我有一个非常小的xml文件,我只想用Java阅读。在引用this post之后,我决定使用SAX解析器。我的xml文件如下所示 -
<?xml version="1.0" encoding="UTF-8"?>
<catalog>
<library name="Central Library">
<read>
<book id="001" lang="ENG" title="Operating System Concepts" author="Silberschatz" />
<book id="002" lang="ENG" title="Design Patterns: Elements of Reusable Object-Oriented Software" author="Gangs of Four" />
</read>
<unread>
<book id="003" lang="ENG" title="Introduction to Algorithms" author="Cormen" />
<book id="004" lang="ENG" title="Computer networks" author="Tanenbaum" />
</unread>
</library>
</catalog>
在阅读此xml时,我无法识别已阅读和未阅读的书籍。 下面是解析器代码 -
import java.io.IOException;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
public class ParseXML extends DefaultHandler {
private Library lib;
public ParseXML(String file) throws ParserConfigurationException, SAXException, IOException {
parse(file);
}
private void parse(String file) throws ParserConfigurationException, SAXException, IOException {
final SAXParserFactory factory = SAXParserFactory.newInstance();
final SAXParser parser = factory.newSAXParser();
parser.parse(file, this);
}
@Override
public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
if (qName.equals("library")) {
String name = attributes.getValue("name");
lib = new Library(name);
}
if (qName.equals("book")) {
String id = attributes.getValue("id");
String lang = attributes.getValue("lang");
String title = attributes.getValue("title");
String author = attributes.getValue("author");
Book book = new Book(id, lang, title, author);
// How to decide here, to which list this book should be added
lib.addIntoReadBooks(book);
// lib.addIntoUnreadBooks(book);
}
}
/**
* @return the library
*/
public Library getLibrary() {
return lib;
}
public static void main(String[] args) {
try {
ParseXML parseXML = new ParseXML("repository/books.xml");
Library library = parseXML.getLibrary();
System.out.println("Library=" + library);
} catch (ParserConfigurationException e) {
System.err.println("Error " + e.getMessage());
} catch (SAXException e) {
System.err.println("Error " + e.getMessage());
} catch (IOException e) {
System.err.println("Error " + e.getMessage());
}
}
}
图书馆和图书课程如下 -
Library.java
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
public final class Library {
private final String name;
private final List<Book> readBooks;
private final List<Book> unreadBooks;
public Library(String name) {
this.name = name;
readBooks = new ArrayList<Book>();
unreadBooks = new ArrayList<Book>();
}
public void addIntoReadBooks(Book book) {
getReadBooks().add(book);
}
public void addIntoUnreadBooks(Book book) {
getUnreadBooks().add(book);
}
//Getters
}
Book.java
public class Book {
private final String id;
private final String lang;
private final String title;
private final String author;
public Book(String id, String lang, String title, String author) {
this.id = id;
this.lang = lang;
this.title = title;
this.author = author;
}
//Getters
}
如何决定应该添加哪本书?
不知何故,我设法使用以下代码,它使用两个标记来跟踪访问过的节点 -
import java.io.IOException;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
public class ParseXML extends DefaultHandler {
private Library lib;
private boolean read;
private boolean unread;
public ParseXML(String file) throws ParserConfigurationException, SAXException, IOException {
parse(file);
}
private void parse(String file) throws ParserConfigurationException, SAXException, IOException {
final SAXParserFactory factory = SAXParserFactory.newInstance();
final SAXParser parser = factory.newSAXParser();
parser.parse(file, this);
}
@Override
public void endElement(String uri, String localName, String qName) throws SAXException {
if (qName.equals("read")) {
read = false;
}
if (qName.equals("unread")) {
unread = false;
}
}
@Override
public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
if (qName.equals("library")) {
String name = attributes.getValue("name");
lib = new Library(name);
}
if (qName.equals("read")) {
read = true;
}
if (qName.equals("unread")) {
unread = true;
}
if (qName.equals("book")) {
String id = attributes.getValue("id");
String lang = attributes.getValue("lang");
String title = attributes.getValue("title");
String author = attributes.getValue("author");
Book book = new Book(id, lang, title, author);
// How to decide here, to which list this book should be added
if (read && !unread) {
lib.addIntoReadBooks(book);
} else if (!read && unread) {
lib.addIntoUnreadBooks(book);
}
}
}
/**
* @return the lib
*/
public Library getLibrary() {
return lib;
}
}
是否有更好的解决办法?
答案 0 :(得分:1)
我不清楚这必然会更好,但您可以在currentList
类中维护ParseXML
字段,以便操作当前列表:
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
public class ParseXML extends DefaultHandler {
private Library lib;
private List<Book> extraBooks = new ArrayList<Book>();
private List<Book> currentList = extraBooks;
public ParseXML(String file) throws ParserConfigurationException, SAXException, IOException {
parse(file);
}
private void parse(String file) throws ParserConfigurationException, SAXException, IOException {
final SAXParserFactory factory = SAXParserFactory.newInstance();
final SAXParser parser = factory.newSAXParser();
parser.parse(file, this);
}
@Override
public void endElement(String uri, String localName, String qName) throws SAXException {
if (qName.equals("read") || qName.equals("unread"))
currentList = extraBooks;
}
@Override
public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
if (qName.equals("library")) {
String name = attributes.getValue("name");
lib = new Library(name);
}
else if (qName.equals("read")) {
currentList = lib.getReadBooks();
}
else if (qName.equals("unread")) {
currentList = lib.getUnreadBooks();
}
else if (qName.equals("book")) {
String id = attributes.getValue("id");
String lang = attributes.getValue("lang");
String title = attributes.getValue("title");
String author = attributes.getValue("author");
currentList.add(new Book(id, lang, title, author));
}
}
/**
* @return the lib
*/
public Library getLibrary() {
return lib;
}
}
作为一种稍微不同的方法,您当然可以将列表和库名称保留为处理程序中的字段,并使用收集的所有数据在Library
方法中创建endElement
。
注意:(已废弃)在此代码中,我使用字段extraBooks
来允许在<book>
和<read>
标记之外发生<unread>
个标记。它比在currentList
方法中将null
设置为endElement
更安全一些。我讨厌NullPointerException
。
<强>更新强>
您不需要一次性字段extraBooks
。
您可以通过将currentList
的初始化更改为
private List<Book> currentList = new ArrayList<Book>();
和endElement
方法
@Override
public void endElement(String uri, String localName, String qName) throws SAXException {
if (qName.equals("read") || qName.equals("unread"))
currentList = new ArrayList<Book>();
}