first import
This commit is contained in:
7
solr-conf/1.4/protwords.txt
Normal file
7
solr-conf/1.4/protwords.txt
Normal file
@@ -0,0 +1,7 @@
|
||||
#-----------------------------------------------------------------------
|
||||
# This file blocks words from being operated on by the stemmer and word delimiter.
|
||||
&
|
||||
<
|
||||
>
|
||||
'
|
||||
"
|
535
solr-conf/1.4/schema.xml
Normal file
535
solr-conf/1.4/schema.xml
Normal file
@@ -0,0 +1,535 @@
|
||||
<?xml version="1.0" encoding="UTF-8" ?>
|
||||
|
||||
<!--
|
||||
This is the Solr schema file. This file should be named "schema.xml" and
|
||||
should be in the conf directory under the solr home
|
||||
(i.e. ./solr/conf/schema.xml by default)
|
||||
or located where the classloader for the Solr webapp can find it.
|
||||
|
||||
For more information, on how to customize this file, please see
|
||||
http://wiki.apache.org/solr/SchemaXml
|
||||
-->
|
||||
|
||||
<schema name="drupal-4.0-solr-1.4" version="1.2">
|
||||
<!-- attribute "name" is the name of this schema and is only used for display purposes.
|
||||
Applications should change this to reflect the nature of the search collection.
|
||||
version="1.2" is Solr's version number for the schema syntax and semantics. It should
|
||||
not normally be changed by applications.
|
||||
1.0: multiValued attribute did not exist, all fields are multiValued by nature
|
||||
1.1: multiValued attribute introduced, false by default
|
||||
1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields.
|
||||
-->
|
||||
<types>
|
||||
<!-- field type definitions. The "name" attribute is
|
||||
just a label to be used by field definitions. The "class"
|
||||
attribute and any other attributes determine the real
|
||||
behavior of the fieldType.
|
||||
Class names starting with "solr" refer to java classes in the
|
||||
org.apache.solr.analysis package.
|
||||
-->
|
||||
|
||||
<!-- The StrField type is not analyzed, but indexed/stored verbatim.
|
||||
- StrField and TextField support an optional compressThreshold which
|
||||
limits compression (if enabled in the derived fields) to values which
|
||||
exceed a certain size (in characters).
|
||||
-->
|
||||
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
|
||||
|
||||
<!-- boolean type: "true" or "false" -->
|
||||
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
|
||||
<!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
|
||||
<fieldtype name="binary" class="solr.BinaryField"/>
|
||||
|
||||
<!-- The optional sortMissingLast and sortMissingFirst attributes are
|
||||
currently supported on types that are sorted internally as strings.
|
||||
- If sortMissingLast="true", then a sort on this field will cause documents
|
||||
without the field to come after documents with the field,
|
||||
regardless of the requested sort order (asc or desc).
|
||||
- If sortMissingFirst="true", then a sort on this field will cause documents
|
||||
without the field to come before documents with the field,
|
||||
regardless of the requested sort order.
|
||||
- If sortMissingLast="false" and sortMissingFirst="false" (the default),
|
||||
then default lucene sorting will be used which places docs without the
|
||||
field first in an ascending sort and last in a descending sort.
|
||||
-->
|
||||
|
||||
<!-- numeric field types that can be sorted, but are not optimized for range queries -->
|
||||
<fieldType name="integer" class="solr.TrieIntField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
|
||||
<fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
|
||||
<fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
|
||||
<fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
|
||||
|
||||
<!--
|
||||
Note:
|
||||
These should only be used for compatibility with existing indexes (created with older Solr versions)
|
||||
or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead.
|
||||
|
||||
Numeric field types that manipulate the value into
|
||||
a string value that isn't human-readable in its internal form,
|
||||
but with a lexicographic ordering the same as the numeric ordering,
|
||||
so that range queries work correctly.
|
||||
-->
|
||||
<fieldType name="sint" class="solr.TrieIntField" sortMissingLast="true" omitNorms="true"/>
|
||||
<fieldType name="slong" class="solr.TrieFloatField" sortMissingLast="true" omitNorms="true"/>
|
||||
<fieldType name="sfloat" class="solr.TrieLongField" sortMissingLast="true" omitNorms="true"/>
|
||||
<fieldType name="sdouble" class="solr.TrieDoubleField" sortMissingLast="true" omitNorms="true"/>
|
||||
|
||||
<!--
|
||||
Numeric field types that index each value at various levels of precision
|
||||
to accelerate range queries when the number of values between the range
|
||||
endpoints is large. See the javadoc for NumericRangeQuery for internal
|
||||
implementation details.
|
||||
|
||||
Smaller precisionStep values (specified in bits) will lead to more tokens
|
||||
indexed per value, slightly larger index size, and faster range queries.
|
||||
A precisionStep of 0 disables indexing at different precision levels.
|
||||
-->
|
||||
<fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
|
||||
<fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
|
||||
<fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
|
||||
<fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
|
||||
|
||||
<!--
|
||||
The ExternalFileField type gets values from an external file instead of the
|
||||
index. This is useful for data such as rankings that might change frequently
|
||||
and require different update frequencies than the documents they are
|
||||
associated with.
|
||||
-->
|
||||
<fieldType name="pfloat" class="solr.FloatField" omitNorms="true"/>
|
||||
<fieldType name="file" keyField="id" defVal="1" stored="false" indexed="false" class="solr.ExternalFileField" valType="pfloat"/>
|
||||
|
||||
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
|
||||
is a more restricted form of the canonical representation of dateTime
|
||||
http://www.w3.org/TR/xmlschema-2/#dateTime
|
||||
The trailing "Z" designates UTC time and is mandatory.
|
||||
Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
|
||||
All other components are mandatory.
|
||||
|
||||
Expressions can also be used to denote calculations that should be
|
||||
performed relative to "NOW" to determine the value, ie...
|
||||
|
||||
NOW/HOUR
|
||||
... Round to the start of the current hour
|
||||
NOW-1DAY
|
||||
... Exactly 1 day prior to now
|
||||
NOW/DAY+6MONTHS+3DAYS
|
||||
... 6 months and 3 days in the future from the start of
|
||||
the current day
|
||||
|
||||
Consult the DateField javadocs for more information.
|
||||
-->
|
||||
<fieldType name="date" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
|
||||
|
||||
<!-- A Trie based date field for faster date range queries and date faceting. -->
|
||||
<fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
|
||||
|
||||
<!-- 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
|
||||
<fieldType name="text_greek" class="solr.TextField">
|
||||
<analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
|
||||
</fieldType>
|
||||
-->
|
||||
|
||||
<!-- A text field that only splits on whitespace for exact matching of words -->
|
||||
<fieldType name="text_ws" class="solr.TextField" omitNorms="true" positionIncrementGap="100">
|
||||
<analyzer>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
|
||||
<!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
|
||||
words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
|
||||
so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
|
||||
Synonyms and stopwords are customized by external files, and stemming is enabled.
|
||||
Duplicate tokens at the same position (which may result from Stemmed Synonyms or
|
||||
WordDelim parts) are removed.
|
||||
-->
|
||||
<fieldType name="text" class="solr.TextField" positionIncrementGap="100">
|
||||
<analyzer type="index">
|
||||
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<!-- in this example, we will only use synonyms at query time
|
||||
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
||||
-->
|
||||
<!-- Case insensitive stop word removal.
|
||||
add enablePositionIncrements=true in both the index and query
|
||||
analyzers to leave a 'gap' for more accurate phrase queries.
|
||||
-->
|
||||
<filter class="solr.StopFilterFactory"
|
||||
ignoreCase="true"
|
||||
words="stopwords.txt"
|
||||
enablePositionIncrements="true"
|
||||
/>
|
||||
<filter class="solr.WordDelimiterFilterFactory"
|
||||
protected="protwords.txt"
|
||||
generateWordParts="1"
|
||||
generateNumberParts="1"
|
||||
catenateWords="1"
|
||||
catenateNumbers="1"
|
||||
catenateAll="0"
|
||||
splitOnCaseChange="1"
|
||||
preserveOriginal="1"/>
|
||||
<filter class="solr.LengthFilterFactory" min="2" max="100" />
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
||||
<filter class="solr.StopFilterFactory"
|
||||
ignoreCase="true"
|
||||
words="stopwords.txt"
|
||||
enablePositionIncrements="true"
|
||||
/>
|
||||
<filter class="solr.WordDelimiterFilterFactory"
|
||||
protected="protwords.txt"
|
||||
generateWordParts="1"
|
||||
generateNumberParts="1"
|
||||
catenateWords="0"
|
||||
catenateNumbers="0"
|
||||
catenateAll="0"
|
||||
splitOnCaseChange="1"
|
||||
preserveOriginal="1"/>
|
||||
<filter class="solr.LengthFilterFactory" min="2" max="100" />
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
|
||||
<!-- An unstemmed text field - good if one does not know the language of the field -->
|
||||
<fieldType name="text_und" class="solr.TextField" positionIncrementGap="100">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
||||
<filter class="solr.WordDelimiterFilterFactory"
|
||||
protected="protwords.txt"
|
||||
generateWordParts="1"
|
||||
generateNumberParts="1"
|
||||
catenateWords="1"
|
||||
catenateNumbers="1"
|
||||
catenateAll="0"
|
||||
splitOnCaseChange="0"/>
|
||||
<filter class="solr.LengthFilterFactory" min="2" max="100" />
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
||||
<filter class="solr.StopFilterFactory"
|
||||
ignoreCase="true"
|
||||
words="stopwords.txt"
|
||||
enablePositionIncrements="true"
|
||||
/>
|
||||
<filter class="solr.WordDelimiterFilterFactory"
|
||||
protected="protwords.txt"
|
||||
generateWordParts="1"
|
||||
generateNumberParts="1"
|
||||
catenateWords="0"
|
||||
catenateNumbers="0"
|
||||
catenateAll="0"
|
||||
splitOnCaseChange="0"/>
|
||||
<filter class="solr.LengthFilterFactory" min="2" max="100" />
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
|
||||
<!-- Edge N gram type - for example for matching against queries with results
|
||||
KeywordTokenizer leaves input string intact as a single term.
|
||||
see: http://www.lucidimagination.com/blog/2009/09/08/auto-suggest-from-popular-queries-using-edgengrams/
|
||||
-->
|
||||
<fieldType name="edge_n2_kw_text" class="solr.TextField" omitNorms="true" positionIncrementGap="100">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="25" />
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
<!-- Setup simple analysis for spell checking -->
|
||||
|
||||
<fieldType name="textSpell" class="solr.TextField" positionIncrementGap="100">
|
||||
<analyzer>
|
||||
<tokenizer class="solr.StandardTokenizerFactory" />
|
||||
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
|
||||
<filter class="solr.LengthFilterFactory" min="4" max="20" />
|
||||
<filter class="solr.LowerCaseFilterFactory" />
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory" />
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
|
||||
<!-- This is an example of using the KeywordTokenizer along
|
||||
With various TokenFilterFactories to produce a sortable field
|
||||
that does not include some properties of the source text
|
||||
-->
|
||||
<fieldType name="sortString" 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 refrences to portions of the orriginal
|
||||
string matched by the pattern.
|
||||
|
||||
See the Java Regular Expression documentation for more
|
||||
infomation on pattern and replacement string syntax.
|
||||
|
||||
http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
|
||||
|
||||
<filter class="solr.PatternReplaceFilterFactory"
|
||||
pattern="(^\p{Punct}+)" replacement="" replace="all"
|
||||
/>
|
||||
-->
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
|
||||
<!-- A random sort type -->
|
||||
<fieldType name="rand" class="solr.RandomSortField" indexed="true" />
|
||||
|
||||
<!-- 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" class="solr.StrField" />
|
||||
|
||||
<!-- Following is a dynamic way to include other types, added by other contrib modules -->
|
||||
<xi:include href="schema_i18n_types.xml" xmlns:xi="http://www.w3.org/2001/XInclude">
|
||||
<xi:fallback></xi:fallback>
|
||||
</xi:include>
|
||||
|
||||
</types>
|
||||
|
||||
|
||||
<fields>
|
||||
<!-- Valid attributes for fields:
|
||||
name: mandatory - the name for the field
|
||||
type: mandatory - the name of a previously defined type from the <types> section
|
||||
indexed: true if this field should be indexed (searchable or sortable)
|
||||
stored: true if this field should be retrievable
|
||||
compressed: [false] if this field should be stored using gzip compression
|
||||
(this will only apply if the field type is compressable; among
|
||||
the standard field types, only TextField and StrField are)
|
||||
multiValued: true if this field may contain multiple values per document
|
||||
omitNorms: (expert) set to true to omit the norms associated with
|
||||
this field (this disables length normalization and index-time
|
||||
boosting for the field, and saves some memory). Only full-text
|
||||
fields or fields that need an index-time boost need norms.
|
||||
-->
|
||||
|
||||
<!-- The document id is usually derived from a site-spcific key (hash) and the
|
||||
entity type and ID like:
|
||||
Search Api :
|
||||
The format used is $document->id = $index_id . '-' . $item_id
|
||||
Apache Solr Search Integration
|
||||
The format used is $document->id = $site_hash . '/' . $entity_type . '/' . $entity->id;
|
||||
-->
|
||||
<field name="id" type="string" indexed="true" stored="true" required="true" />
|
||||
|
||||
<!-- Search Api specific fields -->
|
||||
<!-- item_id contains the entity ID, e.g. a node's nid. -->
|
||||
<field name="item_id" type="string" indexed="true" stored="true" />
|
||||
<!-- index_id is the machine name of the search index this entry belongs to. -->
|
||||
<field name="index_id" type="string" indexed="true" stored="true" />
|
||||
<!-- Since sorting by ID is explicitly allowed, store item_id also in a sortable way. -->
|
||||
<copyField source="item_id" dest="sort_search_api_id" />
|
||||
|
||||
<!-- Apache Solr Search Integration specific fields -->
|
||||
<!-- entity_id is the numeric object ID, e.g. Node ID, File ID -->
|
||||
<field name="entity_id" type="long" indexed="true" stored="true" />
|
||||
<!-- entity_type is 'node', 'file', 'user', or some other Drupal object type -->
|
||||
<field name="entity_type" type="string" indexed="true" stored="true" />
|
||||
<!-- bundle is a node type, or as appropriate for other entity types -->
|
||||
<field name="bundle" type="string" indexed="true" stored="true"/>
|
||||
<field name="bundle_name" type="string" indexed="true" stored="true"/>
|
||||
<field name="site" type="string" indexed="true" stored="true"/>
|
||||
<field name="hash" type="string" indexed="true" stored="true"/>
|
||||
<field name="url" type="string" indexed="true" stored="true"/>
|
||||
<!-- label is the default field for a human-readable string for this entity (e.g. the title of a node) -->
|
||||
<field name="label" type="text" indexed="true" stored="true" termVectors="true" omitNorms="true"/>
|
||||
<!-- The string version of the title is used for sorting -->
|
||||
<copyField source="label" dest="sort_label"/>
|
||||
|
||||
<!-- content is the default field for full text search - dump crap here -->
|
||||
<field name="content" type="text" indexed="true" stored="true" termVectors="true"/>
|
||||
<field name="teaser" type="text" indexed="false" stored="true"/>
|
||||
<field name="path" type="string" indexed="true" stored="true"/>
|
||||
<field name="path_alias" type="text" indexed="true" stored="true" termVectors="true" omitNorms="true"/>
|
||||
|
||||
<!-- These are the fields that correspond to a Drupal node. The beauty of having
|
||||
Lucene store title, body, type, etc., is that we retrieve them with the search
|
||||
result set and don't need to go to the database with a node_load. -->
|
||||
<field name="tid" type="long" indexed="true" stored="true" multiValued="true"/>
|
||||
<field name="taxonomy_names" type="text" indexed="true" stored="false" termVectors="true" multiValued="true" omitNorms="true"/>
|
||||
<!-- Copy terms to a single field that contains all taxonomy term names -->
|
||||
<copyField source="tm_vid_*" dest="taxonomy_names"/>
|
||||
|
||||
<!-- Here, default is used to create a "timestamp" field indicating
|
||||
when each document was indexed.-->
|
||||
<field name="timestamp" type="tdate" indexed="true" stored="true" default="NOW" multiValued="false"/>
|
||||
|
||||
<!-- This field is used to build the spellchecker index -->
|
||||
<field name="spell" type="textSpell" indexed="true" stored="true" multiValued="true"/>
|
||||
|
||||
<!-- copyField commands copy one field to another at the time a document
|
||||
is added to the index. It's used either to index the same field differently,
|
||||
or to add multiple fields to the same field for easier/faster searching. -->
|
||||
<copyField source="label" dest="spell"/>
|
||||
<copyField source="content" dest="spell"/>
|
||||
|
||||
<copyField source="ts_*" dest="spell"/>
|
||||
<copyField source="tm_*" dest="spell"/>
|
||||
|
||||
<!-- Dynamic field definitions. If a field name is not found, dynamicFields
|
||||
will be used if the name matches any of the patterns.
|
||||
RESTRICTION: the glob-like pattern in the name attribute must have
|
||||
a "*" only at the start or the end.
|
||||
EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
|
||||
Longer patterns will be matched first. if equal size patterns
|
||||
both match, the first appearing in the schema will be used. -->
|
||||
|
||||
<!-- A set of fields to contain text extracted from HTML tag contents which we
|
||||
can boost at query time. -->
|
||||
<dynamicField name="tags_*" type="text" indexed="true" stored="false" omitNorms="true"/>
|
||||
|
||||
<!-- For 2 and 3 letter prefix dynamic fields, the 1st letter indicates the data type and
|
||||
the last letter is 's' for single valued, 'm' for multi-valued -->
|
||||
|
||||
<!-- We use long for integer since 64 bit ints are now common in PHP. -->
|
||||
<dynamicField name="is_*" type="long" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="im_*" type="long" indexed="true" stored="true" multiValued="true"/>
|
||||
<!-- List of floats can be saved in a regular float field -->
|
||||
<dynamicField name="fs_*" type="float" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="fm_*" type="float" indexed="true" stored="true" multiValued="true"/>
|
||||
<!-- List of doubles can be saved in a regular double field -->
|
||||
<dynamicField name="ps_*" type="double" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="pm_*" type="double" indexed="true" stored="true" multiValued="true"/>
|
||||
<!-- List of booleans can be saved in a regular boolean field -->
|
||||
<dynamicField name="bm_*" type="boolean" indexed="true" stored="true" multiValued="true"/>
|
||||
<dynamicField name="bs_*" type="boolean" indexed="true" stored="true" multiValued="false"/>
|
||||
<!-- Regular text (without processing) can be stored in a string field-->
|
||||
<dynamicField name="ss_*" type="string" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="sm_*" type="string" indexed="true" stored="true" multiValued="true"/>
|
||||
<!-- Normal text fields are for full text - the relevance of a match depends on the length of the text -->
|
||||
<dynamicField name="ts_*" type="text" indexed="true" stored="true" multiValued="false" termVectors="true"/>
|
||||
<dynamicField name="tm_*" type="text" indexed="true" stored="true" multiValued="true" termVectors="true"/>
|
||||
<!-- Unstemmed text fields for full text - the relevance of a match depends on the length of the text -->
|
||||
<dynamicField name="tus_*" type="text_und" indexed="true" stored="true" multiValued="false" termVectors="true"/>
|
||||
<dynamicField name="tum_*" type="text_und" indexed="true" stored="true" multiValued="true" termVectors="true"/>
|
||||
<!-- These text fields omit norms - useful for extracted text like taxonomy_names -->
|
||||
<dynamicField name="tos_*" type="text" indexed="true" stored="true" multiValued="false" termVectors="true" omitNorms="true"/>
|
||||
<dynamicField name="tom_*" type="text" indexed="true" stored="true" multiValued="true" termVectors="true" omitNorms="true"/>
|
||||
<!-- Special-purpose text fields -->
|
||||
<dynamicField name="tes_*" type="edge_n2_kw_text" indexed="true" stored="true" multiValued="false" omitTermFreqAndPositions="true" />
|
||||
<dynamicField name="tem_*" type="edge_n2_kw_text" indexed="true" stored="true" multiValued="true" omitTermFreqAndPositions="true" />
|
||||
<dynamicField name="tws_*" type="text_ws" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="twm_*" type="text_ws" indexed="true" stored="true" multiValued="true"/>
|
||||
|
||||
<!-- trie dates are preferred, so give them the 2 letter prefix -->
|
||||
<dynamicField name="ds_*" type="tdate" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="dm_*" type="tdate" indexed="true" stored="true" multiValued="true"/>
|
||||
<dynamicField name="its_*" type="tlong" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="itm_*" type="tlong" indexed="true" stored="true" multiValued="true"/>
|
||||
<dynamicField name="fts_*" type="tfloat" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="ftm_*" type="tfloat" indexed="true" stored="true" multiValued="true"/>
|
||||
<dynamicField name="pts_*" type="tdouble" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="ptm_*" type="tdouble" indexed="true" stored="true" multiValued="true"/>
|
||||
<!-- Binary fields can be populated using base64 encoded data. Useful e.g. for embedding
|
||||
a small image in a search result using the data URI scheme -->
|
||||
<dynamicField name="xs_*" type="binary" indexed="false" stored="true" multiValued="false"/>
|
||||
<dynamicField name="xm_*" type="binary" indexed="false" stored="true" multiValued="true"/>
|
||||
<!-- In rare cases a date rather than tdate is needed for sortMissingLast -->
|
||||
<dynamicField name="dds_*" type="date" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="ddm_*" type="date" indexed="true" stored="true" multiValued="true"/>
|
||||
<!-- Sortable fields, good for sortMissingLast support &
|
||||
We use long for integer since 64 bit ints are now common in PHP. -->
|
||||
<dynamicField name="iss_*" type="slong" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="ism_*" type="slong" indexed="true" stored="true" multiValued="true"/>
|
||||
<!-- In rare cases a sfloat rather than tfloat is needed for sortMissingLast -->
|
||||
<dynamicField name="fss_*" type="sfloat" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="fsm_*" type="sfloat" indexed="true" stored="true" multiValued="true"/>
|
||||
<dynamicField name="pss_*" type="sdouble" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="psm_*" type="sdouble" indexed="true" stored="true" multiValued="true"/>
|
||||
<!-- In case a 32 bit int is really needed, we provide these fields. 'h' is mnemonic for 'half word', i.e. 32 bit on 64 arch -->
|
||||
<dynamicField name="hs_*" type="integer" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="hm_*" type="integer" indexed="true" stored="true" multiValued="true"/>
|
||||
<dynamicField name="hss_*" type="sint" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="hsm_*" type="sint" indexed="true" stored="true" multiValued="true"/>
|
||||
<dynamicField name="hts_*" type="tint" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="htm_*" type="tint" indexed="true" stored="true" multiValued="true"/>
|
||||
|
||||
<!-- Unindexed string fields that can be used to store values that won't be searchable -->
|
||||
<dynamicField name="zs_*" type="string" indexed="false" stored="true" multiValued="false"/>
|
||||
<dynamicField name="zm_*" type="string" indexed="false" stored="true" multiValued="true"/>
|
||||
|
||||
<!-- Begin compatibility code for added fields in Solr 3.4+
|
||||
http://wiki.apache.org/solr/SpatialSearch#geodist_-_The_distance_function -->
|
||||
<dynamicField name="points_*" type="string" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="pointm_*" type="string" indexed="true" stored="true" multiValued="true"/>
|
||||
<dynamicField name="locs_*" type="string" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="locm_*" type="string" indexed="true" stored="true" multiValued="true"/>
|
||||
<dynamicField name="geos_*" type="string" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="geom_*" type="string" indexed="true" stored="true" multiValued="true"/>
|
||||
|
||||
<!-- External file fields -->
|
||||
<dynamicField name="eff_*" type="string"/>
|
||||
<!-- End compatibility code -->
|
||||
|
||||
<!-- Sortable version of the dynamic string field -->
|
||||
<dynamicField name="sort_*" type="sortString" indexed="true" stored="false"/>
|
||||
<copyField source="ss_*" dest="sort_*"/>
|
||||
<!-- A random sort field -->
|
||||
<dynamicField name="random_*" type="rand" indexed="true" stored="true"/>
|
||||
<!-- This field is used to store access information (e.g. node access grants), as opposed to field data -->
|
||||
<dynamicField name="access_*" type="integer" indexed="true" stored="false" multiValued="true"/>
|
||||
|
||||
<!-- Following is a dynamic way to include other fields, added by other contrib modules -->
|
||||
<xi:include href="schema_i18n_fields.xml" xmlns:xi="http://www.w3.org/2001/XInclude">
|
||||
<xi:fallback></xi:fallback>
|
||||
</xi:include>
|
||||
|
||||
<!-- The following causes solr to ignore any fields that don't already match an existing
|
||||
field name or dynamic field, rather than reporting them as an error.
|
||||
Alternately, change the type="ignored" to some other type e.g. "text" if you want
|
||||
unknown fields indexed and/or stored by default -->
|
||||
<dynamicField name="*" type="ignored" multiValued="true" />
|
||||
|
||||
</fields>
|
||||
|
||||
<!-- Field to use to determine and enforce document uniqueness.
|
||||
Unless this field is marked with required="false", it will be a required field
|
||||
-->
|
||||
<uniqueKey>id</uniqueKey>
|
||||
|
||||
<!-- field for the QueryParser to use when an explicit fieldname is absent -->
|
||||
<defaultSearchField>content</defaultSearchField>
|
||||
|
||||
<!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
|
||||
<solrQueryParser defaultOperator="AND"/>
|
||||
|
||||
</schema>
|
1637
solr-conf/1.4/solrconfig.xml
Normal file
1637
solr-conf/1.4/solrconfig.xml
Normal file
File diff suppressed because it is too large
Load Diff
8
solr-conf/1.4/solrcore.properties
Normal file
8
solr-conf/1.4/solrcore.properties
Normal file
@@ -0,0 +1,8 @@
|
||||
#solrcore.properties for this specific core
|
||||
enable.master=false
|
||||
enable.slave=false
|
||||
pollTime=00:00:60
|
||||
masterCoreUrl=http://localhost:8983/solr
|
||||
confFiles=schema.xml,mapping-ISOLatin1Accent.txt,protwords.txt,stopwords.txt,synonyms.txt,elevate.xml
|
||||
mlt.timeAllowed=2000
|
||||
pinkPony.timeAllowed=-1
|
7
solr-conf/3.x/protwords.txt
Normal file
7
solr-conf/3.x/protwords.txt
Normal file
@@ -0,0 +1,7 @@
|
||||
#-----------------------------------------------------------------------
|
||||
# This file blocks words from being operated on by the stemmer and word delimiter.
|
||||
&
|
||||
<
|
||||
>
|
||||
'
|
||||
"
|
548
solr-conf/3.x/schema.xml
Normal file
548
solr-conf/3.x/schema.xml
Normal file
@@ -0,0 +1,548 @@
|
||||
<?xml version="1.0" encoding="UTF-8" ?>
|
||||
|
||||
<!--
|
||||
This is the Solr schema file. This file should be named "schema.xml" and
|
||||
should be in the conf directory under the solr home
|
||||
(i.e. ./solr/conf/schema.xml by default)
|
||||
or located where the classloader for the Solr webapp can find it.
|
||||
|
||||
For more information, on how to customize this file, please see
|
||||
http://wiki.apache.org/solr/SchemaXml
|
||||
-->
|
||||
|
||||
<schema name="drupal-4.0-solr-3.x" version="1.3">
|
||||
<!-- attribute "name" is the name of this schema and is only used for display purposes.
|
||||
Applications should change this to reflect the nature of the search collection.
|
||||
version="1.2" is Solr's version number for the schema syntax and semantics. It should
|
||||
not normally be changed by applications.
|
||||
1.0: multiValued attribute did not exist, all fields are multiValued by nature
|
||||
1.1: multiValued attribute introduced, false by default
|
||||
1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields.
|
||||
1.3: removed optional field compress feature
|
||||
-->
|
||||
<types>
|
||||
<!-- field type definitions. The "name" attribute is
|
||||
just a label to be used by field definitions. The "class"
|
||||
attribute and any other attributes determine the real
|
||||
behavior of the fieldType.
|
||||
Class names starting with "solr" refer to java classes in the
|
||||
org.apache.solr.analysis package.
|
||||
-->
|
||||
|
||||
<!-- The StrField type is not analyzed, but indexed/stored verbatim.
|
||||
- StrField and TextField support an optional compressThreshold which
|
||||
limits compression (if enabled in the derived fields) to values which
|
||||
exceed a certain size (in characters).
|
||||
-->
|
||||
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
|
||||
|
||||
<!-- boolean type: "true" or "false" -->
|
||||
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
|
||||
<!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
|
||||
<fieldtype name="binary" class="solr.BinaryField"/>
|
||||
|
||||
<!-- The optional sortMissingLast and sortMissingFirst attributes are
|
||||
currently supported on types that are sorted internally as strings.
|
||||
- If sortMissingLast="true", then a sort on this field will cause documents
|
||||
without the field to come after documents with the field,
|
||||
regardless of the requested sort order (asc or desc).
|
||||
- If sortMissingFirst="true", then a sort on this field will cause documents
|
||||
without the field to come before documents with the field,
|
||||
regardless of the requested sort order.
|
||||
- If sortMissingLast="false" and sortMissingFirst="false" (the default),
|
||||
then default lucene sorting will be used which places docs without the
|
||||
field first in an ascending sort and last in a descending sort.
|
||||
-->
|
||||
|
||||
<!-- numeric field types that can be sorted, but are not optimized for range queries -->
|
||||
<fieldType name="integer" class="solr.TrieIntField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
|
||||
<fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
|
||||
<fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
|
||||
<fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
|
||||
|
||||
<!--
|
||||
Note:
|
||||
These should only be used for compatibility with existing indexes (created with older Solr versions)
|
||||
or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead.
|
||||
|
||||
Numeric field types that manipulate the value into
|
||||
a string value that isn't human-readable in its internal form,
|
||||
but with a lexicographic ordering the same as the numeric ordering,
|
||||
so that range queries work correctly.
|
||||
-->
|
||||
<fieldType name="sint" class="solr.TrieIntField" sortMissingLast="true" omitNorms="true"/>
|
||||
<fieldType name="slong" class="solr.TrieFloatField" sortMissingLast="true" omitNorms="true"/>
|
||||
<fieldType name="sfloat" class="solr.TrieLongField" sortMissingLast="true" omitNorms="true"/>
|
||||
<fieldType name="sdouble" class="solr.TrieDoubleField" sortMissingLast="true" omitNorms="true"/>
|
||||
|
||||
<!--
|
||||
Numeric field types that index each value at various levels of precision
|
||||
to accelerate range queries when the number of values between the range
|
||||
endpoints is large. See the javadoc for NumericRangeQuery for internal
|
||||
implementation details.
|
||||
|
||||
Smaller precisionStep values (specified in bits) will lead to more tokens
|
||||
indexed per value, slightly larger index size, and faster range queries.
|
||||
A precisionStep of 0 disables indexing at different precision levels.
|
||||
-->
|
||||
<fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
|
||||
<fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
|
||||
<fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
|
||||
<fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
|
||||
|
||||
<!--
|
||||
The ExternalFileField type gets values from an external file instead of the
|
||||
index. This is useful for data such as rankings that might change frequently
|
||||
and require different update frequencies than the documents they are
|
||||
associated with.
|
||||
-->
|
||||
<fieldType name="pfloat" class="solr.FloatField" omitNorms="true"/>
|
||||
<fieldType name="file" keyField="id" defVal="1" stored="false" indexed="false" class="solr.ExternalFileField" valType="pfloat"/>
|
||||
|
||||
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
|
||||
is a more restricted form of the canonical representation of dateTime
|
||||
http://www.w3.org/TR/xmlschema-2/#dateTime
|
||||
The trailing "Z" designates UTC time and is mandatory.
|
||||
Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
|
||||
All other components are mandatory.
|
||||
|
||||
Expressions can also be used to denote calculations that should be
|
||||
performed relative to "NOW" to determine the value, ie...
|
||||
|
||||
NOW/HOUR
|
||||
... Round to the start of the current hour
|
||||
NOW-1DAY
|
||||
... Exactly 1 day prior to now
|
||||
NOW/DAY+6MONTHS+3DAYS
|
||||
... 6 months and 3 days in the future from the start of
|
||||
the current day
|
||||
|
||||
Consult the DateField javadocs for more information.
|
||||
-->
|
||||
<fieldType name="date" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
|
||||
|
||||
<!-- A Trie based date field for faster date range queries and date faceting. -->
|
||||
<fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
|
||||
|
||||
<!-- 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
|
||||
<fieldType name="text_greek" class="solr.TextField">
|
||||
<analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
|
||||
</fieldType>
|
||||
-->
|
||||
|
||||
<!-- A text field that only splits on whitespace for exact matching of words -->
|
||||
<fieldType name="text_ws" class="solr.TextField" omitNorms="true" positionIncrementGap="100">
|
||||
<analyzer>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
|
||||
<!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
|
||||
words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
|
||||
so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
|
||||
Synonyms and stopwords are customized by external files, and stemming is enabled.
|
||||
Duplicate tokens at the same position (which may result from Stemmed Synonyms or
|
||||
WordDelim parts) are removed.
|
||||
-->
|
||||
<fieldType name="text" class="solr.TextField" positionIncrementGap="100">
|
||||
<analyzer type="index">
|
||||
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<!-- in this example, we will only use synonyms at query time
|
||||
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
||||
-->
|
||||
<!-- Case insensitive stop word removal.
|
||||
add enablePositionIncrements=true in both the index and query
|
||||
analyzers to leave a 'gap' for more accurate phrase queries.
|
||||
-->
|
||||
<filter class="solr.StopFilterFactory"
|
||||
ignoreCase="true"
|
||||
words="stopwords.txt"
|
||||
enablePositionIncrements="true"
|
||||
/>
|
||||
<filter class="solr.WordDelimiterFilterFactory"
|
||||
protected="protwords.txt"
|
||||
generateWordParts="1"
|
||||
generateNumberParts="1"
|
||||
catenateWords="1"
|
||||
catenateNumbers="1"
|
||||
catenateAll="0"
|
||||
splitOnCaseChange="1"
|
||||
preserveOriginal="1"/>
|
||||
<filter class="solr.LengthFilterFactory" min="2" max="100" />
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
||||
<filter class="solr.StopFilterFactory"
|
||||
ignoreCase="true"
|
||||
words="stopwords.txt"
|
||||
enablePositionIncrements="true"
|
||||
/>
|
||||
<filter class="solr.WordDelimiterFilterFactory"
|
||||
protected="protwords.txt"
|
||||
generateWordParts="1"
|
||||
generateNumberParts="1"
|
||||
catenateWords="0"
|
||||
catenateNumbers="0"
|
||||
catenateAll="0"
|
||||
splitOnCaseChange="1"
|
||||
preserveOriginal="1"/>
|
||||
<filter class="solr.LengthFilterFactory" min="2" max="100" />
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
|
||||
<!-- An unstemmed text field - good if one does not know the language of the field -->
|
||||
<fieldType name="text_und" class="solr.TextField" positionIncrementGap="100">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
||||
<filter class="solr.WordDelimiterFilterFactory"
|
||||
protected="protwords.txt"
|
||||
generateWordParts="1"
|
||||
generateNumberParts="1"
|
||||
catenateWords="1"
|
||||
catenateNumbers="1"
|
||||
catenateAll="0"
|
||||
splitOnCaseChange="0"/>
|
||||
<filter class="solr.LengthFilterFactory" min="2" max="100" />
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
||||
<filter class="solr.StopFilterFactory"
|
||||
ignoreCase="true"
|
||||
words="stopwords.txt"
|
||||
enablePositionIncrements="true"
|
||||
/>
|
||||
<filter class="solr.WordDelimiterFilterFactory"
|
||||
protected="protwords.txt"
|
||||
generateWordParts="1"
|
||||
generateNumberParts="1"
|
||||
catenateWords="0"
|
||||
catenateNumbers="0"
|
||||
catenateAll="0"
|
||||
splitOnCaseChange="0"/>
|
||||
<filter class="solr.LengthFilterFactory" min="2" max="100" />
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
|
||||
<!-- Edge N gram type - for example for matching against queries with results
|
||||
KeywordTokenizer leaves input string intact as a single term.
|
||||
see: http://www.lucidimagination.com/blog/2009/09/08/auto-suggest-from-popular-queries-using-edgengrams/
|
||||
-->
|
||||
<fieldType name="edge_n2_kw_text" class="solr.TextField" omitNorms="true" positionIncrementGap="100">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
<filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="25" />
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
||||
<filter class="solr.LowerCaseFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
<!-- Setup simple analysis for spell checking -->
|
||||
|
||||
<fieldType name="textSpell" class="solr.TextField" positionIncrementGap="100">
|
||||
<analyzer>
|
||||
<tokenizer class="solr.StandardTokenizerFactory" />
|
||||
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
|
||||
<filter class="solr.LengthFilterFactory" min="4" max="20" />
|
||||
<filter class="solr.LowerCaseFilterFactory" />
|
||||
<filter class="solr.RemoveDuplicatesTokenFilterFactory" />
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
|
||||
<!-- This is an example of using the KeywordTokenizer along
|
||||
With various TokenFilterFactories to produce a sortable field
|
||||
that does not include some properties of the source text
|
||||
-->
|
||||
<fieldType name="sortString" 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 refrences to portions of the orriginal
|
||||
string matched by the pattern.
|
||||
|
||||
See the Java Regular Expression documentation for more
|
||||
infomation on pattern and replacement string syntax.
|
||||
|
||||
http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
|
||||
|
||||
<filter class="solr.PatternReplaceFilterFactory"
|
||||
pattern="(^\p{Punct}+)" replacement="" replace="all"
|
||||
/>
|
||||
-->
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
|
||||
<!-- A random sort type -->
|
||||
<fieldType name="rand" class="solr.RandomSortField" indexed="true" />
|
||||
|
||||
<!-- 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" class="solr.StrField" />
|
||||
|
||||
<!-- Begin added types to use features in Solr 3.4+ -->
|
||||
<fieldType name="point" class="solr.PointType" dimension="2" subFieldType="tdouble"/>
|
||||
|
||||
<!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
|
||||
<fieldType name="location" class="solr.LatLonType" subFieldType="tdouble"/>
|
||||
|
||||
<!-- 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"/>
|
||||
<!-- End added Solr 3.4+ types -->
|
||||
|
||||
<!-- Following is a dynamic way to include other types, added by other contrib modules -->
|
||||
<xi:include href="schema_i18n_types.xml" xmlns:xi="http://www.w3.org/2001/XInclude">
|
||||
<xi:fallback></xi:fallback>
|
||||
</xi:include>
|
||||
|
||||
</types>
|
||||
|
||||
|
||||
<fields>
|
||||
<!-- Valid attributes for fields:
|
||||
name: mandatory - the name for the field
|
||||
type: mandatory - the name of a previously defined type from the <types> section
|
||||
indexed: true if this field should be indexed (searchable or sortable)
|
||||
stored: true if this field should be retrievable
|
||||
compressed: [false] if this field should be stored using gzip compression
|
||||
(this will only apply if the field type is compressable; among
|
||||
the standard field types, only TextField and StrField are)
|
||||
multiValued: true if this field may contain multiple values per document
|
||||
omitNorms: (expert) set to true to omit the norms associated with
|
||||
this field (this disables length normalization and index-time
|
||||
boosting for the field, and saves some memory). Only full-text
|
||||
fields or fields that need an index-time boost need norms.
|
||||
-->
|
||||
|
||||
<!-- The document id is usually derived from a site-spcific key (hash) and the
|
||||
entity type and ID like:
|
||||
Search Api :
|
||||
The format used is $document->id = $index_id . '-' . $item_id
|
||||
Apache Solr Search Integration
|
||||
The format used is $document->id = $site_hash . '/' . $entity_type . '/' . $entity->id;
|
||||
-->
|
||||
<field name="id" type="string" indexed="true" stored="true" required="true" />
|
||||
|
||||
<!-- Search Api specific fields -->
|
||||
<!-- item_id contains the entity ID, e.g. a node's nid. -->
|
||||
<field name="item_id" type="string" indexed="true" stored="true" />
|
||||
<!-- index_id is the machine name of the search index this entry belongs to. -->
|
||||
<field name="index_id" type="string" indexed="true" stored="true" />
|
||||
<!-- Since sorting by ID is explicitly allowed, store item_id also in a sortable way. -->
|
||||
<copyField source="item_id" dest="sort_search_api_id" />
|
||||
|
||||
<!-- Apache Solr Search Integration specific fields -->
|
||||
<!-- entity_id is the numeric object ID, e.g. Node ID, File ID -->
|
||||
<field name="entity_id" type="long" indexed="true" stored="true" />
|
||||
<!-- entity_type is 'node', 'file', 'user', or some other Drupal object type -->
|
||||
<field name="entity_type" type="string" indexed="true" stored="true" />
|
||||
<!-- bundle is a node type, or as appropriate for other entity types -->
|
||||
<field name="bundle" type="string" indexed="true" stored="true"/>
|
||||
<field name="bundle_name" type="string" indexed="true" stored="true"/>
|
||||
<field name="site" type="string" indexed="true" stored="true"/>
|
||||
<field name="hash" type="string" indexed="true" stored="true"/>
|
||||
<field name="url" type="string" indexed="true" stored="true"/>
|
||||
<!-- label is the default field for a human-readable string for this entity (e.g. the title of a node) -->
|
||||
<field name="label" type="text" indexed="true" stored="true" termVectors="true" omitNorms="true"/>
|
||||
<!-- The string version of the title is used for sorting -->
|
||||
<copyField source="label" dest="sort_label"/>
|
||||
|
||||
<!-- content is the default field for full text search - dump crap here -->
|
||||
<field name="content" type="text" indexed="true" stored="true" termVectors="true"/>
|
||||
<field name="teaser" type="text" indexed="false" stored="true"/>
|
||||
<field name="path" type="string" indexed="true" stored="true"/>
|
||||
<field name="path_alias" type="text" indexed="true" stored="true" termVectors="true" omitNorms="true"/>
|
||||
|
||||
<!-- These are the fields that correspond to a Drupal node. The beauty of having
|
||||
Lucene store title, body, type, etc., is that we retrieve them with the search
|
||||
result set and don't need to go to the database with a node_load. -->
|
||||
<field name="tid" type="long" indexed="true" stored="true" multiValued="true"/>
|
||||
<field name="taxonomy_names" type="text" indexed="true" stored="false" termVectors="true" multiValued="true" omitNorms="true"/>
|
||||
<!-- Copy terms to a single field that contains all taxonomy term names -->
|
||||
<copyField source="tm_vid_*" dest="taxonomy_names"/>
|
||||
|
||||
<!-- Here, default is used to create a "timestamp" field indicating
|
||||
when each document was indexed.-->
|
||||
<field name="timestamp" type="tdate" indexed="true" stored="true" default="NOW" multiValued="false"/>
|
||||
|
||||
<!-- This field is used to build the spellchecker index -->
|
||||
<field name="spell" type="textSpell" indexed="true" stored="true" multiValued="true"/>
|
||||
|
||||
<!-- copyField commands copy one field to another at the time a document
|
||||
is added to the index. It's used either to index the same field differently,
|
||||
or to add multiple fields to the same field for easier/faster searching. -->
|
||||
<copyField source="label" dest="spell"/>
|
||||
<copyField source="content" dest="spell"/>
|
||||
|
||||
<copyField source="ts_*" dest="spell"/>
|
||||
<copyField source="tm_*" dest="spell"/>
|
||||
|
||||
<!-- Dynamic field definitions. If a field name is not found, dynamicFields
|
||||
will be used if the name matches any of the patterns.
|
||||
RESTRICTION: the glob-like pattern in the name attribute must have
|
||||
a "*" only at the start or the end.
|
||||
EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
|
||||
Longer patterns will be matched first. if equal size patterns
|
||||
both match, the first appearing in the schema will be used. -->
|
||||
|
||||
<!-- A set of fields to contain text extracted from HTML tag contents which we
|
||||
can boost at query time. -->
|
||||
<dynamicField name="tags_*" type="text" indexed="true" stored="false" omitNorms="true"/>
|
||||
|
||||
<!-- For 2 and 3 letter prefix dynamic fields, the 1st letter indicates the data type and
|
||||
the last letter is 's' for single valued, 'm' for multi-valued -->
|
||||
|
||||
<!-- We use long for integer since 64 bit ints are now common in PHP. -->
|
||||
<dynamicField name="is_*" type="long" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="im_*" type="long" indexed="true" stored="true" multiValued="true"/>
|
||||
<!-- List of floats can be saved in a regular float field -->
|
||||
<dynamicField name="fs_*" type="float" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="fm_*" type="float" indexed="true" stored="true" multiValued="true"/>
|
||||
<!-- List of doubles can be saved in a regular double field -->
|
||||
<dynamicField name="ps_*" type="double" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="pm_*" type="double" indexed="true" stored="true" multiValued="true"/>
|
||||
<!-- List of booleans can be saved in a regular boolean field -->
|
||||
<dynamicField name="bm_*" type="boolean" indexed="true" stored="true" multiValued="true"/>
|
||||
<dynamicField name="bs_*" type="boolean" indexed="true" stored="true" multiValued="false"/>
|
||||
<!-- Regular text (without processing) can be stored in a string field-->
|
||||
<dynamicField name="ss_*" type="string" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="sm_*" type="string" indexed="true" stored="true" multiValued="true"/>
|
||||
<!-- Normal text fields are for full text - the relevance of a match depends on the length of the text -->
|
||||
<dynamicField name="ts_*" type="text" indexed="true" stored="true" multiValued="false" termVectors="true"/>
|
||||
<dynamicField name="tm_*" type="text" indexed="true" stored="true" multiValued="true" termVectors="true"/>
|
||||
<!-- Unstemmed text fields for full text - the relevance of a match depends on the length of the text -->
|
||||
<dynamicField name="tus_*" type="text_und" indexed="true" stored="true" multiValued="false" termVectors="true"/>
|
||||
<dynamicField name="tum_*" type="text_und" indexed="true" stored="true" multiValued="true" termVectors="true"/>
|
||||
<!-- These text fields omit norms - useful for extracted text like taxonomy_names -->
|
||||
<dynamicField name="tos_*" type="text" indexed="true" stored="true" multiValued="false" termVectors="true" omitNorms="true"/>
|
||||
<dynamicField name="tom_*" type="text" indexed="true" stored="true" multiValued="true" termVectors="true" omitNorms="true"/>
|
||||
<!-- Special-purpose text fields -->
|
||||
<dynamicField name="tes_*" type="edge_n2_kw_text" indexed="true" stored="true" multiValued="false" omitTermFreqAndPositions="true" />
|
||||
<dynamicField name="tem_*" type="edge_n2_kw_text" indexed="true" stored="true" multiValued="true" omitTermFreqAndPositions="true" />
|
||||
<dynamicField name="tws_*" type="text_ws" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="twm_*" type="text_ws" indexed="true" stored="true" multiValued="true"/>
|
||||
|
||||
<!-- trie dates are preferred, so give them the 2 letter prefix -->
|
||||
<dynamicField name="ds_*" type="tdate" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="dm_*" type="tdate" indexed="true" stored="true" multiValued="true"/>
|
||||
<dynamicField name="its_*" type="tlong" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="itm_*" type="tlong" indexed="true" stored="true" multiValued="true"/>
|
||||
<dynamicField name="fts_*" type="tfloat" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="ftm_*" type="tfloat" indexed="true" stored="true" multiValued="true"/>
|
||||
<dynamicField name="pts_*" type="tdouble" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="ptm_*" type="tdouble" indexed="true" stored="true" multiValued="true"/>
|
||||
<!-- Binary fields can be populated using base64 encoded data. Useful e.g. for embedding
|
||||
a small image in a search result using the data URI scheme -->
|
||||
<dynamicField name="xs_*" type="binary" indexed="false" stored="true" multiValued="false"/>
|
||||
<dynamicField name="xm_*" type="binary" indexed="false" stored="true" multiValued="true"/>
|
||||
<!-- In rare cases a date rather than tdate is needed for sortMissingLast -->
|
||||
<dynamicField name="dds_*" type="date" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="ddm_*" type="date" indexed="true" stored="true" multiValued="true"/>
|
||||
<!-- Sortable fields, good for sortMissingLast support &
|
||||
We use long for integer since 64 bit ints are now common in PHP. -->
|
||||
<dynamicField name="iss_*" type="slong" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="ism_*" type="slong" indexed="true" stored="true" multiValued="true"/>
|
||||
<!-- In rare cases a sfloat rather than tfloat is needed for sortMissingLast -->
|
||||
<dynamicField name="fss_*" type="sfloat" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="fsm_*" type="sfloat" indexed="true" stored="true" multiValued="true"/>
|
||||
<dynamicField name="pss_*" type="sdouble" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="psm_*" type="sdouble" indexed="true" stored="true" multiValued="true"/>
|
||||
<!-- In case a 32 bit int is really needed, we provide these fields. 'h' is mnemonic for 'half word', i.e. 32 bit on 64 arch -->
|
||||
<dynamicField name="hs_*" type="integer" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="hm_*" type="integer" indexed="true" stored="true" multiValued="true"/>
|
||||
<dynamicField name="hss_*" type="sint" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="hsm_*" type="sint" indexed="true" stored="true" multiValued="true"/>
|
||||
<dynamicField name="hts_*" type="tint" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="htm_*" type="tint" indexed="true" stored="true" multiValued="true"/>
|
||||
|
||||
<!-- Unindexed string fields that can be used to store values that won't be searchable -->
|
||||
<dynamicField name="zs_*" type="string" indexed="false" stored="true" multiValued="false"/>
|
||||
<dynamicField name="zm_*" type="string" indexed="false" stored="true" multiValued="true"/>
|
||||
|
||||
<!-- Begin added fields to use features in Solr 3.4+
|
||||
http://wiki.apache.org/solr/SpatialSearch#geodist_-_The_distance_function -->
|
||||
<dynamicField name="points_*" type="point" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="pointm_*" type="point" indexed="true" stored="true" multiValued="true"/>
|
||||
<dynamicField name="locs_*" type="location" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="locm_*" type="location" indexed="true" stored="true" multiValued="true"/>
|
||||
<dynamicField name="geos_*" type="geohash" indexed="true" stored="true" multiValued="false"/>
|
||||
<dynamicField name="geom_*" type="geohash" indexed="true" stored="true" multiValued="true"/>
|
||||
|
||||
<!-- External file fields -->
|
||||
<dynamicField name="eff_*" type="file"/>
|
||||
<!-- End added fields for Solr 3.4+ -->
|
||||
|
||||
<!-- Sortable version of the dynamic string field -->
|
||||
<dynamicField name="sort_*" type="sortString" indexed="true" stored="false"/>
|
||||
<copyField source="ss_*" dest="sort_*"/>
|
||||
<!-- A random sort field -->
|
||||
<dynamicField name="random_*" type="rand" indexed="true" stored="true"/>
|
||||
<!-- This field is used to store access information (e.g. node access grants), as opposed to field data -->
|
||||
<dynamicField name="access_*" type="integer" indexed="true" stored="false" multiValued="true"/>
|
||||
|
||||
<!-- Following is a dynamic way to include other fields, added by other contrib modules -->
|
||||
<xi:include href="schema_i18n_fields.xml" xmlns:xi="http://www.w3.org/2001/XInclude">
|
||||
<xi:fallback></xi:fallback>
|
||||
</xi:include>
|
||||
|
||||
<!-- The following causes solr to ignore any fields that don't already match an existing
|
||||
field name or dynamic field, rather than reporting them as an error.
|
||||
Alternately, change the type="ignored" to some other type e.g. "text" if you want
|
||||
unknown fields indexed and/or stored by default -->
|
||||
<dynamicField name="*" type="ignored" multiValued="true" />
|
||||
|
||||
</fields>
|
||||
|
||||
<!-- Field to use to determine and enforce document uniqueness.
|
||||
Unless this field is marked with required="false", it will be a required field
|
||||
-->
|
||||
<uniqueKey>id</uniqueKey>
|
||||
|
||||
<!-- field for the QueryParser to use when an explicit fieldname is absent -->
|
||||
<defaultSearchField>content</defaultSearchField>
|
||||
|
||||
<!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
|
||||
<solrQueryParser defaultOperator="AND"/>
|
||||
|
||||
</schema>
|
1645
solr-conf/3.x/solrconfig.xml
Normal file
1645
solr-conf/3.x/solrconfig.xml
Normal file
File diff suppressed because it is too large
Load Diff
10
solr-conf/3.x/solrcore.properties
Normal file
10
solr-conf/3.x/solrcore.properties
Normal file
@@ -0,0 +1,10 @@
|
||||
#solrcore.properties for this specific core
|
||||
enable.master=false
|
||||
enable.slave=false
|
||||
pollTime=00:00:60
|
||||
masterCoreUrl=http://localhost:8983/solr
|
||||
confFiles=schema.xml,mapping-ISOLatin1Accent.txt,protwords.txt,stopwords.txt,synonyms.txt,elevate.xml
|
||||
mlt.timeAllowed=2000
|
||||
# You should not set your luceneVersion to anything lower then your Solr Version
|
||||
luceneVersion=LUCENE_35
|
||||
pinkPony.timeAllowed=-1
|
Reference in New Issue
Block a user