You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@uima.apache.org by mb...@apache.org on 2008/06/23 14:41:35 UTC
svn commit: r670547 - in
/incubator/uima/sandbox/trunk/ConceptMapper/desc/analysis_engine/primitive:
ConceptMapperOffsetTokenizer.xml DictTerm.xml OffsetTokenizer.xml
Author: mbaessler
Date: Mon Jun 23 05:41:35 2008
New Revision: 670547
URL: http://svn.apache.org/viewvc?rev=670547&view=rev
Log:
UIMA-1033
format XML files
https://issues.apache.org/jira/browse/UIMA-1033
Modified:
incubator/uima/sandbox/trunk/ConceptMapper/desc/analysis_engine/primitive/ConceptMapperOffsetTokenizer.xml
incubator/uima/sandbox/trunk/ConceptMapper/desc/analysis_engine/primitive/DictTerm.xml
incubator/uima/sandbox/trunk/ConceptMapper/desc/analysis_engine/primitive/OffsetTokenizer.xml
Modified: incubator/uima/sandbox/trunk/ConceptMapper/desc/analysis_engine/primitive/ConceptMapperOffsetTokenizer.xml
URL: http://svn.apache.org/viewvc/incubator/uima/sandbox/trunk/ConceptMapper/desc/analysis_engine/primitive/ConceptMapperOffsetTokenizer.xml?rev=670547&r1=670546&r2=670547&view=diff
==============================================================================
--- incubator/uima/sandbox/trunk/ConceptMapper/desc/analysis_engine/primitive/ConceptMapperOffsetTokenizer.xml (original)
+++ incubator/uima/sandbox/trunk/ConceptMapper/desc/analysis_engine/primitive/ConceptMapperOffsetTokenizer.xml Mon Jun 23 05:41:35 2008
@@ -1,392 +1,495 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<taeDescription xmlns="http://uima.apache.org/resourceSpecifier">
-<frameworkImplementation>org.apache.uima.java</frameworkImplementation>
-<primitive>true</primitive>
-<annotatorImplementationName>org.apache.uima.conceptMapper.ConceptMapper</annotatorImplementationName>
-<analysisEngineMetaData>
-<name>ConceptMapper</name>
-<description></description>
-<version>1</version>
-<vendor></vendor>
-<configurationParameters>
-<configurationParameter>
-<name>caseMatch</name>
-<description>this parameter specifies the case folding mode: ignoreall - fold everything to lowercase for matching insensitive - fold only tokens with initial caps to lowercase digitfold - fold all (and only) tokens with a digit sensitive - perform no case folding</description>
-<type>String</type>
-<multiValued>false</multiValued>
-<mandatory>true</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>Stemmer</name>
-<description>Name of stemmer class to use before matching. MUST have a zero-parameter constructor! If not specified, no stemming will be performed.</description>
-<type>String</type>
-<multiValued>false</multiValued>
-<mandatory>false</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>ResultingAnnotationName</name>
-<description>Name of the annotation type created by this TAE, must match the typeSystemDescription entry</description>
-<type>String</type>
-<multiValued>false</multiValued>
-<mandatory>true</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>ResultingEnclosingSpanName</name>
-<description>Name of the feature in the resultingAnnotation to contain the span that encloses it (i.e. its sentence)</description>
-<type>String</type>
-<multiValued>false</multiValued>
-<mandatory>false</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>AttributeList</name>
-<description>List of attribute names for XML dictionary entry record - must correspond to FeatureList</description>
-<type>String</type>
-<multiValued>true</multiValued>
-<mandatory>true</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>FeatureList</name>
-<description>List of feature names for CAS annotation - must correspond to AttributeList</description>
-<type>String</type>
-<multiValued>true</multiValued>
-<mandatory>true</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>TokenAnnotation</name>
-<description></description>
-<type>String</type>
-<multiValued>false</multiValued>
-<mandatory>true</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>TokenClassFeatureName</name>
-<description>Name of feature used when doing lookups against IncludedTokenClasses and ExcludedTokenClasses</description>
-<type>String</type>
-<multiValued>false</multiValued>
-<mandatory>false</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>TokenTextFeatureName</name>
-<description></description>
-<type>String</type>
-<multiValued>false</multiValued>
-<mandatory>false</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>SpanFeatureStructure</name>
-<description>Type of annotation which corresponds to spans of data for processing (e.g. a Sentence)</description>
-<type>String</type>
-<multiValued>false</multiValued>
-<mandatory>true</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>OrderIndependentLookup</name>
-<description>True if should ignore element order during lookup (i.e., "top box" would equal "box top"). Default is False.</description>
-<type>Boolean</type>
-<multiValued>false</multiValued>
-<mandatory>false</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>TokenTypeFeatureName</name>
-<description>Name of feature used when doing lookups against IncludedTokenTypes and ExcludedTokenTypes</description>
-<type>String</type>
-<multiValued>false</multiValued>
-<mandatory>false</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>IncludedTokenTypes</name>
-<description>Type of tokens to include in lookups (if not supplied, then all types are included except those specifically mentioned in ExcludedTokenTypes)</description>
-<type>Integer</type>
-<multiValued>true</multiValued>
-<mandatory>false</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>ExcludedTokenTypes</name>
-<description></description>
-<type>Integer</type>
-<multiValued>true</multiValued>
-<mandatory>false</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>ExcludedTokenClasses</name>
-<description>Class of tokens to exclude from lookups (if not supplied, then all classes are excluded except those specifically mentioned in IncludedTokenClasses, unless IncludedTokenClasses is not supplied, in which case none are excluded)</description>
-<type>String</type>
-<multiValued>true</multiValued>
-<mandatory>false</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>IncludedTokenClasses</name>
-<description>Class of tokens to include in lookups (if not supplied, then all classes are included except those specifically mentioned in ExcludedTokenClasses)</description>
-<type>String</type>
-<multiValued>true</multiValued>
-<mandatory>false</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>TokenClassWriteBackFeatureNames</name>
-<description>names of features that should be written back to a token, such as a POS tag</description>
-<type>String</type>
-<multiValued>true</multiValued>
-<mandatory>false</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>ResultingAnnotationMatchedTextFeature</name>
-<type>String</type>
-<multiValued>false</multiValued>
-<mandatory>false</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>PrintDictionary</name>
-<type>Boolean</type>
-<multiValued>false</multiValued>
-<mandatory>false</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>SearchStrategy</name>
-<description>Can be either "SkipAnyMatch", "SkipAnyMatchAllowOverlap" or "ContiguousMatch" ContiguousMatch: longest match of contiguous tokens within enclosing span(taking into account included/excluded items). DEFAULT strategy SkipAnyMatch: longest match of not-necessarily contiguous tokens within enclosing span (taking into account included/excluded items). Subsequent lookups begin in span after complete match. IMPLIES order-independent lookup SkipAnyMatchAllowOverlap: longest match of not-necessarily contiguous tokens within enclosing span (taking into account included/excluded items). Subsequent lookups begin in span after next token. IMPLIES order-independent lookup</description>
-<type>String</type>
-<multiValued>false</multiValued>
-<mandatory>false</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>StopWords</name>
-<type>String</type>
-<multiValued>true</multiValued>
-<mandatory>false</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>FindAllMatches</name>
-<type>Boolean</type>
-<multiValued>false</multiValued>
-<mandatory>false</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>MatchedTokensFeatureName</name>
-<type>String</type>
-<multiValued>false</multiValued>
-<mandatory>false</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>ReplaceCommaWithAND</name>
-<type>Boolean</type>
-<multiValued>false</multiValued>
-<mandatory>false</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>TokenizerDescriptorPath</name>
-<type>String</type>
-<multiValued>false</multiValued>
-<mandatory>true</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>LanguageID</name>
-<type>String</type>
-<multiValued>false</multiValued>
-<mandatory>false</mandatory>
-</configurationParameter>
-</configurationParameters>
-<configurationParameterSettings>
-<nameValuePair>
-<name>caseMatch</name>
-<value>
-<string>ignoreall</string>
-</value>
-</nameValuePair>
-<nameValuePair>
-<name>AttributeList</name>
-<value>
-<array>
-<string>canonical</string>
-</array>
-</value>
-</nameValuePair>
-<nameValuePair>
-<name>FeatureList</name>
-<value>
-<array>
-<string>DictCanon</string>
-</array>
-</value>
-</nameValuePair>
-<nameValuePair>
-<name>TokenAnnotation</name>
-<value>
-<string>uima.tt.TokenAnnotation</string>
-</value>
-</nameValuePair>
-<nameValuePair>
-<name>ResultingAnnotationName</name>
-<value>
-<string>org.apache.uima.conceptMapper.DictTerm</string>
-</value>
-</nameValuePair>
-<nameValuePair>
-<name>SpanFeatureStructure</name>
-<value>
-<string>uima.tcas.DocumentAnnotation</string>
-</value>
-</nameValuePair>
-<nameValuePair>
-<name>OrderIndependentLookup</name>
-<value>
-<boolean>false</boolean>
-</value>
-</nameValuePair>
-<nameValuePair>
-<name>TokenClassWriteBackFeatureNames</name>
-<value>
-<array/>
-</value>
-</nameValuePair>
-<nameValuePair>
-<name>IncludedTokenClasses</name>
-<value>
-<array/>
-</value>
-</nameValuePair>
-<nameValuePair>
-<name>PrintDictionary</name>
-<value>
-<boolean>false</boolean>
-</value>
-</nameValuePair>
-<nameValuePair>
-<name>FindAllMatches</name>
-<value>
-<boolean>false</boolean>
-</value>
-</nameValuePair>
-<nameValuePair>
-<name>StopWords</name>
-<value>
-<array/>
-</value>
-</nameValuePair>
-<nameValuePair>
-<name>ReplaceCommaWithAND</name>
-<value>
-<boolean>false</boolean>
-</value>
-</nameValuePair>
-<nameValuePair>
-<name>TokenizerDescriptorPath</name>
-<value>
-<string>/OtherStuff/IBM/eclipse-apacheuima/conceptMapper/descriptors/analysis_engine/primitive/OffsetTokenizer.xml</string>
-</value>
-</nameValuePair>
-<nameValuePair>
-<name>ResultingEnclosingSpanName</name>
-<value>
-<string>enclosingSpan</string>
-</value>
-</nameValuePair>
-<nameValuePair>
-<name>MatchedTokensFeatureName</name>
-<value>
-<string>matchedTokens</string>
-</value>
-</nameValuePair>
-<nameValuePair>
-<name>ResultingAnnotationMatchedTextFeature</name>
-<value>
-<string>matchedText</string>
-</value>
-</nameValuePair>
-<nameValuePair>
-<name>SearchStrategy</name>
-<value>
-<string>ContiguousMatch</string>
-</value>
-</nameValuePair>
-<nameValuePair>
-<name>LanguageID</name>
-<value>
-<string>en</string>
-</value>
-</nameValuePair>
-</configurationParameterSettings>
-<typeSystemDescription>
-<imports>
-<import name="org.apache.uima.conceptMapper.DictTerm"/>
-<import name="org.apache.uima.conceptMapper.support.tokenizer.TokenAnnotation"/>
-</imports>
-<types>
-<typeDescription>
-<name>uima.tt.TokenAnnotation</name>
-<description></description>
-<supertypeName>uima.tcas.Annotation</supertypeName>
-<features>
-<featureDescription>
-<name>SemClass</name>
-<description>semantic class of token</description>
-<rangeTypeName>uima.cas.String</rangeTypeName>
-</featureDescription>
-<featureDescription>
-<name>POS</name>
-<description>Part of SPeech of term to which this token is a part</description>
-<rangeTypeName>uima.cas.String</rangeTypeName>
-</featureDescription>
-<featureDescription>
-<name>frost_TokenType</name>
-<description></description>
-<rangeTypeName>uima.cas.Integer</rangeTypeName>
-</featureDescription>
-</features>
-</typeDescription>
-</types>
-</typeSystemDescription>
-<typePriorities>
-<priorityList>
-<!-- <type>uima.tt.SentenceAnnotation</type> -->
-<type>uima.tt.TokenAnnotation</type>
-</priorityList>
-</typePriorities>
-<fsIndexCollection/>
-<capabilities>
-<capability>
-<inputs>
-<type allAnnotatorFeatures="true">uima.tt.TokenAnnotation</type>
-<!-- <type allAnnotatorFeatures="true">uima.tt.SentenceAnnotation</type>
-<type allAnnotatorFeatures="true">uima.tt.ParagraphAnnotation</type> -->
-</inputs>
-<outputs>
-<type allAnnotatorFeatures="true">org.apache.uima.conceptMapper.DictTerm</type>
-<type allAnnotatorFeatures="true">uima.tt.TokenAnnotation</type>
-<type allAnnotatorFeatures="true">org.apache.uima.conceptMapper.support.tokenizer.TokenAnnotation</type>
-<type allAnnotatorFeatures="true">uima.tcas.DocumentAnnotation</type>
-</outputs>
-<languagesSupported/>
-</capability>
-</capabilities>
-<operationalProperties>
-<modifiesCas>true</modifiesCas>
-<multipleDeploymentAllowed>true</multipleDeploymentAllowed>
-<outputsNewCASes>false</outputsNewCASes>
-</operationalProperties>
-</analysisEngineMetaData>
-<externalResourceDependencies>
-<externalResourceDependency>
-<key>DictionaryFile</key>
-<description>dictionary file loader.</description>
-<interfaceName>org.apache.uima.conceptMapper.support.dictionaryResource.DictionaryResource</interfaceName>
-<optional>false</optional>
-</externalResourceDependency>
-</externalResourceDependencies>
-<resourceManagerConfiguration>
-<externalResources>
-<externalResource>
-<name>DictionaryFileName</name>
-<description>A file containing the dictionary. Modify this URL to use a different dictionary.</description>
-<fileResourceSpecifier>
-<fileUrl>file:dict/testDict.xml</fileUrl>
-</fileResourceSpecifier>
-<implementationName>org.apache.uima.conceptMapper.support.dictionaryResource.DictionaryResource_impl</implementationName>
-</externalResource>
-</externalResources>
-<externalResourceBindings>
-<externalResourceBinding>
-<key>DictionaryFile</key>
-<resourceName>DictionaryFileName</resourceName>
-</externalResourceBinding>
-</externalResourceBindings>
-</resourceManagerConfiguration>
-</taeDescription>
+<?xml version="1.0" encoding="UTF-8"?>
+<taeDescription xmlns="http://uima.apache.org/resourceSpecifier">
+ <frameworkImplementation>org.apache.uima.java</frameworkImplementation>
+ <primitive>true</primitive>
+ <annotatorImplementationName>org.apache.uima.conceptMapper.ConceptMapper</annotatorImplementationName>
+ <analysisEngineMetaData>
+ <name>ConceptMapper</name>
+ <description></description>
+ <version>1</version>
+ <vendor></vendor>
+ <configurationParameters>
+ <configurationParameter>
+ <name>caseMatch</name>
+ <description>
+ this parameter specifies the case folding mode:
+ ignoreall - fold everything to lowercase for
+ matching insensitive - fold only tokens with initial
+ caps to lowercase digitfold - fold all (and only)
+ tokens with a digit sensitive - perform no case
+ folding
+ </description>
+ <type>String</type>
+ <multiValued>false</multiValued>
+ <mandatory>true</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>Stemmer</name>
+ <description>
+ Name of stemmer class to use before matching. MUST
+ have a zero-parameter constructor! If not specified,
+ no stemming will be performed.
+ </description>
+ <type>String</type>
+ <multiValued>false</multiValued>
+ <mandatory>false</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>ResultingAnnotationName</name>
+ <description>
+ Name of the annotation type created by this TAE,
+ must match the typeSystemDescription entry
+ </description>
+ <type>String</type>
+ <multiValued>false</multiValued>
+ <mandatory>true</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>ResultingEnclosingSpanName</name>
+ <description>
+ Name of the feature in the resultingAnnotation to
+ contain the span that encloses it (i.e. its
+ sentence)
+ </description>
+ <type>String</type>
+ <multiValued>false</multiValued>
+ <mandatory>false</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>AttributeList</name>
+ <description>
+ List of attribute names for XML dictionary entry
+ record - must correspond to FeatureList
+ </description>
+ <type>String</type>
+ <multiValued>true</multiValued>
+ <mandatory>true</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>FeatureList</name>
+ <description>
+ List of feature names for CAS annotation - must
+ correspond to AttributeList
+ </description>
+ <type>String</type>
+ <multiValued>true</multiValued>
+ <mandatory>true</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>TokenAnnotation</name>
+ <description></description>
+ <type>String</type>
+ <multiValued>false</multiValued>
+ <mandatory>true</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>TokenClassFeatureName</name>
+ <description>
+ Name of feature used when doing lookups against
+ IncludedTokenClasses and ExcludedTokenClasses
+ </description>
+ <type>String</type>
+ <multiValued>false</multiValued>
+ <mandatory>false</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>TokenTextFeatureName</name>
+ <description></description>
+ <type>String</type>
+ <multiValued>false</multiValued>
+ <mandatory>false</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>SpanFeatureStructure</name>
+ <description>
+ Type of annotation which corresponds to spans of
+ data for processing (e.g. a Sentence)
+ </description>
+ <type>String</type>
+ <multiValued>false</multiValued>
+ <mandatory>true</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>OrderIndependentLookup</name>
+ <description>
+ True if should ignore element order during lookup
+ (i.e., "top box" would equal "box top"). Default is
+ False.
+ </description>
+ <type>Boolean</type>
+ <multiValued>false</multiValued>
+ <mandatory>false</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>TokenTypeFeatureName</name>
+ <description>
+ Name of feature used when doing lookups against
+ IncludedTokenTypes and ExcludedTokenTypes
+ </description>
+ <type>String</type>
+ <multiValued>false</multiValued>
+ <mandatory>false</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>IncludedTokenTypes</name>
+ <description>
+ Type of tokens to include in lookups (if not
+ supplied, then all types are included except those
+ specifically mentioned in ExcludedTokenTypes)
+ </description>
+ <type>Integer</type>
+ <multiValued>true</multiValued>
+ <mandatory>false</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>ExcludedTokenTypes</name>
+ <description></description>
+ <type>Integer</type>
+ <multiValued>true</multiValued>
+ <mandatory>false</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>ExcludedTokenClasses</name>
+ <description>
+ Class of tokens to exclude from lookups (if not
+ supplied, then all classes are excluded except those
+ specifically mentioned in IncludedTokenClasses,
+ unless IncludedTokenClasses is not supplied, in
+ which case none are excluded)
+ </description>
+ <type>String</type>
+ <multiValued>true</multiValued>
+ <mandatory>false</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>IncludedTokenClasses</name>
+ <description>
+ Class of tokens to include in lookups (if not
+ supplied, then all classes are included except those
+ specifically mentioned in ExcludedTokenClasses)
+ </description>
+ <type>String</type>
+ <multiValued>true</multiValued>
+ <mandatory>false</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>TokenClassWriteBackFeatureNames</name>
+ <description>
+ names of features that should be written back to a
+ token, such as a POS tag
+ </description>
+ <type>String</type>
+ <multiValued>true</multiValued>
+ <mandatory>false</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>ResultingAnnotationMatchedTextFeature</name>
+ <type>String</type>
+ <multiValued>false</multiValued>
+ <mandatory>false</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>PrintDictionary</name>
+ <type>Boolean</type>
+ <multiValued>false</multiValued>
+ <mandatory>false</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>SearchStrategy</name>
+ <description>
+ Can be either "SkipAnyMatch",
+ "SkipAnyMatchAllowOverlap" or
+ "ContiguousMatch" ContiguousMatch: longest
+ match of contiguous tokens within enclosing
+ span(taking into account included/excluded items).
+ DEFAULT strategy SkipAnyMatch: longest match of
+ not-necessarily contiguous tokens within enclosing
+ span (taking into account included/excluded items).
+ Subsequent lookups begin in span after complete
+ match. IMPLIES order-independent lookup
+ SkipAnyMatchAllowOverlap: longest match of
+ not-necessarily contiguous tokens within enclosing
+ span (taking into account included/excluded items).
+ Subsequent lookups begin in span after next token.
+ IMPLIES order-independent lookup
+ </description>
+ <type>String</type>
+ <multiValued>false</multiValued>
+ <mandatory>false</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>StopWords</name>
+ <type>String</type>
+ <multiValued>true</multiValued>
+ <mandatory>false</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>FindAllMatches</name>
+ <type>Boolean</type>
+ <multiValued>false</multiValued>
+ <mandatory>false</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>MatchedTokensFeatureName</name>
+ <type>String</type>
+ <multiValued>false</multiValued>
+ <mandatory>false</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>ReplaceCommaWithAND</name>
+ <type>Boolean</type>
+ <multiValued>false</multiValued>
+ <mandatory>false</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>TokenizerDescriptorPath</name>
+ <type>String</type>
+ <multiValued>false</multiValued>
+ <mandatory>true</mandatory>
+ </configurationParameter>
+ <configurationParameter>
+ <name>LanguageID</name>
+ <type>String</type>
+ <multiValued>false</multiValued>
+ <mandatory>false</mandatory>
+ </configurationParameter>
+ </configurationParameters>
+ <configurationParameterSettings>
+ <nameValuePair>
+ <name>caseMatch</name>
+ <value>
+ <string>ignoreall</string>
+ </value>
+ </nameValuePair>
+ <nameValuePair>
+ <name>AttributeList</name>
+ <value>
+ <array>
+ <string>canonical</string>
+ </array>
+ </value>
+ </nameValuePair>
+ <nameValuePair>
+ <name>FeatureList</name>
+ <value>
+ <array>
+ <string>DictCanon</string>
+ </array>
+ </value>
+ </nameValuePair>
+ <nameValuePair>
+ <name>TokenAnnotation</name>
+ <value>
+ <string>uima.tt.TokenAnnotation</string>
+ </value>
+ </nameValuePair>
+ <nameValuePair>
+ <name>ResultingAnnotationName</name>
+ <value>
+ <string>
+ org.apache.uima.conceptMapper.DictTerm
+ </string>
+ </value>
+ </nameValuePair>
+ <nameValuePair>
+ <name>SpanFeatureStructure</name>
+ <value>
+ <string>uima.tcas.DocumentAnnotation</string>
+ </value>
+ </nameValuePair>
+ <nameValuePair>
+ <name>OrderIndependentLookup</name>
+ <value>
+ <boolean>false</boolean>
+ </value>
+ </nameValuePair>
+ <nameValuePair>
+ <name>TokenClassWriteBackFeatureNames</name>
+ <value>
+ <array />
+ </value>
+ </nameValuePair>
+ <nameValuePair>
+ <name>IncludedTokenClasses</name>
+ <value>
+ <array />
+ </value>
+ </nameValuePair>
+ <nameValuePair>
+ <name>PrintDictionary</name>
+ <value>
+ <boolean>false</boolean>
+ </value>
+ </nameValuePair>
+ <nameValuePair>
+ <name>FindAllMatches</name>
+ <value>
+ <boolean>false</boolean>
+ </value>
+ </nameValuePair>
+ <nameValuePair>
+ <name>StopWords</name>
+ <value>
+ <array />
+ </value>
+ </nameValuePair>
+ <nameValuePair>
+ <name>ReplaceCommaWithAND</name>
+ <value>
+ <boolean>false</boolean>
+ </value>
+ </nameValuePair>
+ <nameValuePair>
+ <name>TokenizerDescriptorPath</name>
+ <value>
+ <string>
+ /OtherStuff/IBM/eclipse-apacheuima/conceptMapper/descriptors/analysis_engine/primitive/OffsetTokenizer.xml
+ </string>
+ </value>
+ </nameValuePair>
+ <nameValuePair>
+ <name>ResultingEnclosingSpanName</name>
+ <value>
+ <string>enclosingSpan</string>
+ </value>
+ </nameValuePair>
+ <nameValuePair>
+ <name>MatchedTokensFeatureName</name>
+ <value>
+ <string>matchedTokens</string>
+ </value>
+ </nameValuePair>
+ <nameValuePair>
+ <name>ResultingAnnotationMatchedTextFeature</name>
+ <value>
+ <string>matchedText</string>
+ </value>
+ </nameValuePair>
+ <nameValuePair>
+ <name>SearchStrategy</name>
+ <value>
+ <string>ContiguousMatch</string>
+ </value>
+ </nameValuePair>
+ <nameValuePair>
+ <name>LanguageID</name>
+ <value>
+ <string>en</string>
+ </value>
+ </nameValuePair>
+ </configurationParameterSettings>
+ <typeSystemDescription>
+ <imports>
+ <import name="org.apache.uima.conceptMapper.DictTerm" />
+ <import
+ name="org.apache.uima.conceptMapper.support.tokenizer.TokenAnnotation" />
+ </imports>
+ <types>
+ <typeDescription>
+ <name>uima.tt.TokenAnnotation</name>
+ <description></description>
+ <supertypeName>uima.tcas.Annotation</supertypeName>
+ <features>
+ <featureDescription>
+ <name>SemClass</name>
+ <description>
+ semantic class of token
+ </description>
+ <rangeTypeName>
+ uima.cas.String
+ </rangeTypeName>
+ </featureDescription>
+ <featureDescription>
+ <name>POS</name>
+ <description>
+ Part of SPeech of term to which this
+ token is a part
+ </description>
+ <rangeTypeName>
+ uima.cas.String
+ </rangeTypeName>
+ </featureDescription>
+ <featureDescription>
+ <name>frost_TokenType</name>
+ <description></description>
+ <rangeTypeName>
+ uima.cas.Integer
+ </rangeTypeName>
+ </featureDescription>
+ </features>
+ </typeDescription>
+ </types>
+ </typeSystemDescription>
+ <typePriorities>
+ <priorityList>
+ <!-- <type>uima.tt.SentenceAnnotation</type> -->
+ <type>uima.tt.TokenAnnotation</type>
+ </priorityList>
+ </typePriorities>
+ <fsIndexCollection />
+ <capabilities>
+ <capability>
+ <inputs>
+ <type allAnnotatorFeatures="true">
+ uima.tt.TokenAnnotation
+ </type>
+ <!-- <type allAnnotatorFeatures="true">uima.tt.SentenceAnnotation</type>
+ <type allAnnotatorFeatures="true">uima.tt.ParagraphAnnotation</type> -->
+ </inputs>
+ <outputs>
+ <type allAnnotatorFeatures="true">
+ org.apache.uima.conceptMapper.DictTerm
+ </type>
+ <type allAnnotatorFeatures="true">
+ uima.tt.TokenAnnotation
+ </type>
+ <type allAnnotatorFeatures="true">
+ org.apache.uima.conceptMapper.support.tokenizer.TokenAnnotation
+ </type>
+ <type allAnnotatorFeatures="true">
+ uima.tcas.DocumentAnnotation
+ </type>
+ </outputs>
+ <languagesSupported />
+ </capability>
+ </capabilities>
+ <operationalProperties>
+ <modifiesCas>true</modifiesCas>
+ <multipleDeploymentAllowed>true</multipleDeploymentAllowed>
+ <outputsNewCASes>false</outputsNewCASes>
+ </operationalProperties>
+ </analysisEngineMetaData>
+ <externalResourceDependencies>
+ <externalResourceDependency>
+ <key>DictionaryFile</key>
+ <description>dictionary file loader.</description>
+ <interfaceName>
+ org.apache.uima.conceptMapper.support.dictionaryResource.DictionaryResource
+ </interfaceName>
+ <optional>false</optional>
+ </externalResourceDependency>
+ </externalResourceDependencies>
+ <resourceManagerConfiguration>
+ <externalResources>
+ <externalResource>
+ <name>DictionaryFileName</name>
+ <description>
+ A file containing the dictionary. Modify this URL to
+ use a different dictionary.
+ </description>
+ <fileResourceSpecifier>
+ <fileUrl>file:dict/testDict.xml</fileUrl>
+ </fileResourceSpecifier>
+ <implementationName>
+ org.apache.uima.conceptMapper.support.dictionaryResource.DictionaryResource_impl
+ </implementationName>
+ </externalResource>
+ </externalResources>
+ <externalResourceBindings>
+ <externalResourceBinding>
+ <key>DictionaryFile</key>
+ <resourceName>DictionaryFileName</resourceName>
+ </externalResourceBinding>
+ </externalResourceBindings>
+ </resourceManagerConfiguration>
+</taeDescription>
Modified: incubator/uima/sandbox/trunk/ConceptMapper/desc/analysis_engine/primitive/DictTerm.xml
URL: http://svn.apache.org/viewvc/incubator/uima/sandbox/trunk/ConceptMapper/desc/analysis_engine/primitive/DictTerm.xml?rev=670547&r1=670546&r2=670547&view=diff
==============================================================================
--- incubator/uima/sandbox/trunk/ConceptMapper/desc/analysis_engine/primitive/DictTerm.xml (original)
+++ incubator/uima/sandbox/trunk/ConceptMapper/desc/analysis_engine/primitive/DictTerm.xml Mon Jun 23 05:41:35 2008
@@ -1,35 +1,35 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<typeSystemDescription xmlns="http://uima.apache.org/resourceSpecifier">
-<name>DictTerm</name>
-<version>1</version>
-<vendor>IBM</vendor>
-<types>
-<typeDescription>
-<name>org.apache.uima.conceptMapper.DictTerm</name>
-<description>Annotation for dictionary lookup matches</description>
-<supertypeName>uima.tcas.Annotation</supertypeName>
-<features>
-<featureDescription>
-<name>DictCanon</name>
-<description>canonical form</description>
-<rangeTypeName>uima.cas.String</rangeTypeName>
-</featureDescription>
-<featureDescription>
-<name>enclosingSpan</name>
-<description>span that this NoTerm is contained within (i.e. its sentence)</description>
-<rangeTypeName>uima.tcas.Annotation</rangeTypeName>
-</featureDescription>
-<featureDescription>
-<name>matchedText</name>
-<description></description>
-<rangeTypeName>uima.cas.String</rangeTypeName>
-</featureDescription>
-<featureDescription>
-<name>matchedTokens</name>
-<description></description>
-<rangeTypeName>uima.cas.FSArray</rangeTypeName>
-</featureDescription>
-</features>
-</typeDescription>
-</types>
-</typeSystemDescription>
+<?xml version="1.0" encoding="UTF-8"?>
+<typeSystemDescription xmlns="http://uima.apache.org/resourceSpecifier">
+ <name>DictTerm</name>
+ <version>1</version>
+ <vendor>IBM</vendor>
+ <types>
+ <typeDescription>
+ <name>org.apache.uima.conceptMapper.DictTerm</name>
+ <description>Annotation for dictionary lookup matches</description>
+ <supertypeName>uima.tcas.Annotation</supertypeName>
+ <features>
+ <featureDescription>
+ <name>DictCanon</name>
+ <description>canonical form</description>
+ <rangeTypeName>uima.cas.String</rangeTypeName>
+ </featureDescription>
+ <featureDescription>
+ <name>enclosingSpan</name>
+ <description>span that this NoTerm is contained within (i.e. its sentence)</description>
+ <rangeTypeName>uima.tcas.Annotation</rangeTypeName>
+ </featureDescription>
+ <featureDescription>
+ <name>matchedText</name>
+ <description></description>
+ <rangeTypeName>uima.cas.String</rangeTypeName>
+ </featureDescription>
+ <featureDescription>
+ <name>matchedTokens</name>
+ <description></description>
+ <rangeTypeName>uima.cas.FSArray</rangeTypeName>
+ </featureDescription>
+ </features>
+ </typeDescription>
+ </types>
+</typeSystemDescription>
Modified: incubator/uima/sandbox/trunk/ConceptMapper/desc/analysis_engine/primitive/OffsetTokenizer.xml
URL: http://svn.apache.org/viewvc/incubator/uima/sandbox/trunk/ConceptMapper/desc/analysis_engine/primitive/OffsetTokenizer.xml?rev=670547&r1=670546&r2=670547&view=diff
==============================================================================
--- incubator/uima/sandbox/trunk/ConceptMapper/desc/analysis_engine/primitive/OffsetTokenizer.xml (original)
+++ incubator/uima/sandbox/trunk/ConceptMapper/desc/analysis_engine/primitive/OffsetTokenizer.xml Mon Jun 23 05:41:35 2008
@@ -1,76 +1,83 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<taeDescription xmlns="http://uima.apache.org/resourceSpecifier">
-<frameworkImplementation>org.apache.uima.java</frameworkImplementation>
-<primitive>true</primitive>
-<annotatorImplementationName>org.apache.uima.conceptMapper.support.tokenizer.OffsetTokenizer</annotatorImplementationName>
-<analysisEngineMetaData>
-<name>OffsetTokenenizer</name>
-<configurationParameters>
-<configurationParameter>
-<name>caseMatch</name>
-<description>matching case sensitive or case insensitive</description>
-<type>String</type>
-<multiValued>false</multiValued>
-<mandatory>true</mandatory>
-</configurationParameter>
-<configurationParameter>
-<name>tokenDelimiters</name>
-<description>String of characters that separate tokens</description>
-<type>String</type>
-<multiValued>false</multiValued>
-<mandatory>false</mandatory>
-</configurationParameter>
-</configurationParameters>
-<configurationParameterSettings>
-<nameValuePair>
-<name>caseMatch</name>
-<value>
-<string>ignoreall</string>
-</value>
-</nameValuePair>
-<nameValuePair>
-<name>tokenDelimiters</name>
-<value>
-<string>/-*&@(){}|[]><\'`":;,$%+.?!</string>
-</value>
-</nameValuePair>
-</configurationParameterSettings>
-<typeSystemDescription>
-<types>
-<typeDescription>
-<name>org.apache.uima.conceptMapper.support.tokenizer.TokenAnnotation</name>
-<description/>
-<supertypeName>uima.tt.TokenAnnotation</supertypeName>
-<features>
-<featureDescription>
-<name>text</name>
-<description></description>
-<rangeTypeName>uima.cas.String</rangeTypeName>
-</featureDescription>
-</features>
-</typeDescription>
-<typeDescription>
-<name>uima.tt.TokenAnnotation</name>
-<description/>
-<supertypeName>uima.tcas.Annotation</supertypeName>
-</typeDescription>
-</types>
-</typeSystemDescription>
-<capabilities>
-<capability>
-<inputs/>
-<outputs>
-<type allAnnotatorFeatures="true">org.apache.uima.conceptMapper.support.tokenizer.TokenAnnotation</type>
-<type allAnnotatorFeatures="true">uima.tt.TokenAnnotation</type>
-<type allAnnotatorFeatures="true">uima.tcas.DocumentAnnotation</type>
-</outputs>
-<languagesSupported/>
-</capability>
-</capabilities>
-<operationalProperties>
-<modifiesCas>true</modifiesCas>
-<multipleDeploymentAllowed>true</multipleDeploymentAllowed>
-<outputsNewCASes>false</outputsNewCASes>
-</operationalProperties>
-</analysisEngineMetaData>
-</taeDescription>
+<?xml version="1.0" encoding="UTF-8"?>
+<taeDescription xmlns="http://uima.apache.org/resourceSpecifier">
+ <frameworkImplementation>org.apache.uima.java</frameworkImplementation>
+ <primitive>true</primitive>
+ <annotatorImplementationName>org.apache.uima.conceptMapper.support.tokenizer.OffsetTokenizer</annotatorImplementationName>
+ <analysisEngineMetaData>
+ <name>OffsetTokenenizer</name>
+ <configurationParameters>
+
+ <configurationParameter>
+ <name>caseMatch</name>
+ <description>matching case sensitive or case insensitive</description>
+ <type>String</type>
+ <multiValued>false</multiValued>
+ <mandatory>true</mandatory>
+ </configurationParameter>
+
+ <configurationParameter>
+ <name>tokenDelimiters</name>
+ <description>String of characters that separate tokens</description>
+ <type>String</type>
+ <multiValued>false</multiValued>
+ <mandatory>false</mandatory>
+ </configurationParameter>
+
+ </configurationParameters>
+
+ <configurationParameterSettings>
+ <nameValuePair>
+ <name>caseMatch</name>
+ <value>
+ <string>ignoreall</string>
+ </value>
+ </nameValuePair>
+ <nameValuePair>
+ <name>tokenDelimiters</name>
+ <value>
+ <string>
+ /-*&@(){}|[]><\'`":;,$%+.?!
+ </string>
+ </value>
+ </nameValuePair>
+ </configurationParameterSettings>
+
+ <typeSystemDescription>
+ <types>
+ <typeDescription>
+ <name>org.apache.uima.conceptMapper.support.tokenizer.TokenAnnotation</name>
+ <description />
+ <supertypeName>uima.tt.TokenAnnotation</supertypeName>
+ <features>
+ <featureDescription>
+ <name>text</name>
+ <description></description>
+ <rangeTypeName>uima.cas.String</rangeTypeName>
+ </featureDescription>
+ </features>
+ </typeDescription>
+ <typeDescription>
+ <name>uima.tt.TokenAnnotation</name>
+ <description />
+ <supertypeName>uima.tcas.Annotation</supertypeName>
+ </typeDescription>
+ </types>
+ </typeSystemDescription>
+ <capabilities>
+ <capability>
+ <inputs />
+ <outputs>
+ <type allAnnotatorFeatures="true">org.apache.uima.conceptMapper.support.tokenizer.TokenAnnotation</type>
+ <type allAnnotatorFeatures="true">uima.tt.TokenAnnotation</type>
+ <type allAnnotatorFeatures="true">uima.tcas.DocumentAnnotation</type>
+ </outputs>
+ <languagesSupported />
+ </capability>
+ </capabilities>
+ <operationalProperties>
+ <modifiesCas>true</modifiesCas>
+ <multipleDeploymentAllowed>true</multipleDeploymentAllowed>
+ <outputsNewCASes>false</outputsNewCASes>
+ </operationalProperties>
+ </analysisEngineMetaData>
+</taeDescription>