You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by cp...@apache.org on 2017/03/30 17:24:40 UTC
[11/73] [abbrv] lucene-solr:jira/solr-6203: SOLR-9221: Remove Solr
contribs: map-reduce, morphlines-core and morphlines-cell
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/53e5f34f/solr/contrib/morphlines-core/src/test-files/solr/solrcloud/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/solr/solrcloud/conf/solrconfig.xml b/solr/contrib/morphlines-core/src/test-files/solr/solrcloud/conf/solrconfig.xml
deleted file mode 100644
index 42ab056..0000000
--- a/solr/contrib/morphlines-core/src/test-files/solr/solrcloud/conf/solrconfig.xml
+++ /dev/null
@@ -1,1437 +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.
--->
-
-<!--
- For more details about configurations options that may appear in
- this file, see http://wiki.apache.org/solr/SolrConfigXml.
--->
-<config>
- <!-- In all configuration below, 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)
-
- You may also specify a fully qualified Java classname if you
- have your own custom plugins.
- -->
-
- <!-- Controls what version of Lucene various components of Solr
- adhere to. Generally, you want to use the latest version to
- get all bug fixes and improvements. It is highly recommended
- that you fully re-index after changing this setting as it can
- affect both how text is indexed and queried.
- -->
- <luceneMatchVersion>${tests.luceneMatchVersion:LATEST}</luceneMatchVersion>
-
- <!-- <lib/> directives can be used to instruct Solr to load any Jars
- identified and use them to resolve any "plugins" specified in
- your solrconfig.xml or schema.xml (ie: Analyzers, Request
- Handlers, etc...).
-
- All directories and paths are resolved relative to the
- instanceDir.
-
- Please note that <lib/> directives are processed in the order
- that they appear in your solrconfig.xml file, and are "stacked"
- on top of each other when building a ClassLoader - so if you have
- plugin jars with dependencies on other jars, the "lower level"
- dependency jars should be loaded first.
-
- If a "./lib" directory exists in your instanceDir, all files
- found in it are included as if you had used the following
- syntax...
-
- <lib dir="./lib" />
- -->
-
- <!-- A 'dir' option by itself adds any files found in the directory
- to the classpath, this is useful for including all jars in a
- directory.
-
- When a 'regex' is specified in addition to a 'dir', only the
- files in that directory which completely match the regex
- (anchored on both ends) will be included.
-
- The examples below can be used to load some solr-contribs along
- with their external dependencies.
- -->
- <lib dir="../../../contrib/extraction/lib" regex=".*\.jar" />
- <lib dir="../../../dist/" regex="solr-cell-\d.*\.jar" />
-
- <lib dir="../../../contrib/clustering/lib/" regex=".*\.jar" />
- <lib dir="../../../dist/" regex="solr-clustering-\d.*\.jar" />
-
- <lib dir="../../../contrib/langid/lib/" regex=".*\.jar" />
- <lib dir="../../../dist/" regex="solr-langid-\d.*\.jar" />
-
- <lib dir="../../../contrib/velocity/lib" regex=".*\.jar" />
- <lib dir="../../../dist/" regex="solr-velocity-\d.*\.jar" />
-
- <!-- If a 'dir' option (with or without a regex) is used and nothing
- is found that matches, a warning will be logged.
- -->
- <lib dir="/non/existent/dir/yields/warning" />
-
- <!-- an exact 'path' can be used instead of a 'dir' to specify a
- specific jar file. This will cause a serious error to be logged
- if it can't be loaded.
- -->
- <!--
- <lib path="../a-jar-that-does-not-exist.jar" />
- -->
-
- <!-- Data Directory
-
- 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:}</dataDir>
-
-
- <!-- The DirectoryFactory to use for indexes.
-
- solr.StandardDirectoryFactory is filesystem
- based and tries to pick the best implementation for the current
- JVM and platform. solr.NRTCachingDirectoryFactory, the default,
- wraps solr.StandardDirectoryFactory and caches small files in memory
- for better NRT performance.
-
- One can force a particular implementation via solr.MMapDirectoryFactory,
- solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
-
- solr.RAMDirectoryFactory is memory based, not
- persistent, and doesn't work with replication.
- -->
- <directoryFactory name="DirectoryFactory" class="org.apache.solr.core.HdfsDirectoryFactory">
- <str name="solr.hdfs.home">${solr.hdfs.home:}</str>
- <str name="solr.hdfs.confdir">${solr.hdfs.confdir:}</str>
- <str name="solr.hdfs.security.kerberos.enabled">${solr.hdfs.security.kerberos.enabled:false}</str>
- <str name="solr.hdfs.security.kerberos.keytabfile">${solr.hdfs.security.kerberos.keytabfile:}</str>
- <str name="solr.hdfs.security.kerberos.principal">${solr.hdfs.security.kerberos.principal:}</str>
- <bool name="solr.hdfs.blockcache.enabled">${solr.hdfs.blockcache.enabled:true}</bool>
- <int name="solr.hdfs.blockcache.slab.count">${solr.hdfs.blockcache.slab.count:1}</int>
- <bool name="solr.hdfs.blockcache.direct.memory.allocation">${solr.hdfs.blockcache.direct.memory.allocation:true}</bool>
- <int name="solr.hdfs.blockcache.blocksperbank">${solr.hdfs.blockcache.blocksperbank:16384}</int>
- <bool name="solr.hdfs.blockcache.read.enabled">${solr.hdfs.blockcache.read.enabled:true}</bool>
- <bool name="solr.hdfs.nrtcachingdirectory.enable">${solr.hdfs.nrtcachingdirectory.enable:true}</bool>
- <int name="solr.hdfs.nrtcachingdirectory.maxmergesizemb">${solr.hdfs.nrtcachingdirectory.maxmergesizemb:16}</int>
- <int name="solr.hdfs.nrtcachingdirectory.maxcachedmb">${solr.hdfs.nrtcachingdirectory.maxcachedmb:192}</int>
- <str name="solr.hdfs.blockcache.global">${solr.hdfs.blockcache.global:false}</str>
- </directoryFactory>
-
- <schemaFactory class="ClassicIndexSchemaFactory"/>
-
- <!-- The CodecFactory for defining the format of the inverted index.
- The default implementation is SchemaCodecFactory, which is the official Lucene
- index format, but hooks into the schema to provide per-field customization of
- the postings lists and per-document values in the fieldType element
- (postingsFormat/docValuesFormat). Note that most of the alternative implementations
- are experimental, so if you choose to customize the index format, it's a good
- idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)
- before upgrading to a newer version to avoid unnecessary reindexing.
- -->
- <codecFactory class="solr.SchemaCodecFactory"/>
-
- <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Index Config - These settings control low-level behavior of indexing
- Most example settings here show the default value, but are commented
- out, to more easily see where customizations have been made.
-
- Note: This replaces <indexDefaults> and <mainIndex> from older versions
- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
- <indexConfig>
- <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
- LimitTokenCountFilterFactory in your fieldType definition. E.g.
- <filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
- -->
- <!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
- <!-- <writeLockTimeout>1000</writeLockTimeout> -->
-
- <!-- Expert: Enabling compound file will use less files for the index,
- using fewer file descriptors on the expense of performance decrease.
- Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
- <!-- <useCompoundFile>false</useCompoundFile> -->
-
- <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
- indexing for buffering added documents and deletions before they are
- flushed to the Directory.
- maxBufferedDocs sets a limit on the number of documents buffered
- before flushing.
- If both ramBufferSizeMB and maxBufferedDocs is set, then
- Lucene will flush based on whichever limit is hit first. -->
- <ramBufferSizeMB>128</ramBufferSizeMB>
- <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
-
- <!-- Expert: Merge Policy
- The Merge Policy in Lucene controls how merging of segments is done.
- The default since Solr/Lucene 3.3 is TieredMergePolicy.
- The default since Lucene 2.3 was the LogByteSizeMergePolicy,
- Even older versions of Lucene used LogDocMergePolicy.
- -->
- <!--
- <mergePolicyFactory class="solr.TieredMergePolicyFactory">
- <int name="maxMergeAtOnce">10</int>
- <int name="segmentsPerTier">10</int>
- </mergePolicyFactory>
- -->
-
- <!-- Expert: Merge Scheduler
- 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 class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
- -->
-
- <!-- LockFactory
-
- 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 - uses OS native file locking.
- Do not use when multiple solr webapps in the same
- JVM are attempting to share a single index.
- simple = SimpleFSLockFactory - uses a plain file for locking
-
- Defaults: 'native' is default for Solr3.6 and later, otherwise
- 'simple' is the default
-
- More details on the nuances of each LockFactory...
- http://wiki.apache.org/lucene-java/AvailableLockFactories
- -->
- <lockType>${solr.lock.type:hdfs}</lockType>
-
- <!-- If true, IndexReaders will be reopened (often more efficient)
- instead of closed and then opened. Default: true
- -->
- <!--
- <reopenReaders>true</reopenReaders>
- -->
-
- <!-- Commit Deletion Policy
- Custom deletion policies can be specified here. The class must
- implement org.apache.lucene.index.IndexDeletionPolicy.
-
- The default Solr IndexDeletionPolicy implementation supports
- deleting index commit points on number of commits, age of
- commit point and optimized status.
-
- The latest commit point should always be preserved regardless
- of the criteria.
- -->
- <!--
- <deletionPolicy class="solr.SolrDeletionPolicy">
- -->
- <!-- The number of commit points to be kept -->
- <!-- <str name="maxCommitsToKeep">1</str> -->
- <!-- The number of optimized commit points to be kept -->
- <!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
- <!--
- Delete all commit points once they have reached the given age.
- Supports DateMathParser syntax e.g.
- -->
- <!--
- <str name="maxCommitAge">30MINUTES</str>
- <str name="maxCommitAge">1DAY</str>
- -->
- <!--
- </deletionPolicy>
- -->
-
- <!-- Lucene Infostream
-
- To aid in advanced debugging, Lucene provides an "InfoStream"
- of detailed information when indexing.
-
- Setting The value to true will instruct the underlying Lucene
- IndexWriter to write its debugging info the specified file
- -->
- <!-- <infoStream file="INFOSTREAM.txt">false</infoStream> -->
- </indexConfig>
-
-
- <!-- JMX
-
- This example 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.
-
- For more details see http://wiki.apache.org/solr/SolrJmx
- -->
- <jmx />
- <!-- If you want to connect to a particular server, specify the
- agentId
- -->
- <!-- <jmx agentId="myAgent" /> -->
- <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
- <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
- -->
-
- <!-- The default high-performance update handler -->
- <updateHandler class="solr.DirectUpdateHandler2">
-
- <!-- Enables a transaction log, used for real-time get, durability, and
- and solr cloud replica recovery. The log can grow as big as
- uncommitted changes to the index, so use of a hard autoCommit
- is recommended (see below).
- "dir" - the target directory for transaction logs, defaults to the
- solr data directory. -->
- <updateLog>
- <str name="dir">${solr.ulog.dir:}</str>
- </updateLog>
-
- <!-- AutoCommit
-
- Perform a hard commit automatically under certain conditions.
- Instead of enabling autoCommit, consider using "commitWithin"
- when adding documents.
-
- http://wiki.apache.org/solr/UpdateXmlMessages
-
- maxDocs - Maximum number of documents to add since the last
- commit before automatically triggering a new commit.
-
- maxTime - Maximum amount of time in ms that is allowed to pass
- since a document was added before automatically
- triggering a new commit.
- openSearcher - if false, the commit causes recent index changes
- to be flushed to stable storage, but does not cause a new
- searcher to be opened to make those changes visible.
-
- If the updateLog is enabled, then it's highly recommended to
- have some sort of hard autoCommit to limit the log size.
- -->
- <autoCommit>
- <maxTime>${solr.autoCommit.maxTime:60000}</maxTime>
- <openSearcher>false</openSearcher>
- </autoCommit>
-
- <!-- softAutoCommit is like autoCommit except it causes a
- 'soft' commit which only ensures that changes are visible
- but does not ensure that data is synced to disk. This is
- faster and more near-realtime friendly than a hard commit.
- -->
- <autoSoftCommit>
- <maxTime>${solr.autoSoftCommit.maxTime:1000}</maxTime>
- </autoSoftCommit>
-
-
- <!-- Update Related Event Listeners
-
- Various IndexWriter related events can trigger Listeners to
- take actions.
-
- postCommit - fired after every commit or optimize command
- postOptimize - fired after every optimize command
- -->
- <!-- The RunExecutableListener executes an external command from a
- hook such as postCommit or postOptimize.
-
- 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 is none)
- env - environment variables to set. (default is none)
- -->
- <!-- This example shows how RunExecutableListener could be used
- with the script based replication...
- http://wiki.apache.org/solr/CollectionDistribution
- -->
- <!--
- <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>
- -->
-
- </updateHandler>
-
- <!-- IndexReaderFactory
-
- Use the following format to specify a custom IndexReaderFactory,
- which allows for alternate IndexReader implementations.
-
- ** Experimental Feature **
-
- Please note - Using a custom IndexReaderFactory may prevent
- certain other features from working. The API to
- IndexReaderFactory may change without warning or may even be
- removed from future releases if the problems cannot be
- resolved.
-
-
- ** Features that may not work with custom IndexReaderFactory **
-
- The ReplicationHandler assumes a disk-resident index. Using a
- custom IndexReader implementation may cause incompatibility
- with ReplicationHandler and may cause replication to not work
- correctly. See SOLR-1366 for details.
-
- -->
- <!--
- <indexReaderFactory name="IndexReaderFactory" class="package.class">
- <str name="someArg">Some Value</str>
- </indexReaderFactory >
- -->
- <!-- By explicitly declaring the Factory, the termIndexDivisor can
- be specified.
- -->
- <!--
- <indexReaderFactory name="IndexReaderFactory"
- class="solr.StandardIndexReaderFactory">
- <int name="setTermIndexDivisor">12</int>
- </indexReaderFactory >
- -->
-
- <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Query section - these settings control query time things like caches
- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
- <query>
- <!-- Max Boolean Clauses
-
- Maximum number of clauses in each BooleanQuery, an exception
- is thrown if exceeded.
-
- ** WARNING **
-
- This option actually modifies a global Lucene property that
- will affect all SolrCores. If multiple solrconfig.xml files
- disagree on this property, the value at any given moment will
- be based on the last SolrCore to be initialized.
-
- -->
- <maxBooleanClauses>1024</maxBooleanClauses>
-
-
- <!-- Solr Internal Query Caches
-
- There are two implementations of cache available for Solr,
- LRUCache, based on a synchronized LinkedHashMap, and
- FastLRUCache, based on a ConcurrentHashMap.
-
- FastLRUCache has faster gets and slower puts in single
- threaded operation and thus is generally faster than LRUCache
- when the hit ratio of the cache is high (> 75%), and may be
- faster under other scenarios on multi-cpu systems.
- -->
-
- <!-- Filter Cache
-
- 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 LRUCache or
- (LRUCache or FastLRUCache)
- size - the maximum number of entries in the cache
- initialSize - the initial capacity (number of entries) of
- the cache. (see java.util.HashMap)
- autowarmCount - the number of entries to prepopulate from
- and old cache.
- -->
- <filterCache class="solr.FastLRUCache"
- size="512"
- initialSize="512"
- autowarmCount="0"/>
-
- <!-- Query Result Cache
-
- 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="0"/>
-
- <!-- Document Cache
-
- 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"/>
-
- <!-- Field Value Cache
-
- Cache used to hold field values that are quickly accessible
- by document id. The fieldValueCache is created by default
- even if not configured here.
- -->
- <!--
- <fieldValueCache class="solr.FastLRUCache"
- size="512"
- autowarmCount="128"
- showItems="32" />
- -->
-
- <!-- Custom Cache
-
- 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.CacheRegenerator
- if autowarming is desired.
- -->
- <!--
- <cache name="myUserCache"
- class="solr.LRUCache"
- size="4096"
- initialSize="1024"
- autowarmCount="1024"
- regenerator="com.mycompany.MyRegenerator"
- />
- -->
-
-
- <!-- Lazy Field Loading
-
- 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>
-
- <!-- Use Filter For Sorted Query
-
- A possible 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.
-
- For most situations, this will not be useful unless you
- frequently get the same search repeatedly with different sort
- options, and none of them ever use "score"
- -->
- <!--
- <useFilterForSortedQuery>true</useFilterForSortedQuery>
- -->
-
- <!-- Result Window Size
-
- 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>20</queryResultWindowSize>
-
- <!-- Maximum number of documents to cache for any entry in the
- queryResultCache.
- -->
- <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
-
- <!-- Query Related Event Listeners
-
- Various IndexSearcher related events can trigger Listeners to
- take actions.
-
- newSearcher - fired whenever a new searcher is being prepared
- and there is a current searcher handling requests (aka
- registered). It can be used to prime certain caches to
- prevent long request times for certain requests.
-
- firstSearcher - fired whenever a new searcher is being
- prepared but there is no current registered searcher to handle
- requests or to gain autowarming data from.
-
-
- -->
- <!-- 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="sort">price asc</str></lst>
- <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
- -->
- </arr>
- </listener>
- <listener event="firstSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <lst>
- <str name="q">static firstSearcher warming in solrconfig.xml</str>
- </lst>
- </arr>
- </listener>
-
- <!-- Use Cold Searcher
-
- 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>
-
- </query>
-
-
- <!-- Request Dispatcher
-
- This section contains instructions for how the SolrDispatchFilter
- should behave when processing requests for this SolrCore.
-
- handleSelect is a legacy option that affects the behavior of requests
- such as /select?qt=XXX
-
- handleSelect="true" will cause the SolrDispatchFilter to process
- the request and dispatch the query to a handler specified by the
- "qt" param, assuming "/select" isn't already registered.
-
- handleSelect="false" will cause the SolrDispatchFilter to
- ignore "/select" requests, resulting in a 404 unless a handler
- is explicitly registered with the name "/select"
-
- handleSelect="true" is not recommended for new users, but is the default
- for backwards compatibility
- -->
- <requestDispatcher handleSelect="false" >
- <!-- Request Parsing
-
- These settings indicate how Solr Requests may be parsed, and
- what restrictions may be placed on the ContentStreams from
- those requests
-
- enableRemoteStreaming - enables use of the stream.file
- and stream.url parameters for specifying remote streams.
-
- multipartUploadLimitInKB - specifies the max size (in KiB) of
- Multipart File Uploads that Solr will allow in a Request.
-
- formdataUploadLimitInKB - specifies the max size (in KiB) of
- form data (application/x-www-form-urlencoded) sent via
- POST. You can use POST to pass request parameters not
- fitting into the URL.
-
- *** WARNING ***
- The settings below authorize Solr to fetch remote files, You
- should make sure your system has some authentication before
- using enableRemoteStreaming="true"
-
- -->
- <requestParsers enableRemoteStreaming="true"
- multipartUploadLimitInKB="2048000"
- formdataUploadLimitInKB="2048"/>
-
- <!-- HTTP Caching
-
- Set HTTP caching related parameters (for proxy caches and clients).
-
- The options below instruct Solr not to output any HTTP Caching
- related headers
- -->
- <httpCaching never304="true" />
- <!-- 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"
- -->
- <!--
- <httpCaching never304="true" >
- <cacheControl>max-age=30, public</cacheControl>
- </httpCaching>
- -->
- <!-- To enable Solr to respond with automatically generated HTTP
- Caching headers, and to response to Cache Validation requests
- correctly, set the value of never304="false"
-
- This will cause Solr to generate Last-Modified and ETag
- headers based on the properties of the Index.
-
- The following options can also be specified to affect the
- values of these headers...
-
- lastModFrom - the default value is "openTime" which means 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 correspond 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
- different 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)
- -->
- <!--
- <httpCaching lastModifiedFrom="openTime"
- etagSeed="Solr">
- <cacheControl>max-age=30, public</cacheControl>
- </httpCaching>
- -->
- </requestDispatcher>
-
- <!-- Request Handlers
-
- http://wiki.apache.org/solr/SolrRequestHandler
-
- Incoming queries will be dispatched to a specific handler by name
- based on the path specified in the request.
-
- Legacy behavior: If the request path uses "/select" but no Request
- Handler has that name, and if handleSelect="true" has been specified in
- the requestDispatcher, then the Request Handler is dispatched based on
- the qt parameter. Handlers without a leading '/' are accessed this way
- like so: http://host/app/[core/]select?qt=name If no qt is
- given, then the requestHandler that declares default="true" will be
- used or the one named "standard".
-
- If a Request Handler is declared with startup="lazy", then it will
- not be initialized until the first request that uses it.
-
- -->
- <!-- SearchHandler
-
- http://wiki.apache.org/solr/SearchHandler
-
- For processing Search Queries, the primary Request Handler
- provided with Solr is "SearchHandler" It delegates to a sequent
- of SearchComponents (see below) and supports distributed
- queries across multiple shards
- -->
- <requestHandler name="/select" class="solr.SearchHandler">
- <!-- default values for query parameters can be specified, these
- will be overridden by parameters in the request
- -->
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <int name="rows">10</int>
- <str name="df">text</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" would 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 would
- be 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>
- -->
- <!-- If the default list of SearchComponents is not desired, that
- list can either be overridden completely, or components can be
- prepended or appended to the default list. (see below)
- -->
- <!--
- <arr name="components">
- <str>nameOfCustomComponent1</str>
- <str>nameOfCustomComponent2</str>
- </arr>
- -->
- </requestHandler>
-
- <!-- A request handler that returns indented JSON by default -->
- <requestHandler name="/query" class="solr.SearchHandler">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <str name="wt">json</str>
- <str name="indent">true</str>
- <str name="df">text</str>
- </lst>
- </requestHandler>
- <!-- Search Components
-
- Search components are registered to SolrCore and used by
- instances of SearchHandler (which can access them by name)
-
- By default, the following components are available:
-
- <searchComponent name="query" class="solr.QueryComponent" />
- <searchComponent name="facet" class="solr.FacetComponent" />
- <searchComponent name="mlt" class="solr.MoreLikeThisComponent" />
- <searchComponent name="highlight" class="solr.HighlightComponent" />
- <searchComponent name="stats" class="solr.StatsComponent" />
- <searchComponent name="debug" class="solr.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>stats</str>
- <str>debug</str>
- </arr>
-
- If you register a searchComponent to one of the standard names,
- that will be used instead of the default.
-
- To insert components before or after the 'standard' components, use:
-
- <arr name="first-components">
- <str>myFirstComponentName</str>
- </arr>
-
- <arr name="last-components">
- <str>myLastComponentName</str>
- </arr>
-
- NOTE: The component registered with the name "debug" will
- always be executed after the "last-components"
-
- -->
-
- <!-- Spell Check
-
- The spell check component can return a list of alternative spelling
- suggestions.
-
- http://wiki.apache.org/solr/SpellCheckComponent
- -->
- <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
-
- <str name="queryAnalyzerFieldType">text_general</str>
-
- <!-- Multiple "Spell Checkers" can be declared and used by this
- component
- -->
-
- <!-- a spellchecker built from a field of the main index -->
- <lst name="spellchecker">
- <str name="name">default</str>
- <str name="field">text</str>
- <str name="classname">solr.DirectSolrSpellChecker</str>
- <!-- the spellcheck distance measure used, the default is the internal levenshtein -->
- <str name="distanceMeasure">internal</str>
- <!-- minimum accuracy needed to be considered a valid spellcheck suggestion -->
- <float name="accuracy">0.5</float>
- <!-- the maximum #edits we consider when enumerating terms: can be 1 or 2 -->
- <int name="maxEdits">2</int>
- <!-- the minimum shared prefix when enumerating terms -->
- <int name="minPrefix">1</int>
- <!-- maximum number of inspections per result. -->
- <int name="maxInspections">5</int>
- <!-- minimum length of a query term to be considered for correction -->
- <int name="minQueryLength">4</int>
- <!-- maximum threshold of documents a query term can appear to be considered for correction -->
- <float name="maxQueryFrequency">0.01</float>
- <!-- uncomment this to require suggestions to occur in 1% of the documents
- <float name="thresholdTokenFrequency">.01</float>
- -->
- </lst>
-
- <!-- a spellchecker that can break or combine words. See "/spell" handler below for usage -->
- <lst name="spellchecker">
- <str name="name">wordbreak</str>
- <str name="classname">solr.WordBreakSolrSpellChecker</str>
- <str name="field">name</str>
- <str name="combineWords">true</str>
- <str name="breakWords">true</str>
- <int name="maxChanges">10</int>
- </lst>
-
- <!-- a spellchecker that uses a different distance measure -->
- <!--
- <lst name="spellchecker">
- <str name="name">jarowinkler</str>
- <str name="field">spell</str>
- <str name="classname">solr.DirectSolrSpellChecker</str>
- <str name="distanceMeasure">
- org.apache.lucene.search.spell.JaroWinklerDistance
- </str>
- </lst>
- -->
-
- <!-- a spellchecker that use an alternate comparator
-
- comparatorClass be one of:
- 1. score (default)
- 2. freq (Frequency first, then score)
- 3. A fully qualified class name
- -->
- <!--
- <lst name="spellchecker">
- <str name="name">freq</str>
- <str name="field">lowerfilt</str>
- <str name="classname">solr.DirectSolrSpellChecker</str>
- <str name="comparatorClass">freq</str>
- -->
-
- <!-- A spellchecker that reads the list of words from a file -->
- <!--
- <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 for demonstrating the spellcheck component.
-
- NOTE: This is purely as an example. The whole purpose of the
- SpellCheckComponent is to hook it into the request handler that
- handles your normal user queries so that a separate request is
- not needed to get suggestions.
-
- IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
- NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
-
- See http://wiki.apache.org/solr/SpellCheckComponent for details
- on the request parameters.
- -->
- <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <str name="df">text</str>
- <!-- Solr will use suggestions from both the 'default' spellchecker
- and from the 'wordbreak' spellchecker and combine them.
- collations (re-written queries) can include a combination of
- corrections from both spellcheckers -->
- <str name="spellcheck.dictionary">default</str>
- <str name="spellcheck.dictionary">wordbreak</str>
- <str name="spellcheck">on</str>
- <str name="spellcheck.extendedResults">true</str>
- <str name="spellcheck.count">10</str>
- <str name="spellcheck.alternativeTermCount">5</str>
- <str name="spellcheck.maxResultsForSuggest">5</str>
- <str name="spellcheck.collate">true</str>
- <str name="spellcheck.collateExtendedResults">true</str>
- <str name="spellcheck.maxCollationTries">10</str>
- <str name="spellcheck.maxCollations">5</str>
- </lst>
- <arr name="last-components">
- <str>spellcheck</str>
- </arr>
- </requestHandler>
-
- <!-- Term Vector Component
-
- http://wiki.apache.org/solr/TermVectorComponent
- -->
- <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
-
- <!-- A request handler for demonstrating the term vector component
-
- This is purely as an example.
-
- In reality you will likely want to add the component to your
- already specified request handlers.
- -->
- <requestHandler name="/tvrh" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <str name="df">text</str>
- <bool name="tv">true</bool>
- </lst>
- <arr name="last-components">
- <str>tvComponent</str>
- </arr>
- </requestHandler>
-
- <!-- Clustering Component
-
- http://wiki.apache.org/solr/ClusteringComponent
-
- You'll need to set the solr.clustering.enabled system property
- when running solr to run with clustering enabled:
-
- java -Dsolr.clustering.enabled=true -jar start.jar
-
- -->
- <searchComponent name="clustering"
- enable="${solr.clustering.enabled:false}"
- class="solr.clustering.ClusteringComponent" >
- <!-- Declare an engine -->
- <lst name="engine">
- <!-- The name, only one can be named "default" -->
- <str name="name">default</str>
-
- <!-- Class name of Carrot2 clustering algorithm.
-
- Currently available algorithms are:
-
- * org.carrot2.clustering.lingo.LingoClusteringAlgorithm
- * org.carrot2.clustering.stc.STCClusteringAlgorithm
- * org.carrot2.clustering.kmeans.BisectingKMeansClusteringAlgorithm
-
- See http://project.carrot2.org/algorithms.html for the
- algorithm's characteristics.
- -->
- <str name="carrot.algorithm">org.carrot2.clustering.lingo.LingoClusteringAlgorithm</str>
-
- <!-- Overriding values for Carrot2 default algorithm attributes.
-
- For a description of all available attributes, see:
- http://download.carrot2.org/stable/manual/#chapter.components.
- Use attribute key as name attribute of str elements
- below. These can be further overridden for individual
- requests by specifying attribute key as request parameter
- name and attribute value as parameter value.
- -->
- <str name="LingoClusteringAlgorithm.desiredClusterCountBase">20</str>
-
- <!-- Location of Carrot2 lexical resources.
-
- A directory from which to load Carrot2-specific stop words
- and stop labels. Absolute or relative to Solr config directory.
- If a specific resource (e.g. stopwords.en) is present in the
- specified dir, it will completely override the corresponding
- default one that ships with Carrot2.
-
- For an overview of Carrot2 lexical resources, see:
- http://download.carrot2.org/head/manual/#chapter.lexical-resources
- -->
- <str name="carrot.lexicalResourcesDir">clustering/carrot2</str>
-
- <!-- The language to assume for the documents.
-
- For a list of allowed values, see:
- http://download.carrot2.org/stable/manual/#section.attribute.lingo.MultilingualClustering.defaultLanguage
- -->
- <str name="MultilingualClustering.defaultLanguage">ENGLISH</str>
- </lst>
- <lst name="engine">
- <str name="name">stc</str>
- <str name="carrot.algorithm">org.carrot2.clustering.stc.STCClusteringAlgorithm</str>
- </lst>
- </searchComponent>
-
- <!-- A request handler for demonstrating the clustering component
-
- This is purely as an example.
-
- In reality you will likely want to add the component to your
- already specified request handlers.
- -->
- <requestHandler name="/clustering"
- startup="lazy"
- enable="${solr.clustering.enabled:false}"
- class="solr.SearchHandler">
- <lst name="defaults">
- <bool name="clustering">true</bool>
- <str name="clustering.engine">default</str>
- <bool name="clustering.results">true</bool>
- <!-- The title field -->
- <str name="carrot.title">name</str>
- <str name="carrot.url">id</str>
- <!-- The field to cluster on -->
- <str name="carrot.snippet">features</str>
- <!-- produce summaries -->
- <bool name="carrot.produceSummary">true</bool>
- <!-- the maximum number of labels per cluster -->
- <!--<int name="carrot.numDescriptions">5</int>-->
- <!-- produce sub clusters -->
- <bool name="carrot.outputSubClusters">false</bool>
-
- <str name="defType">edismax</str>
- <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="q.alt">*:*</str>
- <str name="rows">10</str>
- <str name="fl">*,score</str>
- </lst>
- <arr name="last-components">
- <str>clustering</str>
- </arr>
- </requestHandler>
-
- <!-- Terms Component
-
- http://wiki.apache.org/solr/TermsComponent
-
- A component to return terms and document frequency of those
- terms
- -->
- <searchComponent name="terms" class="solr.TermsComponent"/>
-
- <!-- A request handler for demonstrating the terms component -->
- <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <bool name="terms">true</bool>
- <bool name="distrib">false</bool>
- </lst>
- <arr name="components">
- <str>terms</str>
- </arr>
- </requestHandler>
-
-
- <!-- Query Elevation Component
-
- http://wiki.apache.org/solr/QueryElevationComponent
-
- a search component that enables you to configure the top
- results for a given query regardless of the normal lucene
- scoring.
- -->
- <searchComponent name="elevator" class="solr.QueryElevationComponent" >
- <!-- pick a fieldType to analyze queries -->
- <str name="queryFieldType">string</str>
- <str name="config-file">elevate.xml</str>
- </searchComponent>
-
- <!-- A request handler for demonstrating the elevator component -->
- <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <str name="df">text</str>
- </lst>
- <arr name="last-components">
- <str>elevator</str>
- </arr>
- </requestHandler>
-
- <!-- Highlighting Component
-
- http://wiki.apache.org/solr/HighlightingParameters
- -->
- <searchComponent class="solr.HighlightComponent" name="highlight">
- <highlighting>
- <!-- Configure the standard fragmenter -->
- <!-- This could most likely be commented out in the "default" case -->
- <fragmenter name="gap"
- default="true"
- class="solr.highlight.GapFragmenter">
- <lst name="defaults">
- <int name="hl.fragsize">100</int>
- </lst>
- </fragmenter>
-
- <!-- A regular-expression-based fragmenter
- (for sentence extraction)
- -->
- <fragmenter name="regex"
- class="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"
- default="true"
- class="solr.highlight.HtmlFormatter">
- <lst name="defaults">
- <str name="hl.simple.pre"><![CDATA[<em>]]></str>
- <str name="hl.simple.post"><![CDATA[</em>]]></str>
- </lst>
- </formatter>
-
- <!-- Configure the standard encoder -->
- <encoder name="html"
- class="solr.highlight.HtmlEncoder" />
-
- <!-- Configure the standard fragListBuilder -->
- <fragListBuilder name="simple"
- class="solr.highlight.SimpleFragListBuilder"/>
-
- <!-- Configure the single fragListBuilder -->
- <fragListBuilder name="single"
- class="solr.highlight.SingleFragListBuilder"/>
-
- <!-- Configure the weighted fragListBuilder -->
- <fragListBuilder name="weighted"
- default="true"
- class="solr.highlight.WeightedFragListBuilder"/>
-
- <!-- default tag FragmentsBuilder -->
- <fragmentsBuilder name="default"
- default="true"
- class="solr.highlight.ScoreOrderFragmentsBuilder">
- <!--
- <lst name="defaults">
- <str name="hl.multiValuedSeparatorChar">/</str>
- </lst>
- -->
- </fragmentsBuilder>
-
- <!-- multi-colored tag FragmentsBuilder -->
- <fragmentsBuilder name="colored"
- class="solr.highlight.ScoreOrderFragmentsBuilder">
- <lst name="defaults">
- <str name="hl.tag.pre"><![CDATA[
- <b style="background:yellow">,<b style="background:lawgreen">,
- <b style="background:aquamarine">,<b style="background:magenta">,
- <b style="background:palegreen">,<b style="background:coral">,
- <b style="background:wheat">,<b style="background:khaki">,
- <b style="background:lime">,<b style="background:deepskyblue">]]></str>
- <str name="hl.tag.post"><![CDATA[</b>]]></str>
- </lst>
- </fragmentsBuilder>
-
- <boundaryScanner name="default"
- default="true"
- class="solr.highlight.SimpleBoundaryScanner">
- <lst name="defaults">
- <str name="hl.bs.maxScan">10</str>
- <str name="hl.bs.chars">.,!? 	 </str>
- </lst>
- </boundaryScanner>
-
- <boundaryScanner name="breakIterator"
- class="solr.highlight.BreakIteratorBoundaryScanner">
- <lst name="defaults">
- <!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
- <str name="hl.bs.type">WORD</str>
- <!-- language and country are used when constructing Locale object. -->
- <!-- And the Locale object will be used when getting instance of BreakIterator -->
- <str name="hl.bs.language">en</str>
- <str name="hl.bs.country">US</str>
- </lst>
- </boundaryScanner>
- </highlighting>
- </searchComponent>
-
- <!-- Update Processors
-
- Chains of Update Processor Factories for dealing with Update
- Requests can be declared, and then used by name in Update
- Request Processors
-
- http://wiki.apache.org/solr/UpdateRequestProcessor
-
- -->
- <!-- Deduplication
-
- An example dedup update processor that creates the "id" field
- on the fly based on the hash code of some other fields. This
- example has overwriteDupes set to false since we are using the
- id field as the signatureField and Solr will maintain
- uniqueness based on that anyway.
-
- -->
- <!--
- <updateRequestProcessorChain name="dedupe">
- <processor class="solr.processor.SignatureUpdateProcessorFactory">
- <bool name="enabled">true</bool>
- <str name="signatureField">id</str>
- <bool name="overwriteDupes">false</bool>
- <str name="fields">name,features,cat</str>
- <str name="signatureClass">solr.processor.Lookup3Signature</str>
- </processor>
- <processor class="solr.LogUpdateProcessorFactory" />
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Language identification
-
- This example update chain identifies the language of the incoming
- documents using the langid contrib. The detected language is
- written to field language_s. No field name mapping is done.
- The fields used for detection are text, title, subject and description,
- making this example suitable for detecting languages form full-text
- rich documents injected via ExtractingRequestHandler.
- See more about langId at http://wiki.apache.org/solr/LanguageDetection
- -->
- <!--
- <updateRequestProcessorChain name="langid">
- <processor class="org.apache.solr.update.processor.TikaLanguageIdentifierUpdateProcessorFactory">
- <str name="langid.fl">text,title,subject,description</str>
- <str name="langid.langField">language_s</str>
- <str name="langid.fallback">en</str>
- </processor>
- <processor class="solr.LogUpdateProcessorFactory" />
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Script update processor
-
- This example hooks in an update processor implemented using JavaScript.
-
- See more about the script update processor at http://wiki.apache.org/solr/ScriptUpdateProcessor
- -->
- <!--
- <updateRequestProcessorChain name="script">
- <processor class="solr.StatelessScriptUpdateProcessorFactory">
- <str name="script">update-script.js</str>
- <lst name="params">
- <str name="config_param">example config parameter</str>
- </lst>
- </processor>
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Response Writers
-
- http://wiki.apache.org/solr/QueryResponseWriter
-
- Request 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.
- -->
- <!-- The following response writers are implicitly configured unless
- overridden...
- -->
- <!--
- <queryResponseWriter name="xml"
- default="true"
- class="solr.XMLResponseWriter" />
- <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
- <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
- <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
- <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
- <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
- <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
- <queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/>
- -->
-
- <queryResponseWriter name="json" class="solr.JSONResponseWriter">
- <!-- For the purposes of the tutorial, JSON responses are written as
- plain text so that they are easy to read in *any* browser.
- If you expect a MIME type of "application/json" just remove this override.
- -->
- <str name="content-type">text/plain; charset=UTF-8</str>
- </queryResponseWriter>
-
- <!--
- Custom response writers can be declared as needed...
- -->
- <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" startup="lazy"/>
-
-
- <!-- 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="solr.XSLTResponseWriter">
- <int name="xsltCacheLifetimeSeconds">5</int>
- </queryResponseWriter>
-
- <!-- Query Parsers
-
- https://cwiki.apache.org/confluence/display/solr/Query+Syntax+and+Parsing
-
- Multiple QParserPlugins can be registered by name, and then
- used in either the "defType" param for the QueryComponent (used
- by SearchHandler) or in LocalParams
- -->
- <!-- example of registering a query parser -->
- <!--
- <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
- -->
-
- <!-- Function Parsers
-
- http://wiki.apache.org/solr/FunctionQuery
-
- Multiple ValueSourceParsers can be registered by name, and then
- used as function names when using the "func" QParser.
- -->
- <!-- example of registering a custom function parser -->
- <!--
- <valueSourceParser name="myfunc"
- class="com.mycompany.MyValueSourceParser" />
- -->
-
-
- <!-- Document Transformers
- http://wiki.apache.org/solr/DocTransformers
- -->
- <!--
- Could be something like:
- <transformer name="db" class="com.mycompany.LoadFromDatabaseTransformer" >
- <int name="connection">jdbc://....</int>
- </transformer>
-
- To add a constant value to all docs, use:
- <transformer name="mytrans2" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
- <int name="value">5</int>
- </transformer>
-
- If you want the user to still be able to change it with _value:something_ use this:
- <transformer name="mytrans3" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
- <double name="defaultValue">5</double>
- </transformer>
-
- If you are using the QueryElevationComponent, you may wish to mark documents that get boosted. The
- EditorialMarkerFactory will do exactly that:
- <transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
- -->
-
-</config>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/53e5f34f/solr/contrib/morphlines-core/src/test-files/test-documents/NullHeader.docx
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/test-documents/NullHeader.docx b/solr/contrib/morphlines-core/src/test-files/test-documents/NullHeader.docx
deleted file mode 100644
index cc62b8d..0000000
Binary files a/solr/contrib/morphlines-core/src/test-files/test-documents/NullHeader.docx and /dev/null differ
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/53e5f34f/solr/contrib/morphlines-core/src/test-files/test-documents/boilerplate.html
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/test-documents/boilerplate.html b/solr/contrib/morphlines-core/src/test-files/test-documents/boilerplate.html
deleted file mode 100644
index 615f84e..0000000
--- a/solr/contrib/morphlines-core/src/test-files/test-documents/boilerplate.html
+++ /dev/null
@@ -1,58 +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.
--->
-
-<?xml version="1.0" encoding="utf-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
- "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
-<head>
- <meta http-equiv="content-type" content="text/html; charset=utf-8" />
- <title>Title</title>
-</head>
-<body>
-
-<table>
- <tr>
- <td>
- <table>
- <tr>
- <td ><a href="Main.php">boilerplate</a></td>
- <td ><a href="Main.php">text</a></td>
- </tr>
- </table>
- </td>
- </tr>
-</table>
-
-<p>This is the real meat of the page,
-and represents the text we want.
-It has lots of juicy content.
-
-We assume that it won't get filtered out.
-And that all of the lines will be in the
-output.
-</p>
-
-<p>
-Here's another paragraph of text.
-This is the end of the text.
-</p>
-
-<p><a href="Footer.html">footer</a></p>
-
-</body>
-</html>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/53e5f34f/solr/contrib/morphlines-core/src/test-files/test-documents/cars.csv
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/test-documents/cars.csv b/solr/contrib/morphlines-core/src/test-files/test-documents/cars.csv
deleted file mode 100644
index 8f1f9e1..0000000
--- a/solr/contrib/morphlines-core/src/test-files/test-documents/cars.csv
+++ /dev/null
@@ -1,6 +0,0 @@
-Age,Color,Extras,Type,Used
-2,blue,GPS,"Gas, with electric",""
-10,green,"Labeled ""Vintage, 1913""",,yes
-100,red,"Labeled ""Vintage 1913""",yes
-5,orange,none,"This is a
-multi, line text",no
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/53e5f34f/solr/contrib/morphlines-core/src/test-files/test-documents/cars.csv.gz
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/test-documents/cars.csv.gz b/solr/contrib/morphlines-core/src/test-files/test-documents/cars.csv.gz
deleted file mode 100644
index ee2a951..0000000
Binary files a/solr/contrib/morphlines-core/src/test-files/test-documents/cars.csv.gz and /dev/null differ
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/53e5f34f/solr/contrib/morphlines-core/src/test-files/test-documents/cars.tar.gz
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/test-documents/cars.tar.gz b/solr/contrib/morphlines-core/src/test-files/test-documents/cars.tar.gz
deleted file mode 100644
index 5ca3cf1..0000000
Binary files a/solr/contrib/morphlines-core/src/test-files/test-documents/cars.tar.gz and /dev/null differ
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/53e5f34f/solr/contrib/morphlines-core/src/test-files/test-documents/complex.mbox
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/test-documents/complex.mbox b/solr/contrib/morphlines-core/src/test-files/test-documents/complex.mbox
deleted file mode 100644
index 27f7017..0000000
--- a/solr/contrib/morphlines-core/src/test-files/test-documents/complex.mbox
+++ /dev/null
@@ -1,291 +0,0 @@
-From core-user-return-14700-apmail-hadoop-core-user-archive=hadoop.apache.org@hadoop.apache.org Mon Jun 01 04:28:28 2009
-Return-Path: <co...@hadoop.apache.org>
-Delivered-To: apmail-hadoop-core-user-archive@www.apache.org
-Received: (qmail 19921 invoked from network); 1 Jun 2009 04:28:28 -0000
-Received: from hermes.apache.org (HELO mail.apache.org) (140.211.11.3)
- by minotaur.apache.org with SMTP; 1 Jun 2009 04:28:28 -0000
-Received: (qmail 84995 invoked by uid 500); 1 Jun 2009 04:28:38 -0000
-Delivered-To: apmail-hadoop-core-user-archive@hadoop.apache.org
-Received: (qmail 84895 invoked by uid 500); 1 Jun 2009 04:28:38 -0000
-Mailing-List: contact core-user-help@hadoop.apache.org; run by ezmlm
-Precedence: bulk
-List-Help: <ma...@hadoop.apache.org>
-List-Unsubscribe: <ma...@hadoop.apache.org>
-List-Post: <ma...@hadoop.apache.org>
-List-Id: <core-user.hadoop.apache.org>
-Reply-To: core-user@hadoop.apache.org
-Delivered-To: mailing list core-user@hadoop.apache.org
-Received: (qmail 84885 invoked by uid 99); 1 Jun 2009 04:28:38 -0000
-Received: from athena.apache.org (HELO athena.apache.org) (140.211.11.136)
- by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 01 Jun 2009 04:28:38 +0000
-X-ASF-Spam-Status: No, hits=1.2 required=10.0
- tests=SPF_NEUTRAL
-X-Spam-Check-By: apache.org
-Received-SPF: neutral (athena.apache.org: local policy)
-Received: from [69.147.107.21] (HELO mrout2-b.corp.re1.wahoo.com) (69.147.107.21)
- by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 01 Jun 2009 04:28:26 +0000
-Received: from SNV-EXPF01.ds.corp.wahoo.com (snv-expf01.ds.corp.wahoo.com [207.126.227.250])
- by mrout2-b.corp.re1.wahoo.com (8.13.8/8.13.8/y.out) with ESMTP id n514QYA6099963
- for <co...@hadoop.apache.org>; Sun, 31 May 2009 21:26:35 -0700 (PDT)
-DomainKey-Signature: a=rsa-sha1; s=serpent; d=wahoo-inc.com; c=nofws; q=dns;
- h=received:user-agent:date:subject:from:to:message-id:
- thread-topic:thread-index:in-reply-to:mime-version:content-type:
- content-transfer-encoding:x-originalarrivaltime;
- b=YVtSNdgjeeSBS1yY3XDolul49i+HrgNG7QszMo9LzGnrwejjgsl5+iUM6EiQgEpV
-Received: from SNV-EXVS08.ds.corp.wahoo.com ([207.126.227.9]) by SNV-EXPF01.ds.corp.wahoo.com with Microsoft SMTPSVC(6.0.3790.3959);
- Sun, 31 May 2009 21:26:34 -0700
-Received: from 10.66.92.213 ([10.66.92.213]) by SNV-EXVS08.ds.corp.wahoo.com ([207.126.227.58]) with Microsoft Exchange Server HTTP-DAV ;
- Mon, 1 Jun 2009 04:26:33 +0000
-User-Agent: Microsoft-Entourage/12.17.0.090302
-Date: Mon, 01 Jun 2009 09:56:31 +0530
-Subject: Re: question about when shuffle/sort start working
-From: Sam Judgement <Sa...@wahoo-inc.com>
-To: <co...@hadoop.apache.org>
-Message-ID: <C6...@wahoo-inc.com>
-Thread-Topic: question about when shuffle/sort start working
-Thread-Index: AcnicSNoBw19cMU8UEaXwAdZ1YYhuw==
-In-Reply-To: <44...@web111005.mail.gq1.wahoo.com>
-Mime-version: 1.0
-Content-type: text/plain;
- charset="US-ASCII"
-Content-transfer-encoding: 7bit
-X-OriginalArrivalTime: 01 Jun 2009 04:26:34.0501 (UTC) FILETIME=[257EAB50:01C9E271]
-X-Virus-Checked: Checked by ClamAV on apache.org
-
-When a Mapper completes, MapCompletionEvents are generated. Reducers try to
-fetch map outputs for a given map only on the receipt of such events.
-
-Sam
-
-
-On 5/30/09 10:00 AM, "Jianmin Foo" <ji...@wahoo.com> wrote:
-
-> Hi,
-> I am being confused by the protocol between mapper and reducer. When mapper
-> emitting the (key,value) pair done, is there any signal the mapper send out to
-> hadoop framework in protocol to indicate that map is done and the shuffle/sort
-> can begin for reducer? If there is no this signal in protocol, when the
-> framework begin the shuffle/sort?
->
-> Thanks,
-> Jianmin
->
->
->
->
-
-
-From core-user-return-14701-apmail-hadoop-core-user-archive=hadoop.apache.org@hadoop.apache.org Mon Jun 01 05:31:14 2009
-Return-Path: <co...@hadoop.apache.org>
-Delivered-To: apmail-hadoop-core-user-archive@www.apache.org
-Received: (qmail 38243 invoked from network); 1 Jun 2009 05:31:14 -0000
-Received: from hermes.apache.org (HELO mail.apache.org) (140.211.11.3)
- by minotaur.apache.org with SMTP; 1 Jun 2009 05:31:14 -0000
-Received: (qmail 15621 invoked by uid 500); 1 Jun 2009 05:31:24 -0000
-Delivered-To: apmail-hadoop-core-user-archive@hadoop.apache.org
-Received: (qmail 15557 invoked by uid 500); 1 Jun 2009 05:31:24 -0000
-Mailing-List: contact core-user-help@hadoop.apache.org; run by ezmlm
-Precedence: bulk
-List-Help: <ma...@hadoop.apache.org>
-List-Unsubscribe: <ma...@hadoop.apache.org>
-List-Post: <ma...@hadoop.apache.org>
-List-Id: <core-user.hadoop.apache.org>
-Reply-To: core-user@hadoop.apache.org
-Delivered-To: mailing list core-user@hadoop.apache.org
-Received: (qmail 15547 invoked by uid 99); 1 Jun 2009 05:31:24 -0000
-Received: from nike.apache.org (HELO nike.apache.org) (192.87.106.230)
- by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 01 Jun 2009 05:31:24 +0000
-X-ASF-Spam-Status: No, hits=2.2 required=10.0
- tests=HTML_MESSAGE,SPF_PASS
-X-Spam-Check-By: apache.org
-Received-SPF: pass (nike.apache.org: local policy)
-Received: from [68.142.237.94] (HELO n9.bullet.re3.wahoo.com) (68.142.237.94)
- by apache.org (qpsmtpd/0.29) with SMTP; Mon, 01 Jun 2009 05:31:11 +0000
-Received: from [68.142.237.88] by n9.bullet.re3.wahoo.com with NNFMP; 01 Jun 2009 05:30:50 -0000
-Received: from [67.195.9.82] by t4.bullet.re3.wahoo.com with NNFMP; 01 Jun 2009 05:30:49 -0000
-Received: from [67.195.9.99] by t2.bullet.mail.gq1.wahoo.com with NNFMP; 01 Jun 2009 05:30:49 -0000
-Received: from [127.0.0.1] by omp103.mail.gq1.wahoo.com with NNFMP; 01 Jun 2009 05:28:01 -0000
-X-wahoo-Newman-Property: ymail-3
-X-wahoo-Newman-Id: 796121.97519.bm@omp103.mail.gq1.wahoo.com
-Received: (qmail 35264 invoked by uid 60001); 1 Jun 2009 05:30:49 -0000
-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=wahoo.com; s=s1024; t=1243834249; bh=R8qzdi/IbLyO8UwpnaujDpT9E+6bJ7nkmZN2803EmRk=; h=Message-ID:X-YMail-OSG:Received:X-Mailer:References:Date:From:Subject:To:In-Reply-To:MIME-Version:Content-Type; b=vq4c6RIDbkuLPYd8mirusIXf6DqTb/IeT55In7W00Y5Sxx1ZiXBb78yE9+TDfXJ0elsEZvqv4ocyvolGE0eGtyYeJA0mZikpRNu6pidxPNpCplOcLHBRz7YQ7iERwv3TagRlWy2Xd3oD9ZeV0A05P7WUOiNNX1PUUJD1IVdrEZo=
-DomainKey-Signature:a=rsa-sha1; q=dns; c=nofws;
- s=s1024; d=wahoo.com;
- h=Message-ID:X-YMail-OSG:Received:X-Mailer:References:Date:From:Subject:To:In-Reply-To:MIME-Version:Content-Type;
- b=6HXZV98ON5vBwmE/xS8stVD0D2F4dkMY7a0suX5KVTb736JdR8G59mqBq/dWcpbFTLiCLtxi18LMb/dU1RKRGOEdn3l3j/jKXhBrhIgfg3qtNskPedXDKBvn7JGXiSkqpA/tUtPjvc0Uuk8/LaA01SQTz40Engg7nD8/EJdIAhA=;
-Message-ID: <59...@web111010.mail.gq1.wahoo.com>
-X-YMail-OSG: KzhhrJYVM1m.MCS6vRpRP2ZZO2PrfnbngosELDCIa91ZqvhJph4RdmzfUW0jw9W04RCSch1K730bPohwNpNBIk2QR_zt4_mfbhfq7YEPkSoz9LSXG90P9vIo5Fc8qyZN0U6vA9gtdyGQTpN5ahvillUH9nAF0TMWv2SvZJLjPlQ0Z0p8oK8ltBwGTgLrM8Jtdn9D29yoRyi3_EpVOfdD9OP.EK50Vr1XwSUYMbnpZ0WGHMwd.Yig7A6Elwadm3YVbfOdx2mfrG.jQsUAxQjRBNvbrOM57.FaE11kHTe9aoBWSeihNg--
-Received: from [216.145.54.7] by web111010.mail.gq1.wahoo.com via HTTP; Sun, 31 May 2009 22:30:49 PDT
-X-Mailer: wahooMailRC/1277.43 wahooMailWebService/0.7.289.10
-References: <C6...@wahoo-inc.com>
-Date: Sun, 31 May 2009 22:30:49 -0700 (PDT)
-From: Jianmin Foo <ji...@wahoo.com>
-Subject: Re: question about when shuffle/sort start working
-To: core-user@hadoop.apache.org
-In-Reply-To: <C6...@wahoo-inc.com>
-MIME-Version: 1.0
-Content-Type: multipart/alternative; boundary="0-1193839393-1243834249=:35091"
-X-Virus-Checked: Checked by ClamAV on apache.org
-
---0-1193839393-1243834249=:35091
-Content-Type: text/plain; charset=us-ascii
-
-Thanks a lot for your explanation, Sam.
-
-So is this event generated by hadoop framework? Is there any API in mapper to fire this event? Actually, I am thinking to implement a mapper that will emit some <key, value> pairs, then fire this event to let the reducer works, the same mapper task then emit some other <key, value> pairs and repeat. Do you think is this logic feasible by current API?
-
-Thanks,
-Jianmin
-
-
-
-
-
-________________________________
-From: Sam Judgement <Sa...@wahoo-inc.com>
-To: core-user@hadoop.apache.org
-Sent: Monday, June 1, 2009 12:26:31 PM
-Subject: Re: question about when shuffle/sort start working
-
-When a Mapper completes, MapCompletionEvents are generated. Reducers try to
-fetch map outputs for a given map only on the receipt of such events.
-
-Sam
-
-
-On 5/30/09 10:00 AM, "Jianmin Foo" <ji...@wahoo.com> wrote:
-
-> Hi,
-> I am being confused by the protocol between mapper and reducer. When mapper
-> emitting the (key,value) pair done, is there any signal the mapper send out to
-> hadoop framework in protocol to indicate that map is done and the shuffle/sort
-> can begin for reducer? If there is no this signal in protocol, when the
-> framework begin the shuffle/sort?
->
-> Thanks,
-> Jianmin
->
->
->
->
-
-
-
---0-1193839393-1243834249=:35091--
-
-
-From core-user-return-14702-apmail-hadoop-core-user-archive=hadoop.apache.org@hadoop.apache.org Mon Jun 01 06:04:30 2009
-Return-Path: <co...@hadoop.apache.org>
-Delivered-To: apmail-hadoop-core-user-archive@www.apache.org
-Received: (qmail 53387 invoked from network); 1 Jun 2009 06:04:29 -0000
-Received: from hermes.apache.org (HELO mail.apache.org) (140.211.11.3)
- by minotaur.apache.org with SMTP; 1 Jun 2009 06:04:29 -0000
-Received: (qmail 39066 invoked by uid 500); 1 Jun 2009 06:04:39 -0000
-Delivered-To: apmail-hadoop-core-user-archive@hadoop.apache.org
-Received: (qmail 38970 invoked by uid 500); 1 Jun 2009 06:04:39 -0000
-Mailing-List: contact core-user-help@hadoop.apache.org; run by ezmlm
-Precedence: bulk
-List-Help: <ma...@hadoop.apache.org>
-List-Unsubscribe: <ma...@hadoop.apache.org>
-List-Post: <ma...@hadoop.apache.org>
-List-Id: <core-user.hadoop.apache.org>
-Reply-To: core-user@hadoop.apache.org
-Delivered-To: mailing list core-user@hadoop.apache.org
-Received: (qmail 38955 invoked by uid 99); 1 Jun 2009 06:04:39 -0000
-Received: from athena.apache.org (HELO athena.apache.org) (140.211.11.136)
- by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 01 Jun 2009 06:04:39 +0000
-X-ASF-Spam-Status: No, hits=1.2 required=10.0
- tests=SPF_NEUTRAL
-X-Spam-Check-By: apache.org
-Received-SPF: neutral (athena.apache.org: local policy)
-Received: from [216.145.54.172] (HELO mrout2.wahoo.com) (216.145.54.172)
- by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 01 Jun 2009 06:04:28 +0000
-Received: from SNV-EXBH01.ds.corp.wahoo.com (snv-exbh01.ds.corp.wahoo.com [207.126.227.249])
- by mrout2.wahoo.com (8.13.6/8.13.6/y.out) with ESMTP id n5163FGq038852
- for <co...@hadoop.apache.org>; Sun, 31 May 2009 23:03:15 -0700 (PDT)
-DomainKey-Signature: a=rsa-sha1; s=serpent; d=wahoo-inc.com; c=nofws; q=dns;
- h=received:user-agent:date:subject:from:to:message-id:
- thread-topic:thread-index:in-reply-to:mime-version:content-type:
- content-transfer-encoding:x-originalarrivaltime;
- b=rChE4SCnwtWaZpjhovkiXDKfDiVNdRRvsadSGG9S9bgvOexn/9/5JjEQx1pOR7Nb
-Received: from SNV-EXVS08.ds.corp.wahoo.com ([207.126.227.9]) by SNV-EXBH01.ds.corp.wahoo.com with Microsoft SMTPSVC(6.0.3790.3959);
- Sun, 31 May 2009 23:03:15 -0700
-Received: from 10.66.92.213 ([10.66.92.213]) by SNV-EXVS08.ds.corp.wahoo.com ([207.126.227.58]) with Microsoft Exchange Server HTTP-DAV ;
- Mon, 1 Jun 2009 06:03:15 +0000
-User-Agent: Microsoft-Entourage/12.17.0.090302
-Date: Mon, 01 Jun 2009 11:33:13 +0530
-Subject: Re: question about when shuffle/sort start working
-From: Sam Judgement <Sa...@wahoo-inc.com>
-To: <co...@hadoop.apache.org>
-Message-ID: <C6...@wahoo-inc.com>
-Thread-Topic: question about when shuffle/sort start working
-Thread-Index: AcnifqWrLG6N7GAk7kqy9QalVWfegQ==
-In-Reply-To: <59...@web111010.mail.gq1.wahoo.com>
-Mime-version: 1.0
-Content-type: text/plain;
- charset="US-ASCII"
-Content-transfer-encoding: 7bit
-X-OriginalArrivalTime: 01 Jun 2009 06:03:15.0462 (UTC) FILETIME=[A7231260:01C9E27E]
-X-Virus-Checked: Checked by ClamAV on apache.org
-
-
-No you cannot raise this event yourself, this event is generated internally
-by the framework.
-
-I am guessing that what you probably want is to have a chain of MapReduce
-Jobs where the output of one is automatically fed as input to another. You
-can look at these classes: JobControl and ChainMapper/ChainReducer.
-
-Sam
-
-On 6/1/09 11:00 AM, "Jianmin Foo" <ji...@wahoo.com> wrote:
-
-> Thanks a lot for your explanation, Sam.
->
-> So is this event generated by hadoop framework? Is there any API in mapper to
-> fire this event? Actually, I am thinking to implement a mapper that will emit
-> some <key, value> pairs, then fire this event to let the reducer works, the
-> same mapper task then emit some other <key, value> pairs and repeat. Do you
-> think is this logic feasible by current API?
->
-> Thanks,
-> Jianmin
->
->
->
->
->
-> ________________________________
-> From: Sam Judgement <Sa...@wahoo-inc.com>
-> To: core-user@hadoop.apache.org
-> Sent: Monday, June 1, 2009 12:26:31 PM
-> Subject: Re: question about when shuffle/sort start working
->
-> When a Mapper completes, MapCompletionEvents are generated. Reducers try to
-> fetch map outputs for a given map only on the receipt of such events.
->
-> Sam
->
->
-> On 5/30/09 10:00 AM, "Jianmin Foo" <ji...@wahoo.com> wrote:
->
->> Hi,
->> I am being confused by the protocol between mapper and reducer. When mapper
->> emitting the (key,value) pair done, is there any signal the mapper send out
->> to
->> hadoop framework in protocol to indicate that map is done and the
->> shuffle/sort
->> can begin for reducer? If there is no this signal in protocol, when the
->> framework begin the shuffle/sort?
->>
->> Thanks,
->> Jianmin
->>
->>
->>
->>
->
->
->
-
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/53e5f34f/solr/contrib/morphlines-core/src/test-files/test-documents/email.eml
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/test-documents/email.eml b/solr/contrib/morphlines-core/src/test-files/test-documents/email.eml
deleted file mode 100644
index d45f430..0000000
--- a/solr/contrib/morphlines-core/src/test-files/test-documents/email.eml
+++ /dev/null
@@ -1,40 +0,0 @@
-MIME-Version: 1.0
-Received: by 10.216.199.5 with HTTP; Wed, 27 Nov 2013 12:01:23 -0800
-(PST)
-Date: Wed, 27 Nov 2013 13:01:23 -0700
-Delivered-To: foo@cloudera.com
-Message-ID:
-<CA...@mail.gmail.com>
-Subject: Test EML
-From: Patrick Foo <fo...@cloudera.com>
-To: Patrick Foo <fo...@cloudera.com>
-Content-Type: multipart/alternative;
-boundary=001a11c3815cb55dda04ec2e0f3b
-
---001a11c3815cb55dda04ec2e0f3b
-Content-Type: text/plain; charset=ISO-8859-1
-
-This is a test
-
---
-Patrick Foo
-Customer Operations Engineer
-
-<http://www.cloudera.com>
-
---001a11c3815cb55dda04ec2e0f3b
-Content-Type: text/html; charset=ISO-8859-1
-Content-Transfer-Encoding: quoted-printable
-
-<div dir=3D"ltr">This is a test<br clear=3D"all"><div><br></div>--
-<br><div=
- dir=3D"ltr">Patrick Foo<div>Customer Operations
-Engineer</div><div><br>=
-</div><div><a href=3D"http://www.cloudera.com" target=3D"_blank"><img
-src=
-=3D"http://files.cloudera.com.s3.amazonaws.com/New%20Branding/cloudera-smal=
-l.png"></a><br>
-</div></div>
-</div>
-
---001a11c3815cb55dda04ec2e0f3b--
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/53e5f34f/solr/contrib/morphlines-core/src/test-files/test-documents/rsstest.rss
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/test-documents/rsstest.rss b/solr/contrib/morphlines-core/src/test-files/test-documents/rsstest.rss
deleted file mode 100644
index 758f6a1..0000000
--- a/solr/contrib/morphlines-core/src/test-files/test-documents/rsstest.rss
+++ /dev/null
@@ -1,36 +0,0 @@
-<?xml version="1.0" encoding="ISO-8859-1" ?>
-<!--
- 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.
--->
-<rss version="0.91">
- <channel>
- <title>TestChannel</title>
- <link>http://test.channel.com/</link>
- <description>Sample RSS File for Junit test</description>
- <language>en-us</language>
-
- <item>
- <title>Home Page of Chris Mattmann</title>
- <link>http://www-scf.usc.edu/~mattmann/</link>
- <description>Chris Mattmann's home page</description>
- </item>
- <item>
- <title>Awesome Open Source Search Engine</title>
- <link>http://www.nutch.org/</link>
- <description>Yup, that's what it is</description>
- </item>
- </channel>
-</rss>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/53e5f34f/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120521-100919.avro
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120521-100919.avro b/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120521-100919.avro
deleted file mode 100644
index 36f01a2..0000000
Binary files a/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120521-100919.avro and /dev/null differ
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/53e5f34f/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120906-141433
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120906-141433 b/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120906-141433
deleted file mode 100644
index e633a1f..0000000
--- a/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120906-141433
+++ /dev/null
@@ -1,4 +0,0 @@
-1000
-{"text":"sample tweet one","retweet_count":0,"in_reply_to_user_id":null,"retweeted":false,"truncated":false,"source":"href=\"http:\/\/sample.com\"","id_str":"1234567891","entities":{"user_mentions":[],"hashtags":[],"urls":[]},"in_reply_to_status_id":null,"place":null,"in_reply_to_status_id_str":null,"coordinates":null,"created_at":"Wed Sep 05 01:01:01 +0000 1985","in_reply_to_screen_name":null,"favorited":false,"in_reply_to_user_id_str":null,"user":{"default_profile_image":false,"friends_count":111,"profile_background_color":"3C0C29","location":"Palo Alto","is_translator":false,"profile_background_tile":true,"favourites_count":11,"verified":false,"profile_sidebar_fill_color":"efefef","follow_request_sent":null,"contributors_enabled":false,"description":"desc1","profile_sidebar_border_color":"eeeeee","profile_image_url_https":"https:\/\/si0.twimg.com\/profile_images\/1\/normal.jpg","id_str":"1111111","listed_count":1,"lang":"en","screen_name":"fake_user1","show_all_inline_media":fals
e,"profile_use_background_image":true,"profile_image_url":"http:\/\/a0.twimg.com\/profile_images\/1111111\/normal.jpg","default_profile":false,"statuses_count":11111,"created_at":"Thu Apr 07 11:04:54 +0000 1985","profile_text_color":"333333","followers_count":111,"protected":false,"following":null,"notifications":null,"profile_background_image_url":"http:\/\/a0.twimg.com\/images\/themes\/theme1\/bg.gif","time_zone":null,"url":null,"name":"name1","geo_enabled":false,"profile_link_color":"009999","id":1111112,"profile_background_image_url_https":"https:\/\/si0.twimg.com\/images\/themes\/theme1\/bg.gif","utc_offset":null},"id":11111112,"contributors":null,"geo":null}
-2000
-{"text":"sample tweet two","retweet_count":0,"in_reply_to_user_id":null,"retweeted":false,"truncated":false,"source":"href=\"http:\/\/sample.com\"","id_str":"2345678902","entities":{"user_mentions":[],"hashtags":[],"urls":[]},"in_reply_to_status_id":null,"place":null,"in_reply_to_status_id_str":null,"coordinates":null,"created_at":"Wed Sep 05 02:14:34 +0000 1985","in_reply_to_screen_name":null,"favorited":false,"in_reply_to_user_id_str":null,"user":{"default_profile_image":false,"friends_count":222,"profile_background_color":"3C0C29","location":"San Francisco","is_translator":false,"profile_background_tile":false,"favourites_count":22,"verified":false,"profile_sidebar_fill_color":"B2D948","follow_request_sent":null,"contributors_enabled":false,"description":"desc2","profile_sidebar_border_color":"8EC63D","profile_image_url_https":"https:\/\/si0.twimg.com\/profile_images\/22222222\/image_normal.jpg","id_str":"2222222","listed_count":0,"lang":"en","screen_name":"fake_user2","show_all_
inline_media":false,"profile_use_background_image":true,"profile_image_url":"http:\/\/a0.twimg.com\/profile_images\/2222222\/image_normal.jpg","default_profile":false,"statuses_count":222222,"created_at":"Thu Aug 04 11:33:28 +0000 1985","profile_text_color":"444444","followers_count":222,"protected":false,"following":null,"notifications":null,"profile_background_image_url":"http:\/\/a0.twimg.com\/profile_background_images\/222222\/222222.jpg","time_zone":"Central Time (US & Canada)","url":null,"name":"name2","geo_enabled":false,"profile_link_color":"9A0057","id":2222223,"profile_background_image_url_https":"https:\/\/si0.twimg.com\/profile_background_images\/2222222\/22222.jpg","utc_offset":-21600},"id":222223,"contributors":null,"geo":null}
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/53e5f34f/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120906-141433-medium.avro
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120906-141433-medium.avro b/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120906-141433-medium.avro
deleted file mode 100644
index 900507c..0000000
Binary files a/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120906-141433-medium.avro and /dev/null differ
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/53e5f34f/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120906-141433.avro
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120906-141433.avro b/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120906-141433.avro
deleted file mode 100644
index 4dbf180..0000000
Binary files a/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120906-141433.avro and /dev/null differ
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/53e5f34f/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120906-141433.bz2
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120906-141433.bz2 b/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120906-141433.bz2
deleted file mode 100644
index a4a9159..0000000
Binary files a/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120906-141433.bz2 and /dev/null differ
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/53e5f34f/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120906-141433.gz
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120906-141433.gz b/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120906-141433.gz
deleted file mode 100644
index 3e7a44c..0000000
Binary files a/solr/contrib/morphlines-core/src/test-files/test-documents/sample-statuses-20120906-141433.gz and /dev/null differ
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/53e5f34f/solr/contrib/morphlines-core/src/test-files/test-documents/test-outlook.msg
----------------------------------------------------------------------
diff --git a/solr/contrib/morphlines-core/src/test-files/test-documents/test-outlook.msg b/solr/contrib/morphlines-core/src/test-files/test-documents/test-outlook.msg
deleted file mode 100644
index c975c0c..0000000
Binary files a/solr/contrib/morphlines-core/src/test-files/test-documents/test-outlook.msg and /dev/null differ