| Methods Summary |
|---|
| public static java.util.HashMap | getStemDict(java.io.File wordstemfile)Reads a stem dictionary. Each line contains:
word\tstem
(i.e. two tab seperated words)
if (wordstemfile == null)
throw new NullPointerException("wordstemfile may not be null");
HashMap result = new HashMap();
BufferedReader br = null;
FileReader fr = null;
try {
fr = new FileReader(wordstemfile);
br = new BufferedReader(fr);
String line;
while ((line = br.readLine()) != null) {
String[] wordstem = line.split("\t", 2);
result.put(wordstem[0], wordstem[1]);
}
} finally {
if (fr != null)
fr.close();
if (br != null)
br.close();
}
return result;
|
| public static java.util.HashSet | getWordSet(java.io.File wordfile)Loads a text file and adds every line as an entry to a HashSet (omitting
leading and trailing whitespace). Every line of the file should contain only
one word. The words need to be in lowercase if you make use of an
Analyzer which uses LowerCaseFilter (like StandardAnalyzer).
HashSet result = new HashSet();
FileReader reader = null;
try {
reader = new FileReader(wordfile);
result = getWordSet(reader);
}
finally {
if (reader != null)
reader.close();
}
return result;
|
| public static java.util.HashSet | getWordSet(java.io.Reader reader)Reads lines from a Reader and adds every line as an entry to a HashSet (omitting
leading and trailing whitespace). Every line of the Reader should contain only
one word. The words need to be in lowercase if you make use of an
Analyzer which uses LowerCaseFilter (like StandardAnalyzer).
HashSet result = new HashSet();
BufferedReader br = null;
try {
if (reader instanceof BufferedReader) {
br = (BufferedReader) reader;
} else {
br = new BufferedReader(reader);
}
String word = null;
while ((word = br.readLine()) != null) {
result.add(word.trim());
}
}
finally {
if (br != null)
br.close();
}
return result;
|
