Author: kmorin Date: 2009-11-20 17:40:10 +0100 (Fri, 20 Nov 2009) New Revision: 332 Removed: wikengo_core-wikitty/wikengo_core-wikitty-jdbc-impl/src/main/resources/protwords.txt wikengo_core-wikitty/wikengo_core-wikitty-jdbc-impl/src/main/resources/schema.xml wikengo_core-wikitty/wikengo_core-wikitty-jdbc-impl/src/main/resources/solrconfig.xml wikengo_core-wikitty/wikengo_core-wikitty-jdbc-impl/src/main/resources/spellwords.txt wikengo_core-wikitty/wikengo_core-wikitty-jdbc-impl/src/main/resources/stopwords.txt wikengo_core-wikitty/wikengo_core-wikitty-jdbc-impl/src/main/resources/synonyms.txt Modified: wikengo_core-wikitty/wikengo_core-wikitty-solr-impl/src/main/resources/schema.xml Log: add the text_fr type Deleted: wikengo_core-wikitty/wikengo_core-wikitty-jdbc-impl/src/main/resources/schema.xml =================================================================== --- wikengo_core-wikitty/wikengo_core-wikitty-jdbc-impl/src/main/resources/schema.xml 2009-11-19 16:29:55 UTC (rev 331) +++ wikengo_core-wikitty/wikengo_core-wikitty-jdbc-impl/src/main/resources/schema.xml 2009-11-20 16:40:10 UTC (rev 332) @@ -1,308 +0,0 @@ -<?xml version="1.0" encoding="UTF-8" ?> -<!-- - Licensed to the Apache Software Foundation (ASF) under one or more - contributor license agreements. See the NOTICE file distributed with - this work for additional information regarding copyright ownership. - The ASF licenses this file to You under the Apache License, Version 2.0 - (the "License"); you may not use this file except in compliance with - the License. You may obtain a copy of the License at - - http://www.apache.org/licenses/LICENSE-2.0 - - Unless required by applicable law or agreed to in writing, software - distributed under the License is distributed on an "AS IS" BASIS, - WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - See the License for the specific language governing permissions and - limitations under the License. ---> - -<!-- - 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. - - This example schema is the recommended starting point for users. - It should be kept correct and concise, usable out-of-the-box. - - For more information, on how to customize this file, please see - http://wiki.apache.org/solr/SchemaXml ---> - -<schema name="wikitty" version="1.1"> - <!-- 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="1.1" 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 --> - - <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"/> - - <!-- 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 store and index the text - value verbatim (and hence don't support range queries, since the - lexicographic ordering isn't equal to the numeric ordering) --> - <fieldType name="integer" class="solr.IntField" omitNorms="true"/> - <fieldType name="long" class="solr.LongField" omitNorms="true"/> - <fieldType name="float" class="solr.FloatField" omitNorms="true"/> - <fieldType name="double" class="solr.DoubleField" omitNorms="true"/> - - - <!-- 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.SortableIntField" sortMissingLast="true" omitNorms="true"/> - <fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/> - <fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/> - <fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/> - - - <!-- 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"/> - - - <!-- The "RandomSortField" is not used to store or search any - data. You can declare fields of this type it in your schema - to generate psuedo-random orderings of your docs for sorting - purposes. The ordering is generated based on the field name - and the version of the index, As long as the index version - remains unchanged, and the same field name is reused, - the ordering of the docs will be consistent. - If you want differend psuedo-random orderings of documents, - for the same version of the index, use a dynamicField and - change the name - --> - <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 - <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" positionIncrementGap="100"> - <analyzer> - <tokenizer class="solr.WhitespaceTokenizerFactory"/> - </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"> - <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. - enablePositionIncrements=true ensures that a 'gap' is left to - allow for accurate phrase queries. - --> - <filter class="solr.StopFilterFactory" - ignoreCase="true" - words="stopwords.txt" - enablePositionIncrements="true" - /> - <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/> - <filter class="solr.RemoveDuplicatesTokenFilterFactory"/> - </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"/> - <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/> - <filter class="solr.RemoveDuplicatesTokenFilterFactory"/> - </analyzer> - </fieldType> - - <fieldType name="text_core" class="solr.TextField" positionIncrementGap="100"> - <analyzer> - <tokenizer class="solr.WhitespaceTokenizerFactory" /> - <filter class="solr.LowerCaseFilterFactory" /> - <!-- filter class="solr.WordDelimiterFilterFactory" - generateWordParts="1" generateNumberParts="1" - catenateWords="1" catenateNumbers="1" - catenateAll="0" splitOnCaseChange="1" / --> - </analyzer> - </fieldType> - - - <!-- Less flexible matching, but less false matches. Probably not ideal for product names, - but may be good for SKUs. Can insert dashes in the wrong place and still match. --> - <fieldType name="textTight" class="solr.TextField" positionIncrementGap="100" > - <analyzer> - <tokenizer class="solr.WhitespaceTokenizerFactory"/> - <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/> - <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/> - <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/> - <filter class="solr.LowerCaseFilterFactory"/> - <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/> - <filter class="solr.RemoveDuplicatesTokenFilterFactory"/> - </analyzer> - </fieldType> - - <!-- - Setup simple analysis for spell checking - --> - <fieldType name="textSpell" class="solr.TextField" positionIncrementGap="100" > - <analyzer> - <tokenizer class="solr.StandardTokenizerFactory"/> - <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="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 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="([^a-z])" replacement="" replace="all" - /> - </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" class="solr.StrField" /> - - </types> - - - <fields> - <field name="id" type="string" indexed="true" stored="true" required="true" /> - <field name="extensions" type="string" indexed="true" stored="false" multiValued="true"/> - - <!-- catchall field, containing all other searchable text fields (implemented - via copyField further on in this schema --> - <field name="text" type="text" indexed="true" stored="false" multiValued="true"/> - - <dynamicField name="Label.label*" type="text" indexed="true" stored="true" multiValued="true"/> - - <dynamicField name="*_i" type="sint" indexed="true" stored="true" multiValued="true"/> - <dynamicField name="*_s" type="string" indexed="true" stored="true" multiValued="true"/> - <dynamicField name="*_l" type="slong" indexed="true" stored="true" multiValued="true"/> - <dynamicField name="*_t" type="string" indexed="true" stored="true" multiValued="true"/> - <dynamicField name="*_b" type="boolean" indexed="true" stored="true" multiValued="true"/> - <dynamicField name="*_f" type="sfloat" indexed="true" stored="true" multiValued="true"/> - <dynamicField name="*_d" type="sdouble" indexed="true" stored="true" multiValued="true"/> - <dynamicField name="*_dt" type="date" indexed="true" stored="true" multiValued="true"/> - - <!-- all wikitty field --> - <dynamicField name="*" type="string" indexed="true" stored="true" multiValued="true"/> - - <!-- copy fields for optimisation --> - <dynamicField name="_*" type="string" indexed="true" stored="true" 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>id</defaultSearchField> - - <!-- SolrQueryParser configuration: defaultOperator="AND|OR" --> - <solrQueryParser defaultOperator="OR"/> - -</schema> Deleted: wikengo_core-wikitty/wikengo_core-wikitty-jdbc-impl/src/main/resources/solrconfig.xml =================================================================== --- wikengo_core-wikitty/wikengo_core-wikitty-jdbc-impl/src/main/resources/solrconfig.xml 2009-11-19 16:29:55 UTC (rev 331) +++ wikengo_core-wikitty/wikengo_core-wikitty-jdbc-impl/src/main/resources/solrconfig.xml 2009-11-20 16:40:10 UTC (rev 332) @@ -1,700 +0,0 @@ -<?xml version="1.0" encoding="UTF-8" ?> -<!-- - Licensed to the Apache Software Foundation (ASF) under one or more - contributor license agreements. See the NOTICE file distributed with - this work for additional information regarding copyright ownership. - The ASF licenses this file to You under the Apache License, Version 2.0 - (the "License"); you may not use this file except in compliance with - the License. You may obtain a copy of the License at - - http://www.apache.org/licenses/LICENSE-2.0 - - Unless required by applicable law or agreed to in writing, software - distributed under the License is distributed on an "AS IS" BASIS, - WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - See the License for the specific language governing permissions and - limitations under the License. ---> - -<config> - <!-- Set this to 'false' if you want solr to continue working after it has - encountered an severe configuration error. In a production environment, - you may want solr to keep working even if one handler is mis-configured. - - You may also set this to false using by setting the system property: - -Dsolr.abortOnConfigurationError=false - --> - <abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError> - - <!-- Used to specify an alternate directory to hold all index data - other than the default ./data under the Solr home. - If replication is in use, this should match the replication configuration. --> - <dataDir>${solr.data.dir:./solr/data}</dataDir> - - - <indexDefaults> - <!-- Values here affect all index writers and act as a default unless overridden. --> - <useCompoundFile>false</useCompoundFile> - - <mergeFactor>10</mergeFactor> - <!-- - If both ramBufferSizeMB and maxBufferedDocs is set, then Lucene will flush based on whichever limit is hit first. - - --> - <!--<maxBufferedDocs>1000</maxBufferedDocs>--> - <!-- Tell Lucene when to flush documents to disk. - Giving Lucene more memory for indexing means faster indexing at the cost of more RAM - - If both ramBufferSizeMB and maxBufferedDocs is set, then Lucene will flush based on whichever limit is hit first. - - --> - <ramBufferSizeMB>32</ramBufferSizeMB> - <maxMergeDocs>2147483647</maxMergeDocs> - <maxFieldLength>10000</maxFieldLength> - <writeLockTimeout>1000</writeLockTimeout> - <commitLockTimeout>10000</commitLockTimeout> - - <!-- - Expert: Turn on Lucene's auto commit capability. - This causes intermediate segment flushes to write a new lucene - index descriptor, enabling it to be opened by an external - IndexReader. - NOTE: Despite the name, this value does not have any relation to Solr's autoCommit functionality - --> - <!--<luceneAutoCommit>false</luceneAutoCommit>--> - <!-- - Expert: - The Merge Policy in Lucene controls how merging is handled by Lucene. The default in 2.3 is the LogByteSizeMergePolicy, previous - versions used LogDocMergePolicy. - - LogByteSizeMergePolicy chooses segments to merge based on their size. The Lucene 2.2 default, LogDocMergePolicy chose when - to merge based on number of documents - - Other implementations of MergePolicy must have a no-argument constructor - --> - <!--<mergePolicy>org.apache.lucene.index.LogByteSizeMergePolicy</mergePolicy>--> - - <!-- - Expert: - The Merge Scheduler in Lucene controls how merges are performed. The ConcurrentMergeScheduler (Lucene 2.3 default) - can perform merges in the background using separate threads. The SerialMergeScheduler (Lucene 2.2 default) does not. - --> - <!--<mergeScheduler>org.apache.lucene.index.ConcurrentMergeScheduler</mergeScheduler>--> - - <!-- - This option specifies which Lucene LockFactory implementation to use. - - single = SingleInstanceLockFactory - suggested for a read-only index - or when there is no possibility of another process trying - to modify the index. - native = NativeFSLockFactory - simple = SimpleFSLockFactory - - (For backwards compatibility with Solr 1.2, 'simple' is the default - if not specified.) - --> - <lockType>single</lockType> - </indexDefaults> - - <mainIndex> - <!-- options specific to the main on-disk lucene index --> - <useCompoundFile>false</useCompoundFile> - <ramBufferSizeMB>32</ramBufferSizeMB> - <mergeFactor>10</mergeFactor> - <!-- Deprecated --> - <!--<maxBufferedDocs>1000</maxBufferedDocs>--> - <maxMergeDocs>2147483647</maxMergeDocs> - <maxFieldLength>10000</maxFieldLength> - - <!-- If true, unlock any held write or commit locks on startup. - This defeats the locking mechanism that allows multiple - processes to safely access a lucene index, and should be - used with care. - This is not needed if lock type is 'none' or 'single' - --> - <unlockOnStartup>false</unlockOnStartup> - </mainIndex> - - <!-- Enables JMX if and only if an existing MBeanServer is found, use - this if you want to configure JMX through JVM parameters. Remove - this to disable exposing Solr configuration and statistics to JMX. - - If you want to connect to a particular server, specify the agentId - e.g. <jmx agentId="myAgent" /> - - If you want to start a new MBeanServer, specify the serviceUrl - e.g <jmx serviceurl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr" /> - - For more details see http://wiki.apache.org/solr/SolrJmx - --> - <jmx /> - - <!-- the default high-performance update handler --> - <updateHandler class="solr.DirectUpdateHandler2"> - - <!-- A prefix of "solr." for class names is an alias that - causes solr to search appropriate packages, including - org.apache.solr.(search|update|request|core|analysis) - --> - - <!-- Perform a <commit/> automatically under certain conditions: - maxDocs - number of updates since last commit is greater than this - maxTime - oldest uncommited update (in ms) is this long ago - <autoCommit> - <maxDocs>10000</maxDocs> - <maxTime>1000</maxTime> - </autoCommit> - --> - - <!-- The RunExecutableListener executes an external command. - exe - the name of the executable to run - dir - dir to use as the current working directory. default="." - wait - the calling thread waits until the executable returns. default="true" - args - the arguments to pass to the program. default=nothing - env - environment variables to set. default=nothing - --> - <!-- A postCommit event is fired after every commit or optimize command - <listener event="postCommit" class="solr.RunExecutableListener"> - <str name="exe">solr/bin/snapshooter</str> - <str name="dir">.</str> - <bool name="wait">true</bool> - <arr name="args"> <str>arg1</str> <str>arg2</str> </arr> - <arr name="env"> <str>MYVAR=val1</str> </arr> - </listener> - --> - <!-- A postOptimize event is fired only after every optimize command, useful - in conjunction with index distribution to only distribute optimized indicies - <listener event="postOptimize" class="solr.RunExecutableListener"> - <str name="exe">snapshooter</str> - <str name="dir">solr/bin</str> - <bool name="wait">true</bool> - </listener> - --> - - </updateHandler> - - - <query> - <!-- Maximum number of clauses in a boolean query... can affect - range or prefix queries that expand to big boolean - queries. An exception is thrown if exceeded. --> - <maxBooleanClauses>1024</maxBooleanClauses> - - - <!-- Cache used by SolrIndexSearcher for filters (DocSets), - unordered sets of *all* documents that match a query. - When a new searcher is opened, its caches may be prepopulated - or "autowarmed" using data from caches in the old searcher. - autowarmCount is the number of items to prepopulate. For LRUCache, - the autowarmed items will be the most recently accessed items. - Parameters: - class - the SolrCache implementation (currently only LRUCache) - size - the maximum number of entries in the cache - initialSize - the initial capacity (number of entries) of - the cache. (seel java.util.HashMap) - autowarmCount - the number of entries to prepopulate from - and old cache. - --> - <filterCache - class="solr.LRUCache" - size="512" - initialSize="512" - autowarmCount="128"/> - - <!-- queryResultCache caches results of searches - ordered lists of - document ids (DocList) based on a query, a sort, and the range - of documents requested. --> - <queryResultCache - class="solr.LRUCache" - size="512" - initialSize="512" - autowarmCount="32"/> - - <!-- documentCache caches Lucene Document objects (the stored fields for each document). - Since Lucene internal document ids are transient, this cache will not be autowarmed. --> - <documentCache - class="solr.LRUCache" - size="512" - initialSize="512" - autowarmCount="0"/> - - <!-- If true, stored fields that are not requested will be loaded lazily. - - This can result in a significant speed improvement if the usual case is to - not load all stored fields, especially if the skipped fields are large compressed - text fields. - --> - <enableLazyFieldLoading>true</enableLazyFieldLoading> - - <!-- Example of a generic cache. These caches may be accessed by name - through SolrIndexSearcher.getCache(),cacheLookup(), and cacheInsert(). - The purpose is to enable easy caching of user/application level data. - The regenerator argument should be specified as an implementation - of solr.search.CacheRegenerator if autowarming is desired. --> - <!-- - <cache name="myUserCache" - class="solr.LRUCache" - size="4096" - initialSize="1024" - autowarmCount="1024" - regenerator="org.mycompany.mypackage.MyRegenerator" - /> - --> - - <!-- An optimization that attempts to use a filter to satisfy a search. - If the requested sort does not include score, then the filterCache - will be checked for a filter matching the query. If found, the filter - will be used as the source of document ids, and then the sort will be - applied to that. - <useFilterForSortedQuery>true</useFilterForSortedQuery> - --> - - <!-- An optimization for use with the queryResultCache. When a search - is requested, a superset of the requested number of document ids - are collected. For example, if a search for a particular query - requests matching documents 10 through 19, and queryWindowSize is 50, - then documents 0 through 49 will be collected and cached. Any further - requests in that range can be satisfied via the cache. --> - <queryResultWindowSize>50</queryResultWindowSize> - - <!-- Maximum number of documents to cache for any entry in the - queryResultCache. --> - <queryResultMaxDocsCached>200</queryResultMaxDocsCached> - - <!-- This entry enables an int hash representation for filters (DocSets) - when the number of items in the set is less than maxSize. For smaller - sets, this representation is more memory efficient, more efficient to - iterate over, and faster to take intersections. --> - <HashDocSet maxSize="3000" loadFactor="0.75"/> - - <!-- a newSearcher event is fired whenever a new searcher is being prepared - and there is a current searcher handling requests (aka registered). --> - <!-- QuerySenderListener takes an array of NamedList and executes a - local query request for each NamedList in sequence. --> - <listener event="newSearcher" class="solr.QuerySenderListener"> - <arr name="queries"> - <lst> <str name="q">solr</str> <str name="start">0</str> <str name="rows">10</str> </lst> - <lst> <str name="q">rocks</str> <str name="start">0</str> <str name="rows">10</str> </lst> - <lst><str name="q">static newSearcher warming query from solrconfig.xml</str></lst> - </arr> - </listener> - - <!-- a firstSearcher event is fired whenever a new searcher is being - prepared but there is no current registered searcher to handle - requests or to gain autowarming data from. --> - <listener event="firstSearcher" class="solr.QuerySenderListener"> - <arr name="queries"> - <lst> <str name="q">fast_warm</str> <str name="start">0</str> <str name="rows">10</str> </lst> - <lst><str name="q">static firstSearcher warming query from solrconfig.xml</str></lst> - </arr> - </listener> - - <!-- If a search request comes in and there is no current registered searcher, - then immediately register the still warming searcher and use it. If - "false" then all requests will block until the first searcher is done - warming. --> - <useColdSearcher>false</useColdSearcher> - - <!-- Maximum number of searchers that may be warming in the background - concurrently. An error is returned if this limit is exceeded. Recommend - 1-2 for read-only slaves, higher for masters w/o cache warming. --> - <maxWarmingSearchers>2</maxWarmingSearchers> - - </query> - - <!-- - Let the dispatch filter handler /select?qt=XXX - handleSelect=true will use consistent error handling for /select and /update - handleSelect=false will use solr1.1 style error formatting - --> - <requestDispatcher handleSelect="true" > - <!--Make sure your system has some authentication before enabling remote streaming! --> - <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" /> - - <!-- Set HTTP caching related parameters (for proxy caches and clients). - - To get the behaviour of Solr 1.2 (ie: no caching related headers) - use the never304="true" option and do not specify a value for - <cacheControl> - --> - <!-- <httpCaching never304="true"> --> - <httpCaching lastModifiedFrom="openTime" - etagSeed="Solr"> - <!-- lastModFrom="openTime" is the default, the Last-Modified value - (and validation against If-Modified-Since requests) will all be - relative to when the current Searcher was opened. - You can change it to lastModFrom="dirLastMod" if you want the - value to exactly corrispond to when the physical index was last - modified. - - etagSeed="..." is an option you can change to force the ETag - header (and validation against If-None-Match requests) to be - differnet even if the index has not changed (ie: when making - significant changes to your config file) - - lastModifiedFrom and etagSeed are both ignored if you use the - never304="true" option. - --> - <!-- If you include a <cacheControl> directive, it will be used to - generate a Cache-Control header, as well as an Expires header - if the value contains "max-age=" - - By default, no Cache-Control header is generated. - - You can use the <cacheControl> option even if you have set - never304="true" - --> - <!-- <cacheControl>max-age=30, public</cacheControl> --> - </httpCaching> - </requestDispatcher> - - - <!-- requestHandler plugins... incoming queries will be dispatched to the - correct handler based on the path or the qt (query type) param. - Names starting with a '/' are accessed with the a path equal to the - registered name. Names without a leading '/' are accessed with: - http://host/app/select?qt=name - If no qt is defined, the requestHandler that declares default="true" - will be used. - --> - <requestHandler name="standard" class="solr.SearchHandler" default="true"> - <!-- default values for query parameters --> - <lst name="defaults"> - <str name="echoParams">explicit</str> - <!-- - <int name="rows">10</int> - <str name="fl">*</str> - <str name="version">2.1</str> - --> - </lst> - </requestHandler> - - - <!-- DisMaxRequestHandler allows easy searching across multiple fields - for simple user-entered phrases. It's implementation is now - just the standard SearchHandler with a default query type - of "dismax". - see http://wiki.apache.org/solr/DisMaxRequestHandler - --> - <requestHandler name="dismax" class="solr.SearchHandler" > - <lst name="defaults"> - <str name="defType">dismax</str> - <str name="echoParams">explicit</str> - <float name="tie">0.01</float> - <str name="qf"> - text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4 - </str> - <str name="pf"> - text^0.2 features^1.1 name^1.5 manu^1.4 manu_exact^1.9 - </str> - <str name="bf"> - ord(popularity)^0.5 recip(rord(price),1,1000,1000)^0.3 - </str> - <str name="fl"> - id,name,price,score - </str> - <str name="mm"> - 2<-1 5<-2 6<90% - </str> - <int name="ps">100</int> - <str name="q.alt">*:*</str> - <!-- example highlighter config, enable per-query with hl=true --> - <str name="hl.fl">text features name</str> - <!-- for this field, we want no fragmenting, just highlighting --> - <str name="f.name.hl.fragsize">0</str> - <!-- instructs Solr to return the field itself if no query terms are - found --> - <str name="f.name.hl.alternateField">name</str> - <str name="f.text.hl.fragmenter">regex</str> <!-- defined below --> - </lst> - </requestHandler> - - <!-- Note how you can register the same handler multiple times with - different names (and different init parameters) - --> - <requestHandler name="partitioned" class="solr.SearchHandler" > - <lst name="defaults"> - <str name="defType">dismax</str> - <str name="echoParams">explicit</str> - <str name="qf">text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0</str> - <str name="mm">2<-1 5<-2 6<90%</str> - <!-- This is an example of using Date Math to specify a constantly - moving date range in a config... - --> - <str name="bq">incubationdate_dt:[* TO NOW/DAY-1MONTH]^2.2</str> - </lst> - <!-- In addition to defaults, "appends" params can be specified - to identify values which should be appended to the list of - multi-val params from the query (or the existing "defaults"). - - In this example, the param "fq=instock:true" will be appended to - any query time fq params the user may specify, as a mechanism for - partitioning the index, independent of any user selected filtering - that may also be desired (perhaps as a result of faceted searching). - - NOTE: there is *absolutely* nothing a client can do to prevent these - "appends" values from being used, so don't use this mechanism - unless you are sure you always want it. - --> - <lst name="appends"> - <str name="fq">inStock:true</str> - </lst> - <!-- "invariants" are a way of letting the Solr maintainer lock down - the options available to Solr clients. Any params values - specified here are used regardless of what values may be specified - in either the query, the "defaults", or the "appends" params. - - In this example, the facet.field and facet.query params are fixed, - limiting the facets clients can use. Faceting is not turned on by - default - but if the client does specify facet=true in the request, - these are the only facets they will be able to see counts for; - regardless of what other facet.field or facet.query params they - may specify. - - NOTE: there is *absolutely* nothing a client can do to prevent these - "invariants" values from being used, so don't use this mechanism - unless you are sure you always want it. - --> - <lst name="invariants"> - <str name="facet.field">cat</str> - <str name="facet.field">manu_exact</str> - <str name="facet.query">price:[* TO 500]</str> - <str name="facet.query">price:[500 TO *]</str> - </lst> - </requestHandler> - - - <!-- - Search components are registered to SolrCore and used by Search Handlers - - By default, the following components are avaliable: - - <searchComponent name="query" class="org.apache.solr.handler.component.QueryComponent" /> - <searchComponent name="facet" class="org.apache.solr.handler.component.FacetComponent" /> - <searchComponent name="mlt" class="org.apache.solr.handler.component.MoreLikeThisComponent" /> - <searchComponent name="highlight" class="org.apache.solr.handler.component.HighlightComponent" /> - <searchComponent name="debug" class="org.apache.solr.handler.component.DebugComponent" /> - - Default configuration in a requestHandler would look like: - <arr name="components"> - <str>query</str> - <str>facet</str> - <str>mlt</str> - <str>highlight</str> - <str>debug</str> - </arr> - - If you register a searchComponent to one of the standard names, that will be used instead. - To insert handlers before or after the 'standard' components, use: - - <arr name="first-components"> - <str>myFirstComponentName</str> - </arr> - - <arr name="last-components"> - <str>myLastComponentName</str> - </arr> - --> - - <!-- The spell check component can return a list of alternative spelling - suggestions. --> - <searchComponent name="spellcheck" class="solr.SpellCheckComponent"> - - <str name="queryAnalyzerFieldType">textSpell</str> - - <lst name="spellchecker"> - <str name="name">default</str> - <str name="field">spell</str> - <str name="spellcheckIndexDir">./spellchecker1</str> - - </lst> - <lst name="spellchecker"> - <str name="name">jarowinkler</str> - <str name="field">spell</str> - <!-- Use a different Distance Measure --> - <str name="distanceMeasure">org.apache.lucene.search.spell.JaroWinklerDistance</str> - <str name="spellcheckIndexDir">./spellchecker2</str> - - </lst> - - <lst name="spellchecker"> - <str name="classname">solr.FileBasedSpellChecker</str> - <str name="name">file</str> - <str name="sourceLocation">spellings.txt</str> - <str name="characterEncoding">UTF-8</str> - <str name="spellcheckIndexDir">./spellcheckerFile</str> - </lst> - </searchComponent> - - <!-- a request handler utilizing the spellcheck component --> - <requestHandler name="/spellCheckCompRH" class="solr.SearchHandler"> - <lst name="defaults"> - <!-- omp = Only More Popular --> - <str name="spellcheck.onlyMorePopular">false</str> - <!-- exr = Extended Results --> - <str name="spellcheck.extendedResults">false</str> - <!-- The number of suggestions to return --> - <str name="spellcheck.count">1</str> - </lst> - <arr name="last-components"> - <str>spellcheck</str> - </arr> - </requestHandler> - - <!-- a search component that enables you to configure the top results for - a given query regardless of the normal lucene scoring.--> - -<!-- poussin 20090902 remove elevate this file is empty, what need ? - <searchComponent name="elevator" class="solr.QueryElevationComponent" > - <str name="queryFieldType">string</str> - <str name="config-file">elevate.xml</str> - </searchComponent> - --> - <!-- a request handler utilizing the elevator component --> -<!-- - <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy"> - <lst name="defaults"> - <str name="echoParams">explicit</str> - </lst> - <arr name="last-components"> - <str>elevator</str> - </arr> - </requestHandler> - --> - - <!-- Update request handler. - - Note: Since solr1.1 requestHandlers requires a valid content type header if posted in - the body. For example, curl now requires: -H 'Content-type:text/xml; charset=utf-8' - The response format differs from solr1.1 formatting and returns a standard error code. - - To enable solr1.1 behavior, remove the /update handler or change its path - --> - <requestHandler name="/update" class="solr.XmlUpdateRequestHandler" /> - - <!-- - Analysis request handler. Since Solr 1.3. Use to returnhow a document is analyzed. Useful - for debugging and as a token server for other types of applications - --> - <requestHandler name="/analysis" class="solr.AnalysisRequestHandler" /> - - - <!-- CSV update handler, loaded on demand --> - <requestHandler name="/update/csv" class="solr.CSVRequestHandler" startup="lazy" /> - - - <!-- - Admin Handlers - This will register all the standard admin RequestHandlers. Adding - this single handler is equivolent to registering: - - <requestHandler name="/admin/luke" class="org.apache.solr.handler.admin.LukeRequestHandler" /> - <requestHandler name="/admin/system" class="org.apache.solr.handler.admin.SystemInfoHandler" /> - <requestHandler name="/admin/plugins" class="org.apache.solr.handler.admin.PluginInfoHandler" /> - <requestHandler name="/admin/threads" class="org.apache.solr.handler.admin.ThreadDumpHandler" /> - <requestHandler name="/admin/properties" class="org.apache.solr.handler.admin.PropertiesRequestHandler" /> - <requestHandler name="/admin/file" class="org.apache.solr.handler.admin.ShowFileRequestHandler" > - - If you wish to hide files under ${solr.home}/conf, explicitly register the ShowFileRequestHandler using: - <requestHandler name="/admin/file" class="org.apache.solr.handler.admin.ShowFileRequestHandler" > - <lst name="invariants"> - <str name="hidden">synonyms.txt</str> - <str name="hidden">anotherfile.txt</str> - </lst> - </requestHandler> - --> - <requestHandler name="/admin/" class="org.apache.solr.handler.admin.AdminHandlers" /> - - <!-- ping/healthcheck --> - <requestHandler name="/admin/ping" class="PingRequestHandler"> - <lst name="defaults"> - <str name="qt">standard</str> - <str name="q">solrpingquery</str> - <str name="echoParams">all</str> - </lst> - </requestHandler> - - <!-- Echo the request contents back to the client --> - <requestHandler name="/debug/dump" class="solr.DumpRequestHandler" > - <lst name="defaults"> - <str name="echoParams">explicit</str> <!-- for all params (including the default etc) use: 'all' --> - <str name="echoHandler">true</str> - </lst> - </requestHandler> - - <highlighting> - <!-- Configure the standard fragmenter --> - <!-- This could most likely be commented out in the "default" case --> - <fragmenter name="gap" class="org.apache.solr.highlight.GapFragmenter" default="true"> - <lst name="defaults"> - <int name="hl.fragsize">100</int> - </lst> - </fragmenter> - - <!-- A regular-expression-based fragmenter (f.i., for sentence extraction) --> - <fragmenter name="regex" class="org.apache.solr.highlight.RegexFragmenter"> - <lst name="defaults"> - <!-- slightly smaller fragsizes work better because of slop --> - <int name="hl.fragsize">70</int> - <!-- allow 50% slop on fragment sizes --> - <float name="hl.regex.slop">0.5</float> - <!-- a basic sentence pattern --> - <str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str> - </lst> - </fragmenter> - - <!-- Configure the standard formatter --> - <formatter name="html" class="org.apache.solr.highlight.HtmlFormatter" default="true"> - <lst name="defaults"> - <str name="hl.simple.pre"><![CDATA[<em>]]></str> - <str name="hl.simple.post"><![CDATA[</em>]]></str> - </lst> - </formatter> - </highlighting> - - - <!-- queryResponseWriter plugins... query responses will be written using the - writer specified by the 'wt' request parameter matching the name of a registered - writer. - The "default" writer is the default and will be used if 'wt' is not specified - in the request. XMLResponseWriter will be used if nothing is specified here. - The json, python, and ruby writers are also available by default. - - <queryResponseWriter name="xml" class="org.apache.solr.request.XMLResponseWriter" default="true"/> - <queryResponseWriter name="json" class="org.apache.solr.request.JSONResponseWriter"/> - <queryResponseWriter name="python" class="org.apache.solr.request.PythonResponseWriter"/> - <queryResponseWriter name="ruby" class="org.apache.solr.request.RubyResponseWriter"/> - <queryResponseWriter name="php" class="org.apache.solr.request.PHPResponseWriter"/> - <queryResponseWriter name="phps" class="org.apache.solr.request.PHPSerializedResponseWriter"/> - - <queryResponseWriter name="custom" class="com.example.MyResponseWriter"/> - --> - - <!-- XSLT response writer transforms the XML output by any xslt file found - in Solr's conf/xslt directory. Changes to xslt files are checked for - every xsltCacheLifetimeSeconds. - --> - <queryResponseWriter name="xslt" class="org.apache.solr.request.XSLTResponseWriter"> - <int name="xsltCacheLifetimeSeconds">5</int> - </queryResponseWriter> - - - <queryParser name="wikitty" class="org.sharengo.wikitty.solr.WikittyQueryParser"/> - - <!-- example of registering a query parser - <queryParser name="lucene" class="org.apache.solr.search.LuceneQParserPlugin"/> - --> - - <!-- example of registering a custom function parser - <valueSourceParser name="myfunc" class="com.mycompany.MyValueSourceParser" /> - --> - - <!-- config for the admin interface --> - <admin> - <defaultQuery>solr</defaultQuery> - - <!-- configure a healthcheck file for servers behind a loadbalancer - <healthcheck type="file">server-enabled</healthcheck> - --> - </admin> - -</config> Deleted: wikengo_core-wikitty/wikengo_core-wikitty-jdbc-impl/src/main/resources/stopwords.txt =================================================================== --- wikengo_core-wikitty/wikengo_core-wikitty-jdbc-impl/src/main/resources/stopwords.txt 2009-11-19 16:29:55 UTC (rev 331) +++ wikengo_core-wikitty/wikengo_core-wikitty-jdbc-impl/src/main/resources/stopwords.txt 2009-11-20 16:40:10 UTC (rev 332) @@ -1,57 +0,0 @@ -# Licensed to the Apache Software Foundation (ASF) under one or more -# contributor license agreements. See the NOTICE file distributed with -# this work for additional information regarding copyright ownership. -# The ASF licenses this file to You under the Apache License, Version 2.0 -# (the "License"); you may not use this file except in compliance with -# the License. You may obtain a copy of the License at -# -# http://www.apache.org/licenses/LICENSE-2.0 -# -# Unless required by applicable law or agreed to in writing, software -# distributed under the License is distributed on an "AS IS" BASIS, -# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -# See the License for the specific language governing permissions and -# limitations under the License. - -#----------------------------------------------------------------------- -# a couple of test stopwords to test that the words are really being -# configured from this file: -stopworda -stopwordb - -#Standard english stop words taken from Lucene's StopAnalyzer -an -and -are -as -at -be -but -by -for -if -in -into -is -it -no -not -of -on -or -s -such -t -that -the -their -then -there -these -they -this -to -was -will -with - Modified: wikengo_core-wikitty/wikengo_core-wikitty-solr-impl/src/main/resources/schema.xml =================================================================== --- wikengo_core-wikitty/wikengo_core-wikitty-solr-impl/src/main/resources/schema.xml 2009-11-19 16:29:55 UTC (rev 331) +++ wikengo_core-wikitty/wikengo_core-wikitty-solr-impl/src/main/resources/schema.xml 2009-11-20 16:40:10 UTC (rev 332) @@ -189,6 +189,17 @@ </analyzer> </fieldType> + <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.ISOLatin1AccentFilterFactory"/> + <filter class="solr.StandardFilterFactory"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/> + <filter class="solr.SnowballPorterFilterFactory" language="French"/> + </analyzer> + </fieldType> + <fieldType name="text_core" class="solr.TextField" positionIncrementGap="100"> <analyzer> <tokenizer class="solr.WhitespaceTokenizerFactory" /> @@ -268,12 +279,12 @@ <fields> - <field name="id" type="text" indexed="true" stored="true" required="true" /> - <field name="extensions" type="text" indexed="true" stored="false" multiValued="true"/> + <field name="id" type="text_fr" indexed="true" stored="true" required="true" /> + <field name="extensions" type="text_fr" indexed="true" stored="false" multiValued="true"/> <!-- catchall field, containing all other searchable text fields (implemented via copyField further on in this schema --> - <field name="text" type="text" indexed="true" stored="false" multiValued="true"/> + <field name="text" type="text_fr" indexed="true" stored="false" multiValued="true"/> <copyField source="*_i" dest="text"/> <copyField source="*_s" dest="text"/> <copyField source="*_l" dest="text"/> @@ -284,19 +295,19 @@ <copyField source="*_dt" dest="text"/> <dynamicField name="*_i" type="sint" indexed="true" stored="true" multiValued="true"/> - <dynamicField name="*_s" type="text" indexed="true" stored="true" multiValued="true"/> + <dynamicField name="*_s" type="text_fr" indexed="true" stored="true" multiValued="true"/> <dynamicField name="*_l" type="slong" indexed="true" stored="true" multiValued="true"/> - <dynamicField name="*_t" type="text" indexed="true" stored="true" multiValued="true"/> + <dynamicField name="*_t" type="text_fr" indexed="true" stored="true" multiValued="true"/> <dynamicField name="*_b" type="boolean" indexed="true" stored="true" multiValued="true"/> <dynamicField name="*_f" type="sfloat" indexed="true" stored="true" multiValued="true"/> <dynamicField name="*_d" type="sdouble" indexed="true" stored="true" multiValued="true"/> <dynamicField name="*_dt" type="date" indexed="true" stored="true" multiValued="true"/> <!-- all wikitty field --> - <dynamicField name="*" type="text" indexed="true" stored="true" multiValued="true"/> + <dynamicField name="*" type="text_fr" indexed="true" stored="true" multiValued="true"/> <!-- copy fields for optimisation --> - <dynamicField name="_*" type="text" indexed="true" stored="true" multiValued="true"/> + <dynamicField name="_*" type="text_fr" indexed="true" stored="true" multiValued="true"/> </fields>