X-Git-Url: https://git.mdrn.pl/wolnelektury.git/blobdiff_plain/af4e1ed7dcda4b22eacae106ef53b1e0ba99ceb3..3839a854bbbc19fe57f83fc23076ece3ef332672:/doc/schema.xml?ds=inline diff --git a/doc/schema.xml b/doc/schema.xml index a2027810f..d3cbbe835 100644 --- a/doc/schema.xml +++ b/doc/schema.xml @@ -90,94 +90,49 @@ and back compatibility is not guaranteed. Names with both leading and trailing underscores (e.g. _version_) are reserved. --> - - <!-- <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" /> --> - <!-- <field name="sku" type="text_en_splitting_tight" indexed="true" stored="true" omitNorms="true"/> --> - <!-- <field name="name" type="text_general" indexed="true" stored="true"/> --> - <!-- <field name="manu" type="text_general" indexed="true" stored="true" omitNorms="true"/> --> - <!-- <field name="cat" type="string" indexed="true" stored="true" multiValued="true"/> --> - <!-- <field name="features" type="text_general" indexed="true" stored="true" multiValued="true"/> --> - <!-- <field name="includes" type="text_general" 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" /> --> - - <!-- <field name="store" type="location" 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. Some metadata is parsed from the documents, - but there are some which come from the client context: - "content_type": From the HTTP headers of incoming stream - "resourcename": From SolrCell request param resource.name - --> - <!-- <field name="title" type="text_general" indexed="true" stored="true" multiValued="true"/> --> - <!-- <field name="subject" type="text_general" indexed="true" stored="true"/> --> - <!-- <field name="description" type="text_general" indexed="true" stored="true"/> --> - <!-- <field name="comments" type="text_general" indexed="true" stored="true"/> --> - <!-- <field name="author" type="text_general" indexed="true" stored="true"/> --> - <!-- <field name="keywords" type="text_general" indexed="true" stored="true"/> --> - <!-- <field name="category" type="text_general" indexed="true" stored="true"/> --> - <!-- <field name="resourcename" type="text_general" indexed="true" stored="true"/> --> - <!-- <field name="url" type="text_general" 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"/> --> <field name="book_id" type="int" indexed="true" stored="true" /> <field name="parent_id" type="int" indexed="false" stored="true" /> - <field name="slug" type="text_general" stored="false" indexed="true" omitNorms="true"/> <!-- no norms --> - <field name="tags" type="lowercase" stored="false" indexed="true" multiValued="true"/> + <field name="slug" type="lowercase" stored="false" indexed="true" omitNorms="true"/> <!-- no norms --> <field name="is_book" type="boolean" stored="false" indexed="true"/> - <field name="authors" type="text_general" stored="false" indexed="true" multiValued="true" termPositions="true" termVectors="true"/> - <field name="translators" type="text_general" stored="false" indexed="true" multiValued="true" termPositions="true" termVectors="true" /> - <field name="title" type="text_pl" stored="false" indexed="true"/> - <field name="title_orig" type="text_general" stored="false" indexed="true"/> + <field name="authors" type="text_pl_nonstop" stored="false" indexed="true" multiValued="true" termPositions="true" termVectors="true"/> + <field name="authors_nonstem" type="text_ascii" stored="false" indexed="true" multiValued="true" termPositions="true" termVectors="true"/> + <field name="translators" type="text_pl_nonstop" stored="false" indexed="true" multiValued="true" termPositions="true" termVectors="true" /> + <field name="title" type="text_pl_nonstop" stored="false" indexed="true"/> + <field name="title_nonstem" type="text_ascii" stored="false" indexed="true"/> <!-- <field name="published_date" type="tdate" stored="false" indexed="true"/>--> <field name="published_date" type="string" stored="true" indexed="true"/> + <field name="epochs" type="lowercase" stored="false" indexed="false" multiValued="true" /> + <field name="kinds" type="lowercase" stored="false" indexed="false" multiValued="true" /> + <field name="genres" type="lowercase" stored="false" indexed="false" multiValued="true" /> + + <field name="metadata" type="text_pl_nonstop" stored="false" indexed="true" multiValued="true" termPositions="true" termVectors="true" /> + <field name="metadata_nonstem" type="text_pl_nonstop" stored="false" indexed="true" multiValued="true" termPositions="true" termVectors="true" /> + <field name="themes" type="lowercase" stored="true" indexed="true" termVectors="true" termPositions="true" multiValued="true" /> - <field name="themes_pl" type="text_pl" stored="true" indexed="true" termVectors="true" termPositions="true" multiValued="true" /> + <field name="themes_pl" type="text_pl_nonstop" stored="true" indexed="true" termVectors="true" termPositions="true" multiValued="true" /> + <field name="themes_pl_nonstem" type="text_ascii" stored="true" indexed="true" termVectors="true" termPositions="true" multiValued="true" /> <field name="header_index" type="int" stored="true" indexed="true"/> <field name="header_span" type="int" stored="true" indexed="true"/> <field name="header_type" type="lowercase" stored="true" indexed="false"/> <field name="text" type="text_pl" stored="false" indexed="true" termVectors="true" termPositions="true" /> + <field name="text_nonstem" type="text_pl_nonstem" stored="false" indexed="true" termVectors="true" termPositions="true" /> <field name="snippets_position" type="int" stored="true" indexed="false"/> <field name="snippets_length" type="int" stored="true" indexed="false"/> <field name="snippets_revision" type="int" stored="true" indexed="false"/> <field name="fragment_anchor" type="string" stored="true" indexed="false"/> + <field name="picture_id" type="int" indexed="true" stored="true" /> + <field name="area_id" type="int" stored="true" indexed="false"/> + <field name="tag_id" type="int" stored="true" indexed="true"/> <field name="tag_name" type="lowercase" stored="true" indexed="true" /> - <field name="tag_name_pl" type="text_pl" stored="false" indexed="true" multiValued="true"/> + <field name="tag_name_pl" type="text_pl_nonstop" stored="false" indexed="true" multiValued="true"/> <field name="tag_category" type="string" stored="true" indexed="true" /> <field name="is_pdcounter" type="boolean" stored="true" indexed="true" /> - <!-- Main body of document extracted by SolrCell. - NOTE: This field is not indexed by default, since it is also copied to "text" - using copyField below. This is to save space. Use this field for returning and - highlighting document content. Use the "text" field to search the content. --> - <!-- <field name="content" type="text_general" indexed="false" 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_general" 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_general_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"/> --> - <field name="_version_" type="long" indexed="true" stored="true"/> <!-- Uncommenting the following will create a "timestamp" field using @@ -187,50 +142,6 @@ <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/> --> - <!-- Dynamic field definitions allow using convention over configuration - for fields via the specification of patterns to match field names. - EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i) - RESTRICTION: the glob-like pattern in the name attribute must have - a "*" only at the start or the end. --> - - <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="*_pi" type="pint" 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 @@ -245,21 +156,6 @@ --> <uniqueKey>uid</uniqueKey> - <!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when - parsing a query string that isn't explicit about the field. Machine (non-user) - generated queries are best made explicit, or they can use the "df" request parameter - which takes precedence over this. - Note: Un-commenting defaultSearchField will be insufficient if your request handler - in solrconfig.xml defines "df", which takes precedence. That would need to be removed. - <defaultSearchField>text</defaultSearchField> --> - - <!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers - when parsing a query string to determine if a clause of the query should be marked as - required or optional, assuming the clause isn't already marked by some operator. - The default is OR, which is generally assumed so it is not a good idea to change it - globally here. The "q.op" request parameter takes precedence over this. - <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. --> @@ -267,40 +163,21 @@ <copyField source="themes" dest="themes_pl"/> <copyField source="tag_name" dest="tag_name_pl"/> -<!-- - <copyField source="cat" dest="text"/> - <copyField source="name" dest="text"/> - <copyField source="manu" dest="text"/> - <copyField source="features" dest="text"/> - <copyField source="includes" dest="text"/> - <copyField source="manu" dest="manu_exact"/> ---> - <!-- Copy the price into a currency enabled field (default USD) --> -<!-- <copyField source="price" dest="price_c"/>--> + <copyField source="translators" dest="metadata"/> + <copyField source="epochs" dest="metadata"/> + <copyField source="kinds" dest="metadata"/> + <copyField source="genres" dest="metadata"/> - <!-- Text fields from SolrCell to search by default in our catch-all field --> -<!-- <copyField source="title" dest="text"/> - <copyField source="author" dest="text"/> - <copyField source="description" dest="text"/> - <copyField source="keywords" dest="text"/> - <copyField source="content" dest="text"/> - <copyField source="content_type" dest="text"/> - <copyField source="resourcename" dest="text"/> - <copyField source="url" dest="text"/>--> + <copyField source="translators" dest="metadata_nonstem"/> + <copyField source="epochs" dest="metadata_nonstem"/> + <copyField source="kinds" dest="metadata_nonstem"/> + <copyField source="genres" dest="metadata_nonstem"/> - <!-- Create a string version of author for faceting --> -<!-- <copyField source="author" dest="author_s"/>--> - - <!-- Above, multiple source fields are copied to the [text] field. - Another way to map multiple source fields to the same - destination field is to use the dynamic field syntax. - copyField also supports a maxChars to copy setting. --> - - <!-- <copyField source="*_t" dest="text" maxChars="3000"/> --> + <copyField source="authors" dest="authors_nonstem"/> + <copyField source="title" dest="title_nonstem"/> + <copyField source="themes" dest="themes_pl_nonstem"/> + <copyField source="text" dest="text_nonstem"/> - <!-- copy name to alphaNameSort, a field designed for sorting by name --> - <!-- <copyField source="name" dest="alphaNameSort"/> --> - <types> <!-- field type definitions. The "name" attribute is just a label to be used by field definitions. The "class" @@ -319,8 +196,8 @@ <!-- 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. + 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). @@ -357,7 +234,7 @@ <!-- 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 + 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. @@ -386,21 +263,6 @@ <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings --> <fieldtype name="binary" class="solr.BinaryField"/> - <!-- - 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) - --> - <fieldType name="pint" class="solr.IntField"/> - <fieldType name="plong" class="solr.LongField"/> - <fieldType name="pfloat" class="solr.FloatField"/> - <fieldType name="pdouble" class="solr.DoubleField"/> - <fieldType name="pdate" class="solr.DateField" sortMissingLast="true"/> - <!-- 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 @@ -414,26 +276,6 @@ --> <fieldType name="random" class="solr.RandomSortField" indexed="true" /> - <!-- 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 class that has a - default constructor via the class attribute on the analyzer element. - Example: - <fieldType name="text_greek" class="solr.TextField"> - <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/> - </fieldType> - --> - <fieldType name="uuid" class="solr.UUIDField" indexed="true" /> @@ -444,153 +286,6 @@ </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" class="solr.TextField" positionIncrementGap="100"> - <analyzer type="index"> - <tokenizer class="solr.StandardTokenizerFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> - <!-- in this example, we will only use synonyms at query time - <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/> - --> - <filter class="solr.LowerCaseFilterFactory"/> - </analyzer> - <analyzer type="query"> - <tokenizer class="solr.StandardTokenizerFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> - <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> - <filter class="solr.LowerCaseFilterFactory"/> - </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" class="solr.TextField" positionIncrementGap="100"> - <analyzer type="index"> - <tokenizer class="solr.StandardTokenizerFactory"/> - <!-- 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="lang/stopwords_en.txt" - enablePositionIncrements="true" - /> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.EnglishPossessiveFilterFactory"/> - <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> - <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: - <filter class="solr.EnglishMinimalStemFilterFactory"/> - --> - <filter class="solr.PorterStemFilterFactory"/> - </analyzer> - <analyzer type="query"> - <tokenizer class="solr.StandardTokenizerFactory"/> - <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> - <filter class="solr.StopFilterFactory" - ignoreCase="true" - words="lang/stopwords_en.txt" - enablePositionIncrements="true" - /> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.EnglishPossessiveFilterFactory"/> - <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> - <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: - <filter class="solr.EnglishMinimalStemFilterFactory"/> - --> - <filter class="solr.PorterStemFilterFactory"/> - </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" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true"> - <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="lang/stopwords_en.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.KeywordMarkerFilterFactory" protected="protwords.txt"/> - <filter class="solr.PorterStemFilterFactory"/> - </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="lang/stopwords_en.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.KeywordMarkerFilterFactory" protected="protwords.txt"/> - <filter class="solr.PorterStemFilterFactory"/> - </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="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true"> - <analyzer> - <tokenizer class="solr.WhitespaceTokenizerFactory"/> - <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/> - <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> - <filter class="solr.EnglishMinimalStemFilterFactory"/> - <!-- 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> - - <!-- Just like text_general except it reverses the characters of - each token, to enable more efficient leading wildcard queries. --> - <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100"> - <analyzer type="index"> - <tokenizer class="solr.StandardTokenizerFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" /> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true" - maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/> - </analyzer> - <analyzer type="query"> - <tokenizer class="solr.StandardTokenizerFactory"/> - <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.LowerCaseFilterFactory"/> - </analyzer> - </fieldType> - <!-- charFilter + WhitespaceTokenizer --> <!-- <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" > @@ -601,64 +296,6 @@ </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" 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" /> - <!-- 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://java.sun.com/j2se/1.6.0/docs/api/java/util/regex/package-summary.html - --> - <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> @@ -667,473 +304,67 @@ </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" class="solr.TextField"> - <analyzer type="index"> - <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" /> - </analyzer> - <analyzer type="query"> - <tokenizer class="solr.KeywordTokenizerFactory" /> - </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" class="solr.TextField"> - <analyzer type="index"> - <tokenizer class="solr.KeywordTokenizerFactory" /> - </analyzer> - <analyzer type="query"> - <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" /> - </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" /> - <!-- 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>. Alternately, if - 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" class="solr.PointType" dimension="2" subFieldSuffix="_d"/> - - <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. --> - <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/> - - <!-- - A Geohash is a compact representation of a latitude longitude pair in a single field. - See http://wiki.apache.org/solr/SpatialSearch - --> - <fieldtype name="geohash" class="solr.GeoHashField"/> - - <!-- 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 exhange 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" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" /> - nie dziala --> - - - - <!-- some examples for different languages (generally ordered by ISO code) --> - - <!-- Arabic --> - <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100"> - <analyzer> - <tokenizer class="solr.StandardTokenizerFactory"/> - <!-- for any non-arabic --> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" enablePositionIncrements="true"/> - <!-- normalizes ﻯ to ï»±, etc --> - <filter class="solr.ArabicNormalizationFilterFactory"/> - <filter class="solr.ArabicStemFilterFactory"/> - </analyzer> - </fieldType> - - <!-- Bulgarian --> - <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100"> - <analyzer> - <tokenizer class="solr.StandardTokenizerFactory"/> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" enablePositionIncrements="true"/> - <filter class="solr.BulgarianStemFilterFactory"/> - </analyzer> - </fieldType> - - <!-- Catalan --> - <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100"> - <analyzer> + <!-- Polish --> + <fieldType name="text_pl" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true"> + <analyzer type="index"> <tokenizer class="solr.StandardTokenizerFactory"/> - <!-- removes l', etc --> - <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/> <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" enablePositionIncrements="true"/> - <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pl.txt" format="snowball"/> + <filter class="solr.MorfologikFilterFactory" dictionary="morfologik/stemming/polish/polish.dict" /> + <filter class="solr.ASCIIFoldingFilterFactory" preserveOriginal="true" /> </analyzer> - </fieldType> - - <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) --> - <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100"> - <analyzer> + <analyzer type="query"> <tokenizer class="solr.StandardTokenizerFactory"/> - <!-- normalize width before bigram, as e.g. half-width dakuten combine --> - <filter class="solr.CJKWidthFilterFactory"/> - <!-- for any non-CJK --> <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.CJKBigramFilterFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pl.txt" format="snowball"/> + <filter class="solr.MorfologikFilterFactory" dictionary="morfologik/stemming/polish/polish.dict" /> </analyzer> </fieldType> - <!-- Czech --> - <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100"> - <analyzer> - <tokenizer class="solr.StandardTokenizerFactory"/> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" enablePositionIncrements="true"/> - <filter class="solr.CzechStemFilterFactory"/> - </analyzer> - </fieldType> - - <!-- Danish --> - <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100"> - <analyzer> - <tokenizer class="solr.StandardTokenizerFactory"/> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" enablePositionIncrements="true"/> - <filter class="solr.SnowballPorterFilterFactory" language="Danish"/> - </analyzer> - </fieldType> - - <!-- German --> - <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100"> - <analyzer> - <tokenizer class="solr.StandardTokenizerFactory"/> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" enablePositionIncrements="true"/> - <filter class="solr.GermanNormalizationFilterFactory"/> - <filter class="solr.GermanLightStemFilterFactory"/> - <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> --> - <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> --> - </analyzer> - </fieldType> - - <!-- Greek --> - <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100"> - <analyzer> - <tokenizer class="solr.StandardTokenizerFactory"/> - <!-- greek specific lowercase for sigma --> - <filter class="solr.GreekLowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" enablePositionIncrements="true"/> - <filter class="solr.GreekStemFilterFactory"/> - </analyzer> - </fieldType> - - <!-- Spanish --> - <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100"> - <analyzer> - <tokenizer class="solr.StandardTokenizerFactory"/> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" enablePositionIncrements="true"/> - <filter class="solr.SpanishLightStemFilterFactory"/> - <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> --> - </analyzer> - </fieldType> - - <!-- Basque --> - <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100"> - <analyzer> - <tokenizer class="solr.StandardTokenizerFactory"/> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" enablePositionIncrements="true"/> - <filter class="solr.SnowballPorterFilterFactory" language="Basque"/> - </analyzer> - </fieldType> - - <!-- Persian --> - <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100"> - <analyzer> - <!-- for ZWNJ --> - <charFilter class="solr.PersianCharFilterFactory"/> - <tokenizer class="solr.StandardTokenizerFactory"/> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.ArabicNormalizationFilterFactory"/> - <filter class="solr.PersianNormalizationFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" enablePositionIncrements="true"/> - </analyzer> - </fieldType> - - <!-- Finnish --> - <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100"> - <analyzer> - <tokenizer class="solr.StandardTokenizerFactory"/> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" enablePositionIncrements="true"/> - <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/> - <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> --> - </analyzer> - </fieldType> - - <!-- French --> - <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100"> - <analyzer> - <tokenizer class="solr.StandardTokenizerFactory"/> - <!-- removes l', etc --> - <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" enablePositionIncrements="true"/> - <filter class="solr.FrenchLightStemFilterFactory"/> - <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> --> - <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> --> - </analyzer> - </fieldType> - - <!-- Irish --> - <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100"> - <analyzer> - <tokenizer class="solr.StandardTokenizerFactory"/> - <!-- removes d', etc --> - <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/> - <!-- removes n-, etc. position increments is intentionally false! --> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt" enablePositionIncrements="false"/> - <filter class="solr.IrishLowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt" enablePositionIncrements="true"/> - <filter class="solr.SnowballPorterFilterFactory" language="Irish"/> - </analyzer> - </fieldType> - - <!-- Galician --> - <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100"> - <analyzer> - <tokenizer class="solr.StandardTokenizerFactory"/> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" enablePositionIncrements="true"/> - <filter class="solr.GalicianStemFilterFactory"/> - <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> --> - </analyzer> - </fieldType> - - <!-- Hindi --> - <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100"> - <analyzer> - <tokenizer class="solr.StandardTokenizerFactory"/> - <filter class="solr.LowerCaseFilterFactory"/> - <!-- normalizes unicode representation --> - <filter class="solr.IndicNormalizationFilterFactory"/> - <!-- normalizes variation in spelling --> - <filter class="solr.HindiNormalizationFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" enablePositionIncrements="true"/> - <filter class="solr.HindiStemFilterFactory"/> - </analyzer> - </fieldType> - - <!-- Hungarian --> - <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100"> - <analyzer> - <tokenizer class="solr.StandardTokenizerFactory"/> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" enablePositionIncrements="true"/> - <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/> - <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> --> - </analyzer> - </fieldType> - - <!-- Armenian --> - <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100"> - <analyzer> - <tokenizer class="solr.StandardTokenizerFactory"/> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" enablePositionIncrements="true"/> - <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/> - </analyzer> - </fieldType> - - <!-- Indonesian --> - <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100"> - <analyzer> + <fieldType name="text_pl_nonstem" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true"> + <analyzer type="index"> <tokenizer class="solr.StandardTokenizerFactory"/> <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" enablePositionIncrements="true"/> - <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false --> - <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pl.txt" format="snowball"/> + <filter class="solr.ASCIIFoldingFilterFactory" preserveOriginal="true" /> </analyzer> - </fieldType> - - <!-- Italian --> - <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100"> - <analyzer> + <analyzer type="query"> <tokenizer class="solr.StandardTokenizerFactory"/> - <!-- removes l', etc --> - <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/> <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" enablePositionIncrements="true"/> - <filter class="solr.ItalianLightStemFilterFactory"/> - <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> --> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pl.txt" format="snowball"/> </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" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false"> - <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 class="solr.JapaneseTokenizerFactory" mode="search"/> - <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>--> - <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (è¾æ¸å½¢) --> - <filter class="solr.JapaneseBaseFormFilterFactory"/> - <!-- Removes tokens with certain part-of-speech tags --> - <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" enablePositionIncrements="true"/> - <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) --> - <filter class="solr.CJKWidthFilterFactory"/> - <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking --> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" enablePositionIncrements="true" /> - <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) --> - <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/> - <!-- Lower-cases romaji characters --> - <filter class="solr.LowerCaseFilterFactory"/> - </analyzer> - </fieldType> - - <!-- Latvian --> - <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100"> - <analyzer> - <tokenizer class="solr.StandardTokenizerFactory"/> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" enablePositionIncrements="true"/> - <filter class="solr.LatvianStemFilterFactory"/> - </analyzer> - </fieldType> - - <!-- Dutch --> - <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100"> - <analyzer> + <fieldType name="text_pl_nonstop" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true"> + <analyzer type="index"> <tokenizer class="solr.StandardTokenizerFactory"/> <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" enablePositionIncrements="true"/> - <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/> - <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/> + <filter class="solr.MorfologikFilterFactory" dictionary="morfologik/stemming/polish/polish.dict" /> + <filter class="solr.ASCIIFoldingFilterFactory" preserveOriginal="true" /> </analyzer> - </fieldType> - - <!-- Norwegian --> - <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100"> - <analyzer> + <analyzer type="query"> <tokenizer class="solr.StandardTokenizerFactory"/> <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" enablePositionIncrements="true"/> - <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/> - <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> --> - <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> --> + <filter class="solr.MorfologikFilterFactory" dictionary="morfologik/stemming/polish/polish.dict" /> </analyzer> </fieldType> - <!-- Polish --> - <fieldType name="text_pl" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true"> - <analyzer> - <tokenizer class="solr.StandardTokenizerFactory"/> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pl.txt" format="snowball" enablePositionIncrements="true"/> - <filter class="solr.MorfologikFilterFactory" dictionary="MORFOLOGIK" /> - <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> --> - <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> --> - <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> --> - </analyzer> - </fieldType> - - - <!-- Portuguese --> - <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100"> - <analyzer> - <tokenizer class="solr.StandardTokenizerFactory"/> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" enablePositionIncrements="true"/> - <filter class="solr.PortugueseLightStemFilterFactory"/> - <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> --> - <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> --> - <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> --> - </analyzer> - </fieldType> - - <!-- Romanian --> - <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100"> - <analyzer> - <tokenizer class="solr.StandardTokenizerFactory"/> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" enablePositionIncrements="true"/> - <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/> - </analyzer> - </fieldType> - - <!-- Russian --> - <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100"> - <analyzer> - <tokenizer class="solr.StandardTokenizerFactory"/> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" enablePositionIncrements="true"/> - <filter class="solr.SnowballPorterFilterFactory" language="Russian"/> - <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> --> - </analyzer> - </fieldType> - - <!-- Swedish --> - <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100"> - <analyzer> + <fieldType name="text_ascii" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true"> + <analyzer type="index"> <tokenizer class="solr.StandardTokenizerFactory"/> <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" enablePositionIncrements="true"/> - <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/> - <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> --> + <filter class="solr.ASCIIFoldingFilterFactory" preserveOriginal="true" /> </analyzer> - </fieldType> - - <!-- Thai --> - <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100"> - <analyzer> + <analyzer type="query"> <tokenizer class="solr.StandardTokenizerFactory"/> <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.ThaiWordFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" enablePositionIncrements="true"/> </analyzer> </fieldType> - - <!-- Turkish --> - <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100"> - <analyzer> - <tokenizer class="solr.StandardTokenizerFactory"/> - <filter class="solr.TurkishLowerCaseFilterFactory"/> - <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" enablePositionIncrements="true"/> - <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/> - </analyzer> - </fieldType> - +cb </types> <!-- Similarity is the scoring routine for each document vs. a query.