org.knowceans.corpus.xpert
Class AuthorTermCorpus

java.lang.Object
  extended by org.knowceans.corpus.TermCorpusOld
      extended by org.knowceans.corpus.xpert.AuthorTermCorpus

public class AuthorTermCorpus
extends TermCorpusOld

AuthorTermCorpus

Author:
heinrich

Field Summary
protected  java.util.Vector<XptAuthor> allAuthors
          all authors
protected  java.util.Vector<java.util.Vector<java.lang.Integer>> docAuthors
          each document's authors
protected  java.util.Vector<java.lang.String> docComments
           
 
Fields inherited from class org.knowceans.corpus.TermCorpusOld
cats, curDoc, DEBUG, docCategories, docFreqs, docNames, docTerms, docTermsUnique, ignoreUnique, maxId, minDf, minTf, ndocs, nterms, ntermsNonUnique, nwords, OFFSET, progress, termFreqs, termIndex
 
Constructor Summary
AuthorTermCorpus()
           
AuthorTermCorpus(ICategories cats)
           
 
Method Summary
 void finaliseDocument(java.lang.String key, java.util.Vector<java.lang.Integer> categories, java.util.Vector<java.lang.Integer> authors, java.lang.String comment)
          finalises the current document with a name (useful to identify documents), its categories (leave null if unused) and authors (leave null if unused).
(package private)  void readAuthorList(java.lang.String file)
          reads the vocabulary from a file with format id = termstring (on each line) TODO: implement.
 void readDocList(java.lang.String file)
          reads the vocabulary from a file with format id = termstring (on each line)
 void setAuthorList(java.util.Vector<XptAuthor> authors)
           
 void writeAuthorList(java.lang.String file)
          write the author list in a file with format id = firstname(s) ; lastname ; group (on each line) TODO: implement.
 void writeDocList(java.lang.String file)
          write the author list in a file with format id = firstname(s) ; lastname ; group (on each line).
 
Methods inherited from class org.knowceans.corpus.TermCorpusOld
add, docToString, finaliseDocument, getDocCategories, getDocNames, getDocTerms, getDocTermsUnique, getNdocs, getNterms, getNwords, getTermIndex, lookup, lookup, lookupDoc, readCorpus, readVocabulary, reorderCorpus, setNdocs, setNterms, setNwords, writeCorpus, writeVocabulary
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

docAuthors

protected java.util.Vector<java.util.Vector<java.lang.Integer>> docAuthors
each document's authors


allAuthors

protected java.util.Vector<XptAuthor> allAuthors
all authors


docComments

protected java.util.Vector<java.lang.String> docComments
Constructor Detail

AuthorTermCorpus

public AuthorTermCorpus()

AuthorTermCorpus

public AuthorTermCorpus(ICategories cats)
Parameters:
cats -
Method Detail

finaliseDocument

public void finaliseDocument(java.lang.String key,
                             java.util.Vector<java.lang.Integer> categories,
                             java.util.Vector<java.lang.Integer> authors,
                             java.lang.String comment)
finalises the current document with a name (useful to identify documents), its categories (leave null if unused) and authors (leave null if unused).


setAuthorList

public void setAuthorList(java.util.Vector<XptAuthor> authors)

writeAuthorList

public void writeAuthorList(java.lang.String file)
                     throws java.io.IOException
write the author list in a file with format id = firstname(s) ; lastname ; group (on each line) TODO: implement.

Parameters:
file -
Throws:
java.io.IOException

readAuthorList

void readAuthorList(java.lang.String file)
              throws java.io.IOException
reads the vocabulary from a file with format id = termstring (on each line) TODO: implement.

Parameters:
file -
Throws:
java.io.IOException
java.lang.NumberFormatException

writeDocList

public void writeDocList(java.lang.String file)
                  throws java.io.IOException
write the author list in a file with format id = firstname(s) ; lastname ; group (on each line).

Overrides:
writeDocList in class TermCorpusOld
Parameters:
file -
Throws:
java.io.IOException

readDocList

public void readDocList(java.lang.String file)
                 throws java.io.IOException
reads the vocabulary from a file with format id = termstring (on each line)

Overrides:
readDocList in class TermCorpusOld
Parameters:
file -
Throws:
java.io.IOException
java.lang.NumberFormatException