JAVA原生API读取XML大文件的DOM方式和SAX方式比较

JAVA原生API读取XML大文件的DOM方式和SAX方式比较

flyflyfly55555

分类专栏： J2SE综合 文章标签： XMLJavaEclipseJDKApache

一直都在使用dom的方式读取xml文件，但如果稍大点的xml文件那么dom方式就有点不太适合。

研究了下jdk的api，用dom和sax方式的解析结果做了个对比

要解析的xml内容格式如下

<?xml version="1.0" encoding="UTF-8"?>
<urlset>
<url>
<loc>商品链接访问地址</loc>
<data>
<display>
<title>商品名称</title>
<price>价格</price>
<image>
商品图片访问地址
</image>
<description>商品描述</description>
<barCode>条形码值</barCode>
<area>产地 （北京）</area>
<producedate>生产日期 （2011-11-11）</producedate>
<manufacturers>生产厂家  （某某某）</manufacturers>
</display>
</data>
</url>
//.....更更多
</urlset>

 

xml文件大小16.5M

 

首先是dom方式读取，代码如下

1. package test.xml;

2.  

3. import java.util.ArrayList;

4. import java.util.HashMap;

5. import java.util.List;

6. import java.util.Map;

7. import java.util.Set;

8.  

9. import javax.xml.parsers.DocumentBuilderFactory;

10.  

11. import org.w3c.dom.Document;

12. import org.w3c.dom.Element;

13. import org.w3c.dom.Node;

14. import org.w3c.dom.NodeList;

15.  

16. public class JDKBigXmlDomParse {

17.  

18. private int statmentSize = 6;

19. private List<Map<String, Object>> dataList = new ArrayList<Map<String, Object>>(statmentSize);

20.  

21. public void test() throws Exception{

22. String uri = "f:\\test.xml";

23. Document doc = DocumentBuilderFactory.newInstance().newDocumentBuilder().parse(uri);

24. NodeList urls = doc.getElementsByTagName("url");

25. int length = urls.getLength();

26. for(int i=0;i<length;i++){

27. Node node = urls.item(i);

28. if(node.getNodeType() != Node.ELEMENT_NODE){

29. continue;

30. }

31. Element urlElement = (Element)node;

32. Map<String,Object> entry = parseEntity(urlElement);

33. if(!entry.isEmpty()){

34. dataList.add(entry);

35. if(dataList.size() == statmentSize){

36. doSomeThing();

37. }

38. }

39. }

40. }

41.  

42. private Map<String,Object> parseEntity(Element element){

43. Map<String,Object> map = new HashMap<String, Object>();

44. map.put("loc", getElementValueByTagName(element,"loc"));

45. map.put("title", getElementValueByTagName(element,"title"));

46. map.put("price", getElementValueByTagName(element,"price"));

47. map.put("image", getElementValueByTagName(element,"image"));

48. map.put("description", getElementValueByTagName(element,"description"));

49. map.put("barCode", getElementValueByTagName(element,"barCode"));

50. map.put("area", getElementValueByTagName(element,"area"));

51. map.put("producedate", getElementValueByTagName(element,"producedate"));

52. map.put("manufacturers", getElementValueByTagName(element,"manufacturers"));

53. return map;

54. }

55.  

56. private String getElementValueByTagName(Element element,String tagName){

57. NodeList nodeList = element.getElementsByTagName(tagName);

58. String value = "";

59. if(nodeList.getLength() != 0){

60. Node node = nodeList.item(0);

61. value = node.getFirstChild().getNodeValue().trim();

62. }

63. return value;

64. }

65.  

66. private void doSomeThing(){

67. //printMapList(dataList);

68. dataList.clear();

69. }

70.  

71. private void printMapList(List<Map<String,Object>> dataList){

72. boolean first = true;

73. for(Map<String,Object> map:dataList){

74. System.out.println();

75. System.out.print("{");

76. Set<Map.Entry<String, Object>> entries = map.entrySet();

77. for(Map.Entry<String, Object> entry:entries){

78. if(!first){

79. System.out.print(",");

80. }

81. System.out.print("\""+entry.getKey()+"\":");

82. System.out.print("\""+entry.getValue()+"\"");

83. first = false;

84. }

85. first = true;

86. System.out.print("}");

87. }

88. System.out.println();

89. }

90.  

91. public static void main(String[] args) throws Exception{

92. long start = System.nanoTime();

93. new JDKBigXmlDomParse().test();

94. long end = System.nanoTime();

95. System.out.println("耗时:"+(end-start)/1000000000.0+"秒");

96. }

97.  

98. }

 运行结果：

耗时:3.212168172秒

 

sax方式读取，代码如下：

1. package test.xml;

2.  

3. import java.io.FileInputStream;

4. import java.io.InputStream;

5. import java.util.ArrayList;

6. import java.util.HashMap;

7. import java.util.List;

8. import java.util.Map;

9. import java.util.Set;

10.  

11. import javax.xml.parsers.SAXParser;

12. import javax.xml.parsers.SAXParserFactory;

13.  

14. import org.apache.commons.lang.StringUtils;

15. import org.xml.sax.Attributes;

16. import org.xml.sax.SAXException;

17. import org.xml.sax.helpers.DefaultHandler;

18.  

19. public class JDKBigXmlSaxParse extends DefaultHandler {

20.  

21. private int statmentSize = 6;

22. private List<Map<String, Object>> dataList = new ArrayList<Map<String, Object>>(statmentSize);

23. private Map<String, Object> dataMap;

24. private String currentTag = "";

25.  

26. public void test() throws Exception {

27. SAXParser sax = SAXParserFactory.newInstance().newSAXParser();

28. InputStream in = new FileInputStream("f:\\test.xml");

29. sax.parse(in, this);

30. in.close();

31. }

32.  

33. @Override

34. public void characters(char[] ch, int start, int length)throws SAXException {

35. String value = new String(ch, start, length);

36. if(!StringUtils.isBlank(value)){

37. dataMap.put(currentTag, value.trim());

38. }

39. }

40.  

41. @Override

42. public void endElement(String uri, String localName, String qName)

43. throws SAXException {

44. if("url".equals(qName)){

45. dataList.add(dataMap);

46. //dataMap.clear();

47. }

48.  

49. if(dataList.size() == statmentSize){

50. doSomeThing();

51. dataList.clear();

52. }

53.  

54. if("urlset".equals(qName) && dataList.size() != 0){

55. doSomeThing();

56. dataList.clear();

57. }

58.  

59. }

60.  

61. @Override

62. public void startElement(String uri, String localName, String qName,

63. Attributes attributes) throws SAXException {

64. if ("url".equals(qName)) {

65. dataMap = new HashMap<String, Object>();

66. return;

67. }

68.  

69. currentTag = qName;

70. }

71.  

72. public static void main(String[] args) throws Exception {

73. long start = System.nanoTime();

74. new JDKBigXmlSaxParse().test();

75. long end = System.nanoTime();

76. System.out.println("耗时:"+(end-start)/1000000000.0+"秒");

77. }

78.  

79. public void doSomeThing(){

80. //printMapList(dataList);

81. }

82.  

83. private void printMapList(List<Map<String,Object>> dataList){

84. boolean first = true;

85. for(Map<String,Object> map:dataList){

86. System.out.println();

87. System.out.print("{");

88. Set<Map.Entry<String, Object>> entries = map.entrySet();

89. for(Map.Entry<String, Object> entry:entries){

90. if(!first){

91. System.out.print(",");

92. }

93. System.out.print("\""+entry.getKey()+"\":");

94. System.out.print("\""+entry.getValue()+"\"");

95. first = false;

96. }

97. first = true;

98. System.out.print("}");

99. }

100. System.out.println();

101. }

102.  

103. }

 运行结果：

耗时:0.639864769秒

 

可以看到dom消耗的时间是sax方式的5倍。结论：如果只是读取xml文件，还是sax方式强。。。

 

而且在eclipse里面用dom方式运行的时候可能会出现eclipse java.lang.OutOfMemoryError: Java heap space这个问题