You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by er...@apache.org on 2016/05/10 14:42:31 UTC
[23/24] lucene-solr:branch_6x: SOLR-9083: Remove deprecated
and from schemas (cherry picked from commit 5341918)
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/03a06bb3/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-schema.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-schema.xml b/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-schema.xml
index 7b10481..8d62c84 100644
--- a/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-schema.xml
+++ b/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-schema.xml
@@ -1,60 +1,62 @@
<schema name="dih_test" version="4.0">
- <types>
- <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
- <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
- <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"/>
- <fieldType name="date" class="solr.TrieDateField" sortMissingLast="true" omitNorms="true"/>
- <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- </fieldType>
- <fieldType name="textTight" class="solr.TextField" positionIncrementGap="100" >
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- </fieldType>
- <fieldType name="ignored" stored="false" indexed="false" class="solr.StrField" />
- </types>
- <fields>
- <field name="id" type="string" indexed="true" stored="true" required="true" />
- <field name="desc" type="string" indexed="true" stored="true" multiValued="true" />
- <field name="date" type="date" indexed="true" stored="true" />
- <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
-
- <field name="NAME" type="text" indexed="true" stored="true" multiValued="false" />
- <field name="COUNTRY_NAME" type="text" indexed="true" stored="true" multiValued="true" />
- <field name="SPORT_NAME" type="text" indexed="true" stored="true" multiValued="true" />
- <field name="DO_NOT_INDEX" type="ignored" />
- <field name="_version_" type="tlong" indexed="true" stored="true" multiValued="false"/>
- <field name="_root_" type="string" indexed="true" stored="true" multiValued="false"/>
-
- <dynamicField name="*_i" type="tint" indexed="true" stored="true"/>
- <dynamicField name="*_s" type="string" indexed="true" stored="true"/>
- <dynamicField name="*_mult_s" type="string" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_l" type="tlong" indexed="true" stored="true"/>
- <dynamicField name="*_t" type="text" indexed="true" stored="true"/>
- <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
- <dynamicField name="*_f" type="tfloat" indexed="true" stored="true"/>
- <dynamicField name="*_d" type="tdouble" indexed="true" stored="true"/>
- <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
- </fields>
+ <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
+ <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
+ <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"/>
+ <fieldType name="date" class="solr.TrieDateField" sortMissingLast="true" omitNorms="true"/>
+ <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+ catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+ catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="textTight" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+ catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="ignored" stored="false" indexed="false" class="solr.StrField"/>
+
+ <field name="id" type="string" indexed="true" stored="true" required="true"/>
+ <field name="desc" type="string" indexed="true" stored="true" multiValued="true"/>
+ <field name="date" type="date" indexed="true" stored="true"/>
+ <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
+
+ <field name="NAME" type="text" indexed="true" stored="true" multiValued="false"/>
+ <field name="COUNTRY_NAME" type="text" indexed="true" stored="true" multiValued="true"/>
+ <field name="SPORT_NAME" type="text" indexed="true" stored="true" multiValued="true"/>
+ <field name="DO_NOT_INDEX" type="ignored"/>
+
+ <field name="_version_" type="tlong" indexed="true" stored="true" multiValued="false"/>
+ <field name="_root_" type="string" indexed="true" stored="true" multiValued="false"/>
+
+ <dynamicField name="*_i" type="tint" indexed="true" stored="true"/>
+ <dynamicField name="*_s" type="string" indexed="true" stored="true"/>
+ <dynamicField name="*_mult_s" type="string" indexed="true" stored="true" multiValued="true"/>
+ <dynamicField name="*_l" type="tlong" indexed="true" stored="true"/>
+ <dynamicField name="*_t" type="text" indexed="true" stored="true"/>
+ <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
+ <dynamicField name="*_f" type="tfloat" indexed="true" stored="true"/>
+ <dynamicField name="*_d" type="tdouble" indexed="true" stored="true"/>
+ <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
+
<uniqueKey>id</uniqueKey>
<defaultSearchField>desc</defaultSearchField>
<solrQueryParser defaultOperator="OR"/>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/03a06bb3/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-solr_id-schema.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-solr_id-schema.xml b/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-solr_id-schema.xml
index d8cb73b..9a95797 100644
--- a/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-solr_id-schema.xml
+++ b/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-solr_id-schema.xml
@@ -37,273 +37,271 @@
1.0: multiValued attribute did not exist, all fields are multiValued by nature
1.1: multiValued attribute introduced, false by default -->
- <types>
- <!-- field type definitions. The "name" attribute is
- just a label to be used by field definitions. The "class"
- attribute and any other attributes determine the real
- behavior of the fieldType.
- Class names starting with "solr" refer to java classes in the
- org.apache.solr.analysis package.
- -->
- <!-- The StrField type is not analyzed, but indexed/stored verbatim.
- - StrField and TextField support an optional compressThreshold which
- limits compression (if enabled in the derived fields) to values which
- exceed a certain size (in characters).
- -->
- <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
-
- <!-- boolean type: "true" or "false" -->
- <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
-
- <!-- The optional sortMissingLast and sortMissingFirst attributes are
- currently supported on types that are sorted internally as strings.
- - If sortMissingLast="true", then a sort on this field will cause documents
- without the field to come after documents with the field,
- regardless of the requested sort order (asc or desc).
- - If sortMissingFirst="true", then a sort on this field will cause documents
- without the field to come before documents with the field,
- regardless of the requested sort order.
- - If sortMissingLast="false" and sortMissingFirst="false" (the default),
- then default lucene sorting will be used which places docs without the
- field first in an ascending sort and last in a descending sort.
+ <!-- field type definitions. The "name" attribute is
+ just a label to be used by field definitions. The "class"
+ attribute and any other attributes determine the real
+ behavior of the fieldType.
+ Class names starting with "solr" refer to java classes in the
+ org.apache.solr.analysis package.
+ -->
+
+ <!-- The StrField type is not analyzed, but indexed/stored verbatim.
+ - StrField and TextField support an optional compressThreshold which
+ limits compression (if enabled in the derived fields) to values which
+ exceed a certain size (in characters).
+ -->
+ <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
+
+ <!-- boolean type: "true" or "false" -->
+ <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
+
+ <!-- The optional sortMissingLast and sortMissingFirst attributes are
+ currently supported on types that are sorted internally as strings.
+ - If sortMissingLast="true", then a sort on this field will cause documents
+ without the field to come after documents with the field,
+ regardless of the requested sort order (asc or desc).
+ - If sortMissingFirst="true", then a sort on this field will cause documents
+ without the field to come before documents with the field,
+ regardless of the requested sort order.
+ - If sortMissingLast="false" and sortMissingFirst="false" (the default),
+ then default lucene sorting will be used which places docs without the
+ field first in an ascending sort and last in a descending sort.
+ -->
+
+
+ <!--
+ Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
+ -->
+ <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 LegacyNumericRangeQuery 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.
-->
+ <fieldType name="date" class="solr.TrieDateField" sortMissingLast="true" omitNorms="true"/>
+
+
+ <!-- The "RandomSortField" is not used to store or search any
+ data. You can declare fields of this type it in your schema
+ to generate psuedo-random orderings of your docs for sorting
+ purposes. The ordering is generated based on the field name
+ and the version of the index, As long as the index version
+ remains unchanged, and the same field name is reused,
+ the ordering of the docs will be consistent.
+ If you want differend psuedo-random orderings of documents,
+ for the same version of the index, use a dynamicField and
+ change the name
+ -->
+ <fieldType name="random" class="solr.RandomSortField" indexed="true"/>
+ <!-- solr.TextField allows the specification of custom text analyzers
+ specified as a tokenizer and a list of token filters. Different
+ analyzers may be specified for indexing and querying.
- <!--
- Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
- -->
- <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 LegacyNumericRangeQuery 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.
+ The optional positionIncrementGap puts space between multiple fields of
+ this type on the same document, with the purpose of preventing false phrase
+ matching across fields.
+
+ For more info on customizing your analyzer chain, please see
+ http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
+ -->
+
+ <!-- One can also specify an existing Analyzer class that has a
+ default constructor via the class attribute on the analyzer element
+ <fieldType name="text_greek" class="solr.TextField">
+ <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
+ </fieldType>
+ -->
+
+ <!-- A text field that only splits on whitespace for exact matching of words -->
+ <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
+ words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
+ so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
+ Synonyms and stopwords are customized by external files, and stemming is enabled.
+ Duplicate tokens at the same position (which may result from Stemmed Synonyms or
+ WordDelim parts) are removed.
-->
- <fieldType name="date" class="solr.TrieDateField" sortMissingLast="true" omitNorms="true"/>
-
-
- <!-- The "RandomSortField" is not used to store or search any
- data. You can declare fields of this type it in your schema
- to generate psuedo-random orderings of your docs for sorting
- purposes. The ordering is generated based on the field name
- and the version of the index, As long as the index version
- remains unchanged, and the same field name is reused,
- the ordering of the docs will be consistent.
- If you want differend psuedo-random orderings of documents,
- for the same version of the index, use a dynamicField and
- change the name
- -->
- <fieldType name="random" class="solr.RandomSortField" indexed="true" />
-
- <!-- solr.TextField allows the specification of custom text analyzers
- specified as a tokenizer and a list of token filters. Different
- analyzers may be specified for indexing and querying.
-
- The optional positionIncrementGap puts space between multiple fields of
- this type on the same document, with the purpose of preventing false phrase
- matching across fields.
-
- For more info on customizing your analyzer chain, please see
- http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
- -->
-
- <!-- One can also specify an existing Analyzer class that has a
- default constructor via the class attribute on the analyzer element
- <fieldType name="text_greek" class="solr.TextField">
- <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
- </fieldType>
+ <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <!-- 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.StopFilterFactory" ignoreCase="true" words="stopwords.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"/>-->
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <!--<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>-->
+ <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+ catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.PorterStemFilterFactory"/>-->
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+
+ <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
+ but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
+ <fieldType name="textTight" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <!--<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>-->
+ <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+ catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>-->
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- This is an example of using the KeywordTokenizer along
+ With various TokenFilterFactories to produce a sortable field
+ that does not include some properties of the source text
-->
-
- <!-- 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.MockTokenizerFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
- words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
- so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
- Synonyms and stopwords are customized by external files, and stemming is enabled.
- Duplicate tokens at the same position (which may result from Stemmed Synonyms or
- WordDelim parts) are removed.
+ <fieldType name="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
-->
- <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.MockTokenizerFactory"/>
- <!-- in this example, we will only use synonyms at query time
- <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
+ <!-- The LowerCase TokenFilter does what you expect, which can be
+ when you want your sorting to be case insensitive
-->
- <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.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"/>-->
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.MockTokenizerFactory"/>
- <!--<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>-->
- <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.PorterStemFilterFactory"/>-->
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- </fieldType>
-
-
- <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
- but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
- <fieldType name="textTight" class="solr.TextField" positionIncrementGap="100" >
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <!--<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>-->
- <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.EnglishMinimalStemFilterFactory"/>-->
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- This is an example of using the KeywordTokenizer along
- With various TokenFilterFactories to produce a sortable field
- that does not include some properties of the source text
- -->
- <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
- <analyzer>
- <!-- KeywordTokenizer does no actual tokenizing, so the entire
- input string is preserved as a single token
- -->
- <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
- <!-- The LowerCase TokenFilter does what you expect, which can be
- when you want your sorting to be case insensitive
- -->
- <filter class="solr.LowerCaseFilterFactory" />
- <!-- The TrimFilter removes any leading or trailing whitespace -->
- <filter class="solr.TrimFilterFactory" />
- <!-- The PatternReplaceFilter gives you the flexibility to use
- Java Regular expression to replace any sequence of characters
- matching a pattern with an arbitrary replacement string,
- which may include back refrences to portions of the orriginal
- string matched by the pattern.
-
- See the Java Regular Expression documentation for more
- infomation on pattern and replacement string syntax.
-
- http://docs.oracle.com/javase/8/docs/api/java/util/regex/package-summary.html
- -->
- <filter class="solr.PatternReplaceFilterFactory"
- pattern="([^a-z])" replacement="" replace="all"
- />
- </analyzer>
- </fieldType>
-
- <!-- since fields of this type are by default not stored or indexed, any data added to
- them will be ignored outright
- -->
- <fieldType name="ignored" stored="false" indexed="false" class="solr.StrField" />
-
- </types>
-
-
- <fields>
- <!-- Valid attributes for fields:
- name: mandatory - the name for the field
- type: mandatory - the name of a previously defined type from the <types> section
- indexed: true if this field should be indexed (searchable or sortable)
- stored: true if this field should be retrievable
- 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.
- 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.
- -->
-
- <field name="solr_id" type="string" indexed="true" stored="true" required="true" />
- <field name="desc" type="string" indexed="true" stored="true" multiValued="true" />
-
- <field name="date" type="date" indexed="true" stored="true" />
-
- <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
-
-
- <!-- Dynamic field definitions. If a field name is not found, dynamicFields
- will be used if the name matches any of the patterns.
- RESTRICTION: the glob-like pattern in the name attribute must have
- a "*" only at the start or the end.
- EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
- Longer patterns will be matched first. if equal size patterns
- both match, the first appearing in the schema will be used. -->
- <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
- <dynamicField name="*_s" type="string" indexed="true" stored="true"/>
- <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
- <dynamicField name="*_t" type="text" indexed="true" stored="true"/>
- <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
- <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
- <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
- <dynamicField name="*_dt" type="date" indexed="true" stored="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" /-->
-
- </fields>
-
- <!-- Field to use to determine and enforce document uniqueness.
- Unless this field is marked with required="false", it will be a required field
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <!-- The TrimFilter removes any leading or trailing whitespace -->
+ <filter class="solr.TrimFilterFactory"/>
+ <!-- The PatternReplaceFilter gives you the flexibility to use
+ Java Regular expression to replace any sequence of characters
+ matching a pattern with an arbitrary replacement string,
+ which may include back refrences to portions of the orriginal
+ string matched by the pattern.
+
+ See the Java Regular Expression documentation for more
+ infomation on pattern and replacement string syntax.
+
+ http://docs.oracle.com/javase/8/docs/api/java/util/regex/package-summary.html
+ -->
+ <filter class="solr.PatternReplaceFilterFactory"
+ pattern="([^a-z])" replacement="" replace="all"
+ />
+ </analyzer>
+ </fieldType>
+
+ <!-- since fields of this type are by default not stored or indexed, any data added to
+ them will be ignored outright
-->
- <uniqueKey>solr_id</uniqueKey>
+ <fieldType name="ignored" stored="false" indexed="false" class="solr.StrField"/>
+
+ <!-- Valid attributes for fields:
+ name: mandatory - the name for the field
+ type: mandatory - the name of a previously defined type from the <fieldType>s
+ indexed: true if this field should be indexed (searchable or sortable)
+ stored: true if this field should be retrievable
+ 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.
+ 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.
+ -->
+
+ <field name="solr_id" type="string" indexed="true" stored="true" required="true"/>
+ <field name="desc" type="string" indexed="true" stored="true" multiValued="true"/>
+
+ <field name="date" type="date" indexed="true" stored="true"/>
+
+ <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
+
+
+ <!-- Dynamic field definitions. If a field name is not found, dynamicFields
+ will be used if the name matches any of the patterns.
+ RESTRICTION: the glob-like pattern in the name attribute must have
+ a "*" only at the start or the end.
+ EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
+ Longer patterns will be matched first. if equal size patterns
+ both match, the first appearing in the schema will be used. -->
+ <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
+ <dynamicField name="*_s" type="string" indexed="true" stored="true"/>
+ <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
+ <dynamicField name="*_t" type="text" indexed="true" stored="true"/>
+ <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
+ <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
+ <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
+ <dynamicField name="*_dt" type="date" indexed="true" stored="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" /-->
+
+
+ <!-- Field to use to determine and enforce document uniqueness.
+ Unless this field is marked with required="false", it will be a required field
+ -->
+ <uniqueKey>solr_id</uniqueKey>
- <!-- field for the QueryParser to use when an explicit fieldname is absent -->
- <defaultSearchField>desc</defaultSearchField>
+ <!-- field for the QueryParser to use when an explicit fieldname is absent -->
+ <defaultSearchField>desc</defaultSearchField>
- <!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
- <solrQueryParser defaultOperator="OR"/>
+ <!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
+ <solrQueryParser defaultOperator="OR"/>
</schema>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/03a06bb3/solr/contrib/extraction/src/test-files/extraction/solr/collection1/conf/schema.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/extraction/src/test-files/extraction/solr/collection1/conf/schema.xml b/solr/contrib/extraction/src/test-files/extraction/solr/collection1/conf/schema.xml
index e3dc2a8..35d123f 100644
--- a/solr/contrib/extraction/src/test-files/extraction/solr/collection1/conf/schema.xml
+++ b/solr/contrib/extraction/src/test-files/extraction/solr/collection1/conf/schema.xml
@@ -26,427 +26,442 @@
-->
<schema name="test" version="1.0">
- <types>
- <!--
- Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
+
+ <!--
+ Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
+ -->
+ <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 LegacyNumericRangeQuery 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"/>
+
+ <!-- Field type demonstrating an Analyzer failure -->
+ <fieldType name="failtype1" class="solr.TextField">
+ <analyzer type="index">
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+ catenateNumbers="0" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Demonstrating ignoreCaseChange -->
+ <fieldType name="wdf_nocase" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+ catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <fieldType name="wdf_preserve" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+ catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+
+ <!-- HighlitText optimizes storage for (long) columns which will be highlit -->
+ <fieldType name="highlittext" class="solr.TextField" compressThreshold="345"/>
+
+ <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
+ <fieldType name="string" class="solr.StrField" sortMissingLast="true"/>
+
+ <!-- format for date is 1995-12-31T23:59:59.999Z and only the fractional
+ seconds part (.999) is optional.
-->
- <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 LegacyNumericRangeQuery 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="date" class="solr.TrieDateField" sortMissingLast="true" omitNorms="true"/>
+
+ <!-- solr.TextField allows the specification of custom
+ text analyzers specified as a tokenizer and a list
+ of token filters.
-->
- <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"/>
-
- <!-- Field type demonstrating an Analyzer failure -->
- <fieldType name="failtype1" class="solr.TextField">
- <analyzer type="index">
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Demonstrating ignoreCaseChange -->
- <fieldType name="wdf_nocase" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <fieldType name="wdf_preserve" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
-
- <!-- HighlitText optimizes storage for (long) columns which will be highlit -->
- <fieldType name="highlittext" class="solr.TextField" compressThreshold="345" />
-
- <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
- <fieldType name="string" class="solr.StrField" sortMissingLast="true"/>
-
- <!-- format for date is 1995-12-31T23:59:59.999Z and only the fractional
- seconds part (.999) is optional.
- -->
- <fieldType name="date" class="solr.TrieDateField" sortMissingLast="true" omitNorms="true"/>
-
- <!-- solr.TextField allows the specification of custom
- text analyzers specified as a tokenizer and a list
- of token filters.
- -->
- <fieldType name="text" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.ClassicTokenizerFactory"/>
- <filter class="solr.ClassicFilterFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory"/>
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
-
- <fieldType name="nametext" class="solr.TextField">
- <analyzer class="org.apache.lucene.analysis.core.WhitespaceAnalyzer"/>
- </fieldType>
-
- <fieldType name="teststop" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.LowerCaseTokenizerFactory"/>
- <filter class="solr.ClassicFilterFactory"/>
- <filter class="solr.StopFilterFactory" words="stopwords.txt"/>
- </analyzer>
- </fieldType>
-
- <!-- fieldTypes in this section isolate tokenizers and tokenfilters for testing -->
- <fieldType name="lowertok" class="solr.TextField">
- <analyzer><tokenizer class="solr.LowerCaseTokenizerFactory"/></analyzer>
- </fieldType>
- <fieldType name="keywordtok" class="solr.TextField">
- <analyzer><tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/></analyzer>
- </fieldType>
- <fieldType name="standardtok" class="solr.TextField">
- <analyzer><tokenizer class="solr.StandardTokenizerFactory"/></analyzer>
- </fieldType>
- <fieldType name="lettertok" class="solr.TextField">
- <analyzer><tokenizer class="solr.LetterTokenizerFactory"/></analyzer>
- </fieldType>
- <fieldType name="whitetok" class="solr.TextField">
- <analyzer><tokenizer class="solr.MockTokenizerFactory"/></analyzer>
- </fieldType>
- <fieldType name="HTMLstandardtok" class="solr.TextField">
- <analyzer>
+ <fieldType name="text" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.ClassicTokenizerFactory"/>
+ <filter class="solr.ClassicFilterFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory"/>
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+
+ <fieldType name="nametext" class="solr.TextField">
+ <analyzer class="org.apache.lucene.analysis.core.WhitespaceAnalyzer"/>
+ </fieldType>
+
+ <fieldType name="teststop" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.LowerCaseTokenizerFactory"/>
+ <filter class="solr.ClassicFilterFactory"/>
+ <filter class="solr.StopFilterFactory" words="stopwords.txt"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- fieldTypes in this section isolate tokenizers and tokenfilters for testing -->
+ <fieldType name="lowertok" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.LowerCaseTokenizerFactory"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="keywordtok" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="standardtok" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="lettertok" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.LetterTokenizerFactory"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="whitetok" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="HTMLstandardtok" class="solr.TextField">
+ <analyzer>
<charFilter class="solr.HTMLStripCharFilterFactory"/>
<tokenizer class="solr.StandardTokenizerFactory"/>
- </analyzer>
- </fieldType>
- <fieldType name="HTMLwhitetok" class="solr.TextField">
- <analyzer>
+ </analyzer>
+ </fieldType>
+ <fieldType name="HTMLwhitetok" class="solr.TextField">
+ <analyzer>
<charFilter class="solr.HTMLStripCharFilterFactory"/>
<tokenizer class="solr.MockTokenizerFactory"/>
- </analyzer>
- </fieldType>
- <fieldType name="standardtokfilt" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.ClassicTokenizerFactory"/>
- <filter class="solr.ClassicFilterFactory"/>
- </analyzer>
- </fieldType>
- <fieldType name="standardfilt" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.ClassicFilterFactory"/>
- </analyzer>
- </fieldType>
- <fieldType name="lowerfilt" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
- <fieldType name="patternreplacefilt" class="solr.TextField">
- <analyzer type="index">
- <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
- <filter class="solr.PatternReplaceFilterFactory"
- pattern="([^a-zA-Z])" replacement="_" replace="all"
- />
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
- </analyzer>
- </fieldType>
- <fieldType name="porterfilt" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- </fieldType>
- <!-- fieldType name="snowballfilt" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.SnowballPorterFilterFactory"/>
- </analyzer>
- </fieldType -->
- <fieldType name="engporterfilt" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- </fieldType>
- <fieldType name="custengporterfilt" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- </fieldType>
- <fieldType name="stopfilt" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true"/>
- </analyzer>
- </fieldType>
- <fieldType name="custstopfilt" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" words="stopwords.txt"/>
- </analyzer>
- </fieldType>
- <fieldType name="lengthfilt" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.LengthFilterFactory" min="2" max="5"/>
- </analyzer>
- </fieldType>
-
- <fieldType name="subword" class="solr.TextField" multiValued="true" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory"/>
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory"/>
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- more flexible in matching skus, but more chance of a false match -->
- <fieldType name="skutype1" class="solr.TextField">
- <analyzer type="index">
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- less flexible in matching skus, but less chance of a false match -->
- <fieldType name="skutype2" class="solr.TextField">
- <analyzer type="index">
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- less flexible in matching skus, but less chance of a false match -->
- <fieldType name="syn" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt"/>
- </analyzer>
- </fieldType>
-
- <!-- Demonstrates How RemoveDuplicatesTokenFilter makes stemmed
- synonyms "better"
- -->
- <fieldType name="dedup" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory"
- synonyms="synonyms.txt" expand="true" />
- <filter class="solr.PorterStemFilterFactory"/>
- <filter class="solr.RemoveDuplicatesTokenFilterFactory" />
- </analyzer>
- </fieldType>
-
- <fieldType name="unstored" class="solr.StrField" indexed="true" stored="false"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="standardtokfilt" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.ClassicTokenizerFactory"/>
+ <filter class="solr.ClassicFilterFactory"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="standardfilt" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.ClassicFilterFactory"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="lowerfilt" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="patternreplacefilt" class="solr.TextField">
+ <analyzer type="index">
+ <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
+ <filter class="solr.PatternReplaceFilterFactory"
+ pattern="([^a-zA-Z])" replacement="_" replace="all"
+ />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="porterfilt" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+ <!-- fieldType name="snowballfilt" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.SnowballPorterFilterFactory"/>
+ </analyzer>
+ </fieldType -->
+ <fieldType name="engporterfilt" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="custengporterfilt" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="stopfilt" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="custstopfilt" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" words="stopwords.txt"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="lengthfilt" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.LengthFilterFactory" min="2" max="5"/>
+ </analyzer>
+ </fieldType>
+
+ <fieldType name="subword" class="solr.TextField" multiValued="true" positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+ catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory"/>
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+ catenateNumbers="0" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory"/>
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- more flexible in matching skus, but more chance of a false match -->
+ <fieldType name="skutype1" class="solr.TextField">
+ <analyzer type="index">
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+ catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+ catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- less flexible in matching skus, but less chance of a false match -->
+ <fieldType name="skutype2" class="solr.TextField">
+ <analyzer type="index">
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+ catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+ catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- less flexible in matching skus, but less chance of a false match -->
+ <fieldType name="syn" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Demonstrates How RemoveDuplicatesTokenFilter makes stemmed
+ synonyms "better"
+ -->
+ <fieldType name="dedup" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.SynonymFilterFactory"
+ synonyms="synonyms.txt" expand="true"/>
+ <filter class="solr.PorterStemFilterFactory"/>
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <fieldType name="unstored" class="solr.StrField" indexed="true" stored="false"/>
<fieldType name="textgap" class="solr.TextField" multiValued="true" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
+ <analyzer>
+ <tokenizer class="solr.MockTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
</fieldType>
- </types>
-
-
- <fields>
- <field name="id" type="string" indexed="true" stored="true" multiValued="false" required="false"/>
- <field name="name" type="nametext" indexed="true" stored="true"/>
- <field name="text" type="text" indexed="true" stored="false"/>
- <field name="subject" type="text" indexed="true" stored="true"/>
- <field name="title" type="nametext" indexed="true" stored="true"/>
- <field name="weight" type="float" indexed="true" stored="true"/>
- <field name="bday" type="date" indexed="true" stored="true"/>
-
- <field name="title_stemmed" type="text" indexed="true" stored="false"/>
- <field name="title_lettertok" type="lettertok" indexed="true" stored="false"/>
-
- <field name="syn" type="syn" indexed="true" stored="true"/>
-
- <!-- to test property inheritance and overriding -->
- <field name="shouldbeunstored" type="unstored" />
- <field name="shouldbestored" type="unstored" stored="true"/>
- <field name="shouldbeunindexed" type="unstored" indexed="false" stored="true"/>
-
-
- <!-- test different combinations of indexed and stored -->
- <field name="bind" type="boolean" indexed="true" stored="false"/>
- <field name="bsto" type="boolean" indexed="false" stored="true"/>
- <field name="bindsto" type="boolean" indexed="true" stored="true"/>
- <field name="isto" type="int" indexed="false" stored="true"/>
- <field name="iind" type="int" indexed="true" stored="false"/>
- <field name="ssto" type="string" indexed="false" stored="true"/>
- <field name="sind" type="string" indexed="true" stored="false"/>
- <field name="sindsto" type="string" indexed="true" stored="true"/>
-
- <!-- test combinations of term vector settings -->
- <field name="test_basictv" type="text" termVectors="true"/>
- <field name="test_notv" type="text" termVectors="false"/>
- <field name="test_postv" type="text" termVectors="true" termPositions="true"/>
- <field name="test_offtv" type="text" termVectors="true" termOffsets="true"/>
- <field name="test_posofftv" type="text" termVectors="true"
- termPositions="true" termOffsets="true"/>
-
- <!-- test highlit field settings -->
- <field name="test_hlt" type="highlittext" indexed="true"/>
- <field name="test_hlt_off" type="highlittext" indexed="true"/>
-
- <!-- fields to test individual tokenizers and tokenfilters -->
- <field name="teststop" type="teststop" indexed="true" stored="true"/>
- <field name="lowertok" type="lowertok" indexed="true" stored="true"/>
- <field name="keywordtok" type="keywordtok" indexed="true" stored="true"/>
- <field name="standardtok" type="standardtok" indexed="true" stored="true"/>
- <field name="HTMLstandardtok" type="HTMLstandardtok" indexed="true" stored="true"/>
- <field name="lettertok" type="lettertok" indexed="true" stored="true"/>
- <field name="whitetok" type="whitetok" indexed="true" stored="true"/>
- <field name="HTMLwhitetok" type="HTMLwhitetok" indexed="true" stored="true"/>
- <field name="standardtokfilt" type="standardtokfilt" indexed="true" stored="true"/>
- <field name="standardfilt" type="standardfilt" indexed="true" stored="true"/>
- <field name="lowerfilt" type="lowerfilt" indexed="true" stored="true"/>
- <field name="patternreplacefilt" type="patternreplacefilt" indexed="true" stored="true"/>
- <field name="porterfilt" type="porterfilt" indexed="true" stored="true"/>
- <field name="engporterfilt" type="engporterfilt" indexed="true" stored="true"/>
- <field name="custengporterfilt" type="custengporterfilt" indexed="true" stored="true"/>
- <field name="stopfilt" type="stopfilt" indexed="true" stored="true"/>
- <field name="custstopfilt" type="custstopfilt" indexed="true" stored="true"/>
- <field name="lengthfilt" type="lengthfilt" indexed="true" stored="true"/>
- <field name="dedup" type="dedup" indexed="true" stored="true"/>
- <field name="wdf_nocase" type="wdf_nocase" indexed="true" stored="true"/>
- <field name="wdf_preserve" type="wdf_preserve" indexed="true" stored="true"/>
-
- <field name="numberpartfail" type="failtype1" indexed="true" stored="true"/>
-
- <field name="nullfirst" type="string" indexed="true" stored="true" sortMissingFirst="true"/>
-
- <field name="subword" type="subword" indexed="true" stored="true"/>
- <field name="sku1" type="skutype1" indexed="true" stored="true"/>
- <field name="sku2" type="skutype2" indexed="true" stored="true"/>
-
- <field name="textgap" type="textgap" indexed="true" stored="true"/>
-
- <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
- <field name="multiDefault" type="string" indexed="true" stored="true" default="muLti-Default" multiValued="true"/>
- <field name="intDefault" type="int" indexed="true" stored="true" default="42" multiValued="false"/>
-
- <field name="extractedDate" type="date" indexed="true" stored="true" multiValued="true"/>
- <field name="extractedContent" type="text" indexed="true" stored="true" multiValued="true"/>
- <field name="extractedProducer" type="text" indexed="true" stored="true" multiValued="true"/>
- <field name="extractedCreator" type="text" indexed="true" stored="true" multiValued="true"/>
- <field name="extractedKeywords" type="text" indexed="true" stored="true" multiValued="true"/>
- <field name="extractedAuthor" type="text" indexed="true" stored="true" multiValued="true"/>
- <field name="extractedLanguage" type="string" indexed="true" stored="true" multiValued="true"/>
- <field name="resourceName" type="string" indexed="true" stored="true" multiValued="true"/>
-
- <field name="extractionLiteralMV" type="string" indexed="true" stored="true" multiValued="true"/>
- <field name="extractionLiteral" type="string" indexed="true" stored="true" multiValued="false"/>
-
- <field name="defaultExtr" type="string" indexed="true" stored="false" />
-
- <!-- Dynamic field definitions. If a field name is not found, dynamicFields
- will be used if the name matches any of the patterns.
- RESTRICTION: the glob-like pattern in the name attribute must have
- a "*" only at the start or the end.
- EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
- Longer patterns will be matched first. if equal size patterns
- both match, the first appearing in the schema will be used.
- -->
- <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
- <dynamicField name="*_s" type="string" indexed="true" stored="true"/>
- <dynamicField name="*_s1" type="string" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
- <dynamicField name="*_t" type="text" indexed="true" stored="true"/>
- <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
- <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
- <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
- <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
-
- <dynamicField name="*_sI" type="string" indexed="true" stored="false"/>
- <dynamicField name="*_sS" type="string" indexed="false" stored="true"/>
- <dynamicField name="t_*" type="text" indexed="true" stored="true"/>
- <dynamicField name="tv_*" type="text" indexed="true" stored="true"
- termVectors="true" termPositions="true" termOffsets="true"/>
-
- <dynamicField name="stream_*" type="text" indexed="true" stored="true"/>
- <dynamicField name="Content*" type="text" indexed="true" stored="true"/>
-
-
- <!-- special fields for dynamic copyField test -->
- <dynamicField name="dynamic_*" type="string" indexed="true" stored="true"/>
- <dynamicField name="*_dynamic" type="string" indexed="true" stored="true"/>
-
- <!-- for testing to ensure that longer patterns are matched first -->
- <dynamicField name="*aa" type="string" indexed="true" stored="true"/>
- <dynamicField name="*aaa" type="int" indexed="false" stored="true"/>
-
- <!-- ignored because not stored or indexed -->
- <dynamicField name="ignored_*" type="text" indexed="false" stored="false"/>
-
- </fields>
-
- <defaultSearchField>text</defaultSearchField>
- <uniqueKey>id</uniqueKey>
+
+ <field name="id" type="string" indexed="true" stored="true" multiValued="false" required="false"/>
+ <field name="name" type="nametext" indexed="true" stored="true"/>
+ <field name="text" type="text" indexed="true" stored="false"/>
+ <field name="subject" type="text" indexed="true" stored="true"/>
+ <field name="title" type="nametext" indexed="true" stored="true"/>
+ <field name="weight" type="float" indexed="true" stored="true"/>
+ <field name="bday" type="date" indexed="true" stored="true"/>
+
+ <field name="title_stemmed" type="text" indexed="true" stored="false"/>
+ <field name="title_lettertok" type="lettertok" indexed="true" stored="false"/>
+
+ <field name="syn" type="syn" indexed="true" stored="true"/>
+
+ <!-- to test property inheritance and overriding -->
+ <field name="shouldbeunstored" type="unstored"/>
+ <field name="shouldbestored" type="unstored" stored="true"/>
+ <field name="shouldbeunindexed" type="unstored" indexed="false" stored="true"/>
+
+
+ <!-- test different combinations of indexed and stored -->
+ <field name="bind" type="boolean" indexed="true" stored="false"/>
+ <field name="bsto" type="boolean" indexed="false" stored="true"/>
+ <field name="bindsto" type="boolean" indexed="true" stored="true"/>
+ <field name="isto" type="int" indexed="false" stored="true"/>
+ <field name="iind" type="int" indexed="true" stored="false"/>
+ <field name="ssto" type="string" indexed="false" stored="true"/>
+ <field name="sind" type="string" indexed="true" stored="false"/>
+ <field name="sindsto" type="string" indexed="true" stored="true"/>
+
+ <!-- test combinations of term vector settings -->
+ <field name="test_basictv" type="text" termVectors="true"/>
+ <field name="test_notv" type="text" termVectors="false"/>
+ <field name="test_postv" type="text" termVectors="true" termPositions="true"/>
+ <field name="test_offtv" type="text" termVectors="true" termOffsets="true"/>
+ <field name="test_posofftv" type="text" termVectors="true"
+ termPositions="true" termOffsets="true"/>
+
+ <!-- test highlit field settings -->
+ <field name="test_hlt" type="highlittext" indexed="true"/>
+ <field name="test_hlt_off" type="highlittext" indexed="true"/>
+
+ <!-- fields to test individual tokenizers and tokenfilters -->
+ <field name="teststop" type="teststop" indexed="true" stored="true"/>
+ <field name="lowertok" type="lowertok" indexed="true" stored="true"/>
+ <field name="keywordtok" type="keywordtok" indexed="true" stored="true"/>
+ <field name="standardtok" type="standardtok" indexed="true" stored="true"/>
+ <field name="HTMLstandardtok" type="HTMLstandardtok" indexed="true" stored="true"/>
+ <field name="lettertok" type="lettertok" indexed="true" stored="true"/>
+ <field name="whitetok" type="whitetok" indexed="true" stored="true"/>
+ <field name="HTMLwhitetok" type="HTMLwhitetok" indexed="true" stored="true"/>
+ <field name="standardtokfilt" type="standardtokfilt" indexed="true" stored="true"/>
+ <field name="standardfilt" type="standardfilt" indexed="true" stored="true"/>
+ <field name="lowerfilt" type="lowerfilt" indexed="true" stored="true"/>
+ <field name="patternreplacefilt" type="patternreplacefilt" indexed="true" stored="true"/>
+ <field name="porterfilt" type="porterfilt" indexed="true" stored="true"/>
+ <field name="engporterfilt" type="engporterfilt" indexed="true" stored="true"/>
+ <field name="custengporterfilt" type="custengporterfilt" indexed="true" stored="true"/>
+ <field name="stopfilt" type="stopfilt" indexed="true" stored="true"/>
+ <field name="custstopfilt" type="custstopfilt" indexed="true" stored="true"/>
+ <field name="lengthfilt" type="lengthfilt" indexed="true" stored="true"/>
+ <field name="dedup" type="dedup" indexed="true" stored="true"/>
+ <field name="wdf_nocase" type="wdf_nocase" indexed="true" stored="true"/>
+ <field name="wdf_preserve" type="wdf_preserve" indexed="true" stored="true"/>
+
+ <field name="numberpartfail" type="failtype1" indexed="true" stored="true"/>
+
+ <field name="nullfirst" type="string" indexed="true" stored="true" sortMissingFirst="true"/>
+
+ <field name="subword" type="subword" indexed="true" stored="true"/>
+ <field name="sku1" type="skutype1" indexed="true" stored="true"/>
+ <field name="sku2" type="skutype2" indexed="true" stored="true"/>
+
+ <field name="textgap" type="textgap" indexed="true" stored="true"/>
+
+ <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
+ <field name="multiDefault" type="string" indexed="true" stored="true" default="muLti-Default" multiValued="true"/>
+ <field name="intDefault" type="int" indexed="true" stored="true" default="42" multiValued="false"/>
+
+ <field name="extractedDate" type="date" indexed="true" stored="true" multiValued="true"/>
+ <field name="extractedContent" type="text" indexed="true" stored="true" multiValued="true"/>
+ <field name="extractedProducer" type="text" indexed="true" stored="true" multiValued="true"/>
+ <field name="extractedCreator" type="text" indexed="true" stored="true" multiValued="true"/>
+ <field name="extractedKeywords" type="text" indexed="true" stored="true" multiValued="true"/>
+ <field name="extractedAuthor" type="text" indexed="true" stored="true" multiValued="true"/>
+ <field name="extractedLanguage" type="string" indexed="true" stored="true" multiValued="true"/>
+ <field name="resourceName" type="string" indexed="true" stored="true" multiValued="true"/>
+
+ <field name="extractionLiteralMV" type="string" indexed="true" stored="true" multiValued="true"/>
+ <field name="extractionLiteral" type="string" indexed="true" stored="true" multiValued="false"/>
+
+ <field name="defaultExtr" type="string" indexed="true" stored="false"/>
+
+ <!-- Dynamic field definitions. If a field name is not found, dynamicFields
+ will be used if the name matches any of the patterns.
+ RESTRICTION: the glob-like pattern in the name attribute must have
+ a "*" only at the start or the end.
+ EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
+ Longer patterns will be matched first. if equal size patterns
+ both match, the first appearing in the schema will be used.
+ -->
+ <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
+ <dynamicField name="*_s" type="string" indexed="true" stored="true"/>
+ <dynamicField name="*_s1" type="string" indexed="true" stored="true" multiValued="false"/>
+ <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
+ <dynamicField name="*_t" type="text" indexed="true" stored="true"/>
+ <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
+ <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
+ <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
+ <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
+
+ <dynamicField name="*_sI" type="string" indexed="true" stored="false"/>
+ <dynamicField name="*_sS" type="string" indexed="false" stored="true"/>
+ <dynamicField name="t_*" type="text" indexed="true" stored="true"/>
+ <dynamicField name="tv_*" type="text" indexed="true" stored="true"
+ termVectors="true" termPositions="true" termOffsets="true"/>
+
+ <dynamicField name="stream_*" type="text" indexed="true" stored="true"/>
+ <dynamicField name="Content*" type="text" indexed="true" stored="true"/>
+
+
+ <!-- special fields for dynamic copyField test -->
+ <dynamicField name="dynamic_*" type="string" indexed="true" stored="true"/>
+ <dynamicField name="*_dynamic" type="string" indexed="true" stored="true"/>
+
+ <!-- for testing to ensure that longer patterns are matched first -->
+ <dynamicField name="*aa" type="string" indexed="true" stored="true"/>
+ <dynamicField name="*aaa" type="int" indexed="false" stored="true"/>
+
+ <!-- ignored because not stored or indexed -->
+ <dynamicField name="ignored_*" type="text" indexed="false" stored="false"/>
+
+
+ <defaultSearchField>text</defaultSearchField>
+ <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 different
ways, or to add multiple fields to the same field for easier/faster searching.
-->
- <copyField source="title" dest="title_stemmed"/>
- <copyField source="title" dest="title_lettertok"/>
-
- <copyField source="title" dest="text"/>
- <copyField source="subject" dest="text"/>
-
- <copyField source="*_t" dest="text"/>
-
- <!-- dynamic destination -->
- <copyField source="*_dynamic" dest="dynamic_*"/>
-
+ <copyField source="title" dest="title_stemmed"/>
+ <copyField source="title" dest="title_lettertok"/>
+
+ <copyField source="title" dest="text"/>
+ <copyField source="subject" dest="text"/>
+
+ <copyField source="*_t" dest="text"/>
+
+ <!-- dynamic destination -->
+ <copyField source="*_dynamic" dest="dynamic_*"/>
+
</schema>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/03a06bb3/solr/contrib/langid/src/test-files/langid/solr/collection1/conf/schema.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/langid/src/test-files/langid/solr/collection1/conf/schema.xml b/solr/contrib/langid/src/test-files/langid/solr/collection1/conf/schema.xml
index cb5a6e8..8fe71e9 100644
--- a/solr/contrib/langid/src/test-files/langid/solr/collection1/conf/schema.xml
+++ b/solr/contrib/langid/src/test-files/langid/solr/collection1/conf/schema.xml
@@ -26,53 +26,50 @@
-->
<schema name="test" version="1.6">
- <types>
- <fieldType name="string" class="solr.StrField" sortMissingLast="true"/>
- <!-- solr.TextField allows the specification of custom
- text analyzers specified as a tokenizer and a list
- of token filters.
- -->
- <fieldType name="text" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.StandardFilterFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory"/>
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <fieldType name="nametext" class="solr.TextField">
- <analyzer class="org.apache.lucene.analysis.core.WhitespaceAnalyzer"/>
- </fieldType>
- </types>
-
-
- <fields>
- <field name="id" type="string" indexed="true" stored="true" multiValued="false" required="false"/>
- <field name="name" type="nametext" indexed="true" stored="true"/>
- <field name="subject" type="text" indexed="true" stored="true"/>
-
-
- <!-- Dynamic field definitions. If a field name is not found, dynamicFields
- will be used if the name matches any of the patterns.
- RESTRICTION: the glob-like pattern in the name attribute must have
- a "*" only at the start or the end.
- EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
- Longer patterns will be matched first. if equal size patterns
- both match, the first appearing in the schema will be used.
- -->
- <dynamicField name="*_s" type="string" indexed="true" stored="true"/>
- <dynamicField name="*_sm" type="string" indexed="true" stored="true" multiValued="true" />
-
- <!-- Fields for language identification -->
- <dynamicField name="name_*" type="string" indexed="true" stored="false"/>
- <dynamicField name="subject_*" type="string" indexed="true" stored="false"/>
-
- </fields>
-
- <defaultSearchField>name</defaultSearchField>
- <uniqueKey>id</uniqueKey>
+
+ <fieldType name="string" class="solr.StrField" sortMissingLast="true"/>
+ <!-- solr.TextField allows the specification of custom
+ text analyzers specified as a tokenizer and a list
+ of token filters.
+ -->
+ <fieldType name="text" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.StandardFilterFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory"/>
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <fieldType name="nametext" class="solr.TextField">
+ <analyzer class="org.apache.lucene.analysis.core.WhitespaceAnalyzer"/>
+ </fieldType>
+
+
+ <field name="id" type="string" indexed="true" stored="true" multiValued="false" required="false"/>
+ <field name="name" type="nametext" indexed="true" stored="true"/>
+ <field name="subject" type="text" indexed="true" stored="true"/>
+
+
+ <!-- Dynamic field definitions. If a field name is not found, dynamicFields
+ will be used if the name matches any of the patterns.
+ RESTRICTION: the glob-like pattern in the name attribute must have
+ a "*" only at the start or the end.
+ EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
+ Longer patterns will be matched first. if equal size patterns
+ both match, the first appearing in the schema will be used.
+ -->
+ <dynamicField name="*_s" type="string" indexed="true" stored="true"/>
+ <dynamicField name="*_sm" type="string" indexed="true" stored="true" multiValued="true"/>
+
+ <!-- Fields for language identification -->
+ <dynamicField name="name_*" type="string" indexed="true" stored="false"/>
+ <dynamicField name="subject_*" type="string" indexed="true" stored="false"/>
+
+
+ <defaultSearchField>name</defaultSearchField>
+ <uniqueKey>id</uniqueKey>
</schema>