Repository: incubator-atlas Updated Branches: refs/heads/master 147242e17 -> 48343db99
http://git-wip-us.apache.org/repos/asf/incubator-atlas/blob/48343db9/src/conf/solr/schema.xml ---------------------------------------------------------------------- diff --git a/src/conf/solr/schema.xml b/src/conf/solr/schema.xml new file mode 100644 index 0000000..1d445b1 --- /dev/null +++ b/src/conf/solr/schema.xml @@ -0,0 +1,534 @@ +<?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="titan-schema" version="1.5"> + <!-- attribute "name" is the name of this schema and is only used for display purposes. + version="x.y" is Solr's version number for the schema syntax and + semantics. It should not normally be changed by applications. + + 1.0: multiValued attribute did not exist, all fields are multiValued + by nature + 1.1: multiValued attribute introduced, false by default + 1.2: omitTermFreqAndPositions attribute introduced, true by default + except for text fields. + 1.3: removed optional field compress feature + 1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser + behavior when a single string produces multiple tokens. Defaults + to off for version >= 1.4 + 1.5: omitNorms defaults to true for primitive field types + (int, float, boolean, string...) + --> + + + <!-- Valid attributes for fields: + name: mandatory - the name for the field + type: mandatory - the name of a field type from the + <types> fieldType section + indexed: true if this field should be indexed (searchable or sortable) + stored: true if this field should be retrievable + docValues: true if this field should have doc values. Doc values are + useful for faceting, grouping, sorting and function queries. Although not + required, doc values will make the index faster to load, more + NRT-friendly and more memory-efficient. They however come with some + limitations: they are currently only supported by StrField, UUIDField + and all Trie*Fields, and depending on the field type, they might + require the field to be single-valued, be required or have a default + value (check the documentation of the field type you're interested in + for more information) + multiValued: true if this field may contain multiple values per document + omitNorms: (expert) set to true to omit the norms associated with + this field (this disables length normalization and index-time + boosting for the field, and saves some memory). Only full-text + fields or fields that need an index-time boost need norms. + Norms are omitted for primitive (non-analyzed) types by default. + termVectors: [false] set to true to store the term vector for a + given field. + When using MoreLikeThis, fields used for similarity should be + stored for best performance. + termPositions: Store position information with the term vector. + This will increase storage costs. + termOffsets: Store offset information with the term vector. This + will increase storage costs. + required: The field is required. It will throw an error if the + value does not exist + default: a value that should be used if no value is specified + when adding a document. + --> + + <!-- field names should consist of alphanumeric or underscore characters only and + not start with a digit. This is not currently strictly enforced, + but other field names will not have first class support from all components + and back compatibility is not guaranteed. Names with both leading and + trailing underscores (e.g. _version_) are reserved. + --> + + <!-- If you remove this field, you must _also_ disable the update log in solrconfig.xml + or Solr won't start. _version_ and update log are required for SolrCloud + --> + <field name="_version_" type="long" indexed="true" stored="true"/> + + <!-- points to the root document of a block of nested documents. Required for nested + document support, may be removed otherwise + --> + <field name="_root_" type="string" indexed="true" stored="false"/> + + <!-- Only remove the "id" field if you have a very good reason to. While not strictly + required, it is highly recommended. A <uniqueKey> is present in almost all Solr + installations. See the <uniqueKey> declaration below where <uniqueKey> is set to "id". + --> + <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" /> + + <!-- Dynamic field definitions allow using convention over configuration + for fields via the specification of patterns to match field names. + EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i) + RESTRICTION: the glob-like pattern in the name attribute must have + a "*" only at the start or the end. --> + + <dynamicField name="*_i" type="int" indexed="true" stored="true"/> + <dynamicField name="*_is" type="int" indexed="true" stored="true" multiValued="true"/> + <dynamicField name="*_s" type="string" indexed="true" stored="true" /> + <dynamicField name="*_ss" type="string" indexed="true" stored="true" multiValued="true"/> + <dynamicField name="*_l" type="long" indexed="true" stored="true"/> + <dynamicField name="*_ls" type="long" indexed="true" stored="true" multiValued="true"/> + <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/> + <dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/> + <dynamicField name="*_en" type="text_en" indexed="true" stored="true" multiValued="true"/> + <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/> + <dynamicField name="*_bs" type="boolean" indexed="true" stored="true" multiValued="true"/> + <dynamicField name="*_f" type="float" indexed="true" stored="true"/> + <dynamicField name="*_fs" type="float" indexed="true" stored="true" multiValued="true"/> + <dynamicField name="*_d" type="double" indexed="true" stored="true"/> + <dynamicField name="*_ds" type="double" indexed="true" stored="true" multiValued="true"/> + + <!-- Type used to index the lat and lon components for the "location" FieldType --> + <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" /> + + <dynamicField name="*_dt" type="date" indexed="true" stored="true"/> + <dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/> + <dynamicField name="*_p" type="location" indexed="true" stored="true"/> + + <!-- some trie-coded dynamic fields for faster range queries --> + <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/> + <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/> + <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/> + <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/> + <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/> + + <dynamicField name="*_c" type="currency" indexed="true" stored="true"/> + + <dynamicField name="ignored_*" type="ignored" multiValued="true"/> + <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/> + + <dynamicField name="random_*" type="random" /> + + <!-- uncomment the following to ignore any fields that don't already match an existing + field name or dynamic field, rather than reporting them as an error. + alternately, change the type="ignored" to some other type e.g. "text" if you want + unknown fields indexed and/or stored by default --> + <!--dynamicField name="*" type="ignored" multiValued="true" /--> + + <!-- 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> + + <!-- copyField commands copy one field to another at the time a document + is added to the index. It's used either to index the same field differently, + or to add multiple fields to the same field for easier/faster searching. --> + + <!-- + <copyField source="title" dest="text"/> + <copyField source="body" dest="text"/> + --> + + <!-- 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 a + standard package such as org.apache.solr.analysis + --> + + <!-- The StrField type is not analyzed, but indexed/stored verbatim. + It supports doc values but in that case the field needs to be + single-valued and either required or have a default value. + --> + <fieldType name="string" class="solr.StrField" sortMissingLast="true" /> + + <!-- boolean type: "true" or "false" --> + <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/> + + <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are + currently supported on types that are sorted internally as strings + and on numeric types. + This includes "string","boolean", and, as of 3.5 (and 4.x), + int, float, long, date, double, including the "Trie" variants. + - 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. + --> + + <!-- + Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types. + + These fields support doc values, but they require the field to be + single-valued and either be required or have a default value. + --> + <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/> + <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/> + <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/> + <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/> + + <!-- + Numeric field types that index each value at various levels of precision + to accelerate range queries when the number of values between the range + endpoints is large. See the javadoc for NumericRangeQuery for internal + implementation details. + + Smaller precisionStep values (specified in bits) will lead to more tokens + indexed per value, slightly larger index size, and faster range queries. + A precisionStep of 0 disables indexing at different precision levels. + --> + <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/> + <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/> + <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/> + <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/> + + <!-- 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 TrieDateField javadocs for more information. + + Note: For faster range queries, consider the tdate type + --> + <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/> + + <!-- A Trie based date field for faster date range queries and date faceting. --> + <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/> + + + <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings --> + <fieldType name="binary" class="solr.BinaryField"/> + + <!-- The "RandomSortField" is not used to store or search any + data. You can declare fields of this type it in your schema + to generate pseudo-random orderings of your docs for sorting + or function 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 different psuedo-random orderings of documents, + for the same version of the index, use a dynamicField and + change the field name in the request. + --> + <fieldType name="random" class="solr.RandomSortField" indexed="true" /> + + <!-- solr.TextField allows the specification of custom text analyzers + specified as a tokenizer and a list of token filters. Different + analyzers may be specified for indexing and querying. + + The optional positionIncrementGap puts space between multiple fields of + this type on the same document, with the purpose of preventing false phrase + matching across fields. + + For more info on customizing your analyzer chain, please see + http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters + --> + + <!-- One can also specify an existing Analyzer class that has a + default constructor via the class attribute on the analyzer element. + Example: + <fieldType name="text_greek" class="solr.TextField"> + <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/> + </fieldType> + --> + + <!-- 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 general text field that has reasonable, generic + cross-language defaults: it tokenizes with StandardTokenizer, + removes stop words from case-insensitive "stopwords.txt" + (empty by default), and down cases. At query time only, it + also applies synonyms. --> + <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100"> + <analyzer type="index"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" /> + <!-- in this example, we will only use synonyms at query time + <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/> + --> + <filter class="solr.LowerCaseFilterFactory"/> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" /> + <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> + <filter class="solr.LowerCaseFilterFactory"/> + </analyzer> + </fieldType> + + <!-- A text field with defaults appropriate for English: it + tokenizes with StandardTokenizer, removes English stop words + (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and + finally applies Porter's stemming. The query time analyzer + also applies synonyms from synonyms.txt. --> + <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100"> + <analyzer type="index"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <!-- in this example, we will only use synonyms at query time + <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/> + --> + <!-- Case insensitive stop word removal. + --> + <filter class="solr.StopFilterFactory" + ignoreCase="true" + words="lang/stopwords_en.txt" + /> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.EnglishPossessiveFilterFactory"/> + <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> + <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: + <filter class="solr.EnglishMinimalStemFilterFactory"/> + --> + <filter class="solr.PorterStemFilterFactory"/> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> + <filter class="solr.StopFilterFactory" + ignoreCase="true" + words="lang/stopwords_en.txt" + /> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.EnglishPossessiveFilterFactory"/> + <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> + <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory: + <filter class="solr.EnglishMinimalStemFilterFactory"/> + --> + <filter class="solr.PorterStemFilterFactory"/> + </analyzer> + </fieldType> + + <!-- A text field with defaults appropriate for English, plus + aggressive word-splitting and autophrase features enabled. + This field is just like text_en, except it adds + WordDelimiterFilter to enable splitting and matching of + words on case-change, alpha numeric boundaries, and + non-alphanumeric chars. This means certain compound word + cases will work, for example query "wi fi" will match + document "WiFi" or "wi-fi". + --> + <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true"> + <analyzer type="index"> + <tokenizer class="solr.WhitespaceTokenizerFactory"/> + <!-- in this example, we will only use synonyms at query time + <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/> + --> + <!-- Case insensitive stop word removal. + --> + <filter class="solr.StopFilterFactory" + ignoreCase="true" + words="lang/stopwords_en.txt" + /> + <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> + <filter class="solr.PorterStemFilterFactory"/> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.WhitespaceTokenizerFactory"/> + <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> + <filter class="solr.StopFilterFactory" + ignoreCase="true" + words="lang/stopwords_en.txt" + /> + <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> + <filter class="solr.PorterStemFilterFactory"/> + </analyzer> + </fieldType> + + <!-- Less flexible matching, but less false matches. Probably not ideal for product names, + but may be good for SKUs. Can insert dashes in the wrong place and still match. --> + <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true"> + <analyzer> + <tokenizer class="solr.WhitespaceTokenizerFactory"/> + <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/> + <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/> + <filter class="solr.EnglishMinimalStemFilterFactory"/> + <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes + possible with WordDelimiterFilter in conjuncton with stemming. --> + <filter class="solr.RemoveDuplicatesTokenFilterFactory"/> + </analyzer> + </fieldType> + + <!-- Just like text_general except it reverses the characters of + each token, to enable more efficient leading wildcard queries. --> + <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100"> + <analyzer type="index"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" /> + <filter class="solr.LowerCaseFilterFactory"/> + <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true" + maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.StandardTokenizerFactory"/> + <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" /> + <filter class="solr.LowerCaseFilterFactory"/> + </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 references to portions of the original + string matched by the pattern. + + See the Java Regular Expression documentation for more + information on pattern and replacement string syntax. + + http://docs.oracle.com/javase/7/docs/api/java/util/regex/package-summary.html + --> + <filter class="solr.PatternReplaceFilterFactory" + pattern="([^a-z])" replacement="" replace="all" + /> + </analyzer> + </fieldType> + + <!-- lowercases the entire field value, keeping it as a single token. --> + <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100"> + <analyzer> + <tokenizer class="solr.KeywordTokenizerFactory"/> + <filter class="solr.LowerCaseFilterFactory" /> + </analyzer> + </fieldType> + + <!-- since fields of this type are by default not stored or indexed, + any data added to them will be ignored outright. --> + <fieldType name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" /> + + <!-- This point type indexes the coordinates as separate fields (subFields) + If subFieldType is defined, it references a type, and a dynamic field + definition is created matching *___<typename>. Alternately, if + subFieldSuffix is defined, that is used to create the subFields. + Example: if subFieldType="double", then the coordinates would be + indexed in fields myloc_0___double,myloc_1___double. + Example: if subFieldSuffix="_d" then the coordinates would be indexed + in fields myloc_0_d,myloc_1_d + The subFields are an implementation detail of the fieldType, and end + users normally should not need to know about them. + --> + <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/> + + <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. --> + <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/> + + <!-- Spatial rectangle (bounding box) field. It supports most spatial predicates, and has + special relevancy modes: score=overlapRatio|area|area2D (local-param to the query). DocValues is recommended for + relevancy. --> + <fieldType name="bbox" class="solr.BBoxField" + geo="true" distanceUnits="kilometers" numberType="_bbox_coord" /> + <fieldType name="_bbox_coord" class="solr.TrieDoubleField" precisionStep="8" docValues="true" stored="false"/> + + <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType + Parameters: + defaultCurrency: Specifies the default currency if none specified. Defaults to "USD" + precisionStep: Specifies the precisionStep for the TrieLong field used for the amount + providerClass: Lets you plug in other exchange provider backend: + solr.FileExchangeRateProvider is the default and takes one parameter: + currencyConfig: name of an xml file holding exchange rates + solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org: + ratesFileLocation: URL or path to rates JSON file (default latest.json on the web) + refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60) + --> + <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" /> + + <!--Titan specific--> + <fieldType name="uuid" + class="solr.UUIDField" + indexed="true" /> + + <dynamicField name="*_uuid" type="uuid" indexed="true" stored="true"/> + + <!-- TTL --> + <field name="ttl" type="string" indexed="true" stored="true" /> + <field name="expire_at" type="date" indexed="true" stored="true" /> + <field name="timestamp" type="date" indexed="true" stored="true" /> + +</schema> http://git-wip-us.apache.org/repos/asf/incubator-atlas/blob/48343db9/src/conf/solr/solrconfig.xml ---------------------------------------------------------------------- diff --git a/src/conf/solr/solrconfig.xml b/src/conf/solr/solrconfig.xml new file mode 100644 index 0000000..ce2e20b --- /dev/null +++ b/src/conf/solr/solrconfig.xml @@ -0,0 +1,625 @@ +<?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>5.0.0</luceneMatchVersion> + + <!-- 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>${solr.data.dir:}</dataDir> + + + <!-- The DirectoryFactory to use for indexes. + + solr.StandardDirectoryFactory is filesystem + based and tries to pick the best implementation for the current + JVM and platform. solr.NRTCachingDirectoryFactory, the default, + wraps solr.StandardDirectoryFactory and caches small files in memory + for better NRT performance. + + One can force a particular implementation via solr.MMapDirectoryFactory, + solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory. + + solr.RAMDirectoryFactory is memory based, not + persistent, and doesn't work with replication. + --> + <directoryFactory name="DirectoryFactory" + class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"> + + <!-- These will be used if you are using the solr.HdfsDirectoryFactory, + otherwise they will be ignored. If you don't plan on using hdfs, + you can safely remove this section. --> + <!-- The root directory that collection data should be written to. --> + <str name="solr.hdfs.home">${solr.hdfs.home:}</str> + <!-- The hadoop configuration files to use for the hdfs client. --> + <str name="solr.hdfs.confdir">${solr.hdfs.confdir:}</str> + <!-- Enable/Disable the hdfs cache. --> + <str name="solr.hdfs.blockcache.enabled">${solr.hdfs.blockcache.enabled:true}</str> + <!-- Enable/Disable using one global cache for all SolrCores. + The settings used will be from the first HdfsDirectoryFactory created. --> + <str name="solr.hdfs.blockcache.global">${solr.hdfs.blockcache.global:true}</str> + + </directoryFactory> + + <!-- 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"/> + + + <!-- To enable dynamic schema REST APIs, use the following for <schemaFactory>: + + <schemaFactory class="ManagedIndexSchemaFactory"> + <bool name="mutable">true</bool> + <str name="managedSchemaResourceName">managed-schema</str> + </schemaFactory> + + When ManagedIndexSchemaFactory is specified, Solr will load the schema from + he resource named in 'managedSchemaResourceName', rather than from schema.xml. + Note that the managed schema resource CANNOT be named schema.xml. If the managed + schema does not exist, Solr will create it after reading schema.xml, then rename + 'schema.xml' to 'schema.xml.bak'. + + Do NOT hand edit the managed schema - external modifications will be ignored and + overwritten as a result of schema modification REST API calls. + + When ManagedIndexSchemaFactory is specified with mutable = true, schema + modification REST API calls will be allowed; otherwise, error responses will be + sent back for these requests. + --> + + <schemaFactory class="ClassicIndexSchemaFactory"/> + + <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + 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> + + <!-- 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>${solr.lock.type:native}</lockType> + + <!-- Lucene Infostream + + To aid in advanced debugging, Lucene provides an "InfoStream" + of detailed information when indexing. + + Setting the value to true will instruct the underlying Lucene + IndexWriter to write its info stream to solr's log. By default, + this is enabled here, and controlled through log4j.properties. + --> + <infoStream>true</infoStream> + </indexConfig> + + + <!-- JMX + + This example enables JMX if and only if an existing MBeanServer + is found, use this if you want to configure JMX through JVM + parameters. Remove this to disable exposing Solr configuration + and statistics to JMX. + + For more details see http://wiki.apache.org/solr/SolrJmx + --> + <jmx /> + <!-- If you want to connect to a particular server, specify the + agentId + --> + <!-- <jmx agentId="myAgent" /> --> + <!-- If you want to start a new MBeanServer, specify the serviceUrl --> + <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/> + --> + + <!-- The default high-performance update handler --> + <updateHandler class="solr.DirectUpdateHandler2"> + + <!-- Enables a transaction log, used for real-time get, durability, and + and solr cloud replica recovery. The log can grow as big as + uncommitted changes to the index, so use of a hard autoCommit + is recommended (see below). + "dir" - the target directory for transaction logs, defaults to the + solr data directory. --> + <updateLog> + <str name="dir">${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>${solr.autoCommit.maxTime:15000}</maxTime> + <openSearcher>false</openSearcher> + </autoCommit> + + <!-- softAutoCommit is like autoCommit except it causes a + 'soft' commit which only ensures that changes are visible + but does not ensure that data is synced to disk. This is + faster and more near-realtime friendly than a hard commit. + --> + <autoSoftCommit> + <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime> + </autoSoftCommit> + + </updateHandler> + + <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + 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"/> + + <!-- custom cache currently used by block join --> + <cache name="perSegFilter" + class="solr.search.LRUCache" + size="10" + initialSize="0" + autowarmCount="10" + regenerator="solr.NoOpRegenerator" /> + + <!-- 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> + + <!-- 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> + + <!-- 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> + + <!-- Max Warming Searchers + + Maximum number of searchers that may be warming in the + background concurrently. An error is returned if this limit + is exceeded. + + Recommend values of 1-2 for read-only slaves, higher for + masters w/o cache warming. + --> + <maxWarmingSearchers>2</maxWarmingSearchers> + + </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. + + addHttpRequestToContext - if set to true, it will instruct + the requestParsers to include the original HttpServletRequest + object in the context map of the SolrQueryRequest under the + key "httpRequest". It will not be used by any of the existing + Solr components, but may be useful when developing custom + plugins. + + *** 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" + addHttpRequestToContext="false"/> + + <!-- 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" /> + + </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> + </lst> + + </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> + + <!-- + The export request handler is used to export full sorted result sets. + Do not change these defaults. + --> + <requestHandler name="/export" class="solr.SearchHandler"> + <lst name="invariants"> + <str name="rq">{!xport}</str> + <str name="wt">xsort</str> + <str name="distrib">false</str> + </lst> + + <arr name="components"> + <str>query</str> + </arr> + </requestHandler> + + + <initParams path="/update/**,/query,/select,/tvrh,/elevate,/spell"> + <lst name="defaults"> + <str name="df">text</str> + </lst> + </initParams> + + <!-- Field Analysis Request Handler + + RequestHandler that provides much the same functionality as + analysis.jsp. Provides the ability to specify multiple field + types and field names in the same request and outputs + index-time and query-time analysis for each of them. + + Request parameters are: + analysis.fieldname - field name whose analyzers are to be used + + analysis.fieldtype - field type whose analyzers are to be used + analysis.fieldvalue - text for index-time analysis + q (or analysis.q) - text for query time analysis + analysis.showmatch (true|false) - When set to true and when + query analysis is performed, the produced tokens of the + field value analysis will be marked as "matched" for every + token that is produces by the query analysis + --> + <requestHandler name="/analysis/field" + startup="lazy" + class="solr.FieldAnalysisRequestHandler" /> + + + <!-- Document Analysis Handler + + http://wiki.apache.org/solr/AnalysisRequestHandler + + An analysis handler that provides a breakdown of the analysis + process of provided documents. This handler expects a (single) + content stream with the following format: + + <docs> + <doc> + <field name="id">1</field> + <field name="name">The Name</field> + <field name="text">The Text Value</field> + </doc> + <doc>...</doc> + <doc>...</doc> + ... + </docs> + + Note: Each document must contain a field which serves as the + unique key. This key is used in the returned response to associate + an analysis breakdown to the analyzed document. + + Like the FieldAnalysisRequestHandler, this handler also supports + query analysis by sending either an "analysis.query" or "q" + request parameter that holds the query text to be analyzed. It + also supports the "analysis.showmatch" parameter which when set to + true, all field tokens that match the query tokens will be marked + as a "match". + --> + <requestHandler name="/analysis/document" + class="solr.DocumentAnalysisRequestHandler" + startup="lazy" /> + + <!-- Echo the request contents back to the client --> + <requestHandler name="/debug/dump" class="solr.DumpRequestHandler" > + <lst name="defaults"> + <str name="echoParams">explicit</str> + <str name="echoHandler">true</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" /> + + --> + + <!-- 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> + + <!-- Legacy config for the admin interface --> + <admin> + <defaultQuery>*:*</defaultQuery> + </admin> + + + <!--Titan specific--> + <updateRequestProcessorChain default="true"> + <processor class="solr.TimestampUpdateProcessorFactory"> + <str name="fieldName">timestamp</str> + </processor> + <processor class="solr.processor.DocExpirationUpdateProcessorFactory"> + <int name="autoDeletePeriodSeconds">5</int> + <str name="ttlFieldName">ttl</str> + <str name="expirationFieldName">expire_at</str> + </processor> + <processor class="solr.FirstFieldValueUpdateProcessorFactory"> + <str name="fieldName">expire_at_dt</str> + </processor> + <processor class="solr.LogUpdateProcessorFactory"/> + <processor class="solr.RunUpdateProcessorFactory"/> + </updateRequestProcessorChain> +</config> http://git-wip-us.apache.org/repos/asf/incubator-atlas/blob/48343db9/src/conf/solr/stopwords.txt ---------------------------------------------------------------------- diff --git a/src/conf/solr/stopwords.txt b/src/conf/solr/stopwords.txt new file mode 100644 index 0000000..ae1e83e --- /dev/null +++ b/src/conf/solr/stopwords.txt @@ -0,0 +1,14 @@ +# 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. http://git-wip-us.apache.org/repos/asf/incubator-atlas/blob/48343db9/src/conf/solr/synonyms.txt ---------------------------------------------------------------------- diff --git a/src/conf/solr/synonyms.txt b/src/conf/solr/synonyms.txt new file mode 100644 index 0000000..7f72128 --- /dev/null +++ b/src/conf/solr/synonyms.txt @@ -0,0 +1,29 @@ +# 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. + +#----------------------------------------------------------------------- +#some test synonym mappings unlikely to appear in real input text +aaafoo => aaabar +bbbfoo => bbbfoo bbbbar +cccfoo => cccbar cccbaz +fooaaa,baraaa,bazaaa + +# Some synonym groups specific to this example +GB,gib,gigabyte,gigabytes +MB,mib,megabyte,megabytes +Television, Televisions, TV, TVs +#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming +#after us won't split it into two words. + +# Synonym mappings can be used for spelling correction too +pixima => pixma +
