我需要修改这个脚本,以便可以检查两个以上的单词,而我对 Java 的了解太有限,无法自己进行更改。 该脚本是 OpenOffice (LanguageTool) 开源语法检查器的一部分,脚本的目的是用其他单词替换某些单词。
要检查的单词文件名为“coherency.txt”,其格式如下: 错误的单词1=正确的单词1 错误词2=正确词2
当我输入:WrongWord1 时,脚本会对其进行标记,并告诉我应该使用 CorrectWord1。
但是我需要能够包含三个或更多单词,如下所示: 错误的单词1=错误的单词2=正确的单词1 错误的单词3=错误的单词4=错误的单词5=正确的单词2 错误的单词6=正确的单词3
这样,当我输入 WrongWord3 时,它会被标记,并且脚本告诉我应该使用 CorrectWord2 或者 当我输入 WrongWord2 时,它也会被标记,并且脚本告诉我应该使用 CorrectWord1
如果您能提供帮助,我可以将您的网页链接放在 http://www.sbbic.org/lang/en-us/volunteer/
如果您能提供有关如何修改此代码以允许比较和替换两个以上单词的任何帮助,我们将不胜感激! 谢谢, 内森
/* LanguageTool, a natural language style checker
* Copyright (C) 2005 Daniel Naber (http://www.danielnaber.de)
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* This library 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
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, write to the Free Software
* Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301
* USA
*/
package de.danielnaber.languagetool.rules;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Locale;
import java.util.Map;
import java.util.ResourceBundle;
import de.danielnaber.languagetool.AnalyzedSentence;
import de.danielnaber.languagetool.AnalyzedTokenReadings;
import de.danielnaber.languagetool.JLanguageTool;
import de.danielnaber.languagetool.tools.StringTools;
/**
* A Khmer rule that matches words or phrases which should not be used and suggests
* correct ones instead. Loads the relevant words from
* <code>rules/km/coherency.txt</code>, where km is a code of the language.
*
* @author Andriy Rysin
*/
public abstract class KhmerWordCoherencyRule extends KhmerRule {
private Map<String, String> wrongWords; // e.g. "вреѿті реѿт" -> "зреѿтою"
private static final String FILE_NAME = "/km/coherency.txt";
public abstract String getFileName();
private static final String FILE_ENCODING = "utf-8";
public String getEncoding() {
return FILE_ENCODING;
}
/**
* Indicates if the rule is case-sensitive. Default value is <code>true</code>.
* @return true if the rule is case-sensitive, false otherwise.
*/
public boolean isCaseSensitive() {
return false;
}
/**
* @return the locale used for case conversion when {@link #isCaseSensitive()} is set to <code>false</code>.
*/
public Locale getLocale() {
return Locale.getDefault();
}
public KhmerWordCoherencyRule(final ResourceBundle messages) throws IOException {
if (messages != null) {
super.setCategory(new Category(messages.getString("category_misc")));
}
wrongWords = loadWords(JLanguageTool.getDataBroker().getFromRulesDirAsStream(getFileName()));
}
public String getId() {
return "KM_WORD_COHERENCY";
}
public String getDescription() {
return "Checks for wrong words/phrases";
}
public String getSuggestion() {
return " is not valid, use ";
}
public String getShort() {
return "Wrong word";
}
public final RuleMatch[] match(final AnalyzedSentence text) {
final List<RuleMatch> ruleMatches = new ArrayList<RuleMatch>();
final AnalyzedTokenReadings[] tokens = text.getTokensWithoutWhitespace();
for (int i = 1; i < tokens.length; i++) {
final String token = tokens[i].getToken();
final String origToken = token;
final String replacement = isCaseSensitive()?wrongWords.get(token):wrongWords.get(token.toLowerCase(getLocale()));
if (replacement != null) {
final String msg = token + getSuggestion() + replacement;
final int pos = tokens[i].getStartPos();
final RuleMatch potentialRuleMatch = new RuleMatch(this, pos, pos
+ origToken.length(), msg, getShort());
if (!isCaseSensitive() && StringTools.startsWithUppercase(token)) {
potentialRuleMatch.setSuggestedReplacement(StringTools.uppercaseFirstChar(replacement));
} else {
potentialRuleMatch.setSuggestedReplacement(replacement);
}
ruleMatches.add(potentialRuleMatch);
}
}
return toRuleMatchArray(ruleMatches);
}
private Map<String, String> loadWords(final InputStream file) throws IOException {
final Map<String, String> map = new HashMap<String, String>();
InputStreamReader isr = null;
BufferedReader br = null;
try {
isr = new InputStreamReader(file, getEncoding());
br = new BufferedReader(isr);
String line;
while ((line = br.readLine()) != null) {
line = line.trim();
if (line.length() < 1) {
continue;
}
if (line.charAt(0) == '#') { // ignore comments
continue;
}
final String[] parts = line.split("=");
if (parts.length != 2) {
throw new IOException("Format error in file "
+ JLanguageTool.getDataBroker().getFromRulesDirAsUrl(getFileName()) + ", line: " + line);
}
map.put(parts[0], parts[1]);
}
} finally {
if (br != null) {
br.close();
}
if (isr != null) {
isr.close();
}
}
return map;
}
public void reset() {
}
}
最佳答案
对于小的调整:
考虑将所需的输入格式更改为
WrongWord = CorrectWord[, CorrectWord]*
键是不正确的单词,值是逗号分隔的正确选项列表。所以你可以保持文件解析不变。
map 类型应为 Map<String, Set<String>>
- 每个 token 映射到一组替代方案。
现在您可以围绕 =
分割每一行获取键/值对以及,
附近的每个值获取建议标记的数组来替换输入。
那么您需要对 match
进行一些更改组装新消息,因为您现在期望不止一个建议。
更改 final String origToken = token;
之后的行至
final String[] replacements = wrongWords.get(token);
if (replacements != null) {
final String msg = createMessage(token, replacements);
final int pos = tokens[i].getStartPos();
并实现createMessage
方法返回人类可读的消息,告诉用户 token 的一对多替代方案。
关于java - 如何允许在此 Java 代码中检查两个以上的单词,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/4644630/