API tools faq
paste
allan_atosho_com

schema.xml

allan_atosho_com
Nov 22nd, 2012
169
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
XML 49.18 KB | None | 0 0
raw download clone embed print report
  1. <?xml version="1.0" encoding="UTF-8" ?>
  2. <schema name="production" version="1.5">
  3.  <fields>
  4.     <field name="brand" type="string" indexed="true" stored="true" />
  5.     <field name="brandid" type="string" indexed="true" stored="true" />
  6.     <field name="categories" type="text_general" indexed="true" stored="true" />
  7.     <field name="colorids" type="int" indexed="true" stored="true" multiValued="true" />
  8.     <field name="currency" type="text_general" indexed="false" stored="true" />
  9.     <field name="currencyid" type="int" indexed="false" stored="true" />
  10.     <field name="currencyiso" type="string" indexed="true" stored="true" />
  11.     <field name="description" type="text_general" indexed="true" stored="true" />
  12.     <field name="featured" type="boolean" indexed="true" stored="true" />
  13.     <field name="globalcategoryids" type="int" indexed="true" stored="true" multiValued="true" />
  14.     <field name="globalcategorynames" type="text_general" indexed="true" stored="true" multiValued="true" />
  15.     <field name="imageid" type="int" indexed="false" stored="true" />
  16.     <field name="imagetype" type="string" indexed="false" stored="true" />
  17.     <field name="indextime" type="string" indexed="false" stored="true" />
  18.     <field name="languageid" type="string" indexed="false" stored="true" />
  19.     <field name="merchant" type="text_general" indexed="false" stored="true" />
  20.     <field name="merchantcategoryids" type="int" indexed="true" stored="true" multiValued="true" />
  21.     <field name="merchantid" type="int" indexed="true" stored="true" />
  22.     <field name="merchantidstr" type="string" indexed="true" stored="false" />
  23.     <field name="merchantimageid" type="int" indexed="false" stored="true" />
  24.     <field name="merchantimagewidth" type="int" indexed="false" stored="true" />
  25.     <field name="merchantimageheight" type="int" indexed="false" stored="true" />
  26.     <field name="merchantimagefiletype" type="string" indexed="false" stored="true" />
  27.     <field name="meta" type="text_general" indexed="true" stored="true" />
  28.     <field name="originalprice" type="double" indexed="false" stored="true" />
  29.     <field name="preview" type="text_general" indexed="false" stored="true" />
  30.     <field name="price" type="double" indexed="true" stored="true" />
  31.     <field name="productid" type="string" indexed="true" stored="true" />
  32.     <field name="productidint" type="int" indexed="true" stored="false" />
  33.     <field name="publishercategoryids" type="int" indexed="true" stored="true" multiValued="true" />
  34.     <field name="savedpercentage" type="double" indexed="true" stored="true" />
  35.     <field name="shippingdiscountthreshold" type="double" indexed="false" stored="true" />
  36.     <field name="shippingprice" type="double" indexed="true" stored="true" />
  37.     <field name="shippingtime" type="string" indexed="false" stored="true" />
  38.     <field name="shippingtype" type="string" indexed="false" stored="true" />
  39.     <field name="SKU" type="string" indexed="true" stored="true" />
  40.     <field name="stock" type="int" indexed="false" stored="true" />
  41.     <field name="thumbnailurl" type="string" indexed="false" stored="true" />
  42.     <field name="thumbnailurlhttps" type="string" indexed="false" stored="true" />
  43.     <field name="title" type="text_general" indexed="true" stored="true" />
  44.     <field name="CVR" type="double" indexed="true" stored="true" />
  45.     <field name="masterEAN" type="string" indexed="true" stored="true" />
  46.     <field name="externalurl" type="string" indexed="true" stored="true" />
  47.     <field name="variantids" type="int" indexed="true" stored="true" multiValued="true" />
  48.  
  49.     <field name="text" type="text_general" indexed="true" stored="true"  multiValued="true" />
  50.     <field name="EAN" type="string" indexed="true" stored="true" multiValued="true" />
  51.     <field name="externalurls" type="string" indexed="true" stored="true" multiValued="true" />
  52.  
  53.     <dynamicField name="headword_random_*" type="random" indexed="true" stored="false" />
  54.  
  55.     <dynamicField name="*_variant_title" type="text_general" indexed="false" stored="true" />
  56.     <dynamicField name="*_variant_EAN" type="string" index="false" stored="true" />
  57.     <dynamicField name="*_variant_externalurl" type="string" indexed="false" stored="true" />
  58.     <dynamicField name="*_variant_meta" type="text_general" indexed="false" stored="true" />
  59.     <!--<dynamicField name="*_variant_SKU" type="string" indexed="true" stored="true" />
  60.    <dynamicField name="*_variant_imageid" type="int" indexed="false" stored="true" />
  61.    <dynamicField name="*_variant_originalprice" type="double" indexed="false" stored="true" />
  62.    <dynamicField name="*_variant_price" type="double" indexed="true" stored="true" />
  63.    <dynamicField name="*_variant_savedpercentage" type="double" indexed="true"  stored="true" />
  64.    <dynamicField name="*_variant_stock" type="int" indexed="false" stored="true" />-->
  65.  </fields>
  66.  
  67.  <uniqueKey>productid</uniqueKey>
  68.  
  69.     <copyField source="title" dest="text"/>
  70.     <copyField source="description" dest="text"/>
  71.     <copyField source="meta" dest="text"/>
  72.     <copyField source="categories" dest="text"/>
  73.     <copyField source="merchant" dest="text"/>
  74.     <copyField source="globalcategorynames" dest="text"/>
  75.     <copyField source="merchantid" dest="merchantidstr" />
  76.     <copyField source="productid" dest="productidint" />
  77.  
  78.     <copyField source="masterEAN" dest="EAN" />
  79.     <copyField source="externalurl" dest="externalurls" />
  80.  
  81.     <copyField source="*_variant_title" dest="text" />
  82.     <copyField source="*_variant_EAN" dest="EAN" />
  83.     <copyField source="*_variant_externalurl" dest="externalurls" />
  84.     <copyField source="*_variant_meta" dest="text" />
  85.  
  86.   <types>
  87.     <!-- field type definitions. The "name" attribute is
  88.       just a label to be used by field definitions.  The "class"
  89.       attribute and any other attributes determine the real
  90.       behavior of the fieldType.
  91.         Class names starting with "solr" refer to java classes in a
  92.       standard package such as org.apache.solr.analysis
  93.    -->
  94.  
  95.     <!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
  96.     <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
  97.  
  98.     <!-- boolean type: "true" or "false" -->
  99.     <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
  100.  
  101.     <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
  102.         currently supported on types that are sorted internally as strings
  103.         and on numeric types.
  104.          This includes "string","boolean", and, as of 3.5 (and 4.x),
  105.          int, float, long, date, double, including the "Trie" variants.
  106.       - If sortMissingLast="true", then a sort on this field will cause documents
  107.         without the field to come after documents with the field,
  108.         regardless of the requested sort order (asc or desc).
  109.       - If sortMissingFirst="true", then a sort on this field will cause documents
  110.         without the field to come before documents with the field,
  111.         regardless of the requested sort order.
  112.       - If sortMissingLast="false" and sortMissingFirst="false" (the default),
  113.         then default lucene sorting will be used which places docs without the
  114.         field first in an ascending sort and last in a descending sort.
  115.    -->    
  116.  
  117.     <!--
  118.      Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
  119.    -->
  120.     <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
  121.     <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
  122.     <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
  123.     <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
  124.  
  125.     <!--
  126.     Numeric field types that index each value at various levels of precision
  127.     to accelerate range queries when the number of values between the range
  128.     endpoints is large. See the javadoc for NumericRangeQuery for internal
  129.     implementation details.
  130.  
  131.     Smaller precisionStep values (specified in bits) will lead to more tokens
  132.     indexed per value, slightly larger index size, and faster range queries.
  133.     A precisionStep of 0 disables indexing at different precision levels.
  134.    -->
  135.     <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
  136.     <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
  137.     <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
  138.     <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
  139.  
  140.     <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
  141.         is a more restricted form of the canonical representation of dateTime
  142.         http://www.w3.org/TR/xmlschema-2/#dateTime    
  143.         The trailing "Z" designates UTC time and is mandatory.
  144.         Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
  145.         All other components are mandatory.
  146.  
  147.         Expressions can also be used to denote calculations that should be
  148.         performed relative to "NOW" to determine the value, ie...
  149.  
  150.               NOW/HOUR
  151.                  ... Round to the start of the current hour
  152.               NOW-1DAY
  153.                  ... Exactly 1 day prior to now
  154.               NOW/DAY+6MONTHS+3DAYS
  155.                  ... 6 months and 3 days in the future from the start of
  156.                      the current day
  157.                      
  158.         Consult the DateField javadocs for more information.
  159.  
  160.         Note: For faster range queries, consider the tdate type
  161.      -->
  162.     <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
  163.  
  164.     <!-- A Trie based date field for faster date range queries and date faceting. -->
  165.     <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
  166.  
  167.  
  168.     <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
  169.     <fieldtype name="binary" class="solr.BinaryField"/>
  170.  
  171.     <!--
  172.      Note:
  173.      These should only be used for compatibility with existing indexes (created with lucene or older Solr versions).
  174.      Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last
  175.      
  176.      Plain numeric field types that store and index the text
  177.      value verbatim (and hence don't correctly support range queries, since the
  178.      lexicographic ordering isn't equal to the numeric ordering)
  179.    -->
  180.     <fieldType name="pint" class="solr.IntField"/>
  181.     <fieldType name="plong" class="solr.LongField"/>
  182.     <fieldType name="pfloat" class="solr.FloatField"/>
  183.     <fieldType name="pdouble" class="solr.DoubleField"/>
  184.     <fieldType name="pdate" class="solr.DateField" sortMissingLast="true"/>
  185.  
  186.     <!-- The "RandomSortField" is not used to store or search any
  187.         data.  You can declare fields of this type it in your schema
  188.         to generate pseudo-random orderings of your docs for sorting
  189.         or function purposes.  The ordering is generated based on the field
  190.         name and the version of the index. As long as the index version
  191.         remains unchanged, and the same field name is reused,
  192.         the ordering of the docs will be consistent.  
  193.         If you want different psuedo-random orderings of documents,
  194.         for the same version of the index, use a dynamicField and
  195.         change the field name in the request.
  196.     -->
  197.     <fieldType name="random" class="solr.RandomSortField" indexed="true" />
  198.  
  199.     <!-- solr.TextField allows the specification of custom text analyzers
  200.         specified as a tokenizer and a list of token filters. Different
  201.         analyzers may be specified for indexing and querying.
  202.  
  203.         The optional positionIncrementGap puts space between multiple fields of
  204.         this type on the same document, with the purpose of preventing false phrase
  205.         matching across fields.
  206.  
  207.         For more info on customizing your analyzer chain, please see
  208.         http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
  209.     -->
  210.  
  211.     <!-- One can also specify an existing Analyzer class that has a
  212.         default constructor via the class attribute on the analyzer element.
  213.         Example:
  214.    <fieldType name="text_greek" class="solr.TextField">
  215.      <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
  216.    </fieldType>
  217.    -->
  218.  
  219.     <!-- A text field that only splits on whitespace for exact matching of words -->
  220.     <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
  221.       <analyzer>
  222.         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
  223.       </analyzer>
  224.     </fieldType>
  225.  
  226.     <!-- A general text field that has reasonable, generic
  227.         cross-language defaults: it tokenizes with StandardTokenizer,
  228.      removes stop words from case-insensitive "stopwords.txt"
  229.      (empty by default), and down cases.  At query time only, it
  230.      also applies synonyms. -->
  231.     <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
  232.       <analyzer type="index">
  233.         <tokenizer class="solr.StandardTokenizerFactory"/>
  234.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
  235.         <!-- in this example, we will only use synonyms at query time
  236.        <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
  237.        -->
  238.         <filter class="solr.LowerCaseFilterFactory"/>
  239.       </analyzer>
  240.       <analyzer type="query">
  241.         <tokenizer class="solr.StandardTokenizerFactory"/>
  242.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
  243.         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
  244.         <filter class="solr.LowerCaseFilterFactory"/>
  245.       </analyzer>
  246.     </fieldType>
  247.  
  248.     <!-- A text field with defaults appropriate for English: it
  249.         tokenizes with StandardTokenizer, removes English stop words
  250.         (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
  251.         finally applies Porter's stemming.  The query time analyzer
  252.         also applies synonyms from synonyms.txt. -->
  253.     <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
  254.       <analyzer type="index">
  255.         <tokenizer class="solr.StandardTokenizerFactory"/>
  256.         <!-- in this example, we will only use synonyms at query time
  257.        <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
  258.        -->
  259.         <!-- Case insensitive stop word removal.
  260.          add enablePositionIncrements=true in both the index and query
  261.          analyzers to leave a 'gap' for more accurate phrase queries.
  262.        -->
  263.         <filter class="solr.StopFilterFactory"
  264.                ignoreCase="true"
  265.                words="lang/stopwords_en.txt"
  266.                enablePositionIncrements="true"
  267.                />
  268.         <filter class="solr.LowerCaseFilterFactory"/>
  269.     <filter class="solr.EnglishPossessiveFilterFactory"/>
  270.         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
  271.     <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
  272.        <filter class="solr.EnglishMinimalStemFilterFactory"/>
  273.     -->
  274.         <filter class="solr.PorterStemFilterFactory"/>
  275.       </analyzer>
  276.       <analyzer type="query">
  277.         <tokenizer class="solr.StandardTokenizerFactory"/>
  278.         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
  279.         <filter class="solr.StopFilterFactory"
  280.                ignoreCase="true"
  281.                words="lang/stopwords_en.txt"
  282.                enablePositionIncrements="true"
  283.                />
  284.         <filter class="solr.LowerCaseFilterFactory"/>
  285.     <filter class="solr.EnglishPossessiveFilterFactory"/>
  286.         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
  287.     <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
  288.        <filter class="solr.EnglishMinimalStemFilterFactory"/>
  289.     -->
  290.         <filter class="solr.PorterStemFilterFactory"/>
  291.       </analyzer>
  292.     </fieldType>
  293.  
  294.     <!-- A text field with defaults appropriate for English, plus
  295.      aggressive word-splitting and autophrase features enabled.
  296.      This field is just like text_en, except it adds
  297.      WordDelimiterFilter to enable splitting and matching of
  298.      words on case-change, alpha numeric boundaries, and
  299.      non-alphanumeric chars.  This means certain compound word
  300.      cases will work, for example query "wi fi" will match
  301.      document "WiFi" or "wi-fi".
  302.        -->
  303.     <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
  304.       <analyzer type="index">
  305.         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
  306.         <!-- in this example, we will only use synonyms at query time
  307.        <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
  308.        -->
  309.         <!-- Case insensitive stop word removal.
  310.          add enablePositionIncrements=true in both the index and query
  311.          analyzers to leave a 'gap' for more accurate phrase queries.
  312.        -->
  313.         <filter class="solr.StopFilterFactory"
  314.                ignoreCase="true"
  315.                words="lang/stopwords_en.txt"
  316.                enablePositionIncrements="true"
  317.                />
  318.         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
  319.         <filter class="solr.LowerCaseFilterFactory"/>
  320.         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
  321.         <filter class="solr.PorterStemFilterFactory"/>
  322.       </analyzer>
  323.       <analyzer type="query">
  324.         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
  325.         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
  326.         <filter class="solr.StopFilterFactory"
  327.                ignoreCase="true"
  328.                words="lang/stopwords_en.txt"
  329.                enablePositionIncrements="true"
  330.                />
  331.         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
  332.         <filter class="solr.LowerCaseFilterFactory"/>
  333.         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
  334.         <filter class="solr.PorterStemFilterFactory"/>
  335.       </analyzer>
  336.     </fieldType>
  337.  
  338.     <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
  339.         but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
  340.     <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
  341.       <analyzer>
  342.         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
  343.         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
  344.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
  345.         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
  346.         <filter class="solr.LowerCaseFilterFactory"/>
  347.         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
  348.         <filter class="solr.EnglishMinimalStemFilterFactory"/>
  349.         <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
  350.             possible with WordDelimiterFilter in conjuncton with stemming. -->
  351.         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  352.       </analyzer>
  353.     </fieldType>
  354.  
  355.     <!-- Just like text_general except it reverses the characters of
  356.      each token, to enable more efficient leading wildcard queries. -->
  357.     <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
  358.       <analyzer type="index">
  359.         <tokenizer class="solr.StandardTokenizerFactory"/>
  360.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
  361.         <filter class="solr.LowerCaseFilterFactory"/>
  362.         <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
  363.           maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
  364.       </analyzer>
  365.       <analyzer type="query">
  366.         <tokenizer class="solr.StandardTokenizerFactory"/>
  367.         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
  368.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
  369.         <filter class="solr.LowerCaseFilterFactory"/>
  370.       </analyzer>
  371.     </fieldType>
  372.  
  373.     <!-- charFilter + WhitespaceTokenizer  -->
  374.     <!--
  375.    <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
  376.      <analyzer>
  377.        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
  378.        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
  379.      </analyzer>
  380.    </fieldType>
  381.    -->
  382.  
  383.     <!-- This is an example of using the KeywordTokenizer along
  384.         With various TokenFilterFactories to produce a sortable field
  385.         that does not include some properties of the source text
  386.      -->
  387.     <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
  388.       <analyzer>
  389.         <!-- KeywordTokenizer does no actual tokenizing, so the entire
  390.             input string is preserved as a single token
  391.          -->
  392.         <tokenizer class="solr.KeywordTokenizerFactory"/>
  393.         <!-- The LowerCase TokenFilter does what you expect, which can be
  394.             when you want your sorting to be case insensitive
  395.          -->
  396.         <filter class="solr.LowerCaseFilterFactory" />
  397.         <!-- The TrimFilter removes any leading or trailing whitespace -->
  398.         <filter class="solr.TrimFilterFactory" />
  399.         <!-- The PatternReplaceFilter gives you the flexibility to use
  400.             Java Regular expression to replace any sequence of characters
  401.             matching a pattern with an arbitrary replacement string,
  402.             which may include back references to portions of the original
  403.             string matched by the pattern.
  404.            
  405.             See the Java Regular Expression documentation for more
  406.             information on pattern and replacement string syntax.
  407.            
  408.             http://java.sun.com/j2se/1.6.0/docs/api/java/util/regex/package-summary.html
  409.          -->
  410.         <filter class="solr.PatternReplaceFilterFactory"
  411.                pattern="([^a-z])" replacement="" replace="all"
  412.        />
  413.       </analyzer>
  414.     </fieldType>
  415.    
  416.     <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
  417.       <analyzer>
  418.         <tokenizer class="solr.StandardTokenizerFactory"/>
  419.         <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
  420.       </analyzer>
  421.     </fieldtype>
  422.  
  423.     <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
  424.       <analyzer>
  425.         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
  426.         <!--
  427.        The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
  428.        a token of "foo|1.4"  would be indexed as "foo" with a payload of 1.4f
  429.        Attributes of the DelimitedPayloadTokenFilterFactory :
  430.         "delimiter" - a one character delimiter. Default is | (pipe)
  431.      "encoder" - how to encode the following value into a playload
  432.         float -> org.apache.lucene.analysis.payloads.FloatEncoder,
  433.         integer -> o.a.l.a.p.IntegerEncoder
  434.         identity -> o.a.l.a.p.IdentityEncoder
  435.            Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
  436.         -->
  437.         <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
  438.       </analyzer>
  439.     </fieldtype>
  440.  
  441.     <!-- lowercases the entire field value, keeping it as a single token.  -->
  442.     <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
  443.       <analyzer>
  444.         <tokenizer class="solr.KeywordTokenizerFactory"/>
  445.         <filter class="solr.LowerCaseFilterFactory" />
  446.       </analyzer>
  447.     </fieldType>
  448.  
  449.     <!--
  450.      Example of using PathHierarchyTokenizerFactory at index time, so
  451.      queries for paths match documents at that path, or in descendent paths
  452.    -->
  453.     <fieldType name="descendent_path" class="solr.TextField">
  454.       <analyzer type="index">
  455.     <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
  456.       </analyzer>
  457.       <analyzer type="query">
  458.     <tokenizer class="solr.KeywordTokenizerFactory" />
  459.       </analyzer>
  460.     </fieldType>
  461.     <!--
  462.      Example of using PathHierarchyTokenizerFactory at query time, so
  463.      queries for paths match documents at that path, or in ancestor paths
  464.    -->
  465.     <fieldType name="ancestor_path" class="solr.TextField">
  466.       <analyzer type="index">
  467.     <tokenizer class="solr.KeywordTokenizerFactory" />
  468.       </analyzer>
  469.       <analyzer type="query">
  470.     <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
  471.       </analyzer>
  472.     </fieldType>
  473.  
  474.     <!-- since fields of this type are by default not stored or indexed,
  475.         any data added to them will be ignored outright.  -->
  476.     <fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
  477.  
  478.     <!-- This point type indexes the coordinates as separate fields (subFields)
  479.      If subFieldType is defined, it references a type, and a dynamic field
  480.      definition is created matching *___<typename>.  Alternately, if
  481.      subFieldSuffix is defined, that is used to create the subFields.
  482.      Example: if subFieldType="double", then the coordinates would be
  483.        indexed in fields myloc_0___double,myloc_1___double.
  484.      Example: if subFieldSuffix="_d" then the coordinates would be indexed
  485.        in fields myloc_0_d,myloc_1_d
  486.      The subFields are an implementation detail of the fieldType, and end
  487.      users normally should not need to know about them.
  488.     -->
  489.     <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
  490.  
  491.     <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
  492.     <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
  493.  
  494.     <!-- An alternative geospatial field type new to Solr 4.  It supports multiValued and polygon shapes.
  495.      For more information about this and other Spatial fields new to Solr 4, see:
  496.      http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
  497.    -->
  498.     <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
  499.        geo="true" distErrPct="0.025" maxDistErr="0.000009" units="degrees" />
  500.  
  501.    <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
  502.        Parameters:
  503.          defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
  504.          precisionStep:   Specifies the precisionStep for the TrieLong field used for the amount
  505.          providerClass:   Lets you plug in other exchange provider backend:
  506.                           solr.FileExchangeRateProvider is the default and takes one parameter:
  507.                             currencyConfig: name of an xml file holding exchange rates
  508.                           solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
  509.                             ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
  510.                             refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
  511.   -->
  512.     <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
  513.              
  514.  
  515.  
  516.    <!-- some examples for different languages (generally ordered by ISO code) -->
  517.  
  518.     <!-- Arabic -->
  519.     <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
  520.       <analyzer>
  521.         <tokenizer class="solr.StandardTokenizerFactory"/>
  522.         <!-- for any non-arabic -->
  523.         <filter class="solr.LowerCaseFilterFactory"/>
  524.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" enablePositionIncrements="true"/>
  525.         <!-- normalizes ﻯ to ﻱ, etc -->
  526.         <filter class="solr.ArabicNormalizationFilterFactory"/>
  527.         <filter class="solr.ArabicStemFilterFactory"/>
  528.       </analyzer>
  529.     </fieldType>
  530.  
  531.     <!-- Bulgarian -->
  532.     <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
  533.       <analyzer>
  534.         <tokenizer class="solr.StandardTokenizerFactory"/>
  535.         <filter class="solr.LowerCaseFilterFactory"/>
  536.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" enablePositionIncrements="true"/>
  537.         <filter class="solr.BulgarianStemFilterFactory"/>      
  538.       </analyzer>
  539.     </fieldType>
  540.    
  541.     <!-- Catalan -->
  542.     <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
  543.       <analyzer>
  544.         <tokenizer class="solr.StandardTokenizerFactory"/>
  545.         <!-- removes l', etc -->
  546.         <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
  547.         <filter class="solr.LowerCaseFilterFactory"/>
  548.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" enablePositionIncrements="true"/>
  549.         <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>      
  550.       </analyzer>
  551.     </fieldType>
  552.    
  553.     <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
  554.     <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
  555.       <analyzer>
  556.         <tokenizer class="solr.StandardTokenizerFactory"/>
  557.         <!-- normalize width before bigram, as e.g. half-width dakuten combine  -->
  558.         <filter class="solr.CJKWidthFilterFactory"/>
  559.         <!-- for any non-CJK -->
  560.         <filter class="solr.LowerCaseFilterFactory"/>
  561.         <filter class="solr.CJKBigramFilterFactory"/>
  562.       </analyzer>
  563.     </fieldType>
  564.  
  565.     <!-- Czech -->
  566.     <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
  567.       <analyzer>
  568.         <tokenizer class="solr.StandardTokenizerFactory"/>
  569.         <filter class="solr.LowerCaseFilterFactory"/>
  570.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" enablePositionIncrements="true"/>
  571.         <filter class="solr.CzechStemFilterFactory"/>      
  572.       </analyzer>
  573.     </fieldType>
  574.    
  575.     <!-- Danish -->
  576.     <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
  577.       <analyzer>
  578.         <tokenizer class="solr.StandardTokenizerFactory"/>
  579.         <filter class="solr.LowerCaseFilterFactory"/>
  580.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" enablePositionIncrements="true"/>
  581.         <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>      
  582.       </analyzer>
  583.     </fieldType>
  584.    
  585.     <!-- German -->
  586.     <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
  587.       <analyzer>
  588.         <tokenizer class="solr.StandardTokenizerFactory"/>
  589.         <filter class="solr.LowerCaseFilterFactory"/>
  590.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" enablePositionIncrements="true"/>
  591.         <filter class="solr.GermanNormalizationFilterFactory"/>
  592.         <filter class="solr.GermanLightStemFilterFactory"/>
  593.         <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
  594.         <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
  595.       </analyzer>
  596.     </fieldType>
  597.    
  598.     <!-- Greek -->
  599.     <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
  600.       <analyzer>
  601.         <tokenizer class="solr.StandardTokenizerFactory"/>
  602.         <!-- greek specific lowercase for sigma -->
  603.         <filter class="solr.GreekLowerCaseFilterFactory"/>
  604.         <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" enablePositionIncrements="true"/>
  605.         <filter class="solr.GreekStemFilterFactory"/>
  606.       </analyzer>
  607.     </fieldType>
  608.    
  609.     <!-- Spanish -->
  610.     <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
  611.       <analyzer>
  612.         <tokenizer class="solr.StandardTokenizerFactory"/>
  613.         <filter class="solr.LowerCaseFilterFactory"/>
  614.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" enablePositionIncrements="true"/>
  615.         <filter class="solr.SpanishLightStemFilterFactory"/>
  616.         <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
  617.       </analyzer>
  618.     </fieldType>
  619.    
  620.     <!-- Basque -->
  621.     <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
  622.       <analyzer>
  623.         <tokenizer class="solr.StandardTokenizerFactory"/>
  624.         <filter class="solr.LowerCaseFilterFactory"/>
  625.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" enablePositionIncrements="true"/>
  626.         <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
  627.       </analyzer>
  628.     </fieldType>
  629.    
  630.     <!-- Persian -->
  631.     <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
  632.       <analyzer>
  633.         <!-- for ZWNJ -->
  634.         <charFilter class="solr.PersianCharFilterFactory"/>
  635.         <tokenizer class="solr.StandardTokenizerFactory"/>
  636.         <filter class="solr.LowerCaseFilterFactory"/>
  637.         <filter class="solr.ArabicNormalizationFilterFactory"/>
  638.         <filter class="solr.PersianNormalizationFilterFactory"/>
  639.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" enablePositionIncrements="true"/>
  640.       </analyzer>
  641.     </fieldType>
  642.    
  643.     <!-- Finnish -->
  644.     <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
  645.       <analyzer>
  646.         <tokenizer class="solr.StandardTokenizerFactory"/>
  647.         <filter class="solr.LowerCaseFilterFactory"/>
  648.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" enablePositionIncrements="true"/>
  649.         <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
  650.         <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
  651.       </analyzer>
  652.     </fieldType>
  653.    
  654.     <!-- French -->
  655.     <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
  656.       <analyzer>
  657.         <tokenizer class="solr.StandardTokenizerFactory"/>
  658.         <!-- removes l', etc -->
  659.         <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
  660.         <filter class="solr.LowerCaseFilterFactory"/>
  661.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" enablePositionIncrements="true"/>
  662.         <filter class="solr.FrenchLightStemFilterFactory"/>
  663.         <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
  664.         <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
  665.       </analyzer>
  666.     </fieldType>
  667.    
  668.     <!-- Irish -->
  669.     <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
  670.       <analyzer>
  671.         <tokenizer class="solr.StandardTokenizerFactory"/>
  672.         <!-- removes d', etc -->
  673.         <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
  674.         <!-- removes n-, etc. position increments is intentionally false! -->
  675.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt" enablePositionIncrements="false"/>
  676.         <filter class="solr.IrishLowerCaseFilterFactory"/>
  677.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt" enablePositionIncrements="true"/>
  678.         <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
  679.       </analyzer>
  680.     </fieldType>
  681.    
  682.     <!-- Galician -->
  683.     <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
  684.       <analyzer>
  685.         <tokenizer class="solr.StandardTokenizerFactory"/>
  686.         <filter class="solr.LowerCaseFilterFactory"/>
  687.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" enablePositionIncrements="true"/>
  688.         <filter class="solr.GalicianStemFilterFactory"/>
  689.         <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
  690.       </analyzer>
  691.     </fieldType>
  692.    
  693.     <!-- Hindi -->
  694.     <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
  695.       <analyzer>
  696.         <tokenizer class="solr.StandardTokenizerFactory"/>
  697.         <filter class="solr.LowerCaseFilterFactory"/>
  698.         <!-- normalizes unicode representation -->
  699.         <filter class="solr.IndicNormalizationFilterFactory"/>
  700.         <!-- normalizes variation in spelling -->
  701.         <filter class="solr.HindiNormalizationFilterFactory"/>
  702.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" enablePositionIncrements="true"/>
  703.         <filter class="solr.HindiStemFilterFactory"/>
  704.       </analyzer>
  705.     </fieldType>
  706.    
  707.     <!-- Hungarian -->
  708.     <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
  709.       <analyzer>
  710.         <tokenizer class="solr.StandardTokenizerFactory"/>
  711.         <filter class="solr.LowerCaseFilterFactory"/>
  712.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" enablePositionIncrements="true"/>
  713.         <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
  714.         <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->  
  715.       </analyzer>
  716.     </fieldType>
  717.    
  718.     <!-- Armenian -->
  719.     <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
  720.       <analyzer>
  721.         <tokenizer class="solr.StandardTokenizerFactory"/>
  722.         <filter class="solr.LowerCaseFilterFactory"/>
  723.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" enablePositionIncrements="true"/>
  724.         <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
  725.       </analyzer>
  726.     </fieldType>
  727.    
  728.     <!-- Indonesian -->
  729.     <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
  730.       <analyzer>
  731.         <tokenizer class="solr.StandardTokenizerFactory"/>
  732.         <filter class="solr.LowerCaseFilterFactory"/>
  733.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" enablePositionIncrements="true"/>
  734.         <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
  735.         <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
  736.       </analyzer>
  737.     </fieldType>
  738.    
  739.     <!-- Italian -->
  740.     <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
  741.       <analyzer>
  742.         <tokenizer class="solr.StandardTokenizerFactory"/>
  743.         <!-- removes l', etc -->
  744.         <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
  745.         <filter class="solr.LowerCaseFilterFactory"/>
  746.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" enablePositionIncrements="true"/>
  747.         <filter class="solr.ItalianLightStemFilterFactory"/>
  748.         <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
  749.       </analyzer>
  750.     </fieldType>
  751.    
  752.     <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
  753.  
  754.         NOTE: If you want to optimize search for precision, use default operator AND in your query
  755.         parser config with <solrQueryParser defaultOperator="AND"/> further down in this file.  Use
  756.         OR if you would like to optimize for recall (default).
  757.    -->
  758.     <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
  759.       <analyzer>
  760.       <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
  761.  
  762.           Kuromoji has a search mode (default) that does segmentation useful for search.  A heuristic
  763.           is used to segment compounds into its parts and the compound itself is kept as synonym.
  764.  
  765.           Valid values for attribute mode are:
  766.              normal: regular segmentation
  767.              search: segmentation useful for search with synonyms compounds (default)
  768.            extended: same as search mode, but unigrams unknown words (experimental)
  769.  
  770.           For some applications it might be good to use search mode for indexing and normal mode for
  771.           queries to reduce recall and prevent parts of compounds from being matched and highlighted.
  772.           Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
  773.  
  774.           Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
  775.           model with your own entries for segmentation, part-of-speech tags and readings without a need
  776.           to specify weights.  Notice that user dictionaries have not been subject to extensive testing.
  777.  
  778.           User dictionary attributes are:
  779.                     userDictionary: user dictionary filename
  780.             userDictionaryEncoding: user dictionary encoding (default is UTF-8)
  781.  
  782.           See lang/userdict_ja.txt for a sample user dictionary file.
  783.  
  784.           Punctuation characters are discarded by default.  Use discardPunctuation="false" to keep them.
  785.  
  786.           See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
  787.        -->
  788.         <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
  789.         <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
  790.         <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
  791.         <filter class="solr.JapaneseBaseFormFilterFactory"/>
  792.         <!-- Removes tokens with certain part-of-speech tags -->
  793.         <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" enablePositionIncrements="true"/>
  794.         <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
  795.         <filter class="solr.CJKWidthFilterFactory"/>
  796.         <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
  797.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" enablePositionIncrements="true" />
  798.         <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
  799.         <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
  800.         <!-- Lower-cases romaji characters -->
  801.         <filter class="solr.LowerCaseFilterFactory"/>
  802.       </analyzer>
  803.     </fieldType>
  804.    
  805.     <!-- Latvian -->
  806.     <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
  807.       <analyzer>
  808.         <tokenizer class="solr.StandardTokenizerFactory"/>
  809.         <filter class="solr.LowerCaseFilterFactory"/>
  810.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" enablePositionIncrements="true"/>
  811.         <filter class="solr.LatvianStemFilterFactory"/>
  812.       </analyzer>
  813.     </fieldType>
  814.    
  815.     <!-- Dutch -->
  816.     <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
  817.       <analyzer>
  818.         <tokenizer class="solr.StandardTokenizerFactory"/>
  819.         <filter class="solr.LowerCaseFilterFactory"/>
  820.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" enablePositionIncrements="true"/>
  821.         <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
  822.         <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
  823.       </analyzer>
  824.     </fieldType>
  825.    
  826.     <!-- Norwegian -->
  827.     <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
  828.       <analyzer>
  829.         <tokenizer class="solr.StandardTokenizerFactory"/>
  830.         <filter class="solr.LowerCaseFilterFactory"/>
  831.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" enablePositionIncrements="true"/>
  832.         <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
  833.         <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
  834.         <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
  835.       </analyzer>
  836.     </fieldType>
  837.    
  838.     <!-- Portuguese -->
  839.     <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
  840.       <analyzer>
  841.         <tokenizer class="solr.StandardTokenizerFactory"/>
  842.         <filter class="solr.LowerCaseFilterFactory"/>
  843.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" enablePositionIncrements="true"/>
  844.         <filter class="solr.PortugueseLightStemFilterFactory"/>
  845.         <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
  846.         <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
  847.         <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
  848.       </analyzer>
  849.     </fieldType>
  850.    
  851.     <!-- Romanian -->
  852.     <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
  853.       <analyzer>
  854.         <tokenizer class="solr.StandardTokenizerFactory"/>
  855.         <filter class="solr.LowerCaseFilterFactory"/>
  856.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" enablePositionIncrements="true"/>
  857.         <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
  858.       </analyzer>
  859.     </fieldType>
  860.    
  861.     <!-- Russian -->
  862.     <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
  863.       <analyzer>
  864.         <tokenizer class="solr.StandardTokenizerFactory"/>
  865.         <filter class="solr.LowerCaseFilterFactory"/>
  866.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" enablePositionIncrements="true"/>
  867.         <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
  868.         <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
  869.       </analyzer>
  870.     </fieldType>
  871.    
  872.     <!-- Swedish -->
  873.     <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
  874.       <analyzer>
  875.         <tokenizer class="solr.StandardTokenizerFactory"/>
  876.         <filter class="solr.LowerCaseFilterFactory"/>
  877.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" enablePositionIncrements="true"/>
  878.         <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
  879.         <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
  880.       </analyzer>
  881.     </fieldType>
  882.    
  883.     <!-- Thai -->
  884.     <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
  885.       <analyzer>
  886.         <tokenizer class="solr.StandardTokenizerFactory"/>
  887.         <filter class="solr.LowerCaseFilterFactory"/>
  888.         <filter class="solr.ThaiWordFilterFactory"/>
  889.         <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" enablePositionIncrements="true"/>
  890.       </analyzer>
  891.     </fieldType>
  892.    
  893.     <!-- Turkish -->
  894.     <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
  895.       <analyzer>
  896.         <tokenizer class="solr.StandardTokenizerFactory"/>
  897.         <filter class="solr.TurkishLowerCaseFilterFactory"/>
  898.         <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" enablePositionIncrements="true"/>
  899.         <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
  900.       </analyzer>
  901.     </fieldType>
  902.  
  903.  </types>
  904.  
  905.   <!-- Similarity is the scoring routine for each document vs. a query.
  906.       A custom Similarity or SimilarityFactory may be specified here, but
  907.       the default is fine for most applications.  
  908.       For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
  909.    -->
  910.   <!--
  911.     <similarity class="com.example.solr.CustomSimilarityFactory">
  912.       <str name="paramkey">param value</str>
  913.     </similarity>
  914.    -->
  915.  
  916. </schema>
Add Comment
Please, Sign In to add comment
Public Pastes
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!