|
|
<?xml version="1.0" encoding="UTF-8" ?>
<schema name="example" version="1.5">
<field name="_version_" type="long" indexed="true" stored="true"/>
<field name="_root_" type="string" indexed="true" stored="false"/>
<field name="ProductCode" type="string" indexed="true" stored="true" required="true" multiValued="false" />
<field name="ProductName" type="text_general" indexed="true" stored="true"/>
<dynamicField name="*_i" type="int" indexed="true" stored="true"/>
<dynamicField name="*_is" type="int" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_s" type="string" indexed="true" stored="true" />
<dynamicField name="*_ss" type="string" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_l" type="long" indexed="true" stored="true"/>
<dynamicField name="*_ls" type="long" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
<dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_en" type="text_en" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
<dynamicField name="*_bs" type="boolean" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_f" type="float" indexed="true" stored="true"/>
<dynamicField name="*_fs" type="float" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_d" type="double" indexed="true" stored="true"/>
<dynamicField name="*_ds" type="double" indexed="true" stored="true" multiValued="true"/>
<!-- Type used to index the lat and lon components for the "location" FieldType -->
<dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" />
<dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
<dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_p" type="location" 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="*_c" type="currency" indexed="true" stored="true"/>
<dynamicField name="ignored_*" type="ignored" multiValued="true"/>
<dynamicField name="attr_*" type="text_general" 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" /-->
<!-- Field to use to determine and enforce document uniqueness.
Unless this field is marked with required="false", it will be a required field
-->
<uniqueKey>ProductCode</uniqueKey>
<fieldType name="string">
<!-- boolean type: "true" or "false" -->
<fieldType name="boolean">
<!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
currently supported on types that are sorted internally as strings
and on numeric types.
This includes "string","boolean", and, as of 3.5 (and 4.x),
int, float, long, date, double, including the "Trie" variants.
- If sortMissingLast="true", then a sort on this field will cause documents
without the field to come after documents with the field,
regardless of the requested sort order (asc or desc).
- If sortMissingFirst="true", then a sort on this field will cause documents
without the field to come before documents with the field,
regardless of the requested sort order.
- If sortMissingLast="false" and sortMissingFirst="false" (the default),
then default lucene sorting will be used which places docs without the
field first in an ascending sort and last in a descending sort.
-->
<!--
Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
These fields support doc values, but they require the field to be
single-valued and either be required or have a default value.
-->
<fieldType name="int">
<fieldType name="float">
<fieldType name="long">
<fieldType name="double">
<!--
Numeric field types that index each value at various levels of precision
to accelerate range queries when the number of values between the range
endpoints is large. See the javadoc for NumericRangeQuery for internal
implementation details.
Smaller precisionStep values (specified in bits) will lead to more tokens
indexed per value, slightly larger index> A precisionStep of 0 disables indexing at different precision levels.
-->
<fieldType name="tint">
<fieldType name="tfloat">
<fieldType name="tlong">
<fieldType name="tdouble">
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
is a more restricted form of the canonical representation of dateTime
http://www.w3.org/TR/xmlschema-2/#dateTime
The trailing "Z" designates UTC time and is mandatory.
Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
All other components are mandatory.
Expressions can also be used to denote calculations that should be
performed>
NOW/HOUR
... Round to the start of the current hour
NOW-1DAY
... Exactly 1 day prior to now
NOW/DAY+6MONTHS+3DAYS
... 6 months and 3 days in the future from the start of
the current day
Consult the DateField javadocs for more information.
Note: For faster range queries, consider the tdate type
-->
<fieldType name="date">
<!-- A Trie based date field for faster date range queries and date>
<fieldType name="tdate">
<!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
<fieldtype name="binary">
<!--
Note:
These should only be used for compatibility with existing indexes (created with lucene or older Solr versions).
Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last
Plain numeric field types that store and index the text
value verbatim (and hence don't correctly support range queries, since the
lexicographic ordering isn't equal to the numeric ordering)
NOTE: These field types are deprecated will be removed in Solr 5.0!
-->
<fieldType name="pint">
<fieldType name="plong">
<fieldType name="pfloat">
<fieldType name="pdouble">
<fieldType name="pdate">
<!-- The "RandomSortField" is not used to store or search any
data. You can declare fields of this type it in your schema
to generate pseudo-random orderings of your docs for sorting
or function purposes. The ordering is generated based on the field
name and the version of the index. As long as the index version
remains unchanged, and the same field name is reused,
the ordering of the docs will be consistent.
If you want different psuedo-random orderings of documents,
for the same version of the index, use a dynamicField and
change the field name in the request.
-->
<fieldType name="random">
<!-- solr.TextField allows the specification of custom text analyzers
specified as a tokenizer and a list of token filters. Different
analyzers may be specified for indexing and querying.
The optional positionIncrementGap puts space between multiple fields of
this type on the same document, with the purpose of preventing false phrase
matching across fields.
For more info on customizing your analyzer chain, please see
http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
-->
<!-- One can also specify an existing Analyzer>
default constructor via the> Example:
<fieldType name="text_greek">
<analyzer> </fieldType>
-->
<!-- A text field that only splits on whitespace for exact matching of words -->
<fieldType name="text_ws"> <analyzer>
<tokenizer> </analyzer>
</fieldType>
<!-- A text type for English text where stopwords and synonyms are managed using the REST API -->
<fieldType name="managed_en"> <analyzer>
<tokenizer>
<filter>
<filter> </analyzer>
</fieldType>
<!-- A general text field that has reasonable, generic
cross-language defaults: it tokenizes with StandardTokenizer,
removes stop words from case-insensitive "stopwords.txt"
(empty by default), and down cases. At query time only, it
also applies synonyms. -->
<fieldType name="text_general"> <analyzer type="index">
<tokenizer>
<filter> <!-- in this example, we will only use synonyms at query time
<filter> -->
<filter> </analyzer>
<analyzer type="query">
<tokenizer>
<filter>
<filter>
<filter> </analyzer>
</fieldType>
<!-- A text field with defaults appropriate for English: it
tokenizes with StandardTokenizer, removes English stop words
(lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
finally applies Porter's stemming. The query time analyzer
also applies synonyms from synonyms.txt. -->
<fieldType name="text_en"> <analyzer type="index">
<tokenizer> <!-- in this example, we will only use synonyms at query time
<filter> -->
<!-- Case insensitive stop word removal.
-->
<filter> ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter>
<filter>
<filter> <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter> -->
<filter> </analyzer>
<analyzer type="query">
<tokenizer>
<filter>
<filter> ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter>
<filter>
<filter> <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter> -->
<filter> </analyzer>
</fieldType>
<!-- A text field with defaults appropriate for English, plus
aggressive word-splitting and autophrase features enabled.
This field is just like text_en, except it adds
WordDelimiterFilter to enable splitting and matching of
words on case-change, alpha numeric boundaries, and
non-alphanumeric chars. This means certain compound word
cases will work, for example query "wi fi" will match
document "WiFi" or "wi-fi".
-->
<fieldType name="text_en_splitting"> <analyzer type="index">
<tokenizer> <!-- in this example, we will only use synonyms at query time
<filter> -->
<!-- Case insensitive stop word removal.
-->
<filter> ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter>
<filter>
<filter>
<filter> </analyzer>
<analyzer type="query">
<tokenizer>
<filter>
<filter> ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter>
<filter>
<filter>
<filter> </analyzer>
</fieldType>
<!-- Less flexible matching, but less false matches. Probably not> but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
<fieldType name="text_en_splitting_tight"> <analyzer>
<tokenizer>
<filter>
<filter>
<filter>
<filter>
<filter>
<filter> <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
possible with WordDelimiterFilter in conjuncton with stemming. -->
<filter> </analyzer>
</fieldType>
<!-- Just like text_general except it reverses the characters of
each token, to enable more efficient leading wildcard queries. -->
<fieldType name="text_general_rev"> <analyzer type="index">
<tokenizer>
<filter>
<filter>
<filter> maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
</analyzer>
<analyzer type="query">
<tokenizer>
<filter>
<filter>
<filter> </analyzer>
</fieldType>
<!-- charFilter + WhitespaceTokenizer -->
<!--
<fieldType name="text_char_norm"> <analyzer>
<charFilter>
<tokenizer> </analyzer>
</fieldType>
-->
<!-- This is an example of using the KeywordTokenizer along
With various TokenFilterFactories to produce a sortable field
that does not include some properties of the source text
-->
<fieldType name="alphaOnlySort"> <analyzer>
<!-- KeywordTokenizer does no actual tokenizing, so the entire
input string is preserved as a single token
-->
<tokenizer> <!-- The LowerCase TokenFilter does what you expect, which can be
when you want your sorting to be case insensitive
-->
<filter> <!-- The TrimFilter removes any leading or trailing whitespace -->
<filter> <!-- The PatternReplaceFilter gives you the flexibility to use
Java Regular expression to replace any sequence of characters
matching a pattern with an arbitrary replacement string,
which may include back references to portions of the original
string matched by the pattern.
See the Java Regular Expression documentation for more
information on pattern and replacement string syntax.
http://docs.oracle.com/javase/7/docs/api/java/util/regex/package-summary.html
-->
<filter> pattern="([^a-z])" replacement="" replace="all"
/>
</analyzer>
</fieldType>
<fieldtype name="phonetic" stored="false" indexed="true"> <analyzer>
<tokenizer>
<filter> </analyzer>
</fieldtype>
<fieldtype name="payloads" stored="false" indexed="true"> <analyzer>
<tokenizer> <!--
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> -->
<filter> </analyzer>
</fieldtype>
<!-- lowercases the entire field value, keeping it as a single token. -->
<fieldType name="lowercase"> <analyzer>
<tokenizer>
<filter> </analyzer>
</fieldType>
<!--
Example of using PathHierarchyTokenizerFactory at index time, so
queries for paths match documents at that path, or in descendent paths
-->
<fieldType name="descendent_path"> <analyzer type="index">
<tokenizer> </analyzer>
<analyzer type="query">
<tokenizer> </analyzer>
</fieldType>
<!--
Example of using PathHierarchyTokenizerFactory at query time, so
queries for paths match documents at that path, or in ancestor paths
-->
<fieldType name="ancestor_path"> <analyzer type="index">
<tokenizer> </analyzer>
<analyzer type="query">
<tokenizer> </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">
<!-- This point type indexes the coordinates as separate fields (subFields)
If subFieldType is defined, it references a type, and a dynamic field
definition is created matching *___<typename>. > subFieldSuffix is defined, that is used to create the subFields.
Example: if subFieldType="double", then the coordinates would be
indexed in fields myloc_0___double,myloc_1___double.
Example: if subFieldSuffix="_d" then the coordinates would be indexed
in fields myloc_0_d,myloc_1_d
The subFields are an implementation detail of the fieldType, and end
users normally should not need to know about them.
-->
<fieldType name="point">
<!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
<fieldType name="location">
<!-- An> For more information about this and other Spatial fields new to Solr 4, see:
http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
-->
<fieldType name="location_rpt"> geo="true" distErrPct="0.025" maxDistErr="0.000009" units="degrees" />
<!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
Parameters:
defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
providerClass: Lets you plug in other exchange provider backend:
solr.FileExchangeRateProvider is the default and takes one parameter:
currencyConfig: name of an xml file holding exchange rates
solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
-->
<fieldType name="currency">
<!-- some examples for different languages (generally ordered by ISO code) -->
<!-- Arabic -->
<fieldType name="text_ar"> <analyzer>
<tokenizer> <!-- for any non-arabic -->
<filter>
<filter> <!-- normalizes ﻯ to ﻱ, etc -->
<filter>
<filter> </analyzer>
</fieldType>
<!-- Bulgarian -->
<fieldType name="text_bg"> <analyzer>
<tokenizer>
<filter>
<filter>
<filter> </analyzer>
</fieldType>
<!-- Catalan -->
<fieldType name="text_ca"> <analyzer>
<tokenizer> <!-- removes l', etc -->
<filter>
<filter>
<filter>
<filter> </analyzer>
</fieldType>
<!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
<fieldType name="text_cjk"> <analyzer>
<tokenizer>
<!-- normalize>
<filter> <!-- for any non-CJK -->
<filter>
<filter> </analyzer>
</fieldType>
<!-- Kurdish -->
<fieldType name="text_ckb"> <analyzer>
<tokenizer>
<filter> <!-- for any latin text -->
<filter>
<filter>
<filter> </analyzer>
</fieldType>
<!-- Czech -->
<fieldType name="text_cz"> <analyzer>
<tokenizer>
<filter>
<filter>
<filter> </analyzer>
</fieldType>
<!-- Danish -->
<fieldType name="text_da"> <analyzer>
<tokenizer>
<filter>
<filter>
<filter> </analyzer>
</fieldType>
<!-- German -->
<fieldType name="text_de"> <analyzer>
<tokenizer>
<filter>
<filter>
<filter>
<filter>
<!-- less aggressive: <filter>
<!-- more aggressive: <filter> </analyzer>
</fieldType>
<!-- Greek -->
<fieldType name="text_el"> <analyzer>
<tokenizer> <!-- greek specific lowercase for sigma -->
<filter>
<filter>
<filter> </analyzer>
</fieldType>
<!-- Spanish -->
<fieldType name="text_es"> <analyzer>
<tokenizer>
<filter>
<filter>
<filter>
<!-- more aggressive: <filter> </analyzer>
</fieldType>
<!-- Basque -->
<fieldType name="text_eu"> <analyzer>
<tokenizer>
<filter>
<filter>
<filter> </analyzer>
</fieldType>
<!-- Persian -->
<fieldType name="text_fa"> <analyzer>
<!-- for ZWNJ -->
<charFilter>
<tokenizer>
<filter>
<filter>
<filter>
<filter> </analyzer>
</fieldType>
<!-- Finnish -->
<fieldType name="text_fi"> <analyzer>
<tokenizer>
<filter>
<filter>
<filter>
<!-- less aggressive: <filter> </analyzer>
</fieldType>
<!-- French -->
<fieldType name="text_fr"> <analyzer>
<tokenizer> <!-- removes l', etc -->
<filter>
<filter>
<filter>
<filter>
<!-- less aggressive: <filter>
<!-- more aggressive: <filter> </analyzer>
</fieldType>
<!-- Irish -->
<fieldType name="text_ga"> <analyzer>
<tokenizer> <!-- removes d', etc -->
<filter> <!-- removes n-, etc. position increments is intentionally false! -->
<filter>
<filter>
<filter>
<filter> </analyzer>
</fieldType>
<!-- Galician -->
<fieldType name="text_gl"> <analyzer>
<tokenizer>
<filter>
<filter>
<filter>
<!-- less aggressive: <filter> </analyzer>
</fieldType>
<!-- Hindi -->
<fieldType name="text_hi"> <analyzer>
<tokenizer>
<filter> <!-- normalizes unicode representation -->
<filter> <!-- normalizes variation in spelling -->
<filter>
<filter>
<filter> </analyzer>
</fieldType>
<!-- Hungarian -->
<fieldType name="text_hu"> <analyzer>
<tokenizer>
<filter>
<filter>
<filter>
<!-- less aggressive: <filter> </analyzer>
</fieldType>
<!-- Armenian -->
<fieldType name="text_hy"> <analyzer>
<tokenizer>
<filter>
<filter>
<filter> </analyzer>
</fieldType>
<!-- Indonesian -->
<fieldType name="text_id"> <analyzer>
<tokenizer>
<filter>
<filter> <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
<filter> </analyzer>
</fieldType>
<!-- Italian -->
<fieldType name="text_it"> <analyzer>
<tokenizer> <!-- removes l', etc -->
<filter>
<filter>
<filter>
<filter>
<!-- more aggressive: <filter> </analyzer>
</fieldType>
<!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
NOTE: If you want to optimize search for precision, use default operator AND in your query
parser config with <solrQueryParser defaultOperator="AND"/> further down in this file. Use
OR if you would like to optimize for recall (default).
-->
<fieldType name="text_ja"> <analyzer>
<!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
is used to segment compounds into its parts and the compound itself is kept as synonym.
Valid values for attribute mode are:
normal: regular segmentation
search: segmentation useful for search with synonyms compounds (default)
extended: same as search mode, but unigrams unknown words (experimental)
For some applications it might be good to use search mode for indexing and normal mode for
queries to reduce recall and prevent parts of compounds from being matched and highlighted.
Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
model with your own entries for segmentation, part-of-speech tags and readings without a need
to specify weights. Notice that user dictionaries have not been subject to extensive testing.
User dictionary attributes are:
userDictionary: user dictionary filename
userDictionaryEncoding: user dictionary encoding (default is UTF-8)
See lang/userdict_ja.txt for a sample user dictionary file.
Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
-->
<tokenizer>
<!--<tokenizer> <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
<filter> <!-- Removes tokens with certain part-of-speech tags -->
<filter> <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
<filter> <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
<filter> <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
<filter> <!-- Lower-cases romaji characters -->
<filter> </analyzer>
</fieldType>
<!-- Latvian -->
<fieldType name="text_lv"> <analyzer>
<tokenizer>
<filter>
<filter>
<filter> </analyzer>
</fieldType>
<!-- Dutch -->
<fieldType name="text_nl"> <analyzer>
<tokenizer>
<filter>
<filter>
<filter>
<filter> </analyzer>
</fieldType>
<!-- Norwegian -->
<fieldType name="text_no"> <analyzer>
<tokenizer>
<filter>
<filter>
<filter>
<!-- less aggressive: <filter>
<!-- singular/plural: <filter> <!-- The "light" and "minimal" stemmers support variants: nb=Bokmål, nn=Nynorsk, no=Both -->
</analyzer>
</fieldType>
<!-- Portuguese -->
<fieldType name="text_pt"> <analyzer>
<tokenizer>
<filter>
<filter>
<filter>
<!-- less aggressive: <filter>
<!-- more aggressive: <filter>
<!-- most aggressive: <filter> </analyzer>
</fieldType>
<!-- Romanian -->
<fieldType name="text_ro"> <analyzer>
<tokenizer>
<filter>
<filter>
<filter> </analyzer>
</fieldType>
<!-- Russian -->
<fieldType name="text_ru"> <analyzer>
<tokenizer>
<filter>
<filter>
<filter>
<!-- less aggressive: <filter> </analyzer>
</fieldType>
<!-- Swedish -->
<fieldType name="text_sv"> <analyzer>
<tokenizer>
<filter>
<filter>
<filter>
<!-- less aggressive: <filter> </analyzer>
</fieldType>
<!-- Thai -->
<fieldType name="text_th"> <analyzer>
<tokenizer>
<filter>
<filter>
<filter> </analyzer>
</fieldType>
<!-- Turkish -->
<fieldType name="text_tr"> <analyzer>
<tokenizer>
<filter>
<filter>
<filter>
<filter> </analyzer>
</fieldType>
<!-- Similarity is the scoring routine for each document vs. a query.
A custom Similarity or SimilarityFactory may be specified here, but
the default is fine for most applications.
For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
-->
<!--
<similarity> <str name="paramkey">param value</str>
</similarity>
-->
</schema>
|
|
QQ群⑧：
窥视卡
雷达卡
发表于 2017-12-19 11:24:45
提升卡
置顶卡
沉默卡
喧嚣卡
变色卡
千斤顶
显身卡