charsequence2tokensequence.java
来自「这是一个matlab的java实现。里面有许多内容。请大家慢慢捉摸。」· Java 代码 · 共 99 行
JAVA
99 行
/* Copyright (C) 2002 Univ. of Massachusetts Amherst, Computer Science Dept. This file is part of "MALLET" (MAchine Learning for LanguagE Toolkit). http://www.cs.umass.edu/~mccallum/mallet This software is provided under the terms of the Common Public License, version 1.0, as published by http://www.opensource.org. For further information, see the file `LICENSE' included with this distribution. *//** @author Andrew McCallum <a href="mailto:mccallum@cs.umass.edu">mccallum@cs.umass.edu</a> */package edu.umass.cs.mallet.base.pipe;import edu.umass.cs.mallet.base.types.TokenSequence;import edu.umass.cs.mallet.base.types.Token;import edu.umass.cs.mallet.base.types.Instance;import edu.umass.cs.mallet.base.util.Lexer;import edu.umass.cs.mallet.base.util.CharSequenceLexer;import java.io.*;import java.net.URI;/** * Pipe that tokenizes a character sequence. Expects a CharSequence * in the Instance data, and converts the sequence into a token * sequence using the given regex or CharSequenceLexer. * (The regex / lexer should specify what counts as a token.) */public class CharSequence2TokenSequence extends Pipe implements Serializable{ CharSequenceLexer lexer; public CharSequence2TokenSequence (CharSequenceLexer lexer) { this.lexer = lexer; } public CharSequence2TokenSequence (String regex) { this.lexer = new CharSequenceLexer (regex); } public CharSequence2TokenSequence () { this (new CharSequenceLexer()); } public Instance pipe (Instance carrier) { CharSequence string = (CharSequence) carrier.getData(); lexer.setCharSequence (string); TokenSequence ts = new TokenSequence (); while (lexer.hasNext()) ts.add (new Token ((String) lexer.next())); carrier.setData(ts); return carrier; } public static void main (String[] args) { try { for (int i = 0; i < args.length; i++) { Instance carrier = new Instance (new File(args[i]), null, null, null); Pipe p = new SerialPipes (new Pipe[] { new Input2CharSequence (), new CharSequence2TokenSequence(new CharSequenceLexer())}); carrier = p.pipe (carrier); TokenSequence ts = (TokenSequence) carrier.getData(); System.out.println ("==="); System.out.println (args[i]); System.out.println (ts.toString()); } } catch (Exception e) { System.out.println (e); e.printStackTrace(); } } // Serialization private static final long serialVersionUID = 1; private static final int CURRENT_SERIAL_VERSION = 0; private void writeObject (ObjectOutputStream out) throws IOException { out.writeInt(CURRENT_SERIAL_VERSION); out.writeObject(lexer); } private void readObject (ObjectInputStream in) throws IOException, ClassNotFoundException { int version = in.readInt (); lexer = (CharSequenceLexer) in.readObject(); } }
⌨️ 快捷键说明
复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?