|
|||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | ||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Objectlemurproject.indri.IndexEnvironment
public class IndexEnvironment
Field Summary | |
---|---|
protected boolean |
swigCMemOwn
|
private long |
swigCPtr
|
Constructor Summary | |
---|---|
|
IndexEnvironment()
|
protected |
IndexEnvironment(long cPtr,
boolean cMemoryOwn)
|
Method Summary | |
---|---|
void |
addFile(java.lang.String fileName)
Add the text in a file to the index and repository. |
void |
addFile(java.lang.String fileName,
java.lang.String fileClass)
add a file of the specified file class to the index and repository |
void |
addFileClass(Specification spec)
Add a file class. |
void |
addFileClass(java.lang.String name,
java.lang.String iterator,
java.lang.String parser,
java.lang.String tokenizer,
java.lang.String startDocTag,
java.lang.String endDocTag,
java.lang.String endMetadataTag,
java.lang.String[] include,
java.lang.String[] exclude,
java.lang.String[] index,
java.lang.String[] metadata,
java.util.Map conflations)
Add parsing information for a file class. |
int |
addParsedDocument(ParsedDocument document)
add an already parsed document to the index and repository |
int |
addString(java.lang.String fileName,
java.lang.String fileClass,
java.util.Map metadata)
Adds a string to the index and repository. |
int |
addString(java.lang.String documentString,
java.lang.String fileClass,
java.util.Map metadata,
TagExtent[] tags)
add an already parsed document to the index and repository |
void |
close()
close the index and repository |
void |
create(java.lang.String repositoryPath)
create a new index and repository |
void |
create(java.lang.String repositoryPath,
IndexStatus callback)
create a new index and repository |
void |
delete()
|
void |
deleteDocument(int documentID)
Delete an existing document. |
int |
documentsIndexed()
Returns the number of documents indexed so far in this session. |
int |
documentsSeen()
Returns the number of documents considered for indexing, which is the sum of the documents indexed and the documents skipped. |
protected void |
finalize()
|
protected static long |
getCPtr(IndexEnvironment obj)
|
Specification |
getFileClassSpec(java.lang.String name)
Get a named file class. |
void |
open(java.lang.String repositoryPath)
open an existing index and repository |
void |
open(java.lang.String repositoryPath,
IndexStatus callback)
open an existing index and repository |
void |
setAnchorTextPath(java.lang.String anchorTextRoot)
Set anchor text root path. |
void |
setDocumentRoot(java.lang.String documentRoot)
Set the document root path |
void |
setIndexedFields(java.lang.String[] fieldNames)
Set names of fields to be indexed. |
void |
setMemory(long memory)
set the amount of memory to use for internal structures |
void |
setMetadataIndexedFields(java.lang.String[] forward,
java.lang.String[] backward)
Set names of metadata fields to be indexed for fast retrieval. |
void |
setNormalization(boolean normalize)
set normalization of case and some punctuation; default is true (normalize during indexing and at query time) |
void |
setNumericField(java.lang.String fieldName,
boolean isNumeric)
Set the numeric property of a field. |
void |
setNumericField(java.lang.String fieldName,
boolean isNumeric,
java.lang.String parserName)
Set the numeric property of a field. |
void |
setOffsetAnnotationsPath(java.lang.String offsetAnnotationsRoot)
Set offset annotations root path. |
void |
setOffsetMetadataPath(java.lang.String offsetMetadataRoot)
Set offset metadata root path. |
void |
setStemmer(java.lang.String stemmer)
set the stemmer to use |
void |
setStopwords(java.lang.String[] stopwords)
set the list of stopwords |
void |
setStoreDocs(boolean flag)
set the storeDocs flag |
Methods inherited from class java.lang.Object |
---|
clone, equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Field Detail |
---|
private long swigCPtr
protected boolean swigCMemOwn
Constructor Detail |
---|
protected IndexEnvironment(long cPtr, boolean cMemoryOwn)
public IndexEnvironment()
Method Detail |
---|
protected static long getCPtr(IndexEnvironment obj)
protected void finalize()
finalize
in class java.lang.Object
public void delete()
public void setDocumentRoot(java.lang.String documentRoot) throws java.lang.Exception
documentRoot
- path to document root.
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public void setAnchorTextPath(java.lang.String anchorTextRoot) throws java.lang.Exception
anchorTextRoot
- path to anchor text root.
java.lang.Exception
- ifpublic void setOffsetMetadataPath(java.lang.String offsetMetadataRoot) throws java.lang.Exception
offsetMetadataRoot
- path to offset metadata root.
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public void setOffsetAnnotationsPath(java.lang.String offsetAnnotationsRoot) throws java.lang.Exception
offsetAnnotationsRoot
- path to offset annotations root.
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public void addFileClass(java.lang.String name, java.lang.String iterator, java.lang.String parser, java.lang.String tokenizer, java.lang.String startDocTag, java.lang.String endDocTag, java.lang.String endMetadataTag, java.lang.String[] include, java.lang.String[] exclude, java.lang.String[] index, java.lang.String[] metadata, java.util.Map conflations) throws java.lang.Exception
name
- name of this file class, eg trecwebiterator
- document iterator for this file classparser
- document parser for this file classtokenizer
- document tokenizer for this file classstartDocTag
- tag indicating start of a documentendDocTag
- tag indicating the end of a documentendMetadataTag
- tag indicating the end of the metadata fieldsinclude
- default tags whose contents should be included in the indexexclude
- tags whose contents should be excluded from the indexindex
- tags that should be forwarded to the index for tag extentsmetadata
- tags whose contents should be indexed as metadataconflations
- tags that should be conflated
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public Specification getFileClassSpec(java.lang.String name) throws java.lang.Exception
name
- The name of the file class to retrieve.
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public void addFileClass(Specification spec) throws java.lang.Exception
spec
- The file class to add.
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public void deleteDocument(int documentID) throws java.lang.Exception
documentID
- The document to delete.
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public void setIndexedFields(java.lang.String[] fieldNames) throws java.lang.Exception
fieldNames
- the list of fields.
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public void setNumericField(java.lang.String fieldName, boolean isNumeric, java.lang.String parserName) throws java.lang.Exception
fieldName
- the field.isNumeric
- true if the field is a numeric field, false if not.parserName
- The name of the Transformation to use to compute the numeric value of the field. Repository currently recognizes the name NumericFieldAnnotator.
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public void setNumericField(java.lang.String fieldName, boolean isNumeric) throws java.lang.Exception
fieldName
- the field.isNumeric
- true if the field is a numeric field, false if not.parserName
- The name of the Transformation to use to compute the numeric value of the field. Repository currently recognizes the name NumericFieldAnnotator.
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public void setMetadataIndexedFields(java.lang.String[] forward, java.lang.String[] backward) throws java.lang.Exception
forward
- the list of fields to forward index.backward
- the list of fields to backward index.
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public void setStopwords(java.lang.String[] stopwords) throws java.lang.Exception
stopwords
- the list of stopwords
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public void setStemmer(java.lang.String stemmer) throws java.lang.Exception
stemmer
- the stemmer to use. One of krovetz, porter
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public void setMemory(long memory) throws java.lang.Exception
memory
- the number of bytes to use.
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public void setNormalization(boolean normalize) throws java.lang.Exception
normalize
- True, if text should be normalized, false otherwise.
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public void setStoreDocs(boolean flag) throws java.lang.Exception
flag,
- false to not store documents in the compressed collection, true to do so (default)
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public void create(java.lang.String repositoryPath, IndexStatus callback) throws java.lang.Exception
repositoryPath
- the path to the repositorycallback
- IndexStatus object to be notified of indexing progress.
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public void create(java.lang.String repositoryPath) throws java.lang.Exception
repositoryPath
- the path to the repositorycallback
- IndexStatus object to be notified of indexing progress.
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public void open(java.lang.String repositoryPath, IndexStatus callback) throws java.lang.Exception
repositoryPath
- the path to the repositorycallback
- IndexStatus object to be notified of indexing progress.
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public void open(java.lang.String repositoryPath) throws java.lang.Exception
repositoryPath
- the path to the repositorycallback
- IndexStatus object to be notified of indexing progress.
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public void close() throws java.lang.Exception
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public void addFile(java.lang.String fileName) throws java.lang.Exception
fileName
- the file to add
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public void addFile(java.lang.String fileName, java.lang.String fileClass) throws java.lang.Exception
fileName
- the file to addfileClass
- the file class to add (eg trecweb).
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public int addString(java.lang.String fileName, java.lang.String fileClass, java.util.Map metadata) throws java.lang.Exception
fileName
- the document to addfileClass
- the file class to add (eg trecweb).metadata
- the metadata pairs associated with the string.
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public int addString(java.lang.String documentString, java.lang.String fileClass, java.util.Map metadata, TagExtent[] tags) throws java.lang.Exception
document
- the document to add
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public int addParsedDocument(ParsedDocument document) throws java.lang.Exception
document
- the document to add
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public int documentsIndexed() throws java.lang.Exception
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.public int documentsSeen() throws java.lang.Exception
java.lang.Exception
- if a lemur::api::Exception was thrown by the JNI library.
|
|||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | ||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |