Many resources are needed to download a project. Please understand that we have to compensate our server costs. Thank you in advance. Project price only 1 $
You can buy this project and download/modify it how often you want.
// StanfordLexicalizedParser -- a probabilistic lexicalized NL CFG parser
// Copyright (c) 2002, 2003, 2004, 2005 The Board of Trustees of
// The Leland Stanford Junior University. All Rights Reserved.
//
// This program is free software; you can redistribute it and/or
// modify it under the terms of the GNU General Public License
// as published by the Free Software Foundation; either version 2
// of the License, or (at your option) any later version.
//
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU General Public License for more details.
//
// You should have received a copy of the GNU General Public License
// along with this program; if not, write to the Free Software
// Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
//
// For more information, bug reports, fixes, contact:
// Christopher Manning
// Dept of Computer Science, Gates 4A
// Stanford CA 94305-9040
// USA
// [email protected]
// http://nlp.stanford.edu/downloads/lex-parser.shtml
package edu.stanford.nlp.parser.ui;
import edu.stanford.nlp.io.ui.OpenPageDialog;
import edu.stanford.nlp.ling.*;
import edu.stanford.nlp.parser.common.ParserQuery;
import edu.stanford.nlp.parser.lexparser.LexicalizedParser;
import edu.stanford.nlp.process.*;
import edu.stanford.nlp.swing.FontDetector;
import edu.stanford.nlp.trees.PennTreebankLanguagePack;
import edu.stanford.nlp.trees.Tree;
import edu.stanford.nlp.trees.TreebankLanguagePack;
import edu.stanford.nlp.trees.international.pennchinese.ChineseTreebankLanguagePack;
import edu.stanford.nlp.ui.JarFileChooser;
import javax.swing.*;
import javax.swing.text.SimpleAttributeSet;
import javax.swing.text.StyleConstants;
import java.awt.*;
import java.awt.event.ActionEvent;
import java.awt.event.ActionListener;
import javax.swing.event.AncestorEvent;
import javax.swing.event.AncestorListener;
import java.awt.event.MouseAdapter;
import java.awt.event.MouseEvent;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.InputStreamReader;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.io.StringReader;
import java.net.URL;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
/**
* Provides a simple GUI Panel for Parsing. Allows a user to load a parser
* created using lexparser.LexicalizedParser, load a text data file or type
* in text, parse sentences within the input text, and view the resultant
* parse tree.
*
* @author Huy Nguyen ([email protected])
*/
public class ParserPanel extends JPanel {
/**
*
*/
private static final long serialVersionUID = -2118491857333662471L;
// constants for language specification
public static final int UNTOKENIZED_ENGLISH = 0;
public static final int TOKENIZED_CHINESE = 1;
public static final int UNTOKENIZED_CHINESE = 2;
private static TreebankLanguagePack tlp;
private String encoding = "UTF-8";
// one second in milliseconds
private static final int ONE_SECOND = 1000;
// parser takes approximately a minute to load
private static final int PARSER_LOAD_TIME = 60;
// parser takes 5-60 seconds to parse a sentence
private static final int PARSE_TIME = 30;
// constants for finding nearest sentence boundary
private static final int SEEK_FORWARD = 1;
private static final int SEEK_BACK = -1;
private final JFileChooser jfc;
private final JFileChooserLocation jfcLocation;
private final JarFileChooser chooseJarParser;
private OpenPageDialog pageDialog;
// for highlighting
private SimpleAttributeSet normalStyle, highlightStyle;
private int startIndex, endIndex;
private TreeJPanel treePanel;
private LexicalizedParser parser;
// worker threads to handle long operations
private LoadParserThread lpThread;
private ParseThread parseThread;
// to monitor progress of long operations
private javax.swing.Timer timer;
//private ProgressMonitor progressMonitor;
private int count; // progress count
// use glass pane to block input to components other than progressMonitor
private Component glassPane;
/** Whether to scroll one sentence forward after parsing. */
private boolean scrollWhenDone;
/**
* Creates new form ParserPanel
*/
public ParserPanel() {
initComponents();
// create dialogs for file selection
jfc = new JFileChooser(System.getProperty("user.dir"));
pageDialog = new OpenPageDialog(new Frame(), true);
pageDialog.setFileChooser(jfc);
jfcLocation = new JFileChooserLocation(jfc);
tlp = new PennTreebankLanguagePack();
encoding = tlp.getEncoding();
setFont();
// create a timer
timer = new javax.swing.Timer(ONE_SECOND, new TimerListener());
// for (un)highlighting text
highlightStyle = new SimpleAttributeSet();
normalStyle = new SimpleAttributeSet();
StyleConstants.setBackground(highlightStyle, Color.yellow);
StyleConstants.setBackground(normalStyle, textPane.getBackground());
this.chooseJarParser = new JarFileChooser(".*\\.ser\\.gz", this);
}
/**
* Scrolls back one sentence in the text
*/
public void scrollBack() {
highlightSentence(startIndex - 1);
// scroll to highlight location
textPane.setCaretPosition(startIndex);
}
/**
* Scrolls forward one sentence in the text
*/
public void scrollForward() {
highlightSentence(endIndex + 1);
// scroll to highlight location
textPane.setCaretPosition(startIndex);
}
/**
* Highlights specified text region by changing the character attributes
*/
private void highlightText(int start, int end, SimpleAttributeSet style) {
if (start < end) {
textPane.getStyledDocument().setCharacterAttributes(start, end - start + 1, style, false);
}
}
/**
* Finds the sentence delimited by the closest sentence delimiter preceding
* start and closest period following start.
*/
private void highlightSentence(int start) {
highlightSentence(start, -1);
}
/**
* Finds the sentence delimited by the closest sentence delimiter preceding
* start and closest period following end. If end is less than start
* (or -1), sets right boundary as closest period following start.
* Actually starts search for preceding sentence delimiter at (start-1)
*/
private void highlightSentence(int start, int end) {
// clears highlight. paints over entire document because the document may have changed
highlightText(0, textPane.getText().length(), normalStyle);
// if start<1 set startIndex to 0, otherwise set to index following closest preceding period
startIndex = (start < 1) ? 0 : nearestDelimiter(textPane.getText(), start, SEEK_BACK) + 1;
// if endseekDir
* is SEEK_FORWARD, finds the nearest delimiter after start. Else, if it is
* SEEK_BACK, finds the nearest delimiter before start.
*/
private int nearestDelimiter(String text, int start, int seekDir) {
if (seekDir != SEEK_BACK && seekDir != SEEK_FORWARD) {
throw new IllegalArgumentException("Unknown seek direction " +
seekDir);
}
StringReader reader = new StringReader(text);
DocumentPreprocessor processor = new DocumentPreprocessor(reader);
TokenizerFactory extends HasWord> tf = tlp.getTokenizerFactory();
processor.setTokenizerFactory(tf);
List boundaries = new ArrayList();
for (List sentence : processor) {
if (sentence.size() == 0)
continue;
if (!(sentence.get(0) instanceof HasOffset)) {
throw new ClassCastException("Expected HasOffsets from the " +
"DocumentPreprocessor");
}
if (boundaries.size() == 0) {
boundaries.add(0);
} else {
HasOffset first = (HasOffset) sentence.get(0);
boundaries.add(first.beginPosition());
}
}
boundaries.add(text.length());
for (int i = 0; i < boundaries.size() - 1; ++i) {
if (boundaries.get(i) <= start && start < boundaries.get(i + 1)) {
if (seekDir == SEEK_BACK) {
return boundaries.get(i) - 1;
} else if (seekDir == SEEK_FORWARD) {
return boundaries.get(i + 1) - 1;
}
}
}
// The cursor position at the end is actually one past the text length.
// We might as well highlight the last interval in that case.
if (boundaries.size() >= 2 && start >= text.length()) {
if (seekDir == SEEK_BACK) {
return boundaries.get(boundaries.size() - 2) - 1;
} else if (seekDir == SEEK_FORWARD) {
return boundaries.get(boundaries.size() - 1) - 1;
}
}
return -1;
}
/**
* Highlights the sentence that is currently being selected by user
* (via mouse highlight)
*/
private void highlightSelectedSentence() {
highlightSentence(textPane.getSelectionStart(), textPane.getSelectionEnd());
}
/**
* Highlights the sentence that is currently being edited
*/
private void highlightEditedSentence() {
highlightSentence(textPane.getCaretPosition());
}
/**
* Sets the status text at the bottom of the ParserPanel.
*/
public void setStatus(String status) {
statusLabel.setText(status);
}
private void setFont() {
if (tlp instanceof ChineseTreebankLanguagePack) {
setChineseFont();
} else {
textPane.setFont(new Font("Sans Serif", Font.PLAIN, 14));
treePanel.setFont(new Font("Sans Serif", Font.PLAIN, 14));
}
}
private void setChineseFont() {
java.util.List fonts = FontDetector.supportedFonts(FontDetector.CHINESE);
if (fonts.size() > 0) {
Font font = new Font(fonts.get(0).getName(), Font.PLAIN, 14);
textPane.setFont(font);
treePanel.setFont(font);
System.err.println("Selected font " + font);
} else if (FontDetector.hasFont("Watanabe Mincho")) {
textPane.setFont(new Font("Watanabe Mincho", Font.PLAIN, 14));
treePanel.setFont(new Font("Watanabe Mincho", Font.PLAIN, 14));
} else {
textPane.setFont(new Font("Sans Serif", Font.PLAIN, 14));
treePanel.setFont(new Font("Sans Serif", Font.PLAIN, 14));
}
}
/**
* Tokenizes the highlighted text (using a tokenizer appropriate for the
* selected language, and initiates the ParseThread to parse the tokenized
* text.
*/
public void parse() {
if (textPane.getText().length() == 0) {
return;
}
// use endIndex+1 because substring subtracts 1
String text = textPane.getText().substring(startIndex, endIndex + 1).trim();
if (parser != null && text.length() > 0) {
//Tokenizer extends HasWord> toke = tlp.getTokenizerFactory().getTokenizer(new CharArrayReader(text.toCharArray()));
Tokenizer extends HasWord> toke = tlp.getTokenizerFactory().getTokenizer(new StringReader(text));
List extends HasWord> wordList = toke.tokenize();
parseThread = new ParseThread(wordList);
parseThread.start();
startProgressMonitor("Parsing", PARSE_TIME);
}
}
/**
* Opens dialog to load a text data file
*/
public void loadFile() {
// centers dialog in panel
pageDialog.setLocation(getLocationOnScreen().x + (getWidth() - pageDialog.getWidth()) / 2, getLocationOnScreen().y + (getHeight() - pageDialog.getHeight()) / 2);
pageDialog.setVisible(true);
if (pageDialog.getStatus() == OpenPageDialog.APPROVE_OPTION) {
loadFile(pageDialog.getPage());
}
}
/**
* Loads a text or html file from a file path or URL. Treats anything
* beginning with http:\\,.htm, or .html as an
* html file, and strips all tags from the document
*/
public void loadFile(String filename) {
if (filename == null) {
return;
}
File file = new File(filename);
String urlOrFile = filename;
// if file can't be found locally, try prepending http:// and looking on web
if (!file.exists() && filename.indexOf("://") == -1) {
urlOrFile = "http://" + filename;
}
// else prepend file:// to handle local html file urls
else if (filename.indexOf("://") == -1) {
urlOrFile = "file://" + filename;
}
// TODO: why do any of this instead of just reading the file?
// Also, is this working correctly still?
// load the document
Document