/** * Constructs a new DocumentReader that will read text from the given * Reader and tokenize it into words using the given Tokenizer. The default * implementation will internally buffer the reader if it is not already * buffered, so there is no need to pre-wrap the reader with a BufferedReader. * This class provides many <tt>getReader</tt> methods for conviniently * reading from many input sources. */ public DocumentReader(Reader in, TokenizerFactory<? extends HasWord> tokenizerFactory, boolean keepOriginalText) { if (in != null) { setReader(in); } setTokenizerFactory(tokenizerFactory); this.keepOriginalText = keepOriginalText; }
/** * Constructs a new DocumentReader that will read text from the given * Reader and tokenize it into words using the given Tokenizer. The default * implementation will internally buffer the reader if it is not already * buffered, so there is no need to pre-wrap the reader with a BufferedReader. * This class provides many <tt>getReader</tt> methods for conviniently * reading from many input sources. */ public DocumentReader(Reader in, TokenizerFactory<? extends HasWord> tokenizerFactory, boolean keepOriginalText) { if (in != null) { setReader(in); } setTokenizerFactory(tokenizerFactory); this.keepOriginalText = keepOriginalText; }
/** * Constructs a new DocumentReader that will read text from the given * Reader and tokenize it into words using the given Tokenizer. The default * implementation will internally buffer the reader if it is not already * buffered, so there is no need to pre-wrap the reader with a BufferedReader. * This class provides many <tt>getReader</tt> methods for conviniently * reading from many input sources. */ public DocumentReader(Reader in, TokenizerFactory<? extends HasWord> tokenizerFactory, boolean keepOriginalText) { if (in != null) { setReader(in); } setTokenizerFactory(tokenizerFactory); this.keepOriginalText = keepOriginalText; }
/** * Constructs a new DocumentReader that will read text from the given * Reader and tokenize it into words using the given Tokenizer. The default * implementation will internally buffer the reader if it is not already * buffered, so there is no need to pre-wrap the reader with a BufferedReader. * This class provides many <tt>getReader</tt> methods for conviniently * reading from many input sources. */ public DocumentReader(Reader in, TokenizerFactory<? extends HasWord> tokenizerFactory, boolean keepOriginalText) { if (in != null) { setReader(in); } setTokenizerFactory(tokenizerFactory); this.keepOriginalText = keepOriginalText; }
/** * Constructs a new DocumentReader that will read text from the given * Reader and tokenize it into words using the given Tokenizer. The default * implementation will internally buffer the reader if it is not already * buffered, so there is no need to pre-wrap the reader with a BufferedReader. * This class provides many <tt>getReader</tt> methods for conviniently * reading from many input sources. */ public DocumentReader(Reader in, TokenizerFactory<? extends HasWord> tokenizerFactory, boolean keepOriginalText) { if (in != null) { setReader(in); } setTokenizerFactory(tokenizerFactory); this.keepOriginalText = keepOriginalText; }