->
<filter class="solr.ElisionFilterFactory" articles="elisionwords_fr.txt"/>
<!-- découpage des mots composés -->
<filter class="solr.WordDelimiterFilterFactory" splitOnCaseChange="1" splitOnNumerics="1" stemEnglishPossessive="1" generateWordParts="1"
generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="1" preserveOriginal="1"/>
<!-- suppression des mots insignifiants -->
<filter class="solr.StopFilterFactory" ignoreCase="1" words="stopwords_fr.txt" enablePositionIncrements="true"/>
<!-- gestion des synonymes -->
<filter class="solr.SynonymFilterFactory" synonyms="synonyms_fr.txt" ignoreCase="true" expand="true"/>
<!-- partie de mot -->
<filter class="solr.EdgeNGramFilterFactory" minGramSize="3" maxGramSize="6"/>
<!-- lemmatisation (pluriels,...) -->
<filter class="solr.SnowballPorterFilterFactory" language="French" protected="protwords_fr.txt"/>
<!-- suppression des doublons éventuels -->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="index">
<!-- normalisation des accents, cédilles, e dans l'o,... -->
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
<!-- découpage selon les espaces -->
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!-- suppression de la ponctuation -->
<filter class="solr.PatternReplaceFilterFactory" pattern="^(\p{Punct}*)(.*?)(\p{Punct}*)$" replacement="$2"/>
<!-- suppression des tokens vides et des mots démesurés -->
<filter class="solr.LengthFilterFactory" min="1" max="100" />
<!-- passage en minuscules -->
<filter class="solr.LowerCaseFilterFactory"/>
<!-- suppression des élisions (l', qu',...) -->
<filter class="solr.ElisionFilterFactory" articles="elisionwords_fr.txt"/>
<!-- découpage des mots composés -->
<filter class="solr.WordDelimiterFilterFactory" splitOnCaseChange="1" splitOnNumerics="1" stemEnglishPossessive="1" generateWordParts="1"
generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="1" preserveOriginal="1"/>
<!-- suppression des mots insignifiants -->
<filter class="solr.StopFilterFactory" ignoreCase="1" words="stopwords_fr.txt" enablePositionIncrements="true"/>
<!-- gestion des synonymes -->
<filter class="solr.SynonymFilterFactory" synonyms="synonyms_fr.txt" ignoreCase="true" expand="true"/>
<!-- partie de mot -->
<filter class="solr.EdgeNGramFilterFactory" minGramSize="3" maxGramSize="6"/>
<!-- lemmatisation (pluriels,...) -->
<filter class="solr.SnowballPorterFilterFactory" language="French" protected="protwords_fr.txt"/>
<!-- suppression des doublons éventuels -->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!-- Less flexible matching, but less false matches. Probably not ideal for product names,
but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
<fieldType name="textTight" class="solr.TextField" positionIncrementGap="100" >
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
possible with WordDelimiterFilter in conjuncton with stemming. -->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!-- A general unstemmed text field - good if one does not know the language of the field -->
<fieldType name="textgen" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="stopwords.txt"
enablePositionIncrements="true"
/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<!-- A general unstemmed text field that indexes tokens normally and also
reversed (via ReversedWildcardFilterFactory), to enable more efficient
leading wildcard queries. -->
<fieldType name="text_rev" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="stopwords.txt"
enablePositionIncrements="true"
/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
<analyzer>
<!-- KeywordTokenizer does no actual tokenizing, so the entire
input string is preserved as a single token
-->
<tokenizer class="solr.KeywordTokenizerFactory"/>
<!-- The LowerCase TokenFilter does what you expect, which can be
when you want your sorting to be case insensitive
-->
<filter class="solr.LowerCaseFilterFactory" />
<!-- The TrimFilter removes any leading or trailing whitespace -->
<filter class="solr.TrimFilterFactory" />
<filter class="solr.PatternReplaceFilterFactory"
pattern="([^a-z])" replacement="" replace="all"
/>
</analyzer>
</fieldType>
<fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
</analyzer>
</fieldtype>
<fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!--
The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
Attributes of the DelimitedPayloadTokenFilterFactory :
"delimiter" - a one character delimiter. Default is | (pipe)
"encoder" - how to encode the following value into a playload
float -> org.apache.lucene.analysis.payloads.FloatEncoder,
integer -> o.a.l.a.p.IntegerEncoder
identity -> o.a.l.a.p.IdentityEncoder
Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
-->
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
</analyzer>
</fieldtype>
<!-- lowercases the entire field value, keeping it as a single token. -->
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory" />
</analyzer>
</fieldType>
<!-- since fields of this type are by default not stored or indexed,
any data added to them will be ignored outright. -->
<fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
</types>
<fields>
<!-- Vu fields -->
<field name="id" type="string" indexed="true" stored="true" required="true" />
<field name="sku" type="string" indexed="true" stored="true" required="false" />
<field name="collection" type="string" indexed="true" stored="true" required="false" />
<field name="title" type="text_fr" required="false" />
<field name="description" type="text_fr" required="false" />
<field name="price" type="float" required="false" indexed="true" stored="false" />
<field name="brand_id" type="text" required="false" />
<field name="date_online" type="date" required="false" />
<field name="product_type" type="text" required="false" />
<field name="selection_id" type="sint" required="false" multiValued="true" indexed="true" stored="false" />
<field name="stock_delay" type="sint" required="false" />
<field name="stock" type="sint" required="false" />
<field name="price_type" type="sint" required="false" />
<field name="main_product_id" type="text" required="false" />
<field name="date_price" type="date" required="false" />
<!-- attributes -->
<dynamicField name="attr_*" type="sint" indexed="true" multiValued="true"/>
<field name="attr_13" type="int" indexed="true" multiValued="false"/>
<field name="attr_14" type="int" indexed="true" multiValued="false"/>
<field name="attr_19" type="int" indexed="true" multiValued="false"/>
<!-- Ce champ contiendra la copie de tous les autres, pour faciliter la recherche -->
<field name="global" type="text_fr" required="false" multiValued="true" />
<!-- Valid attributes for fields:
name: mandatory - the name for the field
type: mandatory - the name of a previously defined type from the
<types> section
indexed: true if this field should be indexed (searchable or sortable)
stored: true if this field should be retrievable
compressed: [false] if this field should be stored using gzip compression
(this will only apply if the field type is compressable; among
the standard field types, only TextField and StrField are)
multiValued: true if this field may contain multiple values per document
omitNorms: (expert) set to true to omit the norms associated with
this field (this disables length normalization and index-time
boosting for the field, and saves some memory). Only full-text
fields or fields that need an index-time boost need norms.
termVectors: [false] set to true to store the term vector for a
given field.
When using MoreLikeThis, fields used for similarity should be
stored for best performance.
termPositions: Store position information with the term vector.
This will increase storage costs.
termOffsets: Store offset information with the term vector. This
will increase storage costs.
default: a value that should be used if no value is specified
when adding a document.
-->
<!--
<field name="id" type="string" indexed="true" stored="true" required="true" />
<field name="sku" type="textTight" indexed="true" stored="true" omitNorms="true"/>
<field name="name" type="textgen" indexed="true" stored="true"/>
<field name="alphaNameSort" type="alphaOnlySort" indexed="true" stored="false"/>
<field name="manu" type="textgen" indexed="true" stored="true" omitNorms="true"/>
<field name="cat" type="text_ws" indexed="true" stored="true" multiValued="true" omitNorms="true" />
<field name="features" type="text" indexed="true" stored="true" multiValued="true"/>
<field name="includes" type="text" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true" />
<field name="weight" type="float" indexed="true" stored="true"/>
<field name="price" type="float" indexed="true" stored="true"/>
<field name="popularity" type="int" indexed="true" stored="true" />
<field name="inStock" type="boolean" indexed="true" stored="true" />
-->
<!-- Common metadata fields, named specifically to match up with
SolrCell metadata when parsing rich documents such as Word, PDF.
Some fields are multiValued only because Tika currently may return
multiple values for them.
-->
<!--
<field name="title" type="text" indexed="true" stored="true" multiValued="true"/>
<field name="subject" type="text" indexed="true" stored="true"/>
<field name="description" type="text" indexed="true" stored="true"/>
<field name="comments" type="text" indexed="true" stored="true"/>
<field name="author" type="textgen" indexed="true" stored="true"/>
<field name="keywords" type="textgen" indexed="true" stored="true"/>
<field name="category" type="textgen" indexed="true" stored="true"/>
<field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="last_modified" type="date" indexed="true" stored="true"/>
<field name="links" type="string" indexed="true" stored="true" multiValued="true"/>
-->
<!-- catchall field, containing all other searchable text fields (implemented
via copyField further on in this schema -->
<!-- <field name="text" type="text" indexed="true" stored="false" multiValued="true"/> -->
<!-- catchall text field that indexes tokens both normally and in reverse for efficient
leading wildcard queries. -->
<!-- <field name="text_rev" type="text_rev" indexed="true" stored="false" multiValued="true"/> -->
<!-- non-tokenized version of manufacturer to make it easier to sort or group
results by manufacturer. copied from "manu" via copyField -->
<!-- <field name="manu_exact" type="string" indexed="true" stored="false"/> -->
<!-- <field name="payloads" type="payloads" indexed="true" stored="true"/> -->
<!-- Uncommenting the following will create a "timestamp" field using
a default value of "NOW" to indicate when each document was indexed.
-->
<!--
<field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
-->
<!-- Dynamic field definitions. If a field name is not found, dynamicFields
will be used if the name matches any of the patterns.
RESTRICTION: the glob-like pattern in the name attribute must have
a "*" only at the start or the end.
EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
Longer patterns will be matched first. if equal size patterns
both match, the first appearing in the schema will be used. -->
<!--
<dynamicField name="*_i" type="int" indexed="true" stored="true"/>
<dynamicField name="*_s" type="string" indexed="true" stored="true"/>
<dynamicField name="*_l" type="long" indexed="true" stored="true"/>
<dynamicField name="*_t" type="text" indexed="true" stored="true"/>
<dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
<dynamicField name="*_f" type="float" indexed="true" stored="true"/>
<dynamicField name="*_d" type="double" indexed="true" stored="true"/>
<dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
-->
<!-- some trie-coded dynamic fields for faster range queries -->
<!--
<dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
<dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
<dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
<dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
<dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
<dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
<dynamicField name="ignored_*" type="ignored" multiValued="true"/>
<dynamicField name="attr_*" type="textgen" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="random_*" type="random" />
-->
<!-- uncomment the following to ignore any fields that don't already match an existing
field name or dynamic field, rather than reporting them as an error.
alternately, change the type="ignored" to some other type e.g. "text" if you want
unknown fields indexed and/or stored by default -->
<!--dynamicField name="*" type="ignored" multiValued="true" /-->
</fields>
<!-- Field to use to determine and enforce document uniqueness.
Unless this field is marked with required="false", it will be a required field
-->
<uniqueKey>id</uniqueKey>
<!-- field for the QueryParser to use when an explicit fieldname is absent -->
<defaultSearchField>global</defaultSearchField>
<!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
<solrQueryParser defaultOperator="OR"/>
<!-- copyField commands copy one field to another at the time a document
is added to the index. It's used either to index the same field differently,
or to add multiple fields to the same field for easier/faster searching. -->
<copyField source="title" dest="global"/>
<copyField source="description" dest="global"/>
</schema>